tests: lock special-char URL naming across an update (#157)

#157 reported accented URLs (pt-BR MediaWiki) losing their .html extension
on an update pass, observed with 3.49-2 on Windows. It does not reproduce on
current master: the update resolves the cached content-type and re-applies
.html consistently, for UTF-8 and ISO-8859-1 sources, raw Latin-1 href bytes,
either percent-encoding case, and dotted tails. The original symptom was a
Windows codepage vs UTF-8 X-Save filename mismatch that cannot occur on a
UTF-8 filesystem.

Add a regression test that locks the invariant: a dotless, accented basename
served as text/html, crawled then updated, must keep its .html name and not
leave an extensionless sibling.

Also assert in the --rerun harness that the update pass reported "files
updated" (a fresh crawl never does), so a regression that bypasses the cache
and silently re-crawls fresh can no longer pass the update tests.

Closes #157

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

.github/workflows/ci.yml

@@ -232,30 +232,42 @@ 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:
-      - 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 \
+          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
+
       # --unsigned: CI has no GPG key (also skips the release sig/checksums).
-      # debuild builds every package, then lintian gates on errors.
+      # mkdeb builds every package then runs the lintian gate (--fail-on=error,
+      # warning); debuild runs the packaged test pass.
       #
       # 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. 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
+      # every core.
+      - name: Build and lint 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

@@ -1,3 +1,8 @@
 # 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

@@ -0,0 +1,3 @@
+# 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

@@ -2468,6 +2468,44 @@ 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

@@ -4766,64 +4766,51 @@ int hts_read(htsblk * r, char *buff, int size) {
 // -- Gestion cache DNS --
 // 'RX98
 
-// 'capsule' contenant uniquement le cache
-t_dnscache *hts_cache(httrackp * opt) {
+// 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) {
   assertf(opt != NULL);
   if (opt->state.dns_cache == NULL) {
-    opt->state.dns_cache = (t_dnscache *) malloct(sizeof(t_dnscache));
-    memset(opt->state.dns_cache, 0, sizeof(t_dnscache));
+    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;
   }
   assertf(opt->state.dns_cache != NULL);
-  /* first entry is NULL */
-  assertf(opt->state.dns_cache->iadr == NULL);
   return opt->state.dns_cache;
 }
 
-// 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
+// MUST BE LOCKED (coucal is not internally serialized vs FTP/web threads)
 // 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(const t_dnscache *cache, const char *const iadr,
+static int hts_ghbn_all(coucal cache, const char *const iadr,
                         SOCaddr *const out, const int max) {
+  void *ptr;
+
   assertf(out != NULL);
   assertf(iadr != NULL);
   if (*iadr == '\0') {
     return -1;
   }
-  /* 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;
+  if (coucal_read_pvoid(cache, iadr, &ptr)) { // ok trouvé
+    const t_dnscache *const record = (const t_dnscache *) ptr;
+    int 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;
+    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]);
     }
+    return record->host_count;
   }
   return -1;
 }
@@ -5088,7 +5075,7 @@ 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];
-  t_dnscache *cache = hts_cache(opt);  // adresse du cache
+  coucal cache = hts_cache(opt); // le cache dns
   int count;
 
   assertf(opt != NULL);
@@ -5109,13 +5096,10 @@ 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
@@ -5126,22 +5110,18 @@ static int hts_dns_resolve_list_(httrackp *opt, const char *_iadr,
     DEBUG_W("gethostbyname done\n");
 #endif
 
-    /* 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;
+    /* 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;
       for (i = 0; i < count; 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]);
+        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->next = NULL;
+      coucal_add_pvoid(cache, iadr, record);
     }
 
     /* copy result to caller (cache store may have failed; result still valid)
@@ -6012,14 +5992,14 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
 
     /* Cache */
     if (opt->state.dns_cache != NULL) {
-      t_dnscache *root;
+      coucal root;
 
       hts_mutexlock(&opt->state.lock);
       root = opt->state.dns_cache;
       opt->state.dns_cache = NULL;
       hts_mutexrelease(&opt->state.lock);
 
-      hts_cache_free(root);
+      coucal_delete(&root); // frees records via hts_cache_value_free
     }
 
     /* Cancel chain */

src/htslib.h

@@ -147,9 +147,8 @@ 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;
@@ -245,8 +244,9 @@ HTSEXT_API int check_hostname_dns(const char *const hostname);
 int ftp_available(void);
 
 #if HTS_DNSCACHE
-void hts_cache_free(t_dnscache *const cache);
-t_dnscache *hts_cache(httrackp * opt);
+/* 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);
 #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)
     }
   }
-  // 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
+  // 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) {
     char *a = fil + strlen(fil) - 1;
 
     if ((opt->debug > 1) && (opt->log != NULL)) {
@@ -774,11 +774,19 @@ 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 == '.')
-        *a = '\0';              // couper
-      strcatbuff(fil, ".");     // recopier point
+      if (*a == '.' && known_ext)
+        *a = '\0';          // cut
+      strcatbuff(fil, "."); // re-add the dot
     } else {
       while((a > fil) && (*a != '/'))
         a--;
@@ -786,7 +794,7 @@ int url_savename(lien_adrfilsave *const afs,
         a++;
       *a = '\0';
     }
-    strcatbuff(fil, ext);       // copier ext/nom
+    strcatbuff(fil, ext); // append ext/name
   }
   // Rechercher premier / et dernier .
   {
@@ -1721,10 +1729,10 @@ char *url_savename_refname_fullpath(httrackp * opt, const char *adr,
     StringBuff(opt->path_log), digest_filename);
 }
 
-/* remove refname if any */
-void url_savename_refname_remove(httrackp * opt, const char *adr,
-                                 const char *fil) {
+/* remove refname if any; HTS_TRUE if it was removed */
+hts_boolean url_savename_refname_remove(httrackp *opt, const char *adr,
+                                        const char *fil) {
   char *filename = url_savename_refname_fullpath(opt, adr, fil);
 
-  (void) UNLINK(filename);
+  return UNLINK(filename) == 0 ? HTS_TRUE : HTS_FALSE;
 }

src/htsname.h

@@ -104,8 +104,9 @@ 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);
-void url_savename_refname_remove(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);
 #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;
-  t_dnscache *dns_cache;  /**< DNS resolution cache */
+  coucal dns_cache; /**< DNS resolution cache: hostname -> t_dnscache record */
   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

@@ -3749,44 +3749,60 @@ 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)
-      ) {                       // Precondition Failed, c'est à dire pour nous redemander TOUT le fichier
-      if (fexist_utf8(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 : "");
+    } 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);
       }
-      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
+      // 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;
+      if (fexist_utf8(heap(ptr)->sav)) {
+        had_partial = 1;
+        remove(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)) {
         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;   // mode test?
-          heap_top()->link_import = 0;   // pas mode import
+          heap_top()->testmode = heap(ptr)->testmode;
+          heap_top()->link_import = 0;
           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 {              // oups erreur, plus de mémoire!!
-          XH_uninit;          // désallocation mémoire & buffers
+          hts_invalidate_link(opt, ptr); // invalidate hashtable entry
+        } else {                         // out of memory
+          XH_uninit;
           return 0;
         }
       } else {
-        hts_log_print(opt, LOG_ERROR, "Can not remove old file %s", urlfil());
+        hts_log_print(opt, LOG_WARNING,
+                      "Giving up on partial reget (%s) for %s%s", r->msg,
+                      urladr(), urlfil());
         error = 1;
       }
 

tests/01_engine-savename.test

@@ -0,0 +1,41 @@
+#!/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'
+
+# 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/20_local-resume-loop.test

@@ -0,0 +1,113 @@
+#!/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

@@ -0,0 +1,11 @@
+#!/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/Makefile.am

@@ -40,6 +40,7 @@ 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 \
@@ -58,6 +59,8 @@ TESTS = \
 	16_local-assume.test \
 	17_local-empty-ct.test \
 	18_local-update.test \
-	19_local-connect-fallback.test
+	19_local-connect-fallback.test \
+	20_local-resume-loop.test \
+	21_local-intl-update.test
 
 CLEANFILES = check-network_sh.cache

tests/local-crawl.sh

@@ -196,6 +196,15 @@ 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) -----------

tests/local-server.py

@@ -15,6 +15,7 @@ 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
 
@@ -176,6 +177,54 @@ class Handler(SimpleHTTPRequestHandler):
         body, ctype = self.TYPE_MATRIX[path]
         self.send_raw(body, ctype)
 
+    # --- 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()
+
     ROUTES = {
         "/cookies/entrance.php": route_entrance,
         "/cookies/second.php": route_second,
@@ -195,6 +244,10 @@ 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,
     }
 
     # --- dispatch ----------------------------------------------------------
@@ -202,7 +255,8 @@ class Handler(SimpleHTTPRequestHandler):
     def dispatch(self):
         self._set_cookies = []
         path = urlsplit(self.path).path
-        handler = self.ROUTES.get(path)
+        # Match percent-encoded paths (accented #157 route) by their decoded form.
+        handler = self.ROUTES.get(path) or self.ROUTES.get(unquote(path))
         if handler is not None:
             handler(self)
             return True