Add HTTRACK_DEBUG_RESOLVE and a deterministic connect-fallback test

Exercising the connect fallback needs a host that resolves to a dead address
first and a live one next, deterministically and offline. A true SYN
black-hole can't be simulated without root, but a refused address can.

HTTRACK_DEBUG_RESOLVE="host:ip[,ip...]" pins a host's resolution to a fixed
address list (curl --resolve style), reusing the PR1 resolver seam: an
addrinfo backend that synthesizes the listed addresses for the named host and
delegates other hosts to libc (copying into its own allocations so one
freeaddrinfo frees both). It is a debug/test hook, inert unless the env var is
set, and IPv6-build-only like the rest of the resolver list.

The new local crawl test binds the server to 127.0.0.1 and resolves a host to
127.0.0.2 (refused) then 127.0.0.1: the mirror only succeeds via the fallback.
A V6_SUPPORT substitution (mirroring HTTPS_SUPPORT) lets it skip on non-IPv6
builds.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

.github/workflows/ci.yml

@@ -232,42 +232,30 @@ jobs:
   deb:
     name: deb package (lintian)
     runs-on: ubuntu-24.04
-    # Build and gate inside Debian sid, the upload target. A Debian dpkg-deb
-    # produces archive-legal xz members (an Ubuntu host defaults to zstd, which
-    # the archive's lintian rejects), and sid's lintian carries the same
-    # data-driven checks (embedded-lib fingerprints and the like) the buildds and
-    # UDD apply -- so issues surface here instead of after upload.
-    container: debian:sid
     steps:
-      - name: Install packaging toolchain
-        run: |
-          set -euo pipefail
-          apt-get update
-          apt-get install -y --no-install-recommends \
-            ca-certificates git \
-            build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev \
-            debhelper devscripts lintian fakeroot
-
       - uses: actions/checkout@v6
         with:
           submodules: recursive
 
+      - name: Install packaging toolchain
+        run: |
+          set -euo pipefail
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            build-essential autoconf automake libtool autoconf-archive \
+            zlib1g-dev libssl-dev \
+            debhelper devscripts lintian fakeroot
+
       # --unsigned: CI has no GPG key (also skips the release sig/checksums).
-      # mkdeb builds every package then runs the lintian gate (--fail-on=error,
-      # warning); debuild runs the packaged test pass.
+      # debuild builds every package, then lintian gates on errors.
       #
       # DEB_BUILD_OPTIONS trims work CI does not need (release builds via
       # mkdeb.sh are untouched): noautodbgsym drops the -dbgsym packages whose
       # LTO payloads are slow to compress and that CI never ships; parallel uses
-      # every core.
-      - name: Build and lint Debian packages
+      # every core. We let debuild run its test pass -- the only one now that
+      # mkdeb no longer runs its own -- so CI exercises the packaged tests.
+      - name: Build Debian packages
         run: |
-          set -euo pipefail
-          # The workspace volume is owned by the host runner uid, but the
-          # container runs as root, so mkdeb's git calls (superproject and the
-          # coucal submodule) trip "dubious ownership"; mark them all safe.
-          git config --global --add safe.directory "*"
           export DEB_BUILD_OPTIONS="noautodbgsym parallel=$(nproc)"
           bash tools/mkdeb.sh --unsigned --no-release-artifacts
 

AGENTS.md

@@ -33,9 +33,8 @@ the operational checklist: toolchain, invariants, and how to ship a change.
 - Be terse. Comment the why, in English; translate French comments you touch.
 - Strip AI tells from prose (em-dash overuse, rule-of-three, filler, vague
   attributions). Ref: Wikipedia "Signs of AI writing". Claude Code: `/humanizer`.
-- Behavior change → add a test. Fast path: a hidden `httrack -#test=NAME` engine
-  self-test (registry in `htsselftest.c`; `-#test` lists them) driven by a
-  `tests/NN_*.test`, over a slow crawl.
+- Behavior change → add a test. Fast path: a hidden `httrack -#N` debug
+  subcommand (`htscoremain.c`) driven by a `tests/NN_*.test`, over a slow crawl.
 
 ## Review your change adversarially (strongly suggested)
 Before pushing, and when reviewing others, don't skim for bugs:

debian/libhttrack3.lintian-overrides

@@ -1,8 +1,3 @@
 # The shared libraries ship without a versioned symbols control file (ABI is
 # tracked via the SONAME plus a >= upstream-version dependency, see debian/rules).
 libhttrack3: no-symbols-control-file usr/lib/*
-
-# Bundled, locally patched minizip (src/minizip): it adds a zipFlush() API the
-# system libminizip lacks (htscache.c flushes the cache .zip so an interrupted
-# crawl leaves a valid archive), plus Android/old-zlib portability fixes.
-libhttrack3: embedded-library *libminizip*

debian/proxytrack.lintian-overrides

@@ -1,3 +0,0 @@
-# Statically linked against httrack's bundled, patched minizip (see src/minizip
-# and libhttrack3's override): the zipFlush() API is absent from the system one.
-proxytrack: embedded-library *libminizip*

man/httrack.1

@@ -3,7 +3,7 @@
 .\"
 .\" This file is generated by man/makeman.sh; do not edit by hand.
 .\" SPDX-License-Identifier: GPL-3.0-or-later
-.TH httrack 1 "26 June 2026" "httrack website copier"
+.TH httrack 1 "13 June 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -313,8 +313,12 @@ debug HTTP headers in logfile (\-\-debug\-headers)
 .SS Guru options: (do NOT use if possible)
 .IP \-#X
 *use optimized engine (limited memory boundary checks) (\-\-fast\-engine)
-.IP \-#test
-list engine self\-tests (run one with \-#test=NAME [args])
+.IP \-#0
+filter test (\-#0 '*.gif' 'www.bar.com/foo.gif') (\-\-debug\-testfilters <param>)
+.IP \-#1
+simplify test (\-#1 ./foo/bar/../foobar)
+.IP \-#2
+type test (\-#2 /foo/bar.php)
 .IP \-#C
 cache list (\-#C '*.com/spider*.gif' (\-\-debug\-cache <param>)
 .IP \-#R

src/Makefile.am

@@ -56,7 +56,7 @@ whttrackrundir = $(bindir)
 whttrackrun_SCRIPTS = webhttrack
 
 libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
-	htscache_selftest.c htsdns_selftest.c htsselftest.c \
+	htscache_selftest.c htsdns_selftest.c \
 	htscatchurl.c htsfilters.c htsftp.c htshash.c coucal/coucal.c \
 	htshelp.c htslib.c htscoremain.c \
 	htsname.c htsrobots.c htstools.c htswizard.c \
@@ -66,7 +66,7 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	md5.c \
 	minizip/ioapi.c minizip/mztools.c minizip/unzip.c minizip/zip.c \
 	hts-indextmpl.h htsalias.h htsback.h htsbase.h htssafe.h \
-	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htsselftest.h htscatchurl.h  \
+	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htscatchurl.h  \
 	htsconfig.h htscore.h htsparse.h htscoremain.h htsdefines.h  \
 	htsfilters.h htsftp.h htsglobal.h htshash.h coucal/coucal.h \
 	htshelp.h htsindex.h htslib.h htsmd5.h \

src/htsback.c

@@ -57,10 +57,7 @@ Please visit our Website: http://www.httrack.com
 // DOS
 #include <process.h>            /* _beginthread, _endthread */
 #endif
-#include <io.h> /* _chsize_s */
-#define HTS_FTRUNCATE(fp, sz) _chsize_s(_fileno(fp), (sz))
 #else
-#define HTS_FTRUNCATE(fp, sz) ftruncate(fileno(fp), (sz))
 #endif
 
 #define VT_CLREOL       "\33[K"
@@ -3766,27 +3763,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     }
 #endif
 /********** **************************** ********** */
-                  }
-                  // MIME type excluded by a -mime: filter: abort, don't fetch
-                  // the body (#58)
-                  else if (HTTP_IS_OK(back[i].r.statuscode) &&
-                           !back[i].testmode &&
-                           strnotempty(back[i].r.contenttype) &&
-                           hts_acceptmime(opt, 0, back[i].url_adr,
-                                          back[i].url_fil,
-                                          back[i].r.contenttype) == 1) {
-                    deletehttp(&back[i].r);
-                    back[i].r.soc = INVALID_SOCKET;
-                    back[i].status = STATUS_READY;
-                    back_set_finished(sback, i);
-                    back[i].r.statuscode = STATUSCODE_EXCLUDED;
-                    strcpybuff(back[i].r.msg, "Excluded by MIME type filter");
-                    hts_log_print(
-                        opt, LOG_NOTICE,
-                        "File excluded by MIME type filter (%s): %s%s",
-                        back[i].r.contenttype, back[i].url_adr,
-                        back[i].url_fil);
-                  } else { // il faut aller le chercher
+                  } else {      // il faut aller le chercher
 
                     // effacer buffer (requète)
                     if (!noFreebuff) {
@@ -3797,70 +3774,35 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     // xxc SI CHUNK VERIFIER QUE CA MARCHE??
                     if (back[i].r.statuscode == 206) {  // on nous envoie un morceau (la fin) coz une partie sur disque!
                       off_t sz = fsize_utf8(back[i].url_sav);
-                      /* RFC 7233: resume at the server's Content-Range start,
-                         not the offset we requested; a server may resume
-                         earlier and appending the overlap duplicates bytes
-                         (#198). */
-                      const LLint resume = back[i].r.crange_start;
-                      const hts_boolean range_ok =
-                          back[i].r.crange > 0 && resume >= 0 &&
-                          resume <= (LLint) sz &&
-                          back[i].r.crange_end + 1 == back[i].r.crange &&
-                          (back[i].r.totalsize < 0 ||
-                           back[i].r.totalsize ==
-                               back[i].r.crange_end - resume + 1);
 
 #if HDEBUG
                       printf("partial content: " LLintP " on disk..\n",
                              (LLint) sz);
 #endif
-                      if (sz >= 0 && range_ok) {
+                      if (sz >= 0) {
                         if (!is_hypertext_mime(opt, back[i].r.contenttype, back[i].url_sav)) {  // pas HTML
                           if (opt->getmode & HTS_GETMODE_NONHTML) {
                             filenote(&opt->state.strc, back[i].url_sav, NULL);  // noter fichier comme connu
                             file_notify(opt, back[i].url_adr, back[i].url_fil,
                                         back[i].url_sav, 0, 1,
                                         back[i].r.notmodified);
-                            back[i].r.out =
-                                FOPEN(fconv(catbuff, sizeof(catbuff),
-                                            back[i].url_sav),
-                                      "r+b"); // resume in place
+                            back[i].r.out = FOPEN(fconv(catbuff, sizeof(catbuff), back[i].url_sav), "ab");       // append
                             if (back[i].r.out && opt->cache != 0) {
-                              back[i].r.is_write = 1;
-                              back[i].r.size = resume; // bytes already on disk
-                              back[i].r.statuscode = HTTP_OK; // force 'OK'
+                              back[i].r.is_write = 1;   // écrire
+                              back[i].r.size = sz;      // déja écrit
+                              back[i].r.statuscode = HTTP_OK;   // Forcer 'OK'
                               if (back[i].r.totalsize >= 0)
-                                back[i].r.totalsize += resume; // -> full size
-                              // drop bytes past the resume point; a silent
-                              // failure could leave a stale tail, so on error
-                              // drop the partial and refetch the whole file
-                              if (HTS_FTRUNCATE(back[i].r.out,
-                                                (off_t) resume) != 0) {
-                                fclose(back[i].r.out);
-                                back[i].r.out = NULL;
-                                url_savename_refname_remove(
-                                    opt, back[i].url_adr, back[i].url_fil);
-                                UNLINK(back[i].url_sav);
-                                back[i].status = STATUS_READY;
-                                back_set_finished(sback, i);
-                                strcpybuff(back[i].r.msg,
-                                           "Can not truncate partial file, "
-                                           "restarting");
-                              } else {
-                                fseeko(back[i].r.out, (off_t) resume, SEEK_SET);
-                                /* create a temporary reference file in case of
-                                 * broken mirror */
-                                if (back_serialize_ref(opt, &back[i]) != 0) {
-                                  hts_log_print(opt, LOG_WARNING,
-                                                "Could not create temporary "
-                                                "reference file for %s%s",
-                                                back[i].url_adr,
-                                                back[i].url_fil);
-                                }
-#if HDEBUG
-                                printf("continue interrupted file\n");
-#endif
+                                back[i].r.totalsize += sz;      // plus en fait
+                              fseek(back[i].r.out, 0, SEEK_END);        // à la fin
+                              /* create a temporary reference file in case of broken mirror */
+                              if (back_serialize_ref(opt, &back[i]) != 0) {
+                                hts_log_print(opt, LOG_WARNING,
+                                              "Could not create temporary reference file for %s%s",
+                                              back[i].url_adr, back[i].url_fil);
                               }
+#if HDEBUG
+                              printf("continue interrupted file\n");
+#endif
                             } else {    // On est dans la m**
                               back[i].status = STATUS_READY;    // terminé (voir plus loin)
                               back_set_finished(sback, i);
@@ -3872,18 +3814,17 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                           FILE *fp =
                             FOPEN(fconv(catbuff, sizeof(catbuff), back[i].url_sav), "rb");
                           if (fp) {
-                            LLint alloc_mem = resume + 1;
+                            LLint alloc_mem = sz + 1;
 
                             if (back[i].r.totalsize >= 0)
                               alloc_mem += back[i].r.totalsize; // AJOUTER RESTANT!
                             if (deleteaddr(&back[i].r)
                                 && (back[i].r.adr =
                                     (char *) malloct((size_t) alloc_mem))) {
-                              back[i].r.size = resume;
+                              back[i].r.size = sz;
                               if (back[i].r.totalsize >= 0)
-                                back[i].r.totalsize += resume; // -> full size
-                              if ((fread(back[i].r.adr, 1, (size_t) resume,
-                                         fp)) != (size_t) resume) {
+                                back[i].r.totalsize += sz;      // plus en fait
+                              if ((fread(back[i].r.adr, 1, sz, fp)) != sz) {
                                 back[i].status = STATUS_READY;  // terminé (voir plus loin)
                                 back_set_finished(sback, i);
                                 strcpybuff(back[i].r.msg,
@@ -3901,30 +3842,14 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                          "No memory for partial file");
                             }
                             fclose(fp);
-                          } else {                              // open failed
+                          } else {      // Argh.. 
                             back[i].status = STATUS_READY;      // terminé (voir plus loin)
                             back_set_finished(sback, i);
                             strcpybuff(back[i].r.msg,
                                        "Can not open partial file");
                           }
                         }
-                      } else if (sz >=
-                                 0) { // unusable range -> restart whole file
-                        hts_log_print(opt, LOG_WARNING,
-                                      "Unusable partial-content range for %s%s "
-                                      "(have " LLintP " bytes, got " LLintP
-                                      "-" LLintP "/" LLintP "), restarting",
-                                      back[i].url_adr, back[i].url_fil,
-                                      (LLint) sz, back[i].r.crange_start,
-                                      back[i].r.crange_end, back[i].r.crange);
-                        url_savename_refname_remove(opt, back[i].url_adr,
-                                                    back[i].url_fil);
-                        UNLINK(back[i].url_sav);
-                        back[i].status = STATUS_READY;
-                        back_set_finished(sback, i);
-                        strcpybuff(back[i].r.msg,
-                                   "Unusable partial content, restarting");
-                      } else {                          // partial not found
+                      } else {  // Non trouvé??
                         back[i].status = STATUS_READY;  // terminé (voir plus loin)
                         back_set_finished(sback, i);
                         strcpybuff(back[i].r.msg, "Can not find partial file");
@@ -4005,6 +3930,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 
                       }
                     }
+
                   }
 
                   /*} */

src/htsbasenet.h

@@ -146,8 +146,7 @@ typedef enum BackStatusCode {
   STATUSCODE_NON_FATAL = -5,
   STATUSCODE_SSL_HANDSHAKE = -6,
   STATUSCODE_TOO_BIG = -7,
-  STATUSCODE_TEST_OK = -10,
-  STATUSCODE_EXCLUDED = -11 /* aborted: MIME excluded by a -mime: filter */
+  STATUSCODE_TEST_OK = -10
 } BackStatusCode;
 
 /** HTTrack status ('status' member of of 'lien_back') **/

src/htscache.c

@@ -220,25 +220,6 @@ struct cache_back_zip_entry {
 	} \
 } while(0)
 
-/* A cache (new.zip) write failed: storage is gone (disk full / dropped share),
-   so the mirror is doomed too. Abort it via exit_xh, don't crash as assertf
-   did. */
-static void cache_zip_write_failed(httrackp *opt, cache_back *cache,
-                                   const char *what, int zErr) {
-  if (!cache->zipWriteFailed) {
-    cache->zipWriteFailed = HTS_TRUE;
-    if (check_fatal_io_errno()) {
-      hts_log_print(opt, LOG_ERROR,
-                    "Mirror aborted: disk full or filesystem problems");
-    } else {
-      hts_log_print(opt, LOG_ERROR,
-                    "Mirror aborted: cache write failed (%s): %s", what,
-                    hts_get_zerror(zErr));
-    }
-  }
-  opt->state.exit_xh = -1; /* fatal: stop the mirror, exit non-zero */
-}
-
 /* Ajout d'un fichier en cache */
 void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
                const char *url_adr, const char *url_fil, const char *url_save,
@@ -255,10 +236,6 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
   const char *url_save_suffix = url_save;
   int zErr;
 
-  /* already failed and aborting; don't touch the broken stream again */
-  if (cache->zipWriteFailed)
-    return;
-
   // robots.txt hack
   if (url_save == NULL) {
     dataincache = 0;            // testing links
@@ -369,8 +346,9 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
                                    */
                                   headers, (uInt) strlen(headers), NULL, 0, NULL,       /* comment */
                                   Z_DEFLATED, Z_DEFAULT_COMPRESSION)) != Z_OK) {
-    cache_zip_write_failed(opt, cache, "opening a cache entry", zErr);
-    return;
+    int zip_zipOpenNewFileInZip_failed = 0;
+
+    assertf(zip_zipOpenNewFileInZip_failed);
   }
 
   /* Write data in cache */
@@ -380,8 +358,9 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
         if ((zErr =
              zipWriteInFileInZip((zipFile) cache->zipOutput, r->adr,
                                  (int) r->size)) != Z_OK) {
-          cache_zip_write_failed(opt, cache, "writing to the cache", zErr);
-          return;
+          int zip_zipWriteInFileInZip_failed = 0;
+
+          assertf(zip_zipWriteInFileInZip_failed);
         }
       }
     } else {
@@ -402,10 +381,9 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
               if ((zErr =
                    zipWriteInFileInZip((zipFile) cache->zipOutput, buff,
                                        (int) nl)) != Z_OK) {
-                cache_zip_write_failed(opt, cache, "writing to the cache",
-                                       zErr);
-                fclose(fp);
-                return;
+                int zip_zipWriteInFileInZip_failed = 0;
+
+                assertf(zip_zipWriteInFileInZip_failed);
               }
             }
           } while(nl > 0);
@@ -419,14 +397,16 @@ void cache_add(httrackp * opt, cache_back * cache, const htsblk * r,
 
   /* Close */
   if ((zErr = zipCloseFileInZip((zipFile) cache->zipOutput)) != Z_OK) {
-    cache_zip_write_failed(opt, cache, "closing a cache entry", zErr);
-    return;
+    int zip_zipCloseFileInZip_failed = 0;
+
+    assertf(zip_zipCloseFileInZip_failed);
   }
 
   /* Flush */
   if ((zErr = zipFlush((zipFile) cache->zipOutput)) != 0) {
-    cache_zip_write_failed(opt, cache, "flushing the cache", zErr);
-    return;
+    int zip_zipFlush_failed = 0;
+
+    assertf(zip_zipFlush_failed);
   }
 }
 

src/htscache_selftest.c

@@ -47,7 +47,6 @@ Please visit our Website: http://www.httrack.com
 #include "htslib.h"
 #include "htszlib.h"
 
-#include <errno.h>
 #include <stdio.h>
 #include <string.h>
 
@@ -317,136 +316,6 @@ static int disk_fallback_selftest(httrackp *opt) {
   return fail;
 }
 
-typedef struct {
-  size_t budget;  /**< bytes allowed through before writes start failing */
-  int fail_errno; /**< errno set on the failing write (ENOSPC, EIO, ...) */
-  int writes;     /**< zwrite call count, to detect re-entry into the stream */
-} writefail_inject;
-
-/* zwrite that copies until the budget runs out, then fails with inj->fail_errno
-   (the #174/#219 condition). Counts calls so the test can prove a flagged cache
-   never re-enters the stream. */
-static uLong selftest_failing_zwrite(voidpf opaque, voidpf stream,
-                                     const void *buf, uLong size) {
-  writefail_inject *inj = (writefail_inject *) opaque;
-
-  inj->writes++;
-  if (inj->budget >= (size_t) size) {
-    inj->budget -= (size_t) size;
-    return (uLong) fwrite(buf, 1, (size_t) size, (FILE *) stream);
-  }
-  errno = inj->fail_errno;
-  return 0; /* short write -> the minizip op returns an error */
-}
-
-/* Open a ZIP whose writes fail past inj->budget, so cache_add() hits an error.
- */
-static zipFile selftest_open_failing_zip(const char *path,
-                                         writefail_inject *inj) {
-  zlib_filefunc_def ff;
-
-  fill_fopen_filefunc(&ff); /* real fopen/read/seek/close; ignores opaque */
-  ff.zwrite_file = selftest_failing_zwrite;
-  ff.opaque = inj;
-  return zipOpen2(path, APPEND_STATUS_CREATE, NULL, &ff);
-}
-
-/* Store one octet-stream body into `cache` (all-in-cache, body in the ZIP). */
-static void writefail_store(httrackp *opt, cache_back *cache, const char *fil,
-                            const char *body, size_t body_len) {
-  htsblk r;
-  char locbuf[4];
-  char *bodycopy = malloct(body_len);
-
-  hts_init_htsblk(&r);
-  r.statuscode = 200;
-  r.size = (LLint) body_len;
-  strcpybuff(r.msg, "OK");
-  strcpybuff(r.contenttype, "application/octet-stream");
-  locbuf[0] = '\0';
-  r.location = locbuf;
-  r.is_write = 0;
-  memcpy(bodycopy, body, body_len);
-  r.adr = bodycopy;
-  cache_add(opt, cache, &r, "example.com", fil, "example.com/blob.bin", 1,
-            NULL);
-  freet(bodycopy);
-}
-
-/* #174/#219: a failing cache write used to crash via assertf(); it must instead
-   stop the mirror (exit_xh = -1) without crashing. Assert that, plus the cache
-   is flagged and a sibling write doesn't re-enter the broken stream. */
-int cache_write_failure_selftest(httrackp *opt, const char *dir) {
-  int fail = 0;
-  char path[HTS_URLMAXSIZE];
-  /* incompressible + big, so deflate flushes (and fails) mid-write, before
-   * close */
-  static const size_t body_len = 256 * 1024;
-  char *body = malloct(body_len);
-  int phase;
-
-  gen_body(body, body_len, 1 /* incompressible */);
-  fconcat(path, sizeof(path), dir, "/wfail.zip");
-
-  /* phase 0: fail on the body write, fatal errno (ENOSPC, the disk-full
-     branch). phase 1: fail on the open, non-fatal errno (EIO, dropped-share
-     branch). Both must abort the mirror. */
-  for (phase = 0; phase < 2; phase++) {
-    cache_back cache;
-    writefail_inject inj;
-    int writes_after_fail;
-
-    inj.budget = (phase == 0) ? 4096 : 0;
-    inj.fail_errno = (phase == 0) ? ENOSPC : EIO;
-    inj.writes = 0;
-    memset(&cache, 0, sizeof(cache));
-    cache.type = 1;
-    cache.log = stderr;
-    cache.errlog = stderr;
-    cache.hashtable = coucal_new(0);
-    cache.zipOutput = selftest_open_failing_zip(path, &inj);
-    if (cache.zipOutput == NULL) {
-      fprintf(stderr, "cache-writefail: could not open injected ZIP\n");
-      fail++;
-      continue;
-    }
-
-    opt->state.exit_xh = 0; /* clear; the failing write must set it to -1 */
-    writefail_store(opt, &cache, "/blob.bin", body, body_len);
-    if (!cache.zipWriteFailed) {
-      fprintf(stderr, "cache-writefail: phase %d: write error not caught\n",
-              phase);
-      fail++;
-    }
-    if (opt->state.exit_xh != -1) {
-      fprintf(stderr,
-              "cache-writefail: phase %d: mirror not aborted (exit_xh=%d)\n",
-              phase, opt->state.exit_xh);
-      fail++;
-    }
-
-    /* a flagged cache must no-op a sibling write: no further backend write */
-    writes_after_fail = inj.writes;
-    writefail_store(opt, &cache, "/blob2.bin", body, 16);
-    if (inj.writes != writes_after_fail) {
-      fprintf(stderr,
-              "cache-writefail: phase %d: sibling write re-entered the broken "
-              "stream (%d extra backend writes)\n",
-              phase, inj.writes - writes_after_fail);
-      fail++;
-    }
-
-    if (cache.zipOutput != NULL) {
-      zipClose(cache.zipOutput,
-               NULL); /* best-effort; may fail on the backend */
-      cache.zipOutput = NULL;
-    }
-  }
-
-  freet(body);
-  return fail;
-}
-
 int cache_selftests(httrackp *opt, const char *dir) {
   int failures = 0;
   cache_back cache;

src/htscache_selftest.h

@@ -52,10 +52,6 @@ int cache_selftests(httrackp *opt, const char *dir);
    committed file, never by the test). Returns the failed-check count. */
 int cache_golden_selftest(httrackp *opt, const char *dir, int regen);
 
-/* #174/#219: assert a failing cache write aborts the mirror cleanly instead of
-   crashing. Returns the failed-check count. */
-int cache_write_failure_selftest(httrackp *opt, const char *dir);
-
 #endif
 
 #endif

src/htscore.c

@@ -736,39 +736,26 @@ int httpmirror(char *url1, httrackp * opt) {
     /* OPTIMIZED for fast load */
     if (StringNotEmpty(opt->filelist)) {
       char *filelist_buff = NULL;
-      size_t filelist_sz = 0;
-      const char *filelist_err = NULL; /* failure reason, NULL on success */
-      const off_t fs = fsize(StringBuff(opt->filelist));
+      const size_t filelist_sz = off_t_to_size_t(fsize(StringBuff(opt->filelist)));
 
-      if (fs < 0) {
-        /* fsize() hides the cause; redo stat() for a precise errno (#49) */
-        struct stat st;
-        filelist_err = stat(StringBuff(opt->filelist), &st) != 0
-                           ? strerror(errno)
-                           : "not a regular file";
-      } else if ((filelist_sz = off_t_to_size_t(fs)) == (size_t) -1) {
-        filelist_err = "file too large";
-        filelist_sz = 0;
-      } else {
+      if (filelist_sz != (size_t) -1) {
         FILE *fp = fopen(StringBuff(opt->filelist), "rb");
 
-        if (fp == NULL) {
-          filelist_err = strerror(errno);
-        } else {
+        if (fp) {
           filelist_buff = malloct(filelist_sz + 1);
-          if (filelist_buff == NULL) {
-            filelist_err = "out of memory";
-          } else if (fread(filelist_buff, 1, filelist_sz, fp) != filelist_sz) {
-            freet(filelist_buff);
-            filelist_err = "read error";
-          } else {
-            filelist_buff[filelist_sz] = '\0';
+          if (filelist_buff) {
+            if (fread(filelist_buff, 1, filelist_sz, fp) != filelist_sz) {
+              freet(filelist_buff);
+              filelist_buff = NULL;
+            } else {
+              *(filelist_buff + filelist_sz) = '\0';
+            }
           }
           fclose(fp);
         }
       }
 
-      if (filelist_buff != NULL) {
+      if (filelist_buff) {
         int filelist_ptr = 0;
         int n = 0;
         char BIGSTK line[HTS_URLMAXSIZE * 2];
@@ -793,8 +780,8 @@ int httpmirror(char *url1, httrackp * opt) {
         // Free buffer
         freet(filelist_buff);
       } else {
-        hts_log_print(opt, LOG_ERROR, "Could not include URL list \"%s\": %s",
-                      StringBuff(opt->filelist), filelist_err);
+        hts_log_print(opt, LOG_ERROR, "Could not include URL list: %s",
+                      StringBuff(opt->filelist));
       }
     }
 

src/htscore.h

@@ -214,8 +214,6 @@ struct cache_back {
   cache_back_zip_entry *zipEntries;
   int zipEntriesOffs;
   int zipEntriesCapa;
-  hts_boolean
-      zipWriteFailed; /**< a cache write failed; stop touching the stream */
 };
 
 #ifndef HTS_DEF_FWSTRUCT_hash_struct

src/htscoremain.c

@@ -45,7 +45,9 @@ Please visit our Website: http://www.httrack.com
 #include "htsmodules.h"
 #include "htszlib.h"
 #include "htscharset.h"
-#include "htsselftest.h"
+#include "htsencoding.h"
+#include "htscache_selftest.h"
+#include "htsdns_selftest.h"
 #include "htsmd5.h"
 
 #include <ctype.h>
@@ -112,6 +114,442 @@ HTSEXT_API int hts_main(int argc, char **argv) {
   return ret;
 }
 
+// very minimalistic internal tests
+static void basic_selftests(void) {
+  // BUG 756328
+  const char *const source = "/intent/tweet?url=https%3A%2F%2Fwww.httrack.com%2Fvacatures%2F1562519%2Fmedewerker-data-services&text=Medewerker+Data+Services&via=httrackcom";
+  char buffer[1024];
+  fil_normalized(source, buffer);
+  // MD5 selftests
+  md5selftest();
+  // cookie_get field extraction (tab-separated, 0-based)
+  {
+    char cbuf[8192];
+
+    assertf(strcmp(cookie_get(cbuf, "a\tb\tc", 0), "a") == 0);
+    assertf(strcmp(cookie_get(cbuf, "a\tb\tc", 1), "b") == 0);
+    assertf(strcmp(cookie_get(cbuf, "a\tb\tc", 2), "c") == 0);
+    // multi-char fields catch length/boundary bugs that 1-char fields hide
+    assertf(strcmp(cookie_get(cbuf, "host\tx\t/path/to", 0), "host") == 0);
+    assertf(strcmp(cookie_get(cbuf, "host\tx\t/path/to", 2), "/path/to") == 0);
+    assertf(strcmp(cookie_get(cbuf, "a\t\tc", 1), "") == 0);  // empty field
+    assertf(strcmp(cookie_get(cbuf, "a\tb\tc", 9), "") == 0); // beyond last
+  }
+  // back_infostr() status-line formatting (no sockets: pure formatting over
+  // in-memory slots). Stresses a few thousand entries across every status-code
+  // arm. Regression for a clobber bug where the size/totalsize trailer was
+  // written straight into the destination, wiping the URL it had just built.
+  {
+    static const struct {
+      int code;
+      const char *tag;
+    } cases[] = {
+        {200, "READY "},     {-1, "ERROR "},       {-2, "TIMEOUT "},
+        {-3, "TOOSLOW "},    {400, "BADREQUEST "}, {403, "FORBIDDEN "},
+        {404, "NOT FOUND "}, {500, "SERVERROR "},  {999, "ERROR(999)"},
+    };
+    const int ncases = (int) (sizeof(cases) / sizeof(cases[0]));
+    const int n = 2000;
+    lien_back *slots = calloct(n, sizeof(lien_back));
+    char line[HTS_URLMAXSIZE * 4 + 1024];
+    char expect[HTS_URLMAXSIZE * 4 + 1024];
+    struct_back sb;
+    int idx;
+
+    sb.lnk = slots;
+    sb.count = n;
+    sb.ready = NULL;
+    sb.ready_size_bytes = 0;
+    for (idx = 0; idx < n; idx++) {
+      lien_back *const slot = &slots[idx];
+
+      slot->r.location = slot->location_buffer;
+      slot->status = STATUS_READY;
+      slot->r.statuscode = cases[idx % ncases].code;
+      slot->r.size = idx;
+      slot->r.totalsize = idx + 1;
+      snprintf(slot->url_adr, sizeof(slot->url_adr), "http://h%d.example", idx);
+      snprintf(slot->url_fil, sizeof(slot->url_fil), "/p/%d.html", idx);
+    }
+    for (idx = 0; idx < n; idx++) {
+      line[0] = '\0';
+      back_infostr(&sb, idx, 3, line, sizeof(line));
+      // Exact match (not substring): pins tag/URL/trailer order and rejects a
+      // partial clobber, duplication, or truncation that a presence check would
+      // let through. The expected format is stated here independently.
+      snprintf(expect, sizeof(expect),
+               "%s\"http://h%d.example/p/%d.html\" " LLintP " " LLintP " ",
+               cases[idx % ncases].tag, idx, idx, (LLint) idx,
+               (LLint) (idx + 1));
+      assertf(strcmp(line, expect) == 0);
+    }
+    // Near-maximal URL, driven through back_info() (which owns the status
+    // buffer internally and prints to a FILE*). url_adr + url_fil together
+    // overrun the old HTS_URLMAXSIZE*2+1024 buffer, so the bounded appends
+    // would abort unless that buffer is sized to hold both fields. Regression
+    // for that sizing -- exercising back_infostr() directly would miss it,
+    // since the caller's buffer is what matters.
+    {
+      lien_back *const slot = &slots[0];
+      const size_t adrlen = sizeof(slot->url_adr) - 8;
+      const size_t fillen = sizeof(slot->url_fil) - 8;
+      FILE *const fp = tmpfile();
+      size_t got;
+
+      assertf(fp != NULL);
+      slot->status = STATUS_READY;
+      slot->r.statuscode = 200;
+      slot->r.size = 1;
+      slot->r.totalsize = 2;
+      memset(slot->url_adr, 'a', adrlen);
+      slot->url_adr[adrlen] = '\0';
+      slot->url_fil[0] = '/';
+      memset(slot->url_fil + 1, 'b', fillen - 1);
+      slot->url_fil[fillen] = '\0';
+      back_info(&sb, 0, 3, fp);
+      rewind(fp);
+      got = fread(line, 1, sizeof(line) - 1, fp);
+      line[got] = '\0';
+      fclose(fp);
+      snprintf(expect, sizeof(expect),
+               "READY \"%s%s\" " LLintP " " LLintP " " LF, slot->url_adr,
+               slot->url_fil, (LLint) 1, (LLint) 2);
+      assertf(strcmp(line, expect) == 0);
+    }
+    freet(slots);
+  }
+  // next_token(): in-place token scanner. Strips surrounding quotes, unescapes
+  // \" and \\ when flag is set, and returns the token terminator (the space, or
+  // NULL at end of string). The unquote/unescape rewrites the string in place
+  // by shifting left, so the result is always shorter -- regression for that
+  // compaction.
+  {
+    char tok[64];
+
+    // plain token: unchanged, returns a pointer AT the separating space (exact
+    // position, not just any space -- a strchr-style impl would land elsewhere
+    // once quotes shift the content)
+    strcpybuff(tok, "abc def");
+    {
+      char *const end = next_token(tok, 0);
+      assertf(end == tok + 3 && *end == ' ' && strcmp(tok, "abc def") == 0);
+    }
+    // surrounding quotes stripped, returns the (post-shift) trailing space
+    strcpybuff(tok, "\"ab\" cd");
+    {
+      char *const end = next_token(tok, 1);
+      assertf(end == tok + 2 && *end == ' ' && strcmp(tok, "ab cd") == 0);
+    }
+    // a space inside quotes does not end the token; end of string returns NULL
+    strcpybuff(tok, "\"a b\"c");
+    {
+      char *const end = next_token(tok, 1);
+      assertf(end == NULL && strcmp(tok, "a bc") == 0);
+    }
+    // \" and \\ are unescaped to literal " and \ in place
+    strcpybuff(tok, "\"a\\\"b\\\\c\"");
+    {
+      char *const end = next_token(tok, 1);
+      assertf(end == NULL && strcmp(tok, "a\"b\\c") == 0);
+    }
+    // unterminated quote: the opening quote is dropped, the rest survives, and
+    // the scan runs to the NUL (returns NULL)
+    strcpybuff(tok, "\"ab");
+    {
+      char *const end = next_token(tok, 1);
+      assertf(end == NULL && strcmp(tok, "ab") == 0);
+    }
+    // trailing lone backslash in a quote: *(p+1) is the NUL, not an escape, so
+    // the backslash is kept intact (and there is no over-read past the NUL)
+    strcpybuff(tok, "\"a\\");
+    {
+      char *const end = next_token(tok, 1);
+      assertf(end == NULL && strcmp(tok, "a\\") == 0);
+    }
+  }
+  // fil_normalized(): canonicalizes a URL path. Query arguments are sorted
+  // alphabetically (by the text after each '?'/'&') and the query is rebuilt
+  // through a bounded builder; outside the query, "//" collapses to "/".
+  // Regression for that builder.
+  {
+    char norm[256];
+
+    assertf(strcmp(fil_normalized("/p?b=2&a=1&c=3", norm), "/p?a=1&b=2&c=3") ==
+            0);
+    assertf(strcmp(fil_normalized("/a//b", norm), "/a/b") == 0);
+    // "//" is collapsed only before the query; inside the query it is kept
+    assertf(strcmp(fil_normalized("/a//b?x=c//d", norm), "/a/b?x=c//d") == 0);
+  }
+  // give_mimext(): mime type -> file extension, bounded into the caller buffer.
+  // Returns 1 when an extension was written, 0 otherwise.
+  {
+    char ext[16];
+
+    assertf(give_mimext(ext, sizeof(ext), "image/gif") == 1);
+    assertf(strcmp(ext, "gif") == 0);
+    assertf(give_mimext(ext, sizeof(ext), "text/html") == 1);
+    assertf(strcmp(ext, "html") == 0);
+    assertf(give_mimext(ext, sizeof(ext), "no/such-mime-type") == 0);
+    assertf(ext[0] == '\0');
+  }
+  // convtolower(): lower-cases into the caller buffer (bounded by its size).
+  {
+    char low[64];
+
+    assertf(strcmp(convtolower(low, sizeof(low), "ABC/Def.HTML"),
+                   "abc/def.html") == 0);
+  }
+  // cut_path(): splits a path into directory (with trailing '/') and basename,
+  // each bounded by its buffer size.
+  {
+    char path[256];
+    char pname[256];
+
+    {
+      char full[] = "/dir/sub/file.html";
+
+      cut_path(full, path, sizeof(path), pname, sizeof(pname));
+      assertf(strcmp(path, "/dir/sub/") == 0);
+      assertf(strcmp(pname, "file.html") == 0);
+    }
+    { // a trailing slash is trimmed before the split
+      char full[] = "/dir/sub/";
+
+      cut_path(full, path, sizeof(path), pname, sizeof(pname));
+      assertf(strcmp(path, "/dir/") == 0);
+      assertf(strcmp(pname, "sub") == 0);
+    }
+    { // a path of length <= 1 yields empty results
+      char full[] = "/";
+
+      cut_path(full, path, sizeof(path), pname, sizeof(pname));
+      assertf(path[0] == '\0' && pname[0] == '\0');
+    }
+  }
+  // get_httptype_sized(): a long MIME type (Office OOXML reaches 73 chars) is
+  // written whole into a contenttype-sized buffer; returns 1 on a match, 0 when
+  // flag==0 and nothing matched. Regression for the old contenttype[64]
+  // overflow.
+  {
+    httrackp *opt = hts_create_opt();
+    htsblk r; // write into the real struct field, not a stand-in
+
+    assertf(opt != NULL);
+    // a long MIME (Office OOXML reaches 73 chars) must fit htsblk.contenttype
+    // whole: a [64] field would make this bounded copy abort.
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "deck.pptx", 0) == 1);
+    assertf(strcmp(r.contenttype,
+                   "application/vnd.openxmlformats-officedocument."
+                   "presentationml.presentation") == 0);
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "x.gif", 0) == 1);
+    assertf(strcmp(r.contenttype, "image/gif") == 0);
+    // no extension and flag==0: nothing written, returns 0
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "noextfile", 0) == 0);
+    assertf(r.contenttype[0] == '\0');
+    // no extension and flag==1: octet-stream fallback, returns 1
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "noextfile", 1) == 1);
+    assertf(strcmp(r.contenttype, "application/octet-stream") == 0);
+    // a user --assume rule with an empty value matches but writes nothing:
+    // get_userhttptype returns 1 with the buffer empty, so get_httptype_sized
+    // must still report 0 (callers test the return like the old
+    // strnotempty(s)).
+    StringCopy(opt->mimedefs, "\ncgi=\n");
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "/x.cgi", 0) == 0);
+    assertf(r.contenttype[0] == '\0');
+    StringCopy(opt->mimedefs, "\ncgi=text/html\n");
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "/x.cgi", 0) == 1);
+    assertf(strcmp(r.contenttype, "text/html") == 0);
+    hts_free_opt(opt);
+  }
+  // adr_normalized_sized(): bounded host normalization (passthrough when
+  // already normal).
+  {
+    char n[HTS_URLMAXSIZE];
+
+    assertf(strcmp(adr_normalized_sized("example.com", n, sizeof(n)),
+                   "example.com") == 0);
+  }
+  // standard_name(): builds "<name><md5?>.<ext>" into a bounded buffer. The md5
+  // is appended (4 chars) only when the URL has a query string (see url_md5),
+  // so test both; pin the structure (name + ext, lengths), not the md5 chars.
+  {
+    char b[HTS_URLMAXSIZE * 2];
+    const char *nom = "index.html"; // name part
+    const char *dot = nom + 5;      // points at ".html"
+    size_t len;
+
+    // no query -> no md5: "index" + ".html"
+    standard_name(b, sizeof(b), dot, nom, "http://example.com/index.html", 0);
+    assertf(strcmp(b, "index.html") == 0);
+    // query -> 4 md5 chars between name and ext: "index" + md5(4) + ".html"
+    standard_name(b, sizeof(b), dot, nom, "http://example.com/index.html?v=1",
+                  0);
+    len = strlen(b);
+    assertf(len == 5 + 4 + 5);
+    assertf(strncmp(b, "index", 5) == 0);
+    assertf(strcmp(b + len - 5, ".html") == 0);
+    // short names: name kept (<=8), the extension is clamped to 3 -> ".htm"
+    standard_name(b, sizeof(b), dot, nom, "http://example.com/index.html?v=1",
+                  1);
+    len = strlen(b);
+    assertf(len == 5 + 4 + 4);
+    assertf(strcmp(b + len - 4, ".htm") == 0);
+    // short names with a >8-char name: the name is clamped to 8 ("indexpag")
+    {
+      const char *lnom = "indexpage.html";
+      const char *ldot = lnom + 9; // points at ".html"
+
+      standard_name(b, sizeof(b), ldot, lnom,
+                    "http://example.com/indexpage.html?v=1", 1);
+      len = strlen(b);
+      assertf(len == 8 + 4 + 4);
+      assertf(strncmp(b, "indexpag", 8) == 0);
+      assertf(strcmp(b + len - 4, ".htm") == 0);
+    }
+  }
+  // longfile_to_83(): single-name 8-3 (mode 1) / ISO9660 (mode 2) conversion;
+  // uppercases, clamps the name (8 / 31) and the extension (3). It rewrites
+  // 'save' in place, so pass a mutable array.
+  {
+    char n83[256];
+
+    {
+      char save[] = "longfilename.html";
+
+      longfile_to_83(1, n83, sizeof(n83), save); // 8-3: name->8, ext->3
+      assertf(strcmp(n83, "LONGFILE.HTM") == 0);
+    }
+    {
+      char save[] = "longfilename.html";
+
+      longfile_to_83(2, n83, sizeof(n83), save); // ISO9660: name->31, ext->3
+      assertf(strcmp(n83, "LONGFILENAME.HTM") == 0);
+    }
+    { // sanitization: leading '.'->'_', interior dots
+      char save[] = ".a b.c.d e"; // collapse to '_', spaces/specials -> '_'
+                                  // (only the last dot stays as the separator)
+      longfile_to_83(1, n83, sizeof(n83), save);
+      assertf(strcmp(n83, "_A_B_C.D_E") == 0);
+    }
+  }
+  // long_to_83(): per-segment 8-3 conversion of a whole path.
+  {
+    char n83[HTS_URLMAXSIZE * 2];
+    char save[] = "dir/longfilename.html";
+
+    long_to_83(1, n83, sizeof(n83), save);
+    assertf(strcmp(n83, "DIR/LONGFILE.HTM") == 0);
+  }
+  // lienrelatif(): relative path from the directory of curr_fil to link.
+  {
+    char s[HTS_URLMAXSIZE * 2];
+
+    // same directory -> just the basename
+    assertf(lienrelatif(s, sizeof(s), "dir/page.html", "dir/index.html") == 0);
+    assertf(strcmp(s, "page.html") == 0);
+    // link one level up -> a "../" prefix
+    assertf(lienrelatif(s, sizeof(s), "a.html", "dir/index.html") == 0);
+    assertf(strcmp(s, "../a.html") == 0);
+  }
+}
+
+/* Self-tests for the htssafe.h bounded string ops (driven by httrack -#8).
+   Returns 0 if every bounded operation behaved correctly, 1 otherwise.
+   The abort-on-overflow guarantee is checked separately by the -#8 "overflow"
+   sub-mode (it aborts the process by design). */
+static int string_safety_selftests(void) {
+  char buf[8];
+
+  /* strcpybuff into a sized array: exact copy */
+  strcpybuff(buf, "abc");
+  if (strcmp(buf, "abc") != 0)
+    return 1;
+
+  /* strcatbuff append within capacity */
+  strcatbuff(buf, "de");
+  if (strcmp(buf, "abcde") != 0)
+    return 1;
+
+  /* strncatbuff appends at most N source chars */
+  strcpybuff(buf, "ab");
+  strncatbuff(buf, "cdef", 2);
+  if (strcmp(buf, "abcd") != 0)
+    return 1;
+
+  /* strlcpybuff: explicit-capacity copy into a pointer destination, the form
+     the migration moves toward */
+  {
+    char storage[8];
+    char *const p = storage;
+
+    strlcpybuff(p, "hello", sizeof(storage));
+    if (strcmp(p, "hello") != 0)
+      return 1;
+  }
+
+  /* strcpybuff into a pointer destination: routes through the unchecked
+     strcpybuff_ptr_ fallback (the path the -#8 warning flags). The warning is
+     intentional here; we only verify the fallback still copies correctly. */
+#if defined(__GNUC__)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wattribute-warning"
+#endif
+  {
+    char storage[8];
+    char *const p = storage;
+
+    strcpybuff(p, "ptr");
+    if (strcmp(p, "ptr") != 0)
+      return 1;
+  }
+#if defined(__GNUC__)
+#pragma GCC diagnostic pop
+#endif
+
+  /* htsbuff: bounded builder over a fixed array (append, truncating append,
+     reset, and length tracking) */
+  {
+    char dst[8];
+    htsbuff b = htsbuff_array(dst);
+
+    htsbuff_cat(&b, "ab");
+    htsbuff_cat(&b, "cd");
+    if (strcmp(htsbuff_str(&b), "abcd") != 0 || b.len != 4)
+      return 1;
+
+    htsbuff_catn(&b, "efghij", 2);      /* append at most 2 */
+    if (strcmp(htsbuff_str(&b), "abcdef") != 0)
+      return 1;
+
+    htsbuff_cpy(&b, "xyz");             /* reset */
+    if (strcmp(htsbuff_str(&b), "xyz") != 0 || b.len != 3)
+      return 1;
+
+    htsbuff_catc(&b, '!'); /* single character */
+    if (strcmp(htsbuff_str(&b), "xyz!") != 0 || b.len != 4)
+      return 1;
+  }
+
+  /* boundary: filling to exactly cap-1 must succeed (one more aborts, which the
+     -#8 overflow-buff mode checks) */
+  {
+    char d2[4];
+    htsbuff c = htsbuff_array(d2);
+
+    htsbuff_cat(&c, "abc");
+    if (strcmp(htsbuff_str(&c), "abc") != 0 || c.len != 3)
+      return 1;
+  }
+
+  return 0;
+}
+
 static int hts_main_internal(int argc, char **argv, httrackp * opt);
 
 // Main, récupère les paramètres et appelle le robot
@@ -906,25 +1344,6 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
      }
    */
 
-  /* Engine self-tests: -#test lists them, -#test=NAME [args] runs one. Handled
-     here, ahead of the no-URL usage gate below, so they need no dummy URL. */
-  {
-    int k;
-
-    for (k = 1; k < argc; k++) {
-      const char *const a = argv[k];
-
-      if (a[0] == '-' && a[1] == '#' && strncmp(a + 2, "test", 4) == 0 &&
-          (a[6] == '\0' || a[6] == '=')) {
-        const char *const name = a[6] == '=' ? a + 7 : NULL;
-        const int code = hts_selftest(opt, name, argc - (k + 1), &argv[k + 1]);
-
-        htsmain_free();
-        return code;
-      }
-    }
-  }
-
   // Pas d'URL
 #if DEBUG_STEPS
   printf("Checking URLs\n");
@@ -2013,6 +2432,42 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
           case '#':{           // non documenté
               com++;
               switch (*com) {
+              case 'A': // cache self-test: httrack -#A <dir>
+                if (na + 1 < argc) {
+                  const int err = cache_selftests(opt, argv[na + 1]);
+
+                  printf("cache-selftest: %s\n", err ? "FAIL" : "OK");
+                  htsmain_free();
+                  return err;
+                } else {
+                  fprintf(stderr, "Option #A requires a directory argument\n");
+                  htsmain_free();
+                  return 1;
+                }
+                break;
+              case 'B': // golden cache fixture read: httrack -#B <dir> [regen]
+                if (na + 1 < argc) {
+                  const int regen =
+                      (na + 2 < argc && strcmp(argv[na + 2], "regen") == 0);
+                  const int err =
+                      cache_golden_selftest(opt, argv[na + 1], regen);
+
+                  printf("cache-golden: %s\n", err ? "FAIL" : "OK");
+                  htsmain_free();
+                  return err;
+                } else {
+                  fprintf(stderr, "Option #B requires a directory argument\n");
+                  htsmain_free();
+                  return 1;
+                }
+                break;
+              case 'D': { // DNS resolver/cache self-test (mock getaddrinfo)
+                const int err = dns_selftests(opt);
+
+                printf("dns-selftest: %s\n", err ? "FAIL" : "OK");
+                htsmain_free();
+                return err;
+              } break;
               case 'C':        // list cache files : httrack -#C '*spid*.gif' will attempt to find the matching file
                 {
                   int hasFilter = 0;
@@ -2310,6 +2765,468 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                 }
                 break;
 
+              case '0':        /* test #0 : filters */
+                if (na + 2 >= argc) {
+                  HTS_PANIC_PRINTF
+                    ("Option #0 needs to be followed by a filter string and a string");
+                  printf("Example: '-#0' '*.gif' 'foo.gif'\n");
+                  htsmain_free();
+                  return -1;
+                } else {
+                  if (strjoker(argv[na + 2], argv[na + 1], NULL, NULL))
+                    printf("%s does match %s\n", argv[na + 2], argv[na + 1]);
+                  else
+                    printf("%s does NOT match %s\n", argv[na + 2],
+                           argv[na + 1]);
+                  htsmain_free();
+                  return 0;
+                }
+                break;
+              case '1':        /* test #1 : fil_simplifie */
+                if (na + 1 >= argc) {
+                  HTS_PANIC_PRINTF("Option #1 needs to be followed by an URL");
+                  printf("Example: '-#1' ./foo/bar/../foobar\n");
+                  htsmain_free();
+                  return -1;
+                } else {
+                  fil_simplifie(argv[na + 1]);
+                  printf("simplified=%s\n", argv[na + 1]);
+                  htsmain_free();
+                  return 0;
+                }
+                break;
+              case 'l': /* lienrelatif: relative link from curr_fil to link */
+                if (na + 2 >= argc) {
+                  HTS_PANIC_PRINTF(
+                      "Option #l needs a link and a current-file path");
+                  printf(
+                      "Example: '-#l' 'host/dir/img.gif' 'host/dir/p.html'\n");
+                  htsmain_free();
+                  return -1;
+                } else {
+                  char s[HTS_URLMAXSIZE * 2];
+
+                  if (lienrelatif(s, sizeof(s), argv[na + 1], argv[na + 2]) ==
+                      0)
+                    printf("relative=%s\n", s);
+                  else
+                    printf("relative=<ERROR>\n");
+                  htsmain_free();
+                  return 0;
+                }
+                break;
+              case 'i': /* ident_url_relatif: resolve a link -> adr/fil */
+                if (na + 3 >= argc) {
+                  HTS_PANIC_PRINTF(
+                      "Option #i needs a link, an origin address and file");
+                  printf("Example: '-#i' '../img.gif' 'www.foo.com' "
+                         "'/d/p.html'\n");
+                  htsmain_free();
+                  return -1;
+                } else {
+                  lien_adrfil af;
+                  const int r = ident_url_relatif(argv[na + 1], argv[na + 2],
+                                                  argv[na + 3], &af);
+
+                  if (r == 0)
+                    printf("adr=%s fil=%s\n", af.adr, af.fil);
+                  else
+                    printf("error=%d\n", r);
+                  htsmain_free();
+                  return 0;
+                }
+                break;
+              case '2':        // mimedefs
+                if (na + 1 >= argc) {
+                  HTS_PANIC_PRINTF("Option #2 needs to be followed by an URL");
+                  printf("Example: '-#2' /foo/bar.php\n");
+                  htsmain_free();
+                  return -1;
+                } else {
+                  char mime[256];
+
+                  // initialiser mimedefs
+                  //get_userhttptype(opt,1,opt->mimedefs,NULL);
+                  // check
+                  if (get_httptype_sized(opt, mime, sizeof(mime), argv[na + 1],
+                                         0)) {
+                    char ext[256];
+
+                    printf("%s is '%s'\n", argv[na + 1], mime);
+                    if (give_mimext(ext, sizeof(ext), mime)) {
+                      printf("and its local type is '.%s'\n", ext);
+                    }
+                  } else {
+                    printf("%s is of an unknown MIME type\n", argv[na + 1]);
+                  }
+                  htsmain_free();
+                  return 0;
+                }
+                break;
+              case '3':        // charset tests: httrack -#3 "iso-8859-1" "café"
+                if (++na + 1 < argc) {
+                  char *s =
+                    hts_convertStringToUTF8(argv[na+1], strlen(argv[na+1]), argv[na]);
+                  if (s != NULL) {
+                    printf("%s\n", s);
+                    free(s);
+                  } else {
+                    fprintf(stderr, "invalid string for charset %s\n", argv[na]);
+                  }
+                  na += 2;
+                } else {
+                  fprintf(stderr,
+                    "Option #3 needs to be followed by a charset and a string");
+                }
+                htsmain_free();
+                return 0;
+                break;
+              case '4':  // IDNA encoder: httrack -#4 "www.café.com"
+                if (++na < argc) {
+                  char *s = hts_convertStringUTF8ToIDNA(argv[na], strlen(argv[na]));
+                  if (s != NULL) {
+                    printf("%s\n", s);
+                    free(s);
+                  } else {
+                    fprintf(stderr, "invalid string '%s'\n", argv[na]);
+                  }
+                  na += 1;
+                } else {
+                  fprintf(stderr,
+                    "Option #4 needs to be followed by an IDNA string");
+                }
+                htsmain_free();
+                return 0;
+                break;
+              case '5':  // IDNA encoder: httrack -#5
+                if (++na < argc) {
+                  char *s = hts_convertStringIDNAToUTF8(argv[na], strlen(argv[na]));
+                  if (s != NULL) {
+                    printf("%s\n", s);
+                    free(s);
+                  } else {
+                    fprintf(stderr, "invalid string '%s'\n", argv[na]);
+                  }
+                  na += 1;
+                } else {
+                  fprintf(stderr,
+                    "Option #5 needs to be followed by an IDNA string");
+                }
+                htsmain_free();
+                return 0;
+                break;
+              case '6':  // entities: httrack -#6 "&foo;" ["encoding"]
+                if (++na < argc) {
+                  char *const s = strdup(argv[na]);
+                  const char *const enc = na + 1 < argc ? argv[na + 1] : "UTF-8";
+                  if (s != NULL 
+                    && hts_unescapeEntitiesWithCharset(s, s, strlen(s), 
+                                                       enc) == 0) {
+                    printf("%s\n", s);
+                    free(s);
+                  } else {
+                    fprintf(stderr, "invalid string '%s'\n", argv[na]);
+                  }
+                  na += 1;
+                } else {
+                  fprintf(stderr,
+                    "Option #6 needs to be followed by a string");
+                }
+                htsmain_free();
+                return 0;
+                break;
+              case '8':        /* string-safety selftest: httrack -#8 [overflow <bigstr>] */
+                if (na + 1 < argc
+                    && strncmp(argv[na + 1], "overflow", 8) == 0) {
+                  /* Deliberately exceed a sized buffer: the bounded op must
+                     abort. The source comes from argv so its length is opaque
+                     to the compiler (no static -Wstringop-overflow, genuine
+                     runtime check). "overflow-buff" exercises htsbuff. */
+                  char small[4];
+                  const char *const src =
+                    (na + 2 < argc) ? argv[na + 2] : "overflowing";
+
+                  if (strcmp(argv[na + 1], "overflow-buff") == 0) {
+                    htsbuff b = htsbuff_array(small);
+
+                    htsbuff_cat(&b, src);
+                  } else {
+                    strcpybuff(small, src);
+                  }
+                  printf("strsafe: NOT aborted\n");     /* must be unreachable */
+                  htsmain_free();
+                  return 1;
+                } else {
+                  const int err = string_safety_selftests();
+
+                  printf("strsafe: %s\n", err ? "FAIL" : "OK");
+                  htsmain_free();
+                  return err;
+                }
+                break;
+              case '7':  // hashtable selftest: httrack -#7 nb_entries
+                basic_selftests();
+                if (++na < argc) {
+                  char *const snum = strdup(argv[na]);
+                  unsigned long count = 0;
+                  const char *const names[] = {
+                    "", "add", "delete", "dry-add", "dry-del",
+                    "test-exists", "test-not-exist"
+                  };
+                  const struct {
+                    enum {
+                      DO_END,
+                      DO_ADD,
+                      DO_DEL,
+                      DO_DRY_ADD,
+                      DO_DRY_DEL,
+                      TEST_ADD,
+                      TEST_DEL
+                    } type;
+                    size_t modulus;
+                    size_t offset;
+                  } bench[] = {
+                    { DO_ADD, 4, 0 },     /* add 4/0 */
+                    { TEST_ADD, 4, 0 },   /* check 4/0 */
+                    { TEST_DEL, 4, 1 },   /* check 4/1 */
+                    { TEST_DEL, 4, 2 },   /* check 4/2 */
+                    { TEST_DEL, 4, 3 },   /* check 4/3 */
+                    { DO_DRY_DEL, 4, 1 }, /* del 4/1 */
+                    { DO_DRY_DEL, 4, 2 }, /* del 4/2 */
+                    { DO_DRY_DEL, 4, 3 }, /* del 4/3 */
+                    { DO_ADD, 4, 1 },     /* add 4/1 */
+                    { DO_DRY_ADD, 4, 1 }, /* add 4/1 */
+                    { TEST_ADD, 4, 0 },   /* check 4/0 */
+                    { TEST_ADD, 4, 1 },   /* check 4/1 */
+                    { TEST_DEL, 4, 2 },   /* check 4/2 */
+                    { TEST_DEL, 4, 3 },   /* check 4/3 */
+                    { DO_ADD, 4, 2 },     /* add 4/2 */
+                    { DO_DRY_DEL, 4, 3 }, /* del 4/3 */
+                    { DO_ADD, 4, 3 },     /* add 4/3 */
+                    { DO_DEL, 4, 3 },     /* del 4/3 */
+                    { TEST_ADD, 4, 0 },   /* check 4/0 */
+                    { TEST_ADD, 4, 1 },   /* check 4/1 */
+                    { TEST_ADD, 4, 2 },   /* check 4/2 */
+                    { TEST_DEL, 4, 3 },   /* check 4/3 */
+                    { DO_DEL, 4, 0 },     /* del 4/0 */
+                    { DO_DEL, 4, 1 },     /* del 4/1 */
+                    { DO_DEL, 4, 2 },     /* del 4/2 */
+                    /* empty here */
+                    { TEST_DEL, 1, 0 },   /* check */
+                    { DO_ADD, 4, 0 },     /* add 4/0 */
+                    { DO_ADD, 4, 1 },     /* add 4/1 */
+                    { DO_ADD, 4, 2 },     /* add 4/2 */
+                    { DO_DEL, 42, 0 },    /* add 42/0 */
+                    { TEST_DEL, 42, 0 },  /* check 42/0 */
+                    { TEST_ADD, 42, 2 },  /* check 42/2 */
+                    { DO_END }
+                  };
+                  char *buff = NULL;
+                  const char **strings = NULL;
+
+                  /* produce key #i */
+#define FMT() \
+                  char buffer[256]; \
+                  const char *name; \
+                  const long expected = (long) i * 1664525 + 1013904223; \
+                  do { \
+                    if (strings == NULL) { \
+                      snprintf(buffer, sizeof(buffer), \
+                        "http://www.example.com/website/sample/for/hashtable/" \
+                        "%ld/index.html?foo=%ld&bar", \
+                        (long) i, (long) (expected)); \
+                      name = buffer; \
+                    } else { \
+                      name = strings[i]; \
+                    } \
+                  } while(0)
+
+                  /* produce random patterns, or read from a file */
+                  if (sscanf(snum, "%lu", &count) != 1) {
+                    const off_t size = fsize(snum);
+                    FILE *fp = fopen(snum, "rb");
+                    if (fp != NULL) {
+                      buff = malloc(size);
+                      if (buff != NULL && fread(buff, 1, size, fp) == size) {
+                        size_t capa = 0;
+                        size_t i, last;
+                        for(i = 0, last = 0, count = 0 ; i < size ; i++) {
+                          if (buff[i] == 10 || buff[i] == 0) {
+                            buff[i] = '\0';
+                            if (capa == count) {
+                              if (capa == 0) {
+                                capa = 16;
+                              } else {
+                                capa <<= 1;
+                              }
+                              strings = (const char **) realloc((void*) strings, capa*sizeof(char*));
+                            }
+                            strings[count++] = &buff[last];
+                            last = i + 1;
+                          }
+                        }
+                      }
+                      fclose(fp);
+                    }
+                  }
+
+                  /* successfully read */
+                  if (count > 0) {
+                    coucal hashtable = coucal_new(0);
+                    size_t loop;
+                    for(loop = 0 ; bench[loop].type != DO_END ; loop++) {
+                      size_t i;
+                      for(i = bench[loop].offset ; i < (size_t) count
+                          ; i += bench[loop].modulus) {
+                        int result;
+                        FMT();
+                        if (bench[loop].type == DO_ADD
+                            || bench[loop].type == DO_DRY_ADD) {
+                          size_t k;
+                          result = coucal_write(hashtable, name, (uintptr_t) expected);
+                          for(k = 0 ; k < /* stash_size*2 */ 32 ; k++) {
+                            (void) coucal_write(hashtable, name, (uintptr_t) expected);
+                          }
+                          /* revert logic */
+                          if (bench[loop].type == DO_DRY_ADD) {
+                            result = result ? 0 : 1;
+                          }
+                        }
+                        else if (bench[loop].type == DO_DEL
+                            || bench[loop].type == DO_DRY_DEL) {
+                          size_t k;
+                          result = coucal_remove(hashtable, name);
+                          for(k = 0 ; k < /* stash_size*2 */ 32 ; k++) {
+                            (void) coucal_remove(hashtable, name);
+                          }
+                          /* revert logic */
+                          if (bench[loop].type == DO_DRY_DEL) {
+                            result = result ? 0 : 1;
+                          }
+                        }
+                        else if (bench[loop].type == TEST_ADD
+                            || bench[loop].type == TEST_DEL) {
+                          intptr_t value = -1;
+                          result = coucal_readptr(hashtable, name, &value);
+                          if (bench[loop].type == TEST_ADD && result
+                              && value != expected) {
+                            fprintf(stderr, "value failed for %s (expected %ld, got %ld)\n",
+                                    name, (long) expected, (long) value);
+                            exit(EXIT_FAILURE);
+                          }
+                          /* revert logic */
+                          if (bench[loop].type == TEST_DEL) {
+                            result = result ? 0 : 1;
+                          }
+                        }
+                        if (!result) {
+                          fprintf(stderr, "failed %s{%d/+%d} test on loop %ld"
+                                  " at offset %ld for %s\n",
+                                  names[bench[loop].type],
+                                  (int) bench[loop].modulus,
+                                  (int) bench[loop].offset,
+                                  (long) loop, (long) i, name);
+                          exit(EXIT_FAILURE);
+                        }
+                      }
+                    }
+                    coucal_delete(&hashtable);
+                    fprintf(stderr, "all hashtable tests were successful!\n");
+                  } else {
+                    fprintf(stderr, "Malformed number\n");
+                    exit(EXIT_FAILURE);
+                  }
+#undef FMT
+                } else {
+                  fprintf(stderr,
+                    "Option #7 needs to be followed by a number");
+                  exit(EXIT_FAILURE);
+                }
+                htsmain_free();
+                return 0;
+                break;
+              case '9': { // copy_htsopt selftest: httrack -#9
+                httrackp *from = hts_create_opt();
+                httrackp *to = hts_create_opt();
+                int err = 0;
+
+                /* from-values differ from both the to-values and the
+                   hts_create_opt() defaults (nearlink FALSE, errpage/parseall
+                   TRUE), so a copy that no-ops or just resets to defaults is
+                   caught too, not only the unsigned-guard bug. */
+                from->retry = 7; /* int field: positive control */
+                to->retry = 0;
+                from->nearlink = HTS_TRUE;
+                to->nearlink = HTS_FALSE;
+                from->errpage = HTS_FALSE;
+                to->errpage = HTS_TRUE;
+                from->parseall = HTS_FALSE;
+                to->parseall = HTS_TRUE;
+
+                copy_htsopt(from, to);
+
+                if (to->retry != 7)
+                  err = 1;
+                if (to->nearlink != HTS_TRUE)
+                  err = 1;
+                if (to->errpage != HTS_FALSE)
+                  err = 1;
+                if (to->parseall != HTS_FALSE)
+                  err = 1;
+
+                /* HTS_DEFAULT (-1) is "unspecified": copy_htsopt must skip it,
+                   leaving the target intact. Only a signed (int-backed) field
+                   can hold -1, so this also guards the type against regressing
+                   to an unsigned hts_boolean. */
+                from->parseall = HTS_DEFAULT;
+                to->parseall = HTS_TRUE;
+                copy_htsopt(from, to);
+                if (to->parseall != HTS_TRUE)
+                  err = 1;
+
+                hts_free_opt(from);
+                hts_free_opt(to);
+                printf("copy-htsopt: %s\n", err ? "FAIL" : "OK");
+                htsmain_free();
+                return err;
+              } break;
+              case 'Q': { // cookie request-header selftest: httrack -#Q
+                static t_cookie cookie;
+                char hdr[1024];
+                /* RFC 6265: bare name=value pairs, no $Version/$Path (#151). */
+                const char *expected = "Cookie: name=value; has_js=1" H_CRLF;
+                int err = 0;
+
+                const char *dom = "www.example.com";
+                int added;
+
+                cookie.max_len = (int) sizeof(cookie.data);
+                cookie.data[0] = '\0';
+                added = cookie_add(&cookie, "name", "value", dom, "/");
+                added |= cookie_add(&cookie, "has_js", "1", dom, "/");
+                /* different domain: must be filtered out */
+                added |= cookie_add(&cookie, "junk", "x", "other.org", "/");
+                if (added) {
+                  printf("cookie-header: FAIL (cookie_add setup)\n");
+                  htsmain_free();
+                  return 1;
+                }
+
+                http_cookie_header_selftest(&cookie, dom, "/", hdr,
+                                            sizeof(hdr));
+                if (strcmp(hdr, expected) != 0)
+                  err = 1;
+                if (strstr(hdr, "$Version") != NULL ||
+                    strstr(hdr, "$Path") != NULL)
+                  err = 1;
+                if (strstr(hdr, "junk") != NULL) // wrong-domain cookie leaked
+                  err = 1;
+                printf("cookie-header: %s\n", err ? "FAIL" : "OK");
+                if (err)
+                  printf("  got: %s\n", hdr);
+                htsmain_free();
+                return err;
+              } break;
               case '!':
                 HTS_PANIC_PRINTF
                   ("Option #! is disabled for security reasons");

src/htsfilters.c

@@ -76,8 +76,7 @@ int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * siz
     }
     if (size)
       sz = *size;
-    /* size unknown (scan time): no size pointer => size tests stay neutral */
-    if (strjoker(nom, filters[i] + filteroffs, size ? &sz : NULL, size_flag)) {
+    if (strjoker(nom, filters[i] + filteroffs, &sz, size_flag)) {       // reconnu
       if (size)
         if (sz != *size)
           sizelimit = sz;

src/htshelp.c

@@ -646,7 +646,9 @@ void help(const char *app, int more) {
   infomsg("");
   infomsg("Guru options: (do NOT use if possible)");
   infomsg(" #X *use optimized engine (limited memory boundary checks)");
-  infomsg(" #test  list engine self-tests (run one with -#test=NAME [args])");
+  infomsg(" #0  filter test (-#0 '*.gif' 'www.bar.com/foo.gif')");
+  infomsg(" #1  simplify test (-#1 ./foo/bar/../foobar)");
+  infomsg(" #2  type test (-#2 /foo/bar.php)");
   infomsg(" #C  cache list (-#C '*.com/spider*.gif'");
   infomsg(" #R  cache repair (damaged cache)");
   infomsg(" #d  debug parser");

src/htslib.c

@@ -4177,10 +4177,9 @@ HTSEXT_API hts_boolean get_httptype_sized(httrackp *opt, char *s, size_t ssize,
     /* Check html -> text/html */
     const char *a = fil + strlen(fil) - 1;
 
-    /* a < fil when fil is empty: bound before dereferencing */
-    while ((a > fil) && (*a != '.') && (*a != '/'))
+    while((*a != '.') && (*a != '/') && (a > fil))
       a--;
-    if (a >= fil && *a == '.' && strlen(a) < 32) {
+    if (*a == '.' && strlen(a) < 32) {
       int j = 0;
 
       a++;
@@ -4767,51 +4766,64 @@ int hts_read(htsblk * r, char *buff, int size) {
 // -- Gestion cache DNS --
 // 'RX98
 
-// Free a DNS cache record (coucal value handler).
-static void hts_cache_value_free(coucal_opaque arg, coucal_value value) {
-  void *record = value.ptr;
-
-  (void) arg;
-  freet(record);
-}
-
-// opt's DNS cache hashtable, created on first use. Records (t_dnscache*) are
-// owned by the table and freed by hts_cache_value_free on coucal_delete.
-coucal hts_cache(httrackp *opt) {
+// 'capsule' contenant uniquement le cache
+t_dnscache *hts_cache(httrackp * opt) {
   assertf(opt != NULL);
   if (opt->state.dns_cache == NULL) {
-    coucal cache = coucal_new(0);
-
-    coucal_set_name(cache, "dns_cache");
-    coucal_value_set_value_handler(cache, hts_cache_value_free, NULL);
-    opt->state.dns_cache = cache;
+    opt->state.dns_cache = (t_dnscache *) malloct(sizeof(t_dnscache));
+    memset(opt->state.dns_cache, 0, sizeof(t_dnscache));
   }
   assertf(opt->state.dns_cache != NULL);
+  /* first entry is NULL */
+  assertf(opt->state.dns_cache->iadr == NULL);
   return opt->state.dns_cache;
 }
 
-// MUST BE LOCKED (coucal is not internally serialized vs FTP/web threads)
+// Free DNS cache.
+void hts_cache_free(t_dnscache *const root) {
+  if (root != NULL) {
+    t_dnscache *cache;
+    for(cache = root; cache != NULL; ) {
+      t_dnscache *const next = cache->next;
+      cache->next = NULL;
+      freet(cache);
+      cache = next;
+    }
+  }
+}
+
+// lock le cache dns pour tout opération d'ajout
+// plus prudent quand plusieurs threads peuvent écrire dedans..
+// -1: status? 0: libérer 1:locker
+
+// MUST BE LOCKED
 // Look up iadr in the DNS cache, filling out[0..min(count,max)-1].
 // Returns: -1 not yet tested; 0 negative-cached (not in DNS); >0 address count.
-static int hts_ghbn_all(coucal cache, const char *const iadr,
+static int hts_ghbn_all(const t_dnscache *cache, const char *const iadr,
                         SOCaddr *const out, const int max) {
-  void *ptr;
-
   assertf(out != NULL);
   assertf(iadr != NULL);
   if (*iadr == '\0') {
     return -1;
   }
-  if (coucal_read_pvoid(cache, iadr, &ptr)) { // ok trouvé
-    const t_dnscache *const record = (const t_dnscache *) ptr;
-    int i;
+  /* first entry is empty */
+  if (cache->iadr == NULL) {
+    cache = cache->next;
+  }
+  for(; cache != NULL; cache = cache->next) {
+    assertf(cache != NULL);
+    assertf(cache->iadr != NULL);
+    assertf(cache->iadr == (const char*) cache + sizeof(t_dnscache));
+    if (strcmp(cache->iadr, iadr) == 0) {       // ok trouvé
+      int i;
 
-    assertf(record->host_count <= HTS_MAXADDRNUM);
-    for (i = 0; i < record->host_count && i < max; i++) {
-      assertf(record->host_length[i] <= sizeof(record->host_addr[i]));
-      SOCaddr_copyaddr2(out[i], record->host_addr[i], record->host_length[i]);
+      assertf(cache->host_count <= HTS_MAXADDRNUM);
+      for (i = 0; i < cache->host_count && i < max; i++) {
+        assertf(cache->host_length[i] <= sizeof(cache->host_addr[i]));
+        SOCaddr_copyaddr2(out[i], cache->host_addr[i], cache->host_length[i]);
+      }
+      return cache->host_count;
     }
-    return record->host_count;
   }
   return -1;
 }
@@ -5076,7 +5088,7 @@ static int hts_dns_resolve_list_(httrackp *opt, const char *_iadr,
                                  SOCaddr *const out, const int max,
                                  const char **error) {
   char BIGSTK iadr[HTS_URLMAXSIZE * 2];
-  coucal cache = hts_cache(opt); // le cache dns
+  t_dnscache *cache = hts_cache(opt);  // adresse du cache
   int count;
 
   assertf(opt != NULL);
@@ -5097,10 +5109,13 @@ static int hts_dns_resolve_list_(httrackp *opt, const char *_iadr,
   if (count >= 0) { // cache hit (0 == negative-cached)
     return count;
   } else { // non présent dans le cache dns, tester
+    const size_t iadr_len = strlen(iadr) + 1;
     SOCaddr resolved[HTS_MAXADDRNUM];
-    t_dnscache *record;
     int i;
 
+    // find queue
+    for(; cache->next != NULL; cache = cache->next) ;
+
 #if DEBUGDNS
     printf("resolving (not cached) %s\n", iadr);
 #endif
@@ -5111,18 +5126,22 @@ static int hts_dns_resolve_list_(httrackp *opt, const char *_iadr,
     DEBUG_W("gethostbyname done\n");
 #endif
 
-    /* attempt to store new entry (coucal owns it and dups the host key) */
-    record = malloct(sizeof(t_dnscache));
-    if (record != NULL) {
-      memset(record, 0, sizeof(*record));
-      record->host_count = count;
+    /* attempt to store new entry */
+    cache->next = malloct(sizeof(t_dnscache) + iadr_len);
+    if (cache->next != NULL) {
+      t_dnscache *const next = cache->next;
+      char *const block = (char*) cache->next;
+      char *const str = block + sizeof(t_dnscache);
+      memcpy(str, iadr, iadr_len);
+      next->iadr = str;
+      next->host_count = count;
       for (i = 0; i < count; i++) {
-        record->host_length[i] = SOCaddr_size(resolved[i]);
-        assertf(record->host_length[i] <= sizeof(record->host_addr[i]));
-        memcpy(record->host_addr[i], &SOCaddr_sockaddr(resolved[i]),
-               record->host_length[i]);
+        next->host_length[i] = SOCaddr_size(resolved[i]);
+        assertf(next->host_length[i] <= sizeof(next->host_addr[i]));
+        memcpy(next->host_addr[i], &SOCaddr_sockaddr(resolved[i]),
+               next->host_length[i]);
       }
-      coucal_add_pvoid(cache, iadr, record);
+      next->next = NULL;
     }
 
     /* copy result to caller (cache store may have failed; result still valid)
@@ -5993,14 +6012,14 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
 
     /* Cache */
     if (opt->state.dns_cache != NULL) {
-      coucal root;
+      t_dnscache *root;
 
       hts_mutexlock(&opt->state.lock);
       root = opt->state.dns_cache;
       opt->state.dns_cache = NULL;
       hts_mutexrelease(&opt->state.lock);
 
-      coucal_delete(&root); // frees records via hts_cache_value_free
+      hts_cache_free(root);
     }
 
     /* Cancel chain */

src/htslib.h

@@ -147,8 +147,9 @@ struct OLD_htsblk {
 #define HTS_DEF_FWSTRUCT_t_dnscache
 typedef struct t_dnscache t_dnscache;
 #endif
-// One DNS cache record, stored as a coucal value keyed by hostname.
 struct t_dnscache {
+  struct t_dnscache *next;
+  const char *iadr;
   // resolved addresses, in resolver (RFC 6724) order; host_count==0 means the
   // name does not resolve (negative cache). host_count<=HTS_MAXADDRNUM.
   int host_count;
@@ -244,9 +245,8 @@ HTSEXT_API int check_hostname_dns(const char *const hostname);
 int ftp_available(void);
 
 #if HTS_DNSCACHE
-/* Return opt's DNS cache hashtable (hostname -> t_dnscache record), creating it
-   on first use. Records are owned by the table and freed on coucal_delete. */
-coucal hts_cache(httrackp *opt);
+void hts_cache_free(t_dnscache *const cache);
+t_dnscache *hts_cache(httrackp * opt);
 #endif
 
 // outils divers

src/htsname.c

@@ -760,9 +760,9 @@ int url_savename(lien_adrfilsave *const afs,
         strcatbuff(fil, DEFAULT_HTML);  // nommer page par défaut (à priori ici html depuis un proxy http)
     }
   }
-  // Change the extension? e.g. php3 saved as html, cgi as html or gif/xbm
-  // depending on the resolved type.
-  if (ext_chg && !opt->no_type_change) {
+  // Changer extension?
+  // par exemple, php3 sera sauvé en html, cgi en html ou gif, xbm etc.. selon les cas
+  if (ext_chg && !opt->no_type_change) {                // changer ext
     char *a = fil + strlen(fil) - 1;
 
     if ((opt->debug > 1) && (opt->log != NULL)) {
@@ -774,19 +774,11 @@ int url_savename(lien_adrfilsave *const afs,
                       adr_complete, fil_complete, ext);
     }
     if (ext_chg == 1) {
-      // Cut the old extension only when it is empty (a bare trailing dot), the
-      // new one, or a recognized one; an unknown trailing ".token" (e.g.
-      // /article-1.884291, #115) is part of the name, not an extension.
-      const char *const old_ext = get_ext(catbuff, sizeof(catbuff), fil);
-      const int known_ext = !*old_ext || strfield2(old_ext, ext) ||
-                            is_knowntype(opt, fil) || is_dyntype(old_ext) ||
-                            ishtml_ext(old_ext) != -1;
-
       while((a > fil) && (*a != '.') && (*a != '/'))
         a--;
-      if (*a == '.' && known_ext)
-        *a = '\0';          // cut
-      strcatbuff(fil, "."); // re-add the dot
+      if (*a == '.')
+        *a = '\0';              // couper
+      strcatbuff(fil, ".");     // recopier point
     } else {
       while((a > fil) && (*a != '/'))
         a--;
@@ -794,7 +786,7 @@ int url_savename(lien_adrfilsave *const afs,
         a++;
       *a = '\0';
     }
-    strcatbuff(fil, ext); // append ext/name
+    strcatbuff(fil, ext);       // copier ext/nom
   }
   // Rechercher premier / et dernier .
   {
@@ -1729,10 +1721,10 @@ char *url_savename_refname_fullpath(httrackp * opt, const char *adr,
     StringBuff(opt->path_log), digest_filename);
 }
 
-/* remove refname if any; HTS_TRUE if it was removed */
-hts_boolean url_savename_refname_remove(httrackp *opt, const char *adr,
-                                        const char *fil) {
+/* remove refname if any */
+void url_savename_refname_remove(httrackp * opt, const char *adr,
+                                 const char *fil) {
   char *filename = url_savename_refname_fullpath(opt, adr, fil);
 
-  return UNLINK(filename) == 0 ? HTS_TRUE : HTS_FALSE;
+  (void) UNLINK(filename);
 }

src/htsname.h

@@ -104,9 +104,8 @@ char *url_md5(char *digest_buffer, const char *fil_complete);
 void url_savename_refname(const char *adr, const char *fil, char *filename);
 char *url_savename_refname_fullpath(httrackp * opt, const char *adr,
                                     const char *fil);
-/* Remove the temp-ref for (adr,fil); HTS_TRUE if it was removed. */
-hts_boolean url_savename_refname_remove(httrackp *opt, const char *adr,
-                                        const char *fil);
+void url_savename_refname_remove(httrackp * opt, const char *adr,
+                                 const char *fil);
 #endif
 
 #endif

src/htsopt.h

@@ -241,7 +241,7 @@ struct htsoptstate {
   char *userhttptype;
   int verif_backblue_done; /**< backblue.gif/fade.gif already emitted */
   int verif_external_status;
-  coucal dns_cache; /**< DNS resolution cache: hostname -> t_dnscache record */
+  t_dnscache *dns_cache;  /**< DNS resolution cache */
   int dns_cache_nthreads; /**< number of in-flight DNS resolver threads */
   /* HTML parsing state */
   char _hts_errmsg[HTS_CDLMAXSIZE + 256]; /**< last engine error message */

src/htsparse.c

@@ -3749,60 +3749,44 @@ int hts_mirror_check_moved(htsmoduleStruct * str,
 
       }                         // bloc
       // erreur HTTP (ex: 404, not found)
-    } else if ((r->statuscode == HTTP_PRECONDITION_FAILED) ||
-               (r->statuscode == HTTP_REQUESTED_RANGE_NOT_SATISFIABLE)) {
-      // 412/416: the resume partial is stale; re-get the whole file (#206)
-      lien_back *itemback = NULL;
-      int had_partial = 0;
-      int ref_existed = 0;
-      int ref_gone;
-
-      // Drop the temp-ref, its partial, and heap->sav so the re-get carries no
-      // Range; else back_add rebuilds the same Range and loops.
-      if (back_unserialize_ref(opt, heap(ptr)->adr, heap(ptr)->fil,
-                               &itemback) == 0) {
-        had_partial = 1;
-        ref_existed = 1;
-        // best-effort: an orphaned partial cannot re-Range once the ref is gone
-        if (fexist_utf8(itemback->url_sav))
-          (void) UNLINK(fconv(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                              itemback->url_sav));
-        back_clear_entry(itemback);
-        freet(itemback);
-      }
-      // don't re-record if the ref survived (it would re-Range and loop)
-      ref_gone =
-          url_savename_refname_remove(opt, heap(ptr)->adr, heap(ptr)->fil) ||
-          !ref_existed;
+    } else if ((r->statuscode == HTTP_PRECONDITION_FAILED)
+               || (r->statuscode == HTTP_REQUESTED_RANGE_NOT_SATISFIABLE)
+      ) {                       // Precondition Failed, c'est à dire pour nous redemander TOUT le fichier
       if (fexist_utf8(heap(ptr)->sav)) {
-        had_partial = 1;
-        remove(heap(ptr)->sav);
+        remove(heap(ptr)->sav);        // Eliminer
+      } else {
+        hts_log_print(opt, LOG_WARNING,
+                      "Unexpected 412/416 error (%s) for %s%s, '%s' could not be found on disk",
+                      r->msg, urladr(), urlfil(),
+                      heap(ptr)->sav != NULL ? heap(ptr)->sav : "");
       }
-
-      // Re-get once, only if a partial existed and both Range triggers are
-      // gone; a failed removal gives up rather than looping. range_used is
-      // unreliable (it does not survive the delayed-type two-pass).
-      if (had_partial && ref_gone && !fexist_utf8(heap(ptr)->sav)) {
+      if (!fexist_utf8(heap(ptr)->sav)) {    // Bien éliminé? (sinon on boucle..)
+#if HDEBUG
+        printf("Partial content NOT up-to-date, reget all file for %s\n",
+               heap(ptr)->sav);
+#endif
         hts_log_print(opt, LOG_DEBUG, "Partial file reget (%s) for %s%s",
                       r->msg, urladr(), urlfil());
+        // enregistrer le MEME lien
         if (hts_record_link(opt, heap(ptr)->adr, heap(ptr)->fil, heap(ptr)->sav, "", "", NULL)) {
-          heap_top()->testmode = heap(ptr)->testmode;
-          heap_top()->link_import = 0;
+          heap_top()->testmode = heap(ptr)->testmode;   // mode test?
+          heap_top()->link_import = 0;   // pas mode import
           heap_top()->depth = heap(ptr)->depth;
           heap_top()->pass2 = max(heap(ptr)->pass2, numero_passe);
           heap_top()->retry = heap(ptr)->retry;
           heap_top()->premier = heap(ptr)->premier;
           heap_top()->precedent = ptr;
+          //
+          // canceller lien actuel
           error = 1;
-          hts_invalidate_link(opt, ptr); // invalidate hashtable entry
-        } else {                         // out of memory
-          XH_uninit;
+          hts_invalidate_link(opt, ptr);  // invalidate hashtable entry
+          //
+        } else {              // oups erreur, plus de mémoire!!
+          XH_uninit;          // désallocation mémoire & buffers
           return 0;
         }
       } else {
-        hts_log_print(opt, LOG_WARNING,
-                      "Giving up on partial reget (%s) for %s%s", r->msg,
-                      urladr(), urlfil());
+        hts_log_print(opt, LOG_ERROR, "Can not remove old file %s", urlfil());
         error = 1;
       }
 

src/htsselftest.h

@@ -1,52 +0,0 @@
-/* ------------------------------------------------------------ */
-/*
-HTTrack Website Copier, Offline Browser for Windows and Unix
-Copyright (C) 2026 Xavier Roche and other contributors
-
-SPDX-License-Identifier: GPL-3.0-or-later
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-Ethical use: we kindly ask that you NOT use this software to harvest email
-addresses or to collect any other private information about people. Doing so
-would dishonor our work and waste the many hours we have spent on it.
-
-Please visit our Website: http://www.httrack.com
-*/
-
-/* ------------------------------------------------------------ */
-/* File: htsselftest.h                                          */
-/*       named dispatch for the hidden engine self-tests        */
-/* Author: Xavier Roche                                         */
-/* ------------------------------------------------------------ */
-
-#ifndef HTSSELFTEST_DEFH
-#define HTSSELFTEST_DEFH
-
-#ifdef HTS_INTERNAL_BYTECODE
-
-#ifndef HTS_DEF_FWSTRUCT_httrackp
-#define HTS_DEF_FWSTRUCT_httrackp
-typedef struct httrackp httrackp;
-#endif
-
-/* Run engine self-test `name` over the positional args argv[0..argc-1], or list
-   the available tests when name is NULL, empty, or "list". Prints the result;
-   returns the process exit code (0 == success). The caller owns option cleanup.
-   Reached through the hidden `httrack -#test[=NAME ...]` subcommand. */
-int hts_selftest(httrackp *opt, const char *name, int argc, char **argv);
-
-#endif
-
-#endif

tests/01_engine-cache-golden.test

@@ -4,7 +4,7 @@
 # POSIX /bin/sh on some platforms (e.g. macOS), so avoid bashisms and GNU-only
 # tool flags despite the #!/bin/bash above.
 
-# Golden cache-format regression test (driven by 'httrack -#test=cache-golden <dir>').
+# Golden cache-format regression test (driven by 'httrack -#B <dir>').
 #
 # 01_engine-cache.test writes the cache with the same build it reads back (a
 # round-trip), so it cannot catch a read-path or ZIP-format regression where
@@ -13,7 +13,7 @@
 # byte-exact.
 #
 # Regenerate the fixture after a deliberate format change with
-# 'httrack -#test=cache-golden <dir> regen', then copy <dir>/hts-cache/new.zip over the
+# 'httrack -#B <dir> regen', then copy <dir>/hts-cache/new.zip over the
 # committed file.
 
 set -eu
@@ -37,11 +37,11 @@ trap 'rm -rf "$dir"' EXIT
 mkdir -p "$dir/hts-cache"
 cp "$fixture/hts-cache/new.zip" "$dir/hts-cache/new.zip"
 
-out=$(httrack -#test=cache-golden "$dir")
+out=$(httrack -#B "$dir")
 
 # Match the exact success line: the read must have found and verified every
-# entry, not merely failed to enter the mode (a renamed/removed test prints the
-# registry to stderr, which also exits non-zero but never prints this).
+# entry, not merely failed to enter the mode (a bad -#B falls through to the
+# usage screen, which also exits non-zero but never prints this).
 test "$out" = "cache-golden: OK" || {
     echo "expected 'cache-golden: OK', got: $out" >&2
     exit 1

tests/01_engine-cache-writefail.test

@@ -1,24 +0,0 @@
-#!/bin/bash
-#
-# Keep this POSIX-portable: the harness runs it via $(BASH), which is a plain
-# POSIX /bin/sh on some platforms (e.g. macOS), so avoid bashisms and GNU-only
-# tool flags despite the #!/bin/bash above.
-
-# Cache write-failure handling (httrack -#test=cache-writefail <dir>). #174/#219.
-# A failing new.zip write (disk full) used to crash the process via assertf; it
-# must instead stop the mirror with a fatal error (exit_xh=-1), no crash. The
-# self-test asserts that; reverting the fix makes -#test=cache-writefail abort (SIGABRT) and fail.
-
-set -eu
-
-dir=$(mktemp -d)
-trap 'rm -rf "$dir"' EXIT
-
-out=$(httrack -#test=cache-writefail "$dir")
-
-# Match the exact success line (error logs also go to stdout); a renamed/removed
-# test prints the registry to stderr, which exits non-zero but never prints this.
-printf '%s\n' "$out" | grep -qx "cache-writefail: OK" || {
-    echo "expected 'cache-writefail: OK', got: $out" >&2
-    exit 1
-}

tests/01_engine-cache.test

@@ -4,7 +4,7 @@
 # POSIX /bin/sh on some platforms (e.g. macOS), so avoid bashisms and GNU-only
 # tool flags despite the #!/bin/bash above.
 
-# Cache create/read/update logic (driven by 'httrack -#test=cache <dir>').
+# Cache create/read/update logic (driven by 'httrack -#A <dir>').
 #
 # The in-process self-test stores several hand-crafted edge entries (normal
 # HTML, an empty redirect with a near-limit location, a non-HTML body kept via
@@ -20,13 +20,13 @@ set -eu
 dir=$(mktemp -d)
 trap 'rm -rf "$dir"' EXIT
 
-# The working directory is a required argument; without it the test prints a
-# usage line to stderr and returns non-zero.
-out=$(httrack -#test=cache "$dir")
+# Like the other -# debug modes, a trailing token (the working directory) is
+# required; a bare '-#A' falls through to the usage screen.
+out=$(httrack -#A "$dir")
 
 # Match the exact success line, so the test cannot pass for an unrelated reason
-# (e.g. the cache test being gone, which prints the registry to stderr but
-# never prints this line).
+# (e.g. the -#A mode being gone and falling through to the usage screen, which
+# also exits non-zero but never prints this).
 test "$out" = "cache-selftest: OK" || {
     echo "expected 'cache-selftest: OK', got: $out" >&2
     exit 1

tests/01_engine-charset.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # charset -> UTF-8 conversion (hts_convertStringToUTF8).
-# -#test=charset <charset> <string> prints the string re-decoded from <charset> as UTF-8.
+# -#3 <charset> <string> prints the string re-decoded from <charset> as UTF-8.
 conv() {
-    test "$(httrack -O /dev/null -#test=charset "$1" "$2")" == "$3" || exit 1
+    test "$(httrack -O /dev/null -#3 "$1" "$2")" == "$3" || exit 1
 }
 # crash probe: malformed input must exit cleanly, not abort.
 runs() {
-    httrack -O /dev/null -#test=charset "$1" "$2" >/dev/null 2>&1 || exit 1
+    httrack -O /dev/null -#3 "$1" "$2" >/dev/null 2>&1 || exit 1
 }
 
 # the source bytes below are UTF-8 (this file is UTF-8); "café" is 0x63 61 66 C3 A9.
@@ -31,7 +31,7 @@ conv 'us-ascii' 'hello' 'hello'
 # unknown charset: ASCII passes through unchanged, but non-ASCII input cannot be
 # decoded and yields empty output (an error is printed to stderr).
 conv 'no-such-charset-xyz' 'abc' 'abc'
-test "$(httrack -O /dev/null -#test=charset 'no-such-charset-xyz' 'café' 2>/dev/null)" == "" || exit 1
+test "$(httrack -O /dev/null -#3 'no-such-charset-xyz' 'café' 2>/dev/null)" == "" || exit 1
 
 # malformed UTF-8 (lone continuation byte, truncated lead byte) must not crash
 runs 'utf-8' $'\x80'

tests/01_engine-cookies.test

@@ -1,15 +1,14 @@
 #!/bin/bash
 #
 # Issue #151 guard: the request Cookie header must be bare RFC 6265 name=value
-# pairs, no $Version/$Path attributes. Driven by the 'httrack -#test=cookies' selftest.
+# pairs, no $Version/$Path attributes. Driven by the 'httrack -#Q' selftest.
 
 set -eu
 
-# 'run' is an ignored placeholder argument.
-out=$(httrack -#test=cookies run)
+# A trailing token is required; a bare '-#Q' falls through to the usage screen.
+out=$(httrack -#Q run)
 
-# Exact-match the success line so a renamed/removed test (it prints the registry
-# to stderr) can't pass.
+# Exact-match the success line so a fall-through to usage can't pass the test.
 test "$out" = "cookie-header: OK" || {
     echo "expected 'cookie-header: OK', got: $out" >&2
     exit 1

tests/01_engine-copyopt.test

@@ -2,16 +2,15 @@
 #
 # Regression guard for the unsigned-enum sentinel trap: copy_htsopt's
 # `if (from->X > -1)` guard is always false for unsigned hts_boolean fields, so
-# they silently stop being copied. Driven by the in-process 'httrack -#test=copyopt' test.
+# they silently stop being copied. Driven by the in-process 'httrack -#9' test.
 # Keep POSIX-portable (harness runs it via $(BASH), a plain /bin/sh on macOS).
 
 set -eu
 
-# 'run' is an ignored placeholder argument.
-out=$(httrack -#test=copyopt run)
+# A trailing token is required; a bare '-#9' falls through to the usage screen.
+out=$(httrack -#9 run)
 
-# Exact-match the success line so a renamed/removed test (it prints the registry
-# to stderr) can't pass.
+# Exact-match the success line so a fall-through to usage can't pass the test.
 test "$out" = "copy-htsopt: OK" || {
     echo "expected 'copy-htsopt: OK', got: $out" >&2
     exit 1

tests/01_engine-dns.test

@@ -5,8 +5,9 @@ set -euo pipefail
 
 # DNS resolver/cache self-test: a mock getaddrinfo (no network) checks address
 # family, single-address selection, the -@i4/-@i6 family filter, and cache reuse.
-# 'run' is an ignored placeholder argument.
-out=$(httrack -#test=dns run)
+# The trailing token is required, like the other -# selftests, so a bare command
+# line isn't treated as "no arguments" and routed to the usage screen.
+out=$(httrack -#D run)
 
 test "$out" = "dns-selftest: OK" || {
     echo "expected 'dns-selftest: OK', got: $out" >&2

tests/01_engine-entities.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # HTML entity unescaping (hts_unescapeEntitiesWithCharset).
-# -#test=entities <string> prints the string with entities decoded (UTF-8 output).
+# -#6 <string> prints the string with entities decoded (UTF-8 output).
 ent() {
-    test "$(httrack -O /dev/null -#test=entities "$1")" == "$2" || exit 1
+    test "$(httrack -O /dev/null -#6 "$1")" == "$2" || exit 1
 }
 # crash probe: malformed input must exit cleanly, not abort.
 runs() {
-    httrack -O /dev/null -#test=entities "$1" >/dev/null 2>&1 || exit 1
+    httrack -O /dev/null -#6 "$1" >/dev/null 2>&1 || exit 1
 }
 
 # named entities

tests/01_engine-filelist.test

@@ -1,65 +0,0 @@
-#!/bin/bash
-#
-# -%L URL-list loading (#49): a readable list is honored; an unusable one fails
-# with the reason (errno / not-a-regular-file), not a bare "Could not include
-# URL list". Offline: file:// fixture, no server. Asserts on httrack's own
-# strings and the message shape, so it is locale-independent.
-
-set -euo pipefail
-
-tmp=$(mktemp -d "${TMPDIR:-/tmp}/httrack_filelist.XXXXXX") || exit 1
-trap 'rm -rf "$tmp"' EXIT HUP INT QUIT PIPE TERM
-
-echo '<html><body>hi</body></html>' >"$tmp/index.html"
-
-# run httrack with the given -%L target; structured log lands in $out/hts-log.txt
-run() {
-    local out="$1" list="$2"
-    rm -rf "$out"
-    mkdir -p "$out"
-    httrack -O "$out" --quiet -n "-%L" "$list" >"$out/.stdout" 2>&1 || true
-    LOG="$out/hts-log.txt"
-}
-
-fail() {
-    echo "FAIL: $1"
-    cat "$LOG"
-    exit 1
-}
-loghas() {
-    grep -Eq "$1" "$LOG" || fail "expected /$1/ in $LOG"
-}
-lognot() {
-    if grep -Eq "$1" "$LOG"; then fail "unexpected /$1/ in $LOG"; fi
-}
-
-# readable list: its one URL is loaded and counted (count must be non-zero)
-printf 'file://%s/index.html\n' "$tmp" >"$tmp/urls.txt"
-run "$tmp/ok" "$tmp/urls.txt"
-loghas '[1-9][0-9]* links added from'
-
-# missing file: quoted name + a non-empty reason, never the old reasonless
-# "Could not include URL list: <name>". The reason is the stat() errno, not the
-# directory fallback literal (guards against dropping the errno lookup).
-run "$tmp/miss" "$tmp/nope.txt"
-loghas 'Could not include URL list "[^"]+": .+'
-lognot 'Could not include URL list: '
-lognot 'not a regular file'
-
-# a directory is rejected with our own reason (locale-independent)
-mkdir -p "$tmp/adir"
-run "$tmp/dir" "$tmp/adir"
-loghas 'Could not include URL list "[^"]+": not a regular file'
-
-# unreadable regular file: the fopen() errno arm fires, distinct from the
-# directory branch. Root bypasses mode 000, so skip it there.
-if test "$(id -u)" -ne 0; then
-    : >"$tmp/noperm.txt"
-    chmod 000 "$tmp/noperm.txt"
-    run "$tmp/perm" "$tmp/noperm.txt"
-    chmod 644 "$tmp/noperm.txt"
-    loghas 'Could not include URL list "[^"]+": .+'
-    lognot 'not a regular file'
-fi
-
-exit 0

tests/01_engine-filter.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # wildcard filter engine (strjoker), the core of +/- include/exclude rules.
-# -#test=filter <filter> <string> prints "<string> does match <filter>" or "... does NOT match ...".
+# -#0 <filter> <string> prints "<string> does match <filter>" or "... does NOT match ...".
 
 match() {
-    test "$(httrack -O /dev/null -#test=filter "$1" "$2")" == "$2 does match $1" || exit 1
+    test "$(httrack -O /dev/null -#0 "$1" "$2")" == "$2 does match $1" || exit 1
 }
 nomatch() {
-    test "$(httrack -O /dev/null -#test=filter "$1" "$2")" == "$2 does NOT match $1" || exit 1
+    test "$(httrack -O /dev/null -#0 "$1" "$2")" == "$2 does NOT match $1" || exit 1
 }
 
 # bare star matches everything
@@ -71,27 +71,3 @@ nomatch '*[\[\]]' '[' # not matched, despite the docs
 match '*[\[\]]' ']'   # only via the empty class-match + trailing ']'
 match '*[\[\]]' '[]'  # one of {'[','\'} then the trailing ']'
 nomatch '*[\[\]]' '[]x'
-
-# Size-based rules (-#test=filtersize <size> <string> <filter...>): a negative size
-# means the size is still unknown (scan time). A size exclusion must stay neutral
-# then, so the file is fetched and only cancelled once its size is known (#143).
-fsize() {
-    local want="$1"
-    shift
-    test "$(httrack -O /dev/null -#test=filtersize "$@")" == "$want" || exit 1
-}
-fsize 'verdict=allowed size_flag=0' -1 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'   # scan time: keep
-fsize 'verdict=forbidden size_flag=1' 5 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'  # <10KB: cancel
-fsize 'verdict=allowed size_flag=1' 20 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'   # >=10KB: keep
-fsize 'verdict=forbidden size_flag=0' -1 foo.txt -* '+*.jpg' '-*.jpg*[<10]' # not a jpg
-# the '>' operator is just as neutral at scan time, and fires once size is known
-fsize 'verdict=allowed size_flag=0' -1 foo.jpg -* '+*.jpg' '-*.jpg*[>10]'   # scan time: keep
-fsize 'verdict=forbidden size_flag=1' 20 foo.jpg -* '+*.jpg' '-*.jpg*[>10]' # >10KB: cancel
-
-# [name]/[file]/[path] never span '?' mid-string; a trailing query is still
-# tolerated by the global '?' rule (same as plain *.aspx), not the class (#144).
-nomatch '*[path]/end' 'a?b/end'
-nomatch '*[file]end' 'foo?xend'
-nomatch '*[name]X' 'abc?X'
-match '*[file]' 'foo?x=1' # trailing query: tolerated, as for *.aspx
-match '*.aspx' 'page.aspx?y=2'

tests/01_engine-hashtable.test

@@ -3,7 +3,5 @@
 
 set -euo pipefail
 
-# httrack internal hashtable autotest on 100K keys. Assert the success line (on
-# stderr) so a misrouted registry entry can't pass on exit code alone.
-out=$(httrack -#test=hashtable 100000 2>&1)
-printf '%s\n' "$out" | grep -q "all hashtable tests were successful!" || exit 1
+# httrack internal hashtable autotest on 100K keys
+httrack -#7 100000

tests/01_engine-idna.test

@@ -3,13 +3,13 @@
 
 set -euo pipefail
 
-# IDNA / punycode encode (-#test=idna-encode) and decode (-#test=idna-decode). This code has a CVE history,
+# IDNA / punycode encode (-#4) and decode (-#5). This code has a CVE history,
 # so the edge cases below cover passthrough, round-trips, and malformed input.
 
-enc() { test "$(httrack -O /dev/null -#test=idna-encode "$1")" == "$2" || exit 1; }
-dec() { test "$(httrack -O /dev/null -#test=idna-decode "$1")" == "$2" || exit 1; }
+enc() { test "$(httrack -O /dev/null -#4 "$1")" == "$2" || exit 1; }
+dec() { test "$(httrack -O /dev/null -#5 "$1")" == "$2" || exit 1; }
 # crash probe: malformed ACE input must exit cleanly, not abort.
-runs() { httrack -O /dev/null -#test=idna-decode "$1" >/dev/null 2>&1 || exit 1; }
+runs() { httrack -O /dev/null -#5 "$1" >/dev/null 2>&1 || exit 1; }
 
 # encode
 enc 'www.café.com' 'www.xn--caf-dma.com'

tests/01_engine-mime.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # MIME type guessing from extension (get_httptype / give_mimext).
-# -#test=mime <path> prints "<path> is '<mime>'" then "and its local type is '.<ext>'".
+# -#2 <path> prints "<path> is '<mime>'" then "and its local type is '.<ext>'".
 
 mime() {
-    test "$(httrack -O /dev/null -#test=mime "$1" | head -1)" == "$1 is '$2'" || exit 1
+    test "$(httrack -O /dev/null -#2 "$1" | head -1)" == "$1 is '$2'" || exit 1
 }
 unknown() {
-    test "$(httrack -O /dev/null -#test=mime "$1" | head -1)" == "$1 is of an unknown MIME type" || exit 1
+    test "$(httrack -O /dev/null -#2 "$1" | head -1)" == "$1 is of an unknown MIME type" || exit 1
 }
 
 mime '/a/b.html' 'text/html'

tests/01_engine-relative.test

@@ -8,7 +8,7 @@ set -euo pipefail
 # relative path from <curr>'s directory to <link>
 rel() {
     local got
-    got=$(httrack -O /dev/null -#test=relative "$1" "$2")
+    got=$(httrack -O /dev/null -#l "$1" "$2")
     test "$got" == "relative=$3" ||
         {
             echo "FAIL rel($1, $2): got '$got' want 'relative=$3'"
@@ -19,7 +19,7 @@ rel() {
 # resolve <link> against origin <adr>/<fil> -> adr=.. fil=..
 ident() {
     local got
-    got=$(httrack -O /dev/null -#test=resolve "$1" "$2" "$3")
+    got=$(httrack -O /dev/null -#i "$1" "$2" "$3")
     test "$got" == "$4" ||
         {
             echo "FAIL ident($1, $2, $3): got '$got' want '$4'"

tests/01_engine-savename.test

@@ -1,41 +0,0 @@
-#!/bin/bash
-#
-
-set -euo pipefail
-
-# Local save-name extension resolution (url_savename via -#test=savename <fil> <content-type>).
-# Asserts on the basename of "savename: <path>".
-
-name() {
-    out="$(httrack -O /dev/null -#test=savename "$1" "$2" | sed -n 's/^savename: //p')"
-    test "${out##*/}" == "$3" || {
-        echo "FAIL: '$1' '$2' -> '$out' (want '$3')"
-        exit 1
-    }
-}
-
-# #115: an unknown trailing ".token" is part of the name, keep it and append the type.
-name '/article-1.884291' 'text/html' 'article-1.884291.html'
-name '/news/story-12345.987654' 'text/html' 'story-12345.987654.html'
-
-# Recognized extensions still collapse to the resolved type.
-name '/page.php' 'text/html' 'page.html'
-name '/page.asp' 'text/html' 'page.html'
-name '/foo' 'text/html' 'foo.html'
-
-# A bare trailing dot is not a tail to keep.
-name '/page.' 'text/html' 'page.html'
-
-# Soft-404 (#267/#408): a binary URL served as HTML is named .html.
-name '/x.pdf' 'text/html' 'x.html'
-name '/x.gif' 'text/html' 'x.html'
-
-# Type agrees with the extension: keep it, no churn, no double extension.
-name '/x.pdf' 'application/pdf' 'x.pdf'
-name '/x.jpg' 'image/jpeg' 'x.jpg'
-name '/x.html' 'text/html' 'x.html'
-name '/x.js' 'application/x-javascript' 'x.js'
-name '/types/data.json' 'application/json' 'data.json'
-
-# Agreeing type must not rewrite the extension's casing (no strip-and-reappend).
-name '/x.JPG' 'image/jpeg' 'x.JPG'

tests/01_engine-selftest-dispatch.test

@@ -1,17 +0,0 @@
-#!/bin/bash
-#
-# The -#test dispatch itself: a bare -#test lists the registry, and an unknown
-# name errors (non-zero, diagnostic) instead of silently passing.
-
-set -eu
-
-# Bare -#test lists known tests (printed to stderr).
-list=$(httrack -#test 2>&1)
-printf '%s\n' "$list" | grep -q "filter" || exit 1
-printf '%s\n' "$list" | grep -q "cache-writefail" || exit 1
-
-# Unknown name: non-zero exit + diagnostic, and no test result line.
-rc=0
-err=$(httrack -#test=bogus 2>&1) || rc=$?
-test "$rc" -ne 0 || exit 1
-printf '%s\n' "$err" | grep -q "Unknown self-test" || exit 1

tests/01_engine-simplify.test

@@ -5,7 +5,7 @@ set -euo pipefail
 
 # path simplify engine (fil_simplifie): collapses ./ and ../ segments.
 simp() {
-    test "$(httrack -O /dev/null -#test=simplify "$1")" == "simplified=$2" || exit 1
+    test "$(httrack -O /dev/null -#1 "$1")" == "simplified=$2" || exit 1
 }
 
 simp './foo/bar/' 'foo/bar/'

tests/01_engine-strsafe.test

@@ -3,22 +3,23 @@
 
 set -euo pipefail
 
-# htssafe.h bounded string operations (driven by 'httrack -#test=strsafe').
+# htssafe.h bounded string operations (driven by 'httrack -#8').
 
 # Success path: every bounded op (strcpybuff/strcatbuff/strncatbuff/strlcpybuff)
-# must behave correctly. 'run' selects the success path (vs the overflow modes).
+# must behave correctly. Like the other -# debug modes, a trailing token is
+# required (a bare '-#8' falls through to the usage screen).
 rc=0
-out=$(httrack -#test=strsafe run) || rc=$?
+out=$(httrack -#8 run) || rc=$?
 test "$rc" -eq 0 || exit 1
 test "$out" == "strsafe: OK" || exit 1
 
 # Overflow path: an over-capacity write into a sized buffer must be caught by
 # the bounded macro and abort the process, not be silently truncated/completed.
 # Assert the htssafe abort signature specifically, so the test cannot pass for
-# an unrelated reason (e.g. the strsafe test being gone, which prints the
-# registry to stderr and also exits non-zero).
+# an unrelated reason (e.g. the -#8 mode being gone and falling through to the
+# usage screen, which also exits non-zero).
 # the bounded macro aborts (non-zero exit), so don't let set -e trip on it
-err=$(httrack -#test=strsafe overflow "this string is far too long for the buffer" 2>&1) || true
+err=$(httrack -#8 overflow "this string is far too long for the buffer" 2>&1) || true
 case "$err" in
 *"strsafe: NOT aborted"*)
     echo "over-capacity write was NOT caught" >&2
@@ -35,7 +36,7 @@ esac
 # capacity (4 bytes into a 4-byte buffer), so this also pins the boundary: a
 # '<=' off-by-one in the capacity check would let it through (and print "NOT
 # aborted"). Match the specific htsbuff abort message, not just any assert.
-err=$(httrack -#test=strsafe overflow-buff "abcd" 2>&1) || true
+err=$(httrack -#8 overflow-buff "abcd" 2>&1) || true
 case "$err" in
 *"strsafe: NOT aborted"*)
     echo "htsbuff over-capacity write was NOT caught" >&2

tests/20_local-resume-loop.test

@@ -1,113 +0,0 @@
-#!/bin/bash
-# Issue #206: a continue/update crawl looped forever when the resume Range got a
-# 416. Pass 1 leaves a partial + temp-ref; pass 2 must terminate and not loop.
-set -u
-
-: "${top_srcdir:=..}"
-testdir=$(cd "$(dirname "$0")" && pwd)
-server="${testdir}/local-server.py"
-
-command -v python3 >/dev/null || ! echo "python3 not found; skipping" || exit 77
-
-tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_206.XXXXXX") || exit 1
-serverpid=
-crawlpid=
-cleanup() {
-    test -n "$crawlpid" && kill -9 "$crawlpid" 2>/dev/null
-    if test -n "$serverpid"; then
-        kill "$serverpid" 2>/dev/null
-        wait "$serverpid" 2>/dev/null
-    fi
-    rm -rf "$tmpdir"
-}
-trap cleanup EXIT HUP INT QUIT PIPE TERM
-
-# --- start the server, discover its ephemeral port --------------------------
-# RESUME_COUNTER gets a byte per /resume/blob.txt request (pass-2 delta bounds re-gets).
-serverlog="${tmpdir}/server.log"
-counter="${tmpdir}/blobcount"
-RESUME_COUNTER="$counter" python3 "$server" --root "${testdir}/server-root" >"$serverlog" 2>&1 &
-serverpid=$!
-port=
-for _ in $(seq 1 50); do
-    line=$(head -n1 "$serverlog" 2>/dev/null)
-    if test "${line%% *}" == "PORT"; then
-        port="${line#PORT }"
-        break
-    fi
-    kill -0 "$serverpid" 2>/dev/null || {
-        echo "server exited early: $(cat "$serverlog")"
-        exit 1
-    }
-    sleep 0.1
-done
-test -n "$port" || {
-    echo "could not discover server port"
-    exit 1
-}
-base="http://127.0.0.1:${port}"
-
-which httrack >/dev/null || {
-    echo "could not find httrack"
-    exit 1
-}
-out="${tmpdir}/crawl"
-mkdir "$out"
-common=(-O "$out" --quiet --disable-security-limits --robots=0 --timeout=30 --retries=0)
-refdir="${out}/hts-cache/ref"
-
-# --- pass 1: crawl, interrupt once the blob download is underway -------------
-printf '[pass 1: interrupt mid-download] ..\t'
-httrack "${common[@]}" "${base}/resume/index.html" >"${tmpdir}/log1" 2>&1 &
-crawlpid=$!
-# Wait until blob.txt is requested, then SIGTERM so httrack's exit handler
-# finalizes the cache and serializes the temp-ref.
-for _ in $(seq 1 300); do
-    test -s "$counter" && break
-    kill -0 "$crawlpid" 2>/dev/null || break
-    sleep 0.1
-done
-sleep 0.5
-kill -TERM "$crawlpid" 2>/dev/null
-wait "$crawlpid" 2>/dev/null
-crawlpid=
-test -n "$(find "$refdir" -name '*.ref' 2>/dev/null)" || {
-    echo "FAIL: no temp-ref survived pass 1; cannot drive #206"
-    exit 1
-}
-echo "OK (temp-ref present)"
-before=$(wc -c <"$counter" 2>/dev/null || echo 0)
-
-# --- pass 2: --continue -> resume Range -> 416, bounded against the #206 loop -
-# Kill pass 2 after a deadline (portable stand-in for `timeout`, absent on macOS).
-printf '[pass 2: resume must terminate] ..\t'
-HANG_RC=137 # 128 + SIGKILL
-httrack "${common[@]}" --continue "${base}/resume/index.html" >"${tmpdir}/log2" 2>&1 &
-crawlpid=$!
-(sleep 30 && kill -9 "$crawlpid" 2>/dev/null) &
-guard=$!
-rc=0
-wait "$crawlpid" 2>/dev/null || rc=$?
-crawlpid=
-kill "$guard" 2>/dev/null || true
-wait "$guard" 2>/dev/null || true
-if test "$rc" -eq "$HANG_RC"; then
-    echo "FAIL: pass 2 did not terminate (#206 resume->416 loop)"
-    exit 1
-fi
-echo "OK (terminated, rc=$rc)"
-
-# The fix re-gets once (resume Range + range-less re-get = 2): the lower bound
-# rejects a drop-the-link non-fix (1), the upper bound rejects the loop (many).
-after=$(wc -c <"$counter" 2>/dev/null || echo 0)
-hits=$((after - before))
-printf '[bounded re-get count] ..\t'
-if test "$hits" -lt 2; then
-    echo "FAIL: only ${hits} pass-2 request(s); the stale partial was not re-got"
-    exit 1
-fi
-if test "$hits" -gt 8; then
-    echo "FAIL: ${hits} pass-2 requests for blob.txt (resume is looping)"
-    exit 1
-fi
-echo "OK (${hits} requests)"

tests/21_local-intl-update.test

@@ -1,11 +0,0 @@
-#!/bin/bash
-#
-# #157: a dotless, accented URL named .html on the first crawl must keep .html
-# across an update -- not revert to the extensionless name.
-
-: "${top_srcdir:=..}"
-
-bash "$top_srcdir/tests/local-crawl.sh" --errors 0 --rerun \
-    --found 'intl/Instalação_CVS_no_Ubuntu.html' \
-    --not-found 'intl/Instalação_CVS_no_Ubuntu' \
-    httrack 'BASEURL/intl/index.html'

tests/22_local-broken-size.test

@@ -1,17 +0,0 @@
-#!/bin/bash
-# Issues #32/#41: a Content-Length that disagrees with the body warns "bogus
-# state (broken size)" and skips the cache; -%B (tolerant) accepts it.
-
-: "${top_srcdir:=..}"
-
-# Default: warn, but the file is still written.
-bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
-    --found 'size/oversize.bin' \
-    --log-found 'bogus state \(broken size' \
-    httrack 'BASEURL/size/index.html'
-
-# -%B (tolerant): no warning, file written.
-bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
-    --found 'size/oversize.bin' \
-    --log-not-found 'bogus state' \
-    httrack 'BASEURL/size/index.html' '-%B'

tests/23_local-errpage.test

@@ -1,19 +0,0 @@
-#!/bin/bash
-# Issue #17: with "no error pages" (-o0), 4xx/5xx bodies must not be written;
-# a genuine 0-byte 200 stays. Default (-o1) writes the error page. (#17's purge
-# half also does not reproduce; the purge path is not exercised here.)
-set -e
-
-: "${top_srcdir:=..}"
-
-# -o0: 404 suppressed, good page and the legit 0-byte 200 kept.
-bash "$top_srcdir/tests/local-crawl.sh" --errors 1 \
-    --found 'errpage/good.html' \
-    --found 'errpage/empty.html' \
-    --not-found 'errpage/missing.html' \
-    httrack 'BASEURL/errpage/index.html' '-o0'
-
-# Control -o1 (default): the 404 error page is written.
-bash "$top_srcdir/tests/local-crawl.sh" --errors 1 \
-    --found 'errpage/missing.html' \
-    httrack 'BASEURL/errpage/index.html' '-o1'

tests/24_local-resume-overlap.test

@@ -1,109 +0,0 @@
-#!/bin/bash
-# Issue #198: on a resumed download the server may answer the Range with a 206
-# that starts *before* the offset we asked for (block-aligned ranges). httrack
-# must honor the returned Content-Range, not blindly append, or the overlap
-# bytes get duplicated and the file grows (corrupt PDFs). Pass 1 interrupts
-# flaky.bin mid-body (partial + temp-ref); pass 2 resumes against a 206 that
-# backs up 8 bytes. The result must equal the same bytes fetched whole (full.bin).
-set -eu
-
-: "${top_srcdir:=..}"
-testdir=$(cd "$(dirname "$0")" && pwd)
-server="${testdir}/local-server.py"
-
-command -v python3 >/dev/null || ! echo "python3 not found; skipping" || exit 77
-
-tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_198.XXXXXX") || exit 1
-serverpid=
-crawlpid=
-cleanup() {
-    if test -n "$crawlpid"; then kill -9 "$crawlpid" 2>/dev/null || true; fi
-    if test -n "$serverpid"; then
-        kill "$serverpid" 2>/dev/null || true
-        wait "$serverpid" 2>/dev/null || true
-    fi
-    rm -rf "$tmpdir"
-}
-trap cleanup EXIT HUP INT QUIT PIPE TERM
-
-# OVERLAP_COUNTER gets a byte per flaky.bin request so pass 1 knows when to interrupt.
-serverlog="${tmpdir}/server.log"
-counter="${tmpdir}/hits"
-resumed="${tmpdir}/resumed" # gets a byte when the server serves a resume 206
-OVERLAP_COUNTER="$counter" OVERLAP_RESUMED="$resumed" \
-    python3 "$server" --root "${testdir}/server-root" \
-    >"$serverlog" 2>&1 &
-serverpid=$!
-port=
-for _ in $(seq 1 50); do
-    line=$(head -n1 "$serverlog" 2>/dev/null)
-    if test "${line%% *}" == "PORT"; then
-        port="${line#PORT }"
-        break
-    fi
-    kill -0 "$serverpid" 2>/dev/null || {
-        echo "server exited early: $(cat "$serverlog")"
-        exit 1
-    }
-    sleep 0.1
-done
-test -n "$port" || {
-    echo "could not discover server port"
-    exit 1
-}
-base="http://127.0.0.1:${port}"
-
-which httrack >/dev/null || {
-    echo "could not find httrack"
-    exit 1
-}
-out="${tmpdir}/crawl"
-common=(-O "$out" --quiet --disable-security-limits --robots=0 --timeout=30 --retries=0 -c1)
-refdir="${out}/hts-cache/ref"
-
-# pass 1: interrupt once flaky.bin's prefix is streaming (partial + temp-ref).
-printf '[pass 1: interrupt flaky.bin] ..\t'
-httrack "${common[@]}" "${base}/overlap/index.html" >"${tmpdir}/log1" 2>&1 &
-crawlpid=$!
-for _ in $(seq 1 300); do
-    test -s "$counter" && break
-    kill -0 "$crawlpid" 2>/dev/null || break
-    sleep 0.1
-done
-sleep 0.5
-kill -TERM "$crawlpid" 2>/dev/null || true
-wait "$crawlpid" 2>/dev/null || true
-crawlpid=
-test -n "$(find "$refdir" -name '*.ref' 2>/dev/null)" || {
-    echo "FAIL: no temp-ref survived pass 1; cannot drive the resume"
-    exit 1
-}
-echo "OK (temp-ref present)"
-
-# pass 2: --continue -> resume Range -> 206 that starts 8 bytes early.
-printf '[pass 2: resume flaky.bin] ..\t'
-httrack "${common[@]}" --continue "${base}/overlap/index.html" >"${tmpdir}/log2" 2>&1 || true
-echo "OK"
-
-# Guard against a silent full re-download: the byte-compare below only tests the
-# fix if pass 2 actually went through the resume Range -> 206 path.
-printf '[resume path was exercised] ..\t'
-if ! test -s "$resumed"; then
-    echo "FAIL: pass 2 never triggered a resume 206; the overlap fix was not exercised"
-    exit 1
-fi
-echo "OK"
-
-printf '[resumed file is not corrupted] ..\t'
-dir=$(find "$out" -maxdepth 1 -type d -name '127.0.0.1*' | head -1)
-flaky="${dir}/overlap/flaky.bin"
-full="${dir}/overlap/full.bin"
-if ! test -f "$flaky" || ! test -f "$full"; then
-    echo "FAIL: flaky.bin or full.bin missing after pass 2"
-    exit 1
-fi
-if ! cmp -s "$flaky" "$full"; then
-    echo "FAIL: resumed flaky.bin ($(wc -c <"$flaky")) != full.bin ($(wc -c <"$full")); overlap duplicated"
-    exit 1
-fi
-echo "OK ($(wc -c <"$flaky") bytes, byte-identical)"

tests/25_local-mime-exclude.test

@@ -1,16 +0,0 @@
-#!/bin/bash
-#
-# A -mime: exclusion must abort the transfer on the response Content-Type, not
-# fetch the whole 1 MB body then discard it (#58). The bytes-received guard is
-# the real one: the file is absent either way, but only the fix keeps the count
-# tiny (header only) instead of pulling the body. Match it positively (a small,
-# <=4-digit count) so a vanished/reworded summary line fails rather than passes.
-
-: "${top_srcdir:=..}"
-
-bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
-    --found 'mimex/real.html' \
-    --not-found 'mimex/blob.pdf' \
-    --log-found 'excluded by MIME type filter' \
-    --log-found '\[[0-9]{1,4} bytes received' \
-    httrack 'BASEURL/mimex/index.html' '-mime:application/pdf'

tests/Makefile.am

@@ -26,7 +26,6 @@ TESTS = \
 	00_runnable.test \
 	01_engine-cache.test \
 	01_engine-cache-golden.test \
-	01_engine-cache-writefail.test \
 	01_engine-charset.test \
 	01_engine-cmdline.test \
 	01_engine-cookies.test \
@@ -34,7 +33,6 @@ TESTS = \
 	01_engine-dns.test \
 	01_engine-doitlog.test \
 	01_engine-entities.test \
-	01_engine-filelist.test \
 	01_engine-filter.test \
 	01_engine-hashtable.test \
 	01_engine-idna.test \
@@ -42,8 +40,6 @@ TESTS = \
 	01_engine-parse.test \
 	01_engine-rcfile.test \
 	01_engine-relative.test \
-	01_engine-savename.test \
-	01_engine-selftest-dispatch.test \
 	01_engine-simplify.test \
 	01_engine-strsafe.test \
 	02_manpage-regen.test \
@@ -62,12 +58,6 @@ TESTS = \
 	16_local-assume.test \
 	17_local-empty-ct.test \
 	18_local-update.test \
-	19_local-connect-fallback.test \
-	20_local-resume-loop.test \
-	21_local-intl-update.test \
-	22_local-broken-size.test \
-	23_local-errpage.test \
-	24_local-resume-overlap.test \
-	25_local-mime-exclude.test
+	19_local-connect-fallback.test
 
 CLEANFILES = check-network_sh.cache

tests/local-crawl.sh

@@ -14,9 +14,7 @@
 # Usage:
 #   bash local-crawl.sh [--tls] [--root DIR] \
 #       --errors N --files N --found PATH ... --directory PATH ... \
-#       --log-found REGEX ... --log-not-found REGEX ... \
 #       httrack BASEURL/some/path [httrack-args...]
-# --log-found/--log-not-found grep (ERE) the crawl's hts-log.txt.
 
 set -u
 
@@ -109,7 +107,7 @@ while test "$pos" -lt "$nargs"; do
         audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
         pos=$((pos + 1))
         ;;
-    --found | --not-found | --directory | --log-found | --log-not-found)
+    --found | --not-found | --directory)
         audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
         pos=$((pos + 1))
         ;;
@@ -198,15 +196,6 @@ if test -n "$rerun"; then
         exit 1
     }
     result "OK (update)"
-    # The update summary reports "files updated"; a fresh crawl never does. Assert
-    # it so a regression that bypasses the cache (re-crawls fresh) can't pass.
-    info "checking update used the cache"
-    if grep -aqE "mirror complete in .*files updated" "${out}/hts-log.txt"; then
-        result "OK"
-    else
-        result "update pass did not report cache activity"
-        exit 1
-    fi
 fi
 
 # --- discover the single host root (127.0.0.1_<port> or 127.0.0.1) -----------
@@ -259,22 +248,6 @@ while test "$i" -lt "${#audit[@]}"; do
             exit 1
         fi
         ;;
-    --log-found)
-        i=$((i + 1))
-        info "checking log matches ${audit[$i]}"
-        if grep -aqE "${audit[$i]}" "${out}/hts-log.txt"; then result "OK"; else
-            result "not in log"
-            exit 1
-        fi
-        ;;
-    --log-not-found)
-        i=$((i + 1))
-        info "checking log lacks ${audit[$i]}"
-        if grep -aqE "${audit[$i]}" "${out}/hts-log.txt"; then
-            result "present in log"
-            exit 1
-        else result "OK"; fi
-        ;;
     esac
     i=$((i + 1))
 done

tests/local-server.py

@@ -15,7 +15,6 @@ stdlib only (http.server + ssl) -- no new build or runtime dependency.
 
 import argparse
 import os
-import time
 from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
 from urllib.parse import quote, unquote, urlsplit
 
@@ -177,170 +176,6 @@ class Handler(SimpleHTTPRequestHandler):
         body, ctype = self.TYPE_MATRIX[path]
         self.send_raw(body, ctype)
 
-    # --- MIME-type exclusion abort (issue #58) -----------------------------
-    # A -mime:application/pdf filter must abort the transfer once the header
-    # arrives, not download the whole body and discard it.
-    def route_mimex_index(self):
-        self.send_html(
-            '\t<a href="blob.pdf">pdf</a>\n' '\t<a href="real.html">real</a>\n'
-        )
-
-    # 1 MB body: the fix aborts after the header, so httrack's "bytes received"
-    # stays tiny; without it the engine reads the body and the count jumps.
-    MIMEX_BLOB = b"%PDF-1.4\n" + b"\x00" * (1024 * 1024)
-
-    def route_mimex_blob(self):
-        self.send_raw(self.MIMEX_BLOB, "application/pdf")
-
-    def route_mimex_real(self):
-        self.send_raw(b"<html><body>real</body></html>", "text/html")
-
-    # --- special chars in URLs across an update (issue #157) ---------------
-    # A dotless, accented basename served as text/html (MediaWiki style). The
-    # name the first crawl picks (.html) must survive the update pass.
-    INTL_NAME = "Instalação_CVS_no_Ubuntu"
-
-    def route_intl_index(self):
-        self.send_html('\t<a href="%s">accented</a>\n' % self.INTL_NAME)
-
-    def route_intl_page(self):
-        self.send_raw(b"<html><body>accented page</body></html>\n", "text/html")
-
-    # resume / 416 loop (#206): the first GET stalls after a prefix so the crawl
-    # can be interrupted (partial + temp-ref); every later request is 416.
-    RESUME_PREFIX = b"PARTIAL-" + b"x" * 4096  # flushed before the stall
-    RESUME_LEN = len(RESUME_PREFIX) + 4096  # declared length never delivered
-    _resume_started = False
-
-    def route_resume_index(self):
-        self.send_html('\t<a href="blob.txt">blob</a>')
-
-    def route_resume(self):
-        counter = os.environ.get("RESUME_COUNTER")
-        if counter:
-            with open(counter, "a") as fp:
-                fp.write("x")
-        # First GET: stall mid-body so the crawl can be interrupted with a partial.
-        if not Handler._resume_started:
-            Handler._resume_started = True
-            self.send_response(200)
-            self.send_header("Content-Type", "image/png")
-            self.send_header("Content-Length", str(self.RESUME_LEN))
-            self.send_header("Accept-Ranges", "bytes")
-            self.end_headers()
-            if self.command != "HEAD":
-                self.wfile.write(self.RESUME_PREFIX)
-                self.wfile.flush()
-                try:
-                    while True:
-                        time.sleep(3600)
-                except OSError:
-                    pass
-            return
-        self.send_response(416, "Requested Range Not Satisfiable")
-        self.send_header("Content-Type", "image/png")
-        self.send_header("Content-Range", "bytes */%d" % self.RESUME_LEN)
-        self.send_header("Content-Length", "0")
-        self.end_headers()
-
-    # 206 resume must honor the server's Content-Range, not the offset we asked
-    # for (#198): a server resuming a few bytes *before* the request must not
-    # leave httrack duplicating the overlap onto the partial. flaky.bin
-    # interrupts once then resumes OVERLAP_EARLY bytes early; full.bin serves
-    # the identical bytes in one shot, so the test can compare the two.
-    OVERLAP_BLOB = b"%PDF-1.4\n" + bytes((i * 37 + 11) % 256 for i in range(8000))
-    OVERLAP_EARLY = 8
-    OVERLAP_PREFIX_LEN = 4000  # flushed before the stall
-    _overlap_started = False
-
-    def route_overlap_index(self):
-        self.send_html('\t<a href="flaky.bin">flaky</a>\n\t<a href="full.bin">full</a>')
-
-    def route_overlap_full(self):
-        self.send_raw(self.OVERLAP_BLOB, "application/octet-stream")
-
-    def route_overlap(self):
-        counter = os.environ.get("OVERLAP_COUNTER")
-        if counter:
-            with open(counter, "a") as fp:
-                fp.write("x")
-        blob = self.OVERLAP_BLOB
-        rng = self.headers.get("Range")
-        # First GET: stream a prefix then stall, so the crawl can be interrupted
-        # mid-body (partial + temp-ref on disk).
-        if rng is None and not Handler._overlap_started:
-            Handler._overlap_started = True
-            self.send_response(200)
-            self.send_header("Content-Type", "application/octet-stream")
-            self.send_header("Content-Length", str(len(blob)))
-            self.send_header("Accept-Ranges", "bytes")
-            self.end_headers()
-            if self.command != "HEAD":
-                self.wfile.write(blob[: self.OVERLAP_PREFIX_LEN])
-                self.wfile.flush()
-                try:
-                    while True:
-                        time.sleep(3600)
-                except OSError:
-                    pass
-            return
-        if rng is None:  # no resume request: serve the whole file
-            return self.route_overlap_full()
-        # Resume: honor the Range, but back up OVERLAP_EARLY bytes.
-        start = (
-            int(rng[len("bytes=") :].split("-")[0]) if rng.startswith("bytes=") else 0
-        )
-        start = max(0, start - self.OVERLAP_EARLY)
-        # Signal that the resume Range -> 206 path actually fired, so the test
-        # can prove it was exercised (not a silent full re-download).
-        resumed = os.environ.get("OVERLAP_RESUMED")
-        if resumed:
-            with open(resumed, "a") as fp:
-                fp.write("x")
-        part = blob[start:]
-        self.send_response(206, "Partial Content")
-        self.send_header("Content-Type", "application/octet-stream")
-        self.send_header("Content-Length", str(len(part)))
-        self.send_header(
-            "Content-Range", "bytes %d-%d/%d" % (start, len(blob) - 1, len(blob))
-        )
-        self.end_headers()
-        if self.command != "HEAD":
-            self.wfile.write(part)
-
-    # error pages / 0-byte files (#17): -o0 ("no error pages") must keep 4xx/5xx
-    # bodies off disk; a genuine 0-byte 200 is a valid file and stays.
-    def route_errpage_index(self):
-        self.send_html(
-            '\t<a href="good.html">good</a>\n'
-            '\t<a href="missing.html">missing</a>\n'
-            '\t<a href="empty.html">empty</a>\n'
-        )
-
-    def route_errpage_good(self):
-        self.send_raw(b"<html><body>good page</body></html>\n", "text/html")
-
-    def route_errpage_missing(self):
-        self.send_html("\t404 error body", status=404, extra_status="Not Found")
-
-    def route_errpage_empty(self):
-        self.send_raw(b"", "text/html")
-
-    # broken Content-Length (#32/#41): declared size != bytes sent. httrack
-    # warns "bogus state (broken size)" and skips the cache unless -%B.
-    def route_size_index(self):
-        self.send_html('\t<a href="oversize.bin">over</a>\n')
-
-    def route_size_oversize(self):
-        body = b"A" * 100
-        self.send_response(200)
-        self.send_header("Content-Type", "application/octet-stream")
-        self.send_header("Content-Length", str(len(body) - 2))  # lie: too short
-        self.send_header("Connection", "close")
-        self.end_headers()
-        if self.command != "HEAD":
-            self.wfile.write(body)
-
     ROUTES = {
         "/cookies/entrance.php": route_entrance,
         "/cookies/second.php": route_second,
@@ -360,22 +195,6 @@ class Handler(SimpleHTTPRequestHandler):
         "/types/style.css": route_types,
         "/types/data.json": route_types,
         "/types/gen.php": route_types,
-        "/intl/index.html": route_intl_index,
-        "/intl/" + INTL_NAME: route_intl_page,
-        "/resume/index.html": route_resume_index,
-        "/resume/blob.txt": route_resume,
-        "/overlap/index.html": route_overlap_index,
-        "/overlap/flaky.bin": route_overlap,
-        "/overlap/full.bin": route_overlap_full,
-        "/size/index.html": route_size_index,
-        "/size/oversize.bin": route_size_oversize,
-        "/errpage/index.html": route_errpage_index,
-        "/errpage/good.html": route_errpage_good,
-        "/errpage/missing.html": route_errpage_missing,
-        "/errpage/empty.html": route_errpage_empty,
-        "/mimex/index.html": route_mimex_index,
-        "/mimex/blob.pdf": route_mimex_blob,
-        "/mimex/real.html": route_mimex_real,
     }
 
     # --- dispatch ----------------------------------------------------------
@@ -383,8 +202,7 @@ class Handler(SimpleHTTPRequestHandler):
     def dispatch(self):
         self._set_cookies = []
         path = urlsplit(self.path).path
-        # Match percent-encoded paths (accented #157 route) by their decoded form.
-        handler = self.ROUTES.get(path) or self.ROUTES.get(unquote(path))
+        handler = self.ROUTES.get(path)
         if handler is not None:
             handler(self)
             return True