Fix heap overflow in HTTP protocol handling (CVE-2017-13090)

* src/retr.c (fd_read_body): Stop processing on negative chunk size

Reported-by: Antti Levomäki, Christian Jalio, Joonas Pihlaja from Forcepoint
Reported-by: Juhani Eronen from Finnish National Cyber Security Centre

.gitlab-ci.yml

@@ -0,0 +1,124 @@
+variables:
+  BUILD_IMAGES_PROJECT: gnuwget/build-images
+  DEBIAN_BUILD: buildenv-debian-stretch
+  FEDORA_BUILD: buildenv-f25
+  CENTOS7_BUILD: buildenv-centos7
+  GET_SOURCES_ATTEMPTS: "3"
+
+# In this build we combine
+#  * syntax-check
+#  * abi-check
+#  * build/valgrind-check
+#  * build/asan-check
+#  * build w/Werror and ubsan-check
+Debian GNU/Linux build:
+  image: $CI_REGISTRY/$BUILD_IMAGES_PROJECT:$DEBIAN_BUILD
+  script:
+  - echo "127.0.0.1 wgettestingserver" >>/etc/hosts
+  - cat /etc/hosts
+  - touch .manywarnings
+  - alias make="make -j$(nproc)"
+  - ./bootstrap
+  - ./configure -C
+  - make syntax-check
+  - make check
+#  - make abi-check
+  - make distcheck
+  - make check-valgrind
+  - ./configure -C --with-ssl=openssl
+  - make clean
+  - make check
+#  - ./configure -C --enable-fsanitize-asan
+#  - make clean
+#  - make check
+#  - ./configure -C --enable-fsanitize-ubsan
+#  - make clean
+#  - make check
+#  - ./configure -C --enable-fsanitize-msan
+#  - make clean
+#  - make check
+  tags:
+  - shared
+  artifacts:
+    expire_in: 2 weeks
+    when: on_failure
+    paths:
+      - tests/*.log
+#      - compat_reports/
+
+#Centos7 build:
+#  image: $CI_REGISTRY/$BUILD_IMAGES_PROJECT:$CENTOS7_BUILD
+#  script:
+#  - sed -i 's/AM_GNU_GETTEXT_VERSION(0.19.3)/AM_GNU_GETTEXT_VERSION(0.18.2)/g' configure.ac
+#  - ./bootstrap && ./configure --enable-gcc-warnings --disable-doc && make -j$(nproc) check
+#  tags:
+#  - shared
+#  artifacts:
+#    expire_in: 2 weeks
+#    when: on_failure
+#    paths:
+#      - tests/*.log
+#      - compat_reports/
+
+#clang-analyzer/Fedora:
+#  image: $CI_REGISTRY/$BUILD_IMAGES_PROJECT:$FEDORA_BUILD
+#  script:
+#  - ./bootstrap
+#  - scan-build ./configure --disable-doc --enable-gcc-warnings
+#  - make -j$(nproc) -C gl
+#  - scan-build --status-bugs -o scan-build-lib make -j$(nproc) -C lib
+#  tags:
+#  - shared
+#  except:
+#  - tags
+#  artifacts:
+#    expire_in: 2 weeks
+#    when: on_failure
+#    paths:
+#      - scan-build-lib/*
+
+#pages:
+#  image: $CI_REGISTRY/$BUILD_IMAGES_PROJECT:$DEBIAN_BUILD
+#  script:
+#  - ./bootstrap
+#  - CFLAGS="-g -O0" ./configure --enable-gtk-doc --enable-code-coverage --disable-gcc-warnings
+#  - make -j$(nproc) check
+#  - make local-code-coverage-output
+#  - mkdir -p public
+#  - rm -rf public/coverage
+#  - mv libidn2-*-coverage public/coverage
+#  - rm -rf public/reference
+#  - mv doc/reference/html public/reference
+#  - make -C doc manual
+#  - rm -rf public/manual
+#  - mv doc/manual public/manual
+#  tags:
+#  - shared
+#  artifacts:
+#    when: on_success
+#    paths:
+#      - public
+#  only:
+#    - master
+
+#MinGW64:
+#  image: $CI_REGISTRY/$BUILD_IMAGES_PROJECT:$FEDORA_BUILD
+#  before_script:
+#  - mount -t binfmt_misc binfmt_misc /proc/sys/fs/binfmt_misc &&
+#    echo ':DOSWin:M::MZ::/usr/bin/wine64:' > /proc/sys/fs/binfmt_misc/register
+#  script:
+#  - ./bootstrap
+#  - mingw64-configure --disable-valgrind-tests --disable-doc
+#  - mingw64-make -j$(nproc)
+#  - mingw64-make -j$(nproc) check
+#  tags:
+#  - shared
+#  - docker
+#  except:
+#  - tags
+#  artifacts:
+#    expire_in: 2 weeks
+#    when: on_failure
+#    paths:
+#      - ./*.log
+#      - tests/*.log

.travis.yml

@@ -1,4 +1,5 @@
 sudo: no
+dist: trusty
 
 language: c
 
@@ -36,7 +37,7 @@ addons:
             - make
             - libhttp-daemon-perl
             - libio-socket-ssl-perl
-            - libidn11-dev
+            - libidn2-dev
             - gettext
             - texlive
             - python3

ChangeLog-2014-12-10

@@ -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

Makefile.am

@@ -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

NEWS

@@ -1,12 +1,87 @@
 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, 2015 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 1.19.2
+
+* Fix CVE-2017-13089 (Stack overflow in HTTP protocol handling)
+
+* Fix CVE-2017-13090 (Heap overflow in HTTP protocol handling)
+
+* New option --compression for gzip Content-Encoding
+
+* New option --[no]-netrc to control .netrc parsing
+
+* Added GNU extensions to .netrc parsing
+
+* Improved IDNA 2003 compatibility
+
+* Fix VPATH issues
+
+* Improved and extended the test suite
+
+* Support Wayback Machine's X-Archive-Orig-last-modified
+
+* Several bug fixes
+
+
+* Changes in Wget 1.19.1
+
+* Fix bugs, a regression, portability/build issues
+
+* Add new option --retry-on-http-error
+
+
+* 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
@@ -646,7 +721,7 @@ addresses when accessing the first one fails.
 non-standard port.
 
 ** Wget now supports the robots.txt directives specified in
-<http://www.robotstxt.org/wc/norobots-rfc.txt>.
+<http://www.robotstxt.org/norobots-rfc.txt>.
 
 ** URL parser has been fixed, especially the infamous overzealous
 quoting.  Wget no longer dequotes reserved characters, e.g. `%3F' is

README.checkout

@@ -4,7 +4,7 @@ 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,
+   more of the following (note that gettext, OpenSSL, GnuTLS, libidn2,
    libiconv, libpsl, libpcre, pkg-config, libmetalink and GnuPG are not
    absolutely required):
 
@@ -32,8 +32,8 @@ Compiling From Repository Sources
        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]Python, 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 python
+     * [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".
 
@@ -69,7 +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.
@@ -104,6 +104,10 @@ Compiling From Repository Sources
        The command line options --dns-servers and --bind-dns-address are
        only available when configured with --with-cares.
 
+     * [49]Gpef is required by some gnulib modules, most notably "unicase". You
+	   need the application installed on the machine to compile Wget from git.
+
+
    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
    that point, a shell script called bootstrap has been provided. After
@@ -116,7 +120,7 @@ Compiling From Repository Sources
  $  cd wget        # assumes you've cloned a repository to "./wget"
     2. Generate all the automatically-generated files required prior to
        configuring the package:
- $  ./bootstrap
+ $  ./bootstrap (or: bash ./bootstrap)
     3. Configure the package and compile it:
  $  ./configure --enable-assert [some_parameters]
  $  make
@@ -159,7 +163,7 @@ Testing and development
 
  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.
 
@@ -183,32 +187,33 @@ Testing and development
 
 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. http://c-ares.haxx.se/
+  48. https://c-ares.haxx.se/
+  49. https://www.gnu.org/software/gperf/

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:

bootstrap.conf

@@ -40,6 +40,7 @@ dirname
 fcntl
 flock
 fnmatch
+fopen
 futimens
 ftello
 getaddrinfo
@@ -52,9 +53,17 @@ gettext
 gitlog-to-changelog
 git-version-gen
 gnupload
+group-member
+hostent
 ioctl
 iconv
 iconv-h
+inet_ntop
+intprops
+inttypes
+langinfo
+limits-h
+link
 listen
 maintainer-makefile
 mbiter
@@ -63,9 +72,16 @@ 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
@@ -73,24 +89,37 @@ 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/u8-strlen
+unicase/u8-tolower
+utimens
 vasprintf
 vsnprintf
+wcwidth
 write
+xmemdup0
 xstrndup
 "
 
@@ -118,4 +147,21 @@ rsync      -
 tar        -
 xz         -
 flex       -
+gperf      -
 "
+
+bootstrap_post_import_hook ()
+{
+  # We need to patch unicase/special-casing-table.h for gperf < 3.1
+  GPERF_VER=$(gperf --version | {
+    IFS=' .' read x y major minor bugfix _
+    printf "%d%02d%02d" $major $minor $bugfix
+  })
+
+  if [ $GPERF_VER -lt 30100 ]; then
+    echo "Creating lib/unicase/special-casing-table.h for gperf < 3.1"
+     gperf -m 10 lib/unicase/special-casing-table.gperf | \
+       sed -e "s/gl_unicase_special_lookup.*/gl_unicase_special_lookup\ \(const char \*str, size_t len\)/g" \
+         > lib/unicase/special-casing-table.h
+  fi
+}

cfg.mk

@@ -1,4 +1,7 @@
-export VC_LIST_EXCEPT_DEFAULT=^(lib/.*|m4/.*|md5/.*|build-aux/.*|src/gettext\.h|.*ChangeLog)$$
+# Explicit syntax-check exceptions.
+exclude_file_name_regexp--sc_trailing_blank = ^doc/annou.*$$
+
+export VC_LIST_EXCEPT_DEFAULT=^(lib/.*|m4/.*|md5/.*|build-aux/.*|src/gettext\.h|.*ChangeLog|tests/certs/.*)$$
 
 local-checks-to-skip = \
     sc_const_long_option \
@@ -21,9 +24,10 @@ local-checks-to-skip = \
     sc_program_name \
     sc_makefile_at_at_check \
     sc_cast_of_argument_to_free \
+    sc_prohibit_undesirable_word_seq
 
 #SHELL=bash -x
 show-vc-list-except:
 	@$(VC_LIST_EXCEPT)
 
-VC_LIST_ALWAYS_EXCLUDE_REGEX = ^ABOUT-NLS|((msdos|vms)/.*)|ChangeLog-2014-12-10$$
+VC_LIST_ALWAYS_EXCLUDE_REGEX = ^ABOUT-NLS|((msdos|vms)/.*)|ChangeLog-2014-12-10|/.*.der|^tests/certs/.*$$

configure.ac

@@ -290,15 +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 $host_os in
   *mingw32* )
@@ -329,6 +320,10 @@ AS_IF([test "x$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, [
@@ -635,9 +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
 
@@ -649,39 +641,23 @@ AS_IF([test "X$iri" != "Xno"],[
       AC_MSG_NOTICE([disabling IRIs because libiconv wasn't found])
     fi
   fi
-],[  # else
-  # For some reason, this seems to be set even when we don't check.
-  # Explicitly unset.
-  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
 
 dnl
@@ -750,7 +726,7 @@ dnl
 dnl Check for libcares (resolver library)
 dnl
 
-AS_IF([test "X$with_cares" == "Xyes"],[
+AS_IF([test "X$with_cares" = "Xyes"],[
   PKG_CHECK_MODULES([CARES], libcares, [
     CFLAGS="$CARES_CFLAGS $CFLAGS"
     AC_CHECK_HEADER(ares.h, [
@@ -771,18 +747,45 @@ AS_IF([test "X$with_cares" == "Xyes"],[
   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
 dnl
 AC_CONFIG_FILES([Makefile src/Makefile doc/Makefile util/Makefile
                  po/Makefile.in tests/Makefile
-                 lib/Makefile testenv/Makefile])
+                 lib/Makefile testenv/Makefile
+                 tests/certs/interca.conf tests/certs/rootca.conf])
 AC_CONFIG_HEADERS([src/config.h])
 AC_OUTPUT
 
@@ -801,10 +804,12 @@ 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
 ])

contrib/check-hard

@@ -12,7 +12,8 @@ if [ $CORES -lt 1 ]; then CORES=1; fi
 echo "Running: make distclean"
 make distclean > /dev/null || true
 
-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"
+CFLAGS="-Wall -Wextra -O2 -g"
 
 CACHEFILE=$PWD/config_check.cache
 
@@ -30,7 +31,7 @@ for CC in gcc clang; do
   # the compiler changed, so we have to remove the cache file here
   rm -f $CACHEFILE
 
-  for options in "" "--with-ssl=openssl"; do
+  for options in "" "--with-ssl=openssl" "--disable-iri"; do
     export DISTCHECK_CONFIGURE_FLAGS="-C --cache-file=$CACHEFILE $options"
     echo "  ./configure $DISTCHECK_CONFIGURE_FLAGS"
     ./configure $DISTCHECK_CONFIGURE_FLAGS CFLAGS="$CFLAGS" > /dev/null

contrib/release

@@ -0,0 +1,112 @@
+#!/bin/bash -e
+#
+# Written 2016 by Tim Ruehsen
+
+extensions="gz xz"
+app_name=$(grep "^PACKAGE_NAME='" configure|cut -d "'" -f2)
+app_ver=$(grep "^PACKAGE_VERSION='" configure|cut -d "'" -f2)
+
+echo "Current version of $app_name is $app_ver"
+echo
+echo -n "Enter Y if that is OK, else enter N and edit configure.ac: "
+read x
+[ "$x" != "y" -a "$x" != "Y" ] && exit 0
+
+echo
+grep -i "Changes in $app_name" NEWS|head -1
+echo -n "Did you edit the NEWS file ? [y/N] "
+read x
+[ "$x" != "y" -a "$x" != "Y" ] && exit 0
+
+echo
+
+export CFLAGS="-g -O2 -Wall"
+
+echo "* Bootstrap"
+./bootstrap >/dev/null
+
+echo "* Configure"
+./configure -q
+
+echo "* Make"
+make -s clean
+make -s
+
+echo "* Make distcheck"
+make -s distcheck >/dev/null
+
+echo "* Make dist"
+make -s dist >/dev/null
+make -s dist-xz >/dev/null
+
+while true; do
+  echo "Alpha or Regular release ? [r/A] "
+  read x
+  if test "$x" = "r" || test "$x" = "R"; then
+    directory="/incoming/ftp"
+    break
+  elif test "$x" = "a" || test "$x" = "A"; then
+    directory="/incoming/alpha"
+    break
+  fi
+done
+
+x=$(gpg --list-secret-keys 2>/dev/null|grep ^sec|awk '{ print $2 }')
+echo $x
+if [ "$x" = "" ]; then
+  echo No signing key found - please check with 'gpg --list-secret-keys'
+  exit 1
+fi
+
+# arrays just work in Bash
+keys=($x)
+if [ ${#keys[@]} -eq 1 ]; then
+  IFS='/' arr=($x)
+  signing_key=${arr[1]}
+else
+  for ((i=0; i < ${#keys[@]}; i++)); do
+    echo "$((i+1))) ${keys[i]}"
+  done
+  while true; do
+    echo -n "Enter 1-${#keys[@]}: "
+    read x
+
+    # check for digits only
+    if [ -n "${i//[0-9]/}" ]; then continue; fi
+
+    if test $x -ge 1 || test $x -le ${#keys[@]}; then
+      IFS='/' arr=(${keys[$((x-1))]})
+      signing_key=${arr[1]}
+      break
+    fi
+  done
+fi
+unset IFS
+echo $signing_key
+
+# fetch app_version again, just in case
+app_ver=$(grep "^PACKAGE_VERSION='" configure|cut -d "'" -f2)
+
+for ext in $extensions; do
+  app_tarball="${app_name}-${app_ver}.tar.$ext"
+  gpg --default-key $signing_key --yes -b $app_tarball
+
+  echo -e "version: 1.2\nfilename: ${app_tarball}\ndirectory: ${app_name}\n" >${app_tarball}.directive
+  gpg --default-key $signing_key --yes --clearsign ${app_tarball}.directive
+
+ftp -v -n -i -p ftp-upload.gnu.org <<EOF
+user anonymous
+cd $directory
+put ${app_tarball}
+put ${app_tarball}.sig
+put ${app_tarball}.directive.asc
+EOF
+
+done
+
+prev_tag=`git tag|tail -2|head -1`
+echo "Don't forget to mention the following contributors in the announcement:"
+(
+  git log ${prev_tag}.. --format="%aN" --reverse
+  git log ${prev_tag}.. --reverse|grep -i reported|cut -d':' -f2|cut -d'<' -f1|cut -d' ' -f2-|tr -d '"'
+) | sort -u

contrib/travis-ci

@@ -21,7 +21,7 @@ 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 -O2 -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 -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

doc/Makefile.am

@@ -57,10 +57,8 @@ 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 $? > $@; \
-	if [ $? != 0 ]; then \
-          $(POD2MAN) --center="GNU Wget" --release="GNU Wget @VERSION@" $? > $@; \
-	fi
+	$(POD2MAN) --center="GNU Wget" --release="GNU Wget @VERSION@" --utf8 $? > $@ || \
+	$(POD2MAN) --center="GNU Wget" --release="GNU Wget @VERSION@" $? > $@
 
 #wget.cat: $(MAN)
 #	nroff -man $? > $@

doc/announcement_1.19.txt

@@ -0,0 +1,104 @@
+Hello,
+
+we are pleased to announce the new version of GNU wget 1.19.
+
+It comes with major improvements for Metalink, IDNA2008 for
+international domain names, an option to call external tools
+for fetching user/password, several bugfixes and improvements.
+
+Many thanks go to all the contributors and list activists !
+
+Contributors (from the git log):
+Ander Juaristi
+Dale R. Worley 
+Eli Zaretskii 
+Gisle Vanem 
+Giuseppe Scrivano
+Göran Uddeborg 
+Jann Horn 
+Jeffery To
+Jérémie Courrèges-Anglas 
+Liam R. Howlett
+losgrandes
+Matthew White
+Misra, Deapesh 
+Nikos Mavrogiannopoulos
+Noël Köthe
+Piotr Wajda
+Rahul Bedarkar
+Sean Burford
+Tim Rühsen
+Tobias Stoeckmann
+vijeth-aradhya
+
+
+The new version is available for download here:
+
+https://ftp.gnu.org/gnu/wget/wget-1.19.tar.gz
+https://ftp.gnu.org/gnu/wget/wget-1.19.tar.xz
+
+and the GPG detached signatures using the key 0x08302DB6A2670428:
+
+https://ftp.gnu.org/gnu/wget/wget-1.19.tar.gz.sig
+https://ftp.gnu.org/gnu/wget/wget-1.19.tar.xz.sig
+
+To reduce load on the main server, you can use this redirector service
+which automatically redirects you to a mirror:
+
+http://ftpmirror.gnu.org/wget/wget-1.19.tar.gz
+http://ftpmirror.gnu.org/wget/wget-1.19.tar.xz
+
+
+Noteworthy changes:
+
+* 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
+
+
+Please report any problem you may experience to the bug-wget@gnu.org
+mailing list.
+
+For the maintainers of Wget,
+Tim

doc/metalink-standard.txt

@@ -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

doc/metalink.txt

@@ -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'.

doc/wget.texi

@@ -193,6 +193,8 @@ options, or via the initialization file @file{.wgetrc} (@pxref{Startup
 File}).  Wget allows you to define @dfn{global} startup files
 (@file{/usr/local/etc/wgetrc} by default) for site settings. You can also
 specify the location of a startup file with the --config option.
+To disable the reading of config files, use --no-config.
+If both --config and --no-config are given, --no-config is ignored.
  
 
 @ignore
@@ -512,11 +514,27 @@ href if none was specified.
 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
@@ -550,7 +568,10 @@ 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.
+Specify the location of a startup file you wish to use instead of the
+default one(s). Use --no-config to disable reading of config files.
+If both --config and --no-config are given, --no-config is ignored.
+
 
 @item --rejected-log=@var{logfile}
 Logs all URL rejections to @var{logfile} as comma separated values.  The values
@@ -687,6 +708,12 @@ Before (over)writing a file, back up an existing file by adding a
 files are rotated to @samp{.2}, @samp{.3}, and so on, up to
 @var{backups} (and lost beyond that).
 
+@cindex authentication credentials
+@item --no-netrc
+Do not try to obtain credentials from @file{.netrc} file. By default
+@file{.netrc} file is searched for credentials in case none have been
+passed on command line and authentication is required.
+
 @cindex continue retrieval
 @cindex incomplete downloads
 @cindex resume download
@@ -802,7 +829,7 @@ 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}.
 
@@ -1154,6 +1181,15 @@ 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
@@ -1310,6 +1346,11 @@ renamed from @samp{--html-extension}, to better reflect its new
 behavior. The old option name is still acceptable, but should now be
 considered deprecated.
 
+As of version 1.19.2, Wget will also ensure that any downloaded files with
+a @code{Content-Encoding} of @samp{br}, @samp{compress}, @samp{deflate}
+or @samp{gzip} end in the suffix @samp{.br}, @samp{.Z}, @samp{.zlib}
+and @samp{.gz} respectively.
+
 At some point in the future, this option may well be expanded to
 include suffixes for other types of content, including content types
 that are not parsed by Wget.
@@ -1327,10 +1368,10 @@ 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
@@ -1494,6 +1535,20 @@ wget --header="Host: foo.bar" http://localhost/
 In versions of Wget prior to 1.10 such use of @samp{--header} caused
 sending of duplicate headers.
 
+@cindex Content-Encoding, choose
+@item --compression=@var{type}
+Choose the type of compression to be used.  Legal values are
+@samp{auto}, @samp{gzip} and @samp{none}.
+
+If @samp{auto} or @samp{gzip} are specified, Wget asks the server to
+compress the file using the gzip compression format. If the server
+compresses the file and responds with the @code{Content-Encoding}
+header field set appropriately, the file will be decompressed
+automatically. This is the default.
+
+If @samp{none} is specified, wget will not ask the server to compress
+the file and will not decompress any server responses.
+
 @cindex redirect
 @item --max-redirect=@var{number}
 Specifies the maximum number of redirections to follow for a resource.
@@ -1662,6 +1717,10 @@ 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
 
@@ -1671,9 +1730,11 @@ 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
@@ -1687,6 +1748,21 @@ some few obscure servers, which never send HTTP authentication
 challenges, but accept unsolicited auth info, say, in addition to
 form-based authentication.
 
+@item --retry-on-http-error=@var{code[,code,...]}
+Consider given HTTP response codes as non-fatal, transient errors.
+Supply a comma-separated list of 3-digit HTTP response codes as
+argument. Useful to work around special circumstances where retries
+are required, but the server responds with an error code normally not
+retried by Wget. Such errors might be 503 (Service Unavailable) and
+429 (Too Many Requests). Retries enabled by this option are performed
+subject to the normal retry timing and retry count limitations of
+Wget.
+
+Using this option is intended to support special use cases only and is
+generally not recommended, as it can force retries even in cases where
+the server is actually trying to decrease its load. Please use wisely
+and only if you know what you are doing.
+
 @end table
 
 @node HTTPS (SSL/TLS) Options, FTP Options, HTTP Options, Invoking
@@ -3199,8 +3275,8 @@ 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
@@ -3306,10 +3382,16 @@ Turn globbing on/off---the same as @samp{--glob} and @samp{--no-glob}.
 Define a header for HTTP downloads, like using
 @samp{--header=@var{string}}.
 
+@item compression = @var{string}
+Choose the compression type to be used.  Legal values are @samp{auto}
+(the default), @samp{gzip}, and @samp{none}.  The same as
+@samp{--compression=@var{string}}.
+
 @item adjust_extension = on/off
 Add a @samp{.html} extension to @samp{text/html} or
-@samp{application/xhtml+xml} files that lack one, or a @samp{.css}
-extension to @samp{text/css} files that lack one, like
+@samp{application/xhtml+xml} files that lack one, a @samp{.css}
+extension to @samp{text/css} files that lack one, and a @samp{.br},
+@samp{.Z}, @samp{.zlib} or @samp{.gz} to compressed files like
 @samp{-E}. Previously named @samp{html_extension} (still acceptable,
 but deprecated).
 
@@ -4220,7 +4302,7 @@ 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/robotstxt.html}.  As of version 1.8,
+@url{http://www.robotstxt.org/orig.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
@@ -4239,7 +4321,7 @@ this:
 @end example
 
 This is explained in some detail at
-@url{http://www.robotstxt.org/wc/meta-user.html}.  Wget supports this
+@url{http://www.robotstxt.org/meta.html}.  Wget supports this
 method of robot exclusion in addition to the usual @file{/robots.txt}
 exclusion.
 

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 ************************************************************

po/POTFILES.in

@@ -35,7 +35,6 @@ src/ptimer.c
 src/recur.c
 src/res.c
 src/retr.c
-src/spider.c
 src/url.c
 src/utils.c
 src/warc.c

src/Makefile.am

@@ -39,9 +39,12 @@ 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
 
@@ -50,17 +53,20 @@ 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 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	\
+		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 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 metalink.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) $(LIBICONV) $(LIBINTL)\
+ $(LIBTHREAD) $(LIBUNISTRING) $(SERVENT_LIB)
 AM_CPPFLAGS = -I$(top_builddir)/lib -I$(top_srcdir)/lib
 
 

src/connect.c

@@ -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>
@@ -55,10 +56,6 @@ as that of the covered work.  */
 #include <string.h>
 #include <sys/time.h>
 
-#ifdef ENABLE_IRI
-#include <idn-free.h>
-#endif
-
 #include "utils.h"
 #include "host.h"
 #include "connect.h"
@@ -279,11 +276,8 @@ connect_to_ip (const ip_address *ip, int port, const char *print)
 
           if (opt.enable_iri && (name = idn_decode ((char *) print)) != NULL)
             {
-              int len = strlen (print) + strlen (name) + 4;
-              str = xmalloc (len);
-              snprintf (str, len, "%s (%s)", name, print);
-              str[len-1] = '\0';
-              idn_free (name);
+              str = aprintf ("%s (%s)", name, print);
+              xfree (name);
             }
 
           logprintf (LOG_VERBOSE, _("Connecting to %s|%s|:%d... "),
@@ -331,8 +325,10 @@ 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.  */
@@ -471,7 +467,9 @@ 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);
@@ -689,6 +687,11 @@ 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)
@@ -731,6 +734,11 @@ 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.  */
 

src/convert.c

@@ -1024,7 +1024,7 @@ convert_cleanup (void)
 
 /* This table should really be merged with dl_file_url_map and
    downloaded_html_files.  This was originally a list, but I changed
-   it to a hash table beause it was actually taking a lot of time to
+   it to a hash table because it was actually taking a lot of time to
    find things in it.  */
 
 static struct hash_table *downloaded_files_hash;

src/cookies.c

@@ -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>
@@ -484,7 +485,7 @@ parse_set_cookie (const char *set_cookie, bool silent)
 /* Check whether ADDR matches <digits>.<digits>.<digits>.<digits>.
 
    We don't want to call network functions like inet_addr() because
-   all we need is a check, preferrably one that is small, fast, and
+   all we need is a check, preferably one that is small, fast, and
    well-defined.  */
 
 static bool
@@ -515,7 +516,7 @@ numeric_address_p (const char *addr)
    psl on our own, if libpsl is compiled without a public suffix list,
    fall back to using the original "tail matching" heuristic. Also if
    libpsl is unable to convert the domain to lowercase, which means that
-   it doesnt have any runtime conversion support, we again fall back to
+   it doesn't have any runtime conversion support, we again fall back to
    "tail matching" since libpsl states the results are unpredictable with
    upper case strings.
    */
@@ -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;
 }

src/css-url.c

@@ -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"));
 }
 

src/css-url.h

@@ -31,7 +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 *);
 

src/ftp-ls.c

@@ -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
             {

src/ftp.c

@@ -52,6 +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"
@@ -239,7 +242,7 @@ print_length (wgint size, wgint start, bool authoritative)
 static uerr_t ftp_get_listing (struct url *, struct url *, ccon *, struct fileinfo **);
 
 static uerr_t
-get_ftp_greeting(int csock, ccon *con)
+get_ftp_greeting (int csock, ccon *con)
 {
   uerr_t err = 0;
 
@@ -356,12 +359,35 @@ getftp (struct url *u, struct url *original_url,
 
   *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;
@@ -535,10 +561,10 @@ Error in server response, closing control connection.\n"));
                 logputs (LOG_VERBOSE, "done.");
 
               if (!opt.server_response)
-                logprintf (LOG_VERBOSE, "  ==> PROT %c ... ", prot);
+                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"), prot);
+                  logprintf (LOG_NOTQUIET, _("Server did not accept the 'PROT %c' command.\n"), (int) prot);
                   return err;
                 }
               if (!opt.server_response)
@@ -872,7 +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"));
@@ -1188,6 +1214,7 @@ 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, original_url, con, &f);
           /* Set the DO_RETR command flag again, because it gets unset when
@@ -1203,6 +1230,8 @@ Error in server response, closing control connection.\n"));
                     {
                       exists = true;
                       break;
+                    } else {
+                      all_exist = false;
                     }
                   f = f->next;
                 }
@@ -1223,7 +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)
@@ -1430,7 +1463,7 @@ Error in server response, closing control connection.\n"));
       else if (opt.noclobber || opt.always_rest || opt.timestamping || opt.dirstruct
                || opt.output_document || count > 0)
         {
-          if (opt.unlink && file_exists_p (con->target))
+          if (opt.unlink_requested && file_exists_p (con->target, NULL))
             {
               if (unlink (con->target) < 0)
                 {
@@ -1546,6 +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)
@@ -1641,10 +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 */
@@ -1788,7 +1826,7 @@ ftp_loop_internal (struct url *u, struct url *original_url, struct fileinfo *f,
   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);
@@ -1819,7 +1857,7 @@ ftp_loop_internal (struct url *u, struct url *original_url, struct fileinfo *f,
   /* If we receive .listing file it is necessary to determine system type of the ftp
      server even if opn.noclobber is given. Thus we must ignore opt.noclobber in
      order to establish connection with the server and get system type. */
-  if (opt.noclobber && !opt.output_document && file_exists_p (con->target)
+  if (opt.noclobber && !opt.output_document && file_exists_p (con->target, NULL)
       && !((con->cmd & DO_LIST) && !(con->cmd & DO_RETR)))
     {
       logprintf (LOG_VERBOSE,
@@ -2091,7 +2129,7 @@ Removing file due to --delete-after in ftp_loop_internal():\n"));
 }
 
 /* Return the directory listing in a reusable format.  The directory
-   is specifed in u->dir.  */
+   is specified in u->dir.  */
 static uerr_t
 ftp_get_listing (struct url *u, struct url *original_url, ccon *con,
                  struct fileinfo **f)
@@ -2211,7 +2249,7 @@ ftp_retrieve_list (struct url *u, struct url *original_url,
       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
@@ -2274,7 +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);
@@ -2334,6 +2372,7 @@ Already have correct symlink %s -> %s\n\n"),
             }
           break;
         case FT_UNKNOWN:
+        default:
           logprintf (LOG_NOTQUIET, _("%s: unknown/unsupported file type.\n"),
                      quote (f->name));
           break;
@@ -2355,7 +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));
         }
@@ -2369,7 +2413,7 @@ Already have correct symlink %s -> %s\n\n"),
               && !(f->type == FT_SYMLINK && !opt.retr_symlinks)
               && f->tstamp != -1
               && dlthis
-              && file_exists_p (con->target))
+              && file_exists_p (con->target, NULL))
             {
               touch (actual_target, f->tstamp);
             }
@@ -2503,7 +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;
@@ -2697,7 +2741,7 @@ ftp_loop (struct url *u, struct url *original_url, char **local_file, int *dt,
                 {
                   if (!opt.output_document)
                     {
-                      struct_stat st;
+                      struct stat st;
                       wgint sz;
                       if (stat (filename, &st) == 0)
                         sz = st.st_size;

src/gnutls.c

@@ -50,7 +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"
@@ -498,7 +498,7 @@ _do_handshake (gnutls_session_t session, int fd, double timeout)
             {
               gnutls_alert_description_t alert = gnutls_alert_get (session);
               const char *str = gnutls_alert_get_name (alert);
-              logprintf (LOG_NOTQUIET, "GnuTLS: received alert [%d]: %s\n",
+              logprintf (LOG_NOTQUIET, "GnuTLS: received alert [%u]: %s\n",
                          alert, str ? str : "(unknown)");
             }
         }
@@ -556,7 +556,6 @@ ssl_connect_wget (int fd, const char *hostname, int *continue_session)
       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)
@@ -571,7 +570,8 @@ ssl_connect_wget (int fd, const char *hostname, int *continue_session)
   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:
@@ -599,7 +599,8 @@ ssl_connect_wget (int fd, const char *hostname, int *continue_session)
       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 ();
     }
@@ -608,6 +609,7 @@ ssl_connect_wget (int fd, const char *hostname, int *continue_session)
   switch (opt.secure_protocol)
     {
     case secure_protocol_auto:
+      err = gnutls_set_default_priority (session);
       break;
 
     case secure_protocol_sslv2:

src/hash.c

@@ -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));

src/host.c

@@ -57,10 +57,6 @@ as that of the covered work.  */
 
 #include <errno.h>
 
-#ifdef ENABLE_IRI
-#include <idn-free.h>
-#endif
-
 #include "utils.h"
 #include "host.h"
 #include "url.h"
@@ -428,14 +424,12 @@ 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
@@ -848,11 +842,8 @@ lookup_host (const char *host, int flags)
 
       if (opt.enable_iri && (name = idn_decode ((char *) host)) != NULL)
         {
-          int len = strlen (host) + strlen (name) + 4;
-          str = xmalloc (len);
-          snprintf (str, len, "%s (%s)", name, host);
-          str[len-1] = '\0';
-          idn_free (name);
+          str = aprintf ("%s (%s)", name, host);
+          xfree (name);
         }
 
       logprintf (LOG_VERBOSE, _("Resolving %s... "),

src/hsts.c

@@ -32,9 +32,9 @@ as that of the covered work.  */
 
 #ifdef HAVE_HSTS
 #include "hsts.h"
+#include "utils.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
@@ -80,7 +80,6 @@ enum hsts_kh_match {
 
 #define DEFAULT_HTTP_PORT 80
 #define DEFAULT_SSL_PORT  443
-#define CHECK_EXPLICIT_PORT(p1, p2) (p1 == 0 || p1 == p2)
 #define MAKE_EXPLICIT_PORT(s, p) (s == SCHEME_HTTPS ? (p == DEFAULT_SSL_PORT ? 0 : p) \
     : (p == DEFAULT_HTTP_PORT ? 0 : p))
 
@@ -327,7 +326,8 @@ hsts_store_dump (hsts_store_t store, FILE *fp)
 
       if (fprintf (fp, "%s\t%d\t%d\t%lu\t%lu\n",
                    kh->host, kh->explicit_port, khi->include_subdomains,
-                   khi->created, khi->max_age) < 0)
+                   (unsigned long) khi->created,
+                   (unsigned long) khi->max_age) < 0)
         {
           logprintf (LOG_ALWAYS, "Could not write the HSTS database correctly.\n");
           break;
@@ -343,12 +343,20 @@ hsts_store_dump (hsts_store_t store, FILE *fp)
 static bool
 hsts_file_access_valid (const char *filename)
 {
-  struct_stat st;
+  struct stat st;
 
   if (stat (filename, &st) == -1)
     return false;
 
-  return !(st.st_mode & S_IWOTH) && S_ISREG (st.st_mode);
+  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 */
@@ -435,7 +443,6 @@ hsts_store_entry (hsts_store_t store,
   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))
     {
@@ -450,17 +457,18 @@ hsts_store_entry (hsts_store_t store,
             }
           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. The RFC also states that we have to
+               * update the entry each time we see HSTS header.
+               * See also Section 11.2. */
+              time_t t = time (NULL);
+
+              if (t != -1 && t != entry->created)
                 {
-                  /* 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->created = t;
                   entry->max_age = max_age;
                   entry->include_subdomains = include_subdomains;
-
                   store->changed = true;
                 }
             }
@@ -492,25 +500,27 @@ hsts_store_t
 hsts_store_open (const char *filename)
 {
   hsts_store_t store = NULL;
+  file_stats_t fstats;
 
   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 (file_exists_p (filename, &fstats))
     {
       if (hsts_file_access_valid (filename))
         {
-          struct_stat st;
-          FILE *fp = fopen (filename, "r");
+          struct stat st;
+          FILE *fp = fopen_stat (filename, "r", &fstats);
 
           if (!fp || !hsts_read_database (store, fp, false))
             {
               /* abort! */
               hsts_store_close (store);
               xfree (store);
-              fclose (fp);
+              if (fp)
+                fclose (fp);
               goto out;
             }
 
@@ -540,7 +550,7 @@ out:
 void
 hsts_store_save (hsts_store_t store, const char *filename)
 {
-  struct_stat st;
+  struct stat st;
   FILE *fp = NULL;
   int fd = 0;
 
@@ -790,9 +800,9 @@ test_hsts_read_database (void)
       if (fp)
         {
           fputs ("# dummy comment\n", fp);
-          fprintf (fp, "foo.example.com\t0\t1\t%ld\t123\n",(long) created);
-          fprintf (fp, "bar.example.com\t0\t0\t%ld\t456\n", (long) created);
-          fprintf (fp, "test.example.com\t8080\t0\t%ld\t789\n", (long) created);
+          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);

src/html-parse.c

@@ -176,8 +176,8 @@ struct pool {
   P->orig_size = P->size;                                       \
 } while (0)
 
-/* Grow the pool to accomodate at least SIZE new bytes.  If the pool
-   already has room to accomodate SIZE bytes of data, this is a no-op.  */
+/* Grow the pool to accommodate at least SIZE new bytes.  If the pool
+   already has room to accommodate SIZE bytes of data, this is a no-op.  */
 
 #define POOL_GROW(p, increase)                                  \
   GROW_ARRAY ((p)->contents, (p)->size, (p)->tail + (increase), \
@@ -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

src/html-url.c

@@ -729,8 +729,11 @@ tag_handle_img (int tagid, struct taginfo *tag, struct map_context *ctx) {
                                             srcset + url_end);
               struct urlpos *up = append_url (url_text, base_ind + url_start,
                                               url_end - url_start, ctx);
-              up->link_inline_p = 1;
-              up->link_noquote_html_p = 1;
+              if (up)
+                {
+                  up->link_inline_p = 1;
+                  up->link_noquote_html_p = 1;
+                }
               xfree (url_text);
             }
 
@@ -842,6 +845,7 @@ get_urls_html (const char *file, const char *url, bool *meta_disallow_follow,
   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)

src/http-ntlm.c

@@ -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, strlen (header));
       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;
@@ -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);
 

src/http.h

@@ -35,7 +35,7 @@ as that of the covered work.  */
 
 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);

src/init.c

@@ -97,6 +97,11 @@ CMD_DECLARE (cmd_directory);
 CMD_DECLARE (cmd_time);
 CMD_DECLARE (cmd_vector);
 
+CMD_DECLARE (cmd_use_askpass);
+
+#ifdef HAVE_LIBZ
+CMD_DECLARE (cmd_spec_compression);
+#endif
 CMD_DECLARE (cmd_spec_dirstruct);
 CMD_DECLARE (cmd_spec_header);
 CMD_DECLARE (cmd_spec_warc_header);
@@ -159,6 +164,9 @@ static const struct {
   { "checkcertificate", &opt.check_cert,        cmd_check_cert },
 #endif
   { "chooseconfig",     &opt.choose_config,     cmd_file },
+#ifdef HAVE_LIBZ
+  { "compression",      &opt.compression,       cmd_spec_compression },
+#endif
   { "connecttimeout",   &opt.connect_timeout,   cmd_time },
   { "contentdisposition", &opt.content_disposition, cmd_boolean },
   { "contentonerror",   &opt.content_on_error,  cmd_boolean },
@@ -210,7 +218,7 @@ static const struct {
   { "header",           NULL,                   cmd_spec_header },
 #ifdef HAVE_HSTS
   { "hsts",             &opt.hsts,              cmd_boolean },
-  { "hsts-file",        &opt.hsts_file,         cmd_file },
+  { "hstsfile",         &opt.hsts_file,         cmd_file },
 #endif
   { "htmlextension",    &opt.adjust_extension,  cmd_boolean }, /* deprecated */
   { "htmlify",          NULL,                   cmd_spec_htmlify },
@@ -223,7 +231,7 @@ static const struct {
 #endif
   { "httpsproxy",       &opt.https_proxy,       cmd_string },
   { "httpuser",         &opt.http_user,         cmd_string },
-  { "if-modified-since", &opt.if_modified_since, cmd_boolean },
+  { "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 },
@@ -234,9 +242,10 @@ static const struct {
 #endif
   { "input",            &opt.input_filename,    cmd_file },
 #ifdef HAVE_METALINK
-  { "input-metalink",   &opt.input_metalink,    cmd_file },
+  { "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 },
@@ -245,7 +254,8 @@ static const struct {
   { "login",            &opt.ftp_user,          cmd_string },/* deprecated*/
   { "maxredirect",      &opt.max_redirect,      cmd_number },
 #ifdef HAVE_METALINK
-  { "metalink-over-http", &opt.metalink_over_http, cmd_boolean },
+  { "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 },
@@ -267,7 +277,7 @@ static const struct {
   { "postfile",         &opt.post_file_name,    cmd_file },
   { "preferfamily",     NULL,                   cmd_spec_prefer_family },
 #ifdef HAVE_METALINK
-  { "preferred-location", &opt.preferred_location, cmd_string },
+  { "preferredlocation", &opt.preferred_location, cmd_string },
 #endif
   { "preservepermissions", &opt.preserve_perm,  cmd_boolean },
 #ifdef HAVE_SSL
@@ -300,6 +310,7 @@ static const struct {
   { "restrictfilenames", NULL,                  cmd_spec_restrict_file_names },
   { "retrsymlinks",     &opt.retr_symlinks,     cmd_boolean },
   { "retryconnrefused", &opt.retry_connrefused, cmd_boolean },
+  { "retryonhttperror", &opt.retry_on_http_error, cmd_string },
   { "robots",           &opt.use_robots,        cmd_boolean },
   { "savecookies",      &opt.cookies_output,    cmd_file },
   { "saveheaders",      &opt.save_headers,      cmd_boolean },
@@ -317,7 +328,8 @@ static const struct {
   { "timestamping",     &opt.timestamping,      cmd_boolean },
   { "tries",            &opt.ntry,              cmd_number_inf },
   { "trustservernames", &opt.trustservernames,  cmd_boolean },
-  { "unlink",           &opt.unlink,            cmd_boolean },
+  { "unlink",           &opt.unlink_requested,  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 },
@@ -339,6 +351,9 @@ 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
@@ -378,6 +393,10 @@ 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;
@@ -432,6 +451,10 @@ defaults (void)
   opt.ftps_clear_data_connection = false;
 #endif
 
+#ifdef HAVE_LIBZ
+  opt.compression = compression_auto;
+#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;
@@ -482,6 +505,12 @@ defaults (void)
   /* 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
@@ -547,10 +576,11 @@ wgetrc_env_file_name (void)
   char *env = getenv ("WGETRC");
   if (env && *env)
     {
-      if (!file_exists_p (env))
+      file_stats_t flstat;
+      if (!file_exists_p (env, &flstat))
         {
-          fprintf (stderr, _("%s: WGETRC points to %s, which doesn't exist.\n"),
-                   exec_name, env);
+          fprintf (stderr, _("%s: WGETRC points to %s, which couldn't be accessed because of error: %s.\n"),
+                   exec_name, env, strerror(flstat.access_err));
           exit (WGET_EXIT_GENERIC_ERROR);
         }
       return xstrdup (env);
@@ -558,7 +588,7 @@ wgetrc_env_file_name (void)
   return NULL;
 }
 
-/* Check for the existance of '$HOME/.wgetrc' and return its path
+/* Check for the existence of '$HOME/.wgetrc' and return its path
    if it exists and is set.  */
 char *
 wgetrc_user_file_name (void)
@@ -578,7 +608,7 @@ wgetrc_user_file_name (void)
 
   if (!file)
     return NULL;
-  if (!file_exists_p (file))
+  if (!file_exists_p (file, NULL))
     {
       xfree (file);
       return NULL;
@@ -611,7 +641,7 @@ wgetrc_file_name (void)
       if (home)
         {
           file = aprintf ("%s/wget.ini", home);
-          if (!file_exists_p (file))
+          if (!file_exists_p (file, NULL))
             {
               xfree (file);
             }
@@ -639,7 +669,7 @@ static bool setval_internal_tilde (int, const char *, const char *);
    there were errors in the file.  */
 
 bool
-run_wgetrc (const char *file)
+run_wgetrc (const char *file, file_stats_t *flstats)
 {
   FILE *fp;
   char *line = NULL;
@@ -647,7 +677,7 @@ run_wgetrc (const char *file)
   int ln;
   int errcnt = 0;
 
-  fp = fopen (file, "r");
+  fp = fopen_stat (file, "r", flstats);
   if (!fp)
     {
       fprintf (stderr, _("%s: Cannot read %s (%s).\n"), exec_name,
@@ -703,14 +733,16 @@ void
 initialize (void)
 {
   char *file, *env_sysrc;
+  file_stats_t flstats;
   bool ok = true;
 
+  memset(&flstats, 0, sizeof(flstats));
   /* Run a non-standard system rc file when the according environment
      variable has been set. For internal testing purposes only!  */
   env_sysrc = getenv ("SYSTEM_WGETRC");
-  if (env_sysrc && file_exists_p (env_sysrc))
+  if (env_sysrc && file_exists_p (env_sysrc, &flstats))
     {
-      ok &= run_wgetrc (env_sysrc);
+      ok &= run_wgetrc (env_sysrc, &flstats);
       /* If there are any problems parsing the system wgetrc file, tell
          the user and exit */
       if (! ok)
@@ -724,8 +756,8 @@ or specify a different file using --config.\n"), env_sysrc);
     }
   /* Otherwise, if SYSTEM_WGETRC is defined, use it.  */
 #ifdef SYSTEM_WGETRC
-  else if (file_exists_p (SYSTEM_WGETRC))
-    ok &= run_wgetrc (SYSTEM_WGETRC);
+  else if (file_exists_p (SYSTEM_WGETRC, &flstats))
+    ok &= run_wgetrc (SYSTEM_WGETRC, &flstats);
   /* If there are any problems parsing the system wgetrc file, tell
      the user and exit */
   if (! ok)
@@ -752,7 +784,8 @@ or specify a different file using --config.\n"), SYSTEM_WGETRC);
     }
   else
 #endif
-    ok &= run_wgetrc (file);
+	if (file_exists_p (file, &flstats))
+        ok &= run_wgetrc (file, &flstats);
 
   /* If there were errors processing either `.wgetrc', abort. */
   if (!ok)
@@ -859,6 +892,10 @@ 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);
 }
@@ -1371,6 +1408,32 @@ 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)
@@ -1392,6 +1455,25 @@ cmd_cert_type (const char *com, const char *val, void *place)
 
 static bool check_user_specified_header (const char *);
 
+#ifdef HAVE_LIBZ
+static bool
+cmd_spec_compression (const char *com, const char *val, void *place)
+{
+  static const struct decode_item choices[] = {
+    { "auto", compression_auto },
+    { "gzip", compression_gzip },
+    { "none", compression_none },
+  };
+  int ok = decode_string (val, choices, countof (choices), place);
+  if (!ok)
+    {
+      fprintf (stderr, _("%s: %s: Invalid value %s.\n"), exec_name, com,
+               quote (val));
+    }
+  return ok;
+}
+#endif
+
 static bool
 cmd_spec_dirstruct (const char *com, const char *val, void *place_ignored _GL_UNUSED)
 {
@@ -1930,6 +2012,8 @@ cleanup (void)
   xfree (opt.body_data);
   xfree (opt.body_file);
   xfree (opt.rejected_log);
+  xfree (opt.use_askpass);
+  xfree (opt.retry_on_http_error);
 
 #ifdef HAVE_LIBCARES
 #include <ares.h>

src/init.h

@@ -41,6 +41,6 @@ void setoptval (const char *, const char *, const char *);
 char *home_dir (void);
 void cleanup (void);
 void defaults (void);
-bool run_wgetrc (const char *file);
+bool run_wgetrc (const char *file, file_stats_t *);
 
 #endif /* INIT_H */

src/iri.c

@@ -33,11 +33,16 @@ 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>
+#if IDN2_VERSION_NUMBER < 0x00140000
+# include <unicase.h>
+# include <unistr.h>
+#endif
 
 #include "utils.h"
 #include "url.h"
@@ -45,9 +50,6 @@ 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,
@@ -88,10 +90,15 @@ parse_charset (const 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. */
@@ -114,6 +121,7 @@ check_encoding_name (const char *encoding)
   return true;
 }
 
+#ifdef HAVE_ICONV
 /* Do the conversion according to the passed conversion descriptor cd. *out
    will contain the transcoded string on success. *out content is
    unspecified otherwise. */
@@ -146,7 +154,7 @@ do_conversion (const char *tocode, const char *fromcode, char const *in_org, siz
 
   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;
@@ -159,7 +167,7 @@ do_conversion (const char *tocode, const char *fromcode, char const *in_org, siz
             if (!strchr(in_org, '@') && !strchr(*out, '@'))
               debug_logprintf ("converted '%s' (%s) -> '%s' (%s)\n", in_org, fromcode, *out, tocode);
             else
-              debug_logprintf ("%s: logging suppressed, strings may contain password\n", __func__);
+              debug_logprintf ("logging suppressed, strings may contain password\n");
           }
           return true;
         }
@@ -201,10 +209,19 @@ do_conversion (const char *tocode, const char *fromcode, char const *in_org, siz
       if (!strchr(in_org, '@') && !strchr(*out, '@'))
         debug_logprintf ("converted '%s' (%s) -> '%s' (%s)\n", in_org, fromcode, *out, tocode);
       else
-        debug_logprintf ("%s: logging suppressed, strings may contain password\n", __func__);
+        debug_logprintf ("logging suppressed, strings may contain password\n");
     }
     return false;
 }
+#else
+static bool
+do_conversion (const char *tocode _GL_UNUSED, const char *fromcode _GL_UNUSED,
+               char const *in_org _GL_UNUSED, size_t inlen _GL_UNUSED, char **out)
+{
+  *out = NULL;
+  return false;
+}
+#endif
 
 /* Try converting string str from locale to UTF-8. Return a new string
    on success, or str on error or if conversion isn't needed. */
@@ -230,50 +247,6 @@ locale_to_utf8 (const char *str)
   return str;
 }
 
-/*
- * Work around a libidn <= 1.30 vulnerability.
- *
- * The function checks for a valid UTF-8 character sequence before
- * passing it to idna_to_ascii_8z().
- *
- * [1] http://lists.gnu.org/archive/html/help-libidn/2015-05/msg00002.html
- * [2] https://lists.gnu.org/archive/html/bug-wget/2015-06/msg00002.html
- * [3] http://curl.haxx.se/mail/lib-2015-06/0143.html
- */
-static bool
-_utf8_is_valid(const char *utf8)
-{
-  const unsigned char *s = (const unsigned char *) utf8;
-
-  while (*s)
-    {
-      if ((*s & 0x80) == 0) /* 0xxxxxxx ASCII char */
-        s++;
-      else if ((*s & 0xE0) == 0xC0) /* 110xxxxx 10xxxxxx */
-        {
-          if ((s[1] & 0xC0) != 0x80)
-            return false;
-          s+=2;
-        }
-      else if ((*s & 0xF0) == 0xE0) /* 1110xxxx 10xxxxxx 10xxxxxx */
-        {
-          if ((s[1] & 0xC0) != 0x80 || (s[2] & 0xC0) != 0x80)
-            return false;
-          s+=3;
-        }
-      else if ((*s & 0xF8) == 0xF0) /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
-        {
-          if ((s[1] & 0xC0) != 0x80 || (s[2] & 0xC0) != 0x80 || (s[3] & 0xC0) != 0x80)
-            return false;
-          s+=4;
-        }
-      else
-        return false;
-    }
-
-  return true;
-}
-
 /* Try to "ASCII encode" UTF-8 host. Return the new domain on success or NULL
    on error. */
 char *
@@ -282,34 +255,62 @@ idn_encode (const struct iri *i, const char *host)
   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, host, &utf8_encoded))
-          return NULL;  /* Nothing to encode or an error occured */
+          return NULL;  /* Nothing to encode or an error occurred */
+      src = utf8_encoded;
     }
+  else
+    src = host;
 
-  if (!_utf8_is_valid(utf8_encoded ? utf8_encoded : host))
+#if IDN2_VERSION_NUMBER >= 0x00140000
+  /* IDN2_TRANSITIONAL implies input NFC encoding */
+  ret = idn2_lookup_u8 ((uint8_t *) src, (uint8_t **) &ascii_encoded, IDN2_NONTRANSITIONAL);
+  if (ret != IDN2_OK)
+    /* fall back to TR46 Transitional mode, max IDNA2003 compatibility */
+    ret = idn2_lookup_u8 ((uint8_t *) src, (uint8_t **) &ascii_encoded, IDN2_TRANSITIONAL);
+
+  if (ret != IDN2_OK)
+    logprintf (LOG_VERBOSE, _("idn_encode failed (%d): %s\n"), 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, _("Invalid UTF-8 sequence: %s\n"),
-                 quote(utf8_encoded ? utf8_encoded : host));
+      logprintf (LOG_VERBOSE, _("Failed to convert to lower: %d: %s\n"),
+                 errno, quote (src));
       xfree (utf8_encoded);
       return NULL;
     }
 
-  /* Store in ascii_encoded the ASCII UTF-8 NULL terminated string */
-  ret = idna_to_ascii_8z (utf8_encoded ? utf8_encoded : host, &ascii_encoded, IDNA_FLAGS);
-  xfree (utf8_encoded);
-
-  if (ret != IDNA_SUCCESS)
+  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 (idna_strerror (ret)));
-      return NULL;
+                 quote (idn2_strerror (ret)));
     }
 
-  return ascii_encoded;
+  xfree (lower);
+#endif
+
+  xfree (utf8_encoded);
+
+  if (ret == IDN2_OK && ascii_encoded)
+    {
+      char *tmp = xstrdup (ascii_encoded);
+      idn2_free (ascii_encoded);
+      ascii_encoded = tmp;
+    }
+
+  return ret == IDN2_OK ? ascii_encoded : NULL;
 }
 
 /* Try to decode an "ASCII encoded" host. Return the new domain in the locale
@@ -317,18 +318,24 @@ idn_encode (const struct iri *i, const char *host)
 char *
 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

src/iri.h

@@ -40,11 +40,8 @@ struct iri {
 
 #ifdef ENABLE_IRI
 
-# include <idna.h>
-# include <idn-free.h>
-
 char *parse_charset (const char *str);
-char *find_locale (void);
+const char *find_locale (void);
 bool check_encoding_name (const char *encoding);
 const char *locale_to_utf8 (const char *str);
 char *idn_encode (const struct iri *i, const char *host);
@@ -66,7 +63,7 @@ extern struct iri dummy_iri;
 #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)

src/log.c

@@ -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;
@@ -520,7 +532,7 @@ log_set_flush (bool flush)
     }
   else
     {
-      /* Reenable flushing.  If anything was printed in no-flush mode,
+      /* Re-enable flushing.  If anything was printed in no-flush mode,
          flush the log now.  */
       if (needs_flushing)
         logflush ();
@@ -611,16 +623,18 @@ log_init (const char *file, bool appendp)
     {
       if (HYPHENP (file))
         {
-          logfp = stdout;
+          stdlogfp = stdout;
+          logfp = stdlogfp;
         }
       else
         {
-          logfp = fopen (file, appendp ? "a" : "w");
-          if (!logfp)
+          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
@@ -631,7 +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
@@ -646,6 +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
@@ -880,59 +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 */
 }

src/log.h

@@ -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 *);

src/main.c

@@ -36,6 +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
@@ -60,6 +61,7 @@ as that of the covered work.  */
 #include "version.h"
 #include "c-strcase.h"
 #include "dirname.h"
+#include "xmemdup0.h"
 #include <getopt.h>
 #include <getpass.h>
 #include <quote.h>
@@ -130,7 +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);
 }
@@ -219,8 +221,8 @@ save_hsts (void)
 
 /* 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
@@ -273,6 +275,9 @@ static struct cmdline_option option_data[] =
     { IF_SSL ("certificate-type"), 0, OPT_VALUE, "certificatetype", -1 },
     { IF_SSL ("check-certificate"), 0, OPT_BOOLEAN, "checkcertificate", -1 },
     { "clobber", 0, OPT__CLOBBER, NULL, optional_argument },
+#ifdef HAVE_LIBZ
+    { "compression", 0, OPT_VALUE, "compression", -1 },
+#endif
     { "config", 0, OPT_VALUE, "chooseconfig", -1 },
     { "connect-timeout", 0, OPT_VALUE, "connecttimeout", -1 },
     { "continue", 'c', OPT_BOOLEAN, "continue", -1 },
@@ -321,7 +326,7 @@ static struct cmdline_option option_data[] =
     { "host-directories", 0, OPT_BOOLEAN, "addhostdir", -1 },
 #ifdef HAVE_HSTS
     { "hsts", 0, OPT_BOOLEAN, "hsts", -1},
-    { "hsts-file", 0, OPT_VALUE, "hsts-file", -1 },
+    { "hsts-file", 0, OPT_VALUE, "hstsfile", -1 },
 #endif
     { "html-extension", 'E', OPT_BOOLEAN, "adjustextension", -1 }, /* deprecated */
     { "htmlify", 0, OPT_BOOLEAN, "htmlify", -1 },
@@ -340,9 +345,10 @@ static struct cmdline_option option_data[] =
 #endif
     { "input-file", 'i', OPT_VALUE, "input", -1 },
 #ifdef HAVE_METALINK
-    { "input-metalink", 0, OPT_VALUE, "input-metalink", -1 },
+    { "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 },
@@ -351,10 +357,12 @@ static struct cmdline_option option_data[] =
     { "rejected-log", 0, OPT_VALUE, "rejectedlog", -1 },
     { "max-redirect", 0, OPT_VALUE, "maxredirect", -1 },
 #ifdef HAVE_METALINK
-    { "metalink-over-http", 0, OPT_BOOLEAN, "metalink-over-http", -1 },
+    { "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 },
+    { "netrc", 0, OPT_BOOLEAN, "netrc", -1 },
     { "no", 'n', OPT__NO, NULL, required_argument },
     { "no-clobber", 0, OPT_BOOLEAN, "noclobber", -1 },
     { "no-config", 0, OPT_BOOLEAN, "noconfig", -1},
@@ -370,7 +378,7 @@ static struct cmdline_option option_data[] =
     { "post-file", 0, OPT_VALUE, "postfile", -1 },
     { "prefer-family", 0, OPT_VALUE, "preferfamily", -1 },
 #ifdef HAVE_METALINK
-    { "preferred-location", 0, OPT_VALUE, "preferred-location", -1 },
+    { "preferred-location", 0, OPT_VALUE, "preferredlocation", -1 },
 #endif
     { "preserve-permissions", 0, OPT_BOOLEAN, "preservepermissions", -1 },
     { IF_SSL ("private-key"), 0, OPT_VALUE, "privatekey", -1 },
@@ -400,6 +408,7 @@ static struct cmdline_option option_data[] =
     { "restrict-file-names", 0, OPT_BOOLEAN, "restrictfilenames", -1 },
     { "retr-symlinks", 0, OPT_BOOLEAN, "retrsymlinks", -1 },
     { "retry-connrefused", 0, OPT_BOOLEAN, "retryconnrefused", -1 },
+    { "retry-on-http-error", 0, OPT_VALUE, "retryonhttperror", -1 },
     { "save-cookies", 0, OPT_VALUE, "savecookies", -1 },
     { "save-headers", 0, OPT_BOOLEAN, "saveheaders", -1 },
     { IF_SSL ("secure-protocol"), 0, OPT_VALUE, "secureprotocol", -1 },
@@ -410,15 +419,15 @@ 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, "if-modified-since", -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 },
     { "verbose", 'v', OPT_BOOLEAN, "verbose", -1 },
-    { "verbose", 0, OPT_BOOLEAN, "verbose", -1 },
     { "version", 'V', OPT_FUNCALL, (void *) print_version, no_argument },
     { "wait", 'w', OPT_VALUE, "wait", -1 },
     { "waitretry", 0, OPT_VALUE, "waitretry", -1 },
@@ -435,6 +444,9 @@ 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
   };
 
@@ -547,7 +559,7 @@ 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
@@ -620,6 +632,8 @@ Download:\n"),
     N_("\
   -nc, --no-clobber                skip downloads that would download to\n\
                                      existing files (overwriting them)\n"),
+    N_("\
+       --no-netrc                  don't try to obtain credentials from .netrc\n"),
     N_("\
   -c,  --continue                  resume getting a partially-downloaded file\n"),
     N_("\
@@ -690,6 +704,11 @@ 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_("\
@@ -699,10 +718,18 @@ Download:\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",
 
@@ -739,6 +766,10 @@ HTTP options:\n"),
        --ignore-length             ignore 'Content-Length' header field\n"),
     N_("\
        --header=STRING             insert STRING among the headers\n"),
+#ifdef HAVE_LIBZ
+    N_("\
+       --compression=TYPE          choose compression, one of auto, gzip and none\n"),
+#endif
     N_("\
        --max-redirect              maximum redirections allowed per page\n"),
     N_("\
@@ -787,7 +818,7 @@ HTTP options:\n"),
 HTTPS (SSL/TLS) options:\n"),
     N_("\
        --secure-protocol=PR        choose secure protocol, one of auto, SSLv2,\n\
-                                     SSLv3, TLSv1 and PFS\n"),
+                                     SSLv3, TLSv1, TLSv1_1, TLSv1_2 and PFS\n"),
     N_("\
        --https-only                only follow secure HTTPS links\n"),
     N_("\
@@ -809,7 +840,7 @@ HTTPS (SSL/TLS) options:\n"),
     N_("\
        --pinnedpubkey=FILE/HASHES  Public key (PEM/DER) file, or any number\n\
                                    of base64 encoded sha256 hashes preceded by\n\
-                                   \'sha256//\' and seperated by \';\', to verify\n\
+                                   \'sha256//\' and separated by \';\', to verify\n\
                                    peer against\n"),
 #if defined(HAVE_LIBSSL) || defined(HAVE_LIBSSL32)
     N_("\
@@ -1019,6 +1050,103 @@ 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
@@ -1080,7 +1208,7 @@ format_and_print_line (const char *prefix, const char *line,
   return 0;
 }
 
-static void _Noreturn
+_Noreturn static void
 print_version (void)
 {
   const char *wgetrc_title  = _("Wgetrc: ");
@@ -1263,10 +1391,10 @@ main (int argc, char **argv)
             }
           else if (strcmp (config_opt->long_name, "config") == 0)
             {
-              bool userrc_ret = true;
-              userrc_ret &= run_wgetrc (optarg);
+              file_stats_t flstats;
               use_userconfig = true;
-              if (userrc_ret)
+              memset(&flstats, 0, sizeof(flstats));
+              if (file_exists_p(optarg, &flstats) && run_wgetrc (optarg, &flstats))
                 break;
               else
                 {
@@ -1339,7 +1467,8 @@ 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:
           {
@@ -1501,7 +1630,7 @@ WARNING: timestamping does nothing in combination with -O. See the manual\n\
 for details.\n\n"));
           opt.timestamping = false;
         }
-      if (opt.noclobber && file_exists_p(opt.output_document))
+      if (opt.noclobber && file_exists_p(opt.output_document, NULL))
            {
               /* Check if output file exists; if it does, exit. */
               logprintf (LOG_VERBOSE,
@@ -1553,6 +1682,26 @@ for details.\n\n"));
         }
     }
 
+#ifdef HAVE_LIBZ
+  if (opt.always_rest || opt.start_pos >= 0)
+    {
+      if (opt.compression == compression_auto)
+        {
+          /* Compression does not work with --continue or --start-pos.
+             Since compression was not explicitly set, it will be disabled. */
+          opt.compression = compression_none;
+        }
+      else if (opt.compression != compression_none)
+        {
+          fprintf (stderr,
+                   _("Compression does not work with --continue or"
+                     " --start-pos, they will be disabled.\n"));
+          opt.always_rest = false;
+          opt.start_pos = -1;
+        }
+    }
+#endif
+
   if (opt.ask_passwd && opt.passwd)
     {
       fprintf (stderr,
@@ -1623,7 +1772,7 @@ 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);
         }
     }
@@ -1702,6 +1851,16 @@ 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();
@@ -1764,7 +1923,7 @@ for details.\n\n"));
         }
       else
         {
-          struct_fstat st;
+          struct stat st;
 
 #ifdef __VMS
 /* Common fopen() optional arguments:
@@ -1920,6 +2079,10 @@ only if 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
 #ifdef HAVE_SSL
@@ -1948,7 +2111,7 @@ only if outputting to a regular file.\n"));
                             &dt, opt.recursive, iri, true);
             }
 
-          if (opt.delete_after && filename != NULL && file_exists_p (filename))
+          if (opt.delete_after && filename != NULL && file_exists_p (filename, NULL))
             {
               DEBUGP (("Removing file due to --delete-after in main():\n"));
               logprintf (LOG_VERBOSE, _("Removing %s.\n"), filename);

src/metalink.h

@@ -46,6 +46,21 @@ as that of the covered work.  */
 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,

src/mswindows.c

@@ -53,9 +53,6 @@ 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
@@ -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;
@@ -583,7 +580,7 @@ run_with_timeout (double seconds, void (*fun) (void *), void *arg)
 const char *
 inet_ntop (int af, const void *src, char *dst, socklen_t cnt)
 {
-  /* struct sockaddr can't accomodate struct sockaddr_in6. */
+  /* struct sockaddr can't accommodate struct sockaddr_in6. */
   union {
     struct sockaddr_in6 sin6;
     struct sockaddr_in sin;

src/mswindows.h

@@ -57,6 +57,9 @@ as that of the covered work.  */
 /* Declares getpid(). */
 #include <process.h>
 
+/* Declares inet_ntop() and inet_pton(). */
+#include <arpa/inet.h>
+
 /* We have strcasecmp and strncasecmp, just under different names.  */
 #ifndef HAVE_STRCASECMP
 # define strcasecmp stricmp
@@ -85,11 +88,6 @@ typedef __int64 wgint;
 
 #define PATH_SEPARATOR '\\'
 
-/* Additional declarations needed for IPv6: */
-#ifdef ENABLE_IPV6
-const char *inet_ntop (int, const void *, char *, socklen_t);
-#endif
-
 /* ioctl needed by set_windows_fd_as_blocking_socket() */
 #include <sys/ioctl.h>
 

src/netrc.c

@@ -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);
@@ -235,7 +235,7 @@ parse_netrc (const char *path)
   /* The latest token we've seen in the file.  */
   enum
   {
-    tok_nothing, tok_account, tok_login, tok_macdef, tok_machine, tok_password
+    tok_nothing, tok_account, tok_login, tok_macdef, tok_machine, tok_password, tok_port, tok_force
   } last_token = tok_nothing;
 
   current = retval = NULL;
@@ -344,6 +344,18 @@ parse_netrc (const char *path)
                 premature_token = "account";
               break;
 
+              /* We don't handle the port keyword at all.  */
+            case tok_port:
+              if (!current)
+                premature_token = "port";
+              break;
+
+              /* We don't handle the force keyword at all.  */
+            case tok_force:
+              if (!current)
+                premature_token = "force";
+              break;
+
               /* We handle tok_nothing below this switch.  */
             case tok_nothing:
               break;
@@ -365,10 +377,10 @@ parse_netrc (const char *path)
               /* Fetch the next token.  */
               if (!strcmp (tok, "account"))
                 last_token = tok_account;
+
               else if (!strcmp (tok, "default"))
-                {
                   maybe_add_to_list (&current, &retval);
-                }
+
               else if (!strcmp (tok, "login"))
                 last_token = tok_login;
 
@@ -381,6 +393,16 @@ parse_netrc (const char *path)
               else if (!strcmp (tok, "password"))
                 last_token = tok_password;
 
+				  /* GNU extensions 'port' and 'force', not operational
+					* see https://www.gnu.org/software/emacs/manual/html_node/gnus/NNTP.html#index-nntp_002dauthinfo_002dfunction-2003
+					* see https://savannah.gnu.org/bugs/index.php?52066
+					*/
+              else if (!strcmp (tok, "port"))
+                last_token = tok_port;
+
+              else if (!strcmp (tok, "force"))
+                last_token = tok_force;
+
               else
                 fprintf (stderr, _("%s: %s:%d: unknown token \"%s\"\n"),
                          exec_name, path, ln, tok);
@@ -439,7 +461,7 @@ 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;
 

src/openssl.c

@@ -204,18 +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;
@@ -583,7 +585,7 @@ ssl_connect_wget (int fd, const char *hostname, int *continue_session)
     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);

src/options.h

@@ -43,6 +43,7 @@ struct options
   bool quiet;                   /* Are we quiet? */
   int ntry;                     /* Number of tries per URL */
   bool retry_connrefused;       /* Treat CONNREFUSED as non-fatal. */
+  char *retry_on_http_error;    /* Treat given HTTP errors as non-fatal. */
   bool background;              /* Whether we should work in background. */
   bool ignore_length;           /* Do we heed content-length at all?  */
   bool recursive;               /* Are we recursive? */
@@ -61,12 +62,13 @@ struct options
   bool add_hostdir;             /* Do we add hostname directory? */
   bool protocol_directories;    /* Whether to prepend "http"/"ftp" to dirs. */
   bool noclobber;               /* Disables clobbering of existing data. */
-  bool unlink;                  /* remove file before clobbering */
+  bool unlink_requested;        /* remove file before clobbering */
   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
@@ -127,9 +129,12 @@ 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. */
@@ -243,7 +248,7 @@ struct options
 
   char *pinnedpubkey;           /* Public key (PEM/DER) file, or any number
                                    of base64 encoded sha256 hashes preceded by
-                                   \'sha256//\' and seperated by \';\', to verify
+                                   \'sha256//\' and separated by \';\', to verify
                                    peer against */
 
   char *random_file;            /* file with random data to seed the PRNG */
@@ -258,6 +263,7 @@ struct options
   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. */
 
@@ -306,7 +312,7 @@ struct options
 
   bool enable_iri;
   char *encoding_remote;
-  char *locale;
+  const char *locale;
 
   bool trustservernames;
 #ifdef __VMS
@@ -320,6 +326,14 @@ struct options
                                    name. */
   bool report_bps;              /*Output bandwidth in bits format*/
 
+#ifdef HAVE_LIBZ
+  enum compression_options {
+    compression_auto,
+    compression_gzip,
+    compression_none
+  } compression;                /* type of HTTP compression to use */
+#endif
+
   char *rejected_log;           /* The file to log rejected URLS to. */
 
 #ifdef HAVE_HSTS

src/progress.c

@@ -75,7 +75,7 @@ static struct progress_implementation implementations[] = {
 static struct progress_implementation *current_impl;
 static int current_impl_locked;
 
-/* Progress implementation used by default.  Can be overriden in
+/* Progress implementation used by default.  Can be overridden in
    wgetrc or by the fallback one.  */
 
 #define DEFAULT_PROGRESS_IMPLEMENTATION "bar"
@@ -892,11 +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)
 {

src/recur.c

@@ -438,10 +438,15 @@ 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);
@@ -451,9 +456,16 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
                   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;
+                    {
+                      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);
@@ -485,7 +497,7 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
 
       if (file
           && (opt.delete_after
-              || opt.spider /* opt.recursive is implicitely true */
+              || opt.spider /* opt.recursive is implicitly true */
               || !acceptable (file)))
         {
           /* Either --delete-after was specified, or we loaded this
@@ -686,7 +698,7 @@ download_child (const struct urlpos *upos, struct url *parent, int depth,
      for directories (no file name to match) and for non-leaf HTMLs,
      which can lead to other files that do need to be downloaded.  (-p
      automatically implies non-leaf because with -p we can, if
-     necesary, overstep the maximum depth to get the page requisites.)  */
+     necessary, overstep the maximum depth to get the page requisites.)  */
   if (u->file[0] != '\0'
       && !(has_html_suffix_p (u->file)
            /* The exception only applies to non-leaf HTMLs (but -p
@@ -801,6 +813,12 @@ descend_redirect (const char *redirected, struct url *orig_parsed, int depth,
 
   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));
 

src/res.c

@@ -37,12 +37,12 @@ as that of the covered work.  */
    disallow access to certain parts of the site.
 
    The first specification was written by Martijn Koster in 1994, and
-   is still available at <http://www.robotstxt.org/wc/norobots.html>.
+   is still available at <http://www.robotstxt.org/orig.html>.
    In 1996, Martijn wrote an Internet Draft specifying an improved RES
    specification; however, that work was apparently abandoned since
    the draft has expired in 1997 and hasn't been replaced since.  The
    draft is available at
-   <http://www.robotstxt.org/wc/norobots-rfc.html>.
+   <http://www.robotstxt.org/norobots-rfc.txt>.
 
    This file implements RES as specified by the draft.  Note that this
    only handles the "robots.txt" support.  The META tag that controls
@@ -428,7 +428,7 @@ free_specs (struct robot_specs *specs)
 
 /* The inner matching engine: return true if RECORD_PATH matches
    URL_PATH.  The rules for matching are described at
-   <http://www.robotstxt.org/wc/norobots-rfc.txt>, section 3.2.2.  */
+   <http://www.robotstxt.org/norobots-rfc.txt>, section 3.2.2.  */
 
 static bool
 matches (const char *record_path, const char *url_path)

src/retr.c

@@ -41,6 +41,10 @@ as that of the covered work.  */
 # include <unixio.h>            /* For delete(). */
 #endif
 
+#ifdef HAVE_LIBZ
+# include <zlib.h>
+#endif
+
 #include "exits.h"
 #include "utils.h"
 #include "retr.h"
@@ -84,6 +88,22 @@ limit_bandwidth_reset (void)
   xzero (limit_data);
 }
 
+#ifdef HAVE_LIBZ
+static voidpf
+zalloc (voidpf opaque, unsigned int items, unsigned int size)
+{
+  (void) opaque;
+  return (voidpf) xcalloc (items, size);
+}
+
+static void
+zfree (voidpf opaque, voidpf address)
+{
+  (void) opaque;
+  xfree (address);
+}
+#endif
+
 /* Limit the bandwidth by pausing the download for an amount of time.
    BYTES is the number of bytes received from the network, and TIMER
    is the timer that started at the beginning of download.  */
@@ -257,6 +277,44 @@ fd_read_body (const char *downloaded_filename, int fd, FILE *out, wgint toread,
   wgint sum_written = 0;
   wgint remaining_chunk_size = 0;
 
+#ifdef HAVE_LIBZ
+  /* try to minimize the number of calls to inflate() and write_data() per
+     call to fd_read() */
+  unsigned int gzbufsize = dlbufsize * 4;
+  char *gzbuf = NULL;
+  z_stream gzstream;
+
+  if (flags & rb_compressed_gzip)
+    {
+      gzbuf = xmalloc (gzbufsize);
+      if (gzbuf != NULL)
+        {
+          gzstream.zalloc = zalloc;
+          gzstream.zfree = zfree;
+          gzstream.opaque = Z_NULL;
+          gzstream.next_in = Z_NULL;
+          gzstream.avail_in = 0;
+
+          #define GZIP_DETECT 32 /* gzip format detection */
+          #define GZIP_WINDOW 15 /* logarithmic window size (default: 15) */
+          ret = inflateInit2 (&gzstream, GZIP_DETECT | GZIP_WINDOW);
+          if (ret != Z_OK)
+            {
+              xfree (gzbuf);
+              errno = (ret == Z_MEM_ERROR) ? ENOMEM : EINVAL;
+              ret = -1;
+              goto out;
+            }
+        }
+      else
+        {
+          errno = ENOMEM;
+          ret = -1;
+          goto out;
+        }
+    }
+#endif
+
   if (flags & rb_skip_startpos)
     skip = startpos;
 
@@ -320,6 +378,12 @@ fd_read_body (const char *downloaded_filename, int fd, FILE *out, wgint toread,
               remaining_chunk_size = strtol (line, &endl, 16);
               xfree (line);
 
+              if (remaining_chunk_size < 0)
+                {
+                  ret = -1;
+                  break;
+                }
+
               if (remaining_chunk_size == 0)
                 {
                   ret = 0;
@@ -383,12 +447,64 @@ fd_read_body (const char *downloaded_filename, int fd, FILE *out, wgint toread,
           int write_res;
 
           sum_read += ret;
-          write_res = write_data (out, out2, dlbuf, ret, &skip, &sum_written);
-          if (write_res < 0)
+
+#ifdef HAVE_LIBZ
+          if (gzbuf != NULL)
             {
-              ret = (write_res == -3) ? -3 : -2;
-              goto out;
+              int err;
+              int towrite;
+              gzstream.avail_in = ret;
+              gzstream.next_in = (unsigned char *) dlbuf;
+
+              do
+                {
+                  gzstream.avail_out = gzbufsize;
+                  gzstream.next_out = (unsigned char *) gzbuf;
+
+                  err = inflate (&gzstream, Z_NO_FLUSH);
+
+                  switch (err)
+                    {
+                    case Z_MEM_ERROR:
+                      errno = ENOMEM;
+                      ret = -1;
+                      goto out;
+                    case Z_NEED_DICT:
+                    case Z_DATA_ERROR:
+                      errno = EINVAL;
+                      ret = -1;
+                      goto out;
+                    case Z_STREAM_END:
+                      if (exact && sum_read != toread)
+                        {
+                          DEBUGP(("zlib stream ended unexpectedly after "
+                                  "%ld/%ld bytes\n", sum_read, toread));
+                        }
+                    }
+
+                  towrite = gzbufsize - gzstream.avail_out;
+                  write_res = write_data (out, out2, gzbuf, towrite, &skip,
+                                          &sum_written);
+                  if (write_res < 0)
+                    {
+                      ret = (write_res == -3) ? -3 : -2;
+                      goto out;
+                    }
+                }
+              while (gzstream.avail_out == 0);
             }
+          else
+#endif
+            {
+              write_res = write_data (out, out2, dlbuf, ret, &skip,
+                                      &sum_written);
+              if (write_res < 0)
+                {
+                  ret = (write_res == -3) ? -3 : -2;
+                  goto out;
+                }
+            }
+
           if (chunked)
             {
               remaining_chunk_size -= ret;
@@ -433,6 +549,31 @@ fd_read_body (const char *downloaded_filename, int fd, FILE *out, wgint toread,
   if (timer)
     ptimer_destroy (timer);
 
+#ifdef HAVE_LIBZ
+  if (gzbuf != NULL)
+    {
+      int err = inflateEnd (&gzstream);
+      if (ret >= 0)
+        {
+          /* with compression enabled, ret must be 0 if successful */
+          if (err == Z_OK)
+            ret = 0;
+          else
+            {
+              errno = EINVAL;
+              ret = -1;
+            }
+        }
+      xfree (gzbuf);
+
+      if (gzstream.total_in != sum_read)
+        {
+          DEBUGP(("zlib read size differs from raw read size (%lu/%lu)\n",
+                  gzstream.total_in, sum_read));
+        }
+    }
+#endif
+
   if (qtyread)
     *qtyread += sum_read;
   if (qtywritten)
@@ -634,7 +775,7 @@ 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]);
 
@@ -869,7 +1010,7 @@ 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;
 
@@ -963,11 +1104,16 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
       u = url_parse (origurl, NULL, iri, true);
       if (u)
         {
-          DEBUGP (("[IRI fallbacking to non-utf8 for %s\n", quote (url)));
-          xfree (url);
-          url = xstrdup (u->url);
-          iri_fallbacked = 1;
-          goto redirected;
+          if (strcmp(u->url, orig_parsed->url))
+            {
+              DEBUGP (("[IRI fallbacking to non-utf8 for %s\n", quote (url)));
+              xfree (url);
+              url = xstrdup (u->url);
+              iri_fallbacked = 1;
+              goto redirected;
+            }
+          else
+              DEBUGP (("[Needn't fallback to non-utf8 for %s\n", quote (url)));
         }
       else
           DEBUGP (("[Couldn't fallback to non-utf8 for %s\n", quote (url)));
@@ -1141,13 +1287,13 @@ retrieve_from_file (const char *file, bool html, int *count)
       if (parsed_url)
           url_free (parsed_url);
 
-      if (filename && opt.delete_after && file_exists_p (filename))
+      if (filename && opt.delete_after && file_exists_p (filename, NULL))
         {
           DEBUGP (("\
 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;
         }
 
@@ -1248,9 +1394,9 @@ 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)
@@ -1267,17 +1413,21 @@ 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 **);

src/retr.h

@@ -49,7 +49,9 @@ enum {
   rb_skip_startpos = 2,
 
   /* Used by HTTP/HTTPS*/
-  rb_chunked_transfer_encoding = 4
+  rb_chunked_transfer_encoding = 4,
+
+  rb_compressed_gzip = 8
 };
 
 int fd_read_body (const char *, int, FILE *, wgint, wgint, wgint *, wgint *, double *, int, FILE *);

src/sysdep.h

@@ -35,53 +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
-
-#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>
 
@@ -95,98 +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
-
-/* 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 */

src/url.c

@@ -43,10 +43,10 @@ as that of the covered work.  */
 #include "host.h"  /* for is_valid_ipv6_address */
 #include "c-strcase.h"
 
-#if HAVE_ICONV
-#include <iconv.h>
-#include <langinfo.h>
+#ifdef HAVE_ICONV
+# include <iconv.h>
 #endif
+#include <langinfo.h>
 
 #ifdef __VMS
 #include "vms.h"
@@ -459,7 +459,7 @@ url_scheme (const char *url)
   int i;
 
   for (i = 0; supported_schemes[i].leading_string; i++)
-    if (0 == strncasecmp (url, supported_schemes[i].leading_string,
+    if (0 == c_strncasecmp (url, supported_schemes[i].leading_string,
                           strlen (supported_schemes[i].leading_string)))
       {
         if (!(supported_schemes[i].flags & scm_disabled))
@@ -512,6 +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.
@@ -919,6 +925,17 @@ url_parse (const char *url, int *error, struct iri *iri, bool percent_encode)
       url_unescape (u->host);
       host_modified = true;
 
+      /* check for invalid control characters in host name */
+      for (p = u->host; *p; p++)
+        {
+          if (c_iscntrl(*p))
+            {
+              url_free(u);
+              error_code = PE_INVALID_HOST_NAME;
+              goto error;
+            }
+        }
+
       /* Apply IDNA regardless of iri->utf8_encode status */
       if (opt.enable_iri && iri)
         {
@@ -927,7 +944,6 @@ url_parse (const char *url, int *error, struct iri *iri, bool percent_encode)
             {
               xfree (u->host);
               u->host = new;
-              u->idn_allocated = true;
               host_modified = true;
             }
         }
@@ -1206,12 +1222,7 @@ url_free (struct url *url)
 {
   if (url)
     {
-      if (url->idn_allocated) {
-        idn_free (url->host);      /* A dummy if !defined(ENABLE_IRI) */
-        url->host = NULL;
-      }
-      else
-        xfree (url->host);
+      xfree (url->host);
 
       xfree (url->path);
       xfree (url->url);
@@ -1236,7 +1247,7 @@ mkalldirs (const char *path)
 {
   const char *p;
   char *t;
-  struct_stat st;
+  struct stat st;
   int res;
 
   p = path + strlen (path);
@@ -1271,12 +1282,14 @@ 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;
 }
@@ -1536,11 +1549,11 @@ append_uri_pathel (const char *b, const char *e, bool escaped,
   append_null (dest);
 }
 
+#ifdef HAVE_ICONV
 static char *
 convert_fname (char *fname)
 {
   char *converted_fname = fname;
-#if HAVE_ICONV
   const char *from_encoding = opt.encoding_remote;
   const char *to_encoding = opt.locale;
   iconv_t cd;
@@ -1555,9 +1568,9 @@ convert_fname (char *fname)
     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));
+  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);
@@ -1566,51 +1579,62 @@ convert_fname (char *fname)
       done = 0;
 
       for (;;)
-	{
-	  if (iconv (cd, &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;
-	    }
+        {
+          errno = 0;
+          if (iconv (cd, (ICONV_CONST char **) &fname, &inlen, &s, &outlen) == 0
+              && iconv (cd, NULL, NULL, &s, &outlen) == 0)
+            {
+              *(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;
-	    }
-	}
+          /* Incomplete or invalid multibyte sequence */
+          if (errno == EINVAL || errno == EILSEQ || errno == 0)
+            {
+              if (errno)
+                logprintf (LOG_VERBOSE,
+                           _ ("Incomplete or invalid multibyte sequence encountered\n"));
+              else
+                logprintf (LOG_VERBOSE,
+                           _ ("Unconvertable 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));
+               orig_fname, from_encoding, to_encoding));
     }
 
     iconv_close(cd);
-#endif
 
   return converted_fname;
 }
+#else
+static char *
+convert_fname (char *fname)
+{
+  return fname;
+}
+#endif
 
 /* Append to DEST the directory structure that corresponds the
    directory part of URL's path.  For example, if the URL is
@@ -1726,6 +1750,9 @@ url_file_name (const struct url *u, char *replaced_filename)
         fname_len_check = concat_strings (u_file, FN_QUERY_SEP_STR, u->query, NULL);
       else
         fname_len_check = strdupdelim (u_file, u_file + strlen (u_file));
+
+      /* convert before concat with local path */
+      fname_len_check = convert_fname (fname_len_check);
     }
   else
     {
@@ -1787,8 +1814,6 @@ 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.
@@ -1800,7 +1825,7 @@ url_file_name (const struct url *u, char *replaced_filename)
      directory (see `mkalldirs' for explanation).  */
 
   if (ALLOW_CLOBBER
-      && !(file_exists_p (fname) && !file_non_directory_p (fname)))
+      && !(file_exists_p (fname, NULL) && !file_non_directory_p (fname)))
     {
       unique = fname;
     }

src/url.h

@@ -99,10 +99,6 @@ struct url
   /* Username and password (unquoted). */
   char *user;
   char *passwd;
-
-  /* 'host' is allocated by idna_to_ascii_8z() via idn_encode().
-   * Call 'idn_free()' to free this memory. */
-  bool idn_allocated;
 };
 
 /* Function declarations */
@@ -124,6 +120,7 @@ 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 *);

src/utils.c

@@ -45,6 +45,7 @@ as that of the covered work.  */
 #include <assert.h>
 #include <stdarg.h>
 #include <locale.h>
+#include <errno.h>
 
 #if HAVE_UTIME
 # include <sys/types.h>
@@ -113,7 +114,7 @@ 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
@@ -235,14 +236,20 @@ 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
@@ -292,13 +299,6 @@ 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, ...)
 {
@@ -318,6 +318,13 @@ 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;
@@ -567,7 +574,7 @@ 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))
     {
@@ -580,21 +587,42 @@ remove_link (const char *file)
   return err;
 }
 
-/* Does FILENAME exist?  This is quite a lousy implementation, since
-   it supplies no error codes -- only a yes-or-no answer.  Thus it
-   will return that a file does not exist if, e.g., the directory is
-   unreadable.  I don't mind it too much currently, though.  The
-   proper way should, of course, be to have a third, error state,
-   other than true/false, but that would introduce uncalled-for
-   additional complexity to the callers.  */
+/* Does FILENAME exist? */
 bool
-file_exists_p (const char *filename)
+file_exists_p (const char *filename, file_stats_t *fstats)
 {
-#ifdef HAVE_ACCESS
-  return access (filename, F_OK) >= 0;
+  struct stat buf;
+
+#if defined(WINDOWS) || defined(__VMS)
+    int ret = stat (filename, &buf);
+    if (ret >= 0)
+    {
+      if (fstats != NULL)
+        fstats->access_err = errno;
+    }
+    return ret >= 0;
 #else
-  struct_stat buf;
-  return stat (filename, &buf) >= 0;
+  errno = 0;
+  if (stat (filename, &buf) == 0 && S_ISREG(buf.st_mode) &&
+              (((S_IRUSR & buf.st_mode) && (getuid() == buf.st_uid))  ||
+               ((S_IRGRP & buf.st_mode) && group_member(buf.st_gid))  ||
+                (S_IROTH & buf.st_mode))) {
+    if (fstats != NULL)
+    {
+      fstats->access_err = 0;
+      fstats->st_ino = buf.st_ino;
+      fstats->st_dev = buf.st_dev;
+    }
+    return true;
+  }
+  else
+  {
+    if (fstats != NULL)
+      fstats->access_err = (errno == 0 ? EACCES : errno);
+    errno = 0;
+    return false;
+  }
+  /* NOTREACHED */
 #endif
 }
 
@@ -603,7 +631,7 @@ 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)
@@ -630,7 +658,7 @@ 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;
@@ -662,7 +690,7 @@ unique_name_1 (const char *prefix)
 
   do
     number_to_string (template_tail, count++);
-  while (file_exists_p (template));
+  while (file_exists_p (template, NULL));
 
   return xstrdup (template);
 }
@@ -690,7 +718,7 @@ unique_name (const char *file, bool allow_passthrough)
 {
   /* If the FILE itself doesn't exist, return it without
      modification. */
-  if (!file_exists_p (file))
+  if (!file_exists_p (file, NULL))
     return allow_passthrough ? (char *)file : xstrdup (file);
 
   /* Otherwise, find a numeric suffix that results in unused file name
@@ -819,7 +847,7 @@ fopen_excl (const char *fname, int binary)
   /* Manually check whether the file exists.  This is prone to race
      conditions, but systems without O_EXCL haven't deserved
      better.  */
-  if (file_exists_p (fname))
+  if (file_exists_p (fname, NULL))
     {
       errno = EEXIST;
       return NULL;
@@ -828,6 +856,113 @@ fopen_excl (const char *fname, int binary)
 #endif /* not O_EXCL */
 }
 
+/* fopen_stat() assumes that file_exists_p() was called earlier.
+   file_stats_t passed to this function was returned from file_exists_p()
+   This is to prevent TOCTTOU race condition.
+   Details : FIO45-C from https://www.securecoding.cert.org/
+   Note that for creating a new file, this check is not useful
+
+   Input:
+     fname  => Name of file to open
+     mode   => File open mode
+     fstats => Saved file_stats_t about file that was checked for existence
+
+   Returns:
+     NULL if there was an error
+     FILE * of opened file stream
+*/
+FILE *
+fopen_stat(const char *fname, const char *mode, file_stats_t *fstats)
+{
+  int fd;
+  FILE *fp;
+  struct stat fdstats;
+
+  fp = fopen (fname, mode);
+  if (fp == NULL)
+  {
+    logprintf (LOG_NOTQUIET, _("Failed to Fopen file %s\n"), fname);
+    return NULL;
+  }
+  fd = fileno (fp);
+  if (fd < 0)
+  {
+    logprintf (LOG_NOTQUIET, _("Failed to get FD for file %s\n"), fname);
+    fclose (fp);
+    return NULL;
+  }
+  memset(&fdstats, 0, sizeof(fdstats));
+  if (fstat (fd, &fdstats) == -1)
+  {
+    logprintf (LOG_NOTQUIET, _("Failed to stat file %s, (check permissions)\n"), fname);
+    fclose (fp);
+    return NULL;
+  }
+#if !(defined(WINDOWS) || defined(__VMS))
+  if (fstats != NULL &&
+      (fdstats.st_dev != fstats->st_dev ||
+       fdstats.st_ino != fstats->st_ino))
+  {
+    /* File changed since file_exists_p() : NOT SAFE */
+    logprintf (LOG_NOTQUIET, _("File %s changed since the last check. Security check failed."), fname);
+    fclose (fp);
+    return NULL;
+  }
+#endif
+
+  return fp;
+}
+
+/* open_stat assumes that file_exists_p() was called earlier to save file_stats
+   file_stats_t passed to this function was returned from file_exists_p()
+   This is to prevent TOCTTOU race condition.
+   Details : FIO45-C from https://www.securecoding.cert.org/
+   Note that for creating a new file, this check is not useful
+
+
+   Input:
+     fname  => Name of file to open
+     flags  => File open flags
+     mode   => File open mode
+     fstats => Saved file_stats_t about file that was checked for existence
+
+   Returns:
+     -1 if there was an error
+     file descriptor of opened file stream
+*/
+int
+open_stat(const char *fname, int flags, mode_t mode, file_stats_t *fstats)
+{
+  int fd;
+  struct stat fdstats;
+
+  fd = open (fname, flags, mode);
+  if (fd < 0)
+  {
+    logprintf (LOG_NOTQUIET, _("Failed to open file %s, reason :%s\n"), fname, strerror(errno));
+    return -1;
+  }
+  memset(&fdstats, 0, sizeof(fdstats));
+  if (fstat (fd, &fdstats) == -1)
+  {
+    logprintf (LOG_NOTQUIET, _("Failed to stat file %s, error: %s\n"), fname, strerror(errno));
+    return -1;
+  }
+#if !(defined(WINDOWS) || defined(__VMS))
+  if (fstats != NULL &&
+      (fdstats.st_dev != fstats->st_dev ||
+       fdstats.st_ino != fstats->st_ino))
+  {
+    /* File changed since file_exists_p() : NOT SAFE */
+    logprintf (LOG_NOTQUIET, _("Trying to open file %s but it changed since last check. Security check failed."), fname);
+    close (fd);
+    return -1;
+  }
+#endif
+
+  return fd;
+}
+
 /* Create DIRECTORY.  If some of the pathname components of DIRECTORY
    are missing, create them first.  In case any mkdir() call fails,
    return its error status.  Returns 0 on successful completion.
@@ -856,7 +991,7 @@ make_directory (const char *directory)
       /* Check whether the directory already exists.  Allow creation of
          of intermediate directories to fail, as the initial path components
          are not necessarily directories!  */
-      if (!file_exists_p (dir))
+      if (!file_exists_p (dir, NULL))
         ret = mkdir (dir, 0777);
       else
         ret = 0;
@@ -1184,7 +1319,7 @@ 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;
@@ -1327,7 +1462,7 @@ 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;
@@ -1600,7 +1735,7 @@ numdigit (wgint number)
 {
   int cnt = 1;
   if (number < 0)
-    ++cnt;                      /* accomodate '-' */
+    ++cnt;                      /* accommodate '-' */
   while ((number /= 10) != 0)
     ++cnt;
   return cnt;
@@ -1930,7 +2065,7 @@ 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);
@@ -2045,13 +2180,16 @@ 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);
 
@@ -2140,7 +2278,7 @@ 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] = {
@@ -2197,7 +2335,7 @@ base64_encode (const void *data, size_t length, char *dest)
 
 /* Decode data from BASE64 (a null-terminated string) into memory
    pointed to by DEST.  DEST is assumed to be large enough to
-   accomodate the decoded data, which is guaranteed to be no more than
+   accommodate the decoded data, which is guaranteed to be no more than
    3/4*strlen(base64).
 
    Since DEST is assumed to contain binary data, it is not
@@ -2208,7 +2346,7 @@ 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, size_t size)
 {
   /* Table of base64 values for first 128 characters.  Note that this
      assumes ASCII (but so does Wget in other places).  */
@@ -2232,7 +2370,8 @@ base64_decode (const char *base64, void *dest)
 #define IS_BASE64(c) ((IS_ASCII (c) && BASE64_CHAR_TO_VALUE (c) >= 0) || c == '=')
 
   const char *p = base64;
-  char *q = dest;
+  unsigned char *q = dest;
+  ssize_t n = 0;
 
   while (1)
     {
@@ -2254,7 +2393,12 @@ base64_decode (const char *base64, void *dest)
       if (c == '=' || !IS_BASE64 (c))
         return -1;              /* illegal char while decoding base64 */
       value |= BASE64_CHAR_TO_VALUE (c) << 12;
-      *q++ = value >> 16;
+      if (size)
+        {
+          *q++ = value >> 16;
+          size--;
+        }
+      n++;
 
       /* Process third byte of a quadruplet.  */
       NEXT_CHAR (c, p);
@@ -2274,7 +2418,12 @@ base64_decode (const char *base64, void *dest)
         }
 
       value |= BASE64_CHAR_TO_VALUE (c) << 6;
-      *q++ = 0xff & value >> 8;
+      if (size)
+        {
+          *q++ = 0xff & value >> 8;
+          size--;
+        }
+      n++;
 
       /* Process fourth byte of a quadruplet.  */
       NEXT_CHAR (c, p);
@@ -2286,12 +2435,17 @@ base64_decode (const char *base64, void *dest)
         return -1;              /* illegal char while decoding base64 */
 
       value |= BASE64_CHAR_TO_VALUE (c);
-      *q++ = 0xff & value;
+      if (size)
+        {
+          *q++ = 0xff & value;
+          size--;
+        }
+      n++;
     }
 #undef IS_BASE64
 #undef BASE64_CHAR_TO_VALUE
 
-  return q - (char *) dest;
+  return n;
 }
 
 #ifdef HAVE_LIBPCRE
@@ -2413,17 +2567,17 @@ 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);
     }
 }
 
@@ -2524,7 +2678,7 @@ wg_hex_to_string (char *str_buffer, const char *hex_buffer, size_t hex_len)
   for (i = 0; i < hex_len; i++)
     {
       /* Each byte takes 2 characters.  */
-      sprintf (str_buffer + 2 * i, "%02x", hex_buffer[i] & 0xFF);
+      sprintf (str_buffer + 2 * i, "%02x", (unsigned) (hex_buffer[i] & 0xFF));
     }
 
   /* Null-terminate result.  */
@@ -2588,7 +2742,7 @@ wg_pubkey_pem_to_der (const char *pem, unsigned char **der, size_t *der_len)
 
   base64data = xmalloc (BASE64_LENGTH(stripped_pem_count));
 
-  size = base64_decode (stripped_pem, base64data);
+  size = wget_base64_decode (stripped_pem, base64data, BASE64_LENGTH(stripped_pem_count));
 
   if (size < 0) {
     xfree (base64data);           /* malformed base64 from server */
@@ -2627,54 +2781,65 @@ wg_pin_peer_pubkey (const char *pinnedpubkey, const char *pubkey, size_t pubkeyl
     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);
+  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);
 
-    /* it starts with sha256//, copy so we can modify it */
-    pinkeylen = strlen (pinnedpubkey) + 1;
-    pinkeycopy = xmalloc (pinkeylen);
-    memcpy (pinkeycopy, pinnedpubkey, pinkeylen);
+      /* 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';
+      /* 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 = 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;
+          /* decode base64 pinnedpubkey, 8 is length of "sha256//" */
+          decoded_hash_length = wget_base64_decode (begin_pos + 8, expectedsha256sumdigest, SHA256_DIGEST_SIZE);
+
+          /* if valid base64, compare sha256 digests directly */
+          if (SHA256_DIGEST_SIZE == decoded_hash_length)
+            {
+              if (!memcmp (sha256sumdigest, expectedsha256sumdigest, SHA256_DIGEST_SIZE))
+                {
+                  result = true;
+                  break;
+                }
+            }
+          else
+            logprintf (LOG_VERBOSE, _ ("Skipping key with wrong size (%d/%d): %s\n"),
+                       (strlen (begin_pos + 8) * 3) / 4, SHA256_DIGEST_SIZE,
+                       quote (begin_pos + 8));
+
+          /*
+           * 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);
 
-        /*
-         * 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);
 
-    xfree (sha256sumdigest);
-    xfree (expectedsha256sumdigest);
-    xfree (pinkeycopy);
-
-    return result;
-  }
+      return result;
+    }
 
   /* fall back to assuming this is a file path */
   fm = wget_read_file (pinnedpubkey);
@@ -2694,11 +2859,12 @@ wg_pin_peer_pubkey (const char *pinnedpubkey, const char *pubkey, size_t pubkeyl
     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;
-  }
+  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
@@ -2720,7 +2886,7 @@ wg_pin_peer_pubkey (const char *pinnedpubkey, const char *pubkey, size_t pubkeyl
   if (pubkeylen == pem_len && !memcmp (pubkey, pem_ptr, pubkeylen))
     result = true;
 
- cleanup:
+cleanup:
   xfree (buf);
   xfree (pem_ptr);
   wget_read_file_free (fm);

src/utils.h

@@ -78,15 +78,23 @@ void fork_to_background (void);
 char *aprintf (const char *, ...) GCC_FORMAT_ATTR (1, 2);
 char *concat_strings (const char *, ...);
 
+typedef struct file_stat_s {
+  int access_err;               /* Error in accecssing file : Not present vs permission */
+  ino_t st_ino;                 /* st_ino from stats() on the file before open() */
+  dev_t st_dev;                 /* st_dev from stats() on the file before open() */
+} file_stats_t;
+
 void touch (const char *, time_t);
 int remove_link (const char *);
-bool file_exists_p (const char *);
+bool file_exists_p (const char *, file_stats_t *);
 bool file_non_directory_p (const char *);
 wgint file_size (const char *);
 int make_directory (const char *);
 char *unique_name (const char *, bool);
 FILE *unique_create (const char *, bool, char **);
 FILE *fopen_excl (const char *, int);
+FILE *fopen_stat (const char *, const char *, file_stats_t *);
+int   open_stat  (const char *, int, mode_t, file_stats_t *);
 char *file_merge (const char *, const char *);
 
 int fnmatch_nocase (const char *, const char *, int);
@@ -140,8 +148,8 @@ 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 *, size_t);
 
 #ifdef HAVE_LIBPCRE
 void *compile_pcre_regex (const char *);

src/warc.c

@@ -32,6 +32,7 @@ as that of the covered work.  */
 #include "utils.h"
 #include "version.h"
 #include "dirname.h"
+#include "url.h"
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -1365,6 +1366,8 @@ warc_write_cdx_record (const char *url, const char *timestamp_str,
     mime_type = "-";
   if (redirect_location == NULL || strlen(redirect_location) == 0)
     redirect_location = "-";
+  else
+    redirect_location = url_escape(redirect_location);
 
   number_to_string (offset_string, offset);
 
@@ -1413,7 +1416,7 @@ warc_write_revisit_record (const char *url, const char *timestamp_str,
   warc_write_header ("WARC-Refers-To", refers_to);
   warc_write_header ("WARC-Profile", "http://netpreserve.org/warc/1.0/revisit/identical-payload-digest");
   warc_write_header ("WARC-Truncated", "length");
-  warc_write_header ("WARC-Target-URI", url);
+  warc_write_header_uri ("WARC-Target-URI", url);
   warc_write_date_header (timestamp_str);
   warc_write_ip_header (ip);
   warc_write_header ("Content-Type", "application/http;msgtype=response");
@@ -1505,7 +1508,7 @@ warc_write_response_record (const char *url, const char *timestamp_str,
   warc_write_header ("WARC-Record-ID", response_uuid);
   warc_write_header ("WARC-Warcinfo-ID", warc_current_warcinfo_uuid_str);
   warc_write_header ("WARC-Concurrent-To", concurrent_to_uuid);
-  warc_write_header ("WARC-Target-URI", url);
+  warc_write_header_uri ("WARC-Target-URI", url);
   warc_write_date_header (timestamp_str);
   warc_write_ip_header (ip);
   warc_write_header ("WARC-Block-Digest", block_digest);
@@ -1562,7 +1565,7 @@ warc_write_record (const char *record_type, const char *resource_uuid,
   warc_write_header ("WARC-Record-ID", resource_uuid);
   warc_write_header ("WARC-Warcinfo-ID", warc_current_warcinfo_uuid_str);
   warc_write_header ("WARC-Concurrent-To", concurrent_to_uuid);
-  warc_write_header ("WARC-Target-URI", url);
+  warc_write_header_uri ("WARC-Target-URI", url);
   warc_write_date_header (timestamp_str);
   warc_write_ip_header (ip);
   warc_write_digest_headers (body, payload_offset);

src/wget.h

@@ -361,7 +361,8 @@ typedef enum
   TIMECONV_ERR,
   METALINK_PARSE_ERROR, METALINK_RETR_ERROR,
   METALINK_CHKSUM_ERROR, METALINK_SIG_ERROR, METALINK_MISSING_RESOURCE,
-  RETR_WITH_METALINK
+  RETR_WITH_METALINK,
+  METALINK_SIZE_ERROR
 } uerr_t;
 
 /* 2005-02-19 SMS.

src/xattr.c

@@ -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;
+}

src/xattr.h

@@ -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 */

testenv/Makefile.am

@@ -27,8 +27,38 @@
 
 
 if METALINK_IS_ENABLED
-  METALINK_TESTS = Test-metalink-xml.py             \
-    Test-metalink-http.py
+  METALINK_TESTS = Test-metalink-http.py            \
+    Test-metalink-http-quoted.py                    \
+    Test-metalink-http-baddigest.py                 \
+    Test-metalink-http-xml.py                       \
+    Test-metalink-http-xml-trust.py                 \
+    Test-metalink-http-xml-trust-name.py            \
+    Test-metalink-http-xml-type.py                  \
+    Test-metalink-http-xml-type-trust.py            \
+    Test-metalink-http-xml-type-content.py          \
+    Test-metalink-http-xml-type-trust-content.py    \
+    Test-metalink-xml.py                            \
+    Test-metalink-xml-continue.py                   \
+    Test-metalink-xml-relpath.py                    \
+    Test-metalink-xml-abspath.py                    \
+    Test-metalink-xml-homepath.py                   \
+    Test-metalink-xml-trust.py                      \
+    Test-metalink-xml-relpath-trust.py              \
+    Test-metalink-xml-abspath-trust.py              \
+    Test-metalink-xml-homepath-trust.py             \
+    Test-metalink-xml-prefix.py                     \
+    Test-metalink-xml-relprefix.py                  \
+    Test-metalink-xml-absprefix.py                  \
+    Test-metalink-xml-homeprefix.py                 \
+    Test-metalink-xml-prefix-trust.py               \
+    Test-metalink-xml-relprefix-trust.py            \
+    Test-metalink-xml-absprefix-trust.py            \
+    Test-metalink-xml-homeprefix-trust.py           \
+    Test-metalink-xml-emptyprefix-trust.py          \
+    Test-metalink-xml-size.py                       \
+    Test-metalink-xml-nohash.py                     \
+    Test-metalink-xml-nourls.py                     \
+    Test-metalink-xml-urlbreak.py
 else
   METALINK_TESTS =
 endif
@@ -42,8 +72,13 @@ if WITH_SSL
 endif
 
 if HAVE_PYTHON3
-  TESTS = Test-auth-basic-fail.py                   \
+  TESTS = Test-504.py                               \
+    Test-auth-basic-fail.py                         \
     Test-auth-basic.py                              \
+    Test-auth-basic-netrc.py                        \
+    Test-auth-basic-netrc-user-given.py             \
+    Test-auth-basic-netrc-pass-given.py             \
+    Test-auth-basic-no-netrc-fail.py                \
     Test-auth-both.py                               \
     Test-auth-digest.py                             \
     Test-auth-no-challenge.py                       \
@@ -51,6 +86,7 @@ if HAVE_PYTHON3
     Test-auth-retcode.py                            \
     Test-auth-with-content-disposition.py           \
     Test-c-full.py                                  \
+    Test-condget.py                                 \
     Test-Content-disposition-2.py                   \
     Test-Content-disposition.py                     \
     Test--convert-links--content-on-error.py        \
@@ -59,24 +95,26 @@ if HAVE_PYTHON3
     Test-cookie-expires.py                          \
     Test-cookie.py                                  \
     Test-Head.py                                    \
+    Test-hsts.py                                    \
     Test--https.py                                  \
     Test--https-crl.py                              \
     Test-missing-scheme-retval.py                   \
+    Test-O.py                                       \
     Test-pinnedpubkey-der-https.py                  \
     Test-pinnedpubkey-der-no-check-https.py         \
     Test-pinnedpubkey-hash-https.py                 \
     Test-pinnedpubkey-hash-no-check-fail-https.py   \
     Test-pinnedpubkey-pem-fail-https.py             \
     Test-pinnedpubkey-pem-https.py                  \
-    Test-hsts.py                                    \
-    Test-O.py                                       \
     Test-Post.py                                    \
-    Test-504.py                                     \
-    Test--spider-r.py                               \
-    Test--rejected-log.py                           \
+    Test-recursive-basic.py                         \
+    Test-recursive-include.py                       \
+    Test-recursive-redirect.py                      \
+    Test-redirect.py                                \
     Test-redirect-crash.py                          \
+    Test--rejected-log.py                           \
     Test-reserved-chars.py                          \
-    Test-condget.py                                 \
+    Test--spider-r.py                               \
     $(METALINK_TESTS)
 
 endif

testenv/README

@@ -4,7 +4,7 @@ Install Instructions:
 ================================================================================
 
 This Test Suite exploits the Parallel Test Harness available in GNU Autotools.
-Since it uses features from a relatively recent verion of Autotools, the minimum
+Since it uses features from a relatively recent version of Autotools, the minimum
 required version as been bumped up to 1.11.
 Run the './configure' command to generate the Makefile and then run 'make check'
 to execute the Test Suite. Use the '-j n' option with 'make check' to execute
@@ -43,7 +43,8 @@ Working:
 ================================================================================
 
 The Test Files are valid Python scripts and the default mask for them is 755.
-A singular Test must be invoked in the following manner:
+A singular Test must be invoked in the following manner, with the current
+directory being the testenv directory:
 $ ./python3 <Name of Test File>      OR
 $ ./<Name of Test File>
 The script will then initialize the various elements and pass them to an object
@@ -117,12 +118,11 @@ from misc.wget_file import WgetFile
 
 It is recommended that a small description of the Test Case is provided next.
 This would be very helpful to future contributors.
-Next, is the const variable, TEST_NAME that defines the name of the Test.
 
 Each File in the Test must be represented as a WgetFile object. The WgetFile
 Class has the following prototype:
 WgetFile (str name, str contents, str timestamp, dict rules)
-None except name is a mandatory paramter, one may pass only those parameters
+None except name is a mandatory parameter, one may pass only those parameters
 that are required by the File object.
 
 The timestamp string should be in a format: "YYYY-MM-DD HH:MM:SS" in UTC zone.
@@ -130,14 +130,15 @@ The rules object is a dictionary element, with the key as the Rule Name and
 value as the Rule Data. In most cases, the Rule Data is another dictionary.
 
 Various variables used consistently across all tests are:
-    * WGET_OPTIONS: The command line string passed to Wget upon invokation. This
+    * WGET_OPTIONS: The command line string passed to Wget upon invocation. This
     string may contain URLs, like in the case where in-URL authentication is
     used. Variable names passed like {{var_name}} will be replaced by the
     contents of the variable self.var_name before being passed to Wget
     * WGET_URLS: This is a list of filenames which will be appended as the URLs
-    to Wget during invokation. This is a list of lists, where WGET_URLS[0]
+    to Wget during invocation. This is a list of lists, where WGET_URLS[0]
     represents the list of Filenames called from Server[0], WGET_URLS[1] is a
-    list of files downloaded from Server[2], etc.
+    list of files downloaded from Server[2], etc.  They must be relative URLs,
+    i.e., not start with "/".
     * Files: This variable defines the files that exist in the Server's
     filesystem. The Files variable is a list of lists of WgetFile objects.
     This means that File[0] is a list of WgetFile objects that lie on Server[0],
@@ -154,13 +155,11 @@ Various variables used consistently across all tests are:
 
 Both, the HTTPTest and FTPTest modules have the same prototype:
 {
-    name,
     pre_hook,
     test_options,
     post_hook,
     protocols
 }
-name should be a string, and is usually passed to the TEST_NAME variable,
 the three hooks should be Python dict objects and protocols should be a list of
 protocols, like [HTTP, HTTPS].
 
@@ -215,7 +214,7 @@ executed. The currently supported options are:
     download. The complete URL will be created and passed to Wget
     automatically. (alias URLs)
     * WgetCommands  : A string consisting of the various commandline switches
-    sent to Wget upon invokation. Any data placed between {{ }} in this string
+    sent to Wget upon invocation. Any data placed between {{ }} in this string
     will be replaced with the contents of self.<data> before being passed to
     Wget. This is particularly useful for getting the hostname and port for a
     file. While all Download URL's are passed to Urls, a notable exception is
@@ -281,13 +280,6 @@ red-flagged as a XPASS. Currently, tests expected to fail under valgrind are not
 explicitly marked as XFAIL. Tests failing under valgrind must always be
 considered a blocking error.
 
-Remember to always name the Test correctly using the TEST_NAME variable. This
-is essential since a directory with the Test Name is created and this can
-cause synchronization problems when the Parallel Test Harness is used.
-One can use the following command on Unix systems to check for TEST_NAME
-clashes:
-$ grep -r -h "TEST_NAME =" | cut -c13- | uniq -c -d
-
 Work Remaining:
 ================================================================================
 
@@ -296,7 +288,7 @@ Some amount of work still remains to be done.
     * Support parallel-wget branch
         * Support to spawn multiple servers is already in place. Need to handle
         multiple requests to a server simultaneously. Use THreading MixIn.
-    * SSL Tests. Use xyne's HTTPS server implemention
+    * SSL Tests. Use xyne's HTTPS server implementation
     * Complete support for FTP Tests
     * IRI Support. This shouldn't require much effort
 

testenv/Test--rejected-log.py

@@ -14,7 +14,7 @@ mainpage = """
 </head>
 <body>
   <p>
-    Recurse to a <a href="http://127.0.0.1:{{port}}/secondpage.html">second page</a>.
+    Recurse to a <a href="http://localhost:{{port}}/secondpage.html">second page</a>.
   </p>
 </body>
 </html>
@@ -27,8 +27,8 @@ secondpage = """
 </head>
 <body>
   <p>
-    Recurse to a <a href="http://127.0.0.1:{{port}}/thirdpage.html">third page</a>.
-    Try the blacklisted <a href="http://127.0.0.1:{{port}}/index.html">main page</a>.
+    Recurse to a <a href="http://localhost:{{port}}/thirdpage.html">third page</a>.
+    Try the blacklisted <a href="http://localhost:{{port}}/index.html">main page</a>.
   </p>
 </body>
 </html>
@@ -41,7 +41,7 @@ thirdpage = """
 </head>
 <body>
   <p>
-    Try a hidden <a href="http://127.0.0.1:{{port}}/dummy.txt">dummy file</a>.
+    Try a hidden <a href="http://localhost:{{port}}/dummy.txt">dummy file</a>.
     Try to leave to <a href="http://no.such.domain/">another domain</a>.
   </p>
 </body>
@@ -55,9 +55,9 @@ Disallow: /dummy.txt
 
 log = """\
 REASON\tU_URL\tU_SCHEME\tU_HOST\tU_PORT\tU_PATH\tU_PARAMS\tU_QUERY\tU_FRAGMENT\tP_URL\tP_SCHEME\tP_HOST\tP_PORT\tP_PATH\tP_PARAMS\tP_QUERY\tP_FRAGMENT
-BLACKLIST\thttp%3A//127.0.0.1%3A{{port}}/index.html\tSCHEME_HTTP\t127.0.0.1\t{{port}}\tindex.html\t\t\t\thttp%3A//127.0.0.1%3A{{port}}/secondpage.html\tSCHEME_HTTP\t127.0.0.1\t{{port}}\tsecondpage.html\t\t\t
-ROBOTS\thttp%3A//127.0.0.1%3A{{port}}/dummy.txt\tSCHEME_HTTP\t127.0.0.1\t{{port}}\tdummy.txt\t\t\t\thttp%3A//127.0.0.1%3A{{port}}/thirdpage.html\tSCHEME_HTTP\t127.0.0.1\t{{port}}\tthirdpage.html\t\t\t
-SPANNEDHOST\thttp%3A//no.such.domain/\tSCHEME_HTTP\tno.such.domain\t80\t\t\t\t\thttp%3A//127.0.0.1%3A{{port}}/thirdpage.html\tSCHEME_HTTP\t127.0.0.1\t{{port}}\tthirdpage.html\t\t\t
+BLACKLIST\thttp%3A//localhost%3A{{port}}/index.html\tSCHEME_HTTP\tlocalhost\t{{port}}\tindex.html\t\t\t\thttp%3A//localhost%3A{{port}}/secondpage.html\tSCHEME_HTTP\tlocalhost\t{{port}}\tsecondpage.html\t\t\t
+ROBOTS\thttp%3A//localhost%3A{{port}}/dummy.txt\tSCHEME_HTTP\tlocalhost\t{{port}}\tdummy.txt\t\t\t\thttp%3A//localhost%3A{{port}}/thirdpage.html\tSCHEME_HTTP\tlocalhost\t{{port}}\tthirdpage.html\t\t\t
+SPANNEDHOST\thttp%3A//no.such.domain/\tSCHEME_HTTP\tno.such.domain\t80\t\t\t\t\thttp%3A//localhost%3A{{port}}/thirdpage.html\tSCHEME_HTTP\tlocalhost\t{{port}}\tthirdpage.html\t\t\t
 """
 
 dummyfile = "Don't care."

testenv/Test--spider-r.py

@@ -14,8 +14,8 @@ mainpage = """
 </head>
 <body>
   <p>
-    Some text and a link to a <a href="http://127.0.0.1:{{port}}/secondpage.html">second page</a>.
-    Also, a <a href="http://127.0.0.1:{{port}}/nonexistent">broken link</a>.
+    Some text and a link to a <a href="http://localhost:{{port}}/secondpage.html">second page</a>.
+    Also, a <a href="http://localhost:{{port}}/nonexistent">broken link</a>.
   </p>
 </body>
 </html>
@@ -29,8 +29,8 @@ secondpage = """
 </head>
 <body>
   <p>
-    Some text and a link to a <a href="http://127.0.0.1:{{port}}/thirdpage.html">third page</a>.
-    Also, a <a href="http://127.0.0.1:{{port}}/nonexistent">broken link</a>.
+    Some text and a link to a <a href="http://localhost:{{port}}/thirdpage.html">third page</a>.
+    Also, a <a href="http://localhost:{{port}}/nonexistent">broken link</a>.
   </p>
 </body>
 </html>
@@ -43,8 +43,8 @@ thirdpage = """
 </head>
 <body>
   <p>
-    Some text and a link to a <a href="http://127.0.0.1:{{port}}/dummy.txt">text file</a>.
-    Also, another <a href="http://127.0.0.1:{{port}}/againnonexistent">broken link</a>.
+    Some text and a link to a <a href="http://localhost:{{port}}/dummy.txt">text file</a>.
+    Also, another <a href="http://localhost:{{port}}/againnonexistent">broken link</a>.
   </p>
 </body>
 </html>

testenv/Test-Proto.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 from sys import exit
 from test.http_test import HTTPTest
-from misc.constants import HTTP, HTTPS
+from test.base_test import HTTP, HTTPS
 from misc.wget_file import WgetFile
 
 """

testenv/Test-auth-basic-netrc-pass-given.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+
+"""
+    This test ensures Wget uses credentials from .netrc for Basic Authorization Negotiation.
+    In this case we test that .netrc credentials are used in case only
+    password is given on the command line.
+    Also, we ensure that Wget saves the host after a successful auth and
+    doesn't wait for a challenge the second time.
+"""
+############# File Definitions ###############################################
+File1 = "I am an invisble man."
+File2 = "I too am an invisible man."
+
+User = "Sauron"
+Password = "TheEye"
+
+File1_rules = {
+    "Authentication"    : {
+        "Type"          : "Basic",
+        "User"          : User,
+        "Pass"          : Password
+    }
+}
+File2_rules = {
+    "ExpectHeader"      : {
+        "Authorization" : "Basic U2F1cm9uOlRoZUV5ZQ=="
+    }
+}
+
+Netrc = "machine localhost\n\tlogin {0}".format(User)
+
+A_File = WgetFile ("File1", File1, rules=File1_rules)
+B_File = WgetFile ("File2", File2, rules=File2_rules)
+Netrc_File = WgetFile (".netrc", Netrc)
+
+WGET_OPTIONS = "--password={0}".format(Password)
+WGET_URLS = [["File1", "File2"]]
+
+Files = [[A_File, B_File]]
+LocalFiles = [Netrc_File]
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [A_File, B_File, Netrc_File]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : LocalFiles
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode
+}
+
+err = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+).begin ()
+
+exit (err)

testenv/Test-auth-basic-netrc-user-given.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+
+"""
+    This test ensures Wget uses credentials from .netrc for Basic Authorization Negotiation.
+    In this case we test that .netrc credentials are used in case only
+    user login is given on the command line.
+    Also, we ensure that Wget saves the host after a successful auth and
+    doesn't wait for a challenge the second time.
+"""
+############# File Definitions ###############################################
+File1 = "I am an invisble man."
+File2 = "I too am an invisible man."
+
+User = "Sauron"
+Password = "TheEye"
+
+File1_rules = {
+    "Authentication"    : {
+        "Type"          : "Basic",
+        "User"          : User,
+        "Pass"          : Password
+    }
+}
+File2_rules = {
+    "ExpectHeader"      : {
+        "Authorization" : "Basic U2F1cm9uOlRoZUV5ZQ=="
+    }
+}
+
+Netrc = "machine localhost\n\tlogin {0}\n\tpassword {1}".format(User, Password)
+
+A_File = WgetFile ("File1", File1, rules=File1_rules)
+B_File = WgetFile ("File2", File2, rules=File2_rules)
+Netrc_File = WgetFile (".netrc", Netrc)
+
+WGET_OPTIONS = "--user={0}".format(User)
+WGET_URLS = [["File1", "File2"]]
+
+Files = [[A_File, B_File]]
+LocalFiles = [Netrc_File]
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [A_File, B_File, Netrc_File]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : LocalFiles
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode
+}
+
+err = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+).begin ()
+
+exit (err)

testenv/Test-auth-basic-netrc.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+
+"""
+    This test ensures Wget uses credentials from .netrc for Basic Authorization Negotiation.
+    In this case we test that .netrc credentials are used in case no user
+    login and no password is given on the command line.
+    Also, we ensure that Wget saves the host after a successful auth and
+    doesn't wait for a challenge the second time.
+"""
+############# File Definitions ###############################################
+File1 = "I am an invisble man."
+File2 = "I too am an invisible man."
+
+User = "Sauron"
+Password = "TheEye"
+
+File1_rules = {
+    "Authentication"    : {
+        "Type"          : "Basic",
+        "User"          : User,
+        "Pass"          : Password
+    }
+}
+File2_rules = {
+    "ExpectHeader"      : {
+        "Authorization" : "Basic U2F1cm9uOlRoZUV5ZQ=="
+    }
+}
+
+Netrc = "machine localhost\n\tlogin {0}\n\tpassword {1}".format(User, Password)
+
+A_File = WgetFile ("File1", File1, rules=File1_rules)
+B_File = WgetFile ("File2", File2, rules=File2_rules)
+Netrc_File = WgetFile (".netrc", Netrc)
+
+WGET_URLS = [["File1", "File2"]]
+
+Files = [[A_File, B_File]]
+LocalFiles = [Netrc_File]
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [A_File, B_File, Netrc_File]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : LocalFiles
+}
+test_options = {
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode
+}
+
+err = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+).begin ()
+
+exit (err)

testenv/Test-auth-basic-no-netrc-fail.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+
+"""
+    This test ensures that Wget will not use credentials from .netrc
+    when --no-netrc option is specified and Basic authentication is required
+    and fails.
+"""
+############# File Definitions ###############################################
+File1 = "I am an invisble man."
+
+User = "Sauron"
+Password = "TheEye"
+
+File1_rules = {
+    "Authentication"    : {
+        "Type"          : "Basic",
+        "User"          : User,
+        "Pass"          : Password
+    }
+}
+
+Netrc = "machine 127.0.0.1\n\tlogin {0}\n\tpassword {1}".format(User, Password)
+
+A_File = WgetFile ("File1", File1, rules=File1_rules)
+Netrc_File = WgetFile (".netrc", Netrc)
+
+WGET_OPTIONS = "--no-netrc"
+WGET_URLS = [["File1"]]
+
+Files = [[A_File]]
+LocalFiles = [Netrc_File]
+
+ExpectedReturnCode = 6
+ExpectedDownloadedFiles = [Netrc_File]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : LocalFiles
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode
+}
+
+err = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+).begin ()
+
+exit (err)

testenv/Test-auth-basic.py

@@ -5,7 +5,7 @@ from misc.wget_file import WgetFile
 
 """
     This test ensures Wget's Basic Authorization Negotiation.
-    Also, we ensure that Wget saves the host after a successfull auth and
+    Also, we ensure that Wget saves the host after a successful auth and
     doesn't wait for a challenge the second time.
 """
 ############# File Definitions ###############################################

testenv/Test-auth-both.py

@@ -5,7 +5,7 @@ from misc.wget_file import WgetFile
 
 """
     This test ensures Wget's Basic Authorization Negotiation.
-    Also, we ensure that Wget saves the host after a successfull auth and
+    Also, we ensure that Wget saves the host after a successful auth and
     doesn't wait for a challenge the second time.
 """
 ############# File Definitions ###############################################

testenv/Test-metalink-http-baddigest.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP with a malformed base64 Digest header.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+bad = "Ouch!"
+bad_sha256 = b64encode (hashlib.sha256 (bad.encode ('UTF-8')).digest ()).decode ('ascii')
+
+LinkHeaders = ["<http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file>; rel=duplicate; pri=1"]
+DigestHeader = "SHA-256=bad_base64,SHA-256={{BAD_HASH}}"
+
+# This will be filled as soon as we know server hostname and port
+MetaHTTPRules = {'SendHeader' : {}}
+
+MetaHTTP = WgetFile ("main.metalink", rules=MetaHTTPRules)
+
+wrong_file = WgetFile ("wrong_file", bad)
+wrong_file_down = WgetFile ("main.metalink", bad)
+
+WGET_OPTIONS = "--metalink-over-http"
+WGET_URLS = [["main.metalink"]]
+
+RequestList = [[
+    "HEAD /main.metalink",
+    "GET /wrong_file"
+]]
+
+Files = [[
+    MetaHTTP,
+    wrong_file
+]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [wrong_file_down]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+)
+
+http_test.server_setup()
+### Get and use dynamic server sockname
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+DigestHeader = DigestHeader.replace('{{BAD_HASH}}', bad_sha256)
+
+# Helper function for hostname, port and digest substitution
+def SubstituteServerInfo (text, host, port):
+    text = text.replace('{{SRV_HOST}}', host)
+    text = text.replace('{{SRV_PORT}}', str (port))
+    return text
+
+MetaHTTPRules["SendHeader"] = {
+        'Link': [ SubstituteServerInfo (LinkHeader, srv_host, srv_port)
+                    for LinkHeader in LinkHeaders ],
+        'Digest': DigestHeader
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http-quoted.py

@@ -0,0 +1,126 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP quoted values support in Wget.
+"""
+
+# Helper function for hostname, port and digest substitution
+def SubstituteServerInfo (text, host, port, digest):
+    text = text.replace('{{FILE1_HASH}}', digest)
+    text = text.replace('{{SRV_HOST}}', host)
+    text = text.replace('{{SRV_PORT}}', str (port))
+    return text
+
+############# File Definitions ###############################################
+File1 = "Would you like some Tea?"
+File1_corrupted = "Would you like some Coffee?"
+File1_lowPref = "Do not take this"
+File1_sha256 = b64encode (hashlib.sha256 (File1.encode ('UTF-8')).digest ()).decode ('ascii')
+Signature = '''-----BEGIN PGP SIGNATURE-----
+Version: GnuPG v1.0.7 (GNU/Linux)
+
+This is no valid signature. But it should be downloaded.
+The attempt to verify should fail but should not prevent
+a successful metalink resource retrieval (the sig failure
+should not be fatal).
+-----END PGP SIGNATURE-----
+'''
+File2 = "No meta data for this file."
+
+LinkHeaders = [
+    # This file has low priority and should not be picked.
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/File1_lowPref>; rel=\"duplicate\"; pri=\"9\"; geo=\"pl\"",
+    # This file should be picked second, after hash failure.
+    "<http://0.0.0.0/File1_try2_badconnection>; rel =\"duplicate\";pref; pri=\"7\"",
+    # This signature download will fail.
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/Sig2.asc>; rel=\"describedby\"; type=\"application/pgp-signature\"",
+    # Two good signatures
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/Sig.asc>; rel=\"describedby\"; type=\"application/pgp-signature\"",
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/Sig.asc>; rel=\"describedby\"; type=\"application/pgp-signature\"",
+    # Bad URL scheme
+    "<invalid_url>; rel=\"duplicate\"; pri=\"4\"",
+    # rel missing
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/File1>; pri=\"1\"; pref",
+    # invalid rel
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/File1>; rel=\"strange\"; pri=\"4\"",
+    # This file should be picked first, because it has the lowest pri among preferred.
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/File1_try1_corrupted>; rel=\"duplicate\"; geo=\"su\"; pri=\"4\"; pref",
+    # This file should NOT be picked third due to preferred location set to 'uk'
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/File1_badgeo>; rel =\"duplicate\";pri=\"5\"",
+    # This file should be picked as third try, and it should succeed
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/File1_try3_ok>; rel=\'duplicate\'; pri=\"5\";geo=\"uk\""
+    ]
+DigestHeader = "SHA-256=\'{{FILE1_HASH}}\'"
+
+# This will be filled as soon as we know server hostname and port
+MetaFileRules = {'SendHeader' : {}}
+
+FileOkServer = WgetFile ("File1_try3_ok", File1)
+FileBadPref = WgetFile ("File1_lowPref", File1_lowPref)
+FileBadHash = WgetFile ("File1_try1_corrupted", File1_corrupted)
+MetaFile = WgetFile ("test.meta", rules=MetaFileRules)
+# In case of Metalink over HTTP, the local file name is
+# derived from the URL suffix.
+FileOkLocal = WgetFile ("test.meta", File1)
+SigFile = WgetFile ("Sig.asc", Signature)
+FileNoMeta = WgetFile ("File2", File2)
+
+WGET_OPTIONS = "--metalink-over-http --preferred-location=uk"
+WGET_URLS = [["test.meta", "File2"]]
+
+Files = [[FileOkServer, FileBadPref, FileBadHash, MetaFile, SigFile, FileNoMeta]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [FileNoMeta, FileOkLocal]
+
+RequestList = [
+    [
+        "HEAD /test.meta",
+        "GET /Sig2.asc",
+        "GET /Sig.asc",
+        "GET /File1_try1_corrupted",
+        "GET /File1_try3_ok",
+        "HEAD /File2",
+        "GET /File2",
+    ]
+]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList,
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test,
+)
+
+http_test.server_setup()
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+MetaFileRules["SendHeader"] = {
+        'Link': [ SubstituteServerInfo (LinkHeader, srv_host, srv_port, File1_sha256)
+                    for LinkHeader in LinkHeaders ],
+        'Digest': SubstituteServerInfo (DigestHeader, srv_host, srv_port, File1_sha256),
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http-xml-trust-name.py

@@ -0,0 +1,272 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP with Metalink/XML Link headers.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+bad = "Ouch!"
+bad_sha256 = hashlib.sha256 (bad.encode ('UTF-8')).hexdigest ()
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+File1_sha256 = hashlib.sha256 (File1.encode ('UTF-8')).hexdigest ()
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+File2_sha256 = hashlib.sha256 (File2.encode ('UTF-8')).hexdigest ()
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+File3_sha256 = hashlib.sha256 (File3.encode ('UTF-8')).hexdigest ()
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+File4_sha256 = hashlib.sha256 (File4.encode ('UTF-8')).hexdigest ()
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+File5_sha256 = hashlib.sha256 (File5.encode ('UTF-8')).hexdigest ()
+
+MetaXml1 = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="dir/File1">
+      <verification>
+        <hash type="sha256">{{FILE1_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File1_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File1</url>
+      </resources>
+    </file>
+    <file name="dir/File2">
+      <verification>
+        <hash type="sha256">{{FILE2_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File2_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File2</url>
+      </resources>
+    </file>
+    <file name="/dir/File3"> <!-- rejected by libmetalink -->
+      <verification>
+        <hash type="sha256">{{FILE3_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File3_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File3</url>
+      </resources>
+    </file>
+    <file name="dir/File4">
+      <verification>
+        <hash type="sha256">{{FILE4_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File4_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File4</url>
+      </resources>
+    </file>
+    <file name="dir/File5">
+      <verification>
+        <hash type="sha256">{{FILE5_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File5_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File5</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+MetaXml2 = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="bad">
+      <verification>
+        <hash type="sha256">{{BAD_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/bad</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+LinkHeaders = [
+    # This file has the lowest priority, and should go last
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/test1.metalink>; rel=describedby; pri=2; type=\"application/metalink4+xml\"; name=\"newname.metalink\"",
+    # This file has the highest priority, and should go first
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/test2.metalink>; rel=describedby; pri=1; type=\"application/metalink4+xml\""
+]
+
+# This will be filled as soon as we know server hostname and port
+MetaHTTPRules = {'SendHeader' : {}}
+
+MetaHTTP = WgetFile ("main.metalink", rules=MetaHTTPRules)
+
+wrong_file = WgetFile ("wrong_file", bad)
+
+File1_orig = WgetFile ("File1", File1)
+File1_down = WgetFile ("dir/File1", File1)
+File1_nono = WgetFile ("File1_lowPref", File1_lowPref)
+
+File2_orig = WgetFile ("File2", File2)
+File2_down = WgetFile ("dir/File2", File2)
+File2_nono = WgetFile ("File2_lowPref", File2_lowPref)
+
+# rejected by libmetalink
+File3_orig = WgetFile ("File3", File3)
+File3_nono = WgetFile ("File3_lowPref", File3_lowPref)
+
+File4_orig = WgetFile ("File4", File4)
+File4_down = WgetFile ("dir/File4", File4)
+File4_nono = WgetFile ("File4_lowPref", File4_lowPref)
+
+File5_orig = WgetFile ("File5", File5)
+File5_down = WgetFile ("dir/File5", File5)
+File5_nono = WgetFile ("File5_lowPref", File5_lowPref)
+
+MetaFile1 = WgetFile ("test1.metalink", MetaXml1)
+MetaFile1_down = WgetFile ("newname.metalink", MetaXml1)
+
+MetaFile2 = WgetFile ("test2.metalink", MetaXml2)
+
+WGET_OPTIONS = "--trust-server-names --metalink-over-http --metalink-index=2"
+WGET_URLS = [["main.metalink"]]
+
+RequestList = [[
+    "HEAD /main.metalink",
+    "GET /404",
+    "GET /wrong_file",
+    "GET /test1.metalink",
+    "GET /File1",
+    "GET /File2",
+    "GET /File4",
+    "GET /File5"
+]]
+
+Files = [[
+    MetaHTTP,
+    wrong_file,
+    MetaFile1, MetaFile2,
+    File1_orig, File1_nono,
+    File2_orig, File2_nono,
+    File3_orig, File3_nono,
+    File4_orig, File4_nono,
+    File5_orig, File5_nono
+]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [
+    MetaFile1_down,
+    File1_down,
+    File2_down,
+    File4_down,
+    File5_down
+]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+)
+
+http_test.server_setup()
+### Get and use dynamic server sockname
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+MetaXml1 = MetaXml1.replace('{{FILE1_HASH}}', File1_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE2_HASH}}', File2_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE3_HASH}}', File3_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE4_HASH}}', File4_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE5_HASH}}', File5_sha256)
+MetaXml1 = MetaXml1.replace('{{SRV_HOST}}', srv_host)
+MetaXml1 = MetaXml1.replace('{{SRV_PORT}}', str (srv_port))
+MetaFile1.content = MetaXml1
+MetaFile1_down.content = MetaXml1
+
+MetaXml2 = MetaXml2.replace('{{BAD_HASH}}', bad_sha256)
+MetaXml2 = MetaXml2.replace('{{SRV_HOST}}', srv_host)
+MetaXml2 = MetaXml2.replace('{{SRV_PORT}}', str (srv_port))
+MetaFile2.content = MetaXml2
+
+# Helper function for hostname, port and digest substitution
+def SubstituteServerInfo (text, host, port):
+    text = text.replace('{{SRV_HOST}}', host)
+    text = text.replace('{{SRV_PORT}}', str (port))
+    return text
+
+MetaHTTPRules["SendHeader"] = {
+        'Link': [ SubstituteServerInfo (LinkHeader, srv_host, srv_port)
+                    for LinkHeader in LinkHeaders ]
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http-xml-trust.py

@@ -0,0 +1,272 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP with Metalink/XML Link headers.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+bad = "Ouch!"
+bad_sha256 = hashlib.sha256 (bad.encode ('UTF-8')).hexdigest ()
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+File1_sha256 = hashlib.sha256 (File1.encode ('UTF-8')).hexdigest ()
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+File2_sha256 = hashlib.sha256 (File2.encode ('UTF-8')).hexdigest ()
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+File3_sha256 = hashlib.sha256 (File3.encode ('UTF-8')).hexdigest ()
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+File4_sha256 = hashlib.sha256 (File4.encode ('UTF-8')).hexdigest ()
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+File5_sha256 = hashlib.sha256 (File5.encode ('UTF-8')).hexdigest ()
+
+MetaXml1 = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="dir/File1">
+      <verification>
+        <hash type="sha256">{{FILE1_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File1_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File1</url>
+      </resources>
+    </file>
+    <file name="dir/File2">
+      <verification>
+        <hash type="sha256">{{FILE2_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File2_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File2</url>
+      </resources>
+    </file>
+    <file name="/dir/File3"> <!-- rejected by libmetalink -->
+      <verification>
+        <hash type="sha256">{{FILE3_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File3_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File3</url>
+      </resources>
+    </file>
+    <file name="dir/File4">
+      <verification>
+        <hash type="sha256">{{FILE4_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File4_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File4</url>
+      </resources>
+    </file>
+    <file name="dir/File5">
+      <verification>
+        <hash type="sha256">{{FILE5_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File5_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File5</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+MetaXml2 = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="bad">
+      <verification>
+        <hash type="sha256">{{BAD_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/bad</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+LinkHeaders = [
+    # This file has the lowest priority, and should go last
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/test1.metalink>; rel=describedby; pri=2; type=\"application/metalink4+xml\"",
+    # This file has the highest priority, and should go first
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/test2.metalink>; rel=describedby; pri=1; type=\"application/metalink4+xml\""
+]
+
+# This will be filled as soon as we know server hostname and port
+MetaHTTPRules = {'SendHeader' : {}}
+
+MetaHTTP = WgetFile ("main.metalink", rules=MetaHTTPRules)
+
+wrong_file = WgetFile ("wrong_file", bad)
+
+File1_orig = WgetFile ("File1", File1)
+File1_down = WgetFile ("dir/File1", File1)
+File1_nono = WgetFile ("File1_lowPref", File1_lowPref)
+
+File2_orig = WgetFile ("File2", File2)
+File2_down = WgetFile ("dir/File2", File2)
+File2_nono = WgetFile ("File2_lowPref", File2_lowPref)
+
+# rejected by libmetalink
+File3_orig = WgetFile ("File3", File3)
+File3_nono = WgetFile ("File3_lowPref", File3_lowPref)
+
+File4_orig = WgetFile ("File4", File4)
+File4_down = WgetFile ("dir/File4", File4)
+File4_nono = WgetFile ("File4_lowPref", File4_lowPref)
+
+File5_orig = WgetFile ("File5", File5)
+File5_down = WgetFile ("dir/File5", File5)
+File5_nono = WgetFile ("File5_lowPref", File5_lowPref)
+
+MetaFile1 = WgetFile ("test1.metalink", MetaXml1)
+MetaFile1_down = WgetFile ("test1.metalink", MetaXml1)
+
+MetaFile2 = WgetFile ("test2.metalink", MetaXml2)
+
+WGET_OPTIONS = "--trust-server-names --metalink-over-http --metalink-index=2"
+WGET_URLS = [["main.metalink"]]
+
+RequestList = [[
+    "HEAD /main.metalink",
+    "GET /404",
+    "GET /wrong_file",
+    "GET /test1.metalink",
+    "GET /File1",
+    "GET /File2",
+    "GET /File4",
+    "GET /File5"
+]]
+
+Files = [[
+    MetaHTTP,
+    wrong_file,
+    MetaFile1, MetaFile2,
+    File1_orig, File1_nono,
+    File2_orig, File2_nono,
+    File3_orig, File3_nono,
+    File4_orig, File4_nono,
+    File5_orig, File5_nono
+]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [
+    MetaFile1_down,
+    File1_down,
+    File2_down,
+    File4_down,
+    File5_down
+]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+)
+
+http_test.server_setup()
+### Get and use dynamic server sockname
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+MetaXml1 = MetaXml1.replace('{{FILE1_HASH}}', File1_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE2_HASH}}', File2_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE3_HASH}}', File3_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE4_HASH}}', File4_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE5_HASH}}', File5_sha256)
+MetaXml1 = MetaXml1.replace('{{SRV_HOST}}', srv_host)
+MetaXml1 = MetaXml1.replace('{{SRV_PORT}}', str (srv_port))
+MetaFile1.content = MetaXml1
+MetaFile1_down.content = MetaXml1
+
+MetaXml2 = MetaXml2.replace('{{BAD_HASH}}', bad_sha256)
+MetaXml2 = MetaXml2.replace('{{SRV_HOST}}', srv_host)
+MetaXml2 = MetaXml2.replace('{{SRV_PORT}}', str (srv_port))
+MetaFile2.content = MetaXml2
+
+# Helper function for hostname, port and digest substitution
+def SubstituteServerInfo (text, host, port):
+    text = text.replace('{{SRV_HOST}}', host)
+    text = text.replace('{{SRV_PORT}}', str (port))
+    return text
+
+MetaHTTPRules["SendHeader"] = {
+        'Link': [ SubstituteServerInfo (LinkHeader, srv_host, srv_port)
+                    for LinkHeader in LinkHeaders ]
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http-xml-type-content.py

@@ -0,0 +1,221 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP with Content-Type Metalink/XML.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+bad = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+File1_sha256 = hashlib.sha256 (File1.encode ('UTF-8')).hexdigest ()
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+File2_sha256 = hashlib.sha256 (File2.encode ('UTF-8')).hexdigest ()
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+File3_sha256 = hashlib.sha256 (File3.encode ('UTF-8')).hexdigest ()
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+File4_sha256 = hashlib.sha256 (File4.encode ('UTF-8')).hexdigest ()
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+File5_sha256 = hashlib.sha256 (File5.encode ('UTF-8')).hexdigest ()
+
+MetaXml = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="dir/File1">
+      <verification>
+        <hash type="sha256">{{FILE1_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File1_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File1</url>
+      </resources>
+    </file>
+    <file name="dir/File2">
+      <verification>
+        <hash type="sha256">{{FILE2_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File2_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File2</url>
+      </resources>
+    </file>
+    <file name="/dir/File3"> <!-- rejected by libmetalink -->
+      <verification>
+        <hash type="sha256">{{FILE3_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File3_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File3</url>
+      </resources>
+    </file>
+    <file name="dir/File4">
+      <verification>
+        <hash type="sha256">{{FILE4_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File4_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File4</url>
+      </resources>
+    </file>
+    <file name="dir/File5">
+      <verification>
+        <hash type="sha256">{{FILE5_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File5_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File5</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+# This will be filled as soon as we know server hostname and port
+MetaHTTPRules = {'SendHeader' : {}}
+
+MetaHTTP = WgetFile ("main.metalink", rules=MetaHTTPRules)
+MetaHTTP_down = WgetFile ("main.metalink.meta#1", MetaXml)
+
+wrong_file = WgetFile ("wrong_file", bad)
+
+File1_orig = WgetFile ("File1", File1)
+File1_down = WgetFile ("main.metalink.meta#1.#1", File1)
+File1_nono = WgetFile ("File1_lowPref", File1_lowPref)
+
+File2_orig = WgetFile ("File2", File2)
+File2_down = WgetFile ("main.metalink.meta#1.#2", File2)
+File2_nono = WgetFile ("File2_lowPref", File2_lowPref)
+
+# rejected by libmetalink
+File3_orig = WgetFile ("File3", File3)
+File3_nono = WgetFile ("File3_lowPref", File3_lowPref)
+
+File4_orig = WgetFile ("File4", File4)
+File4_down = WgetFile ("main.metalink.meta#1.#3", File4)
+File4_nono = WgetFile ("File4_lowPref", File4_lowPref)
+
+File5_orig = WgetFile ("File5", File5)
+File5_down = WgetFile ("main.metalink.meta#1.#4", File5)
+File5_nono = WgetFile ("File5_lowPref", File5_lowPref)
+
+WGET_OPTIONS = "--metalink-over-http --content-disposition --metalink-index=0"
+WGET_URLS = [["main.metalink"]]
+
+RequestList = [[
+    "HEAD /main.metalink",
+    "GET /main.metalink",
+    "GET /404",
+    "GET /wrong_file",
+    "GET /File1",
+    "GET /File2",
+    "GET /File4",
+    "GET /File5"
+]]
+
+Files = [[
+    MetaHTTP,
+    wrong_file,
+    File1_orig, File1_nono,
+    File2_orig, File2_nono,
+    File3_orig, File3_nono,
+    File4_orig, File4_nono,
+    File5_orig, File5_nono
+]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [
+    MetaHTTP_down,
+    File1_down,
+    File2_down,
+    File4_down,
+    File5_down
+]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+)
+
+http_test.server_setup()
+### Get and use dynamic server sockname
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+MetaXml = MetaXml.replace('{{FILE1_HASH}}', File1_sha256)
+MetaXml = MetaXml.replace('{{FILE2_HASH}}', File2_sha256)
+MetaXml = MetaXml.replace('{{FILE3_HASH}}', File3_sha256)
+MetaXml = MetaXml.replace('{{FILE4_HASH}}', File4_sha256)
+MetaXml = MetaXml.replace('{{FILE5_HASH}}', File5_sha256)
+MetaXml = MetaXml.replace('{{SRV_HOST}}', srv_host)
+MetaXml = MetaXml.replace('{{SRV_PORT}}', str (srv_port))
+MetaHTTP_down.content = MetaXml
+
+MetaHTTP.content = MetaXml
+
+MetaHTTPRules["SendHeader"] = {
+    'Content-Type': 'application/metalink4+xml',
+    'Content-Disposition': 'filename="newname.metalink"'
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http-xml-type-trust-content.py

@@ -0,0 +1,221 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP with Content-Type Metalink/XML.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+bad = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+File1_sha256 = hashlib.sha256 (File1.encode ('UTF-8')).hexdigest ()
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+File2_sha256 = hashlib.sha256 (File2.encode ('UTF-8')).hexdigest ()
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+File3_sha256 = hashlib.sha256 (File3.encode ('UTF-8')).hexdigest ()
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+File4_sha256 = hashlib.sha256 (File4.encode ('UTF-8')).hexdigest ()
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+File5_sha256 = hashlib.sha256 (File5.encode ('UTF-8')).hexdigest ()
+
+MetaXml = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="dir/File1">
+      <verification>
+        <hash type="sha256">{{FILE1_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File1_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File1</url>
+      </resources>
+    </file>
+    <file name="dir/File2">
+      <verification>
+        <hash type="sha256">{{FILE2_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File2_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File2</url>
+      </resources>
+    </file>
+    <file name="/dir/File3"> <!-- rejected by libmetalink -->
+      <verification>
+        <hash type="sha256">{{FILE3_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File3_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File3</url>
+      </resources>
+    </file>
+    <file name="dir/File4">
+      <verification>
+        <hash type="sha256">{{FILE4_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File4_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File4</url>
+      </resources>
+    </file>
+    <file name="dir/File5">
+      <verification>
+        <hash type="sha256">{{FILE5_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File5_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File5</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+# This will be filled as soon as we know server hostname and port
+MetaHTTPRules = {'SendHeader' : {}}
+
+MetaHTTP = WgetFile ("main.metalink", rules=MetaHTTPRules)
+MetaHTTP_down = WgetFile ("newname.metalink", MetaXml)
+
+wrong_file = WgetFile ("wrong_file", bad)
+
+File1_orig = WgetFile ("File1", File1)
+File1_down = WgetFile ("dir/File1", File1)
+File1_nono = WgetFile ("File1_lowPref", File1_lowPref)
+
+File2_orig = WgetFile ("File2", File2)
+File2_down = WgetFile ("dir/File2", File2)
+File2_nono = WgetFile ("File2_lowPref", File2_lowPref)
+
+# rejected by libmetalink
+File3_orig = WgetFile ("File3", File3)
+File3_nono = WgetFile ("File3_lowPref", File3_lowPref)
+
+File4_orig = WgetFile ("File4", File4)
+File4_down = WgetFile ("dir/File4", File4)
+File4_nono = WgetFile ("File4_lowPref", File4_lowPref)
+
+File5_orig = WgetFile ("File5", File5)
+File5_down = WgetFile ("dir/File5", File5)
+File5_nono = WgetFile ("File5_lowPref", File5_lowPref)
+
+WGET_OPTIONS = "--trust-server-names --metalink-over-http --content-disposition --metalink-index=0"
+WGET_URLS = [["main.metalink"]]
+
+RequestList = [[
+    "HEAD /main.metalink",
+    "GET /main.metalink",
+    "GET /404",
+    "GET /wrong_file",
+    "GET /File1",
+    "GET /File2",
+    "GET /File4",
+    "GET /File5"
+]]
+
+Files = [[
+    MetaHTTP,
+    wrong_file,
+    File1_orig, File1_nono,
+    File2_orig, File2_nono,
+    File3_orig, File3_nono,
+    File4_orig, File4_nono,
+    File5_orig, File5_nono
+]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [
+    MetaHTTP_down,
+    File1_down,
+    File2_down,
+    File4_down,
+    File5_down
+]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+)
+
+http_test.server_setup()
+### Get and use dynamic server sockname
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+MetaXml = MetaXml.replace('{{FILE1_HASH}}', File1_sha256)
+MetaXml = MetaXml.replace('{{FILE2_HASH}}', File2_sha256)
+MetaXml = MetaXml.replace('{{FILE3_HASH}}', File3_sha256)
+MetaXml = MetaXml.replace('{{FILE4_HASH}}', File4_sha256)
+MetaXml = MetaXml.replace('{{FILE5_HASH}}', File5_sha256)
+MetaXml = MetaXml.replace('{{SRV_HOST}}', srv_host)
+MetaXml = MetaXml.replace('{{SRV_PORT}}', str (srv_port))
+MetaHTTP_down.content = MetaXml
+
+MetaHTTP.content = MetaXml
+
+MetaHTTPRules["SendHeader"] = {
+    'Content-Type': 'application/metalink4+xml',
+    'Content-Disposition': 'filename="newname.metalink"'
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http-xml-type-trust.py

@@ -0,0 +1,221 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP with Content-Type Metalink/XML.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+bad = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+File1_sha256 = hashlib.sha256 (File1.encode ('UTF-8')).hexdigest ()
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+File2_sha256 = hashlib.sha256 (File2.encode ('UTF-8')).hexdigest ()
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+File3_sha256 = hashlib.sha256 (File3.encode ('UTF-8')).hexdigest ()
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+File4_sha256 = hashlib.sha256 (File4.encode ('UTF-8')).hexdigest ()
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+File5_sha256 = hashlib.sha256 (File5.encode ('UTF-8')).hexdigest ()
+
+MetaXml = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="dir/File1">
+      <verification>
+        <hash type="sha256">{{FILE1_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File1_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File1</url>
+      </resources>
+    </file>
+    <file name="dir/File2">
+      <verification>
+        <hash type="sha256">{{FILE2_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File2_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File2</url>
+      </resources>
+    </file>
+    <file name="/dir/File3"> <!-- rejected by libmetalink -->
+      <verification>
+        <hash type="sha256">{{FILE3_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File3_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File3</url>
+      </resources>
+    </file>
+    <file name="dir/File4">
+      <verification>
+        <hash type="sha256">{{FILE4_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File4_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File4</url>
+      </resources>
+    </file>
+    <file name="dir/File5">
+      <verification>
+        <hash type="sha256">{{FILE5_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File5_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File5</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+# This will be filled as soon as we know server hostname and port
+MetaHTTPRules = {'SendHeader' : {}}
+
+MetaHTTP = WgetFile ("main.metalink", rules=MetaHTTPRules)
+MetaHTTP_down = WgetFile ("main.metalink", MetaXml)
+
+wrong_file = WgetFile ("wrong_file", bad)
+
+File1_orig = WgetFile ("File1", File1)
+File1_down = WgetFile ("dir/File1", File1)
+File1_nono = WgetFile ("File1_lowPref", File1_lowPref)
+
+File2_orig = WgetFile ("File2", File2)
+File2_down = WgetFile ("dir/File2", File2)
+File2_nono = WgetFile ("File2_lowPref", File2_lowPref)
+
+# rejected by libmetalink
+File3_orig = WgetFile ("File3", File3)
+File3_nono = WgetFile ("File3_lowPref", File3_lowPref)
+
+File4_orig = WgetFile ("File4", File4)
+File4_down = WgetFile ("dir/File4", File4)
+File4_nono = WgetFile ("File4_lowPref", File4_lowPref)
+
+File5_orig = WgetFile ("File5", File5)
+File5_down = WgetFile ("dir/File5", File5)
+File5_nono = WgetFile ("File5_lowPref", File5_lowPref)
+
+WGET_OPTIONS = "--trust-server-names --metalink-over-http --metalink-index=0"
+WGET_URLS = [["main.metalink"]]
+
+RequestList = [[
+    "HEAD /main.metalink",
+    "GET /main.metalink",
+    "GET /404",
+    "GET /wrong_file",
+    "GET /File1",
+    "GET /File2",
+    "GET /File4",
+    "GET /File5"
+]]
+
+Files = [[
+    MetaHTTP,
+    wrong_file,
+    File1_orig, File1_nono,
+    File2_orig, File2_nono,
+    File3_orig, File3_nono,
+    File4_orig, File4_nono,
+    File5_orig, File5_nono
+]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [
+    MetaHTTP_down,
+    File1_down,
+    File2_down,
+    File4_down,
+    File5_down
+]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+)
+
+http_test.server_setup()
+### Get and use dynamic server sockname
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+MetaXml = MetaXml.replace('{{FILE1_HASH}}', File1_sha256)
+MetaXml = MetaXml.replace('{{FILE2_HASH}}', File2_sha256)
+MetaXml = MetaXml.replace('{{FILE3_HASH}}', File3_sha256)
+MetaXml = MetaXml.replace('{{FILE4_HASH}}', File4_sha256)
+MetaXml = MetaXml.replace('{{FILE5_HASH}}', File5_sha256)
+MetaXml = MetaXml.replace('{{SRV_HOST}}', srv_host)
+MetaXml = MetaXml.replace('{{SRV_PORT}}', str (srv_port))
+MetaHTTP_down.content = MetaXml
+
+MetaHTTP.content = MetaXml
+
+MetaHTTPRules["SendHeader"] = {
+    'Content-Type': 'application/metalink4+xml',
+    'Content-Disposition': 'filename="newname.metalink"'
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http-xml-type.py

@@ -0,0 +1,221 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP with Content-Type Metalink/XML.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+bad = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+File1_sha256 = hashlib.sha256 (File1.encode ('UTF-8')).hexdigest ()
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+File2_sha256 = hashlib.sha256 (File2.encode ('UTF-8')).hexdigest ()
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+File3_sha256 = hashlib.sha256 (File3.encode ('UTF-8')).hexdigest ()
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+File4_sha256 = hashlib.sha256 (File4.encode ('UTF-8')).hexdigest ()
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+File5_sha256 = hashlib.sha256 (File5.encode ('UTF-8')).hexdigest ()
+
+MetaXml = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="dir/File1">
+      <verification>
+        <hash type="sha256">{{FILE1_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File1_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File1</url>
+      </resources>
+    </file>
+    <file name="dir/File2">
+      <verification>
+        <hash type="sha256">{{FILE2_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File2_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File2</url>
+      </resources>
+    </file>
+    <file name="/dir/File3"> <!-- rejected by libmetalink -->
+      <verification>
+        <hash type="sha256">{{FILE3_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File3_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File3</url>
+      </resources>
+    </file>
+    <file name="dir/File4">
+      <verification>
+        <hash type="sha256">{{FILE4_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File4_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File4</url>
+      </resources>
+    </file>
+    <file name="dir/File5">
+      <verification>
+        <hash type="sha256">{{FILE5_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File5_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File5</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+# This will be filled as soon as we know server hostname and port
+MetaHTTPRules = {'SendHeader' : {}}
+
+MetaHTTP = WgetFile ("main.metalink", rules=MetaHTTPRules)
+MetaHTTP_down = WgetFile ("main.metalink.meta#1", MetaXml)
+
+wrong_file = WgetFile ("wrong_file", bad)
+
+File1_orig = WgetFile ("File1", File1)
+File1_down = WgetFile ("main.metalink.meta#1.#1", File1)
+File1_nono = WgetFile ("File1_lowPref", File1_lowPref)
+
+File2_orig = WgetFile ("File2", File2)
+File2_down = WgetFile ("main.metalink.meta#1.#2", File2)
+File2_nono = WgetFile ("File2_lowPref", File2_lowPref)
+
+# rejected by libmetalink
+File3_orig = WgetFile ("File3", File3)
+File3_nono = WgetFile ("File3_lowPref", File3_lowPref)
+
+File4_orig = WgetFile ("File4", File4)
+File4_down = WgetFile ("main.metalink.meta#1.#3", File4)
+File4_nono = WgetFile ("File4_lowPref", File4_lowPref)
+
+File5_orig = WgetFile ("File5", File5)
+File5_down = WgetFile ("main.metalink.meta#1.#4", File5)
+File5_nono = WgetFile ("File5_lowPref", File5_lowPref)
+
+WGET_OPTIONS = "--metalink-over-http --metalink-index=0"
+WGET_URLS = [["main.metalink"]]
+
+RequestList = [[
+    "HEAD /main.metalink",
+    "GET /main.metalink",
+    "GET /404",
+    "GET /wrong_file",
+    "GET /File1",
+    "GET /File2",
+    "GET /File4",
+    "GET /File5"
+]]
+
+Files = [[
+    MetaHTTP,
+    wrong_file,
+    File1_orig, File1_nono,
+    File2_orig, File2_nono,
+    File3_orig, File3_nono,
+    File4_orig, File4_nono,
+    File5_orig, File5_nono
+]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [
+    MetaHTTP_down,
+    File1_down,
+    File2_down,
+    File4_down,
+    File5_down
+]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+)
+
+http_test.server_setup()
+### Get and use dynamic server sockname
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+MetaXml = MetaXml.replace('{{FILE1_HASH}}', File1_sha256)
+MetaXml = MetaXml.replace('{{FILE2_HASH}}', File2_sha256)
+MetaXml = MetaXml.replace('{{FILE3_HASH}}', File3_sha256)
+MetaXml = MetaXml.replace('{{FILE4_HASH}}', File4_sha256)
+MetaXml = MetaXml.replace('{{FILE5_HASH}}', File5_sha256)
+MetaXml = MetaXml.replace('{{SRV_HOST}}', srv_host)
+MetaXml = MetaXml.replace('{{SRV_PORT}}', str (srv_port))
+MetaHTTP_down.content = MetaXml
+
+MetaHTTP.content = MetaXml
+
+MetaHTTPRules["SendHeader"] = {
+    'Content-Type': 'application/metalink4+xml',
+    'Content-Disposition': 'filename="newname.metalink"'
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http-xml.py

@@ -0,0 +1,272 @@
+#!/usr/bin/env python3
+from sys import exit
+from test.http_test import HTTPTest
+from misc.wget_file import WgetFile
+import hashlib
+from base64 import b64encode
+
+"""
+    This is to test Metalink/HTTP with Metalink/XML Link headers.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+bad = "Ouch!"
+bad_sha256 = hashlib.sha256 (bad.encode ('UTF-8')).hexdigest ()
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+File1_sha256 = hashlib.sha256 (File1.encode ('UTF-8')).hexdigest ()
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+File2_sha256 = hashlib.sha256 (File2.encode ('UTF-8')).hexdigest ()
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+File3_sha256 = hashlib.sha256 (File3.encode ('UTF-8')).hexdigest ()
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+File4_sha256 = hashlib.sha256 (File4.encode ('UTF-8')).hexdigest ()
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+File5_sha256 = hashlib.sha256 (File5.encode ('UTF-8')).hexdigest ()
+
+MetaXml1 = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="dir/File1">
+      <verification>
+        <hash type="sha256">{{FILE1_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File1_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File1</url>
+      </resources>
+    </file>
+    <file name="dir/File2">
+      <verification>
+        <hash type="sha256">{{FILE2_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File2_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File2</url>
+      </resources>
+    </file>
+    <file name="/dir/File3"> <!-- rejected by libmetalink -->
+      <verification>
+        <hash type="sha256">{{FILE3_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File3_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File3</url>
+      </resources>
+    </file>
+    <file name="dir/File4">
+      <verification>
+        <hash type="sha256">{{FILE4_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File4_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File4</url>
+      </resources>
+    </file>
+    <file name="dir/File5">
+      <verification>
+        <hash type="sha256">{{FILE5_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="25">http://{{SRV_HOST}}:{{SRV_PORT}}/File5_lowPref</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/File5</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+MetaXml2 = \
+"""<?xml version="1.0" encoding="utf-8"?>
+<metalink version="3.0" xmlns="http://www.metalinker.org/">
+  <publisher>
+    <name>GNU Wget</name>
+  </publisher>
+  <license>
+    <name>GNU GPL</name>
+    <url>http://www.gnu.org/licenses/gpl.html</url>
+  </license>
+  <identity>Wget Test Files</identity>
+  <version>1.2.3</version>
+  <description>Wget Test Files description</description>
+  <files>
+    <file name="bad">
+      <verification>
+        <hash type="sha256">{{BAD_HASH}}</hash>
+      </verification>
+      <resources>
+        <url type="http" preference="35">http://{{SRV_HOST}}:{{SRV_PORT}}/wrong_file</url>
+        <url type="http" preference="40">http://{{SRV_HOST}}:{{SRV_PORT}}/404</url>
+        <url type="http" preference="30">http://{{SRV_HOST}}:{{SRV_PORT}}/bad</url>
+      </resources>
+    </file>
+  </files>
+</metalink>
+"""
+
+LinkHeaders = [
+    # This file has the lowest priority, and should go last
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/test1.metalink>; rel=describedby; pri=2; type=\"application/metalink4+xml\"",
+    # This file has the highest priority, and should go first
+    "<http://{{SRV_HOST}}:{{SRV_PORT}}/test2.metalink>; rel=describedby; pri=1; type=\"application/metalink4+xml\""
+]
+
+# This will be filled as soon as we know server hostname and port
+MetaHTTPRules = {'SendHeader' : {}}
+
+MetaHTTP = WgetFile ("main.metalink", rules=MetaHTTPRules)
+
+wrong_file = WgetFile ("wrong_file", bad)
+
+File1_orig = WgetFile ("File1", File1)
+File1_down = WgetFile ("main.metalink.meta#2.#1", File1)
+File1_nono = WgetFile ("File1_lowPref", File1_lowPref)
+
+File2_orig = WgetFile ("File2", File2)
+File2_down = WgetFile ("main.metalink.meta#2.#2", File2)
+File2_nono = WgetFile ("File2_lowPref", File2_lowPref)
+
+# rejected by libmetalink
+File3_orig = WgetFile ("File3", File3)
+File3_nono = WgetFile ("File3_lowPref", File3_lowPref)
+
+File4_orig = WgetFile ("File4", File4)
+File4_down = WgetFile ("main.metalink.meta#2.#3", File4)
+File4_nono = WgetFile ("File4_lowPref", File4_lowPref)
+
+File5_orig = WgetFile ("File5", File5)
+File5_down = WgetFile ("main.metalink.meta#2.#4", File5)
+File5_nono = WgetFile ("File5_lowPref", File5_lowPref)
+
+MetaFile1 = WgetFile ("test1.metalink", MetaXml1)
+MetaFile1_down = WgetFile ("main.metalink.meta#2", MetaXml1)
+
+MetaFile2 = WgetFile ("test2.metalink", MetaXml2)
+
+WGET_OPTIONS = "--metalink-over-http --metalink-index=2"
+WGET_URLS = [["main.metalink"]]
+
+RequestList = [[
+    "HEAD /main.metalink",
+    "GET /404",
+    "GET /wrong_file",
+    "GET /test1.metalink",
+    "GET /File1",
+    "GET /File2",
+    "GET /File4",
+    "GET /File5"
+]]
+
+Files = [[
+    MetaHTTP,
+    wrong_file,
+    MetaFile1, MetaFile2,
+    File1_orig, File1_nono,
+    File2_orig, File2_nono,
+    File3_orig, File3_nono,
+    File4_orig, File4_nono,
+    File5_orig, File5_nono
+]]
+Existing_Files = []
+
+ExpectedReturnCode = 0
+ExpectedDownloadedFiles = [
+    MetaFile1_down,
+    File1_down,
+    File2_down,
+    File4_down,
+    File5_down
+]
+
+################ Pre and Post Test Hooks #####################################
+pre_test = {
+    "ServerFiles"       : Files,
+    "LocalFiles"        : Existing_Files
+}
+test_options = {
+    "WgetCommands"      : WGET_OPTIONS,
+    "Urls"              : WGET_URLS
+}
+post_test = {
+    "ExpectedFiles"     : ExpectedDownloadedFiles,
+    "ExpectedRetcode"   : ExpectedReturnCode,
+    "FilesCrawled"      : RequestList
+}
+
+http_test = HTTPTest (
+                pre_hook=pre_test,
+                test_params=test_options,
+                post_hook=post_test
+)
+
+http_test.server_setup()
+### Get and use dynamic server sockname
+srv_host, srv_port = http_test.servers[0].server_inst.socket.getsockname ()
+
+MetaXml1 = MetaXml1.replace('{{FILE1_HASH}}', File1_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE2_HASH}}', File2_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE3_HASH}}', File3_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE4_HASH}}', File4_sha256)
+MetaXml1 = MetaXml1.replace('{{FILE5_HASH}}', File5_sha256)
+MetaXml1 = MetaXml1.replace('{{SRV_HOST}}', srv_host)
+MetaXml1 = MetaXml1.replace('{{SRV_PORT}}', str (srv_port))
+MetaFile1.content = MetaXml1
+MetaFile1_down.content = MetaXml1
+
+MetaXml2 = MetaXml2.replace('{{BAD_HASH}}', bad_sha256)
+MetaXml2 = MetaXml2.replace('{{SRV_HOST}}', srv_host)
+MetaXml2 = MetaXml2.replace('{{SRV_PORT}}', str (srv_port))
+MetaFile2.content = MetaXml2
+
+# Helper function for hostname, port and digest substitution
+def SubstituteServerInfo (text, host, port):
+    text = text.replace('{{SRV_HOST}}', host)
+    text = text.replace('{{SRV_PORT}}', str (port))
+    return text
+
+MetaHTTPRules["SendHeader"] = {
+        'Link': [ SubstituteServerInfo (LinkHeader, srv_host, srv_port)
+                    for LinkHeader in LinkHeaders ]
+}
+
+err = http_test.begin ()
+
+exit (err)

testenv/Test-metalink-http.py

@@ -2,7 +2,6 @@
 from sys import exit
 from test.http_test import HTTPTest
 from misc.wget_file import WgetFile
-import re
 import hashlib
 from base64 import b64encode
 
@@ -12,9 +11,9 @@ from base64 import b64encode
 
 # Helper function for hostname, port and digest substitution
 def SubstituteServerInfo (text, host, port, digest):
-    text = re.sub (r'{{FILE1_HASH}}', digest, text)
-    text = re.sub (r'{{SRV_HOST}}', host, text)
-    text = re.sub (r'{{SRV_PORT}}', str (port), text)
+    text = text.replace('{{FILE1_HASH}}', digest)
+    text = text.replace('{{SRV_HOST}}', host)
+    text = text.replace('{{SRV_PORT}}', str (port))
     return text
 
 ############# File Definitions ###############################################

testenv/Test-metalink-xml-abspath-trust.py

@@ -0,0 +1,101 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test if Metalink/XML forbids absolute paths.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["/File1", None, File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["File2", "File2", File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["/File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["/File4", None, File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["File5", "File5", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--trust-server-names " + \
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-abspath.py

@@ -0,0 +1,100 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test if Metalink/XML forbids absolute paths.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["/File1", None, File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["File2", XmlName + ".#1", File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["/File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["/File4", None, File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["File5", XmlName + ".#2", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-absprefix-trust.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test Metalink/XML absolute directory prefix support in Wget.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["subdir/File1", "File1", File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["/subdir/File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["~/subdir/File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["../subdir/File4", None, File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["subdir/File5", "File5", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--trust-server-names " + \
+    "--directory-prefix /dir " + \
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-absprefix.py

@@ -0,0 +1,101 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test Metalink/XML absolute directory prefix support in Wget.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["subdir/File1", XmlName + ".#1", File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["/subdir/File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["~/subdir/File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["../subdir/File4", None, File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["subdir/File5", XmlName + ".#2", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--directory-prefix /dir " + \
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-continue.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test Metalink/XML --continue support in Wget.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type (http, ftp, etc.)
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.add_LocalFiles (
+    [XmlName + ".#1", File1[0:14]], # File1 to continue from partial file
+    [XmlName + ".#2", File2],       # File2 to keep, different from server
+    [XmlName + ".#3", File3],       # File3 to keep, already fully retrieved
+    [XmlName + ".#4", File4],       # File4 to keep, different from server
+)
+
+Meta.add_ExpectedFiles (
+    [XmlName + ".#2", File2],       # File2 to keep, different from server
+    [XmlName + ".#3", File3],       # File3 to keep, already fully retrieved
+    [XmlName + ".#4", File4],       # File4 to keep, different from server
+)
+
+Meta.print_meta ()
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["File1", XmlName + ".#1", File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["File2", XmlName + ".#2", wrong_file, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["File3", XmlName + ".#3", File3, None, True,
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["File4", XmlName + ".#4", File4_lowPref, None, True,
+     ["wrong_file", wrong_file, "http", None, 35]],
+    ["File5", XmlName + ".#5", File5, None, True,
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--continue " + \
+    "--input-metalink " + XmlName, 1
+)
+
+exit (err)

testenv/Test-metalink-xml-emptyprefix-trust.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test Metalink/XML with an empty directory prefix.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["subdir/File1", "subdir/File1", File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["/subdir/File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["~/subdir/File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["../subdir/File4", None, File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["subdir/File5", "subdir/File5", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--trust-server-names " + \
+    "--directory-prefix '' " + \
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-homepath-trust.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test if Metalink/XML forbids the home path and names
+    beginning with the ~ (tilde) character.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["~File1", None, File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["~/File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["dir/~File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["dir/File4~", "dir/File4~", File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["dir/~/File5", "dir/~/File5", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--trust-server-names " + \
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-homepath.py

@@ -0,0 +1,101 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test if Metalink/XML forbids the home path and names
+    beginning with the ~ (tilde) character.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["~File1", None, File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["~/File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["dir/~File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["dir/File4~", XmlName + ".#1", File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["dir/~/File5", XmlName + ".#2", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-homeprefix-trust.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test Metalink/XML home directory prefix support in Wget.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["subdir/File1", "File1", File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["/subdir/File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["~/subdir/File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["../subdir/File4", None, File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["subdir/File5", "File5", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--trust-server-names " + \
+    "--directory-prefix ~/dir " + \
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-homeprefix.py

@@ -0,0 +1,101 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test Metalink/XML home directory prefix support in Wget.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["subdir/File1", XmlName + ".#1", File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["/subdir/File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["~/subdir/File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["../subdir/File4", None, File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["subdir/File5", XmlName + ".#2", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--directory-prefix ~/dir " + \
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)

testenv/Test-metalink-xml-nohash.py

@@ -0,0 +1,100 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test if Metalink/XML with no hashes generates a SIGSEGV.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type (http, ftp, etc.)
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["File1", None, File1, None, False,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["File2", XmlName + ".#2", File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["File3", None, File3, None, None,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["File4", XmlName + ".#4", File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["File5", None, File5, None, "",
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--input-metalink " + XmlName, 1
+)
+
+exit (err)

testenv/Test-metalink-xml-nourls.py

@@ -0,0 +1,100 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test Metalink/XML with unknown url types.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type (http, ftp, etc.)
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["File1", XmlName + ".#1", File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "unknown", None, 35],
+     ["404", None, "unknown", None, 40],
+     ["File2_lowPref", File2_lowPref, "unknown", None, 25],
+     ["File2", File2, "unknown", None, 30]],
+    ["File3", XmlName + ".#3", File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["File4", XmlName + ".#4", File4, None, True,
+     ["wrong_file", wrong_file, "unknown", None, 35],
+     ["404", None, "unknown", None, 40],
+     ["File4_lowPref", File4_lowPref, "unknown", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["File5", XmlName + ".#5", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--input-metalink " + XmlName, 1
+)
+
+exit (err)

testenv/Test-metalink-xml-prefix-trust.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+
+from sys import exit
+from misc.metalinkv3_xml import Metalinkv3_XML
+
+"""
+    This is to test Metalink/XML directory prefix support in Wget.
+
+    With --trust-server-names, trust the metalink:file names.
+
+    Without --trust-server-names, don't trust the metalink:file names:
+    use the basename of --input-metalink, and add a sequential number
+    (e.g. .#1, .#2, etc.).
+
+    Strip the directory from unsafe paths.
+"""
+
+############# File Definitions ###############################################
+wrong_file = "Ouch!"
+
+File1 = "Would you like some Tea?"
+File1_lowPref = "Do not take this"
+
+File2 = "This is gonna be good"
+File2_lowPref = "Not this one too"
+
+File3 = "A little more, please"
+File3_lowPref = "That's just too much"
+
+File4 = "Maybe a biscuit?"
+File4_lowPref = "No, thanks"
+
+File5 = "More Tea...?"
+File5_lowPref = "I have to go..."
+
+############# Metalink/XML ###################################################
+Meta = Metalinkv3_XML()
+
+# file_name: metalink:file "name" field
+# save_name: metalink:file save name, if None the file is rejected
+# content  : metalink:file content
+#
+# size:
+#   True     auto-compute size
+#   None     no <size></size>
+#    any     use this size
+#
+# hash_sha256:
+#   False    no <verification></verification>
+#   True     auto-compute sha256
+#   None     no <hash></hash>
+#    any     use this hash
+#
+# srv_file   : metalink:url server file
+# srv_content: metalink:url server file content, if None the file doesn't exist
+# utype      : metalink:url type
+# location   : metalink:url location (default 'no location field')
+# preference : metalink:url preference (default 999999)
+
+XmlName = "test.metalink"
+
+Meta.xml (
+    # Metalink/XML file name
+    XmlName,
+    # file_name, save_name, content, size, hash_sha256
+    ["subdir/File1", "dir/" + "subdir/File1", File1, None, True,
+     # srv_file, srv_content, utype, location, preference
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File1_lowPref", File1_lowPref, "http", None, 25],
+     ["File1", File1, "http", None, 30]],
+    ["/subdir/File2", None, File2, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File2_lowPref", File2_lowPref, "http", None, 25],
+     ["File2", File2, "http", None, 30]],
+    ["~/subdir/File3", None, File3, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File3_lowPref", File3_lowPref, "http", None, 25],
+     ["File3", File3, "http", None, 30]],
+    ["../subdir/File4", None, File4, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File4_lowPref", File4_lowPref, "http", None, 25],
+     ["File4", File4, "http", None, 30]],
+    ["subdir/File5", "dir/" + "subdir/File5", File5, None, True,
+     ["wrong_file", wrong_file, "http", None, 35],
+     ["404", None, "http", None, 40],
+     ["File5_lowPref", File5_lowPref, "http", None, 25],
+     ["File5", File5, "http", None, 30]],
+)
+
+Meta.print_meta ()
+
+err = Meta.http_test (
+    "--trust-server-names " + \
+    "--directory-prefix dir " + \
+    "--input-metalink " + XmlName, 0
+)
+
+exit (err)