mirror of
https://github.com/mirror/wget.git
synced 2026-08-21 18:33:28 +08:00
Compare commits
353 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
366d82f349 | ||
|
|
f2574e90b7 | ||
|
|
81b3aaf75c | ||
|
|
17d2f42a3d | ||
|
|
638df40476 | ||
|
|
00bafe72f1 | ||
|
|
e777c01f43 | ||
|
|
3ba112ea57 | ||
|
|
485fcfcc20 | ||
|
|
a5094731cd | ||
|
|
3186eb2976 | ||
|
|
9947663af8 | ||
|
|
cfae085665 | ||
|
|
e69808256b | ||
|
|
11989ef669 | ||
|
|
5fceab6cb9 | ||
|
|
d6eead1794 | ||
|
|
d0e02a54ae | ||
|
|
2e70409844 | ||
|
|
4734e8d4d7 | ||
|
|
0fe8a5c40e | ||
|
|
1b9374ee59 | ||
|
|
6de24fe3c0 | ||
|
|
0ab3d92c85 | ||
|
|
4cf8af84e0 | ||
|
|
42b8761cbc | ||
|
|
fd0f759597 | ||
|
|
a384f5e2e9 | ||
|
|
5ae1f37902 | ||
|
|
0eb4a21b6c | ||
|
|
60dc3c21b2 | ||
|
|
1a01a6b2d0 | ||
|
|
2427ca4ac0 | ||
|
|
42c2ce71bc | ||
|
|
def133f26f | ||
|
|
b9ed06afd8 | ||
|
|
1bdc20d774 | ||
|
|
e4e9d3c1c8 | ||
|
|
dcdd618b18 | ||
|
|
3c796b9a85 | ||
|
|
00ae9b4ee2 | ||
|
|
2242d5aee4 | ||
|
|
77a546348c | ||
|
|
be5517f98f | ||
|
|
dd5c549f6a | ||
|
|
78e0ec5f03 | ||
|
|
807d1c7d94 | ||
|
|
3d1d5b317b | ||
|
|
517d799b6f | ||
|
|
f79bb20f1b | ||
|
|
e5164a8260 | ||
|
|
a35f3dd4f6 | ||
|
|
c403e67935 | ||
|
|
3021466817 | ||
|
|
c89767d8d1 | ||
|
|
f030cdf8e2 | ||
|
|
5dccb2a9ce | ||
|
|
0538e791fb | ||
|
|
acb1d1a668 | ||
|
|
628fb565c7 | ||
|
|
64ab90ee66 | ||
|
|
9532861aef | ||
|
|
8aca8fc80d | ||
|
|
ba82a47173 | ||
|
|
70360b3eab | ||
|
|
c29983a044 | ||
|
|
5f3ed5eec8 | ||
|
|
43ec7008f2 | ||
|
|
7d4942864b | ||
|
|
666b7862bf | ||
|
|
f3f349a0cf | ||
|
|
6b1860da37 | ||
|
|
ff444ebc2a | ||
|
|
96554861f9 | ||
|
|
bcb9bf7ae4 | ||
|
|
ea038006d1 | ||
|
|
77e2c54991 | ||
|
|
7ffbccec4c | ||
|
|
a2c4849900 | ||
|
|
40870e1271 | ||
|
|
15c1e0eb7b | ||
|
|
eba724a128 | ||
|
|
66a9883c8f | ||
|
|
4febe72bd2 | ||
|
|
c629ec7fd1 | ||
|
|
03da900c5b | ||
|
|
b7b67e23cd | ||
|
|
22aed3ed4b | ||
|
|
b4465afa8a | ||
|
|
a232835fd1 | ||
|
|
a78b83b1e9 | ||
|
|
37a5257c66 | ||
|
|
49af22ca94 | ||
|
|
d505714a32 | ||
|
|
21e1725e12 | ||
|
|
796e30dcea | ||
|
|
b919f988f2 | ||
|
|
ca1ee7d32f | ||
|
|
690c47e3b1 | ||
|
|
9ffb64ba6a | ||
|
|
6698260f15 | ||
|
|
0787d7253e | ||
|
|
964f4646da | ||
|
|
262baeb113 | ||
|
|
f4aeb41899 | ||
|
|
a9d49e5b15 | ||
|
|
0fe79eeacb | ||
|
|
e3fb4c3859 | ||
|
|
943a6d585f | ||
|
|
7fad76db4c | ||
|
|
3e7e29f358 | ||
|
|
e0b60fd073 | ||
|
|
9db02a0c46 | ||
|
|
edad3c1df3 | ||
|
|
20cac2c5ab | ||
|
|
a933bdd31e | ||
|
|
ef372a4f27 | ||
|
|
0b151f51eb | ||
|
|
309e72c74f | ||
|
|
2318c309d4 | ||
|
|
cdc3e28d8e | ||
|
|
43359f47c4 | ||
|
|
e1e7afb210 | ||
|
|
7e585fe23d | ||
|
|
526e98f7c4 | ||
|
|
d75f43f083 | ||
|
|
d4f97dc9af | ||
|
|
ade62eb400 | ||
|
|
bd7f36705b | ||
|
|
e996e322ff | ||
|
|
2bdfc4f521 | ||
|
|
2c736abb4c | ||
|
|
7c0752c4cb | ||
|
|
302aa79abb | ||
|
|
5224d752a5 | ||
|
|
2aaf12990c | ||
|
|
2e6f629061 | ||
|
|
a952f81f3e | ||
|
|
42cc84b6b6 | ||
|
|
96ab9cad88 | ||
|
|
268163444d | ||
|
|
53800415a9 | ||
|
|
528770ca8b | ||
|
|
2f1c6a05c8 | ||
|
|
33d860e1ef | ||
|
|
99fc712f21 | ||
|
|
54746578e9 | ||
|
|
926e42d467 | ||
|
|
d286d5408b | ||
|
|
9883f9fb10 | ||
|
|
d26377053d | ||
|
|
722675553c | ||
|
|
281ad7dfb9 | ||
|
|
f3e63f0071 | ||
|
|
b916595168 | ||
|
|
76ef65b23c | ||
|
|
d7726f8a13 | ||
|
|
598445ebd1 | ||
|
|
7cb9efa668 | ||
|
|
44aedd8321 | ||
|
|
c28f51aadf | ||
|
|
7099f48998 | ||
|
|
75e5be7aad | ||
|
|
100da11312 | ||
|
|
cceb5932b4 | ||
|
|
cacac6f996 | ||
|
|
3056617e9c | ||
|
|
c190677cab | ||
|
|
4c2dc5010f | ||
|
|
b30500f0f4 | ||
|
|
59b920874d | ||
|
|
9a6e63bee9 | ||
|
|
cbbeca2af4 | ||
|
|
93c1517c40 | ||
|
|
bf5d7e9236 | ||
|
|
94d9b68db9 | ||
|
|
be7d19f478 | ||
|
|
358a3c330f | ||
|
|
478a584609 | ||
|
|
994c4dcce7 | ||
|
|
f65f522f58 | ||
|
|
be84711ea4 | ||
|
|
bf56bf4560 | ||
|
|
3eddf5c173 | ||
|
|
160f0e908f | ||
|
|
30b0705fa6 | ||
|
|
9933da2b9f | ||
|
|
df7cb9a1b9 | ||
|
|
636a5f9a1c | ||
|
|
44937634a3 | ||
|
|
2257d3ebf8 | ||
|
|
b0d2fa5748 | ||
|
|
ca0c272eae | ||
|
|
8977e63239 | ||
|
|
ad5a283528 | ||
|
|
3dd2e78256 | ||
|
|
81061571d1 | ||
|
|
4e37fb6191 | ||
|
|
218d81f6e5 | ||
|
|
46cd721c0f | ||
|
|
b1c7777037 | ||
|
|
8c12260d4b | ||
|
|
99aa7b4f5e | ||
|
|
76da642aaf | ||
|
|
2cfcadf5e6 | ||
|
|
08ece891b5 | ||
|
|
4ed540ddc7 | ||
|
|
d1a329536a | ||
|
|
2b418d1146 | ||
|
|
b041658451 | ||
|
|
6cdfc9c143 | ||
|
|
b14eeb5aee | ||
|
|
71979f1643 | ||
|
|
4ad201a7e7 | ||
|
|
3608c3001c | ||
|
|
d484b14174 | ||
|
|
b8ee370571 | ||
|
|
f5a63e3100 | ||
|
|
077e897819 | ||
|
|
1e7ccfe275 | ||
|
|
26fadc55c2 | ||
|
|
e51076e683 | ||
|
|
c387db6451 | ||
|
|
12dfc03116 | ||
|
|
3ea0beec6f | ||
|
|
b50300a7a2 | ||
|
|
f8901af4e0 | ||
|
|
e624732563 | ||
|
|
f2cb6e050a | ||
|
|
84b9abbf3c | ||
|
|
58917dcde1 | ||
|
|
ab47d9fa3a | ||
|
|
187edb604a | ||
|
|
b06fca60ac | ||
|
|
c809398e8c | ||
|
|
88a1a79bc1 | ||
|
|
398699c438 | ||
|
|
d3504b9261 | ||
|
|
6b5acff566 | ||
|
|
5c4489db9b | ||
|
|
7bed9a6f8f | ||
|
|
d080a70a3a | ||
|
|
2d2ddb25d8 | ||
|
|
030c3379d1 | ||
|
|
d3d8de8223 | ||
|
|
e04c5989ff | ||
|
|
12bae50b28 | ||
|
|
f71887bbe5 | ||
|
|
84c405e690 | ||
|
|
075d755696 | ||
|
|
7578e47d49 | ||
|
|
3a708f7ef8 | ||
|
|
474935665e | ||
|
|
f8519b52f0 | ||
|
|
98272d2c8d | ||
|
|
7e5079c40f | ||
|
|
e4db00d74d | ||
|
|
670eb924e7 | ||
|
|
5d55018ce6 | ||
|
|
4e56a91001 | ||
|
|
595f219a17 | ||
|
|
b6e242cd6f | ||
|
|
207006ef25 | ||
|
|
843634db59 | ||
|
|
54058d2b18 | ||
|
|
b60131a399 | ||
|
|
fc8a545bfd | ||
|
|
9e12b8ca39 | ||
|
|
4c3043d19d | ||
|
|
6064f21c66 | ||
|
|
97389a7497 | ||
|
|
225a87d4a2 | ||
|
|
92a889b278 | ||
|
|
1113e78534 | ||
|
|
70cbd59ed6 | ||
|
|
0e7aff7623 | ||
|
|
792dd09a87 | ||
|
|
a4f5ced797 | ||
|
|
05c30c3b1b | ||
|
|
37b58e3976 | ||
|
|
80303366ae | ||
|
|
bd0ffcf8bc | ||
|
|
25c9b462bf | ||
|
|
77f5a27e65 | ||
|
|
ae58d8a78b | ||
|
|
58702ffd4f | ||
|
|
103f940950 | ||
|
|
5f0818d9f1 | ||
|
|
c6ac51d5bc | ||
|
|
fd3a3245eb | ||
|
|
48acb6693d | ||
|
|
885eaaa214 | ||
|
|
8a8d138dcc | ||
|
|
0e8d2d4251 | ||
|
|
be4f91737a | ||
|
|
901bc98edf | ||
|
|
e397a48f6a | ||
|
|
83537f2415 | ||
|
|
8682c2612f | ||
|
|
b0820d553b | ||
|
|
b6b1388fb7 | ||
|
|
9b1dd6dab8 | ||
|
|
1cc835dc5b | ||
|
|
6b8dfe1d6e | ||
|
|
0e6d6ca963 | ||
|
|
3765a1b266 | ||
|
|
8654f7e2e7 | ||
|
|
566696cb82 | ||
|
|
bebe462a67 | ||
|
|
c579c7bf1e | ||
|
|
4dde3e200f | ||
|
|
8e0dd0d870 | ||
|
|
c6af2fddee | ||
|
|
e7e3227b34 | ||
|
|
5c5d45ae49 | ||
|
|
f4072e5d0b | ||
|
|
bef5945202 | ||
|
|
ac40b84ee1 | ||
|
|
45463eaad7 | ||
|
|
d03b40e31e | ||
|
|
268e6aef72 | ||
|
|
5efb24e4a2 | ||
|
|
eae8b1d565 | ||
|
|
045463b814 | ||
|
|
621c313b94 | ||
|
|
52a7d0ad85 | ||
|
|
59e9ef00e6 | ||
|
|
14bbc18512 | ||
|
|
8aa63e482e | ||
|
|
0bc2757713 | ||
|
|
f8abb9dd00 | ||
|
|
29850e77d0 | ||
|
|
799c545722 | ||
|
|
014b1d6041 | ||
|
|
8d4bb928b9 | ||
|
|
d0f406a13f | ||
|
|
87b52e510c | ||
|
|
cc9f76c5a4 | ||
|
|
53b22974cb | ||
|
|
7d5a7ef9ca | ||
|
|
735cc220e3 | ||
|
|
524f26a200 | ||
|
|
16f1fb1d1f | ||
|
|
b74ac4c7e0 | ||
|
|
91e9a20752 | ||
|
|
4a214bc9a3 | ||
|
|
b7b6d7fd89 | ||
|
|
3a00b37bc2 | ||
|
|
adcc793a26 | ||
|
|
d94d9cd98b | ||
|
|
882ed28d59 | ||
|
|
e316d253fa | ||
|
|
9dde436dd6 |
2
.gitignore
vendored
2
.gitignore
vendored
@@ -2,6 +2,7 @@
|
||||
/.sc-start-sc_bindtextdomain
|
||||
/.sc-start-sc_prohibit_HAVE_MBRTOWC
|
||||
/.version
|
||||
/ABOUT-NLS
|
||||
/GNUmakefile
|
||||
/INSTALL
|
||||
/Makefile
|
||||
@@ -25,6 +26,7 @@ testenv/*.log
|
||||
testenv/*.trs
|
||||
# build-aux/
|
||||
build-aux/.gitignore
|
||||
build-aux/ar-lib
|
||||
build-aux/compile
|
||||
build-aux/config.guess
|
||||
build-aux/config.sub
|
||||
|
||||
50
.travis.yml
Normal file
50
.travis.yml
Normal file
@@ -0,0 +1,50 @@
|
||||
sudo: no
|
||||
|
||||
language: c
|
||||
|
||||
compiler:
|
||||
- gcc
|
||||
|
||||
notifications:
|
||||
email:
|
||||
recipients:
|
||||
- darnir@gmail.com
|
||||
- bug-wget@gnu.org
|
||||
on_success: change
|
||||
on_failure: always
|
||||
|
||||
env:
|
||||
global:
|
||||
- PERLLIB=$PERLLIB:../../tests
|
||||
- PERL5LIB=$PERL5LIB:../../tests
|
||||
matrix:
|
||||
- SSL=""
|
||||
- SSL="openssl"
|
||||
- SSL="gnutls"
|
||||
|
||||
addons:
|
||||
apt:
|
||||
packages:
|
||||
- automake
|
||||
- autoconf
|
||||
- autopoint
|
||||
- flex
|
||||
- texinfo
|
||||
- pkg-config
|
||||
- libgnutls-dev
|
||||
- libssl-dev
|
||||
- make
|
||||
- libhttp-daemon-perl
|
||||
- libio-socket-ssl-perl
|
||||
- libidn2-dev
|
||||
- gettext
|
||||
- texlive
|
||||
- python3
|
||||
- valgrind
|
||||
- language-pack-tr
|
||||
- language-pack-ru
|
||||
|
||||
script:
|
||||
- make distclean || true
|
||||
- ./bootstrap
|
||||
- ./contrib/travis-ci $SSL
|
||||
@@ -729,7 +729,7 @@
|
||||
* testenv/Makefile.am: Run the tests in Python's Optimizedmode
|
||||
* testenv/conf/__init__.py (gen_hook): Use try..except instead of if..else
|
||||
* testenv/misc/color_terminal.py: System and check will not change while a test is
|
||||
run. Do not test for them on every invokation of printer()
|
||||
run. Do not test for them on every invocation of printer()
|
||||
* testenv/server/http/http_server.py: The ssl and re modules are required by
|
||||
specific functions. Load them lazily
|
||||
(HTTPSServer.__init__): Lazy load ssl module here
|
||||
|
||||
@@ -23,15 +23,6 @@ Gmane archives conveniently include messages from both the current
|
||||
list, and the previous one. Messages also show up in the Gmane archives
|
||||
sooner than they do at `lists.gnu.org'.
|
||||
|
||||
Bug Notices List
|
||||
----------------
|
||||
|
||||
Additionally, there is the <wget-notify@addictivecode.org> mailing
|
||||
list. This is a non-discussion list that receives bug report
|
||||
notifications from the bug-tracker. To subscribe to this list, send an
|
||||
email to <wget-notify-join@addictivecode.org>, or visit
|
||||
`http://addictivecode.org/mailman/listinfo/wget-notify'.
|
||||
|
||||
Obsolete Lists
|
||||
--------------
|
||||
|
||||
|
||||
@@ -77,3 +77,6 @@ gen-ChangeLog:
|
||||
{ rm -f $(distdir)/ChangeLog && \
|
||||
mv $(distdir)/cl-t $(distdir)/ChangeLog; } \
|
||||
fi
|
||||
|
||||
check-valgrind:
|
||||
TESTS_ENVIRONMENT="VALGRIND_TESTS=1" $(MAKE) check
|
||||
|
||||
116
NEWS
116
NEWS
@@ -1,12 +1,120 @@
|
||||
GNU Wget NEWS -- history of user-visible changes.
|
||||
|
||||
Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005,
|
||||
2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 1997-2017 Free Software Foundation, Inc.
|
||||
See the end for copying conditions.
|
||||
|
||||
Please send GNU Wget bug reports to <bug-wget@gnu.org>.
|
||||
|
||||
* Changes in Wget 1.19
|
||||
|
||||
* New option --use-askpass=COMMAND. Fetch user/password by calling
|
||||
an external program.
|
||||
|
||||
* Use IDNA2008 (+ TR46 if available) through libidn2
|
||||
|
||||
* When processing a Metalink header, --metalink-index=<number> allows
|
||||
to process the header's application/metalink4+xml files.
|
||||
|
||||
* When processing a Metalink file, --trust-server-names enables the
|
||||
use of the destination file names specified in the Metalink file,
|
||||
otherwise a safe destination file name is computed.
|
||||
|
||||
* When processing a Metalink file, enforce a safe destination path.
|
||||
Remove any drive letter prefix under w32, i.e. 'C:D:file'. Call
|
||||
libmetalink's metalink_check_safe_path() to prevent absolute,
|
||||
relative, or home paths:
|
||||
https://tools.ietf.org/html/rfc5854#section-4.1.2.1
|
||||
https://tools.ietf.org/html/rfc5854#section-4.2.8.3
|
||||
|
||||
* When processing a Metalink file, --directory-prefix=<prefix> sets
|
||||
the top of the retrieval tree to prefix for Metalink downloads.
|
||||
|
||||
* When processing a Metalink file, reject downloaded files which don't
|
||||
agree with their own metalink:size value:
|
||||
https://tools.ietf.org/html/rfc5854#section-4.2.16
|
||||
|
||||
* When processing a Metalink file, with --continue resume partially
|
||||
downloaded files and keep fully downloaded files even if they fail
|
||||
the verification.
|
||||
|
||||
* When processing a Metalink file, create the parent directories of a
|
||||
"path/file" destination file name:
|
||||
https://tools.ietf.org/html/rfc5854#section-4.1.2.1
|
||||
https://tools.ietf.org/html/rfc5854#section-4.2.8.3
|
||||
|
||||
* On a recursive download, append a .tmp suffix to temporary files
|
||||
that will be deleted after being parsed, and create them
|
||||
readable/writable only by the owner.
|
||||
|
||||
* New make target 'check-valgrind'
|
||||
|
||||
* Fix several bugs
|
||||
|
||||
* Fix compatibility issues
|
||||
|
||||
* Changes in Wget 1.18
|
||||
|
||||
* By default, on server redirects to a FTP resource, use the original
|
||||
URL to get the local file name. Close CVE-2016-4971. This
|
||||
introduces a backward-incompatibility for HTTP->FTP redirects and
|
||||
any script that relies on the old behaviour must use
|
||||
--trust-server-names.
|
||||
|
||||
* Check the HSTS file is not world-writable before using it.
|
||||
|
||||
* Parse <img srcset> attributes on a recursive download.
|
||||
|
||||
* Fix problem with SNI server names having trailing dot(s)
|
||||
|
||||
* New options --bind-dns-address and --dns-servers.
|
||||
|
||||
* When Wget is built with libiconv, it now converts non-ASCII URIs to
|
||||
the locale's codeset when it creates files. The encoding of the
|
||||
remote files and URIs is taken from --remote-encoding, defaulting to
|
||||
UTF-8. The result is that non-ASCII URIs and files downloaded via
|
||||
HTTP/HTTPS and FTP will have names on the local filesystem that
|
||||
correspond to their remote names.
|
||||
|
||||
* Changes in Wget 1.17.1
|
||||
|
||||
* Fix compile error when IPv6 is disabled or SSL is not present.
|
||||
|
||||
* Fix HSTS memory leak.
|
||||
|
||||
* Fix progress output in non-C locales.
|
||||
|
||||
* Fix SIGSEGV when -N and --content-disposition are used together.
|
||||
|
||||
* Add --check-certificate=quiet to tell wget to not print any warning about
|
||||
invalid certificates.
|
||||
|
||||
* Changes in Wget 1.17
|
||||
|
||||
** Remove FTP passive to active fallback due to privacy concerns.
|
||||
|
||||
** Add support for --if-modified-since.
|
||||
|
||||
** Add support for metalink through --input-metalink and --metalink-over-http.
|
||||
|
||||
** Add support for HSTS through --hsts and --hsts-file.
|
||||
|
||||
** Add option to restrict filenames under VMS.
|
||||
|
||||
** Add support for --rejected-log which logs to a separate file the reasons why
|
||||
URLs are being rejected and some context around it.
|
||||
|
||||
** Add support for FTPS.
|
||||
|
||||
** Do not download/save file on error when --spider enabled
|
||||
|
||||
** Add --convert-file-only option. This option converts only the
|
||||
filename part of the URLs, leaving the rest of the URLs untouched.
|
||||
|
||||
* Changes in Wget 1.16.3
|
||||
|
||||
** Fix a regression introduced by wget 1.16.2 that --quiet is not
|
||||
really quiet anymore.
|
||||
|
||||
* Changes in Wget 1.16.2
|
||||
|
||||
** Native uuid generation on Windows
|
||||
@@ -114,7 +222,7 @@ Please send GNU Wget bug reports to <bug-wget@gnu.org>.
|
||||
|
||||
** Add support for TLS Server Name Indication.
|
||||
|
||||
** Accept the arguments --accept-reject and --reject-regex.
|
||||
** Accept the arguments --accept-regex and --reject-regex.
|
||||
|
||||
** The GNU TLS backend honors correctly the timeout value.
|
||||
|
||||
|
||||
@@ -4,8 +4,9 @@ Compiling From Repository Sources
|
||||
does not contain automatically-generated files, even when these are
|
||||
normally present in the distribution tarballs. Therefore, to build GNU
|
||||
Wget from the sources in the repository, you'll need to have one or
|
||||
more of the following (note that gettext, OpenSSL, GnuTLS, libidn,
|
||||
libiconv, libpsl, libpcre and pkg-config are not absolutely required):
|
||||
more of the following (note that gettext, OpenSSL, GnuTLS, libidn2,
|
||||
libiconv, libpsl, libpcre, pkg-config, libmetalink and GnuPG are not
|
||||
absolutely required):
|
||||
|
||||
* [20]autoconf (currently, GNU Wget requires version 2.61). This is
|
||||
needed to generate the configure script from configure.in. This is
|
||||
@@ -23,13 +24,19 @@ Compiling From Repository Sources
|
||||
* [23]Perl, if you wish to generate the wget(1) manpage, or run the
|
||||
tests in the tests/ sub directory. Tarball distributions include an
|
||||
already-generated wget.1 manual. The command "make check" runs the
|
||||
test suite written in perl. To execute all the tests you need
|
||||
[24]libwww-perl and libio-socket-ssl-perl perl library. If
|
||||
"perl -MCPAN -e 'install Bundle::LWP'" fails then you most likely don't
|
||||
have cpan module installed. First download [25]CPAN and [26]install it.
|
||||
Then execute "perl -MCPAN -e 'install Bundle::LWP'".
|
||||
test suite written in perl and python (see below). To execute all the tests
|
||||
you need libwww-perl and libio-socket-ssl-perl perl library.
|
||||
GNU/Linux distros likely have these two libraries packaged.
|
||||
If not, install them directly with "perl -MCPAN -e 'install Bundle::LWP'"[24].
|
||||
If that fails then you most likely don't have the CPAN module installed.
|
||||
First download [25]CPAN and [26]install it, then try again the above command.
|
||||
Now "make check" should pass most of the tests in the test suite.
|
||||
|
||||
* [45]Python3, if you want to run the tests in the testenv/ subdirectory.
|
||||
Keep in mind that "make check" will try to run all the Perl and Python3
|
||||
tests. More information about the test suite below in the section
|
||||
"Testing and development".
|
||||
|
||||
* [27]texinfo in order to generate Info, PostScript and/or HTML
|
||||
documentation. You don't need texinfo in order to generate the
|
||||
wget(1) manpage; however, note that the manpage does not include
|
||||
@@ -62,7 +69,7 @@ Compiling From Repository Sources
|
||||
If you want to compile+link a non-system library version use
|
||||
--with-libssl-prefix (or if having pkg-config: see description below).
|
||||
|
||||
* [31]libidn is required for IDN/IRI support (non-ASCII characters
|
||||
* [31]libidn2 is required for IDN/IRI support (non-ASCII characters
|
||||
within what would otherwise be URLs).
|
||||
|
||||
* [32]libiconv is required on non-GNU systems, for IDN/IRI support.
|
||||
@@ -89,6 +96,13 @@ Compiling From Repository Sources
|
||||
saved the .pc file. Example:
|
||||
$ PKG_CONFIG_PATH="." ./configure
|
||||
|
||||
* [46]libmetalink is needed to enable Metalink files support.
|
||||
|
||||
* [47]GnuPG with GPGME is used to verify GPG-signed Metalink resources.
|
||||
|
||||
* [48]libcares is needed to bind DNS resolving to a given IP address.
|
||||
The command line options --dns-servers and --bind-dns-address are
|
||||
only available when configured with --with-cares.
|
||||
|
||||
For those who might be confused as to what to do once they check out
|
||||
the source code, considering configure and Makefile do not yet exist at
|
||||
@@ -110,6 +124,8 @@ Compiling From Repository Sources
|
||||
$ src/wget --version
|
||||
GNU Wget 1.12-devel (9cb2563197bc)
|
||||
|
||||
Testing and development
|
||||
|
||||
All developers are requested to enable the assertions on their development
|
||||
builds to ensure a stable codebase. Assertions are added to state certain
|
||||
assumptions about the code and its data which all developers should be mindful
|
||||
@@ -118,9 +134,32 @@ Compiling From Repository Sources
|
||||
|
||||
$ ./configure --enable-assert [other configure options]
|
||||
|
||||
Both the Perl and Python test suites (test/ and testenv/) include support for GDB and Valgrind.
|
||||
The environment variables GDB_TESTS and VALGRIND_TESTS are available to
|
||||
enable such wrappers. If specified, Wget would be run through either of them
|
||||
during the test. For example:
|
||||
|
||||
$ cd testenv
|
||||
$ VALGRIND_TESTS=1 ./Test-O.py
|
||||
|
||||
That would execute Test-O.py test case, but running Wget through Valgrind.
|
||||
|
||||
GDB has preference over Valgrind. If both variables have been asserted,
|
||||
Wget would be run through GDB.
|
||||
|
||||
If you run a test case through GDB, please bear in mind that it could give
|
||||
a false negative. This is because some tests that expect Wget to fail
|
||||
rely on Wget's return code. However, when run through GDB, its return code
|
||||
will always be zero, causing the test to claim failure. This wrapper for
|
||||
GDB is, however, very useful to tackle bugs, allowing one to write a test case
|
||||
for some specific bug and then using GDB to fix it more easily. Otherwise,
|
||||
a dedicated server would have to be set up and write a custom CGI just to reproduce
|
||||
that bug, which might be tedious. Tests should only be run through GDB for that purpose.
|
||||
|
||||
|
||||
Copyright (C) 2008,2010,2014,2015 Free Software Foundation, Inc.
|
||||
License GPLv3+: GNU GPL version 3 or later
|
||||
<http://www.gnu.org/licenses/gpl.html>.
|
||||
<https://www.gnu.org/licenses/gpl.html>.
|
||||
This is free software: you are free to change and redistribute it.
|
||||
There is NO WARRANTY, to the extent permitted by law.
|
||||
|
||||
@@ -144,28 +183,32 @@ Compiling From Repository Sources
|
||||
|
||||
References
|
||||
|
||||
20. http://www.gnu.org/software/autoconf/
|
||||
21. http://www.gnu.org/software/automake/
|
||||
22. http://flex.sourceforge.net/
|
||||
23. http://www.perl.org/
|
||||
20. https://www.gnu.org/software/autoconf/
|
||||
21. https://www.gnu.org/software/automake/
|
||||
22. https://github.com/westes/flex
|
||||
23. https://www.perl.org/
|
||||
24. http://search.cpan.org/dist/libwww-perl/lib/Bundle/LWP.pm
|
||||
25. http://search.cpan.org/CPAN/authors/id/A/AN/ANDK/CPAN-1.9402.tar.gz
|
||||
26. http://apthorpe.cynistar.net/code/configuring_cpan.html
|
||||
27. http://www.gnu.org/software/texinfo/
|
||||
28. http://www.gnu.org/software/gettext/
|
||||
29. http://www.gnu.org/software/gnutls/
|
||||
30. http://www.openssl.org/
|
||||
31. http://www.gnu.org/software/libidn/
|
||||
32. http://www.gnu.org/software/libiconv/
|
||||
33. http://git-scm.com/
|
||||
27. https://www.gnu.org/software/texinfo/
|
||||
28. https://www.gnu.org/software/gettext/
|
||||
29. https://www.gnu.org/software/gnutls/
|
||||
30. https://www.openssl.org/
|
||||
31. https://www.gnu.org/software/libidn/#libidn2
|
||||
32. https://www.gnu.org/software/libiconv/
|
||||
33. https://git-scm.com/
|
||||
34. https://github.com/rockdaboot/libpsl
|
||||
35. http://www.pcre.org
|
||||
36. http://wget.addictivecode.org/CompilingRepoSources?action=edit&editor=text
|
||||
37. http://wget.addictivecode.org/CompilingRepoSources
|
||||
38. http://wget.addictivecode.org/CompilingRepoSources?action=info
|
||||
39. http://wget.addictivecode.org/CompilingRepoSources?action=AttachFile
|
||||
40. http://moinmo.in/
|
||||
41. http://moinmo.in/Python
|
||||
42. http://moinmo.in/GPL
|
||||
43. http://validator.w3.org/check?uri=referer
|
||||
40. https://moinmo.in/
|
||||
41. https://moinmo.in/Python
|
||||
42. https://moinmo.in/GPL
|
||||
43. https://validator.w3.org/check?uri=referer
|
||||
44. http://wget.addictivecode.org/WikiLicense
|
||||
45. https://www.python.org/
|
||||
46. https://launchpad.net/libmetalink
|
||||
47. https://www.gnupg.org
|
||||
48. https://c-ares.haxx.se/
|
||||
|
||||
24
bootstrap
24
bootstrap
@@ -1,10 +1,10 @@
|
||||
#! /bin/sh
|
||||
# Print a version string.
|
||||
scriptversion=2013-12-05.23; # UTC
|
||||
scriptversion=2016-01-24.06; # UTC
|
||||
|
||||
# Bootstrap this package from checked-out sources.
|
||||
|
||||
# Copyright (C) 2003-2014 Free Software Foundation, Inc.
|
||||
# Copyright (C) 2003-2016 Free Software Foundation, Inc.
|
||||
|
||||
# This program is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
@@ -42,6 +42,9 @@ export LC_ALL
|
||||
|
||||
local_gl_dir=gl
|
||||
|
||||
# Honor $PERL, but work even if there is none.
|
||||
PERL="${PERL-perl}"
|
||||
|
||||
me=$0
|
||||
|
||||
usage() {
|
||||
@@ -456,6 +459,7 @@ check_versions() {
|
||||
test "$appvar" = TAR && appvar=AMTAR
|
||||
case $appvar in
|
||||
GZIP) ;; # Do not use $GZIP: it contains gzip options.
|
||||
PERL::*) ;; # Keep perl modules as-is
|
||||
*) eval "app=\${$appvar-$app}" ;;
|
||||
esac
|
||||
|
||||
@@ -473,6 +477,17 @@ check_versions() {
|
||||
ret=1
|
||||
continue
|
||||
} ;;
|
||||
# Another check is for perl modules. These can be written as
|
||||
# e.g. perl::XML::XPath in case of XML::XPath module, etc.
|
||||
perl::*)
|
||||
# Extract module name
|
||||
app="${app#perl::}"
|
||||
if ! $PERL -m"$app" -e 'exit 0' >/dev/null 2>&1; then
|
||||
warn_ "Error: perl module '$app' not found"
|
||||
ret=1
|
||||
fi
|
||||
continue
|
||||
;;
|
||||
esac
|
||||
if [ "$req_ver" = "-" ]; then
|
||||
# Merely require app to exist; not all prereq apps are well-behaved
|
||||
@@ -900,7 +915,8 @@ if test $use_libtool = 1; then
|
||||
esac
|
||||
fi
|
||||
echo "$0: $gnulib_tool $gnulib_tool_options --import ..."
|
||||
$gnulib_tool $gnulib_tool_options --import $gnulib_modules &&
|
||||
$gnulib_tool $gnulib_tool_options --import $gnulib_modules \
|
||||
|| die "gnulib-tool failed"
|
||||
|
||||
for file in $gnulib_files; do
|
||||
symlink_to_dir "$GNULIB_SRCDIR" $file \
|
||||
@@ -1005,6 +1021,6 @@ echo "$0: done. Now you can run './configure'."
|
||||
# eval: (add-hook 'write-file-hooks 'time-stamp)
|
||||
# time-stamp-start: "scriptversion="
|
||||
# time-stamp-format: "%:y-%02m-%02d.%02H"
|
||||
# time-stamp-time-zone: "UTC"
|
||||
# time-stamp-time-zone: "UTC0"
|
||||
# time-stamp-end: "; # UTC"
|
||||
# End:
|
||||
|
||||
@@ -38,7 +38,9 @@ close
|
||||
connect
|
||||
dirname
|
||||
fcntl
|
||||
flock
|
||||
fnmatch
|
||||
fopen
|
||||
futimens
|
||||
ftello
|
||||
getaddrinfo
|
||||
@@ -51,9 +53,16 @@ gettext
|
||||
gitlog-to-changelog
|
||||
git-version-gen
|
||||
gnupload
|
||||
hostent
|
||||
ioctl
|
||||
iconv
|
||||
iconv-h
|
||||
inet_ntop
|
||||
intprops
|
||||
inttypes
|
||||
langinfo
|
||||
limits-h
|
||||
link
|
||||
listen
|
||||
maintainer-makefile
|
||||
mbiter
|
||||
@@ -62,8 +71,16 @@ memrchr
|
||||
mkdir
|
||||
mkstemp
|
||||
mkostemp
|
||||
nanosleep
|
||||
crypto/md2
|
||||
crypto/md4
|
||||
crypto/md5
|
||||
crypto/sha1
|
||||
crypto/sha256
|
||||
crypto/sha512
|
||||
open
|
||||
pipe-posix
|
||||
posix_spawn
|
||||
quote
|
||||
quotearg
|
||||
recv
|
||||
@@ -71,24 +88,36 @@ regex
|
||||
select
|
||||
send
|
||||
setsockopt
|
||||
signal-h
|
||||
sigprocmask
|
||||
sigpipe
|
||||
snprintf
|
||||
socket
|
||||
spawn-pipe
|
||||
stat
|
||||
stdbool
|
||||
stdint
|
||||
strcase
|
||||
strerror_r-posix
|
||||
strpbrk
|
||||
strptime
|
||||
strtok_r
|
||||
strtoll
|
||||
symlink
|
||||
sys_types
|
||||
timegm
|
||||
tmpdir
|
||||
unlink
|
||||
unlocked-io
|
||||
update-copyright
|
||||
libunistring-optional
|
||||
unistr/base
|
||||
unicase/tolower
|
||||
utimens
|
||||
vasprintf
|
||||
vsnprintf
|
||||
write
|
||||
xmemdup0
|
||||
xstrndup
|
||||
"
|
||||
|
||||
|
||||
2
cfg.mk
2
cfg.mk
@@ -26,4 +26,4 @@ local-checks-to-skip = \
|
||||
show-vc-list-except:
|
||||
@$(VC_LIST_EXCEPT)
|
||||
|
||||
VC_LIST_ALWAYS_EXCLUDE_REGEX = ^ABOUT-NLS|((msdos|vms)/.*)|ChangeLog-2014-12-10$$
|
||||
VC_LIST_ALWAYS_EXCLUDE_REGEX = ^ABOUT-NLS|((msdos|vms)/.*)|ChangeLog-2014-12-10|/.*.der$$
|
||||
|
||||
159
configure.ac
159
configure.ac
@@ -57,6 +57,8 @@ AC_CANONICAL_HOST
|
||||
AC_DEFINE_UNQUOTED([OS_TYPE], "$host_os",
|
||||
[Define to be the name of the operating system.])
|
||||
|
||||
dnl Non-verbose make
|
||||
m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])])
|
||||
|
||||
dnl
|
||||
dnl Process External Libraries
|
||||
@@ -70,11 +72,16 @@ dnl SSL: Configure SSL backend to use
|
||||
AC_ARG_WITH([ssl],
|
||||
[AS_HELP_STRING([--with-ssl={gnutls,openssl}], [specify SSL backend. GNU TLS is the default.])])
|
||||
|
||||
|
||||
dnl Zlib: Configure use iof zlib for compression
|
||||
dnl Zlib: Configure use of zlib for compression
|
||||
AC_ARG_WITH([zlib],
|
||||
[AS_HELP_STRING([--without-zlib], [disable zlib.])])
|
||||
|
||||
dnl Metalink: Configure use of the Metalink library
|
||||
AC_ARG_WITH([metalink],
|
||||
[AS_HELP_STRING([--with-metalink], [enable support for metalinks.])])
|
||||
|
||||
dnl C-Ares: Configure use of the c-ares library for DNS lookup
|
||||
AC_ARG_WITH(cares, AS_HELP_STRING([--with-cares], [enable support for C-Ares DNS lookup.]), with_cares=$withval, with_cares=no)
|
||||
|
||||
dnl
|
||||
dnl Process features
|
||||
@@ -177,7 +184,7 @@ dnl
|
||||
dnl Gettext
|
||||
dnl
|
||||
AM_GNU_GETTEXT([external],[need-ngettext])
|
||||
AM_GNU_GETTEXT_VERSION([0.17])
|
||||
AM_GNU_GETTEXT_VERSION([0.18.1])
|
||||
|
||||
AC_PROG_RANLIB
|
||||
|
||||
@@ -283,15 +290,6 @@ AC_DEFINE([HAVE_STRNCASECMP], 1, [Define to 1 if you have the `strncasecmp' func
|
||||
AC_DEFINE([HAVE_STRDUP], 1, [Define to 1 if you have the `strdup' function.])
|
||||
AC_DEFINE([HAVE_ISATTY], 1, [Define to 1 if you have the `isatty' function.])
|
||||
|
||||
dnl
|
||||
dnl Call Wget-specific macros defined in aclocal.
|
||||
dnl
|
||||
WGET_STRUCT_UTIMBUF
|
||||
WGET_FNMATCH
|
||||
WGET_NANOSLEEP
|
||||
WGET_POSIX_CLOCK
|
||||
WGET_NSL_SOCKET
|
||||
|
||||
dnl Deal with specific hosts
|
||||
case $host_os in
|
||||
*mingw32* )
|
||||
@@ -322,6 +320,10 @@ AS_IF([test "x$with_libpsl" != xno], [
|
||||
])
|
||||
])
|
||||
|
||||
AS_IF([test x"$with_libpsl" = xyes], [
|
||||
AC_CHECK_FUNCS(psl_latest)
|
||||
])
|
||||
|
||||
AS_IF([test x"$with_zlib" != xno], [
|
||||
with_zlib=yes
|
||||
PKG_CHECK_MODULES([ZLIB], zlib, [
|
||||
@@ -475,6 +477,34 @@ else
|
||||
fi
|
||||
fi
|
||||
|
||||
dnl
|
||||
dnl Check for libmetalink
|
||||
dnl
|
||||
AS_IF([test x"$with_metalink" != xno], [
|
||||
PKG_CHECK_MODULES([METALINK], libmetalink, [
|
||||
LIBS="$METALINK_LIBS $LIBS"
|
||||
CFLAGS="$METALINK_CFLAGS $CFLAGS"
|
||||
AC_DEFINE([HAVE_METALINK], [1], [Define if using metalink.])
|
||||
with_metalink=yes
|
||||
], [
|
||||
with_metalink=no
|
||||
])
|
||||
|
||||
have_gpg=no
|
||||
AS_IF([test x"$with_metalink" = xyes], [
|
||||
dnl
|
||||
dnl Check for GPGME
|
||||
dnl
|
||||
m4_ifdef([AM_PATH_GPGME], [
|
||||
AM_PATH_GPGME([], [
|
||||
LIBS="$GPGME_LIBS $LIBS"
|
||||
CFLAGS="$GPGME_CFLAGS $CFLAGS"
|
||||
AC_DEFINE([HAVE_GPGME], [1], [Define if GPGME is available.])
|
||||
have_gpg=yes
|
||||
])
|
||||
])
|
||||
])
|
||||
])
|
||||
|
||||
dnl **********************************************************************
|
||||
dnl Checks for IPv6
|
||||
@@ -600,9 +630,6 @@ AC_ARG_ENABLE(iri,
|
||||
]
|
||||
)
|
||||
|
||||
AC_ARG_WITH(libidn, AC_HELP_STRING([--with-libidn=[DIR]],
|
||||
[Support IDN/IRIs (needs GNU Libidn)]),
|
||||
libidn=$withval, libidn="")
|
||||
AS_IF([test "X$iri" != "Xno"],[
|
||||
AM_ICONV
|
||||
|
||||
@@ -620,33 +647,26 @@ AS_IF([test "X$iri" != "Xno"],[
|
||||
LIBICONV=
|
||||
])
|
||||
|
||||
AC_ARG_WITH(libidn, AC_HELP_STRING([--with-libidn=[DIR]],
|
||||
[Support IDN2008/IRIs (needs GNU libidn2 + libunicode)]),
|
||||
libidn=$withval, libidn="")
|
||||
if test "X$iri" != "Xno"; then
|
||||
if test "$libidn" != ""; then
|
||||
LDFLAGS="${LDFLAGS} -L$libidn/lib"
|
||||
CPPFLAGS="${CPPFLAGS} -I$libidn/include"
|
||||
fi
|
||||
AS_IF([test "x$with_libidn2" != xno], [
|
||||
AC_SEARCH_LIBS(idn2_lookup_u8, idn2,
|
||||
[with_libidn2=yes; AC_DEFINE([ENABLE_IRI], 1, [Define if IRI support is enabled.])],
|
||||
[with_libidn2=no; iri=no; AC_MSG_WARN(*** LIBIDN2 was not found. You will not be able to use IDN2008 support)])
|
||||
|
||||
# If idna.h can't be found, check to see if it was installed under
|
||||
# /usr/include/idn (OpenSolaris, at least, places it there).
|
||||
# Check for idn-int.h in that case, because idna.h won't find
|
||||
# idn-int.h until we've decided to add -I/usr/include/idn.
|
||||
AC_CHECK_HEADER(idna.h, ,
|
||||
[AC_CHECK_HEADER(idn/idn-int.h,
|
||||
[CPPFLAGS="${CPPFLAGS} -I/usr/include/idn"],
|
||||
[iri=no])]
|
||||
)
|
||||
|
||||
if test "X$iri" != "Xno"; then
|
||||
AC_CHECK_LIB(idn, stringprep_check_version,
|
||||
[iri=yes LIBS="${LIBS} -lidn"], iri=no)
|
||||
fi
|
||||
|
||||
if test "X$iri" != "Xno" ; then
|
||||
AC_DEFINE([ENABLE_IRI], 1, [Define if IRI support is enabled.])
|
||||
AC_MSG_NOTICE([Enabling support for IRI.])
|
||||
else
|
||||
AC_MSG_WARN([Libidn not found])
|
||||
fi
|
||||
# AS_IF([test "x$with_libidn2" = xyes], [
|
||||
# AC_SEARCH_LIBS(u8_tolower, unistring,
|
||||
# [AC_DEFINE([ENABLE_IRI], 1, [Define if IRI support is enabled.])],
|
||||
# [iri=no; AC_MSG_WARN(*** LIBUNISTRING was not found. You will not be able to use IDN2008 support)])
|
||||
# ])
|
||||
])
|
||||
fi
|
||||
if test "X$iri" = "Xno"; then
|
||||
# we don't need libunistring - clear settings from gnulib module
|
||||
LIBUNISTRING=""
|
||||
LTLIBUNISTRING=""
|
||||
fi
|
||||
|
||||
dnl
|
||||
@@ -711,10 +731,62 @@ AS_IF([test "X$enable_pcre" != "Xno"],[
|
||||
])
|
||||
])
|
||||
|
||||
dnl
|
||||
dnl Check for libcares (resolver library)
|
||||
dnl
|
||||
|
||||
AS_IF([test "X$with_cares" = "Xyes"],[
|
||||
PKG_CHECK_MODULES([CARES], libcares, [
|
||||
CFLAGS="$CARES_CFLAGS $CFLAGS"
|
||||
AC_CHECK_HEADER(ares.h, [
|
||||
LIBS="$CARES_LIBS $LIBS"
|
||||
AC_DEFINE([HAVE_LIBCARES], [1], [Define if libcares is available.])
|
||||
RESOLVER_INFO="libcares, --bind-dns-address and --dns-servers available"
|
||||
])
|
||||
], [
|
||||
AC_CHECK_HEADER(ares.h, [
|
||||
AC_CHECK_LIB(cares, ares_set_local_ip4, [
|
||||
LIBS="-lcares ${LIBS}"
|
||||
AC_DEFINE([HAVE_LIBCARES], 1, [Define if libcares is available.])
|
||||
RESOLVER_INFO="libcares, --bind-dns-address and --dns-servers available"
|
||||
])
|
||||
])
|
||||
])
|
||||
], [
|
||||
RESOLVER_INFO="libc, --bind-dns-address and --dns-servers not available"
|
||||
])
|
||||
|
||||
dnl
|
||||
dnl Extended Attribute support
|
||||
dnl
|
||||
|
||||
AC_ARG_ENABLE([xattr],
|
||||
[AS_HELP_STRING([--disable-xattr], [disable support for POSIX Extended Attributes])],
|
||||
[ENABLE_XATTR=$enableval],
|
||||
[ENABLE_XATTR=yes])
|
||||
|
||||
case "$host_os" in
|
||||
*linux* | *darwin*) xattr_syscalls="fsetxattr" ;;
|
||||
freebsd*) xattr_syscalls="extattr_set_fd" ;;
|
||||
*) AC_MSG_NOTICE([Disabling Extended Attribute support: your system is not known to support extended attributes.])
|
||||
ENABLE_XATTR=no
|
||||
esac
|
||||
|
||||
if test "X${ENABLE_XATTR}" = "Xyes"; then
|
||||
AC_CHECK_FUNCS([$xattr_syscalls], [], [
|
||||
AC_MSG_NOTICE([Disabling Extended Attribute support: your system does not support $xattr_syscalls])
|
||||
ENABLE_XATTR=no
|
||||
])
|
||||
fi
|
||||
|
||||
test "X${ENABLE_XATTR}" = "Xyes" && AC_DEFINE([ENABLE_XATTR], 1,
|
||||
[Define if you want file meta-data storing into POSIX Extended Attributes compiled in.])
|
||||
|
||||
dnl Needed by src/Makefile.am
|
||||
AM_CONDITIONAL([IRI_IS_ENABLED], [test "X$iri" != "Xno"])
|
||||
|
||||
AM_CONDITIONAL([WITH_SSL], [test "X$with_ssl" != "Xno"])
|
||||
AM_CONDITIONAL([METALINK_IS_ENABLED], [test "X$with_metalink" != "Xno"])
|
||||
AM_CONDITIONAL([WITH_XATTR], [test "X$ENABLE_XATTR" != "Xno"])
|
||||
|
||||
dnl
|
||||
dnl Create output
|
||||
@@ -740,7 +812,12 @@ AC_MSG_NOTICE([Summary of build options:
|
||||
Digest: $ENABLE_DIGEST
|
||||
NTLM: $ENABLE_NTLM
|
||||
OPIE: $ENABLE_OPIE
|
||||
POSIX xattr: $ENABLE_XATTR
|
||||
Debugging: $ENABLE_DEBUG
|
||||
Assertions: $ENABLE_ASSERTION
|
||||
Valgrind: $VALGRIND_INFO
|
||||
Metalink: $with_metalink
|
||||
Resolver: $RESOLVER_INFO
|
||||
GPGME: $have_gpg
|
||||
IRI: $iri
|
||||
])
|
||||
|
||||
@@ -2,28 +2,30 @@
|
||||
#
|
||||
# Do some checking before 'git push'.
|
||||
|
||||
CORES=`grep -c ^processor /proc/cpuinfo 2>/dev/null || echo 0`
|
||||
# Set a stricter bash mode
|
||||
set -e
|
||||
set -u
|
||||
|
||||
CORES=$(grep -c ^processor /proc/cpuinfo 2> /dev/null || echo 0)
|
||||
if [ $CORES -lt 1 ]; then CORES=1; fi
|
||||
|
||||
make -f Makefile distclean 2>/dev/null
|
||||
echo "Running: make distclean"
|
||||
make distclean > /dev/null || true
|
||||
|
||||
# automatically exit on error
|
||||
set -e
|
||||
|
||||
export CFLAGS="-std=c89 -pedantic -O2 -g -Wall -Wextra -Wstrict-prototypes -Wold-style-definition -Wwrite-strings -Wshadow -Wformat -Wformat-security -Wunreachable-code -Wstrict-prototypes -Wmissing-prototypes -Wold-style-definition"
|
||||
CFLAGS="-std=c89 -pedantic -O0 -g -Wall -Wextra -Wstrict-prototypes -Wold-style-definition -Wwrite-strings -Wshadow -Wformat -Wformat-security -Wunreachable-code -Wstrict-prototypes -Wmissing-prototypes -Wold-style-definition"
|
||||
|
||||
CACHEFILE=$PWD/config_check.cache
|
||||
|
||||
# measure time consumed and print it at the end of the script
|
||||
START=$(date +%s.%N)
|
||||
|
||||
echo "./bootstrap"
|
||||
./bootstrap >/dev/null
|
||||
echo "Running: ./bootstrap"
|
||||
./bootstrap > /dev/null
|
||||
echo
|
||||
|
||||
for CC in gcc clang; do
|
||||
export CC
|
||||
echo "*** checking CC=$CC"
|
||||
echo "*** Testing with CC=$CC"
|
||||
|
||||
# the compiler changed, so we have to remove the cache file here
|
||||
rm -f $CACHEFILE
|
||||
@@ -31,20 +33,20 @@ for CC in gcc clang; do
|
||||
for options in "" "--with-ssl=openssl"; do
|
||||
export DISTCHECK_CONFIGURE_FLAGS="-C --cache-file=$CACHEFILE $options"
|
||||
echo " ./configure $DISTCHECK_CONFIGURE_FLAGS"
|
||||
./configure $DISTCHECK_CONFIGURE_FLAGS >/dev/null
|
||||
./configure $DISTCHECK_CONFIGURE_FLAGS CFLAGS="$CFLAGS" > /dev/null
|
||||
|
||||
for xVALGRIND in 0 1; do
|
||||
for xLCALL in C tr_TR.utf8; do
|
||||
export TESTS_ENVIRONMENT="LC_ALL=$xLCALL VALGRIND_TESTS=$xVALGRIND"
|
||||
echo " TESTS_ENVIRONMENT=\"$TESTS_ENVIRONMENT\"" make check -j$CORES
|
||||
make check -j$CORES >/dev/null
|
||||
make check -j$CORES > /dev/null
|
||||
done
|
||||
done
|
||||
|
||||
unset TESTS_ENVIRONMENT
|
||||
export TESTS_ENVIRONMENT
|
||||
echo " make distcheck -j$CORES"
|
||||
make distcheck -j$CORES
|
||||
echo " make distcheck CFLAGS=$CFLAGS -j$CORES"
|
||||
make distcheck CFLAGS="$CFLAGS" -j$CORES > /dev/null
|
||||
done
|
||||
done
|
||||
|
||||
|
||||
60
contrib/travis-ci
Executable file
60
contrib/travis-ci
Executable file
@@ -0,0 +1,60 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Set a stricter bash mode
|
||||
set -e
|
||||
set -u
|
||||
|
||||
# Set up the subset of tests this Matrix instance will run.
|
||||
|
||||
# One instance is forked for each of the SSL library possibilities
|
||||
SSL=${1:-""}
|
||||
case $SSL in
|
||||
"") SSL_LIB="--without-ssl";;
|
||||
"openssl") SSL_LIB="--with-ssl=openssl";;
|
||||
"gnutls") SSL_LIB="--with-ssl=gnutls";;
|
||||
esac
|
||||
|
||||
# For some reason. /proc/cpuinfo reports 16 cores on Travis, while the docs
|
||||
# claim that each instance has only 2 cores. We believe the docs and force a
|
||||
# value of n+1 here.
|
||||
CORES=3
|
||||
|
||||
# Define a large number of Warning flags for the compiler. Hopefully, someone
|
||||
# will sit and analyze the output to clean the warnings from the codebase.
|
||||
CFLAGS="-std=c89 -pedantic -O0 -Wall -Wextra -Wstrict-prototypes -Wold-style-definition -Wwrite-strings -Wshadow -Wformat -Wformat-security -Wunreachable-code -Wstrict-prototypes -Wmissing-prototypes -Wold-style-definition"
|
||||
|
||||
# A cachefile for ./configure. Saves significant time when reconfiguring
|
||||
CACHEFILE=$PWD/config_check.cache
|
||||
|
||||
# measure time consumed and print it at the end of the script
|
||||
START=$(date +%s)
|
||||
|
||||
# Test different Permutations of Wget. Always under Valgrind
|
||||
#
|
||||
# Options:
|
||||
# - All Features Enabled
|
||||
# - C [Default Locale]
|
||||
# - Russian [Multibyte / Multicolumn Locale]
|
||||
# - Turkish [Special Test due to issues with language]
|
||||
# - IPv6 Disabled
|
||||
# - C
|
||||
for options in "" "--disable-ipv6"; do
|
||||
export DISTCHECK_CONFIGURE_FLAGS="-C --cache-file=$CACHEFILE --enable-assert --enable-valgrind-tests $SSL_LIB $options"
|
||||
echo " ./configure $DISTCHECK_CONFIGURE_FLAGS CFLAGS=\"$CFLAGS\""
|
||||
./configure $DISTCHECK_CONFIGURE_FLAGS CFLAGS="$CFLAGS"
|
||||
|
||||
if [[ -z $options ]]; then
|
||||
LANG_ARR=("ru_RU.UTF-8" "tr_TR.UTF-8" "C")
|
||||
else
|
||||
LANG_ARR=("C")
|
||||
fi
|
||||
|
||||
for xLCALL in "${LANG_ARR[@]}"; do
|
||||
export TESTS_ENVIRONMENT="LC_ALL=$xLCALL VALGRIND_TESTS=1"
|
||||
echo " TESTS_ENVIRONMENT=\"$TESTS_ENVIRONMENT\" make distcheck CFLAGS=$CFLAGS -j$CORES"
|
||||
make distcheck CFLAGS="$CFLAGS" -j$CORES
|
||||
done
|
||||
done
|
||||
|
||||
END=$(date +%s)
|
||||
echo "Duration: $((END-START))"
|
||||
@@ -1,6 +1,6 @@
|
||||
# Makefile for `wget' utility
|
||||
# Copyright (C) 1995, 1996, 1997, 2007, 2008, 2009, 2010, 2011 Free
|
||||
# Software Foundation, Inc.
|
||||
# Copyright (C) 1995, 1996, 1997, 2007, 2008, 2009, 2010, 2011, 2015
|
||||
# Free Software Foundation, Inc.
|
||||
|
||||
# This program is free software; you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
@@ -57,6 +57,7 @@ wget.pod: $(srcdir)/wget.texi version.texi
|
||||
$(TEXI2POD) -D VERSION="$(VERSION)" $(srcdir)/wget.texi $@
|
||||
|
||||
$(MAN): wget.pod
|
||||
$(POD2MAN) --center="GNU Wget" --release="GNU Wget @VERSION@" --utf8 $? > $@ || \
|
||||
$(POD2MAN) --center="GNU Wget" --release="GNU Wget @VERSION@" $? > $@
|
||||
|
||||
#wget.cat: $(MAN)
|
||||
|
||||
@@ -5,7 +5,8 @@
|
||||
@c hence no sectioning command or @node.
|
||||
|
||||
@display
|
||||
Copyright @copyright{} 2000, 2001, 2002, 2007, 2008 Free Software Foundation, Inc.
|
||||
Copyright @copyright{} 2000, 2001, 2002, 2007, 2008, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
@uref{http://fsf.org/}
|
||||
|
||||
Everyone is permitted to copy and distribute verbatim copies
|
||||
|
||||
233
doc/metalink-standard.txt
Normal file
233
doc/metalink-standard.txt
Normal file
@@ -0,0 +1,233 @@
|
||||
GNU Wget Metalink recommended behaviour
|
||||
|
||||
Metalink/XML and Metalink/HTTP standard reference
|
||||
|
||||
|
||||
1. Security features
|
||||
********************
|
||||
|
||||
Only metalink:file elements with safe "name" fields shall be accepted
|
||||
[1 #section-4.1.2.1]. If unsafe metalink:file elements are saved, any
|
||||
related test shall fail (see '2. Tests').
|
||||
|
||||
By design, libmetalink rejects unsafe metalink:file elements [3]:
|
||||
* lib/metalink_helper.c (metalink_check_safe_path): Verify path
|
||||
|
||||
1.1 Exceptions
|
||||
==============
|
||||
|
||||
The option --directory-prefix could allow to use an absolute, relative
|
||||
or home path.
|
||||
|
||||
2. Tests
|
||||
********
|
||||
|
||||
Saving a file to an unexpected path poses a security problem. We must
|
||||
ensure that Wget's automated tests never modify the root and the home
|
||||
paths or descend/escalate to a relative path unexpectedly.
|
||||
|
||||
2.1 Metalink/XML implemented tests
|
||||
==================================
|
||||
|
||||
See testenv/Makefile.am (METALINK_TESTS).
|
||||
|
||||
2.2 Metalink/HTTP implemented tests
|
||||
===================================
|
||||
|
||||
See testenv/Makefile.am (METALINK_TESTS).
|
||||
|
||||
3. Download file name
|
||||
*********************
|
||||
|
||||
The download file name shall be decided by precise rules which prevent
|
||||
any naming uncertainty and security issues.
|
||||
|
||||
3.1 Naming rules
|
||||
================
|
||||
|
||||
The final name of downloaded files is computed starting from a trusted
|
||||
name, which is then combined with the "Directory Options". The result
|
||||
is verified and eventually made safer following security rules. If the
|
||||
final name isn't found safe enough, then the file isn't downloaded.
|
||||
|
||||
Depending on the options used, a suffix could be appended to the final
|
||||
name to not overwrite existing files.
|
||||
|
||||
3.1.1 The trusted name
|
||||
======================
|
||||
|
||||
The option --trust-server-names decides what is the trusted name.
|
||||
|
||||
Any Metalink/XML element with an unsafe metalink:file "name" field is
|
||||
ignored, see '1. Security features'.
|
||||
|
||||
3.1.1.1 Without --trust-server-names
|
||||
====================================
|
||||
|
||||
When --trust-server-names is off, the basename of the --input-metalink
|
||||
file, if available, or of the mother URL is trusted. This trusted name
|
||||
is the radix of any subsequent file name.
|
||||
|
||||
When a Metalink/HTTP in encountered, any fetched Metalink/XML file has
|
||||
its own ordinal number appended as suffix to the trusted name. In this
|
||||
case scenario, an unique Metalink/XML file is saved each time applying
|
||||
an additional suffix to the currently computed name when necessary.
|
||||
|
||||
The files described by a Metalink/XML file will be named sequentially
|
||||
applying an additional suffix to the currently trusted/computed name.
|
||||
|
||||
3.1.1.2 With --trust-server-names
|
||||
=================================
|
||||
|
||||
When --trust-server-names is on, the metalink:file "name" field parsed
|
||||
from Metalink/XML files is trusted. When no Metalink/XML is available,
|
||||
the mother URL is trusted.
|
||||
|
||||
Any Metalink/HTTP application/metalink4+xml file is saved using the
|
||||
basename of its own Link header "name" field, if available.
|
||||
|
||||
In conjunction with the option --content-disposition, a 'Content-Type:
|
||||
application/metalink4+xml' file is saved using the basename of its own
|
||||
Content-Disposition header "filename" field, if available.
|
||||
|
||||
3.1.2 The final name
|
||||
====================
|
||||
|
||||
The "Directory Options" are combined with the trusted name. The result
|
||||
is evaluated again by the '1. Security features'. If the path is found
|
||||
unsafe, only the basename of the final name is considered. If this is
|
||||
found unsafe too, the file is not downloaded.
|
||||
|
||||
4. Metalink/XML
|
||||
***************
|
||||
|
||||
4.1 Example files
|
||||
=================
|
||||
|
||||
See [1 #section-1.1].
|
||||
|
||||
cat > bugus.meta4 << EOF
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<metalink xmlns="urn:ietf:params:xml:ns:metalink">
|
||||
<file name="/dir/A/File1">
|
||||
<size>1617</size>
|
||||
<hash type="sha256">ecb3dff2648667513e31554b3ad054ccd89fce38e33367c9459ac3a285153742</hash>
|
||||
<url>http://another.url/common_name</url>
|
||||
<url>http://ftpmirror.gnu.org/bash/bash-4.3-patches/bash43-001</url>
|
||||
</file>
|
||||
<file name="dir/B/File2">
|
||||
<size>1594</size>
|
||||
<hash type="sha256">eee7cd7062ab29a9e4f02924d9c367264dcb8b162703f74ff6eb8f175a91502b</hash>
|
||||
<url>http://another.url/again/common_name</url>
|
||||
<url>http://ftpmirror.gnu.org/bash/bash-4.3-patches/bash43-002</url>
|
||||
</file>
|
||||
</metalink>
|
||||
EOF
|
||||
|
||||
4.2 Command line example
|
||||
========================
|
||||
|
||||
$ wget --input-metalink=bogus.meta4
|
||||
|
||||
4.3 Metalink/XML file parsing
|
||||
=============================
|
||||
|
||||
The metalink xml file is parsed by one of the following libmetalink's
|
||||
functions [3], depending upon the library configured to use:
|
||||
* lib/libexpat_metalink_parser.c (metalink_parse_file): Expat [4]
|
||||
* lib/libxml2_metalink_parser.c (metalink_parse_file): Libxml2 [5]
|
||||
|
||||
The result returned doesn't include unsafe metalink:file elements, as
|
||||
stated at point '1. Security features'.
|
||||
|
||||
An empty result shall not be considered an error. Parsing errors will
|
||||
be informed to the caller of libmetalink's metalink_parse_file().
|
||||
|
||||
4.4 Saving files
|
||||
================
|
||||
|
||||
Fetched metalink:file elements shall be wrote using the unique "name"
|
||||
field as file name [1 #section-4.1.2.1].
|
||||
|
||||
A metalink:file url's file name shall not substitute the "name" field.
|
||||
|
||||
Security exceptions are explained in '3. Download file name'.
|
||||
|
||||
4.5 Multi-Source download
|
||||
=========================
|
||||
|
||||
Parallel range requests are allowed [1 #section-1].
|
||||
|
||||
5. Metalink/HTTP
|
||||
****************
|
||||
|
||||
5.1 HTTP server
|
||||
===============
|
||||
|
||||
The local server http://127.0.0.1 is used as reference in the course
|
||||
of this chapter. Any server service capable of sending Metalink/HTTP
|
||||
header answers may be used.
|
||||
|
||||
5.2 Command line example
|
||||
========================
|
||||
|
||||
$ wget --metalink-over-http http://127.0.0.1/dir/file.ext
|
||||
|
||||
5.3 Metalink/HTTP header answer
|
||||
===============================
|
||||
|
||||
See [2 #section-1.1].
|
||||
|
||||
Etag: "thvDyvhfIqlvFe+A9MYgxAfm1q5="
|
||||
Link: <http://www2.example.com/example.ext>; rel=duplicate
|
||||
Link: <ftp://ftp.example.com/example.ext>; rel=duplicate
|
||||
Link: <http://example.com/example.ext.torrent>; rel=describedby;
|
||||
type="application/x-bittorrent"
|
||||
Link: <http://example.com/example.ext.meta4>; rel=describedby;
|
||||
type="application/metalink4+xml"
|
||||
Link: <http://example.com/example.ext.asc>; rel=describedby;
|
||||
type="application/pgp-signature"
|
||||
Digest: SHA-256=MWVkMWQxYTRiMzk5MDQ0MzI3NGU5NDEyZTk5OWY1ZGFmNzgyZTJlO
|
||||
DYzYjRjYzFhOTlmNTQwYzI2M2QwM2U2MQ==
|
||||
|
||||
See [2 #section-4].
|
||||
|
||||
Link: <http://example.com/example.ext.torrent>; rel=describedby;
|
||||
type="application/x-bittorrent"; name="differentname.ext"
|
||||
Link: <http://example.com/example.ext.meta4>; rel=describedby;
|
||||
type="application/metalink4+xml"
|
||||
|
||||
5.4 Saving files
|
||||
================
|
||||
|
||||
When none of --output-document and/or --content-disposition is used,
|
||||
the file name to wrote is computed from the cli's url hierarchy. The
|
||||
purpose of the "Directory Options" is as usual, and the file name is
|
||||
the cli's url file name, see wget(1).
|
||||
|
||||
The url followed to download the file shall not substitute the cli's
|
||||
url to compute the file name to wrote, except when it redirects to a
|
||||
Metalink/XML file, following the rules in '3. Download file name'.
|
||||
|
||||
5.5 Multi-Source download
|
||||
=========================
|
||||
|
||||
Parallel range requests are allowed [2 #section-7].
|
||||
|
||||
4. References
|
||||
*************
|
||||
|
||||
[1] The Metalink Download Description Format
|
||||
https://tools.ietf.org/html/rfc5854
|
||||
|
||||
[2] Metalink/HTTP: Mirrors and Hashes
|
||||
https://tools.ietf.org/html/rfc6249
|
||||
|
||||
[3] Libmetalink
|
||||
https://github.com/metalink-dev/libmetalink
|
||||
|
||||
[4] Expat
|
||||
http://www.libexpat.org
|
||||
|
||||
[5] Libxml2
|
||||
http://xmlsoft.org
|
||||
165
doc/metalink.txt
Normal file
165
doc/metalink.txt
Normal file
@@ -0,0 +1,165 @@
|
||||
GNU Wget Metalink module
|
||||
|
||||
Evaluation of the Metalink/XML and Metalink/HTTP implementations
|
||||
|
||||
|
||||
1. Introduction
|
||||
***************
|
||||
|
||||
This document, and the results contained in it, is focused over the
|
||||
evaluation of the Metalink/XML and Metalink/HTTP implementations.
|
||||
|
||||
The "Directory Options" mentioned here are used on the command line in
|
||||
conjunction with the option '--input-metalink=file' for Metalink/XML,
|
||||
and '--metalink-over-http' for Metalink/HTTP.
|
||||
|
||||
$ wget --input-metalink=<file> [directory options]
|
||||
$ wget --metalink-over-http [directory options] <url>
|
||||
|
||||
2. Notes
|
||||
********
|
||||
|
||||
Tests for metalink:file names beginning with '/', '~/', './', or '../'
|
||||
(e.g. "/path/file") shall be run manually due to security concerns.
|
||||
|
||||
3. Metalink files used as reference
|
||||
***********************************
|
||||
|
||||
3.1 Test: metalink:file with "path/file" name format
|
||||
====================================================
|
||||
|
||||
cat > test.meta4 << EOF
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<metalink xmlns="urn:ietf:params:xml:ns:metalink">
|
||||
<file name="path/file">
|
||||
<size>543</size>
|
||||
<hash type="sha256">d37d3965f8e1a7b16504b4273b09c392776b7e4dd17e601256c7b2fd9ce5f56e</hash>
|
||||
<hash type="md5">0f6ff5cdc15603f1b81227b5a296f001</hash>
|
||||
<url>http://wrongurl.really/gnu/wget/wget-1.18.tar.xz.sig</url>
|
||||
<url>http://ftpmirror.gnu.org/wget/wget-1.18.tar.xz.sig</url>
|
||||
<url>http://ftp.gnu.org/gnu/wget/wget-1.18.tar.xz.sig</url>
|
||||
<url>http://nl.mirror.babylon.network/gnu/wget/wget-1.18.tar.xz.sig</url>
|
||||
</file>
|
||||
</metalink>
|
||||
EOF
|
||||
|
||||
4. `wget --input-metalink=test.meta4`
|
||||
*************************************
|
||||
|
||||
4.1 Implemented safety features
|
||||
===============================
|
||||
|
||||
Any metalink:file name containing an absolute, relative, or home path
|
||||
(see '2. Notes') parsed from Metalink/XML files is rejected.
|
||||
|
||||
This is a libmetalink's design decision implemented in the function
|
||||
metalink_check_safe_path(). This feature shall not be modified.
|
||||
|
||||
All the above conform to the RFC5854 standard.
|
||||
|
||||
References:
|
||||
https://tools.ietf.org/html/rfc5854#section-4.1.2.1
|
||||
https://tools.ietf.org/html/rfc5854#section-4.2.8.3
|
||||
|
||||
4.2 File download behaviour
|
||||
===========================
|
||||
|
||||
When a Metalink/XML file is parsed:
|
||||
1. create the metalink:file "path/file" tree;
|
||||
2. download the metalink:url file as "path/file";
|
||||
3. verify the "path/file" size, if declared;
|
||||
4. verify the "path/file" checksum.
|
||||
|
||||
All the above conform to the RFC5854 standard.
|
||||
|
||||
References:
|
||||
https://tools.ietf.org/html/rfc5854
|
||||
|
||||
4.3 Questionable behaviours
|
||||
===========================
|
||||
|
||||
If more metalink:file elements are the same, wget downloads them all.
|
||||
|
||||
5. `wget --metalink-over-http`
|
||||
******************************
|
||||
|
||||
5.1 Implemented safety features
|
||||
===============================
|
||||
|
||||
The function url_file_name() is responsible of parsing the url's file
|
||||
name and mixing in the "Directory Options" wrote on the command line.
|
||||
|
||||
The use of libmetalink's metalink_check_safe_path() shouldn't be
|
||||
necessary (see '4.1 Implemented safety features').
|
||||
|
||||
All the above comform to the usual Wget's download behaviour.
|
||||
|
||||
References:
|
||||
wget(1)
|
||||
|
||||
5.2 File download behaviour
|
||||
===========================
|
||||
|
||||
When a Metalink/HTTP header is parsed:
|
||||
1. extract metalink metadata from the header;
|
||||
2. download the file from the mirror with the highest priority;
|
||||
3. verify the file's size, if declared;
|
||||
4. verify the file's checksum.
|
||||
|
||||
All the above comform to the usual Wget's download behaviour and to
|
||||
the RFC6249 standard.
|
||||
|
||||
References:
|
||||
wget(1)
|
||||
https://tools.ietf.org/html/rfc6249
|
||||
|
||||
6. Directory Options
|
||||
********************
|
||||
|
||||
'-nd'
|
||||
'--no-directories'
|
||||
|
||||
Do not apply to Metalink/XML files (aka --input-metalink=<file>).
|
||||
|
||||
Apply to Metalink/HTTP urls as described in the Wget's manual, see
|
||||
wget(1). The target url is the url wrote on the command line.
|
||||
|
||||
'-x'
|
||||
'--force-directories'
|
||||
|
||||
Do not apply to Metalink/XML files (aka --input-metalink=<file>).
|
||||
|
||||
Apply to Metalink/HTTP urls as described in the Wget's manual, see
|
||||
wget(1). The target url is the url wrote on the command line.
|
||||
|
||||
'-nH'
|
||||
'--no-host-directories'
|
||||
|
||||
Do not apply to Metalink/XML files (aka --input-metalink=<file>).
|
||||
|
||||
Apply to Metalink/HTTP urls as described in the Wget's manual, see
|
||||
wget(1). The target url is the url wrote on the command line.
|
||||
|
||||
'--protocol-directories'
|
||||
|
||||
Do not apply to Metalink/XML files (aka --input-metalink=<file>).
|
||||
|
||||
Apply to Metalink/HTTP urls as described in the Wget's manual, see
|
||||
wget(1). The target url is the url wrote on the command line.
|
||||
|
||||
'--cut-dirs=number'
|
||||
|
||||
Do not apply to Metalink/XML files (aka --input-metalink=<file>).
|
||||
|
||||
Apply to Metalink/HTTP urls as described in the Wget's manual, see
|
||||
wget(1). The target url is the url wrote on the command line.
|
||||
|
||||
'-P prefix'
|
||||
'--directory-prefix=prefix'
|
||||
|
||||
Set the top of the retrieval tree to prefix for both Metalink/XML
|
||||
and Metalink/HTTP downloads, see wget(1).
|
||||
|
||||
If combining the prefix with the file name results in an absolute,
|
||||
relative, or home path, the directory components are stripped and
|
||||
only the basename is used. See '4.1 Implemented safety features'.
|
||||
@@ -1,7 +1,7 @@
|
||||
#! /usr/bin/env perl
|
||||
|
||||
# Copyright (C) 1999, 2000, 2001, 2003, 2007, 2009, 2010, 2011 Free
|
||||
# Software Foundation, Inc.
|
||||
# Copyright (C) 1999, 2000, 2001, 2003, 2007, 2009, 2010, 2011, 2015
|
||||
# Free Software Foundation, Inc.
|
||||
|
||||
# This file is part of GCC.
|
||||
|
||||
@@ -315,6 +315,8 @@ die "No filename or title\n" unless defined $fn && defined $tl;
|
||||
$sects{NAME} = "$fn \- $tl\n";
|
||||
$sects{FOOTNOTES} .= "=back\n" if exists $sects{FOOTNOTES};
|
||||
|
||||
print "=encoding utf-8\n\n";
|
||||
|
||||
for $sect (qw(NAME SYNOPSIS DESCRIPTION OPTIONS ENVIRONMENT EXITSTATUS
|
||||
FILES BUGS NOTES FOOTNOTES SEEALSO AUTHOR COPYRIGHT)) {
|
||||
if(exists $sects{$sect}) {
|
||||
|
||||
489
doc/wget.texi
489
doc/wget.texi
@@ -2,6 +2,7 @@
|
||||
|
||||
@c %**start of header
|
||||
@setfilename wget.info
|
||||
@documentencoding UTF-8
|
||||
@include version.texi
|
||||
@settitle GNU Wget @value{VERSION} Manual
|
||||
@c Disable the monstrous rectangles beside overfull hbox-es.
|
||||
@@ -31,8 +32,8 @@ data.
|
||||
|
||||
@c man begin COPYRIGHT
|
||||
Copyright @copyright{} 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
|
||||
2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
@iftex
|
||||
Permission is granted to make and distribute verbatim copies of
|
||||
@@ -59,11 +60,11 @@ Texts. A copy of the license is included in the section entitled
|
||||
@title GNU Wget @value{VERSION}
|
||||
@subtitle The non-interactive download utility
|
||||
@subtitle Updated for Wget @value{VERSION}, @value{UPDATED}
|
||||
@author by Hrvoje Nik@v{s}i@'{c} and others
|
||||
@author by Hrvoje Nikšić and others
|
||||
|
||||
@ignore
|
||||
@c man begin AUTHOR
|
||||
Originally written by Hrvoje Niksic <hniksic@xemacs.org>.
|
||||
Originally written by Hrvoje Nikšić <hniksic@xemacs.org>.
|
||||
@c man end
|
||||
@c man begin SEEALSO
|
||||
This is @strong{not} the complete manual for GNU Wget.
|
||||
@@ -506,6 +507,39 @@ treated as @samp{html} if the Content-Type matches @samp{text/html}.
|
||||
Furthermore, the @var{file}'s location will be implicitly used as base
|
||||
href if none was specified.
|
||||
|
||||
@cindex input-metalink
|
||||
@item --input-metalink=@var{file}
|
||||
Downloads files covered in local Metalink @var{file}. Metalink version 3
|
||||
and 4 are supported.
|
||||
|
||||
@cindex keep-badhash
|
||||
@item --keep-badhash
|
||||
Keeps downloaded Metalink's files with a bad hash. It appends .badhash
|
||||
to the name of Metalink's files which have a checksum mismatch, except
|
||||
without overwriting existing files.
|
||||
|
||||
@cindex metalink-over-http
|
||||
@item --metalink-over-http
|
||||
Issues HTTP HEAD request instead of GET and extracts Metalink metadata
|
||||
from response headers. Then it switches to Metalink download.
|
||||
If no valid Metalink metadata is found, it falls back to ordinary HTTP download.
|
||||
Enables @samp{Content-Type: application/metalink4+xml} files download/processing.
|
||||
|
||||
@cindex metalink-index
|
||||
@item --metalink-index=@var{number}
|
||||
Set the Metalink @samp{application/metalink4+xml} metaurl ordinal
|
||||
NUMBER. From 1 to the total number of ``application/metalink4+xml''
|
||||
available. Specify 0 or @samp{inf} to choose the first good one.
|
||||
Metaurls, such as those from a @samp{--metalink-over-http}, may have
|
||||
been sorted by priority key's value; keep this in mind to choose the
|
||||
right NUMBER.
|
||||
|
||||
@cindex preferred-location
|
||||
@item --preferred-location
|
||||
Set preferred location for Metalink resources. This has effect if multiple
|
||||
resources with same priority are available.
|
||||
|
||||
|
||||
@cindex force html
|
||||
@item -F
|
||||
@itemx --force-html
|
||||
@@ -533,6 +567,11 @@ would be resolved to @samp{http://foo/baz/b.html}.
|
||||
@cindex specify config
|
||||
@item --config=@var{FILE}
|
||||
Specify the location of a startup file you wish to use.
|
||||
|
||||
@item --rejected-log=@var{logfile}
|
||||
Logs all URL rejections to @var{logfile} as comma separated values. The values
|
||||
include the reason of rejection, the URL and the parent URL it was found in.
|
||||
|
||||
@end table
|
||||
|
||||
@node Download Options, Directory Options, Logging and Input File Options, Invoking
|
||||
@@ -548,6 +587,27 @@ the local machine. @var{ADDRESS} may be specified as a hostname or IP
|
||||
address. This option can be useful if your machine is bound to multiple
|
||||
IPs.
|
||||
|
||||
@cindex bind DNS address
|
||||
@cindex client DNS address
|
||||
@cindex DNS IP address, client, DNS
|
||||
@item --bind-dns-address=@var{ADDRESS}
|
||||
[libcares only]
|
||||
This address overrides the route for DNS requests. If you ever need to
|
||||
circumvent the standard settings from /etc/resolv.conf, this option together
|
||||
with @samp{--dns-servers} is your friend.
|
||||
@var{ADDRESS} must be specified either as IPv4 or IPv6 address.
|
||||
Wget needs to be built with libcares for this option to be available.
|
||||
|
||||
@cindex DNS server
|
||||
@cindex DNS IP address, client, DNS
|
||||
@item --dns-servers=@var{ADDRESSES}
|
||||
[libcares only]
|
||||
The given address(es) override the standard nameserver
|
||||
addresses, e.g. as configured in /etc/resolv.conf.
|
||||
@var{ADDRESSES} may be specified either as IPv4 or IPv6 addresses,
|
||||
comma-separated.
|
||||
Wget needs to be built with libcares for this option to be available.
|
||||
|
||||
@cindex retries
|
||||
@cindex tries
|
||||
@cindex number of tries
|
||||
@@ -585,6 +645,9 @@ content will be placed in @var{file}. This was disabled in version
|
||||
1.11, but has been reinstated (with a warning) in 1.11.2, as there are
|
||||
some cases where this behavior can actually have some use.
|
||||
|
||||
A combination with @samp{-nc} is only accepted if the given output
|
||||
file does not exist.
|
||||
|
||||
Note that a combination with @samp{-k} is only permitted when
|
||||
downloading a single document, as in that case it will just convert
|
||||
all relative URIs to external ones; @samp{-k} makes no sense for
|
||||
@@ -626,6 +689,9 @@ of a file depends on the local and remote timestamp and size of the
|
||||
file (@pxref{Time-Stamping}). @samp{-nc} may not be specified at the
|
||||
same time as @samp{-N}.
|
||||
|
||||
A combination with @samp{-O}/@samp{--output-document} is only accepted
|
||||
if the given output file does not exist.
|
||||
|
||||
Note that when @samp{-nc} is specified, files with the suffixes
|
||||
@samp{.html} or @samp{.htm} will be loaded from the local disk and
|
||||
parsed as if they had been retrieved from the Web.
|
||||
@@ -665,13 +731,11 @@ Without @samp{-c}, the previous example would just download the remote
|
||||
file to @file{ls-lR.Z.1}, leaving the truncated @file{ls-lR.Z} file
|
||||
alone.
|
||||
|
||||
Beginning with Wget 1.7, if you use @samp{-c} on a non-empty file, and
|
||||
it turns out that the server does not support continued downloading,
|
||||
Wget will refuse to start the download from scratch, which would
|
||||
effectively ruin existing contents. If you really want the download to
|
||||
start from scratch, remove the file.
|
||||
If you use @samp{-c} on a non-empty file, and the server does not support
|
||||
continued downloading, Wget will restart the download from scratch and overwrite
|
||||
the existing file entirely.
|
||||
|
||||
Also beginning with Wget 1.7, if you use @samp{-c} on a file which is of
|
||||
Beginning with Wget 1.7, if you use @samp{-c} on a file which is of
|
||||
equal size as the one on the server, Wget will refuse to download the
|
||||
file and print an explanatory message. The same happens when the file
|
||||
is smaller on the server than locally (presumably because it was changed
|
||||
@@ -754,7 +818,7 @@ With @samp{--progress=bar}, there are currently two possible parameters,
|
||||
@var{force} and @var{noscroll}.
|
||||
|
||||
When the output is not a TTY, the progress bar always falls back to ``dot'',
|
||||
even if @samp{--progress=bar} was passed to Wget during invokation. This
|
||||
even if @samp{--progress=bar} was passed to Wget during invocation. This
|
||||
behaviour can be overridden and the ``bar'' output forced by using the ``force''
|
||||
parameter as @samp{--progress=bar:force}.
|
||||
|
||||
@@ -787,6 +851,10 @@ used alongside the @samp{--logfile} option.
|
||||
@itemx --timestamping
|
||||
Turn on time-stamping. @xref{Time-Stamping}, for details.
|
||||
|
||||
@item --no-if-modified-since
|
||||
Do not send If-Modified-Since header in @samp{-N} mode. Send preliminary HEAD
|
||||
request instead. This has only effect in @samp{-N} mode.
|
||||
|
||||
@item --no-use-server-timestamps
|
||||
Don't set the local file's timestamp by the one on the server.
|
||||
|
||||
@@ -950,7 +1018,7 @@ specified in bytes (default), kilobytes (with @samp{k} suffix), or
|
||||
megabytes (with @samp{m} suffix).
|
||||
|
||||
Note that quota will never affect downloading a single file. So if you
|
||||
specify @samp{wget -Q10k ftp://wuarchive.wustl.edu/ls-lR.gz}, all of the
|
||||
specify @samp{wget -Q10k https://example.com/ls-lR.gz}, all of the
|
||||
@file{ls-lR.gz} will be downloaded. The same goes even when several
|
||||
@sc{url}s are specified on the command-line. However, quota is
|
||||
respected when retrieving either recursively, or from an input file.
|
||||
@@ -1102,6 +1170,15 @@ options for @sc{http} connections.
|
||||
Prompt for a password for each connection established. Cannot be specified
|
||||
when @samp{--password} is being used, because they are mutually exclusive.
|
||||
|
||||
@item --use-askpass=@var{command}
|
||||
Prompt for a user and password using the specified command. If no command is
|
||||
specified then the command in the environment variable WGET_ASKPASS is used.
|
||||
If WGET_ASKPASS is not set then the command in the environment variable
|
||||
SSH_ASKPASS is used.
|
||||
|
||||
You can set the default command for use-askpass in the @file{.wgetrc}. That
|
||||
setting may be overridden from the command line.
|
||||
|
||||
@cindex iri support
|
||||
@cindex idn support
|
||||
@item --no-iri
|
||||
@@ -1275,10 +1352,10 @@ the @code{digest}, or the Windows @code{NTLM} authentication scheme.
|
||||
Another way to specify username and password is in the @sc{url} itself
|
||||
(@pxref{URL Format}). Either method reveals your password to anyone who
|
||||
bothers to run @code{ps}. To prevent the passwords from being seen,
|
||||
store them in @file{.wgetrc} or @file{.netrc}, and make sure to protect
|
||||
those files from other users with @code{chmod}. If the passwords are
|
||||
really important, do not leave them lying in those files either---edit
|
||||
the files and delete them after Wget has started the download.
|
||||
use the @samp{--use-askpass} or store them in @file{.wgetrc} or @file{.netrc},
|
||||
and make sure to protect those files from other users with @code{chmod}. If
|
||||
the passwords are really important, do not leave them lying in those files
|
||||
either---edit the files and delete them after Wget has started the download.
|
||||
|
||||
@iftex
|
||||
@xref{Security Considerations}, for more information about security
|
||||
@@ -1521,6 +1598,11 @@ Please note that wget does not require the content to be of the form
|
||||
simply transmit whatever data is provided to it. Most servers however expect
|
||||
the POST data to be in the above format when processing HTML Forms.
|
||||
|
||||
When sending a POST request using the @samp{--post-file} option, Wget treats
|
||||
the file as a binary file and will send every character in the POST request
|
||||
without stripping trailing newline or formfeed characters. Any other control
|
||||
characters in the text will also be sent as-is in the POST request.
|
||||
|
||||
Please be aware that Wget needs to know the size of the POST data in
|
||||
advance. Therefore the argument to @code{--post-file} must be a regular
|
||||
file; specifying a FIFO or something like @file{/dev/stdin} won't work.
|
||||
@@ -1548,11 +1630,11 @@ users:
|
||||
# @r{Log in to the server. This can be done only once.}
|
||||
wget --save-cookies cookies.txt \
|
||||
--post-data 'user=foo&password=bar' \
|
||||
http://server.com/auth.php
|
||||
http://example.com/auth.php
|
||||
|
||||
# @r{Now grab the page or pages we care about.}
|
||||
wget --load-cookies cookies.txt \
|
||||
-p http://server.com/interesting/article.php
|
||||
-p http://example.com/interesting/article.php
|
||||
@end group
|
||||
@end example
|
||||
|
||||
@@ -1605,6 +1687,10 @@ This option is useful for some file-downloading CGI programs that use
|
||||
@code{Content-Disposition} headers to describe what the name of a
|
||||
downloaded file should be.
|
||||
|
||||
When combined with @samp{--metalink-over-http} and @samp{--trust-server-names},
|
||||
a @samp{Content-Type: application/metalink4+xml} file is named using the
|
||||
@code{Content-Disposition} filename field, if available.
|
||||
|
||||
@cindex Content On Error
|
||||
@item --content-on-error
|
||||
|
||||
@@ -1614,9 +1700,11 @@ with a http status code that indicates error.
|
||||
@cindex Trust server names
|
||||
@item --trust-server-names
|
||||
|
||||
If this is set to on, on a redirect the last component of the
|
||||
redirection URL will be used as the local file name. By default it is
|
||||
used the last component in the original URL.
|
||||
If this is set, on a redirect, the local file name will be based
|
||||
on the redirection URL. By default the local file name is based on
|
||||
the original URL. When doing recursive retrieving this can be helpful
|
||||
because in many web sites redirected URLs correspond to an underlying
|
||||
file structure, while link URLs do not.
|
||||
|
||||
@cindex authentication
|
||||
@item --auth-no-challenge
|
||||
@@ -1637,8 +1725,9 @@ form-based authentication.
|
||||
|
||||
@cindex SSL
|
||||
To support encrypted HTTP (HTTPS) downloads, Wget must be compiled
|
||||
with an external SSL library, currently OpenSSL. If Wget is compiled
|
||||
without SSL support, none of these options are available.
|
||||
with an external SSL library. The current default is GnuTLS.
|
||||
In addition, Wget also supports HSTS (HTTP Strict Transport Security).
|
||||
If Wget is compiled without SSL support, none of these options are available.
|
||||
|
||||
@table @samp
|
||||
@cindex SSL protocol, choose
|
||||
@@ -1686,6 +1775,12 @@ this option to bypass the verification and proceed with the download.
|
||||
site's authenticity, or if you really don't care about the validity of
|
||||
its certificate.} It is almost always a bad idea not to check the
|
||||
certificates when transmitting confidential or important data.
|
||||
For self-signed/internal certificates, you should download the certificate
|
||||
and verify against that instead of forcing this insecure mode.
|
||||
If you are really sure of not desiring any certificate verification, you
|
||||
can specify --check-certificate=quiet to tell wget to not print any
|
||||
warning about invalid certificates, albeit in most cases this is the
|
||||
wrong thing to do.
|
||||
|
||||
@cindex SSL certificate
|
||||
@item --certificate=@var{file}
|
||||
@@ -1733,6 +1828,18 @@ system-specified locations, chosen at OpenSSL installation time.
|
||||
Specifies a CRL file in @var{file}. This is needed for certificates
|
||||
that have been revocated by the CAs.
|
||||
|
||||
@cindex SSL Public Key Pin
|
||||
@item --pinnedpubkey=file/hashes
|
||||
Tells wget to use the specified public key file (or hashes) to verify the peer.
|
||||
This can be a path to a file which contains a single public key in PEM or DER
|
||||
format, or any number of base64 encoded sha256 hashes preceded by ``sha256//''
|
||||
and separated by ``;''
|
||||
|
||||
When negotiating a TLS or SSL connection, the server sends a certificate
|
||||
indicating its identity. A public key is extracted from this certificate and if
|
||||
it does not exactly match the public key(s) provided to this option, wget will
|
||||
abort the connection before sending or receiving any data.
|
||||
|
||||
@cindex entropy, specifying source of
|
||||
@cindex randomness, specifying source of
|
||||
@item --random-file=@var{file}
|
||||
@@ -1768,6 +1875,71 @@ read random data from EGD socket specified using this option.
|
||||
If this option is not specified (and the equivalent startup command is
|
||||
not used), EGD is never contacted. EGD is not needed on modern Unix
|
||||
systems that support @file{/dev/urandom}.
|
||||
|
||||
@cindex HSTS
|
||||
@item --no-hsts
|
||||
Wget supports HSTS (HTTP Strict Transport Security, RFC 6797) by default.
|
||||
Use @samp{--no-hsts} to make Wget act as a non-HSTS-compliant UA. As a
|
||||
consequence, Wget would ignore all the @code{Strict-Transport-Security}
|
||||
headers, and would not enforce any existing HSTS policy.
|
||||
|
||||
@item --hsts-file=@var{file}
|
||||
By default, Wget stores its HSTS database in @file{~/.wget-hsts}.
|
||||
You can use @samp{--hsts-file} to override this. Wget will use
|
||||
the supplied file as the HSTS database. Such file must conform to the
|
||||
correct HSTS database format used by Wget. If Wget cannot parse the provided
|
||||
file, the behaviour is unspecified.
|
||||
|
||||
The Wget's HSTS database is a plain text file. Each line contains an HSTS entry
|
||||
(ie. a site that has issued a @code{Strict-Transport-Security} header and that
|
||||
therefore has specified a concrete HSTS policy to be applied). Lines starting with
|
||||
a dash (@code{#}) are ignored by Wget. Please note that in spite of this convenient
|
||||
human-readability hand-hacking the HSTS database is generally not a good idea.
|
||||
|
||||
An HSTS entry line consists of several fields separated by one or more whitespace:
|
||||
|
||||
@code{<hostname> SP [<port>] SP <include subdomains> SP <created> SP <max-age>}
|
||||
|
||||
The @var{hostname} and @var{port} fields indicate the hostname and port to which
|
||||
the given HSTS policy applies. The @var{port} field may be zero, and it will, in
|
||||
most of the cases. That means that the port number will not be taken into account
|
||||
when deciding whether such HSTS policy should be applied on a given request (only
|
||||
the hostname will be evaluated). When @var{port} is different to zero, both the
|
||||
target hostname and the port will be evaluated and the HSTS policy will only be applied
|
||||
if both of them match. This feature has been included for testing/development purposes only.
|
||||
The Wget testsuite (in @file{testenv/}) creates HSTS databases with explicit ports
|
||||
with the purpose of ensuring Wget's correct behaviour. Applying HSTS policies to ports
|
||||
other than the default ones is discouraged by RFC 6797 (see Appendix B "Differences
|
||||
between HSTS Policy and Same-Origin Policy"). Thus, this functionality should not be used
|
||||
in production environments and @var{port} will typically be zero. The last three fields
|
||||
do what they are expected to. The field @var{include_subdomains} can either be @code{1}
|
||||
or @code{0} and it signals whether the subdomains of the target domain should be
|
||||
part of the given HSTS policy as well. The @var{created} and @var{max-age} fields
|
||||
hold the timestamp values of when such entry was created (first seen by Wget) and the
|
||||
HSTS-defined value 'max-age', which states how long should that HSTS policy remain active,
|
||||
measured in seconds elapsed since the timestamp stored in @var{created}. Once that time
|
||||
has passed, that HSTS policy will no longer be valid and will eventually be removed
|
||||
from the database.
|
||||
|
||||
If you supply your own HSTS database via @samp{--hsts-file}, be aware that Wget
|
||||
may modify the provided file if any change occurs between the HSTS policies
|
||||
requested by the remote servers and those in the file. When Wget exists,
|
||||
it effectively updates the HSTS database by rewriting the database file with the new entries.
|
||||
|
||||
If the supplied file does not exist, Wget will create one. This file will contain the new HSTS
|
||||
entries. If no HSTS entries were generated (no @code{Strict-Transport-Security} headers
|
||||
were sent by any of the servers) then no file will be created, not even an empty one. This
|
||||
behaviour applies to the default database file (@file{~/.wget-hsts}) as well: it will not be
|
||||
created until some server enforces an HSTS policy.
|
||||
|
||||
Care is taken not to override possible changes made by other Wget processes at
|
||||
the same time over the HSTS database. Before dumping the updated HSTS entries
|
||||
on the file, Wget will re-read it and merge the changes.
|
||||
|
||||
Using a custom HSTS database and/or modifying an existing one is discouraged.
|
||||
For more information about the potential security threats arised from such practice,
|
||||
see section 14 "Security Considerations" of RFC 6797, specially section 14.9
|
||||
"Creative Manipulation of HSTS Policy Store".
|
||||
@end table
|
||||
|
||||
@cindex WARC
|
||||
@@ -1910,6 +2082,43 @@ this option has no effect. Symbolic links are always traversed in this
|
||||
case.
|
||||
@end table
|
||||
|
||||
@section FTPS Options
|
||||
|
||||
@table @samp
|
||||
@item --ftps-implicit
|
||||
This option tells Wget to use FTPS implicitly. Implicit FTPS consists of initializing
|
||||
SSL/TLS from the very beginning of the control connection. This option does not send
|
||||
an @code{AUTH TLS} command: it assumes the server speaks FTPS and directly starts an
|
||||
SSL/TLS connection. If the attempt is successful, the session continues just like
|
||||
regular FTPS (@code{PBSZ} and @code{PROT} are sent, etc.).
|
||||
Implicit FTPS is no longer a requirement for FTPS implementations, and thus
|
||||
many servers may not support it. If @samp{--ftps-implicit} is passed and no explicit
|
||||
port number specified, the default port for implicit FTPS, 990, will be used, instead
|
||||
of the default port for the "normal" (explicit) FTPS which is the same as that of FTP,
|
||||
21.
|
||||
|
||||
@item --no-ftps-resume-ssl
|
||||
Do not resume the SSL/TLS session in the data channel. When starting a data connection,
|
||||
Wget tries to resume the SSL/TLS session previously started in the control connection.
|
||||
SSL/TLS session resumption avoids performing an entirely new handshake by reusing
|
||||
the SSL/TLS parameters of a previous session. Typically, the FTPS servers want it that way,
|
||||
so Wget does this by default. Under rare circumstances however, one might want to
|
||||
start an entirely new SSL/TLS session in every data connection.
|
||||
This is what @samp{--no-ftps-resume-ssl} is for.
|
||||
|
||||
@item --ftps-clear-data-connection
|
||||
All the data connections will be in plain text. Only the control connection will be
|
||||
under SSL/TLS. Wget will send a @code{PROT C} command to achieve this, which must be
|
||||
approved by the server.
|
||||
|
||||
@item --ftps-fallback-to-ftp
|
||||
Fall back to FTP if FTPS is not supported by the target server. For security reasons,
|
||||
this option is not asserted by default. The default behaviour is to exit with an error.
|
||||
If a server does not successfully reply to the initial @code{AUTH TLS} command, or in the
|
||||
case of implicit FTPS, if the initial SSL/TLS connection attempt is rejected, it is
|
||||
considered that such server does not support FTPS.
|
||||
@end table
|
||||
|
||||
@node Recursive Retrieval Options, Recursive Accept/Reject Options, FTP Options, Invoking
|
||||
@section Recursive Retrieval Options
|
||||
|
||||
@@ -1988,6 +2197,23 @@ Note that only at the end of the download can Wget know which links have
|
||||
been downloaded. Because of that, the work done by @samp{-k} will be
|
||||
performed at the end of all the downloads.
|
||||
|
||||
@item --convert-file-only
|
||||
This option converts only the filename part of the URLs, leaving the rest
|
||||
of the URLs untouched. This filename part is sometimes referred to as the
|
||||
"basename", although we avoid that term here in order not to cause confusion.
|
||||
|
||||
It works particularly well in conjunction with @samp{--adjust-extension}, although
|
||||
this coupling is not enforced. It proves useful to populate Internet caches
|
||||
with files downloaded from different hosts.
|
||||
|
||||
Example: if some link points to @file{//foo.com/bar.cgi?xyz} with
|
||||
@samp{--adjust-extension} asserted and its local destination is intended to be
|
||||
@file{./foo.com/bar.cgi?xyz.css}, then the link would be converted to
|
||||
@file{//foo.com/bar.cgi?xyz.css}. Note that only the filename part has been
|
||||
modified. The rest of the URL has been left untouched, including the net path
|
||||
(@code{//}) which would otherwise be processed by Wget and converted to the
|
||||
effective scheme (ie. @code{http://}).
|
||||
|
||||
@cindex backing up converted files
|
||||
@item -K
|
||||
@itemx --backup-converted
|
||||
@@ -2397,11 +2623,11 @@ The @samp{-D} option allows you to specify the domains that will be
|
||||
followed, thus limiting the recursion only to the hosts that belong to
|
||||
these domains. Obviously, this makes sense only in conjunction with
|
||||
@samp{-H}. A typical example would be downloading the contents of
|
||||
@samp{www.server.com}, but allowing downloads from
|
||||
@samp{images.server.com}, etc.:
|
||||
@samp{www.example.com}, but allowing downloads from
|
||||
@samp{images.example.com}, etc.:
|
||||
|
||||
@example
|
||||
wget -rH -Dserver.com http://www.server.com/
|
||||
wget -rH -Dexample.com http://www.example.com/
|
||||
@end example
|
||||
|
||||
You can specify more than one address by separating them with a comma,
|
||||
@@ -2641,7 +2867,7 @@ These links are not relative:
|
||||
@example
|
||||
<a href="/foo.gif">
|
||||
<a href="/foo/bar.gif">
|
||||
<a href="http://www.server.com/foo/bar.gif">
|
||||
<a href="http://www.example.com/foo/bar.gif">
|
||||
@end example
|
||||
|
||||
Using this option guarantees that recursive retrieval will not span
|
||||
@@ -3004,8 +3230,8 @@ Turn on recognition of the (non-standard) @samp{Content-Disposition}
|
||||
HTTP header---if set to @samp{on}, the same as @samp{--content-disposition}.
|
||||
|
||||
@item trust_server_names = on/off
|
||||
If set to on, use the last component of a redirection URL for the local
|
||||
file name.
|
||||
If set to on, construct the local file name from redirection URLs
|
||||
rather than original URLs.
|
||||
|
||||
@item continue = on/off
|
||||
If set to on, force continuation of preexistent partially retrieved
|
||||
@@ -3511,7 +3737,7 @@ same directory structure the original has, with only one try per
|
||||
document, saving the log of the activities to @file{gnulog}:
|
||||
|
||||
@example
|
||||
wget -r http://www.gnu.org/ -o gnulog
|
||||
wget -r https://www.gnu.org/ -o gnulog
|
||||
@end example
|
||||
|
||||
@item
|
||||
@@ -3519,7 +3745,7 @@ The same as the above, but convert the links in the downloaded files to
|
||||
point to local files, so you can view the documents off-line:
|
||||
|
||||
@example
|
||||
wget --convert-links -r http://www.gnu.org/ -o gnulog
|
||||
wget --convert-links -r https://www.gnu.org/ -o gnulog
|
||||
@end example
|
||||
|
||||
@item
|
||||
@@ -3529,22 +3755,22 @@ sheets, are also downloaded. Also make sure the downloaded page
|
||||
references the downloaded links.
|
||||
|
||||
@example
|
||||
wget -p --convert-links http://www.server.com/dir/page.html
|
||||
wget -p --convert-links http://www.example.com/dir/page.html
|
||||
@end example
|
||||
|
||||
The @sc{html} page will be saved to @file{www.server.com/dir/page.html}, and
|
||||
the images, stylesheets, etc., somewhere under @file{www.server.com/},
|
||||
The @sc{html} page will be saved to @file{www.example.com/dir/page.html}, and
|
||||
the images, stylesheets, etc., somewhere under @file{www.example.com/},
|
||||
depending on where they were on the remote server.
|
||||
|
||||
@item
|
||||
The same as the above, but without the @file{www.server.com/} directory.
|
||||
The same as the above, but without the @file{www.example.com/} directory.
|
||||
In fact, I don't want to have all those random server directories
|
||||
anyway---just save @emph{all} those files under a @file{download/}
|
||||
subdirectory of the current directory.
|
||||
|
||||
@example
|
||||
wget -p --convert-links -nH -nd -Pdownload \
|
||||
http://www.server.com/dir/page.html
|
||||
http://www.example.com/dir/page.html
|
||||
@end example
|
||||
|
||||
@item
|
||||
@@ -3573,12 +3799,12 @@ wget -r -l2 -P/tmp ftp://wuarchive.wustl.edu/
|
||||
|
||||
@item
|
||||
You want to download all the @sc{gif}s from a directory on an @sc{http}
|
||||
server. You tried @samp{wget http://www.server.com/dir/*.gif}, but that
|
||||
server. You tried @samp{wget http://www.example.com/dir/*.gif}, but that
|
||||
didn't work because @sc{http} retrieval does not support globbing. In
|
||||
that case, use:
|
||||
|
||||
@example
|
||||
wget -r -l1 --no-parent -A.gif http://www.server.com/dir/
|
||||
wget -r -l1 --no-parent -A.gif http://www.example.com/dir/
|
||||
@end example
|
||||
|
||||
More verbose, but the effect is the same. @samp{-r -l1} means to
|
||||
@@ -3594,7 +3820,7 @@ interrupted. Now you do not want to clobber the files already present.
|
||||
It would be:
|
||||
|
||||
@example
|
||||
wget -nc -r http://www.gnu.org/
|
||||
wget -nc -r https://www.gnu.org/
|
||||
@end example
|
||||
|
||||
@item
|
||||
@@ -3602,7 +3828,7 @@ If you want to encode your own username and password to @sc{http} or
|
||||
@sc{ftp}, use the appropriate @sc{url} syntax (@pxref{URL Format}).
|
||||
|
||||
@example
|
||||
wget ftp://hniksic:mypassword@@unix.server.com/.emacs
|
||||
wget ftp://hniksic:mypassword@@unix.example.com/.emacs
|
||||
@end example
|
||||
|
||||
Note, however, that this usage is not advisable on multi-user systems
|
||||
@@ -3639,7 +3865,7 @@ to recheck a site each Sunday:
|
||||
|
||||
@example
|
||||
crontab
|
||||
0 0 * * 0 wget --mirror http://www.gnu.org/ -o /home/me/weeklog
|
||||
0 0 * * 0 wget --mirror https://www.gnu.org/ -o /home/me/weeklog
|
||||
@end example
|
||||
|
||||
@item
|
||||
@@ -3651,7 +3877,7 @@ would look like this:
|
||||
|
||||
@example
|
||||
wget --mirror --convert-links --backup-converted \
|
||||
http://www.gnu.org/ -o /home/me/weeklog
|
||||
https://www.gnu.org/ -o /home/me/weeklog
|
||||
@end example
|
||||
|
||||
@item
|
||||
@@ -3664,13 +3890,13 @@ or @samp{application/xhtml+xml} to @file{@var{name}.html}.
|
||||
@example
|
||||
wget --mirror --convert-links --backup-converted \
|
||||
--html-extension -o /home/me/weeklog \
|
||||
http://www.gnu.org/
|
||||
https://www.gnu.org/
|
||||
@end example
|
||||
|
||||
Or, with less typing:
|
||||
|
||||
@example
|
||||
wget -m -k -K -E http://www.gnu.org/ -o /home/me/weeklog
|
||||
wget -m -k -K -E https://www.gnu.org/ -o /home/me/weeklog
|
||||
@end example
|
||||
@end itemize
|
||||
@c man end
|
||||
@@ -3777,14 +4003,14 @@ username and password.
|
||||
Like all GNU utilities, the latest version of Wget can be found at the
|
||||
master GNU archive site ftp.gnu.org, and its mirrors. For example,
|
||||
Wget @value{VERSION} can be found at
|
||||
@url{ftp://ftp.gnu.org/pub/gnu/wget/wget-@value{VERSION}.tar.gz}
|
||||
@url{https://ftp.gnu.org/pub/gnu/wget/wget-@value{VERSION}.tar.gz}
|
||||
|
||||
@node Web Site, Mailing Lists, Distribution, Various
|
||||
@section Web Site
|
||||
@cindex web site
|
||||
|
||||
The official web site for GNU Wget is at
|
||||
@url{http://www.gnu.org/software/wget/}. However, most useful
|
||||
@url{https//www.gnu.org/software/wget/}. However, most useful
|
||||
information resides at ``The Wget Wgiki'',
|
||||
@url{http://wget.addictivecode.org/}.
|
||||
|
||||
@@ -3798,14 +4024,14 @@ information resides at ``The Wget Wgiki'',
|
||||
The primary mailinglist for discussion, bug-reports, or questions
|
||||
about GNU Wget is at @email{bug-wget@@gnu.org}. To subscribe, send an
|
||||
email to @email{bug-wget-join@@gnu.org}, or visit
|
||||
@url{http://lists.gnu.org/mailman/listinfo/bug-wget}.
|
||||
@url{https://lists.gnu.org/mailman/listinfo/bug-wget}.
|
||||
|
||||
You do not need to subscribe to send a message to the list; however,
|
||||
please note that unsubscribed messages are moderated, and may take a
|
||||
while before they hit the list---@strong{usually around a day}. If
|
||||
you want your message to show up immediately, please subscribe to the
|
||||
list before posting. Archives for the list may be found at
|
||||
@url{http://lists.gnu.org/pipermail/bug-wget/}.
|
||||
@url{https://lists.gnu.org/archive/html/bug-wget/}.
|
||||
|
||||
An NNTP/Usenettish gateway is also available via
|
||||
@uref{http://gmane.org/about.php,Gmane}. You can see the Gmane
|
||||
@@ -3813,15 +4039,7 @@ archives at
|
||||
@url{http://news.gmane.org/gmane.comp.web.wget.general}. Note that the
|
||||
Gmane archives conveniently include messages from both the current
|
||||
list, and the previous one. Messages also show up in the Gmane
|
||||
archives sooner than they do at @url{lists.gnu.org}.
|
||||
|
||||
@unnumberedsubsec Bug Notices List
|
||||
|
||||
Additionally, there is the @email{wget-notify@@addictivecode.org} mailing
|
||||
list. This is a non-discussion list that receives bug report
|
||||
notifications from the bug-tracker. To subscribe to this list,
|
||||
send an email to @email{wget-notify-join@@addictivecode.org},
|
||||
or visit @url{http://addictivecode.org/mailman/listinfo/wget-notify}.
|
||||
archives sooner than they do at @url{https://lists.gnu.org}.
|
||||
|
||||
@unnumberedsubsec Obsolete Lists
|
||||
|
||||
@@ -3833,7 +4051,7 @@ discussing patches to GNU Wget.
|
||||
Messages from @email{wget@@sunsite.dk} are archived at
|
||||
@itemize @tie{}
|
||||
@item
|
||||
@url{http://www.mail-archive.com/wget%40sunsite.dk/} and at
|
||||
@url{https://www.mail-archive.com/wget%40sunsite.dk/} and at
|
||||
@item
|
||||
@url{http://news.gmane.org/gmane.comp.web.wget.general} (which also
|
||||
continues to archive the current list, @email{bug-wget@@gnu.org}).
|
||||
@@ -3862,7 +4080,7 @@ via IRC at @code{irc.freenode.org}, @code{#wget}. Come check it out!
|
||||
|
||||
@c man begin BUGS
|
||||
You are welcome to submit bug reports via the GNU Wget bug tracker (see
|
||||
@url{http://wget.addictivecode.org/BugTracker}).
|
||||
@url{https://savannah.gnu.org/bugs/?func=additem&group=wget}).
|
||||
|
||||
Before actually submitting a bug report, please try to follow a few
|
||||
simple guidelines.
|
||||
@@ -3879,7 +4097,7 @@ Lists}).
|
||||
@item
|
||||
Try to repeat the bug in as simple circumstances as possible. E.g. if
|
||||
Wget crashes while downloading @samp{wget -rl0 -kKE -t5 --no-proxy
|
||||
http://yoyodyne.com -o /tmp/log}, you should try to see if the crash is
|
||||
http://example.com -o /tmp/log}, you should try to see if the crash is
|
||||
repeatable, and if will occur with a simpler set of options. You might
|
||||
even try to start the download at the page where the crash occurred to
|
||||
see if that page somehow triggered the crash.
|
||||
@@ -3944,7 +4162,7 @@ Windows-related features might look at them.
|
||||
|
||||
Support for building on MS-DOS via DJGPP has been contributed by Gisle
|
||||
Vanem; a port to VMS is maintained by Steven Schweda, and is available
|
||||
at @url{http://antinode.org/}.
|
||||
at @url{https://antinode.info/dec/sw/wget.html}.
|
||||
|
||||
@node Signals, , Portability, Various
|
||||
@section Signals
|
||||
@@ -4022,23 +4240,23 @@ download an individual page. Because of that, Wget honors RES when
|
||||
downloading recursively. For instance, when you issue:
|
||||
|
||||
@example
|
||||
wget -r http://www.server.com/
|
||||
wget -r http://www.example.com/
|
||||
@end example
|
||||
|
||||
First the index of @samp{www.server.com} will be downloaded. If Wget
|
||||
First the index of @samp{www.example.com} will be downloaded. If Wget
|
||||
finds that it wants to download more documents from that server, it will
|
||||
request @samp{http://www.server.com/robots.txt} and, if found, use it
|
||||
request @samp{http://www.example.com/robots.txt} and, if found, use it
|
||||
for further downloads. @file{robots.txt} is loaded only once per each
|
||||
server.
|
||||
|
||||
Until version 1.8, Wget supported the first version of the standard,
|
||||
written by Martijn Koster in 1994 and available at
|
||||
@url{http://www.robotstxt.org/wc/norobots.html}. As of version 1.8,
|
||||
@url{http://www.robotstxt.org/robotstxt.html}. As of version 1.8,
|
||||
Wget has supported the additional directives specified in the internet
|
||||
draft @samp{<draft-koster-robots-00.txt>} titled ``A Method for Web
|
||||
Robots Control''. The draft, which has as far as I know never made to
|
||||
an @sc{rfc}, is available at
|
||||
@url{http://www.robotstxt.org/wc/norobots-rfc.txt}.
|
||||
@url{http://www.robotstxt.org/norobots-rfc.txt}.
|
||||
|
||||
This manual no longer includes the text of the Robot Exclusion Standard.
|
||||
|
||||
@@ -4096,12 +4314,7 @@ me).
|
||||
@section Contributors
|
||||
@cindex contributors
|
||||
|
||||
@iftex
|
||||
GNU Wget was written by Hrvoje Nik@v{s}i@'{c} @email{hniksic@@xemacs.org},
|
||||
@end iftex
|
||||
@ifnottex
|
||||
GNU Wget was written by Hrvoje Niksic @email{hniksic@@xemacs.org}.
|
||||
@end ifnottex
|
||||
GNU Wget was written by Hrvoje Nikšić @email{hniksic@@xemacs.org},
|
||||
|
||||
However, the development of Wget could never have gone as far as it has, were
|
||||
it not for the help of many people, either with bug reports, feature proposals,
|
||||
@@ -4141,14 +4354,8 @@ portability fixes.
|
||||
Gordon Matzigkeit---@file{.netrc} support.
|
||||
|
||||
@item
|
||||
@iftex
|
||||
Zlatko @v{C}alu@v{s}i@'{c}, Tomislav Vujec and Dra@v{z}en
|
||||
Ka@v{c}ar---feature suggestions and ``philosophical'' discussions.
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Zlatko Calusic, Tomislav Vujec and Drazen Kacar---feature suggestions
|
||||
and ``philosophical'' discussions.
|
||||
@end ifnottex
|
||||
Zlatko Čalušić, Tomislav Vujec and Dražen
|
||||
Kačar---feature suggestions and ``philosophical'' discussions.
|
||||
|
||||
@item
|
||||
Darko Budor---initial port to Windows.
|
||||
@@ -4158,21 +4365,11 @@ Antonio Rosella---help and suggestions, plus the initial Italian
|
||||
translation.
|
||||
|
||||
@item
|
||||
@iftex
|
||||
Tomislav Petrovi@'{c}, Mario Miko@v{c}evi@'{c}---many bug reports and
|
||||
Tomislav Petrović, Mario Mikočević---many bug reports and
|
||||
suggestions.
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Tomislav Petrovic, Mario Mikocevic---many bug reports and suggestions.
|
||||
@end ifnottex
|
||||
|
||||
@item
|
||||
@iftex
|
||||
Fran@,{c}ois Pinard---many thorough bug reports and discussions.
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Francois Pinard---many thorough bug reports and discussions.
|
||||
@end ifnottex
|
||||
François Pinard---many thorough bug reports and discussions.
|
||||
|
||||
@item
|
||||
Karl Eichwalder---lots of help with internationalization, Makefile
|
||||
@@ -4235,12 +4432,7 @@ Wanderlei Cavassin,
|
||||
Gilles Cedoc,
|
||||
Tim Charron,
|
||||
Noel Cragg,
|
||||
@iftex
|
||||
Kristijan @v{C}onka@v{s},
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Kristijan Conkas,
|
||||
@end ifnottex
|
||||
Kristijan Čonkaš,
|
||||
John Daily,
|
||||
Andreas Damm,
|
||||
Ahmon Dancy,
|
||||
@@ -4250,27 +4442,12 @@ Alexander Dergachev,
|
||||
Andrew Deryabin,
|
||||
Ulrich Drepper,
|
||||
Marc Duponcheel,
|
||||
@iftex
|
||||
Damir D@v{z}eko,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Damir Dzeko,
|
||||
@end ifnottex
|
||||
Damir Džeko,
|
||||
Alan Eldridge,
|
||||
Hans-Andreas Engel,
|
||||
@iftex
|
||||
Aleksandar Erkalovi@'{c},
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Aleksandar Erkalovic,
|
||||
@end ifnottex
|
||||
Aleksandar Erkalović,
|
||||
Andy Eskilsson,
|
||||
@iftex
|
||||
Jo@~{a}o Ferreira,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Joao Ferreira,
|
||||
@end ifnottex
|
||||
João Ferreira,
|
||||
Christian Fraenkel,
|
||||
David Fritz,
|
||||
Mike Frysinger,
|
||||
@@ -4295,25 +4472,10 @@ Richard Huveneers,
|
||||
Jonas Jensen,
|
||||
Larry Jones,
|
||||
Simon Josefsson,
|
||||
@iftex
|
||||
Mario Juri@'{c},
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Mario Juric,
|
||||
@end ifnottex
|
||||
@iftex
|
||||
Hack Kampbj@o rn,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Hack Kampbjorn,
|
||||
@end ifnottex
|
||||
Mario Jurić,
|
||||
Hack Kampbjørn,
|
||||
Const Kaplinsky,
|
||||
@iftex
|
||||
Goran Kezunovi@'{c},
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Goran Kezunovic,
|
||||
@end ifnottex
|
||||
Goran Kezunović,
|
||||
Igor Khristophorov,
|
||||
Robert Kleine,
|
||||
KOJIMA Haime,
|
||||
@@ -4322,31 +4484,14 @@ Alexander Kourakos,
|
||||
Martin Kraemer,
|
||||
Sami Krank,
|
||||
Jay Krell,
|
||||
@tex
|
||||
$\Sigma\acute{\iota}\mu o\varsigma\;
|
||||
\Xi\varepsilon\nu\iota\tau\acute{\epsilon}\lambda\lambda\eta\varsigma$
|
||||
(Simos KSenitellis),
|
||||
@end tex
|
||||
@ifnottex
|
||||
Simos KSenitellis,
|
||||
@end ifnottex
|
||||
Σίμος Ξενιτέλλης (Simos KSenitellis),
|
||||
Christian Lackas,
|
||||
Hrvoje Lacko,
|
||||
Daniel S.@: Lewart,
|
||||
@iftex
|
||||
Nicol@'{a}s Lichtmeier,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Nicolas Lichtmeier,
|
||||
@end ifnottex
|
||||
Nicolás Lichtmeier,
|
||||
Dave Love,
|
||||
Alexander V.@: Lukyanov,
|
||||
@iftex
|
||||
Thomas Lu@ss{}nig,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Thomas Lussnig,
|
||||
@end ifnottex
|
||||
Thomas Lußnig,
|
||||
Andre Majorel,
|
||||
Aurelien Marchand,
|
||||
Matthew J.@: Mellon,
|
||||
@@ -4367,31 +4512,15 @@ Leonid Petrov,
|
||||
Simone Piunno,
|
||||
Andrew Pollock,
|
||||
Steve Pothier,
|
||||
@iftex
|
||||
Jan P@v{r}ikryl,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Jan Prikryl,
|
||||
@end ifnottex
|
||||
Jan Přikryl,
|
||||
Marin Purgar,
|
||||
@iftex
|
||||
Csaba R@'{a}duly,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Csaba Raduly,
|
||||
@end ifnottex
|
||||
Csaba Ráduly,
|
||||
Keith Refson,
|
||||
Bill Richardson,
|
||||
Tyler Riddle,
|
||||
Tobias Ringstrom,
|
||||
Jochen Roderburg,
|
||||
@c Texinfo doesn't grok @'{@i}, so we have to use TeX itself.
|
||||
@tex
|
||||
Juan Jos\'{e} Rodr\'{\i}guez,
|
||||
@end tex
|
||||
@ifnottex
|
||||
Juan Jose Rodriguez,
|
||||
@end ifnottex
|
||||
Juan José Rodríguez,
|
||||
Maciej W.@: Rozycki,
|
||||
Edward J.@: Sabol,
|
||||
Heinz Salzmann,
|
||||
@@ -4418,12 +4547,7 @@ Dave Turner,
|
||||
Gisle Vanem,
|
||||
Rabin Vincent,
|
||||
Russell Vincent,
|
||||
@iftex
|
||||
@v{Z}eljko Vrba,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Zeljko Vrba,
|
||||
@end ifnottex
|
||||
Željko Vrba,
|
||||
Charles G Waldman,
|
||||
Douglas E.@: Wegscheid,
|
||||
Ralf Wildenhues,
|
||||
@@ -4432,12 +4556,7 @@ Benjamin Wolsey,
|
||||
Saint Xavier,
|
||||
YAMAZAKI Makoto,
|
||||
Jasmin Zainul,
|
||||
@iftex
|
||||
Bojan @v{Z}drnja,
|
||||
@end iftex
|
||||
@ifnottex
|
||||
Bojan Zdrnja,
|
||||
@end ifnottex
|
||||
Bojan Ždrnja,
|
||||
Kristijan Zimmer,
|
||||
Xin Zou.
|
||||
|
||||
|
||||
2
gnulib
2
gnulib
Submodule gnulib updated: ecc5d3e148...916a632413
83
m4/wget.m4
83
m4/wget.m4
@@ -27,89 +27,6 @@ dnl Corresponding Source for a non-source form of such a combination
|
||||
dnl shall include the source code for the parts of OpenSSL used as well
|
||||
dnl as that of the covered work.
|
||||
|
||||
dnl
|
||||
dnl Check for `struct utimbuf'.
|
||||
dnl
|
||||
|
||||
AC_DEFUN([WGET_STRUCT_UTIMBUF], [
|
||||
AC_CHECK_TYPES([struct utimbuf], [], [], [
|
||||
#include <stdio.h>
|
||||
#if HAVE_SYS_TYPES_H
|
||||
# include <sys/types.h>
|
||||
#endif
|
||||
#if HAVE_UTIME_H
|
||||
# include <utime.h>
|
||||
#endif
|
||||
])
|
||||
])
|
||||
|
||||
dnl Check whether fnmatch.h can be included. This doesn't use
|
||||
dnl AC_FUNC_FNMATCH because Wget is already careful to only use
|
||||
dnl fnmatch on certain OS'es. However, fnmatch.h is sometimes broken
|
||||
dnl even on those because Apache installs its own fnmatch.h to
|
||||
dnl /usr/local/include (!), which GCC uses before /usr/include.
|
||||
|
||||
AC_DEFUN([WGET_FNMATCH], [
|
||||
AC_MSG_CHECKING([for working fnmatch.h])
|
||||
AC_COMPILE_IFELSE([AC_LANG_SOURCE([#include <fnmatch.h>
|
||||
])], [
|
||||
AC_MSG_RESULT(yes)
|
||||
AC_DEFINE([HAVE_WORKING_FNMATCH_H], 1,
|
||||
[Define if fnmatch.h can be included.])
|
||||
], [
|
||||
AC_MSG_RESULT(no)
|
||||
])
|
||||
])
|
||||
|
||||
dnl Check for nanosleep. For nanosleep to work on Solaris, we must
|
||||
dnl link with -lrt (recently) or with -lposix4 (older releases).
|
||||
|
||||
AC_DEFUN([WGET_NANOSLEEP], [
|
||||
AC_CHECK_FUNCS(nanosleep, [], [
|
||||
AC_CHECK_LIB(rt, nanosleep, [
|
||||
AC_DEFINE([HAVE_NANOSLEEP], 1,
|
||||
[Define if you have the nanosleep function.])
|
||||
LIBS="-lrt $LIBS"
|
||||
], [
|
||||
AC_CHECK_LIB(posix4, nanosleep, [
|
||||
AC_DEFINE([HAVE_NANOSLEEP], 1,
|
||||
[Define if you have the nanosleep function.])
|
||||
LIBS="-lposix4 $LIBS"
|
||||
])
|
||||
])
|
||||
])
|
||||
])
|
||||
|
||||
AC_DEFUN([WGET_POSIX_CLOCK], [
|
||||
AC_CHECK_FUNCS(clock_gettime, [], [
|
||||
AC_CHECK_LIB(rt, clock_gettime)
|
||||
])
|
||||
])
|
||||
|
||||
dnl Check whether we need to link with -lnsl and -lsocket, as is the
|
||||
dnl case on e.g. Solaris.
|
||||
|
||||
AC_DEFUN([WGET_NSL_SOCKET], [
|
||||
dnl On Solaris, -lnsl is needed to use gethostbyname. But checking
|
||||
dnl for gethostbyname is not enough because on "NCR MP-RAS 3.0"
|
||||
dnl gethostbyname is in libc, but -lnsl is still needed to use
|
||||
dnl -lsocket, as well as for functions such as inet_ntoa. We look
|
||||
dnl for such known offenders and if one of them is not found, we
|
||||
dnl check if -lnsl is needed.
|
||||
wget_check_in_nsl=NONE
|
||||
AC_CHECK_FUNCS(gethostbyname, [], [
|
||||
wget_check_in_nsl=gethostbyname
|
||||
])
|
||||
AC_CHECK_FUNCS(inet_ntoa, [], [
|
||||
wget_check_in_nsl=inet_ntoa
|
||||
])
|
||||
if test $wget_check_in_nsl != NONE; then
|
||||
AC_CHECK_LIB(nsl, $wget_check_in_nsl)
|
||||
fi
|
||||
AC_CHECK_LIB(socket, socket)
|
||||
])
|
||||
|
||||
|
||||
dnl ************************************************************
|
||||
dnl START OF IPv6 AUTOCONFIGURATION SUPPORT MACROS
|
||||
dnl ************************************************************
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Configuration header file for MS-DOS/Watt-32
|
||||
Copyright (C) 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
Copyright (C) 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/* MSDOS utility functions.
|
||||
Copyright (C) 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
Copyright (C) 2009, 2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -26,6 +26,7 @@ src/init.c
|
||||
src/iri.c
|
||||
src/log.c
|
||||
src/main.c
|
||||
src/metalink.c
|
||||
src/mswindows.c
|
||||
src/netrc.c
|
||||
src/openssl.c
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Makefile for `wget' utility
|
||||
# Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
|
||||
# 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
# 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
# Foundation, Inc.
|
||||
|
||||
# This program is free software; you can redistribute it and/or modify
|
||||
@@ -35,28 +35,38 @@ if IRI_IS_ENABLED
|
||||
IRI_OBJ = iri.c
|
||||
endif
|
||||
|
||||
if METALINK_IS_ENABLED
|
||||
METALINK_OBJ = metalink.c
|
||||
endif
|
||||
|
||||
if WITH_XATTR
|
||||
XATTR_OBJ = xattr.c
|
||||
endif
|
||||
|
||||
# The following line is losing on some versions of make!
|
||||
DEFS = @DEFS@ -DSYSTEM_WGETRC=\"$(sysconfdir)/wgetrc\" -DLOCALEDIR=\"$(localedir)\"
|
||||
LIBS = @LIBICONV@ @LIBINTL@ @LIBS@ $(LIB_CLOCK_GETTIME)
|
||||
|
||||
EXTRA_DIST = css.l css.c css_.c build_info.c.in
|
||||
|
||||
bin_PROGRAMS = wget
|
||||
wget_SOURCES = connect.c convert.c cookies.c ftp.c \
|
||||
css_.c css-url.c \
|
||||
ftp-basic.c ftp-ls.c hash.c host.c html-parse.c html-url.c \
|
||||
ftp-basic.c ftp-ls.c hash.c host.c hsts.c html-parse.c html-url.c \
|
||||
http.c init.c log.c main.c netrc.c progress.c ptimer.c \
|
||||
recur.c res.c retr.c spider.c url.c warc.c \
|
||||
utils.c exits.c build_info.c $(IRI_OBJ) \
|
||||
recur.c res.c retr.c spider.c url.c warc.c $(XATTR_OBJ) \
|
||||
utils.c exits.c build_info.c $(IRI_OBJ) $(METALINK_OBJ) \
|
||||
css-url.h css-tokens.h connect.h convert.h cookies.h \
|
||||
ftp.h hash.h host.h html-parse.h html-url.h \
|
||||
ftp.h hash.h host.h hsts.h html-parse.h html-url.h \
|
||||
http.h http-ntlm.h init.h log.h mswindows.h netrc.h \
|
||||
options.h progress.h ptimer.h recur.h res.h retr.h \
|
||||
spider.h ssl.h sysdep.h url.h warc.h utils.h wget.h iri.h \
|
||||
exits.h version.h
|
||||
exits.h version.h metalink.h xattr.h
|
||||
nodist_wget_SOURCES = version.c
|
||||
EXTRA_wget_SOURCES = iri.c
|
||||
LDADD = $(LIBOBJS) ../lib/libgnu.a
|
||||
LDADD = $(LIBOBJS) ../lib/libgnu.a $(GETADDRINFO_LIB) $(HOSTENT_LIB)\
|
||||
$(INET_NTOP_LIB) $(LIBSOCKET) $(LIB_CLOCK_GETTIME) $(LIB_CRYPTO)\
|
||||
$(LIB_NANOSLEEP) $(LIB_POSIX_SPAWN) $(LIB_SELECT) $(LTLIBICONV) $(LTLIBINTL)\
|
||||
$(LTLIBTHREAD) $(LTLIBUNISTRING) $(SERVENT_LIB)
|
||||
AM_CPPFLAGS = -I$(top_builddir)/lib -I$(top_srcdir)/lib
|
||||
|
||||
|
||||
|
||||
@@ -8,6 +8,10 @@ nls defined ENABLE_NLS
|
||||
ntlm defined ENABLE_NTLM
|
||||
opie defined ENABLE_OPIE
|
||||
psl defined HAVE_LIBPSL
|
||||
cares defined HAVE_LIBCARES
|
||||
|
||||
metalink defined HAVE_METALINK
|
||||
gpgme defined HAVE_GPGME
|
||||
|
||||
ssl choice:
|
||||
openssl defined HAVE_LIBSSL || defined HAVE_LIBSSL32
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Establishing and handling network connections.
|
||||
Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
|
||||
2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
@@ -31,6 +31,7 @@ as that of the covered work. */
|
||||
|
||||
#include "wget.h"
|
||||
|
||||
#include "exits.h"
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <unistd.h>
|
||||
@@ -56,7 +57,7 @@ as that of the covered work. */
|
||||
#include <sys/time.h>
|
||||
|
||||
#ifdef ENABLE_IRI
|
||||
#include <idn-free.h>
|
||||
#include <idn2.h>
|
||||
#endif
|
||||
|
||||
#include "utils.h"
|
||||
@@ -283,7 +284,7 @@ connect_to_ip (const ip_address *ip, int port, const char *print)
|
||||
str = xmalloc (len);
|
||||
snprintf (str, len, "%s (%s)", name, print);
|
||||
str[len-1] = '\0';
|
||||
idn_free (name);
|
||||
idn2_free (name);
|
||||
}
|
||||
|
||||
logprintf (LOG_VERBOSE, _("Connecting to %s|%s|:%d... "),
|
||||
@@ -331,8 +332,10 @@ connect_to_ip (const ip_address *ip, int port, const char *print)
|
||||
if (bufsize < 512)
|
||||
bufsize = 512; /* avoid pathologically small values */
|
||||
#ifdef SO_RCVBUF
|
||||
setsockopt (sock, SOL_SOCKET, SO_RCVBUF,
|
||||
(void *)&bufsize, (socklen_t)sizeof (bufsize));
|
||||
if (setsockopt (sock, SOL_SOCKET, SO_RCVBUF,
|
||||
(void *) &bufsize, (socklen_t) sizeof (bufsize)))
|
||||
logprintf (LOG_NOTQUIET, _("setsockopt SO_RCVBUF failed: %s\n"),
|
||||
strerror (errno));
|
||||
#endif
|
||||
/* When we add limit_rate support for writing, which is useful
|
||||
for POST, we should also set SO_SNDBUF here. */
|
||||
@@ -369,7 +372,14 @@ connect_to_ip (const ip_address *ip, int port, const char *print)
|
||||
logprintf. */
|
||||
int save_errno = errno;
|
||||
if (sock >= 0)
|
||||
fd_close (sock);
|
||||
{
|
||||
#ifdef WIN32
|
||||
/* If the connection timed out, fd_close will hang in Gnulib's
|
||||
close_fd_maybe_socket, inside the call to WSAEnumNetworkEvents. */
|
||||
if (errno != ETIMEDOUT)
|
||||
#endif
|
||||
fd_close (sock);
|
||||
}
|
||||
if (print)
|
||||
logprintf (LOG_NOTQUIET, _("failed: %s.\n"), strerror (errno));
|
||||
errno = save_errno;
|
||||
@@ -464,7 +474,9 @@ bind_local (const ip_address *bind_address, int *port)
|
||||
return -1;
|
||||
|
||||
#ifdef SO_REUSEADDR
|
||||
setsockopt (sock, SOL_SOCKET, SO_REUSEADDR, setopt_ptr, setopt_size);
|
||||
if (setsockopt (sock, SOL_SOCKET, SO_REUSEADDR, setopt_ptr, setopt_size))
|
||||
logprintf (LOG_NOTQUIET, _("setsockopt SO_REUSEADDR failed: %s\n"),
|
||||
strerror (errno));
|
||||
#endif
|
||||
|
||||
xzero (ss);
|
||||
@@ -682,6 +694,11 @@ select_fd (int fd, double maxtime, int wait_for)
|
||||
struct timeval tmout;
|
||||
int result;
|
||||
|
||||
if (fd >= FD_SETSIZE)
|
||||
{
|
||||
logprintf (LOG_NOTQUIET, _("Too many fds open. Cannot use select on a fd >= %d\n"), FD_SETSIZE);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
FD_ZERO (&fdset);
|
||||
FD_SET (fd, &fdset);
|
||||
if (wait_for & WAIT_FOR_READ)
|
||||
@@ -724,6 +741,11 @@ test_socket_open (int sock)
|
||||
struct timeval to;
|
||||
int ret = 0;
|
||||
|
||||
if (sock >= FD_SETSIZE)
|
||||
{
|
||||
logprintf (LOG_NOTQUIET, _("Too many fds open. Cannot use select on a fd >= %d\n"), FD_SETSIZE);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
/* Check if we still have a valid (non-EOF) connection. From Andrew
|
||||
* Maholski's code in the Unix Socket FAQ. */
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/* Declarations for connect.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
128
src/convert.c
128
src/convert.c
@@ -1,6 +1,6 @@
|
||||
/* Conversion of links to local files.
|
||||
Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014
|
||||
Free Software Foundation, Inc.
|
||||
Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011,
|
||||
2014, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -46,6 +46,7 @@ as that of the covered work. */
|
||||
#include "html-url.h"
|
||||
#include "css-url.h"
|
||||
#include "iri.h"
|
||||
#include "xstrndup.h"
|
||||
|
||||
static struct hash_table *dl_file_url_map;
|
||||
struct hash_table *dl_url_file_map;
|
||||
@@ -136,8 +137,9 @@ convert_links_in_hashtable (struct hash_table *downloaded_set,
|
||||
form. We do this even if the URL already is in
|
||||
relative form, because our directory structure may
|
||||
not be identical to that on the server (think `-nd',
|
||||
`--cut-dirs', etc.) */
|
||||
cur_url->convert = CO_CONVERT_TO_RELATIVE;
|
||||
`--cut-dirs', etc.). If --convert-file-only was passed,
|
||||
we only convert the basename portion of the URL. */
|
||||
cur_url->convert = (opt.convert_file_only ? CO_CONVERT_BASENAME_ONLY : CO_CONVERT_TO_RELATIVE);
|
||||
cur_url->local_name = xstrdup (local_name);
|
||||
DEBUGP (("will convert url %s to local %s\n", u->url, local_name));
|
||||
}
|
||||
@@ -193,7 +195,7 @@ convert_all_links (void)
|
||||
convert_links_in_hashtable (downloaded_css_set, 1, &file_count);
|
||||
|
||||
secs = ptimer_measure (timer);
|
||||
logprintf (LOG_VERBOSE, _("Converted %d files in %s seconds.\n"),
|
||||
logprintf (LOG_VERBOSE, _("Converted links in %d files in %s seconds.\n"),
|
||||
file_count, print_decimal (secs));
|
||||
|
||||
ptimer_destroy (timer);
|
||||
@@ -206,6 +208,7 @@ static const char *replace_attr_refresh_hack (const char *, int, FILE *,
|
||||
const char *, int);
|
||||
static char *local_quote_string (const char *, bool);
|
||||
static char *construct_relative (const char *, const char *);
|
||||
static char *convert_basename (const char *, const struct urlpos *);
|
||||
|
||||
/* Change the links in one file. LINKS is a list of links in the
|
||||
document, along with their positions and the desired direction of
|
||||
@@ -221,7 +224,7 @@ convert_links (const char *file, struct urlpos *links)
|
||||
struct urlpos *link;
|
||||
int to_url_count = 0, to_file_count = 0;
|
||||
|
||||
logprintf (LOG_VERBOSE, _("Converting %s... "), file);
|
||||
logprintf (LOG_VERBOSE, _("Converting links in %s... "), file);
|
||||
|
||||
{
|
||||
/* First we do a "dry run": go through the list L and see whether
|
||||
@@ -305,7 +308,7 @@ convert_links (const char *file, struct urlpos *links)
|
||||
char *quoted_newname = local_quote_string (newname,
|
||||
link->link_css_p);
|
||||
|
||||
if (link->link_css_p)
|
||||
if (link->link_css_p || link->link_noquote_html_p)
|
||||
p = replace_plain (p, link->size, fp, quoted_newname);
|
||||
else if (!link->link_refresh_p)
|
||||
p = replace_attr (p, link->size, fp, quoted_newname);
|
||||
@@ -315,9 +318,32 @@ convert_links (const char *file, struct urlpos *links)
|
||||
|
||||
DEBUGP (("TO_RELATIVE: %s to %s at position %d in %s.\n",
|
||||
link->url->url, newname, link->pos, file));
|
||||
|
||||
xfree (newname);
|
||||
xfree (quoted_newname);
|
||||
++to_file_count;
|
||||
break;
|
||||
}
|
||||
case CO_CONVERT_BASENAME_ONLY:
|
||||
{
|
||||
char *newname = convert_basename (p, link);
|
||||
char *quoted_newname = local_quote_string (newname, link->link_css_p);
|
||||
|
||||
if (link->link_css_p || link->link_noquote_html_p)
|
||||
p = replace_plain (p, link->size, fp, quoted_newname);
|
||||
else if (!link->link_refresh_p)
|
||||
p = replace_attr (p, link->size, fp, quoted_newname);
|
||||
else
|
||||
p = replace_attr_refresh_hack (p, link->size, fp, quoted_newname,
|
||||
link->refresh_timeout);
|
||||
|
||||
DEBUGP (("Converted file part only: %s to %s at position %d in %s.\n",
|
||||
link->url->url, newname, link->pos, file));
|
||||
|
||||
xfree (newname);
|
||||
xfree (quoted_newname);
|
||||
++to_file_count;
|
||||
|
||||
break;
|
||||
}
|
||||
case CO_CONVERT_TO_COMPLETE:
|
||||
@@ -326,7 +352,7 @@ convert_links (const char *file, struct urlpos *links)
|
||||
char *newlink = link->url->url;
|
||||
char *quoted_newlink = html_quote_string (newlink);
|
||||
|
||||
if (link->link_css_p)
|
||||
if (link->link_css_p || link->link_noquote_html_p)
|
||||
p = replace_plain (p, link->size, fp, newlink);
|
||||
else if (!link->link_refresh_p)
|
||||
p = replace_attr (p, link->size, fp, quoted_newlink);
|
||||
@@ -336,6 +362,7 @@ convert_links (const char *file, struct urlpos *links)
|
||||
|
||||
DEBUGP (("TO_COMPLETE: <something> to %s at position %d in %s.\n",
|
||||
newlink, link->pos, file));
|
||||
|
||||
xfree (quoted_newlink);
|
||||
++to_url_count;
|
||||
break;
|
||||
@@ -414,14 +441,89 @@ construct_relative (const char *basefile, const char *linkfile)
|
||||
++basedirs;
|
||||
}
|
||||
|
||||
/* Construct LINK as explained above. */
|
||||
link = xmalloc (3 * basedirs + strlen (linkfile) + 1);
|
||||
for (i = 0; i < basedirs; i++)
|
||||
memcpy (link + 3 * i, "../", 3);
|
||||
strcpy (link + 3 * i, linkfile);
|
||||
if (!basedirs && (b = strpbrk (linkfile, "/:")) && *b == ':')
|
||||
{
|
||||
link = xmalloc (2 + strlen (linkfile) + 1);
|
||||
memcpy (link, "./", 2);
|
||||
strcpy (link + 2, linkfile);
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Construct LINK as explained above. */
|
||||
link = xmalloc (3 * basedirs + strlen (linkfile) + 1);
|
||||
for (i = 0; i < basedirs; i++)
|
||||
memcpy (link + 3 * i, "../", 3);
|
||||
strcpy (link + 3 * i, linkfile);
|
||||
}
|
||||
|
||||
return link;
|
||||
}
|
||||
|
||||
/* Construct and return a "transparent proxy" URL
|
||||
reflecting changes made by --adjust-extension to the file component
|
||||
(i.e., "basename") of the original URL, but leaving the "dirname"
|
||||
of the URL (protocol://hostname... portion) untouched.
|
||||
|
||||
Think: populating a squid cache via a recursive wget scrape, where
|
||||
changing URLs to work locally with "file://..." is NOT desirable.
|
||||
|
||||
Example:
|
||||
|
||||
if
|
||||
p = "//foo.com/bar.cgi?xyz"
|
||||
and
|
||||
link->local_name = "docroot/foo.com/bar.cgi?xyz.css"
|
||||
then
|
||||
|
||||
new_construct_func(p, link);
|
||||
will return
|
||||
"//foo.com/bar.cgi?xyz.css"
|
||||
|
||||
Essentially, we do s/$(basename orig_url)/$(basename link->local_name)/
|
||||
*/
|
||||
static char *
|
||||
convert_basename (const char *p, const struct urlpos *link)
|
||||
{
|
||||
int len = link->size;
|
||||
char *url = NULL;
|
||||
char *org_basename = NULL, *local_basename = NULL;
|
||||
char *result = NULL;
|
||||
|
||||
if (*p == '"' || *p == '\'')
|
||||
{
|
||||
len -= 2;
|
||||
p++;
|
||||
}
|
||||
|
||||
url = xstrndup (p, len);
|
||||
|
||||
org_basename = strrchr (url, '/');
|
||||
if (org_basename)
|
||||
org_basename++;
|
||||
else
|
||||
org_basename = url;
|
||||
|
||||
local_basename = strrchr (link->local_name, '/');
|
||||
if (local_basename)
|
||||
local_basename++;
|
||||
else
|
||||
local_basename = url;
|
||||
|
||||
/*
|
||||
* If the basenames differ, graft the adjusted basename (local_basename)
|
||||
* onto the original URL.
|
||||
*/
|
||||
if (strcmp (org_basename, local_basename) == 0)
|
||||
result = url;
|
||||
else
|
||||
{
|
||||
result = uri_merge (url, local_basename);
|
||||
xfree (url);
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/* Used by write_backup_file to remember which files have been
|
||||
written. */
|
||||
static struct hash_table *converted_files;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Declarations for convert.c
|
||||
Copyright (C) 2003, 2004, 2005, 2006, 2009, 2010, 2011 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2003, 2004, 2005, 2006, 2009, 2010, 2011, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -40,6 +40,8 @@ enum convert_options {
|
||||
CO_NOCONVERT = 0, /* don't convert this URL */
|
||||
CO_CONVERT_TO_RELATIVE, /* convert to relative, e.g. to
|
||||
"../../otherdir/foo.gif" */
|
||||
CO_CONVERT_BASENAME_ONLY, /* convert the file portion only (basename)
|
||||
leaving the rest of the URL unchanged */
|
||||
CO_CONVERT_TO_COMPLETE, /* convert to absolute, e.g. to
|
||||
"http://orighost/somedir/bar.jpg". */
|
||||
CO_NULLIFY_BASE /* change to empty string. */
|
||||
@@ -67,6 +69,7 @@ struct urlpos {
|
||||
unsigned int link_base_p :1; /* the url came from <base href=...> */
|
||||
unsigned int link_inline_p :1; /* needed to render the page */
|
||||
unsigned int link_css_p :1; /* the url came from CSS */
|
||||
unsigned int link_noquote_html_p :1; /* from HTML, but doesn't need " */
|
||||
unsigned int link_expect_html :1; /* expected to contain HTML */
|
||||
unsigned int link_expect_css :1; /* expected to contain CSS */
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Support for cookies.
|
||||
Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009,
|
||||
2010, 2011 Free Software Foundation, Inc.
|
||||
2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -45,6 +45,7 @@ as that of the covered work. */
|
||||
|
||||
#include "wget.h"
|
||||
|
||||
#include <stdint.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <stdlib.h>
|
||||
@@ -525,19 +526,51 @@ check_domain_match (const char *cookie_domain, const char *host)
|
||||
{
|
||||
|
||||
#ifdef HAVE_LIBPSL
|
||||
static int init_psl;
|
||||
static const psl_ctx_t *psl;
|
||||
|
||||
char *cookie_domain_lower = NULL;
|
||||
char *host_lower = NULL;
|
||||
const psl_ctx_t *psl;
|
||||
int is_acceptable;
|
||||
|
||||
DEBUGP (("cdm: 1"));
|
||||
if (!(psl = psl_builtin()))
|
||||
DEBUGP (("cdm: 1\n"));
|
||||
if (!init_psl)
|
||||
{
|
||||
DEBUGP (("\nlibpsl not built with a public suffix list. "
|
||||
"Falling back to simple heuristics.\n"));
|
||||
goto no_psl;
|
||||
}
|
||||
init_psl = 1;
|
||||
|
||||
#ifdef HAVE_PSL_LATEST
|
||||
if ((psl = psl_latest (NULL)))
|
||||
goto have_psl;
|
||||
|
||||
DEBUGP (("\nPSL: Failed to load any PSL data. "
|
||||
"Falling back to insecure heuristics.\n"));
|
||||
#else
|
||||
if ((psl = psl_builtin ()) && !psl_builtin_outdated ())
|
||||
goto have_psl;
|
||||
|
||||
DEBUGP (("\nPSL: built-in data outdated. "
|
||||
"Trying to load data from %s.\n",
|
||||
quote (psl_builtin_filename ())));
|
||||
|
||||
if ((psl = psl_load_file (psl_builtin_filename ())))
|
||||
goto have_psl;
|
||||
|
||||
DEBUGP (("\nPSL: %s not found or not readable. "
|
||||
"Falling back to built-in data.\n",
|
||||
quote (psl_builtin_filename ())));
|
||||
|
||||
if (!(psl = psl_builtin ()))
|
||||
{
|
||||
DEBUGP (("\nPSL: libpsl not built with a public suffix list. "
|
||||
"Falling back to insecure heuristics.\n"));
|
||||
goto no_psl;
|
||||
}
|
||||
#endif
|
||||
}
|
||||
else if (!psl)
|
||||
goto no_psl;
|
||||
|
||||
have_psl:
|
||||
if (psl_str_to_utf8lower (cookie_domain, NULL, NULL, &cookie_domain_lower) == PSL_SUCCESS &&
|
||||
psl_str_to_utf8lower (host, NULL, NULL, &host_lower) == PSL_SUCCESS)
|
||||
{
|
||||
@@ -562,13 +595,13 @@ no_psl:
|
||||
#endif
|
||||
|
||||
/* For efficiency make some elementary checks first */
|
||||
DEBUGP (("cdm: 2"));
|
||||
DEBUGP (("cdm: 2\n"));
|
||||
|
||||
/* For the sake of efficiency, check for exact match first. */
|
||||
if (0 == strcasecmp (cookie_domain, host))
|
||||
return true;
|
||||
|
||||
DEBUGP ((" 3"));
|
||||
DEBUGP (("cdm: 3\n"));
|
||||
|
||||
/* HOST must match the tail of cookie_domain. */
|
||||
if (!match_tail (host, cookie_domain, true))
|
||||
@@ -608,7 +641,7 @@ no_psl:
|
||||
if (*p == '.')
|
||||
/* Ignore leading period in this calculation. */
|
||||
++p;
|
||||
DEBUGP ((" 4"));
|
||||
DEBUGP (("cdm: 4\n"));
|
||||
for (out = 0; !out; p++)
|
||||
switch (*p)
|
||||
{
|
||||
@@ -634,12 +667,12 @@ no_psl:
|
||||
++ldcl;
|
||||
}
|
||||
|
||||
DEBUGP ((" 5"));
|
||||
DEBUGP (("cdm: 5\n"));
|
||||
|
||||
if (dccount < 2)
|
||||
return false;
|
||||
|
||||
DEBUGP ((" 6"));
|
||||
DEBUGP (("cdm: 6\n"));
|
||||
|
||||
if (dccount == 2)
|
||||
{
|
||||
@@ -659,7 +692,7 @@ no_psl:
|
||||
}
|
||||
}
|
||||
|
||||
DEBUGP ((" 7"));
|
||||
DEBUGP (("cdm: 7\n"));
|
||||
|
||||
/* Don't allow the host "foobar.com" to set a cookie for domain
|
||||
"bar.com". */
|
||||
@@ -674,7 +707,7 @@ no_psl:
|
||||
return false;
|
||||
}
|
||||
|
||||
DEBUGP ((" 8"));
|
||||
DEBUGP (("cdm: 8\n"));
|
||||
|
||||
return true;
|
||||
}
|
||||
@@ -1018,7 +1051,7 @@ cookie_header (struct cookie_jar *jar, const char *host,
|
||||
|
||||
struct cookie *cookie;
|
||||
struct weighed_cookie *outgoing;
|
||||
int count, i, ocnt;
|
||||
size_t count, i, ocnt;
|
||||
char *result;
|
||||
int result_size, pos;
|
||||
PREPEND_SLASH (path); /* see cookie_handle_set_cookie */
|
||||
@@ -1032,7 +1065,7 @@ cookie_header (struct cookie_jar *jar, const char *host,
|
||||
chain_count = find_chains_of_host (jar, host, chains);
|
||||
|
||||
/* No cookies for this host. */
|
||||
if (!chain_count)
|
||||
if (chain_count <= 0)
|
||||
return NULL;
|
||||
|
||||
cookies_now = time (NULL);
|
||||
@@ -1043,7 +1076,7 @@ cookie_header (struct cookie_jar *jar, const char *host,
|
||||
|
||||
/* Count the number of matching cookies. */
|
||||
count = 0;
|
||||
for (i = 0; i < chain_count; i++)
|
||||
for (i = 0; i < (unsigned) chain_count; i++)
|
||||
for (cookie = chains[i]; cookie; cookie = cookie->next)
|
||||
if (cookie_matches_url (cookie, host, port, path, secflag, NULL))
|
||||
++count;
|
||||
@@ -1051,12 +1084,14 @@ cookie_header (struct cookie_jar *jar, const char *host,
|
||||
return NULL; /* no cookies matched */
|
||||
|
||||
/* Allocate the array. */
|
||||
outgoing = alloca_array (struct weighed_cookie, count);
|
||||
if (count > SIZE_MAX / sizeof (struct weighed_cookie))
|
||||
return NULL; /* unable to process so many cookies */
|
||||
outgoing = xmalloc (count * sizeof (struct weighed_cookie));
|
||||
|
||||
/* Fill the array with all the matching cookies from the chains that
|
||||
match HOST. */
|
||||
ocnt = 0;
|
||||
for (i = 0; i < chain_count; i++)
|
||||
for (i = 0; i < (unsigned) chain_count; i++)
|
||||
for (cookie = chains[i]; cookie; cookie = cookie->next)
|
||||
{
|
||||
int pg;
|
||||
@@ -1111,6 +1146,7 @@ cookie_header (struct cookie_jar *jar, const char *host,
|
||||
}
|
||||
}
|
||||
result[pos++] = '\0';
|
||||
xfree (outgoing);
|
||||
assert (pos == result_size);
|
||||
return result;
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Support for cookies.
|
||||
Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009,
|
||||
2010, 2011 Free Software Foundation, Inc.
|
||||
2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
/* Declarations for css.lex
|
||||
Copyright (C) 2006, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
Copyright (C) 2006, 2009, 2010, 2011, 2015 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Collect URLs from CSS source.
|
||||
Copyright (C) 1998, 2000, 2001, 2002, 2003, 2009, 2010, 2011, 2014 Free
|
||||
Software Foundation, Inc.
|
||||
Copyright (C) 1998, 2000, 2001, 2002, 2003, 2009, 2010, 2011, 2014,
|
||||
2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -59,6 +59,7 @@ extern char *yytext;
|
||||
extern int yyleng;
|
||||
typedef struct yy_buffer_state *YY_BUFFER_STATE;
|
||||
extern YY_BUFFER_STATE yy_scan_bytes (const char *bytes,int len );
|
||||
extern void yy_delete_buffer (YY_BUFFER_STATE b);
|
||||
extern int yylex (void);
|
||||
|
||||
/*
|
||||
@@ -109,9 +110,10 @@ get_urls_css (struct map_context *ctx, int offset, int buf_length)
|
||||
int buffer_pos = 0;
|
||||
int pos, length;
|
||||
char *uri;
|
||||
YY_BUFFER_STATE b;
|
||||
|
||||
/* tell flex to scan from this buffer */
|
||||
yy_scan_bytes (ctx->text + offset, buf_length);
|
||||
b = yy_scan_bytes (ctx->text + offset, buf_length);
|
||||
|
||||
while((token = yylex()) != CSSEOF)
|
||||
{
|
||||
@@ -188,6 +190,9 @@ get_urls_css (struct map_context *ctx, int offset, int buf_length)
|
||||
}
|
||||
buffer_pos += yyleng;
|
||||
}
|
||||
|
||||
yy_delete_buffer(b);
|
||||
|
||||
DEBUGP (("\n"));
|
||||
}
|
||||
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
/* Declarations for css-url.c.
|
||||
Copyright (C) 2006, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
Copyright (C) 2006, 2009, 2010, 2011, 2015 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -30,7 +31,6 @@ as that of the covered work. */
|
||||
#ifndef CSS_URL_H
|
||||
#define CSS_URL_H
|
||||
|
||||
void get_urls_css (struct map_context *, int, int);
|
||||
void get_urls_css (struct map_context *, int, int);
|
||||
struct urlpos *get_urls_css_file (const char *, const char *);
|
||||
|
||||
|
||||
@@ -6,7 +6,8 @@
|
||||
%{
|
||||
/* Lex source for CSS tokenizing.
|
||||
Taken from http://www.w3.org/TR/CSS21/grammar.html#q2
|
||||
Copyright (C) 2006, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
Copyright (C) 2006, 2009, 2010, 2011, 2015 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
/* Exit status handling.
|
||||
Copyright (C) 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
|
||||
Copyright (C) 2009, 2010, 2011, 2012, 2015 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
/* Exit status related declarations.
|
||||
Copyright (C) 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
|
||||
Copyright (C) 2009, 2010, 2011, 2012, 2015 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
144
src/ftp-basic.c
144
src/ftp-basic.c
@@ -1,7 +1,7 @@
|
||||
/* Basic FTP routines.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -135,6 +135,23 @@ ftp_request (const char *command, const char *value)
|
||||
return res;
|
||||
}
|
||||
|
||||
uerr_t
|
||||
ftp_greeting (int csock)
|
||||
{
|
||||
uerr_t err = FTPOK;
|
||||
char *response = NULL;
|
||||
|
||||
err = ftp_response (csock, &response);
|
||||
if (err != FTPOK)
|
||||
goto bail;
|
||||
if (*response != '2')
|
||||
err = FTPSRVERR;
|
||||
|
||||
bail:
|
||||
if (response)
|
||||
xfree (response);
|
||||
return err;
|
||||
}
|
||||
/* Sends the USER and PASS commands to the server, to control
|
||||
connection socket csock. */
|
||||
uerr_t
|
||||
@@ -144,16 +161,6 @@ ftp_login (int csock, const char *acc, const char *pass)
|
||||
char *request, *respline;
|
||||
int nwritten;
|
||||
|
||||
/* Get greeting. */
|
||||
err = ftp_response (csock, &respline);
|
||||
if (err != FTPOK)
|
||||
return err;
|
||||
if (*respline != '2')
|
||||
{
|
||||
xfree (respline);
|
||||
return FTPSRVERR;
|
||||
}
|
||||
xfree (respline);
|
||||
/* Send USER username. */
|
||||
request = ftp_request ("USER", acc);
|
||||
nwritten = fd_write (csock, request, strlen (request), -1);
|
||||
@@ -481,6 +488,119 @@ ftp_eprt (int csock, int *local_sock)
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
/*
|
||||
* The following three functions defined into this #ifdef block
|
||||
* wrap the extended FTP commands defined in RFC 2228 (FTP Security Extensions).
|
||||
* Currently, only FTPS is supported, so these functions are only compiled when SSL
|
||||
* support is available, because there's no point in using FTPS when there's no SSL.
|
||||
* Shall someone add new secure FTP protocols in the future, feel free to remove this
|
||||
* #ifdef, or add new constants to it.
|
||||
*/
|
||||
|
||||
/*
|
||||
* Sends an AUTH command as defined by RFC 2228,
|
||||
* deriving its argument from the scheme. For example, if the provided scheme
|
||||
* is SCHEME_FTPS, the command sent will be "AUTH TLS". Currently, this is the only
|
||||
* scheme supported, so this function will return FTPNOAUTH when supplied a different
|
||||
* one. It will also return FTPNOAUTH if the target server does not support FTPS.
|
||||
*/
|
||||
uerr_t
|
||||
ftp_auth (int csock, enum url_scheme scheme)
|
||||
{
|
||||
uerr_t err = 0;
|
||||
int written = 0;
|
||||
char *request = NULL, *response = NULL;
|
||||
|
||||
if (scheme == SCHEME_FTPS)
|
||||
{
|
||||
request = ftp_request ("AUTH", "TLS");
|
||||
written = fd_write (csock, request, strlen (request), -1);
|
||||
if (written < 0)
|
||||
{
|
||||
err = WRITEFAILED;
|
||||
goto bail;
|
||||
}
|
||||
err = ftp_response (csock, &response);
|
||||
if (err != FTPOK)
|
||||
goto bail;
|
||||
if (*response != '2')
|
||||
err = FTPNOAUTH;
|
||||
}
|
||||
else
|
||||
err = FTPNOAUTH;
|
||||
|
||||
bail:
|
||||
xfree (request);
|
||||
xfree (response);
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
uerr_t
|
||||
ftp_pbsz (int csock, int pbsz)
|
||||
{
|
||||
uerr_t err = 0;
|
||||
int written = 0;
|
||||
char spbsz[5];
|
||||
char *request = NULL, *response = NULL;
|
||||
|
||||
snprintf (spbsz, 5, "%d", pbsz);
|
||||
request = ftp_request ("PBSZ", spbsz);
|
||||
written = fd_write (csock, request, strlen (request), -1);
|
||||
if (written < 0)
|
||||
{
|
||||
err = WRITEFAILED;
|
||||
goto bail;
|
||||
}
|
||||
|
||||
err = ftp_response (csock, &response);
|
||||
if (err != FTPOK)
|
||||
goto bail;
|
||||
if (*response != '2')
|
||||
err = FTPNOPBSZ;
|
||||
|
||||
bail:
|
||||
xfree (request);
|
||||
xfree (response);
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
uerr_t
|
||||
ftp_prot (int csock, enum prot_level prot)
|
||||
{
|
||||
uerr_t err = 0;
|
||||
int written = 0;
|
||||
char *request = NULL, *response = NULL;
|
||||
/* value must be a single character value */
|
||||
char value[2];
|
||||
|
||||
value[0] = prot;
|
||||
value[1] = '\0';
|
||||
|
||||
request = ftp_request ("PROT", value);
|
||||
written = fd_write (csock, request, strlen (request), -1);
|
||||
if (written < 0)
|
||||
{
|
||||
err = WRITEFAILED;
|
||||
goto bail;
|
||||
}
|
||||
|
||||
err = ftp_response (csock, &response);
|
||||
if (err != FTPOK)
|
||||
goto bail;
|
||||
if (*response != '2')
|
||||
err = FTPNOPROT;
|
||||
|
||||
bail:
|
||||
xfree (request);
|
||||
xfree (response);
|
||||
|
||||
return err;
|
||||
}
|
||||
#endif /* HAVE_SSL */
|
||||
|
||||
/* Similar to ftp_port, but uses `PASV' to initiate the passive FTP
|
||||
transfer. Reads the response from server and parses it. Reads the
|
||||
host and port addresses and returns them. */
|
||||
|
||||
11
src/ftp-ls.c
11
src/ftp-ls.c
@@ -1,7 +1,7 @@
|
||||
/* Parsing FTP `ls' output.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -167,12 +167,12 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
|
||||
/*cur.perms = 1023;*/ /* #### What is this? --hniksic */
|
||||
cur.perms = 0644;
|
||||
}
|
||||
DEBUGP (("implicit perms %0o; ", cur.perms));
|
||||
DEBUGP (("implicit perms %0o; ", (unsigned) cur.perms));
|
||||
}
|
||||
else
|
||||
{
|
||||
cur.perms = symperms (tok + 1);
|
||||
DEBUGP (("perms %0o; ", cur.perms));
|
||||
DEBUGP (("perms %0o; ", (unsigned) cur.perms));
|
||||
}
|
||||
|
||||
error = ignore = 0; /* Erroneous and ignoring entries are
|
||||
@@ -478,6 +478,7 @@ ftp_parse_winnt_ls (const char *file)
|
||||
}
|
||||
/* Now it is possible to determine the position of the first symbol in
|
||||
filename. */
|
||||
memset(&cur, 0, sizeof (cur));
|
||||
cur.name = xstrdup(filename);
|
||||
DEBUGP (("Name: '%s'\n", cur.name));
|
||||
|
||||
@@ -931,7 +932,7 @@ ftp_parse_vms_ls (const char *file)
|
||||
}
|
||||
}
|
||||
cur.perms = perms;
|
||||
DEBUGP (("Prot. perms = %0o.\n", cur.perms));
|
||||
DEBUGP (("Prot. perms = %0o.\n", (unsigned) cur.perms));
|
||||
}
|
||||
else
|
||||
{
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Opie (s/key) support for FTP.
|
||||
Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
|
||||
2007, 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
2007, 2008, 2009, 2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
436
src/ftp.c
436
src/ftp.c
@@ -1,7 +1,7 @@
|
||||
/* File Transfer Protocol support.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -44,6 +44,7 @@ as that of the covered work. */
|
||||
#include "url.h"
|
||||
#include "retr.h"
|
||||
#include "ftp.h"
|
||||
#include "ssl.h"
|
||||
#include "connect.h"
|
||||
#include "host.h"
|
||||
#include "netrc.h"
|
||||
@@ -51,6 +52,9 @@ as that of the covered work. */
|
||||
#include "recur.h" /* for INFINITE_RECURSION */
|
||||
#include "warc.h"
|
||||
#include "c-strcase.h"
|
||||
#ifdef ENABLE_XATTR
|
||||
#include "xattr.h"
|
||||
#endif
|
||||
|
||||
#ifdef __VMS
|
||||
# include "vms.h"
|
||||
@@ -235,24 +239,96 @@ print_length (wgint size, wgint start, bool authoritative)
|
||||
logputs (LOG_VERBOSE, !authoritative ? _(" (unauthoritative)\n") : "\n");
|
||||
}
|
||||
|
||||
static uerr_t ftp_get_listing (struct url *, ccon *, struct fileinfo **);
|
||||
static uerr_t ftp_get_listing (struct url *, struct url *, ccon *, struct fileinfo **);
|
||||
|
||||
static uerr_t
|
||||
get_ftp_greeting (int csock, ccon *con)
|
||||
{
|
||||
uerr_t err = 0;
|
||||
|
||||
/* Get the server's greeting */
|
||||
err = ftp_greeting (csock);
|
||||
if (err != FTPOK)
|
||||
{
|
||||
logputs (LOG_NOTQUIET, "Error in server response. Closing.\n");
|
||||
fd_close (csock);
|
||||
con->csock = -1;
|
||||
}
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
static uerr_t
|
||||
init_control_ssl_connection (int csock, struct url *u, bool *using_control_security)
|
||||
{
|
||||
bool using_security = false;
|
||||
|
||||
/* If '--ftps-implicit' was passed, perform the SSL handshake directly,
|
||||
* and do not send an AUTH command.
|
||||
* Otherwise send an AUTH sequence before login,
|
||||
* and perform the SSL handshake if accepted by server.
|
||||
*/
|
||||
if (!opt.ftps_implicit && !opt.server_response)
|
||||
logputs (LOG_VERBOSE, "==> AUTH TLS ... ");
|
||||
if (opt.ftps_implicit || ftp_auth (csock, SCHEME_FTPS) == FTPOK)
|
||||
{
|
||||
if (!ssl_connect_wget (csock, u->host, NULL))
|
||||
{
|
||||
fd_close (csock);
|
||||
return CONSSLERR;
|
||||
}
|
||||
else if (!ssl_check_certificate (csock, u->host))
|
||||
{
|
||||
fd_close (csock);
|
||||
return VERIFCERTERR;
|
||||
}
|
||||
|
||||
if (!opt.ftps_implicit && !opt.server_response)
|
||||
logputs (LOG_VERBOSE, " done.\n");
|
||||
|
||||
/* If implicit FTPS was requested, we act as "normal" FTP, but over SSL.
|
||||
* We're not using RFC 2228 commands.
|
||||
*/
|
||||
using_security = true;
|
||||
}
|
||||
else
|
||||
{
|
||||
/* The server does not support 'AUTH TLS'.
|
||||
* Check if --ftps-fallback-to-ftp was passed. */
|
||||
if (opt.ftps_fallback_to_ftp)
|
||||
{
|
||||
logputs (LOG_NOTQUIET, "Server does not support AUTH TLS. Falling back to FTP.\n");
|
||||
using_security = false;
|
||||
}
|
||||
else
|
||||
{
|
||||
fd_close (csock);
|
||||
return FTPNOAUTH;
|
||||
}
|
||||
}
|
||||
|
||||
*using_control_security = using_security;
|
||||
return NOCONERROR;
|
||||
}
|
||||
#endif
|
||||
|
||||
/* Retrieves a file with denoted parameters through opening an FTP
|
||||
connection to the server. It always closes the data connection,
|
||||
and closes the control connection in case of error. If warc_tmp
|
||||
is non-NULL, the downloaded data will be written there as well. */
|
||||
static uerr_t
|
||||
getftp (struct url *u, wgint passed_expected_bytes, wgint *qtyread,
|
||||
getftp (struct url *u, struct url *original_url,
|
||||
wgint passed_expected_bytes, wgint *qtyread,
|
||||
wgint restval, ccon *con, int count, wgint *last_expected_bytes,
|
||||
FILE *warc_tmp)
|
||||
{
|
||||
int csock, dtsock, local_sock, res;
|
||||
uerr_t err = RETROK; /* appease the compiler */
|
||||
FILE *fp;
|
||||
FILE *fp = NULL;
|
||||
char *respline, *tms;
|
||||
const char *user, *passwd, *tmrate;
|
||||
int cmd = con->cmd;
|
||||
bool pasv_mode_open = false;
|
||||
wgint expected_bytes = 0;
|
||||
bool got_expected_bytes = false;
|
||||
bool rest_failed = false;
|
||||
@@ -261,6 +337,15 @@ getftp (struct url *u, wgint passed_expected_bytes, wgint *qtyread,
|
||||
char type_char;
|
||||
bool try_again;
|
||||
bool list_a_used = false;
|
||||
#ifdef HAVE_SSL
|
||||
enum prot_level prot = (opt.ftps_clear_data_connection ? PROT_CLEAR : PROT_PRIVATE);
|
||||
/* these variables tell whether the target server
|
||||
* accepts the security extensions (RFC 2228) or not,
|
||||
* and whether we're actually using any of them
|
||||
* (encryption at the control connection only,
|
||||
* or both at control and data connections) */
|
||||
bool using_control_security = false, using_data_security = false;
|
||||
#endif
|
||||
|
||||
assert (con != NULL);
|
||||
assert (con->target != NULL);
|
||||
@@ -274,20 +359,71 @@ getftp (struct url *u, wgint passed_expected_bytes, wgint *qtyread,
|
||||
|
||||
*qtyread = restval;
|
||||
|
||||
user = u->user;
|
||||
passwd = u->passwd;
|
||||
search_netrc (u->host, (const char **)&user, (const char **)&passwd, 1);
|
||||
user = user ? user : (opt.ftp_user ? opt.ftp_user : opt.user);
|
||||
/* Find the username with priority */
|
||||
if (u->user)
|
||||
user = u->user;
|
||||
else if (opt.user && (opt.use_askpass || opt.ask_passwd))
|
||||
user = opt.user;
|
||||
else if (opt.ftp_user)
|
||||
user = opt.ftp_user;
|
||||
else if (opt.user)
|
||||
user = opt.user;
|
||||
else
|
||||
user = NULL;
|
||||
|
||||
/* Find the password with priority */
|
||||
if (u->passwd)
|
||||
passwd = u->passwd;
|
||||
else if (opt.passwd && (opt.use_askpass || opt.ask_passwd))
|
||||
passwd = opt.passwd;
|
||||
else if (opt.ftp_passwd)
|
||||
passwd = opt.ftp_passwd;
|
||||
else if (opt.passwd)
|
||||
passwd = opt.passwd;
|
||||
else
|
||||
passwd = NULL;
|
||||
|
||||
/* Check for ~/.netrc if none of the above match */
|
||||
if (opt.netrc && (!user || !passwd))
|
||||
search_netrc (u->host, (const char **) &user, (const char **) &passwd, 1);
|
||||
|
||||
if (!user) user = "anonymous";
|
||||
passwd = passwd ? passwd : (opt.ftp_passwd ? opt.ftp_passwd : opt.passwd);
|
||||
if (!passwd) passwd = "-wget@";
|
||||
|
||||
dtsock = -1;
|
||||
local_sock = -1;
|
||||
con->dltime = 0;
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
if (u->scheme == SCHEME_FTPS)
|
||||
{
|
||||
/* Initialize SSL layer first */
|
||||
if (!ssl_init ())
|
||||
{
|
||||
scheme_disable (SCHEME_FTPS);
|
||||
logprintf (LOG_NOTQUIET, _("Could not initialize SSL. It will be disabled."));
|
||||
err = SSLINITFAILED;
|
||||
return err;
|
||||
}
|
||||
|
||||
/* If we're using the default FTP port and implicit FTPS was requested,
|
||||
* rewrite the port to the default *implicit* FTPS port.
|
||||
*/
|
||||
if (opt.ftps_implicit && u->port == DEFAULT_FTP_PORT)
|
||||
{
|
||||
DEBUGP (("Implicit FTPS was specified. Rewriting default port to %d.\n", DEFAULT_FTPS_IMPLICIT_PORT));
|
||||
u->port = DEFAULT_FTPS_IMPLICIT_PORT;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
if (!(cmd & DO_LOGIN))
|
||||
csock = con->csock;
|
||||
{
|
||||
csock = con->csock;
|
||||
#ifdef HAVE_SSL
|
||||
using_data_security = con->st & DATA_CHANNEL_SECURITY;
|
||||
#endif
|
||||
}
|
||||
else /* cmd & DO_LOGIN */
|
||||
{
|
||||
char *host = con->proxy ? con->proxy->host : u->host;
|
||||
@@ -309,6 +445,43 @@ getftp (struct url *u, wgint passed_expected_bytes, wgint *qtyread,
|
||||
else
|
||||
con->csock = -1;
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
if (u->scheme == SCHEME_FTPS)
|
||||
{
|
||||
/* If we're in implicit FTPS mode, we have to set up SSL/TLS before everything else.
|
||||
* Otherwise we first read the server's greeting, and then send an "AUTH TLS".
|
||||
*/
|
||||
if (opt.ftps_implicit)
|
||||
{
|
||||
err = init_control_ssl_connection (csock, u, &using_control_security);
|
||||
if (err != NOCONERROR)
|
||||
return err;
|
||||
err = get_ftp_greeting (csock, con);
|
||||
if (err != FTPOK)
|
||||
return err;
|
||||
}
|
||||
else
|
||||
{
|
||||
err = get_ftp_greeting (csock, con);
|
||||
if (err != FTPOK)
|
||||
return err;
|
||||
err = init_control_ssl_connection (csock, u, &using_control_security);
|
||||
if (err != NOCONERROR)
|
||||
return err;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
err = get_ftp_greeting (csock, con);
|
||||
if (err != FTPOK)
|
||||
return err;
|
||||
}
|
||||
#else
|
||||
err = get_ftp_greeting (csock, con);
|
||||
if (err != FTPOK)
|
||||
return err;
|
||||
#endif
|
||||
|
||||
/* Second: Login with proper USER/PASS sequence. */
|
||||
logprintf (LOG_VERBOSE, _("Logging in as %s ... "),
|
||||
quotearg_style (escape_quoting_style, user));
|
||||
@@ -366,6 +539,46 @@ Error in server response, closing control connection.\n"));
|
||||
default:
|
||||
abort ();
|
||||
}
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
if (using_control_security)
|
||||
{
|
||||
/* Send the PBSZ and PROT commands, in that order.
|
||||
* If we are here it means that the server has already accepted
|
||||
* some form of FTPS. Thus, these commands must work.
|
||||
* If they don't work, that's an error. There's no sense in honoring
|
||||
* --ftps-fallback-to-ftp or similar options. */
|
||||
if (u->scheme == SCHEME_FTPS)
|
||||
{
|
||||
if (!opt.server_response)
|
||||
logputs (LOG_VERBOSE, "==> PBSZ 0 ... ");
|
||||
if ((err = ftp_pbsz (csock, 0)) == FTPNOPBSZ)
|
||||
{
|
||||
logputs (LOG_NOTQUIET, _("Server did not accept the 'PBSZ 0' command.\n"));
|
||||
return err;
|
||||
}
|
||||
if (!opt.server_response)
|
||||
logputs (LOG_VERBOSE, "done.");
|
||||
|
||||
if (!opt.server_response)
|
||||
logprintf (LOG_VERBOSE, " ==> PROT %c ... ", (int) prot);
|
||||
if ((err = ftp_prot (csock, prot)) == FTPNOPROT)
|
||||
{
|
||||
logprintf (LOG_NOTQUIET, _("Server did not accept the 'PROT %c' command.\n"), (int) prot);
|
||||
return err;
|
||||
}
|
||||
if (!opt.server_response)
|
||||
logputs (LOG_VERBOSE, "done.\n");
|
||||
|
||||
if (prot != PROT_CLEAR)
|
||||
{
|
||||
using_data_security = true;
|
||||
con->st |= DATA_CHANNEL_SECURITY;
|
||||
}
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
/* Third: Get the system type */
|
||||
if (!opt.server_response)
|
||||
logprintf (LOG_VERBOSE, "==> SYST ... ");
|
||||
@@ -685,7 +898,7 @@ Error in server response, closing control connection.\n"));
|
||||
Unlike the rest of this block, this particular behavior
|
||||
_is_ VMS-specific, so it gets its own VMS test.
|
||||
*/
|
||||
if ((con->rs == ST_VMS) && (strchr( target, '/') != NULL))
|
||||
if ((con->rs == ST_VMS) && (strchr (target, '/') != NULL))
|
||||
{
|
||||
cwd_end = 3;
|
||||
DEBUGP (("Using extra \"CWD []\" step for VMS server.\n"));
|
||||
@@ -883,13 +1096,19 @@ Error in server response, closing control connection.\n"));
|
||||
? CONERROR : CONIMPOSSIBLE);
|
||||
}
|
||||
|
||||
pasv_mode_open = true; /* Flag to avoid accept port */
|
||||
if (!opt.server_response)
|
||||
logputs (LOG_VERBOSE, _("done. "));
|
||||
} /* err==FTP_OK */
|
||||
}
|
||||
}
|
||||
else
|
||||
return err;
|
||||
|
||||
if (!pasv_mode_open) /* Try to use a port command if PASV failed */
|
||||
/*
|
||||
* We do not want to fall back from PASSIVE mode to ACTIVE mode !
|
||||
* The reason is the PORT command exposes the client's real IP address
|
||||
* to the server. Bad for someone who relies on privacy via a ftp proxy.
|
||||
*/
|
||||
}
|
||||
else
|
||||
{
|
||||
err = ftp_do_port (csock, &local_sock);
|
||||
/* FTPRERR, WRITEFAILED, bindport (FTPSYSERR), HOSTERR,
|
||||
@@ -995,8 +1214,9 @@ Error in server response, closing control connection.\n"));
|
||||
if (opt.spider)
|
||||
{
|
||||
bool exists = false;
|
||||
bool all_exist = true;
|
||||
struct fileinfo *f;
|
||||
uerr_t _res = ftp_get_listing (u, con, &f);
|
||||
uerr_t _res = ftp_get_listing (u, original_url, con, &f);
|
||||
/* Set the DO_RETR command flag again, because it gets unset when
|
||||
calling ftp_get_listing() and would otherwise cause an assertion
|
||||
failure earlier on when this function gets repeatedly called
|
||||
@@ -1010,6 +1230,8 @@ Error in server response, closing control connection.\n"));
|
||||
{
|
||||
exists = true;
|
||||
break;
|
||||
} else {
|
||||
all_exist = false;
|
||||
}
|
||||
f = f->next;
|
||||
}
|
||||
@@ -1030,7 +1252,11 @@ Error in server response, closing control connection.\n"));
|
||||
con->csock = -1;
|
||||
fd_close (dtsock);
|
||||
fd_close (local_sock);
|
||||
return RETRFINISHED;
|
||||
if (all_exist) {
|
||||
return RETRFINISHED;
|
||||
} else {
|
||||
return FTPNSFOD;
|
||||
}
|
||||
}
|
||||
|
||||
if (opt.verbose)
|
||||
@@ -1148,8 +1374,8 @@ Error in server response, closing control connection.\n"));
|
||||
}
|
||||
|
||||
/* If no transmission was required, then everything is OK. */
|
||||
if (!pasv_mode_open) /* we are not using pasive mode so we need
|
||||
to accept */
|
||||
if (!opt.ftp_pasv) /* we are not using passive mode so we need
|
||||
to accept */
|
||||
{
|
||||
/* Wait for the server to connect to the address we're waiting
|
||||
at. */
|
||||
@@ -1308,6 +1534,38 @@ Error in server response, closing control connection.\n"));
|
||||
else if (expected_bytes)
|
||||
print_length (expected_bytes, restval, false);
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
if (u->scheme == SCHEME_FTPS && using_data_security)
|
||||
{
|
||||
/* We should try to restore the existing SSL session in the data connection
|
||||
* and fall back to establishing a new session if the server doesn't want to restore it.
|
||||
*/
|
||||
if (!opt.ftps_resume_ssl || !ssl_connect_wget (dtsock, u->host, &csock))
|
||||
{
|
||||
if (opt.ftps_resume_ssl)
|
||||
logputs (LOG_NOTQUIET, "Server does not want to resume the SSL session. Trying with a new one.\n");
|
||||
if (!ssl_connect_wget (dtsock, u->host, NULL))
|
||||
{
|
||||
fd_close (csock);
|
||||
fd_close (dtsock);
|
||||
err = CONERROR;
|
||||
logputs (LOG_NOTQUIET, "Could not perform SSL handshake.\n");
|
||||
goto exit_error;
|
||||
}
|
||||
}
|
||||
else
|
||||
logputs (LOG_NOTQUIET, "Resuming SSL session in data connection.\n");
|
||||
|
||||
if (!ssl_check_certificate (dtsock, u->host))
|
||||
{
|
||||
fd_close (csock);
|
||||
fd_close (dtsock);
|
||||
err = CONERROR;
|
||||
goto exit_error;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
/* Get the contents of the document. */
|
||||
flags = 0;
|
||||
if (restval && rest_failed)
|
||||
@@ -1321,6 +1579,11 @@ Error in server response, closing control connection.\n"));
|
||||
tmrate = retr_rate (rd_size, con->dltime);
|
||||
total_download_time += con->dltime;
|
||||
|
||||
#ifdef ENABLE_XATTR
|
||||
if (opt.enable_xattr)
|
||||
set_file_metadata (u->url, NULL, fp);
|
||||
#endif
|
||||
|
||||
fd_close (local_sock);
|
||||
/* Close the local file. */
|
||||
if (!output_stream || con->cmd & DO_LIST)
|
||||
@@ -1372,10 +1635,18 @@ Error in server response, closing control connection.\n"));
|
||||
become apparent later. */
|
||||
if (*respline != '2')
|
||||
{
|
||||
xfree (respline);
|
||||
if (res != -1)
|
||||
logprintf (LOG_NOTQUIET, "%s (%s) - ", tms, tmrate);
|
||||
logputs (LOG_NOTQUIET, _("Data transfer aborted.\n"));
|
||||
#ifdef HAVE_SSL
|
||||
if (!c_strncasecmp (respline, "425", 3) && u->scheme == SCHEME_FTPS)
|
||||
{
|
||||
logputs (LOG_NOTQUIET, "FTPS server rejects new SSL sessions in the data connection.\n");
|
||||
xfree (respline);
|
||||
return FTPRESTFAIL;
|
||||
}
|
||||
#endif
|
||||
xfree (respline);
|
||||
return FTPRETRINT;
|
||||
}
|
||||
xfree (respline);
|
||||
@@ -1408,10 +1679,10 @@ Error in server response, closing control connection.\n"));
|
||||
#ifdef __VMS
|
||||
char *targ;
|
||||
|
||||
targ = ods_conform( con->target);
|
||||
targ = ods_conform (con->target);
|
||||
if (targ != con->target)
|
||||
{
|
||||
xfree( con->target);
|
||||
xfree (con->target);
|
||||
con->target = targ;
|
||||
}
|
||||
#endif /* def __VMS */
|
||||
@@ -1532,6 +1803,13 @@ Error in server response, closing control connection.\n"));
|
||||
}
|
||||
} while (try_again);
|
||||
return RETRFINISHED;
|
||||
|
||||
exit_error:
|
||||
|
||||
/* If fp is a regular file, close and try to remove it */
|
||||
if (fp && !output_stream)
|
||||
fclose (fp);
|
||||
return err;
|
||||
}
|
||||
|
||||
/* A one-file FTP loop. This is the part where FTP retrieval is
|
||||
@@ -1540,14 +1818,15 @@ Error in server response, closing control connection.\n"));
|
||||
This loop either gets commands from con, or (if ON_YOUR_OWN is
|
||||
set), makes them up to retrieve the file given by the URL. */
|
||||
static uerr_t
|
||||
ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_file)
|
||||
ftp_loop_internal (struct url *u, struct url *original_url, struct fileinfo *f,
|
||||
ccon *con, char **local_file, bool force_full_retrieve)
|
||||
{
|
||||
int count, orig_lp;
|
||||
wgint restval, len = 0, qtyread = 0;
|
||||
char *tms, *locf;
|
||||
const char *tmrate = NULL;
|
||||
uerr_t err;
|
||||
struct_stat st;
|
||||
struct stat st;
|
||||
|
||||
/* Declare WARC variables. */
|
||||
bool warc_enabled = (opt.warc_filename != NULL);
|
||||
@@ -1565,7 +1844,7 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
|
||||
{
|
||||
/* URL-derived file. Consider "-O file" name. */
|
||||
xfree (con->target);
|
||||
con->target = url_file_name (u, NULL);
|
||||
con->target = url_file_name (opt.trustservernames || !original_url ? u : original_url, NULL);
|
||||
if (!opt.output_document)
|
||||
locf = con->target;
|
||||
else
|
||||
@@ -1642,6 +1921,8 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
|
||||
/* Decide whether or not to restart. */
|
||||
if (con->cmd & DO_LIST)
|
||||
restval = 0;
|
||||
else if (force_full_retrieve)
|
||||
restval = 0;
|
||||
else if (opt.start_pos >= 0)
|
||||
restval = opt.start_pos;
|
||||
else if (opt.always_rest
|
||||
@@ -1681,8 +1962,8 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
|
||||
|
||||
/* If we are working on a WARC record, getftp should also write
|
||||
to the warc_tmp file. */
|
||||
err = getftp (u, len, &qtyread, restval, con, count, &last_expected_bytes,
|
||||
warc_tmp);
|
||||
err = getftp (u, original_url, len, &qtyread, restval, con, count,
|
||||
&last_expected_bytes, warc_tmp);
|
||||
|
||||
if (con->csock == -1)
|
||||
con->st &= ~DONE_CWD;
|
||||
@@ -1692,11 +1973,17 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
|
||||
switch (err)
|
||||
{
|
||||
case HOSTERR: case CONIMPOSSIBLE: case FWRITEERR: case FOPENERR:
|
||||
case FTPNSFOD: case FTPLOGINC: case FTPNOPASV: case CONTNOTSUPPORTED:
|
||||
case UNLINKERR: case WARC_TMP_FWRITEERR:
|
||||
case FTPNSFOD: case FTPLOGINC: case FTPNOPASV: case FTPNOAUTH: case FTPNOPBSZ: case FTPNOPROT:
|
||||
case UNLINKERR: case WARC_TMP_FWRITEERR: case CONSSLERR: case CONTNOTSUPPORTED:
|
||||
#ifdef HAVE_SSL
|
||||
if (err == FTPNOAUTH)
|
||||
logputs (LOG_NOTQUIET, "Server does not support AUTH TLS.\n");
|
||||
if (opt.ftps_implicit)
|
||||
logputs (LOG_NOTQUIET, "Server does not like implicit FTPS connections.\n");
|
||||
#endif
|
||||
/* Fatal errors, give up. */
|
||||
if (warc_tmp != NULL)
|
||||
fclose (warc_tmp);
|
||||
fclose (warc_tmp);
|
||||
return err;
|
||||
case CONSOCKERR: case CONERROR: case FTPSRVERR: case FTPRERR:
|
||||
case WRITEFAILED: case FTPUNKNOWNTYPE: case FTPSYSERR:
|
||||
@@ -1771,10 +2058,12 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
|
||||
|
||||
warc_res = warc_write_resource_record (NULL, u->url, NULL, NULL,
|
||||
warc_ip, NULL, warc_tmp, -1);
|
||||
|
||||
if (! warc_res)
|
||||
return WARC_ERR;
|
||||
|
||||
/* warc_write_resource_record has also closed warc_tmp. */
|
||||
warc_tmp = NULL;
|
||||
}
|
||||
|
||||
if (con->cmd & DO_LIST)
|
||||
@@ -1821,6 +2110,9 @@ Removing file due to --delete-after in ftp_loop_internal():\n"));
|
||||
if (local_file)
|
||||
*local_file = xstrdup (locf);
|
||||
|
||||
if (warc_tmp != NULL)
|
||||
fclose (warc_tmp);
|
||||
|
||||
return RETROK;
|
||||
} while (!opt.ntry || (count < opt.ntry));
|
||||
|
||||
@@ -1829,13 +2121,18 @@ Removing file due to --delete-after in ftp_loop_internal():\n"));
|
||||
fd_close (con->csock);
|
||||
con->csock = -1;
|
||||
}
|
||||
|
||||
if (warc_tmp != NULL)
|
||||
fclose (warc_tmp);
|
||||
|
||||
return TRYLIMEXC;
|
||||
}
|
||||
|
||||
/* Return the directory listing in a reusable format. The directory
|
||||
is specifed in u->dir. */
|
||||
static uerr_t
|
||||
ftp_get_listing (struct url *u, ccon *con, struct fileinfo **f)
|
||||
ftp_get_listing (struct url *u, struct url *original_url, ccon *con,
|
||||
struct fileinfo **f)
|
||||
{
|
||||
uerr_t err;
|
||||
char *uf; /* url file name */
|
||||
@@ -1856,7 +2153,7 @@ ftp_get_listing (struct url *u, ccon *con, struct fileinfo **f)
|
||||
|
||||
con->target = xstrdup (lf);
|
||||
xfree (lf);
|
||||
err = ftp_loop_internal (u, NULL, con, NULL);
|
||||
err = ftp_loop_internal (u, original_url, NULL, con, NULL, false);
|
||||
lf = xstrdup (con->target);
|
||||
xfree (con->target);
|
||||
con->target = old_target;
|
||||
@@ -1879,8 +2176,9 @@ ftp_get_listing (struct url *u, ccon *con, struct fileinfo **f)
|
||||
return err;
|
||||
}
|
||||
|
||||
static uerr_t ftp_retrieve_dirs (struct url *, struct fileinfo *, ccon *);
|
||||
static uerr_t ftp_retrieve_glob (struct url *, ccon *, int);
|
||||
static uerr_t ftp_retrieve_dirs (struct url *, struct url *,
|
||||
struct fileinfo *, ccon *);
|
||||
static uerr_t ftp_retrieve_glob (struct url *, struct url *, ccon *, int);
|
||||
static struct fileinfo *delelement (struct fileinfo *, struct fileinfo **);
|
||||
static void freefileinfo (struct fileinfo *f);
|
||||
|
||||
@@ -1892,7 +2190,8 @@ static void freefileinfo (struct fileinfo *f);
|
||||
If opt.recursive is set, after all files have been retrieved,
|
||||
ftp_retrieve_dirs will be called to retrieve the directories. */
|
||||
static uerr_t
|
||||
ftp_retrieve_list (struct url *u, struct fileinfo *f, ccon *con)
|
||||
ftp_retrieve_list (struct url *u, struct url *original_url,
|
||||
struct fileinfo *f, ccon *con)
|
||||
{
|
||||
static int depth = 0;
|
||||
uerr_t err;
|
||||
@@ -1901,6 +2200,7 @@ ftp_retrieve_list (struct url *u, struct fileinfo *f, ccon *con)
|
||||
time_t tml;
|
||||
bool dlthis; /* Download this (file). */
|
||||
const char *actual_target = NULL;
|
||||
bool force_full_retrieve = false;
|
||||
|
||||
/* Increase the depth. */
|
||||
++depth;
|
||||
@@ -1949,7 +2249,7 @@ ftp_retrieve_list (struct url *u, struct fileinfo *f, ccon *con)
|
||||
dlthis = true;
|
||||
if (opt.timestamping && f->type == FT_PLAINFILE)
|
||||
{
|
||||
struct_stat st;
|
||||
struct stat st;
|
||||
/* If conversion of HTML files retrieved via FTP is ever implemented,
|
||||
we'll need to stat() <file>.orig here when -K has been specified.
|
||||
I'm not implementing it now since files on an FTP server are much
|
||||
@@ -1980,9 +2280,10 @@ ftp_retrieve_list (struct url *u, struct fileinfo *f, ccon *con)
|
||||
Remote file no newer than local file %s -- not retrieving.\n"), quote (con->target));
|
||||
dlthis = false;
|
||||
}
|
||||
else if (eq_size)
|
||||
else if (f->tstamp > tml)
|
||||
{
|
||||
/* Remote file is newer or sizes cannot be matched */
|
||||
/* Remote file is newer */
|
||||
force_full_retrieve = true;
|
||||
logprintf (LOG_VERBOSE, _("\
|
||||
Remote file is newer than local file %s -- retrieving.\n\n"),
|
||||
quote (con->target));
|
||||
@@ -2011,7 +2312,7 @@ The sizes do not match (local %s) -- retrieving.\n\n"),
|
||||
_("Invalid name of the symlink, skipping.\n"));
|
||||
else
|
||||
{
|
||||
struct_stat st;
|
||||
struct stat st;
|
||||
/* Check whether we already have the correct
|
||||
symbolic link. */
|
||||
int rc = lstat (con->target, &st);
|
||||
@@ -2051,7 +2352,10 @@ Already have correct symlink %s -> %s\n\n"),
|
||||
else /* opt.retr_symlinks */
|
||||
{
|
||||
if (dlthis)
|
||||
err = ftp_loop_internal (u, f, con, NULL);
|
||||
{
|
||||
err = ftp_loop_internal (u, original_url, f, con, NULL,
|
||||
force_full_retrieve);
|
||||
}
|
||||
} /* opt.retr_symlinks */
|
||||
break;
|
||||
case FT_DIRECTORY:
|
||||
@@ -2062,9 +2366,13 @@ Already have correct symlink %s -> %s\n\n"),
|
||||
case FT_PLAINFILE:
|
||||
/* Call the retrieve loop. */
|
||||
if (dlthis)
|
||||
err = ftp_loop_internal (u, f, con, NULL);
|
||||
{
|
||||
err = ftp_loop_internal (u, original_url, f, con, NULL,
|
||||
force_full_retrieve);
|
||||
}
|
||||
break;
|
||||
case FT_UNKNOWN:
|
||||
default:
|
||||
logprintf (LOG_NOTQUIET, _("%s: unknown/unsupported file type.\n"),
|
||||
quote (f->name));
|
||||
break;
|
||||
@@ -2086,7 +2394,12 @@ Already have correct symlink %s -> %s\n\n"),
|
||||
(f->type == FT_PLAINFILE) && opt.preserve_perm)
|
||||
{
|
||||
if (f->perms)
|
||||
chmod (actual_target, f->perms);
|
||||
{
|
||||
if (chmod (actual_target, f->perms))
|
||||
logprintf (LOG_NOTQUIET,
|
||||
_("Failed to set permissions for %s.\n"),
|
||||
actual_target);
|
||||
}
|
||||
else
|
||||
DEBUGP (("Unrecognized permissions for %s.\n", actual_target));
|
||||
}
|
||||
@@ -2127,7 +2440,7 @@ Already have correct symlink %s -> %s\n\n"),
|
||||
/* We do not want to call ftp_retrieve_dirs here */
|
||||
if (opt.recursive &&
|
||||
!(opt.reclevel != INFINITE_RECURSION && depth >= opt.reclevel))
|
||||
err = ftp_retrieve_dirs (u, orig, con);
|
||||
err = ftp_retrieve_dirs (u, original_url, orig, con);
|
||||
else if (opt.recursive)
|
||||
DEBUGP ((_("Will not retrieve dirs since depth is %d (max %d).\n"),
|
||||
depth, opt.reclevel));
|
||||
@@ -2140,7 +2453,8 @@ Already have correct symlink %s -> %s\n\n"),
|
||||
ftp_retrieve_glob on each directory entry. The function knows
|
||||
about excluded directories. */
|
||||
static uerr_t
|
||||
ftp_retrieve_dirs (struct url *u, struct fileinfo *f, ccon *con)
|
||||
ftp_retrieve_dirs (struct url *u, struct url *original_url,
|
||||
struct fileinfo *f, ccon *con)
|
||||
{
|
||||
char *container = NULL;
|
||||
int container_size = 0;
|
||||
@@ -2190,7 +2504,7 @@ Not descending to %s as it is excluded/not-included.\n"),
|
||||
odir = xstrdup (u->dir); /* because url_set_dir will free
|
||||
u->dir. */
|
||||
url_set_dir (u, newdir);
|
||||
ftp_retrieve_glob (u, con, GLOB_GETALL);
|
||||
ftp_retrieve_glob (u, original_url, con, GLOB_GETALL);
|
||||
url_set_dir (u, odir);
|
||||
xfree (odir);
|
||||
|
||||
@@ -2233,7 +2547,7 @@ is_invalid_entry (struct fileinfo *f)
|
||||
while (cur->next)
|
||||
{
|
||||
cur = cur->next;
|
||||
if (strcmp(f_name, cur->name) == 0)
|
||||
if (strcmp (f_name, cur->name) == 0)
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
@@ -2249,14 +2563,15 @@ is_invalid_entry (struct fileinfo *f)
|
||||
GLOB_GLOBALL, use globbing; if it's GLOB_GETALL, download the whole
|
||||
directory. */
|
||||
static uerr_t
|
||||
ftp_retrieve_glob (struct url *u, ccon *con, int action)
|
||||
ftp_retrieve_glob (struct url *u, struct url *original_url,
|
||||
ccon *con, int action)
|
||||
{
|
||||
struct fileinfo *f, *start;
|
||||
uerr_t res;
|
||||
|
||||
con->cmd |= LEAVE_PENDING;
|
||||
|
||||
res = ftp_get_listing (u, con, &start);
|
||||
res = ftp_get_listing (u, original_url, con, &start);
|
||||
if (res != RETROK)
|
||||
return res;
|
||||
/* First: weed out that do not conform the global rules given in
|
||||
@@ -2352,7 +2667,7 @@ ftp_retrieve_glob (struct url *u, ccon *con, int action)
|
||||
if (start)
|
||||
{
|
||||
/* Just get everything. */
|
||||
res = ftp_retrieve_list (u, start, con);
|
||||
res = ftp_retrieve_list (u, original_url, start, con);
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -2368,7 +2683,7 @@ ftp_retrieve_glob (struct url *u, ccon *con, int action)
|
||||
{
|
||||
/* Let's try retrieving it anyway. */
|
||||
con->st |= ON_YOUR_OWN;
|
||||
res = ftp_loop_internal (u, NULL, con, NULL);
|
||||
res = ftp_loop_internal (u, original_url, NULL, con, NULL, false);
|
||||
return res;
|
||||
}
|
||||
|
||||
@@ -2388,8 +2703,8 @@ ftp_retrieve_glob (struct url *u, ccon *con, int action)
|
||||
of URL. Inherently, its capabilities are limited on what can be
|
||||
encoded into a URL. */
|
||||
uerr_t
|
||||
ftp_loop (struct url *u, char **local_file, int *dt, struct url *proxy,
|
||||
bool recursive, bool glob)
|
||||
ftp_loop (struct url *u, struct url *original_url, char **local_file, int *dt,
|
||||
struct url *proxy, bool recursive, bool glob)
|
||||
{
|
||||
ccon con; /* FTP connection */
|
||||
uerr_t res;
|
||||
@@ -2410,22 +2725,23 @@ ftp_loop (struct url *u, char **local_file, int *dt, struct url *proxy,
|
||||
if (!*u->file && !recursive)
|
||||
{
|
||||
struct fileinfo *f;
|
||||
res = ftp_get_listing (u, &con, &f);
|
||||
res = ftp_get_listing (u, original_url, &con, &f);
|
||||
|
||||
if (res == RETROK)
|
||||
{
|
||||
if (opt.htmlify && !opt.spider)
|
||||
{
|
||||
struct url *url_file = opt.trustservernames ? u : original_url;
|
||||
char *filename = (opt.output_document
|
||||
? xstrdup (opt.output_document)
|
||||
: (con.target ? xstrdup (con.target)
|
||||
: url_file_name (u, NULL)));
|
||||
: url_file_name (url_file, NULL)));
|
||||
res = ftp_index (filename, u, f);
|
||||
if (res == FTPOK && opt.verbose)
|
||||
{
|
||||
if (!opt.output_document)
|
||||
{
|
||||
struct_stat st;
|
||||
struct stat st;
|
||||
wgint sz;
|
||||
if (stat (filename, &st) == 0)
|
||||
sz = st.st_size;
|
||||
@@ -2464,11 +2780,13 @@ ftp_loop (struct url *u, char **local_file, int *dt, struct url *proxy,
|
||||
/* ftp_retrieve_glob is a catch-all function that gets called
|
||||
if we need globbing, time-stamping, recursion or preserve
|
||||
permissions. Its third argument is just what we really need. */
|
||||
res = ftp_retrieve_glob (u, &con,
|
||||
res = ftp_retrieve_glob (u, original_url, &con,
|
||||
ispattern ? GLOB_GLOBALL : GLOB_GETONE);
|
||||
}
|
||||
else
|
||||
res = ftp_loop_internal (u, NULL, &con, local_file);
|
||||
{
|
||||
res = ftp_loop_internal (u, original_url, NULL, &con, local_file, false);
|
||||
}
|
||||
}
|
||||
if (res == FTPOK)
|
||||
res = RETROK;
|
||||
|
||||
28
src/ftp.h
28
src/ftp.h
@@ -1,7 +1,7 @@
|
||||
/* Declarations for FTP support.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -33,6 +33,7 @@ as that of the covered work. */
|
||||
#define FTP_H
|
||||
|
||||
#include "host.h"
|
||||
#include "url.h"
|
||||
|
||||
/* System types. */
|
||||
enum stype
|
||||
@@ -53,10 +54,27 @@ enum ustype
|
||||
UST_OTHER
|
||||
};
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
/* Data channel protection levels (to be used with PBSZ) */
|
||||
enum prot_level
|
||||
{
|
||||
PROT_CLEAR = 'C',
|
||||
PROT_SAFE = 'S',
|
||||
PROT_CONFIDENTIAL = 'E',
|
||||
PROT_PRIVATE = 'P'
|
||||
};
|
||||
#endif
|
||||
|
||||
uerr_t ftp_response (int, char **);
|
||||
uerr_t ftp_greeting (int);
|
||||
uerr_t ftp_login (int, const char *, const char *);
|
||||
uerr_t ftp_port (int, int *);
|
||||
uerr_t ftp_pasv (int, ip_address *, int *);
|
||||
#ifdef HAVE_SSL
|
||||
uerr_t ftp_auth (int, enum url_scheme);
|
||||
uerr_t ftp_pbsz (int, int);
|
||||
uerr_t ftp_prot (int, enum prot_level);
|
||||
#endif
|
||||
#ifdef ENABLE_IPV6
|
||||
uerr_t ftp_lprt (int, int *);
|
||||
uerr_t ftp_lpsv (int, ip_address *, int *);
|
||||
@@ -142,15 +160,17 @@ enum wget_ftp_fstatus
|
||||
AVOID_LIST = 0x0008, /* It tells us if during this
|
||||
session we have to avoid to use
|
||||
"LIST". */
|
||||
LIST_AFTER_LIST_A_CHECK_DONE = 0x0010
|
||||
LIST_AFTER_LIST_A_CHECK_DONE = 0x0010,
|
||||
/* It tells us if we have already
|
||||
checked "LIST" after the first
|
||||
"LIST -a" to handle the case of
|
||||
file/folders named "-a". */
|
||||
DATA_CHANNEL_SECURITY = 0x0020 /* Establish a secure data channel */
|
||||
};
|
||||
|
||||
struct fileinfo *ftp_parse_ls (const char *, const enum stype);
|
||||
uerr_t ftp_loop (struct url *, char **, int *, struct url *, bool, bool);
|
||||
uerr_t ftp_loop (struct url *, struct url *, char **, int *, struct url *,
|
||||
bool, bool);
|
||||
|
||||
uerr_t ftp_index (const char *, struct url *, struct fileinfo *);
|
||||
|
||||
|
||||
304
src/gnutls.c
304
src/gnutls.c
@@ -1,6 +1,6 @@
|
||||
/* SSL support via GnuTLS library.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2015
|
||||
Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -36,7 +36,9 @@ as that of the covered work. */
|
||||
#include <stdio.h>
|
||||
#include <dirent.h>
|
||||
#include <stdlib.h>
|
||||
#include <xalloc.h>
|
||||
|
||||
#include <gnutls/abstract.h>
|
||||
#include <gnutls/gnutls.h>
|
||||
#include <gnutls/x509.h>
|
||||
#include <sys/ioctl.h>
|
||||
@@ -48,7 +50,7 @@ as that of the covered work. */
|
||||
#include "hash.h"
|
||||
#include "ssl.h"
|
||||
|
||||
#include <sys/fcntl.h>
|
||||
#include <fcntl.h>
|
||||
|
||||
#ifdef WIN32
|
||||
# include "w32sock.h"
|
||||
@@ -56,6 +58,9 @@ as that of the covered work. */
|
||||
|
||||
#include "host.h"
|
||||
|
||||
static int
|
||||
_do_handshake (gnutls_session_t session, int fd, double timeout);
|
||||
|
||||
static int
|
||||
key_type_to_gnutls_type (enum keyfile_type type)
|
||||
{
|
||||
@@ -184,13 +189,13 @@ ssl_init (void)
|
||||
/* Use the private key from the cert file unless otherwise specified. */
|
||||
if (opt.cert_file && !opt.private_key)
|
||||
{
|
||||
opt.private_key = opt.cert_file;
|
||||
opt.private_key = xstrdup (opt.cert_file);
|
||||
opt.private_key_type = opt.cert_type;
|
||||
}
|
||||
/* Use the cert from the private key file unless otherwise specified. */
|
||||
if (!opt.cert_file && opt.private_key)
|
||||
{
|
||||
opt.cert_file = opt.private_key;
|
||||
opt.cert_file = xstrdup (opt.private_key);
|
||||
opt.cert_type = opt.private_key_type;
|
||||
}
|
||||
|
||||
@@ -219,6 +224,7 @@ cert to be of the same type.\n"));
|
||||
struct wgnutls_transport_context
|
||||
{
|
||||
gnutls_session_t session; /* GnuTLS session handle */
|
||||
gnutls_datum_t *session_data;
|
||||
int last_error; /* last error returned by read/write/... */
|
||||
|
||||
/* Since GnuTLS doesn't support the equivalent to recv(...,
|
||||
@@ -276,6 +282,12 @@ wgnutls_read_timeout (int fd, char *buf, int bufsize, void *arg, double timeout)
|
||||
{
|
||||
ret = gnutls_record_recv (ctx->session, buf, bufsize);
|
||||
timed_out = timeout && ptimer_measure (timer) >= timeout;
|
||||
if (!timed_out && ret == GNUTLS_E_REHANDSHAKE)
|
||||
{
|
||||
DEBUGP (("GnuTLS: *** REHANDSHAKE while reading\n"));
|
||||
if ((ret = _do_handshake (ctx->session, fd, timeout)) == 0)
|
||||
ret = GNUTLS_E_AGAIN; /* restart reading */
|
||||
}
|
||||
}
|
||||
}
|
||||
while (ret == GNUTLS_E_INTERRUPTED || (ret == GNUTLS_E_AGAIN && !timed_out));
|
||||
@@ -405,6 +417,11 @@ wgnutls_close (int fd, void *arg)
|
||||
{
|
||||
struct wgnutls_transport_context *ctx = arg;
|
||||
/*gnutls_bye (ctx->session, GNUTLS_SHUT_RDWR);*/
|
||||
if (ctx->session_data)
|
||||
{
|
||||
gnutls_free (ctx->session_data->data);
|
||||
gnutls_free (ctx->session_data);
|
||||
}
|
||||
gnutls_deinit (ctx->session);
|
||||
xfree (ctx);
|
||||
close (fd);
|
||||
@@ -419,27 +436,126 @@ static struct transport_implementation wgnutls_transport =
|
||||
wgnutls_peek, wgnutls_errstr, wgnutls_close
|
||||
};
|
||||
|
||||
bool
|
||||
ssl_connect_wget (int fd, const char *hostname)
|
||||
static int
|
||||
_do_handshake (gnutls_session_t session, int fd, double timeout)
|
||||
{
|
||||
#ifdef F_GETFL
|
||||
int flags = 0;
|
||||
#endif
|
||||
int err;
|
||||
|
||||
if (timeout)
|
||||
{
|
||||
#ifdef F_GETFL
|
||||
flags = fcntl (fd, F_GETFL, 0);
|
||||
if (flags < 0)
|
||||
return flags;
|
||||
if (fcntl (fd, F_SETFL, flags | O_NONBLOCK))
|
||||
return -1;
|
||||
#else
|
||||
/* XXX: Assume it was blocking before. */
|
||||
const int one = 1;
|
||||
if (ioctl (fd, FIONBIO, &one) < 0)
|
||||
return -1;
|
||||
#endif
|
||||
}
|
||||
|
||||
/* We don't stop the handshake process for non-fatal errors */
|
||||
do
|
||||
{
|
||||
err = gnutls_handshake (session);
|
||||
|
||||
if (timeout && err == GNUTLS_E_AGAIN)
|
||||
{
|
||||
if (gnutls_record_get_direction (session))
|
||||
{
|
||||
/* wait for writeability */
|
||||
err = select_fd (fd, timeout, WAIT_FOR_WRITE);
|
||||
}
|
||||
else
|
||||
{
|
||||
/* wait for readability */
|
||||
err = select_fd (fd, timeout, WAIT_FOR_READ);
|
||||
}
|
||||
|
||||
if (err <= 0)
|
||||
{
|
||||
if (err == 0)
|
||||
{
|
||||
errno = ETIMEDOUT;
|
||||
err = -1;
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
err = GNUTLS_E_AGAIN;
|
||||
}
|
||||
else if (err < 0)
|
||||
{
|
||||
logprintf (LOG_NOTQUIET, "GnuTLS: %s\n", gnutls_strerror (err));
|
||||
if (err == GNUTLS_E_WARNING_ALERT_RECEIVED ||
|
||||
err == GNUTLS_E_FATAL_ALERT_RECEIVED)
|
||||
{
|
||||
gnutls_alert_description_t alert = gnutls_alert_get (session);
|
||||
const char *str = gnutls_alert_get_name (alert);
|
||||
logprintf (LOG_NOTQUIET, "GnuTLS: received alert [%u]: %s\n",
|
||||
alert, str ? str : "(unknown)");
|
||||
}
|
||||
}
|
||||
}
|
||||
while (err && gnutls_error_is_fatal (err) == 0);
|
||||
|
||||
if (timeout)
|
||||
{
|
||||
#ifdef F_GETFL
|
||||
if (fcntl (fd, F_SETFL, flags) < 0)
|
||||
return -1;
|
||||
#else
|
||||
const int zero = 0;
|
||||
if (ioctl (fd, FIONBIO, &zero) < 0)
|
||||
return -1;
|
||||
#endif
|
||||
}
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
static const char *
|
||||
_sni_hostname(const char *hostname)
|
||||
{
|
||||
size_t len = strlen(hostname);
|
||||
|
||||
char *sni_hostname = xmemdup(hostname, len + 1);
|
||||
|
||||
/* Remove trailing dot(s) to fix #47408.
|
||||
* Regarding RFC 6066 (SNI): The hostname is represented as a byte
|
||||
* string using ASCII encoding without a trailing dot. */
|
||||
while (len && sni_hostname[--len] == '.')
|
||||
sni_hostname[len] = 0;
|
||||
|
||||
return sni_hostname;
|
||||
}
|
||||
|
||||
bool
|
||||
ssl_connect_wget (int fd, const char *hostname, int *continue_session)
|
||||
{
|
||||
struct wgnutls_transport_context *ctx;
|
||||
gnutls_session_t session;
|
||||
int err;
|
||||
const char *str;
|
||||
|
||||
gnutls_init (&session, GNUTLS_CLIENT);
|
||||
|
||||
/* We set the server name but only if it's not an IP address. */
|
||||
if (! is_valid_ip_address (hostname))
|
||||
{
|
||||
gnutls_server_name_set (session, GNUTLS_NAME_DNS, hostname,
|
||||
strlen (hostname));
|
||||
/* GnuTLS 3.4.x (x<=10) disrespects the length parameter, we have to construct a new string */
|
||||
/* see https://gitlab.com/gnutls/gnutls/issues/78 */
|
||||
const char *sni_hostname = _sni_hostname(hostname);
|
||||
|
||||
gnutls_server_name_set (session, GNUTLS_NAME_DNS, sni_hostname, strlen(sni_hostname));
|
||||
xfree(sni_hostname);
|
||||
}
|
||||
|
||||
gnutls_set_default_priority (session);
|
||||
gnutls_credentials_set (session, GNUTLS_CRD_CERTIFICATE, credentials);
|
||||
#ifndef FD_TO_SOCKET
|
||||
# define FD_TO_SOCKET(X) (X)
|
||||
@@ -454,7 +570,8 @@ ssl_connect_wget (int fd, const char *hostname)
|
||||
switch (opt.secure_protocol)
|
||||
{
|
||||
case secure_protocol_auto:
|
||||
err = gnutls_priority_set_direct (session, "NORMAL:%COMPAT:-VERS-SSL3.0", NULL);
|
||||
err = gnutls_set_default_priority (session);
|
||||
gnutls_session_enable_compatibility_mode(session);
|
||||
break;
|
||||
|
||||
case secure_protocol_sslv2:
|
||||
@@ -482,7 +599,8 @@ ssl_connect_wget (int fd, const char *hostname)
|
||||
break;
|
||||
|
||||
default:
|
||||
logprintf (LOG_NOTQUIET, _("GnuTLS: unimplemented 'secure-protocol' option value %d\n"), opt.secure_protocol);
|
||||
logprintf (LOG_NOTQUIET, _("GnuTLS: unimplemented 'secure-protocol' option value %u\n"),
|
||||
(unsigned) opt.secure_protocol);
|
||||
logprintf (LOG_NOTQUIET, _("Please report this issue to bug-wget@gnu.org\n"));
|
||||
abort ();
|
||||
}
|
||||
@@ -491,6 +609,7 @@ ssl_connect_wget (int fd, const char *hostname)
|
||||
switch (opt.secure_protocol)
|
||||
{
|
||||
case secure_protocol_auto:
|
||||
err = gnutls_set_default_priority (session);
|
||||
break;
|
||||
|
||||
case secure_protocol_sslv2:
|
||||
@@ -531,79 +650,32 @@ ssl_connect_wget (int fd, const char *hostname)
|
||||
return false;
|
||||
}
|
||||
|
||||
if (opt.connect_timeout)
|
||||
if (continue_session)
|
||||
{
|
||||
#ifdef F_GETFL
|
||||
flags = fcntl (fd, F_GETFL, 0);
|
||||
if (flags < 0)
|
||||
return flags;
|
||||
if (fcntl (fd, F_SETFL, flags | O_NONBLOCK))
|
||||
return -1;
|
||||
#else
|
||||
/* XXX: Assume it was blocking before. */
|
||||
const int one = 1;
|
||||
if (ioctl (fd, FIONBIO, &one) < 0)
|
||||
return -1;
|
||||
#endif
|
||||
}
|
||||
|
||||
/* We don't stop the handshake process for non-fatal errors */
|
||||
do
|
||||
{
|
||||
err = gnutls_handshake (session);
|
||||
|
||||
if (opt.connect_timeout && err == GNUTLS_E_AGAIN)
|
||||
ctx = (struct wgnutls_transport_context *) fd_transport_context (*continue_session);
|
||||
if (!gnutls_session_is_resumed (session))
|
||||
{
|
||||
if (gnutls_record_get_direction (session))
|
||||
if (!ctx || !ctx->session_data || gnutls_session_set_data (session, ctx->session_data->data, ctx->session_data->size))
|
||||
{
|
||||
/* wait for writeability */
|
||||
err = select_fd (fd, opt.connect_timeout, WAIT_FOR_WRITE);
|
||||
}
|
||||
else
|
||||
{
|
||||
/* wait for readability */
|
||||
err = select_fd (fd, opt.connect_timeout, WAIT_FOR_READ);
|
||||
}
|
||||
|
||||
if (err <= 0)
|
||||
{
|
||||
if (err == 0)
|
||||
if (ctx && ctx->session_data)
|
||||
{
|
||||
errno = ETIMEDOUT;
|
||||
err = -1;
|
||||
/* server does not want to continue the session */
|
||||
if (ctx->session_data->data)
|
||||
gnutls_free (ctx->session_data->data);
|
||||
gnutls_free (ctx->session_data);
|
||||
}
|
||||
break;
|
||||
gnutls_deinit (session);
|
||||
return false;
|
||||
}
|
||||
|
||||
err = GNUTLS_E_AGAIN;
|
||||
}
|
||||
else if (err < 0)
|
||||
else
|
||||
{
|
||||
logprintf (LOG_NOTQUIET, "GnuTLS: %s\n", gnutls_strerror (err));
|
||||
if (err == GNUTLS_E_WARNING_ALERT_RECEIVED ||
|
||||
err == GNUTLS_E_FATAL_ALERT_RECEIVED)
|
||||
{
|
||||
gnutls_alert_description_t alert = gnutls_alert_get (session);
|
||||
str = gnutls_alert_get_name (alert);
|
||||
if (str == NULL)
|
||||
str = "(unknown)";
|
||||
logprintf (LOG_NOTQUIET, "GnuTLS: received alert [%d]: %s\n", alert, str);
|
||||
}
|
||||
logputs (LOG_ALWAYS, "SSL session has already been resumed. Continuing.\n");
|
||||
continue_session = NULL;
|
||||
}
|
||||
}
|
||||
while (err && gnutls_error_is_fatal (err) == 0);
|
||||
|
||||
if (opt.connect_timeout)
|
||||
{
|
||||
#ifdef F_GETFL
|
||||
if (fcntl (fd, F_SETFL, flags) < 0)
|
||||
return -1;
|
||||
#else
|
||||
const int zero = 0;
|
||||
if (ioctl (fd, FIONBIO, &zero) < 0)
|
||||
return -1;
|
||||
#endif
|
||||
}
|
||||
err = _do_handshake (session, fd, opt.connect_timeout);
|
||||
|
||||
if (err < 0)
|
||||
{
|
||||
@@ -612,11 +684,70 @@ ssl_connect_wget (int fd, const char *hostname)
|
||||
}
|
||||
|
||||
ctx = xnew0 (struct wgnutls_transport_context);
|
||||
ctx->session_data = xnew0 (gnutls_datum_t);
|
||||
ctx->session = session;
|
||||
if (gnutls_session_get_data2 (session, ctx->session_data))
|
||||
{
|
||||
xfree (ctx->session_data);
|
||||
logprintf (LOG_NOTQUIET, "WARNING: Could not save SSL session data for socket %d\n", fd);
|
||||
}
|
||||
fd_register_transport (fd, &wgnutls_transport, ctx);
|
||||
return true;
|
||||
}
|
||||
|
||||
static bool
|
||||
pkp_pin_peer_pubkey (gnutls_x509_crt_t cert, const char *pinnedpubkey)
|
||||
{
|
||||
/* Scratch */
|
||||
size_t len1 = 0, len2 = 0;
|
||||
char *buff1 = NULL;
|
||||
|
||||
gnutls_pubkey_t key = NULL;
|
||||
|
||||
/* Result is returned to caller */
|
||||
int ret = 0;
|
||||
bool result = false;
|
||||
|
||||
/* if a path wasn't specified, don't pin */
|
||||
if (NULL == pinnedpubkey)
|
||||
return true;
|
||||
|
||||
if (NULL == cert)
|
||||
return result;
|
||||
|
||||
/* Begin Gyrations to get the public key */
|
||||
gnutls_pubkey_init (&key);
|
||||
|
||||
ret = gnutls_pubkey_import_x509 (key, cert, 0);
|
||||
if (ret < 0)
|
||||
goto cleanup; /* failed */
|
||||
|
||||
ret = gnutls_pubkey_export (key, GNUTLS_X509_FMT_DER, NULL, &len1);
|
||||
if (ret != GNUTLS_E_SHORT_MEMORY_BUFFER || len1 == 0)
|
||||
goto cleanup; /* failed */
|
||||
|
||||
buff1 = xmalloc (len1);
|
||||
|
||||
len2 = len1;
|
||||
|
||||
ret = gnutls_pubkey_export (key, GNUTLS_X509_FMT_DER, buff1, &len2);
|
||||
if (ret < 0 || len1 != len2)
|
||||
goto cleanup; /* failed */
|
||||
|
||||
/* End Gyrations */
|
||||
|
||||
/* The one good exit point */
|
||||
result = wg_pin_peer_pubkey (pinnedpubkey, buff1, len1);
|
||||
|
||||
cleanup:
|
||||
if (NULL != key)
|
||||
gnutls_pubkey_deinit (key);
|
||||
|
||||
xfree (buff1);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
#define _CHECK_CERT(flag,msg) \
|
||||
if (status & (flag))\
|
||||
{\
|
||||
@@ -637,6 +768,11 @@ ssl_check_certificate (int fd, const char *host)
|
||||
him about problems with the server's certificate. */
|
||||
const char *severity = opt.check_cert ? _("ERROR") : _("WARNING");
|
||||
bool success = true;
|
||||
bool pinsuccess = opt.pinnedpubkey == NULL;
|
||||
|
||||
/* The user explicitly said to not check for the certificate. */
|
||||
if (opt.check_cert == CHECK_CERT_QUIET && pinsuccess)
|
||||
return success;
|
||||
|
||||
err = gnutls_certificate_verify_peers2 (ctx->session, &status);
|
||||
if (err < 0)
|
||||
@@ -661,6 +797,7 @@ ssl_check_certificate (int fd, const char *host)
|
||||
gnutls_x509_crt_t cert;
|
||||
const gnutls_datum_t *cert_list;
|
||||
unsigned int cert_list_size;
|
||||
const char *sni_hostname;
|
||||
|
||||
if ((err = gnutls_x509_crt_init (&cert)) < 0)
|
||||
{
|
||||
@@ -695,13 +832,23 @@ ssl_check_certificate (int fd, const char *host)
|
||||
logprintf (LOG_NOTQUIET, _("The certificate has expired\n"));
|
||||
success = false;
|
||||
}
|
||||
if (!gnutls_x509_crt_check_hostname (cert, host))
|
||||
sni_hostname = _sni_hostname(host);
|
||||
if (!gnutls_x509_crt_check_hostname (cert, sni_hostname))
|
||||
{
|
||||
logprintf (LOG_NOTQUIET,
|
||||
_("The certificate's owner does not match hostname %s\n"),
|
||||
quote (host));
|
||||
quote (sni_hostname));
|
||||
success = false;
|
||||
}
|
||||
xfree(sni_hostname);
|
||||
|
||||
pinsuccess = pkp_pin_peer_pubkey (cert, opt.pinnedpubkey);
|
||||
if (!pinsuccess)
|
||||
{
|
||||
logprintf (LOG_ALWAYS, _("The public key does not match pinned public key!\n"));
|
||||
success = false;
|
||||
}
|
||||
|
||||
crt_deinit:
|
||||
gnutls_x509_crt_deinit (cert);
|
||||
}
|
||||
@@ -712,5 +859,6 @@ ssl_check_certificate (int fd, const char *host)
|
||||
}
|
||||
|
||||
out:
|
||||
return opt.check_cert ? success : true;
|
||||
/* never return true if pinsuccess fails */
|
||||
return !pinsuccess ? false : (opt.check_cert == CHECK_CERT_ON ? success : true);
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Hash tables.
|
||||
Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008,
|
||||
2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
2009, 2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -283,10 +283,10 @@ hash_table_new (int items,
|
||||
|
||||
/* Calculate the size that ensures that the table will store at
|
||||
least ITEMS keys without the need to resize. */
|
||||
size = 1 + items / HASH_MAX_FULLNESS;
|
||||
size = (int) (1 + items / HASH_MAX_FULLNESS);
|
||||
size = prime_size (size, &ht->prime_offset);
|
||||
ht->size = size;
|
||||
ht->resize_threshold = size * HASH_MAX_FULLNESS;
|
||||
ht->resize_threshold = (int) (size * HASH_MAX_FULLNESS);
|
||||
/*assert (ht->resize_threshold >= items);*/
|
||||
|
||||
ht->cells = xnew_array (struct cell, ht->size);
|
||||
@@ -394,7 +394,7 @@ grow_hash_table (struct hash_table *ht)
|
||||
#endif
|
||||
|
||||
ht->size = newsize;
|
||||
ht->resize_threshold = newsize * HASH_MAX_FULLNESS;
|
||||
ht->resize_threshold = (int) (newsize * HASH_MAX_FULLNESS);
|
||||
|
||||
cells = xnew_array (struct cell, newsize);
|
||||
memset (cells, INVALID_PTR_CHAR, newsize * sizeof (struct cell));
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/* Hash table declarations.
|
||||
Copyright (C) 2000, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Copyright (C) 2000, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
279
src/host.c
279
src/host.c
@@ -1,7 +1,7 @@
|
||||
/* Host name resolution and matching.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -58,13 +58,14 @@ as that of the covered work. */
|
||||
#include <errno.h>
|
||||
|
||||
#ifdef ENABLE_IRI
|
||||
#include <idn-free.h>
|
||||
#include <idn2.h>
|
||||
#endif
|
||||
|
||||
#include "utils.h"
|
||||
#include "host.h"
|
||||
#include "url.h"
|
||||
#include "hash.h"
|
||||
#include "ptimer.h"
|
||||
|
||||
#ifndef NO_ADDRESS
|
||||
# define NO_ADDRESS NO_DATA
|
||||
@@ -427,14 +428,12 @@ getaddrinfo_with_timeout (const char *node, const char *service,
|
||||
const char *
|
||||
print_address (const ip_address *addr)
|
||||
{
|
||||
#ifdef ENABLE_IPV6
|
||||
static char buf[64];
|
||||
|
||||
if (!inet_ntop (addr->family, IP_INADDR_DATA (addr), buf, sizeof buf))
|
||||
snprintf (buf, sizeof buf, "<error: %s>", strerror (errno));
|
||||
|
||||
return buf;
|
||||
#else
|
||||
return inet_ntoa (addr->data.d4);
|
||||
#endif
|
||||
}
|
||||
|
||||
/* The following two functions were adapted from glibc's
|
||||
@@ -649,6 +648,112 @@ cache_remove (const char *host)
|
||||
}
|
||||
}
|
||||
|
||||
#ifdef HAVE_LIBCARES
|
||||
#include <sys/select.h>
|
||||
#include <ares.h>
|
||||
extern ares_channel ares;
|
||||
|
||||
static struct address_list *
|
||||
merge_address_lists (struct address_list *al1, struct address_list *al2)
|
||||
{
|
||||
int count = al1->count + al2->count;
|
||||
|
||||
/* merge al2 into al1 */
|
||||
al1->addresses = xrealloc (al1->addresses, sizeof (ip_address) * count);
|
||||
memcpy (al1->addresses + al1->count, al2->addresses, sizeof (ip_address) * al2->count);
|
||||
al1->count = count;
|
||||
|
||||
address_list_delete (al2);
|
||||
|
||||
return al1;
|
||||
}
|
||||
|
||||
static struct address_list *
|
||||
address_list_from_hostent (struct hostent *host)
|
||||
{
|
||||
int count, i;
|
||||
struct address_list *al = xnew0 (struct address_list);
|
||||
|
||||
for (count = 0; host->h_addr_list[count]; count++)
|
||||
;
|
||||
|
||||
assert (count > 0);
|
||||
|
||||
al->addresses = xnew_array (ip_address, count);
|
||||
al->count = count;
|
||||
al->refcount = 1;
|
||||
|
||||
for (i = 0; i < count; i++)
|
||||
{
|
||||
ip_address *ip = &al->addresses[i];
|
||||
ip->family = host->h_addrtype;
|
||||
memcpy (IP_INADDR_DATA (ip), host->h_addr_list[i], ip->family == AF_INET ? 4 : 16);
|
||||
}
|
||||
|
||||
return al;
|
||||
}
|
||||
|
||||
/* Since GnuLib's select() (i.e. rpl_select()) cannot handle socket-numbers
|
||||
* returned from C-ares, we must use the original select() from Winsock.
|
||||
*/
|
||||
#ifdef WINDOWS
|
||||
#undef select
|
||||
#endif
|
||||
|
||||
static void
|
||||
wait_ares (ares_channel channel)
|
||||
{
|
||||
struct ptimer *timer = NULL;
|
||||
|
||||
if (opt.dns_timeout)
|
||||
timer = ptimer_new ();
|
||||
|
||||
for (;;)
|
||||
{
|
||||
struct timeval *tvp, tv;
|
||||
fd_set read_fds, write_fds;
|
||||
int nfds, rc;
|
||||
|
||||
FD_ZERO (&read_fds);
|
||||
FD_ZERO (&write_fds);
|
||||
nfds = ares_fds (channel, &read_fds, &write_fds);
|
||||
if (nfds == 0)
|
||||
break;
|
||||
|
||||
if (timer)
|
||||
{
|
||||
double max = opt.dns_timeout - ptimer_measure (timer);
|
||||
|
||||
tv.tv_sec = (long) max;
|
||||
tv.tv_usec = 1000000 * (max - (long) max);
|
||||
tvp = ares_timeout (channel, &tv, &tv);
|
||||
}
|
||||
else
|
||||
tvp = ares_timeout (channel, NULL, &tv);
|
||||
|
||||
rc = select (nfds, &read_fds, &write_fds, NULL, tvp);
|
||||
if (rc == 0 && timer && ptimer_measure (timer) >= opt.dns_timeout)
|
||||
ares_cancel (channel);
|
||||
else
|
||||
ares_process (channel, &read_fds, &write_fds);
|
||||
}
|
||||
}
|
||||
|
||||
static void
|
||||
callback (void *arg, int status, int timeouts _GL_UNUSED, struct hostent *host)
|
||||
{
|
||||
struct address_list **al = (struct address_list **) arg;
|
||||
|
||||
if (!host || status != ARES_SUCCESS)
|
||||
{
|
||||
*al = NULL;
|
||||
return;
|
||||
}
|
||||
|
||||
*al = address_list_from_hostent (host);
|
||||
}
|
||||
#endif
|
||||
|
||||
/* Look up HOST in DNS and return a list of IP addresses.
|
||||
|
||||
This function caches its result so that, if the same host is passed
|
||||
@@ -745,7 +850,7 @@ lookup_host (const char *host, int flags)
|
||||
str = xmalloc (len);
|
||||
snprintf (str, len, "%s (%s)", name, host);
|
||||
str[len-1] = '\0';
|
||||
idn_free (name);
|
||||
idn2_free (name);
|
||||
}
|
||||
|
||||
logprintf (LOG_VERBOSE, _("Resolving %s... "),
|
||||
@@ -755,80 +860,112 @@ lookup_host (const char *host, int flags)
|
||||
}
|
||||
|
||||
#ifdef ENABLE_IPV6
|
||||
{
|
||||
int err;
|
||||
struct addrinfo hints, *res;
|
||||
#ifdef HAVE_LIBCARES
|
||||
if (ares)
|
||||
{
|
||||
struct address_list *al4;
|
||||
struct address_list *al6;
|
||||
|
||||
xzero (hints);
|
||||
hints.ai_socktype = SOCK_STREAM;
|
||||
if (opt.ipv4_only)
|
||||
hints.ai_family = AF_INET;
|
||||
else if (opt.ipv6_only)
|
||||
hints.ai_family = AF_INET6;
|
||||
else
|
||||
/* We tried using AI_ADDRCONFIG, but removed it because: it
|
||||
misinterprets IPv6 loopbacks, it is broken on AIX 5.1, and
|
||||
it's unneeded since we sort the addresses anyway. */
|
||||
if (opt.ipv4_only || !opt.ipv6_only)
|
||||
ares_gethostbyname (ares, host, AF_INET, callback, &al4);
|
||||
if (opt.ipv6_only || !opt.ipv4_only)
|
||||
ares_gethostbyname (ares, host, AF_INET6, callback, &al6);
|
||||
|
||||
wait_ares (ares);
|
||||
|
||||
if (al4 && al6)
|
||||
al = merge_address_lists (al4, al6);
|
||||
else if (al4)
|
||||
al = al4;
|
||||
else
|
||||
al = al6;
|
||||
}
|
||||
else
|
||||
#endif
|
||||
{
|
||||
int err;
|
||||
struct addrinfo hints, *res;
|
||||
|
||||
xzero (hints);
|
||||
hints.ai_socktype = SOCK_STREAM;
|
||||
if (opt.ipv4_only)
|
||||
hints.ai_family = AF_INET;
|
||||
else if (opt.ipv6_only)
|
||||
hints.ai_family = AF_INET6;
|
||||
else
|
||||
/* We tried using AI_ADDRCONFIG, but removed it because: it
|
||||
misinterprets IPv6 loopbacks, it is broken on AIX 5.1, and
|
||||
it's unneeded since we sort the addresses anyway. */
|
||||
hints.ai_family = AF_UNSPEC;
|
||||
|
||||
if (flags & LH_BIND)
|
||||
hints.ai_flags |= AI_PASSIVE;
|
||||
if (flags & LH_BIND)
|
||||
hints.ai_flags |= AI_PASSIVE;
|
||||
|
||||
#ifdef AI_NUMERICHOST
|
||||
if (numeric_address)
|
||||
{
|
||||
/* Where available, the AI_NUMERICHOST hint can prevent costly
|
||||
access to DNS servers. */
|
||||
hints.ai_flags |= AI_NUMERICHOST;
|
||||
timeout = 0; /* no timeout needed when "resolving"
|
||||
if (numeric_address)
|
||||
{
|
||||
/* Where available, the AI_NUMERICHOST hint can prevent costly
|
||||
access to DNS servers. */
|
||||
hints.ai_flags |= AI_NUMERICHOST;
|
||||
timeout = 0; /* no timeout needed when "resolving"
|
||||
numeric hosts -- avoid setting up
|
||||
signal handlers and such. */
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
err = getaddrinfo_with_timeout (host, NULL, &hints, &res, timeout);
|
||||
if (err != 0 || res == NULL)
|
||||
{
|
||||
if (!silent)
|
||||
logprintf (LOG_VERBOSE, _("failed: %s.\n"),
|
||||
err != EAI_SYSTEM ? gai_strerror (err) : strerror (errno));
|
||||
return NULL;
|
||||
}
|
||||
al = address_list_from_addrinfo (res);
|
||||
freeaddrinfo (res);
|
||||
if (!al)
|
||||
{
|
||||
logprintf (LOG_VERBOSE,
|
||||
_("failed: No IPv4/IPv6 addresses for host.\n"));
|
||||
return NULL;
|
||||
}
|
||||
err = getaddrinfo_with_timeout (host, NULL, &hints, &res, timeout);
|
||||
|
||||
/* Reorder addresses so that IPv4 ones (or IPv6 ones, as per
|
||||
--prefer-family) come first. Sorting is stable so the order of
|
||||
the addresses with the same family is undisturbed. */
|
||||
if (al->count > 1 && opt.prefer_family != prefer_none)
|
||||
stable_sort (al->addresses, al->count, sizeof (ip_address),
|
||||
opt.prefer_family == prefer_ipv4
|
||||
? cmp_prefer_ipv4 : cmp_prefer_ipv6);
|
||||
}
|
||||
if (err != 0 || res == NULL)
|
||||
{
|
||||
if (!silent)
|
||||
logprintf (LOG_VERBOSE, _ ("failed: %s.\n"),
|
||||
err != EAI_SYSTEM ? gai_strerror (err) : strerror (errno));
|
||||
return NULL;
|
||||
}
|
||||
al = address_list_from_addrinfo (res);
|
||||
freeaddrinfo (res);
|
||||
}
|
||||
|
||||
if (!al)
|
||||
{
|
||||
logprintf (LOG_VERBOSE,
|
||||
_ ("failed: No IPv4/IPv6 addresses for host.\n"));
|
||||
return NULL;
|
||||
}
|
||||
|
||||
/* Reorder addresses so that IPv4 ones (or IPv6 ones, as per
|
||||
--prefer-family) come first. Sorting is stable so the order of
|
||||
the addresses with the same family is undisturbed. */
|
||||
if (al->count > 1 && opt.prefer_family != prefer_none)
|
||||
stable_sort (al->addresses, al->count, sizeof (ip_address),
|
||||
opt.prefer_family == prefer_ipv4
|
||||
? cmp_prefer_ipv4 : cmp_prefer_ipv6);
|
||||
#else /* not ENABLE_IPV6 */
|
||||
{
|
||||
struct hostent *hptr = gethostbyname_with_timeout (host, timeout);
|
||||
if (!hptr)
|
||||
{
|
||||
if (!silent)
|
||||
{
|
||||
if (errno != ETIMEDOUT)
|
||||
logprintf (LOG_VERBOSE, _("failed: %s.\n"),
|
||||
host_errstr (h_errno));
|
||||
else
|
||||
logputs (LOG_VERBOSE, _("failed: timed out.\n"));
|
||||
}
|
||||
return NULL;
|
||||
}
|
||||
/* Do older systems have h_addr_list? */
|
||||
al = address_list_from_ipv4_addresses (hptr->h_addr_list);
|
||||
}
|
||||
#ifdef HAVE_LIBCARES
|
||||
if (ares)
|
||||
{
|
||||
ares_gethostbyname (ares, host, AF_INET, callback, &al);
|
||||
wait_ares (ares);
|
||||
}
|
||||
else
|
||||
#endif
|
||||
{
|
||||
struct hostent *hptr = gethostbyname_with_timeout (host, timeout);
|
||||
if (!hptr)
|
||||
{
|
||||
if (!silent)
|
||||
{
|
||||
if (errno != ETIMEDOUT)
|
||||
logprintf (LOG_VERBOSE, _ ("failed: %s.\n"),
|
||||
host_errstr (h_errno));
|
||||
else
|
||||
logputs (LOG_VERBOSE, _ ("failed: timed out.\n"));
|
||||
}
|
||||
return NULL;
|
||||
}
|
||||
/* Do older systems have h_addr_list? */
|
||||
al = address_list_from_ipv4_addresses (hptr->h_addr_list);
|
||||
}
|
||||
#endif /* not ENABLE_IPV6 */
|
||||
|
||||
/* Print the addresses determined by DNS lookup, but no more than
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/* Declarations for host.c
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
828
src/hsts.c
Normal file
828
src/hsts.c
Normal file
@@ -0,0 +1,828 @@
|
||||
/* HTTP Strict Transport Security (HSTS) support.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
GNU Wget is free software; you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation; either version 3 of the License, or
|
||||
(at your option) any later version.
|
||||
|
||||
GNU Wget is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with Wget. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
Additional permission under GNU GPL version 3 section 7
|
||||
|
||||
If you modify this program, or any covered work, by linking or
|
||||
combining it with the OpenSSL project's OpenSSL library (or a
|
||||
modified version of that library), containing parts covered by the
|
||||
terms of the OpenSSL or SSLeay licenses, the Free Software Foundation
|
||||
grants you additional permission to convey the resulting work.
|
||||
Corresponding Source for a non-source form of such a combination
|
||||
shall include the source code for the parts of OpenSSL used as well
|
||||
as that of the covered work. */
|
||||
#include "wget.h"
|
||||
|
||||
#ifdef HAVE_HSTS
|
||||
#include "hsts.h"
|
||||
#include "host.h" /* for is_valid_ip_address() */
|
||||
#include "init.h" /* for home_dir() */
|
||||
#include "utils.h"
|
||||
#include "hash.h"
|
||||
#include "c-ctype.h"
|
||||
#ifdef TESTING
|
||||
#include "test.h"
|
||||
#endif
|
||||
|
||||
#include <unistd.h>
|
||||
#include <sys/types.h>
|
||||
#include <stdlib.h>
|
||||
#include <time.h>
|
||||
#include <sys/stat.h>
|
||||
#include <string.h>
|
||||
#include <stdio.h>
|
||||
#include <sys/file.h>
|
||||
|
||||
struct hsts_store {
|
||||
struct hash_table *table;
|
||||
time_t last_mtime;
|
||||
bool changed;
|
||||
};
|
||||
|
||||
struct hsts_kh {
|
||||
char *host;
|
||||
int explicit_port;
|
||||
};
|
||||
|
||||
struct hsts_kh_info {
|
||||
time_t created;
|
||||
time_t max_age;
|
||||
bool include_subdomains;
|
||||
};
|
||||
|
||||
enum hsts_kh_match {
|
||||
NO_MATCH,
|
||||
SUPERDOMAIN_MATCH,
|
||||
CONGRUENT_MATCH
|
||||
};
|
||||
|
||||
#define hsts_is_host_name_valid(host) (!is_valid_ip_address (host))
|
||||
#define hsts_is_scheme_valid(scheme) (scheme == SCHEME_HTTPS)
|
||||
#define hsts_is_host_eligible(scheme, host) \
|
||||
(hsts_is_scheme_valid (scheme) && hsts_is_host_name_valid (host))
|
||||
|
||||
#define DEFAULT_HTTP_PORT 80
|
||||
#define DEFAULT_SSL_PORT 443
|
||||
#define MAKE_EXPLICIT_PORT(s, p) (s == SCHEME_HTTPS ? (p == DEFAULT_SSL_PORT ? 0 : p) \
|
||||
: (p == DEFAULT_HTTP_PORT ? 0 : p))
|
||||
|
||||
/* Hashing and comparison functions for the hash table */
|
||||
|
||||
static unsigned long
|
||||
hsts_hash_func (const void *key)
|
||||
{
|
||||
struct hsts_kh *k = (struct hsts_kh *) key;
|
||||
const char *h = NULL;
|
||||
unsigned int hash = k->explicit_port;
|
||||
|
||||
for (h = k->host; *h; h++)
|
||||
hash = hash * 31 + *h;
|
||||
|
||||
return hash;
|
||||
}
|
||||
|
||||
static int
|
||||
hsts_cmp_func (const void *h1, const void *h2)
|
||||
{
|
||||
struct hsts_kh *kh1 = (struct hsts_kh *) h1,
|
||||
*kh2 = (struct hsts_kh *) h2;
|
||||
|
||||
return (!strcmp (kh1->host, kh2->host)) && (kh1->explicit_port == kh2->explicit_port);
|
||||
}
|
||||
|
||||
/* Private functions. Feel free to make some of these public when needed. */
|
||||
|
||||
static struct hsts_kh_info *
|
||||
hsts_find_entry (hsts_store_t store,
|
||||
const char *host, int explicit_port,
|
||||
enum hsts_kh_match *match_type,
|
||||
struct hsts_kh *kh)
|
||||
{
|
||||
struct hsts_kh *k = NULL;
|
||||
struct hsts_kh_info *khi = NULL;
|
||||
enum hsts_kh_match match = NO_MATCH;
|
||||
char *pos = NULL;
|
||||
char *org_ptr = NULL;
|
||||
|
||||
k = (struct hsts_kh *) xnew (struct hsts_kh);
|
||||
k->host = xstrdup_lower (host);
|
||||
k->explicit_port = explicit_port;
|
||||
|
||||
/* save pointer so that we don't get into trouble later when freeing */
|
||||
org_ptr = k->host;
|
||||
|
||||
khi = (struct hsts_kh_info *) hash_table_get (store->table, k);
|
||||
if (khi)
|
||||
{
|
||||
match = CONGRUENT_MATCH;
|
||||
goto end;
|
||||
}
|
||||
|
||||
while (match == NO_MATCH &&
|
||||
(pos = strchr (k->host, '.')) && pos - k->host > 0 &&
|
||||
strchr (pos + 1, '.'))
|
||||
{
|
||||
k->host += (pos - k->host + 1);
|
||||
khi = (struct hsts_kh_info *) hash_table_get (store->table, k);
|
||||
if (khi)
|
||||
match = SUPERDOMAIN_MATCH;
|
||||
}
|
||||
|
||||
end:
|
||||
/* restore pointer or we'll get a SEGV */
|
||||
k->host = org_ptr;
|
||||
|
||||
/* copy parameters to previous frame */
|
||||
if (match_type)
|
||||
*match_type = match;
|
||||
if (kh)
|
||||
memcpy (kh, k, sizeof (struct hsts_kh));
|
||||
else
|
||||
xfree (k->host);
|
||||
|
||||
xfree (k);
|
||||
return khi;
|
||||
}
|
||||
|
||||
static bool
|
||||
hsts_new_entry_internal (hsts_store_t store,
|
||||
const char *host, int port,
|
||||
time_t created, time_t max_age,
|
||||
bool include_subdomains,
|
||||
bool check_validity,
|
||||
bool check_expired,
|
||||
bool check_duplicates)
|
||||
{
|
||||
struct hsts_kh *kh = xnew (struct hsts_kh);
|
||||
struct hsts_kh_info *khi = xnew0 (struct hsts_kh_info);
|
||||
bool success = false;
|
||||
|
||||
kh->host = xstrdup_lower (host);
|
||||
kh->explicit_port = MAKE_EXPLICIT_PORT (SCHEME_HTTPS, port);
|
||||
|
||||
khi->created = created;
|
||||
khi->max_age = max_age;
|
||||
khi->include_subdomains = include_subdomains;
|
||||
|
||||
/* Check validity */
|
||||
if (check_validity && !hsts_is_host_name_valid (host))
|
||||
goto bail;
|
||||
|
||||
if (check_expired && ((khi->created + khi->max_age) < khi->created))
|
||||
goto bail;
|
||||
|
||||
if (check_duplicates && hash_table_contains (store->table, kh))
|
||||
goto bail;
|
||||
|
||||
/* Now store the new entry */
|
||||
hash_table_put (store->table, kh, khi);
|
||||
success = true;
|
||||
|
||||
bail:
|
||||
if (!success)
|
||||
{
|
||||
/* abort! */
|
||||
xfree (kh->host);
|
||||
xfree (kh);
|
||||
xfree (khi);
|
||||
}
|
||||
|
||||
return success;
|
||||
}
|
||||
|
||||
/*
|
||||
Creates a new entry, but does not check whether that entry already exists.
|
||||
This function assumes that check has already been done by the caller.
|
||||
*/
|
||||
static bool
|
||||
hsts_add_entry (hsts_store_t store,
|
||||
const char *host, int port,
|
||||
time_t max_age, bool include_subdomains)
|
||||
{
|
||||
time_t t = time (NULL);
|
||||
|
||||
/* It might happen time() returned -1 */
|
||||
return (t < 0 ?
|
||||
false :
|
||||
hsts_new_entry_internal (store, host, port, t, max_age, include_subdomains, false, true, false));
|
||||
}
|
||||
|
||||
/* Creates a new entry, unless an identical one already exists. */
|
||||
static bool
|
||||
hsts_new_entry (hsts_store_t store,
|
||||
const char *host, int port,
|
||||
time_t created, time_t max_age,
|
||||
bool include_subdomains)
|
||||
{
|
||||
return hsts_new_entry_internal (store, host, port, created, max_age, include_subdomains, true, true, true);
|
||||
}
|
||||
|
||||
static void
|
||||
hsts_remove_entry (hsts_store_t store, struct hsts_kh *kh)
|
||||
{
|
||||
hash_table_remove (store->table, kh);
|
||||
}
|
||||
|
||||
static bool
|
||||
hsts_store_merge (hsts_store_t store,
|
||||
const char *host, int port,
|
||||
time_t created, time_t max_age,
|
||||
bool include_subdomains)
|
||||
{
|
||||
enum hsts_kh_match match_type = NO_MATCH;
|
||||
struct hsts_kh_info *khi = NULL;
|
||||
bool success = false;
|
||||
|
||||
port = MAKE_EXPLICIT_PORT (SCHEME_HTTPS, port);
|
||||
khi = hsts_find_entry (store, host, port, &match_type, NULL);
|
||||
if (khi && match_type == CONGRUENT_MATCH && created > khi->created)
|
||||
{
|
||||
/* update the entry with the new info */
|
||||
khi->created = created;
|
||||
khi->max_age = max_age;
|
||||
khi->include_subdomains = include_subdomains;
|
||||
|
||||
success = true;
|
||||
}
|
||||
else if (!khi)
|
||||
success = hsts_new_entry (store, host, port, created, max_age, include_subdomains);
|
||||
|
||||
return success;
|
||||
}
|
||||
|
||||
static bool
|
||||
hsts_read_database (hsts_store_t store, FILE *fp, bool merge_with_existing_entries)
|
||||
{
|
||||
char *line = NULL, *p;
|
||||
size_t len = 0;
|
||||
int items_read;
|
||||
bool result = false;
|
||||
bool (*func)(hsts_store_t, const char *, int, time_t, time_t, bool);
|
||||
|
||||
char host[256];
|
||||
int port;
|
||||
time_t created, max_age;
|
||||
int include_subdomains;
|
||||
|
||||
func = (merge_with_existing_entries ? hsts_store_merge : hsts_new_entry);
|
||||
|
||||
while (getline (&line, &len, fp) > 0)
|
||||
{
|
||||
for (p = line; c_isspace (*p); p++)
|
||||
;
|
||||
|
||||
if (*p == '#')
|
||||
continue;
|
||||
|
||||
items_read = sscanf (p, "%255s %d %d %lu %lu",
|
||||
host,
|
||||
&port,
|
||||
&include_subdomains,
|
||||
(unsigned long *) &created,
|
||||
(unsigned long *) &max_age);
|
||||
|
||||
if (items_read == 5)
|
||||
func (store, host, port, created, max_age, !!include_subdomains);
|
||||
}
|
||||
|
||||
xfree (line);
|
||||
result = true;
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
static void
|
||||
hsts_store_dump (hsts_store_t store, FILE *fp)
|
||||
{
|
||||
hash_table_iterator it;
|
||||
|
||||
/* Print preliminary comments. We don't care if any of these fail. */
|
||||
fputs ("# HSTS 1.0 Known Hosts database for GNU Wget.\n", fp);
|
||||
fputs ("# Edit at your own risk.\n", fp);
|
||||
fputs ("# <hostname>\t<port>\t<incl. subdomains>\t<created>\t<max-age>\n", fp);
|
||||
|
||||
/* Now cycle through the HSTS store in memory and dump the entries */
|
||||
for (hash_table_iterate (store->table, &it); hash_table_iter_next (&it);)
|
||||
{
|
||||
struct hsts_kh *kh = (struct hsts_kh *) it.key;
|
||||
struct hsts_kh_info *khi = (struct hsts_kh_info *) it.value;
|
||||
|
||||
if (fprintf (fp, "%s\t%d\t%d\t%lu\t%lu\n",
|
||||
kh->host, kh->explicit_port, khi->include_subdomains,
|
||||
(unsigned long) khi->created,
|
||||
(unsigned long) khi->max_age) < 0)
|
||||
{
|
||||
logprintf (LOG_ALWAYS, "Could not write the HSTS database correctly.\n");
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Test:
|
||||
* - The file is a regular file (ie. not a symlink), and
|
||||
* - The file is not world-writable.
|
||||
*/
|
||||
static bool
|
||||
hsts_file_access_valid (const char *filename)
|
||||
{
|
||||
struct stat st;
|
||||
|
||||
if (stat (filename, &st) == -1)
|
||||
return false;
|
||||
|
||||
return
|
||||
#ifndef WINDOWS
|
||||
/*
|
||||
* The world-writable concept is a Unix-centric notion.
|
||||
* We bypass this test on Windows.
|
||||
*/
|
||||
!(st.st_mode & S_IWOTH) &&
|
||||
#endif
|
||||
S_ISREG (st.st_mode);
|
||||
}
|
||||
|
||||
/* HSTS API */
|
||||
|
||||
/*
|
||||
Changes the given URLs according to the HSTS policy.
|
||||
|
||||
If there's no host in the store that either congruently
|
||||
or not, matches the given URL, no changes are made.
|
||||
Returns true if the URL was changed, or false
|
||||
if it was left intact.
|
||||
*/
|
||||
bool
|
||||
hsts_match (hsts_store_t store, struct url *u)
|
||||
{
|
||||
bool url_changed = false;
|
||||
struct hsts_kh_info *entry = NULL;
|
||||
struct hsts_kh *kh = xnew(struct hsts_kh);
|
||||
enum hsts_kh_match match = NO_MATCH;
|
||||
int port = MAKE_EXPLICIT_PORT (u->scheme, u->port);
|
||||
|
||||
/* avoid doing any computation if we're already in HTTPS */
|
||||
if (!hsts_is_scheme_valid (u->scheme))
|
||||
{
|
||||
entry = hsts_find_entry (store, u->host, port, &match, kh);
|
||||
if (entry)
|
||||
{
|
||||
if ((entry->created + entry->max_age) >= time(NULL))
|
||||
{
|
||||
if ((match == CONGRUENT_MATCH) ||
|
||||
(match == SUPERDOMAIN_MATCH && entry->include_subdomains))
|
||||
{
|
||||
/* we found a matching Known HSTS Host
|
||||
rewrite the URL */
|
||||
u->scheme = SCHEME_HTTPS;
|
||||
if (u->port == 80)
|
||||
u->port = 443;
|
||||
url_changed = true;
|
||||
store->changed = true;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
hsts_remove_entry (store, kh);
|
||||
store->changed = true;
|
||||
}
|
||||
}
|
||||
xfree (kh->host);
|
||||
}
|
||||
|
||||
xfree (kh);
|
||||
|
||||
return url_changed;
|
||||
}
|
||||
|
||||
/*
|
||||
Add a new HSTS Known Host to the HSTS store.
|
||||
|
||||
If the host already exists, its information is updated,
|
||||
or it'll be removed from the store if max_age is zero.
|
||||
|
||||
Bear in mind that the store is kept in memory, and will not
|
||||
be written to disk until hsts_store_save is called.
|
||||
This function regrows the in-memory HSTS store if necessary.
|
||||
|
||||
Currently, for a host to be taken into consideration,
|
||||
two conditions have to be met:
|
||||
- Connection must be through a secure channel (HTTPS).
|
||||
- The host must not be an IPv4 or IPv6 address.
|
||||
|
||||
The RFC 6797 states that hosts that match IPv4 or IPv6 format
|
||||
should be discarded at URI rewrite time. But we short-circuit
|
||||
that check here, since there's no point in storing a host that
|
||||
will never be matched.
|
||||
|
||||
Returns true if a new entry was actually created, or false
|
||||
if an existing entry was updated/deleted. */
|
||||
bool
|
||||
hsts_store_entry (hsts_store_t store,
|
||||
enum url_scheme scheme, const char *host, int port,
|
||||
time_t max_age, bool include_subdomains)
|
||||
{
|
||||
bool result = false;
|
||||
enum hsts_kh_match match = NO_MATCH;
|
||||
struct hsts_kh *kh = xnew(struct hsts_kh);
|
||||
struct hsts_kh_info *entry = NULL;
|
||||
time_t t = 0;
|
||||
|
||||
if (hsts_is_host_eligible (scheme, host))
|
||||
{
|
||||
port = MAKE_EXPLICIT_PORT (scheme, port);
|
||||
entry = hsts_find_entry (store, host, port, &match, kh);
|
||||
if (entry && match == CONGRUENT_MATCH)
|
||||
{
|
||||
if (max_age == 0)
|
||||
{
|
||||
hsts_remove_entry (store, kh);
|
||||
store->changed = true;
|
||||
}
|
||||
else if (max_age > 0)
|
||||
{
|
||||
if (entry->max_age != max_age ||
|
||||
entry->include_subdomains != include_subdomains)
|
||||
{
|
||||
/* RFC 6797 states that 'max_age' is a TTL relative to the reception of the STS header
|
||||
so we have to update the 'created' field too */
|
||||
t = time (NULL);
|
||||
if (t != -1)
|
||||
entry->created = t;
|
||||
entry->max_age = max_age;
|
||||
entry->include_subdomains = include_subdomains;
|
||||
|
||||
store->changed = true;
|
||||
}
|
||||
}
|
||||
/* we ignore negative max_ages */
|
||||
}
|
||||
else if (entry == NULL || match == SUPERDOMAIN_MATCH)
|
||||
{
|
||||
/* Either we didn't find a matching host,
|
||||
or we got a superdomain match.
|
||||
In either case, we create a new entry.
|
||||
|
||||
We have to perform an explicit check because it might
|
||||
happen we got a non-existent entry with max_age == 0.
|
||||
*/
|
||||
result = hsts_add_entry (store, host, port, max_age, include_subdomains);
|
||||
if (result)
|
||||
store->changed = true;
|
||||
}
|
||||
/* we ignore new entries with max_age == 0 */
|
||||
xfree (kh->host);
|
||||
}
|
||||
|
||||
xfree (kh);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
hsts_store_t
|
||||
hsts_store_open (const char *filename)
|
||||
{
|
||||
hsts_store_t store = NULL;
|
||||
|
||||
store = xnew0 (struct hsts_store);
|
||||
store->table = hash_table_new (0, hsts_hash_func, hsts_cmp_func);
|
||||
store->last_mtime = 0;
|
||||
store->changed = false;
|
||||
|
||||
if (file_exists_p (filename))
|
||||
{
|
||||
if (hsts_file_access_valid (filename))
|
||||
{
|
||||
struct stat st;
|
||||
FILE *fp = fopen (filename, "r");
|
||||
|
||||
if (!fp || !hsts_read_database (store, fp, false))
|
||||
{
|
||||
/* abort! */
|
||||
hsts_store_close (store);
|
||||
xfree (store);
|
||||
if (fp)
|
||||
fclose (fp);
|
||||
goto out;
|
||||
}
|
||||
|
||||
if (fstat (fileno (fp), &st) == 0)
|
||||
store->last_mtime = st.st_mtime;
|
||||
|
||||
fclose (fp);
|
||||
}
|
||||
else
|
||||
{
|
||||
/*
|
||||
* If we're not reading the HSTS database,
|
||||
* then by all means act as if HSTS was disabled.
|
||||
*/
|
||||
hsts_store_close (store);
|
||||
xfree (store);
|
||||
|
||||
logprintf (LOG_NOTQUIET, "Will not apply HSTS. "
|
||||
"The HSTS database must be a regular and non-world-writable file.\n");
|
||||
}
|
||||
}
|
||||
|
||||
out:
|
||||
return store;
|
||||
}
|
||||
|
||||
void
|
||||
hsts_store_save (hsts_store_t store, const char *filename)
|
||||
{
|
||||
struct stat st;
|
||||
FILE *fp = NULL;
|
||||
int fd = 0;
|
||||
|
||||
if (filename && hash_table_count (store->table) > 0)
|
||||
{
|
||||
fp = fopen (filename, "a+");
|
||||
if (fp)
|
||||
{
|
||||
/* Lock the file to avoid potential race conditions */
|
||||
fd = fileno (fp);
|
||||
flock (fd, LOCK_EX);
|
||||
|
||||
/* If the file has changed, merge the changes with our in-memory data
|
||||
before dumping them to the file.
|
||||
Otherwise we could potentially overwrite the data stored by other Wget processes.
|
||||
*/
|
||||
if (store->last_mtime && stat (filename, &st) == 0 && st.st_mtime > store->last_mtime)
|
||||
hsts_read_database (store, fp, true);
|
||||
|
||||
/* We've merged the latest changes so we can now truncate the file
|
||||
and dump everything. */
|
||||
fseek (fp, 0, SEEK_SET);
|
||||
ftruncate (fd, 0);
|
||||
|
||||
/* now dump to the file */
|
||||
hsts_store_dump (store, fp);
|
||||
|
||||
/* fclose is expected to unlock the file for us */
|
||||
fclose (fp);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
bool
|
||||
hsts_store_has_changed (hsts_store_t store)
|
||||
{
|
||||
return (store ? store->changed : false);
|
||||
}
|
||||
|
||||
void
|
||||
hsts_store_close (hsts_store_t store)
|
||||
{
|
||||
hash_table_iterator it;
|
||||
|
||||
/* free all the host fields */
|
||||
for (hash_table_iterate (store->table, &it); hash_table_iter_next (&it);)
|
||||
{
|
||||
xfree (((struct hsts_kh *) it.key)->host);
|
||||
xfree (it.key);
|
||||
xfree (it.value);
|
||||
}
|
||||
|
||||
hash_table_destroy (store->table);
|
||||
}
|
||||
|
||||
#ifdef TESTING
|
||||
/* I know I'm really evil because I'm writing macros
|
||||
that change control flow. But we're testing, who will tell? :D
|
||||
*/
|
||||
#define TEST_URL_RW(s, u, p) do { \
|
||||
if (test_url_rewrite (s, u, p, true)) \
|
||||
return test_url_rewrite (s, u, p, true); \
|
||||
} while (0)
|
||||
|
||||
#define TEST_URL_NORW(s, u, p) do { \
|
||||
if (test_url_rewrite (s, u, p, false)) \
|
||||
return test_url_rewrite (s, u, p, false); \
|
||||
} while (0)
|
||||
|
||||
static char *
|
||||
get_hsts_store_filename (void)
|
||||
{
|
||||
char *home = NULL, *filename = NULL;
|
||||
FILE *fp = NULL;
|
||||
|
||||
home = home_dir ();
|
||||
if (home)
|
||||
{
|
||||
filename = aprintf ("%s/.wget-hsts-test", home);
|
||||
fp = fopen (filename, "w");
|
||||
if (fp)
|
||||
fclose (fp);
|
||||
}
|
||||
|
||||
xfree (home);
|
||||
return filename;
|
||||
}
|
||||
|
||||
static hsts_store_t
|
||||
open_hsts_test_store (void)
|
||||
{
|
||||
char *filename = NULL;
|
||||
hsts_store_t table = NULL;
|
||||
|
||||
filename = get_hsts_store_filename ();
|
||||
table = hsts_store_open (filename);
|
||||
xfree (filename);
|
||||
|
||||
return table;
|
||||
}
|
||||
|
||||
static void
|
||||
close_hsts_test_store (hsts_store_t store)
|
||||
{
|
||||
char *filename = NULL;
|
||||
|
||||
filename = get_hsts_store_filename ();
|
||||
unlink (filename);
|
||||
xfree (filename);
|
||||
xfree (store);
|
||||
}
|
||||
|
||||
static const char*
|
||||
test_url_rewrite (hsts_store_t s, const char *url, int port, bool rewrite)
|
||||
{
|
||||
bool result;
|
||||
struct url u;
|
||||
|
||||
u.host = xstrdup (url);
|
||||
u.port = port;
|
||||
u.scheme = SCHEME_HTTP;
|
||||
|
||||
result = hsts_match (s, &u);
|
||||
|
||||
if (rewrite)
|
||||
{
|
||||
if (port == 80)
|
||||
mu_assert("URL: port should've been rewritten to 443", u.port == 443);
|
||||
else
|
||||
mu_assert("URL: port should've been left intact", u.port == port);
|
||||
mu_assert("URL: scheme should've been rewritten to HTTPS", u.scheme == SCHEME_HTTPS);
|
||||
mu_assert("result should've been true", result == true);
|
||||
}
|
||||
else
|
||||
{
|
||||
mu_assert("URL: port should've been left intact", u.port == port);
|
||||
mu_assert("URL: scheme should've been left intact", u.scheme == SCHEME_HTTP);
|
||||
mu_assert("result should've been false", result == false);
|
||||
}
|
||||
|
||||
xfree (u.host);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
const char *
|
||||
test_hsts_new_entry (void)
|
||||
{
|
||||
enum hsts_kh_match match = NO_MATCH;
|
||||
struct hsts_kh_info *khi;
|
||||
hsts_store_t s;
|
||||
bool created;
|
||||
|
||||
s = open_hsts_test_store ();
|
||||
mu_assert("Could not open the HSTS store. This could be due to lack of memory.", s != NULL);
|
||||
|
||||
created = hsts_store_entry (s, SCHEME_HTTP, "www.foo.com", 80, 1234, true);
|
||||
mu_assert("No entry should have been created.", created == false);
|
||||
|
||||
created = hsts_store_entry (s, SCHEME_HTTPS, "www.foo.com", 443, 1234, true);
|
||||
mu_assert("A new entry should have been created", created == true);
|
||||
|
||||
khi = hsts_find_entry (s, "www.foo.com", MAKE_EXPLICIT_PORT (SCHEME_HTTPS, 443), &match, NULL);
|
||||
mu_assert("Should've been a congruent match", match == CONGRUENT_MATCH);
|
||||
mu_assert("No valid HSTS info was returned", khi != NULL);
|
||||
mu_assert("Variable 'max_age' should be 1234", khi->max_age == 1234);
|
||||
mu_assert("Variable 'include_subdomains' should be asserted", khi->include_subdomains == true);
|
||||
|
||||
khi = hsts_find_entry (s, "b.www.foo.com", MAKE_EXPLICIT_PORT (SCHEME_HTTPS, 443), &match, NULL);
|
||||
mu_assert("Should've been a superdomain match", match == SUPERDOMAIN_MATCH);
|
||||
mu_assert("No valid HSTS info was returned", khi != NULL);
|
||||
mu_assert("Variable 'max_age' should be 1234", khi->max_age == 1234);
|
||||
mu_assert("Variable 'include_subdomains' should be asserted", khi->include_subdomains == true);
|
||||
|
||||
khi = hsts_find_entry (s, "ww.foo.com", MAKE_EXPLICIT_PORT (SCHEME_HTTPS, 443), &match, NULL);
|
||||
mu_assert("Should've been no match", match == NO_MATCH);
|
||||
|
||||
khi = hsts_find_entry (s, "foo.com", MAKE_EXPLICIT_PORT (SCHEME_HTTPS, 443), &match, NULL);
|
||||
mu_assert("Should've been no match", match == NO_MATCH);
|
||||
|
||||
khi = hsts_find_entry (s, ".foo.com", MAKE_EXPLICIT_PORT (SCHEME_HTTPS, 443), &match, NULL);
|
||||
mu_assert("Should've been no match", match == NO_MATCH);
|
||||
|
||||
khi = hsts_find_entry (s, ".www.foo.com", MAKE_EXPLICIT_PORT (SCHEME_HTTPS, 443), &match, NULL);
|
||||
mu_assert("Should've been no match", match == NO_MATCH);
|
||||
|
||||
hsts_store_close (s);
|
||||
close_hsts_test_store (s);
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
const char*
|
||||
test_hsts_url_rewrite_superdomain (void)
|
||||
{
|
||||
hsts_store_t s;
|
||||
bool created;
|
||||
|
||||
s = open_hsts_test_store ();
|
||||
mu_assert("Could not open the HSTS store", s != NULL);
|
||||
|
||||
created = hsts_store_entry (s, SCHEME_HTTPS, "www.foo.com", 443, 1234, true);
|
||||
mu_assert("A new entry should've been created", created == true);
|
||||
|
||||
TEST_URL_RW (s, "www.foo.com", 80);
|
||||
TEST_URL_RW (s, "bar.www.foo.com", 80);
|
||||
|
||||
hsts_store_close (s);
|
||||
close_hsts_test_store (s);
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
const char*
|
||||
test_hsts_url_rewrite_congruent (void)
|
||||
{
|
||||
hsts_store_t s;
|
||||
bool created;
|
||||
|
||||
s = open_hsts_test_store ();
|
||||
mu_assert("Could not open the HSTS store", s != NULL);
|
||||
|
||||
created = hsts_store_entry (s, SCHEME_HTTPS, "foo.com", 443, 1234, false);
|
||||
mu_assert("A new entry should've been created", created == true);
|
||||
|
||||
TEST_URL_RW (s, "foo.com", 80);
|
||||
TEST_URL_NORW (s, "www.foo.com", 80);
|
||||
|
||||
hsts_store_close (s);
|
||||
close_hsts_test_store (s);
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
const char*
|
||||
test_hsts_read_database (void)
|
||||
{
|
||||
hsts_store_t table;
|
||||
char *home = home_dir();
|
||||
char *file = NULL;
|
||||
FILE *fp = NULL;
|
||||
time_t created = time(NULL) - 10;
|
||||
|
||||
if (home)
|
||||
{
|
||||
file = aprintf ("%s/.wget-hsts-testing", home);
|
||||
fp = fopen (file, "w");
|
||||
if (fp)
|
||||
{
|
||||
fputs ("# dummy comment\n", fp);
|
||||
fprintf (fp, "foo.example.com\t0\t1\t%lu\t123\n",(unsigned long) created);
|
||||
fprintf (fp, "bar.example.com\t0\t0\t%lu\t456\n", (unsigned long) created);
|
||||
fprintf (fp, "test.example.com\t8080\t0\t%lu\t789\n", (unsigned long) created);
|
||||
fclose (fp);
|
||||
|
||||
table = hsts_store_open (file);
|
||||
|
||||
TEST_URL_RW (table, "foo.example.com", 80);
|
||||
TEST_URL_RW (table, "www.foo.example.com", 80);
|
||||
TEST_URL_RW (table, "bar.example.com", 80);
|
||||
|
||||
TEST_URL_NORW(table, "www.bar.example.com", 80);
|
||||
|
||||
TEST_URL_RW (table, "test.example.com", 8080);
|
||||
|
||||
hsts_store_close (table);
|
||||
close_hsts_test_store (table);
|
||||
unlink (file);
|
||||
}
|
||||
xfree (file);
|
||||
xfree (home);
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
#endif /* TESTING */
|
||||
#endif /* HAVE_HSTS */
|
||||
54
src/hsts.h
Normal file
54
src/hsts.h
Normal file
@@ -0,0 +1,54 @@
|
||||
/* Declarations for hsts.c
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
GNU Wget is free software; you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation; either version 3 of the License, or
|
||||
(at your option) any later version.
|
||||
|
||||
GNU Wget is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with Wget. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
Additional permission under GNU GPL version 3 section 7
|
||||
|
||||
If you modify this program, or any covered work, by linking or
|
||||
combining it with the OpenSSL project's OpenSSL library (or a
|
||||
modified version of that library), containing parts covered by the
|
||||
terms of the OpenSSL or SSLeay licenses, the Free Software Foundation
|
||||
grants you additional permission to convey the resulting work.
|
||||
Corresponding Source for a non-source form of such a combination
|
||||
shall include the source code for the parts of OpenSSL used as well
|
||||
as that of the covered work. */
|
||||
#include "wget.h"
|
||||
|
||||
#ifdef HAVE_HSTS
|
||||
|
||||
#ifndef HSTS_H
|
||||
#define HSTS_H
|
||||
|
||||
#include "url.h"
|
||||
|
||||
typedef struct hsts_store *hsts_store_t;
|
||||
|
||||
hsts_store_t hsts_store_open (const char *);
|
||||
|
||||
void hsts_store_save (hsts_store_t, const char *);
|
||||
void hsts_store_close (hsts_store_t);
|
||||
bool hsts_store_has_changed (hsts_store_t);
|
||||
|
||||
bool hsts_store_entry (hsts_store_t,
|
||||
enum url_scheme, const char *, int,
|
||||
time_t, bool);
|
||||
bool hsts_match (hsts_store_t, struct url *);
|
||||
|
||||
#endif /* HSTS_H */
|
||||
#endif /* HAVE_HSTS */
|
||||
@@ -1,6 +1,6 @@
|
||||
/* HTML parser for Wget.
|
||||
Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
|
||||
2007, 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
2007, 2008, 2009, 2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -801,14 +801,6 @@ name_allowed (const struct hash_table *ht, const char *b, const char *e)
|
||||
} \
|
||||
} while (0)
|
||||
|
||||
/* Skip non-whitespace, if any. */
|
||||
|
||||
#define SKIP_NON_WS(p) do { \
|
||||
while (!c_isspace (*p)) { \
|
||||
ADVANCE (p); \
|
||||
} \
|
||||
} while (0)
|
||||
|
||||
#ifdef STANDALONE
|
||||
static int tag_backout_count;
|
||||
#endif
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Declarations for html-parse.c.
|
||||
Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
|
||||
2007, 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
2007, 2008, 2009, 2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
100
src/html-url.c
100
src/html-url.c
@@ -1,6 +1,7 @@
|
||||
/* Collect URLs from HTML source.
|
||||
Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
|
||||
2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
|
||||
2007, 2008, 2009, 2010, 2011, 2012, 2015 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -55,6 +56,7 @@ typedef void (*tag_handler_t) (int, struct taginfo *, struct map_context *);
|
||||
DECLARE_TAG_HANDLER (tag_find_urls);
|
||||
DECLARE_TAG_HANDLER (tag_handle_base);
|
||||
DECLARE_TAG_HANDLER (tag_handle_form);
|
||||
DECLARE_TAG_HANDLER (tag_handle_img);
|
||||
DECLARE_TAG_HANDLER (tag_handle_link);
|
||||
DECLARE_TAG_HANDLER (tag_handle_meta);
|
||||
|
||||
@@ -104,7 +106,7 @@ static struct known_tag {
|
||||
{ TAG_FORM, "form", tag_handle_form },
|
||||
{ TAG_FRAME, "frame", tag_find_urls },
|
||||
{ TAG_IFRAME, "iframe", tag_find_urls },
|
||||
{ TAG_IMG, "img", tag_find_urls },
|
||||
{ TAG_IMG, "img", tag_handle_img },
|
||||
{ TAG_INPUT, "input", tag_find_urls },
|
||||
{ TAG_LAYER, "layer", tag_find_urls },
|
||||
{ TAG_LINK, "link", tag_handle_link },
|
||||
@@ -182,7 +184,8 @@ static const char *additional_attributes[] = {
|
||||
"name", /* used by tag_handle_meta */
|
||||
"content", /* used by tag_handle_meta */
|
||||
"action", /* used by tag_handle_form */
|
||||
"style" /* used by check_style_attr */
|
||||
"style", /* used by check_style_attr */
|
||||
"srcset", /* used by tag_handle_img */
|
||||
};
|
||||
|
||||
static struct hash_table *interesting_tags;
|
||||
@@ -303,6 +306,7 @@ append_url (const char *link_uri, int position, int size,
|
||||
logprintf (LOG_NOTQUIET,
|
||||
_("%s: Cannot resolve incomplete link %s.\n"),
|
||||
ctx->document_file, link_uri);
|
||||
iri_free (iri);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
@@ -311,6 +315,7 @@ append_url (const char *link_uri, int position, int size,
|
||||
{
|
||||
DEBUGP (("%s: link \"%s\" doesn't parse.\n",
|
||||
ctx->document_file, link_uri));
|
||||
iri_free (iri);
|
||||
return NULL;
|
||||
}
|
||||
}
|
||||
@@ -334,6 +339,7 @@ append_url (const char *link_uri, int position, int size,
|
||||
DEBUGP (("%s: merged link \"%s\" doesn't parse.\n",
|
||||
ctx->document_file, complete_uri));
|
||||
xfree (complete_uri);
|
||||
iri_free (iri);
|
||||
return NULL;
|
||||
}
|
||||
xfree (complete_uri);
|
||||
@@ -670,6 +676,91 @@ tag_handle_meta (int tagid _GL_UNUSED, struct taginfo *tag, struct map_context *
|
||||
}
|
||||
}
|
||||
|
||||
/* Handle the IMG tag. This requires special handling for the srcset attr,
|
||||
while the traditional src/lowsrc/href attributes can be handled generically.
|
||||
*/
|
||||
|
||||
static void
|
||||
tag_handle_img (int tagid, struct taginfo *tag, struct map_context *ctx) {
|
||||
int attrind;
|
||||
char *srcset;
|
||||
|
||||
/* Use the generic approach for the attributes without special syntax. */
|
||||
tag_find_urls(tagid, tag, ctx);
|
||||
|
||||
srcset = find_attr (tag, "srcset", &attrind);
|
||||
if (srcset)
|
||||
{
|
||||
/* These are relative to the input text. */
|
||||
int base_ind = ATTR_POS (tag,attrind,ctx);
|
||||
int size = strlen (srcset);
|
||||
|
||||
/* These are relative to srcset. */
|
||||
int offset, url_start, url_end;
|
||||
|
||||
/* Make sure to line up base_ind with srcset[0], not outside quotes. */
|
||||
if (ctx->text[base_ind] == '"' || ctx->text[base_ind] == '\'')
|
||||
++base_ind;
|
||||
|
||||
offset = 0;
|
||||
while (offset < size)
|
||||
{
|
||||
bool has_descriptor = true;
|
||||
|
||||
/* Skip over initial whitespace and commas. Note there is no \v
|
||||
in HTML5 whitespace. */
|
||||
url_start = offset + strspn (srcset + offset, " \f\n\r\t,");
|
||||
|
||||
if (url_start == size)
|
||||
return;
|
||||
|
||||
/* URL is any non-whitespace chars (including commas) - but with
|
||||
trailing commas removed. */
|
||||
url_end = url_start + strcspn (srcset + url_start, " \f\n\r\t");
|
||||
while ((url_end - 1) > url_start && srcset[url_end - 1] == ',')
|
||||
{
|
||||
has_descriptor = false;
|
||||
--url_end;
|
||||
}
|
||||
|
||||
if (url_end > url_start)
|
||||
{
|
||||
char *url_text = strdupdelim (srcset + url_start,
|
||||
srcset + url_end);
|
||||
struct urlpos *up = append_url (url_text, base_ind + url_start,
|
||||
url_end - url_start, ctx);
|
||||
if (up)
|
||||
{
|
||||
up->link_inline_p = 1;
|
||||
up->link_noquote_html_p = 1;
|
||||
}
|
||||
xfree (url_text);
|
||||
}
|
||||
|
||||
/* If the URL wasn't terminated by a , there may also be a descriptor
|
||||
which we just skip. */
|
||||
if (has_descriptor)
|
||||
{
|
||||
/* This is comma-terminated, except there may be one level of
|
||||
parentheses escaping that. */
|
||||
bool in_paren = false;
|
||||
for (offset = url_end; offset < size; ++offset)
|
||||
{
|
||||
char c = srcset[offset];
|
||||
if (c == '(')
|
||||
in_paren = true;
|
||||
else if (c == ')' && in_paren)
|
||||
in_paren = false;
|
||||
else if (c == ',' && !in_paren)
|
||||
break;
|
||||
}
|
||||
}
|
||||
else
|
||||
offset = url_end;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/* Dispatch the tag handler appropriate for the tag we're mapping
|
||||
over. See known_tags[] for definition of tag handlers. */
|
||||
|
||||
@@ -748,10 +839,13 @@ get_urls_html (const char *file, const char *url, bool *meta_disallow_follow,
|
||||
map_html_tags (fm->content, fm->length, collect_tags_mapper, &ctx, flags,
|
||||
NULL, interesting_attributes);
|
||||
|
||||
#ifdef ENABLE_IRI
|
||||
/* Meta charset is only valid if there was no HTTP header Content-Type charset. */
|
||||
/* This is true for HTTP 1.0 and 1.1. */
|
||||
if (iri && !iri->content_encoding && meta_charset)
|
||||
set_content_encoding (iri, meta_charset);
|
||||
#endif
|
||||
xfree (meta_charset);
|
||||
|
||||
DEBUGP (("no-follow in %s: %d\n", file, ctx.nofollow));
|
||||
if (meta_disallow_follow)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/* Declarations for html-url.c.
|
||||
Copyright (C) 1995, 1996, 1997, 2009, 2010, 2011 Free Software
|
||||
Copyright (C) 1995, 1996, 1997, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* NTLM code.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
Contributed by Daniel Stenberg.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
@@ -122,7 +122,7 @@ ntlm_input (struct ntlmdata *ntlm, const char *header)
|
||||
|
||||
DEBUGP (("Received a type-2 NTLM message.\n"));
|
||||
|
||||
size = base64_decode (header, buffer);
|
||||
size = wget_base64_decode (header, buffer);
|
||||
if (size < 0)
|
||||
return false; /* malformed base64 from server */
|
||||
|
||||
@@ -411,7 +411,7 @@ ntlm_output (struct ntlmdata *ntlm, const char *user, const char *passwd,
|
||||
size = 32 + hostlen + domlen;
|
||||
|
||||
base64 = (char *) alloca (BASE64_LENGTH (size) + 1);
|
||||
base64_encode (ntlmbuf, size, base64);
|
||||
wget_base64_encode (ntlmbuf, size, base64);
|
||||
|
||||
output = concat_strings ("NTLM ", base64, (char *) 0);
|
||||
break;
|
||||
@@ -523,13 +523,13 @@ ntlm_output (struct ntlmdata *ntlm, const char *user, const char *passwd,
|
||||
0x0, 0x0,
|
||||
|
||||
#ifdef USE_NTRESPONSES
|
||||
SHORTPAIR (0x18), /* NT-response length, twice */
|
||||
SHORTPAIR (0x18), /* NT-response length, twice */
|
||||
SHORTPAIR (0x18),
|
||||
#else
|
||||
0x0, 0x0,
|
||||
0x0, 0x0,
|
||||
0x0, 0x0,
|
||||
#endif
|
||||
SHORTPAIR (ntrespoff),
|
||||
SHORTPAIR (ntrespoff),
|
||||
0x0, 0x0,
|
||||
|
||||
SHORTPAIR (domlen),
|
||||
@@ -584,7 +584,7 @@ ntlm_output (struct ntlmdata *ntlm, const char *user, const char *passwd,
|
||||
|
||||
/* convert the binary blob into base64 */
|
||||
base64 = (char *) alloca (BASE64_LENGTH (size) + 1);
|
||||
base64_encode (ntlmbuf, size, base64);
|
||||
wget_base64_encode (ntlmbuf, size, base64);
|
||||
|
||||
output = concat_strings ("NTLM ", base64, (char *) 0);
|
||||
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
#ifndef __HTTP_NTLM_H
|
||||
#define __HTTP_NTLM_H
|
||||
/* Declarations for http_ntlm.c
|
||||
Copyright (C) 1995, 1996, 1997, 2000, 2007, 2008, 2009, 2010, 2011
|
||||
Free Software Foundation, Inc.
|
||||
Copyright (C) 1995, 1996, 1997, 2000, 2007, 2008, 2009, 2010, 2011,
|
||||
2015 Free Software Foundation, Inc.
|
||||
Contributed by Daniel Stenberg.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
2663
src/http.c
2663
src/http.c
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
/* Declarations for HTTP.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -31,9 +31,11 @@ as that of the covered work. */
|
||||
#ifndef HTTP_H
|
||||
#define HTTP_H
|
||||
|
||||
#include "hsts.h"
|
||||
|
||||
struct url;
|
||||
|
||||
uerr_t http_loop (struct url *, struct url *, char **, char **, const char *,
|
||||
uerr_t http_loop (const struct url *, struct url *, char **, char **, const char *,
|
||||
int *, struct url *, struct iri *);
|
||||
void save_cookies (void);
|
||||
void http_cleanup (void);
|
||||
|
||||
201
src/init.c
201
src/init.c
@@ -1,7 +1,7 @@
|
||||
/* Reading/parsing the initialization file.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2014 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2014, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -97,6 +97,8 @@ CMD_DECLARE (cmd_directory);
|
||||
CMD_DECLARE (cmd_time);
|
||||
CMD_DECLARE (cmd_vector);
|
||||
|
||||
CMD_DECLARE (cmd_use_askpass);
|
||||
|
||||
CMD_DECLARE (cmd_spec_dirstruct);
|
||||
CMD_DECLARE (cmd_spec_header);
|
||||
CMD_DECLARE (cmd_spec_warc_header);
|
||||
@@ -115,6 +117,7 @@ CMD_DECLARE (cmd_spec_secure_protocol);
|
||||
CMD_DECLARE (cmd_spec_timeout);
|
||||
CMD_DECLARE (cmd_spec_useragent);
|
||||
CMD_DECLARE (cmd_spec_verbose);
|
||||
CMD_DECLARE (cmd_check_cert);
|
||||
|
||||
/* List of recognized commands, each consisting of name, place and
|
||||
function. When adding a new command, simply add it to the list,
|
||||
@@ -142,6 +145,9 @@ static const struct {
|
||||
{ "backups", &opt.backups, cmd_number },
|
||||
{ "base", &opt.base_href, cmd_string },
|
||||
{ "bindaddress", &opt.bind_address, cmd_string },
|
||||
#ifdef HAVE_LIBCARES
|
||||
{ "binddnsaddress", &opt.bind_dns_address, cmd_string },
|
||||
#endif
|
||||
{ "bodydata", &opt.body_data, cmd_string },
|
||||
{ "bodyfile", &opt.body_file, cmd_string },
|
||||
#ifdef HAVE_SSL
|
||||
@@ -152,13 +158,14 @@ static const struct {
|
||||
{ "cadirectory", &opt.ca_directory, cmd_directory },
|
||||
{ "certificate", &opt.cert_file, cmd_file },
|
||||
{ "certificatetype", &opt.cert_type, cmd_cert_type },
|
||||
{ "checkcertificate", &opt.check_cert, cmd_boolean },
|
||||
{ "checkcertificate", &opt.check_cert, cmd_check_cert },
|
||||
#endif
|
||||
{ "chooseconfig", &opt.choose_config, cmd_file },
|
||||
{ "connecttimeout", &opt.connect_timeout, cmd_time },
|
||||
{ "contentdisposition", &opt.content_disposition, cmd_boolean },
|
||||
{ "contentonerror", &opt.content_on_error, cmd_boolean },
|
||||
{ "continue", &opt.always_rest, cmd_boolean },
|
||||
{ "convertfileonly", &opt.convert_file_only, cmd_boolean },
|
||||
{ "convertlinks", &opt.convert_links, cmd_boolean },
|
||||
{ "cookies", &opt.cookies, cmd_boolean },
|
||||
#ifdef HAVE_SSL
|
||||
@@ -171,6 +178,9 @@ static const struct {
|
||||
{ "dirprefix", &opt.dir_prefix, cmd_directory },
|
||||
{ "dirstruct", NULL, cmd_spec_dirstruct },
|
||||
{ "dnscache", &opt.dns_cache, cmd_boolean },
|
||||
#ifdef HAVE_LIBCARES
|
||||
{ "dnsservers", &opt.dns_servers, cmd_string },
|
||||
#endif
|
||||
{ "dnstimeout", &opt.dns_timeout, cmd_time },
|
||||
{ "domains", &opt.domains, cmd_vector },
|
||||
{ "dotbytes", &opt.dot_bytes, cmd_bytes },
|
||||
@@ -188,12 +198,22 @@ static const struct {
|
||||
{ "ftppasswd", &opt.ftp_passwd, cmd_string }, /* deprecated */
|
||||
{ "ftppassword", &opt.ftp_passwd, cmd_string },
|
||||
{ "ftpproxy", &opt.ftp_proxy, cmd_string },
|
||||
#ifdef HAVE_SSL
|
||||
{ "ftpscleardataconnection", &opt.ftps_clear_data_connection, cmd_boolean },
|
||||
{ "ftpsfallbacktoftp", &opt.ftps_fallback_to_ftp, cmd_boolean },
|
||||
{ "ftpsimplicit", &opt.ftps_implicit, cmd_boolean },
|
||||
{ "ftpsresumessl", &opt.ftps_resume_ssl, cmd_boolean },
|
||||
#endif
|
||||
#ifdef __VMS
|
||||
{ "ftpstmlf", &opt.ftp_stmlf, cmd_boolean },
|
||||
#endif /* def __VMS */
|
||||
{ "ftpuser", &opt.ftp_user, cmd_string },
|
||||
{ "glob", &opt.ftp_glob, cmd_boolean },
|
||||
{ "header", NULL, cmd_spec_header },
|
||||
#ifdef HAVE_HSTS
|
||||
{ "hsts", &opt.hsts, cmd_boolean },
|
||||
{ "hstsfile", &opt.hsts_file, cmd_file },
|
||||
#endif
|
||||
{ "htmlextension", &opt.adjust_extension, cmd_boolean }, /* deprecated */
|
||||
{ "htmlify", NULL, cmd_spec_htmlify },
|
||||
{ "httpkeepalive", &opt.http_keep_alive, cmd_boolean },
|
||||
@@ -205,6 +225,7 @@ static const struct {
|
||||
#endif
|
||||
{ "httpsproxy", &opt.https_proxy, cmd_string },
|
||||
{ "httpuser", &opt.http_user, cmd_string },
|
||||
{ "ifmodifiedsince", &opt.if_modified_since, cmd_boolean },
|
||||
{ "ignorecase", &opt.ignore_case, cmd_boolean },
|
||||
{ "ignorelength", &opt.ignore_length, cmd_boolean },
|
||||
{ "ignoretags", &opt.ignore_tags, cmd_vector },
|
||||
@@ -214,7 +235,11 @@ static const struct {
|
||||
{ "inet6only", &opt.ipv6_only, cmd_boolean },
|
||||
#endif
|
||||
{ "input", &opt.input_filename, cmd_file },
|
||||
#ifdef HAVE_METALINK
|
||||
{ "inputmetalink", &opt.input_metalink, cmd_file },
|
||||
#endif
|
||||
{ "iri", &opt.enable_iri, cmd_boolean },
|
||||
{ "keepbadhash", &opt.keep_badhash, cmd_boolean },
|
||||
{ "keepsessioncookies", &opt.keep_session_cookies, cmd_boolean },
|
||||
{ "limitrate", &opt.limit_rate, cmd_bytes },
|
||||
{ "loadcookies", &opt.cookies_input, cmd_file },
|
||||
@@ -222,6 +247,10 @@ static const struct {
|
||||
{ "logfile", &opt.lfilename, cmd_file },
|
||||
{ "login", &opt.ftp_user, cmd_string },/* deprecated*/
|
||||
{ "maxredirect", &opt.max_redirect, cmd_number },
|
||||
#ifdef HAVE_METALINK
|
||||
{ "metalinkindex", &opt.metalink_index, cmd_number_inf },
|
||||
{ "metalinkoverhttp", &opt.metalink_over_http, cmd_boolean },
|
||||
#endif
|
||||
{ "method", &opt.method, cmd_string_uppercase },
|
||||
{ "mirror", NULL, cmd_spec_mirror },
|
||||
{ "netrc", &opt.netrc, cmd_boolean },
|
||||
@@ -235,9 +264,15 @@ static const struct {
|
||||
{ "passiveftp", &opt.ftp_pasv, cmd_boolean },
|
||||
{ "passwd", &opt.ftp_passwd, cmd_string },/* deprecated*/
|
||||
{ "password", &opt.passwd, cmd_string },
|
||||
#ifdef HAVE_SSL
|
||||
{ "pinnedpubkey", &opt.pinnedpubkey, cmd_string },
|
||||
#endif
|
||||
{ "postdata", &opt.post_data, cmd_string },
|
||||
{ "postfile", &opt.post_file_name, cmd_file },
|
||||
{ "preferfamily", NULL, cmd_spec_prefer_family },
|
||||
#ifdef HAVE_METALINK
|
||||
{ "preferredlocation", &opt.preferred_location, cmd_string },
|
||||
#endif
|
||||
{ "preservepermissions", &opt.preserve_perm, cmd_boolean },
|
||||
#ifdef HAVE_SSL
|
||||
{ "privatekey", &opt.private_key, cmd_file },
|
||||
@@ -260,6 +295,7 @@ static const struct {
|
||||
{ "referer", &opt.referer, cmd_string },
|
||||
{ "regextype", &opt.regex_type, cmd_spec_regex_type },
|
||||
{ "reject", &opt.rejects, cmd_vector },
|
||||
{ "rejectedlog", &opt.rejected_log, cmd_file },
|
||||
{ "rejectregex", &opt.rejectregex_s, cmd_string },
|
||||
{ "relativeonly", &opt.relative_only, cmd_boolean },
|
||||
{ "remoteencoding", &opt.encoding_remote, cmd_string },
|
||||
@@ -286,6 +322,7 @@ static const struct {
|
||||
{ "tries", &opt.ntry, cmd_number_inf },
|
||||
{ "trustservernames", &opt.trustservernames, cmd_boolean },
|
||||
{ "unlink", &opt.unlink, cmd_boolean },
|
||||
{ "useaskpass" , &opt.use_askpass, cmd_use_askpass },
|
||||
{ "useproxy", &opt.use_proxy, cmd_boolean },
|
||||
{ "user", &opt.user, cmd_string },
|
||||
{ "useragent", NULL, cmd_spec_useragent },
|
||||
@@ -307,6 +344,9 @@ static const struct {
|
||||
#ifdef USE_WATT32
|
||||
{ "wdebug", &opt.wdebug, cmd_boolean },
|
||||
#endif
|
||||
#ifdef ENABLE_XATTR
|
||||
{ "xattr", &opt.enable_xattr, cmd_boolean },
|
||||
#endif
|
||||
};
|
||||
|
||||
/* Look up CMDNAME in the commands[] and return its position in the
|
||||
@@ -346,6 +386,10 @@ defaults (void)
|
||||
bit pattern will be the least of the implementors' worries. */
|
||||
xzero (opt);
|
||||
|
||||
#ifdef HAVE_METALINK
|
||||
opt.metalink_index = -1;
|
||||
#endif
|
||||
|
||||
opt.cookies = true;
|
||||
opt.verbose = -1;
|
||||
opt.ntry = 20;
|
||||
@@ -356,11 +400,13 @@ defaults (void)
|
||||
opt.htmlify = true;
|
||||
opt.http_keep_alive = true;
|
||||
opt.use_proxy = true;
|
||||
opt.convert_file_only = false;
|
||||
tmp = getenv ("no_proxy");
|
||||
if (tmp)
|
||||
opt.no_proxy = sepstring (tmp);
|
||||
opt.prefer_family = prefer_none;
|
||||
opt.allow_cache = true;
|
||||
opt.if_modified_since = true;
|
||||
|
||||
opt.read_timeout = 900;
|
||||
opt.use_robots = true;
|
||||
@@ -391,12 +437,18 @@ defaults (void)
|
||||
opt.retr_symlinks = true;
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
opt.check_cert = true;
|
||||
opt.check_cert = CHECK_CERT_ON;
|
||||
opt.ftps_resume_ssl = true;
|
||||
opt.ftps_fallback_to_ftp = false;
|
||||
opt.ftps_implicit = false;
|
||||
opt.ftps_clear_data_connection = false;
|
||||
#endif
|
||||
|
||||
/* The default for file name restriction defaults to the OS type. */
|
||||
#if defined(WINDOWS) || defined(MSDOS) || defined(__CYGWIN__)
|
||||
opt.restrict_files_os = restrict_windows;
|
||||
#elif defined(__VMS)
|
||||
opt.restrict_files_os = restrict_vms;
|
||||
#else
|
||||
opt.restrict_files_os = restrict_unix;
|
||||
#endif
|
||||
@@ -437,6 +489,17 @@ defaults (void)
|
||||
opt.start_pos = -1;
|
||||
opt.show_progress = -1;
|
||||
opt.noscroll = false;
|
||||
|
||||
#ifdef HAVE_HSTS
|
||||
/* HSTS is enabled by default */
|
||||
opt.hsts = true;
|
||||
#endif
|
||||
|
||||
#ifdef ENABLE_XATTR
|
||||
opt.enable_xattr = true;
|
||||
#else
|
||||
opt.enable_xattr = false;
|
||||
#endif
|
||||
}
|
||||
|
||||
/* Return the user's home directory (strdup-ed), or NULL if none is
|
||||
@@ -562,9 +625,7 @@ wgetrc_file_name (void)
|
||||
SYSTEM_WGETRC should not be defined under WINDOWS. */
|
||||
if (!file)
|
||||
{
|
||||
char *home = home_dir ();
|
||||
xfree (file);
|
||||
home = ws_mypath ();
|
||||
char *home = ws_mypath ();
|
||||
if (home)
|
||||
{
|
||||
file = aprintf ("%s/wget.ini", home);
|
||||
@@ -816,6 +877,10 @@ static bool
|
||||
setval_internal (int comind, const char *com, const char *val)
|
||||
{
|
||||
assert (0 <= comind && ((size_t) comind) < countof (commands));
|
||||
|
||||
if ((unsigned) comind >= countof (commands))
|
||||
return NULL;
|
||||
|
||||
DEBUGP (("Setting %s (%s) to %s\n", com, commands[comind].name, val));
|
||||
return commands[comind].action (com, val, commands[comind].place);
|
||||
}
|
||||
@@ -922,6 +987,18 @@ static bool simple_atof (const char *, const char *, double *);
|
||||
&& (p)[3] == '\0')
|
||||
|
||||
|
||||
static int
|
||||
cmd_boolean_internal (const char *com _GL_UNUSED, const char *val, void *place _GL_UNUSED)
|
||||
{
|
||||
if (CMP2 (val, 'o', 'n') || CMP3 (val, 'y', 'e', 's') || CMP1 (val, '1'))
|
||||
/* "on", "yes" and "1" mean true. */
|
||||
return 1;
|
||||
else if (CMP3 (val, 'o', 'f', 'f') || CMP2 (val, 'n', 'o') || CMP1 (val, '0'))
|
||||
/* "off", "no" and "0" mean false. */
|
||||
return 0;
|
||||
return -1;
|
||||
}
|
||||
|
||||
/* Store the boolean value from VAL to PLACE. COM is ignored,
|
||||
except for error messages. */
|
||||
static bool
|
||||
@@ -929,24 +1006,62 @@ cmd_boolean (const char *com, const char *val, void *place)
|
||||
{
|
||||
bool value;
|
||||
|
||||
if (CMP2 (val, 'o', 'n') || CMP3 (val, 'y', 'e', 's') || CMP1 (val, '1'))
|
||||
/* "on", "yes" and "1" mean true. */
|
||||
value = true;
|
||||
else if (CMP3 (val, 'o', 'f', 'f') || CMP2 (val, 'n', 'o') || CMP1 (val, '0'))
|
||||
/* "off", "no" and "0" mean false. */
|
||||
value = false;
|
||||
else
|
||||
switch (cmd_boolean_internal (com, val, place))
|
||||
{
|
||||
fprintf (stderr,
|
||||
_("%s: %s: Invalid boolean %s; use `on' or `off'.\n"),
|
||||
exec_name, com, quote (val));
|
||||
return false;
|
||||
}
|
||||
case 0:
|
||||
value = false;
|
||||
break;
|
||||
|
||||
case 1:
|
||||
value = true;
|
||||
break;
|
||||
|
||||
default:
|
||||
{
|
||||
fprintf (stderr,
|
||||
_("%s: %s: Invalid boolean %s; use `on' or `off'.\n"),
|
||||
exec_name, com, quote (val));
|
||||
return false;
|
||||
}
|
||||
}
|
||||
*(bool *) place = value;
|
||||
return true;
|
||||
}
|
||||
|
||||
/* Store the check_cert value from VAL to PLACE. COM is ignored,
|
||||
except for error messages. */
|
||||
static bool
|
||||
cmd_check_cert (const char *com, const char *val, void *place)
|
||||
{
|
||||
int value;
|
||||
|
||||
switch (cmd_boolean_internal (com, val, place))
|
||||
{
|
||||
case 0:
|
||||
value = CHECK_CERT_OFF;
|
||||
break;
|
||||
|
||||
case 1:
|
||||
value = CHECK_CERT_ON;
|
||||
break;
|
||||
|
||||
default:
|
||||
{
|
||||
if (!c_strcasecmp (val, "quiet"))
|
||||
value = CHECK_CERT_QUIET;
|
||||
else
|
||||
{
|
||||
fprintf (stderr,
|
||||
_("%s: %s: Invalid %s; use `on', `off' or `quiet'.\n"),
|
||||
exec_name, com, quote (val));
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
*(int *) place = value;
|
||||
return true;
|
||||
}
|
||||
|
||||
/* Set the non-negative integer value from VAL to PLACE. With
|
||||
incorrect specification, the number remains unchanged. */
|
||||
static bool
|
||||
@@ -1278,6 +1393,32 @@ cmd_time (const char *com, const char *val, void *place)
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
static bool
|
||||
cmd_use_askpass (const char *com _GL_UNUSED, const char *val, void *place)
|
||||
{
|
||||
const char *env_name = "WGET_ASKPASS";
|
||||
const char *env;
|
||||
|
||||
if (val && *val)
|
||||
return cmd_string (com, val, place);
|
||||
|
||||
env = getenv (env_name);
|
||||
if (!(env && *env))
|
||||
{
|
||||
env_name = "SSH_ASKPASS";
|
||||
env = getenv (env_name);
|
||||
}
|
||||
|
||||
if (!(env && *env))
|
||||
{
|
||||
fprintf (stderr, _("use-askpass requires a string or either environment variable WGET_ASKPASS or SSH_ASKPASS to be set.\n"));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
return cmd_string (com, env, place);
|
||||
}
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
static bool
|
||||
cmd_cert_type (const char *com, const char *val, void *place)
|
||||
@@ -1481,6 +1622,8 @@ cmd_spec_restrict_file_names (const char *com, const char *val, void *place_igno
|
||||
|
||||
if (VAL_IS ("unix"))
|
||||
restrict_os = restrict_unix;
|
||||
else if (VAL_IS ("vms"))
|
||||
restrict_os = restrict_vms;
|
||||
else if (VAL_IS ("windows"))
|
||||
restrict_os = restrict_windows;
|
||||
else if (VAL_IS ("lowercase"))
|
||||
@@ -1495,7 +1638,7 @@ cmd_spec_restrict_file_names (const char *com, const char *val, void *place_igno
|
||||
{
|
||||
fprintf (stderr, _("\
|
||||
%s: %s: Invalid restriction %s,\n\
|
||||
use [unix|windows],[lowercase|uppercase],[nocontrol],[ascii].\n"),
|
||||
use [unix|vms|windows],[lowercase|uppercase],[nocontrol],[ascii].\n"),
|
||||
exec_name, com, quote (val));
|
||||
return false;
|
||||
}
|
||||
@@ -1789,6 +1932,10 @@ cleanup (void)
|
||||
xfree (opt.lfilename);
|
||||
xfree (opt.dir_prefix);
|
||||
xfree (opt.input_filename);
|
||||
#ifdef HAVE_METALINK
|
||||
xfree (opt.input_metalink);
|
||||
xfree (opt.preferred_location);
|
||||
#endif
|
||||
xfree (opt.output_document);
|
||||
free_vec (opt.accepts);
|
||||
free_vec (opt.rejects);
|
||||
@@ -1830,6 +1977,20 @@ cleanup (void)
|
||||
xfree (opt.post_data);
|
||||
xfree (opt.body_data);
|
||||
xfree (opt.body_file);
|
||||
xfree (opt.rejected_log);
|
||||
xfree (opt.use_askpass);
|
||||
|
||||
#ifdef HAVE_LIBCARES
|
||||
#include <ares.h>
|
||||
{
|
||||
extern ares_channel ares;
|
||||
|
||||
xfree (opt.bind_dns_address);
|
||||
xfree (opt.dns_servers);
|
||||
ares_destroy (ares);
|
||||
ares_library_cleanup ();
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* DEBUG_MALLOC */
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/* Declarations for init.c.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
155
src/iri.c
155
src/iri.c
@@ -1,5 +1,6 @@
|
||||
/* IRI related functions.
|
||||
Copyright (C) 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
Copyright (C) 2008, 2009, 2010, 2011, 2015 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -32,11 +33,14 @@ as that of the covered work. */
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <iconv.h>
|
||||
#include <stringprep.h>
|
||||
#include <idna.h>
|
||||
#include <idn-free.h>
|
||||
#include <langinfo.h>
|
||||
#include <errno.h>
|
||||
#ifdef HAVE_ICONV
|
||||
# include <iconv.h>
|
||||
#endif
|
||||
#include <idn2.h>
|
||||
#include <unicase.h>
|
||||
#include <unistr.h>
|
||||
|
||||
#include "utils.h"
|
||||
#include "url.h"
|
||||
@@ -44,16 +48,14 @@ as that of the covered work. */
|
||||
#include "c-strcasestr.h"
|
||||
#include "xstrndup.h"
|
||||
|
||||
/* RFC3987 section 3.1 mandates STD3 ASCII RULES */
|
||||
#define IDNA_FLAGS IDNA_USE_STD3_ASCII_RULES
|
||||
|
||||
/* Note: locale encoding is kept in options struct (opt.locale) */
|
||||
|
||||
/* Given a string containing "charset=XXX", return the encoding if found,
|
||||
or NULL otherwise */
|
||||
char *
|
||||
parse_charset (char *str)
|
||||
parse_charset (const char *str)
|
||||
{
|
||||
const char *end;
|
||||
char *charset;
|
||||
|
||||
if (!str || !*str)
|
||||
@@ -64,14 +66,14 @@ parse_charset (char *str)
|
||||
return NULL;
|
||||
|
||||
str += 8;
|
||||
charset = str;
|
||||
end = str;
|
||||
|
||||
/* sXXXav: which chars should be banned ??? */
|
||||
while (*charset && !c_isspace (*charset))
|
||||
charset++;
|
||||
while (*end && !c_isspace (*end))
|
||||
end++;
|
||||
|
||||
/* sXXXav: could strdupdelim return NULL ? */
|
||||
charset = strdupdelim (str, charset);
|
||||
charset = strdupdelim (str, end);
|
||||
|
||||
/* Do a minimum check on the charset value */
|
||||
if (!check_encoding_name (charset))
|
||||
@@ -86,17 +88,22 @@ parse_charset (char *str)
|
||||
}
|
||||
|
||||
/* Find the locale used, or fall back on a default value */
|
||||
char *
|
||||
const char *
|
||||
find_locale (void)
|
||||
{
|
||||
return (char *) stringprep_locale_charset ();
|
||||
const char *encoding = nl_langinfo(CODESET);
|
||||
|
||||
if (!encoding || !*encoding)
|
||||
return "ASCII";
|
||||
|
||||
return encoding;
|
||||
}
|
||||
|
||||
/* Basic check of an encoding name. */
|
||||
bool
|
||||
check_encoding_name (char *encoding)
|
||||
check_encoding_name (const char *encoding)
|
||||
{
|
||||
char *s = encoding;
|
||||
const char *s = encoding;
|
||||
|
||||
while (*s)
|
||||
{
|
||||
@@ -116,27 +123,26 @@ check_encoding_name (char *encoding)
|
||||
will contain the transcoded string on success. *out content is
|
||||
unspecified otherwise. */
|
||||
static bool
|
||||
do_conversion (const char *tocode, const char *fromcode, char *in, size_t inlen, char **out)
|
||||
do_conversion (const char *tocode, const char *fromcode, char const *in_org, size_t inlen, char **out)
|
||||
{
|
||||
iconv_t cd;
|
||||
/* sXXXav : hummm hard to guess... */
|
||||
size_t len, done, outlen;
|
||||
int invalid = 0, tooshort = 0;
|
||||
char *s, *in_org, *in_save;
|
||||
char *s, *in, *in_save;
|
||||
|
||||
cd = iconv_open (tocode, fromcode);
|
||||
if (cd == (iconv_t)(-1))
|
||||
{
|
||||
logprintf (LOG_VERBOSE, _("Conversion from %s to UTF-8 isn't supported\n"),
|
||||
quote (opt.locale));
|
||||
logprintf (LOG_VERBOSE, _("Conversion from %s to %s isn't supported\n"),
|
||||
quote (fromcode), quote (tocode));
|
||||
*out = NULL;
|
||||
return false;
|
||||
}
|
||||
|
||||
/* iconv() has to work on an unescaped string */
|
||||
in_org = in;
|
||||
in_save = in = xstrndup(in, inlen);
|
||||
url_unescape(in);
|
||||
in_save = in = xstrndup (in_org, inlen);
|
||||
url_unescape_except_reserved (in);
|
||||
inlen = strlen(in);
|
||||
|
||||
len = outlen = inlen * 2;
|
||||
@@ -145,13 +151,21 @@ do_conversion (const char *tocode, const char *fromcode, char *in, size_t inlen,
|
||||
|
||||
for (;;)
|
||||
{
|
||||
if (iconv (cd, &in, &inlen, out, &outlen) != (size_t)(-1))
|
||||
if (iconv (cd, (ICONV_CONST char **) &in, &inlen, out, &outlen) != (size_t)(-1) &&
|
||||
iconv (cd, NULL, NULL, out, &outlen) != (size_t)(-1))
|
||||
{
|
||||
*out = s;
|
||||
*(s + len - outlen - done) = '\0';
|
||||
xfree(in_save);
|
||||
iconv_close(cd);
|
||||
DEBUGP (("converted '%s' (%s) -> '%s' (%s)\n", in_org, fromcode, *out, tocode));
|
||||
IF_DEBUG
|
||||
{
|
||||
/* not not print out embedded passwords, in_org might be an URL */
|
||||
if (!strchr(in_org, '@') && !strchr(*out, '@'))
|
||||
debug_logprintf ("converted '%s' (%s) -> '%s' (%s)\n", in_org, fromcode, *out, tocode);
|
||||
else
|
||||
debug_logprintf ("logging suppressed, strings may contain password\n");
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -171,16 +185,10 @@ do_conversion (const char *tocode, const char *fromcode, char *in, size_t inlen,
|
||||
}
|
||||
else if (errno == E2BIG) /* Output buffer full */
|
||||
{
|
||||
char *new;
|
||||
|
||||
tooshort++;
|
||||
done = len;
|
||||
outlen = done + inlen * 2;
|
||||
new = xmalloc (outlen + 1);
|
||||
memcpy (new, s, done);
|
||||
xfree (s);
|
||||
s = new;
|
||||
len = outlen;
|
||||
len = outlen = done + inlen * 2;
|
||||
s = xrealloc (s, outlen + 1);
|
||||
*out = s + done;
|
||||
}
|
||||
else /* Weird, we got an unspecified error */
|
||||
@@ -192,7 +200,14 @@ do_conversion (const char *tocode, const char *fromcode, char *in, size_t inlen,
|
||||
|
||||
xfree(in_save);
|
||||
iconv_close(cd);
|
||||
DEBUGP (("converted '%s' (%s) -> '%s' (%s)\n", in_org, fromcode, *out, tocode));
|
||||
IF_DEBUG
|
||||
{
|
||||
/* not not print out embedded passwords, in_org might be an URL */
|
||||
if (!strchr(in_org, '@') && !strchr(*out, '@'))
|
||||
debug_logprintf ("converted '%s' (%s) -> '%s' (%s)\n", in_org, fromcode, *out, tocode);
|
||||
else
|
||||
debug_logprintf ("logging suppressed, strings may contain password\n");
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
@@ -216,61 +231,93 @@ locale_to_utf8 (const char *str)
|
||||
if (do_conversion ("UTF-8", opt.locale, (char *) str, strlen ((char *) str), &new))
|
||||
return (const char *) new;
|
||||
|
||||
xfree (new);
|
||||
return str;
|
||||
}
|
||||
|
||||
/* Try to "ASCII encode" UTF-8 host. Return the new domain on success or NULL
|
||||
on error. */
|
||||
char *
|
||||
idn_encode (struct iri *i, char *host)
|
||||
idn_encode (const struct iri *i, const char *host)
|
||||
{
|
||||
char *new;
|
||||
int ret;
|
||||
char *ascii_encoded;
|
||||
char *utf8_encoded = NULL;
|
||||
const char *src;
|
||||
#if IDN2_VERSION_NUMBER < 0x00140000
|
||||
uint8_t *lower;
|
||||
size_t len = 0;
|
||||
#endif
|
||||
|
||||
/* Encode to UTF-8 if not done */
|
||||
if (!i->utf8_encode)
|
||||
{
|
||||
if (!remote_to_utf8 (i, (const char *) host, (const char **) &new))
|
||||
if (!remote_to_utf8 (i, host, &utf8_encoded))
|
||||
return NULL; /* Nothing to encode or an error occured */
|
||||
host = new;
|
||||
src = utf8_encoded;
|
||||
}
|
||||
else
|
||||
src = host;
|
||||
|
||||
/* toASCII UTF-8 NULL terminated string */
|
||||
ret = idna_to_ascii_8z (host, &new, IDNA_FLAGS);
|
||||
if (ret != IDNA_SUCCESS)
|
||||
#if IDN2_VERSION_NUMBER >= 0x00140000
|
||||
/* IDN2_TRANSITIONAL implies input NFC encoding */
|
||||
if ((ret = idn2_lookup_u8 ((uint8_t *) src, (uint8_t **) &ascii_encoded, IDN2_NONTRANSITIONAL)) != IDN2_OK)
|
||||
{
|
||||
/* sXXXav : free new when needed ! */
|
||||
logprintf (LOG_VERBOSE, _("idn_encode failed (%d): %s\n"), ret,
|
||||
quote (idna_strerror (ret)));
|
||||
quote (idn2_strerror (ret)));
|
||||
}
|
||||
#else
|
||||
/* we need a conversion to lowercase */
|
||||
lower = u8_tolower ((uint8_t *) src, u8_strlen ((uint8_t *) src) + 1, 0, UNINORM_NFKC, NULL, &len);
|
||||
if (!lower)
|
||||
{
|
||||
logprintf (LOG_VERBOSE, _("Failed to convert to lower: %d: %s\n"),
|
||||
errno, quote (src));
|
||||
xfree (utf8_encoded);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
return new;
|
||||
if ((ret = idn2_lookup_u8 (lower, (uint8_t **) &ascii_encoded, IDN2_NFC_INPUT)) != IDN2_OK)
|
||||
{
|
||||
logprintf (LOG_VERBOSE, _("idn_encode failed (%d): %s\n"), ret,
|
||||
quote (idn2_strerror (ret)));
|
||||
}
|
||||
|
||||
xfree (lower);
|
||||
#endif
|
||||
|
||||
return ret == IDN2_OK ? ascii_encoded : NULL;
|
||||
}
|
||||
|
||||
/* Try to decode an "ASCII encoded" host. Return the new domain in the locale
|
||||
on success or NULL on error. */
|
||||
char *
|
||||
idn_decode (char *host)
|
||||
idn_decode (const char *host)
|
||||
{
|
||||
/*
|
||||
char *new;
|
||||
int ret;
|
||||
|
||||
ret = idna_to_unicode_8zlz (host, &new, IDNA_FLAGS);
|
||||
if (ret != IDNA_SUCCESS)
|
||||
ret = idn2_register_u8 (NULL, host, (uint8_t **) &new, 0);
|
||||
if (ret != IDN2_OK)
|
||||
{
|
||||
logprintf (LOG_VERBOSE, _("idn_decode failed (%d): %s\n"), ret,
|
||||
quote (idna_strerror (ret)));
|
||||
logprintf (LOG_VERBOSE, _("idn2_register_u8 failed (%d): %s: %s\n"), ret,
|
||||
quote (idn2_strerror (ret)), host);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
return new;
|
||||
*/
|
||||
/* idn2_register_u8() just works label by label.
|
||||
* That is pretty much overhead for just displaying the original ulabels.
|
||||
* To keep at least the debug output format, return a cloned host. */
|
||||
return xstrdup(host);
|
||||
}
|
||||
|
||||
/* Try to transcode string str from remote encoding to UTF-8. On success, *new
|
||||
contains the transcoded string. *new content is unspecified otherwise. */
|
||||
bool
|
||||
remote_to_utf8 (struct iri *iri, const char *str, const char **new)
|
||||
remote_to_utf8 (const struct iri *iri, const char *str, char **new)
|
||||
{
|
||||
bool ret = false;
|
||||
|
||||
@@ -292,7 +339,7 @@ remote_to_utf8 (struct iri *iri, const char *str, const char **new)
|
||||
return false;
|
||||
}
|
||||
|
||||
if (do_conversion ("UTF-8", iri->uri_encoding, (char *) str, strlen (str), (char **) new))
|
||||
if (do_conversion ("UTF-8", iri->uri_encoding, str, strlen (str), new))
|
||||
ret = true;
|
||||
|
||||
/* Test if something was converted */
|
||||
@@ -344,7 +391,7 @@ iri_free (struct iri *i)
|
||||
/* Set uri_encoding of struct iri i. If a remote encoding was specified, use
|
||||
it unless force is true. */
|
||||
void
|
||||
set_uri_encoding (struct iri *i, char *charset, bool force)
|
||||
set_uri_encoding (struct iri *i, const char *charset, bool force)
|
||||
{
|
||||
DEBUGP (("URI encoding = %s\n", charset ? quote (charset) : "None"));
|
||||
if (!force && opt.encoding_remote)
|
||||
@@ -361,7 +408,7 @@ set_uri_encoding (struct iri *i, char *charset, bool force)
|
||||
|
||||
/* Set content_encoding of struct iri i. */
|
||||
void
|
||||
set_content_encoding (struct iri *i, char *charset)
|
||||
set_content_encoding (struct iri *i, const char *charset)
|
||||
{
|
||||
DEBUGP (("URI content encoding = %s\n", charset ? quote (charset) : "None"));
|
||||
if (opt.encoding_remote)
|
||||
|
||||
26
src/iri.h
26
src/iri.h
@@ -1,5 +1,6 @@
|
||||
/* Internationalization related declarations.
|
||||
Copyright (C) 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
Copyright (C) 2008, 2009, 2010, 2011, 2015 Free Software Foundation,
|
||||
Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -39,33 +40,32 @@ struct iri {
|
||||
|
||||
#ifdef ENABLE_IRI
|
||||
|
||||
# include <idna.h>
|
||||
# include <idn-free.h>
|
||||
# include <idn2.h>
|
||||
|
||||
char *parse_charset (char *str);
|
||||
char *find_locale (void);
|
||||
bool check_encoding_name (char *encoding);
|
||||
char *parse_charset (const char *str);
|
||||
const char *find_locale (void);
|
||||
bool check_encoding_name (const char *encoding);
|
||||
const char *locale_to_utf8 (const char *str);
|
||||
char *idn_encode (struct iri *i, char *host);
|
||||
char *idn_decode (char *host);
|
||||
bool remote_to_utf8 (struct iri *i, const char *str, const char **new);
|
||||
char *idn_encode (const struct iri *i, const char *host);
|
||||
char *idn_decode (const char *host);
|
||||
bool remote_to_utf8 (const struct iri *i, const char *str, char **new);
|
||||
struct iri *iri_new (void);
|
||||
struct iri *iri_dup (const struct iri *);
|
||||
void iri_free (struct iri *i);
|
||||
void set_uri_encoding (struct iri *i, char *charset, bool force);
|
||||
void set_content_encoding (struct iri *i, char *charset);
|
||||
void set_uri_encoding (struct iri *i, const char *charset, bool force);
|
||||
void set_content_encoding (struct iri *i, const char *charset);
|
||||
|
||||
#else /* ENABLE_IRI */
|
||||
|
||||
extern struct iri dummy_iri;
|
||||
|
||||
#define parse_charset(str) (str, NULL)
|
||||
#define parse_charset(str) NULL
|
||||
#define find_locale() NULL
|
||||
#define check_encoding_name(str) false
|
||||
#define locale_to_utf8(str) (str)
|
||||
#define idn_encode(a,b) NULL
|
||||
#define idn_decode(str) NULL
|
||||
#define idn_free(str) ((void)0)
|
||||
#define idn2_free(str) ((void)0)
|
||||
#define remote_to_utf8(a,b,c) false
|
||||
#define iri_new() (&dummy_iri)
|
||||
#define iri_dup(a) (&dummy_iri)
|
||||
|
||||
149
src/log.c
149
src/log.c
@@ -1,6 +1,6 @@
|
||||
/* Messages logging.
|
||||
Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
|
||||
2007, 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
2007, 2008, 2009, 2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -80,6 +80,18 @@ as that of the covered work. */
|
||||
logging is inhibited, logfp is set back to NULL. */
|
||||
static FILE *logfp;
|
||||
|
||||
/* Descriptor of the stdout|stderr */
|
||||
static FILE *stdlogfp;
|
||||
|
||||
/* Descriptor of the wget.log* file (if created) */
|
||||
static FILE *filelogfp;
|
||||
|
||||
/* Name of log file */
|
||||
static char *logfile;
|
||||
|
||||
/* Is interactive shell ? */
|
||||
static int shell_is_interactive;
|
||||
|
||||
/* A second file descriptor pointing to the temporary log file for the
|
||||
WARC writer. If WARC writing is disabled, this is NULL. */
|
||||
static FILE *warclogfp;
|
||||
@@ -351,6 +363,7 @@ logputs (enum log_options o, const char *s)
|
||||
{
|
||||
FILE *fp;
|
||||
FILE *warcfp;
|
||||
int errno_save = errno;
|
||||
|
||||
check_redirect_output ();
|
||||
if (o == LOG_PROGRESS)
|
||||
@@ -358,10 +371,14 @@ logputs (enum log_options o, const char *s)
|
||||
else
|
||||
fp = get_log_fp ();
|
||||
|
||||
errno = errno_save;
|
||||
|
||||
if (fp == NULL)
|
||||
return;
|
||||
|
||||
warcfp = get_warc_log_fp ();
|
||||
errno = errno_save;
|
||||
|
||||
CHECK_VERBOSE (o);
|
||||
|
||||
FPUTS (s, fp);
|
||||
@@ -373,6 +390,8 @@ logputs (enum log_options o, const char *s)
|
||||
logflush ();
|
||||
else
|
||||
needs_flushing = true;
|
||||
|
||||
errno = errno_save;
|
||||
}
|
||||
|
||||
struct logvprintf_state {
|
||||
@@ -543,8 +562,10 @@ logprintf (enum log_options o, const char *fmt, ...)
|
||||
va_list args;
|
||||
struct logvprintf_state lpstate;
|
||||
bool done;
|
||||
int errno_saved = errno;
|
||||
|
||||
check_redirect_output ();
|
||||
errno = errno_saved;
|
||||
if (inhibit_logging)
|
||||
return;
|
||||
CHECK_VERBOSE (o);
|
||||
@@ -561,6 +582,8 @@ logprintf (enum log_options o, const char *fmt, ...)
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
while (!done);
|
||||
|
||||
errno = errno_saved;
|
||||
}
|
||||
|
||||
#ifdef ENABLE_DEBUG
|
||||
@@ -598,11 +621,20 @@ log_init (const char *file, bool appendp)
|
||||
{
|
||||
if (file)
|
||||
{
|
||||
logfp = fopen (file, appendp ? "a" : "w");
|
||||
if (!logfp)
|
||||
if (HYPHENP (file))
|
||||
{
|
||||
fprintf (stderr, "%s: %s: %s\n", exec_name, file, strerror (errno));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
stdlogfp = stdout;
|
||||
logfp = stdlogfp;
|
||||
}
|
||||
else
|
||||
{
|
||||
filelogfp = fopen (file, appendp ? "a" : "w");
|
||||
if (!filelogfp)
|
||||
{
|
||||
fprintf (stderr, "%s: %s: %s\n", exec_name, file, strerror (errno));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
logfp = filelogfp;
|
||||
}
|
||||
}
|
||||
else
|
||||
@@ -613,7 +645,8 @@ log_init (const char *file, bool appendp)
|
||||
stderr only if the user actually specifies `-O -'. He says
|
||||
this inconsistency is harder to document, but is overall
|
||||
easier on the user. */
|
||||
logfp = stderr;
|
||||
stdlogfp = stderr;
|
||||
logfp = stdlogfp;
|
||||
|
||||
if (1
|
||||
#ifdef HAVE_ISATTY
|
||||
@@ -628,6 +661,11 @@ log_init (const char *file, bool appendp)
|
||||
save_context_p = true;
|
||||
}
|
||||
}
|
||||
|
||||
#ifndef WINDOWS
|
||||
/* Initialize this values so we don't have to ask every time we print line */
|
||||
shell_is_interactive = isatty (STDIN_FILENO);
|
||||
#endif
|
||||
}
|
||||
|
||||
/* Close LOGFP (only if we opened it, not if it's stderr), inhibit
|
||||
@@ -862,59 +900,78 @@ log_cleanup (void)
|
||||
|
||||
/* When SIGHUP or SIGUSR1 are received, the output is redirected
|
||||
elsewhere. Such redirection is only allowed once. */
|
||||
static enum { RR_NONE, RR_REQUESTED, RR_DONE } redirect_request = RR_NONE;
|
||||
static const char *redirect_request_signal_name;
|
||||
|
||||
/* Redirect output to `wget-log'. */
|
||||
/* Redirect output to `wget-log' or back to stdout/stderr. */
|
||||
|
||||
static void
|
||||
redirect_output (void)
|
||||
void
|
||||
redirect_output (bool to_file, const char *signal_name)
|
||||
{
|
||||
char *logfile;
|
||||
logfp = unique_create (DEFAULT_LOGFILE, false, &logfile);
|
||||
if (logfp)
|
||||
if (to_file && logfp != filelogfp)
|
||||
{
|
||||
fprintf (stderr, _("\n%s received, redirecting output to %s.\n"),
|
||||
redirect_request_signal_name, quote (logfile));
|
||||
xfree (logfile);
|
||||
/* Dump the context output to the newly opened log. */
|
||||
if (signal_name)
|
||||
{
|
||||
fprintf (stderr, "\n%s received.", signal_name);
|
||||
}
|
||||
if (!filelogfp)
|
||||
{
|
||||
filelogfp = unique_create (DEFAULT_LOGFILE, false, &logfile);
|
||||
if (filelogfp)
|
||||
{
|
||||
fprintf (stderr, _("\nRedirecting output to %s.\n"),
|
||||
quote (logfile));
|
||||
/* Store signal name to tell wget it's permanent redirect to log file */
|
||||
redirect_request_signal_name = signal_name;
|
||||
logfp = filelogfp;
|
||||
/* Dump the context output to the newly opened log. */
|
||||
log_dump_context ();
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Eek! Opening the alternate log file has failed. Nothing we
|
||||
can do but disable printing completely. */
|
||||
fprintf (stderr, _("%s: %s; disabling logging.\n"),
|
||||
(logfile) ? logfile : DEFAULT_LOGFILE, strerror (errno));
|
||||
inhibit_logging = true;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
fprintf (stderr, _("\nRedirecting output to %s.\n"),
|
||||
quote (logfile));
|
||||
logfp = filelogfp;
|
||||
log_dump_context ();
|
||||
}
|
||||
}
|
||||
else if (!to_file && logfp != stdlogfp)
|
||||
{
|
||||
logfp = stdlogfp;
|
||||
log_dump_context ();
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Eek! Opening the alternate log file has failed. Nothing we
|
||||
can do but disable printing completely. */
|
||||
fprintf (stderr, _("\n%s received.\n"), redirect_request_signal_name);
|
||||
fprintf (stderr, _("%s: %s; disabling logging.\n"),
|
||||
(logfile) ? logfile : DEFAULT_LOGFILE, strerror (errno));
|
||||
inhibit_logging = true;
|
||||
}
|
||||
save_context_p = false;
|
||||
}
|
||||
|
||||
/* Check whether a signal handler requested the output to be
|
||||
redirected. */
|
||||
/* Check whether there's a need to redirect output. */
|
||||
|
||||
static void
|
||||
check_redirect_output (void)
|
||||
{
|
||||
if (redirect_request == RR_REQUESTED)
|
||||
#ifndef WINDOWS
|
||||
/* If it was redirected already to log file by SIGHUP, SIGUSR1 or -o parameter,
|
||||
* it was permanent.
|
||||
* If there was no SIGHUP or SIGUSR1 and shell is interactive
|
||||
* we check if process is fg or bg before every line is printed.*/
|
||||
if (!redirect_request_signal_name && shell_is_interactive && !opt.lfilename)
|
||||
{
|
||||
redirect_request = RR_DONE;
|
||||
redirect_output ();
|
||||
if (tcgetpgrp (STDIN_FILENO) != getpgrp ())
|
||||
{
|
||||
/* Process backgrounded */
|
||||
redirect_output (true,NULL);
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Process foregrounded */
|
||||
redirect_output (false,NULL);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/* Request redirection at a convenient time. This may be called from
|
||||
a signal handler. */
|
||||
|
||||
void
|
||||
log_request_redirect_output (const char *signal_name)
|
||||
{
|
||||
if (redirect_request == RR_NONE && save_context_p)
|
||||
/* Request output redirection. The request will be processed by
|
||||
check_redirect_output(), which is called from entry point log
|
||||
functions. */
|
||||
redirect_request = RR_REQUESTED;
|
||||
redirect_request_signal_name = signal_name;
|
||||
#endif /* WINDOWS */
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Declarations for log.c.
|
||||
Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
|
||||
2007, 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
|
||||
2007, 2008, 2009, 2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -52,6 +52,7 @@ void log_init (const char *, bool);
|
||||
void log_close (void);
|
||||
void log_cleanup (void);
|
||||
void log_request_redirect_output (const char *);
|
||||
void redirect_output (bool, const char *);
|
||||
|
||||
const char *escnonprint (const char *);
|
||||
const char *escnonprint_uri (const char *);
|
||||
|
||||
514
src/main.c
514
src/main.c
@@ -1,5 +1,7 @@
|
||||
/* Command line parsing.
|
||||
Copyright (C) 1996-2014 Free Software Foundation, Inc.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -34,6 +36,7 @@ as that of the covered work. */
|
||||
#include <unistd.h>
|
||||
#include <string.h>
|
||||
#include <signal.h>
|
||||
#include <spawn.h>
|
||||
#ifdef ENABLE_NLS
|
||||
# include <locale.h>
|
||||
#endif
|
||||
@@ -52,15 +55,22 @@ as that of the covered work. */
|
||||
#include "convert.h"
|
||||
#include "spider.h"
|
||||
#include "http.h" /* for save_cookies */
|
||||
#include "hsts.h" /* for initializing hsts_store to NULL */
|
||||
#include "ptimer.h"
|
||||
#include "warc.h"
|
||||
#include "version.h"
|
||||
#include "c-strcase.h"
|
||||
#include "dirname.h"
|
||||
#include "xmemdup0.h"
|
||||
#include <getopt.h>
|
||||
#include <getpass.h>
|
||||
#include <quote.h>
|
||||
|
||||
#ifdef HAVE_METALINK
|
||||
# include <metalink/metalink_parser.h>
|
||||
# include "metalink.h"
|
||||
#endif
|
||||
|
||||
#ifdef WINDOWS
|
||||
# include <io.h>
|
||||
# include <fcntl.h>
|
||||
@@ -78,6 +88,13 @@ as that of the covered work. */
|
||||
struct iri dummy_iri;
|
||||
#endif
|
||||
|
||||
#ifdef HAVE_LIBCARES
|
||||
#include <ares.h>
|
||||
ares_channel ares;
|
||||
#else
|
||||
void *ares;
|
||||
#endif
|
||||
|
||||
struct options opt;
|
||||
|
||||
/* defined in version.c */
|
||||
@@ -115,7 +132,7 @@ redirect_output_signal (int sig)
|
||||
signal_name = "SIGUSR1";
|
||||
#endif
|
||||
|
||||
log_request_redirect_output (signal_name);
|
||||
redirect_output (true,signal_name);
|
||||
progress_schedule_redirect ();
|
||||
signal (sig, redirect_output_signal);
|
||||
}
|
||||
@@ -134,10 +151,78 @@ i18n_initialize (void)
|
||||
#endif /* ENABLE_NLS */
|
||||
}
|
||||
|
||||
#ifdef HAVE_HSTS
|
||||
/* make the HSTS store global */
|
||||
hsts_store_t hsts_store;
|
||||
|
||||
static char*
|
||||
get_hsts_database (void)
|
||||
{
|
||||
char *home;
|
||||
|
||||
if (opt.hsts_file)
|
||||
return xstrdup (opt.hsts_file);
|
||||
|
||||
home = home_dir ();
|
||||
if (home)
|
||||
{
|
||||
char *dir = aprintf ("%s/.wget-hsts", home);
|
||||
xfree(home);
|
||||
return dir;
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static void
|
||||
load_hsts (void)
|
||||
{
|
||||
if (!hsts_store)
|
||||
{
|
||||
char *filename = get_hsts_database ();
|
||||
|
||||
if (filename)
|
||||
{
|
||||
DEBUGP (("Reading HSTS entries from %s\n", filename));
|
||||
|
||||
hsts_store = hsts_store_open (filename);
|
||||
|
||||
if (!hsts_store)
|
||||
logprintf (LOG_NOTQUIET, "ERROR: could not open HSTS store at '%s'. "
|
||||
"HSTS will be disabled.\n",
|
||||
filename);
|
||||
}
|
||||
else
|
||||
logprintf (LOG_NOTQUIET, "ERROR: could not open HSTS store. HSTS will be disabled.\n");
|
||||
|
||||
xfree (filename);
|
||||
}
|
||||
}
|
||||
|
||||
static void
|
||||
save_hsts (void)
|
||||
{
|
||||
if (hsts_store)
|
||||
{
|
||||
char *filename = get_hsts_database ();
|
||||
|
||||
if (filename && hsts_store_has_changed (hsts_store))
|
||||
{
|
||||
DEBUGP (("Saving HSTS entries to %s\n", filename));
|
||||
hsts_store_save (hsts_store, filename);
|
||||
}
|
||||
|
||||
hsts_store_close (hsts_store);
|
||||
|
||||
xfree (filename);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
/* Definition of command-line options. */
|
||||
|
||||
static void _Noreturn print_help (void);
|
||||
static void _Noreturn print_version (void);
|
||||
_Noreturn static void print_help (void);
|
||||
_Noreturn static void print_version (void);
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
# define IF_SSL(x) x
|
||||
@@ -178,6 +263,9 @@ static struct cmdline_option option_data[] =
|
||||
{ "backups", 0, OPT_BOOLEAN, "backups", -1 },
|
||||
{ "base", 'B', OPT_VALUE, "base", -1 },
|
||||
{ "bind-address", 0, OPT_VALUE, "bindaddress", -1 },
|
||||
#ifdef HAVE_LIBCARES
|
||||
{ "bind-dns-address", 0, OPT_VALUE, "binddnsaddress", -1 },
|
||||
#endif
|
||||
{ "body-data", 0, OPT_VALUE, "bodydata", -1 },
|
||||
{ "body-file", 0, OPT_VALUE, "bodyfile", -1 },
|
||||
{ IF_SSL ("ca-certificate"), 0, OPT_VALUE, "cacertificate", -1 },
|
||||
@@ -190,6 +278,7 @@ static struct cmdline_option option_data[] =
|
||||
{ "config", 0, OPT_VALUE, "chooseconfig", -1 },
|
||||
{ "connect-timeout", 0, OPT_VALUE, "connecttimeout", -1 },
|
||||
{ "continue", 'c', OPT_BOOLEAN, "continue", -1 },
|
||||
{ "convert-file-only", 0, OPT_BOOLEAN, "convertfileonly", -1 },
|
||||
{ "convert-links", 'k', OPT_BOOLEAN, "convertlinks", -1 },
|
||||
{ "content-disposition", 0, OPT_BOOLEAN, "contentdisposition", -1 },
|
||||
{ "content-on-error", 0, OPT_BOOLEAN, "contentonerror", -1 },
|
||||
@@ -202,6 +291,9 @@ static struct cmdline_option option_data[] =
|
||||
{ "directories", 0, OPT_BOOLEAN, "dirstruct", -1 },
|
||||
{ "directory-prefix", 'P', OPT_VALUE, "dirprefix", -1 },
|
||||
{ "dns-cache", 0, OPT_BOOLEAN, "dnscache", -1 },
|
||||
#ifdef HAVE_LIBCARES
|
||||
{ "dns-servers", 0, OPT_VALUE, "dnsservers", -1 },
|
||||
#endif
|
||||
{ "dns-timeout", 0, OPT_VALUE, "dnstimeout", -1 },
|
||||
{ "domains", 'D', OPT_VALUE, "domains", -1 },
|
||||
{ "dont-remove-listing", 0, OPT__DONT_REMOVE_LISTING, NULL, no_argument },
|
||||
@@ -219,10 +311,20 @@ static struct cmdline_option option_data[] =
|
||||
{ "ftp-stmlf", 0, OPT_BOOLEAN, "ftpstmlf", -1 },
|
||||
#endif /* def __VMS */
|
||||
{ "ftp-user", 0, OPT_VALUE, "ftpuser", -1 },
|
||||
#ifdef HAVE_SSL
|
||||
{ "ftps-clear-data-connection", 0, OPT_BOOLEAN, "ftpscleardataconnection", -1 },
|
||||
{ "ftps-fallback-to-ftp", 0, OPT_BOOLEAN, "ftpsfallbacktoftp", -1 },
|
||||
{ "ftps-implicit", 0, OPT_BOOLEAN, "ftpsimplicit", -1 },
|
||||
{ "ftps-resume-ssl", 0, OPT_BOOLEAN, "ftpsresumessl", -1 },
|
||||
#endif
|
||||
{ "glob", 0, OPT_BOOLEAN, "glob", -1 },
|
||||
{ "header", 0, OPT_VALUE, "header", -1 },
|
||||
{ "help", 'h', OPT_FUNCALL, (void *)print_help, no_argument },
|
||||
{ "host-directories", 0, OPT_BOOLEAN, "addhostdir", -1 },
|
||||
#ifdef HAVE_HSTS
|
||||
{ "hsts", 0, OPT_BOOLEAN, "hsts", -1},
|
||||
{ "hsts-file", 0, OPT_VALUE, "hstsfile", -1 },
|
||||
#endif
|
||||
{ "html-extension", 'E', OPT_BOOLEAN, "adjustextension", -1 }, /* deprecated */
|
||||
{ "htmlify", 0, OPT_BOOLEAN, "htmlify", -1 },
|
||||
{ "http-keep-alive", 0, OPT_BOOLEAN, "httpkeepalive", -1 },
|
||||
@@ -239,13 +341,22 @@ static struct cmdline_option option_data[] =
|
||||
{ "inet6-only", '6', OPT_BOOLEAN, "inet6only", -1 },
|
||||
#endif
|
||||
{ "input-file", 'i', OPT_VALUE, "input", -1 },
|
||||
#ifdef HAVE_METALINK
|
||||
{ "input-metalink", 0, OPT_VALUE, "inputmetalink", -1 },
|
||||
#endif
|
||||
{ "iri", 0, OPT_BOOLEAN, "iri", -1 },
|
||||
{ "keep-badhash", 0, OPT_BOOLEAN, "keepbadhash", -1 },
|
||||
{ "keep-session-cookies", 0, OPT_BOOLEAN, "keepsessioncookies", -1 },
|
||||
{ "level", 'l', OPT_VALUE, "reclevel", -1 },
|
||||
{ "limit-rate", 0, OPT_VALUE, "limitrate", -1 },
|
||||
{ "load-cookies", 0, OPT_VALUE, "loadcookies", -1 },
|
||||
{ "local-encoding", 0, OPT_VALUE, "localencoding", -1 },
|
||||
{ "rejected-log", 0, OPT_VALUE, "rejectedlog", -1 },
|
||||
{ "max-redirect", 0, OPT_VALUE, "maxredirect", -1 },
|
||||
#ifdef HAVE_METALINK
|
||||
{ "metalink-index", 0, OPT_VALUE, "metalinkindex", -1 },
|
||||
{ "metalink-over-http", 0, OPT_BOOLEAN, "metalinkoverhttp", -1 },
|
||||
#endif
|
||||
{ "method", 0, OPT_VALUE, "method", -1 },
|
||||
{ "mirror", 'm', OPT_BOOLEAN, "mirror", -1 },
|
||||
{ "no", 'n', OPT__NO, NULL, required_argument },
|
||||
@@ -258,9 +369,13 @@ static struct cmdline_option option_data[] =
|
||||
{ "parent", 0, OPT__PARENT, NULL, optional_argument },
|
||||
{ "passive-ftp", 0, OPT_BOOLEAN, "passiveftp", -1 },
|
||||
{ "password", 0, OPT_VALUE, "password", -1 },
|
||||
{ IF_SSL ("pinnedpubkey"), 0, OPT_VALUE, "pinnedpubkey", -1 },
|
||||
{ "post-data", 0, OPT_VALUE, "postdata", -1 },
|
||||
{ "post-file", 0, OPT_VALUE, "postfile", -1 },
|
||||
{ "prefer-family", 0, OPT_VALUE, "preferfamily", -1 },
|
||||
#ifdef HAVE_METALINK
|
||||
{ "preferred-location", 0, OPT_VALUE, "preferredlocation", -1 },
|
||||
#endif
|
||||
{ "preserve-permissions", 0, OPT_BOOLEAN, "preservepermissions", -1 },
|
||||
{ IF_SSL ("private-key"), 0, OPT_VALUE, "privatekey", -1 },
|
||||
{ IF_SSL ("private-key-type"), 0, OPT_VALUE, "privatekeytype", -1 },
|
||||
@@ -299,9 +414,11 @@ static struct cmdline_option option_data[] =
|
||||
{ "strict-comments", 0, OPT_BOOLEAN, "strictcomments", -1 },
|
||||
{ "timeout", 'T', OPT_VALUE, "timeout", -1 },
|
||||
{ "timestamping", 'N', OPT_BOOLEAN, "timestamping", -1 },
|
||||
{ "if-modified-since", 0, OPT_BOOLEAN, "ifmodifiedsince", -1 },
|
||||
{ "tries", 't', OPT_VALUE, "tries", -1 },
|
||||
{ "unlink", 0, OPT_BOOLEAN, "unlink", -1 },
|
||||
{ "trust-server-names", 0, OPT_BOOLEAN, "trustservernames", -1 },
|
||||
{ "use-askpass", 0, OPT_VALUE, "useaskpass", -1},
|
||||
{ "use-server-timestamps", 0, OPT_BOOLEAN, "useservertimestamps", -1 },
|
||||
{ "user", 0, OPT_VALUE, "user", -1 },
|
||||
{ "user-agent", 'U', OPT_VALUE, "useragent", -1 },
|
||||
@@ -323,6 +440,9 @@ static struct cmdline_option option_data[] =
|
||||
{ "warc-tempdir", 0, OPT_VALUE, "warctempdir", -1 },
|
||||
#ifdef USE_WATT32
|
||||
{ "wdebug", 0, OPT_BOOLEAN, "wdebug", -1 },
|
||||
#endif
|
||||
#ifdef ENABLE_XATTR
|
||||
{ "xattr", 0, OPT_BOOLEAN, "xattr", -1 },
|
||||
#endif
|
||||
};
|
||||
|
||||
@@ -340,8 +460,7 @@ no_prefix (const char *s)
|
||||
|
||||
char *cp = p;
|
||||
int size = 3 + strlen (s) + 1; /* "no-STRING\0" */
|
||||
if (p + size >= buffer + sizeof (buffer))
|
||||
abort ();
|
||||
assert(p + size <= buffer + sizeof (buffer));
|
||||
|
||||
cp[0] = 'n', cp[1] = 'o', cp[2] = '-';
|
||||
strcpy (cp + 3, s);
|
||||
@@ -436,7 +555,7 @@ print_usage (int error)
|
||||
|
||||
/* Print the help message, describing all the available options. If
|
||||
you add an option, be sure to update this list. */
|
||||
static void _Noreturn
|
||||
_Noreturn static void
|
||||
print_help (void)
|
||||
{
|
||||
/* We split the help text this way to ease translation of individual
|
||||
@@ -481,6 +600,10 @@ Logging and input file:\n"),
|
||||
--report-speed=TYPE output bandwidth as TYPE. TYPE can be bits\n"),
|
||||
N_("\
|
||||
-i, --input-file=FILE download URLs found in local or external FILE\n"),
|
||||
#ifdef HAVE_METALINK
|
||||
N_("\
|
||||
--input-metalink=FILE download files covered in local Metalink FILE\n"),
|
||||
#endif
|
||||
N_("\
|
||||
-F, --force-html treat input file as HTML\n"),
|
||||
N_("\
|
||||
@@ -490,6 +613,8 @@ Logging and input file:\n"),
|
||||
--config=FILE specify config file to use\n"),
|
||||
N_("\
|
||||
--no-config do not read any config file\n"),
|
||||
N_("\
|
||||
--rejected-log=FILE log reasons for URL rejection to FILE\n"),
|
||||
"\n",
|
||||
|
||||
N_("\
|
||||
@@ -515,7 +640,10 @@ Download:\n"),
|
||||
-N, --timestamping don't re-retrieve files unless newer than\n\
|
||||
local\n"),
|
||||
N_("\
|
||||
--no-use-server-timestamps don't set the local file's timestamp by\n\
|
||||
--no-if-modified-since don't use conditional if-modified-since get\n\
|
||||
requests in timestamping mode\n"),
|
||||
N_("\
|
||||
--no-use-server-timestamps don't set the local file's timestamp by\n\
|
||||
the one on the server\n"),
|
||||
N_("\
|
||||
-S, --server-response print server response\n"),
|
||||
@@ -523,6 +651,12 @@ Download:\n"),
|
||||
--spider don't download anything\n"),
|
||||
N_("\
|
||||
-T, --timeout=SECONDS set all timeout values to SECONDS\n"),
|
||||
#ifdef HAVE_LIBCARES
|
||||
N_("\
|
||||
--dns-servers=ADDRESSES list of DNS servers to query (comma separated)\n"),
|
||||
N_("\
|
||||
--bind-dns-address=ADDRESS bind DNS resolver to ADDRESS (hostname or IP) on local host\n"),
|
||||
#endif
|
||||
N_("\
|
||||
--dns-timeout=SECS set the DNS lookup timeout to SECS\n"),
|
||||
N_("\
|
||||
@@ -564,6 +698,11 @@ Download:\n"),
|
||||
--password=PASS set both ftp and http password to PASS\n"),
|
||||
N_("\
|
||||
--ask-password prompt for passwords\n"),
|
||||
N_("\
|
||||
--use-askpass=COMMAND specify credential handler for requesting \n\
|
||||
username and password. If no COMMAND is \n\
|
||||
specified the WGET_ASKPASS or the SSH_ASKPASS \n\
|
||||
environment variable is used.\n"),
|
||||
N_("\
|
||||
--no-iri turn off IRI support\n"),
|
||||
N_("\
|
||||
@@ -572,6 +711,20 @@ Download:\n"),
|
||||
--remote-encoding=ENC use ENC as the default remote encoding\n"),
|
||||
N_("\
|
||||
--unlink remove file before clobber\n"),
|
||||
#ifdef HAVE_METALINK
|
||||
N_("\
|
||||
--keep-badhash keep files with checksum mismatch (append .badhash)\n"),
|
||||
N_("\
|
||||
--metalink-index=NUMBER Metalink application/metalink4+xml metaurl ordinal NUMBER\n"),
|
||||
N_("\
|
||||
--metalink-over-http use Metalink metadata from HTTP response headers\n"),
|
||||
N_("\
|
||||
--preferred-location preferred location for Metalink resources\n"),
|
||||
#endif
|
||||
#ifdef ENABLE_XATTR
|
||||
N_("\
|
||||
--no-xattr turn off storage of metadata in extended file attributes\n"),
|
||||
#endif
|
||||
"\n",
|
||||
|
||||
N_("\
|
||||
@@ -674,6 +827,11 @@ HTTPS (SSL/TLS) options:\n"),
|
||||
--ca-directory=DIR directory where hash list of CAs is stored\n"),
|
||||
N_("\
|
||||
--crl-file=FILE file with bundle of CRLs\n"),
|
||||
N_("\
|
||||
--pinnedpubkey=FILE/HASHES Public key (PEM/DER) file, or any number\n\
|
||||
of base64 encoded sha256 hashes preceded by\n\
|
||||
\'sha256//\' and separated by \';\', to verify\n\
|
||||
peer against\n"),
|
||||
#if defined(HAVE_LIBSSL) || defined(HAVE_LIBSSL32)
|
||||
N_("\
|
||||
--random-file=FILE file with random data for seeding the SSL PRNG\n"),
|
||||
@@ -685,6 +843,16 @@ HTTPS (SSL/TLS) options:\n"),
|
||||
"\n",
|
||||
#endif /* HAVE_SSL */
|
||||
|
||||
#ifdef HAVE_HSTS
|
||||
N_("\
|
||||
HSTS options:\n"),
|
||||
N_("\
|
||||
--no-hsts disable HSTS\n"),
|
||||
N_("\
|
||||
--hsts-file path of HSTS database (will override default)\n"),
|
||||
"\n",
|
||||
#endif
|
||||
|
||||
N_("\
|
||||
FTP options:\n"),
|
||||
#ifdef __VMS
|
||||
@@ -707,6 +875,20 @@ FTP options:\n"),
|
||||
--retr-symlinks when recursing, get linked-to files (not dir)\n"),
|
||||
"\n",
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
N_("\
|
||||
FTPS options:\n"),
|
||||
N_("\
|
||||
--ftps-implicit use implicit FTPS (default port is 990)\n"),
|
||||
N_("\
|
||||
--ftps-resume-ssl resume the SSL/TLS session started in the control connection when\n"
|
||||
" opening a data connection\n"),
|
||||
N_("\
|
||||
--ftps-clear-data-connection cipher the control channel only; all the data will be in plaintext\n"),
|
||||
N_("\
|
||||
--ftps-fallback-to-ftp fall back to FTP if FTPS is not supported in the target server\n"),
|
||||
#endif
|
||||
|
||||
N_("\
|
||||
WARC options:\n"),
|
||||
N_("\
|
||||
@@ -743,6 +925,8 @@ Recursive download:\n"),
|
||||
N_("\
|
||||
-k, --convert-links make links in downloaded HTML or CSS point to\n\
|
||||
local files\n"),
|
||||
N_("\
|
||||
--convert-file-only convert the file part of the URLs only (usually known as the basename)\n"),
|
||||
N_("\
|
||||
--backups=N before writing file X, rotate up to N backup files\n"),
|
||||
|
||||
@@ -856,6 +1040,103 @@ prompt_for_password (void)
|
||||
return getpass("");
|
||||
}
|
||||
|
||||
|
||||
/* Execute external application opt.use_askpass */
|
||||
static void
|
||||
run_use_askpass (char *question, char **answer)
|
||||
{
|
||||
char tmp[1024];
|
||||
pid_t pid;
|
||||
int status;
|
||||
int com[2];
|
||||
ssize_t bytes = 0;
|
||||
char *argv[3], *p;
|
||||
posix_spawn_file_actions_t fa;
|
||||
|
||||
if (pipe (com) == -1)
|
||||
{
|
||||
fprintf (stderr, _("Cannot create pipe\n"));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
status = posix_spawn_file_actions_init (&fa);
|
||||
if (status)
|
||||
{
|
||||
fprintf (stderr,
|
||||
_("Error initializing spawn file actions for use-askpass: %d\n"),
|
||||
status);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
status = posix_spawn_file_actions_adddup2 (&fa, com[1], STDOUT_FILENO);
|
||||
if (status)
|
||||
{
|
||||
fprintf (stderr,
|
||||
_("Error setting spawn file actions for use-askpass: %d\n"),
|
||||
status);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
/* C89 initializer lists must be computable at load time,
|
||||
* thus this explicit initialization. */
|
||||
argv[0] = opt.use_askpass;
|
||||
argv[1] = question;
|
||||
argv[2] = NULL;
|
||||
|
||||
status = posix_spawnp (&pid, opt.use_askpass, &fa, NULL, argv, environ);
|
||||
if (status)
|
||||
{
|
||||
fprintf (stderr, "Error spawning %s: %d\n", opt.use_askpass, status);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
/* Parent process reads from child. */
|
||||
close (com[1]);
|
||||
bytes = read (com[0], tmp, sizeof (tmp) - 1);
|
||||
if (bytes <= 0)
|
||||
{
|
||||
fprintf (stderr,
|
||||
_("Error reading response from command \"%s %s\": %s\n"),
|
||||
opt.use_askpass, question, strerror (errno));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
/* Make sure there is a trailing 0 */
|
||||
tmp[bytes] = '\0';
|
||||
|
||||
/* Remove a possible new line */
|
||||
if ((p = strpbrk (tmp, "\r\n")))
|
||||
bytes = p - tmp;
|
||||
|
||||
*answer = xmemdup0 (tmp, bytes);
|
||||
}
|
||||
|
||||
/* set the user name and password*/
|
||||
static void
|
||||
use_askpass (struct url *u)
|
||||
{
|
||||
static char question[1024];
|
||||
|
||||
if (u->user == NULL || u->user[0] == '\0')
|
||||
{
|
||||
snprintf (question, sizeof (question), _("Username for '%s%s': "),
|
||||
scheme_leading_string(u->scheme), u->host);
|
||||
/* Prompt for username */
|
||||
run_use_askpass (question, &u->user);
|
||||
if (opt.recursive)
|
||||
opt.user = xstrdup (u->user);
|
||||
}
|
||||
|
||||
if (u->passwd == NULL || u->passwd[0] == '\0')
|
||||
{
|
||||
snprintf(question, sizeof (question), _("Password for '%s%s@%s': "),
|
||||
scheme_leading_string (u->scheme), u->user, u->host);
|
||||
/* Prompt for password */
|
||||
run_use_askpass (question, &u->passwd);
|
||||
if (opt.recursive)
|
||||
opt.passwd = xstrdup (u->passwd);
|
||||
}
|
||||
}
|
||||
/* Function that prints the line argument while limiting it
|
||||
to at most line_length. prefix is printed on the first line
|
||||
and an appropriate number of spaces are added on subsequent
|
||||
@@ -874,7 +1155,10 @@ format_and_print_line (const char *prefix, const char *line,
|
||||
line_dup = xstrdup (line);
|
||||
|
||||
if (printf ("%s", prefix) < 0)
|
||||
return -1;
|
||||
{
|
||||
xfree (line_dup);
|
||||
return -1;
|
||||
}
|
||||
|
||||
/* Wrap to new line after prefix. */
|
||||
remaining_chars = 0;
|
||||
@@ -889,7 +1173,10 @@ format_and_print_line (const char *prefix, const char *line,
|
||||
if (remaining_chars <= (int) strlen (token))
|
||||
{
|
||||
if (printf ("\n%*c", TABULATION, ' ') < 0)
|
||||
return -1;
|
||||
{
|
||||
xfree (line_dup);
|
||||
return -1;
|
||||
}
|
||||
remaining_chars = line_length - TABULATION;
|
||||
}
|
||||
if (printf ("%s ", token) < 0)
|
||||
@@ -902,13 +1189,16 @@ format_and_print_line (const char *prefix, const char *line,
|
||||
}
|
||||
|
||||
if (printf ("\n") < 0)
|
||||
return -1;
|
||||
{
|
||||
xfree (line_dup);
|
||||
return -1;
|
||||
}
|
||||
|
||||
xfree (line_dup);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void _Noreturn
|
||||
_Noreturn static void
|
||||
print_version (void)
|
||||
{
|
||||
const char *wgetrc_title = _("Wgetrc: ");
|
||||
@@ -986,7 +1276,7 @@ print_version (void)
|
||||
/* TRANSLATORS: When available, an actual copyright character
|
||||
(circle-c) should be used in preference to "(C)". */
|
||||
if (printf (_("\
|
||||
Copyright (C) %s Free Software Foundation, Inc.\n"), "2014") < 0)
|
||||
Copyright (C) %s Free Software Foundation, Inc.\n"), "2015") < 0)
|
||||
exit (WGET_EXIT_IO_FAIL);
|
||||
if (fputs (_("\
|
||||
License GPLv3+: GNU GPL version 3 or later\n\
|
||||
@@ -1167,7 +1457,8 @@ main (int argc, char **argv)
|
||||
append_to_log = true;
|
||||
break;
|
||||
case OPT__EXECUTE:
|
||||
run_command (optarg);
|
||||
if (optarg) /* check silences static analyzer */
|
||||
run_command (optarg);
|
||||
break;
|
||||
case OPT__NO:
|
||||
{
|
||||
@@ -1245,11 +1536,14 @@ main (int argc, char **argv)
|
||||
/* All user options have now been processed, so it's now safe to do
|
||||
interoption dependency checks. */
|
||||
|
||||
if (opt.noclobber && opt.convert_links)
|
||||
if (opt.noclobber && (opt.convert_links || opt.convert_file_only))
|
||||
{
|
||||
fprintf (stderr,
|
||||
_("Both --no-clobber and --convert-links were specified,"
|
||||
" only --convert-links will be used.\n"));
|
||||
opt.convert_links ?
|
||||
_("Both --no-clobber and --convert-links were specified,"
|
||||
" only --convert-links will be used.\n") :
|
||||
_("Both --no-clobber and --convert-file-only were specified,"
|
||||
" only --convert-file-only will be used.\n"));
|
||||
opt.noclobber = false;
|
||||
}
|
||||
|
||||
@@ -1272,6 +1566,12 @@ main (int argc, char **argv)
|
||||
if (opt.verbose == -1)
|
||||
opt.verbose = !opt.quiet;
|
||||
|
||||
if (!opt.verbose && opt.show_progress == -1)
|
||||
opt.show_progress = false;
|
||||
|
||||
if (opt.quiet && opt.show_progress == -1)
|
||||
opt.show_progress = false;
|
||||
|
||||
/* Sanity checks. */
|
||||
if (opt.verbose && opt.quiet)
|
||||
{
|
||||
@@ -1297,11 +1597,11 @@ Can't timestamp and not clobber old files at the same time.\n"));
|
||||
#endif
|
||||
if (opt.output_document)
|
||||
{
|
||||
if (opt.convert_links
|
||||
if ((opt.convert_links || opt.convert_file_only)
|
||||
&& (nurl > 1 || opt.page_requisites || opt.recursive))
|
||||
{
|
||||
fputs (_("\
|
||||
Cannot specify both -k and -O if multiple URLs are given, or in combination\n\
|
||||
Cannot specify both -k or --convert-file-only and -O if multiple URLs are given, or in combination\n\
|
||||
with -p or -r. See the manual for details.\n\n"), stderr);
|
||||
print_usage (1);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
@@ -1388,7 +1688,11 @@ for details.\n\n"));
|
||||
opt.always_rest = false;
|
||||
}
|
||||
|
||||
if (!nurl && !opt.input_filename)
|
||||
if (!nurl && !opt.input_filename
|
||||
#ifdef HAVE_METALINK
|
||||
&& !opt.input_metalink
|
||||
#endif
|
||||
)
|
||||
{
|
||||
/* No URL specified. */
|
||||
fprintf (stderr, _("%s: missing URL\n"), exec_name);
|
||||
@@ -1438,7 +1742,7 @@ for details.\n\n"));
|
||||
else if (opt.method)
|
||||
{
|
||||
fprintf (stderr, _("You cannot use --post-data or --post-file along with --method. "
|
||||
"--method expects data through --body-data and --body-file options"));
|
||||
"--method expects data through --body-data and --body-file options\n"));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
}
|
||||
@@ -1517,6 +1821,16 @@ for details.\n\n"));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
if (opt.use_askpass)
|
||||
{
|
||||
if (opt.use_askpass[0] == '\0')
|
||||
{
|
||||
fprintf (stderr,
|
||||
_("use-askpass requires a string or either environment variable WGET_ASKPASS or SSH_ASKPASS to be set.\n"));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
}
|
||||
|
||||
#ifdef USE_WATT32
|
||||
if (opt.wdebug)
|
||||
dbug_init();
|
||||
@@ -1579,7 +1893,7 @@ for details.\n\n"));
|
||||
}
|
||||
else
|
||||
{
|
||||
struct_fstat st;
|
||||
struct stat st;
|
||||
|
||||
#ifdef __VMS
|
||||
/* Common fopen() optional arguments:
|
||||
@@ -1602,15 +1916,72 @@ for details.\n\n"));
|
||||
if (fstat (fileno (output_stream), &st) == 0 && S_ISREG (st.st_mode))
|
||||
output_stream_regular = true;
|
||||
}
|
||||
if (!output_stream_regular && opt.convert_links)
|
||||
if (!output_stream_regular && (opt.convert_links || opt.recursive))
|
||||
{
|
||||
fprintf (stderr, _("-k can be used together with -O only if \
|
||||
fprintf (stderr, _("-k or -r can be used together with -O only if \
|
||||
outputting to a regular file.\n"));
|
||||
print_usage (1);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
if (!output_stream_regular && (opt.convert_links || opt.convert_file_only))
|
||||
{
|
||||
fprintf (stderr, _("--convert-links or --convert-file-only can be used together \
|
||||
only if outputting to a regular file.\n"));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
}
|
||||
|
||||
#ifdef HAVE_LIBCARES
|
||||
if (opt.bind_dns_address || opt.dns_servers)
|
||||
{
|
||||
if (ares_library_init (ARES_LIB_INIT_ALL))
|
||||
{
|
||||
fprintf (stderr, _("Failed to init libcares\n"));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
if (ares_init (&ares) != ARES_SUCCESS)
|
||||
{
|
||||
fprintf (stderr, _("Failed to init c-ares channel\n"));
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
|
||||
if (opt.bind_dns_address)
|
||||
{
|
||||
struct in_addr a4;
|
||||
#ifdef ENABLE_IPV6
|
||||
struct in6_addr a6;
|
||||
#endif
|
||||
|
||||
if (inet_pton (AF_INET, opt.bind_dns_address, &a4) == 1)
|
||||
{
|
||||
ares_set_local_ip4 (ares, ntohl (a4.s_addr));
|
||||
}
|
||||
#ifdef ENABLE_IPV6
|
||||
else if (inet_pton (AF_INET6, opt.bind_dns_address, &a6) == 1)
|
||||
{
|
||||
ares_set_local_ip6 (ares, (unsigned char *) &a6);
|
||||
}
|
||||
#endif
|
||||
else
|
||||
{
|
||||
fprintf (stderr, _("Failed to parse IP address '%s'\n"), opt.bind_dns_address);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
}
|
||||
|
||||
if (opt.dns_servers)
|
||||
{
|
||||
int result;
|
||||
|
||||
if ((result = ares_set_servers_csv (ares, opt.dns_servers)) != ARES_SUCCESS)
|
||||
{
|
||||
fprintf (stderr, _("Failed to set DNS server(s) '%s' (%d)\n"), opt.dns_servers, result);
|
||||
exit (WGET_EXIT_GENERIC_ERROR);
|
||||
}
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifdef __VMS
|
||||
/* Set global ODS5 flag according to the specified destination (if
|
||||
any), otherwise according to the current default device.
|
||||
@@ -1645,6 +2016,16 @@ outputting to a regular file.\n"));
|
||||
signal (SIGWINCH, progress_handle_sigwinch);
|
||||
#endif
|
||||
|
||||
#ifdef HAVE_HSTS
|
||||
/* Load the HSTS database.
|
||||
Maybe all the URLs are FTP(S), in which case HSTS would not be needed,
|
||||
but this is the best place to do it, and it shouldn't be a critical
|
||||
performance hit.
|
||||
*/
|
||||
if (opt.hsts)
|
||||
load_hsts ();
|
||||
#endif
|
||||
|
||||
/* Retrieve the URLs from argument list. */
|
||||
for (t = url; *t; t++)
|
||||
{
|
||||
@@ -1668,13 +2049,26 @@ outputting to a regular file.\n"));
|
||||
}
|
||||
else
|
||||
{
|
||||
/* Request credentials if use_askpass is set. */
|
||||
if (opt.use_askpass)
|
||||
use_askpass (url_parsed);
|
||||
|
||||
if ((opt.recursive || opt.page_requisites)
|
||||
&& (url_scheme (*t) != SCHEME_FTP || url_uses_proxy (url_parsed)))
|
||||
&& ((url_scheme (*t) != SCHEME_FTP
|
||||
#ifdef HAVE_SSL
|
||||
&& url_scheme (*t) != SCHEME_FTPS
|
||||
#endif
|
||||
)
|
||||
|| url_uses_proxy (url_parsed)))
|
||||
{
|
||||
int old_follow_ftp = opt.follow_ftp;
|
||||
|
||||
/* Turn opt.follow_ftp on in case of recursive FTP retrieval */
|
||||
if (url_scheme (*t) == SCHEME_FTP)
|
||||
if (url_scheme (*t) == SCHEME_FTP
|
||||
#ifdef HAVE_SSL
|
||||
|| url_scheme (*t) == SCHEME_FTPS
|
||||
#endif
|
||||
)
|
||||
opt.follow_ftp = 1;
|
||||
|
||||
retrieve_tree (url_parsed, NULL);
|
||||
@@ -1682,10 +2076,10 @@ outputting to a regular file.\n"));
|
||||
opt.follow_ftp = old_follow_ftp;
|
||||
}
|
||||
else
|
||||
{
|
||||
retrieve_url (url_parsed, *t, &filename, &redirected_URL, NULL,
|
||||
&dt, opt.recursive, iri, true);
|
||||
}
|
||||
{
|
||||
retrieve_url (url_parsed, *t, &filename, &redirected_URL, NULL,
|
||||
&dt, opt.recursive, iri, true);
|
||||
}
|
||||
|
||||
if (opt.delete_after && filename != NULL && file_exists_p (filename))
|
||||
{
|
||||
@@ -1713,6 +2107,57 @@ outputting to a regular file.\n"));
|
||||
opt.input_filename);
|
||||
}
|
||||
|
||||
#ifdef HAVE_METALINK
|
||||
/* Finally, from metlink file, if any. */
|
||||
if (opt.input_metalink)
|
||||
{
|
||||
metalink_error_t meta_err;
|
||||
uerr_t retr_err;
|
||||
metalink_t *metalink;
|
||||
|
||||
meta_err = metalink_parse_file (opt.input_metalink, &metalink);
|
||||
|
||||
if (meta_err)
|
||||
{
|
||||
logprintf (LOG_NOTQUIET, _("Unable to parse metalink file %s.\n"),
|
||||
opt.input_metalink);
|
||||
retr_err = METALINK_PARSE_ERROR;
|
||||
}
|
||||
else
|
||||
{
|
||||
/* We need to sort the resources if preferred location
|
||||
was specified by the user. */
|
||||
if (opt.preferred_location && opt.preferred_location[0])
|
||||
{
|
||||
metalink_file_t **mfile_ptr;
|
||||
for (mfile_ptr = metalink->files; *mfile_ptr; mfile_ptr++)
|
||||
{
|
||||
metalink_resource_t **mres_ptr;
|
||||
metalink_file_t *mfile = *mfile_ptr;
|
||||
size_t mres_count = 0;
|
||||
|
||||
for (mres_ptr = mfile->resources; *mres_ptr; mres_ptr++)
|
||||
mres_count++;
|
||||
|
||||
stable_sort (mfile->resources,
|
||||
mres_count,
|
||||
sizeof (metalink_resource_t *),
|
||||
metalink_res_cmp);
|
||||
}
|
||||
}
|
||||
retr_err = retrieve_from_metalink (metalink);
|
||||
if (retr_err != RETROK)
|
||||
{
|
||||
logprintf (LOG_NOTQUIET,
|
||||
_("Could not download all resources from %s.\n"),
|
||||
quote (opt.input_metalink));
|
||||
}
|
||||
metalink_delete (metalink);
|
||||
}
|
||||
inform_exit_status (retr_err);
|
||||
}
|
||||
#endif /* HAVE_METALINK */
|
||||
|
||||
/* Print broken links. */
|
||||
if (opt.recursive && opt.spider)
|
||||
print_broken_links ();
|
||||
@@ -1752,7 +2197,12 @@ outputting to a regular file.\n"));
|
||||
if (opt.cookies_output)
|
||||
save_cookies ();
|
||||
|
||||
if (opt.convert_links && !opt.delete_after)
|
||||
#ifdef HAVE_HSTS
|
||||
if (opt.hsts && hsts_store)
|
||||
save_hsts ();
|
||||
#endif
|
||||
|
||||
if ((opt.convert_links || opt.convert_file_only) && !opt.delete_after)
|
||||
convert_all_links ();
|
||||
|
||||
cleanup ();
|
||||
|
||||
1599
src/metalink.c
Normal file
1599
src/metalink.c
Normal file
File diff suppressed because it is too large
Load Diff
75
src/metalink.h
Normal file
75
src/metalink.h
Normal file
@@ -0,0 +1,75 @@
|
||||
/* Declarations for metalink.c.
|
||||
Copyright (C) 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
GNU Wget is free software; you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation; either version 3 of the License, or
|
||||
(at your option) any later version.
|
||||
|
||||
GNU Wget is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with Wget. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
Additional permission under GNU GPL version 3 section 7
|
||||
|
||||
If you modify this program, or any covered work, by linking or
|
||||
combining it with the OpenSSL project's OpenSSL library (or a
|
||||
modified version of that library), containing parts covered by the
|
||||
terms of the OpenSSL or SSLeay licenses, the Free Software Foundation
|
||||
grants you additional permission to convey the resulting work.
|
||||
Corresponding Source for a non-source form of such a combination
|
||||
shall include the source code for the parts of OpenSSL used as well
|
||||
as that of the covered work. */
|
||||
#if ! defined METALINK_H && defined HAVE_METALINK
|
||||
#define METALINK_H
|
||||
|
||||
#include <metalink/metalink_types.h>
|
||||
#include "wget.h"
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
# define RES_TYPE_SUPPORTED(x)\
|
||||
((!x) || !strcmp (x, "http") || !strcmp (x, "https") || !strcmp (x, "ftp") || !strcmp (x, "ftps"))
|
||||
#else
|
||||
# define RES_TYPE_SUPPORTED(x)\
|
||||
((!x) || !strcmp (x, "ftp") || !strcmp (x, "http"))
|
||||
#endif
|
||||
|
||||
#define DEFAULT_PRI 999999
|
||||
#define VALID_PRI_RANGE(x) ((x) > 0 && (x) < 1000000)
|
||||
|
||||
uerr_t retrieve_from_metalink (const metalink_t *metalink);
|
||||
|
||||
int metalink_res_cmp (const void *res1, const void *res2);
|
||||
int metalink_meta_cmp (const void* meta1, const void* meta2);
|
||||
|
||||
int metalink_check_safe_path (const char *path);
|
||||
|
||||
char *last_component (char const *name);
|
||||
void replace_metalink_basename (char **name, char *ref);
|
||||
char *get_metalink_basename (char *name);
|
||||
void append_suffix_number (char **str, const char *sep, wgint num);
|
||||
void clean_metalink_string (char **str);
|
||||
void dequote_metalink_string (char **str);
|
||||
void badhash_suffix (char *name);
|
||||
void badhash_or_remove (char *name);
|
||||
uerr_t fetch_metalink_file (const char *url_str,
|
||||
bool resume, bool metalink_http,
|
||||
const char *filename, char **destname);
|
||||
|
||||
bool find_key_value (const char *start,
|
||||
const char *end,
|
||||
const char *key,
|
||||
char **value);
|
||||
bool has_key (const char *start, const char *end, const char *key);
|
||||
const char *find_key_values (const char *start,
|
||||
const char *end,
|
||||
char **key,
|
||||
char **value);
|
||||
|
||||
#endif /* METALINK_H */
|
||||
@@ -1,7 +1,7 @@
|
||||
/* mswindows.c -- Windows-specific support
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -53,16 +53,13 @@ as that of the covered work. */
|
||||
#endif
|
||||
|
||||
|
||||
/* Defined in log.c. */
|
||||
void log_request_redirect_output (const char *);
|
||||
|
||||
/* Windows version of xsleep in utils.c. */
|
||||
|
||||
void
|
||||
xsleep (double seconds)
|
||||
{
|
||||
#if defined(HAVE_USLEEP) && defined(HAVE_SLEEP)
|
||||
if (seconds > 1000)
|
||||
if (seconds >= 1)
|
||||
{
|
||||
/* Explained in utils.c. */
|
||||
sleep (seconds);
|
||||
@@ -98,7 +95,7 @@ static void
|
||||
ws_hangup (const char *reason)
|
||||
{
|
||||
fprintf (stderr, _("Continuing in background.\n"));
|
||||
log_request_redirect_output (reason);
|
||||
redirect_output (true, reason);
|
||||
|
||||
/* Detach process from the current console. Under Windows 9x, if we
|
||||
were launched from a 16-bit process (which is usually the case;
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/* Declarations for windows
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/* Read and parse the .netrc file to get hosts, accounts, and passwords.
|
||||
Copyright (C) 1996, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Copyright (C) 1996, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
@@ -75,7 +75,7 @@ search_netrc (const char *host, const char **acc, const char **passwd,
|
||||
#ifdef __VMS
|
||||
|
||||
int err;
|
||||
struct_stat buf;
|
||||
struct stat buf;
|
||||
char *path = "SYS$LOGIN:.netrc";
|
||||
|
||||
netrc_list = NULL;
|
||||
@@ -94,7 +94,7 @@ search_netrc (const char *host, const char **acc, const char **passwd,
|
||||
if (home)
|
||||
{
|
||||
int err;
|
||||
struct_stat buf;
|
||||
struct stat buf;
|
||||
char *path = (char *)alloca (strlen (home) + 1
|
||||
+ strlen (NETRC_FILE_NAME) + 1);
|
||||
sprintf (path, "%s/%s", home, NETRC_FILE_NAME);
|
||||
@@ -439,7 +439,7 @@ free_netrc(acc_t *l)
|
||||
int
|
||||
main (int argc, char **argv)
|
||||
{
|
||||
struct_stat sb;
|
||||
struct stat sb;
|
||||
char *program_name, *file, *target;
|
||||
acc_t *head, *a;
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Declarations for netrc.c
|
||||
Copyright (C) 1996, 1996, 1997, 2007, 2008, 2009, 2010, 2011 Free
|
||||
Software Foundation, Inc.
|
||||
Copyright (C) 1996, 1996, 1997, 2007, 2008, 2009, 2010, 2011, 2015
|
||||
Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
147
src/openssl.c
147
src/openssl.c
@@ -1,6 +1,6 @@
|
||||
/* SSL support via OpenSSL library.
|
||||
Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008,
|
||||
2009, 2010, 2011, 2012 Free Software Foundation, Inc.
|
||||
2009, 2010, 2011, 2012, 2015 Free Software Foundation, Inc.
|
||||
Originally contributed by Christian Fraenkel.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
@@ -35,6 +35,7 @@ as that of the covered work. */
|
||||
#include <errno.h>
|
||||
#include <unistd.h>
|
||||
#include <string.h>
|
||||
#include <xalloc.h>
|
||||
|
||||
#include <openssl/ssl.h>
|
||||
#include <openssl/x509v3.h>
|
||||
@@ -203,18 +204,20 @@ ssl_init (void)
|
||||
#endif
|
||||
SSL_library_init ();
|
||||
SSL_load_error_strings ();
|
||||
#if OPENSSL_VERSION_NUMBER < 0x10100000L
|
||||
SSLeay_add_all_algorithms ();
|
||||
SSLeay_add_ssl_algorithms ();
|
||||
#endif
|
||||
|
||||
switch (opt.secure_protocol)
|
||||
{
|
||||
#ifndef OPENSSL_NO_SSL2
|
||||
#if !defined OPENSSL_NO_SSL2 && OPENSSL_VERSION_NUMBER < 0x10100000L
|
||||
case secure_protocol_sslv2:
|
||||
meth = SSLv2_client_method ();
|
||||
break;
|
||||
#endif
|
||||
|
||||
#ifndef OPENSSL_NO_SSL3
|
||||
#ifndef OPENSSL_NO_SSL3_METHOD
|
||||
case secure_protocol_sslv3:
|
||||
meth = SSLv3_client_method ();
|
||||
break;
|
||||
@@ -292,10 +295,17 @@ ssl_init (void)
|
||||
/* Use the private key from the cert file unless otherwise specified. */
|
||||
if (opt.cert_file && !opt.private_key)
|
||||
{
|
||||
opt.private_key = opt.cert_file;
|
||||
opt.private_key = xstrdup (opt.cert_file);
|
||||
opt.private_key_type = opt.cert_type;
|
||||
}
|
||||
|
||||
/* Use cert from private key file unless otherwise specified. */
|
||||
if (opt.private_key && !opt.cert_file)
|
||||
{
|
||||
opt.cert_file = xstrdup (opt.private_key);
|
||||
opt.cert_type = opt.private_key_type;
|
||||
}
|
||||
|
||||
if (opt.cert_file)
|
||||
if (SSL_CTX_use_certificate_file (ssl_ctx, opt.cert_file,
|
||||
key_type_to_ssl_type (opt.cert_type))
|
||||
@@ -327,6 +337,7 @@ ssl_init (void)
|
||||
struct openssl_transport_context
|
||||
{
|
||||
SSL *conn; /* SSL connection handle */
|
||||
SSL_SESSION *sess; /* SSL session info */
|
||||
char *last_error; /* last error printed with openssl_errstr */
|
||||
};
|
||||
|
||||
@@ -498,6 +509,22 @@ ssl_connect_with_timeout_callback(void *arg)
|
||||
ctx->result = SSL_connect(ctx->ssl);
|
||||
}
|
||||
|
||||
static const char *
|
||||
_sni_hostname(const char *hostname)
|
||||
{
|
||||
size_t len = strlen(hostname);
|
||||
|
||||
char *sni_hostname = xmemdup(hostname, len + 1);
|
||||
|
||||
/* Remove trailing dot(s) to fix #47408.
|
||||
* Regarding RFC 6066 (SNI): The hostname is represented as a byte
|
||||
* string using ASCII encoding without a trailing dot. */
|
||||
while (len && sni_hostname[--len] == '.')
|
||||
sni_hostname[len] = 0;
|
||||
|
||||
return sni_hostname;
|
||||
}
|
||||
|
||||
/* Perform the SSL handshake on file descriptor FD, which is assumed
|
||||
to be connected to an SSL server. The SSL handle provided by
|
||||
OpenSSL is registered with the file descriptor FD using
|
||||
@@ -507,7 +534,7 @@ ssl_connect_with_timeout_callback(void *arg)
|
||||
Returns true on success, false on failure. */
|
||||
|
||||
bool
|
||||
ssl_connect_wget (int fd, const char *hostname)
|
||||
ssl_connect_wget (int fd, const char *hostname, int *continue_session)
|
||||
{
|
||||
SSL *conn;
|
||||
struct scwt_context scwt_ctx;
|
||||
@@ -520,11 +547,16 @@ ssl_connect_wget (int fd, const char *hostname)
|
||||
if (!conn)
|
||||
goto error;
|
||||
#if OPENSSL_VERSION_NUMBER >= 0x0090806fL && !defined(OPENSSL_NO_TLSEXT)
|
||||
/* If the SSL library was build with support for ServerNameIndication
|
||||
/* If the SSL library was built with support for ServerNameIndication
|
||||
then use it whenever we have a hostname. If not, don't, ever. */
|
||||
if (! is_valid_ip_address (hostname))
|
||||
{
|
||||
if (! SSL_set_tlsext_host_name (conn, hostname))
|
||||
const char *sni_hostname = _sni_hostname(hostname);
|
||||
|
||||
long rc = SSL_set_tlsext_host_name (conn, sni_hostname);
|
||||
xfree(sni_hostname);
|
||||
|
||||
if (rc == 0)
|
||||
{
|
||||
DEBUGP (("Failed to set TLS server-name indication."));
|
||||
goto error;
|
||||
@@ -532,6 +564,14 @@ ssl_connect_wget (int fd, const char *hostname)
|
||||
}
|
||||
#endif
|
||||
|
||||
if (continue_session)
|
||||
{
|
||||
/* attempt to resume a previous SSL session */
|
||||
ctx = (struct openssl_transport_context *) fd_transport_context (*continue_session);
|
||||
if (!ctx || !ctx->sess || !SSL_set_session (conn, ctx->sess))
|
||||
goto error;
|
||||
}
|
||||
|
||||
#ifndef FD_TO_SOCKET
|
||||
# define FD_TO_SOCKET(X) (X)
|
||||
#endif
|
||||
@@ -545,11 +585,14 @@ ssl_connect_wget (int fd, const char *hostname)
|
||||
DEBUGP (("SSL handshake timed out.\n"));
|
||||
goto timeout;
|
||||
}
|
||||
if (scwt_ctx.result <= 0 || SSL_state(conn) != SSL_ST_OK)
|
||||
if (scwt_ctx.result <= 0 || !SSL_is_init_finished(conn))
|
||||
goto error;
|
||||
|
||||
ctx = xnew0 (struct openssl_transport_context);
|
||||
ctx->conn = conn;
|
||||
ctx->sess = SSL_get0_session (conn);
|
||||
if (!ctx->sess)
|
||||
logprintf (LOG_NOTQUIET, "WARNING: Could not save SSL session data for socket %d\n", fd);
|
||||
|
||||
/* Register FD with Wget's transport layer, i.e. arrange that our
|
||||
functions are used for reading, writing, and polling. */
|
||||
@@ -631,6 +674,65 @@ static char *_get_rfc2253_formatted (X509_NAME *name)
|
||||
return out ? out : xstrdup("");
|
||||
}
|
||||
|
||||
/*
|
||||
* Heavily modified from:
|
||||
* https://www.owasp.org/index.php/Certificate_and_Public_Key_Pinning#OpenSSL
|
||||
*/
|
||||
static bool
|
||||
pkp_pin_peer_pubkey (X509* cert, const char *pinnedpubkey)
|
||||
{
|
||||
/* Scratch */
|
||||
int len1 = 0, len2 = 0;
|
||||
char *buff1 = NULL, *temp = NULL;
|
||||
|
||||
/* Result is returned to caller */
|
||||
bool result = false;
|
||||
|
||||
/* if a path wasn't specified, don't pin */
|
||||
if (!pinnedpubkey)
|
||||
return true;
|
||||
|
||||
if (!cert)
|
||||
return result;
|
||||
|
||||
/* Begin Gyrations to get the subjectPublicKeyInfo */
|
||||
/* Thanks to Viktor Dukhovni on the OpenSSL mailing list */
|
||||
|
||||
/* https://groups.google.com/group/mailing.openssl.users/browse_thread
|
||||
/thread/d61858dae102c6c7 */
|
||||
len1 = i2d_X509_PUBKEY (X509_get_X509_PUBKEY (cert), NULL);
|
||||
if (len1 < 1)
|
||||
goto cleanup; /* failed */
|
||||
|
||||
/* https://www.openssl.org/docs/crypto/buffer.html */
|
||||
buff1 = temp = OPENSSL_malloc (len1);
|
||||
if (!buff1)
|
||||
goto cleanup; /* failed */
|
||||
|
||||
/* https://www.openssl.org/docs/crypto/d2i_X509.html */
|
||||
len2 = i2d_X509_PUBKEY (X509_get_X509_PUBKEY (cert), (unsigned char **) &temp);
|
||||
|
||||
/*
|
||||
* These checks are verifying we got back the same values as when we
|
||||
* sized the buffer. It's pretty weak since they should always be the
|
||||
* same. But it gives us something to test.
|
||||
*/
|
||||
if ((len1 != len2) || !temp || ((temp - buff1) != len1))
|
||||
goto cleanup; /* failed */
|
||||
|
||||
/* End Gyrations */
|
||||
|
||||
/* The one good exit point */
|
||||
result = wg_pin_peer_pubkey (pinnedpubkey, buff1, len1);
|
||||
|
||||
cleanup:
|
||||
/* https://www.openssl.org/docs/crypto/buffer.html */
|
||||
if (NULL != buff1)
|
||||
OPENSSL_free (buff1);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/* Verify the validity of the certificate presented by the server.
|
||||
Also check that the "common name" of the server, as presented by
|
||||
its certificate, corresponds to HOST. (HOST typically comes from
|
||||
@@ -654,6 +756,7 @@ ssl_check_certificate (int fd, const char *host)
|
||||
long vresult;
|
||||
bool success = true;
|
||||
bool alt_name_checked = false;
|
||||
bool pinsuccess = opt.pinnedpubkey == NULL;
|
||||
|
||||
/* If the user has specified --no-check-cert, we still want to warn
|
||||
him about problems with the server's certificate. */
|
||||
@@ -663,6 +766,10 @@ ssl_check_certificate (int fd, const char *host)
|
||||
SSL *conn = ctx->conn;
|
||||
assert (conn != NULL);
|
||||
|
||||
/* The user explicitly said to not check for the certificate. */
|
||||
if (opt.check_cert == CHECK_CERT_QUIET && pinsuccess)
|
||||
return success;
|
||||
|
||||
cert = SSL_get_peer_certificate (conn);
|
||||
if (!cert)
|
||||
{
|
||||
@@ -739,9 +846,12 @@ ssl_check_certificate (int fd, const char *host)
|
||||
{
|
||||
/* Test subject alternative names */
|
||||
|
||||
/* SNI hostname must not have a trailing dot */
|
||||
const char *sni_hostname = _sni_hostname(host);
|
||||
|
||||
/* Do we want to check for dNSNAmes or ipAddresses (see RFC 2818)?
|
||||
* Signal it by host_in_octet_string. */
|
||||
ASN1_OCTET_STRING *host_in_octet_string = a2i_IPADDRESS (host);
|
||||
ASN1_OCTET_STRING *host_in_octet_string = a2i_IPADDRESS (sni_hostname);
|
||||
|
||||
int numaltnames = sk_GENERAL_NAME_num (subjectAltNames);
|
||||
int i;
|
||||
@@ -776,7 +886,7 @@ ssl_check_certificate (int fd, const char *host)
|
||||
if (0 <= ASN1_STRING_to_UTF8 (&name_in_utf8, name->d.dNSName))
|
||||
{
|
||||
/* Compare and check for NULL attack in ASN1_STRING */
|
||||
if (pattern_match ((char *)name_in_utf8, host) &&
|
||||
if (pattern_match ((char *)name_in_utf8, sni_hostname) &&
|
||||
(strlen ((char *)name_in_utf8) ==
|
||||
(size_t) ASN1_STRING_length (name->d.dNSName)))
|
||||
{
|
||||
@@ -797,9 +907,11 @@ ssl_check_certificate (int fd, const char *host)
|
||||
logprintf (LOG_NOTQUIET,
|
||||
_("%s: no certificate subject alternative name matches\n"
|
||||
"\trequested host name %s.\n"),
|
||||
severity, quote_n (1, host));
|
||||
severity, quote_n (1, sni_hostname));
|
||||
success = false;
|
||||
}
|
||||
|
||||
xfree(sni_hostname);
|
||||
}
|
||||
|
||||
if (alt_name_checked == false)
|
||||
@@ -854,6 +966,13 @@ ssl_check_certificate (int fd, const char *host)
|
||||
}
|
||||
}
|
||||
|
||||
pinsuccess = pkp_pin_peer_pubkey (cert, opt.pinnedpubkey);
|
||||
if (!pinsuccess)
|
||||
{
|
||||
logprintf (LOG_ALWAYS, _("The public key does not match pinned public key!\n"));
|
||||
success = false;
|
||||
}
|
||||
|
||||
|
||||
if (success)
|
||||
DEBUGP (("X509 certificate successfully verified and matches host %s\n",
|
||||
@@ -861,13 +980,13 @@ ssl_check_certificate (int fd, const char *host)
|
||||
X509_free (cert);
|
||||
|
||||
no_cert:
|
||||
if (opt.check_cert && !success)
|
||||
if (opt.check_cert == CHECK_CERT_ON && !success)
|
||||
logprintf (LOG_NOTQUIET, _("\
|
||||
To connect to %s insecurely, use `--no-check-certificate'.\n"),
|
||||
quotearg_style (escape_quoting_style, host));
|
||||
|
||||
/* Allow --no-check-cert to disable certificate checking. */
|
||||
return opt.check_cert ? success : true;
|
||||
/* never return true if pinsuccess fails */
|
||||
return !pinsuccess ? false : (opt.check_cert == CHECK_CERT_ON ? success : true);
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/* struct options.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -29,6 +29,13 @@ Corresponding Source for a non-source form of such a combination
|
||||
shall include the source code for the parts of OpenSSL used as well
|
||||
as that of the covered work. */
|
||||
|
||||
enum CHECK_CERT_MODES
|
||||
{
|
||||
CHECK_CERT_OFF,
|
||||
CHECK_CERT_ON,
|
||||
CHECK_CERT_QUIET
|
||||
};
|
||||
|
||||
struct options
|
||||
{
|
||||
int verbose; /* Are we verbose? (First set to -1,
|
||||
@@ -58,6 +65,12 @@ struct options
|
||||
char *dir_prefix; /* The top of directory tree */
|
||||
char *lfilename; /* Log filename */
|
||||
char *input_filename; /* Input filename */
|
||||
#ifdef HAVE_METALINK
|
||||
char *input_metalink; /* Input metalink file */
|
||||
int metalink_index; /* Metalink application/metalink4+xml metaurl ordinal number. */
|
||||
bool metalink_over_http; /* Use Metalink if present in HTTP response */
|
||||
char *preferred_location; /* Preferred location for Metalink resources */
|
||||
#endif
|
||||
char *choose_config; /* Specified config file */
|
||||
bool noconfig; /* Ignore all config files? */
|
||||
bool force_html; /* Is the input file an HTML file? */
|
||||
@@ -87,6 +100,11 @@ struct options
|
||||
void *(*regex_compile_fun)(const char *); /* Function to compile a regex. */
|
||||
bool (*regex_match_fun)(const void *, const char *); /* Function to match a string to a regex. */
|
||||
|
||||
#ifdef HAVE_LIBCARES
|
||||
char *bind_dns_address;
|
||||
char *dns_servers;
|
||||
#endif
|
||||
|
||||
char **domains; /* See host.c */
|
||||
char **exclude_domains;
|
||||
bool dns_cache; /* whether we cache DNS lookups. */
|
||||
@@ -110,9 +128,12 @@ struct options
|
||||
bool warc_keep_log; /* Store the log file in a WARC record. */
|
||||
char **warc_user_headers; /* User-defined WARC header(s). */
|
||||
|
||||
bool enable_xattr; /* Store metadata in POSIX extended attributes. */
|
||||
|
||||
char *user; /* Generic username */
|
||||
char *passwd; /* Generic password */
|
||||
bool ask_passwd; /* Ask for password? */
|
||||
char *use_askpass; /* value to use for use-askpass if WGET_ASKPASS is not set */
|
||||
|
||||
bool always_rest; /* Always use REST. */
|
||||
wgint start_pos; /* Start position of a download. */
|
||||
@@ -165,6 +186,7 @@ struct options
|
||||
#endif
|
||||
|
||||
bool timestamping; /* Whether to use time-stamping. */
|
||||
bool if_modified_since; /* Whether to use conditional get requests. */
|
||||
|
||||
bool backup_converted; /* Do we save pre-converted files as *.orig? */
|
||||
int backups; /* Are numeric backups made? */
|
||||
@@ -176,6 +198,9 @@ struct options
|
||||
NULL. */
|
||||
bool convert_links; /* Will the links be converted
|
||||
locally? */
|
||||
bool convert_file_only; /* Convert only the file portion of the URI (i.e. basename).
|
||||
Leave everything else untouched. */
|
||||
|
||||
bool remove_listing; /* Do we remove .listing files
|
||||
generated by FTP? */
|
||||
bool htmlify; /* Do we HTML-ify the OS-dependent
|
||||
@@ -206,7 +231,7 @@ struct options
|
||||
secure_protocol_tlsv1_2,
|
||||
secure_protocol_pfs
|
||||
} secure_protocol; /* type of secure protocol to use. */
|
||||
bool check_cert; /* whether to validate the server's cert */
|
||||
int check_cert; /* whether to validate the server's cert */
|
||||
char *cert_file; /* external client certificate to use. */
|
||||
char *private_key; /* private key file (if not internal). */
|
||||
enum keyfile_type {
|
||||
@@ -220,14 +245,24 @@ struct options
|
||||
char *ca_cert; /* CA certificate file to use */
|
||||
char *crl_file; /* file with CRLs */
|
||||
|
||||
char *pinnedpubkey; /* Public key (PEM/DER) file, or any number
|
||||
of base64 encoded sha256 hashes preceded by
|
||||
\'sha256//\' and separated by \';\', to verify
|
||||
peer against */
|
||||
|
||||
char *random_file; /* file with random data to seed the PRNG */
|
||||
char *egd_file; /* file name of the egd daemon socket */
|
||||
bool https_only; /* whether to follow HTTPS only */
|
||||
bool ftps_resume_ssl;
|
||||
bool ftps_fallback_to_ftp;
|
||||
bool ftps_implicit;
|
||||
bool ftps_clear_data_connection;
|
||||
#endif /* HAVE_SSL */
|
||||
|
||||
bool cookies; /* whether cookies are used. */
|
||||
char *cookies_input; /* file we're loading the cookies from. */
|
||||
char *cookies_output; /* file we're saving the cookies to. */
|
||||
bool keep_badhash; /* Keep files with checksum mismatch. */
|
||||
bool keep_session_cookies; /* whether session cookies should be
|
||||
saved and loaded. */
|
||||
|
||||
@@ -239,6 +274,7 @@ struct options
|
||||
|
||||
enum {
|
||||
restrict_unix,
|
||||
restrict_vms,
|
||||
restrict_windows
|
||||
} restrict_files_os; /* file name restriction ruleset. */
|
||||
bool restrict_files_ctrl; /* non-zero if control chars in URLs
|
||||
@@ -275,7 +311,7 @@ struct options
|
||||
|
||||
bool enable_iri;
|
||||
char *encoding_remote;
|
||||
char *locale;
|
||||
const char *locale;
|
||||
|
||||
bool trustservernames;
|
||||
#ifdef __VMS
|
||||
@@ -288,6 +324,13 @@ struct options
|
||||
bool show_all_dns_entries; /* Show all the DNS entries when resolving a
|
||||
name. */
|
||||
bool report_bps; /*Output bandwidth in bits format*/
|
||||
|
||||
char *rejected_log; /* The file to log rejected URLS to. */
|
||||
|
||||
#ifdef HAVE_HSTS
|
||||
bool hsts;
|
||||
char *hsts_file;
|
||||
#endif
|
||||
};
|
||||
|
||||
extern struct options opt;
|
||||
|
||||
159
src/progress.c
159
src/progress.c
@@ -1,6 +1,6 @@
|
||||
/* Download progress.
|
||||
Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009,
|
||||
2010, 2011 Free Software Foundation, Inc.
|
||||
2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -594,7 +594,8 @@ bar_create (const char *f_download, wgint initial, wgint total)
|
||||
bp->width = screen_width - 1;
|
||||
/* + enough space for the terminating zero, and hopefully enough room
|
||||
* for multibyte characters. */
|
||||
bp->buffer = xmalloc (bp->width + 100);
|
||||
#define BUF_LEN (bp->width + 100)
|
||||
bp->buffer = xmalloc (BUF_LEN);
|
||||
|
||||
logputs (LOG_VERBOSE, "\n");
|
||||
|
||||
@@ -693,7 +694,7 @@ bar_finish (void *progress, double dltime)
|
||||
The idea is that for fast downloads, we get the speed over exactly
|
||||
the last three seconds. For slow downloads (where a network read
|
||||
takes more than 150ms to complete), we get the speed over a larger
|
||||
time period, as large as it takes to complete thirty reads. This
|
||||
time period, as large as it takes to complete twenty reads. This
|
||||
is good because slow downloads tend to fluctuate more and a
|
||||
3-second average would be too erratic. */
|
||||
|
||||
@@ -854,7 +855,7 @@ get_eta (int *bcd)
|
||||
{
|
||||
/* TRANSLATORS: "ETA" is English-centric, but this must
|
||||
be short, ideally 3 chars. Abbreviate if necessary. */
|
||||
static const char eta_str[] = N_(" eta %s");
|
||||
static const char eta_str[] = N_(" eta %s");
|
||||
static const char *eta_trans;
|
||||
static int bytes_cols_diff;
|
||||
if (eta_trans == NULL)
|
||||
@@ -891,11 +892,6 @@ get_eta (int *bcd)
|
||||
p += sizeof (s) - 1; \
|
||||
} while (0)
|
||||
|
||||
/* Use move_to_end (s) to get S to point the end of the string (the
|
||||
terminating \0). This is faster than s+=strlen(s), but some people
|
||||
are confused when they see strchr (s, '\0') in the code. */
|
||||
#define move_to_end(s) s = strchr (s, '\0');
|
||||
|
||||
static void
|
||||
create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
{
|
||||
@@ -903,11 +899,11 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
char *p = bp->buffer;
|
||||
wgint size = bp->initial_length + bp->count;
|
||||
|
||||
int size_grouped_pad; /* Used to pad the field width for size_grouped. */
|
||||
|
||||
struct bar_progress_hist *hist = &bp->hist;
|
||||
int orig_filename_cols = count_cols (bp->f_download);
|
||||
|
||||
int padding;
|
||||
|
||||
/* The progress bar should look like this:
|
||||
file xx% [=======> ] nnn.nnK 12.34KB/s eta 36m 51s
|
||||
|
||||
@@ -928,12 +924,16 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
"=====>..." - progress bar - the rest
|
||||
*/
|
||||
|
||||
/* TODO: Ask the Turkish Translators to fix their translation for the "done"
|
||||
* mode of progress bar. Use one less character. Once that is done, redice
|
||||
* PROGRESS_ETA_LEN by 1.
|
||||
*/
|
||||
#define PROGRESS_FILENAME_LEN MAX_FILENAME_COLS + 1
|
||||
#define PROGRESS_PERCENT_LEN 4
|
||||
#define PROGRESS_DECORAT_LEN 2
|
||||
#define PROGRESS_FILESIZE_LEN 7 + 1
|
||||
#define PROGRESS_DWNLOAD_RATE 8 + 1
|
||||
#define PROGRESS_ETA_LEN 14
|
||||
#define PROGRESS_DWNLOAD_RATE 8 + 2
|
||||
#define PROGRESS_ETA_LEN 15
|
||||
|
||||
int progress_size = bp->width - (PROGRESS_FILENAME_LEN + PROGRESS_PERCENT_LEN +
|
||||
PROGRESS_DECORAT_LEN + PROGRESS_FILESIZE_LEN +
|
||||
@@ -945,41 +945,55 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
int cols_diff;
|
||||
const char *down_size;
|
||||
|
||||
memset (bp->buffer, '\0', BUF_LEN);
|
||||
|
||||
if (progress_size < 5)
|
||||
progress_size = 0;
|
||||
|
||||
if (orig_filename_cols <= MAX_FILENAME_COLS)
|
||||
{
|
||||
int padding = MAX_FILENAME_COLS - orig_filename_cols;
|
||||
sprintf (p, "%s ", bp->f_download);
|
||||
p += orig_filename_cols + 1;
|
||||
for (;padding;padding--)
|
||||
*p++ = ' ';
|
||||
padding = MAX_FILENAME_COLS - orig_filename_cols;
|
||||
p += sprintf (p, "%s ", bp->f_download);
|
||||
memset (p, ' ', padding);
|
||||
p += padding;
|
||||
}
|
||||
else
|
||||
{
|
||||
int offset_cols;
|
||||
int bytes_in_filename, offset_bytes, col;
|
||||
int *cols_ret = &col;
|
||||
int padding;
|
||||
|
||||
#define MIN_SCROLL_TEXT 5
|
||||
if ((orig_filename_cols > MAX_FILENAME_COLS + MIN_SCROLL_TEXT) &&
|
||||
!opt.noscroll &&
|
||||
!done)
|
||||
offset_cols = ((int) bp->tick) % (orig_filename_cols - MAX_FILENAME_COLS + 1);
|
||||
{
|
||||
offset_cols = ((int) bp->tick + orig_filename_cols + MAX_FILENAME_COLS / 2)
|
||||
% (orig_filename_cols + MAX_FILENAME_COLS);
|
||||
if (offset_cols > orig_filename_cols)
|
||||
{
|
||||
padding = MAX_FILENAME_COLS - (offset_cols - orig_filename_cols);
|
||||
memset(p, ' ', padding);
|
||||
p += padding;
|
||||
offset_cols = 0;
|
||||
}
|
||||
else
|
||||
padding = 0;
|
||||
}
|
||||
else
|
||||
offset_cols = 0;
|
||||
{
|
||||
padding = 0;
|
||||
offset_cols = 0;
|
||||
}
|
||||
offset_bytes = cols_to_bytes (bp->f_download, offset_cols, cols_ret);
|
||||
bytes_in_filename = cols_to_bytes (bp->f_download + offset_bytes,
|
||||
MAX_FILENAME_COLS,
|
||||
MAX_FILENAME_COLS - padding,
|
||||
cols_ret);
|
||||
memcpy (p, bp->f_download + offset_bytes, bytes_in_filename);
|
||||
p += bytes_in_filename;
|
||||
padding = MAX_FILENAME_COLS - *cols_ret;
|
||||
for (;padding;padding--)
|
||||
*p++ = ' ';
|
||||
*p++ = ' ';
|
||||
padding = MAX_FILENAME_COLS - (padding + *cols_ret);
|
||||
memset (p, ' ', padding + 1);
|
||||
p += padding + 1;
|
||||
}
|
||||
|
||||
/* "xx% " */
|
||||
@@ -987,15 +1001,13 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
{
|
||||
int percentage = 100.0 * size / bp->total_length;
|
||||
assert (percentage <= 100);
|
||||
|
||||
if (percentage < 100)
|
||||
sprintf (p, "%3d%%", percentage);
|
||||
else
|
||||
strcpy (p, "100%");
|
||||
p += 4;
|
||||
p += sprintf (p, "%3d%%", percentage);
|
||||
}
|
||||
else
|
||||
APPEND_LITERAL (" ");
|
||||
{
|
||||
memset (p, ' ', PROGRESS_PERCENT_LEN);
|
||||
p += PROGRESS_PERCENT_LEN;
|
||||
}
|
||||
|
||||
/* The progress bar: "[====> ]" or "[++==> ]". */
|
||||
if (progress_size && bp->total_length > 0)
|
||||
@@ -1007,7 +1019,6 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
int dlsz = (double)size / bp->total_length * progress_size;
|
||||
|
||||
char *begin;
|
||||
int i;
|
||||
|
||||
assert (dlsz <= progress_size);
|
||||
assert (insz <= dlsz);
|
||||
@@ -1017,18 +1028,19 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
|
||||
/* Print the initial portion of the download with '+' chars, the
|
||||
rest with '=' and one '>'. */
|
||||
for (i = 0; i < insz; i++)
|
||||
*p++ = '+';
|
||||
memset (p, '+', insz);
|
||||
p += insz;
|
||||
|
||||
dlsz -= insz;
|
||||
if (dlsz > 0)
|
||||
{
|
||||
for (i = 0; i < dlsz - 1; i++)
|
||||
*p++ = '=';
|
||||
memset (p, '=', dlsz-1);
|
||||
p += dlsz - 1;
|
||||
*p++ = '>';
|
||||
}
|
||||
|
||||
while (p - begin < progress_size)
|
||||
*p++ = ' ';
|
||||
memset (p, ' ', (progress_size - (p - begin)));
|
||||
p += (progress_size - (p - begin));
|
||||
*p++ = ']';
|
||||
}
|
||||
else if (progress_size)
|
||||
@@ -1056,27 +1068,14 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
*p++ = ']';
|
||||
|
||||
}
|
||||
++bp->tick;
|
||||
++bp->tick;
|
||||
|
||||
/* " 234.56M" */
|
||||
down_size = human_readable (size, 1000, 2);
|
||||
cols_diff = 7 - count_cols (down_size);
|
||||
while (cols_diff > 0)
|
||||
{
|
||||
*p++=' ';
|
||||
cols_diff--;
|
||||
}
|
||||
sprintf (p, " %s", down_size);
|
||||
move_to_end (p);
|
||||
/* Pad with spaces to 7 chars for the size_grouped field;
|
||||
* couldn't use the field width specifier in sprintf, because
|
||||
* it counts in bytes, not characters. */
|
||||
for (size_grouped_pad = PROGRESS_FILESIZE_LEN - 7;
|
||||
size_grouped_pad > 0;
|
||||
--size_grouped_pad)
|
||||
{
|
||||
*p++ = ' ';
|
||||
}
|
||||
cols_diff = PROGRESS_FILESIZE_LEN - count_cols (down_size);
|
||||
memset (p, ' ', cols_diff);
|
||||
p += cols_diff;
|
||||
p += sprintf (p, "%s", down_size);
|
||||
|
||||
/* " 12.52Kb/s or 12.52KB/s" */
|
||||
if (hist->total_time > 0 && hist->total_bytes)
|
||||
@@ -1089,12 +1088,11 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
wgint dlquant = hist->total_bytes + bp->recent_bytes;
|
||||
double dltime = hist->total_time + (dl_total_time - bp->recent_start);
|
||||
double dlspeed = calc_rate (dlquant, dltime, &units);
|
||||
sprintf (p, " %4.*f%s", dlspeed >= 99.95 ? 0 : dlspeed >= 9.995 ? 1 : 2,
|
||||
p += sprintf (p, " %4.*f%s", dlspeed >= 99.95 ? 0 : dlspeed >= 9.995 ? 1 : 2,
|
||||
dlspeed, !opt.report_bps ? short_units[units] : short_units_bits[units]);
|
||||
move_to_end (p);
|
||||
}
|
||||
else
|
||||
APPEND_LITERAL (" --.-KB/s");
|
||||
APPEND_LITERAL (" --.-KB/s");
|
||||
|
||||
if (!done)
|
||||
{
|
||||
@@ -1129,14 +1127,14 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
bp->last_eta_time = dl_total_time;
|
||||
}
|
||||
|
||||
sprintf (p, get_eta(&bytes_cols_diff),
|
||||
p += sprintf (p, get_eta(&bytes_cols_diff),
|
||||
eta_to_human_short (eta, false));
|
||||
move_to_end (p);
|
||||
}
|
||||
else if (bp->total_length > 0)
|
||||
{
|
||||
skip_eta:
|
||||
APPEND_LITERAL (" ");
|
||||
memset (p, ' ', PROGRESS_ETA_LEN);
|
||||
p += PROGRESS_ETA_LEN;
|
||||
}
|
||||
}
|
||||
else
|
||||
@@ -1146,21 +1144,25 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
int ncols;
|
||||
|
||||
/* Note to translators: this should not take up more room than
|
||||
available here. Abbreviate if necessary. */
|
||||
strcpy (p, _(" in "));
|
||||
available here (6 columns). Abbreviate if necessary. */
|
||||
strcpy (p, _(" in "));
|
||||
nbytes = strlen (p);
|
||||
ncols = count_cols (p);
|
||||
bytes_cols_diff = nbytes - ncols;
|
||||
p += nbytes;
|
||||
if (dl_total_time >= 10)
|
||||
strcpy (p, eta_to_human_short ((int) (dl_total_time + 0.5), false));
|
||||
ncols += sprintf (p + nbytes, "%s", eta_to_human_short ((int) (dl_total_time + 0.5), false));
|
||||
else
|
||||
sprintf (p, "%ss", print_decimal (dl_total_time));
|
||||
move_to_end (p);
|
||||
ncols += sprintf (p + nbytes, "%ss", print_decimal (dl_total_time));
|
||||
p += ncols + bytes_cols_diff;
|
||||
memset (p, ' ', PROGRESS_ETA_LEN - ncols);
|
||||
p += PROGRESS_ETA_LEN - ncols;
|
||||
}
|
||||
|
||||
while (p - bp->buffer - bytes_cols_diff < bp->width)
|
||||
*p++ = ' ';
|
||||
padding = bp->width - count_cols (bp->buffer);
|
||||
assert (padding >= 0 && "Padding length became non-positive!");
|
||||
padding = padding > 0 ? padding : 0;
|
||||
memset (p, ' ', padding);
|
||||
p += padding;
|
||||
*p = '\0';
|
||||
|
||||
/* 2014-11-14 Darshit Shah <darnir@gmail.com>
|
||||
@@ -1169,8 +1171,11 @@ create_image (struct bar_progress *bp, double dl_total_time, bool done)
|
||||
* from the release code since we do not want Wget to crash and burn when the
|
||||
* assertion fails. Instead Wget should continue downloading and display a
|
||||
* horrible and irritating progress bar that spams the screen with newlines.
|
||||
*
|
||||
* By default, all assertions are disabled in a Wget build and are enabled
|
||||
* only with the --enable-assert configure option.
|
||||
*/
|
||||
assert (count_cols (bp->buffer) <= bp->width + 1);
|
||||
assert (count_cols (bp->buffer) == bp->width);
|
||||
}
|
||||
|
||||
/* Print the contents of the buffer as a one-line ASCII "image" so
|
||||
@@ -1188,8 +1193,6 @@ display_image (char *buf)
|
||||
static void
|
||||
bar_set_params (char *params)
|
||||
{
|
||||
char *term = getenv ("TERM");
|
||||
|
||||
if (params)
|
||||
{
|
||||
char *param = strtok (params, ":");
|
||||
@@ -1209,12 +1212,6 @@ bar_set_params (char *params)
|
||||
dots. */
|
||||
|| !isatty (fileno (stderr))
|
||||
#endif
|
||||
/* Normally we don't depend on terminal type because the
|
||||
progress bar only uses ^M to move the cursor to the
|
||||
beginning of line, which works even on dumb terminals. But
|
||||
Jamie Zawinski reports that ^M and ^H tricks don't work in
|
||||
Emacs shell buffers, and only make a mess. */
|
||||
|| (term && 0 == strcmp (term, "emacs"))
|
||||
)
|
||||
&& !current_impl_locked)
|
||||
{
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Download progress.
|
||||
Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009,
|
||||
2010, 2011 Free Software Foundation, Inc.
|
||||
2010, 2011, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Portable timers.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Declarations for ptimer.c.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
322
src/recur.c
322
src/recur.c
@@ -1,7 +1,7 @@
|
||||
/* Handling of recursive HTTP retrieving.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -50,6 +50,7 @@ as that of the covered work. */
|
||||
#include "html-url.h"
|
||||
#include "css-url.h"
|
||||
#include "spider.h"
|
||||
#include "exits.h"
|
||||
|
||||
/* Functions for maintaining the URL queue. */
|
||||
|
||||
@@ -181,11 +182,20 @@ static int blacklist_contains (struct hash_table *blacklist, const char *url)
|
||||
return ret;
|
||||
}
|
||||
|
||||
static bool download_child_p (const struct urlpos *, struct url *, int,
|
||||
struct url *, struct hash_table *, struct iri *);
|
||||
static bool descend_redirect_p (const char *, struct url *, int,
|
||||
struct url *, struct hash_table *, struct iri *);
|
||||
typedef enum
|
||||
{
|
||||
WG_RR_SUCCESS, WG_RR_BLACKLIST, WG_RR_NOTHTTPS, WG_RR_NONHTTP, WG_RR_ABSOLUTE,
|
||||
WG_RR_DOMAIN, WG_RR_PARENT, WG_RR_LIST, WG_RR_REGEX, WG_RR_RULES,
|
||||
WG_RR_SPANNEDHOST, WG_RR_ROBOTS
|
||||
} reject_reason;
|
||||
|
||||
static reject_reason download_child (const struct urlpos *, struct url *, int,
|
||||
struct url *, struct hash_table *, struct iri *);
|
||||
static reject_reason descend_redirect (const char *, struct url *, int,
|
||||
struct url *, struct hash_table *, struct iri *);
|
||||
static void write_reject_log_header (FILE *);
|
||||
static void write_reject_log_reason (FILE *, reject_reason,
|
||||
const struct url *, const struct url *);
|
||||
|
||||
/* Retrieve a part of the web beginning with START_URL. This used to
|
||||
be called "recursive retrieval", because the old function was
|
||||
@@ -222,17 +232,21 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
|
||||
|
||||
struct iri *i = iri_new ();
|
||||
|
||||
#define COPYSTR(x) (x) ? xstrdup(x) : NULL;
|
||||
FILE *rejectedlog = NULL; /* Don't write a rejected log. */
|
||||
|
||||
/* Duplicate pi struct if not NULL */
|
||||
if (pi)
|
||||
{
|
||||
#define COPYSTR(x) (x) ? xstrdup(x) : NULL;
|
||||
i->uri_encoding = COPYSTR (pi->uri_encoding);
|
||||
i->content_encoding = COPYSTR (pi->content_encoding);
|
||||
i->utf8_encode = pi->utf8_encode;
|
||||
#undef COPYSTR
|
||||
}
|
||||
#ifdef ENABLE_IRI
|
||||
else
|
||||
set_uri_encoding (i, opt.locale, true);
|
||||
#undef COPYSTR
|
||||
#endif
|
||||
|
||||
queue = url_queue_new ();
|
||||
blacklist = make_string_hash_table (0);
|
||||
@@ -243,6 +257,14 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
|
||||
false);
|
||||
blacklist_add (blacklist, start_url_parsed->url);
|
||||
|
||||
if (opt.rejected_log)
|
||||
{
|
||||
rejectedlog = fopen (opt.rejected_log, "w");
|
||||
write_reject_log_header (rejectedlog);
|
||||
if (!rejectedlog)
|
||||
logprintf (LOG_NOTQUIET, "%s: %s\n", opt.rejected_log, strerror (errno));
|
||||
}
|
||||
|
||||
while (1)
|
||||
{
|
||||
bool descend = false;
|
||||
@@ -265,9 +287,9 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
|
||||
break;
|
||||
|
||||
/* ...and download it. Note that this download is in most cases
|
||||
unconditional, as download_child_p already makes sure a file
|
||||
unconditional, as download_child already makes sure a file
|
||||
doesn't get enqueued twice -- and yet this check is here, and
|
||||
not in download_child_p. This is so that if you run `wget -r
|
||||
not in download_child. This is so that if you run `wget -r
|
||||
URL1 URL2', and a random URL is encountered once under URL1
|
||||
and again under URL2, but at a different (possibly smaller)
|
||||
depth, we want the URL's children to be taken into account
|
||||
@@ -298,52 +320,69 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
|
||||
char *redirected = NULL;
|
||||
struct url *url_parsed = url_parse (url, &url_err, i, true);
|
||||
|
||||
status = retrieve_url (url_parsed, url, &file, &redirected, referer,
|
||||
&dt, false, i, true);
|
||||
|
||||
if (html_allowed && file && status == RETROK
|
||||
&& (dt & RETROKF) && (dt & TEXTHTML))
|
||||
if (!url_parsed)
|
||||
{
|
||||
descend = true;
|
||||
is_css = false;
|
||||
}
|
||||
|
||||
/* a little different, css_allowed can override content type
|
||||
lots of web servers serve css with an incorrect content type
|
||||
*/
|
||||
if (file && status == RETROK
|
||||
&& (dt & RETROKF) &&
|
||||
((dt & TEXTCSS) || css_allowed))
|
||||
{
|
||||
descend = true;
|
||||
is_css = true;
|
||||
}
|
||||
|
||||
if (redirected)
|
||||
{
|
||||
/* We have been redirected, possibly to another host, or
|
||||
different path, or wherever. Check whether we really
|
||||
want to follow it. */
|
||||
if (descend)
|
||||
{
|
||||
if (!descend_redirect_p (redirected, url_parsed, depth,
|
||||
start_url_parsed, blacklist, i))
|
||||
descend = false;
|
||||
else
|
||||
/* Make sure that the old pre-redirect form gets
|
||||
blacklisted. */
|
||||
blacklist_add (blacklist, url);
|
||||
}
|
||||
|
||||
xfree (url);
|
||||
url = redirected;
|
||||
char *error = url_error (url, url_err);
|
||||
logprintf (LOG_NOTQUIET, "%s: %s.\n",url, error);
|
||||
xfree (error);
|
||||
inform_exit_status (URLERROR);
|
||||
}
|
||||
else
|
||||
{
|
||||
xfree (url);
|
||||
url = xstrdup (url_parsed->url);
|
||||
|
||||
status = retrieve_url (url_parsed, url, &file, &redirected, referer,
|
||||
&dt, false, i, true);
|
||||
|
||||
if (html_allowed && file && status == RETROK
|
||||
&& (dt & RETROKF) && (dt & TEXTHTML))
|
||||
{
|
||||
descend = true;
|
||||
is_css = false;
|
||||
}
|
||||
|
||||
/* a little different, css_allowed can override content type
|
||||
lots of web servers serve css with an incorrect content type
|
||||
*/
|
||||
if (file && status == RETROK
|
||||
&& (dt & RETROKF) &&
|
||||
((dt & TEXTCSS) || css_allowed))
|
||||
{
|
||||
descend = true;
|
||||
is_css = true;
|
||||
}
|
||||
|
||||
if (redirected)
|
||||
{
|
||||
/* We have been redirected, possibly to another host, or
|
||||
different path, or wherever. Check whether we really
|
||||
want to follow it. */
|
||||
if (descend)
|
||||
{
|
||||
reject_reason r = descend_redirect (redirected, url_parsed,
|
||||
depth, start_url_parsed, blacklist, i);
|
||||
if (r == WG_RR_SUCCESS)
|
||||
{
|
||||
/* Make sure that the old pre-redirect form gets
|
||||
blacklisted. */
|
||||
blacklist_add (blacklist, url);
|
||||
}
|
||||
else
|
||||
{
|
||||
write_reject_log_reason (rejectedlog, r, url_parsed, start_url_parsed);
|
||||
descend = false;
|
||||
}
|
||||
}
|
||||
|
||||
xfree (url);
|
||||
url = redirected;
|
||||
}
|
||||
else
|
||||
{
|
||||
xfree (url);
|
||||
url = xstrdup (url_parsed->url);
|
||||
}
|
||||
url_free (url_parsed);
|
||||
}
|
||||
url_free (url_parsed);
|
||||
}
|
||||
|
||||
if (opt.spider)
|
||||
@@ -399,22 +438,38 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
|
||||
struct url *url_parsed = url_parse (url, NULL, i, true);
|
||||
struct iri *ci;
|
||||
char *referer_url = url;
|
||||
bool strip_auth = (url_parsed != NULL
|
||||
&& url_parsed->user != NULL);
|
||||
bool strip_auth;
|
||||
|
||||
assert (url_parsed != NULL);
|
||||
|
||||
if (!url_parsed)
|
||||
continue;
|
||||
|
||||
strip_auth = (url_parsed && url_parsed->user);
|
||||
|
||||
/* Strip auth info if present */
|
||||
if (strip_auth)
|
||||
referer_url = url_string (url_parsed, URL_AUTH_HIDE);
|
||||
|
||||
for (; child; child = child->next)
|
||||
{
|
||||
reject_reason r;
|
||||
|
||||
if (child->ignore_when_downloading)
|
||||
continue;
|
||||
{
|
||||
DEBUGP (("Not following due to 'ignore' flag: %s\n", child->url->url));
|
||||
continue;
|
||||
}
|
||||
|
||||
if (dash_p_leaf_HTML && !child->link_inline_p)
|
||||
continue;
|
||||
if (download_child_p (child, url_parsed, depth, start_url_parsed,
|
||||
blacklist, i))
|
||||
{
|
||||
DEBUGP (("Not following due to 'link inline' flag: %s\n", child->url->url));
|
||||
continue;
|
||||
}
|
||||
|
||||
r = download_child (child, url_parsed, depth,
|
||||
start_url_parsed, blacklist, i);
|
||||
if (r == WG_RR_SUCCESS)
|
||||
{
|
||||
ci = iri_new ();
|
||||
set_uri_encoding (ci, i->content_encoding, false);
|
||||
@@ -427,6 +482,10 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
|
||||
same URL twice. */
|
||||
blacklist_add (blacklist, child->url->url);
|
||||
}
|
||||
else
|
||||
{
|
||||
write_reject_log_reason (rejectedlog, r, child->url, url_parsed);
|
||||
}
|
||||
}
|
||||
|
||||
if (strip_auth)
|
||||
@@ -466,6 +525,9 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
|
||||
iri_free (i);
|
||||
}
|
||||
|
||||
if (rejectedlog)
|
||||
fclose (rejectedlog);
|
||||
|
||||
/* If anything is left of the queue due to a premature exit, free it
|
||||
now. */
|
||||
{
|
||||
@@ -501,14 +563,15 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
|
||||
by storing these URLs to BLACKLIST. This may or may not help. It
|
||||
will help if those URLs are encountered many times. */
|
||||
|
||||
static bool
|
||||
download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
static reject_reason
|
||||
download_child (const struct urlpos *upos, struct url *parent, int depth,
|
||||
struct url *start_url_parsed, struct hash_table *blacklist,
|
||||
struct iri *iri)
|
||||
{
|
||||
struct url *u = upos->url;
|
||||
const char *url = u->url;
|
||||
bool u_scheme_like_http;
|
||||
reject_reason reason = WG_RR_SUCCESS;
|
||||
|
||||
DEBUGP (("Deciding whether to enqueue \"%s\".\n", url));
|
||||
|
||||
@@ -517,11 +580,12 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
if (opt.spider)
|
||||
{
|
||||
char *referrer = url_string (parent, URL_AUTH_HIDE_PASSWD);
|
||||
DEBUGP (("download_child_p: parent->url is: %s\n", quote (parent->url)));
|
||||
DEBUGP (("download_child: parent->url is: %s\n", quote (parent->url)));
|
||||
visited_url (url, referrer);
|
||||
xfree (referrer);
|
||||
}
|
||||
DEBUGP (("Already on the black list.\n"));
|
||||
reason = WG_RR_BLACKLIST;
|
||||
goto out;
|
||||
}
|
||||
|
||||
@@ -551,6 +615,7 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
if (opt.https_only && u->scheme != SCHEME_HTTPS)
|
||||
{
|
||||
DEBUGP (("Not following non-HTTPS links.\n"));
|
||||
reason = WG_RR_NOTHTTPS;
|
||||
goto out;
|
||||
}
|
||||
#endif
|
||||
@@ -559,9 +624,14 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
u_scheme_like_http = schemes_are_similar_p (u->scheme, SCHEME_HTTP);
|
||||
|
||||
/* 1. Schemes other than HTTP are normally not recursed into. */
|
||||
if (!u_scheme_like_http && !(u->scheme == SCHEME_FTP && opt.follow_ftp))
|
||||
if (!u_scheme_like_http && !((u->scheme == SCHEME_FTP
|
||||
#ifdef HAVE_SSL
|
||||
|| u->scheme == SCHEME_FTPS
|
||||
#endif
|
||||
) && opt.follow_ftp))
|
||||
{
|
||||
DEBUGP (("Not following non-HTTP schemes.\n"));
|
||||
reason = WG_RR_NONHTTP;
|
||||
goto out;
|
||||
}
|
||||
|
||||
@@ -571,6 +641,7 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
if (opt.relative_only && !upos->link_relative_p)
|
||||
{
|
||||
DEBUGP (("It doesn't really look like a relative link.\n"));
|
||||
reason = WG_RR_ABSOLUTE;
|
||||
goto out;
|
||||
}
|
||||
|
||||
@@ -579,6 +650,7 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
if (!accept_domain (u))
|
||||
{
|
||||
DEBUGP (("The domain was not accepted.\n"));
|
||||
reason = WG_RR_DOMAIN;
|
||||
goto out;
|
||||
}
|
||||
|
||||
@@ -598,6 +670,7 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
{
|
||||
DEBUGP (("Going to \"%s\" would escape \"%s\" with no_parent on.\n",
|
||||
u->dir, start_url_parsed->dir));
|
||||
reason = WG_RR_PARENT;
|
||||
goto out;
|
||||
}
|
||||
}
|
||||
@@ -610,12 +683,14 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
if (!accdir (u->dir))
|
||||
{
|
||||
DEBUGP (("%s (%s) is excluded/not-included.\n", url, u->dir));
|
||||
reason = WG_RR_LIST;
|
||||
goto out;
|
||||
}
|
||||
}
|
||||
if (!accept_url (url))
|
||||
{
|
||||
DEBUGP (("%s is excluded/not-included through regex.\n", url));
|
||||
reason = WG_RR_REGEX;
|
||||
goto out;
|
||||
}
|
||||
|
||||
@@ -640,6 +715,7 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
{
|
||||
DEBUGP (("%s (%s) does not match acc/rej rules.\n",
|
||||
url, u->file));
|
||||
reason = WG_RR_RULES;
|
||||
goto out;
|
||||
}
|
||||
}
|
||||
@@ -650,6 +726,7 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
{
|
||||
DEBUGP (("This is not the same hostname as the parent's (%s and %s).\n",
|
||||
u->host, parent->host));
|
||||
reason = WG_RR_SPANNEDHOST;
|
||||
goto out;
|
||||
}
|
||||
|
||||
@@ -692,35 +769,36 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
|
||||
{
|
||||
DEBUGP (("Not following %s because robots.txt forbids it.\n", url));
|
||||
blacklist_add (blacklist, url);
|
||||
reason = WG_RR_ROBOTS;
|
||||
goto out;
|
||||
}
|
||||
}
|
||||
|
||||
/* The URL has passed all the tests. It can be placed in the
|
||||
download queue. */
|
||||
DEBUGP (("Decided to load it.\n"));
|
||||
out:
|
||||
|
||||
return true;
|
||||
if (reason == WG_RR_SUCCESS)
|
||||
/* The URL has passed all the tests. It can be placed in the
|
||||
download queue. */
|
||||
DEBUGP (("Decided to load it.\n"));
|
||||
else
|
||||
DEBUGP (("Decided NOT to load it.\n"));
|
||||
|
||||
out:
|
||||
DEBUGP (("Decided NOT to load it.\n"));
|
||||
|
||||
return false;
|
||||
return reason;
|
||||
}
|
||||
|
||||
/* This function determines whether we will consider downloading the
|
||||
children of a URL whose download resulted in a redirection,
|
||||
possibly to another host, etc. It is needed very rarely, and thus
|
||||
it is merely a simple-minded wrapper around download_child_p. */
|
||||
it is merely a simple-minded wrapper around download_child. */
|
||||
|
||||
static bool
|
||||
descend_redirect_p (const char *redirected, struct url *orig_parsed, int depth,
|
||||
static reject_reason
|
||||
descend_redirect (const char *redirected, struct url *orig_parsed, int depth,
|
||||
struct url *start_url_parsed, struct hash_table *blacklist,
|
||||
struct iri *iri)
|
||||
{
|
||||
struct url *new_parsed;
|
||||
struct urlpos *upos;
|
||||
bool success;
|
||||
reject_reason reason;
|
||||
|
||||
assert (orig_parsed != NULL);
|
||||
|
||||
@@ -730,18 +808,110 @@ descend_redirect_p (const char *redirected, struct url *orig_parsed, int depth,
|
||||
upos = xnew0 (struct urlpos);
|
||||
upos->url = new_parsed;
|
||||
|
||||
success = download_child_p (upos, orig_parsed, depth,
|
||||
reason = download_child (upos, orig_parsed, depth,
|
||||
start_url_parsed, blacklist, iri);
|
||||
|
||||
if (success)
|
||||
if (reason == WG_RR_SUCCESS)
|
||||
blacklist_add (blacklist, upos->url->url);
|
||||
else if (reason == WG_RR_LIST || reason == WG_RR_REGEX)
|
||||
{
|
||||
DEBUGP (("Ignoring decision for redirects, decided to load it.\n"));
|
||||
blacklist_add (blacklist, upos->url->url);
|
||||
reason = WG_RR_SUCCESS;
|
||||
}
|
||||
else
|
||||
DEBUGP (("Redirection \"%s\" failed the test.\n", redirected));
|
||||
|
||||
url_free (new_parsed);
|
||||
xfree (upos);
|
||||
|
||||
return success;
|
||||
return reason;
|
||||
}
|
||||
|
||||
|
||||
/* This function writes the rejected log header. */
|
||||
static void
|
||||
write_reject_log_header (FILE *f)
|
||||
{
|
||||
if (!f)
|
||||
return;
|
||||
|
||||
/* Note: Update this header when columns change in any way. */
|
||||
fprintf (f, "REASON\t"
|
||||
"U_URL\tU_SCHEME\tU_HOST\tU_PORT\tU_PATH\tU_PARAMS\tU_QUERY\tU_FRAGMENT\t"
|
||||
"P_URL\tP_SCHEME\tP_HOST\tP_PORT\tP_PATH\tP_PARAMS\tP_QUERY\tP_FRAGMENT\n");
|
||||
}
|
||||
|
||||
/* This function writes a URL to the reject log. Internal use only. */
|
||||
static void
|
||||
write_reject_log_url (FILE *fp, const struct url *url)
|
||||
{
|
||||
const char *escaped_str;
|
||||
const char *scheme_str;
|
||||
|
||||
if (!fp)
|
||||
return;
|
||||
|
||||
escaped_str = url_escape (url->url);
|
||||
|
||||
switch (url->scheme)
|
||||
{
|
||||
case SCHEME_HTTP: scheme_str = "SCHEME_HTTP"; break;
|
||||
#ifdef HAVE_SSL
|
||||
case SCHEME_HTTPS: scheme_str = "SCHEME_HTTPS"; break;
|
||||
case SCHEME_FTPS: scheme_str = "SCHEME_FTPS"; break;
|
||||
#endif
|
||||
case SCHEME_FTP: scheme_str = "SCHEME_FTP"; break;
|
||||
default: scheme_str = "SCHEME_INVALID"; break;
|
||||
}
|
||||
|
||||
fprintf (fp, "%s\t%s\t%s\t%i\t%s\t%s\t%s\t%s",
|
||||
escaped_str,
|
||||
scheme_str,
|
||||
url->host,
|
||||
url->port,
|
||||
url->path,
|
||||
url->params ? url->params : "",
|
||||
url->query ? url->query : "",
|
||||
url->fragment ? url->fragment : "");
|
||||
|
||||
xfree (escaped_str);
|
||||
}
|
||||
|
||||
/* This function writes out information on why a URL was rejected and its
|
||||
context from download_child such as the URL being rejected and it's
|
||||
parent's URL. The format it uses is comma separated values but with tabs. */
|
||||
static void
|
||||
write_reject_log_reason (FILE *fp, reject_reason reason,
|
||||
const struct url *url, const struct url *parent)
|
||||
{
|
||||
const char *reason_str;
|
||||
|
||||
if (!fp)
|
||||
return;
|
||||
|
||||
switch (reason)
|
||||
{
|
||||
case WG_RR_SUCCESS: reason_str = "SUCCESS"; break;
|
||||
case WG_RR_BLACKLIST: reason_str = "BLACKLIST"; break;
|
||||
case WG_RR_NOTHTTPS: reason_str = "NOTHTTPS"; break;
|
||||
case WG_RR_NONHTTP: reason_str = "NONHTTP"; break;
|
||||
case WG_RR_ABSOLUTE: reason_str = "ABSOLUTE"; break;
|
||||
case WG_RR_DOMAIN: reason_str = "DOMAIN"; break;
|
||||
case WG_RR_PARENT: reason_str = "PARENT"; break;
|
||||
case WG_RR_LIST: reason_str = "LIST"; break;
|
||||
case WG_RR_REGEX: reason_str = "REGEX"; break;
|
||||
case WG_RR_RULES: reason_str = "RULES"; break;
|
||||
case WG_RR_SPANNEDHOST: reason_str = "SPANNEDHOST"; break;
|
||||
case WG_RR_ROBOTS: reason_str = "ROBOTS"; break;
|
||||
default: reason_str = "UNKNOWN"; break;
|
||||
}
|
||||
|
||||
fprintf (fp, "%s\t", reason_str);
|
||||
write_reject_log_url (fp, url);
|
||||
fprintf (fp, "\t");
|
||||
write_reject_log_url (fp, parent);
|
||||
fprintf (fp, "\n");
|
||||
}
|
||||
|
||||
/* vim:set sts=2 sw=2 cino+={s: */
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/* Declarations for recur.c.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* Support for Robot Exclusion Standard (RES).
|
||||
Copyright (C) 2001, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2001, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of Wget.
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/* Declarations for res.c.
|
||||
Copyright (C) 2001, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Copyright (C) 2001, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of Wget.
|
||||
|
||||
97
src/retr.c
97
src/retr.c
@@ -1,7 +1,7 @@
|
||||
/* File retrieval.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2014, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -56,6 +56,7 @@ as that of the covered work. */
|
||||
#include "ptimer.h"
|
||||
#include "html-url.h"
|
||||
#include "iri.h"
|
||||
#include "hsts.h"
|
||||
|
||||
/* Total size of downloaded files. Used to enforce quota. */
|
||||
SUM_SIZE_INT total_downloaded_bytes;
|
||||
@@ -633,7 +634,7 @@ retr_rate (wgint bytes, double secs)
|
||||
double dlrate = calc_rate (bytes, secs, &units);
|
||||
/* Use more digits for smaller numbers (regardless of unit used),
|
||||
e.g. "1022", "247", "12.5", "2.38". */
|
||||
sprintf (res, "%.*f %s",
|
||||
snprintf (res, sizeof(res), "%.*f %s",
|
||||
dlrate >= 99.95 ? 0 : dlrate >= 9.995 ? 1 : 2,
|
||||
dlrate, !opt.report_bps ? rate_names[units]: rate_names_bits[units]);
|
||||
|
||||
@@ -725,7 +726,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
char *mynewloc, *proxy;
|
||||
struct url *u = orig_parsed, *proxy_url;
|
||||
int up_error_code; /* url parse error code */
|
||||
char *local_file;
|
||||
char *local_file = NULL;
|
||||
int redirection_count = 0;
|
||||
|
||||
bool method_suspended = false;
|
||||
@@ -753,7 +754,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
|
||||
result = NOCONERROR;
|
||||
mynewloc = NULL;
|
||||
local_file = NULL;
|
||||
xfree(local_file);
|
||||
proxy_url = NULL;
|
||||
|
||||
proxy = getproxy (u);
|
||||
@@ -772,6 +773,8 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
proxy, error);
|
||||
xfree (url);
|
||||
xfree (error);
|
||||
xfree (proxy);
|
||||
iri_free (pi);
|
||||
RESTORE_METHOD;
|
||||
result = PROXERR;
|
||||
goto bail;
|
||||
@@ -781,6 +784,8 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
logprintf (LOG_NOTQUIET, _("Error in proxy URL %s: Must be HTTP.\n"), proxy);
|
||||
url_free (proxy_url);
|
||||
xfree (url);
|
||||
xfree (proxy);
|
||||
iri_free (pi);
|
||||
RESTORE_METHOD;
|
||||
result = PROXERR;
|
||||
goto bail;
|
||||
@@ -795,10 +800,28 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
#endif
|
||||
|| (proxy_url && proxy_url->scheme == SCHEME_HTTP))
|
||||
{
|
||||
#ifdef HAVE_HSTS
|
||||
#ifdef TESTING
|
||||
/* we don't link against main.o when we're testing */
|
||||
hsts_store_t hsts_store = NULL;
|
||||
#else
|
||||
extern hsts_store_t hsts_store;
|
||||
#endif
|
||||
|
||||
if (opt.hsts && hsts_store)
|
||||
{
|
||||
if (hsts_match (hsts_store, u))
|
||||
logprintf (LOG_VERBOSE, "URL transformed to HTTPS due to an HSTS policy\n");
|
||||
}
|
||||
#endif
|
||||
result = http_loop (u, orig_parsed, &mynewloc, &local_file, refurl, dt,
|
||||
proxy_url, iri);
|
||||
}
|
||||
else if (u->scheme == SCHEME_FTP)
|
||||
else if (u->scheme == SCHEME_FTP
|
||||
#ifdef HAVE_SSL
|
||||
|| u->scheme == SCHEME_FTPS
|
||||
#endif
|
||||
)
|
||||
{
|
||||
/* If this is a redirection, temporarily turn off opt.ftp_glob
|
||||
and opt.recursive, both being undesirable when following
|
||||
@@ -807,14 +830,19 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
if (redirection_count)
|
||||
oldrec = glob = false;
|
||||
|
||||
result = ftp_loop (u, &local_file, dt, proxy_url, recursive, glob);
|
||||
result = ftp_loop (u, orig_parsed, &local_file, dt, proxy_url,
|
||||
recursive, glob);
|
||||
recursive = oldrec;
|
||||
|
||||
/* There is a possibility of having HTTP being redirected to
|
||||
FTP. In these cases we must decide whether the text is HTML
|
||||
according to the suffix. The HTML suffixes are `.html',
|
||||
`.htm' and a few others, case-insensitive. */
|
||||
if (redirection_count && local_file && u->scheme == SCHEME_FTP)
|
||||
if (redirection_count && local_file && (u->scheme == SCHEME_FTP
|
||||
#ifdef HAVE_SSL
|
||||
|| u->scheme == SCHEME_FTPS
|
||||
#endif
|
||||
))
|
||||
{
|
||||
if (has_html_suffix_p (local_file))
|
||||
*dt |= TEXTHTML;
|
||||
@@ -841,15 +869,19 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
redirects, but a ton of boneheaded webservers and CGIs out
|
||||
there break the rules and use relative URLs, and popular
|
||||
browsers are lenient about this, so wget should be too. */
|
||||
construced_newloc = uri_merge (url, mynewloc);
|
||||
construced_newloc = uri_merge (url, mynewloc ? mynewloc : "");
|
||||
xfree (mynewloc);
|
||||
mynewloc = construced_newloc;
|
||||
|
||||
/* Reset UTF-8 encoding state, keep the URI encoding and reset
|
||||
#ifdef ENABLE_IRI
|
||||
/* Reset UTF-8 encoding state, set the URI encoding and reset
|
||||
the content encoding. */
|
||||
iri->utf8_encode = opt.enable_iri;
|
||||
if (opt.encoding_remote)
|
||||
set_uri_encoding (iri, opt.encoding_remote, true);
|
||||
set_content_encoding (iri, NULL);
|
||||
xfree (iri->orig_url);
|
||||
#endif
|
||||
|
||||
/* Now, see if this new location makes sense. */
|
||||
newloc_parsed = url_parse (mynewloc, &up_error_code, iri, true);
|
||||
@@ -941,7 +973,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
DEBUGP (("[Couldn't fallback to non-utf8 for %s\n", quote (url)));
|
||||
}
|
||||
|
||||
if (local_file && u && *dt & RETROKF)
|
||||
if (local_file && u && (*dt & RETROKF || opt.content_on_error))
|
||||
{
|
||||
register_download (u->url, local_file);
|
||||
|
||||
@@ -984,6 +1016,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
|
||||
bail:
|
||||
if (register_status)
|
||||
inform_exit_status (result);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
@@ -1019,6 +1052,7 @@ retrieve_from_file (const char *file, bool html, int *count)
|
||||
char *error = url_error (url, url_err);
|
||||
logprintf (LOG_NOTQUIET, "%s: %s.\n", url, error);
|
||||
xfree (error);
|
||||
iri_free (iri);
|
||||
return URLERROR;
|
||||
}
|
||||
|
||||
@@ -1035,10 +1069,12 @@ retrieve_from_file (const char *file, bool html, int *count)
|
||||
if (dt & TEXTHTML)
|
||||
html = true;
|
||||
|
||||
#ifdef ENABLE_IRI
|
||||
/* If we have a found a content encoding, use it.
|
||||
* ( == is okay, because we're checking for identical object) */
|
||||
if (iri->content_encoding != opt.locale)
|
||||
set_uri_encoding (iri, iri->content_encoding, false);
|
||||
#endif
|
||||
|
||||
/* Reset UTF-8 encode status */
|
||||
iri->utf8_encode = opt.enable_iri;
|
||||
@@ -1074,12 +1110,20 @@ retrieve_from_file (const char *file, bool html, int *count)
|
||||
|
||||
proxy = getproxy (cur_url->url);
|
||||
if ((opt.recursive || opt.page_requisites)
|
||||
&& (cur_url->url->scheme != SCHEME_FTP || proxy))
|
||||
&& ((cur_url->url->scheme != SCHEME_FTP
|
||||
#ifdef HAVE_SSL
|
||||
&& cur_url->url->scheme != SCHEME_FTPS
|
||||
#endif
|
||||
) || proxy))
|
||||
{
|
||||
int old_follow_ftp = opt.follow_ftp;
|
||||
|
||||
/* Turn opt.follow_ftp on in case of recursive FTP retrieval */
|
||||
if (cur_url->url->scheme == SCHEME_FTP)
|
||||
if (cur_url->url->scheme == SCHEME_FTP
|
||||
#ifdef HAVE_SSL
|
||||
|| cur_url->url->scheme == SCHEME_FTPS
|
||||
#endif
|
||||
)
|
||||
opt.follow_ftp = 1;
|
||||
|
||||
status = retrieve_tree (parsed_url ? parsed_url : cur_url->url,
|
||||
@@ -1103,7 +1147,7 @@ retrieve_from_file (const char *file, bool html, int *count)
|
||||
Removing file due to --delete-after in retrieve_from_file():\n"));
|
||||
logprintf (LOG_VERBOSE, _("Removing %s.\n"), filename);
|
||||
if (unlink (filename))
|
||||
logprintf (LOG_NOTQUIET, "unlink: %s\n", strerror (errno));
|
||||
logprintf (LOG_NOTQUIET, "Failed to unlink %s: (%d) %s\n", filename, errno, strerror (errno));
|
||||
dt &= ~RETROKF;
|
||||
}
|
||||
|
||||
@@ -1204,9 +1248,9 @@ rotate_backups(const char *fname)
|
||||
#endif
|
||||
|
||||
int maxlen = strlen (fname) + sizeof (SEP) + numdigit (opt.backups) + AVSL;
|
||||
char *from = (char *)alloca (maxlen);
|
||||
char *to = (char *)alloca (maxlen);
|
||||
struct_stat sb;
|
||||
char *from = alloca (maxlen);
|
||||
char *to = alloca (maxlen);
|
||||
struct stat sb;
|
||||
int i;
|
||||
|
||||
if (stat (fname, &sb) == 0)
|
||||
@@ -1223,17 +1267,21 @@ rotate_backups(const char *fname)
|
||||
*/
|
||||
if (i == opt.backups)
|
||||
{
|
||||
sprintf (to, "%s%s%d%s", fname, SEP, i, AVS);
|
||||
snprintf (to, sizeof(to), "%s%s%d%s", fname, SEP, i, AVS);
|
||||
delete (to);
|
||||
}
|
||||
#endif
|
||||
sprintf (to, "%s%s%d", fname, SEP, i);
|
||||
sprintf (from, "%s%s%d", fname, SEP, i - 1);
|
||||
rename (from, to);
|
||||
snprintf (to, maxlen, "%s%s%d", fname, SEP, i);
|
||||
snprintf (from, maxlen, "%s%s%d", fname, SEP, i - 1);
|
||||
if (rename (from, to))
|
||||
logprintf (LOG_NOTQUIET, "Failed to rename %s to %s: (%d) %s\n",
|
||||
from, to, errno, strerror (errno));
|
||||
}
|
||||
|
||||
sprintf (to, "%s%s%d", fname, SEP, 1);
|
||||
rename(fname, to);
|
||||
snprintf (to, maxlen, "%s%s%d", fname, SEP, 1);
|
||||
if (rename(fname, to))
|
||||
logprintf (LOG_NOTQUIET, "Failed to rename %s to %s: (%d) %s\n",
|
||||
fname, to, errno, strerror (errno));
|
||||
}
|
||||
|
||||
static bool no_proxy_match (const char *, const char **);
|
||||
@@ -1260,6 +1308,9 @@ getproxy (struct url *u)
|
||||
case SCHEME_HTTPS:
|
||||
proxy = opt.https_proxy ? opt.https_proxy : getenv ("https_proxy");
|
||||
break;
|
||||
case SCHEME_FTPS:
|
||||
proxy = opt.ftp_proxy ? opt.ftp_proxy : getenv ("ftps_proxy");
|
||||
break;
|
||||
#endif
|
||||
case SCHEME_FTP:
|
||||
proxy = opt.ftp_proxy ? opt.ftp_proxy : getenv ("ftp_proxy");
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
/* Declarations for retr.c.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/* Keep track of visited URLs in spider mode.
|
||||
Copyright (C) 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Copyright (C) 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/* Declarations for spider.c
|
||||
Copyright (C) 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Copyright (C) 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/* SSL support.
|
||||
Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008,
|
||||
2009, 2010, 2011, 2012 Free Software Foundation, Inc.
|
||||
2009, 2010, 2011, 2012, 2015 Free Software Foundation, Inc.
|
||||
Originally contributed by Christian Fraenkel.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
@@ -33,7 +33,7 @@ as that of the covered work. */
|
||||
#define GEN_SSLFUNC_H
|
||||
|
||||
bool ssl_init (void);
|
||||
bool ssl_connect_wget (int, const char *);
|
||||
bool ssl_connect_wget (int, const char *, int *);
|
||||
bool ssl_check_certificate (int, const char *);
|
||||
|
||||
#endif /* GEN_SSLFUNC_H */
|
||||
|
||||
154
src/sysdep.h
154
src/sysdep.h
@@ -1,7 +1,7 @@
|
||||
/* Dirty system-dependent hacks.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -35,56 +35,11 @@ as that of the covered work. */
|
||||
#ifndef SYSDEP_H
|
||||
#define SYSDEP_H
|
||||
|
||||
/* Testing for __sun is not enough because it's also defined on SunOS. */
|
||||
#ifdef __sun
|
||||
# ifdef __SVR4
|
||||
# define solaris
|
||||
# endif
|
||||
#endif
|
||||
|
||||
#if defined(__INTERIX) && !defined(_ALL_SOURCE)
|
||||
# define _ALL_SOURCE
|
||||
#endif
|
||||
|
||||
/* The "namespace tweaks" below attempt to set a friendly "compilation
|
||||
environment" under popular operating systems. Default compilation
|
||||
environment often means that some functions that are "extensions"
|
||||
are not declared -- `strptime' is one example.
|
||||
|
||||
But non-default environments can expose bugs in the system header
|
||||
files, crippling compilation in _very_ non-obvious ways. Because
|
||||
of that, we define them only on well-tested architectures where we
|
||||
know they will work. */
|
||||
|
||||
#undef NAMESPACE_TWEAKS
|
||||
|
||||
#ifdef solaris
|
||||
# define NAMESPACE_TWEAKS
|
||||
#endif
|
||||
|
||||
#if defined(__linux__) || defined(__GLIBC__)
|
||||
# define NAMESPACE_TWEAKS
|
||||
#endif
|
||||
|
||||
#ifdef NAMESPACE_TWEAKS
|
||||
|
||||
/* Request the "Unix 98 compilation environment". */
|
||||
#define _XOPEN_SOURCE 500
|
||||
|
||||
#endif /* NAMESPACE_TWEAKS */
|
||||
|
||||
|
||||
/* Alloca declaration, based on recommendation in the Autoconf manual.
|
||||
These have to be after the above namespace tweaks, but before any
|
||||
non-preprocessor code. */
|
||||
/* Provided by gnulib on systems that don't have it: */
|
||||
|
||||
#include <alloca.h>
|
||||
|
||||
/* Must include these, so we can test for the missing stat macros and
|
||||
define them as necessary. */
|
||||
#include <sys/types.h>
|
||||
#include <sys/stat.h>
|
||||
|
||||
#include <stdint.h>
|
||||
#include <inttypes.h>
|
||||
|
||||
@@ -98,108 +53,9 @@ as that of the covered work. */
|
||||
# include "mswindows.h"
|
||||
#endif
|
||||
|
||||
/* Provided by gnulib on systems that don't have it: */
|
||||
# include <stdbool.h>
|
||||
|
||||
#ifndef struct_stat
|
||||
# define struct_stat struct stat
|
||||
#endif
|
||||
#ifndef struct_fstat
|
||||
# define struct_fstat struct stat
|
||||
#endif
|
||||
|
||||
#include <intprops.h>
|
||||
|
||||
/* For CHAR_BIT, LONG_MAX, etc. */
|
||||
#include <stdbool.h>
|
||||
#include <limits.h>
|
||||
|
||||
#ifndef CHAR_BIT
|
||||
# define CHAR_BIT 8
|
||||
#endif
|
||||
|
||||
/* These are defined in cmpt.c if missing, so we must declare
|
||||
them. */
|
||||
#ifndef HAVE_STRCASECMP
|
||||
int strcasecmp ();
|
||||
#endif
|
||||
#ifndef HAVE_STRNCASECMP
|
||||
int strncasecmp ();
|
||||
#endif
|
||||
#ifndef HAVE_STRPTIME
|
||||
char *strptime ();
|
||||
#endif
|
||||
#ifndef HAVE_TIMEGM
|
||||
# include <time.h>
|
||||
time_t timegm (struct tm *);
|
||||
#endif
|
||||
#ifndef HAVE_MEMRCHR
|
||||
void *memrchr (const void *, int, size_t);
|
||||
#endif
|
||||
|
||||
/* These are defined in snprintf.c. It would be nice to have an
|
||||
snprintf.h, though. */
|
||||
#ifndef HAVE_SNPRINTF
|
||||
int snprintf (char *str, size_t count, const char *fmt, ...);
|
||||
#endif
|
||||
#ifndef HAVE_VSNPRINTF
|
||||
#include <stdarg.h>
|
||||
int vsnprintf (char *str, size_t count, const char *fmt, va_list arg);
|
||||
#endif
|
||||
|
||||
/* Some systems (Linux libc5, "NCR MP-RAS 3.0", and others) don't
|
||||
provide MAP_FAILED, a symbolic constant for the value returned by
|
||||
mmap() when it doesn't work. Usually, this constant should be -1.
|
||||
This only makes sense for files that use mmap() and include
|
||||
sys/mman.h *before* sysdep.h, but doesn't hurt others. */
|
||||
|
||||
#ifndef MAP_FAILED
|
||||
# define MAP_FAILED ((void *) -1)
|
||||
#endif
|
||||
|
||||
/* Enable system fnmatch only on systems where fnmatch.h is usable.
|
||||
If the fnmatch on your system is buggy, undef this symbol and a
|
||||
replacement implementation will be used instead. */
|
||||
#ifdef HAVE_WORKING_FNMATCH_H
|
||||
# define SYSTEM_FNMATCH
|
||||
#endif
|
||||
|
||||
#include <fnmatch.h>
|
||||
|
||||
/* Provide sig_atomic_t if the system doesn't. */
|
||||
#ifndef HAVE_SIG_ATOMIC_T
|
||||
typedef int sig_atomic_t;
|
||||
#endif
|
||||
|
||||
/* Provide uint32_t on the platforms that don't define it. Although
|
||||
most code should be agnostic about integer sizes, some code really
|
||||
does need a 32-bit integral type. Such code should use uint32_t.
|
||||
(The exception is gnu-md5.[ch], which uses its own detection for
|
||||
portability across platforms.) */
|
||||
|
||||
#ifndef HAVE_UINT32_T
|
||||
# if SIZEOF_INT == 4
|
||||
typedef unsigned int uint32_t;
|
||||
# else
|
||||
# if SIZEOF_LONG == 4
|
||||
typedef unsigned long uint32_t;
|
||||
# else
|
||||
# if SIZEOF_SHORT == 4
|
||||
typedef unsigned short uint32_t;
|
||||
# else
|
||||
#error "Cannot determine a 32-bit unsigned integer type"
|
||||
# endif
|
||||
# endif
|
||||
# endif
|
||||
#endif
|
||||
|
||||
/* If uintptr_t isn't defined, simply typedef it to unsigned long. */
|
||||
#ifndef HAVE_UINTPTR_T
|
||||
typedef unsigned long uintptr_t;
|
||||
#endif
|
||||
|
||||
/* If intptr_t isn't defined, simply typedef it to long. */
|
||||
#ifndef HAVE_INTPTR_T
|
||||
typedef long intptr_t;
|
||||
#endif
|
||||
#include "intprops.h"
|
||||
|
||||
#endif /* SYSDEP_H */
|
||||
|
||||
29
src/test.c
29
src/test.c
@@ -1,6 +1,6 @@
|
||||
/* Unit testing.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -41,24 +41,20 @@ as that of the covered work. */
|
||||
#error "TESTING not set!!!"
|
||||
#endif
|
||||
|
||||
const char *test_parse_content_disposition(void);
|
||||
const char *test_subdir_p(void);
|
||||
const char *test_dir_matches_p(void);
|
||||
const char *test_commands_sorted(void);
|
||||
const char *test_cmd_spec_restrict_file_names(void);
|
||||
const char *test_path_simplify (void);
|
||||
const char *test_append_uri_pathel(void);
|
||||
const char *test_are_urls_equal(void);
|
||||
const char *test_is_robots_txt_url(void);
|
||||
|
||||
const char *program_argstring = "TEST";
|
||||
|
||||
int tests_run;
|
||||
static int tests_run;
|
||||
|
||||
static const char *
|
||||
all_tests(void)
|
||||
{
|
||||
#ifdef HAVE_METALINK
|
||||
mu_run_test (test_find_key_value);
|
||||
mu_run_test (test_find_key_values);
|
||||
mu_run_test (test_has_key);
|
||||
#endif
|
||||
mu_run_test (test_parse_content_disposition);
|
||||
mu_run_test (test_parse_range_header);
|
||||
mu_run_test (test_subdir_p);
|
||||
mu_run_test (test_dir_matches_p);
|
||||
mu_run_test (test_commands_sorted);
|
||||
@@ -67,6 +63,12 @@ all_tests(void)
|
||||
mu_run_test (test_append_uri_pathel);
|
||||
mu_run_test (test_are_urls_equal);
|
||||
mu_run_test (test_is_robots_txt_url);
|
||||
#ifdef HAVE_HSTS
|
||||
mu_run_test (test_hsts_new_entry);
|
||||
mu_run_test (test_hsts_url_rewrite_superdomain);
|
||||
mu_run_test (test_hsts_url_rewrite_congruent);
|
||||
mu_run_test (test_hsts_read_database);
|
||||
#endif
|
||||
|
||||
return NULL;
|
||||
}
|
||||
@@ -78,6 +80,7 @@ main (int argc _GL_UNUSED, const char *argv[])
|
||||
{
|
||||
const char *result;
|
||||
|
||||
printf ("[DEBUG] Testing...\n\n");
|
||||
#ifdef ENABLE_NLS
|
||||
/* Set the current locale. */
|
||||
setlocale (LC_ALL, "");
|
||||
|
||||
13
src/test.h
13
src/test.h
@@ -1,6 +1,6 @@
|
||||
/* Unit testing declarations.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software
|
||||
Foundation, Inc.
|
||||
Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free
|
||||
Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -43,9 +43,12 @@ do { \
|
||||
puts("PASSED\n"); \
|
||||
} while (0)
|
||||
|
||||
extern int tests_run;
|
||||
|
||||
const char *test_has_key (void);
|
||||
const char *test_find_key_value (void);
|
||||
const char *test_find_key_values (void);
|
||||
const char *test_parse_content_disposition(void);
|
||||
const char *test_parse_range_header(void);
|
||||
const char *test_commands_sorted(void);
|
||||
const char *test_cmd_spec_restrict_file_names(void);
|
||||
const char *test_is_robots_txt_url(void);
|
||||
@@ -54,6 +57,10 @@ const char *test_append_uri_pathel(void);
|
||||
const char *test_are_urls_equal(void);
|
||||
const char *test_subdir_p(void);
|
||||
const char *test_dir_matches_p(void);
|
||||
const char *test_hsts_new_entry(void);
|
||||
const char *test_hsts_url_rewrite_superdomain(void);
|
||||
const char *test_hsts_url_rewrite_congruent(void);
|
||||
const char *test_hsts_read_database(void);
|
||||
|
||||
#endif /* TEST_H */
|
||||
|
||||
|
||||
222
src/url.c
222
src/url.c
@@ -1,7 +1,7 @@
|
||||
/* URL handling.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -43,6 +43,11 @@ as that of the covered work. */
|
||||
#include "host.h" /* for is_valid_ipv6_address */
|
||||
#include "c-strcase.h"
|
||||
|
||||
#ifdef HAVE_ICONV
|
||||
# include <iconv.h>
|
||||
#endif
|
||||
#include <langinfo.h>
|
||||
|
||||
#ifdef __VMS
|
||||
#include "vms.h"
|
||||
#endif /* def __VMS */
|
||||
@@ -78,6 +83,13 @@ static struct scheme_data supported_schemes[] =
|
||||
{ "https", "https://", DEFAULT_HTTPS_PORT, scm_has_query|scm_has_fragment },
|
||||
#endif
|
||||
{ "ftp", "ftp://", DEFAULT_FTP_PORT, scm_has_params|scm_has_fragment },
|
||||
#ifdef HAVE_SSL
|
||||
/*
|
||||
* Explicit FTPS uses the same port as FTP.
|
||||
* Implicit FTPS has its own port (990), but it is disabled by default.
|
||||
*/
|
||||
{ "ftps", "ftps://", DEFAULT_FTP_PORT, scm_has_params|scm_has_fragment },
|
||||
#endif
|
||||
|
||||
/* SCHEME_INVALID */
|
||||
{ NULL, NULL, -1, 0 }
|
||||
@@ -161,17 +173,8 @@ static const unsigned char urlchr_table[256] =
|
||||
#undef U
|
||||
#undef RU
|
||||
|
||||
/* URL-unescape the string S.
|
||||
|
||||
This is done by transforming the sequences "%HH" to the character
|
||||
represented by the hexadecimal digits HH. If % is not followed by
|
||||
two hexadecimal digits, it is inserted literally.
|
||||
|
||||
The transformation is done in place. If you need the original
|
||||
string intact, make a copy before calling this function. */
|
||||
|
||||
void
|
||||
url_unescape (char *s)
|
||||
static void
|
||||
url_unescape_1 (char *s, unsigned char mask)
|
||||
{
|
||||
char *t = s; /* t - tortoise */
|
||||
char *h = s; /* h - hare */
|
||||
@@ -190,6 +193,8 @@ url_unescape (char *s)
|
||||
if (!h[1] || !h[2] || !(c_isxdigit (h[1]) && c_isxdigit (h[2])))
|
||||
goto copychar;
|
||||
c = X2DIGITS_TO_NUM (h[1], h[2]);
|
||||
if (urlchr_test(c, mask))
|
||||
goto copychar;
|
||||
/* Don't unescape %00 because there is no way to insert it
|
||||
into a C string without effectively truncating it. */
|
||||
if (c == '\0')
|
||||
@@ -201,6 +206,31 @@ url_unescape (char *s)
|
||||
*t = '\0';
|
||||
}
|
||||
|
||||
/* URL-unescape the string S.
|
||||
|
||||
This is done by transforming the sequences "%HH" to the character
|
||||
represented by the hexadecimal digits HH. If % is not followed by
|
||||
two hexadecimal digits, it is inserted literally.
|
||||
|
||||
The transformation is done in place. If you need the original
|
||||
string intact, make a copy before calling this function. */
|
||||
void
|
||||
url_unescape (char *s)
|
||||
{
|
||||
url_unescape_1 (s, 0);
|
||||
}
|
||||
|
||||
/* URL-unescape the string S.
|
||||
|
||||
This functions behaves identically as url_unescape(), but does not
|
||||
convert characters from "reserved". In other words, it only converts
|
||||
"unsafe" characters. */
|
||||
void
|
||||
url_unescape_except_reserved (char *s)
|
||||
{
|
||||
url_unescape_1 (s, urlchr_reserved);
|
||||
}
|
||||
|
||||
/* The core of url_escape_* functions. Escapes the characters that
|
||||
match the provided mask in urlchr_table.
|
||||
|
||||
@@ -482,6 +512,12 @@ scheme_disable (enum url_scheme scheme)
|
||||
supported_schemes[scheme].flags |= scm_disabled;
|
||||
}
|
||||
|
||||
const char *
|
||||
scheme_leading_string (enum url_scheme scheme)
|
||||
{
|
||||
return supported_schemes[scheme].leading_string;
|
||||
}
|
||||
|
||||
/* Skip the username and password, if present in the URL. The
|
||||
function should *not* be called with the complete URL, but with the
|
||||
portion after the scheme.
|
||||
@@ -701,7 +737,7 @@ url_parse (const char *url, int *error, struct iri *iri, bool percent_encode)
|
||||
{
|
||||
char *new_url = NULL;
|
||||
|
||||
iri->utf8_encode = remote_to_utf8 (iri, iri->orig_url ? iri->orig_url : url, (const char **) &new_url);
|
||||
iri->utf8_encode = remote_to_utf8 (iri, iri->orig_url ? iri->orig_url : url, &new_url);
|
||||
if (!iri->utf8_encode)
|
||||
new_url = NULL;
|
||||
else
|
||||
@@ -1177,7 +1213,7 @@ url_free (struct url *url)
|
||||
if (url)
|
||||
{
|
||||
if (url->idn_allocated) {
|
||||
idn_free (url->host); /* A dummy if !defined(ENABLE_IRI) */
|
||||
idn2_free (url->host); /* A dummy if !defined(ENABLE_IRI) */
|
||||
url->host = NULL;
|
||||
}
|
||||
else
|
||||
@@ -1206,7 +1242,7 @@ mkalldirs (const char *path)
|
||||
{
|
||||
const char *p;
|
||||
char *t;
|
||||
struct_stat st;
|
||||
struct stat st;
|
||||
int res;
|
||||
|
||||
p = path + strlen (path);
|
||||
@@ -1241,12 +1277,14 @@ mkalldirs (const char *path)
|
||||
name exists, we just remove it and create the directory
|
||||
anyway. */
|
||||
DEBUGP (("Removing %s because of directory danger!\n", t));
|
||||
unlink (t);
|
||||
if (unlink (t))
|
||||
logprintf (LOG_NOTQUIET, "Failed to unlink %s (%d): %s\n",
|
||||
t, errno, strerror(errno));
|
||||
}
|
||||
}
|
||||
res = make_directory (t);
|
||||
if (res != 0)
|
||||
logprintf (LOG_NOTQUIET, "%s: %s", t, strerror (errno));
|
||||
logprintf (LOG_NOTQUIET, "%s: %s\n", t, strerror (errno));
|
||||
xfree (t);
|
||||
return res;
|
||||
}
|
||||
@@ -1328,8 +1366,9 @@ append_string (const char *str, struct growable *dest)
|
||||
|
||||
enum {
|
||||
filechr_not_unix = 1, /* unusable on Unix, / and \0 */
|
||||
filechr_not_windows = 2, /* unusable on Windows, one of \|/<>?:*" */
|
||||
filechr_control = 4 /* a control character, e.g. 0-31 */
|
||||
filechr_not_vms = 2, /* unusable on VMS (ODS5), 0x00-0x1F * ? */
|
||||
filechr_not_windows = 4, /* unusable on Windows, one of \|/<>?:*" */
|
||||
filechr_control = 8 /* a control character, e.g. 0-31 */
|
||||
};
|
||||
|
||||
#define FILE_CHAR_TEST(c, mask) \
|
||||
@@ -1338,11 +1377,14 @@ enum {
|
||||
|
||||
/* Shorthands for the table: */
|
||||
#define U filechr_not_unix
|
||||
#define V filechr_not_vms
|
||||
#define W filechr_not_windows
|
||||
#define C filechr_control
|
||||
|
||||
#define UVWC U|V|W|C
|
||||
#define UW U|W
|
||||
#define UWC U|W|C
|
||||
#define VC V|C
|
||||
#define VW V|W
|
||||
|
||||
/* Table of characters unsafe under various conditions (see above).
|
||||
|
||||
@@ -1353,25 +1395,25 @@ enum {
|
||||
|
||||
static const unsigned char filechr_table[256] =
|
||||
{
|
||||
UWC, C, C, C, C, C, C, C, /* NUL SOH STX ETX EOT ENQ ACK BEL */
|
||||
C, C, C, C, C, C, C, C, /* BS HT LF VT FF CR SO SI */
|
||||
C, C, C, C, C, C, C, C, /* DLE DC1 DC2 DC3 DC4 NAK SYN ETB */
|
||||
C, C, C, C, C, C, C, C, /* CAN EM SUB ESC FS GS RS US */
|
||||
0, 0, W, 0, 0, 0, 0, 0, /* SP ! " # $ % & ' */
|
||||
0, 0, W, 0, 0, 0, 0, UW, /* ( ) * + , - . / */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* 0 1 2 3 4 5 6 7 */
|
||||
0, 0, W, 0, W, 0, W, W, /* 8 9 : ; < = > ? */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* @ A B C D E F G */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* H I J K L M N O */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* P Q R S T U V W */
|
||||
0, 0, 0, 0, W, 0, 0, 0, /* X Y Z [ \ ] ^ _ */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* ` a b c d e f g */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* h i j k l m n o */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* p q r s t u v w */
|
||||
0, 0, 0, 0, W, 0, 0, C, /* x y z { | } ~ DEL */
|
||||
UVWC, VC, VC, VC, VC, VC, VC, VC, /* NUL SOH STX ETX EOT ENQ ACK BEL */
|
||||
VC, VC, VC, VC, VC, VC, VC, VC, /* BS HT LF VT FF CR SO SI */
|
||||
VC, VC, VC, VC, VC, VC, VC, VC, /* DLE DC1 DC2 DC3 DC4 NAK SYN ETB */
|
||||
VC, VC, VC, VC, VC, VC, VC, VC, /* CAN EM SUB ESC FS GS RS US */
|
||||
0, 0, W, 0, 0, 0, 0, 0, /* SP ! " # $ % & ' */
|
||||
0, 0, VW, 0, 0, 0, 0, UW, /* ( ) * + , - . / */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* 0 1 2 3 4 5 6 7 */
|
||||
0, 0, W, 0, W, 0, W, VW, /* 8 9 : ; < = > ? */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* @ A B C D E F G */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* H I J K L M N O */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* P Q R S T U V W */
|
||||
0, 0, 0, 0, W, 0, 0, 0, /* X Y Z [ \ ] ^ _ */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* ` a b c d e f g */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* h i j k l m n o */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, /* p q r s t u v w */
|
||||
0, 0, 0, 0, W, 0, 0, C, /* x y z { | } ~ DEL */
|
||||
|
||||
C, C, C, C, C, C, C, C, C, C, C, C, C, C, C, C, /* 128-143 */
|
||||
C, C, C, C, C, C, C, C, C, C, C, C, C, C, C, C, /* 144-159 */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 128-143 */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 144-159 */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
|
||||
@@ -1381,10 +1423,13 @@ UWC, C, C, C, C, C, C, C, /* NUL SOH STX ETX EOT ENQ ACK BEL */
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
};
|
||||
#undef U
|
||||
#undef V
|
||||
#undef W
|
||||
#undef C
|
||||
#undef UW
|
||||
#undef UWC
|
||||
#undef UVWC
|
||||
#undef VC
|
||||
#undef VW
|
||||
|
||||
/* FN_PORT_SEP is the separator between host and port in file names
|
||||
for non-standard port numbers. On Unix this is normally ':', as in
|
||||
@@ -1393,10 +1438,14 @@ UWC, C, C, C, C, C, C, C, /* NUL SOH STX ETX EOT ENQ ACK BEL */
|
||||
#define FN_PORT_SEP (opt.restrict_files_os != restrict_windows ? ':' : '+')
|
||||
|
||||
/* FN_QUERY_SEP is the separator between the file name and the URL
|
||||
query, normally '?'. Since Windows cannot handle '?' as part of
|
||||
query, normally '?'. Because VMS and Windows cannot handle '?' in a
|
||||
file name, we use '@' instead there. */
|
||||
#define FN_QUERY_SEP (opt.restrict_files_os != restrict_windows ? '?' : '@')
|
||||
#define FN_QUERY_SEP_STR (opt.restrict_files_os != restrict_windows ? "?" : "@")
|
||||
#define FN_QUERY_SEP \
|
||||
(((opt.restrict_files_os != restrict_vms) && \
|
||||
(opt.restrict_files_os != restrict_windows)) ? '?' : '@')
|
||||
#define FN_QUERY_SEP_STR \
|
||||
(((opt.restrict_files_os != restrict_vms) && \
|
||||
(opt.restrict_files_os != restrict_windows)) ? "?" : "@")
|
||||
|
||||
/* Quote path element, characters in [b, e), as file name, and append
|
||||
the quoted string to DEST. Each character is quoted as per
|
||||
@@ -1415,6 +1464,8 @@ append_uri_pathel (const char *b, const char *e, bool escaped,
|
||||
int mask;
|
||||
if (opt.restrict_files_os == restrict_unix)
|
||||
mask = filechr_not_unix;
|
||||
else if (opt.restrict_files_os == restrict_vms)
|
||||
mask = filechr_not_vms;
|
||||
else
|
||||
mask = filechr_not_windows;
|
||||
if (opt.restrict_files_ctrl)
|
||||
@@ -1493,6 +1544,80 @@ append_uri_pathel (const char *b, const char *e, bool escaped,
|
||||
append_null (dest);
|
||||
}
|
||||
|
||||
static char *
|
||||
convert_fname (char *fname)
|
||||
{
|
||||
char *converted_fname = fname;
|
||||
const char *from_encoding = opt.encoding_remote;
|
||||
const char *to_encoding = opt.locale;
|
||||
iconv_t cd;
|
||||
size_t len, done, inlen, outlen;
|
||||
char *s;
|
||||
const char *orig_fname = fname;
|
||||
|
||||
/* Defaults for remote and local encodings. */
|
||||
if (!from_encoding)
|
||||
from_encoding = "UTF-8";
|
||||
if (!to_encoding)
|
||||
to_encoding = nl_langinfo (CODESET);
|
||||
|
||||
cd = iconv_open (to_encoding, from_encoding);
|
||||
if (cd == (iconv_t)(-1))
|
||||
logprintf (LOG_VERBOSE, _("Conversion from %s to %s isn't supported\n"),
|
||||
quote (from_encoding), quote (to_encoding));
|
||||
else
|
||||
{
|
||||
inlen = strlen (fname);
|
||||
len = outlen = inlen * 2;
|
||||
converted_fname = s = xmalloc (outlen + 1);
|
||||
done = 0;
|
||||
|
||||
for (;;)
|
||||
{
|
||||
if (iconv (cd, (ICONV_CONST char **) &fname, &inlen, &s, &outlen) != (size_t)(-1)
|
||||
&& iconv (cd, NULL, NULL, &s, &outlen) != (size_t)(-1))
|
||||
{
|
||||
*(converted_fname + len - outlen - done) = '\0';
|
||||
iconv_close(cd);
|
||||
DEBUGP (("Converted file name '%s' (%s) -> '%s' (%s)\n",
|
||||
orig_fname, from_encoding, converted_fname, to_encoding));
|
||||
xfree (orig_fname);
|
||||
return converted_fname;
|
||||
}
|
||||
|
||||
/* Incomplete or invalid multibyte sequence */
|
||||
if (errno == EINVAL || errno == EILSEQ)
|
||||
{
|
||||
logprintf (LOG_VERBOSE,
|
||||
_("Incomplete or invalid multibyte sequence encountered\n"));
|
||||
xfree (converted_fname);
|
||||
converted_fname = (char *)orig_fname;
|
||||
break;
|
||||
}
|
||||
else if (errno == E2BIG) /* Output buffer full */
|
||||
{
|
||||
done = len;
|
||||
len = outlen = done + inlen * 2;
|
||||
converted_fname = xrealloc (converted_fname, outlen + 1);
|
||||
s = converted_fname + done;
|
||||
}
|
||||
else /* Weird, we got an unspecified error */
|
||||
{
|
||||
logprintf (LOG_VERBOSE, _("Unhandled errno %d\n"), errno);
|
||||
xfree (converted_fname);
|
||||
converted_fname = (char *)orig_fname;
|
||||
break;
|
||||
}
|
||||
}
|
||||
DEBUGP (("Failed to convert file name '%s' (%s) -> '?' (%s)\n",
|
||||
orig_fname, from_encoding, to_encoding));
|
||||
}
|
||||
|
||||
iconv_close(cd);
|
||||
|
||||
return converted_fname;
|
||||
}
|
||||
|
||||
/* Append to DEST the directory structure that corresponds the
|
||||
directory part of URL's path. For example, if the URL is
|
||||
http://server/dir1/dir2/file, this appends "/dir1/dir2".
|
||||
@@ -1668,6 +1793,8 @@ url_file_name (const struct url *u, char *replaced_filename)
|
||||
|
||||
xfree (temp_fnres.base);
|
||||
|
||||
fname = convert_fname (fname);
|
||||
|
||||
/* Check the cases in which the unique extensions are not used:
|
||||
1) Clobbering is turned off (-nc).
|
||||
2) Retrieval with regetting.
|
||||
@@ -1741,7 +1868,7 @@ path_simplify (enum url_scheme scheme, char *path)
|
||||
else if (h[0] == '.' && h[1] == '.' && (h[2] == '/' || h[2] == '\0'))
|
||||
{
|
||||
/* Handle "../" by retreating the tortoise by one path
|
||||
element -- but not past beggining. */
|
||||
element -- but not past beginning. */
|
||||
if (t > beg)
|
||||
{
|
||||
/* Move backwards until T hits the beginning of the
|
||||
@@ -1749,7 +1876,11 @@ path_simplify (enum url_scheme scheme, char *path)
|
||||
for (--t; t > beg && t[-1] != '/'; t--)
|
||||
;
|
||||
}
|
||||
else if (scheme == SCHEME_FTP)
|
||||
else if (scheme == SCHEME_FTP
|
||||
#ifdef HAVE_SSL
|
||||
|| scheme == SCHEME_FTPS
|
||||
#endif
|
||||
)
|
||||
{
|
||||
/* If we're at the beginning, copy the "../" literally
|
||||
and move the beginning so a later ".." doesn't remove
|
||||
@@ -2319,6 +2450,7 @@ test_append_uri_pathel(void)
|
||||
|
||||
mu_assert ("test_append_uri_pathel: wrong result",
|
||||
strcmp (dest.base, test_array[i].expected_result) == 0);
|
||||
xfree (dest.base);
|
||||
}
|
||||
|
||||
return NULL;
|
||||
|
||||
14
src/url.h
14
src/url.h
@@ -1,7 +1,7 @@
|
||||
/* Declarations for url.c.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -36,6 +36,7 @@ as that of the covered work. */
|
||||
#define DEFAULT_HTTP_PORT 80
|
||||
#define DEFAULT_FTP_PORT 21
|
||||
#define DEFAULT_HTTPS_PORT 443
|
||||
#define DEFAULT_FTPS_IMPLICIT_PORT 990
|
||||
|
||||
/* This represents how many characters less than the OS max name length a file
|
||||
* should be. More precisely, a file name should be at most
|
||||
@@ -70,6 +71,9 @@ enum url_scheme {
|
||||
SCHEME_HTTPS,
|
||||
#endif
|
||||
SCHEME_FTP,
|
||||
#ifdef HAVE_SSL
|
||||
SCHEME_FTPS,
|
||||
#endif
|
||||
SCHEME_INVALID
|
||||
};
|
||||
|
||||
@@ -96,8 +100,8 @@ struct url
|
||||
char *user;
|
||||
char *passwd;
|
||||
|
||||
/* 'host' is allocated by idna_to_ascii_8z() via idn_encode().
|
||||
* Call 'idn_free()' to free this memory. */
|
||||
/* 'host' is allocated by idn2_lookup_u8() via idn_encode().
|
||||
* Call 'idn2_free()' to free this memory. */
|
||||
bool idn_allocated;
|
||||
};
|
||||
|
||||
@@ -106,6 +110,7 @@ struct url
|
||||
char *url_escape (const char *);
|
||||
char *url_escape_unsafe_and_reserved (const char *);
|
||||
void url_unescape (char *);
|
||||
void url_unescape_except_reserved (char *);
|
||||
|
||||
struct url *url_parse (const char *, int *, struct iri *iri, bool percent_encode);
|
||||
char *url_error (const char *, int);
|
||||
@@ -119,6 +124,7 @@ bool url_has_scheme (const char *);
|
||||
bool url_valid_scheme (const char *);
|
||||
int scheme_default_port (enum url_scheme);
|
||||
void scheme_disable (enum url_scheme);
|
||||
const char *scheme_leading_string (enum url_scheme);
|
||||
|
||||
char *url_string (const struct url *, enum url_auth_mode);
|
||||
char *url_file_name (const struct url *, char *);
|
||||
|
||||
304
src/utils.c
304
src/utils.c
@@ -1,7 +1,7 @@
|
||||
/* Various utility functions.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -31,14 +31,12 @@ as that of the covered work. */
|
||||
|
||||
#include "wget.h"
|
||||
|
||||
#include "sha256.h"
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <time.h>
|
||||
#include <unistd.h>
|
||||
#ifdef HAVE_MMAP
|
||||
# include <sys/mman.h>
|
||||
#endif
|
||||
#ifdef HAVE_PROCESS_H
|
||||
# include <process.h> /* getpid() */
|
||||
#endif
|
||||
@@ -89,6 +87,18 @@ as that of the covered work. */
|
||||
# define USE_SIGNAL_TIMEOUT
|
||||
#endif
|
||||
|
||||
/* Some systems (Linux libc5, "NCR MP-RAS 3.0", and others) don't
|
||||
provide MAP_FAILED, a symbolic constant for the value returned by
|
||||
mmap() when it doesn't work. Usually, this constant should be -1.
|
||||
This only makes sense for files that use mmap() and include
|
||||
sys/mman.h *before* sysdep.h, but doesn't hurt others. */
|
||||
#ifdef HAVE_MMAP
|
||||
# include <sys/mman.h>
|
||||
# ifndef MAP_FAILED
|
||||
# define MAP_FAILED ((void *) -1)
|
||||
# endif
|
||||
#endif
|
||||
|
||||
#include "utils.h"
|
||||
#include "hash.h"
|
||||
|
||||
@@ -103,7 +113,7 @@ as that of the covered work. */
|
||||
#include "exits.h"
|
||||
#include "c-strcase.h"
|
||||
|
||||
static void _Noreturn
|
||||
_Noreturn static void
|
||||
memfatal (const char *context, long attempted_size)
|
||||
{
|
||||
/* Make sure we don't try to store part of the log line, and thus
|
||||
@@ -225,14 +235,20 @@ xstrdup_lower (const char *s)
|
||||
|
||||
/* Copy the string formed by two pointers (one on the beginning, other
|
||||
on the char after the last char) to a new, malloc-ed location.
|
||||
0-terminate it. */
|
||||
0-terminate it.
|
||||
If both pointers are NULL, the function returns an empty string. */
|
||||
char *
|
||||
strdupdelim (const char *beg, const char *end)
|
||||
{
|
||||
char *res = xmalloc (end - beg + 1);
|
||||
memcpy (res, beg, end - beg);
|
||||
res[end - beg] = '\0';
|
||||
return res;
|
||||
if (beg && beg <= end)
|
||||
{
|
||||
char *res = xmalloc (end - beg + 1);
|
||||
memcpy (res, beg, end - beg);
|
||||
res[end - beg] = '\0';
|
||||
return res;
|
||||
}
|
||||
|
||||
return xstrdup("");
|
||||
}
|
||||
|
||||
/* Parse a string containing comma-separated elements, and return a
|
||||
@@ -282,13 +298,6 @@ sepstring (const char *s)
|
||||
vsnprintf until the correct size is found. Since Wget also ships a
|
||||
fallback implementation of vsnprintf, this should be portable. */
|
||||
|
||||
/* Constant is using for limits memory allocation for text buffer.
|
||||
Applicable in situation when: vasprintf is not available in the system
|
||||
and vsnprintf return -1 when long line is truncated (in old versions of
|
||||
glibc and in other system where C99 doesn`t support) */
|
||||
|
||||
#define FMT_MAX_LENGTH 1048576
|
||||
|
||||
char *
|
||||
aprintf (const char *fmt, ...)
|
||||
{
|
||||
@@ -308,6 +317,13 @@ aprintf (const char *fmt, ...)
|
||||
return str;
|
||||
#else /* not HAVE_VASPRINTF */
|
||||
|
||||
/* Constant is using for limits memory allocation for text buffer.
|
||||
Applicable in situation when: vasprintf is not available in the system
|
||||
and vsnprintf return -1 when long line is truncated (in old versions of
|
||||
glibc and in other system where C99 doesn`t support) */
|
||||
|
||||
#define FMT_MAX_LENGTH 1048576
|
||||
|
||||
/* vasprintf is unavailable. snprintf into a small buffer and
|
||||
resize it as necessary. */
|
||||
int size = 32;
|
||||
@@ -336,7 +352,7 @@ aprintf (const char *fmt, ...)
|
||||
{ /* maybe we have some wrong
|
||||
format string? */
|
||||
logprintf (LOG_ALWAYS,
|
||||
_("%s: aprintf: text buffer is too big (%ld bytes), "
|
||||
_("%s: aprintf: text buffer is too big (%d bytes), "
|
||||
"aborting.\n"),
|
||||
exec_name, size); /* printout a log message */
|
||||
abort (); /* and abort... */
|
||||
@@ -557,7 +573,7 @@ int
|
||||
remove_link (const char *file)
|
||||
{
|
||||
int err = 0;
|
||||
struct_stat st;
|
||||
struct stat st;
|
||||
|
||||
if (lstat (file, &st) == 0 && S_ISLNK (st.st_mode))
|
||||
{
|
||||
@@ -583,7 +599,7 @@ file_exists_p (const char *filename)
|
||||
#ifdef HAVE_ACCESS
|
||||
return access (filename, F_OK) >= 0;
|
||||
#else
|
||||
struct_stat buf;
|
||||
struct stat buf;
|
||||
return stat (filename, &buf) >= 0;
|
||||
#endif
|
||||
}
|
||||
@@ -593,7 +609,7 @@ file_exists_p (const char *filename)
|
||||
bool
|
||||
file_non_directory_p (const char *path)
|
||||
{
|
||||
struct_stat buf;
|
||||
struct stat buf;
|
||||
/* Use lstat() rather than stat() so that symbolic links pointing to
|
||||
directories can be identified correctly. */
|
||||
if (lstat (path, &buf) != 0)
|
||||
@@ -620,7 +636,7 @@ file_size (const char *filename)
|
||||
fclose (fp);
|
||||
return size;
|
||||
#else
|
||||
struct_stat st;
|
||||
struct stat st;
|
||||
if (stat (filename, &st) < 0)
|
||||
return -1;
|
||||
return st.st_size;
|
||||
@@ -1174,7 +1190,7 @@ wget_read_file (const char *file)
|
||||
|
||||
#ifdef HAVE_MMAP
|
||||
{
|
||||
struct_fstat buf;
|
||||
struct stat buf;
|
||||
if (fstat (fd, &buf) < 0)
|
||||
goto mmap_lose;
|
||||
fm->length = buf.st_size;
|
||||
@@ -1284,7 +1300,10 @@ free_vec (char **vec)
|
||||
{
|
||||
char **p = vec;
|
||||
while (*p)
|
||||
xfree (*p++);
|
||||
{
|
||||
xfree (*p);
|
||||
p++;
|
||||
}
|
||||
xfree (vec);
|
||||
}
|
||||
}
|
||||
@@ -1314,7 +1333,7 @@ merge_vecs (char **v1, char **v2)
|
||||
for (j = 0; v2[j]; j++)
|
||||
;
|
||||
/* Reallocate v1. */
|
||||
v1 = xrealloc (v1, (i + j + 1) * sizeof (char **));
|
||||
v1 = xrealloc (v1, (i + j + 1) * sizeof (char *));
|
||||
memcpy (v1 + i, v2, (j + 1) * sizeof (char *));
|
||||
xfree (v2);
|
||||
return v1;
|
||||
@@ -1917,7 +1936,7 @@ random_float (void)
|
||||
|
||||
static sigjmp_buf run_with_timeout_env;
|
||||
|
||||
static void _Noreturn
|
||||
_Noreturn static void
|
||||
abort_run_with_timeout (int sig _GL_UNUSED)
|
||||
{
|
||||
assert (sig == SIGALRM);
|
||||
@@ -2032,13 +2051,16 @@ run_with_timeout (double timeout, void (*fun) (void *), void *arg)
|
||||
return false;
|
||||
}
|
||||
|
||||
signal (SIGALRM, abort_run_with_timeout);
|
||||
if (SETJMP (run_with_timeout_env) != 0)
|
||||
{
|
||||
/* Longjumped out of FUN with a timeout. */
|
||||
signal (SIGALRM, SIG_DFL);
|
||||
return true;
|
||||
}
|
||||
else
|
||||
{
|
||||
signal (SIGALRM, abort_run_with_timeout);
|
||||
}
|
||||
alarm_set (timeout);
|
||||
fun (arg);
|
||||
|
||||
@@ -2127,7 +2149,7 @@ xsleep (double seconds)
|
||||
base64 data. */
|
||||
|
||||
size_t
|
||||
base64_encode (const void *data, size_t length, char *dest)
|
||||
wget_base64_encode (const void *data, size_t length, char *dest)
|
||||
{
|
||||
/* Conversion table. */
|
||||
static const char tbl[64] = {
|
||||
@@ -2195,7 +2217,7 @@ base64_encode (const void *data, size_t length, char *dest)
|
||||
This function originates from Free Recode. */
|
||||
|
||||
ssize_t
|
||||
base64_decode (const char *base64, void *dest)
|
||||
wget_base64_decode (const char *base64, void *dest)
|
||||
{
|
||||
/* Table of base64 values for first 128 characters. Note that this
|
||||
assumes ASCII (but so does Wget in other places). */
|
||||
@@ -2400,17 +2422,17 @@ mergesort_internal (void *base, void *temp, size_t size, size_t from, size_t to,
|
||||
}
|
||||
|
||||
/* Stable sort with interface exactly like standard library's qsort.
|
||||
Uses mergesort internally, allocating temporary storage with
|
||||
alloca. */
|
||||
Uses mergesort internally. */
|
||||
|
||||
void
|
||||
stable_sort (void *base, size_t nmemb, size_t size,
|
||||
int (*cmpfun) (const void *, const void *))
|
||||
{
|
||||
if (size > 1)
|
||||
if (nmemb > 1 && size > 1)
|
||||
{
|
||||
void *temp = alloca (nmemb * size * sizeof (void *));
|
||||
void *temp = xmalloc (nmemb * size);
|
||||
mergesort_internal (base, temp, size, 0, nmemb - 1, cmpfun);
|
||||
xfree(temp);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2503,6 +2525,220 @@ get_max_length (const char *path, int length, int name)
|
||||
return ret;
|
||||
}
|
||||
|
||||
void
|
||||
wg_hex_to_string (char *str_buffer, const char *hex_buffer, size_t hex_len)
|
||||
{
|
||||
size_t i;
|
||||
|
||||
for (i = 0; i < hex_len; i++)
|
||||
{
|
||||
/* Each byte takes 2 characters. */
|
||||
sprintf (str_buffer + 2 * i, "%02x", (unsigned) (hex_buffer[i] & 0xFF));
|
||||
}
|
||||
|
||||
/* Null-terminate result. */
|
||||
str_buffer[2 * i] = '\0';
|
||||
}
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
|
||||
/*
|
||||
* Public key pem to der conversion
|
||||
*/
|
||||
|
||||
static bool
|
||||
wg_pubkey_pem_to_der (const char *pem, unsigned char **der, size_t *der_len)
|
||||
{
|
||||
char *stripped_pem, *begin_pos, *end_pos;
|
||||
size_t pem_count, stripped_pem_count = 0, pem_len;
|
||||
ssize_t size;
|
||||
unsigned char *base64data;
|
||||
|
||||
*der = NULL;
|
||||
*der_len = 0;
|
||||
|
||||
/* if no pem, exit. */
|
||||
if (!pem)
|
||||
return false;
|
||||
|
||||
begin_pos = strstr (pem, "-----BEGIN PUBLIC KEY-----");
|
||||
if (!begin_pos)
|
||||
return false;
|
||||
|
||||
pem_count = begin_pos - pem;
|
||||
/* Invalid if not at beginning AND not directly following \n */
|
||||
if (0 != pem_count && '\n' != pem[pem_count - 1])
|
||||
return false;
|
||||
|
||||
/* 26 is length of "-----BEGIN PUBLIC KEY-----" */
|
||||
pem_count += 26;
|
||||
|
||||
/* Invalid if not directly following \n */
|
||||
end_pos = strstr (pem + pem_count, "\n-----END PUBLIC KEY-----");
|
||||
if (!end_pos)
|
||||
return false;
|
||||
|
||||
pem_len = end_pos - pem;
|
||||
|
||||
stripped_pem = xmalloc (pem_len - pem_count + 1);
|
||||
|
||||
/*
|
||||
* Here we loop through the pem array one character at a time between the
|
||||
* correct indices, and place each character that is not '\n' or '\r'
|
||||
* into the stripped_pem array, which should represent the raw base64 string
|
||||
*/
|
||||
while (pem_count < pem_len) {
|
||||
if ('\n' != pem[pem_count] && '\r' != pem[pem_count])
|
||||
stripped_pem[stripped_pem_count++] = pem[pem_count];
|
||||
++pem_count;
|
||||
}
|
||||
/* Place the null terminator in the correct place */
|
||||
stripped_pem[stripped_pem_count] = '\0';
|
||||
|
||||
base64data = xmalloc (BASE64_LENGTH(stripped_pem_count));
|
||||
|
||||
size = wget_base64_decode (stripped_pem, base64data);
|
||||
|
||||
if (size < 0) {
|
||||
xfree (base64data); /* malformed base64 from server */
|
||||
} else {
|
||||
*der = base64data;
|
||||
*der_len = (size_t) size;
|
||||
}
|
||||
|
||||
xfree (stripped_pem);
|
||||
|
||||
return *der_len > 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Generic pinned public key check.
|
||||
*/
|
||||
|
||||
bool
|
||||
wg_pin_peer_pubkey (const char *pinnedpubkey, const char *pubkey, size_t pubkeylen)
|
||||
{
|
||||
struct file_memory *fm;
|
||||
unsigned char *buf = NULL, *pem_ptr = NULL;
|
||||
size_t size, pem_len;
|
||||
bool pem_read;
|
||||
bool result = false;
|
||||
|
||||
size_t pinkeylen;
|
||||
ssize_t decoded_hash_length;
|
||||
char *pinkeycopy, *begin_pos, *end_pos;
|
||||
unsigned char *sha256sumdigest = NULL, *expectedsha256sumdigest = NULL;
|
||||
|
||||
/* if a path wasn't specified, don't pin */
|
||||
if (!pinnedpubkey)
|
||||
return true;
|
||||
if (!pubkey || !pubkeylen)
|
||||
return result;
|
||||
|
||||
/* only do this if pinnedpubkey starts with "sha256//", length 8 */
|
||||
if (strncmp (pinnedpubkey, "sha256//", 8) == 0) {
|
||||
/* compute sha256sum of public key */
|
||||
sha256sumdigest = xmalloc (SHA256_DIGEST_SIZE);
|
||||
sha256_buffer (pubkey, pubkeylen, sha256sumdigest);
|
||||
expectedsha256sumdigest = xmalloc (SHA256_DIGEST_SIZE + 1);
|
||||
|
||||
/* it starts with sha256//, copy so we can modify it */
|
||||
pinkeylen = strlen (pinnedpubkey) + 1;
|
||||
pinkeycopy = xmalloc (pinkeylen);
|
||||
memcpy (pinkeycopy, pinnedpubkey, pinkeylen);
|
||||
|
||||
/* point begin_pos to the copy, and start extracting keys */
|
||||
begin_pos = pinkeycopy;
|
||||
do
|
||||
{
|
||||
end_pos = strstr (begin_pos, ";sha256//");
|
||||
/*
|
||||
* if there is an end_pos, null terminate,
|
||||
* otherwise it'll go to the end of the original string
|
||||
*/
|
||||
if (end_pos)
|
||||
end_pos[0] = '\0';
|
||||
|
||||
/* decode base64 pinnedpubkey, 8 is length of "sha256//" */
|
||||
decoded_hash_length = wget_base64_decode (begin_pos + 8, expectedsha256sumdigest);
|
||||
/* if valid base64, compare sha256 digests directly */
|
||||
if (SHA256_DIGEST_SIZE == decoded_hash_length &&
|
||||
!memcmp (sha256sumdigest, expectedsha256sumdigest, SHA256_DIGEST_SIZE)) {
|
||||
result = true;
|
||||
break;
|
||||
}
|
||||
|
||||
/*
|
||||
* change back the null-terminator we changed earlier,
|
||||
* and look for next begin
|
||||
*/
|
||||
if (end_pos) {
|
||||
end_pos[0] = ';';
|
||||
begin_pos = strstr (end_pos, "sha256//");
|
||||
}
|
||||
} while (end_pos && begin_pos);
|
||||
|
||||
xfree (sha256sumdigest);
|
||||
xfree (expectedsha256sumdigest);
|
||||
xfree (pinkeycopy);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/* fall back to assuming this is a file path */
|
||||
fm = wget_read_file (pinnedpubkey);
|
||||
if (!fm)
|
||||
return result;
|
||||
|
||||
/* Check the file's size */
|
||||
if (fm->length < 0 || fm->length > MAX_PINNED_PUBKEY_SIZE)
|
||||
goto cleanup;
|
||||
|
||||
/*
|
||||
* if the size of our certificate is bigger than the file
|
||||
* size then it can't match
|
||||
*/
|
||||
size = (size_t) fm->length;
|
||||
if (pubkeylen > size)
|
||||
goto cleanup;
|
||||
|
||||
/* If the sizes are the same, it can't be base64 encoded, must be der */
|
||||
if (pubkeylen == size) {
|
||||
if (!memcmp (pubkey, fm->content, pubkeylen))
|
||||
result = true;
|
||||
goto cleanup;
|
||||
}
|
||||
|
||||
/*
|
||||
* Otherwise we will assume it's PEM and try to decode it
|
||||
* after placing null terminator
|
||||
*/
|
||||
buf = xmalloc (size + 1);
|
||||
memcpy (buf, fm->content, size);
|
||||
buf[size] = '\0';
|
||||
|
||||
pem_read = wg_pubkey_pem_to_der ((const char *) buf, &pem_ptr, &pem_len);
|
||||
/* if it wasn't read successfully, exit */
|
||||
if (!pem_read)
|
||||
goto cleanup;
|
||||
|
||||
/*
|
||||
* if the size of our certificate doesn't match the size of
|
||||
* the decoded file, they can't be the same, otherwise compare
|
||||
*/
|
||||
if (pubkeylen == pem_len && !memcmp (pubkey, pem_ptr, pubkeylen))
|
||||
result = true;
|
||||
|
||||
cleanup:
|
||||
xfree (buf);
|
||||
xfree (pem_ptr);
|
||||
wget_read_file_free (fm);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
#endif /* HAVE_SSL */
|
||||
|
||||
#ifdef TESTING
|
||||
|
||||
const char *
|
||||
|
||||
21
src/utils.h
21
src/utils.h
@@ -1,7 +1,7 @@
|
||||
/* Declarations for utils.c.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -32,9 +32,15 @@ as that of the covered work. */
|
||||
#ifndef UTILS_H
|
||||
#define UTILS_H
|
||||
|
||||
# include <stdlib.h>
|
||||
|
||||
/* Constant is using when we don`t know attempted size exactly */
|
||||
#define UNKNOWN_ATTEMPTED_SIZE -3
|
||||
|
||||
#ifndef MAX_PINNED_PUBKEY_SIZE
|
||||
#define MAX_PINNED_PUBKEY_SIZE 1048576 /* 1MB */
|
||||
#endif
|
||||
|
||||
/* Macros that interface to malloc, but know about type sizes, and
|
||||
cast the result to the appropriate type. The casts are not
|
||||
necessary in standard C, but Wget performs them anyway for the sake
|
||||
@@ -134,8 +140,8 @@ void xsleep (double);
|
||||
/* How many bytes it will take to store LEN bytes in base64. */
|
||||
#define BASE64_LENGTH(len) (4 * (((len) + 2) / 3))
|
||||
|
||||
size_t base64_encode (const void *, size_t, char *);
|
||||
ssize_t base64_decode (const char *, void *);
|
||||
size_t wget_base64_encode (const void *, size_t, char *);
|
||||
ssize_t wget_base64_decode (const char *, void *);
|
||||
|
||||
#ifdef HAVE_LIBPCRE
|
||||
void *compile_pcre_regex (const char *);
|
||||
@@ -155,6 +161,13 @@ long get_max_length (const char *path, int length, int name);
|
||||
size_t strlcpy (char *dst, const char *src, size_t size);
|
||||
#endif
|
||||
|
||||
void wg_hex_to_string (char *str_buffer, const char *hex_buffer, size_t hex_len);
|
||||
|
||||
extern unsigned char char_prop[];
|
||||
|
||||
#ifdef HAVE_SSL
|
||||
/* Check pinned public key. */
|
||||
bool wg_pin_peer_pubkey (const char *pinnedpubkey, const char *pubkey, size_t pubkeylen);
|
||||
#endif
|
||||
|
||||
#endif /* UTILS_H */
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/* Extern declarations for printing version information
|
||||
Copyright (C) 2013 Free Software Foundation, Inc.
|
||||
Copyright (C) 2013, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
|
||||
131
src/warc.c
131
src/warc.c
@@ -1,5 +1,5 @@
|
||||
/* Utility functions for writing WARC files.
|
||||
Copyright (C) 2011, 2012 Free Software Foundation, Inc.
|
||||
Copyright (C) 2011, 2012, 2015 Free Software Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -27,10 +27,6 @@ Corresponding Source for a non-source form of such a combination
|
||||
shall include the source code for the parts of OpenSSL used as well
|
||||
as that of the covered work. */
|
||||
|
||||
#ifndef _GNU_SOURCE
|
||||
#define _GNU_SOURCE
|
||||
#endif
|
||||
|
||||
#include "wget.h"
|
||||
#include "hash.h"
|
||||
#include "utils.h"
|
||||
@@ -102,7 +98,7 @@ static bool warc_write_ok;
|
||||
static FILE *warc_current_cdx_file;
|
||||
|
||||
/* The record id of the warcinfo record of the current WARC file. */
|
||||
static char *warc_current_warcinfo_uuid_str;
|
||||
static char warc_current_warcinfo_uuid_str[48];
|
||||
|
||||
/* The file name of the current WARC file. */
|
||||
static char *warc_current_filename;
|
||||
@@ -250,6 +246,22 @@ warc_write_header (const char *name, const char *value)
|
||||
return warc_write_ok;
|
||||
}
|
||||
|
||||
/* Writes a WARC header with a URI as value to the current WARC record.
|
||||
This method may be run after warc_write_start_record and
|
||||
before warc_write_block_from_file. */
|
||||
static bool
|
||||
warc_write_header_uri (const char *name, const char *value)
|
||||
{
|
||||
if (value)
|
||||
{
|
||||
warc_write_string (name);
|
||||
warc_write_string (": <");
|
||||
warc_write_string (value);
|
||||
warc_write_string (">\r\n");
|
||||
}
|
||||
return warc_write_ok;
|
||||
}
|
||||
|
||||
/* Copies the contents of DATA_IN to the WARC record.
|
||||
Adds a Content-Length header to the WARC record.
|
||||
Run this method after warc_write_header,
|
||||
@@ -404,7 +416,7 @@ warc_write_date_header (const char *timestamp)
|
||||
the current WARC record. If IP is NULL, no header will
|
||||
be written. */
|
||||
static bool
|
||||
warc_write_ip_header (ip_address *ip)
|
||||
warc_write_ip_header (const ip_address *ip)
|
||||
{
|
||||
if (ip != NULL)
|
||||
return warc_write_header ("WARC-IP-Address", print_address (ip));
|
||||
@@ -435,9 +447,7 @@ warc_sha1_stream_with_payload (FILE *stream, void *res_block, void *res_payload,
|
||||
off_t pos;
|
||||
off_t sum;
|
||||
|
||||
char *buffer = malloc (BLOCKSIZE + 72);
|
||||
if (!buffer)
|
||||
return 1;
|
||||
char *buffer = xmalloc (BLOCKSIZE + 72);
|
||||
|
||||
/* Initialize the computation context. */
|
||||
sha1_init_ctx (&ctx_block);
|
||||
@@ -542,14 +552,17 @@ warc_sha1_stream_with_payload (FILE *stream, void *res_block, void *res_payload,
|
||||
/* Converts the SHA1 digest to a base32-encoded string.
|
||||
"sha1:DIGEST\0" (Allocates a new string for the response.) */
|
||||
static char *
|
||||
warc_base32_sha1_digest (char *sha1_digest)
|
||||
warc_base32_sha1_digest (const char *sha1_digest, char *sha1_base32, size_t sha1_base32_size)
|
||||
{
|
||||
/* length: "sha1:" + digest + "\0" */
|
||||
char *sha1_base32 = malloc (BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1 + 5 );
|
||||
base32_encode (sha1_digest, SHA1_DIGEST_SIZE, sha1_base32 + 5,
|
||||
BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1);
|
||||
memcpy (sha1_base32, "sha1:", 5);
|
||||
sha1_base32[BASE32_LENGTH(SHA1_DIGEST_SIZE) + 5] = '\0';
|
||||
if (sha1_base32_size >= BASE32_LENGTH(SHA1_DIGEST_SIZE) + 5 + 1)
|
||||
{
|
||||
memcpy (sha1_base32, "sha1:", 5);
|
||||
base32_encode (sha1_digest, SHA1_DIGEST_SIZE, sha1_base32 + 5,
|
||||
sha1_base32_size - 5);
|
||||
}
|
||||
else
|
||||
*sha1_base32 = 0;
|
||||
|
||||
return sha1_base32;
|
||||
}
|
||||
|
||||
@@ -571,18 +584,14 @@ warc_write_digest_headers (FILE *file, long payload_offset)
|
||||
if (warc_sha1_stream_with_payload (file, sha1_res_block,
|
||||
sha1_res_payload, payload_offset) == 0)
|
||||
{
|
||||
char *digest;
|
||||
char digest[BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1 + 5];
|
||||
|
||||
digest = warc_base32_sha1_digest (sha1_res_block);
|
||||
warc_write_header ("WARC-Block-Digest", digest);
|
||||
xfree (digest);
|
||||
warc_write_header ("WARC-Block-Digest",
|
||||
warc_base32_sha1_digest (sha1_res_block, digest, sizeof(digest)));
|
||||
|
||||
if (payload_offset >= 0)
|
||||
{
|
||||
digest = warc_base32_sha1_digest (sha1_res_payload);
|
||||
warc_write_header ("WARC-Payload-Digest", digest);
|
||||
xfree (digest);
|
||||
}
|
||||
warc_write_header ("WARC-Payload-Digest",
|
||||
warc_base32_sha1_digest (sha1_res_payload, digest, sizeof(digest)));
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -734,7 +743,7 @@ warc_uuid_str (char *urn_str)
|
||||
/* Write a warcinfo record to the current file.
|
||||
Updates warc_current_warcinfo_uuid_str. */
|
||||
static bool
|
||||
warc_write_warcinfo_record (char *filename)
|
||||
warc_write_warcinfo_record (const char *filename)
|
||||
{
|
||||
FILE *warc_tmp;
|
||||
char timestamp[22];
|
||||
@@ -743,7 +752,6 @@ warc_write_warcinfo_record (char *filename)
|
||||
/* Write warc-info record as the first record of the file. */
|
||||
/* We add the record id of this info record to the other records in the
|
||||
file. */
|
||||
warc_current_warcinfo_uuid_str = (char *) malloc (48);
|
||||
warc_uuid_str (warc_current_warcinfo_uuid_str);
|
||||
|
||||
warc_timestamp (timestamp, sizeof(timestamp));
|
||||
@@ -827,14 +835,15 @@ warc_start_new_file (bool meta)
|
||||
if (warc_current_file != NULL)
|
||||
fclose (warc_current_file);
|
||||
|
||||
xfree (warc_current_warcinfo_uuid_str);
|
||||
*warc_current_warcinfo_uuid_str = 0;
|
||||
xfree (warc_current_filename);
|
||||
|
||||
warc_current_file_number++;
|
||||
|
||||
base_filename_length = strlen (opt.warc_filename);
|
||||
/* filename format: base + "-" + 5 digit serial number + ".warc.gz" */
|
||||
new_filename = malloc (base_filename_length + 1 + 5 + 8 + 1);
|
||||
new_filename = xmalloc (base_filename_length + 1 + 5 + 8 + 1);
|
||||
|
||||
warc_current_filename = new_filename;
|
||||
|
||||
/* If max size is enabled, we add a serial number to the file names. */
|
||||
@@ -995,7 +1004,7 @@ warc_process_cdx_line (char *lineptr, int field_num_original_url,
|
||||
{
|
||||
/* This is a valid line with a valid checksum. */
|
||||
struct warc_cdx_record *rec;
|
||||
rec = malloc (sizeof (struct warc_cdx_record));
|
||||
rec = xmalloc (sizeof (struct warc_cdx_record));
|
||||
rec->url = original_url;
|
||||
rec->uuid = record_id;
|
||||
memcpy (rec->digest, checksum_v, SHA1_DIGEST_SIZE);
|
||||
@@ -1098,7 +1107,7 @@ _("CDX file does not list record ids. (Missing column 'u'.)\n"));
|
||||
digest. Returns NULL if the url is not found or if the payload digest
|
||||
does not match, or if CDX deduplication is disabled. */
|
||||
static struct warc_cdx_record *
|
||||
warc_find_duplicate_cdx_record (char *url, char *sha1_digest_payload)
|
||||
warc_find_duplicate_cdx_record (const char *url, char *sha1_digest_payload)
|
||||
{
|
||||
struct warc_cdx_record *rec_existing;
|
||||
|
||||
@@ -1228,7 +1237,7 @@ warc_close (void)
|
||||
if (warc_current_file != NULL)
|
||||
{
|
||||
warc_write_metadata ();
|
||||
xfree (warc_current_warcinfo_uuid_str);
|
||||
*warc_current_warcinfo_uuid_str = 0;
|
||||
fclose (warc_current_file);
|
||||
}
|
||||
if (warc_current_cdx_file != NULL)
|
||||
@@ -1293,12 +1302,13 @@ warc_tempfile (void)
|
||||
Calling this function will close body.
|
||||
Returns true on success, false on error. */
|
||||
bool
|
||||
warc_write_request_record (char *url, char *timestamp_str, char *record_uuid,
|
||||
ip_address *ip, FILE *body, off_t payload_offset)
|
||||
warc_write_request_record (const char *url, const char *timestamp_str,
|
||||
const char *record_uuid, const ip_address *ip,
|
||||
FILE *body, off_t payload_offset)
|
||||
{
|
||||
warc_write_start_record ();
|
||||
warc_write_header ("WARC-Type", "request");
|
||||
warc_write_header ("WARC-Target-URI", url);
|
||||
warc_write_header_uri ("WARC-Target-URI", url);
|
||||
warc_write_header ("Content-Type", "application/http;msgtype=request");
|
||||
warc_write_date_header (timestamp_str);
|
||||
warc_write_header ("WARC-Record-ID", record_uuid);
|
||||
@@ -1382,18 +1392,18 @@ warc_write_cdx_record (const char *url, const char *timestamp_str,
|
||||
Calling this function will close body.
|
||||
Returns true on success, false on error. */
|
||||
static bool
|
||||
warc_write_revisit_record (char *url, char *timestamp_str,
|
||||
char *concurrent_to_uuid, char *payload_digest,
|
||||
char *refers_to, ip_address *ip, FILE *body)
|
||||
warc_write_revisit_record (const char *url, const char *timestamp_str,
|
||||
const char *concurrent_to_uuid, const char *payload_digest,
|
||||
const char *refers_to, const ip_address *ip, FILE *body)
|
||||
{
|
||||
char revisit_uuid [48];
|
||||
char *block_digest = NULL;
|
||||
char block_digest[BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1 + 5];
|
||||
char sha1_res_block[SHA1_DIGEST_SIZE];
|
||||
|
||||
warc_uuid_str (revisit_uuid);
|
||||
|
||||
sha1_stream (body, sha1_res_block);
|
||||
block_digest = warc_base32_sha1_digest (sha1_res_block);
|
||||
warc_base32_sha1_digest (sha1_res_block, block_digest, sizeof(block_digest));
|
||||
|
||||
warc_write_start_record ();
|
||||
warc_write_header ("WARC-Type", "revisit");
|
||||
@@ -1413,7 +1423,6 @@ warc_write_revisit_record (char *url, char *timestamp_str,
|
||||
warc_write_end_record ();
|
||||
|
||||
fclose (body);
|
||||
xfree (block_digest);
|
||||
|
||||
return warc_write_ok;
|
||||
}
|
||||
@@ -1432,13 +1441,13 @@ warc_write_revisit_record (char *url, char *timestamp_str,
|
||||
Calling this function will close body.
|
||||
Returns true on success, false on error. */
|
||||
bool
|
||||
warc_write_response_record (char *url, char *timestamp_str,
|
||||
char *concurrent_to_uuid, ip_address *ip,
|
||||
FILE *body, off_t payload_offset, char *mime_type,
|
||||
int response_code, char *redirect_location)
|
||||
warc_write_response_record (const char *url, const char *timestamp_str,
|
||||
const char *concurrent_to_uuid, const ip_address *ip,
|
||||
FILE *body, off_t payload_offset, const char *mime_type,
|
||||
int response_code, const char *redirect_location)
|
||||
{
|
||||
char *block_digest = NULL;
|
||||
char *payload_digest = NULL;
|
||||
char block_digest[BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1 + 5];
|
||||
char payload_digest[BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1 + 5];
|
||||
char sha1_res_block[SHA1_DIGEST_SIZE];
|
||||
char sha1_res_payload[SHA1_DIGEST_SIZE];
|
||||
char response_uuid [48];
|
||||
@@ -1471,17 +1480,16 @@ warc_write_response_record (char *url, char *timestamp_str,
|
||||
}
|
||||
|
||||
/* Send the original payload digest. */
|
||||
payload_digest = warc_base32_sha1_digest (sha1_res_payload);
|
||||
warc_base32_sha1_digest (sha1_res_payload, payload_digest, sizeof(payload_digest));
|
||||
result = warc_write_revisit_record (url, timestamp_str,
|
||||
concurrent_to_uuid, payload_digest, rec_existing->uuid,
|
||||
ip, body);
|
||||
xfree (payload_digest);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
block_digest = warc_base32_sha1_digest (sha1_res_block);
|
||||
payload_digest = warc_base32_sha1_digest (sha1_res_payload);
|
||||
warc_base32_sha1_digest (sha1_res_block, block_digest, sizeof(block_digest));
|
||||
warc_base32_sha1_digest (sha1_res_payload, payload_digest, sizeof(payload_digest));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1516,9 +1524,6 @@ warc_write_response_record (char *url, char *timestamp_str,
|
||||
response_uuid);
|
||||
}
|
||||
|
||||
xfree (block_digest);
|
||||
xfree (payload_digest);
|
||||
|
||||
return warc_write_ok;
|
||||
}
|
||||
|
||||
@@ -1535,16 +1540,18 @@ warc_write_response_record (char *url, char *timestamp_str,
|
||||
Calling this function will close body.
|
||||
Returns true on success, false on error. */
|
||||
static bool
|
||||
warc_write_record (const char *record_type, char *resource_uuid,
|
||||
warc_write_record (const char *record_type, const char *resource_uuid,
|
||||
const char *url, const char *timestamp_str,
|
||||
const char *concurrent_to_uuid,
|
||||
ip_address *ip, const char *content_type, FILE *body,
|
||||
const ip_address *ip, const char *content_type, FILE *body,
|
||||
off_t payload_offset)
|
||||
{
|
||||
if (resource_uuid == NULL)
|
||||
{
|
||||
resource_uuid = alloca (48);
|
||||
warc_uuid_str (resource_uuid);
|
||||
/* using uuid_buf allows const for resource_uuid in function declaration */
|
||||
char *uuid_buf = alloca (48);
|
||||
warc_uuid_str (uuid_buf);
|
||||
resource_uuid = uuid_buf;
|
||||
}
|
||||
|
||||
if (content_type == NULL)
|
||||
@@ -1580,9 +1587,9 @@ warc_write_record (const char *record_type, char *resource_uuid,
|
||||
Calling this function will close body.
|
||||
Returns true on success, false on error. */
|
||||
bool
|
||||
warc_write_resource_record (char *resource_uuid, const char *url,
|
||||
warc_write_resource_record (const char *resource_uuid, const char *url,
|
||||
const char *timestamp_str, const char *concurrent_to_uuid,
|
||||
ip_address *ip, const char *content_type, FILE *body,
|
||||
const ip_address *ip, const char *content_type, FILE *body,
|
||||
off_t payload_offset)
|
||||
{
|
||||
return warc_write_record ("resource",
|
||||
@@ -1602,7 +1609,7 @@ warc_write_resource_record (char *resource_uuid, const char *url,
|
||||
Calling this function will close body.
|
||||
Returns true on success, false on error. */
|
||||
bool
|
||||
warc_write_metadata_record (char *record_uuid, const char *url,
|
||||
warc_write_metadata_record (const char *record_uuid, const char *url,
|
||||
const char *timestamp_str, const char *concurrent_to_uuid,
|
||||
ip_address *ip, const char *content_type, FILE *body,
|
||||
off_t payload_offset)
|
||||
|
||||
16
src/warc.h
16
src/warc.h
@@ -12,15 +12,15 @@ char * warc_timestamp (char *timestamp, size_t timestamp_size);
|
||||
|
||||
FILE * warc_tempfile (void);
|
||||
|
||||
bool warc_write_request_record (char *url, char *timestamp_str,
|
||||
char *concurrent_to_uuid, ip_address *ip, FILE *body, off_t payload_offset);
|
||||
bool warc_write_response_record (char *url, char *timestamp_str,
|
||||
char *concurrent_to_uuid, ip_address *ip, FILE *body, off_t payload_offset,
|
||||
char *mime_type, int response_code, char *redirect_location);
|
||||
bool warc_write_resource_record (char *resource_uuid, const char *url,
|
||||
const char *timestamp_str, const char *concurrent_to_uuid, ip_address *ip,
|
||||
bool warc_write_request_record (const char *url, const char *timestamp_str,
|
||||
const char *concurrent_to_uuid, const ip_address *ip, FILE *body, off_t payload_offset);
|
||||
bool warc_write_response_record (const char *url, const char *timestamp_str,
|
||||
const char *concurrent_to_uuid, const ip_address *ip, FILE *body, off_t payload_offset,
|
||||
const char *mime_type, int response_code, const char *redirect_location);
|
||||
bool warc_write_resource_record (const char *resource_uuid, const char *url,
|
||||
const char *timestamp_str, const char *concurrent_to_uuid, const ip_address *ip,
|
||||
const char *content_type, FILE *body, off_t payload_offset);
|
||||
bool warc_write_metadata_record (char *record_uuid, const char *url,
|
||||
bool warc_write_metadata_record (const char *record_uuid, const char *url,
|
||||
const char *timestamp_str, const char *concurrent_to_uuid, ip_address *ip,
|
||||
const char *content_type, FILE *body, off_t payload_offset);
|
||||
|
||||
|
||||
21
src/wget.h
21
src/wget.h
@@ -1,7 +1,7 @@
|
||||
/* Miscellaneous declarations.
|
||||
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
|
||||
Inc.
|
||||
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
|
||||
Foundation, Inc.
|
||||
|
||||
This file is part of GNU Wget.
|
||||
|
||||
@@ -48,12 +48,15 @@ as that of the covered work. */
|
||||
|
||||
/* Disable assertions when debug support is not compiled in. */
|
||||
#ifndef ENABLE_DEBUG
|
||||
#ifndef NDEBUG
|
||||
# define NDEBUG
|
||||
#endif
|
||||
#endif
|
||||
|
||||
/* Is OpenSSL or GNUTLS available? */
|
||||
#if defined HAVE_LIBSSL || defined HAVE_LIBSSL32 || defined HAVE_LIBGNUTLS
|
||||
# define HAVE_SSL
|
||||
# define HAVE_HSTS /* There's no sense in enabling HSTS without SSL */
|
||||
#endif
|
||||
|
||||
/* `gettext (FOO)' is long to write, so we use `_(FOO)'. If NLS is
|
||||
@@ -331,7 +334,9 @@ enum
|
||||
SEND_NOCACHE = 0x0008, /* send Pragma: no-cache directive */
|
||||
ACCEPTRANGES = 0x0010, /* Accept-ranges header was found */
|
||||
ADDED_HTML_EXTENSION = 0x0020, /* added ".html" extension due to -E */
|
||||
TEXTCSS = 0x0040 /* document is of type text/css */
|
||||
TEXTCSS = 0x0040, /* document is of type text/css */
|
||||
IF_MODIFIED_SINCE = 0x0080, /* use if-modified-since header */
|
||||
METALINK_METADATA = 0x0100 /* use HTTP response for Metalink metadata */
|
||||
};
|
||||
|
||||
/* Universal error type -- used almost everywhere. Error reporting of
|
||||
@@ -346,12 +351,18 @@ typedef enum
|
||||
FTPSRVERR, FTPRETRINT, FTPRESTFAIL, URLERROR, FOPENERR,
|
||||
FOPEN_EXCL_ERR, FWRITEERR, HEOF, GATEWAYTIMEOUT,
|
||||
HERR, RETROK, RECLEVELEXC, WRONGCODE,
|
||||
FTPINVPASV, FTPNOPASV, CONTNOTSUPPORTED, RETRUNNEEDED, RETRFINISHED,
|
||||
FTPINVPASV, FTPNOPASV, FTPNOPBSZ, FTPNOPROT, FTPNOAUTH,
|
||||
CONTNOTSUPPORTED, RETRUNNEEDED, RETRFINISHED,
|
||||
READERR, TRYLIMEXC, FILEBADFILE, RANGEERR,
|
||||
RETRBADPATTERN, PROXERR,
|
||||
AUTHFAILED, QUOTEXC, WRITEFAILED, SSLINITFAILED, VERIFCERTERR,
|
||||
UNLINKERR, NEWLOCATION_KEEP_POST, CLOSEFAILED, ATTRMISSING, UNKNOWNATTR,
|
||||
WARC_ERR, WARC_TMP_FOPENERR, WARC_TMP_FWRITEERR
|
||||
WARC_ERR, WARC_TMP_FOPENERR, WARC_TMP_FWRITEERR,
|
||||
TIMECONV_ERR,
|
||||
METALINK_PARSE_ERROR, METALINK_RETR_ERROR,
|
||||
METALINK_CHKSUM_ERROR, METALINK_SIG_ERROR, METALINK_MISSING_RESOURCE,
|
||||
RETR_WITH_METALINK,
|
||||
METALINK_SIZE_ERROR
|
||||
} uerr_t;
|
||||
|
||||
/* 2005-02-19 SMS.
|
||||
|
||||
79
src/xattr.c
Normal file
79
src/xattr.c
Normal file
@@ -0,0 +1,79 @@
|
||||
/* xattr.h -- POSIX Extended Attribute support.
|
||||
|
||||
Copyright (C) 2016 Free Software Foundation, Inc.
|
||||
|
||||
This program is free software; you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation; either version 3, or (at your option)
|
||||
any later version.
|
||||
|
||||
This program is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with this program; if not, see <http://www.gnu.org/licenses/>. */
|
||||
|
||||
#include "wget.h"
|
||||
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
|
||||
#include "log.h"
|
||||
#include "xattr.h"
|
||||
|
||||
#ifdef USE_XATTR
|
||||
|
||||
static int
|
||||
write_xattr_metadata (const char *name, const char *value, FILE *fp)
|
||||
{
|
||||
int retval = -1;
|
||||
|
||||
if (name && value && fp)
|
||||
{
|
||||
retval = fsetxattr (fileno (fp), name, value, strlen (value), 0);
|
||||
/* FreeBSD's extattr_set_fd returns the length of the extended attribute. */
|
||||
retval = (retval < 0) ? retval : 0;
|
||||
if (retval)
|
||||
DEBUGP (("Failed to set xattr %s.\n", quote(name)));
|
||||
}
|
||||
|
||||
return retval;
|
||||
}
|
||||
|
||||
#else /* USE_XATTR */
|
||||
|
||||
static int
|
||||
write_xattr_metadata (const char *name, const char *value, FILE *fp)
|
||||
{
|
||||
(void)name;
|
||||
(void)value;
|
||||
(void)fp;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
#endif /* USE_XATTR */
|
||||
|
||||
int
|
||||
set_file_metadata (const char *origin_url, const char *referrer_url, FILE *fp)
|
||||
{
|
||||
/* Save metadata about where the file came from (requested, final URLs) to
|
||||
* user POSIX Extended Attributes of retrieved file.
|
||||
*
|
||||
* For more details about the user namespace see
|
||||
* [http://freedesktop.org/wiki/CommonExtendedAttributes] and
|
||||
* [http://0pointer.de/lennart/projects/mod_mime_xattr/].
|
||||
*/
|
||||
int retval = -1;
|
||||
|
||||
if (!origin_url || !fp)
|
||||
return retval;
|
||||
|
||||
retval = write_xattr_metadata ("user.xdg.origin.url", escnonprint_uri (origin_url), fp);
|
||||
if ((!retval) && referrer_url)
|
||||
retval = write_xattr_metadata ("user.xdg.referrer.url", escnonprint_uri (referrer_url), fp);
|
||||
|
||||
return retval;
|
||||
}
|
||||
45
src/xattr.h
Normal file
45
src/xattr.h
Normal file
@@ -0,0 +1,45 @@
|
||||
/* xattr.h -- POSIX Extended Attribute function mappings.
|
||||
|
||||
Copyright (C) 2016 Free Software Foundation, Inc.
|
||||
|
||||
This program is free software; you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation; either version 3, or (at your option)
|
||||
any later version.
|
||||
|
||||
This program is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with this program; if not, see <http://www.gnu.org/licenses/>. */
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
#ifndef _XATTR_H
|
||||
#define _XATTR_H
|
||||
|
||||
/* Store metadata name/value attributes against fp. */
|
||||
int set_file_metadata (const char *origin_url, const char *referrer_url, FILE *fp);
|
||||
|
||||
#if defined(__linux)
|
||||
/* libc on Linux has fsetxattr (5 arguments). */
|
||||
# include <sys/xattr.h>
|
||||
# define USE_XATTR
|
||||
#elif defined(__APPLE__)
|
||||
/* libc on OS/X has fsetxattr (6 arguments). */
|
||||
# include <sys/xattr.h>
|
||||
# define fsetxattr (file, name, buffer, size, flags) \
|
||||
fsetxattr ((file), (name), (buffer), (size), 0, (flags))
|
||||
# define USE_XATTR
|
||||
#elif defined(__FreeBSD_version) && (__FreeBSD_version > 500000)
|
||||
/* FreeBSD */
|
||||
# include <sys/types.h>
|
||||
# include <sys/extattr.h>
|
||||
# define fsetxattr (file, name, buffer, size, flags) \
|
||||
extattr_set_fd ((file), EXTATTR_NAMESPACE_USER, (name), (buffer), (size))
|
||||
# define USE_XATTR
|
||||
#endif
|
||||
|
||||
#endif /* _XATTR_H */
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user