ci: alias 127.0.0.2/.3 on macOS lo0 for the connect-fallback test

macOS configures only 127.0.0.1 as loopback, so 19_local-connect-fallback's
dead 127.0.0.2/.3 addresses have no fast-refuse path: the connect intermittently
stalls to the timeout and logs "Connect Time Out", which the zero-errors
assertion rejects (flaked ~1/6 on the macOS runner). #531's --timeout/--retries
bound the stall but not the spurious error. Aliasing the addresses onto lo0
makes them refuse instantly like Linux, so the fallback runs cleanly.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

.github/workflows/ci.yml

@@ -55,7 +55,9 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        run: make check
+        run: |
+          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
+          make check -j"$jobs"
 
       - name: Print the test log on failure
         if: failure()
@@ -99,7 +101,8 @@ jobs:
           sudo find /usr/bin /usr/local/bin -maxdepth 1 -name 'python3*' \
             -exec mv {} {}.hidden \;
           ! command -v python3
-          make check
+          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
+          make check -j"$jobs"
 
       - name: Print the test log on failure
         if: failure()
@@ -132,8 +135,18 @@ jobs:
       - name: Build
         run: make -j"$(sysctl -n hw.ncpu)"
 
+      - name: Add loopback aliases (macOS lacks 127.0.0.2/.3)
+        # 19_local-connect-fallback needs the dead 127.0.0.2/.3 to refuse
+        # instantly like Linux; alias them onto lo0 so they don't stall to timeout.
+        run: |
+          set -euo pipefail
+          sudo ifconfig lo0 alias 127.0.0.2 up
+          sudo ifconfig lo0 alias 127.0.0.3 up
+
       - name: Test
-        run: make check
+        run: |
+          jobs=$(( $(sysctl -n hw.ncpu) * 2 )); [ "$jobs" -le 16 ] || jobs=16
+          make check -j"$jobs"
 
       - name: Print the test log on failure
         if: failure()
@@ -171,7 +184,9 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        run: make check
+        run: |
+          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
+          make check -j"$jobs"
 
       - name: Print the test log on failure
         if: failure()
@@ -226,7 +241,9 @@ jobs:
         env:
           ASAN_OPTIONS: detect_leaks=0:abort_on_error=1:halt_on_error=1:strict_string_checks=1:malloc_fill_byte=202:max_malloc_fill_size=2147483647:free_fill_byte=203:max_free_fill_size=2147483647
           UBSAN_OPTIONS: print_stacktrace=1:halt_on_error=1
-        run: make check
+        run: |
+          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
+          make check -j"$jobs"
 
       - name: Print the test log on failure
         if: failure()
@@ -272,7 +289,8 @@ jobs:
           # 01_engine-* only; zlib-dependent self-tests are named 01_zlib-* and
           # skipped here (uninstrumented libz floods MSan with false positives).
           tests="$(cd tests && ls 01_engine-*.test | tr '\n' ' ')"
-          make check TESTS="$tests"
+          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
+          make check -j"$jobs" TESTS="$tests"
 
       - name: Print the test log on failure
         if: failure()
@@ -347,7 +365,9 @@ jobs:
         run: make -j"$(nproc)"
 
       - name: Test
-        run: make check
+        run: |
+          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
+          make check -j"$jobs"
 
       - name: Print the test log on failure
         if: failure()

AGENTS.md

@@ -6,8 +6,19 @@ the operational checklist: toolchain, invariants, and how to ship a change.
 ## Build & test
 - Fresh clone first: `git submodule update --init src/coucal`
 - `./bootstrap` (regenerates `configure` via `autoreconf`; needs autoconf,
-  automake, libtool), then `bash configure && make && make check`. Or run
-  `sh build.sh` to do bootstrap + configure + make in one shot.
+  automake, libtool), then `bash configure && make -j"$(nproc)" && make check
+  -j"$(nproc)"`. Always pass `-j` to `make check`: the suite runs under
+  automake's parallel harness and each crawl test binds its own ephemeral-port
+  server, so `-j` never contends and a multi-minute serial run drops to
+  seconds. A new `.test` added to `$(TESTS)` is scheduled onto a free worker
+  automatically; only a test slower than the current longest raises the floor.
+  On a few-core Linux box, `-j` at 2x the core count is faster still: the tests
+  spend much of their wall time asleep (server trickles, httrack self-pacing),
+  so an idle core covers a sleeping one. CI uses `min(2*cores, 16)` on every
+  platform, macOS included: the test server raises its listen backlog
+  (`request_queue_size`) so macOS/BSD don't drop connections under a parallel
+  `-c16` bigcrawl the way Python's default backlog of 5 did.
+  Or run `sh build.sh` to do bootstrap + configure + make in one shot.
 
 ## Hard invariants
 - **Generated autotools files are NOT in git.** `configure`, every

src/htsback.c

@@ -68,6 +68,15 @@ static int slot_can_be_cached_on_disk(const lien_back * back);
 static int slot_can_be_cleaned(const lien_back * back);
 static int slot_can_be_finalized(httrackp * opt, const lien_back * back);
 
+/* Which hard quota, if any, is currently aborting the mirror. */
+typedef enum {
+  HTS_MIRROR_LIMIT_NONE = 0,
+  HTS_MIRROR_LIMIT_SIZE,
+  HTS_MIRROR_LIMIT_TIME,
+} hts_mirror_limit;
+
+static hts_mirror_limit back_mirror_limit(httrackp *opt);
+
 struct_back *back_new(httrackp *opt, int back_max) {
   int i;
   struct_back *sback = calloct(1, sizeof(struct_back));
@@ -524,22 +533,22 @@ int back_nsoc_overall(const struct_back * sback) {
 
 /* generate temporary file on lien_back */
 /* Note: utf-8 */
-static int create_back_tmpfile(httrackp * opt, lien_back *const back) {
+static int create_back_tmpfile(httrackp *opt, lien_back *const back,
+                               const char *ext) {
   // do not use tempnam() but a regular filename
   back->tmpfile_buffer[0] = '\0';
   if (back->url_sav != NULL && back->url_sav[0] != '\0') {
-    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.z", 
-             back->url_sav);
+    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.%s",
+             back->url_sav, ext);
     back->tmpfile = back->tmpfile_buffer;
     if (structcheck(back->tmpfile) != 0) {
-      hts_log_print(opt, LOG_WARNING, "can not create directory to %s", 
+      hts_log_print(opt, LOG_WARNING, "can not create directory to %s",
                     back->tmpfile);
       return -1;
     }
   } else {
-    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer),
-             "%s/tmp%d.z", StringBuff(opt->path_html_utf8),
-             opt->state.tmpnameid++);
+    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s/tmp%d.%s",
+             StringBuff(opt->path_html_utf8), opt->state.tmpnameid++, ext);
     back->tmpfile = back->tmpfile_buffer;
   }
   /* OK */
@@ -547,6 +556,32 @@ static int create_back_tmpfile(httrackp * opt, lien_back *const back) {
   return 0;
 }
 
+/* Commit or restore a re-fetch backup (#77 follow-up): a re-fetch over an
+   existing file moved the good copy to back->tmpfile before truncating url_sav.
+   commit keeps the new file and drops the backup; else restore it so an aborted
+   transfer leaves the previous copy intact. Skips the zlib .z temp. */
+static void back_finalize_backup(httrackp *opt, lien_back *const back,
+                                 const hts_boolean commit) {
+  if (back->tmpfile == NULL || back->r.compressed)
+    return;
+  if (commit) {
+    (void) UNLINK(back->tmpfile); /* new copy is good; drop the backup */
+  } else {
+    if (back->r.out != NULL) {
+      fclose(back->r.out);
+      back->r.out = NULL;
+    }
+    (void) UNLINK(back->url_sav); /* drop the failed partial */
+    /* On rename failure keep the backup: it still holds the good copy, so
+       losing it would be worse than an orphaned temp. */
+    if (RENAME(back->tmpfile, back->url_sav) != 0)
+      hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
+                    "could not restore %s; previous copy kept as %s",
+                    back->url_sav, back->tmpfile);
+  }
+  back->tmpfile = NULL;
+}
+
 // objet (lien) téléchargé ou transféré depuis le cache
 //
 // fermer les paramètres de transfert,
@@ -582,6 +617,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                       LLintP " got " LLintP "): %s%s", back[p].r.totalsize,
                       back[p].r.size, back[p].url_adr, back[p].url_fil);
       }
+      back_finalize_backup(opt, &back[p], HTS_FALSE);
       return -1;
     }
 
@@ -600,7 +636,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
             // en mémoire -> passage sur disque
             if (!back[p].r.is_write) {
               // do not use tempnam() but a regular filename
-              if (create_back_tmpfile(opt, &back[p]) == 0) {
+              if (create_back_tmpfile(opt, &back[p], "z") == 0) {
                 assertf(back[p].tmpfile != NULL);
                 /* note: tmpfile is utf-8 */
                 back[p].r.out = FOPEN(back[p].tmpfile, "wb");
@@ -673,6 +709,9 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
           }
         }
 #endif
+        /* Body fully received: keep the freshly written url_sav, drop the
+           backup of the previous copy. */
+        back_finalize_backup(opt, &back[p], HTS_TRUE);
         /* Write mode to disk */
         if (back[p].r.is_write && back[p].r.adr != NULL) {
           freet(back[p].r.adr);
@@ -901,6 +940,9 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
       }
     }
   }
+  /* Aborted, error, or not ready: url_sav (if written) is broken; restore the
+     previous copy from the backup. */
+  back_finalize_backup(opt, &back[p], HTS_FALSE);
   return -1;
 }
 
@@ -2050,13 +2092,9 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
 
       if (!back_trylive(opt, cache, sback, p)) {
 #if HTS_XGETHOST
-#if HDEBUG
-        printf("back_solve..\n");
-#endif
-        back[p].status = STATUS_WAIT_DNS;       // tentative de résolution du nom de host
-        soc = INVALID_SOCKET;   // pas encore ouverte
-        back_solve(opt, &back[p]);      // préparer
-        if (host_wait(opt, &back[p])) { // prêt, par ex fichier ou dispo dans dns
+        back[p].status = STATUS_WAIT_DNS; // host name resolution attempt
+        soc = INVALID_SOCKET;             // not opened yet
+        if (host_wait(opt, &back[p])) {   // ready (file, or cached dns)
 #if HDEBUG
           printf("ok, dns cache ready..\n");
 #endif
@@ -2199,37 +2237,9 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
 }
 
 #if HTS_XGETHOST
-// attendre que le host (ou celui du proxy) ait été résolu
-// si c'est un fichier, la résolution est immédiate
-// idem pour ftp://
-void back_solve(httrackp * opt, lien_back * back) {
-  assertf(opt != NULL);
-  assertf(back != NULL);
-  if ((!strfield(back->url_adr, "file://"))
-      && !strfield(back->url_adr, "ftp://")
-    ) {
-    const char *a;
-
-    if (!(back->r.req.proxy.active))
-      a = back->url_adr;
-    else
-      a = back->r.req.proxy.name;
-    assertf(a != NULL);
-    a = jump_protocol_const(a);
-    if (check_hostname_dns(a)) {
-      hts_log_print(opt, LOG_DEBUG, "resolved: %s", a);
-    } else {
-      hts_log_print(opt, LOG_DEBUG, "failed to resolve: %s", a);
-    }
-  }
-}
-
-// détermine si le host a pu être résolu
-int host_wait(httrackp * opt, lien_back * back) {
-  // Always synchronous. No more background DNS resolution
-  // (does not really improve performances)
-  return 1;
-}
+// Resolution is synchronous inside the connect path; no pre-resolve step, so
+// the host is always immediately ready.
+int host_wait(httrackp *opt, lien_back *back) { return 1; }
 #endif
 
 // élimine les fichiers non html en backing (anticipation)
@@ -2416,9 +2426,15 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
   back_clean(opt, cache, sback);
 #endif
 
-  /* Time limit exceeded past grace: abort in-flight transfers so no wait loop
-     starves (#481). FTP slots stay, their thread owns the socket. */
+  /* Time/size limit exceeded past grace: abort in-flight transfers so no wait
+     loop starves (#481, #77). FTP slots stay, their thread owns the socket. */
   if (!back_checkmirror(opt)) {
+    const hts_mirror_limit limit = back_mirror_limit(opt);
+    const char *const reason =
+        (limit == HTS_MIRROR_LIMIT_SIZE) ? "size limit" : "time limit";
+    const char *const slotmsg = (limit == HTS_MIRROR_LIMIT_SIZE)
+                                    ? "Mirror Size Limit"
+                                    : "Mirror Time Out";
     int aborted = 0;
     unsigned int i;
 
@@ -2432,15 +2448,15 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
         if (back[i].r.is_write && IS_DELAYED_EXT(back[i].url_sav))
           back_delayed_discard(opt, &back[i]);
         back[i].r.statuscode = STATUSCODE_TIMEOUT;
-        strcpybuff(back[i].r.msg, "Mirror Time Out");
+        strcpybuff(back[i].r.msg, slotmsg);
         back[i].status = STATUS_READY;
         back_set_finished(sback, i);
         aborted++;
       }
     }
     if (aborted > 0)
-      hts_log_print(opt, LOG_WARNING,
-                    "time limit reached, %d transfer(s) aborted", aborted);
+      hts_log_print(opt, LOG_WARNING, "%s reached, %d transfer(s) aborted",
+                    reason, aborted);
     return;
   }
 
@@ -2930,7 +2946,8 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                 strfield(get_ext(catbuff, sizeof(catbuff), back[i].url_sav), "gz") == 0
                                 && strfield(get_ext(catbuff, sizeof(catbuff), back[i].url_sav), "tgz") == 0
                               ) {
-                              if (create_back_tmpfile(opt, &back[i]) == 0) {
+                              if (create_back_tmpfile(opt, &back[i], "z") ==
+                                  0) {
                                 assertf(back[i].tmpfile != NULL);
                                 /* note: tmpfile is utf-8 */
                                 if ((back[i].r.out =
@@ -2943,6 +2960,20 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                           back[i].url_sav, 1, 1,
                                           back[i].r.notmodified);
                               back[i].r.compressed = 0;
+                              /* Re-fetch over an existing file (#77 follow-up):
+                                 move the good copy aside before truncating it
+                                 so an aborted transfer can restore it. url_sav
+                                 is still written normally (file list intact).
+                               */
+                              back[i].tmpfile = NULL;
+                              if (fexist_utf8(back[i].url_sav)) {
+                                if (create_back_tmpfile(opt, &back[i], "bak") !=
+                                        0 ||
+                                    RENAME(back[i].url_sav, back[i].tmpfile) !=
+                                        0) {
+                                  back[i].tmpfile = NULL;
+                                }
+                              }
                               if ((back[i].r.out =
                                    filecreate(&opt->state.strc,
                                               back[i].url_sav)) == NULL) {
@@ -3481,6 +3512,11 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     continue;
                   }
 
+                  // The server really sent 304 here; the *-hacks below force
+                  // NOT_MODIFIED only after confirming the file is complete.
+                  const hts_boolean server_sent_304 =
+                      (back[i].r.statuscode == HTTP_NOT_MODIFIED);
+
                   /*
                      Solve "false" 416 problems
                    */
@@ -3509,22 +3545,20 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                   if (back[i].r.statuscode == 406) {    // 'Not Acceptable'
                     back[i].r.statuscode = HTTP_OK;
                   }
-                  // 'do not erase already downloaded file'
-                  // on an updated file
-                  // with an error : consider a 304 error
-                  if (!opt->delete_old) {
-                    if (HTTP_IS_ERROR(back[i].r.statuscode) && back[i].is_update
-                        && !back[i].testmode) {
-                      if (back[i].url_sav[0] && fexist_utf8(back[i].url_sav)) {
-                        hts_log_print(opt, LOG_DEBUG,
-                                      "Error ignored %d (%s) because of 'no purge' option for %s%s",
-                                      back[i].r.statuscode, back[i].r.msg,
-                                      back[i].url_adr, back[i].url_fil);
-                        back[i].r.statuscode = HTTP_NOT_MODIFIED;
-                        deletehttp(&back[i].r);
-                        back[i].r.soc = INVALID_SOCKET;
-                      }
-                    }
+                  // On update, keep the good copy on error (mask as 304); skip
+                  // resume paths so a stale-partial 416 still re-fetches.
+                  if (HTTP_IS_ERROR(back[i].r.statuscode) &&
+                      back[i].is_update && !back[i].testmode &&
+                      back[i].range_req_size == 0 && back[i].url_sav[0] &&
+                      fexist_utf8(back[i].url_sav)) {
+                    hts_log_print(opt, LOG_DEBUG,
+                                  "Error %d (%s) ignored on update, keeping "
+                                  "existing copy: %s%s",
+                                  back[i].r.statuscode, back[i].r.msg,
+                                  back[i].url_adr, back[i].url_fil);
+                    back[i].r.statuscode = HTTP_NOT_MODIFIED;
+                    deletehttp(&back[i].r);
+                    back[i].r.soc = INVALID_SOCKET;
                   }
                   // Various hacks to limit re-transfers when updating a mirror
                   // Force update if same size detected
@@ -3577,7 +3611,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                       if (back[i].r.statuscode == HTTP_OK && !back[i].testmode) {       // 'OK'
                         if (!is_hypertext_mime(opt, back[i].r.contenttype, back[i].url_fil)) {  // not HTML
                           if (strnotempty(back[i].url_sav)) {   // target found
-                            int size = fsize_utf8(back[i].url_sav);     // target size
+                            off_t size = fsize_utf8(back[i].url_sav);
 
                             if (size >= 0) {
                               if (back[i].r.totalsize == size) {        // same size!
@@ -3672,6 +3706,21 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     }
                   }
 
+                  // Out-of-protocol 304 to a Range resume: the file is still
+                  // partial, so drop it and refetch instead of trusting it.
+                  if (server_sent_304 && back[i].range_req_size > 0) {
+                    url_savename_refname_remove(opt, back[i].url_adr,
+                                                back[i].url_fil);
+                    UNLINK(back[i].url_sav);
+                    deletehttp(&back[i].r);
+                    back[i].r.soc = INVALID_SOCKET;
+                    back[i].r.statuscode = STATUSCODE_NON_FATAL;
+                    strcpybuff(back[i].r.msg,
+                               "Bogus 304 on resume, restarting");
+                    back[i].status = STATUS_READY;
+                    back_set_finished(sback, i);
+                  }
+
                   /* sinon, continuer */
                   /* if (back[i].r.soc!=INVALID_SOCKET) {   // ok récupérer body? */
                   // head: terminé
@@ -3790,7 +3839,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                       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.crange_end == back[i].r.crange - 1 &&
                           (back[i].r.totalsize < 0 ||
                            back[i].r.totalsize ==
                                back[i].r.crange_end - resume + 1);
@@ -3859,11 +3908,20 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                           if (fp) {
                             LLint alloc_mem = resume + 1;
 
-                            if (back[i].r.totalsize >= 0)
+                            // Bound the in-memory buffer to a 32-bit size (real
+                            // in-RAM resources are far smaller); a hostile
+                            // Content-Length that would overflow the add or the
+                            // (size_t) cast is dropped and refetched instead.
+                            if (back[i].r.totalsize > INT32_MAX - alloc_mem) {
+                              url_savename_refname_remove(opt, back[i].url_adr,
+                                                          back[i].url_fil);
+                              UNLINK(back[i].url_sav);
+                              alloc_mem = -1;
+                            } else 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))) {
+                            if (alloc_mem >= 0 && deleteaddr(&back[i].r) &&
+                                (back[i].r.adr =
+                                     (char *) malloct((size_t) alloc_mem))) {
                               back[i].r.size = resume;
                               if (back[i].r.totalsize >= 0)
                                 back[i].r.totalsize += resume; // -> full size
@@ -4145,38 +4203,46 @@ static int back_maxtime_grace(const int maxtime) {
   return maximum(5, minimum(30, maxtime / 10));
 }
 
-int back_checkmirror(httrackp * opt) {
-  // Check max size
-  if ((opt->maxsite > 0) && (HTS_STAT.stat_bytes >= opt->maxsite)) {
-    if (!opt->state.stop) {     /* not yet stopped */
-      hts_log_print(opt, LOG_ERROR,
-                    "More than " LLintP
-                    " bytes have been transferred.. giving up",
-                    (LLint) opt->maxsite);
-      /* cancel mirror smoothly */
-      hts_request_stop(opt, 0);
-    }
-    return 1;                   /* don'k break mirror too sharply for size limits, but stop requested */
-    /*return 0;
-     */
-  }
-  // Check max time
+/* Bytes the smooth stop may overrun before in-flight transfers are aborted.
+   No floor (unlike the time grace): a size overrun should abort promptly. */
+static LLint back_maxsize_grace(const LLint maxsite) { return maxsite / 10; }
+
+/* Which cap has overrun its grace and must hard-stop the mirror (#77, #481).
+   -M measures received volume (HTS_TOTAL_RECV), not saved 200-only stat_bytes
+   which undercounts redirect/error-heavy crawls (#520). */
+static hts_mirror_limit back_mirror_limit(httrackp *opt) {
+  if (opt->maxsite > 0 && HTS_STAT.HTS_TOTAL_RECV >= opt->maxsite &&
+      HTS_STAT.HTS_TOTAL_RECV - opt->maxsite >=
+          back_maxsize_grace(opt->maxsite))
+    return HTS_MIRROR_LIMIT_SIZE;
   if (opt->maxtime > 0) {
     const TStamp elapsed = time_local() - HTS_STAT.stat_timestart;
 
-    if (elapsed >= opt->maxtime) {
-      if (!opt->state.stop) { /* not yet stopped */
-        hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
-                      opt->maxtime);
-        /* cancel mirror smoothly */
-        hts_request_stop(opt, 0);
-      }
-      /* smooth stop starved past the grace period: stop waiting (#481) */
-      if (elapsed - opt->maxtime >= back_maxtime_grace(opt->maxtime))
-        return 0;
-    }
+    if (elapsed >= opt->maxtime &&
+        elapsed - opt->maxtime >= back_maxtime_grace(opt->maxtime))
+      return HTS_MIRROR_LIMIT_TIME;
   }
-  return 1;                     /* Ok, go on */
+  return HTS_MIRROR_LIMIT_NONE;
+}
+
+int back_checkmirror(httrackp *opt) {
+  /* request a smooth stop the first time each cap is reached */
+  if (opt->maxsite > 0 && HTS_STAT.HTS_TOTAL_RECV >= opt->maxsite &&
+      !opt->state.stop) {
+    hts_log_print(opt, LOG_ERROR,
+                  "More than " LLintP
+                  " bytes have been transferred.. giving up",
+                  (LLint) opt->maxsite);
+    hts_request_stop(opt, 0);
+  }
+  if (opt->maxtime > 0 && !opt->state.stop &&
+      (time_local() - HTS_STAT.stat_timestart) >= opt->maxtime) {
+    hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
+                  opt->maxtime);
+    hts_request_stop(opt, 0);
+  }
+  /* hard stop once a cap overruns its grace (callers must stop waiting) */
+  return back_mirror_limit(opt) == HTS_MIRROR_LIMIT_NONE;
 }
 
 // octets transférés + add

src/htsback.h

@@ -138,12 +138,11 @@ LLint back_transferred(LLint add, struct_back * sback);
 
 // hostback
 #if HTS_XGETHOST
-void back_solve(httrackp * opt, lien_back * sback);
 int host_wait(httrackp * opt, lien_back * sback);
 #endif
 int back_checksize(httrackp * opt, lien_back * eback, int check_only_totalsize);
-/* Enforce -M/-E quotas: requests a smooth stop when reached; returns 0 once
-   the -E deadline overran its grace period (callers must stop waiting). */
+/* Enforce -M/-E quotas: smooth-stops when reached; returns 0 once the -M cap
+   or -E deadline overruns its grace period (callers must stop waiting). */
 int back_checkmirror(httrackp * opt);
 
 #endif

src/htscore.c

@@ -1904,8 +1904,11 @@ int httpmirror(char *url1, httrackp * opt) {
             }
           }
 
-          // ATTENTION C'EST ICI QU'ON SAUVE LE FICHIER!!          
-          if (r.adr != NULL || r.size == 0) {
+          // ATTENTION C'EST ICI QU'ON SAUVE LE FICHIER!!
+          // An empty body must not overwrite the file when the transfer failed
+          // (statuscode <= 0, e.g. an -M hard-stop): it would truncate a good
+          // copy to 0 (#77 follow-up).
+          if (r.adr != NULL || (r.size == 0 && r.statuscode > 0)) {
             file_notify(opt, urladr(), urlfil(), savename(), 1, 1, r.notmodified);
             if (filesave(opt, r.adr, (int) r.size, savename(), urladr(), urlfil()) !=
                 0) {
@@ -1926,7 +1929,6 @@ int httpmirror(char *url1, httrackp * opt) {
                */
             }
           }
-
         }
 
         /* Parsing of other media types (java, ram..) */

src/htsdns_selftest.c

@@ -297,6 +297,26 @@ int dns_selftests(httrackp *opt) {
     IPV6_resolver = 0;
   }
 
+  /* "host:port" resolves as the bare host: the cache/connect path strips
+     ":port" before both the backend and the cache key (#181). */
+  mock_reset_calls();
+  {
+    SOCaddr a;
+    char ip[64];
+    const char *err = NULL;
+
+    /* cache miss: the backend is hit with the stripped host, not "host:port" */
+    CHECK(hts_dns_resolve2(opt, "v6only.test:8080", &a, &err) != NULL);
+    CHECK(mock_find("v6only.test")->calls == 1);
+    /* the bare host shares that one cache entry (stripped key) */
+    CHECK(hts_dns_resolve2(opt, "v6only.test", &a, &err) != NULL);
+    CHECK(mock_find("v6only.test")->calls == 1);
+    /* a port variant of an already-cached host also hits, right address */
+    CHECK(hts_dns_resolve2(opt, "v4only.test:1234", &a, &err) != NULL);
+    SOCaddr_inetntoa(ip, sizeof(ip), a);
+    CHECK(strcmp(ip, "1.2.3.4") == 0);
+  }
+
   /* newhttp_addr() must connect to the addr_index-th address, not always the
      first: this is what back_connect_next relies on to reach the fallback. */
   {

src/htsglobal.h

@@ -56,6 +56,10 @@ Please visit our Website: http://www.httrack.com
 // Platform detection (sizes, feature macros)
 #include "htsconfig.h"
 
+// Fixed-width integer types + PRI* format macros for the LLint/TStamp typedefs
+#include <stdint.h>
+#include <inttypes.h>
+
 // WIN32 types
 #ifdef _WIN32
 #ifndef SIZEOF_LONG
@@ -111,29 +115,6 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DO_NOT_USE_UID
 #endif
 
-#ifndef HTS_LONGLONG
-#ifdef SIZEOF_LONG_LONG
-#if SIZEOF_LONG_LONG == 8
-#define HTS_LONGLONG 1
-#endif
-#endif
-
-#ifndef HTS_LONGLONG
-#ifdef __sun
-#define HTS_LONGLONG 0
-#endif
-#ifdef __osf__
-#define HTS_LONGLONG 0
-#endif
-#ifdef __linux
-#define HTS_LONGLONG 1
-#endif
-#ifdef _WIN32
-#define HTS_LONGLONG 1
-#endif
-#endif
-#endif
-
 #ifdef DLLIB
 #define HTS_DLOPEN 1
 #else
@@ -326,59 +307,11 @@ typedef int hts_tristate;
 #define HTS_DEPRECATED(msg)
 #endif
 
-#ifndef HTS_LONGLONG
-#ifdef HTS_NO_64_BIT
-#define HTS_LONGLONG 0
-#else
-#define HTS_LONGLONG 1
-#endif
-#endif
-
-/* Wide integer types, chosen per platform.
-   LLint:  signed 64-bit counter for byte counts and large sizes (falls back to
-           plain int where 64-bit is unavailable).
-   TStamp: timestamp/duration in the same width (a double in the no-64-bit
-           fallback).
-   LLintP: the printf conversion for an LLint. */
-#if HTS_LONGLONG
-#ifdef LLINT_FORMAT
-typedef LLINT_TYPE LLint;
-
-typedef LLINT_TYPE TStamp;
-
-#define LLintP LLINT_FORMAT
-#else
-
-#ifdef _WIN32
-typedef __int64 LLint;
-
-typedef __int64 TStamp;
-
-#define LLintP "%I64d"
-#elif (defined(_LP64) || defined(__x86_64__) || defined(__powerpc64__) ||      \
-       defined(__64BIT__))
-
-typedef long int LLint;
-
-typedef long int TStamp;
-
-#define LLintP "%ld"
-#else
-typedef long long int LLint;
-
-typedef long long int TStamp;
-
-#define LLintP "%lld"
-#endif
-
-#endif /* HTS_LONGLONG */
-
-#else
-typedef int LLint;
-
-#define LLintP "%d"
-typedef double TStamp;
-#endif
+/* LLint/TStamp: signed exact-width 64-bit; -1 is a sentinel engine-wide. */
+typedef int64_t LLint;
+typedef int64_t TStamp;
+/* Full printf conversion, '%' included (PRId64 has none): "X: " LLintP. */
+#define LLintP "%" PRId64
 
 /* Integer type for file offsets/sizes passed to the C library. Widens to
    LLint (with HTS_FSEEKO for fseeko/ftello) under large-file support, plain

src/htslib.c

@@ -1059,10 +1059,10 @@ static int append_cookie_header(buff_struct *bstr, t_cookie *cookie,
   return cook;
 }
 
-/* Self-test entry for append_cookie_header(): build the request Cookie line
-   into dst (always NUL-terminated). Returns the number of cookies emitted. */
-int http_cookie_header_selftest(t_cookie *cookie, const char *domain,
-                                const char *path, char *dst, size_t dst_size) {
+/* Build the request Cookie line for domain/path into dst (always
+   NUL-terminated). Returns the number of cookies emitted. */
+int http_cookie_header(t_cookie *cookie, const char *domain, const char *path,
+                       char *dst, size_t dst_size) {
   buff_struct bstr = {dst, dst_size, 0};
 
   assertf(dst != NULL && dst_size > 0);
@@ -1586,7 +1586,7 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
         a = strchr(rcvd + p, '/');
         if (a != NULL) {
           a++;
-          if (sscanf(a, LLintP, &retour->crange) == 1) {
+          if (sscanf(a, LLintP, &retour->crange) == 1 && retour->crange >= 0) {
             retour->crange_start = 0;
             retour->crange_end = retour->crange - 1;
           } else {
@@ -1594,6 +1594,12 @@ void treathead(t_cookie * cookie, const char *adr, const char *fil, htsblk * ret
           }
         }
       }
+      // A valid Content-Range has no negative field; reject hostile values so
+      // the crange +/- 1 arithmetic downstream cannot sign-overflow (UB).
+      if (retour->crange_start < 0 || retour->crange_end < 0 ||
+          retour->crange < 0) {
+        retour->crange_start = retour->crange_end = retour->crange = 0;
+      }
     }
   } else if ((p = strfield(rcvd, "Connection:")) != 0) {
     char *a = rcvd + p;
@@ -1998,6 +2004,15 @@ LLint http_xfread1(htsblk * r, int bufl) {
 
   if (bufl > 0) {
     if (!r->is_write) {         // stocker en mémoire
+      // In-memory content must fit a 32-bit index (allocs below add 1, reads
+      // use int offsets): reject a hostile Content-Length or endless stream.
+      const LLint inmem_want =
+          (r->totalsize >= 0) ? r->totalsize : (r->size + bufl);
+      if (inmem_want >= INT32_MAX) {
+        r->statuscode = STATUSCODE_INVALID;
+        strcpybuff(r->msg, "In-memory content too large");
+        return READ_ERROR;
+      }
       if (r->totalsize >= 0) {  // totalsize déterminé ET ALLOUE
         if (r->adr == NULL) {
           r->adr = (char *) malloct((size_t) r->totalsize + 1);
@@ -3038,12 +3053,11 @@ HTSEXT_API char *int2char(strc_int2bytes2 * strc, int n) {
 /* See http://physics.nist.gov/cuu/Units/binary.html */
 #define ToLLint(a) ((LLint)(a))
 #define ToLLintKiB (ToLLint(1024))
-#define ToLLintMiB (ToLLintKiB*ToLLintKiB)
-#ifdef HTS_LONGLONG
-#define ToLLintGiB (ToLLintKiB*ToLLintKiB*ToLLintKiB)
-#define ToLLintTiB (ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB)
-#define ToLLintPiB (ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB)
-#endif
+#define ToLLintMiB (ToLLintKiB * ToLLintKiB)
+#define ToLLintGiB (ToLLintKiB * ToLLintKiB * ToLLintKiB)
+#define ToLLintTiB (ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB)
+#define ToLLintPiB                                                             \
+  (ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB)
 HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
   if (n < ToLLintKiB) {
     sprintf(strc->buff1, "%d", (int) (LLint) n);
@@ -3052,9 +3066,7 @@ HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
     sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / ToLLintKiB)),
             (int) ((LLint) ((n % ToLLintKiB) * 100) / ToLLintKiB));
     strcpybuff(strc->buff2, "KiB");
-  }
-#ifdef HTS_LONGLONG
-  else if (n < ToLLintGiB) {
+  } else if (n < ToLLintGiB) {
     sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / (ToLLintMiB))),
             (int) ((LLint) (((n % (ToLLintMiB)) * 100) / (ToLLintMiB))));
     strcpybuff(strc->buff2, "MiB");
@@ -3071,13 +3083,6 @@ HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
             (int) ((LLint) (((n % (ToLLintPiB)) * 100) / (ToLLintPiB))));
     strcpybuff(strc->buff2, "PiB");
   }
-#else
-  else {
-    sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / (ToLLintMiB))),
-            (int) ((LLint) (((n % (ToLLintMiB)) * 100) / (ToLLintMiB))));
-    strcpybuff(strc->buff2, "MiB");
-  }
-#endif
   strc->buffadr[0] = strc->buff1;
   strc->buffadr[1] = strc->buff2;
   return strc->buffadr;

src/htslib.h

@@ -184,10 +184,10 @@ int http_sendhead(httrackp * opt, t_cookie * cookie, int mode, const char *xsend
                   const char *referer_adr, const char *referer_fil,
                   htsblk * retour);
 /* Build the request "Cookie:" header line for stored cookies matching
-   domain/path into dst (NUL-terminated). Exposed for the -#Q self-test;
-   wraps the same logic http_sendhead() uses. Returns cookies emitted. */
-int http_cookie_header_selftest(t_cookie *cookie, const char *domain,
-                                const char *path, char *dst, size_t dst_size);
+   domain/path into dst (NUL-terminated), wrapping the logic http_sendhead()
+   uses. Returns cookies emitted. */
+int http_cookie_header(t_cookie *cookie, const char *domain, const char *path,
+                       char *dst, size_t dst_size);
 
 T_SOC newhttp(httrackp * opt, const char *iadr, htsblk * retour, int port,
               int waitconnect);

src/htsparse.c

@@ -4311,6 +4311,8 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
       *forbidden_url == 0 && IS_DELAYED_EXT(afs->save) && !opt->state.stop) {
     int loops;
     int continue_loop;
+    char BIGSTK
+        cookie_before[16384]; /* #15: this URL's Cookie header, pre-request */
 
     hts_log_print(opt, LOG_DEBUG, "Waiting for type to be known: %s%s", afs->af.adr,
                   afs->af.fil);
@@ -4319,6 +4321,12 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
     for(loops = 0, continue_loop = 1;
         IS_DELAYED_EXT(afs->save) && continue_loop && loops < 7; loops++) {
       continue_loop = 0;
+      /* #15: snapshot the Cookie header THIS url would send, so only its own
+         self-redirect Set-Cookie trips the retry, not a concurrent slot's. */
+      cookie_before[0] = '\0';
+      if (opt->accept_cookie && opt->cookie != NULL)
+        http_cookie_header(opt->cookie, jump_identification_const(afs->af.adr),
+                           afs->af.fil, cookie_before, sizeof(cookie_before));
 
       /* Wait for an available slot */
       if (!hts_wait_available_socket(sback, opt, cache, ptr))
@@ -4516,6 +4524,17 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
           /* Moved! */
           else if (HTTP_IS_REDIRECT(back[b].r.statuscode)) {
             char BIGSTK mov_url[HTS_URLMAXSIZE * 2];
+            char BIGSTK cookie_after[16384];
+            hts_boolean cookies_changed;
+
+            /* #15: cookie-wall signal: this URL's own Cookie header changed
+               across its self-redirect (a Set-Cookie it just set). */
+            cookie_after[0] = '\0';
+            if (opt->accept_cookie && opt->cookie != NULL)
+              http_cookie_header(
+                  opt->cookie, jump_identification_const(afs->af.adr),
+                  afs->af.fil, cookie_after, sizeof(cookie_after));
+            cookies_changed = strcmp(cookie_before, cookie_after) != 0;
 
             mov_url[0] = '\0';
             strcpybuff(mov_url, back[b].r.location);    // copier URL
@@ -4585,11 +4604,24 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
                   url_savename(afs, former, heap(ptr)->adr, heap(ptr)->fil, 
                                opt, sback, cache, hash, ptr, numero_passe,
                                &delayed_back);
+                } else if (cookies_changed) {
+                  // #15: cookie-wall self-redirect; evict the cached
+                  // fast-header so the re-issue refetches with the cookie.
+                  if (cache->cached_tests != NULL)
+                    coucal_remove(cache->cached_tests,
+                                  concat(OPT_GET_BUFF(opt),
+                                         OPT_GET_BUFF_SIZE(opt), afs->af.adr,
+                                         afs->af.fil));
+                  afs->save[0] = '\0';
+                  url_savename(afs, former, heap(ptr)->adr, heap(ptr)->fil, opt,
+                               sback, cache, hash, ptr, numero_passe,
+                               &delayed_back);
+                  continue_loop = 1;
                 } else {
                   hts_log_print(opt, LOG_WARNING,
                                 "Unable to test %s%s (loop to same filename)",
                                 afs->af.adr, afs->af.fil);
-                }               // loop to same location
+                } // loop to same location
               }                 // ident_url_relatif()
             }                   // location
           }                     // redirect

src/htsselftest.c

@@ -1310,6 +1310,82 @@ static int st_headerlong(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* http_xfread1 must refuse an in-memory buffer whose size would exceed a 32-bit
+   index (hostile Content-Length or endless stream) rather than allocate it.
+   The guard returns before any socket read, so no real connection is needed. */
+static int st_xfread_limit(httrackp *opt, int argc, char **argv) {
+  htsblk r;
+
+  (void) opt;
+  (void) argc;
+  (void) argv;
+
+  // Content-Length just over 2 GiB.
+  memset(&r, 0, sizeof(r));
+  r.soc = INVALID_SOCKET;
+  r.totalsize = (LLint) INT32_MAX + 1;
+  printf("bylen: refused=%d adr=%s msg=%s\n",
+         http_xfread1(&r, 8192) == READ_ERROR, r.adr != NULL ? "alloc" : "null",
+         r.msg);
+  if (r.adr != NULL)
+    freet(r.adr);
+
+  // Unknown length, buffer already at the limit: the next read would exceed it.
+  memset(&r, 0, sizeof(r));
+  r.soc = INVALID_SOCKET;
+  r.totalsize = -1;
+  r.size = (LLint) INT32_MAX;
+  printf("bygrow: refused=%d adr=%s msg=%s\n",
+         http_xfread1(&r, 8192) == READ_ERROR, r.adr != NULL ? "alloc" : "null",
+         r.msg);
+  if (r.adr != NULL)
+    freet(r.adr);
+
+  // Exactly at the 2 GiB index (size + bufl == INT32_MAX): must also be
+  // refused, since the reallocs below add 1 (a `> INT32_MAX` check would let
+  // this through and overflow the int realloc size).
+  memset(&r, 0, sizeof(r));
+  r.soc = INVALID_SOCKET;
+  r.totalsize = -1;
+  r.size = (LLint) INT32_MAX - 8192;
+  http_xfread1(&r, 8192);
+  printf("boundary: msg=%s\n", r.msg);
+
+  // A legitimate small size must NOT be refused by the guard (the read then
+  // fails on the invalid socket, but the size-too-large msg must not be set).
+  memset(&r, 0, sizeof(r));
+  r.soc = INVALID_SOCKET;
+  r.totalsize = 1000;
+  http_xfread1(&r, 8192);
+  printf("accept: msg=%s\n", r.msg);
+  if (r.adr != NULL)
+    freet(r.adr);
+  return 0;
+}
+
+/* Parse a Content-Range header and print the sanitized triple. A hostile value
+   (negative or INT64 extreme) must clamp to 0 without signed-overflow UB. */
+static int st_crange(httrackp *opt, int argc, char **argv) {
+  int i;
+
+  (void) opt;
+  if (argc < 1) {
+    fprintf(stderr, "crange: needs at least one raw Content-Range line\n");
+    return 1;
+  }
+  for (i = 0; i < argc; i++) {
+    htsblk r;
+    char BIGSTK line[HTS_URLMAXSIZE * 2];
+
+    memset(&r, 0, sizeof(r));
+    strcpybuff(line, argv[i]);
+    treathead(NULL, "www.example.com", "/", &r, line);
+    printf("crange_start=" LLintP " crange_end=" LLintP " crange=" LLintP "\n",
+           (LLint) r.crange_start, (LLint) r.crange_end, (LLint) r.crange);
+  }
+  return 0;
+}
+
 /* Decode a body argument ("hex:FFD8.." or literal text) into buf. */
 static size_t st_decode_body(const char *arg, char *buf, size_t size) {
   size_t n = 0;
@@ -1679,7 +1755,7 @@ static int st_cookies(httrackp *opt, int argc, char **argv) {
     return 1;
   }
 
-  http_cookie_header_selftest(&cookie, dom, "/", hdr, sizeof(hdr));
+  http_cookie_header(&cookie, dom, "/", hdr, sizeof(hdr));
   if (strcmp(hdr, expected) != 0)
     err = 1;
   if (strstr(hdr, "$Version") != NULL || strstr(hdr, "$Path") != NULL)
@@ -2496,6 +2572,10 @@ static const struct selftest_entry {
     {"headerlong", "[header-name:]",
      "over-long header value must not overflow the parse scratch",
      st_headerlong},
+    {"crange", "<raw-content-range-line> ...",
+     "Content-Range parse integer safety", st_crange},
+    {"xfread-limit", "", "in-memory receive buffer size bound",
+     st_xfread_limit},
     {"savename", "<fil> <content-type> [key=value ...]",
      "local save-name for a URL", st_savename},
     {"sniff", "<content-type> <hex:..|text>", "MIME magic consistency",

tests/01_engine-crange.test

@@ -0,0 +1,34 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# Content-Range parse (treathead via -#test=crange). Hostile values must clamp
+# to 0, and the crange +/- 1 arithmetic must not sign-overflow (UBSan aborts on
+# the pre-fix binary at the INT64_MIN cases).
+
+cr() {
+    local want="$1"
+    shift
+    out="$(httrack -O /dev/null -#test=crange "$@")"
+    test "$out" == "$want" || {
+        echo "FAIL: $* -> '$out' (want '$want')"
+        exit 1
+    }
+}
+
+# Normal range and the '*/N' fallback both parse through unchanged.
+cr 'crange_start=0 crange_end=70870 crange=70871' 'Content-Range: bytes 0-70870/70871'
+cr 'crange_start=0 crange_end=70870 crange=70871' 'Content-Range: bytes */70871'
+
+# INT64_MIN total in the fallback would make crange-1 overflow: clamp to 0.
+cr 'crange_start=0 crange_end=0 crange=0' 'Content-Range: bytes */-9223372036854775808'
+
+# Any negative field in the 3-field form clamps the whole triple to 0 (each
+# field independently: a leading negative start/end alone still zeroes all).
+cr 'crange_start=0 crange_end=0 crange=0' 'Content-Range: bytes -1--1/-1'
+cr 'crange_start=0 crange_end=0 crange=0' 'Content-Range: bytes -5-10/20'
+
+# INT64_MAX is non-negative: it passes through, the parse must not mangle it.
+cr 'crange_start=0 crange_end=9223372036854775807 crange=9223372036854775807' \
+    'Content-Range: bytes 0-9223372036854775807/9223372036854775807'

tests/01_engine-xfread.test

@@ -0,0 +1,29 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# http_xfread1 must refuse an in-memory receive buffer that would exceed a
+# 32-bit index (hostile Content-Length, or an endless stream) rather than
+# allocate it, while still accepting a normal small size. -#test=xfread-limit
+# drives both refusal paths and the accept path.
+
+out="$(httrack -O /dev/null -#test=xfread-limit)"
+for case in bylen bygrow; do
+    echo "$out" | grep -q "${case}: refused=1 adr=null msg=In-memory content too large" || {
+        echo "FAIL ${case}: $out"
+        exit 1
+    }
+done
+
+# Exactly INT32_MAX must be refused too (the reallocs add 1).
+echo "$out" | grep -q 'boundary: msg=In-memory content too large' || {
+    echo "FAIL boundary: $out"
+    exit 1
+}
+
+# The guard must NOT fire for a legitimate small size.
+if echo "$out" | grep -q 'accept: msg=In-memory content too large'; then
+    echo "FAIL accept (guard fired on a legit size): $out"
+    exit 1
+fi

tests/19_local-connect-fallback.test

@@ -66,9 +66,12 @@ test -n "$port" || {
 }
 
 out="$tmpdir/crawl"
+# macOS has only 127.0.0.1, so the dead 127.0.0.x connects block to the timeout
+# instead of refusing instantly (as on Linux); a small --timeout + --retries=0
+# bound the stall without changing what the fallback exercises.
 HTTRACK_DEBUG_RESOLVE="deadhost:127.0.0.2,127.0.0.1" \
     httrack "http://deadhost:$port/simple/basic.html" -O "$out" \
-    -c1 --robots=0 --timeout=30 --quiet -Z >"$tmpdir/log" 2>&1
+    -c1 --robots=0 --timeout=5 --retries=0 --quiet -Z >"$tmpdir/log" 2>&1
 
 log="$out/hts-log.txt"
 
@@ -92,12 +95,12 @@ test -f "$out/deadhost_$port/simple/basic.html" || {
     exit 1
 }
 
-# every address refused: the slot exhausts the list, then errors out (the
-# harness timeout would catch a hang/loop; refused connects are instant)
+# every address dead: the slot exhausts the list, then errors out (the harness
+# timeout would catch a hang/loop)
 out2="$tmpdir/crawl2"
 HTTRACK_DEBUG_RESOLVE="alldead:127.0.0.2,127.0.0.3" \
     httrack "http://alldead:$port/simple/basic.html" -O "$out2" \
-    -c1 --robots=0 --timeout=30 --quiet -Z >"$tmpdir/log2" 2>&1
+    -c1 --robots=0 --timeout=5 --retries=0 --quiet -Z >"$tmpdir/log2" 2>&1
 log2="$out2/hts-log.txt"
 
 grep -q "trying next address" "$log2" || {

tests/31_local-javaclass.test

@@ -17,7 +17,10 @@ printf 'GIF89a' >"$tmproot/javaclass/hello.gif"
 printf '\xCA\xFE\xBA\xBE\x00\x00\x00\x32\x00\x02\x01\x00\x09hello.gif\x00\x00\x00\x00' \
     >"$tmproot/javaclass/Foo.class"
 
+# --log-found first: a plugin-load failure (wrong soname, shadowing system
+# libhtsjava) trips here on the banner suffix, not as an opaque "not found".
 bash "$top_srcdir/tests/local-crawl.sh" --root "$tmproot" --errors 0 \
+    --log-found '\+libhtsjava' \
     --found 'javaclass/Foo.class' \
     --found 'javaclass/hello.gif' \
     httrack 'BASEURL/javaclass/index.html'

tests/36_local-bigcrawl.test

@@ -9,7 +9,7 @@ set -euo pipefail
 : "${top_srcdir:=..}"
 
 bash "$top_srcdir/tests/local-crawl.sh" --rerun \
-    --errors 4 --files 361 \
+    --errors-content 4 --files 361 \
     --found 'big/p/95.html' \
     --found 'big/a/d1/d2/d3/d4/d5/d6/d7/d8/deep.png' \
     --found 'big/a/f2-2x.png' \
@@ -53,4 +53,4 @@ bash "$top_srcdir/tests/local-crawl.sh" --rerun \
     --log-found ', no files updated' \
     --max-mirror-bytes 700000 \
     --min-mirror-bytes 500000 \
-    httrack 'BASEURL/big/index.html' --retries=0 -c8 -%c100 -A100000000
+    httrack 'BASEURL/big/index.html' --retries=0 -c16 -%c100 -A100000000

tests/42_local-maxsize-slow.test

@@ -0,0 +1,21 @@
+#!/bin/bash
+#
+# -M byte cap under a slow server (#77): p0 overruns -M at once while p1..p3
+# trickle for a minute; the cap must abort the in-flight transfers, not wait
+# them out. Unfixed, the smooth stop drains the trickle at server pace.
+
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+start=$(date +%s)
+bash "$top_srcdir/tests/local-crawl.sh" \
+    --log-found 'More than 400000 bytes have been transferred.. giving up' \
+    httrack 'BASEURL/bigtrickle/index.html' -M400000 -c4
+wall=$(($(date +%s) - start))
+# trickle runs 60s; a smooth-only stop waits it out, the hard stop lands near 8s.
+# Wall clock is the discriminating check: the log line above fires either way.
+if [ "$wall" -ge 30 ]; then
+    echo "crawl took ${wall}s, -M hard stop did not engage" >&2
+    exit 1
+fi

tests/43_local-update-truncate.test

@@ -0,0 +1,24 @@
+#!/bin/bash
+#
+# -M hard-abort must not destroy already-complete files (#77 follow-up).
+# Pass 1 mirrors bigtrunc fully. Pass 2 re-fetches under --update -M: fast.bin
+# overruns the cap, its abort tears down slow.bin's stalled re-fetch. Both were
+# complete on disk from pass 1, and both must survive the aborted update:
+#   - slow.bin's re-fetch is incomplete; the direct-to-disk write must not be
+#     left truncated (the previous copy is restored).
+#   - fast.bin fully arrives but is torn down; the aborted slot must not overwrite
+#     it with an empty body.
+# Unfixed, slow.bin is truncated and fast.bin is zeroed while the cache still
+# records them complete.
+
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+bash "$top_srcdir/tests/local-crawl.sh" \
+    --rerun-args '--update -M400000' \
+    --log-found 'More than 400000 bytes have been transferred.. giving up' \
+    --found bigtrunc/slow.bin \
+    --file-min-bytes bigtrunc/slow.bin 655360 \
+    --file-min-bytes bigtrunc/fast.bin 655360 \
+    httrack 'BASEURL/bigtrunc/index.html' -c2

tests/44_local-update-errormask.test

@@ -0,0 +1,13 @@
+#!/bin/bash
+# Issue #176: on --update a page that 200'd on the first crawl but now 403s must
+# keep its good local copy, not be overwritten by the error body nor purged.
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+bash "$top_srcdir/tests/local-crawl.sh" --rerun \
+    --found 'errmask/keep.dat' \
+    --file-min-bytes 'errmask/keep.dat' 1024 \
+    --file-matches 'errmask/keep.dat' '^KEEP' \
+    --file-not-matches 'errmask/keep.dat' 'error 403' \
+    httrack 'BASEURL/errmask/index.html'

tests/45_local-maxsize-recv.test

@@ -0,0 +1,16 @@
+#!/bin/bash
+#
+# -M caps received volume, not saved 200-only bytes (#520): links to large 404
+# bodies pump received >> saved; the cap must trip though little lands on disk.
+
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+# The mirror bound is the load-bearing half: it fires while <100 KB is saved,
+# so the cap can only have tripped on received volume, not saved bytes (which
+# would exceed the cap and fetch all 16 links).
+bash "$top_srcdir/tests/local-crawl.sh" \
+    --log-found 'More than 500000 bytes have been transferred.. giving up' \
+    --max-mirror-bytes 100000 \
+    httrack 'BASEURL/maxrecv/index.html' -M500000 -c4

tests/46_local-update-304-resume.test

@@ -0,0 +1,118 @@
+#!/bin/bash
+# C7: a server 304 answering a resume's Range request is out of protocol; httrack
+# must drop the partial and refetch, not finalize it as complete at the partial
+# byte count. Pass 1 leaves a partial + temp-ref; pass 2 resumes, gets a bogus
+# 304, and must recover the whole file.
+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_c7.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
+
+serverlog="${tmpdir}/server.log"
+counter="${tmpdir}/reqcount"
+mark="${tmpdir}/got304"
+RESUME304_COUNTER="$counter" RESUME304_MARK="$mark" python3 "$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 "$out" --quiet --disable-security-limits --robots=0 --timeout=30 --retries=1 -c1)
+refdir="${out}/hts-cache/ref"
+
+# --- pass 1: crawl, interrupt once the blob download is underway -------------
+printf '[pass 1: interrupt mid-download] ..\t'
+httrack "${common[@]}" "${base}/resume304/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
+wait "$crawlpid" 2>/dev/null
+crawlpid=
+test -n "$(find "$refdir" -name '*.ref' 2>/dev/null)" || {
+    echo "FAIL: no temp-ref survived pass 1; cannot drive C7"
+    exit 1
+}
+echo "OK (temp-ref present)"
+before=$(wc -c <"$counter" 2>/dev/null || echo 0)
+
+# --- pass 2: --continue -> resume Range -> bogus 304 -> drop + refetch --------
+printf '[pass 2: resume gets 304, must refetch] ..\t'
+httrack "${common[@]}" --continue "${base}/resume304/index.html" >"${tmpdir}/log2" 2>&1
+echo "OK (terminated)"
+
+blob=$(find "$out" -name blob.bin 2>/dev/null | head -1)
+full=8200 # len(RESUME304_BODY) = len("C7DATA--") + 8192
+
+printf '[file recovered whole] ..\t'
+test -s "$blob" || {
+    echo "FAIL: blob.bin missing after the 304 resume (partial dropped, not refetched)"
+    exit 1
+}
+got=$(wc -c <"$blob")
+test "$got" -eq "$full" || {
+    echo "FAIL: blob.bin is ${got} bytes, expected ${full} (partial finalized as complete)"
+    exit 1
+}
+echo "OK (${got} bytes)"
+
+# Pass 2 must issue at least two requests: the resume (Range -> 304) and the
+# range-less refetch (-> 200). Exactly one means the partial was trusted.
+after=$(wc -c <"$counter" 2>/dev/null || echo 0)
+hits=$((after - before))
+printf '[resume then refetch] ..\t'
+test "$hits" -ge 2 || {
+    echo "FAIL: only ${hits} pass-2 request(s); the 304 was trusted, no refetch"
+    exit 1
+}
+echo "OK (${hits} requests)"
+
+# The recovery must go through the resume path: a Range request that drew the
+# bogus 304 (a fresh re-crawl sends no Range, so this marker stays empty).
+printf '[resume Range drew a 304] ..\t'
+test -s "$mark" || {
+    echo "FAIL: no Range request got a 304; the resume path was not exercised"
+    exit 1
+}
+echo "OK"

tests/47_local-crange-overflow.test

@@ -0,0 +1,96 @@
+#!/bin/bash
+# C2: a resume whose 206 carries a Content-Range end of INT64_MAX must not
+# sign-overflow the crange+1 range check (UBSan aborts on the pre-fix binary).
+# Pass 1 leaves a partial + temp-ref; pass 2 resumes, gets the hostile 206, and
+# must reject the range and refetch the whole file rather than overflow. Teeth
+# are UBSan-only: a normal build wraps to the same reject+restart.
+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_crange.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
+
+serverlog="${tmpdir}/server.log"
+python3 "$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 "$out" --quiet --disable-security-limits --robots=0 --timeout=30 --retries=1 -c1)
+refdir="${out}/hts-cache/ref"
+
+# --- pass 1: crawl, interrupt once the blob download is underway -------------
+printf '[pass 1: interrupt mid-download] ..\t'
+httrack "${common[@]}" "${base}/crange206/index.html" >"${tmpdir}/log1" 2>&1 &
+crawlpid=$!
+for _ in $(seq 1 300); do
+    test -n "$(find "$refdir" -name '*.ref' 2>/dev/null)" && break
+    kill -0 "$crawlpid" 2>/dev/null || break
+    sleep 0.1
+done
+sleep 0.3
+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 the resume"
+    exit 1
+}
+echo "OK (temp-ref present)"
+
+# --- pass 2: --continue -> resume -> hostile INT64_MAX Content-Range ----------
+printf '[pass 2: hostile 206, no overflow, refetch] ..\t'
+httrack "${common[@]}" --continue "${base}/crange206/index.html" >"${tmpdir}/log2" 2>&1
+echo "OK (terminated)"
+
+blob=$(find "$out" -name blob.bin 2>/dev/null | head -1)
+full=6008 # len(CRANGE206_BODY) = len("CR206DAT") + 6000
+
+printf '[file recovered whole] ..\t'
+test -s "$blob" || {
+    echo "FAIL: blob.bin missing after the hostile 206"
+    exit 1
+}
+got=$(wc -c <"$blob")
+test "$got" -eq "$full" || {
+    echo "FAIL: blob.bin is ${got} bytes, expected ${full}"
+    exit 1
+}
+echo "OK (${got} bytes)"

tests/48_local-crange-memresume.test

@@ -0,0 +1,96 @@
+#!/bin/bash
+# C2 (memory branch): a resume whose 206 lies text/html with a matching
+# INT64_MAX Content-Length must not overflow the resume buffer-size add
+# (UBSan aborts on the pre-fix binary at alloc_mem += totalsize). Pass 1 leaves
+# a partial + temp-ref; pass 2 resumes and must reject and refetch the whole
+# file. Teeth are UBSan-only: a normal build wraps to the same reject+restart.
+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_crangemem.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
+
+serverlog="${tmpdir}/server.log"
+python3 "$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 "$out" --quiet --disable-security-limits --robots=0 --timeout=30 --retries=1 -c1)
+refdir="${out}/hts-cache/ref"
+
+# --- pass 1: crawl, interrupt once the blob download is underway -------------
+printf '[pass 1: interrupt mid-download] ..\t'
+httrack "${common[@]}" "${base}/crange206mem/index.html" >"${tmpdir}/log1" 2>&1 &
+crawlpid=$!
+for _ in $(seq 1 300); do
+    test -n "$(find "$refdir" -name '*.ref' 2>/dev/null)" && break
+    kill -0 "$crawlpid" 2>/dev/null || break
+    sleep 0.1
+done
+sleep 0.3
+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 the resume"
+    exit 1
+}
+echo "OK (temp-ref present)"
+
+# --- pass 2: --continue -> resume -> hostile INT64_MAX Content-Range ----------
+printf '[pass 2: hostile 206, no overflow, refetch] ..\t'
+httrack "${common[@]}" --continue "${base}/crange206mem/index.html" >"${tmpdir}/log2" 2>&1
+echo "OK (terminated)"
+
+blob=$(find "$out" -name blob.bin 2>/dev/null | head -1)
+full=6008 # len(CRANGE206_BODY) = len("CR206DAT") + 6000
+
+printf '[file recovered whole] ..\t'
+test -s "$blob" || {
+    echo "FAIL: blob.bin missing after the hostile 206"
+    exit 1
+}
+got=$(wc -c <"$blob")
+test "$got" -eq "$full" || {
+    echo "FAIL: blob.bin is ${got} bytes, expected ${full}"
+    exit 1
+}
+echo "OK (${got} bytes)"

tests/49_local-cookiewall.test

@@ -0,0 +1,34 @@
+#!/bin/bash
+#
+# Cookie-wall self-redirect (#15): httrack replays a Set-Cookie to mirror the
+# real page, gives up when nothing changes, and stays bounded when it never does.
+
+set -euo pipefail
+
+: "${top_srcdir:=..}"
+
+# Unknown-ext (wall.php) and known-ext (wall.html): the wall sets the cookie once,
+# then serves real content; httrack must replay it and mirror that content.
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
+    --found 'cookiewall/wall.html' \
+    --file-matches 'cookiewall/wall.html' 'REAL-CONTENT-BEHIND-COOKIE-WALL' \
+    httrack 'BASEURL/cookiewall/index.html'
+
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
+    --found 'cookiewall2/wall.html' \
+    --file-matches 'cookiewall2/wall.html' 'REAL-CONTENT-BEHIND-COOKIE-WALL' \
+    httrack 'BASEURL/cookiewall2/index.html'
+
+# No Set-Cookie: the jar never changes, so httrack must give up at once (retry
+# stays gated) and not mirror the wall. A dropped gate would skip this log line.
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
+    --not-found 'cookiewall3/wall.html' \
+    --log-found 'loop to same filename' \
+    httrack 'BASEURL/cookiewall3/index.html'
+
+# Ever-changing cookie never satisfies the wall: httrack must stop at the retry
+# cap (bounded, no early give-up) and not mirror it.
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
+    --not-found 'cookiewall4/wall.html' \
+    --log-not-found 'loop to same filename' \
+    httrack 'BASEURL/cookiewall4/index.html'

tests/Makefile.am

@@ -30,6 +30,7 @@ TESTS = \
 	01_engine-cmdline.test \
 	01_engine-cookies.test \
 	01_engine-copyopt.test \
+	01_engine-crange.test \
 	01_engine-dns.test \
 	01_engine-doitlog.test \
 	01_engine-entities.test \
@@ -65,6 +66,7 @@ TESTS = \
 	01_engine-urlhack.test \
 	01_engine-unescape-bounds.test \
 	01_engine-useragent.test \
+	01_engine-xfread.test \
 	01_zlib-acceptencoding.test \
 	01_zlib-cache.test \
 	01_zlib-cache-corrupt.test \
@@ -110,6 +112,14 @@ TESTS = \
 	38_local-update-304.test \
 	39_local-delayed-cancel.test \
 	40_local-why.test \
-	41_local-utf8-link.test
+	41_local-utf8-link.test \
+	42_local-maxsize-slow.test \
+	43_local-update-truncate.test \
+	44_local-update-errormask.test \
+	45_local-maxsize-recv.test \
+	46_local-update-304-resume.test \
+	47_local-crange-overflow.test \
+	48_local-crange-memresume.test \
+	49_local-cookiewall.test
 
 CLEANFILES = check-network_sh.cache

tests/crawl-test.sh

@@ -105,7 +105,7 @@ function start-crawl {
     log="${tmp}/log"
     debug starting httrack -O "${tmp}" "${moreargs[@]}" "${@:pos}"
     info "running httrack ${*:pos}"
-    httrack -O "${tmp}" --user-agent="httrack $ver ut ($(uname -omrs))" "${moreargs[@]}" "${@:pos}" >"${log}" 2>&1 &
+    httrack -O "${tmp}" --user-agent="httrack $ver ut ($(uname -mrs))" "${moreargs[@]}" "${@:pos}" >"${log}" 2>&1 &
     crawlpid="$!"
     debug "started cralwer on pid $crawlpid"
     wait "$crawlpid"

tests/local-crawl.sh

@@ -13,15 +13,21 @@
 #
 # Usage:
 #   bash local-crawl.sh [--tls] [--root DIR] [--cookie NAME=VALUE ...] \
-#       --errors N --files N --found PATH ... --directory PATH ... \
+#       [--rerun-args 'ARGS'] \
+#       --errors N --errors-content N --files N --found PATH ... --directory PATH ... \
 #       --log-found REGEX ... --log-not-found REGEX ... \
 #       --file-matches PATH REGEX ... --file-not-matches PATH REGEX ... \
-#       --max-mirror-bytes N \
+#       --file-min-bytes PATH N --max-mirror-bytes N \
 #       httrack BASEURL/some/path [httrack-args...]
+# --errors counts every "Error:" log line; --errors-content drops transient
+# network failures (codes -2..-6) that flake on busy loopback under -c8.
 # --log-found/--log-not-found grep (ERE) the crawl's hts-log.txt.
 # --max/--min-mirror-bytes bound the mirrored content bytes (host root).
 # --file-matches/--file-not-matches grep (ERE) a mirrored file (PATH under the
 # host root), to assert rewritten link/content survived the crawl.
+# --file-min-bytes asserts a mirrored file (PATH) is at least N bytes.
+# --rerun-args runs a second pass (same server and mirror dir) with the given
+# extra httrack args appended, e.g. an --update run under a cap.
 # --cookie writes a Netscape cookies.txt (scoped to the discovered host:port,
 # which the ephemeral port forces into the cookie domain) and passes it to
 # httrack via --cookies-file, to exercise preloaded cookies.
@@ -39,6 +45,7 @@ key="${testdir}/server.key"
 tls=
 verbose=
 rerun=
+rerun_args=
 rerun_dead=
 tmpdir=
 serverpid=
@@ -122,7 +129,11 @@ while test "$pos" -lt "$nargs"; do
         pos=$((pos + 1))
         cookies+=("${args[$pos]}")
         ;;
-    --errors | --files)
+    --rerun-args)
+        pos=$((pos + 1))
+        rerun_args="${args[$pos]}"
+        ;;
+    --errors | --errors-content | --files)
         audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
         pos=$((pos + 1))
         ;;
@@ -130,7 +141,7 @@ while test "$pos" -lt "$nargs"; do
         audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
         pos=$((pos + 1))
         ;;
-    --file-matches | --file-not-matches)
+    --file-matches | --file-not-matches | --file-min-bytes)
         audit+=("${args[$pos]}" "${args[$((pos + 1))]}" "${args[$((pos + 2))]}")
         pos=$((pos + 2))
         ;;
@@ -202,7 +213,7 @@ mkdir "$out" || die "could not create $out"
 declare -a moreargs=(--quiet --max-time=120 --timeout=30 --disable-security-limits --robots=0)
 log="${tmpdir}/log"
 info "running httrack ${hts[*]}"
-httrack -O "$out" --user-agent="httrack $ver local ($(uname -omrs))" "${moreargs[@]}" "${hts[@]}" >"$log" 2>&1 &
+httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" "${moreargs[@]}" "${hts[@]}" >"$log" 2>&1 &
 crawlpid=$!
 wait "$crawlpid"
 crawlres=$?
@@ -219,7 +230,7 @@ grep -iE "^[0-9:]*[[:space:]]Error:" "${out}/hts-log.txt" >&2
 # --- optional second pass: re-mirror into the same dir (cache/update path) ----
 if test -n "$rerun"; then
     info "re-running httrack (update pass)"
-    httrack -O "$out" --user-agent="httrack $ver local ($(uname -omrs))" \
+    httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" \
         "${moreargs[@]}" "${hts[@]}" >"${log}.2" 2>&1 &
     crawlpid=$!
     wait "$crawlpid"
@@ -241,6 +252,25 @@ if test -n "$rerun"; then
     fi
 fi
 
+# --- optional second pass with extra args (e.g. an --update run under a cap) ---
+# Same server and mirror dir as the first pass, so the second pass sees the
+# cache the first pass wrote. Used to exercise re-fetch/update behaviour.
+if test -n "$rerun_args"; then
+    read -ra extra <<<"$rerun_args"
+    info "re-running httrack with ${rerun_args}"
+    httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" \
+        "${moreargs[@]}" "${hts[@]}" "${extra[@]}" >"${log}.2" 2>&1 &
+    crawlpid=$!
+    wait "$crawlpid"
+    crawlres=$?
+    crawlpid=
+    test "$crawlres" -eq 0 || ! result "second pass exited $crawlres" || {
+        cat "${log}.2" >&2
+        exit 1
+    }
+    result "OK (second pass)"
+fi
+
 # --- optional dead pass: server stopped, the cache must survive the rollback --
 if test -n "$rerun_dead"; then
     zip="${out}/hts-cache/new.zip"
@@ -251,7 +281,7 @@ if test -n "$rerun_dead"; then
     wait "$serverpid" 2>/dev/null
     serverpid=
     info "re-running httrack against the stopped server"
-    httrack -O "$out" --user-agent="httrack $ver local ($(uname -omrs))" \
+    httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" \
         "${moreargs[@]}" "${hts[@]}" >"${log}.dead" 2>&1 &
     crawlpid=$!
     wait "$crawlpid" || true
@@ -306,6 +336,14 @@ while test "$i" -lt "${#audit[@]}"; do
         assert_equals "checking errors" "${audit[$i]}" \
             "$(grep -iEc "^[0-9:]*[[:space:]]Error:" "${out}/hts-log.txt")"
         ;;
+    --errors-content)
+        i=$((i + 1))
+        total=$(grep -icE "^[0-9:]*[[:space:]]Error:" "${out}/hts-log.txt")
+        # transient network failures (statuscode -2..-6) flake on busy loopback;
+        # the code parens are followed by " at link" or " after N retries at link"
+        transient=$(grep -cE '\(-[2-6]\) (at link|after )' "${out}/hts-log.txt" || true)
+        assert_equals "checking content errors" "${audit[$i]}" "$((total - transient))"
+        ;;
     --files)
         i=$((i + 1))
         nFiles=$(grep -E "^HTTrack Website Copier/[^ ]* mirror complete in " "${out}/hts-log.txt" |
@@ -388,6 +426,16 @@ while test "$i" -lt "${#audit[@]}"; do
             exit 1
         else result "OK"; fi
         ;;
+    --file-min-bytes)
+        path="${audit[$((i + 1))]}"
+        i=$((i + 2))
+        sz=$(wc -c <"${hostroot}/${path}" 2>/dev/null | tr -d '[:space:]')
+        info "checking ${path} size ${sz:-0} >= ${audit[$i]} bytes"
+        if test -n "$sz" && test "$sz" -ge "${audit[$i]}"; then result "OK"; else
+            result "file too small (or missing)"
+            exit 1
+        fi
+        ;;
     esac
     i=$((i + 1))
 done

tests/local-server.py

@@ -790,6 +790,56 @@ class Handler(SimpleHTTPRequestHandler):
         self.send_header("Content-Length", "0")
         self.end_headers()
 
+    # C7: stall the first GET (partial + temp-ref), then answer the resume's
+    # Range with a bogus 304; httrack must drop the partial and refetch.
+    RESUME304_BODY = b"C7DATA--" + bytes((i * 7 + 3) % 256 for i in range(8192))
+    _resume304_started = False
+
+    def route_resume304_index(self):
+        self.send_html('\t<a href="blob.bin">blob</a>')
+
+    def route_resume304(self):
+        counter = os.environ.get("RESUME304_COUNTER")
+        if counter:
+            with open(counter, "a") as fp:
+                fp.write("x")
+        rng = self.headers.get("Range")
+        if not Handler._resume304_started:
+            Handler._resume304_started = True
+            self.send_response(200)
+            self.send_header("Content-Type", "application/octet-stream")
+            self.send_header("Content-Length", str(len(self.RESUME304_BODY)))
+            self.send_header("Accept-Ranges", "bytes")
+            self.send_header("Last-Modified", BIG_LASTMOD)
+            self.send_header("ETag", '"c7"')
+            self.end_headers()
+            if self.command != "HEAD":
+                self.wfile.write(self.RESUME304_BODY[:4096])
+                self.wfile.flush()
+                try:
+                    while True:
+                        time.sleep(3600)
+                except OSError:
+                    pass
+            return
+        if rng is not None:  # resume request: bogus out-of-protocol 304
+            mark = os.environ.get("RESUME304_MARK")
+            if mark:
+                with open(mark, "a") as fp:
+                    fp.write("z")
+            self.send_response(304)
+            self.send_header("ETag", '"c7"')
+            self.send_header("Content-Length", "0")
+            self.end_headers()
+            return
+        # Range-less refetch after the partial is dropped: whole file.
+        self.send_response(200)
+        self.send_header("Content-Type", "application/octet-stream")
+        self.send_header("Content-Length", str(len(self.RESUME304_BODY)))
+        self.end_headers()
+        if self.command != "HEAD":
+            self.wfile.write(self.RESUME304_BODY)
+
     # 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
@@ -855,6 +905,94 @@ class Handler(SimpleHTTPRequestHandler):
         if self.command != "HEAD":
             self.wfile.write(part)
 
+    # C2: a resume answered with a 206 whose Content-Range end is INT64_MAX would
+    # sign-overflow the crange+1 range check (UBSan abort). Stall first (partial +
+    # ref), then answer the resume Range with that hostile 206; httrack must reject
+    # the range and refetch, never overflow.
+    CRANGE206_BODY = b"CR206DAT" + bytes((i * 5 + 1) % 256 for i in range(6000))
+    _crange206_started = False
+
+    def route_crange206_index(self):
+        self.send_html('\t<a href="blob.bin">blob</a>')
+
+    def route_crange206(self):
+        rng = self.headers.get("Range")
+        if not Handler._crange206_started:
+            Handler._crange206_started = True
+            self.send_response(200)
+            self.send_header("Content-Type", "application/octet-stream")
+            self.send_header("Content-Length", str(len(self.CRANGE206_BODY)))
+            self.send_header("Accept-Ranges", "bytes")
+            self.end_headers()
+            if self.command != "HEAD":
+                self.wfile.write(self.CRANGE206_BODY[:3000])
+                self.wfile.flush()
+                try:
+                    while True:
+                        time.sleep(3600)
+                except OSError:
+                    pass
+            return
+        if rng is not None:  # resume: hostile 206, Content-Range end = INT64_MAX
+            self.send_response(206, "Partial Content")
+            self.send_header("Content-Type", "application/octet-stream")
+            self.send_header("Content-Length", str(len(self.CRANGE206_BODY)))
+            self.send_header("Content-Range", "bytes 0-9223372036854775807/1")
+            self.end_headers()
+            if self.command != "HEAD":
+                self.wfile.write(self.CRANGE206_BODY)
+            return
+        # range-less refetch after the bad range is rejected: whole file.
+        self.send_response(200)
+        self.send_header("Content-Type", "application/octet-stream")
+        self.send_header("Content-Length", str(len(self.CRANGE206_BODY)))
+        self.end_headers()
+        if self.command != "HEAD":
+            self.wfile.write(self.CRANGE206_BODY)
+
+    # C2 memory branch: a resume answered with a 206 that lies text/html (so the
+    # resume buffers in memory) plus a matching INT64_MAX Content-Length would
+    # overflow the buffer-size add. Stall first, then send that hostile 206.
+    _crange206mem_started = False
+
+    def route_crange206mem_index(self):
+        self.send_html('\t<a href="blob.bin">blob</a>')
+
+    def route_crange206mem(self):
+        rng = self.headers.get("Range")
+        if not Handler._crange206mem_started:
+            Handler._crange206mem_started = True
+            self.send_response(200)
+            self.send_header("Content-Type", "application/octet-stream")
+            self.send_header("Content-Length", str(len(self.CRANGE206_BODY)))
+            self.send_header("Accept-Ranges", "bytes")
+            self.end_headers()
+            if self.command != "HEAD":
+                self.wfile.write(self.CRANGE206_BODY[:3000])
+                self.wfile.flush()
+                try:
+                    while True:
+                        time.sleep(3600)
+                except OSError:
+                    pass
+            return
+        if rng is not None:  # resume: text/html + matching INT64_MAX Content-Length
+            self.send_response(206, "Partial Content")
+            self.send_header("Content-Type", "text/html")
+            self.send_header("Content-Length", "9223372036854775807")
+            self.send_header(
+                "Content-Range", "bytes 0-9223372036854775806/9223372036854775807"
+            )
+            self.end_headers()
+            return  # the overflow is computed before any body read
+        # range-less refetch after the resume is rejected: whole file.
+        self.send_response(200)
+        self.send_header("Content-Type", "application/octet-stream")
+        self.send_header("Content-Length", str(len(self.CRANGE206_BODY)))
+        self.end_headers()
+        if self.command != "HEAD":
+            self.wfile.write(self.CRANGE206_BODY)
+
     # 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):
@@ -934,6 +1072,33 @@ class Handler(SimpleHTTPRequestHandler):
     def route_mini304_page(self):
         self.big_send(b"<html><body>tiny cacheable page</body></html>\n", "text/html")
 
+    # --- /errmask/: issue #176 — a page that 200'd on the first crawl but 403s
+    # on the update fetch must keep its good copy, not be overwritten nor purged.
+    ERRMASK_GOOD = b"KEEP" + b"." * 1020  # 1024 B distinctive non-HTML body
+    ERRMASK_ERR = b"<html><body>error 403</body></html>\n"
+
+    def route_errmask_index(self):
+        self.send_html('\t<a href="keep.dat">keep</a>\n')
+
+    def route_errmask_keep(self):
+        # First crawl (no validator) gets the 1024 B body + Last-Modified; the
+        # update sends a conditional and gets a 403 error page.
+        if self.headers.get("If-Modified-Since") or self.headers.get("If-None-Match"):
+            self.send_response(403, "Forbidden")
+            self.send_header("Content-Type", "text/html")
+            self.send_header("Content-Length", str(len(self.ERRMASK_ERR)))
+            self.end_headers()
+            if self.command != "HEAD":
+                self.wfile.write(self.ERRMASK_ERR)
+            return
+        self.send_response(200)
+        self.send_header("Content-Type", "application/octet-stream")
+        self.send_header("Last-Modified", BIG_LASTMOD)
+        self.send_header("Content-Length", str(len(self.ERRMASK_GOOD)))
+        self.end_headers()
+        if self.command != "HEAD":
+            self.wfile.write(self.ERRMASK_GOOD)
+
     # --- delayed-type degenerate paths (issues #5/#107) --------------------
     def route_delayed_index(self):
         self.send_html(
@@ -978,6 +1143,56 @@ class Handler(SimpleHTTPRequestHandler):
     def route_delayed_empty(self):
         self.send_raw(b"", "text/html")  # 200 + Content-Length: 0
 
+    # --- /cookiewall/ (#15): a self-redirect that only sets a cookie is a
+    # consent wall; httrack must replay the cookie and fetch the real page.
+    WALL_MARK = b"REAL-CONTENT-BEHIND-COOKIE-WALL"
+
+    def route_cookiewall_index(self):
+        self.send_html('\t<a href="wall.php">wall</a>')
+
+    def route_cookiewall_wall(self):
+        self._cookiewall_reply("wall.php")
+
+    # Known-extension twin: .html so the type is not delayed-resolved.
+    def route_cookiewall2_index(self):
+        self.send_html('\t<a href="wall.html">wall</a>')
+
+    def route_cookiewall2_wall(self):
+        self._cookiewall_reply("wall.html")
+
+    def _cookiewall_reply(self, location):
+        if self.request_cookies().get("gate") == "1":
+            self.send_raw(
+                b"<html><body>" + self.WALL_MARK + b"</body></html>\n", "text/html"
+            )
+        else:
+            self._wall_redirect(location, "gate=1; Path=/")
+
+    # No-cookie self-redirect: the jar never changes, so httrack must give up at
+    # once rather than re-fetch (proves the cookie-wall retry stays gated on #15).
+    def route_cookiewall3_index(self):
+        self.send_html('\t<a href="wall.php">wall</a>')
+
+    def route_cookiewall3_wall(self):
+        self._wall_redirect("wall.php", None)
+
+    # Ever-changing cookie: every hit sets a fresh value, so the jar keeps
+    # changing; httrack must stop at the loops<7 cap, not spin forever.
+    def route_cookiewall4_index(self):
+        self.send_html('\t<a href="wall.php">wall</a>')
+
+    def route_cookiewall4_wall(self):
+        nonce = int(self.request_cookies().get("gate", "0")) + 1
+        self._wall_redirect("wall.php", f"gate={nonce}; Path=/")
+
+    def _wall_redirect(self, location, set_cookie):
+        self.send_response(302, "Found")
+        self.send_header("Location", location)
+        if set_cookie is not None:
+            self.send_header("Set-Cookie", set_cookie)
+        self.send_header("Content-Length", "0")
+        self.end_headers()
+
     # -E time-limit (#481): pages that trickle far longer than any -E budget,
     # so only an engine-side abort can end the crawl.
     TRICKLE_SECONDS = 60
@@ -1035,6 +1250,64 @@ class Handler(SimpleHTTPRequestHandler):
     def route_bigfile(self):
         self.send_raw(b"x" * self.BIGFILE_BYTES, "application/octet-stream")
 
+    # -M under a slow server (#77): p0 is a fast 640KB file that alone overruns
+    # -M; p1..p3 trickle for a minute. The cap must abort those in-flight
+    # transfers, not wait them out.
+    def route_bigtrickle_index(self):
+        self.send_html(
+            "".join('\t<a href="p%d.bin">p%d</a>\n' % (i, i) for i in range(4))
+        )
+
+    # -M hard-abort must not destroy an already-complete file (#77 follow-up).
+    # "fast.bin" alone overruns -M and completes; "slow.bin" transfers fully on
+    # its first fetch (initial mirror) but stalls on every later fetch (the
+    # --update re-fetch), so the -M abort tears it down mid-body. An engine that
+    # truncates the good local copy on the aborted re-fetch loses data.
+    slow_seen = 0
+
+    def route_bigtrunc_index(self):
+        self.send_html('\t<a href="fast.bin">fast</a>\n\t<a href="slow.bin">slow</a>\n')
+
+    def route_bigtrunc_slow(self):
+        self.send_response(200)
+        self.send_header("Content-Type", "application/octet-stream")
+        self.send_header("Content-Length", str(self.BIGFILE_BYTES))
+        self.end_headers()
+        if self.command == "HEAD":
+            return
+        # Count body fetches only, so a stray HEAD can't shift which pass stalls.
+        Handler.slow_seen += 1
+        first = Handler.slow_seen == 1
+        try:
+            if first:
+                self.wfile.write(b"x" * self.BIGFILE_BYTES)
+                self.wfile.flush()
+            else:
+                self.wfile.write(b"x" * 4096)
+                self.wfile.flush()
+                for _ in range(120):
+                    self.wfile.write(b"x")
+                    self.wfile.flush()
+                    time.sleep(1.0)
+        except OSError:
+            pass
+
+    # -M received-volume cap (#520): links to large 404 bodies. httrack receives
+    # each (HTS_TOTAL_RECV climbs) but saves none, so saved stays far below -M.
+    def route_maxrecv_index(self):
+        self.send_html(
+            "".join('\t<a href="r%d.bin">r%d</a>\n' % (i, i) for i in range(16))
+        )
+
+    def route_maxrecv_404(self):
+        body = b"x" * self.BIGFILE_BYTES
+        self.send_response(404, "Not Found")
+        self.send_header("Content-Type", "application/octet-stream")
+        self.send_header("Content-Length", str(len(body)))
+        self.end_headers()
+        if self.command != "HEAD":
+            self.wfile.write(body)
+
     ROUTES = {
         "/cookies/entrance.php": route_entrance,
         "/cookies/second.php": route_second,
@@ -1064,9 +1337,15 @@ class Handler(SimpleHTTPRequestHandler):
         "/intl/" + INTL_NAME: route_intl_page,
         "/resume/index.html": route_resume_index,
         "/resume/blob.txt": route_resume,
+        "/resume304/index.html": route_resume304_index,
+        "/resume304/blob.bin": route_resume304,
         "/overlap/index.html": route_overlap_index,
         "/overlap/flaky.bin": route_overlap,
         "/overlap/full.bin": route_overlap_full,
+        "/crange206/index.html": route_crange206_index,
+        "/crange206/blob.bin": route_crange206,
+        "/crange206mem/index.html": route_crange206mem_index,
+        "/crange206mem/blob.bin": route_crange206mem,
         "/size/index.html": route_size_index,
         "/size/oversize.bin": route_size_oversize,
         "/errpage/index.html": route_errpage_index,
@@ -1107,6 +1386,14 @@ class Handler(SimpleHTTPRequestHandler):
         "/bigfiles/p5.bin": route_bigfile,
         "/bigfiles/p6.bin": route_bigfile,
         "/bigfiles/p7.bin": route_bigfile,
+        "/bigtrickle/index.html": route_bigtrickle_index,
+        "/bigtrickle/p0.bin": route_bigfile,
+        "/bigtrickle/p1.bin": route_trickle_page,
+        "/bigtrickle/p2.bin": route_trickle_page,
+        "/bigtrickle/p3.bin": route_trickle_page,
+        "/bigtrunc/index.html": route_bigtrunc_index,
+        "/bigtrunc/fast.bin": route_bigfile,
+        "/bigtrunc/slow.bin": route_bigtrunc_slow,
         "/delayed/noloc.php": route_delayed_noloc,
         "/delayed/selfloop.php": route_delayed_selfloop,
         "/delayed/redir.php": route_delayed_redir,
@@ -1122,11 +1409,38 @@ class Handler(SimpleHTTPRequestHandler):
         "/delayed/chain7.php": route_delayed_chain,
         "/delayed/chain8.php": route_delayed_chain,
         "/delayed/chain9.php": route_delayed_chain,
+        "/cookiewall/index.html": route_cookiewall_index,
+        "/cookiewall/wall.php": route_cookiewall_wall,
+        "/cookiewall2/index.html": route_cookiewall2_index,
+        "/cookiewall2/wall.html": route_cookiewall2_wall,
+        "/cookiewall3/index.html": route_cookiewall3_index,
+        "/cookiewall3/wall.php": route_cookiewall3_wall,
+        "/cookiewall4/index.html": route_cookiewall4_index,
+        "/cookiewall4/wall.php": route_cookiewall4_wall,
         "/redir/index.html": route_redir_index,
         "/redir/go.php": route_redir_go,
         "/redir/target.html": route_redir_target,
         "/mini304/index.html": route_mini304_index,
         "/mini304/page.html": route_mini304_page,
+        "/errmask/index.html": route_errmask_index,
+        "/errmask/keep.dat": route_errmask_keep,
+        "/maxrecv/index.html": route_maxrecv_index,
+        "/maxrecv/r0.bin": route_maxrecv_404,
+        "/maxrecv/r1.bin": route_maxrecv_404,
+        "/maxrecv/r2.bin": route_maxrecv_404,
+        "/maxrecv/r3.bin": route_maxrecv_404,
+        "/maxrecv/r4.bin": route_maxrecv_404,
+        "/maxrecv/r5.bin": route_maxrecv_404,
+        "/maxrecv/r6.bin": route_maxrecv_404,
+        "/maxrecv/r7.bin": route_maxrecv_404,
+        "/maxrecv/r8.bin": route_maxrecv_404,
+        "/maxrecv/r9.bin": route_maxrecv_404,
+        "/maxrecv/r10.bin": route_maxrecv_404,
+        "/maxrecv/r11.bin": route_maxrecv_404,
+        "/maxrecv/r12.bin": route_maxrecv_404,
+        "/maxrecv/r13.bin": route_maxrecv_404,
+        "/maxrecv/r14.bin": route_maxrecv_404,
+        "/maxrecv/r15.bin": route_maxrecv_404,
     }
 
     # --- /big/ seeded pseudo-site ------------------------------------------
@@ -1331,7 +1645,12 @@ def main():
     def factory(*a, **kw):
         return Handler(*a, directory=root, **kw)
 
-    httpd = ThreadingHTTPServer((args.bind, 0), factory)
+    # macOS/BSD drop SYNs when the listen backlog overflows (Linux is lenient);
+    # raise it from Python's default 5 so a busy -c8 crawl can't lose fetches.
+    class BacklogHTTPServer(ThreadingHTTPServer):
+        request_queue_size = 128
+
+    httpd = BacklogHTTPServer((args.bind, 0), factory)
 
     if args.tls:
         import ssl