Bound the option-token sscanf to the buffer size

CodeQL flagged the %s read into cmd[32] as an unbounded copy on the line the previous commit touched. The tokens come from HTTrack's own help strings, not hostile input, so it was not reachable in practice, but the copy should be bounded regardless. Limit it to %30s (the buffer holds the leading '-' plus 30 chars and a NUL). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: Xavier Roche <roche@httrack.com>
Advertise -%N's long option and document the real long forms
2026-07-22 16:51:25 +03:00 · 2026-07-22 07:51:08 +02:00 · 2026-07-22 07:32:51 +02:00
19 changed files with 1016 additions and 1246 deletions
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -618,31 +618,3 @@ jobs:
              echo "Fix locally with: git clang-format --binary clang-format-19 $base"
              exit 1 ;;
          esac
-
-  man-page-sync:
-    name: man page / html in sync
-    if: github.event_name == 'pull_request'
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-
-      # html/httrack.man.html is groff-rendered from man/httrack.1 and committed.
-      # Rendering needs the full groff html device, so CI can't regenerate it;
-      # instead require the two to move together: a PR that touches httrack.1
-      # must also touch the html, catching the "regenerated roff, forgot html".
-      - name: httrack.1 changes must include html/httrack.man.html
-        run: |
-          set -euo pipefail
-          git fetch --no-tags origin \
-            "+refs/heads/${{ github.base_ref }}:refs/remotes/origin/${{ github.base_ref }}"
-          base="origin/${{ github.base_ref }}"
-          changed="$(git diff --name-only "$base"...HEAD)"
-          has() { printf '%s\n' "$changed" | grep -qx "$1"; }
-          if has man/httrack.1 && ! has html/httrack.man.html; then
-            echo "::error::man/httrack.1 changed but html/httrack.man.html did not."
-            echo "Regenerate it with: make -C man regen-man-html (needs the full groff package)."
-            exit 1
-          fi
-          echo "man/html sync OK."
--- a/.github/workflows/codeql.yml
+++ b/.github/workflows/codeql.yml
@@ -55,9 +55,6 @@ jobs:
            query-filters:
              - exclude:
                  id: cpp/world-writable-file-creation
-              # Models auth-bypass-by-spoofing; httrack has no auth surface, its +/- crawl filter is a mirror boundary, not a security one.
-              - exclude:
-                  id: cpp/user-controlled-bypass

      # Manual build: CodeQL traces the compiler, so build exactly what ships.
      - name: Build
--- a/html/cmdguide.html
+++ b/html/cmdguide.html
@@ -219,23 +219,6 @@ that a <tt>403 Forbidden</tt> is a server refusal, not a robots rule: robots
 options will not help there. That is an
 <a href="#identity">identity</a> problem.</p>

-<h4>Filter wildcards</h4>
-<p>Inside a filter pattern, <tt>*</tt> matches any run of characters; a few
-bracket forms match narrower sets. The full table, with size and mime rules, is on
-<a href="filters.html">the filters page</a>.</p>
-<table class="tblRegular tableWidth" border="0">
-  <tr class="tblHeaderColor"><td><b>Wildcard</b></td><td><b>Matches</b></td><td><b>Example</b></td></tr>
-  <tr><td><tt>*</tt></td><td>any run of characters</td><td><tt>+*.pdf</tt> &mdash; any URL ending <tt>.pdf</tt></td></tr>
-  <tr><td><tt>*[file]</tt>, <tt>*[name]</tt></td><td>one path segment (any char but <tt>/</tt> and <tt>?</tt>)</td><td><tt>example.com/*[file]/</tt> &mdash; a directory-index page</td></tr>
-  <tr><td><tt>*[path]</tt></td><td>a path, slashes allowed (any char but <tt>?</tt>)</td><td><tt>example.com/*[path].zip</tt></td></tr>
-  <tr><td><tt>*[param]</tt></td><td>an optional query string</td><td><tt>page.html*[param]</tt> matches with or without <tt>?...</tt></td></tr>
-  <tr><td><tt>*[a,b,c]</tt></td><td>any one character in the set</td><td><tt>*[a,b,c].txt</tt></td></tr>
-  <tr><td><tt>*[a-z]</tt></td><td>any one character in the range</td><td><tt>img*[0-9].gif</tt></td></tr>
-  <tr><td><tt>*[\x]</tt></td><td>the literal character x (escapes <tt>* [ ] \</tt>)</td><td><tt>*[\*]</tt> matches a real <tt>*</tt></td></tr>
-  <tr><td><tt>*[&lt;NN]</tt>, <tt>*[&gt;NN]</tt></td><td>file size in KB below / above NN</td><td><tt>-*.gif*[&lt;5]</tt> skips GIFs under 5&nbsp;KB</td></tr>
-  <tr><td><tt>*[]</tt></td><td>end anchor: nothing may follow</td><td><tt>*.html*[]</tt> rejects <tt>i.html?p=1</tt></td></tr>
-</table>
-
 <h3 id="limits">4. Limits and politeness</h3>

 <p>HTTrack ships cautious on purpose: it is easy to hammer a small site by
@@ -421,16 +404,14 @@ host and stops the crawl; start from the final URL, or add
 rule wins.</small></p>

 <h4>Download the PDFs on a site</h4>
-<p><tt>httrack https://example.com/ "-*" "+https://example.com/*.html" "+https://example.com/*[path]/" "+https://example.com/*.pdf" --path mydir</tt><br>
-<small>HTTrack finds PDFs by parsing the site's HTML, so a plain
-<tt>"-*" "+example.com/*.pdf"</tt> is wrong: it prunes the pages that carry the
-links and keeps only PDFs reachable from the front page. Instead admit the HTML as
-scaffolding (<tt>*.html</tt> and <tt>*[path]/</tt> for directory-index pages at any
-depth, e.g. <tt>docs/</tt> or <tt>a/b/deep/</tt>; <tt>*[file]/</tt> would stop at one
-level), keep the PDFs, and let <tt>-*</tt> drop everything else (images,
-archives, off-site assets). PDFs on another host (a CDN or docs subdomain) are not
-included by default; allow that host too, e.g. <tt>"+docs.example.com/*.pdf"</tt>,
-or widen to <tt>"+*.pdf"</tt> for PDFs anywhere.</small></p>
+<p><tt>httrack https://example.com/ --path mydir</tt><br>
+<small>There is no PDF-only crawl. HTTrack discovers PDF links by parsing the
+site's HTML pages, so a <tt>"-*" "+example.com/*.pdf"</tt> filter blocks the very
+pages that carry the links and grabs only the PDFs linked from the front page. Let
+it crawl the site: the HTML pages come along as the scaffolding, and every reachable
+PDF is saved with them. If some PDFs live on another host (a CDN or a docs
+subdomain), allow that host too, for example
+<tt>"+docs.example.com/*.pdf"</tt>.</small></p>

 <h4>Keep page requisites, including off-host images</h4>
 <p><tt>httrack https://example.com/blog/ --near --path mydir</tt><br>
--- a/html/faq.html
+++ b/html/faq.html
@@ -3,7 +3,7 @@
 <head>
 	<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
 	<meta name="description" content="HTTrack is an easy-to-use website mirror utility. It allows you to download a World Wide website from the Internet to a local directory,building recursively all structures, getting html, images, and other files from the server to your computer. Links are rebuiltrelatively so that you can freely browse to the local site (works with any browser). You can mirror several sites together so that you can jump from one toanother. You can, also, update an existing mirror site, or resume an interrupted download. The robot is fully configurable, with an integrated help" />
-	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, linux, windows, macos, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
+	<meta name="keywords" content="httrack, HTTRACK, HTTrack, winhttrack, WINHTTRACK, WinHTTrack, offline browser, web mirror utility, aspirateur web, surf offline, web capture, www mirror utility, browse offline, local  site builder, website mirroring, aspirateur www, internet grabber, capture de site web, internet tool, hors connexion, unix, dos, windows vista, windows seven, windows 8, solaris, ibm580, AIX 4.0, HTS, HTGet, web aspirator, web aspirateur, libre, GPL, GNU, free software" />
 	<title>HTTrack Website Copier - Offline Browser</title>

 	<style type="text/css">
@@ -135,7 +135,9 @@ clear language!

 <li><a href="#QG2">Where can I find French/other languages documentation?</a><br></li>

-<li><a href="#QG3">Which systems does HTTrack run on?</a><br></li>
+<li><a href="#QG3b">Is HTTrack working on Windows Vista/Windows Seven/Windows 8 ?</a><br></li>
+
+<li><a href="#QG3">Is HTTrack working on Windows 95/98 ?</a><br></li>

 <li><a href="#QG4">What's the difference between HTTrack, WinHTTrack and WebHTTrack?</a><br></li>

@@ -318,10 +320,10 @@ This can easily done by using filters: go to the Option panel, select the 'Scan
 <tt>+www.example.com/gallery/trees/*<br>
 +www.example.com/photos/*</tt><br>
 <br>
-This means "accept all links beginning with <tt>www.example.com/gallery/trees/</tt> and <tt>www.example.com/photos/</tt>" 
+This means "accept all links begining with <tt>www.example.com/gallery/trees/</tt> and <tt>www.example.com/photos/</tt>" 
 - the <tt>+</tt> means "accept" and the final <tt>*</tt> means "any character will match after the previous ones".
 Remember the <tt>*.doc</tt> or <tt>*.zip</tt> encountered when you want to select all files from a certain type on your computer: 
-it is almost the same here, except the beginning "+"<br>
+it is almost the same here, except the begining "+"<br>
 <br>
 Now, we might want to exclude all links in <tt>www.example.com/gallery/trees/hugetrees/</tt>, because with the previous filter,
 we accepted too many files. Here again, you can add a filter rule to refuse these links. Modify the previous filters to:<br>
@@ -329,8 +331,8 @@ we accepted too many files. Here again, you can add a filter rule to refuse thes
 +www.example.com/photos/*<br>
 -www.example.com/gallery/trees/hugetrees/*</tt><br>
 <br>
-You have noticed the <tt>-</tt> in the beginning of the third rule: this means "refuse links matching the rule" 
-; and the rule is "any files beginning with <tt>www.example.com/gallery/trees/hugetrees/</tt><br>
+You have noticed the <tt>-</tt> in the begining of the third rule: this means "refuse links matching the rule" 
+; and the rule is "any files begining with <tt>www.example.com/gallery/trees/hugetrees/</tt><br>

 Voila! With these three rules, you have precisely defined what you wanted to capture.<br>
 <br>
@@ -359,12 +361,12 @@ You can freely download it, without paying any fees, copy it to your friends, an
 There are NO official/authorized resellers, because HTTrack is <b>NOT</b> a commercial product.
 But you can be charged for duplication fees, or any other services (example: software CDroms or shareware collections, or fees for maintenance), 
 but you should have been informed that the software was free software/GPL, and you <b><u>MUST</u></b> have received a copy of the GNU General Public License.
-Otherwise this is dishonest and unfair (ie. selling httrack on ebay without telling that it was a free software is a scam).
+Otherwise this is dishonnest and unfair (ie. selling httrack on ebay without telling that it was a free software is a scam).
 </em>

 <br><br><a NAME="QG0b">Q: <strong>Are there any risks of viruses with this software?</strong></a><br>
 A: <em>For the software itself: 
-All official releases (at httrack.com) are checked against all known viruses, and the packaging process is also checked. Archives are stored on Un*x servers, not really concerned by viruses. It has been reported, however, that some rogue freeware sites are embedding free software and freeware inside badware installers. Always download httrack from the main site (www.httrack.com), and never from an untrusted source!<br>
+All official releases (at httrack.com) are checked against all known viruses, and the packaging process is also checked. Archives are stored on Un*x servers, not really concerned by viruses. It has been reported, however, that some rogue freeware sites are embedding free softwares and freewares inside badware installers. Always download httrack from the main site (www.httrack.com), and never from an untrusted source!<br>
 For files you are downloading on the WWW using HTTrack: You may encounter websites which were corrupted by viruses, and downloading data on these websites might be dangerous if you execute downloaded executables, or if embedded pages contain infected material (as dangerous as if using a regular Browser). Always ensure that websites you are crawling are safe.
 (Note: remember that using an antivirus software is a good idea once you are connected to the Internet)</em>

@@ -374,8 +376,11 @@ A: <em>That's right. You can, however, install WinHTTrack on your own machine, a
 <br><br><a NAME="QG2">Q: <strong>Where can I find French/other languages documentation?</strong></a><br>
 A: <em>Windows interface is available on several languages, but not yet the documentation!</em>

-<br><br><a NAME="QG3">Q: <strong>Which systems does HTTrack run on?</strong></a><br>
-A: <em>HTTrack runs on current Windows, Linux and other Unix-like systems, and macOS. Very old platforms such as Windows 95/98 are no longer supported; you may try an older release (such as 3.33) on those.</em>
+<br><br><a NAME="QG3b">Q: <strong>Is HTTrack working on Windows Vista/Windows Seven/Windows 8 ?</strong></a><br>
+A: <em>Yes, it does</em>
+
+<br><br><a NAME="QG3">Q: <strong>Is HTTrack working on Windows 95/98 ?</strong></a><br>
+A: <em>No, not anymore. You may try to pick an older release (such as 3.33)</em>

 <br><br><a NAME="QG4">Q: <strong>What's the difference between HTTrack, WinHTTrack and WebHTTrack?</strong></a><br>
 A: <em>WinHTTrack is the Windows GUI release of HTTrack (with a native graphic shell) and WebHTTrack is the Linux/Posix release of HTTrack (with an html graphic shell)</em>
@@ -389,7 +394,7 @@ A: <em>It should. The <tt>configure.ac</tt> may be modified in some cases, howev
 <br><br><a NAME="QG7">Q: <strong>I use HTTrack for professional purpose. What about restrictions/license fee?</strong></a><br>
 A: <em>HTTrack is covered by the GNU General Public License (GPL). There is no restrictions using HTTrack for professional purpose, 
 except if you develop a software which uses HTTrack components (parts of the source, or any other component).
-See the <tt>license.txt</tt> file for more information</em>. See also the next question regarding copyright issues when redistributing downloaded material.
+See the <tt>license.txt</tt> file for more information</em>. See also the next question regarding copyright issues when reditributing downloaded material.

 <br><br><a NAME="QG7b">Q: <strong>Is there any license royalties for distributing a mirror made with HTTrack?</strong></a><br>
 A: <em>On the HTTrack side, no. However, sharing, publishing or reusing copyrighted material downloaded from a site requires the authorization of the copyright holders, and possibly paying royalty fees. Always ask the authorization before creating a mirror of a site, even if the site appears to be royalty-free and/or without copyright notice.</em>
@@ -410,7 +415,7 @@ There are several reasons (and solutions) for a mirror to fail. Reading the log

 <ul>
 <li>Links within the site refers to external links, or links located in another (or upper) directories, not captured by default - the use of filters is generally THE solution, as this is one of the powerful option in HTTrack. <u>See the above questions/answers</u>.</li>
- <li>Website <a href="#Q1b1">'robots.txt' rules</a> forbid access to several website parts - you can disable them, but only with great care!</li>
+ <li>Website <a href="#Q1b1">'robots.txt' rules</a> forbide access to several website parts - you can disable them, but only with great care!</li>
 <li>HTTrack is filtered (by its default User-agent IDentity) - you can change the Browser User-Agent identity to an anonymous one (MSIE, Netscape..) - here again, use this option with care, as this measure might have been put to avoid some bandwidth abuse (see also the <a href="abuse.html">abuse faq</a>!)</li>
 </ul>

@@ -452,14 +457,14 @@ A: <em>Yes, HTTrack does support (since 3.20 release) ipv6 sites, using A/AAAA e
 A: <em>Check the build options (you may have selected user-defined structure with wrong parameters!)</em>

 <br><br><a NAME="QT5">Q: <strong>When capturing real audio/video links (.ram), I only get a shortcut!</a></strong></a></br>
-A: <em>The .ra/.rm associated file can be captured together with the shortcut, if proper filters are set. Streaming protocols such as rtsp:// are out of scope: HTTrack is an HTTP/FTP mirror and does not capture rtsp streams.</em>
+A: <em>Yes, but .ra/.rm associated file should be captured together - except if rtsp:// protocol is used (not supported by HTTrack yet), or if proper filters are needed</em>

 <br><br><a NAME="QT6">Q: <strong>Using user:password@address is not working!</a></strong></a></br>
 A: <em>Again, first check the <tt>hts-log.txt</tt> and <tt>hts-err.txt</tt> error log files - this can give you precious information<br>
 The site may have a different authentication scheme - form based authentication, for example.
 In this case, use the URL capture features of HTTrack, it might work.
 <br>Note: If your username and/or password contains a '<tt>@</tt>' character, you may have to replace all '<tt>@</tt>' 
-occurrences by '<tt>%40</tt>' so that it can work, such as in <tt>user%40domain.com:foobar@www.foo.com/auth/. 
+occurences by '<tt>%40</tt>' so that it can work, such as in <tt>user%40domain.com:foobar@www.foo.com/auth/. 
 You may have to do the same for all "special" characters like spaces (%20), quotes (%22)..</tt>
 </em>
 <br><br>
@@ -515,7 +520,7 @@ These rules, stored in a file called robots.txt, are given by the website, to sp
 - for example, /cgi-bin or large images files.
 They are followed by default by HTTrack, as it is advised. Therefore, you may miss some files that would have been downloaded without
 these rules - check in your logs if it is the case:<br>
-<tt>Info: Note: due to www.foobar.com remote robots.txt rules, links beginning with these path will be forbidden: /cgi-bin/,/images/ (see in the options to disable this)
+<tt>Info: Note: due to www.foobar.com remote robots.txt rules, links begining with these path will be forbidden: /cgi-bin/,/images/ (see in the options to disable this)
 </tt>
 <br>
 If you want to disable them, just change the corresponding option in the option list! (but only disable this option with great care, 
@@ -535,7 +540,7 @@ HTTrack must find one. Therefore, two index.html will be produced, one with the
 <br>
 It might be a good idea to consider that http://www.foobar.com/ and http://www.foobar.com/index.html are the same links, to avoid
 duplicate files, isn't it?
-NO, because the top index (/) can refer to ANY filename, and if index.html is generally the default name, index.htm can be chosen,
+NO, because the top index (/) can refer to ANY filename, and if index.html is generally the default name, index.htm can be choosen,
 or index.php3, mydog.jpg, or anything you may imagine. (some webmasters are really crazy)
 <br>
 <br>
@@ -590,7 +595,8 @@ A: <em>Simply use the <tt>--assume dat=application/x-zip</tt> option
 A: <em>You may need cookies! Cookies are specific data (for example, your username or password) that are sent to your browser once
 you have logged in certain sites so that you only have to log-in once. For example, after having entered your username in a website, you can
 view pages and articles, and the next time you will go to this site, you will not have to re-enter your username/password.<br>
-To supply your own cookies to an HTTrack project, put a Netscape-format <tt>cookies.txt</tt> file in your project folder, or point HTTrack at one with the <tt>--cookies-file</tt> option. You can export your browser's session cookies to that format with a browser extension.
+To "merge" your personnal cookies to an HTTrack project, just copy the cookies.txt file from your Netscape folder (or the cookies located into the Temporary Internet Files folder for IE)
+into your project folder (or even the HTTrack folder)
 </em>
 <br>
 <br>
@@ -655,7 +661,7 @@ Shell version, skip some slow files, too.</em><br>

 </a><a NAME="Q3b">Q: <strong>I want to update a site, but it's taking too much time! What's happening?</strong><br>
 A: <em>First, HTTrack always tries to minimize the download flow by interrogating the server about the
-file changes. But, because HTTrack has to rescan all files from the beginning to rebuild the local site structure, 
+file changes. But, because HTTrack has to rescan all files from the begining to rebuild the local site structure, 
 it can take some time. 
 Besides, some servers are not very smart and always consider that they get newer files, forcing HTTrack to reload them,
 even if no changes have been made!
@@ -734,7 +740,7 @@ retransferred.</em><br>
 </a><a NAME="Q7">Q: <strong>I just want to retrieve all ZIP files or other files in a web
 site/in a page. How do I do it?</strong><br>
 A: <em>You can use different methods. You can use the 'get files near a link' option if
-files are in a foreign domain. You can use, too, a filter address: adding <tt>+*.zip</tt>
+files are in a foreign domain. You can use, too, a filter adress: adding <tt>+*.zip</tt>
 in the URL list (or in the filter list) will accept all ZIP files, even if these files are
 outside the address. <br>
 Example : <tt>httrack www.example.com/someaddress.html +*.zip</tt> will allow
--- a/html/httrack.man.html
+++ b/html/httrack.man.html
--- a/man/Makefile.am
+++ b/man/Makefile.am
@@ -16,11 +16,6 @@ regen-man: makeman.sh $(top_builddir)/src/httrack$(EXEEXT)

 # Render html/httrack.man.html from httrack.1. Needs the groff html device
 # (Debian: full "groff" package, not "groff-base"). Run by hand: make -C man regen-man-html
-# Strip groff's version-stamp and creation-date comments so the committed file
-# doesn't churn across groff versions or rebuilds; the ci man-page-sync guard
-# only requires this file to change whenever httrack.1 does.
 regen-man-html: httrack.1
-	groff -t -man -Thtml $(srcdir)/httrack.1 \
-		| sed -e 's/groff version [0-9][0-9.]*/groff/' -e '/^<!-- CreationDate:/d' \
-		> $(top_srcdir)/html/httrack.man.html
+	groff -t -man -Thtml $(srcdir)/httrack.1 > $(top_srcdir)/html/httrack.man.html
 .PHONY: regen-man-html
--- a/src/htsback.c
+++ b/src/htsback.c
@@ -1617,15 +1617,14 @@ int back_add_if_not_exists(struct_back * sback, httrackp * opt,
  back_clean(opt, cache, sback);        /* first cleanup the backlog to ensure that we have some entry left */
  if (!back_exist(sback, opt, adr, fil, save)) {
    return back_add(sback, opt, cache, adr, fil, save, referer_adr, referer_fil,
-                    test, HTS_FALSE);
+                    test);
  }
  return 0;
 }

-int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
-             const char *adr, const char *fil, const char *save,
-             const char *referer_adr, const char *referer_fil, int test,
-             hts_boolean refetch_whole) {
+int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char *adr,
+             const char *fil, const char *save, const char *referer_adr, const char *referer_fil,
+             int test) {
  lien_back *const back = sback->lnk;
  const int back_max = sback->count;
  int p = 0;
@@ -1702,12 +1701,6 @@ int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
    else if (strcmp(back[p].url_sav, BACK_ADD_TEST2) == 0)      // test en GET
      back[p].head_request = 2; // test en get

-    /* Forced whole refetch (#581): drop the stale temp-ref and skip the resume
-       branches below, so a surviving partial can't Range-loop. */
-    if (refetch_whole) {
-      url_savename_refname_remove(opt, adr, fil);
-    }
-
    /* Stop requested - abort backing */
    /* For update mode: second check after cache lookup not to lose all previous cache data ! */
    if (opt->state.stop && !opt->is_update) {
@@ -1963,9 +1956,8 @@ int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
        }
      }
      /* Not in cache ; maybe in temporary cache ? Warning: non-movable
-         "url_sav" (skipped on a forced whole refetch, #581) */
-      else if (!refetch_whole &&
-               back_unserialize_ref(opt, adr, fil, &itemback) == 0) {
+         "url_sav" */
+      else if (back_unserialize_ref(opt, adr, fil, &itemback) == 0) {
        const LLint file_size = fsize_utf8(itemback->url_sav);

        /* Found file on disk */
@@ -1999,9 +1991,8 @@ int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
        freet(itemback);        /* delete item */
        itemback = NULL;
      }
-      /* Not in cache or temporary cache ; found on disk ? (hack)
-         (skipped on a forced whole refetch, #581) */
-      else if (!refetch_whole && fexist_utf8(save)) {
+      /* Not in cache or temporary cache ; found on disk ? (hack) */
+      else if (fexist_utf8(save)) {
        const LLint sz = fsize_utf8(save);

        // Bon, là il est possible que le fichier ait été partiellement transféré
@@ -3856,8 +3847,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                    deletehttp(&back[i].r);
                    back[i].r.soc = INVALID_SOCKET;
                    back[i].r.statuscode = STATUSCODE_NON_FATAL;
-                    back[i].r.refetch_wholefile =
-                        HTS_TRUE; // retry whole, no Range (#581)
                    strcpybuff(back[i].r.msg,
                               "Bogus 304 on resume, restarting");
                    back[i].status = STATUS_READY;
@@ -4129,9 +4118,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                        }
                        back[i].r.soc = INVALID_SOCKET;
                        back[i].r.statuscode = STATUSCODE_NON_FATAL;
-                        // the resume was rejected: the retry must GET the whole
-                        // file, never re-Range a surviving partial/ref (#581)
-                        back[i].r.refetch_wholefile = HTS_TRUE;
                        if (strnotempty(back[i].r.msg))
                          strcpybuff(back[i].r.msg,
                                     "Error attempting to solve status 206 (partial file)");
--- a/src/htsback.h
+++ b/src/htsback.h
@@ -83,12 +83,9 @@ HTS_INLINE int back_exist(struct_back * sback, httrackp * opt, const char *adr,
                          const char *fil, const char *sav);
 int back_nsoc(const struct_back * sback);
 int back_nsoc_overall(const struct_back * sback);
-/* refetch_whole: force a whole-file GET, ignoring any partial/temp-ref resume
-   (set when a prior 206 was rejected as unusable, #581). */
-int back_add(struct_back *sback, httrackp *opt, cache_back *cache,
-             const char *adr, const char *fil, const char *save,
-             const char *referer_adr, const char *referer_fil, int test,
-             hts_boolean refetch_whole);
+int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char *adr,
+             const char *fil, const char *save, const char *referer_adr, const char *referer_fil,
+             int test);
 int back_add_if_not_exists(struct_back * sback, httrackp * opt,
                           cache_back * cache, const char *adr, const char *fil, const char *save,
                           const char *referer_adr, const char *referer_fil, int test);
--- a/src/htscache.c
+++ b/src/htscache.c
@@ -856,41 +856,7 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
 // si save==null alors test unqiquement
 static int hts_rename(httrackp * opt, const char *a, const char *b) {
  hts_log_print(opt, LOG_DEBUG, "Cache: rename %s -> %s (%p %p)", a, b, a, b);
-  return RENAME(a, b);
-}
-
-/* Open the cache ZIP via hts_fopen_utf8 so a non-ASCII path_log isn't mangled
-   to ANSI (#630); 64-bit funcs keep multi-GB caches whole on Windows LLP64. */
-static voidpf ZCALLBACK hts_zip_fopen_utf8(voidpf opaque, const void *filename,
-                                           int mode) {
-  const char *mode_fopen = NULL;
-
-  (void) opaque;
-  if ((mode & ZLIB_FILEFUNC_MODE_READWRITEFILTER) == ZLIB_FILEFUNC_MODE_READ)
-    mode_fopen = "rb";
-  else if (mode & ZLIB_FILEFUNC_MODE_EXISTING)
-    mode_fopen = "r+b";
-  else if (mode & ZLIB_FILEFUNC_MODE_CREATE)
-    mode_fopen = "wb";
-  if (filename == NULL || mode_fopen == NULL)
-    return NULL;
-  return (voidpf) FOPEN((const char *) filename, mode_fopen);
-}
-
-static unzFile hts_unzOpen_utf8(const char *path) {
-  zlib_filefunc64_def ff;
-
-  fill_fopen64_filefunc(&ff);
-  ff.zopen64_file = hts_zip_fopen_utf8;
-  return unzOpen2_64(path, &ff);
-}
-
-static zipFile hts_zipOpen_utf8(const char *path, int append) {
-  zlib_filefunc64_def ff;
-
-  fill_fopen64_filefunc(&ff);
-  ff.zopen64_file = hts_zip_fopen_utf8;
-  return zipOpen2_64(path, append, NULL, &ff);
+  return rename(a, b);
 }

 /* Pathname of a file inside the mirror dir (rotating concat buffer). */
@@ -908,9 +874,9 @@ static char *reconcile_path(httrackp *opt, const char *name) {
 /* Replace the new-generation file by the old one, when the old one exists. */
 static void reconcile_promote(httrackp *opt, const char *oldname,
                              const char *newname) {
-  if (fexist_utf8(reconcile_path(opt, oldname))) {
-    UNLINK(reconcile_path(opt, newname));
-    RENAME(reconcile_path(opt, oldname), reconcile_path(opt, newname));
+  if (fexist(reconcile_path(opt, oldname))) {
+    remove(reconcile_path(opt, newname));
+    rename(reconcile_path(opt, oldname), reconcile_path(opt, newname));
  }
 }

@@ -919,7 +885,7 @@ void hts_cache_reconcile(httrackp *opt, hts_cache_reconcile_mode mode) {
  case CACHE_RECONCILE_PROMOTE:
    /* Previous run rotated new.* to old.* then died before writing: promote
       the old generation back, whichever format it uses. */
-    if (!fexist_utf8(reconcile_path(opt, "hts-cache/new.zip")))
+    if (!fexist(reconcile_path(opt, "hts-cache/new.zip")))
      reconcile_promote(opt, "hts-cache/old.zip", "hts-cache/new.zip");
    break;
  case CACHE_RECONCILE_INTERRUPTED:
@@ -928,17 +894,16 @@ void hts_cache_reconcile(httrackp *opt, hts_cache_reconcile_mode mode) {
       is -1 for a missing file, which would spuriously pass the "< TINY" test
       and overwrite a solid old generation that PROMOTE/ROLLBACK should keep.
     */
-    if (!opt->cache ||
-        !fexist_utf8(reconcile_path(opt, "hts-in_progress.lock")))
+    if (!opt->cache || !fexist(reconcile_path(opt, "hts-in_progress.lock")))
      break;
-    if (fexist_utf8(reconcile_path(opt, "hts-cache/new.zip")) &&
-        fexist_utf8(reconcile_path(opt, "hts-cache/old.zip")) &&
-        fsize_utf8(reconcile_path(opt, "hts-cache/new.zip")) <
+    if (fexist(reconcile_path(opt, "hts-cache/new.zip")) &&
+        fexist(reconcile_path(opt, "hts-cache/old.zip")) &&
+        fsize(reconcile_path(opt, "hts-cache/new.zip")) <
            CACHE_RECONCILE_NEW_TINY &&
-        fsize_utf8(reconcile_path(opt, "hts-cache/old.zip")) >
+        fsize(reconcile_path(opt, "hts-cache/old.zip")) >
            CACHE_RECONCILE_OLD_SOLID &&
-        fsize_utf8(reconcile_path(opt, "hts-cache/old.zip")) >
-            fsize_utf8(reconcile_path(opt, "hts-cache/new.zip")))
+        fsize(reconcile_path(opt, "hts-cache/old.zip")) >
+            fsize(reconcile_path(opt, "hts-cache/new.zip")))
      reconcile_promote(opt, "hts-cache/old.zip", "hts-cache/new.zip");
    break;
  case CACHE_RECONCILE_ROLLBACK:
@@ -975,26 +940,24 @@ void cache_init(cache_back * cache, httrackp * opt) {
 #endif
    if (!cache->ro) {
 #ifdef _WIN32
-      /* Windows mkdir takes no mode; use the UTF-8 wrapper for #630. */
-      MKDIR(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                    StringBuff(opt->path_log), "hts-cache"));
+      mkdir(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache"));
 #else
-      /* keep the cache dir 0700, not MKDIR's 0755. */
-      mkdir(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                    StringBuff(opt->path_log), "hts-cache"),
+      mkdir(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache"),
            HTS_PROTECT_FOLDER);
 #endif
-      if ((fexist_utf8(fconcat(
+      if ((fexist(fconcat(
              OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
              StringBuff(opt->path_log),
              "hts-cache/new.zip")))) { // a previous cache exists.. rename it
        /* Remove OLD cache */
-        if (fexist_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                                StringBuff(opt->path_log),
-                                "hts-cache/old.zip"))) {
-          if (UNLINK(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                             StringBuff(opt->path_log), "hts-cache/old.zip")) !=
-              0) {
+        if (fexist
+            (fconcat
+             (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+              "hts-cache/old.zip"))) {
+          if (remove
+              (fconcat
+               (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                "hts-cache/old.zip")) != 0) {
            hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
                          "Cache: error while moving previous cache");
          }
@@ -1017,27 +980,33 @@ void cache_init(cache_back * cache, httrackp * opt) {
      hts_log_print(opt, LOG_DEBUG, "Cache: no cache found");
    }
    hts_log_print(opt, LOG_DEBUG, "Cache: size %d",
-                  (int) fsize_utf8(
-                      fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                              StringBuff(opt->path_log), "hts-cache/old.zip")));
+                  (int)
+                  fsize(fconcat
+                        (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                         "hts-cache/old.zip")));

    // charger index cache précédent
-    if ((!cache->ro &&
-         fsize_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                            StringBuff(opt->path_log), "hts-cache/old.zip")) >
-             0) ||
-        (cache->ro &&
-         fsize_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                            StringBuff(opt->path_log), "hts-cache/new.zip")) >
-             0)) {
+    if ((!cache->ro
+         &&
+         fsize(fconcat
+               (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                "hts-cache/old.zip")) > 0)
+        || (cache->ro
+            &&
+            fsize(fconcat
+                  (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                   "hts-cache/new.zip")) > 0)
+      ) {
      if (!cache->ro) {
-        cache->zipInput = hts_unzOpen_utf8(
-            fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                    StringBuff(opt->path_log), "hts-cache/old.zip"));
+        cache->zipInput =
+          unzOpen(fconcat
+                  (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                   "hts-cache/old.zip"));
      } else {
-        cache->zipInput = hts_unzOpen_utf8(
-            fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                    StringBuff(opt->path_log), "hts-cache/new.zip"));
+        cache->zipInput =
+          unzOpen(fconcat
+                  (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                   "hts-cache/new.zip"));
      }

      // Corrupted ZIP file ? Try to repair!
@@ -1057,8 +1026,6 @@ void cache_init(cache_back * cache, httrackp * opt) {
        }
        hts_log_print(opt, LOG_WARNING,
                      "Cache: damaged cache, trying to repair");
-        /* mztools has no UTF-8 hook, so repairing a corrupt cache under a
-           non-ASCII path_log fails cleanly (re-crawl), never forks a twin. */
        if (unzRepair
            (name,
             fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
@@ -1066,11 +1033,11 @@ void cache_init(cache_back * cache, httrackp * opt) {
                                                      StringBuff(opt->path_log),
                                                      "hts-cache/repair.tmp"),
             &repaired, &repairedBytes) == Z_OK) {
-          UNLINK(name);
-          RENAME(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                         StringBuff(opt->path_log), "hts-cache/repair.zip"),
-                 name);
-          cache->zipInput = hts_unzOpen_utf8(name);
+          unlink(name);
+          rename(fconcat
+                 (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                  "hts-cache/repair.zip"), name);
+          cache->zipInput = unzOpen(name);
          hts_log_print(opt, LOG_WARNING,
                        "Cache: %d bytes successfully recovered in %d entries",
                        (int) repairedBytes, (int) repaired);
@@ -1166,8 +1133,8 @@ void cache_init(cache_back * cache, httrackp * opt) {
                      "Cache: error trying to open the cache");
      }

-    } else if (fsize_utf8(reconcile_path(opt, "hts-cache/old.ndx")) > 0 ||
-               fsize_utf8(reconcile_path(opt, "hts-cache/new.ndx")) > 0) {
+    } else if (fsize(reconcile_path(opt, "hts-cache/old.ndx")) > 0 ||
+               fsize(reconcile_path(opt, "hts-cache/new.ndx")) > 0) {
      /* pre-3.31 (2003) .dat/.ndx cache: import support removed */
      hts_log_print(opt, LOG_ERROR,
                    "Cache: the pre-3.31 .dat/.ndx cache format is no longer "
@@ -1183,58 +1150,67 @@ void cache_init(cache_back * cache, httrackp * opt) {
 #endif
    if (!cache->ro) {
      // ouvrir caches actuels
-      structcheck_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                               StringBuff(opt->path_log), "hts-cache/"));
+      structcheck(fconcat
+                  (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log), "hts-cache/"));

      {
        /* Create ZIP file cache */
-        cache->zipOutput = (void *) hts_zipOpen_utf8(
-            fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                    StringBuff(opt->path_log), "hts-cache/new.zip"),
-            0);
+        cache->zipOutput =
+          (void *)
+          zipOpen(fconcat
+                  (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                   "hts-cache/new.zip"), 0);

        if (cache->zipOutput != NULL) {
          // supprimer old.lst
-          if (fexist_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                                  StringBuff(opt->path_log),
-                                  "hts-cache/old.lst")))
-            UNLINK(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                           StringBuff(opt->path_log), "hts-cache/old.lst"));
+          if (fexist
+              (fconcat
+               (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                "hts-cache/old.lst")))
+            remove(fconcat
+                   (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                    "hts-cache/old.lst"));
          // renommer
-          if (fexist_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                                  StringBuff(opt->path_log),
-                                  "hts-cache/new.lst")))
-            RENAME(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                           StringBuff(opt->path_log), "hts-cache/new.lst"),
-                   fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                           StringBuff(opt->path_log), "hts-cache/old.lst"));
+          if (fexist
+              (fconcat
+               (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                "hts-cache/new.lst")))
+            rename(fconcat
+                   (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                    "hts-cache/new.lst"), fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                                                  StringBuff(opt->path_log),
+                                                  "hts-cache/old.lst"));
          // ouvrir
          cache->lst =
-              FOPEN(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                            StringBuff(opt->path_log), "hts-cache/new.lst"),
-                    "wb");
+            fopen(fconcat
+                  (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                   "hts-cache/new.lst"), "wb");
          strcpybuff(opt->state.strc.path, StringBuff(opt->path_html));
          opt->state.strc.lst = cache->lst;

          // supprimer old.txt
-          if (fexist_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                                  StringBuff(opt->path_log),
-                                  "hts-cache/old.txt")))
-            UNLINK(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                           StringBuff(opt->path_log), "hts-cache/old.txt"));
+          if (fexist
+              (fconcat
+               (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                "hts-cache/old.txt")))
+            remove(fconcat
+                   (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                    "hts-cache/old.txt"));
          // renommer
-          if (fexist_utf8(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                                  StringBuff(opt->path_log),
-                                  "hts-cache/new.txt")))
-            RENAME(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                           StringBuff(opt->path_log), "hts-cache/new.txt"),
-                   fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                           StringBuff(opt->path_log), "hts-cache/old.txt"));
+          if (fexist
+              (fconcat
+               (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                "hts-cache/new.txt")))
+            rename(fconcat
+                   (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                    "hts-cache/new.txt"), fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
+                                                  StringBuff(opt->path_log),
+                                                  "hts-cache/old.txt"));
          // ouvrir
          cache->txt =
-              FOPEN(fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                            StringBuff(opt->path_log), "hts-cache/new.txt"),
-                    "wb");
+            fopen(fconcat
+                  (OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), StringBuff(opt->path_log),
+                   "hts-cache/new.txt"), "wb");
          if (cache->txt) {
            fprintf(cache->txt,
                    "date\tsize'/'remotesize\tflags(request:Update,Range state:File response:Modified,Chunked,gZipped)\t");
--- a/src/htscore.c
+++ b/src/htscore.c
@@ -3293,10 +3293,10 @@ int back_fill(struct_back * sback, httrackp * opt, cache_back * cache,
      if (ok) {
        if (!back_exist
            (sback, opt, heap(p)->adr, heap(p)->fil, heap(p)->sav)) {
-          if (back_add(sback, opt, cache, heap(p)->adr, heap(p)->fil,
-                       heap(p)->sav, heap(heap(p)->precedent)->adr,
-                       heap(heap(p)->precedent)->fil, heap(p)->testmode,
-                       heap(p)->refetch_whole) == -1) {
+          if (back_add
+              (sback, opt, cache, heap(p)->adr, heap(p)->fil, heap(p)->sav,
+               heap(heap(p)->precedent)->adr, heap(heap(p)->precedent)->fil,
+               heap(p)->testmode) == -1) {
            hts_log_print(opt, LOG_DEBUG,
                          "error: unable to add more links through back_add for back_fill");
 #if BDEBUG==1
--- a/src/htsname.c
+++ b/src/htsname.c
@@ -615,9 +615,9 @@ int url_savename(lien_adrfilsave *const afs,
            strcpybuff(current.fil, fil_complete);
            // ajouter dans le backing le fichier en mode test
            // savename: rien car en mode test
-            if (back_add(sback, opt, cache, current.adr, current.fil,
-                         BACK_ADD_TEST, referer_adr, referer_fil, 1,
-                         HTS_FALSE) != -1) {
+            if (back_add
+                (sback, opt, cache, current.adr, current.fil, BACK_ADD_TEST,
+                 referer_adr, referer_fil, 1) != -1) {
              int b;

              b = back_index(opt, sback, current.adr, current.fil, BACK_ADD_TEST);
@@ -706,10 +706,7 @@ int url_savename(lien_adrfilsave *const afs,
                                if (!hts_wait_available_socket(sback, opt,
                                                               cache, ptr))
                                  return -1;
-                                if (back_add(sback, opt, cache, moved.adr,
-                                             moved.fil, methode, referer_adr,
-                                             referer_fil, 1,
-                                             HTS_FALSE) != -1) { // OK
+                                if (back_add(sback, opt, cache, moved.adr, moved.fil, methode, referer_adr, referer_fil, 1) != -1) {        // OK
                                  hts_log_print(opt, LOG_DEBUG,
                                                "(during prefetch) %s (%d) to link %s at %s%s",
                                                back[b].r.msg,
@@ -728,8 +725,7 @@ int url_savename(lien_adrfilsave *const afs,
                                    has_been_moved = 1; // sinon ne pas forcer has_been_moved car non déplacé
                                  petits_tours++;
                                  //
-                                } else { // sinon on fait rien et on s'en va..
-                                         // (ftp etc)
+                                } else {        // sinon on fait rien et on s'en va.. (ftp etc)
                                  hts_log_print(opt, LOG_DEBUG,
                                                "Warning: Savename redirect backing error at %s%s",
                                                moved.adr, moved.fil);
@@ -800,6 +796,7 @@ int url_savename(lien_adrfilsave *const afs,
              hts_log_print(opt, LOG_ERROR,
                            "Unexpected savename backing error at %s%s", adr,
                            fil_complete);
+
            }
            // restaurer
            opt->state._hts_in_html_parsing = hihp;
--- a/src/htsopt.h
+++ b/src/htsopt.h
@@ -658,9 +658,6 @@ struct htsblk {
  int debugid;           /**< connection debug id */
  /* */
  htsrequest req; /**< parameters used for the request */
-  /* Restart-whole signal: a resume this response rejected (unusable 206) must
-     retry with no Range, else a surviving partial/temp-ref loops (#581). */
-  hts_boolean refetch_wholefile;
  /*char digest[32+2];   // md5 digest generated by the engine ("" if none) */
 };

@@ -684,9 +681,6 @@ struct lien_url {
  char link_import; /**< imported after a move; skip the usual up/down rules */
  int retry;    /**< remaining retries */
  int testmode; /**< test only: send just a HEAD */
-  hts_boolean
-      refetch_whole; /**< force a whole-file GET, ignoring any partial/temp-ref
-                   resume, so a rejected 206 can't loop (#581) */
 };

 /* A file being fetched in the background. */
--- a/src/htsparse.c
+++ b/src/htsparse.c
@@ -315,18 +315,9 @@ static void escape_url_parens(char *const s, const size_t size) {
  strlcpybuff(s, buff, size);
 }

-/* Default port for lien's scheme (case-insensitive), 80 if absent/unknown; so
-   schemeless and protocol-relative //host links default to 80 (known gap). */
-static int scheme_default_port(const char *lien) {
-  if (strfield(lien, "https:"))
-    return 443;
-  if (strfield(lien, "ftp:"))
-    return 21;
-  return 80;
-}
-
-/* Strip the scheme's own default port (80 http, 443 https, 21 ftp) from lien's
-   authority in place; :80 on https/ftp stays as a real port (#638, #614). */
+/* Strip a default ":80" from lien's authority in place. Any spelling that
+   range-parses to 80 (":80", ":080") is dropped by its matched length, not a
+   hardcoded 3 chars; a value that merely wraps to 80 as an int (#614) stays. */
 void hts_strip_default_port(char *lien, size_t size) {
  char *a;

@@ -348,8 +339,7 @@ void hts_strip_default_port(char *lien, size_t size) {
      b++;
    saved = *b;
    *b = '\0';
-    is_default =
-        hts_parse_url_port(a + 1, &port) && port == scheme_default_port(lien);
+    is_default = hts_parse_url_port(a + 1, &port) && port == 80;
    *b = saved;
    if (is_default) { // default port, strip it
      char BIGSTK tempo[HTS_URLMAXSIZE * 2];
@@ -3756,9 +3746,6 @@ int hts_mirror_check_moved(htsmoduleStruct * str,
            heap_top()->retry = heap(ptr)->retry - 1;     // moins 1 retry!
            heap_top()->premier = heap(ptr)->premier;
            heap_top()->precedent = heap(ptr)->precedent;
-            // a rejected resume (unusable 206) must refetch whole, no Range
-            // (#581)
-            heap_top()->refetch_whole = r->refetch_wholefile;
          } else {              // oups erreur, plus de mémoire!!
            return 0;
          }
@@ -3990,17 +3977,18 @@ int hts_mirror_wait_for_next_file(htsmoduleStruct * str,
 #if BDEBUG==1
    printf("crash backing: %s%s\n", heap(ptr)->adr, heap(ptr)->fil);
 #endif
-    if (back_add(sback, opt, cache, urladr(), urlfil(), savename(),
-                 heap(heap(ptr)->precedent)->adr,
-                 heap(heap(ptr)->precedent)->fil, heap(ptr)->testmode,
-                 heap(ptr)->refetch_whole) == -1) {
+    if (back_add
+        (sback, opt, cache, urladr(), urlfil(), savename(),
+         heap(heap(ptr)->precedent)->adr, heap(heap(ptr)->precedent)->fil,
+         heap(ptr)->testmode) == -1) {
      printf("PANIC! : Crash adding error, unexpected error found.. [%d]\n",
             __LINE__);
 #if BDEBUG==1
      printf("error while crash adding\n");
 #endif
-      hts_log_print(opt, LOG_ERROR, "Unexpected backing error for %s%s",
-                    urladr(), urlfil());
+      hts_log_print(opt, LOG_ERROR, "Unexpected backing error for %s%s", urladr(),
+                    urlfil());
+
    }
  }
 #if BDEBUG==1
--- a/src/htsselftest.c
+++ b/src/htsselftest.c
@@ -1589,8 +1589,10 @@ static int st_identabs(httrackp *opt, int argc, char **argv) {
  return 0;
 }

-/* Default-port strip is scheme-aware (#638), overflow-safe (#614): a scheme's
-   own default (any spelling) is dropped, a real port stays; guards #627. */
+/* Default-port strip (#627): a genuine 80 (any spelling) is removed by its
+   matched length, host preserved; a non-80 port or one that only wraps to 80 as
+   a 32-bit int (#614) is left intact. Guards the old bug where ":080"/":0080"
+   dropped a hardcoded 3 chars and glued the leftover digits onto the host. */
 static int st_stripport(httrackp *opt, int argc, char **argv) {
  static const struct {
    const char *in, *out;
@@ -1604,13 +1606,6 @@ static int st_stripport(httrackp *opt, int argc, char **argv) {
      {"http://127.0.0.1:8080/x", "http://127.0.0.1:8080/x"},
      {"http://127.0.0.1:4294967376/x", "http://127.0.0.1:4294967376/x"},
      {"http://127.0.0.1/x", "http://127.0.0.1/x"},
-      {"https://127.0.0.1:443/x", "https://127.0.0.1/x"},
-      {"https://127.0.0.1:80/x", "https://127.0.0.1:80/x"},
-      // Scheme match is case-insensitive: HTTPS' default is 443, so :80 stays.
-      {"HTTPS://127.0.0.1:80/x", "HTTPS://127.0.0.1:80/x"},
-      {"ftp://127.0.0.1:21/x", "ftp://127.0.0.1/x"},
-      {"ftp://127.0.0.1:80/x", "ftp://127.0.0.1:80/x"},
-      {"http://127.0.0.1:443/x", "http://127.0.0.1:443/x"},
  };

  size_t k;
--- a/src/minizip/mztools.c.diff
+++ b/src/minizip/mztools.c.diff
@@ -1,6 +1,6 @@
 --- mztools.c.orig	2024-01-27 14:07:18.636193212 +0100
 +++ mztools.c	2024-01-27 14:09:55.356620093 +0100
-@@ -10,10 +10,11 @@
+@@ -10,6 +10,7 @@
 #include <string.h>
 #include "zlib.h"
 #include "unzip.h"
@@ -8,11 +8,6 @@
 
 #define READ_8(adr)  ((unsigned char)*(adr))
 #define READ_16(adr) ( READ_8(adr) | (READ_8(adr+1) << 8) )
-#define READ_32(adr) ( READ_16(adr) | (READ_16((adr)+2) << 16) )
-+#define READ_32(adr) ((uLong) READ_16(adr) | ((uLong) READ_16((adr) + 2) << 16))
- 
- #define WRITE_8(buff, n) do { \
-   *((unsigned char*)(buff)) = (unsigned char) ((n) & 0xff); \
@@ -141,8 +142,8 @@
         /* Central directory entry */
         {
--- a/tests/66_engine-port80-strip.test
+++ b/tests/66_engine-port80-strip.test
@@ -6,7 +6,6 @@ set -euo pipefail
 # Stripping a default :80 from a crawled link used to skip a hardcoded 3 chars
 # (#627): ":080"/":0080" lost only ":80" and glued the rest onto the host
 # (127.0.0.1:080/x -> 127.0.0.10/x), and a value wrapping to 80 as a 32-bit int
-# (#614) was stripped as if it were the default. The default is scheme-aware
-# (#638): an explicit :80 on https/ftp stays, :443/:21 strip under their own
-# scheme. All assertions live in the engine self-test.
+# (#614) was stripped as if it were the default. All assertions live in the
+# engine self-test.
 httrack -O /dev/null -#test=stripport | grep -q "stripport self-test OK"
--- a/tests/69_local-intl-logdir.test
+++ b/tests/69_local-intl-logdir.test
@@ -1,17 +1,15 @@
 #!/bin/bash
 #
 # A single non-ASCII -O sets both path_html and path_log to "café" (#630). The
-# logs (hts-log.txt/hts-err.txt) and the hts-cache must land there, not in an
-# ANSI-mangled twin: on Windows path_log holds UTF-8 bytes the raw file calls
-# read as the codepage. The --log-found audit greps logroot=café/hts-log.txt and
-# --cache-under-logroot checks café/hts-cache/new.zip, so anything written to the
-# twin fails them. POSIX has no twin, so this bites on the Windows CI leg (test
-# 64), exercising only the code path elsewhere.
+# logs (hts-log.txt/hts-err.txt) must land there, not in an ANSI-mangled twin:
+# on Windows path_log holds UTF-8 bytes the raw file calls read as the codepage.
+# The --errors/--files/--log-found audits all grep logroot=café/hts-log.txt, so
+# a log written to the twin fails them. POSIX has no twin, so this bites on the
+# Windows CI leg (like test 64). The cache twin is a separate, larger fix.

 : "${top_srcdir:=..}"

 bash "$top_srcdir/tests/local-crawl.sh" --outdir-intl 'café' --errors 0 --files 5 \
    --found 'simple/basic.html' \
    --log-found 'mirror complete in' \
-    --cache-under-logroot \
    httrack 'BASEURL/simple/basic.html'
--- a/tests/71_local-crange-repaircache.test
+++ b/tests/71_local-crange-repaircache.test
@@ -16,12 +16,11 @@ root=$(nativepath "${testdir}/server-root")

 python=$(find_python) || ! echo "python3 not found; skipping" >&2 || exit 77

-# Windows-only repro of #581 (a hard-killed pass 1 + repaired cache loses the
-# file). The engine now forces a no-Range whole refetch on the restart, but that
-# fix is unverified on Windows CI, and this test's pass-1 interrupt/port-race
-# behavior there is unconfirmed; lift this skip on a Windows runner to verify.
+# On Windows the pass-1 interrupt is a hard kill (MSYS can't signal a native
+# exe) and the restart-whole path fails on the repaired cache (#581) -- the very
+# bug this exercises; skip until the engine fix lands.
 if is_windows; then
-    echo "Windows: #581 fix unverified on CI, skipping"
+    echo "Windows: restart-whole fails on a repaired cache (#581), skipping"
    exit 77
 fi

--- a/tests/local-crawl.sh
+++ b/tests/local-crawl.sh
@@ -118,9 +118,6 @@ while test "$pos" -lt "$nargs"; do
        nopurge=1
        audit+=("--no-purge")
        ;;
-    --cache-under-logroot)
-        audit+=("--cache-under-logroot")
-        ;;
    --tls)
        tls=1
        scheme=https
@@ -382,15 +379,6 @@ while test "$i" -lt "${#audit[@]}"; do
            sed -e 's/.*[[:space:]]\([^ ]*\)[[:space:]]files written.*/\1/g')
        assert_equals "checking files" "${audit[$i]}" "$nFiles"
        ;;
-    --cache-under-logroot)
-        # The cache must sit under path_log (logroot), not an ANSI-mangled twin
-        # of a non-ASCII -O dir (#630 cache half). Bites only on the Windows leg.
-        info "checking cache under logroot"
-        if test -e "${logroot}/hts-cache/new.zip"; then result "OK"; else
-            result "cache not under logroot (mangled twin?)"
-            exit 1
-        fi
-        ;;
    --found)
        i=$((i + 1))
        info "checking for ${audit[$i]}"