Prepare release 1.15

Previously wget didn't honor the --timeout option if the remote host did
not answer SSL handshake

Signed-off-by: Tomas Hozza <thozza@redhat.com>

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "gnulib"]
+	path = gnulib
+	url = git://git.sv.gnu.org/gnulib.git

ChangeLog

@@ -1,3 +1,44 @@
+2013-12-22  Giuseppe Scrivano  <gscrivan@redhat.com>
+
+	* gnulib: add git submodule.
+
+2013-09-13  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* configure.ac: added a summary of build options
+	  fixed some indentations
+	  removed the unconditionally adding of libz with --with-ssl
+	  removed -lgcrypt and -lgpg-error for gnutls
+
+2013-07-23  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* configure.ac: Remove AM_CONDITIONAL HAVE_NETTLE.
+	Reported by: Darshit Shah  <darnir@gmail.com>.
+
+2013-07-13  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* configure.ac: check for libnettle when GNU TLS is used.
+
+2013-05-17 Bykov Aleksey <gnfalex@rambler.ru>
+
+	* bootstrap: Add `mkostemp'
+
+2012-10-07  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* configure.ac: Check for patchconf.
+
+2012-09-23  Merinov Nikolay  <kim.roader@gmail.com>
+
+	* m4/wget.m4 (WGET_FNMATCH): Add AC_LANG_SOURCE into
+	AC_COMPILE_IFELSE in order to silence autoconf 2.68 warning.
+
+2012-09-20  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* bootstrap: Update from gnulib.
+
+2012-09-02  Nguyễn Thái Ngọc Duy  <pclouds@gmail.com> (tiny change)
+
+	* po/POTFILES.in: Add more files.
+
 2012-07-08  Giuseppe Scrivano  <gscrivano@gnu.org>
 
 	* bootstrap: Update from gnulib.

NEWS

@@ -6,6 +6,38 @@ See the end for copying conditions.
 
 Please send GNU Wget bug reports to <bug-wget@gnu.org>.
 
+* Changes in Wget 1.15
+
+** Add support for --method.
+
+** Add support for file names longer than MAX_FILE.
+
+** Support FTP listing for the FTP Server on Windows Server 2008 R2.
+
+** Fix a regression when -c and --content-disposition are used together.
+
+** Support shorthand URLs in an input file.
+
+** Fix -c with servers that don't specify a content-length.
+
+** Add support for MD5-SESS
+
+** Do not fail on non fatal GNU TLS alerts during handshake.
+
+** Add support for --https-only.  When used wget will follow only
+   HTTPS links in recursive mode.
+
+** Support Perfect-Forward Secrecy in --secure-protocol.
+
+** Fix a problem with some IRI links that are not followed when contained in a
+   HTML document.
+
+** Support some FTP servers that return an empty list with "LIST -a".
+
+** Specify Host with the HTTP CONNECT method.
+
+** Use the correct HTTP method on a redirection.
+
 * Changes in Wget 1.14
 
 ** Add support for content-on-error.  It allows to store the HTTP

bootstrap

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Print a version string.
-scriptversion=2012-07-06.11; # UTC
+scriptversion=2012-07-19.14; # UTC
 
 # Bootstrap this package from checked-out sources.
 
@@ -77,15 +77,32 @@ Running without arguments will suffice in most cases.
 EOF
 }
 
-warn()
+# warnf_ FORMAT-STRING ARG1...
+warnf_ ()
 {
-  for i
-  do
-    echo "$i"
-  done | sed -e "s/^/$me: /" >&2
+  warnf_format_=$1
+  shift
+  nl='
+'
+  case $* in
+    *$nl*) me_=$(printf "$me"|tr "$nl|" '??')
+       printf "$warnf_format_" "$@" | sed "s|^|$me_: |" ;;
+    *) printf "$me: $warnf_format_" "$@" ;;
+  esac >&2
 }
 
-die() { warn "$@"; exit 1; }
+# warn_ WORD1...
+warn_ ()
+{
+  # If IFS does not start with ' ', set it and emit the warning in a subshell.
+  case $IFS in
+    ' '*) warnf_ '%s\n' "$*";;
+    *)    (IFS=' '; warn_ "$@");;
+  esac
+}
+
+# die WORD1...
+die() { warn_ "$@"; exit 1; }
 
 # Configuration.
 
@@ -197,6 +214,8 @@ use_git=true
 # otherwise find the first of the NAMES that can be run (i.e.,
 # supports --version).  If found, set ENVVAR to the program name,
 # die otherwise.
+#
+# FIXME: code duplication, see also gnu-web-doc-update.
 find_tool ()
 {
   find_tool_envvar=$1
@@ -335,8 +354,7 @@ grep '^[	 ]*AC_CONFIG_AUX_DIR(\['"$build_aux"'\])' configure.ac \
 grep '^[	 ]*AC_CONFIG_AUX_DIR('"$build_aux"')' configure.ac \
     >/dev/null && found_aux_dir=yes
 test $found_aux_dir = yes \
-  || die "expected line not found in configure.ac. Add the following:" \
-         "  AC_CONFIG_AUX_DIR([$build_aux])"
+  || die "configure.ac lacks 'AC_CONFIG_AUX_DIR([$build_aux])'; add it"
 
 # If $build_aux doesn't exist, create it now, otherwise some bits
 # below will malfunction.  If creating it, also mark it as ignored.
@@ -442,7 +460,7 @@ check_versions() {
       automake-ng|aclocal-ng)
         app=${app%-ng}
         ($app --version | grep '(GNU automake-ng)') >/dev/null 2>&1 || {
-          warn "Error: '$app' not found or not from Automake-NG"
+          warn_ "Error: '$app' not found or not from Automake-NG"
           ret=1
           continue
         } ;;
@@ -452,20 +470,21 @@ check_versions() {
       # so we have to rely on $? rather than get_version.
       $app --version >/dev/null 2>&1
       if [ 126 -le $? ]; then
-        warn "Error: '$app' not found"
+        warn_ "Error: '$app' not found"
         ret=1
       fi
     else
       # Require app to produce a new enough version string.
       inst_ver=$(get_version $app)
       if [ ! "$inst_ver" ]; then
-        warn "Error: '$app' not found"
+        warn_ "Error: '$app' not found"
         ret=1
       else
         latest_ver=$(sort_ver $req_ver $inst_ver | cut -d' ' -f2)
         if [ ! "$latest_ver" = "$inst_ver" ]; then
-          warn "Error: '$app' version == $inst_ver is too old" \
-               "       '$app' version >= $req_ver is required"
+          warnf_ '%s\n'                                        \
+              "Error: '$app' version == $inst_ver is too old"  \
+              "       '$app' version >= $req_ver is required"
           ret=1
         fi
       fi
@@ -761,7 +780,7 @@ version_controlled_file() {
     grep -F "/${file##*/}/" "$parent/CVS/Entries" 2>/dev/null |
              grep '^/[^/]*/[0-9]' > /dev/null
   else
-    warn "no version control for $file?"
+    warn_ "no version control for $file?"
     false
   fi
 }

bootstrap.conf

@@ -52,6 +52,7 @@ maintainer-makefile
 mbtowc
 mkdir
 mkstemp
+mkostemp
 crypto/md5
 crypto/sha1
 pipe

configure.ac

@@ -198,7 +198,7 @@ dnl Checks for library functions.
 dnl
 AC_FUNC_MMAP
 AC_FUNC_FSEEKO
-AC_CHECK_FUNCS(strptime timegm vsnprintf vasprintf drand48)
+AC_CHECK_FUNCS(strptime timegm vsnprintf vasprintf drand48 pathconf)
 AC_CHECK_FUNCS(strtoll usleep ftello sigblock sigsetjmp memrchr wcwidth mbtowc)
 AC_CHECK_FUNCS(sleep symlink utime)
 
@@ -238,57 +238,54 @@ dnl Checks for libraries.
 dnl
 
 AS_IF([test x"$with_zlib" != xno], [
+  with_zlib=yes
   AC_CHECK_LIB(z, compress)
 ])
 
 AS_IF([test x"$with_ssl" = xopenssl], [
-    dnl some versions of openssl use zlib compression
-    AC_CHECK_LIB(z, compress)
+  dnl As of this writing (OpenSSL 0.9.6), the libcrypto shared library
+  dnl doesn't record its dependency on libdl, so we need to make sure
+  dnl -ldl ends up in LIBS on systems that have it.  Most OSes use
+  dnl dlopen(), but HP-UX uses shl_load().
+  AC_CHECK_LIB(dl, dlopen, [], [
+    AC_CHECK_LIB(dl, shl_load)
+  ])
 
-    dnl As of this writing (OpenSSL 0.9.6), the libcrypto shared library
-    dnl doesn't record its dependency on libdl, so we need to make sure
-    dnl -ldl ends up in LIBS on systems that have it.  Most OSes use
-    dnl dlopen(), but HP-UX uses shl_load().
-    AC_CHECK_LIB(dl, dlopen, [], [
-      AC_CHECK_LIB(dl, shl_load)
-    ])
-
-    ssl_found=no
-    case $host_os in
-      *mingw32* )
-        dnl prefer link to openssl dlls if possible. if not then fallback on static libs. if not then error
+  ssl_found=no
+  case $host_os in
+    *mingw32* )
+      dnl prefer link to openssl dlls if possible. if not then fallback on static libs. if not then error
         
-        AC_CHECK_LIB(eay32, EVP_MD_CTX_init)
-        if test x"$ac_cv_lib_eay32_EVP_MD_CTX_init" != xno
-        then
-          AC_CHECK_LIB(ssl32, SSL_connect, [
-            ssl_found=yes
-            AC_MSG_NOTICE([Enabling support for SSL via OpenSSL (shared)])
-            AC_LIBOBJ([openssl])
-            LIBS="${LIBS} -lssl32"
-            AC_DEFINE([HAVE_LIBSSL32], [1], [Define to 1 if you have the `ssl32' library (-lssl32).])
-          ],
-          AC_MSG_ERROR([openssl not found: shared lib eay32 found but ssl32 not found]))
+      AC_CHECK_LIB(eay32, EVP_MD_CTX_init)
+      if test x"$ac_cv_lib_eay32_EVP_MD_CTX_init" != xno
+      then
+        AC_CHECK_LIB(ssl32, SSL_connect, [
+          ssl_found=yes
+          AC_MSG_NOTICE([Enabling support for SSL via OpenSSL (shared)])
+          AC_LIBOBJ([openssl])
+          LIBS="${LIBS} -lssl32"
+          AC_DEFINE([HAVE_LIBSSL32], [1], [Define to 1 if you have the `ssl32' library (-lssl32).])
+        ],
+        AC_MSG_ERROR([openssl not found: shared lib eay32 found but ssl32 not found]))
           
-        else
-          LIBS+=' -lgdi32'
-          dnl fallback and test static libs
-        fi
-        dnl add zdll lib as dep for above tests?
-      ;;
-    esac
+      else
+        LIBS+=' -lgdi32'
+        dnl fallback and test static libs
+      fi
+      dnl add zdll lib as dep for above tests?
+    ;;
+  esac
 
-AS_IF([test x$ssl_found != xyes],
-[
-  dnl Now actually check for -lssl if it wasn't already found
-    AC_LIB_HAVE_LINKFLAGS([ssl], [crypto z], [
-  #include <openssl/ssl.h>
-  #include <openssl/x509.h>
-  #include <openssl/err.h>
-  #include <openssl/rand.h>
-  #include <openssl/des.h>
-  #include <openssl/md4.h>
-  #include <openssl/md5.h>
+  AS_IF([test x$ssl_found != xyes], [
+    dnl Now actually check for -lssl if it wasn't already found
+    AC_LIB_HAVE_LINKFLAGS([ssl], [crypto], [
+#include <openssl/ssl.h>
+#include <openssl/x509.h>
+#include <openssl/err.h>
+#include <openssl/rand.h>
+#include <openssl/des.h>
+#include <openssl/md4.h>
+#include <openssl/md5.h>
     ], [SSL_library_init ()])
     if test x"$LIBSSL" != x
     then
@@ -300,33 +297,30 @@ AS_IF([test x$ssl_found != xyes],
     then
       AC_MSG_ERROR([--with-ssl=openssl was given, but SSL is not available.])
     fi
-])
+  ])
 
 ], [
-  # --with-ssl is not gnutls: check if it's no
+  # --with-ssl is not openssl: check if it's no
   AS_IF([test x"$with_ssl" != xno], [
-    dnl Now actually check for -lssl
+    dnl default is -lgnutls
+    with_ssl=gnutls
 
-    AC_CHECK_LIB(z, compress)
-    AC_CHECK_LIB(gpg-error, gpg_err_init)
-    AC_CHECK_LIB(gcrypt, gcry_control)
-
-  dnl Now actually check for -lssl
-  AC_LIB_HAVE_LINKFLAGS([gnutls], [], [
+    dnl Now actually check for -lgnutls
+    AC_LIB_HAVE_LINKFLAGS([gnutls], [], [
 #include <gnutls/gnutls.h>
-  ], [gnutls_global_init()])
-  if test x"$LIBGNUTLS" != x
-  then
-    ssl_found=yes
-    AC_MSG_NOTICE([compiling in support for SSL via GnuTLS])
-    AC_LIBOBJ([gnutls])
-    LIBS="$LIBGNUTLS $LIBS"
-  else
-    AC_MSG_ERROR([--with-ssl was given, but GNUTLS is not available.])
-  fi
+    ], [gnutls_global_init()])
+    if test x"$LIBGNUTLS" != x
+    then
+      ssl_found=yes
+      AC_MSG_NOTICE([compiling in support for SSL via GnuTLS])
+      AC_LIBOBJ([gnutls])
+      LIBS="$LIBGNUTLS $LIBS"
+    else
+      AC_MSG_ERROR([--with-ssl=gnutls was given, but GNUTLS is not available.])
+    fi
 
-  AC_CHECK_FUNCS(gnutls_priority_set_direct)
-  ]) # endif: --with-ssl == no?
+    AC_CHECK_FUNCS(gnutls_priority_set_direct)
+  ]) # endif: --with-ssl != no?
 ]) # endif: --with-ssl == openssl?
 
 dnl Enable NTLM if requested and if SSL is available.
@@ -334,16 +328,33 @@ if test x"$LIBSSL" != x || test "$ac_cv_lib_ssl32_SSL_connect" = yes
 then
   if test x"$ENABLE_NTLM" != xno
   then
+    ENABLE_NTLM=yes
     AC_DEFINE([ENABLE_NTLM], 1,
      [Define if you want the NTLM authorization support compiled in.])
     AC_LIBOBJ([http-ntlm])
   fi
 else
-  dnl If SSL is unavailable and the user explicitly requested NTLM,
-  dnl abort.
-  if test x"$ENABLE_NTLM" = xyes
+  AC_CHECK_LIB(nettle, nettle_md4_init, [HAVE_NETTLE=yes], [HAVE_NETTLE=no; AC_MSG_WARN(*** libnettle was not found. You will not be able to use NTLM)])
+
+  if test x"$HAVE_NETTLE" = xyes
   then
-    AC_MSG_ERROR([NTLM authorization requested and OpenSSL not found; aborting])
+    AC_SUBST(NETTLE_LIBS, "-lnettle")
+    AC_DEFINE([HAVE_NETTLE], [1], [Use libnettle])
+    if test x"$ENABLE_NTLM" != xno
+    then
+      ENABLE_NTLM=yes
+      AC_DEFINE([ENABLE_NTLM], 1,
+       [Define if you want the NTLM authorization support compiled in.])
+      AC_LIBOBJ([http-ntlm])
+      LIBS="$NETTLE_LIBS $LIBS"
+    fi
+  else
+    dnl If SSL is unavailable and the user explicitly requested NTLM,
+    dnl abort.
+    if test x"$ENABLE_NTLM" = xyes
+    then
+      AC_MSG_ERROR([NTLM authorization requested and SSL not enabled; aborting])
+    fi
   fi
 fi
 
@@ -557,3 +568,20 @@ AC_CONFIG_FILES([Makefile src/Makefile doc/Makefile util/Makefile
                  lib/Makefile])
 AC_CONFIG_HEADERS([src/config.h])
 AC_OUTPUT
+
+AC_MSG_NOTICE([Summary of build options:
+
+  Version:           $PACKAGE_VERSION
+  Host OS:           $host_os
+  Install prefix:    $prefix
+  Compiler:          $CC
+  CFlags:            $CFLAGS $CPPFLAGS
+  LDFlags:           $LDFLAGS
+  Libs:              $LIBS
+  SSL:               $with_ssl
+  Zlib:              $with_zlib
+  Digest:            $ENABLE_DIGEST
+  NTLM:              $ENABLE_NTLM
+  OPIE:              $ENABLE_OPIE
+  Debugging:         $ENABLE_DEBUG
+])

doc/ChangeLog

@@ -1,3 +1,89 @@
+2013-12-29  Giuseppe Scrivano  <gscrivan@redhat.com>
+
+	* wget.texi: Update to GFDL 1.3.
+
+2013-12-22  Mike Frysinger  <vapier@gentoo.org>
+
+	* sample.wgetrc: add links to the manual.
+
+2013-10-06  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* wget.texi: add/explain quoting of wildcard patterns
+
+2013-09-04  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* sample.wgetrc: added "secureprotocol" example
+	* wget.texi (HTTPS (SSL/TLS) Options): Document PFS.
+
+2013-08-23  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* sample.wgetrc: added "httpsonly" example
+
+2013-08-22  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* wget.texi: added description for --https-only
+
+2013-08-13  Hrvoje Niksic  <hniksic@xemacs.org>
+
+	* wget.texi (Download Options): Fix misspelling.
+
+2013-07-09  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* wget.texi (Download Options): Add documentation for --backups.
+	(Wgetrc Commands): Add documentation for backups.
+	Reported by: Tomas Hozza <thozza@redhat.com>.
+
+2013-07-11  Tomas Hozza  <thozza@redhat.com>
+
+	* wget.texi: Document --regex-type and --preserve-permissions.
+
+2013-06-17  Dave Reisner  <dreisner@archlinux.org> (tiny change)
+
+	* texi2pod.pl: Fix formatting error that causes build to fail with
+	Perl 5.18
+
+2013-06-17  Darshit Shah  <darnir@gmail.com>
+
+	* wget.texi (POST): Explain the new redirection rules.
+	* wget.texi (Other HTTP Methods): Same.
+	* wget.texi (body-data): Fix typo in description.
+
+2013-05-10  Darshit Shah <darnir@gmail.com>  (tiny change)
+
+	* wget.texi (No of tries): Fix typo to make it clear that --tries
+	option sets number of tries not retries.
+	Reported by: Hauke Hoffman <haukebjoernhoffman@googlemail.com>
+
+2013-04-28  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* wget.texi (Types of Files...): Document --accept-regex,
+	--reject-regex.
+	Reported by: Tomas Hozza <thozza@redhat.com>.
+
+2013-04-14  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* wget.texi (Download Options): Document "mega" dot style.
+
+2013-04-05  Darshit Shah <darnir@gmail.com>
+
+	* doc/wget.texi: Fix ambiguous wording in --post-data section. Make it
+	clear that wget does not check for the format of the post-data.
+	* doc/wget.texi: Add documentation for --method, --body-data and
+	--body-file.
+
+2012-10-08  Stefano Lattarini <stefano.lattarini@gmail.com>  (tiny change)
+
+	docs: fix errors and warnings with Texinfo 5
+	Or rather, with the development version 4.13.90, which will
+	eventually become Texinfo 5.0.
+	* wget.texi: Use '@item' instead of '@itemx' in several places,
+	as Texinfo 5 refuses to process an '@itemx' that is not preceded
+	by an '@item'.
+
+2012-08-28  Tim Ruehsen <tim.ruehsen@gmx.de>
+
+        * doc/wget.texi: remove -nv from --report-speed
+
 2012-08-04  mancha <mancha@mac.hush.com> (tiny change)
 
 	* wget.texi: Export ENVIRONMENT to the man page.

doc/sample.wgetrc

@@ -5,7 +5,10 @@
 ## You can use this file to change the default behaviour of wget or to
 ## avoid having to type many many command-line options. This file does
 ## not contain a comprehensive list of commands -- look at the manual
-## to find out what you can put into this file.
+## to find out what you can put into this file. You can find this here:
+##   $ info wget.info 'Startup File'
+## Or online here:
+##   https://www.gnu.org/software/wget/manual/wget.html#Startup-File
 ##
 ## Wget initialization file can reside in /usr/local/etc/wgetrc
 ## (global, for all users) or $HOME/.wgetrc (for a single user).
@@ -123,3 +126,9 @@
 
 # Force the default remote server encoding
 #remoteencoding = UTF-8
+
+# Turn on to prevent following non-HTTPS links when in recursive mode
+#httpsonly = off
+
+# Tune HTTPS security (auto, SSLv2, SSLv3, TLSv1, PFS)
+#secureprotocol = auto

doc/texi2pod.pl

@@ -291,7 +291,7 @@ while(<$inf>) {
 	if (defined $1) {
             my $thing = $1;
             if ($ic =~ /\@asis/) {
-                $_ = "\n=item $thing\n";
+                $_ = "\n=item C<$thing>\n";
             } else {
                 # Entity escapes prevent munging by the <> processing below.
                 $_ = "\n=item $ic\&LT;$thing\&GT;\n";

doc/wget.texi

@@ -47,11 +47,11 @@ notice identical to this one except for the removal of this paragraph
 (this paragraph not being relevant to the printed manual).
 @end ignore
 Permission is granted to copy, distribute and/or modify this document
-under the terms of the GNU Free Documentation License, Version 1.2 or
+under the terms of the GNU Free Documentation License, Version 1.3 or
 any later version published by the Free Software Foundation; with no
-Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts.  A
-copy of the license is included in the section entitled ``GNU Free
-Documentation License''.
+Invariant Sections, with no Front-Cover Texts, and with no Back-Cover
+Texts.  A copy of the license is included in the section entitled
+``GNU Free Documentation License''.
 @c man end
 @end copying
 
@@ -479,8 +479,7 @@ Turn off verbose without being completely quiet (use @samp{-q} for
 that), which means that error messages and basic information still get
 printed.
 
-@item -nv
-@itemx --report-speed=@var{type}
+@item --report-speed=@var{type}
 Output bandwidth as @var{type}.  The only accepted value is @samp{bits}.
 
 @cindex input-file
@@ -551,10 +550,10 @@ IPs.
 
 @cindex retries
 @cindex tries
-@cindex number of retries
+@cindex number of tries
 @item -t @var{number}
 @itemx --tries=@var{number}
-Set number of retries to @var{number}.  Specify 0 or @samp{inf} for
+Set number of tries to @var{number}. Specify 0 or @samp{inf} for
 infinite retrying.  The default is to retry 20 times, with the exception
 of fatal errors like ``connection refused'' or ``not found'' (404),
 which are not retried.
@@ -631,6 +630,13 @@ Note that when @samp{-nc} is specified, files with the suffixes
 @samp{.html} or @samp{.htm} will be loaded from the local disk and
 parsed as if they had been retrieved from the Web.
 
+@cindex backing up files
+@item --backups=@var{backups}
+Before (over)writing a file, back up an existing file by adding a
+@samp{.1} suffix (@samp{_1} on VMS) to the file name.  Such backup
+files are rotated to @samp{.2}, @samp{.3}, and so on, up to
+@var{backups} (and lost beyond that).
+
 @cindex continue retrieval
 @cindex incomplete downloads
 @cindex resume download
@@ -716,9 +722,12 @@ different meaning to one dot.  With the @code{default} style each dot
 represents 1K, there are ten dots in a cluster and 50 dots in a line.
 The @code{binary} style has a more ``computer''-like orientation---8K
 dots, 16-dots clusters and 48 dots per line (which makes for 384K
-lines).  The @code{mega} style is suitable for downloading very large
+lines).  The @code{mega} style is suitable for downloading large
 files---each dot represents 64K retrieved, there are eight dots in a
 cluster, and 48 dots on each line (so each line contains 3M).
+If @code{mega} is not enough then you can use the @code{giga}
+style---each dot represents 1M retrieved, there are eight dots in a
+cluster, and 32 dots on each line (so each line contains 32M).
 
 Note that you can set the default style using the @code{progress}
 command in @file{.wgetrc}.  That setting may be overridden from the
@@ -733,7 +742,7 @@ Turn on time-stamping.  @xref{Time-Stamping}, for details.
 @item --no-use-server-timestamps
 Don't set the local file's timestamp by the one on the server.
 
-By default, when a file is downloaded, it's timestamps are set to
+By default, when a file is downloaded, its timestamps are set to
 match those from the remote file. This allows the use of
 @samp{--timestamping} on subsequent invocations of wget. However, it
 is sometimes useful to base the local file's timestamp on when it was
@@ -876,7 +885,7 @@ recommendation to block many unrelated users from a web site due to the
 actions of one.
 
 @cindex proxy
-@itemx --no-proxy
+@item --no-proxy
 Don't use proxies, even if the appropriate @code{*_proxy} environment
 variable is defined.
 
@@ -977,7 +986,7 @@ are outside the range of @sc{ascii} characters (that is, greater than
 whose encoding does not match the one used locally.
 
 @cindex IPv6
-@itemx -4
+@item -4
 @itemx --inet4-only
 @itemx -6
 @itemx --inet6-only
@@ -1458,6 +1467,11 @@ like everything else. Wget does not currently support
 @code{application/x-www-form-urlencoded}. Only one of
 @samp{--post-data} and @samp{--post-file} should be specified.
 
+Please note that wget does not require the content to be of the form
+@code{key1=value1&key2=value2}, and neither does it test for it. Wget will
+simply transmit whatever data is provided to it. Most servers however expect
+the POST data to be in the above format when processing HTML Forms.
+
 Please be aware that Wget needs to know the size of the POST data in
 advance.  Therefore the argument to @code{--post-file} must be a regular
 file; specifying a FIFO or something like @file{/dev/stdin} won't work.
@@ -1468,14 +1482,15 @@ use chunked unless it knows it's talking to an HTTP/1.1 server.  And it
 can't know that until it receives a response, which in turn requires the
 request to have been completed -- a chicken-and-egg problem.
 
-Note: if Wget is redirected after the POST request is completed, it
-will not send the POST data to the redirected URL.  This is because
-URLs that process POST often respond with a redirection to a regular
-page, which does not desire or accept POST.  It is not completely
-clear that this behavior is optimal; if it doesn't work out, it might
-be changed in the future.
+Note: As of version 1.15 if Wget is redirected after the POST request is
+completed, its behaviour will depend on the response code returned by the
+server.  In case of a 301 Moved Permanently, 302 Moved Temporarily or
+307 Temporary Redirect, Wget will, in accordance with RFC2616, continue
+to send a POST request.
+In case a server wants the client to change the Request method upon
+redirection, it should send a 303 See Other response code.
 
-This example shows how to log to a server using POST and then proceed to
+This example shows how to log in to a server using POST and then proceed to
 download the desired pages, presumably only accessible to authorized
 users:
 
@@ -1498,6 +1513,37 @@ them (and neither will browsers) and the @file{cookies.txt} file will
 be empty.  In that case use @samp{--keep-session-cookies} along with
 @samp{--save-cookies} to force saving of session cookies.
 
+@cindex Other HTTP Methods
+@item --method=@var{HTTP-Method}
+For the purpose of RESTful scripting, Wget allows sending of other HTTP Methods
+without the need to explicitly set them using @samp{--header=Header-Line}.
+Wget will use whatever string is passed to it after @samp{--method} as the HTTP
+Method to the server.
+
+@item --body-data=@var{Data-String}
+@itemx --body-file=@var{Data-File}
+Must be set when additional data needs to be sent to the server along with the
+Method specified using @samp{--method}.  @samp{--body-data} sends @var{string} as
+data, whereas @samp{--body-file} sends the contents of @var{file}.  Other than that,
+they work in exactly the same way.
+
+Currently, @samp{--body-file} is @emph{not} for transmitting files as a whole.
+Wget does not currently support @code{multipart/form-data} for transmitting data;
+only @code{application/x-www-form-urlencoded}. In the future, this may be changed
+so that wget sends the @samp{--body-file} as a complete file instead of sending its
+contents to the server. Please be aware that Wget needs to know the contents of
+BODY Data in advance, and hence the argument to @samp{--body-file} should be a
+regular file. See @samp{--post-file} for a more detailed explanation.
+Only one of @samp{--body-data} and @samp{--body-file} should be specified.
+
+If Wget is redirected after the request is completed, Wget will
+suspend the current method and send a GET request till the redirection
+is completed.  This is true for all redirection response codes except
+307 Temporary Redirect which is used to explicitly specify that the
+request method should @emph{not} change.  Another exception is when
+the method is set to @code{POST}, in which case the redirection rules
+specified under @samp{--post-data} are followed.
+
 @cindex Content-Disposition
 @item --content-disposition
 
@@ -1549,16 +1595,24 @@ without SSL support, none of these options are available.
 @cindex SSL protocol, choose
 @item --secure-protocol=@var{protocol}
 Choose the secure protocol to be used.  Legal values are @samp{auto},
-@samp{SSLv2}, @samp{SSLv3}, and @samp{TLSv1}.  If @samp{auto} is used,
-the SSL library is given the liberty of choosing the appropriate
+@samp{SSLv2}, @samp{SSLv3}, @samp{TLSv1} and @samp{PFS}.  If @samp{auto}
+is used, the SSL library is given the liberty of choosing the appropriate
 protocol automatically, which is achieved by sending an SSLv2 greeting
 and announcing support for SSLv3 and TLSv1.  This is the default.
 
 Specifying @samp{SSLv2}, @samp{SSLv3}, or @samp{TLSv1} forces the use
 of the corresponding protocol.  This is useful when talking to old and
-buggy SSL server implementations that make it hard for OpenSSL to
-choose the correct protocol version.  Fortunately, such servers are
-quite rare.
+buggy SSL server implementations that make it hard for the underlying
+SSL library to choose the correct protocol version.  Fortunately, such
+servers are quite rare.
+
+Specifying @samp{PFS} enforces the use of the so-called Perfect Forward
+Security cipher suites. In short, PFS adds security by creating a one-time
+key for each SSL connection. It has a bit more CPU impact on client and server.
+We use known to be secure ciphers (e.g. no MD4) and the TLS protocol.
+
+@item --https-only
+When in recursive mode, only HTTPS links are followed.
 
 @cindex SSL certificate, check
 @item --no-check-certificate
@@ -1777,6 +1831,10 @@ in some rare firewall configurations, active FTP actually works when
 passive FTP doesn't.  If you suspect this to be the case, use this
 option, or set @code{passive_ftp=off} in your init file.
 
+@cindex file permissions
+@item --preserve-permissions
+Preserve remote file permissions instead of permissions set by umask.
+
 @cindex symbolic links, retrieving
 @item --retr-symlinks
 Usually, when retrieving @sc{ftp} directories recursively and a symbolic
@@ -2013,6 +2071,17 @@ accept or reject (@pxref{Types of Files}). Note that if
 any of the wildcard characters, @samp{*}, @samp{?}, @samp{[} or
 @samp{]}, appear in an element of @var{acclist} or @var{rejlist},
 it will be treated as a pattern, rather than a suffix.
+In this case, you have to enclose the pattern into quotes to prevent
+your shell from expanding it, like in @samp{-A "*.mp3"} or @samp{-A '*.mp3'}.
+
+@item --accept-regex @var{urlregex}
+@itemx --reject-regex @var{urlregex}
+Specify a regular expression to accept or reject the complete URL.
+
+@item --regex-type @var{regextype}
+Specify the regular expression type.  Possible types are @samp{posix} or
+@samp{pcre}.  Note that to be able to use @samp{pcre} type, wget has to be
+compiled with libpcre support.
 
 @item -D @var{domain-list}
 @itemx --domains=@var{domain-list}
@@ -2061,8 +2130,10 @@ dedicated @samp{--page-requisites} option.
 Ignore case when matching files and directories.  This influences the
 behavior of -R, -A, -I, and -X options, as well as globbing
 implemented when downloading from FTP sites.  For example, with this
-option, @samp{-A *.txt} will match @samp{file1.txt}, but also
+option, @samp{-A "*.txt"} will match @samp{file1.txt}, but also
 @samp{file2.TXT}, @samp{file3.TxT}, and so on.
+The quotes in the example are to prevent the shell from expanding the
+pattern.
 
 @item -H
 @itemx --span-hosts
@@ -2830,9 +2901,11 @@ enables it).
 Enable/disable saving pre-converted files with the suffix
 @samp{.orig}---the same as @samp{-K} (which enables it).
 
-@c @item backups = @var{number}
-@c #### Document me!
-@c
+@item backups = @var{number}
+Use up to @var{number} backups for a file.  Backups are rotated by
+adding an incremental counter that starts at @samp{1}.  The default is
+@samp{0}.
+
 @item base = @var{string}
 Consider relative @sc{url}s in input files (specified via the
 @samp{input} command or the @samp{--input-file}/@samp{-i} option,
@@ -3094,7 +3167,7 @@ display properly---the same as @samp{-p}.
 Change setting of passive @sc{ftp}, equivalent to the
 @samp{--passive-ftp} option.
 
-@itemx password = @var{string}
+@item password = @var{string}
 Specify password @var{string} for both @sc{ftp} and @sc{http} file retrieval. 
 This command can be overridden using the @samp{ftp_password} and 
 @samp{http_password} command for @sc{ftp} and @sc{http} respectively.
@@ -3605,7 +3678,7 @@ In addition to the environment variables, proxy location and settings
 may be specified from within Wget itself.
 
 @table @samp
-@itemx --no-proxy
+@item --no-proxy
 @itemx proxy = on/off
 This option and the corresponding command may be used to suppress the
 use of proxy, even if the appropriate environment variables are set.
@@ -4317,7 +4390,7 @@ subscribers of the Wget mailing list.
 @appendix Copying this manual
   
 @menu
-* GNU Free Documentation License::  Licnse for copying this manual.
+* GNU Free Documentation License::  License for copying this manual.
 @end menu
 
 @node GNU Free Documentation License,  , Copying this manual, Copying this manual

m4/wget.m4

@@ -51,8 +51,8 @@ dnl /usr/local/include (!), which GCC uses before /usr/include.
 
 AC_DEFUN([WGET_FNMATCH], [
   AC_MSG_CHECKING([for working fnmatch.h])
-  AC_COMPILE_IFELSE([#include <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.])

po/POTFILES.in

@@ -5,8 +5,12 @@
 
 # Package source files
 lib/error.c
+lib/gai_strerror.c
 lib/getopt.c
 lib/quotearg.c
+lib/spawn-pipe.c
+lib/w32spawn.h
+lib/wait-process.c
 lib/xalloc-die.c
 src/connect.c
 src/convert.c
@@ -32,3 +36,4 @@ src/retr.c
 src/spider.c
 src/url.c
 src/utils.c
+src/warc.c

src/ChangeLog

@@ -1,3 +1,457 @@
+2014-01-05  Håkon Vågsether <hauk142@gmail.com> (tiny change)
+
+	* http.c (http_loop): Fix checking the URL length when filename is
+	specified.
+
+2013-12-29  Giuseppe Scrivano  <gscrivan@redhat.com>
+
+	* init.c (home_dir): Remove useless 'if'.
+	* warc.c (warc_start_new_file): Likewise.
+	(warc_process_cdx_line): Likewise.
+	(warc_write_response_record): Likewise.
+
+2013-12-26  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* gnutls.c (ssl_connect_wget): Fix connect timeout failure
+
+2013-11-02  Giuseppe Scrivano  <gscrivan@redhat.com>
+
+	* http.c (gethttp): Increase max header value length to 512.
+
+2013-01-30  Pavel Mateja  <pavel@netsafe.cz> (tiny change)
+
+	* http.c (gethttp): Specify "Host" for CONNECT method.
+
+2013-10-30  Giuseppe Scrivano  <gscrivan@redhat.com>
+
+	* http.c (skip_short_body): Remove assert which is always true.
+	Reported by: David Binderman <dcb314@hotmail.com>
+
+2013-10-17  Andrea Urbani  <matfanjol@mail.com>
+
+	* ftp.c (getftp): force "LIST" or "LIST -a"
+	  according to the remote system type. If the remote
+	  system is not known, it tries, only the first time,
+	  "LIST -a", after "LIST" and decides which one to use.
+	  For more information look for "__LIST_A_EXPLANATION__"
+	* ftp.h (enum ustype): New ustype enum.
+	* ftp.h (ftp_syst): New enum ustype *unix_type parameter.
+	* ftp.h (ftp_list): Removed enum stype rs parameter, added.
+	  bool avoid_list_a, bool avoid_list, bool *list_a_used
+	  parameters.
+	* ftp.h (wget_ftp_fstatus): New AVOID_LIST_A, AVOID_LIST,
+	  LIST_AFTER_LIST_A_CHECK_DONE values.
+	* ftp-basic.c (ftp_list): it handles the new avoid_list_a,
+	  avoid_list and list_a_used parameters.
+	* ftp.h (ftp_syst): it stores information about the "215 UNIX"
+	  systems into the new unix_type parameter.
+
+2013-10-26  Bykov Aleksey <gnfalex@rambler.ru>
+
+	* utils.c (match_tail): Fix cookies reject
+
+	* ftp-ls.c (ftp_parse_unix_ls): Fix parsing month name in uppercase
+
+2013-09-09  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* gnutls.c (ssl_connect_wget): changed checking of option "PFS"
+	  to be better prepared for some kinds of backports.
+	  Reported by: Daniel Kahn Gillmor <dkg@fifthhorseman.net>
+
+2013-10-10  Giuseppe Scrivano  <gscrivan@redhat.com>
+
+	* url.c (url_parse): Try to convert UTF-8 URLs to IDN.
+	* html-url.c (append_url): Parse URLs specifying an IRI structure.
+
+2013-09-13  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* recur.c (download_child_p): fix compile error when
+	  configured using --without-ssl.
+
+2013-09-07  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* gnutls.c (ssl_connect_wget): use gnutls_check_version()
+	  to check if option "PFS" is available
+	  Reported by: Daniel Kahn Gillmor <dkg@fifthhorseman.net>
+
+2013-09-03  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* main.c: Add new value 'PFS' to --secure-protocol to
+	  enforce the so-called Perfect Forward Security.
+	* init.c (cmd_spec_secure_protocol): added secure_protocol_pfs
+	* openssl.c, gnutls.c, options.h: likewise
+
+2013-08-22  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* main.c: Add new option --https-only.
+	* options.h: Likewise.
+	* recur.c (download_child_p): add check for HTTPS.
+
+2013-08-09  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* gnutls.c (ssl_init): Prevent CA files from being loaded twice
+	  if possible.
+	* gnutls.c (ssl_check_certificate): Added some error messages
+	* gnutls.c: Fixed some compiler warnings
+
+2013-08-08  Will Dietz  <w@wdtz.org> (tiny change):
+
+	* main.c (format_and_print_line): Wrap correctly long tokens.
+
+2013-07-16  Darshit Shah  <darnir@gmail.com>
+
+	* wget.h (err_t): Added new errors, ATTRMISSING and UNKNOWNATTR to
+	handle missing attributes and Unknown attribute values respectively in
+	HTTP Headers.
+	* exits.c (get_status_for_err): ATTRMISSING is a Protocol Error while
+	UNKNOWNATTR is a general error, presumably because of a feature that
+	is not yet implemented.
+	* http.c (gethttp): Call create_authorization_line () separately. In
+	case the auth_err flag has been set with an error, handle it and exit.
+	* http.c (create_authorization_line): Pass a pointer, auth_err to set
+	the flag for different kinds of errors encountered.
+	* http.c (http_loop): Handle the errors raised by the authentication
+	handlers.
+	* http.c (digest_authentication_encode): Pass pointer auth_err to set
+	the error flags.
+	Set qop to NULL in case the value of the qop / algorithm attribute is
+	unknown to Wget. Set an	appropriate error too.
+
+2013-07-13  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* http.c (digest_authentication_encode): Fix a crash when the algorithm
+	is not specified in the server response.  Free dynamic memory used by
+	the function when the function exits.
+	* http-ntlm.c [HAVE_NETTLE]: Include <nettle/md4.h> and <nettle/des.h>.
+	(setup_des_key) [HAVE_NETTLE]: New function to deal with
+	libnettle.
+	(calc_resp) [HAVE_NETTLE]: Add support for libnettle.
+	(mkhash) [HAVE_NETTLE]: Likewise.
+	Reported by: Tim Ruehsen  <tim.ruehsen@gmx.de>.
+
+2013-07-13  Steven M. Schweda <sms@antinode.info>
+
+	* warc.c (warc_tempfile): Fix a portability issue on VMS.
+
+2013-07-10  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* http.c (read_response_body) [ALLOW_CLOBBER]: Move definition to..
+	* options.h (struct options): Make `backups' an int.
+	* url.h [ALLOW_CLOBBER]: .. Here.  Do not clobber when backups are used.
+	* url.c (url_file_name): Use the ALLOW_CLOBBER macro instead of
+	repeating the code.
+
+2013-07-08  Steven M. Schweda <sms@antinode.info>
+
+	* retr.c (rotate_backups): Support for VMS files.
+
+2013-07-12  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* http.c (digest_authentication_encode): Set default value of
+	`algorithm' to "MD5".  Check if `qop' is not-NULL before access it.
+
+2013-07-11  Karsten Hopp  <karsten@redhat.com>
+
+	* openssl.c (struct openssl_read_args, struct scwt_context): New struct.
+	(openssl_read, ssl_connect_with_timeout_callback): New function.
+	(ssl_connect_wget): respect connect timeout.
+
+2013-07-11  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+        * gnutls.c (ssl_connect_wget): respect connect timeout.
+
+2013-07-11  Tomas Hozza  <thozza@redhat.com>
+
+	* ftp.c (ftp_loop): Use ftp_retrieve_glob() also in case
+	--preserve-permissions was specified.
+
+2013-03-20  Tomas Hozza  <thozza@redhat.com>
+
+	* http.c (gethttp): Set "sock" to -1 if it's not and we have no
+	persistent connection
+
+2013-04-26  Tomas Hozza  <thozza@redhat.com> (tiny change)
+
+	* log.c (redirect_output): Use DEFAULT_LOGFILE in diagnostic message
+	when `logfile' is NULL.
+	* utils.c (unique_create): Ensure `logfile' has always a value.
+
+2013-06-26  Darshit Shah <darnir@gmail.com>
+
+	* http.c (gethttp): Reverse change by commit 90896 that prevented
+	downloading response body data to non-GET Request methods.
+
+2013-06-19 Ciprian Vieru <devel.php@gmail.com> (tiny change)
+
+        * html-url.c: Define TAG_TD, TAG_TH, TAG_VIDEO, TAG_AUDIO, TAG_SOURCE.
+	(tag_url_attributes, known_tags): Likewise.
+
+2013-06-22  Ángel González <keisial@gmail.com>
+
+	* init.c (cmd_string_uppercase): Rewrite function.
+
+2013-06-19  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* connect.c (socket_ip_address): zero out ip address structure to
+	avoid access to uninitialized values by inet_ntop().
+	* ftp.c (ftp_loop_internal): fix segfault caused by warc_tmp NULL pointer.
+
+2013-05-21  Ray Satiro  <raysatiro@yahoo.com>
+
+	* url.c (url_file_name): Use MAX_PATH in Windows.
+
+2013-06-13  Darshit Shah  <darnir@gmail.com>
+
+	* http.c (gethttp): Follow RFC 2616 and httpbis specifications when
+	handling redirections. Do not suspend the method on 301/302 redirects.
+	(gethttp): If method if not GET, we do not intend to download
+	anything.
+	* main.c (main): Set spider mode when opt.method is HEAD. This will
+	prevent Wget from downloading any file.
+	* retr.c (SUSPEND_METHOD): Rename macro SUSPEND_POST_DATA to
+	SUSPEND_METHOD to more accurately reflect its use. Similarly rename
+	related variables.
+
+2013-05-14 Bykov Aleksey <gnfalex@rambler.ru>
+
+	* warc.c (warc_tempfile): For fix "Could not open temporary WARC manifest
+	file." issue in Win system force to use `mkostemp(filename, O_TEMPORARY)'
+	instead  of `mkstemp(filename)'. Thank to Angel Gonzalez for help.
+
+2013-05-14  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* cookies.c (cookie_jar_load): Replaced read_whole_file() by getline().
+	* init.c (run_wgetrc): Likewise.
+	* netrc.c (parse_netrc): Likewise.
+	* utils.c: Likewise.
+	* ftp.c (getftp): Likewise.
+	* ftp-ls.c (ftp_parse_unix_ls, ftp_parse_winnt_ls, ftp_parse_vms_ls): Likewise.
+	* ftp-ls.c (clean_line): Accept the string length as parameter.
+	* ftp-ls.c: Replaced indent tabs by spaces.
+	* ftp.c: Likewise.
+	* utils.c: Removed read_whole_file() definition.
+	* netrc.c: Removed read_whole_file() definition for STANDALONE.
+	* utils.h: Removed read_whole_file() declaration.
+
+2013-05-09  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* utils.c (acceptable): use standard string functions instead of
+	self-written code.
+	(match_tail): Likewise.
+	(suffix): Likewise.
+	(has_wildcards_p): Likewise.
+	(test_subdir_p): Fix some warnings.
+	(test_dir_matches_p): Likewise.
+
+2013-05-05  mancha  <mancha1@hush.com> (tiny change)
+
+	* gnutls.c (ssl_connect_wget): Don't abort on non-fatal alerts
+        received during handshake. For example, when connecting to servers
+        using TSL-SNI that send warning-level unrecognized_name alerts.
+
+2013-05-04  Darshit Shah <darnir@gmail.com>
+
+	* init.c (cmd_string_uppercase): Fix issue that cased invalid headers
+	when converting to uppercase.
+
+2013-05-01  Gijs van Tulder  <gvtulder@gmail.com>
+
+	* retr.c (retrieve_url): New variable `saved_method'.
+	(SUSPEND_POST_DATA): Save the method to `saved_method'.
+	(RESTORE_POST_DATA): Restore the method from `saved_method'.
+
+2013-05-01  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* init.c: Declare `cmd_string_uppercase'.
+	(commands): Now `method' uses cmd_string_uppercase.
+	(cmd_string_uppercase): New method
+	* http.c (gethttp): Do not transform opt.method to uppercase.
+	Reported by: Stefano Lattarini <stefano.lattarini@gmail.com>
+
+2013-04-24  Darshit Shah <darnir@gmail.com>
+
+	* http.c (gethttp): Remove check for opt.post_data and
+	opt.post_file_name.
+	* main.c (main): Change location in code where --post-data and
+	--post-file options are converted to --body-data --body-file.
+
+2013-04-21  Gijs van Tulder  <gvtulder@gmail.com>
+
+	* http.c: Copy opt.body_data to the WARC file, instead of
+	opt.post_data (the old option).
+
+2013-04-12  Gijs van Tulder  <gvtulder@gmail.com>
+
+	* warc.c: Generate unique UUIDs for the manifest and the record
+	holding the command-line arguments.
+	Write the manifest to a "metadata" record to follow the WARC
+	implementation guidelines.
+	* warc.h: Declare new function warc_write_metadata_record.
+
+2013-03-15  Darshit Shah <darnir@gmail.com>
+
+	* http.c (post_file): Rename function to body_file_send to more
+	accurately reflect its use.
+	* http.c (gethttp): Add support for --method, --body-data and
+	--body-file
+	* init.c (commands): Same.
+	* options.h (options): Same.
+	* main.c (option_data): Same.
+	* main.c (print_help): Add --method command.
+	* main.c (main): Make old --post-{data,file} commands aliases to
+	--method.
+	Add sanity checks for --method, --body-data and --body-file.
+	* retr.c (SUSPEND_POST_DATA): Edit Macro Definition to use body_data.
+	* retr.c (RESTORE_POST_DATA): Same.
+
+2013-03-31  Gijs van Tulder  <gvtulder@gmail.com>
+
+	* warc.c: Correctly write the field length in the skip length field
+	of .warc.gz files. (Following the GZIP spec in RFC 1952.)
+
+2013-03-12  Darshit Shah <darnir@gmail.com>
+
+	* http.c (gethttp): Make wget return FILEBADFILE error and abort if
+	post-file does not exist.
+
+	* http.c (http_loop): Handle FILEBADFILE as a valid err.
+
+	* exits.c (get_status_for_err): Mark FILEBADFILE as an IO error.
+
+2013-02-15  Darshit Shah <darnir@gmail.com>
+
+	* cookies.c (cookie_handle_set_cookie): Set cookie->discard_requested
+	to true on domain mismatch.
+
+2012-12-20  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* gnutls.c (ssl_connect_wget): added +VERS-SSL3.0 to fix
+	--secure-protocol=SSLv2/SSLv3.
+
+2012-12-09  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* main.c (main): Keep looking for "config" until there are
+	arguments to parse.
+	Reported by: Adrien Dumont <adr.dum@hotmail.fr>
+
+	* test.c: Include "wget.h".
+
+2012-12-08  Michael Stapelberg <michael@stapelberg.de> (tiny change)
+
+	* retr.c (retrieve_url): Set iri->orig_url to NULL after it is
+	freed.
+
+2012-11-26  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* wget.h (MAX_INT_TO_STRING_LEN): Define macro.
+	* warc.c (warc_write_block_from_file): Use `MAX_INT_TO_STRING_LEN'
+	to find the buffer size.
+	(warc_write_cdx_record): Likewise.
+
+2012-09-03  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* http.c (digest_authentication_encode): Add support for RFC 2617
+	MD5-sess authentication algorithm.
+	Feature request and testing by: Avinash <pavinash@gmail.com>
+
+2012-11-14  Ángel González  <keisial@gmail.com>
+
+	* warc.c (warc_sha1_stream_with_payload): Fix compilation under
+	gcc -std=c89.
+
+2012-11-24  Gijs van Tulder  <gvtulder@gmail.com>
+
+	* warc.c (warc_write_cdx_record): Use `number_to_string' to
+	convert the offset to a string.
+
+2012-11-24  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* warc.c (warc_write_block_from_file): Use `number_to_string' to
+	convert the content-length to a string.
+
+2012-11-15  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* retr.c (write_data): Fix comment.
+
+2012-11-13  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* retr.c (fd_read_body): Correctly check the return code from
+	write_data.
+	Reported by: Torsten Scheck <torsten.scheck@gmx.de>
+
+2012-08-29  Rohit Mathulla <rohit_mathulla@yahoo.com> (tiny change)
+
+	* html-url.c (get_urls_file): Convert shorthand URLs.
+
+2012-10-07  Ray Satiro <raysatiro@yahoo.com>
+
+	* url.c: Change the functions of a growable string object to null
+	terminate the string.
+	* url.c (append_null): New function to null terminate a growable
+	string object.
+	* url.c (shorten_length): New function to shorten the length of a
+	growable string object.
+
+2012-10-03 Merinov Nikolay <kim.roader@gmail.com>
+
+	* ftp.c (ftp_loop_internal): Ignore --no-clobber option when
+	receiving directory listing.
+
+2012-10-07  Tim Ruehsen  <tim.ruehsen@gmx.de>
+	    Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* utils.c (get_max_length): If `pathconf' is not available
+	fallback to PATH_MAX.
+
+2012-10-06  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* http.c (http_loop): Send a HEAD request when -c and
+	--content-disposition are used together.
+
+2012-09-29 Merinov Nikolay <kim.roader@gmail.com>
+
+	* ftp-ls.c (ftp_parse_winnt_ls): Support filename extracting with
+	new listing format.
+
+2012-09-29  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* url.h (CHOMP_BUFFER): Add definition.
+	* url.c (url_file_name): New local variables `fname_len_check' and
+	`max_length'. Check that the length of the file name is acceptable.
+	* utils.h (get_max_length): Declare function.
+	* utils.c (get_max_length): New function.
+
+2012-09-28  Steven Schubiger  <stsc@member.fsf.org>
+
+	* src/recur.c (retrieve_tree): Combine duplicated code.
+
+2012-09-02  Nguyễn Thái Ngọc Duy  <pclouds@gmail.com> (tiny change)
+
+	* src/main.c (main): mark more strings for translation.
+	* src/mswindows.c (fork_to_background): Likewise.
+	* src/recur.c (download_child_p): Likewise.
+
+2012-08-28  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* gnutls.c (ssl_check_certificate): deinit gnutls_x509_crt_t.
+	* gnutls.c (ssl_init): don't error if CA directory is empty.
+
+2012-07-07  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+	* html-url.c (cleanup_html_url): Remove "static" modifier.
+	* init.c (cleanup_html_url): Likewise.
+	Reported by: Mike Frysinger <vapier@gentoo.org>.
+
+2012-08-25  Hrvoje Niksic  <hniksic@gmail.com>
+
+	* warc.c (warc_find_duplicate_cdx_record): Use hash_table_get
+	instead of hash_table_get_pair.
+
+2012-08-21  <y-iida@secom.co.jp> (tiny change)
+
+	* connect.c (connect_to_ip) [ENABLE_IPV6]: Attempt to use IPv6.
+	* http.c (gethttp): Likewise.
+
 2012-07-03  Steven Schubiger  <stsc@member.fsf.org>
 
 	* init.c: Include warc.h for warc_close in cleanup function.

src/connect.c

@@ -294,8 +294,10 @@ connect_to_ip (const ip_address *ip, int port, const char *print)
        {
            if (ip->family == AF_INET)
                logprintf (LOG_VERBOSE, _("Connecting to %s:%d... "), txt_addr, port);
+#ifdef ENABLE_IPV6
            else if (ip->family == AF_INET6)
                logprintf (LOG_VERBOSE, _("Connecting to [%s]:%d... "), txt_addr, port);
+#endif
        }
     }
 
@@ -557,6 +559,7 @@ socket_ip_address (int sock, ip_address *ip, int endpoint)
   if (ret < 0)
     return false;
 
+  memset(ip, 0, sizeof(ip_address));
   ip->family = sockaddr->sa_family;
   switch (sockaddr->sa_family)
     {

src/cookies.c

@@ -673,9 +673,6 @@ cookie_handle_set_cookie (struct cookie_jar *jar,
 
   if (!cookie->domain)
     {
-    copy_domain:
-      /* If the domain was not provided, we use the one we're talking
-         to, and set exact match.  */
       cookie->domain = xstrdup (host);
       cookie->domain_exact = 1;
       /* Set the port, but only if it's non-default. */
@@ -687,11 +684,12 @@ cookie_handle_set_cookie (struct cookie_jar *jar,
       if (!check_domain_match (cookie->domain, host))
         {
           logprintf (LOG_NOTQUIET,
-                     _("Cookie coming from %s attempted to set domain to %s\n"),
-                     quotearg_style (escape_quoting_style, host),
+                     _("Cookie coming from %s attempted to set domain to "),
+                     quotearg_style (escape_quoting_style, host));
+          logprintf (LOG_NOTQUIET,
+                     _("%s\n"),
                      quotearg_style (escape_quoting_style, cookie->domain));
-          xfree (cookie->domain);
-          goto copy_domain;
+          cookie->discard_requested = true;
         }
     }
 
@@ -1131,7 +1129,9 @@ domain_port (const char *domain_b, const char *domain_e,
 void
 cookie_jar_load (struct cookie_jar *jar, const char *file)
 {
-  char *line;
+  char *line = NULL;
+  size_t bufsize = 0;
+
   FILE *fp = fopen (file, "r");
   if (!fp)
     {
@@ -1139,9 +1139,10 @@ cookie_jar_load (struct cookie_jar *jar, const char *file)
                  quote (file), strerror (errno));
       return;
     }
+
   cookies_now = time (NULL);
 
-  for (; ((line = read_whole_line (fp)) != NULL); xfree (line))
+  while (getline (&line, &bufsize, fp) > 0)
     {
       struct cookie *cookie;
       char *p = line;
@@ -1235,6 +1236,8 @@ cookie_jar_load (struct cookie_jar *jar, const char *file)
     abort_cookie:
       delete_cookie (cookie);
     }
+
+  xfree(line);
   fclose (fp);
 }
 

src/exits.c

@@ -58,7 +58,7 @@ get_status_for_err (uerr_t err)
     case RETROK:
       return WGET_EXIT_SUCCESS;
     case FOPENERR: case FOPEN_EXCL_ERR: case FWRITEERR: case WRITEFAILED:
-    case UNLINKERR: case CLOSEFAILED:
+    case UNLINKERR: case CLOSEFAILED: case FILEBADFILE:
       return WGET_EXIT_IO_FAIL;
     case NOCONERROR: case HOSTERR: case CONSOCKERR: case CONERROR:
     case CONSSLERR: case CONIMPOSSIBLE: case FTPRERR: case FTPINVPASV:
@@ -68,7 +68,7 @@ get_status_for_err (uerr_t err)
       return WGET_EXIT_SSL_AUTH_FAIL;
     case FTPLOGINC: case FTPLOGREFUSED: case AUTHFAILED:
       return WGET_EXIT_SERVER_AUTH_FAIL;
-    case HEOF: case HERR:
+    case HEOF: case HERR: case ATTRMISSING:
       return WGET_EXIT_PROTOCOL_ERROR;
     case WRONGCODE: case FTPPORTERR: case FTPSYSERR:
     case FTPNSFOD: case FTPUNKNOWNTYPE: case FTPSRVERR:
@@ -76,7 +76,7 @@ get_status_for_err (uerr_t err)
     case CONTNOTSUPPORTED: case RANGEERR: case RETRBADPATTERN:
     case PROXERR:
       return WGET_EXIT_SERVER_ERROR;
-    case URLERROR: case QUOTEXC: case SSLINITFAILED:
+    case URLERROR: case QUOTEXC: case SSLINITFAILED: case UNKNOWNATTR:
     default:
       return WGET_EXIT_UNKNOWN;
     }

src/ftp-basic.c

@@ -960,23 +960,32 @@ ftp_retr (int csock, const char *file)
 /* Sends the LIST command to the server.  If FILE is NULL, send just
    `LIST' (no space).  */
 uerr_t
-ftp_list (int csock, const char *file, enum stype rs)
+ftp_list (int csock, const char *file, bool avoid_list_a, bool avoid_list,
+          bool *list_a_used)
 {
   char *request, *respline;
   int nwritten;
   uerr_t err;
   bool ok = false;
   size_t i = 0;
-  /* Try `LIST -a' first and revert to `LIST' in case of failure.  */
+
+  *list_a_used = false;
+
+  /* 2013-10-12 Andrea Urbani (matfanjol)
+     For more information about LIST and "LIST -a" please look at ftp.c,
+     function getftp, text "__LIST_A_EXPLANATION__".
+
+     If somebody changes the following commands, please, checks also the
+     later "i" variable.  */
   const char *list_commands[] = { "LIST -a",
                                   "LIST" };
 
-  /* 2008-01-29  SMS.  For a VMS FTP server, where "LIST -a" may not
-     fail, but will never do what is desired here, skip directly to the
-     simple "LIST" command (assumed to be the last one in the list).
-  */
-  if (rs == ST_VMS)
-    i = countof (list_commands)- 1;
+  if (avoid_list_a)
+    {
+      i = countof (list_commands)- 1;
+      DEBUGP (("(skipping \"LIST -a\")"));
+    }
+
 
   do {
     /* Send request.  */
@@ -1000,6 +1009,8 @@ ftp_list (int csock, const char *file, enum stype rs)
           {
             err = FTPOK;
             ok = true;
+            /* Which list command was used? */
+            *list_a_used = (i == 0);
           }
         else
           {
@@ -1008,6 +1019,12 @@ ftp_list (int csock, const char *file, enum stype rs)
         xfree (respline);
       }
     ++i;
+    if ((avoid_list) && (i == 1))
+      {
+        /* I skip LIST */
+        ++i;
+        DEBUGP (("(skipping \"LIST\")"));
+      }
   } while (i < countof (list_commands) && !ok);
 
   return err;
@@ -1015,7 +1032,7 @@ ftp_list (int csock, const char *file, enum stype rs)
 
 /* Sends the SYST command to the server. */
 uerr_t
-ftp_syst (int csock, enum stype *server_type)
+ftp_syst (int csock, enum stype *server_type, enum ustype *unix_type)
 {
   char *request, *respline;
   int nwritten;
@@ -1048,12 +1065,23 @@ ftp_syst (int csock, enum stype *server_type)
      first word of the server response)?  */
   request = strtok (NULL, " ");
 
+  *unix_type = UST_OTHER;
+
   if (request == NULL)
     *server_type = ST_OTHER;
   else if (!strcasecmp (request, "VMS"))
     *server_type = ST_VMS;
   else if (!strcasecmp (request, "UNIX"))
-    *server_type = ST_UNIX;
+    {
+      *server_type = ST_UNIX;
+      /* 2013-10-17 Andrea Urbani (matfanjol)
+         I check more in depth the system type */
+      if (!strncasecmp (ftp_last_respline, "215 UNIX Type: L8", 17))
+        *unix_type = UST_TYPE_L8;
+      else if (!strncasecmp (ftp_last_respline,
+                             "215 UNIX MultiNet Unix Emulation V5.3(93)", 41))
+        *unix_type = UST_MULTINET;
+    }
   else if (!strcasecmp (request, "WINDOWS_NT")
            || !strcasecmp (request, "WINDOWS2000"))
     *server_type = ST_WINNT;

src/ftp-ls.c

@@ -68,16 +68,17 @@ symperms (const char *s)
    replaces all <TAB> character with <SPACE>. Returns the length of the
    modified line. */
 static int
-clean_line(char *line)
+clean_line (char *line, int len)
 {
-  int len = strlen (line);
-  if (!len) return 0;
-  if (line[len - 1] == '\n')
+  if (len <= 0) return 0;
+
+  while (len > 0 && (line[len - 1] == '\n' || line[len - 1] == '\r'))
     line[--len] = '\0';
+
   if (!len) return 0;
-  if (line[len - 1] == '\r')
-    line[--len] = '\0';
+
   for ( ; *line ; line++ ) if (*line == '\t') *line = ' ';
+
   return len;
 }
 
@@ -102,8 +103,9 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
   int hour, min, sec, ptype;
   struct tm timestruct, *tnow;
   time_t timenow;
+  size_t bufsize = 0;
 
-  char *line, *tok, *ptok;      /* tokenizer */
+  char *line = NULL, *tok, *ptok;      /* tokenizer */
   struct fileinfo *dir, *l, cur; /* list creation */
 
   fp = fopen (file, "rb");
@@ -115,22 +117,16 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
   dir = l = NULL;
 
   /* Line loop to end of file: */
-  while ((line = read_whole_line (fp)) != NULL)
+  while ((len = getline (&line, &bufsize, fp)) > 0)
     {
-      len = clean_line (line);
+      len = clean_line (line, len);
       /* Skip if total...  */
       if (!strncasecmp (line, "total", 5))
-        {
-          xfree (line);
-          continue;
-        }
+        continue;
       /* Get the first token (permissions).  */
       tok = strtok (line, " ");
       if (!tok)
-        {
-          xfree (line);
-          continue;
-        }
+        continue;
 
       cur.name = NULL;
       cur.linkto = NULL;
@@ -203,7 +199,7 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
           if (next < 0)         /* a month name was not encountered */
             {
               for (i = 0; i < 12; i++)
-                if (!strcmp (tok, months[i]))
+                if (!strcasecmp (tok, months[i]))
                   break;
               /* If we got a month, it means the token before it is the
                  size, and the filename is three tokens away.  */
@@ -368,7 +364,6 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
           DEBUGP (("Skipping.\n"));
           xfree_null (cur.name);
           xfree_null (cur.linkto);
-          xfree (line);
           continue;
         }
 
@@ -416,10 +411,9 @@ ftp_parse_unix_ls (const char *file, int ignore_perms)
       timestruct.tm_isdst = -1;
       l->tstamp = mktime (&timestruct); /* store the time-stamp */
       l->ptype = ptype;
-
-      xfree (line);
     }
 
+  xfree (line);
   fclose (fp);
   return dir;
 }
@@ -431,9 +425,11 @@ ftp_parse_winnt_ls (const char *file)
   int len;
   int year, month, day;         /* for time analysis */
   int hour, min;
+  size_t bufsize = 0;
   struct tm timestruct;
 
-  char *line, *tok;             /* tokenizer */
+  char *line = NULL, *tok;             /* tokenizer */
+  char *filename;
   struct fileinfo *dir, *l, cur; /* list creation */
 
   fp = fopen (file, "rb");
@@ -445,43 +441,53 @@ ftp_parse_winnt_ls (const char *file)
   dir = l = NULL;
 
   /* Line loop to end of file: */
-  while ((line = read_whole_line (fp)) != NULL)
+  while ((len = getline (&line, &bufsize, fp)) > 0)
     {
-      len = clean_line (line);
+      len = clean_line (line, len);
 
-      /* Extracting name is a bit of black magic and we have to do it
-         before `strtok' inserted extra \0 characters in the line
-         string. For the moment let us just suppose that the name starts at
-         column 39 of the listing. This way we could also recognize
-         filenames that begin with a series of space characters (but who
-         really wants to use such filenames anyway?). */
-      if (len < 40) goto continue_loop;
-      tok = line + 39;
-      cur.name = xstrdup(tok);
-      DEBUGP (("Name: '%s'\n", cur.name));
+      /* Name begins at 39 column of the listing if date presented in `mm-dd-yy'
+         format or at 41 column if date presented in `mm-dd-yyyy' format. Thus,
+         we cannot extract name before we parse date. Using this information we
+         also can recognize filenames that begin with a series of space
+         characters (but who really wants to use such filenames anyway?). */
+      if (len < 40) continue;
+      filename = line + 39;
 
-      /* First column: mm-dd-yy. Should atoi() on the month fail, january
-         will be assumed.  */
+      /* First column: mm-dd-yy or mm-dd-yyyy. Should atoi() on the month fail,
+         january will be assumed.  */
       tok = strtok(line, "-");
-      if (tok == NULL) goto continue_loop;
+      if (tok == NULL) continue;
       month = atoi(tok) - 1;
       if (month < 0) month = 0;
       tok = strtok(NULL, "-");
-      if (tok == NULL) goto continue_loop;
+      if (tok == NULL) continue;
       day = atoi(tok);
       tok = strtok(NULL, " ");
-      if (tok == NULL) goto continue_loop;
+      if (tok == NULL) continue;
       year = atoi(tok);
       /* Assuming the epoch starting at 1.1.1970 */
-      if (year <= 70) year += 100;
+      if (year <= 70)
+        {
+          year += 100;
+        }
+      else if (year >= 1900)
+        {
+          year -= 1900;
+          filename += 2;
+        }
+      /* Now it is possible to determine the position of the first symbol in
+         filename. */
+      cur.name = xstrdup(filename);
+      DEBUGP (("Name: '%s'\n", cur.name));
+
 
       /* Second column: hh:mm[AP]M, listing does not contain value for
          seconds */
       tok = strtok(NULL,  ":");
-      if (tok == NULL) goto continue_loop;
+      if (tok == NULL) continue;
       hour = atoi(tok);
       tok = strtok(NULL,  "M");
-      if (tok == NULL) goto continue_loop;
+      if (tok == NULL) continue;
       min = atoi(tok);
       /* Adjust hour from AM/PM. Just for the record, the sequence goes
          11:00AM, 12:00PM, 01:00PM ... 11:00PM, 12:00AM, 01:00AM . */
@@ -512,9 +518,9 @@ ftp_parse_winnt_ls (const char *file)
          directories as the listing does not give us a clue) and filetype
          here. */
       tok = strtok(NULL, " ");
-      if (tok == NULL) goto continue_loop;
+      if (tok == NULL) continue;
       while ((tok != NULL) && (*tok == '\0'))  tok = strtok(NULL, " ");
-      if (tok == NULL) goto continue_loop;
+      if (tok == NULL) continue;
       if (*tok == '<')
         {
           cur.type  = FT_DIRECTORY;
@@ -553,11 +559,9 @@ ftp_parse_winnt_ls (const char *file)
           memcpy (l, &cur, sizeof (cur));
           l->next = NULL;
         }
-
-continue_loop:
-      xfree (line);
     }
 
+  xfree (line);
   fclose(fp);
   return dir;
 }
@@ -678,11 +682,12 @@ ftp_parse_vms_ls (const char *file)
   FILE *fp;
   int dt, i, j, len;
   int perms;
+  size_t bufsize = 0;
   time_t timenow;
   struct tm *timestruct;
   char date_str[ 32];
 
-  char *line, *tok;		 /* tokenizer */
+  char *line = NULL, *tok; /* tokenizer */
   struct fileinfo *dir, *l, cur; /* list creation */
 
   fp = fopen (file, "r");
@@ -695,52 +700,34 @@ ftp_parse_vms_ls (const char *file)
 
   /* Skip blank lines, Directory heading, and more blank lines. */
 
-  j = 0; /* Expecting initial blank line(s). */
-  while (1)
+  for (j = 0; (i = getline (&line, &bufsize, fp)) > 0; )
     {
-      line = read_whole_line (fp);
-      if (line == NULL)
+      i = clean_line (line, i);
+      if (i <= 0)
+        continue; /* Ignore blank line. */
+
+      if ((j == 0) && (line[i - 1] == ']'))
         {
-        break;
+          /* Found Directory heading line.  Next non-blank line
+          is significant. */
+          j = 1;
+        }
+      else if (!strncmp (line, "Total of ", 9))
+        {
+          /* Found "Total of ..." footing line.  No valid data
+             will follow (empty directory). */
+          i = 0; /* Arrange for early exit. */
+          break;
         }
       else
         {
-          i = clean_line (line);
-          if (i <= 0)
-            {
-              xfree (line); /* Free useless line storage. */
-              continue; /* Blank line.  Keep looking. */
-            }
-          else
-            {
-              if ((j == 0) && (line[ i- 1] == ']'))
-                {
-                  /* Found Directory heading line.  Next non-blank line
-                  is significant.
-                  */
-                  j = 1;
-                }
-              else if (!strncmp (line, "Total of ", 9))
-                {
-                  /* Found "Total of ..." footing line.  No valid data
-                     will follow (empty directory).
-                  */
-                  xfree (line); /* Free useless line storage. */
-                  line = NULL; /* Arrange for early exit. */
-                  break;
-                }
-              else
-                {
-                  break; /* Must be significant data. */
-                }
-            }
-          xfree (line); /* Free useless line storage. */
+          break; /* Must be significant data. */
         }
     }
 
   /* Read remainder of file until the next blank line or EOF. */
 
-  while (line != NULL)
+  while (i > 0)
     {
       char *p;
 
@@ -831,9 +818,8 @@ ftp_parse_vms_ls (const char *file)
       if (tok == NULL)
         {
           DEBUGP (("Getting additional line.\n"));
-          xfree (line);
-          line = read_whole_line (fp);
-          if (!line)
+          i = getline (&line, &bufsize, fp);
+          if (i <= 0)
             {
               DEBUGP (("EOF.  Leaving listing parser.\n"));
               break;
@@ -842,14 +828,14 @@ ftp_parse_vms_ls (const char *file)
           /* Second line must begin with " ".  Otherwise, it's a first
              line (and we may be confused).
           */
+          i = clean_line (line, i);
           if (i <= 0)
             {
               /* Blank line.  End of significant file listing. */
               DEBUGP (("Blank line.  Leaving listing parser.\n"));
-              xfree (line); /* Free useless line storage. */
               break;
             }
-          else if (line[ 0] != ' ')
+          else if (line[0] != ' ')
             {
               DEBUGP (("Non-blank in column 1.  Must be a new file name?\n"));
               continue;
@@ -861,7 +847,6 @@ ftp_parse_vms_ls (const char *file)
                 {
                   /* Unexpected non-empty but apparently blank line. */
                   DEBUGP (("Null token.  Leaving listing parser.\n"));
-                  xfree (line); /* Free useless line storage. */
                   break;
                 }
             }
@@ -900,7 +885,7 @@ ftp_parse_vms_ls (const char *file)
                        (sizeof( date_str)- strlen (date_str) - 1));
               DEBUGP (("Date time: >%s<\n", date_str));
             }
-          else if (strchr ( tok, '[') != NULL)
+          else if (strchr (tok, '[') != NULL)
             {
               /* Owner.  (Ignore.) */
               DEBUGP (("Owner.\n"));
@@ -910,7 +895,7 @@ ftp_parse_vms_ls (const char *file)
               /* Protections (permissions). */
               perms = 0;
               j = 0;
-              for (i = 0; i < strlen( tok); i++)
+              for (i = 0; i < strlen(tok); i++)
                 {
                   switch (tok[ i])
                     {
@@ -1004,21 +989,19 @@ ftp_parse_vms_ls (const char *file)
           l->next = NULL;
         }
 
-      /* Free old line storage.  Read a new line. */
-      xfree (line);
-      line = read_whole_line (fp);
-      if (line != NULL)
+      i = getline (&line, &bufsize, fp);
+      if (i > 0)
         {
-          i = clean_line (line);
+          i = clean_line (line, i);
           if (i <= 0)
-	    {
+            {
               /* Blank line.  End of significant file listing. */
-              xfree (line); /* Free useless line storage. */
-	      break;
-	    }
+              break;
+            }
         }
     }
 
+  xfree (line);
   fclose (fp);
   return dir;
 }

src/ftp.c

@@ -70,6 +70,7 @@ typedef struct
   int csock;                    /* control connection socket */
   double dltime;                /* time of the download in msecs */
   enum stype rs;                /* remote system reported by ftp server */
+  enum ustype rsu;              /* when rs is ST_UNIX, here there are more details */
   char *id;                     /* initial directory */
   char *target;                 /* target file name */
   struct url *proxy;            /* FTWK-style proxy */
@@ -255,8 +256,10 @@ getftp (struct url *u, wgint passed_expected_bytes, wgint *qtyread,
   bool got_expected_bytes = false;
   bool rest_failed = false;
   int flags;
-  wgint rd_size;
+  wgint rd_size, previous_rd_size = 0;
   char type_char;
+  bool try_again;
+  bool list_a_used = false;
 
   assert (con != NULL);
   assert (con->target != NULL);
@@ -365,7 +368,7 @@ Error in server response, closing control connection.\n"));
       /* Third: Get the system type */
       if (!opt.server_response)
         logprintf (LOG_VERBOSE, "==> SYST ... ");
-      err = ftp_syst (csock, &con->rs);
+      err = ftp_syst (csock, &con->rs, &con->rsu);
       /* FTPRERR */
       switch (err)
         {
@@ -390,6 +393,44 @@ Error in server response, closing control connection.\n"));
       if (!opt.server_response && err != FTPSRVERR)
         logputs (LOG_VERBOSE, _("done.    "));
 
+      /* 2013-10-17 Andrea Urbani (matfanjol)
+         According to the system type I choose which
+         list command will be used.
+         If I don't know that system, I will try, the
+         first time of each session, "LIST -a" and
+         "LIST". (see __LIST_A_EXPLANATION__ below) */
+      switch (con->rs)
+        {
+        case ST_VMS:
+          /* About ST_VMS there is an old note:
+             2008-01-29  SMS.  For a VMS FTP server, where "LIST -a" may not
+             fail, but will never do what is desired here,
+             skip directly to the simple "LIST" command
+             (assumed to be the last one in the list).  */
+          DEBUGP (("\nVMS: I know it and I will use \"LIST\" as standard list command\n"));
+          con->st |= LIST_AFTER_LIST_A_CHECK_DONE;
+          con->st |= AVOID_LIST_A;
+          break;
+        case ST_UNIX:
+          if (con->rsu == UST_MULTINET)
+            {
+              DEBUGP (("\nUNIX MultiNet: I know it and I will use \"LIST\" "
+                       "as standard list command\n"));
+              con->st |= LIST_AFTER_LIST_A_CHECK_DONE;
+              con->st |= AVOID_LIST_A;
+            }
+          else if (con->rsu == UST_TYPE_L8)
+            {
+              DEBUGP (("\nUNIX TYPE L8: I know it and I will use \"LIST -a\" "
+                       "as standard list command\n"));
+              con->st |= LIST_AFTER_LIST_A_CHECK_DONE;
+              con->st |= AVOID_LIST;
+            }
+          break;
+        default:
+          break;
+        }
+
       /* Fourth: Find the initial ftp directory */
 
       if (!opt.server_response)
@@ -616,16 +657,16 @@ Error in server response, closing control connection.\n"));
              The VMS restriction may be relaxed when the squirrely code
              above is reformed.
           */
-	  if ((con->rs == ST_VMS) && (target[0] != '/'))
-	    {
-	      cwd_start = 0;
-	      DEBUGP (("Using two-step CWD for relative path.\n"));
-	    }
-	  else
-	    {
+          if ((con->rs == ST_VMS) && (target[0] != '/'))
+            {
+              cwd_start = 0;
+              DEBUGP (("Using two-step CWD for relative path.\n"));
+            }
+          else
+            {
               /* Go straight to the target. */
-	      cwd_start = 1;
-	    }
+              cwd_start = 1;
+            }
 
           /* At least one VMS FTP server (TCPware V5.6-2) can switch to
              a UNIX emulation mode when given a UNIX-like directory
@@ -643,10 +684,10 @@ 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"));
+              DEBUGP (("Using extra \"CWD []\" step for VMS server.\n"));
             }
           else
             {
@@ -656,22 +697,22 @@ Error in server response, closing control connection.\n"));
           /* 2004-09-20 SMS. */
           /* Sorry about the deviant indenting.  Laziness. */
 
-	  for (cwd_count = cwd_start; cwd_count < cwd_end; cwd_count++)
-	{
+          for (cwd_count = cwd_start; cwd_count < cwd_end; cwd_count++)
+            {
           switch (cwd_count)
             {
               case 0:
-	        /* Step one (optional): Go to the initial directory,
-	           exactly as reported by the server.
-	        */
-	        targ = con->id;
+                /* Step one (optional): Go to the initial directory,
+                   exactly as reported by the server.
+                */
+                targ = con->id;
                 break;
 
               case 1:
-	        /* Step two: Go to the target directory.  (Absolute or
-	           relative will work now.)
-	        */
-	        targ = target;
+                /* Step two: Go to the target directory.  (Absolute or
+                   relative will work now.)
+                */
+                targ = target;
                 break;
 
               case 2:
@@ -684,7 +725,7 @@ Error in server response, closing control connection.\n"));
               default:
                 /* Can't happen. */
                 assert (1);
-	    }
+            }
 
           if (!opt.server_response)
             logprintf (LOG_VERBOSE, "==> CWD (%d) %s ... ", cwd_count,
@@ -775,6 +816,9 @@ Error in server response, closing control connection.\n"));
       return RETRFINISHED;
     }
 
+  do
+  {
+  try_again = false;
   /* If anything is to be retrieved, PORT (or PASV) must be sent.  */
   if (cmd & (DO_LIST | DO_RETR))
     {
@@ -938,42 +982,42 @@ Error in server response, closing control connection.\n"));
   if (cmd & DO_RETR)
     {
       /* If we're in spider mode, don't really retrieve anything except
-	 the directory listing and verify whether the given "file" exists.  */
+         the directory listing and verify whether the given "file" exists.  */
       if (opt.spider)
         {
-	  bool exists = false;
-	  uerr_t res;
-	  struct fileinfo *f;
-	  res = ftp_get_listing (u, con, &f);
-	  /* Set the DO_RETR command flag again, because it gets unset when
-	     calling ftp_get_listing() and would otherwise cause an assertion
-	     failure earlier on when this function gets repeatedly called
-	     (e.g., when recursing).  */
-	  con->cmd |= DO_RETR;
-	  if (res == RETROK)
-	    {
-	      while (f)
-		{
-		  if (!strcmp (f->name, u->file))
-		    {
-		      exists = true;
-		      break;
-		    }
-		  f = f->next;
-		}
+          bool exists = false;
+          uerr_t res;
+          struct fileinfo *f;
+          res = ftp_get_listing (u, con, &f);
+          /* Set the DO_RETR command flag again, because it gets unset when
+             calling ftp_get_listing() and would otherwise cause an assertion
+             failure earlier on when this function gets repeatedly called
+             (e.g., when recursing).  */
+          con->cmd |= DO_RETR;
+          if (res == RETROK)
+            {
+              while (f)
+                {
+                  if (!strcmp (f->name, u->file))
+                    {
+                      exists = true;
+                      break;
+                    }
+                  f = f->next;
+                }
               if (exists)
                 {
                   logputs (LOG_VERBOSE, "\n");
                   logprintf (LOG_NOTQUIET, _("File %s exists.\n"),
                              quote (u->file));
                 }
-	      else
+              else
                 {
-		  logputs (LOG_VERBOSE, "\n");
-		  logprintf (LOG_NOTQUIET, _("No such file %s.\n"),
-			     quote (u->file));
-		}
-	    }
+                  logputs (LOG_VERBOSE, "\n");
+                  logprintf (LOG_NOTQUIET, _("No such file %s.\n"),
+                             quote (u->file));
+                }
+            }
           fd_close (csock);
           con->csock = -1;
           fd_close (dtsock);
@@ -1041,7 +1085,8 @@ Error in server response, closing control connection.\n"));
       /* As Maciej W. Rozycki (macro@ds2.pg.gda.pl) says, `LIST'
          without arguments is better than `LIST .'; confirmed by
          RFC959.  */
-      err = ftp_list (csock, NULL, con->rs);
+      err = ftp_list (csock, NULL, con->st&AVOID_LIST_A, con->st&AVOID_LIST, &list_a_used);
+
       /* FTPRERR, WRITEFAILED */
       switch (err)
         {
@@ -1184,20 +1229,20 @@ 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))
-	    {
-	      int res = unlink (con->target);
-	      if (res < 0)
-		{
-		  logprintf (LOG_NOTQUIET, "%s: %s\n", con->target,
-			     strerror (errno));
-		  fd_close (csock);
-		  con->csock = -1;
-		  fd_close (dtsock);
-		  fd_close (local_sock);
-		  return UNLINKERR;
-		}
-	    }
+          if (opt.unlink && file_exists_p (con->target))
+            {
+              int res = unlink (con->target);
+              if (res < 0)
+                {
+                  logprintf (LOG_NOTQUIET, "%s: %s\n", con->target,
+                    strerror (errno));
+                    fd_close (csock);
+                    con->csock = -1;
+                    fd_close (dtsock);
+                    fd_close (local_sock);
+                    return UNLINKERR;
+                }
+            }
 
 #ifdef __VMS
           int open_id;
@@ -1343,8 +1388,10 @@ Error in server response, closing control connection.\n"));
     }
   /* If it was a listing, and opt.server_response is true,
      print it out.  */
-  if (opt.server_response && (con->cmd & DO_LIST))
+  if (con->cmd & DO_LIST)
     {
+      if (opt.server_response)
+        {
 /* 2005-02-25 SMS.
    Much of this work may already have been done, but repeating it should
    do no damage beyond wasting time.
@@ -1367,22 +1414,115 @@ Error in server response, closing control connection.\n"));
         logprintf (LOG_ALWAYS, "%s: %s\n", con->target, strerror (errno));
       else
         {
-          char *line;
-          /* The lines are being read with read_whole_line because of
+          char *line = NULL;
+          size_t bufsize = 0;
+          ssize_t len;
+
+          /* The lines are being read with getline because of
              no-buffering on opt.lfile.  */
-          while ((line = read_whole_line (fp)) != NULL)
+          while ((len = getline (&line, &bufsize, fp)) > 0)
             {
-              char *p = strchr (line, '\0');
-              while (p > line && (p[-1] == '\n' || p[-1] == '\r'))
-                *--p = '\0';
+              while (len > 0 && (line[len - 1] == '\n' || line[len - 1] == '\r'))
+                line[--len] = '\0';
               logprintf (LOG_ALWAYS, "%s\n",
                          quotearg_style (escape_quoting_style, line));
-              xfree (line);
             }
+          xfree (line);
           fclose (fp);
         }
-    } /* con->cmd & DO_LIST && server_response */
+        } /* server_response */
 
+      /* 2013-10-17 Andrea Urbani (matfanjol)
+         < __LIST_A_EXPLANATION__ >
+          After the SYST command, looks if it knows that system.
+          If yes, wget will force the use of "LIST" or "LIST -a".
+          If no, wget will try, only the first time of each session, before the
+          "LIST -a" command and after the "LIST".
+          If "LIST -a" works and returns more or equal data of the "LIST",
+          "LIST -a" will be the standard list command for all the session.
+          If "LIST -a" fails or returns less data than "LIST" (think on the case
+          of an existing file called "-a"), "LIST" will be the standard list
+          command for all the session.
+          ("LIST -a" is used to get also the hidden files)
+
+          */
+      if (!(con->st & LIST_AFTER_LIST_A_CHECK_DONE))
+        {
+          /* We still have to check "LIST" after the first "LIST -a" to see
+             if with "LIST" we get more data than "LIST -a", that means
+             "LIST -a" returned files/folders with "-a" name. */
+          if (con->st & AVOID_LIST_A)
+            {
+              /* LIST was used in this cycle.
+                 Let's see the result. */
+              if (rd_size > previous_rd_size)
+                {
+                  /* LIST returns more data than "LIST -a".
+                     "LIST" is the official command to use. */
+                  con->st |= LIST_AFTER_LIST_A_CHECK_DONE;
+                  DEBUGP (("LIST returned more data than \"LIST -a\": "
+                           "I will use \"LIST\" as standard list command\n"));
+                }
+              else if (previous_rd_size > rd_size)
+                {
+                  /* "LIST -a" returned more data then LIST.
+                     "LIST -a" is the official command to use. */
+                  con->st |= LIST_AFTER_LIST_A_CHECK_DONE;
+                  con->st |= AVOID_LIST;
+                  con->st &= ~AVOID_LIST_A;
+                  /* Sorry, please, download again the "LIST -a"... */
+                  try_again = true;
+                  DEBUGP (("LIST returned less data than \"LIST -a\": I will "
+                           "use \"LIST -a\" as standard list command\n"));
+                }
+              else
+                {
+                  /* LIST and "LIST -a" return the same data. */
+                  if (rd_size == 0)
+                    {
+                      /* Same empty data. We will check both again because
+                         we cannot check if "LIST -a" has returned an empty
+                         folder instead of a folder content. */
+                      con->st &= ~AVOID_LIST_A;
+                    }
+                  else
+                    {
+                      /* Same data, so, better to take "LIST -a" that
+                         shows also hidden files/folders (when present) */
+                      con->st |= LIST_AFTER_LIST_A_CHECK_DONE;
+                      con->st |= AVOID_LIST;
+                      con->st &= ~AVOID_LIST_A;
+                      DEBUGP (("LIST returned the same amount of data of "
+                               "\"LIST -a\": I will use \"LIST -a\" as standard "
+                               "list command\n"));
+                    }
+                }
+            }
+          else
+            {
+              /* In this cycle "LIST -a" should being used. Is it true? */
+              if (list_a_used)
+                {
+                  /* Yes, it is.
+                     OK, let's save the amount of data and try again
+                     with LIST */
+                  previous_rd_size = rd_size;
+                  try_again = true;
+                  con->st |= AVOID_LIST_A;
+                }
+              else
+                {
+                  /* No: something happens and LIST was used.
+                     This means "LIST -a" raises an error. */
+                  con->st |= LIST_AFTER_LIST_A_CHECK_DONE;
+                  con->st |= AVOID_LIST_A;
+                  DEBUGP (("\"LIST -a\" failed: I will use \"LIST\" "
+                           "as standard list command\n"));
+                }
+            }
+        }
+    }
+  } while (try_again);
   return RETRFINISHED;
 }
 
@@ -1424,7 +1564,12 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
 
   /* If the output_document was given, then this check was already done and
      the file didn't exist. Hence the !opt.output_document */
-  if (opt.noclobber && !opt.output_document && file_exists_p (con->target))
+
+  /* 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)
+      && !((con->cmd & DO_LIST) && !(con->cmd & DO_RETR)))
     {
       logprintf (LOG_VERBOSE,
                  _("File %s already there; not retrieving.\n"), quote (con->target));
@@ -1442,21 +1587,6 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
 
   orig_lp = con->cmd & LEAVE_PENDING ? 1 : 0;
 
-  /* For file RETR requests, we can write a WARC record.
-     We record the file contents to a temporary file. */
-  if (warc_enabled && (con->cmd & DO_RETR))
-    {
-      warc_tmp = warc_tempfile ();
-      if (warc_tmp == NULL)
-        return WARC_TMP_FOPENERR;
-
-      if (!con->proxy && con->csock != -1)
-        {
-          warc_ip = (ip_address *) alloca (sizeof (ip_address));
-          socket_ip_address (con->csock, warc_ip, ENDPOINT_PEER);
-        }
-    }
-
   /* THE loop.  */
   do
     {
@@ -1484,6 +1614,21 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
             con->cmd |= DO_CWD;
         }
 
+      /* For file RETR requests, we can write a WARC record.
+         We record the file contents to a temporary file. */
+      if (warc_enabled && (con->cmd & DO_RETR) && warc_tmp == NULL)
+        {
+          warc_tmp = warc_tempfile ();
+          if (warc_tmp == NULL)
+            return WARC_TMP_FOPENERR;
+
+          if (!con->proxy && con->csock != -1)
+            {
+              warc_ip = (ip_address *) alloca (sizeof (ip_address));
+              socket_ip_address (con->csock, warc_ip, ENDPOINT_PEER);
+            }
+        }
+
       /* Decide whether or not to restart.  */
       if (con->cmd & DO_LIST)
         restval = 0;
@@ -1619,7 +1764,7 @@ ftp_loop_internal (struct url *u, struct fileinfo *f, ccon *con, char **local_fi
           /* warc_write_resource_record has also closed warc_tmp. */
         }
 
-      if ((con->cmd & DO_LIST))
+      if (con->cmd & DO_LIST)
         /* This is a directory listing file. */
         {
           if (!opt.remove_listing)
@@ -2278,11 +2423,11 @@ ftp_loop (struct url *u, char **local_file, int *dt, struct url *proxy,
             file_part = u->path;
           ispattern = has_wildcards_p (file_part);
         }
-      if (ispattern || recursive || opt.timestamping)
+      if (ispattern || recursive || opt.timestamping || opt.preserve_perm)
         {
           /* ftp_retrieve_glob is a catch-all function that gets called
-             if we need globbing, time-stamping or recursion.  Its
-             third argument is just what we really need.  */
+             if we need globbing, time-stamping, recursion or preserve
+             permissions.  Its third argument is just what we really need.  */
           res = ftp_retrieve_glob (u, &con,
                                    ispattern ? GLOB_GLOBALL : GLOB_GETONE);
         }

src/ftp.h

@@ -45,6 +45,14 @@ enum stype
   ST_OTHER
 };
 
+/* Extensions of the ST_UNIX */
+enum ustype
+{
+  UST_TYPE_L8,
+  UST_MULTINET,
+  UST_OTHER
+};
+
 extern char ftp_last_respline[];
 
 uerr_t ftp_response (int, char **);
@@ -61,8 +69,8 @@ uerr_t ftp_type (int, int);
 uerr_t ftp_cwd (int, const char *);
 uerr_t ftp_retr (int, const char *);
 uerr_t ftp_rest (int, wgint);
-uerr_t ftp_list (int, const char *, enum stype);
-uerr_t ftp_syst (int, enum stype *);
+uerr_t ftp_list (int, const char *, bool, bool, bool *);
+uerr_t ftp_syst (int, enum stype *, enum ustype *);
 uerr_t ftp_pwd (int, char **);
 uerr_t ftp_size (int, const char *, wgint *);
 
@@ -124,8 +132,23 @@ enum wget_ftp_fstatus
   NOTHING       = 0x0000,	/* Nothing done yet.  */
   ON_YOUR_OWN   = 0x0001,	/* The ftp_loop_internal sets the
 				   defaults.  */
-  DONE_CWD      = 0x0002	/* The current working directory is
+  DONE_CWD      = 0x0002,	/* The current working directory is
 				   correct.  */
+
+  /* 2013-10-17 Andrea Urbani (matfanjol)
+     For more information about the following entries, please,
+     look at ftp.c, function getftp, text "__LIST_A_EXPLANATION__". */
+  AVOID_LIST_A  = 0x0004,	/* It tells us if during this
+				 session we have to avoid the use
+				 of "LIST -a".*/
+  AVOID_LIST    = 0x0008,	/* It tells us if during this
+				 session we have to avoid to use
+				 "LIST". */
+  LIST_AFTER_LIST_A_CHECK_DONE  = 0x0010
+				/* It tells us if we have already
+				 checked "LIST" after the first
+				 "LIST -a" to handle the case of
+				 file/folders named "-a". */
 };
 
 struct fileinfo *ftp_parse_ls (const char *, const enum stype);

src/gnutls.c

@@ -46,6 +46,7 @@ as that of the covered work.  */
 #include "connect.h"
 #include "url.h"
 #include "ptimer.h"
+#include "hash.h"
 #include "ssl.h"
 
 #include <sys/fcntl.h>
@@ -81,49 +82,76 @@ ssl_init (void)
 {
   /* Becomes true if GnuTLS is initialized. */
   static bool ssl_initialized = false;
+  const char *ca_directory;
+  DIR *dir;
+  int ncerts = -1;
 
   /* GnuTLS should be initialized only once. */
   if (ssl_initialized)
     return true;
 
-  const char *ca_directory;
-  DIR *dir;
-
   gnutls_global_init ();
   gnutls_certificate_allocate_credentials (&credentials);
-  gnutls_certificate_set_verify_flags(credentials,
-                                      GNUTLS_VERIFY_ALLOW_X509_V1_CA_CRT);
+  gnutls_certificate_set_verify_flags (credentials,
+                                       GNUTLS_VERIFY_ALLOW_X509_V1_CA_CRT);
 
-  ca_directory = opt.ca_directory ? opt.ca_directory : "/etc/ssl/certs";
+#if GNUTLS_VERSION_MAJOR >= 3
+  if (!opt.ca_directory)
+    ncerts = gnutls_certificate_set_x509_system_trust (credentials);
+#endif
 
-  dir = opendir (ca_directory);
-  if (dir == NULL)
+  /* If GnuTLS version is too old or CA loading failed, fallback to old behaviour.
+   * Also use old behaviour if the CA directory is user-provided.  */
+  if (ncerts <= 0)
     {
-      if (opt.ca_directory)
-        logprintf (LOG_NOTQUIET, _("ERROR: Cannot open directory %s.\n"),
-                   opt.ca_directory);
-    }
-  else
-    {
-      struct dirent *dent;
-      while ((dent = readdir (dir)) != NULL)
+      ca_directory = opt.ca_directory ? opt.ca_directory : "/etc/ssl/certs";
+      if ((dir = opendir (ca_directory)) == NULL)
         {
-          struct stat st;
-          char *ca_file;
-          asprintf (&ca_file, "%s/%s", ca_directory, dent->d_name);
-
-          stat (ca_file, &st);
-
-          if (S_ISREG (st.st_mode))
-            gnutls_certificate_set_x509_trust_file (credentials, ca_file,
-                                                    GNUTLS_X509_FMT_PEM);
-
-          free (ca_file);
+          if (opt.ca_directory && *opt.ca_directory)
+            logprintf (LOG_NOTQUIET, _("ERROR: Cannot open directory %s.\n"),
+                       opt.ca_directory);
         }
+      else
+        {
+          struct hash_table *inode_map = hash_table_new (196, NULL, NULL);
+          struct dirent *dent;
+          size_t dirlen = strlen(ca_directory);
+          int rc;
 
-      closedir (dir);
+          ncerts = 0;
+
+          while ((dent = readdir (dir)) != NULL)
+            {
+              struct stat st;
+              char ca_file[dirlen + strlen(dent->d_name) + 2];
+
+              snprintf (ca_file, sizeof(ca_file), "%s/%s", ca_directory, dent->d_name);
+              if (stat (ca_file, &st) != 0)
+                continue;
+
+              if (! S_ISREG (st.st_mode))
+                continue;
+
+              /* avoid loading the same file twice by checking the inode.  */
+              if (hash_table_contains (inode_map, (void *)(intptr_t) st.st_ino))
+                continue;
+
+              hash_table_put (inode_map, (void *)(intptr_t) st.st_ino, NULL);
+              if ((rc = gnutls_certificate_set_x509_trust_file (credentials, ca_file,
+                                                                GNUTLS_X509_FMT_PEM)) <= 0)
+                logprintf (LOG_NOTQUIET, _("ERROR: Failed to open cert %s: (%d).\n"),
+                           ca_file, rc);
+              else
+                ncerts += rc;
+            }
+
+          hash_table_destroy (inode_map);
+          closedir (dir);
+        }
     }
 
+  DEBUGP (("Certificates loaded: %d\n", ncerts));
+
   /* Use the private key from the cert file unless otherwise specified. */
   if (opt.cert_file && !opt.private_key)
     {
@@ -141,17 +169,17 @@ ssl_init (void)
     {
       int type;
       if (opt.private_key_type != opt.cert_type)
-	{
-	  /* GnuTLS can't handle this */
-	  logprintf (LOG_NOTQUIET, _("ERROR: GnuTLS requires the key and the \
+        {
+          /* GnuTLS can't handle this */
+          logprintf (LOG_NOTQUIET, _("ERROR: GnuTLS requires the key and the \
 cert to be of the same type.\n"));
-	}
+        }
 
       type = key_type_to_gnutls_type (opt.private_key_type);
 
       gnutls_certificate_set_x509_key_file (credentials, opt.cert_file,
-					    opt.private_key,
-					    type);
+                                            opt.private_key,
+                                            type);
     }
 
   if (opt.ca_cert)
@@ -278,7 +306,7 @@ wgnutls_read (int fd, char *buf, int bufsize, void *arg)
 }
 
 static int
-wgnutls_write (int fd, char *buf, int bufsize, void *arg)
+wgnutls_write (int fd _GL_UNUSED, char *buf, int bufsize, void *arg)
 {
   int ret;
   struct wgnutls_transport_context *ctx = arg;
@@ -315,7 +343,7 @@ wgnutls_peek (int fd, char *buf, int bufsize, void *arg)
       return offset;
     }
 
-  if (bufsize > sizeof ctx->peekbuf)
+  if (bufsize > (int) sizeof ctx->peekbuf)
     bufsize = sizeof ctx->peekbuf;
 
   if (bufsize > offset)
@@ -346,7 +374,7 @@ wgnutls_peek (int fd, char *buf, int bufsize, void *arg)
 }
 
 static const char *
-wgnutls_errstr (int fd, void *arg)
+wgnutls_errstr (int fd _GL_UNUSED, void *arg)
 {
   struct wgnutls_transport_context *ctx = arg;
   return gnutls_strerror (ctx->last_error);
@@ -374,16 +402,20 @@ static struct transport_implementation wgnutls_transport =
 bool
 ssl_connect_wget (int fd, const char *hostname)
 {
+#ifdef F_GETFL
+  int flags = 0;
+#endif
   struct wgnutls_transport_context *ctx;
   gnutls_session_t session;
-  int err;
+  int err,alert;
   gnutls_init (&session, GNUTLS_CLIENT);
+  const char *str;
 
   /* We set the server name but only if it's not an IP address. */
   if (! is_valid_ip_address (hostname))
     {
       gnutls_server_name_set (session, GNUTLS_NAME_DNS, hostname,
-			      strlen (hostname));
+                              strlen (hostname));
     }
 
   gnutls_set_default_priority (session);
@@ -391,7 +423,11 @@ ssl_connect_wget (int fd, const char *hostname)
 #ifndef FD_TO_SOCKET
 # define FD_TO_SOCKET(X) (X)
 #endif
+#ifdef HAVE_INTPTR_T
+  gnutls_transport_set_ptr (session, (gnutls_transport_ptr_t) (intptr_t) FD_TO_SOCKET (fd));
+#else
   gnutls_transport_set_ptr (session, (gnutls_transport_ptr_t) FD_TO_SOCKET (fd));
+#endif
 
   err = 0;
 #if HAVE_GNUTLS_PRIORITY_SET_DIRECT
@@ -401,11 +437,17 @@ ssl_connect_wget (int fd, const char *hostname)
       break;
     case secure_protocol_sslv2:
     case secure_protocol_sslv3:
-      err = gnutls_priority_set_direct (session, "NORMAL:-VERS-TLS-ALL", NULL);
+      err = gnutls_priority_set_direct (session, "NORMAL:-VERS-TLS-ALL:+VERS-SSL3.0", NULL);
       break;
     case secure_protocol_tlsv1:
       err = gnutls_priority_set_direct (session, "NORMAL:-VERS-SSL3.0", NULL);
       break;
+    case secure_protocol_pfs:
+      err = gnutls_priority_set_direct (session, "PFS", NULL);
+      if (err != GNUTLS_E_SUCCESS)
+        /* fallback if PFS is not available */
+        err = gnutls_priority_set_direct (session, "NORMAL:-RSA", NULL);
+      break;
     default:
       abort ();
     }
@@ -440,10 +482,82 @@ ssl_connect_wget (int fd, const char *hostname)
       return false;
     }
 
-  err = gnutls_handshake (session);
+  if (opt.connect_timeout)
+    {
+#ifdef F_GETFL
+      flags = fcntl (fd, F_GETFL, 0);
+      if (flags < 0)
+        return flags;
+      if (fcntl (fd, F_SETFL, flags | O_NONBLOCK))
+        return -1;
+#else
+      /* XXX: Assume it was blocking before.  */
+      const int one = 1;
+      if (ioctl (fd, FIONBIO, &one) < 0)
+        return -1;
+#endif
+    }
+
+  /* We don't stop the handshake process for non-fatal errors */
+  do
+    {
+      err = gnutls_handshake (session);
+
+      if (opt.connect_timeout && err == GNUTLS_E_AGAIN)
+        {
+          if (gnutls_record_get_direction (session))
+            {
+              /* wait for writeability */
+              err = select_fd (fd, opt.connect_timeout, WAIT_FOR_WRITE);
+            }
+          else
+            {
+              /* wait for readability */
+              err = select_fd (fd, opt.connect_timeout, WAIT_FOR_READ);
+            }
+
+          if (err <= 0)
+            {
+              if (err == 0)
+                {
+                  errno = ETIMEDOUT;
+                  err = -1;
+                }
+              break;
+            }
+
+           err = GNUTLS_E_AGAIN;
+        }
+      else if (err < 0)
+        {
+          logprintf (LOG_NOTQUIET, "GnuTLS: %s\n", gnutls_strerror (err));
+          if (err == GNUTLS_E_WARNING_ALERT_RECEIVED ||
+              err == GNUTLS_E_FATAL_ALERT_RECEIVED)
+            {
+              alert = gnutls_alert_get (session);
+              str = gnutls_alert_get_name (alert);
+              if (str == NULL)
+                str = "(unknown)";
+              logprintf (LOG_NOTQUIET, "GnuTLS: received alert [%d]: %s\n", alert, str);
+            }
+        }
+    }
+  while (err && gnutls_error_is_fatal (err) == 0);
+
+  if (opt.connect_timeout)
+    {
+#ifdef F_GETFL
+      if (fcntl (fd, F_SETFL, flags) < 0)
+        return -1;
+#else
+      const int zero = 0;
+      if (ioctl (fd, FIONBIO, &zero) < 0)
+        return -1;
+#endif
+    }
+
   if (err < 0)
     {
-      logprintf (LOG_NOTQUIET, "GnuTLS: %s\n", gnutls_strerror (err));
       gnutls_deinit (session);
       return false;
     }
@@ -454,6 +568,14 @@ ssl_connect_wget (int fd, const char *hostname)
   return true;
 }
 
+#define _CHECK_CERT(flag,msg) \
+  if (status & (flag))\
+    {\
+      logprintf (LOG_NOTQUIET, (msg),\
+                 severity, quote (host));\
+      success = false;\
+    }
+
 bool
 ssl_check_certificate (int fd, const char *host)
 {
@@ -476,24 +598,13 @@ ssl_check_certificate (int fd, const char *host)
       goto out;
     }
 
-  if (status & GNUTLS_CERT_INVALID)
-    {
-      logprintf (LOG_NOTQUIET, _("%s: The certificate of %s is not trusted.\n"),
-                 severity, quote (host));
-      success = false;
-    }
-  if (status & GNUTLS_CERT_SIGNER_NOT_FOUND)
-    {
-      logprintf (LOG_NOTQUIET, _("%s: The certificate of %s hasn't got a known issuer.\n"),
-                 severity, quote (host));
-      success = false;
-    }
-  if (status & GNUTLS_CERT_REVOKED)
-    {
-      logprintf (LOG_NOTQUIET, _("%s: The certificate of %s has been revoked.\n"),
-                 severity, quote (host));
-      success = false;
-    }
+  _CHECK_CERT (GNUTLS_CERT_INVALID, _("%s: The certificate of %s is not trusted.\n"));
+  _CHECK_CERT (GNUTLS_CERT_SIGNER_NOT_FOUND, _("%s: The certificate of %s hasn't got a known issuer.\n"));
+  _CHECK_CERT (GNUTLS_CERT_REVOKED, _("%s: The certificate of %s has been revoked.\n"));
+  _CHECK_CERT (GNUTLS_CERT_SIGNER_NOT_CA, _("%s: The certificate signer of %s was not a CA.\n"));
+  _CHECK_CERT (GNUTLS_CERT_INSECURE_ALGORITHM, _("%s: The certificate of %s was signed using an insecure algorithm.\n"));
+  _CHECK_CERT (GNUTLS_CERT_NOT_ACTIVATED, _("%s: The certificate of %s is not yet activated.\n"));
+  _CHECK_CERT (GNUTLS_CERT_EXPIRED, _("%s: The certificate of %s has expired.\n"));
 
   if (gnutls_certificate_type_get (ctx->session) == GNUTLS_CRT_X509)
     {
@@ -515,7 +626,7 @@ ssl_check_certificate (int fd, const char *host)
         {
           logprintf (LOG_NOTQUIET, _("No certificate found\n"));
           success = false;
-          goto out;
+          goto crt_deinit;
         }
       err = gnutls_x509_crt_import (cert, cert_list, GNUTLS_X509_FMT_DER);
       if (err < 0)
@@ -523,7 +634,7 @@ ssl_check_certificate (int fd, const char *host)
           logprintf (LOG_NOTQUIET, _("Error parsing certificate: %s\n"),
                      gnutls_strerror (err));
           success = false;
-          goto out;
+          goto crt_deinit;
         }
       if (now < gnutls_x509_crt_get_activation_time (cert))
         {
@@ -542,8 +653,14 @@ ssl_check_certificate (int fd, const char *host)
                      quote (host));
           success = false;
         }
+ crt_deinit:
       gnutls_x509_crt_deinit (cert);
-   }
+    }
+  else
+    {
+      logprintf (LOG_NOTQUIET, _("Certificate must be X.509\n"));
+      success = false;
+    }
 
  out:
   return opt.check_cert ? success : true;

src/html-url.c

@@ -79,7 +79,10 @@ enum {
   TAG_SCRIPT,
   TAG_TABLE,
   TAG_TD,
-  TAG_TH
+  TAG_TH,
+  TAG_VIDEO,
+  TAG_AUDIO,
+  TAG_SOURCE
 };
 
 /* The list of known tags and functions used for handling them.  Most
@@ -110,7 +113,10 @@ static struct known_tag {
   { TAG_SCRIPT,  "script",      tag_find_urls },
   { TAG_TABLE,   "table",       tag_find_urls },
   { TAG_TD,      "td",          tag_find_urls },
-  { TAG_TH,      "th",          tag_find_urls }
+  { TAG_TH,      "th",          tag_find_urls },
+  { TAG_VIDEO,   "video",       tag_find_urls },
+  { TAG_AUDIO,   "audio",       tag_find_urls },
+  { TAG_SOURCE,  "source",      tag_find_urls }
 };
 
 /* tag_url_attributes documents which attributes of which tags contain
@@ -157,7 +163,12 @@ static struct {
   { TAG_SCRIPT,         "src",          ATTR_INLINE },
   { TAG_TABLE,          "background",   ATTR_INLINE },
   { TAG_TD,             "background",   ATTR_INLINE },
-  { TAG_TH,             "background",   ATTR_INLINE }
+  { TAG_TH,             "background",   ATTR_INLINE },
+  { TAG_VIDEO,          "src",          ATTR_INLINE },
+  { TAG_VIDEO,          "poster",       ATTR_INLINE },
+  { TAG_AUDIO,          "src",          ATTR_INLINE },
+  { TAG_AUDIO,          "poster",       ATTR_INLINE },
+  { TAG_SOURCE,         "src",          ATTR_INLINE }
 };
 
 /* The lists of interesting tags and attributes are built dynamically,
@@ -273,6 +284,10 @@ append_url (const char *link_uri, int position, int size,
   const char *base = ctx->base ? ctx->base : ctx->parent_base;
   struct url *url;
 
+  struct iri *iri = iri_new ();
+  set_uri_encoding (iri, opt.locale, true);
+  iri->utf8_encode = true;
+
   if (!base)
     {
       DEBUGP (("%s: no base, merge will use \"%s\".\n",
@@ -290,7 +305,7 @@ append_url (const char *link_uri, int position, int size,
           return NULL;
         }
 
-      url = url_parse (link_uri, NULL, NULL, false);
+      url = url_parse (link_uri, NULL, iri, false);
       if (!url)
         {
           DEBUGP (("%s: link \"%s\" doesn't parse.\n",
@@ -312,7 +327,7 @@ append_url (const char *link_uri, int position, int size,
                quote_n (2, link_uri),
                quotearg_n_style (3, escape_quoting_style, complete_uri)));
 
-      url = url_parse (complete_uri, NULL, NULL, false);
+      url = url_parse (complete_uri, NULL, iri, false);
       if (!url)
         {
           DEBUGP (("%s: merged link \"%s\" doesn't parse.\n",
@@ -323,6 +338,8 @@ append_url (const char *link_uri, int position, int size,
       xfree (complete_uri);
     }
 
+  iri_free (iri);
+
   DEBUGP (("appending %s to urlpos.\n", quote (url->url)));
 
   newel = xnew0 (struct urlpos);
@@ -804,6 +821,13 @@ get_urls_file (const char *file)
           url_text = merged;
         }
 
+      char *new_url = rewrite_shorthand_url (url_text);
+      if (new_url)
+        {
+          xfree (url_text);
+          url_text = new_url;
+        }
+
       url = url_parse (url_text, &up_error_code, NULL, false);
       if (!url)
         {
@@ -830,7 +854,7 @@ get_urls_file (const char *file)
   return head;
 }
 
-static void
+void
 cleanup_html_url (void)
 {
   /* Destroy the hash tables.  The hash table keys and values are not

src/http-ntlm.c

@@ -42,27 +42,33 @@ as that of the covered work.  */
 #include <string.h>
 #include <stdlib.h>
 
-#include <openssl/des.h>
-#include <openssl/md4.h>
-#include <openssl/opensslv.h>
-
 #include "utils.h"
 #include "http-ntlm.h"
 
-#if OPENSSL_VERSION_NUMBER < 0x00907001L
-#define DES_key_schedule des_key_schedule
-#define DES_cblock des_cblock
-#define DES_set_odd_parity des_set_odd_parity
-#define DES_set_key des_set_key
-#define DES_ecb_encrypt des_ecb_encrypt
+#ifdef HAVE_NETTLE
+# include <nettle/md4.h>
+# include <nettle/des.h>
+#else
+# include <openssl/des.h>
+# include <openssl/md4.h>
+# include <openssl/opensslv.h>
+
+# if OPENSSL_VERSION_NUMBER < 0x00907001L
+#  define DES_key_schedule des_key_schedule
+#  define DES_cblock des_cblock
+#  define DES_set_odd_parity des_set_odd_parity
+#  define DES_set_key des_set_key
+#  define DES_ecb_encrypt des_ecb_encrypt
 
 /* This is how things were done in the old days */
-#define DESKEY(x) x
-#define DESKEYARG(x) x
-#else
+#  define DESKEY(x) x
+#  define DESKEYARG(x) x
+# else
 /* Modern version */
-#define DESKEYARG(x) *x
-#define DESKEY(x) &x
+#  define DESKEYARG(x) *x
+#  define DESKEY(x) &x
+# endif
+
 #endif
 
 /* Define this to make the type-3 message include the NT response message */
@@ -176,6 +182,25 @@ ntlm_input (struct ntlmdata *ntlm, const char *header)
  * Turns a 56 bit key into the 64 bit, odd parity key and sets the key.  The
  * key schedule ks is also set.
  */
+#ifdef HAVE_NETTLE
+static void
+setup_des_key(unsigned char *key_56,
+              struct des_ctx *des)
+{
+  unsigned char key[8];
+
+  key[0] = key_56[0];
+  key[1] = ((key_56[0] << 7) & 0xFF) | (key_56[1] >> 1);
+  key[2] = ((key_56[1] << 6) & 0xFF) | (key_56[2] >> 2);
+  key[3] = ((key_56[2] << 5) & 0xFF) | (key_56[3] >> 3);
+  key[4] = ((key_56[3] << 4) & 0xFF) | (key_56[4] >> 4);
+  key[5] = ((key_56[4] << 3) & 0xFF) | (key_56[5] >> 5);
+  key[6] = ((key_56[5] << 2) & 0xFF) | (key_56[6] >> 6);
+  key[7] =  (key_56[6] << 1) & 0xFF;
+
+  nettle_des_set_key(des, key);
+}
+#else
 static void
 setup_des_key(unsigned char *key_56,
               DES_key_schedule DESKEYARG(ks))
@@ -194,6 +219,7 @@ setup_des_key(unsigned char *key_56,
   DES_set_odd_parity(&key);
   DES_set_key(&key, ks);
 }
+#endif
 
  /*
   * takes a 21 byte array and treats it as 3 56-bit DES keys. The
@@ -203,6 +229,18 @@ setup_des_key(unsigned char *key_56,
 static void
 calc_resp(unsigned char *keys, unsigned char *plaintext, unsigned char *results)
 {
+#ifdef HAVE_NETTLE
+  struct des_ctx des;
+
+  setup_des_key(keys, &des);
+  nettle_des_encrypt(&des, 8, results, plaintext);
+
+  setup_des_key(keys + 7, &des);
+  nettle_des_encrypt(&des, 8, results + 8, plaintext);
+
+  setup_des_key(keys + 14, &des);
+  nettle_des_encrypt(&des, 8, results + 16, plaintext);
+#else
   DES_key_schedule ks;
 
   setup_des_key(keys, DESKEY(ks));
@@ -216,6 +254,7 @@ calc_resp(unsigned char *keys, unsigned char *plaintext, unsigned char *results)
   setup_des_key(keys+14, DESKEY(ks));
   DES_ecb_encrypt((DES_cblock*) plaintext, (DES_cblock*) (results+16),
                   DESKEY(ks), DES_ENCRYPT);
+#endif
 }
 
 /*
@@ -255,6 +294,15 @@ mkhash(const char *password,
 
   {
     /* create LanManager hashed password */
+#ifdef HAVE_NETTLE
+    struct des_ctx des;
+
+    setup_des_key(pw, &des);
+    nettle_des_encrypt(&des, 8, lmbuffer, magic);
+
+    setup_des_key(pw + 7, &des);
+    nettle_des_encrypt(&des, 8, lmbuffer + 8, magic);
+#else
     DES_key_schedule ks;
 
     setup_des_key(pw, DESKEY(ks));
@@ -264,6 +312,7 @@ mkhash(const char *password,
     setup_des_key(pw+7, DESKEY(ks));
     DES_ecb_encrypt((DES_cblock *)magic, (DES_cblock *)(lmbuffer+8),
                     DESKEY(ks), DES_ENCRYPT);
+#endif
 
     memset(lmbuffer+16, 0, 5);
   }
@@ -272,8 +321,11 @@ mkhash(const char *password,
 
 #ifdef USE_NTRESPONSES
   {
-    /* create NT hashed password */
+#ifdef HAVE_NETTLE
+    struct md4_ctx MD4;
+#else
     MD4_CTX MD4;
+#endif
 
     len = strlen(password);
 
@@ -282,9 +334,16 @@ mkhash(const char *password,
       pw[2*i+1] = 0;
     }
 
+#ifdef HAVE_NETTLE
+    nettle_md4_init(&MD4);
+    nettle_md4_update(&MD4, 2*len, pw);
+    nettle_md4_digest(&MD4, MD4_DIGEST_SIZE, ntbuffer);
+#else
+    /* create NT hashed password */
     MD4_Init(&MD4);
     MD4_Update(&MD4, pw, 2*len);
     MD4_Final(ntbuffer, &MD4);
+#endif
 
     memset(ntbuffer+16, 0, 5);
   }

src/http.c

@@ -74,7 +74,7 @@ extern char *version_string;
 struct http_stat;
 static char *create_authorization_line (const char *, const char *,
                                         const char *, const char *,
-                                        const char *, bool *);
+                                        const char *, bool *, uerr_t *);
 static char *basic_authentication_encode (const char *, const char *);
 static bool known_authentication_scheme_p (const char *, const char *);
 static void ensure_extension (struct http_stat *, const char *, int *);
@@ -147,27 +147,20 @@ struct request {
 
 extern int numurls;
 
-/* Create a new, empty request.  At least request_set_method must be
-   called before the request can be used.  */
+/* Create a new, empty request. Set the request's method and its
+   arguments.  METHOD should be a literal string (or it should outlive
+   the request) because it will not be freed.  ARG will be freed by
+   request_free.  */
 
 static struct request *
-request_new (void)
+request_new (const char *method, char *arg)
 {
   struct request *req = xnew0 (struct request);
   req->hcapacity = 8;
   req->headers = xnew_array (struct request_header, req->hcapacity);
-  return req;
-}
-
-/* Set the request's method and its arguments.  METH should be a
-   literal string (or it should outlive the request) because it will
-   not be freed.  ARG will be freed by request_free.  */
-
-static void
-request_set_method (struct request *req, const char *meth, char *arg)
-{
-  req->method = meth;
+  req->method = method;
   req->arg = arg;
+  return req;
 }
 
 /* Return the method string passed with the last call to
@@ -459,14 +452,14 @@ register_basic_auth_host (const char *hostname)
    also be written to that file.  */
 
 static int
-post_file (int sock, const char *file_name, wgint promised_size, FILE *warc_tmp)
+body_file_send (int sock, const char *file_name, wgint promised_size, FILE *warc_tmp)
 {
   static char chunk[8192];
   wgint written = 0;
   int write_error;
   FILE *fp;
 
-  DEBUGP (("[writing POST file %s ... ", file_name));
+  DEBUGP (("[writing BODY file %s ... ", file_name));
 
   fp = fopen (file_name, "rb");
   if (!fp)
@@ -931,8 +924,6 @@ skip_short_body (int fd, wgint contlen, bool chunked)
   char dlbuf[SKIP_SIZE + 1];
   dlbuf[SKIP_SIZE] = '\0';        /* so DEBUGP can safely print it */
 
-  assert (contlen != -1 || contlen);
-
   /* If the body is too large, it makes more sense to simply close the
      connection than to try to read the body.  */
   if (contlen > SKIP_THRESHOLD)
@@ -1648,12 +1639,6 @@ read_response_body (struct http_stat *hs, int sock, FILE *fp, wgint contlen,
 } while (0)
 #endif /* def __VMS [else] */
 
-/* The flags that allow clobbering the file (opening with "wb").
-   Defined here to avoid repetition later.  #### This will require
-   rework.  */
-#define ALLOW_CLOBBER (opt.noclobber || opt.always_rest || opt.timestamping \
-                       || opt.dirstruct || opt.output_document)
-
 /* Retrieve a document through HTTP protocol.  It recognizes status
    code, and correctly handles redirections.  It closes the network
    socket.  If it receives an error from the functions below it, it
@@ -1703,7 +1688,7 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
 
   char *head;
   struct response *resp;
-  char hdrval[256];
+  char hdrval[512];
   char *message;
 
   /* Declare WARC variables. */
@@ -1726,7 +1711,7 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
     !opt.http_keep_alive || opt.ignore_length;
 
   /* Headers sent when using POST. */
-  wgint post_data_size = 0;
+  wgint body_data_size = 0;
 
   bool host_lookup_failed = false;
 
@@ -1758,15 +1743,13 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
   conn = u;
 
   /* Prepare the request to send. */
-
-  req = request_new ();
   {
     char *meth_arg;
     const char *meth = "GET";
     if (head_only)
       meth = "HEAD";
-    else if (opt.post_file_name || opt.post_data)
-      meth = "POST";
+    else if (opt.method)
+      meth = opt.method;
     /* Use the full path, i.e. one that includes the leading slash and
        the query string.  E.g. if u->path is "foo/bar" and u->query is
        "param=value", full_path will be "/foo/bar?param=value".  */
@@ -1781,7 +1764,7 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
       meth_arg = xstrdup (u->url);
     else
       meth_arg = url_full_path (u);
-    request_set_method (req, meth, meth_arg);
+    req = request_new (meth, meth_arg);
   }
 
   request_set_header (req, "Referer", (char *) hs->referer, rel_none);
@@ -1852,25 +1835,30 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
         }
     }
 
-  if (opt.post_data || opt.post_file_name)
+  if (opt.method)
     {
-      request_set_header (req, "Content-Type",
-                          "application/x-www-form-urlencoded", rel_none);
-      if (opt.post_data)
-        post_data_size = strlen (opt.post_data);
-      else
+
+      if (opt.body_data || opt.body_file)
         {
-          post_data_size = file_size (opt.post_file_name);
-          if (post_data_size == -1)
+          request_set_header (req, "Content-Type",
+                              "application/x-www-form-urlencoded", rel_none);
+
+          if (opt.body_data)
+            body_data_size = strlen (opt.body_data);
+          else
             {
-              logprintf (LOG_NOTQUIET, _("POST data file %s missing: %s\n"),
-                         quote (opt.post_file_name), strerror (errno));
-              post_data_size = 0;
+              body_data_size = file_size (opt.body_file);
+              if (body_data_size == -1)
+                {
+                  logprintf (LOG_NOTQUIET, _("BODY data file %s missing: %s\n"),
+                             quote (opt.body_file), strerror (errno));
+                  return FILEBADFILE;
+                }
             }
+          request_set_header (req, "Content-Length",
+                              xstrdup (number_to_static_string (body_data_size)),
+                              rel_value);
         }
-      request_set_header (req, "Content-Length",
-                          xstrdup (number_to_static_string (post_data_size)),
-                          rel_value);
     }
 
  retry_with_auth:
@@ -1962,11 +1950,13 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
           int family = socket_family (pconn.socket, ENDPOINT_PEER);
           sock = pconn.socket;
           using_ssl = pconn.ssl;
+#if ENABLE_IPV6
           if (family == AF_INET6)
              logprintf (LOG_VERBOSE, _("Reusing existing connection to [%s]:%d.\n"),
                         quotearg_style (escape_quoting_style, pconn.host),
                          pconn.port);
           else
+#endif
              logprintf (LOG_VERBOSE, _("Reusing existing connection to %s:%d.\n"),
                         quotearg_style (escape_quoting_style, pconn.host),
                         pconn.port);
@@ -1985,6 +1975,10 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
                     exec_name, quote (relevant->host));
           return HOSTERR;
         }
+      else if (sock != -1)
+        {
+          sock = -1;
+        }
     }
 
   if (sock < 0)
@@ -2007,8 +2001,7 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
         {
           /* When requesting SSL URLs through proxies, use the
              CONNECT method to request passthrough.  */
-          struct request *connreq = request_new ();
-          request_set_method (connreq, "CONNECT",
+          struct request *connreq = request_new ("CONNECT",
                               aprintf ("%s:%d", u->host, u->port));
           SET_USER_AGENT (connreq);
           if (proxyauth)
@@ -2020,10 +2013,9 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
                  the regular request below.  */
               proxyauth = NULL;
             }
-          /* Examples in rfc2817 use the Host header in CONNECT
-             requests.  I don't see how that gains anything, given
-             that the contents of Host would be exactly the same as
-             the contents of CONNECT.  */
+          request_set_header (connreq, "Host",
+                              aprintf ("%s:%d", u->host, u->port),
+                              rel_value);
 
           write_error = request_send (connreq, sock, 0);
           request_free (connreq);
@@ -2126,28 +2118,28 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
 
   if (write_error >= 0)
     {
-      if (opt.post_data)
+      if (opt.body_data)
         {
-          DEBUGP (("[POST data: %s]\n", opt.post_data));
-          write_error = fd_write (sock, opt.post_data, post_data_size, -1);
+          DEBUGP (("[BODY data: %s]\n", opt.body_data));
+          write_error = fd_write (sock, opt.body_data, body_data_size, -1);
           if (write_error >= 0 && warc_tmp != NULL)
             {
               /* Remember end of headers / start of payload. */
               warc_payload_offset = ftello (warc_tmp);
 
               /* Write a copy of the data to the WARC record. */
-              int warc_tmp_written = fwrite (opt.post_data, 1, post_data_size, warc_tmp);
-              if (warc_tmp_written != post_data_size)
+              int warc_tmp_written = fwrite (opt.body_data, 1, body_data_size, warc_tmp);
+              if (warc_tmp_written != body_data_size)
                 write_error = -2;
             }
-        }
-      else if (opt.post_file_name && post_data_size != 0)
+         }
+      else if (opt.body_file && body_data_size != 0)
         {
           if (warc_tmp != NULL)
-            /* Remember end of headers / start of payload. */
+            /* Remember end of headers / start of payload */
             warc_payload_offset = ftello (warc_tmp);
 
-          write_error = post_file (sock, opt.post_file_name, post_data_size, warc_tmp);
+          write_error = body_file_send (sock, opt.body_file, body_data_size, warc_tmp);
         }
     }
 
@@ -2355,6 +2347,7 @@ read_header:
         }
 
       pconn.authorized = false;
+      uerr_t auth_err = RETROK;
       if (!auth_finished && (user && passwd))
         {
           /* IIS sends multiple copies of WWW-Authenticate, one with
@@ -2382,28 +2375,44 @@ read_header:
           else if (!basic_auth_finished
                    || !BEGINS_WITH (www_authenticate, "Basic"))
             {
-              char *pth;
-              pth = url_full_path (u);
-              request_set_header (req, "Authorization",
-                                  create_authorization_line (www_authenticate,
-                                                             user, passwd,
-                                                             request_method (req),
-                                                             pth,
-                                                             &auth_finished),
-                                  rel_value);
-              if (BEGINS_WITH (www_authenticate, "NTLM"))
-                ntlm_seen = true;
-              else if (!u->user && BEGINS_WITH (www_authenticate, "Basic"))
+              char *pth = url_full_path (u);
+              const char *value;
+              uerr_t *auth_stat;
+              auth_stat = xmalloc (sizeof (uerr_t));
+              *auth_stat = RETROK;
+
+              value =  create_authorization_line (www_authenticate,
+                                                  user, passwd,
+                                                  request_method (req),
+                                                  pth,
+                                                  &auth_finished,
+                                                  auth_stat);
+
+              auth_err = *auth_stat;
+              if (auth_err == RETROK)
                 {
-                  /* Need to register this host as using basic auth,
-                   * so we automatically send creds next time. */
-                  register_basic_auth_host (u->host);
+                  request_set_header (req, "Authorization", value, rel_value);
+
+                  if (BEGINS_WITH (www_authenticate, "NTLM"))
+                    ntlm_seen = true;
+                  else if (!u->user && BEGINS_WITH (www_authenticate, "Basic"))
+                    {
+                      /* Need to register this host as using basic auth,
+                       * so we automatically send creds next time. */
+                      register_basic_auth_host (u->host);
+                    }
+
+                  xfree (pth);
+                  xfree_null (message);
+                  resp_free (resp);
+                  xfree (head);
+                  xfree (auth_stat);
+                  goto retry_with_auth;
+                }
+              else
+                {
+                  /* Creating the Authorization header went wrong */
                 }
-              xfree (pth);
-              xfree_null (message);
-              resp_free (resp);
-              xfree (head);
-              goto retry_with_auth;
             }
           else
             {
@@ -2411,12 +2420,14 @@ read_header:
                * give up. */
             }
         }
-      logputs (LOG_NOTQUIET, _("Authorization failed.\n"));
       request_free (req);
       xfree_null (message);
       resp_free (resp);
       xfree (head);
-      return AUTHFAILED;
+      if (auth_err == RETROK)
+        return AUTHFAILED;
+      else
+        return auth_err;
     }
   else /* statcode != HTTP_STATUS_UNAUTHORIZED */
     {
@@ -2644,12 +2655,35 @@ read_header:
           /* From RFC2616: The status codes 303 and 307 have
              been added for servers that wish to make unambiguously
              clear which kind of reaction is expected of the client.
-             
+
              A 307 should be redirected using the same method,
              in other words, a POST should be preserved and not
-             converted to a GET in that case. */
-          if (statcode == HTTP_STATUS_TEMPORARY_REDIRECT)
-            return NEWLOCATION_KEEP_POST;
+             converted to a GET in that case.
+
+             With strict adherence to RFC2616, POST requests are not
+             converted to a GET request on 301 Permanent Redirect
+             or 302 Temporary Redirect.
+
+             A switch may be provided later based on the HTTPbis draft
+             that allows clients to convert POST requests to GET
+             requests on 301 and 302 response codes. */
+          switch (statcode)
+            {
+            case HTTP_STATUS_TEMPORARY_REDIRECT:
+              return NEWLOCATION_KEEP_POST;
+              break;
+            case HTTP_STATUS_MOVED_PERMANENTLY:
+              if (opt.method && strcasecmp (opt.method, "post") != 0)
+                return NEWLOCATION_KEEP_POST;
+              break;
+            case HTTP_STATUS_MOVED_TEMPORARILY:
+              if (opt.method && strcasecmp (opt.method, "post") != 0)
+                return NEWLOCATION_KEEP_POST;
+              break;
+            default:
+              return NEWLOCATION;
+              break;
+            }
           return NEWLOCATION;
         }
     }
@@ -3002,9 +3036,17 @@ http_loop (struct url *u, struct url *original_url, char **newloc,
   if (!opt.spider)
     send_head_first = false;
 
+  /* Send preliminary HEAD request if --content-disposition and -c are used
+     together.  */
+  if (opt.content_disposition && opt.always_rest)
+    send_head_first = true;
+
   /* Send preliminary HEAD request if -N is given and we have an existing
    * destination file. */
-  file_name = url_file_name (opt.trustservernames ? u : original_url, NULL);
+  if (!opt.output_document)
+      file_name = url_file_name (opt.trustservernames ? u : original_url, NULL);
+  else
+    file_name = xstrdup (opt.output_document);
   if (opt.timestamping && (file_exists_p (file_name)
                            || opt.content_disposition))
     send_head_first = true;
@@ -3110,11 +3152,23 @@ Spider mode enabled. Check if remote file exists.\n"));
           logputs (LOG_VERBOSE, "\n");
           logprintf (LOG_NOTQUIET, _("Cannot write to %s (%s).\n"),
                      quote (hstat.local_file), strerror (errno));
-        case HOSTERR: case CONIMPOSSIBLE: case PROXERR: case AUTHFAILED:
-        case SSLINITFAILED: case CONTNOTSUPPORTED: case VERIFCERTERR:
+        case HOSTERR: case CONIMPOSSIBLE: case PROXERR: case SSLINITFAILED:
+        case CONTNOTSUPPORTED: case VERIFCERTERR: case FILEBADFILE:
+        case UNKNOWNATTR:
           /* Fatal errors just return from the function.  */
           ret = err;
           goto exit;
+        case ATTRMISSING:
+          /* A missing attribute in a Header is a fatal Protocol error. */
+          logputs (LOG_VERBOSE, "\n");
+          logprintf (LOG_NOTQUIET, _("Required attribute missing from Header received.\n"));
+          ret = err;
+          goto exit;
+        case AUTHFAILED:
+          logputs (LOG_VERBOSE, "\n");
+          logprintf (LOG_NOTQUIET, _("Username/Password Authentication Failed.\n"));
+          ret = err;
+          goto exit;
         case WARC_ERR:
           /* A fatal WARC error. */
           logputs (LOG_VERBOSE, "\n");
@@ -3653,9 +3707,9 @@ dump_hash (char *buf, const unsigned char *hash)
 static char *
 digest_authentication_encode (const char *au, const char *user,
                               const char *passwd, const char *method,
-                              const char *path)
+                              const char *path, uerr_t *auth_err)
 {
-  static char *realm, *opaque, *nonce, *qop;
+  static char *realm, *opaque, *nonce, *qop, *algorithm;
   static struct {
     const char *name;
     char **variable;
@@ -3663,15 +3717,17 @@ digest_authentication_encode (const char *au, const char *user,
     { "realm", &realm },
     { "opaque", &opaque },
     { "nonce", &nonce },
-    { "qop", &qop }
+    { "qop", &qop },
+    { "algorithm", &algorithm }
   };
   char cnonce[16] = "";
   char *res;
+  int res_len;
   size_t res_size;
   param_token name, value;
 
 
-  realm = opaque = nonce = qop = NULL;
+  realm = opaque = nonce = algorithm = qop = NULL;
 
   au += 6;                      /* skip over `Digest' */
   while (extract_param (&au, &name, &value, ','))
@@ -3691,15 +3747,27 @@ digest_authentication_encode (const char *au, const char *user,
   if (qop != NULL && strcmp(qop,"auth"))
     {
       logprintf (LOG_NOTQUIET, _("Unsupported quality of protection '%s'.\n"), qop);
-      user = NULL; /* force freeing mem and return */
+      xfree_null (qop); /* force freeing mem and return */
+      qop = NULL;
+    }
+  else if (algorithm != NULL && strcmp (algorithm,"MD5") && strcmp (algorithm,"MD5-sess"))
+    {
+      logprintf (LOG_NOTQUIET, _("Unsupported algorithm '%s'.\n"), algorithm);
+      xfree_null (qop); /* force freeing mem and return */
+      qop = NULL;
     }
 
-  if (!realm || !nonce || !user || !passwd || !path || !method)
+  if (!realm || !nonce || !user || !passwd || !path || !method || !qop)
     {
       xfree_null (realm);
       xfree_null (opaque);
       xfree_null (nonce);
       xfree_null (qop);
+      xfree_null (algorithm);
+      if (!qop)
+        *auth_err = UNKNOWNATTR;
+      else
+        *auth_err = ATTRMISSING;
       return NULL;
     }
 
@@ -3718,8 +3786,26 @@ digest_authentication_encode (const char *au, const char *user,
     md5_process_bytes ((unsigned char *)":", 1, &ctx);
     md5_process_bytes ((unsigned char *)passwd, strlen (passwd), &ctx);
     md5_finish_ctx (&ctx, hash);
+
     dump_hash (a1buf, hash);
 
+    if (algorithm && !strcmp (algorithm, "MD5-sess"))
+      {
+        /* A1BUF = H( H(user ":" realm ":" password) ":" nonce ":" cnonce ) */
+        snprintf (cnonce, sizeof (cnonce), "%08x", random_number(INT_MAX));
+
+        md5_init_ctx (&ctx);
+        // md5_process_bytes (hash, MD5_DIGEST_SIZE, &ctx);
+        md5_process_bytes (a1buf, MD5_DIGEST_SIZE * 2, &ctx);
+        md5_process_bytes ((unsigned char *)":", 1, &ctx);
+        md5_process_bytes ((unsigned char *)nonce, strlen (nonce), &ctx);
+        md5_process_bytes ((unsigned char *)":", 1, &ctx);
+        md5_process_bytes ((unsigned char *)cnonce, strlen (cnonce), &ctx);
+        md5_finish_ctx (&ctx, hash);
+
+        dump_hash (a1buf, hash);
+      }
+
     /* A2BUF = H(method ":" path) */
     md5_init_ctx (&ctx);
     md5_process_bytes ((unsigned char *)method, strlen (method), &ctx);
@@ -3728,11 +3814,12 @@ digest_authentication_encode (const char *au, const char *user,
     md5_finish_ctx (&ctx, hash);
     dump_hash (a2buf, hash);
 
-    if (!strcmp(qop,"auth"))
+    if (qop && (!strcmp(qop, "auth") || !strcmp (qop, "auth-int")))
       {
         /* RFC 2617 Digest Access Authentication */
         /* generate random hex string */
-        snprintf(cnonce, sizeof(cnonce), "%08x", random_number(INT_MAX));
+        if (!*cnonce)
+          snprintf(cnonce, sizeof(cnonce), "%08x", random_number(INT_MAX));
 
         /* RESPONSE_DIGEST = H(A1BUF ":" nonce ":" noncecount ":" clientnonce ":" qop ": " A2BUF) */
         md5_init_ctx (&ctx);
@@ -3765,20 +3852,21 @@ digest_authentication_encode (const char *au, const char *user,
     dump_hash (response_digest, hash);
 
     res_size = strlen (user)
-             + strlen (user)
              + strlen (realm)
              + strlen (nonce)
              + strlen (path)
              + 2 * MD5_DIGEST_SIZE /*strlen (response_digest)*/
              + (opaque ? strlen (opaque) : 0)
+             + (algorithm ? strlen (algorithm) : 0)
              + (qop ? 128: 0)
+             + strlen (cnonce)
              + 128;
 
     res = xmalloc (res_size);
 
-    if (!strcmp(qop,"auth"))
+    if (qop && !strcmp (qop, "auth"))
       {
-        snprintf (res, res_size, "Digest "\
+        res_len = snprintf (res, res_size, "Digest "\
                 "username=\"%s\", realm=\"%s\", nonce=\"%s\", uri=\"%s\", response=\"%s\""\
                 ", qop=auth, nc=00000001, cnonce=\"%s\"",
                   user, realm, nonce, path, response_digest, cnonce);
@@ -3786,19 +3874,28 @@ digest_authentication_encode (const char *au, const char *user,
       }
     else
       {
-        snprintf (res, res_size, "Digest "\
+        res_len = snprintf (res, res_size, "Digest "\
                 "username=\"%s\", realm=\"%s\", nonce=\"%s\", uri=\"%s\", response=\"%s\"",
                   user, realm, nonce, path, response_digest);
       }
 
     if (opaque)
       {
-        char *p = res + strlen (res);
-        strcat (p, ", opaque=\"");
-        strcat (p, opaque);
-        strcat (p, "\"");
+        res_len += snprintf(res + res_len, res_size - res_len, ", opaque=\"%s\"", opaque);
+      }
+
+    if (algorithm)
+      {
+        snprintf(res + res_len, res_size - res_len, ", algorithm=\"%s\"", algorithm);
       }
   }
+
+  xfree_null (realm);
+  xfree_null (opaque);
+  xfree_null (nonce);
+  xfree_null (qop);
+  xfree_null (algorithm);
+
   return res;
 }
 #endif /* ENABLE_DIGEST */
@@ -3840,7 +3937,7 @@ known_authentication_scheme_p (const char *hdrbeg, const char *hdrend)
 static char *
 create_authorization_line (const char *au, const char *user,
                            const char *passwd, const char *method,
-                           const char *path, bool *finished)
+                           const char *path, bool *finished, uerr_t *auth_err)
 {
   /* We are called only with known schemes, so we can dispatch on the
      first letter. */
@@ -3852,7 +3949,7 @@ create_authorization_line (const char *au, const char *user,
 #ifdef ENABLE_DIGEST
     case 'D':                   /* Digest */
       *finished = true;
-      return digest_authentication_encode (au, user, passwd, method, path);
+      return digest_authentication_encode (au, user, passwd, method, path, auth_err);
 #endif
 #ifdef ENABLE_NTLM
     case 'N':                   /* NTLM */

src/init.c

@@ -87,6 +87,7 @@ CMD_DECLARE (cmd_directory_vector);
 CMD_DECLARE (cmd_number);
 CMD_DECLARE (cmd_number_inf);
 CMD_DECLARE (cmd_string);
+CMD_DECLARE (cmd_string_uppercase);
 CMD_DECLARE (cmd_file);
 CMD_DECLARE (cmd_directory);
 CMD_DECLARE (cmd_time);
@@ -136,6 +137,8 @@ static const struct {
   { "backups",          &opt.backups,           cmd_number },
   { "base",             &opt.base_href,         cmd_string },
   { "bindaddress",      &opt.bind_address,      cmd_string },
+  { "bodydata",         &opt.body_data,         cmd_string },
+  { "bodyfile",         &opt.body_file,         cmd_string },
 #ifdef HAVE_SSL
   { "cacertificate",    &opt.ca_cert,           cmd_file },
 #endif
@@ -157,7 +160,7 @@ static const struct {
 #ifdef ENABLE_DEBUG
   { "debug",            &opt.debug,             cmd_boolean },
 #endif
-  { "defaultpage", 	&opt.default_page,      cmd_string},
+  { "defaultpage", 	&opt.default_page,      cmd_string },
   { "deleteafter",      &opt.delete_after,      cmd_boolean },
   { "dirprefix",        &opt.dir_prefix,        cmd_directory },
   { "dirstruct",        NULL,                   cmd_spec_dirstruct },
@@ -191,6 +194,9 @@ static const struct {
   { "httppasswd",       &opt.http_passwd,       cmd_string }, /* deprecated */
   { "httppassword",     &opt.http_passwd,       cmd_string },
   { "httpproxy",        &opt.http_proxy,        cmd_string },
+#ifdef HAVE_SSL
+  { "httpsonly",        &opt.https_only,        cmd_boolean },
+#endif
   { "httpsproxy",       &opt.https_proxy,       cmd_string },
   { "httpuser",         &opt.http_user,         cmd_string },
   { "ignorecase",       &opt.ignore_case,       cmd_boolean },
@@ -210,6 +216,7 @@ static const struct {
   { "logfile",          &opt.lfilename,         cmd_file },
   { "login",            &opt.ftp_user,          cmd_string },/* deprecated*/
   { "maxredirect",      &opt.max_redirect,      cmd_number },
+  { "method",           &opt.method,            cmd_string_uppercase },
   { "mirror",           NULL,                   cmd_spec_mirror },
   { "netrc",            &opt.netrc,             cmd_boolean },
   { "noclobber",        &opt.noclobber,         cmd_boolean },
@@ -455,8 +462,7 @@ home_dir (void)
     }
 
   ret = home ? xstrdup (home) : NULL;
-  if (buf)
-    free (buf);
+  free (buf);
 
   return ret;
 }
@@ -570,7 +576,8 @@ bool
 run_wgetrc (const char *file)
 {
   FILE *fp;
-  char *line;
+  char *line = NULL;
+  size_t bufsize = 0;
   int ln;
   int errcnt = 0;
 
@@ -582,7 +589,7 @@ run_wgetrc (const char *file)
       return true;                      /* not a fatal error */
     }
   ln = 1;
-  while ((line = read_whole_line (fp)) != NULL)
+  while (getline (&line, &bufsize, fp) > 0)
     {
       char *com = NULL, *val = NULL;
       int comind;
@@ -616,9 +623,9 @@ run_wgetrc (const char *file)
         }
       xfree_null (com);
       xfree_null (val);
-      xfree (line);
       ++ln;
     }
+  xfree (line);
   fclose (fp);
 
   return errcnt == 0;
@@ -956,8 +963,25 @@ cmd_string (const char *com, const char *val, void *place)
   return true;
 }
 
+/* Like cmd_string but ensure the string is upper case.  */
+static bool
+cmd_string_uppercase (const char *com, const char *val, void *place)
+{
+  char *q, **pstring;
+  pstring = (char **)place;
+  xfree_null (*pstring);
 
-/* Like the above, but handles tilde-expansion when reading a user's
+  *pstring = xmalloc (strlen (val) + 1);
+
+  for (q = *pstring; *val; val++, q++)
+    *q = c_toupper (*val);
+
+  *q = '\0';
+  return true;
+}
+
+
+/* Like cmd_string, but handles tilde-expansion when reading a user's
    `.wgetrc'.  In that case, and if VAL begins with `~', the tilde
    gets expanded to the user's home directory.  */
 static bool
@@ -1472,6 +1496,7 @@ cmd_spec_secure_protocol (const char *com, const char *val, void *place)
     { "sslv2", secure_protocol_sslv2 },
     { "sslv3", secure_protocol_sslv3 },
     { "tlsv1", secure_protocol_tlsv1 },
+    { "pfs", secure_protocol_pfs },
   };
   int ok = decode_string (val, choices, countof (choices), place);
   if (!ok)
@@ -1669,6 +1694,7 @@ decode_string (const char *val, const struct decode_item *items, int itemcount,
 
 
 void cleanup_html_url (void);
+void spider_cleanup (void);
 
 
 /* Free the memory allocated by global variables.  */
@@ -1703,6 +1729,7 @@ cleanup (void)
   res_cleanup ();
   http_cleanup ();
   cleanup_html_url ();
+  spider_cleanup ();
   host_cleanup ();
   log_cleanup ();
 
@@ -1752,6 +1779,7 @@ cleanup (void)
   xfree_null (opt.user);
   xfree_null (opt.passwd);
   xfree_null (opt.base_href);
+  xfree_null (opt.method);
 
 #endif /* DEBUG_MALLOC */
 }

src/log.c

@@ -871,7 +871,7 @@ redirect_output (void)
          can do but disable printing completely. */
       fprintf (stderr, _("\n%s received.\n"), redirect_request_signal_name);
       fprintf (stderr, _("%s: %s; disabling logging.\n"),
-               logfile, strerror (errno));
+               (logfile) ? logfile : DEFAULT_LOGFILE, strerror (errno));
       inhibit_logging = true;
     }
   save_context_p = false;

src/main.c

@@ -167,6 +167,8 @@ static struct cmdline_option option_data[] =
     { "backups", 0, OPT_BOOLEAN, "backups", -1 },
     { "base", 'B', OPT_VALUE, "base", -1 },
     { "bind-address", 0, OPT_VALUE, "bindaddress", -1 },
+    { "body-data", 0, OPT_VALUE, "bodydata", -1 },
+    { "body-file", 0, OPT_VALUE, "bodyfile", -1 },
     { IF_SSL ("ca-certificate"), 0, OPT_VALUE, "cacertificate", -1 },
     { IF_SSL ("ca-directory"), 0, OPT_VALUE, "cadirectory", -1 },
     { "cache", 0, OPT_BOOLEAN, "cache", -1 },
@@ -215,6 +217,7 @@ static struct cmdline_option option_data[] =
     { "http-passwd", 0, OPT_VALUE, "httppassword", -1 }, /* deprecated */
     { "http-password", 0, OPT_VALUE, "httppassword", -1 },
     { "http-user", 0, OPT_VALUE, "httpuser", -1 },
+    { IF_SSL ("https-only"), 0, OPT_BOOLEAN, "httpsonly", -1 },
     { "ignore-case", 0, OPT_BOOLEAN, "ignorecase", -1 },
     { "ignore-length", 0, OPT_BOOLEAN, "ignorelength", -1 },
     { "ignore-tags", 0, OPT_VALUE, "ignoretags", -1 },
@@ -231,6 +234,7 @@ static struct cmdline_option option_data[] =
     { "load-cookies", 0, OPT_VALUE, "loadcookies", -1 },
     { "local-encoding", 0, OPT_VALUE, "localencoding", -1 },
     { "max-redirect", 0, OPT_VALUE, "maxredirect", -1 },
+    { "method", 0, OPT_VALUE, "method", -1 },
     { "mirror", 'm', OPT_BOOLEAN, "mirror", -1 },
     { "no", 'n', OPT__NO, NULL, required_argument },
     { "no-clobber", 0, OPT_BOOLEAN, "noclobber", -1 },
@@ -609,6 +613,12 @@ HTTP options:\n"),
        --post-data=STRING      use the POST method; send STRING as the data.\n"),
     N_("\
        --post-file=FILE        use the POST method; send contents of FILE.\n"),
+    N_("\
+       --method=HTTPMethod     use method \"HTTPMethod\" in the header.\n"),
+    N_("\
+       --body-data=STRING      Send STRING as data. --method MUST be set.\n"),
+    N_("\
+       --body-file=FILE        Send contents of FILE. --method MUST be set.\n"),
     N_("\
        --content-disposition   honor the Content-Disposition header when\n\
                                choosing local file names (EXPERIMENTAL).\n"),
@@ -625,7 +635,9 @@ HTTP options:\n"),
 HTTPS (SSL/TLS) options:\n"),
     N_("\
        --secure-protocol=PR     choose secure protocol, one of auto, SSLv2,\n\
-                                SSLv3, and TLSv1.\n"),
+                                SSLv3, TLSv1 and PFS.\n"),
+    N_("\
+       --https-only             only follow secure HTTPS links\n"),
     N_("\
        --no-check-certificate   don't validate the server's certificate.\n"),
     N_("\
@@ -705,6 +717,9 @@ Recursive download:\n"),
     N_("\
   -k,  --convert-links      make links in downloaded HTML or CSS point to\n\
                             local files.\n"),
+    N_("\
+  --backups=N   before writing file X, rotate up to N backup files.\n"),
+
 #ifdef __VMS
     N_("\
   -K,  --backup-converted   before converting file X, back up as X_orig.\n"),
@@ -828,15 +843,16 @@ format_and_print_line (const char *prefix, const char *line,
 
   assert (prefix != NULL);
   assert (line != NULL);
+  assert (line_length > TABULATION);
 
   line_dup = xstrdup (line);
 
-  if (line_length <= 0)
-    line_length = MAX_CHARS_PER_LINE - TABULATION;
-
   if (printf ("%s", prefix) < 0)
     return -1;
-  remaining_chars = line_length;
+
+  /* Wrap to new line after prefix. */
+  remaining_chars = 0;
+
   /* We break on spaces. */
   token = strtok (line_dup, " ");
   while (token != NULL)
@@ -844,7 +860,7 @@ format_and_print_line (const char *prefix, const char *line,
       /* If however a token is much larger than the maximum
          line length, all bets are off and we simply print the
          token on the next line. */
-      if (remaining_chars <= strlen (token))
+      if (remaining_chars <= (int) strlen (token))
         {
           if (printf ("\n%*c", TABULATION, ' ') < 0)
             return -1;
@@ -918,7 +934,7 @@ print_version (void)
 
 #ifdef ENABLE_NLS
   if (format_and_print_line (locale_title,
-                        LOCALEDIR,
+                             LOCALEDIR,
                              MAX_CHARS_PER_LINE) < 0)
     exit (3);
 #endif /* def ENABLE_NLS */
@@ -1034,7 +1050,6 @@ main (int argc, char **argv)
                                 short_options, long_options, &longindex)) != -1)
     {
       int confval;
-      bool userrc_ret = true;
       struct cmdline_option *config_opt;
 
       /* There is no short option for "--config". */
@@ -1044,16 +1059,17 @@ main (int argc, char **argv)
           config_opt = &option_data[confval & ~BOOLEAN_NEG_MARKER];
           if (strcmp (config_opt->long_name, "config") == 0)
             {
+              bool userrc_ret = true;
               userrc_ret &= run_wgetrc (optarg);
               use_userconfig = true;
+              if (userrc_ret)
+                break;
+              else
+                {
+                  fprintf (stderr, _("Exiting due to error in %s\n"), optarg);
+                  exit (2);
+                }
             }
-          if (!userrc_ret)
-            {
-              fprintf (stderr, "Exiting due to error in %s\n", optarg);
-              exit (2);
-            }
-          else
-            break;
         }
     }
 
@@ -1211,6 +1227,7 @@ main (int argc, char **argv)
   if (opt.verbose == -1)
     opt.verbose = !opt.quiet;
 
+
   /* Sanity checks.  */
   if (opt.verbose && opt.quiet)
     {
@@ -1358,6 +1375,64 @@ for details.\n\n"));
       if (!opt.rejectregex)
         exit (1);
     }
+  if (opt.post_data || opt.post_file_name)
+    {
+      if (opt.post_data && opt.post_file_name)
+        {
+          fprintf (stderr, _("You cannot specify both --post-data and --post-file.\n"));
+          exit (1);
+        }
+      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"));
+          exit (1);
+        }
+    }
+  if (opt.body_data || opt.body_file)
+    {
+      if (!opt.method)
+        {
+          fprintf (stderr, _("You must specify a method through --method=HTTPMethod "
+                              "to use with --body-data or --body-file.\n"));
+          exit (1);
+        }
+      else if (opt.body_data && opt.body_file)
+        {
+          fprintf (stderr, _("You cannot specify both --body-data and --body-file.\n"));
+          exit (1);
+        }
+    }
+
+  /* Set various options as required for opt.method.  */
+
+  /* When user specifies HEAD as the method, we do not wish to download any
+     files. Hence, set wget to run in spider mode.  */
+  if (opt.method && strcasecmp (opt.method, "HEAD") == 0)
+    setoptval ("spider", "1", "spider");
+
+  /* Convert post_data to body-data and post_file_name to body-file options.
+     This is required so as to remove redundant code later on in gethttp().
+     The --post-data and --post-file options may also be removed in
+     the future hence it makes sense to convert them to aliases for
+     the more generic --method options.
+     This MUST occur only after the sanity checks so as to prevent the
+     user from setting both post and body options simultaneously.
+  */
+  if (opt.post_data || opt.post_file_name)
+    {
+        setoptval ("method", "POST", "method");
+        if (opt.post_data)
+          {
+            setoptval ("bodydata", opt.post_data, "body-data");
+            opt.post_data = NULL;
+          }
+        else
+          {
+            setoptval ("bodyfile", opt.post_file_name, "body-file");
+            opt.post_file_name = NULL;
+          }
+    }
 
 #ifdef ENABLE_IRI
   if (opt.enable_iri)

src/mswindows.c

@@ -323,7 +323,7 @@ fork_to_background (void)
   rv = fake_fork_child ();
   if (rv < 0)
     {
-      fprintf (stderr, "fake_fork_child() failed\n");
+      fprintf (stderr, _("fake_fork_child() failed\n"));
       abort ();
     }
   else if (rv == 0)
@@ -331,7 +331,7 @@ fork_to_background (void)
       /* We're the parent.  */
       fake_fork ();
       /* If fake_fork() returns, it failed.  */
-      fprintf (stderr, "fake_fork() failed\n");
+      fprintf (stderr, _("fake_fork() failed\n"));
       abort ();
     }
   /* If we get here, we're the child.  */
@@ -646,7 +646,7 @@ set_windows_fd_as_blocking_socket (int fd)
 	if(ret)
     {
       fprintf (stderr,
-               "ioctl() failed.  The socket could not be set as blocking.\n" );
+               _("ioctl() failed.  The socket could not be set as blocking.\n") );
       DEBUGP (("Winsock error: %d\n", WSAGetLastError ()));
       abort ();
     }

src/netrc.c

@@ -164,48 +164,6 @@ search_netrc (const char *host, const char **acc, const char **passwd,
 
 # define xrealloc realloc
 
-/* Read a line from FP.  The function reallocs the storage as needed
-   to accomodate for any length of the line.  Reallocs are done
-   storage exponentially, doubling the storage after each overflow to
-   minimize the number of calls to realloc() and fgets().  The newline
-   character at the end of line is retained.
-
-   After end-of-file is encountered without anything being read, NULL
-   is returned.  NULL is also returned on error.  To distinguish
-   between these two cases, use the stdio function ferror().  */
-
-char *
-read_whole_line (FILE *fp)
-{
-  int length = 0;
-  int bufsize = 81;
-  char *line = xmalloc (bufsize);
-
-  while (fgets (line + length, bufsize - length, fp))
-    {
-      length += strlen (line + length);
-      assert (length > 0);
-      if (line[length - 1] == '\n')
-        break;
-      /* fgets() guarantees to read the whole line, or to use up the
-         space we've given it.  We can double the buffer
-         unconditionally.  */
-      bufsize <<= 1;
-      line = xrealloc (line, bufsize);
-    }
-  if (length == 0 || ferror (fp))
-    {
-      xfree (line);
-      return NULL;
-    }
-  if (length + 1 < bufsize)
-    /* Relieve the memory from our exponential greediness.  We say
-       `length + 1' because the terminating \0 is not included in
-       LENGTH.  We don't need to zero-terminate the string ourselves,
-       though, because fgets() does that.  */
-    line = xrealloc (line, length + 1);
-  return line;
-}
 #endif /* STANDALONE */
 
 /* Maybe add NEWENTRY to the account information list, LIST.  NEWENTRY is
@@ -264,10 +222,11 @@ static acc_t *
 parse_netrc (const char *path)
 {
   FILE *fp;
-  char *line, *p, *tok;
+  char *line = NULL, *p, *tok;
   const char *premature_token;
   acc_t *current, *retval;
   int ln, qmark;
+  size_t bufsize = 0;
 
   /* The latest token we've seen in the file.  */
   enum
@@ -290,7 +249,7 @@ parse_netrc (const char *path)
   premature_token = NULL;
 
   /* While there are lines in the file...  */
-  while ((line = read_whole_line (fp)) != NULL)
+  while (getline (&line, &bufsize, fp) > 0)
     {
       ln ++;
 
@@ -423,10 +382,9 @@ parse_netrc (const char *path)
                          exec_name, path, ln, tok);
             }
         }
-
-      xfree (line);
     }
 
+  xfree (line);
   fclose (fp);
 
   /* Finalize the last machine entry we found.  */

src/openssl.c

@@ -194,6 +194,7 @@ ssl_init (void)
     case secure_protocol_sslv3:
       meth = SSLv3_client_method ();
       break;
+    case secure_protocol_pfs:
     case secure_protocol_tlsv1:
       meth = TLSv1_client_method ();
       break;
@@ -207,6 +208,12 @@ ssl_init (void)
   if (!ssl_ctx)
     goto error;
 
+  /* OpenSSL ciphers: https://www.openssl.org/docs/apps/ciphers.html
+   * Since we want a good protection, we also use HIGH (that excludes MD4 ciphers and some more)
+   */
+  if (opt.secure_protocol == secure_protocol_pfs)
+    SSL_CTX_set_cipher_list (ssl_ctx, "HIGH:MEDIUM:!RC4:!SRP:!PSK:!RSA:!aNULL@STRENGTH");
+
   SSL_CTX_set_default_verify_paths (ssl_ctx);
   SSL_CTX_load_verify_locations (ssl_ctx, opt.ca_cert, opt.ca_directory);
 
@@ -251,24 +258,50 @@ ssl_init (void)
   return false;
 }
 
-struct openssl_transport_context {
+struct openssl_transport_context
+{
   SSL *conn;                    /* SSL connection handle */
   char *last_error;             /* last error printed with openssl_errstr */
 };
 
+struct openssl_read_args
+{
+  int fd;
+  struct openssl_transport_context *ctx;
+  char *buf;
+  int bufsize;
+  int retval;
+};
+
+static void openssl_read_callback(void *arg)
+{
+  struct openssl_read_args *args = (struct openssl_read_args *) arg;
+  struct openssl_transport_context *ctx = args->ctx;
+  SSL *conn = ctx->conn;
+  char *buf = args->buf;
+  int bufsize = args->bufsize;
+  int ret;
+
+  do
+    ret = SSL_read (conn, buf, bufsize);
+  while (ret == -1 && SSL_get_error (conn, ret) == SSL_ERROR_SYSCALL
+         && errno == EINTR);
+  args->retval = ret;
+}
+
 static int
 openssl_read (int fd, char *buf, int bufsize, void *arg)
 {
-  int ret;
-  struct openssl_transport_context *ctx = arg;
-  SSL *conn = ctx->conn;
-  do
-    ret = SSL_read (conn, buf, bufsize);
-  while (ret == -1
-         && SSL_get_error (conn, ret) == SSL_ERROR_SYSCALL
-         && errno == EINTR);
+  struct openssl_read_args args;
+  args.fd = fd;
+  args.buf = buf;
+  args.bufsize = bufsize;
+  args.ctx = (struct openssl_transport_context*) arg;
 
-  return ret;
+  if (run_with_timeout(opt.read_timeout, openssl_read_callback, &args)) {
+    return -1;
+  }
+  return args.retval;
 }
 
 static int
@@ -386,6 +419,19 @@ static struct transport_implementation openssl_transport = {
   openssl_peek, openssl_errstr, openssl_close
 };
 
+struct scwt_context
+{
+  SSL *ssl;
+  int result;
+};
+
+static void
+ssl_connect_with_timeout_callback(void *arg)
+{
+  struct scwt_context *ctx = (struct scwt_context *)arg;
+  ctx->result = SSL_connect(ctx->ssl);
+}
+
 /* Perform the SSL handshake on file descriptor FD, which is assumed
    to be connected to an SSL server.  The SSL handle provided by
    OpenSSL is registered with the file descriptor FD using
@@ -398,6 +444,7 @@ bool
 ssl_connect_wget (int fd, const char *hostname)
 {
   SSL *conn;
+  struct scwt_context scwt_ctx;
   struct openssl_transport_context *ctx;
 
   DEBUGP (("Initiating SSL handshake.\n"));
@@ -425,7 +472,14 @@ ssl_connect_wget (int fd, const char *hostname)
   if (!SSL_set_fd (conn, FD_TO_SOCKET (fd)))
     goto error;
   SSL_set_connect_state (conn);
-  if (SSL_connect (conn) <= 0 || conn->state != SSL_ST_OK)
+
+  scwt_ctx.ssl = conn;
+  if (run_with_timeout(opt.read_timeout, ssl_connect_with_timeout_callback,
+                       &scwt_ctx)) {
+    DEBUGP (("SSL handshake timed out.\n"));
+    goto timeout;
+  }
+  if (scwt_ctx.result <= 0 || conn->state != SSL_ST_OK)
     goto error;
 
   ctx = xnew0 (struct openssl_transport_context);
@@ -441,6 +495,7 @@ ssl_connect_wget (int fd, const char *hostname)
  error:
   DEBUGP (("SSL handshake failed.\n"));
   print_errors ();
+ timeout:
   if (conn)
     SSL_free (conn);
   return false;

src/options.h

@@ -166,7 +166,7 @@ struct options
   bool timestamping;		/* Whether to use time-stamping. */
 
   bool backup_converted;	/* Do we save pre-converted files as *.orig? */
-  bool backups;			/* Are numeric backups made? */
+  int backups;			/* Are numeric backups made? */
 
   char *useragent;		/* User-Agent string, which can be set
 				   to something other than Wget. */
@@ -200,7 +200,8 @@ struct options
     secure_protocol_auto,
     secure_protocol_sslv2,
     secure_protocol_sslv3,
-    secure_protocol_tlsv1
+    secure_protocol_tlsv1,
+    secure_protocol_pfs
   } secure_protocol;		/* type of secure protocol to use. */
   bool check_cert;		/* whether to validate the server's cert */
   char *cert_file;		/* external client certificate to use. */
@@ -215,9 +216,9 @@ struct options
   char *ca_directory;		/* CA directory (hash files) */
   char *ca_cert;		/* CA certificate file to use */
 
-
   char *random_file;		/* file with random data to seed the PRNG */
   char *egd_file;		/* file name of the egd daemon socket */
+  bool https_only;		/* whether to follow HTTPS only */
 #endif /* HAVE_SSL */
 
   bool cookies;			/* whether cookies are used. */
@@ -228,6 +229,9 @@ struct options
 
   char *post_data;		/* POST query string */
   char *post_file_name;		/* File to post */
+  char *method;                 /* HTTP Method to use in Header */
+  char *body_data;              /* HTTP Method Data String */
+  char *body_file;              /* HTTP Method File */
 
   enum {
     restrict_unix,

src/recur.c

@@ -1,6 +1,6 @@
 /* Handling of recursive HTTP retrieving.
    Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
-   2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
+   2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation,
    Inc.
 
 This file is part of GNU Wget.
@@ -253,26 +253,23 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
          the second time.  */
       if (dl_url_file_map && hash_table_contains (dl_url_file_map, url))
         {
+	  bool is_css_bool;
+
           file = xstrdup (hash_table_get (dl_url_file_map, url));
 
           DEBUGP (("Already downloaded \"%s\", reusing it from \"%s\".\n",
                    url, file));
 
-          /* this sucks, needs to be combined! */
-          if (html_allowed
-              && downloaded_html_set
-              && string_set_contains (downloaded_html_set, file))
-            {
-              descend = true;
-              is_css = false;
-            }
-          if (css_allowed
-              && downloaded_css_set
-              && string_set_contains (downloaded_css_set, file))
-            {
-              descend = true;
-              is_css = true;
-            }
+	  if ((is_css_bool = (css_allowed
+			      && downloaded_css_set
+			      && string_set_contains (downloaded_css_set, file)))
+	      || (html_allowed
+		  && downloaded_html_set
+		  && string_set_contains (downloaded_html_set, file)))
+	    {
+	      descend = true;
+	      is_css = is_css_bool;
+	    }
         }
       else
         {
@@ -508,15 +505,16 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
     }
 
   /* Several things to check for:
-     1. if scheme is not http, and we don't load it
-     2. check for relative links (if relative_only is set)
-     3. check for domain
-     4. check for no-parent
-     5. check for excludes && includes
-     6. check for suffix
-     7. check for same host (if spanhost is unset), with possible
+     1. if scheme is not https and https_only requested
+     2. if scheme is not http, and we don't load it
+     3. check for relative links (if relative_only is set)
+     4. check for domain
+     5. check for no-parent
+     6. check for excludes && includes
+     7. check for suffix
+     8. check for same host (if spanhost is unset), with possible
      gethostbyname baggage
-     8. check for robots.txt
+     9. check for robots.txt
 
      Addendum: If the URL is FTP, and it is to be loaded, only the
      domain and suffix settings are "stronger".
@@ -528,6 +526,14 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
      More time- and memory- consuming tests should be put later on
      the list.  */
 
+#ifdef HAVE_SSL
+  if (opt.https_only && u->scheme != SCHEME_HTTPS)
+    {
+      DEBUGP (("Not following non-HTTPS links.\n"));
+      goto out;
+    }
+#endif
+
   /* Determine whether URL under consideration has a HTTP-like scheme. */
   u_scheme_like_http = schemes_are_similar_p (u->scheme, SCHEME_HTTP);
 
@@ -641,7 +647,7 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
                  files after downloading or we're just running a spider. */
               if (opt.delete_after || opt.spider)
                 {
-                  logprintf (LOG_VERBOSE, "Removing %s.\n", rfile);
+                  logprintf (LOG_VERBOSE, _("Removing %s.\n"), rfile);
                   if (unlink (rfile))
                       logprintf (LOG_NOTQUIET, "unlink: %s\n",
                                  strerror (errno));

src/retr.c

@@ -37,6 +37,9 @@ as that of the covered work.  */
 #include <errno.h>
 #include <string.h>
 #include <assert.h>
+#ifdef VMS
+# include <unixio.h>            /* For delete(). */
+#endif
 
 #include "exits.h"
 #include "utils.h"
@@ -141,8 +144,8 @@ limit_bandwidth (wgint bytes, struct ptimer *timer)
    amount of data and decrease SKIP.  Increment *TOTAL by the amount
    of data written.  If OUT2 is not NULL, also write BUF to OUT2.
    In case of error writing to OUT, -1 is returned.  In case of error
-   writing to OUT2, -2 is returned.  In case of any other error,
-   1 is returned.  */
+   writing to OUT2, -2 is returned.  Return 1 if the whole BUF was
+   skipped.  */
 
 static int
 write_data (FILE *out, FILE *out2, const char *buf, int bufsize,
@@ -376,7 +379,7 @@ fd_read_body (int fd, FILE *out, wgint toread, wgint startpos,
         {
           sum_read += ret;
           int write_res = write_data (out, out2, dlbuf, ret, &skip, &sum_written);
-          if (write_res != 0)
+          if (write_res < 0)
             {
               ret = (write_res == -3) ? -3 : -2;
               goto out;
@@ -677,20 +680,23 @@ calc_rate (wgint bytes, double secs, int *units)
 }
 
 
-#define SUSPEND_POST_DATA do {                  \
-  post_data_suspended = true;                   \
-  saved_post_data = opt.post_data;              \
-  saved_post_file_name = opt.post_file_name;    \
-  opt.post_data = NULL;                         \
-  opt.post_file_name = NULL;                    \
+#define SUSPEND_METHOD do {                     \
+  method_suspended = true;                      \
+  saved_body_data = opt.body_data;              \
+  saved_body_file_name = opt.body_file;         \
+  saved_method = opt.method;                    \
+  opt.body_data = NULL;                         \
+  opt.body_file = NULL;                         \
+  opt.method = NULL;                            \
 } while (0)
 
-#define RESTORE_POST_DATA do {                          \
-  if (post_data_suspended)                              \
+#define RESTORE_METHOD do {                             \
+  if (method_suspended)                                 \
     {                                                   \
-      opt.post_data = saved_post_data;                  \
-      opt.post_file_name = saved_post_file_name;        \
-      post_data_suspended = false;                      \
+      opt.body_data = saved_body_data;                  \
+      opt.body_file = saved_body_file_name;             \
+      opt.method = saved_method;                        \
+      method_suspended = false;                         \
     }                                                   \
 } while (0)
 
@@ -718,9 +724,10 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
   char *local_file;
   int redirection_count = 0;
 
-  bool post_data_suspended = false;
-  char *saved_post_data = NULL;
-  char *saved_post_file_name = NULL;
+  bool method_suspended = false;
+  char *saved_body_data = NULL;
+  char *saved_method = NULL;
+  char *saved_body_file_name = NULL;
 
   /* If dt is NULL, use local storage.  */
   if (!dt)
@@ -761,7 +768,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
                      proxy, error);
           xfree (url);
           xfree (error);
-          RESTORE_POST_DATA;
+          RESTORE_METHOD;
           result = PROXERR;
           goto bail;
         }
@@ -770,7 +777,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
           logprintf (LOG_NOTQUIET, _("Error in proxy URL %s: Must be HTTP.\n"), proxy);
           url_free (proxy_url);
           xfree (url);
-          RESTORE_POST_DATA;
+          RESTORE_METHOD;
           result = PROXERR;
           goto bail;
         }
@@ -838,6 +845,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
       iri->utf8_encode = opt.enable_iri;
       set_content_encoding (iri, NULL);
       xfree_null (iri->orig_url);
+      iri->orig_url = NULL;
 
       /* Now, see if this new location makes sense. */
       newloc_parsed = url_parse (mynewloc, &up_error_code, iri, true);
@@ -853,7 +861,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
           xfree (url);
           xfree (mynewloc);
           xfree (error);
-          RESTORE_POST_DATA;
+          RESTORE_METHOD;
           goto bail;
         }
 
@@ -875,7 +883,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
             }
           xfree (url);
           xfree (mynewloc);
-          RESTORE_POST_DATA;
+          RESTORE_METHOD;
           result = WRONGCODE;
           goto bail;
         }
@@ -898,8 +906,8 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
 	 RFC2616 HTTP/1.1 introduces code 307 Temporary Redirect
 	 specifically to preserve the method of the request.
 	 */
-      if (result != NEWLOCATION_KEEP_POST && !post_data_suspended)
-        SUSPEND_POST_DATA;
+      if (result != NEWLOCATION_KEEP_POST && !method_suspended)
+        SUSPEND_METHOD;
 
       goto redirected;
     }
@@ -962,7 +970,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
       xfree (url);
     }
 
-  RESTORE_POST_DATA;
+  RESTORE_METHOD;
 
 bail:
   if (register_status)
@@ -1177,7 +1185,16 @@ free_urlpos (struct urlpos *l)
 void
 rotate_backups(const char *fname)
 {
-  int maxlen = strlen (fname) + 1 + numdigit (opt.backups) + 1;
+#ifdef __VMS
+# define SEP "_"
+# define AVS ";*"                       /* All-version suffix. */
+# define AVSL (sizeof (AVS) - 1)
+#else
+# define SEP "."
+# define AVSL 0
+#endif
+
+  int maxlen = strlen (fname) + sizeof (SEP) + numdigit (opt.backups) + AVSL;
   char *from = (char *)alloca (maxlen);
   char *to = (char *)alloca (maxlen);
   struct_stat sb;
@@ -1189,12 +1206,24 @@ rotate_backups(const char *fname)
 
   for (i = opt.backups; i > 1; i--)
     {
-      sprintf (from, "%s.%d", fname, i - 1);
-      sprintf (to, "%s.%d", fname, i);
+#ifdef VMS
+      /* Delete (all versions of) any existing max-suffix file, to avoid
+       * creating multiple versions of it.  (On VMS, rename() will
+       * create a new version of an existing destination file, not
+       * destroy/overwrite it.)
+       */
+      if (i == opt.backups)
+        {
+          sprintf (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);
     }
 
-  sprintf (to, "%s.%d", fname, 1);
+  sprintf (to, "%s%s%d", fname, SEP, 1);
   rename(fname, to);
 }
 

src/spider.c

@@ -45,7 +45,7 @@ static struct hash_table *nonexisting_urls_set;
 
 /* Cleanup the data structures associated with this file.  */
 
-static void
+void
 spider_cleanup (void)
 {
   if (nonexisting_urls_set)

src/test.c

@@ -28,6 +28,8 @@ Corresponding Source for a non-source form of such a combination
 shall include the source code for the parts of OpenSSL used as well
 as that of the covered work.  */
 
+#include "wget.h"
+
 #include <stdio.h>
 
 #include "test.h"

src/url.c

@@ -701,7 +701,10 @@ url_parse (const char *url, int *error, struct iri *iri, bool percent_encode)
       if (!iri->utf8_encode)
         new_url = NULL;
       else
-        iri->orig_url = xstrdup (url);
+        {
+          iri->orig_url = xstrdup (url);
+          percent_encode = true;
+        }
     }
 
   /* XXX XXX Could that change introduce (security) bugs ???  XXX XXX*/
@@ -1245,12 +1248,16 @@ mkalldirs (const char *path)
    The idea is to have a convenient and efficient way to construct a
    string by having various functions append data to it.  Instead of
    passing the obligatory BASEVAR, SIZEVAR and TAILPOS to all the
-   functions in questions, we pass the pointer to this struct.  */
+   functions in questions, we pass the pointer to this struct.
+
+   Functions that write to the members in this struct must make sure
+   that base remains null terminated by calling append_null().
+   */
 
 struct growable {
   char *base;
-  int size;
-  int tail;
+  int size;   /* memory allocated */
+  int tail;   /* string length */
 };
 
 /* Ensure that the string can accept APPEND_COUNT more characters past
@@ -1268,28 +1275,55 @@ struct growable {
 /* Move the tail position by APPEND_COUNT characters. */
 #define TAIL_INCR(r, append_count) ((r)->tail += append_count)
 
-/* Append the string STR to DEST.  NOTICE: the string in DEST is not
-   terminated.  */
 
+/* Append NULL to DEST. */
+static void
+append_null (struct growable *dest)
+{
+  GROW (dest, 1);
+  *TAIL (dest) = 0;
+}
+
+/* Shorten DEST to LENGTH. */
+static void
+shorten_length (size_t length, struct growable *dest)
+{
+  if (length < dest->tail)
+    dest->tail = length;
+
+  append_null (dest);
+}
+
+/* Append CH to DEST. */
+static void
+append_char (char ch, struct growable *dest)
+{
+  if (ch)
+    {
+      GROW (dest, 1);
+      *TAIL (dest) = ch;
+      TAIL_INCR (dest, 1);
+    }
+
+  append_null (dest);
+}
+
+/* Append the string STR to DEST. */
 static void
 append_string (const char *str, struct growable *dest)
 {
   int l = strlen (str);
-  GROW (dest, l);
-  memcpy (TAIL (dest), str, l);
-  TAIL_INCR (dest, l);
+
+  if (l)
+    {
+      GROW (dest, l);
+      memcpy (TAIL (dest), str, l);
+      TAIL_INCR (dest, l);
+    }
+
+  append_null (dest);
 }
 
-/* Append CH to DEST.  For example, append_char (0, DEST)
-   zero-terminates DEST.  */
-
-static void
-append_char (char ch, struct growable *dest)
-{
-  GROW (dest, 1);
-  *TAIL (dest) = ch;
-  TAIL_INCR (dest, 1);
-}
 
 enum {
   filechr_not_unix    = 1,      /* unusable on Unix, / and \0 */
@@ -1361,6 +1395,7 @@ UWC,  C,  C,  C,   C,  C,  C,  C,   /* NUL SOH STX ETX  EOT ENQ ACK BEL */
    query, normally '?'.  Since Windows cannot handle '?' as part of
    file name, we use '@' instead there.  */
 #define FN_QUERY_SEP (opt.restrict_files_os != restrict_windows ? '?' : '@')
+#define FN_QUERY_SEP_STR (opt.restrict_files_os != restrict_windows ? "?" : "@")
 
 /* Quote path element, characters in [b, e), as file name, and append
    the quoted string to DEST.  Each character is quoted as per
@@ -1454,6 +1489,7 @@ append_uri_pathel (const char *b, const char *e, bool escaped,
     }
 
   TAIL_INCR (dest, outlen);
+  append_null (dest);
 }
 
 /* Append to DEST the directory structure that corresponds the
@@ -1494,22 +1530,28 @@ append_dir_structure (const struct url *u, struct growable *dest)
     }
 }
 
-/* Return a unique file name that matches the given URL as good as
+/* Return a unique file name that matches the given URL as well as
    possible.  Does not create directories on the file system.  */
 
 char *
 url_file_name (const struct url *u, char *replaced_filename)
 {
   struct growable fnres;        /* stands for "file name result" */
+  struct growable temp_fnres;
 
   const char *u_file;
-  char *fname, *unique;
+  char *fname, *unique, *fname_len_check;
   const char *index_filename = "index.html"; /* The default index file is index.html */
+  size_t max_length;
 
   fnres.base = NULL;
   fnres.size = 0;
   fnres.tail = 0;
 
+  temp_fnres.base = NULL;
+  temp_fnres.size = 0;
+  temp_fnres.tail = 0;
+
   /* If an alternative index file was defined, change index_filename */
   if (opt.default_page)
     index_filename = opt.default_page;
@@ -1555,43 +1597,87 @@ url_file_name (const struct url *u, char *replaced_filename)
 
   if (!replaced_filename)
     {
-      /* Add the file name. */
-      if (fnres.tail)
-	append_char ('/', &fnres);
+      /* Create the filename. */
       u_file = *u->file ? u->file : index_filename;
-      append_uri_pathel (u_file, u_file + strlen (u_file), false, &fnres);
 
-      /* Append "?query" to the file name, even if empty */
+      /* Append "?query" to the file name, even if empty,
+       * and create fname_len_check. */
       if (u->query)
-	{
-	  append_char (FN_QUERY_SEP, &fnres);
-	  append_uri_pathel (u->query, u->query + strlen (u->query),
-			     true, &fnres);
-	}
+        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));
     }
   else
     {
-      if (fnres.tail)
-	append_char ('/', &fnres);
       u_file = replaced_filename;
-      append_uri_pathel (u_file, u_file + strlen (u_file), false, &fnres);
+      fname_len_check = strdupdelim (u_file, u_file + strlen (u_file));
     }
 
-  /* Zero-terminate the file name. */
-  append_char ('\0', &fnres);
+  append_uri_pathel (fname_len_check,
+    fname_len_check + strlen (fname_len_check), false, &temp_fnres);
+
+  /* Zero-terminate the temporary file name. */
+  append_char ('\0', &temp_fnres);
+
+  /* Check that the length of the file name is acceptable. */
+#ifdef WINDOWS
+  if (MAX_PATH > (fnres.tail + CHOMP_BUFFER + 2))
+    {
+      max_length = MAX_PATH - (fnres.tail + CHOMP_BUFFER + 2);
+      /* FIXME: In Windows a filename is usually limited to 255 characters.
+      To really be accurate you could call GetVolumeInformation() to get
+      lpMaximumComponentLength
+      */
+      if (max_length > 255)
+        {
+          max_length = 255;
+        }
+    }
+  else
+    {
+      max_length = 0;
+    }
+#else
+  max_length = get_max_length (fnres.base, fnres.tail, _PC_NAME_MAX) - CHOMP_BUFFER;
+#endif
+  if (max_length > 0 && strlen (temp_fnres.base) > max_length)
+    {
+      logprintf (LOG_NOTQUIET, "The name is too long, %lu chars total.\n",
+          (unsigned long) strlen (temp_fnres.base));
+      logprintf (LOG_NOTQUIET, "Trying to shorten...\n");
+
+      /* Shorten the file name. */
+      temp_fnres.base[max_length] = '\0';
+
+      logprintf (LOG_NOTQUIET, "New name is %s.\n", temp_fnres.base);
+    }
+
+  free (fname_len_check);
+
+  /* The filename has already been 'cleaned' by append_uri_pathel() above.  So,
+   * just append it. */
+  if (fnres.tail)
+    append_char ('/', &fnres);
+  append_string (temp_fnres.base, &fnres);
 
   fname = fnres.base;
 
+  /* Make a final check that the path length is acceptable? */
+  /* TODO: check fnres.base for path length problem */
+
+  free (temp_fnres.base);
+
   /* Check the cases in which the unique extensions are not used:
      1) Clobbering is turned off (-nc).
      2) Retrieval with regetting.
      3) Timestamping is used.
      4) Hierarchy is built.
+     5) Backups are specified.
 
      The exception is the case when file does exist and is a
      directory (see `mkalldirs' for explanation).  */
 
-  if ((opt.noclobber || opt.always_rest || opt.timestamping || opt.dirstruct)
+  if (ALLOW_CLOBBER
       && !(file_exists_p (fname) && !file_non_directory_p (fname)))
     {
       unique = fname;
@@ -2228,7 +2314,6 @@ test_append_uri_pathel()
 
       append_string (test_array[i].original_url, &dest);
       append_uri_pathel (p, p + strlen(p), test_array[i].escaped, &dest);
-      append_char ('\0', &dest);
 
       mu_assert ("test_append_uri_pathel: wrong result",
                  strcmp (dest.base, test_array[i].expected_result) == 0);

src/url.h

@@ -37,6 +37,22 @@ as that of the covered work.  */
 #define DEFAULT_FTP_PORT 21
 #define DEFAULT_HTTPS_PORT 443
 
+/* This represents how many characters less than the OS max name length a file
+ * should be.  More precisely, a file name should be at most
+ * (NAME_MAX - CHOMP_BUFFER) characters in length.  This number was arrived at
+ * by adding the lengths of all possible strings that could be appended to a
+ * file name later in the code (e.g. ".orig", ".html", etc.).  This is
+ * hopefully plenty of extra characters, but I am not guaranteeing that a file
+ * name will be of the proper length by the time the code wants to open a
+ * file descriptor. */
+#define CHOMP_BUFFER 19
+
+/* The flags that allow clobbering the file (opening with "wb").
+   Defined here to avoid repetition later.  #### This will require
+   rework.  */
+#define ALLOW_CLOBBER (opt.noclobber || opt.always_rest || opt.timestamping \
+                  || opt.dirstruct || opt.output_document || opt.backups > 0)
+
 /* Specifies how, or whether, user auth information should be included
  * in URLs regenerated from URL parse structures. */
 enum url_auth_mode {

src/utils.c

@@ -703,7 +703,7 @@ unique_create (const char *name, bool binary, char **opened_name)
       xfree (uname);
       uname = unique_name (name, false);
     }
-  if (opened_name && fp != NULL)
+  if (opened_name)
     {
       if (fp)
         *opened_name = uname;
@@ -900,15 +900,14 @@ static bool in_acclist (const char *const *, const char *, bool);
 bool
 acceptable (const char *s)
 {
-  int l = strlen (s);
+  const char *p;
 
   if (opt.output_document && strcmp (s, opt.output_document) == 0)
     return true;
 
-  while (l && s[l] != '/')
-    --l;
-  if (s[l] == '/')
-    s += (l + 1);
+  if ((p = strrchr (s, '/')))
+    s = p + 1;
+
   if (opt.accepts)
     {
       if (opt.rejects)
@@ -919,6 +918,7 @@ acceptable (const char *s)
     }
   else if (opt.rejects)
     return !in_acclist ((const char *const *)opt.rejects, s, true);
+
   return true;
 }
 
@@ -1018,29 +1018,15 @@ accdir (const char *directory)
 bool
 match_tail (const char *string, const char *tail, bool fold_case)
 {
-  int i, j;
+  int pos = strlen (string) - strlen (tail);
 
-  /* We want this to be fast, so we code two loops, one with
-     case-folding, one without. */
+  if (pos < 0)
+    return false;  /* tail is longer than string.  */
 
   if (!fold_case)
-    {
-      for (i = strlen (string), j = strlen (tail); i >= 0 && j >= 0; i--, j--)
-        if (string[i] != tail[j])
-          break;
-    }
+    return !strcmp (string + pos, tail);
   else
-    {
-      for (i = strlen (string), j = strlen (tail); i >= 0 && j >= 0; i--, j--)
-        if (c_tolower (string[i]) != c_tolower (tail[j]))
-          break;
-    }
-
-  /* If the tail was exhausted, the match was succesful.  */
-  if (j == -1)
-    return true;
-  else
-    return false;
+    return !strcasecmp (string + pos, tail);
 }
 
 /* Checks whether string S matches each element of ACCEPTS.  A list
@@ -1089,15 +1075,12 @@ in_acclist (const char *const *accepts, const char *s, bool backward)
 char *
 suffix (const char *str)
 {
-  int i;
+  char *p;
 
-  for (i = strlen (str); i && str[i] != '/' && str[i] != '.'; i--)
-    ;
+  if ((p = strrchr (str, '.')) && !strchr (p + 1, '/'))
+    return p + 1;
 
-  if (str[i++] == '.')
-    return (char *)str + i;
-  else
-    return NULL;
+  return NULL;
 }
 
 /* Return true if S contains globbing wildcards (`*', `?', `[' or
@@ -1106,10 +1089,7 @@ suffix (const char *str)
 bool
 has_wildcards_p (const char *s)
 {
-  for (; *s; s++)
-    if (*s == '*' || *s == '?' || *s == '[' || *s == ']')
-      return true;
-  return false;
+  return !!strpbrk (s, "*?[]");
 }
 
 /* Return true if FNAME ends with a typical HTML suffix.  The
@@ -1138,56 +1118,6 @@ has_html_suffix_p (const char *fname)
   return false;
 }
 
-/* Read a line from FP and return the pointer to freshly allocated
-   storage.  The storage space is obtained through malloc() and should
-   be freed with free() when it is no longer needed.
-
-   The length of the line is not limited, except by available memory.
-   The newline character at the end of line is retained.  The line is
-   terminated with a zero character.
-
-   After end-of-file is encountered without anything being read, NULL
-   is returned.  NULL is also returned on error.  To distinguish
-   between these two cases, use the stdio function ferror().  */
-
-char *
-read_whole_line (FILE *fp)
-{
-  int length = 0;
-  int bufsize = 82;
-  char *line = xmalloc (bufsize);
-
-  while (fgets (line + length, bufsize - length, fp))
-    {
-      length += strlen (line + length);
-      if (length == 0)
-        /* Possible for example when reading from a binary file where
-           a line begins with \0.  */
-        continue;
-
-      if (line[length - 1] == '\n')
-        break;
-
-      /* fgets() guarantees to read the whole line, or to use up the
-         space we've given it.  We can double the buffer
-         unconditionally.  */
-      bufsize <<= 1;
-      line = xrealloc (line, bufsize);
-    }
-  if (length == 0 || ferror (fp))
-    {
-      xfree (line);
-      return NULL;
-    }
-  if (length + 1 < bufsize)
-    /* Relieve the memory from our exponential greediness.  We say
-       `length + 1' because the terminating \0 is not included in
-       LENGTH.  We don't need to zero-terminate the string ourselves,
-       though, because fgets() does that.  */
-    line = xrealloc (line, length + 1);
-  return line;
-}
-
 /* Read FILE into memory.  A pointer to `struct file_memory' are
    returned; use struct element `content' to access file contents, and
    the element `length' to know the file length.  `content' is *not*
@@ -2494,21 +2424,75 @@ print_decimal (double number)
   return buf;
 }
 
+/* Get the maximum name length for the given path. */
+/* Return 0 if length is unknown. */
+size_t
+get_max_length (const char *path, int length, int name)
+{
+  long ret;
+  char *p, *d;
+
+  /* Make a copy of the path that we can modify. */
+  p = path ? strdupdelim (path, path + length) : strdup ("");
+
+  for (;;)
+    {
+      errno = 0;
+      /* For an empty path query the current directory. */
+#if HAVE_PATHCONF
+      ret = pathconf (*p ? p : ".", name);
+      if (!(ret < 0 && errno == ENOENT))
+        break;
+#else
+      ret = PATH_MAX;
+#endif
+
+      /* The path does not exist yet, but may be created. */
+      /* Already at current or root directory, give up. */
+      if (!*p || strcmp (p, "/") == 0)
+        break;
+
+      /* Remove one directory level and try again. */
+      d = strrchr (p, '/');
+      if (d == p)
+        p[1] = '\0';  /* check root directory */
+      else if (d)
+        *d = '\0';  /* remove last directory part */
+      else
+        *p = '\0';  /* check current directory */
+    }
+
+  xfree (p);
+
+  if (ret < 0)
+    {
+      /* pathconf() has a message for us. */
+      if (errno != 0)
+          perror ("pathconf");
+
+      /* If (errno == 0) then there is no max length.
+         Even on error return 0 so the caller can continue. */
+      return 0;
+    }
+
+  return ret;
+}
+
 #ifdef TESTING
 
 const char *
 test_subdir_p()
 {
-  int i;
-  struct {
-    char *d1;
-    char *d2;
+  static struct {
+    const char *d1;
+    const char *d2;
     bool result;
   } test_array[] = {
     { "/somedir", "/somedir", true },
     { "/somedir", "/somedir/d2", true },
     { "/somedir/d1", "/somedir", false },
   };
+  unsigned i;
 
   for (i = 0; i < countof(test_array); ++i)
     {
@@ -2524,10 +2508,9 @@ test_subdir_p()
 const char *
 test_dir_matches_p()
 {
-  int i;
-  struct {
-    char *dirlist[3];
-    char *dir;
+  static struct {
+    const char *dirlist[3];
+    const char *dir;
     bool result;
   } test_array[] = {
     { { "/somedir", "/someotherdir", NULL }, "somedir", true },
@@ -2546,6 +2529,7 @@ test_dir_matches_p()
     { { "/Tmp/has", NULL, NULL }, "/Tmp/has space", false },
     { { "/Tmp/has", NULL, NULL }, "/Tmp/has,comma", false },
   };
+  unsigned i;
 
   for (i = 0; i < countof(test_array); ++i)
     {

src/utils.h

@@ -98,7 +98,6 @@ bool has_wildcards_p (const char *);
 
 bool has_html_suffix_p (const char *);
 
-char *read_whole_line (FILE *);
 struct file_memory *wget_read_file (const char *);
 void wget_read_file_free (struct file_memory *);
 
@@ -155,6 +154,8 @@ void stable_sort (void *, size_t, size_t, int (*) (const void *, const void *));
 
 const char *print_decimal (double);
 
+size_t get_max_length (const char *path, int length, int name);
+
 extern unsigned char char_prop[];
 
 #endif /* UTILS_H */

src/warc.c

@@ -51,10 +51,16 @@ as that of the covered work.  */
 
 #ifndef WINDOWS
 #include <libgen.h>
+#else
+#include <fcntl.h>
 #endif
 
 #include "warc.h"
 
+#ifndef O_TEMPORARY
+#define O_TEMPORARY 0
+#endif
+
 extern char *version_string;
 
 /* Set by main in main.c */
@@ -165,7 +171,7 @@ warc_write_string (const char *str)
 }
 
 
-#define EXTRA_GZIP_HEADER_SIZE 12
+#define EXTRA_GZIP_HEADER_SIZE 14
 #define GZIP_STATIC_HEADER_SIZE  10
 #define FLG_FEXTRA          0x04
 #define OFF_FLG             3
@@ -200,7 +206,7 @@ warc_write_start_record (void)
          In warc_write_end_record we will fill this space
          with information about the uncompressed and
          compressed size of the record. */
-      fprintf (warc_current_file, "XXXXXXXXXXXX");
+      fseek (warc_current_file, EXTRA_GZIP_HEADER_SIZE, SEEK_CUR);
       fflush (warc_current_file);
 
       /* Start a new GZIP stream. */
@@ -245,15 +251,10 @@ static bool
 warc_write_block_from_file (FILE *data_in)
 {
   /* Add the Content-Length header. */
-  char *content_length;
+  char content_length[MAX_INT_TO_STRING_LEN(off_t)];
   fseeko (data_in, 0L, SEEK_END);
-  if (! asprintf (&content_length, "%ld", ftello (data_in)))
-    {
-      warc_write_ok = false;
-      return false;
-    }
+  number_to_string (content_length, ftello (data_in));
   warc_write_header ("Content-Length", content_length);
-  free (content_length);
 
   /* End of the WARC header section. */
   warc_write_string ("\r\n");
@@ -347,16 +348,19 @@ warc_write_end_record (void)
       /* The extra header field identifier for the WARC skip length. */
       extra_header[2]  = 's';
       extra_header[3]  = 'l';
+      /* The size of the field value (8 bytes).  */
+      extra_header[4]  = (8 & 255);
+      extra_header[5]  = ((8 >> 8) & 255);
       /* The size of the uncompressed record.  */
-      extra_header[4]  = (uncompressed_size & 255);
-      extra_header[5]  = (uncompressed_size >> 8) & 255;
-      extra_header[6]  = (uncompressed_size >> 16) & 255;
-      extra_header[7]  = (uncompressed_size >> 24) & 255;
+      extra_header[6]  = (uncompressed_size & 255);
+      extra_header[7]  = (uncompressed_size >> 8) & 255;
+      extra_header[8]  = (uncompressed_size >> 16) & 255;
+      extra_header[9]  = (uncompressed_size >> 24) & 255;
       /* The size of the compressed record.  */
-      extra_header[8]  = (compressed_size & 255);
-      extra_header[9]  = (compressed_size >> 8) & 255;
-      extra_header[10] = (compressed_size >> 16) & 255;
-      extra_header[11] = (compressed_size >> 24) & 255;
+      extra_header[10] = (compressed_size & 255);
+      extra_header[11] = (compressed_size >> 8) & 255;
+      extra_header[12] = (compressed_size >> 16) & 255;
+      extra_header[13] = (compressed_size >> 24) & 255;
 
       /* Write the extra header after the static header. */
       fseeko (warc_current_file, warc_current_gzfile_offset
@@ -532,7 +536,7 @@ warc_sha1_stream_with_payload (FILE *stream, void *res_block, void *res_payload,
 static char *
 warc_base32_sha1_digest (char *sha1_digest)
 {
-  // length: "sha1:" + digest + "\0"
+  /* length: "sha1:" + digest + "\0" */
   char *sha1_base32 = malloc (BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1 + 5 );
   base32_encode (sha1_digest, SHA1_DIGEST_SIZE, sha1_base32 + 5,
                  BASE32_LENGTH(SHA1_DIGEST_SIZE) + 1);
@@ -722,10 +726,9 @@ warc_start_new_file (bool meta)
 
   if (warc_current_file != NULL)
     fclose (warc_current_file);
-  if (warc_current_warcinfo_uuid_str)
-    free (warc_current_warcinfo_uuid_str);
-  if (warc_current_filename)
-    free (warc_current_filename);
+  
+  free (warc_current_warcinfo_uuid_str);
+  free (warc_current_filename);
 
   warc_current_file_number++;
 
@@ -734,8 +737,14 @@ warc_start_new_file (bool meta)
   char *new_filename = malloc (base_filename_length + 1 + 5 + 8 + 1);
   warc_current_filename = new_filename;
 
+#ifdef __VMS
+# define WARC_GZ "warc-gz"
+#else /* def __VMS */
+# define WARC_GZ "warc.gz"
+#endif /* def __VMS [else] */
+
 #ifdef HAVE_LIBZ
-  const char *extension = (opt.warc_compression_enabled ? "warc.gz" : "warc");
+  const char *extension = (opt.warc_compression_enabled ? WARC_GZ : "warc");
 #else
   const char *extension = "warc";
 #endif
@@ -908,8 +917,7 @@ warc_process_cdx_line (char *lineptr, int field_num_original_url,
       else
         {
           free (original_url);
-          if (checksum_v != NULL)
-            free (checksum_v);
+          free (checksum_v);
           free (record_id);
         }
     }
@@ -1005,12 +1013,10 @@ warc_find_duplicate_cdx_record (char *url, char *sha1_digest_payload)
   if (warc_cdx_dedup_table == NULL)
     return NULL;
 
-  char *key;
-  struct warc_cdx_record *rec_existing;
-  int found = hash_table_get_pair (warc_cdx_dedup_table, sha1_digest_payload,
-                                   &key, &rec_existing);
+  struct warc_cdx_record *rec_existing
+    = hash_table_get (warc_cdx_dedup_table, sha1_digest_payload);
 
-  if (found && strcmp (rec_existing->url, url) == 0)
+  if (rec_existing && strcmp (rec_existing->url, url) == 0)
     return rec_existing;
   else
     return NULL;
@@ -1087,7 +1093,7 @@ warc_write_metadata (void)
   warc_uuid_str (manifest_uuid);
 
   fflush (warc_manifest_fp);
-  warc_write_resource_record (manifest_uuid,
+  warc_write_metadata_record (manifest_uuid,
                               "metadata://gnu.org/software/wget/warc/MANIFEST.txt",
                               NULL, NULL, NULL, "text/plain",
                               warc_manifest_fp, -1);
@@ -1102,9 +1108,9 @@ warc_write_metadata (void)
   fflush (warc_tmp_fp);
   fprintf (warc_tmp_fp, "%s\n", program_argstring);
 
-  warc_write_resource_record (manifest_uuid,
+  warc_write_resource_record (NULL,
                    "metadata://gnu.org/software/wget/warc/wget_arguments.txt",
-                              NULL, NULL, NULL, "text/plain",
+                              NULL, manifest_uuid, NULL, "text/plain",
                               warc_tmp_fp, -1);
   /* warc_write_resource_record has closed warc_tmp_fp. */
 
@@ -1151,14 +1157,32 @@ warc_tempfile (void)
   if (path_search (filename, 100, opt.warc_tempdir, "wget", true) == -1)
     return NULL;
 
-  int fd = mkstemp (filename);
+#ifdef __VMS
+  /* 2013-07-12 SMS.
+   * mkostemp()+unlink()+fdopen() scheme causes trouble on VMS, so use
+   * mktemp() to uniquify the (VMS-style) name, and then use a normal
+   * fopen() with a "create temp file marked for delete" option.
+   */
+  {
+    char *tfn;
+
+    tfn = mktemp (filename);            /* Get unique name from template. */
+    if (tfn == NULL)
+      return NULL;
+    return fopen (tfn, "w+", "fop=tmd");    /* Create auto-delete temp file. */
+  }
+#else /* def __VMS */
+  int fd = mkostemp (filename, O_TEMPORARY);
   if (fd < 0)
     return NULL;
 
+#if !O_TEMPORARY
   if (unlink (filename) < 0)
     return NULL;
+#endif
 
   return fdopen (fd, "wb+");
+#endif /* def __VMS [else] */
 }
 
 
@@ -1232,10 +1256,14 @@ warc_write_cdx_record (const char *url, const char *timestamp_str,
   if (redirect_location == NULL || strlen(redirect_location) == 0)
     redirect_location = "-";
 
+  char offset_string[MAX_INT_TO_STRING_LEN(off_t)];
+  number_to_string (offset_string, offset);
+
   /* Print the CDX line. */
-  fprintf (warc_current_cdx_file, "%s %s %s %s %d %s %s - %ld %s %s\n", url,
+  fprintf (warc_current_cdx_file, "%s %s %s %s %d %s %s - %s %s %s\n", url,
            timestamp_str_cdx, url, mime_type, response_code, checksum,
-           redirect_location, offset, warc_current_filename, response_uuid);
+           redirect_location, offset_string, warc_current_filename,
+           response_uuid);
   fflush (warc_current_cdx_file);
 
   return true;
@@ -1387,28 +1415,28 @@ warc_write_response_record (char *url, char *timestamp_str,
       response_uuid);
     }
 
-  if (block_digest)
-    free (block_digest);
-  if (payload_digest)
-    free (payload_digest);
+  free (block_digest);
+  free (payload_digest);
 
   return warc_write_ok;
 }
 
-/* Writes a resource record to the WARC file.
+/* Writes a resource or metadata record to the WARC file.
+   warc_type  is either "resource" or "metadata",
    resource_uuid  is the uuid of the resource (or NULL),
    url  is the target uri of the resource,
    timestamp_str  is the timestamp (generated with warc_timestamp),
-   concurrent_to_uuid  is the uuid of the request for that generated this
+   concurrent_to_uuid  is the uuid of the record that generated this,
    resource (generated with warc_uuid_str) or NULL,
    ip  is the ip address of the server (or NULL),
    content_type  is the mime type of the body (or NULL),
    body  is a pointer to a file containing the resource data.
    Calling this function will close body.
    Returns true on success, false on error. */
-bool
-warc_write_resource_record (char *resource_uuid, const char *url,
-                 const char *timestamp_str, const char *concurrent_to_uuid,
+static bool
+warc_write_record (const char *record_type, char *resource_uuid,
+                 const char *url, const char *timestamp_str,
+                 const char *concurrent_to_uuid,
                  ip_address *ip, const char *content_type, FILE *body,
                  off_t payload_offset)
 {
@@ -1422,7 +1450,7 @@ warc_write_resource_record (char *resource_uuid, const char *url,
     content_type = "application/octet-stream";
 
   warc_write_start_record ();
-  warc_write_header ("WARC-Type", "resource");
+  warc_write_header ("WARC-Type", record_type);
   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);
@@ -1438,3 +1466,47 @@ warc_write_resource_record (char *resource_uuid, const char *url,
 
   return warc_write_ok;
 }
+
+/* Writes a resource record to the WARC file.
+   resource_uuid  is the uuid of the resource (or NULL),
+   url  is the target uri of the resource,
+   timestamp_str  is the timestamp (generated with warc_timestamp),
+   concurrent_to_uuid  is the uuid of the record that generated this,
+   resource (generated with warc_uuid_str) or NULL,
+   ip  is the ip address of the server (or NULL),
+   content_type  is the mime type of the body (or NULL),
+   body  is a pointer to a file containing the resource data.
+   Calling this function will close body.
+   Returns true on success, false on error. */
+bool
+warc_write_resource_record (char *resource_uuid, const char *url,
+                 const char *timestamp_str, const char *concurrent_to_uuid,
+                 ip_address *ip, const char *content_type, FILE *body,
+                 off_t payload_offset)
+{
+  return warc_write_record ("resource",
+      resource_uuid, url, timestamp_str, concurrent_to_uuid,
+      ip, content_type, body, payload_offset);
+}
+
+/* Writes a metadata record to the WARC file.
+   record_uuid  is the uuid of the record (or NULL),
+   url  is the target uri of the record,
+   timestamp_str  is the timestamp (generated with warc_timestamp),
+   concurrent_to_uuid  is the uuid of the record that generated this,
+   record (generated with warc_uuid_str) or NULL,
+   ip  is the ip address of the server (or NULL),
+   content_type  is the mime type of the body (or NULL),
+   body  is a pointer to a file containing the record data.
+   Calling this function will close body.
+   Returns true on success, false on error. */
+bool
+warc_write_metadata_record (char *record_uuid, const char *url,
+                 const char *timestamp_str, const char *concurrent_to_uuid,
+                 ip_address *ip, const char *content_type, FILE *body,
+                 off_t payload_offset)
+{
+  return warc_write_record ("metadata",
+      record_uuid, url, timestamp_str, concurrent_to_uuid,
+      ip, content_type, body, payload_offset);
+}

src/warc.h

@@ -19,5 +19,8 @@ bool warc_write_response_record (char *url, char *timestamp_str,
 bool warc_write_resource_record (char *resource_uuid, const char *url,
   const char *timestamp_str, const char *concurrent_to_uuid, ip_address *ip,
   const char *content_type, FILE *body, off_t payload_offset);
+bool warc_write_metadata_record (char *record_uuid, const char *url,
+  const char *timestamp_str, const char *concurrent_to_uuid, ip_address *ip,
+  const char *content_type, FILE *body, off_t payload_offset);
 
 #endif /* WARC_H */

src/wget.h

@@ -314,6 +314,10 @@ typedef double SUM_SIZE_INT;
    0-pad the address.)  */
 #define PTR_FORMAT(p) (int) (2 * sizeof (void *)), (unsigned long) (p)
 
+/* Find the maximum buffer length needed to print an integer of type `x'
+   in base 10. 24082 / 10000 = 8*log_{10}(2).  */
+#define MAX_INT_TO_STRING_LEN(x) ((sizeof(x) * 24082 / 10000) + 2)
+
 extern const char *exec_name;
 
 /* Document type ("dt") flags */
@@ -353,7 +357,7 @@ typedef enum
   PROXERR,
   /* 50  */
   AUTHFAILED, QUOTEXC, WRITEFAILED, SSLINITFAILED, VERIFCERTERR,
-  UNLINKERR, NEWLOCATION_KEEP_POST, CLOSEFAILED,
+  UNLINKERR, NEWLOCATION_KEEP_POST, CLOSEFAILED, ATTRMISSING, UNKNOWNATTR,
 
   WARC_ERR, WARC_TMP_FOPENERR, WARC_TMP_FWRITEERR
 } uerr_t;

tests/ChangeLog

@@ -1,3 +1,65 @@
+2013-11-04  Darshit Shah  <darnir@gmail.com>
+
+	* Makefile.am: Add new tests introduced in last commit to
+          EXTRA_DIST.
+        Reported by: Andrea Urbani  <matfanjol@mail.com>
+
+2013-10-17  Andrea Urbani  <matfanjol@mail.com>
+
+	* FTPServer.pm (GetBehavior): new routine.
+	* FTPServer.pm (get_list): new parameter to skip hidden files
+	* Test-ftp-list-Multinet.px: Test LIST on a "UNIX MultiNet
+	  Unix Emulation" system that returns an empty content when
+	  "LIST -a" is requested (probably because no "-a" files
+	  exist)
+	* Test-ftp-list-Unknown.px: Test LIST on a "Unknown ftp
+	  service" system that returns an empty content when
+	  "LIST -a" is requested (probably because no "-a" files
+	  exist)
+	* Test-ftp-list-Unknown-a.px: Test LIST on a "Unknown ftp
+	  service" system that recognises "LIST -a" as "give me the
+	  -a file" and there is a "-a" file + other two files.
+	  "LIST -a" will return only "-a", "LIST" all the three files.
+	* Test-ftp-list-Unknown-hidden.px: Test LIST on a "Unknown ftp
+	  service" system that recognises "LIST -a" as an "UNIX Type:
+	  L8" system (show me also the hidden files) and there is an
+	  hidden file.
+	* Test-ftp-list-Unknown-list-a-fails.px: Test LIST on a
+	  "Unknown ftp service" system that raises an error on
+	  "LIST -a" command.
+	* Test-ftp-list-UNIX-hidden.px: Test LIST on a "UNIX Type:
+	  L8" system that recognises "LIST -a" as "show me also the
+	  hidden files" and there is an hidden file.
+
+2013-10-10  Giuseppe Scrivano  <gscrivan@redhat.com>
+
+	* Test-idn-robots-utf8.px: Remove -H.
+	* Test-idn-cmd.px: Likewise.
+	* Test-idn-cmd-utf8.px: Likewise.
+	Suggested by: Tim Ruehsen <tim.ruehsen@gmx.de>
+
+2013-10-07  Tim Ruehsen <tim.ruehsen@gmx.de>
+
+	* Test-idn-robots.px: added punycoded and escaped URLs to follow
+	  removed -H
+
+2013-08-22  Tim Ruehsen <tim.ruehsen@gmx.de>
+
+	* Makefile.am (EXTRA_DIST): Add Test--httpsonly-r.px.
+	* run-px (tests): Likewise.
+	* Test--httpsonly-r.px: New file.
+
+2013-03-12  Darshit Shah <darnir@gmail.com>
+
+	* Makefile.am (EXTRA_DIST): Add Test--post-file.px.
+	* run-px (tests): Likewise.
+	* Test--post-file.px: New file.
+
+2012-11-09  Tim Ruehsen  <tim.ruehsen@gmx.de>
+
+	* HTTPServer.pm: added check for must-not-match request-header
+	* Test-cookies.px: check cookie deletion and cookie domain matching
+
 2012-06-16  Giuseppe Scrivano  <gscrivano@gnu.org>
 
 	* Makefile.am (EXTRA_DIST): Add Test-stdouterr.px.

tests/FTPServer.pm

@@ -81,10 +81,25 @@ sub _LIST_command
     my ($conn, $cmd, $path) = @_;
     my $paths = $conn->{'paths'};
 
-    # This is something of a hack. Some clients expect a Unix server
-    # to respond to flags on the 'ls command line'. Remove these flags
-    # and ignore them. This is particularly an issue with ncftp 2.4.3.
-    $path =~ s/^-[a-zA-Z0-9]+\s?//;
+    my $ReturnEmptyList = ( $paths->GetBehavior('list_empty_if_list_a') &&
+                            $path eq '-a');
+    my $SkipHiddenFiles = ( $paths->GetBehavior('list_no_hidden_if_list') &&
+                            ( ! $path ) );
+
+    if ($paths->GetBehavior('list_fails_if_list_a') && $path eq '-a')
+      {
+            print {$conn->{socket}} "500 Unknown command\r\n";
+            return;
+      }
+
+
+    if (!$paths->GetBehavior('list_dont_clean_path'))
+      {
+        # This is something of a hack. Some clients expect a Unix server
+        # to respond to flags on the 'ls command line'. Remove these flags
+        # and ignore them. This is particularly an issue with ncftp 2.4.3.
+        $path =~ s/^-[a-zA-Z0-9]+\s?//;
+      }
 
     my $dir = $conn->{'dir'};
 
@@ -94,12 +109,16 @@ sub _LIST_command
     # working directory.
     local $_;
 
-    $dir = FTPPaths::path_merge($dir, $path);
-    my $listing = $paths->get_list($dir);
-    unless ($listing) {
-        print {$conn->{socket}} "550 File or directory not found.\r\n";
-        return;
-    }
+    my $listing;
+    if (!$ReturnEmptyList)
+      {
+        $dir = FTPPaths::path_merge($dir, $path);
+        $listing = $paths->get_list($dir,$SkipHiddenFiles);
+        unless ($listing) {
+            print {$conn->{socket}} "550 File or directory not found.\r\n";
+            return;
+        }
+      }
 
     print STDERR "_LIST_command - dir is: $dir\n" if $log;
 
@@ -112,9 +131,12 @@ sub _LIST_command
         return;
     }
 
-    for my $item (@$listing) {
-        print $sock "$item\r\n";
-    }
+    if (!$ReturnEmptyList)
+      {
+        for my $item (@$listing) {
+            print $sock "$item\r\n";
+        }
+      }
 
     unless ($sock->close) {
         print {$conn->{socket}} "550 Error closing data connection: $!\r\n";
@@ -372,7 +394,14 @@ sub _SYST_command
 {
     my ($conn, $cmd, $dummy) = @_;
 
-    print {$conn->{socket}} "215 UNIX Type: L8\r\n";
+    if ($conn->{'paths'}->GetBehavior('syst_response'))
+      {
+        print {$conn->{socket}} $conn->{'paths'}->GetBehavior('syst_response') . "\r\n";
+      }
+    else
+      {
+        print {$conn->{socket}} "215 UNIX Type: L8\r\n";
+      }
 }
 
 sub _TYPE_command
@@ -780,7 +809,7 @@ sub _format_for_list {
 }
 
 sub get_list {
-    my ($self, $path) = @_;
+    my ($self, $path, $no_hidden) = @_;
     my $info = $self->get_info($path);
     return undef unless defined $info;
     my $list = [];
@@ -788,7 +817,19 @@ sub get_list {
     if ($info->{'_type'} eq 'd') {
         for my $item (keys %$info) {
             next if $item =~ /^_/;
-            push @$list, $self->_format_for_list($item, $info->{$item});
+            # 2013-10-17 Andrea Urbani (matfanjol)
+            #            I skip the hidden files if requested
+            if (($no_hidden) &&
+                (defined($info->{$item}->{'attr'})) &&
+                (index($info->{$item}->{'attr'}, "H")>=0))
+              {
+                # This is an hidden file and I don't want to see it!
+                print STDERR "get_list: Skipped hidden file [$item]\n";
+              }
+            else
+              {
+                push @$list, $self->_format_for_list($item, $info->{$item});
+              }
         }
     } else {
         push @$list, $self->_format_for_list(final_component($path), $info);
@@ -797,6 +838,29 @@ sub get_list {
     return $list;
 }
 
+# 2013-10-17 Andrea Urbani (matfanjol)
+# It returns the behavior of the given name.
+# In this file I handle also the following behaviors:
+#  list_dont_clean_path  : if defined, the command
+#                           $path =~ s/^-[a-zA-Z0-9]+\s?//;
+#                          is not runt and the given path
+#                          remains the original one
+#  list_empty_if_list_a  : if defined, "LIST -a" returns an
+#                          empty content
+#  list_fails_if_list_a  : if defined, "LIST -a" returns an
+#                          error
+#  list_no_hidden_if_list: if defined, "LIST" doesn't return
+#                          hidden files.
+#                          To define an hidden file add
+#                            attr => "H"
+#                          to the url files
+#  syst_response         : if defined, its content is printed
+#                          out as SYST response
+sub GetBehavior {
+  my ($self, $name) = @_;
+  return $self->{'_behavior'}{$name};
+}
+
 1;
 
 # vim: et ts=4 sw=4

tests/HTTPServer.pm

@@ -218,12 +218,24 @@ sub verify_request_headers {
 
     return 1 unless exists $url_rec->{'request_headers'};
     for my $hdrname (keys %{$url_rec->{'request_headers'}}) {
-        my $rhdr = $req->header ($hdrname);
+        my $must_not_match;
         my $ehdr = $url_rec->{'request_headers'}{$hdrname};
-        unless (defined $rhdr && $rhdr =~ $ehdr) {
-            $rhdr = '' unless defined $rhdr;
-            print STDERR "\n*** Mismatch on $hdrname: $rhdr =~ $ehdr\n";
-            return undef;
+        if ($must_not_match = ($hdrname =~ /^!(\w+)/)) {
+            $hdrname = $1;
+        }
+        my $rhdr = $req->header ($hdrname);
+        if ($must_not_match) {
+            if (defined $rhdr && $rhdr =~ $ehdr) {
+                $rhdr = '' unless defined $rhdr;
+                print STDERR "\n*** Match forbidden $hdrname: $rhdr =~ $ehdr\n";
+                return undef;
+            }
+        } else {
+            unless (defined $rhdr && $rhdr =~ $ehdr) {
+                $rhdr = '' unless defined $rhdr;
+                print STDERR "\n*** Mismatch on $hdrname: $rhdr =~ $ehdr\n";
+                return undef;
+            }
         }
     }
 

tests/Makefile.am

@@ -82,6 +82,12 @@ EXTRA_DIST = FTPServer.pm FTPTest.pm HTTPServer.pm HTTPTest.pm \
              Test-ftp-iri-fallback.px \
              Test-ftp-iri-recursive.px \
              Test-ftp-iri-disabled.px \
+             Test-ftp-list-Multinet.px \
+             Test-ftp-list-Unknown.px \
+             Test-ftp-list-Unknown-a.px \
+             Test-ftp-list-Unknown-hidden.px \
+             Test-ftp-list-Unknown-list-a-fails.px \
+             Test-ftp-list-UNIX-hidden.px \
              Test-HTTP-Content-Disposition-1.px \
              Test-HTTP-Content-Disposition-2.px \
              Test-HTTP-Content-Disposition.px \
@@ -119,6 +125,7 @@ EXTRA_DIST = FTPServer.pm FTPTest.pm HTTPServer.pm HTTPTest.pm \
              Test-O--no-content-disposition-trivial.px \
              Test-O-nonexisting.px \
              Test-O.px \
+             Test--post-file.px \
              Test-proxied-https-auth.px \
              Test-proxy-auth-basic.px \
              Test-restrict-ascii.px \
@@ -131,6 +138,7 @@ EXTRA_DIST = FTPServer.pm FTPTest.pm HTTPServer.pm HTTPTest.pm \
              Test--spider-r--no-content-disposition.px \
              Test--spider-r--no-content-disposition-trivial.px \
              Test--spider-r.px \
+             Test--httpsonly-r.px \
              run-px certs
 
 check_PROGRAMS = unit-tests

tests/Test--httpsonly-r.px

@@ -0,0 +1,79 @@
+#!/usr/bin/env perl
+
+use strict;
+use warnings;
+
+use HTTPTest;
+
+
+###############################################################################
+
+my $mainpage = <<EOF;
+<html>
+<head>
+  <title>Main Page</title>
+</head>
+<body>
+  <p>
+    Some text and a link to a <a href="http://localhost:{{port}}/secondpage.html">second page</a>.
+  </p>
+</body>
+</html>
+EOF
+
+my $secondpage = <<EOF;
+<html>
+<head>
+  <title>Second Page</title>
+</head>
+<body>
+  <p>
+    Anything.
+  </p>
+</body>
+</html>
+EOF
+
+# code, msg, headers, content
+my %urls = (
+    '/index.html' => {
+        code => "200",
+        msg => "Dontcare",
+        headers => {
+            "Content-type" => "text/html",
+        },
+        content => $mainpage,
+    },
+    '/secondpage.html' => {
+        code => "200",
+        msg => "Dontcare",
+        headers => {
+            "Content-type" => "text/html",
+        },
+        content => $secondpage,
+    }
+);
+
+my $cmdline = $WgetTest::WGETPATH . " --https-only -r -nH http://localhost:{{port}}/";
+
+my $expected_error_code = 0;
+
+my %expected_downloaded_files = (
+    'index.html' => {
+        content => $mainpage,
+    },
+);
+
+###############################################################################
+
+my $the_test = HTTPTest->new (name => "Test--httpsonly-r",
+                              input => \%urls,
+                              cmdline => $cmdline,
+                              errcode => $expected_error_code,
+                              output => \%expected_downloaded_files);
+print $expected_error_code."\n";
+
+exit $the_test->run();
+
+# vim: et ts=4 sw=4
+

tests/Test--post-file.px

@@ -0,0 +1,23 @@
+#!/usr/bin/env perl
+
+use strict;
+use warnings;
+
+use HTTPTest;
+
+
+###############################################################################
+
+my $cmdline = $WgetTest::WGETPATH . " -d --post-file=nofile http://localhost:{{port}}/";
+
+my $expected_error_code = 3;
+
+
+###############################################################################
+
+my $the_test = HTTPTest->new (name => "Test-missing-file",
+                              cmdline => $cmdline,
+                              errcode => $expected_error_code);
+exit $the_test->run();
+
+# vim: et ts=4 sw=4

tests/Test-cookies.px

@@ -10,6 +10,10 @@ use HTTPTest;
 
 my $page1 = "Hello, world!\n";
 my $page2 = "Goodbye, Sam.\n";
+my $page3 = "Page three.\n";
+my $page4 = "Page four.\n";
+my $page5 = "Page five.\n";
+my $page6 = "Page six.\n";
 
 # code, msg, headers, content
 my %urls = (
@@ -30,10 +34,49 @@ my %urls = (
             "Cookie" => qr|foo=bar|,
         },
     },
+# remove the cookie 'foo'
+    '/three.txt' => {
+        code => "200",
+        msg => "Ok",
+        headers => {
+            "Content-type" => "text/plain",
+            "Set-Cookie" => "foo=; Expires=Sun, 06 Nov 1994 08:49:37 GMT",
+        },
+        content => $page3,
+    },
+    '/four.txt' => {
+        code => "200",
+        msg => "Ok",
+        content => $page4,
+        request_headers => {
+            "!Cookie" => qr|foo=|,
+        },
+    },
+# try to set a cookie 'foo' with mismatching domain
+# see RFC 6265 5.3.6: ignore the cookie if it doesn't domain-match
+    '/five.txt' => {
+        code => "200",
+        msg => "Ok",
+        headers => {
+            "Content-type" => "text/plain",
+            "Set-Cookie" => "foo=bar; domain=.example.com",
+        },
+        content => $page5,
+    },
+    '/six.txt' => {
+        code => "200",
+        msg => "Ok",
+        content => $page6,
+        request_headers => {
+            "!Cookie" => qr|foo=bar|,
+        },
+    },
 );
 
 my $cmdline = $WgetTest::WGETPATH . " http://localhost:{{port}}/one.txt"
-    . " http://localhost:{{port}}/two.txt";
+    . " http://localhost:{{port}}/two.txt" . " http://localhost:{{port}}/three.txt"
+    . " http://localhost:{{port}}/four.txt" . " http://localhost:{{port}}/five.txt"
+	 . " http://localhost:{{port}}/six.txt";
 
 my $expected_error_code = 0;
 
@@ -44,6 +87,18 @@ my %expected_downloaded_files = (
     'two.txt' => {
         content => $page2,
     },
+    'three.txt' => {
+        content => $page3,
+    },
+    'four.txt' => {
+        content => $page4,
+    },
+    'five.txt' => {
+        content => $page5,
+    },
+    'six.txt' => {
+        content => $page6,
+    },
 );
 
 ###############################################################################

tests/Test-ftp-list-Multinet.px

@@ -0,0 +1,67 @@
+#!/usr/bin/env perl
+
+
+# 2013-10-17 Andrea Urbani (matfanjol)
+# In this ftp test:
+# - the response of SYST command is
+#   215 UNIX MultiNet Unix Emulation V5.3(93)
+# - the response of "LIST -a" command is an empty
+#   directory.
+# wget should use directly the "LIST" command to get
+# the right content, but it will be ok also "LIST -a"
+# if followed by "LIST" (in the case of future changes).
+
+
+use strict;
+use warnings;
+
+use FTPTest;
+
+
+###############################################################################
+
+my $afile = <<EOF;
+Some text.
+EOF
+
+my $bfile = <<EOF;
+Some more text.
+EOF
+
+$afile =~ s/\n/\r\n/g;
+$bfile =~ s/\n/\r\n/g;
+
+# code, msg, headers, content
+my %urls = (
+    '/afile.txt' => {
+        content => $afile,
+    },
+    '/bfile.txt' => {
+        content => $bfile,
+    },
+);
+
+my $cmdline = $WgetTest::WGETPATH . " --no-directories --recursive --level=1 --accept \"?file.txt\" ftp://localhost:{{port}}/";
+
+my $expected_error_code = 0;
+
+my %expected_downloaded_files = (
+    'afile.txt' => {
+        content => $afile,
+    },
+    'bfile.txt' => {
+        content => $bfile,
+    },
+);
+
+###############################################################################
+
+my $the_test = FTPTest->new (name => "Test-ftp-list-Multinet",
+                             input => \%urls,
+                             cmdline => $cmdline,
+                             errcode => $expected_error_code,
+                             output => \%expected_downloaded_files,
+                             server_behavior => {list_empty_if_list_a => 1,
+                                                 syst_response => "215 UNIX MultiNet Unix Emulation V5.3(93)"});
+exit $the_test->run();
+

tests/Test-ftp-list-UNIX-hidden.px

@@ -0,0 +1,65 @@
+#!/usr/bin/env perl
+
+# 2013-10-17 Andrea Urbani (matfanjol)
+# In this ftp test:
+# - the response of "LIST -a" command contains
+#   all the files
+# - the response of "LIST" command contains
+#   the normal files (hidden files are not present)
+# wget should use only "LIST -a" because it recognise
+# the system as "UNIX Type: L8" and so it should see
+# and download the hidden file too.
+
+use strict;
+use warnings;
+
+use FTPTest;
+
+
+###############################################################################
+
+my $normalfile = <<EOF;
+I'm a normal file
+EOF
+
+my $hiddenfile = <<EOF;
+I'm an hidden file
+EOF
+
+$normalfile =~ s/\n/\r\n/g;
+$hiddenfile =~ s/\n/\r\n/g;
+
+# code, msg, headers, content
+my %urls = (
+    '/normalfile.txt' => {
+        content => $normalfile,
+    },
+    '/hiddenfile.txt' => {
+        content => $hiddenfile,
+        attr => "H",
+    },
+);
+
+my $cmdline = $WgetTest::WGETPATH . " --no-directories --recursive --level=1 ftp://localhost:{{port}}/";
+
+my $expected_error_code = 0;
+
+my %expected_downloaded_files = (
+    'normalfile.txt' => {
+        content => $normalfile,
+    },
+    'hiddenfile.txt' => {
+        content => $hiddenfile,
+    },
+);
+
+###############################################################################
+
+my $the_test = FTPTest->new (name => "Test-ftp-list-UNIX-hidden",
+                             input => \%urls,
+                             cmdline => $cmdline,
+                             errcode => $expected_error_code,
+                             output => \%expected_downloaded_files,
+                             server_behavior => {list_no_hidden_if_list => 1});
+exit $the_test->run();
+

tests/Test-ftp-list-Unknown-a.px

@@ -0,0 +1,77 @@
+#!/usr/bin/env perl
+
+# 2013-10-17 Andrea Urbani (matfanjol)
+# In this ftp test:
+# - the response of SYST command is
+#   215 Unknown ftp service
+# - the response of "LIST -a" command is a file
+#   called "-a".
+# wget should use "LIST -a", but also "LIST".
+# After "LIST", wget will see more data is available.
+# (See also Test-ftp-list-Unknown-b.px)
+
+use strict;
+use warnings;
+
+use FTPTest;
+
+
+###############################################################################
+
+my $afile = <<EOF;
+Some text.
+EOF
+
+my $bfile = <<EOF;
+Some more text.
+EOF
+
+
+my $minusafile = <<EOF;
+The strange situation.
+EOF
+
+$afile =~ s/\n/\r\n/g;
+$bfile =~ s/\n/\r\n/g;
+$minusafile =~ s/\n/\r\n/g;
+
+# code, msg, headers, content
+my %urls = (
+    '/afile.txt' => {
+        content => $afile,
+    },
+    '/bfile.txt' => {
+        content => $bfile,
+    },
+    '/-a' => {
+        content => $minusafile,
+    },
+);
+
+my $cmdline = $WgetTest::WGETPATH . " --no-directories --recursive --level=1 ftp://localhost:{{port}}/";
+
+my $expected_error_code = 0;
+
+my %expected_downloaded_files = (
+    'afile.txt' => {
+        content => $afile,
+    },
+    'bfile.txt' => {
+        content => $bfile,
+    },
+    '-a' => {
+        content => $minusafile,
+    },
+);
+
+###############################################################################
+
+my $the_test = FTPTest->new (name => "Test-ftp-list-Unknown-a",
+                             input => \%urls,
+                             cmdline => $cmdline,
+                             errcode => $expected_error_code,
+                             output => \%expected_downloaded_files,
+                             server_behavior => {list_dont_clean_path => 1,
+                                                 syst_response => "215 Unknown ftp service"});
+exit $the_test->run();
+

tests/Test-ftp-list-Unknown-hidden.px

@@ -0,0 +1,69 @@
+#!/usr/bin/env perl
+
+# 2013-10-17 Andrea Urbani (matfanjol)
+# In this ftp test:
+# - the response of SYST command is
+#   215 Unknown ftp service
+# - the response of "LIST -a" command contains
+#   all the files
+# - the response of "LIST" command contains
+#   the normal files (hidden files are not present)
+# wget should use "LIST -a", but also "LIST".
+# After "LIST", wget will see more data is available
+# on "LIST -a", so it should go back to "LIST -a".
+# (See also Test-ftp-list-Unknown-a.px)
+
+use strict;
+use warnings;
+
+use FTPTest;
+
+
+###############################################################################
+
+my $normalfile = <<EOF;
+I'm a normal file
+EOF
+
+my $hiddenfile = <<EOF;
+I'm an hidden file
+EOF
+
+$normalfile =~ s/\n/\r\n/g;
+$hiddenfile =~ s/\n/\r\n/g;
+
+# code, msg, headers, content
+my %urls = (
+    '/normalfile.txt' => {
+        content => $normalfile,
+    },
+    '/hiddenfile.txt' => {
+        content => $hiddenfile,
+        attr => "H",
+    },
+);
+
+my $cmdline = $WgetTest::WGETPATH . " --no-directories --recursive --level=1 ftp://localhost:{{port}}/";
+
+my $expected_error_code = 0;
+
+my %expected_downloaded_files = (
+    'normalfile.txt' => {
+        content => $normalfile,
+    },
+    'hiddenfile.txt' => {
+        content => $hiddenfile,
+    },
+);
+
+###############################################################################
+
+my $the_test = FTPTest->new (name => "Test-ftp-list-Unknown-hidden",
+                             input => \%urls,
+                             cmdline => $cmdline,
+                             errcode => $expected_error_code,
+                             output => \%expected_downloaded_files,
+                             server_behavior => {list_no_hidden_if_list => 1,
+                                                 syst_response => "215 Unknown ftp service"});
+exit $the_test->run();
+

tests/Test-ftp-list-Unknown-list-a-fails.px

@@ -0,0 +1,62 @@
+#!/usr/bin/env perl
+
+
+# 2013-10-17 Andrea Urbani (matfanjol)
+# In this ftp test:
+# - the response of "LIST -a" command is a failure
+# wget should use "LIST -a" then "LIST" to get the right
+# content.
+
+use strict;
+use warnings;
+
+use FTPTest;
+
+
+###############################################################################
+
+my $afile = <<EOF;
+Some text.
+EOF
+
+my $bfile = <<EOF;
+Some more text.
+EOF
+
+$afile =~ s/\n/\r\n/g;
+$bfile =~ s/\n/\r\n/g;
+
+# code, msg, headers, content
+my %urls = (
+    '/afile.txt' => {
+        content => $afile,
+    },
+    '/bfile.txt' => {
+        content => $bfile,
+    },
+);
+
+my $cmdline = $WgetTest::WGETPATH . " --no-directories --recursive --level=1 --accept \"?file.txt\" ftp://localhost:{{port}}/";
+
+my $expected_error_code = 0;
+
+my %expected_downloaded_files = (
+    'afile.txt' => {
+        content => $afile,
+    },
+    'bfile.txt' => {
+        content => $bfile,
+    },
+);
+
+###############################################################################
+
+my $the_test = FTPTest->new (name => "Test-ftp-list-Unknown-list-a-fails",
+                             input => \%urls,
+                             cmdline => $cmdline,
+                             errcode => $expected_error_code,
+                             output => \%expected_downloaded_files,
+                             server_behavior => {list_fails_if_list_a => 1,
+                                                 syst_response => "215 Unknown ftp service"});
+exit $the_test->run();
+

tests/Test-ftp-list-Unknown.px

@@ -0,0 +1,65 @@
+#!/usr/bin/env perl
+
+
+# 2013-10-17 Andrea Urbani (matfanjol)
+# In this ftp test:
+# - the response of SYST command is
+#   215 Unknown ftp service
+# - the response of "LIST -a" command is an empty
+#   directory.
+# wget should use "LIST -a" then "LIST" to get the right
+# content.
+
+use strict;
+use warnings;
+
+use FTPTest;
+
+
+###############################################################################
+
+my $afile = <<EOF;
+Some text.
+EOF
+
+my $bfile = <<EOF;
+Some more text.
+EOF
+
+$afile =~ s/\n/\r\n/g;
+$bfile =~ s/\n/\r\n/g;
+
+# code, msg, headers, content
+my %urls = (
+    '/afile.txt' => {
+        content => $afile,
+    },
+    '/bfile.txt' => {
+        content => $bfile,
+    },
+);
+
+my $cmdline = $WgetTest::WGETPATH . " --no-directories --recursive --level=1 --accept \"?file.txt\" ftp://localhost:{{port}}/";
+
+my $expected_error_code = 0;
+
+my %expected_downloaded_files = (
+    'afile.txt' => {
+        content => $afile,
+    },
+    'bfile.txt' => {
+        content => $bfile,
+    },
+);
+
+###############################################################################
+
+my $the_test = FTPTest->new (name => "Test-ftp-list-Unknown",
+                             input => \%urls,
+                             cmdline => $cmdline,
+                             errcode => $expected_error_code,
+                             output => \%expected_downloaded_files,
+                             server_behavior => {list_empty_if_list_a => 1,
+                                                 syst_response => "215 Unknown ftp service"});
+exit $the_test->run();
+

tests/Test-idn-cmd-utf8.px

@@ -28,7 +28,7 @@ my %urls = (
     },
 );
 
-my $cmdline = $WgetTest::WGETPATH . " --iri -rH"
+my $cmdline = $WgetTest::WGETPATH . " --iri -r"
     . " -e http_proxy=localhost:{{port}} --local-encoding=UTF-8 $utf8_hostname";
 
 my $expected_error_code = 0;

tests/Test-idn-cmd.px

@@ -28,7 +28,7 @@ my %urls = (
     },
 );
 
-my $cmdline = $WgetTest::WGETPATH . " --iri -rH"
+my $cmdline = $WgetTest::WGETPATH . " --iri -r"
     . " -e http_proxy=localhost:{{port}} --local-encoding=EUC-JP $euc_jp_hostname";
 
 my $expected_error_code = 0;

tests/Test-idn-robots-utf8.px

@@ -48,7 +48,7 @@ my %urls = (
     },
 );
 
-my $cmdline = $WgetTest::WGETPATH . " --iri -rH"
+my $cmdline = $WgetTest::WGETPATH . " --iri -r"
     . " -e http_proxy=localhost:{{port}} --local-encoding=UTF-8"
     . " http://$utf8_hostname/";
 

tests/Test-idn-robots.px

@@ -9,11 +9,14 @@ use HTTPTest;
 # " Kon'nichiwa <dot> Japan
 my $euc_jp_hostname = "\272\243\306\374\244\317.\306\374\313\334";
 my $punycoded_hostname = 'xn--v9ju72g90p.xn--wgv71a';
+my $escaped_hostname = "%ba%a3%c6%fc%a4%cf.%c6%fc%cb%dc";
 
 ###############################################################################
 
 my $starter_file = <<EOF;
 <a href="http://$euc_jp_hostname/foo.txt">The link</a>
+<a href="http://$punycoded_hostname/foo2.txt">The second link</a>
+<a href="http://$escaped_hostname/foo3.txt">The third link</a>
 EOF
 
 my $result_file = <<EOF;
@@ -38,6 +41,22 @@ my %urls = (
         },
         content => $result_file,
     },
+    "http://$punycoded_hostname/foo2.txt" => {
+        code => "200",
+        msg => "Uh-huh2",
+        headers => {
+            'Content-Type' => 'text/plain',
+        },
+        content => $result_file,
+    },
+    "http://$punycoded_hostname/foo3.txt" => {
+        code => "200",
+        msg => "Uh-huh3",
+        headers => {
+            'Content-Type' => 'text/plain',
+        },
+        content => $result_file,
+    },
     "http://$punycoded_hostname/robots.txt" => {
         code => "200",
         msg => "Uh-huh",
@@ -48,7 +67,7 @@ my %urls = (
     },
 );
 
-my $cmdline = $WgetTest::WGETPATH . " --iri -rH"
+my $cmdline = $WgetTest::WGETPATH . " --iri -r"
     . " -e http_proxy=localhost:{{port}} --local-encoding=EUC-JP"
     . " http://$euc_jp_hostname/";
 
@@ -61,6 +80,12 @@ my %expected_downloaded_files = (
     "$punycoded_hostname/foo.txt" => {
         content => $result_file,
     },
+    "$punycoded_hostname/foo2.txt" => {
+        content => $result_file,
+    },
+    "$punycoded_hostname/foo3.txt" => {
+        content => $result_file,
+    },
     "$punycoded_hostname/robots.txt" => {
         content => '',
     },

tests/run-px

@@ -35,6 +35,12 @@ my @tests = (
     'Test-ftp-iri-fallback.px',
     'Test-ftp-iri-recursive.px',
     'Test-ftp-iri-disabled.px',
+    'Test-ftp-list-Multinet.px',
+    'Test-ftp-list-Unknown.px',
+    'Test-ftp-list-Unknown-a.px',
+    'Test-ftp-list-Unknown-hidden.px',
+    'Test-ftp-list-Unknown-list-a-fails.px',
+    'Test-ftp-list-UNIX-hidden.px',
     'Test-HTTP-Content-Disposition-1.px',
     'Test-HTTP-Content-Disposition-2.px',
     'Test-HTTP-Content-Disposition.px',
@@ -70,6 +76,7 @@ my @tests = (
     'Test-O--no-content-disposition-trivial.px',
     'Test-O-nonexisting.px',
     'Test-O.px',
+    'Test--post-file.px',
     'Test-O-nc.px',
     'Test-restrict-ascii.px',
     'Test-Restrict-Lowercase.px',
@@ -80,6 +87,7 @@ my @tests = (
     'Test--spider-r--no-content-disposition.px',
     'Test--spider-r--no-content-disposition-trivial.px',
     'Test--spider-r.px',
+    'Test--httpsonly-r.px',
 );
 
 foreach my $var (qw(SYSTEM_WGETRC WGETRC)) {