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
 

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*

src/htscoremain.c

@@ -2468,44 +2468,6 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                 htsmain_free();
                 return err;
               } break;
-              case 'N': { // url_savename name resolution: httrack -#N <fil>
-                          // <content-type>
-                if (na + 2 < argc) {
-                  lien_adrfilsave afs;
-                  cache_back cache;
-                  struct_back *sback;
-                  hash_struct hash;
-                  lien_back headers;
-
-                  memset(&afs, 0, sizeof(afs));
-                  strcpybuff(afs.af.adr, "www.example.com");
-                  strcpybuff(afs.af.fil, argv[na + 1]);
-
-                  memset(&cache, 0, sizeof(cache));
-                  cache.hashtable = (void *) coucal_new(0);
-
-                  sback = back_new(opt, opt->maxsoc * 32 + 1024);
-                  hash_init(opt, &hash, opt->urlhack);
-
-                  memset(&headers, 0, sizeof(headers));
-                  headers.status = 0;
-                  headers.r.statuscode = HTTP_OK;
-                  strcpybuff(headers.r.contenttype, argv[na + 2]);
-                  strcpybuff(headers.url_fil, argv[na + 1]);
-
-                  url_savename(&afs, NULL, NULL, NULL, opt, sback, &cache,
-                               &hash, 0, 0, &headers);
-                  printf("savename: %s\n", afs.save);
-                  htsmain_free();
-                  return 0;
-                } else {
-                  fprintf(
-                      stderr,
-                      "Option #N requires <fil> <content-type> arguments\n");
-                  htsmain_free();
-                  return 1;
-                }
-              } break;
               case 'C':        // list cache files : httrack -#C '*spid*.gif' will attempt to find the matching file
                 {
                   int hasFilter = 0;

src/htslib.c

@@ -4766,51 +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;
 }
@@ -5075,7 +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);
@@ -5096,10 +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
@@ -5110,18 +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)
@@ -5992,14 +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)) {
@@ -774,18 +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 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 to replace.
-      const char *const old_ext = get_ext(catbuff, sizeof(catbuff), fil);
-      const int known_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--;
@@ -793,7 +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 .
   {

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 */

tests/01_engine-savename.test

@@ -1,35 +0,0 @@
-#!/bin/bash
-#
-
-set -euo pipefail
-
-# Local save-name extension resolution (url_savename via -#N <fil> <content-type>).
-# Asserts on the basename of "savename: <path>".
-
-name() {
-    out="$(httrack -O /dev/null -#N "$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'
-
-# 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'

tests/Makefile.am

@@ -40,7 +40,6 @@ TESTS = \
 	01_engine-parse.test \
 	01_engine-rcfile.test \
 	01_engine-relative.test \
-	01_engine-savename.test \
 	01_engine-simplify.test \
 	01_engine-strsafe.test \
 	02_manpage-regen.test \