Lock CSS background-image url() rewriting in the parser test

background-image is already captured and rewritten through the style/CSS
url() path, in both an external <style> block and an inline style attribute,
with the URL unquoted, double-quoted or single-quoted. Extend the offline
parser test to cover all of these so the behavior stays locked.

closes #237

README.md

@@ -23,7 +23,7 @@ http://www.httrack.com/
 
 ## Compile trunk release
 ```sh
-git clone https://github.com/xroche/httrack.git --recurse
+git clone https://github.com/xroche/httrack.git --recurse-submodules
 cd httrack
 ./configure --prefix=$HOME/usr && make -j8 && make install
 ```

html/fcguide.html

@@ -181,17 +181,17 @@ used for some time.
 
 <p align=justify> The rest of this manual is dedicated to detailing what
 you find in the help message and providing examples - lots and lots of
-examples...  Here is what you get (page by page - use <enter> to move to
+examples...  Here is what you get (page by page - use &lt;enter&gt; to move to
 the next page in the real program) if you type 'httrack --help':
 
 <pre>
 >httrack --help
  HTTrack version 3.03BETAo4 (compiled Jul  1 2001)
-	usage: ./httrack <URLs [-option] [+<FILTERs>] [-<FILTERs>]
+	usage: ./httrack &lt;URLs&gt; [-option] [+&lt;FILTERs&gt;] [-&lt;FILTERs&gt;]
 	with options listed below: (* is the default value)
 
 General options:
-  O  path for mirror/logfiles+cache (-O path_mirror[,path_cache_and_logfiles]) (--path <param>)
+  O  path for mirror/logfiles+cache (-O path_mirror[,path_cache_and_logfiles]) (--path &lt;param&gt;)
  %O  top path if no path defined (-O path_mirror[,path_cache_and_logfiles])
 
 Action options:
@@ -202,7 +202,7 @@ Action options:
   Y   mirror ALL links located in the first level pages (mirror links) (--mirrorlinks)
 
 Proxy options:
-  P  proxy use (-P proxy:port or -P user:pass@proxy:port) (--proxy <param>)
+  P  proxy use (-P proxy:port or -P user:pass@proxy:port) (--proxy &lt;param&gt;)
  %f *use proxy for ftp (f0 don't use) (--httpproxy-ftp[=N])
 
 Limits options:
@@ -227,7 +227,7 @@ Links options:
  %P *extended parsing, attempt to parse all links, even in unknown tags or Javascript (%P0 don't use) (--extended-parsing[=N])
   n  get non-html files 'near' an html file (ex: an image located outside) (--near)
   t  test all URLs (even forbidden ones) (--test)
- %L <file add all URL located in this text file (one URL per line) (--list <param>)
+ %L &lt;file&gt; add all URL located in this text file (one URL per line) (--list &lt;param&gt;)
 
 Build options:
   NN structure type (0 *original structure, 1+: see below) (--structure[=N])
@@ -248,12 +248,12 @@ Spider options:
  %h  force HTTP/1.0 requests (reduce update features, only for old servers or proxies) (--http-10)
  %B  tolerant requests (accept bogus responses on some servers, but not standard!) (--tolerant)
  %s  update hacks: various hacks to limit re-transfers when updating (identical size, bogus response..) (--updatehack)
- %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3=text/html) (--assume <param>)
+ %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3=text/html) (--assume &lt;param&gt;)
 
 Browser ID:
-  F  user-agent field (-F "user-agent name") (--user-agent <param>)
- %F  footer string in Html code (-%F "Mirrored [from host %s [file %s [at %s]]]" (--footer <param>)
- %l  preferred language (-%l "fr, en, jp, *" (--language <param>)
+  F  user-agent field (-F "user-agent name") (--user-agent &lt;param&gt;)
+ %F  footer string in Html code (-%F "Mirrored [from host %s [file %s [at %s]]]" (--footer &lt;param&gt;)
+ %l  preferred language (-%l "fr, en, jp, *" (--language &lt;param&gt;)
 
 Log, index, cache
   C  create/use a cache for updates and retries (C0 no cache,C1 cache is prioritary,* C2 test update before) (--cache[=N])
@@ -303,8 +303,8 @@ Guru options: (do NOT use)
  #!  Execute a shell command (-#! "echo hello")
 
 Command-line specific options:
-  V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd <param>)
- %U run the engine with another id when called as root (-%U smith) (--user <param>)
+  V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd &lt;param&gt;)
+ %U run the engine with another id when called as root (-%U smith) (--user &lt;param&gt;)
 
 Details: Option N
   N0 Site-structure (default)
@@ -340,14 +340,14 @@ Details: User-defined option N
   %[param] param variable in query string
 
 Shortcuts:
---mirror      <URLs *make a mirror of site(s) (default)
---get         <URLs  get the files indicated, do not seek other URLs (-qg)
---list   <text file  add all URL located in this text file (-%L)
---mirrorlinks <URLs  mirror all links in 1st level pages (-Y)
---testlinks   <URLs  test links in pages (-r1p0C0I0t)
---spider      <URLs  spider site(s), to test links: reports Errors & Warnings (-p0C0I0t)
---testsite    <URLs  identical to --spider
---skeleton    <URLs  make a mirror, but gets only html files (-p1)
+--mirror      &lt;URLs&gt; *make a mirror of site(s) (default)
+--get         &lt;URLs&gt;  get the files indicated, do not seek other URLs (-qg)
+--list   &lt;text file&gt;  add all URL located in this text file (-%L)
+--mirrorlinks &lt;URLs&gt;  mirror all links in 1st level pages (-Y)
+--testlinks   &lt;URLs&gt;  test links in pages (-r1p0C0I0t)
+--spider      &lt;URLs&gt;  spider site(s), to test links: reports Errors & Warnings (-p0C0I0t)
+--testsite    &lt;URLs&gt;  identical to --spider
+--skeleton    &lt;URLs&gt;  make a mirror, but gets only html files (-p1)
 --update              update a mirror, without confirmation (-iC2)
 --continue            continue a mirror, without confirmation (-iC1)
 
@@ -387,13 +387,13 @@ with examples... I will be here a while...
 <hr>
 <h2> Syntax </h2>
 
-<pre><b><i>httrack <URLs> [-option] [+<FILTERs>] [-<FILTERs>] </i></b></pre>
+<pre><b><i>httrack &lt;URLs&gt; [-option] [+&lt;FILTERs&gt;] [-&lt;FILTERs&gt;] </i></b></pre>
 
 <p align=justify> The syntax of httrack is quite simple.  You specify
-the URLs you wish to start the process from (<URLS>), any options you
+the URLs you wish to start the process from (&lt;URLS&gt;), any options you
 might want to add ([-option], any filters specifying places you should
-([+<FILTERs>]) and should not ([-<FILTERs>]) go, and end the command
-line by pressing <enter>.  Httrack then goes off and does your bidding.
+([+&lt;FILTERs&gt;]) and should not ([-&lt;FILTERs&gt;]) go, and end the command
+line by pressing &lt;enter&gt;.  Httrack then goes off and does your bidding.
 For example:
 
 <pre><b><i>
@@ -425,7 +425,7 @@ site. Specifically, the defauls are:
   pN priority mode: (* p3)  *3 save all files
   D  *can only go down into subdirs
   a  *stay on the same address
-  --mirror      <URLs> *make a mirror of site(s) (default)
+  --mirror      &lt;URLs&gt; *make a mirror of site(s) (default)
 </pre>
 
 <p align=justify> Here's what all of that means:
@@ -542,7 +542,7 @@ subdirectories of the starting directory to be investigated.
 search started are to be collected.  Other sites they point to are not
 to be imaged. 
 
-<pre><b><i>  --mirror      <URLs> *make a mirror of site(s) (default) </i></b></pre>
+<pre><b><i>  --mirror      &lt;URLs&gt; *make a mirror of site(s) (default) </i></b></pre>
 
 <p align=justify> This indicates that the program should try to make a
 copy of the site as well as it can. 
@@ -921,7 +921,7 @@ Links options:
  %P *extended parsing, attempt to parse all links, even in unknown tags or Javascript (%P0 don't use)
   n   get non-html files 'near' an html file (ex: an image located outside)
   t   test all URLs (even forbidden ones)
- %L <file> add all URL located in this text file (one URL per line)
+ %L &lt;file&gt; add all URL located in this text file (one URL per line)
 </i></b></pre>
 
 <p align=justify> The links options allow you to control what links are
@@ -1183,7 +1183,7 @@ Spider options:
  %h  force HTTP/1.0 requests (reduce update features, only for old servers or proxies)
  %B  tolerant requests (accept bogus responses on some servers, but not standard!)
  %s  update hacks: various hacks to limit re-transfers when updating
- %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3=text/html) (--assume <param>)
+ %A  assume that a type (cgi,asp..) is always linked with a mime type (-%A php3=text/html) (--assume &lt;param&gt;)
 </i></b></pre>
 
 <p align=justify> By default, cookies are universally accepted and
@@ -1387,7 +1387,7 @@ web servers leave footprints in the browser.
 Browser ID:
   F  user-agent field (-F "user-agent name")
  %F  footer string in Html code (-%F "Mirrored [from host %s [file %s [at %s]]]"
- %l  preferred language (-%l "fr, en, jp, *" (--language <param>)
+ %l  preferred language (-%l "fr, en, jp, *" (--language &lt;param&gt;)
 </i></b></pre>
 
 <p align=justify> The user-agent field is used by browsers to determine
@@ -1799,7 +1799,7 @@ based authentication)
 
 <pre><b><i>
 Command-line specific options:
-  V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd <param>)
+  V execute system command after each files ($0 is the filename: -V "rm \$0") (--userdef-cmd &lt;param&gt;)
 </i></b></pre>
 
 <p align=justify> This option is very nice for a wide array of actions
@@ -1811,7 +1811,7 @@ httrack http://www.shoesizes.com/bob/ -O /tmp/shoesizes -V "/bin/echo \$0"
 </i></b></pre>
 
 <pre>
- %U run the engine with another id when called as root (-%U smith) (--user <param>)
+ %U run the engine with another id when called as root (-%U smith) (--user &lt;param&gt;)
 </pre>
 
 <p align=justify> Change the UID of the owner when running as r00t
@@ -1856,14 +1856,14 @@ of other options that are commonly used.
 
 <pre><b><i>
 Shortcuts:
---mirror      <URLs> *make a mirror of site(s) (default)
---get         <URLs>  get the files indicated, do not seek other URLs (-qg)
---list   <text file>  add all URL located in this text file (-%L)
---mirrorlinks <URLs>  mirror all links in 1st level pages (-Y)
---testlinks   <URLs>  test links in pages (-r1p0C0I0t)
---spider      <URLs>  spider site(s), to test links: reports Errors & Warnings (-p0C0I0t)
---testsite    <URLs>  identical to --spider
---skeleton    <URLs>  make a mirror, but gets only html files (-p1)
+--mirror      &lt;URLs&gt; *make a mirror of site(s) (default)
+--get         &lt;URLs&gt;  get the files indicated, do not seek other URLs (-qg)
+--list   &lt;text file&gt;  add all URL located in this text file (-%L)
+--mirrorlinks &lt;URLs&gt;  mirror all links in 1st level pages (-Y)
+--testlinks   &lt;URLs&gt;  test links in pages (-r1p0C0I0t)
+--spider      &lt;URLs&gt;  spider site(s), to test links: reports Errors & Warnings (-p0C0I0t)
+--testsite    &lt;URLs&gt;  identical to --spider
+--skeleton    &lt;URLs&gt;  make a mirror, but gets only html files (-p1)
 --update              update a mirror, without confirmation (-iC2)
 --continue            continue a mirror, without confirmation (-iC1)
 --catchurl            create a temporary proxy to capture an URL or a form post URL
@@ -2019,15 +2019,15 @@ are in reverse priority order.  Here's an example:
         <td>no characters must be present after</a></td>
       </tr>
 	<tr>
-		<td> <b> <filter>*[&lt NN]</b></td>
+		<td> <b> &lt;filter&gt;*[&lt NN]</b></td>
 		<td> size less than NN Kbytes</td>
 	</tr>
 	<tr>
-		<td> <b> <filter>*[&gt PP]</b></td>
+		<td> <b> &lt;filter&gt;*[&gt PP]</b></td>
 		<td> size more than PP Kbytes</td>
 	</tr>
 	<tr>
-		<td> <b> <filter>*[&lt NN &gt PP]</b></td>
+		<td> <b> &lt;filter&gt;*[&lt NN &gt PP]</b></td>
 		<td> size less than NN Kbytes and more than PP Kbytes</td>
 	</tr>
     </table>

lang/Ukrainian.txt

@@ -7,7 +7,7 @@ uk
 LANGUAGE_AUTHOR
 Andrij Shevchuk (http://programy.com.ua, http://vic-info.com.ua) \r\n
 LANGUAGE_CHARSET
-ISO-8859-5
+windows-1251
 LANGUAGE_WINDOWSID
 Ukrainian
 OK

src/htslib.c

@@ -121,6 +121,7 @@ const char *hts_detect[] = {
   "lowsrc",
   "profile",                    // element META
   "src",
+  "srcset",                     // HTML5 responsive images (<img>, <source>)
   "swurl",
   "url",
   "usemap",

src/htsparse.c

@@ -532,6 +532,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
         int valid_p = 0;        // force to take p even if == 0
         int ending_p = '\0';    // ending quote?
         int archivetag_p = 0;   // avoid multiple-archives with commas
+        int srcset_p = 0;       // srcset="url1 480w, url2 2x": list of URLs
         int unquoted_script = 0;
         INSCRIPT inscript_state_pos_prev = inscript_state_pos;
 
@@ -1050,6 +1051,12 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                           if (strcmp(hts_detect[i], "archive") == 0) {
                             archivetag_p = 1;
                           }
+                          /* srcset: a comma-list of candidate URLs, each split
+                             out and rewritten below (#235, #236) */
+                          else if (strcmp(hts_detect[i], "srcset") == 0
+                                   || strcmp(hts_detect[i], "data-srcset") == 0) {
+                            srcset_p = 1;
+                          }
                         }
                         i++;
                       }
@@ -1815,6 +1822,14 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                 html++;          // sauter # pour usemap etc
               }
             }
+ srcset_next:
+            /* srcset: skip leading whitespace/commas before each candidate;
+               the skipped bytes flush verbatim below */
+            if (srcset_p) {
+              while(html < r->adr + r->size
+                    && (is_realspace(*html) || *html == ','))
+                INCREMENT_CURRENT_ADR(1);
+            }
             eadr = html;
 
             // ne pas flusher après code si on doit écrire le codebase avant!
@@ -1844,6 +1859,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                     if ((*eadr == quote && (!quoteinscript || *(eadr - 1) == '\\'))     // end quote
                         || (noquote && (*eadr == '\"' || *eadr == '\''))        // end at any quote
                         || (!noquote && quote == '\0' && is_realspace(*eadr))   // unquoted href
+                        || srcset_p     // whitespace ends a srcset candidate URL
                       )         // si pas d'attente de quote spéciale ou si quote atteinte
                       ok = 0;
                   } else if (ending_p && (*eadr == ending_p))
@@ -1872,6 +1888,16 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                       break;    // \" ou \' point d'arrêt
                     case '?':  /*quote_adr=adr; */
                       break;    // noter position query
+                    case ',':
+                      if (srcset_p) {
+                        /* split only on a trailing comma; one inside the URL
+                           (data: URI, CDN path) is kept, per the WHATWG algo */
+                        const char *const n = eadr + 1;
+
+                        if (n >= r->adr + r->size || is_space(*n) || *n == ',')
+                          ok = 0;
+                      }
+                      break;
                     }
                   }
                   //}
@@ -3250,6 +3276,28 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
             }
             // adr=eadr-1;  // ** sauter
 
+            /* srcset candidate loop: skip the descriptor and comma, then
+               re-enter the capture for the next URL. Backward goto, not a loop:
+               the per-candidate body is this whole block. */
+            if (srcset_p && ok == 0) {
+              const char *const endp = r->adr + r->size;
+              const char *q = html;
+              while(q < endp && *q != '\0' && *q != ',' && *q != quote
+                    && *q != '<' && *q != '>' && (unsigned char) *q >= 32)
+                q++;            // skip the descriptor
+              if (q < endp && *q == ',') {
+                q++;
+                while(q < endp && (is_realspace(*q) || *q == ','))
+                  q++;          // skip whitespace and empty candidates
+                if (q < endp && *q != '\0' && *q != ',' && *q != quote
+                    && *q != '<' && *q != '>' && (unsigned char) *q >= 32) {
+                  INCREMENT_CURRENT_ADR(q - html);   // keep the automate in sync
+                  ok = 1;
+                  goto srcset_next;
+                }
+              }
+            }
+
             /* We skipped bytes and skip the " : reset state */
             /*if (inscript) {
                inscript_state_pos = INSCRIPT_START;

tests/01_engine-filter.test

@@ -47,3 +47,25 @@ match '*foo*bar' 'foozbar'
 
 # '?' is the query-string marker, not a single-char wildcard
 nomatch 'a?c' 'abc'
+
+# backslash escapes a metacharacter inside a class so it is matched literally.
+# Quirk: the decoder also adds the backslash itself to the set, so '\X' matches
+# both X and '\'. These assertions pin that behavior.
+match '*[\*]' '*'
+match '*[\*]' "\\"
+nomatch '*[\*]' 'a'
+match '*[\\]' "\\"
+nomatch '*[\\]' 'a'
+match '*[\[]' '['
+match '*[\[]' "\\"
+nomatch '*[\[]' 'a'
+
+# A literal ']' cannot be a class member: the class parser stops at the first
+# ']', escaped or not. So '*[\[\]]' does NOT mean "the [ or ] character" as the
+# filter guide claims (GitHub #148); it parses as the class {'[','\'} followed
+# by a trailing literal ']'. These assertions document the current (buggy)
+# behavior so any future matcher fix is a deliberate, visible change.
+nomatch '*[\[\]]' '['   # not matched, despite the docs
+match '*[\[\]]' ']'     # only via the empty class-match + trailing ']'
+match '*[\[\]]' '[]'    # one of {'[','\'} then the trailing ']'
+nomatch '*[\[\]]' '[]x'

tests/01_engine-parse.test

@@ -0,0 +1,155 @@
+#!/bin/bash
+#
+
+# Offline HTML parser tests: each section crawls a file:// fixture (no network)
+# and checks which assets the parser captured and how it rewrote the links.
+
+set -u
+
+tmp=$(mktemp -d "${TMPDIR:-/tmp}/httrack_parse.XXXXXX") || exit 1
+trap 'rm -rf "$tmp"' EXIT HUP INT QUIT PIPE TERM
+
+# a minimal valid 1x1 GIF, reused for every referenced asset
+gif() {
+    printf 'GIF89a\1\0\1\0\200\0\0\0\0\0\377\377\377!\371\4\1\0\0\0\0,\0\0\0\0\1\0\1\0\0\2\2D\1\0;' >"$1"
+}
+
+# crawl <fixture-html> into <out> with link rewriting on, no extra fetching
+crawl() {
+    local html="$1" out="$2"
+    rm -rf "$out"
+    mkdir -p "$out"
+    httrack "file://$html" -O "$out" --quiet --near -n >"$out/.log" 2>&1
+}
+
+# assert a file with the given basename was saved somewhere under <out>
+found() {
+    test -n "$(find "$2" -type f -name "$1" -print -quit)" ||
+        ! echo "FAIL: expected '$1' to be downloaded under $2" || exit 1
+}
+
+# assert NO file with the given basename was saved (e.g. a descriptor token must
+# not be mistaken for a URL)
+notfound() {
+    test -z "$(find "$2" -type f -name "$1" -print -quit)" ||
+        ! echo "FAIL: '$1' should not have been downloaded under $2" || exit 1
+}
+
+# the mirrored fixture page (under "file/"), not HTTrack's own landing index
+savedhtml() {
+    find "$1" -type f -path '*/file/*' -name index.html -print -quit
+}
+
+# srcset on <img> and <source> (#235, #236): every candidate captured and
+# rewritten, descriptors preserved, following attributes left intact.
+site="$tmp/srcset"
+mkdir -p "$site"
+for f in a b c d e f g h i j v dz; do gif "$site/$f.gif"; done
+# unquoted heredoc: $site expands in the absolute-URL candidate
+cat >"$site/index.html" <<EOF
+<html><body>
+<img src="a.gif" srcset="b.gif 480w, c.gif 800w">
+<picture><source srcset="d.gif 1x, c.gif 2x"><img src="a.gif"></picture>
+<img srcset="e.gif, f.gif">
+<img srcset="g.gif 2x" alt="trailing attr after srcset">
+<img srcset="  h.gif   2x ,  i.gif  ">
+<video><source src="v.gif"></video>
+<img srcset="file://$site/j.gif 2x">
+<img srcset="data:image/gif;base64,R0lGODlhAQABAAAAACw= 1x, dz.gif 2x">
+<img srcset="">
+<a href="a.gif">plain link still works</a>
+</body></html>
+EOF
+out="$tmp/srcset-out"
+crawl "$site/index.html" "$out"
+
+# every candidate downloads, incl. unique tails (catches first-only parsing),
+# whitespace-padded (h,i), <source src> (v), absolute (j), post-data: URI (dz)
+for f in a b c d e f g h i j v dz; do found "$f.gif" "$out"; done
+
+# the width/density descriptors are not URLs and must not be fetched
+notfound "480w" "$out"
+notfound "800w" "$out"
+notfound "2x" "$out"
+
+saved=$(savedhtml "$out")
+test -n "$saved" || ! echo "FAIL: saved index.html not found" || exit 1
+
+# descriptors must survive the rewrite (no "b.gif 480w" mangled into a path)
+grep -Eq 'srcset="[^"]*480w[^"]*800w' "$saved" ||
+    ! echo "FAIL: srcset width descriptors lost/reordered in rewritten HTML" || exit 1
+grep -Eq 'srcset="[^"]*1x[^"]*2x' "$saved" ||
+    ! echo "FAIL: srcset density descriptors lost/reordered in rewritten HTML" || exit 1
+# the descriptor-less comma form keeps both candidates and the separator verbatim
+grep -Eq 'srcset="e\.gif, f\.gif"' "$saved" ||
+    ! echo "FAIL: comma-separated srcset without descriptors was altered" || exit 1
+# an attribute following srcset in the same tag must be left intact
+grep -q 'alt="trailing attr after srcset"' "$saved" ||
+    ! echo "FAIL: srcset swallowed a following attribute" || exit 1
+
+# a comma inside a URL (data: URI, CDN path) is part of the URL, not a split
+# point (WHATWG): the data: URI stays verbatim; the next candidate (dz) downloads
+grep -Fq 'data:image/gif;base64,R0lGODlhAQABAAAAACw= 1x' "$saved" ||
+    ! echo "FAIL: a comma inside a data: URI srcset candidate was mis-split" || exit 1
+
+# real rewrite, not passthrough: the absolute file:// candidate becomes local
+# (a flat fixture can't show this; the footer comment's file:// is not in srcset)
+grep -Eq 'srcset="j\.gif 2x"' "$saved" ||
+    ! echo "FAIL: absolute file:// srcset URL was not rewritten to a local link" || exit 1
+! grep -Eq 'srcset="[^"]*file://' "$saved" ||
+    ! echo "FAIL: a file:// URL survived inside a rewritten srcset attribute" || exit 1
+
+# xlink:href (#298) and CSS background-image (#237): detected and rewritten to
+# local. background-image is covered in both an external <style> block and an
+# inline style attribute, with the URL unquoted, double-quoted and single-quoted
+# (the quote style is preserved on rewrite). No-detect attributes (title, alt,
+# ...) are left untouched. Asserted by rewrite (deterministic), not download.
+# data-* (#201/#203) is omitted: its detection is currently nondeterministic and
+# can't be locked yet.
+site2="$tmp/attrs"
+mkdir -p "$site2"
+for f in xl ibg ibgs cex cexd cexs tt; do gif "$site2/$f.gif"; done
+cat >"$site2/index.html" <<EOF
+<html><head><style>
+.a { background-image: url(file://$site2/cex.gif); }
+.b { background-image: url("file://$site2/cexd.gif"); }
+.c { background-image: url('file://$site2/cexs.gif'); }
+</style></head><body>
+<a xlink:href="file://$site2/xl.gif">xlink:href (#298)</a>
+<div style="background-image:url(file://$site2/ibg.gif)"></div>
+<div style="background-image:url('file://$site2/ibgs.gif')"></div>
+<span title="file://$site2/tt.gif">excluded attribute</span>
+</body></html>
+EOF
+out2="$tmp/attrs-out"
+crawl "$site2/index.html" "$out2"
+saved2=$(savedhtml "$out2")
+test -n "$saved2" || ! echo "FAIL: saved attrs page not found" || exit 1
+
+# detected attributes: the absolute URL is rewritten to a local link
+grep -Eq 'xlink:href="xl\.gif"' "$saved2" ||
+    ! echo "FAIL #298: xlink:href not detected/rewritten" || exit 1
+
+# #237 external <style> block, each quoting form, quote style preserved
+grep -Eq 'url\(cex\.gif\)' "$saved2" ||
+    ! echo "FAIL #237: unquoted background-image in <style> not rewritten" || exit 1
+grep -Eq 'url\("cexd\.gif"\)' "$saved2" ||
+    ! echo "FAIL #237: double-quoted background-image in <style> not rewritten" || exit 1
+grep -Eq "url\('cexs\.gif'\)" "$saved2" ||
+    ! echo "FAIL #237: single-quoted background-image in <style> not rewritten" || exit 1
+
+# #237 inline style attribute, unquoted and single-quoted url()
+grep -Eq 'style="background-image:url\(ibg\.gif\)"' "$saved2" ||
+    ! echo "FAIL #237: inline unquoted background-image not rewritten" || exit 1
+grep -Eq "style=\"background-image:url\('ibgs\.gif'\)\"" "$saved2" ||
+    ! echo "FAIL #237: inline single-quoted background-image not rewritten" || exit 1
+
+# no file:// URL survived inside any rewritten background-image
+! grep -Eq 'background-image:[^;"]*file://' "$saved2" ||
+    ! echo "FAIL #237: a file:// URL survived inside a rewritten background-image" || exit 1
+
+# excluded attribute: title is on the no-detect list, so its value is left as-is
+grep -q 'title="file://' "$saved2" ||
+    ! echo "FAIL: a no-detect attribute (title) was wrongly rewritten" || exit 1
+
+exit 0

tests/Makefile.am

@@ -9,6 +9,6 @@ TESTS_ENVIRONMENT += HTTPS_SUPPORT=$(HTTPS_SUPPORT)
 TESTS_ENVIRONMENT += top_srcdir=$(top_srcdir)
 
 TEST_EXTENSIONS = .test
-TESTS = 00_runnable.test 01_engine-charset.test 01_engine-entities.test 01_engine-filter.test 01_engine-hashtable.test 01_engine-idna.test 01_engine-mime.test 01_engine-simplify.test 02_manpage-regen.test 10_crawl-simple.test 11_crawl-cookies.test 11_crawl-idna.test 11_crawl-international.test 11_crawl-longurl.test 11_crawl-parsing.test 12_crawl_https.test
+TESTS = 00_runnable.test 01_engine-charset.test 01_engine-entities.test 01_engine-filter.test 01_engine-hashtable.test 01_engine-idna.test 01_engine-mime.test 01_engine-parse.test 01_engine-simplify.test 02_manpage-regen.test 10_crawl-simple.test 11_crawl-cookies.test 11_crawl-idna.test 11_crawl-international.test 11_crawl-longurl.test 11_crawl-parsing.test 12_crawl_https.test
 
 CLEANFILES = check-network_sh.cache

tests/Makefile.in

@@ -472,7 +472,7 @@ TESTS_ENVIRONMENT = PATH=$(top_builddir)/src$(PATH_SEPARATOR)$$PATH \
 	ONLINE_UNIT_TESTS=$(ONLINE_UNIT_TESTS) \
 	HTTPS_SUPPORT=$(HTTPS_SUPPORT) top_srcdir=$(top_srcdir)
 TEST_EXTENSIONS = .test
-TESTS = 00_runnable.test 01_engine-charset.test 01_engine-entities.test 01_engine-filter.test 01_engine-hashtable.test 01_engine-idna.test 01_engine-mime.test 01_engine-simplify.test 02_manpage-regen.test 10_crawl-simple.test 11_crawl-cookies.test 11_crawl-idna.test 11_crawl-international.test 11_crawl-longurl.test 11_crawl-parsing.test 12_crawl_https.test
+TESTS = 00_runnable.test 01_engine-charset.test 01_engine-entities.test 01_engine-filter.test 01_engine-hashtable.test 01_engine-idna.test 01_engine-mime.test 01_engine-parse.test 01_engine-simplify.test 02_manpage-regen.test 10_crawl-simple.test 11_crawl-cookies.test 11_crawl-idna.test 11_crawl-international.test 11_crawl-longurl.test 11_crawl-parsing.test 12_crawl_https.test
 CLEANFILES = check-network_sh.cache
 all: all-am