Remove the pre-3.31 (.dat/.ndx) cache import

The zip cache replaced this format in 3.31 (2003); what remained was an
import-only parser for hostile input, compiled unconditionally, plus a
tail of dead code keyed to it: the CACHE-1.5 writer behind if(1), the
cross-session HTML-MD5 dedup (its store was never written in the zip
era), the legacy legs of the startup rotation (which silently renamed
or deleted a user's .dat/.ndx pair) and of hts_cache_reconcile.

cache_init now detects a legacy pair, logs a clear refusal, leaves the
files untouched, and re-crawls. The cache-legacy self-test pins refusal
for both layouts (--update old.* and ro new.*), no is_update flag, and
untouched files; proven end-to-end against the local server. The
cacheindex self-test and fuzz-cachendx stay: cache_brstr/cache_binput
still back the -#C cache listing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

.github/workflows/codeql.yml

@@ -43,12 +43,6 @@ jobs:
           languages: c-cpp
           build-mode: manual
           queries: security-extended
-          # fopen's umask-controlled 0666 is intended for mirror/cache/log
-          # output; the one credential file (cookies.txt) is kept 0600 on Unix.
-          config: |
-            query-filters:
-              - exclude:
-                  id: cpp/world-writable-file-creation
 
       # Manual build: CodeQL traces the compiler, so build exactly what ships.
       - name: Build

configure.ac

@@ -1,6 +1,6 @@
 AC_PREREQ([2.71])
 
-AC_INIT([httrack], [3.49.12], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
+AC_INIT([httrack], [3.49.11], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
 AC_COPYRIGHT([
 HTTrack Website Copier, Offline Browser for Windows and Unix
 Copyright (C) 1998-2015 Xavier Roche and other contributors
@@ -29,11 +29,11 @@ AC_CONFIG_SRCDIR(src/httrack.c)
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_HEADERS(config.h)
 AM_INIT_AUTOMAKE([subdir-objects])
-# 3:4:0: 3.49.12 tail-appends one field (why_url) to httrackp and otherwise only
-# deletes dead comments; no struct layout or exported signature broke vs 3.49.11,
-# so it stays soname .so.3; bump revision.
+# 3:3:0: 3.49.11 only adds enum values, macros and inline helpers to the
+# installed headers (no struct layout or exported signature changed vs
+# 3.49.10), so it stays soname .so.3; bump revision.
 # (3:0:0 was the htsblk mime-buffer widening, the ABI break that moved .so.2 -> .so.3.)
-VERSION_INFO="3:4:0"
+VERSION_INFO="3:3:0"
 AM_MAINTAINER_MODE
 AC_USE_SYSTEM_EXTENSIONS
 

debian/changelog

@@ -1,13 +1,3 @@
-httrack (3.49.12-1) unstable; urgency=medium
-
-  * New upstream release: security and crawl-correctness fixes (remote stack
-    overflow in Content-Type/-Encoding parsing, fuzzer-found parser over-reads,
-    world-readable cookies.txt, filter-pattern denial of service) plus a new
-    --why filter diagnostic; full list in history.txt.
-  * Build with _FORTIFY_SOURCE and -fstack-protector-strong.
-
- -- Xavier Roche <xavier@debian.org>  Fri, 10 Jul 2026 21:11:09 +0200
-
 httrack (3.49.11-1) unstable; urgency=medium
 
   * New upstream release: crawl correctness and security fixes (network-facing

fuzz/Makefile.am

@@ -36,7 +36,6 @@ EXTRA_DIST = README.md run-fuzzers.sh \
 	corpus/unescape/percent.txt \
 	corpus/filters/filter.bin corpus/filters/filter-size.bin \
 	corpus/filters/regress-empty-subject-unique.bin \
-	corpus/filters/redos-star-classes.bin \
 	corpus/url/http-url.txt corpus/url/relative-path.txt \
 	corpus/url/regress-file-empty-path.txt corpus/url/regress-long-path-abort.txt \
 	corpus/header/full-response.txt corpus/header/redirect.txt \

fuzz/corpus/meta/meta-content-first.html

@@ -1 +0,0 @@
-<meta content="text/html; charset=gb2312" http-equiv="content-type">

fuzz/corpus/meta/meta-truncated.html

@@ -1 +0,0 @@
-<meta charset='utf-8

fuzz/corpus/meta/meta-unquoted.html

@@ -1 +0,0 @@
-<meta   charset = utf-8 />

fuzz/fuzz-header.c

@@ -50,13 +50,9 @@ int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
   while (p != NULL && *p != '\0') {
     char *nl = strchr(p, '\n');
     size_t n = (nl != NULL) ? (size_t) (nl - p) : strlen(p);
-    size_t i, len = 0;
 
-    /* binput drops every '\r' on the wire; mirror it */
-    for (i = 0; i < n; i++)
-      if (p[i] != '\r')
-        line[len++] = p[i];
-    line[len] = '\0';
+    memcpy(line, p, n);
+    line[n] = '\0';
     if (first) {
       treatfirstline(&r, line);
       first = 0;

fuzz/run-fuzzers.sh

@@ -2,8 +2,8 @@
 # Drive every built harness against its seed corpus.
 #   run-fuzzers.sh <build-fuzz-dir> check       deterministic replay (CI smoke)
 #   run-fuzzers.sh <build-fuzz-dir> [seconds]   timed mutation run (discovery)
-# Replay is crash/leak-only and never mutates; the per-unit -timeout guards
-# both modes against pathological slowdowns (e.g. pre-#501 strjoker).
+# Replay is crash/leak-only and never mutates, so it can't hit strjoker's
+# catastrophic backtracking; the timed mode can, hence the per-unit -timeout.
 set -euo pipefail
 
 srcdir=$(cd "$(dirname "$0")" && pwd)

history.txt

@@ -4,23 +4,6 @@ HTTrack Website Copier release history:
 
 This file lists all changes and fixes that have been made for HTTrack
 
-3.49-12
-+ New: --why explains which filter rule accepts or rejects a given URL, then exits (#505)
-+ Fixed: links carrying raw UTF-8 bytes were fetched double-encoded and 404'd (#516)
-+ Fixed: an uncompressed body mislabeled as gzip no longer loses the page (#515)
-+ Fixed: remote stack overflow and uninitialized read in Content-Type/-Encoding parsing (#506)
-+ Fixed: several over-reads and a leak in the filter, URL and IDNA parsers (#499)
-+ Fixed: bound the cache-index (.ndx) parser to its buffer (#507)
-+ Fixed: catastrophic backtracking on '*'-heavy filter patterns (#513)
-+ Fixed: cookies.txt was created world-readable (#511)
-+ Fixed: a single corrupt cache entry no longer aborts the whole mirror (#494)
-+ Fixed: cache-reconcile policy was broken for zip caches (#491, #493, #495)
-+ Fixed: cancelling a crawl mid type-check no longer orphans .delayed placeholders (#496)
-+ Fixed: detect URLs after the first inline script and in mid-tag attributes (#497)
-+ Changed: build with _FORTIFY_SOURCE and -fstack-protector-strong (#504)
-+ Changed: removed the pre-3.31 (.dat/.ndx) cache import (#512)
-+ Changed: multiple internal hardening and build improvements (libFuzzer harnesses, CodeQL, dead-code removal)
-
 3.49-11
 + New: parse robots.txt Allow rules and path wildcards per RFC 9309 (#452)
 + New: advertise deflate in Accept-Encoding and decode deflate responses (#450)

src/htsback.c

@@ -1646,104 +1646,138 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
       }
     }
     // tester cache
-    if ((strcmp(adr, "file://")) /* pas fichier */
-        && ((!test) ||
-            (cache->type == 1)) /* cache prioritaire, laisser passer en test! */
-        &&
-        ((strnotempty(save)) || (strcmp(fil, "/robots.txt") ==
-                                 0))) { // si en test on ne doit pas utiliser le
-                                        // cache sinon telescopage avec le 302..
+    if ((strcmp(adr, "file://"))        /* pas fichier */
+        &&((!test) || (cache->type == 1))       /* cache prioritaire, laisser passer en test! */
+        &&((strnotempty(save)) || (strcmp(fil, "/robots.txt") == 0))) { // si en test on ne doit pas utiliser le cache sinon telescopage avec le 302..
+#if HTS_FAST_CACHE
       intptr_t hash_pos;
       int hash_pos_return = 0;
-
+#else
+      char *a = NULL;
+#endif
+#if HTS_FAST_CACHE
       if (cache->hashtable) {
+#else
+      if (cache->use) {
+#endif
         char BIGSTK buff[HTS_URLMAXSIZE * 4];
 
+#if HTS_FAST_CACHE
         strcpybuff(buff, adr);
         strcatbuff(buff, fil);
         hash_pos_return = coucal_read(cache->hashtable, buff, &hash_pos);
+#else
+        buff[0] = '\0';
+        strcatbuff(buff, "\n");
+        strcatbuff(buff, adr);
+        strcatbuff(buff, "\n");
+        strcatbuff(buff, fil);
+        strcatbuff(buff, "\n");
+        a = strstr(cache->use, buff);
+#endif
 
+        // Ok, noté en cache->. mais bien présent dans le cache ou sur disque?
+#if HTS_FAST_CACHE
         // negative values when data is not in cache
         if (hash_pos_return < 0) {
-          if (!test) { // not test mode
-            /* note: no check with IS_DELAYED_EXT() enabled - postcheck by
-             * client please! */
-            if (save[0] != '\0' && !IS_DELAYED_EXT(save) &&
-                fsize_utf8(fconv(catbuff, sizeof(catbuff), save)) <=
-                    0) { // final file missing or empty
-              int found = 0;
+#else
+        if (a) {
+#endif
+          if (!test) {          // non mode test
+#if HTS_FAST_CACHE==0
+            int pos = -1;
 
-              /* It is possible that the file has been moved due to changes in
-               * build structure */
-              {
-                char BIGSTK previous_save[HTS_URLMAXSIZE * 2];
-                htsblk r;
+            a += strlen(buff);
+            sscanf(a, "%d", &pos);      // lire position
+#endif
 
-                previous_save[0] = '\0';
-                r = cache_readex(opt, cache, adr, fil, /*head */ NULL,
+#if HTS_FAST_CACHE==0
+            if (pos < 0) {      // pas de mise en cache data, vérifier existence
+#endif
+              /* note: no check with IS_DELAYED_EXT() enabled - postcheck by client please! */
+              if (save[0] != '\0' && !IS_DELAYED_EXT(save) && fsize_utf8(fconv(catbuff, sizeof(catbuff), save)) <= 0) {  // fichier final n'existe pas ou est vide!
+                int found = 0;
+
+                /* It is possible that the file has been moved due to changes in build structure */
+                {
+                  char BIGSTK previous_save[HTS_URLMAXSIZE * 2];
+                  htsblk r;
+
+                  previous_save[0] = '\0';
+                  r =
+                    cache_readex(opt, cache, adr, fil, /*head */ NULL,
                                  /*bound to back[p] (temporary) */
                                  back[p].location_buffer, previous_save, /*ro */
                                  1);
-                /* Is supposed to be on disk only */
-                if (r.is_write && previous_save[0] != '\0') {
-                  /* Exists, but with another (old) filename: rename (almost)
-                   * silently */
-                  if (strcmp(previous_save, save) != 0 &&
-                      fexist_utf8(
-                          fconv(catbuff, sizeof(catbuff), previous_save))) {
-                    rename(fconv(catbuff, sizeof(catbuff), previous_save),
-                           fconv(catbuff2, sizeof(catbuff2), save));
-                    if (fexist_utf8(fconv(catbuff, sizeof(catbuff), save))) {
-                      found = 1;
-                      hts_log_print(opt, LOG_DEBUG,
-                                    "File '%s' has been renamed since last "
-                                    "mirror to '%s' ; applying changes",
-                                    previous_save, save);
-                    } else {
-                      hts_log_print(opt, LOG_ERROR,
-                                    "Could not rename '%s' to '%s' ; will have "
-                                    "to retransfer it",
-                                    previous_save, save);
+                  /* Is supposed to be on disk only */
+                  if (r.is_write && previous_save[0] != '\0') {
+                    /* Exists, but with another (old) filename: rename (almost) silently */
+                    if (strcmp(previous_save, save) != 0
+                        && fexist_utf8(fconv(catbuff, sizeof(catbuff), previous_save))) {
+                      rename(fconv(catbuff, sizeof(catbuff), previous_save),
+                             fconv(catbuff2, sizeof(catbuff2), save));
+                      if (fexist_utf8(fconv(catbuff, sizeof(catbuff), save))) {
+                        found = 1;
+                        hts_log_print(opt, LOG_DEBUG,
+                                      "File '%s' has been renamed since last mirror to '%s' ; applying changes",
+                                      previous_save, save);
+                      } else {
+                        hts_log_print(opt, LOG_ERROR,
+                                      "Could not rename '%s' to '%s' ; will have to retransfer it",
+                                      previous_save, save);
+                      }
                     }
                   }
+                  back[p].location_buffer[0] = '\0';
                 }
-                back[p].location_buffer[0] = '\0';
-              }
 
-              /* Not found ? */
-              if (!found) {
-                // invalidate: gone from disk, force a refetch
-                hash_pos_return = 0;
-                if (opt->norecatch) {
-                  if (!fexist_utf8(fconv(
-                          catbuff, sizeof(catbuff),
-                          save))) { // declared but missing: user erased it
-                    FILE *fp =
-                        FOPEN(fconv(catbuff, sizeof(catbuff), save), "wb");
+                /* Not found ? */
+                if (!found) {
+#if HTS_FAST_CACHE
+                  hash_pos_return = 0;
+#else
+                  a = NULL;
+#endif
+                  // dévalider car non présent sur disque dans structure originale!!!
+                  // sinon, le fichier est ok à priori, mais on renverra un if-modified-since pour
+                  // en être sûr
+                  if (opt->norecatch) { // tester norecatch
+                    if (!fexist_utf8(fconv(catbuff, sizeof(catbuff), save))) {   // fichier existe pas mais déclaré: on l'a effacé
+                      FILE *fp = FOPEN(fconv(catbuff, sizeof(catbuff), save), "wb");
 
-                    if (fp)
-                      fclose(fp);
+                      if (fp)
+                        fclose(fp);
+                      hts_log_print(opt, LOG_WARNING,
+                                    "Previous file '%s' not found (erased by user ?), ignoring: %s%s",
+                                    save, back[p].url_adr, back[p].url_fil);
+                    }
+                  } else {
                     hts_log_print(opt, LOG_WARNING,
-                                  "Previous file '%s' not found (erased by "
-                                  "user ?), ignoring: %s%s",
+                                  "Previous file '%s' not found (erased by user ?), recatching: %s%s",
                                   save, back[p].url_adr, back[p].url_fil);
                   }
-                } else {
-                  hts_log_print(opt, LOG_WARNING,
-                                "Previous file '%s' not found (erased by user "
-                                "?), recatching: %s%s",
-                                save, back[p].url_adr, back[p].url_fil);
                 }
-              }
-            } // fsize() <= 0
+              }                 // fsize() <= 0
+#if HTS_FAST_CACHE==0
+            }
+#endif
           }
         }
         //
       } else {
+#if HTS_FAST_CACHE
         hash_pos_return = 0;
+#else
+        a = NULL;
+#endif
       }
 
-      if (hash_pos_return) { // in cache, with data
+      // Existe pas en cache, ou bien pas de cache présent
+#if HTS_FAST_CACHE
+      if (hash_pos_return) {    // OK existe en cache (et données aussi)!
+#else
+      if (a != NULL) {          // OK existe en cache (et données aussi)!
+#endif
         const int cache_is_prioritary = cache->type == 1
           || opt->state.stop != 0;
         if (cache_is_prioritary) {      // cache prioritaire (pas de test if-modified..)
@@ -1864,8 +1898,7 @@ int back_add(struct_back * sback, httrackp * opt, cache_back * cache, const char
 #endif
         }
       }
-      /* Not in cache ; maybe in temporary cache ? Warning: non-movable
-         "url_sav" */
+      /* Not in cache ; maybe in temporary cache ? Warning: non-movable "url_sav" */
       else if (back_unserialize_ref(opt, adr, fil, &itemback) == 0) {
         const off_t file_size = fsize_utf8(itemback->url_sav);
 

src/htsbauth.c

@@ -307,25 +307,14 @@ int cookie_load(t_cookie * cookie, const char *fpath, const char *name) {
   return -1;
 }
 
-/* Write cookies.txt; returns 0 on success. The jar holds live session
-   cookies, so keep it owner-only on Unix (Windows inherits folder ACLs). */
+// écrire cookies.txt
+// !=0 : erreur
 int cookie_save(t_cookie * cookie, const char *name) {
   char catbuff[CATBUFF_SIZE];
 
   if (strnotempty(cookie->data)) {
     char BIGSTK line[8192];
-#ifdef _WIN32
     FILE *fp = fopen(fconv(catbuff, sizeof(catbuff), name), "wb");
-#else
-    const int fd = open(fconv(catbuff, sizeof(catbuff), name),
-                        O_WRONLY | O_CREAT | O_TRUNC, HTS_PROTECT_FILE);
-    FILE *fp = fd != -1 ? fdopen(fd, "wb") : NULL;
-
-    if (fd != -1 && fp == NULL)
-      close(fd);    /* fdopen failed: don't leak the descriptor */
-    if (fp != NULL) /* O_CREAT's mode skips pre-existing jars: tighten those */
-      (void) fchmod(fd, HTS_PROTECT_FILE);
-#endif
 
     if (fp) {
       char *a = cookie->data;

src/htscache.c

@@ -491,7 +491,11 @@ static htsblk cache_readex_new(httrackp * opt, cache_back * cache,
   hash_pos_return = coucal_read(cache->hashtable, buff, &hash_pos);
   /* avoid errors on data entries */
   if (adr[0] == '/' && adr[1] == '/' && adr[2] == '[') {
+#if HTS_FAST_CACHE
     hash_pos_return = 0;
+#else
+    a = NULL;
+#endif
   }
 
   if (hash_pos_return != 0) {

src/htscharset.c

@@ -84,7 +84,7 @@ static int hts_equalsAlphanum(const char *a, const char *b) {
 
 /* Copy the memory region [s .. s + size - 1 ] as a \0-terminated string. */
 static char *hts_stringMemCopy(const char *s, size_t size) {
-  char *dest = malloct(size + 1);
+  char *dest = malloc(size + 1);
 
   if (dest != NULL) {
     memcpy(dest, s, size);
@@ -549,6 +549,42 @@ char *hts_convertStringFromUTF8(const char *s, size_t size, const char *charset)
 
 #endif
 
+HTS_STATIC char *hts_getCharsetFromContentType(const char *mime) {
+  /* text/html; charset=utf-8 */
+  const char *const charset = "charset";
+  char *pos = strstr(mime, charset);
+
+  if (pos != NULL) {
+    /* Skip spaces */
+    int eq = 0;
+
+    for(pos += strlen(charset);
+        *pos == ' ' || *pos == '=' || *pos == '"' || *pos == '\''; pos++) {
+      if (*pos == '=') {
+        eq = 1;
+      }
+    }
+    if (eq == 1) {
+      int len;
+
+      for(len = 0;
+          pos[len] == ' ' || pos[len] == ';' || pos[len] == '"' || *pos == '\'';
+          pos++) ;
+      if (len != 0) {
+        char *const s = malloc(len + 1);
+        int i;
+
+        for(i = 0; i < len; i++) {
+          s[i] = pos[i];
+        }
+        s[len] = '\0';
+        return s;
+      }
+    }
+  }
+  return NULL;
+}
+
 #ifdef _WIN32
 #define strcasecmp(a,b) stricmp(a,b)
 #define strncasecmp(a,b,n) strnicmp(a,b,n)
@@ -608,106 +644,58 @@ int hts_isCharsetUTF8(const char *charset) {
          || strcasecmp(charset, "utf8") == 0 );
 }
 
-/* Extract X from a "text/html; charset=X" content= attribute value. */
-static char *charset_from_content(const char *s, size_t len) {
-  size_t i;
-
-  for (i = 0; i + 7 < len; i++) {
-    if ((i == 0 || is_space(s[i - 1]) || s[i - 1] == ';') &&
-        strncasecmp(&s[i], "charset", 7) == 0 && is_space_or_equal(s[i + 7])) {
-      size_t j, val;
-
-      for (j = i + 7; j < len && is_space_or_equal_or_quote(s[j]); j++)
-        ;
-      for (val = j; j < len && s[j] != '"' && s[j] != '\'' && s[j] != ';' &&
-                    !is_space(s[j]);
-           j++)
-        ;
-      if (j != val) {
-        return hts_stringMemCopy(&s[val], j - val);
-      }
-    }
-  }
-  return NULL;
-}
-
 char *hts_getCharsetFromMeta(const char *html, size_t size) {
-  size_t i;
+  int i;
 
-  /* HTML5 <meta charset=X> or legacy
-     <meta http-equiv="Content-Type" content="text/html; charset=X">,
-     attributes in any order; first resolvable tag wins. */
-  for (i = 0; i + 6 < size; i++) {
-    size_t j;
-    const char *equiv = NULL, *content = NULL;
-    size_t equiv_len = 0, content_len = 0;
+  /* <META HTTP-EQUIV="CONTENT-TYPE" CONTENT="text/html; charset=utf-8" > */
+  for(i = 0; i < size; i++) {
+    if (html[i] == '<' && strncasecmp(&html[i + 1], "meta", 4) == 0
+        && is_space(html[i + 5])) {
+      /* Skip spaces */
+      for(i += 5; is_space(html[i]); i++) ;
+      if (strncasecmp(&html[i], "HTTP-EQUIV", 10) == 0
+          && is_space_or_equal(html[i + 10])) {
+        for(i += 10; is_space_or_equal_or_quote(html[i]); i++) ;
+        if (strncasecmp(&html[i], "CONTENT-TYPE", 12) == 0) {
+          for(i += 12; is_space_or_equal_or_quote(html[i]); i++) ;
+          if (strncasecmp(&html[i], "CONTENT", 7) == 0
+              && is_space_or_equal(html[i + 7])) {
+            for(i += 7; is_space_or_equal_or_quote(html[i]); i++) ;
+            /* Skip content-type */
+            for(;
+                i < size && html[i] != ';' && html[i] != '"' && html[i] != '\'';
+                i++) ;
+            /* Expect charset attribute here */
+            if (html[i] == ';') {
+              for(i++; is_space(html[i]); i++) ;
+              /* Look for charset */
+              if (strncasecmp(&html[i], "charset", 7) == 0
+                  && is_space_or_equal(html[i + 7])) {
+                int len;
 
-    if (html[i] != '<' || strncasecmp(&html[i + 1], "meta", 4) != 0 ||
-        !is_space(html[i + 5])) {
-      continue;
-    }
-    /* Attribute scan, strictly bounded by size. */
-    for (j = i + 6; j < size && html[j] != '>';) {
-      size_t name, name_len, val = 0, val_len = 0;
+                for(i += 7; is_space_or_equal(html[i]) || html[i] == '\'';
+                    i++) ;
+                /* Charset */
+                for(len = 0;
+                    i + len < size && html[i + len] != '"'
+                    && html[i + len] != '\'' && html[i + len] != ' '; len++) ;
+                /* No error ? */
+                if (len != 0 && i < size) {
+                  char *const s = malloc(len + 1);
+                  int j;
 
-      if (is_space(html[j]) || html[j] == '/') {
-        j++;
-        continue;
-      }
-      for (name = j; j < size && html[j] != '=' && html[j] != '>' &&
-                     html[j] != '/' && !is_space(html[j]);
-           j++)
-        ;
-      name_len = j - name;
-      for (; j < size && is_space(html[j]); j++)
-        ;
-      if (j < size && html[j] == '=') {
-        for (j++; j < size && is_space(html[j]); j++)
-          ;
-        if (j < size && (html[j] == '"' || html[j] == '\'')) {
-          const char quote = html[j++];
-
-          for (val = j; j < size && html[j] != quote; j++)
-            ;
-          if (j >= size) /* unterminated quote: drop the tag */
-            break;
-          val_len = j++ - val;
-        } else {
-          /* unquoted: ends at whitespace or '>' only (HTML5 prescan); '/'
-             belongs to the value except as the tail of a self-close */
-          for (val = j; j < size && !is_space(html[j]) && html[j] != '>'; j++)
-            ;
-          val_len = j - val;
-          if (val_len != 0 && j < size && html[j] == '>' &&
-              html[val + val_len - 1] == '/') {
-            val_len--;
+                  for(j = 0; j < len; j++) {
+                    s[j] = html[i + j];
+                  }
+                  s[len] = '\0';
+                  return s;
+                }
+              }
+            }
           }
         }
       }
-      /* first occurrence of each attribute wins, as in browsers */
-      if (val_len != 0) {
-        if (name_len == 7 && strncasecmp(&html[name], "charset", 7) == 0) {
-          return hts_stringMemCopy(&html[val], val_len);
-        } else if (equiv == NULL && name_len == 10 &&
-                   strncasecmp(&html[name], "http-equiv", 10) == 0) {
-          equiv = &html[val];
-          equiv_len = val_len;
-        } else if (content == NULL && name_len == 7 &&
-                   strncasecmp(&html[name], "content", 7) == 0) {
-          content = &html[val];
-          content_len = val_len;
-        }
-      }
     }
-    if (equiv_len == 12 && strncasecmp(equiv, "content-type", 12) == 0 &&
-        content != NULL) {
-      char *const s = charset_from_content(content, content_len);
-
-      if (s != NULL) {
-        return s;
-      }
-    }
-    i = j;
   }
   return NULL;
 }
@@ -1152,45 +1140,17 @@ int hts_isStringUTF8(const char *s, size_t size) {
   const unsigned char *const data = (const unsigned char*) s;
   size_t i;
 
-  /* Strict RFC 3629: reject overlongs, surrogates, > U+10FFFF, 5/6-byte. */
   for(i = 0 ; i < size ; ) {
-    const unsigned char c = data[i];
-    size_t len, k;
-    hts_UCS4 uc, min;
+    /* Reader: can read bytes up to j */
+#define RD ( i < size ? data[i++] : -1 )
 
-    if (c < 0x80) {
-      i++;
-      continue;
-    } else if (c >= 0xc2 && c <= 0xdf) {
-      len = 2;
-      min = 0x80;
-      uc = c & 0x1f;
-    } else if (c >= 0xe0 && c <= 0xef) {
-      len = 3;
-      min = 0x800;
-      uc = c & 0x0f;
-    } else if (c >= 0xf0 && c <= 0xf4) {
-      len = 4;
-      min = 0x10000;
-      uc = c & 0x07;
-    } else { /* continuation byte, overlong C0/C1, or F5..FF lead */
-      return 0;
-    }
-    if (size - i < len) {
-      return 0;
-    }
-    for (k = 1; k < len; k++) {
-      const unsigned char cc = data[i + k];
+    /* Writer: a malformed sequence means the string is not UTF-8 (return 0) */
+#define WR(C) if ((C) == -1) { return 0; }
 
-      if ((cc & 0xc0) != 0x80) {
-        return 0;
-      }
-      uc = (uc << 6) | (cc & 0x3f);
-    }
-    if (uc < min || uc > 0x10FFFF || (uc >= 0xD800 && uc <= 0xDFFF)) {
-      return 0;
-    }
-    i += len;
+    /* Read Unicode character. */
+    READ_UNICODE(RD, WR);
+#undef RD
+#undef WR
   }
 
   return 1;

src/htscharset.h

@@ -76,8 +76,7 @@ extern char *hts_convertStringIDNAToUTF8(const char *s, size_t size);
 extern int hts_isStringIDNA(const char *s, size_t size);
 
 /**
- * Extract the <meta> charset from the HTML buffer "html" (HTML5 charset= or
- * legacy http-equiv form). Returns a malloc'ed string, or NULL if none.
+ * Extract the charset from the HTML buffer "html"
  **/
 extern char *hts_getCharsetFromMeta(const char *html, size_t size);
 
@@ -87,8 +86,7 @@ extern char *hts_getCharsetFromMeta(const char *html, size_t size);
 extern int hts_isStringAscii(const char *s, size_t size);
 
 /**
- * Is the given string valid UTF-8 ? Strict RFC 3629: overlong forms,
- * surrogates, codepoints above U+10FFFF and 5/6-byte sequences are rejected.
+ * Is the given string an UTF-8 string ?
  **/
 extern int hts_isStringUTF8(const char *s, size_t size);
 

src/htsconfig.h

@@ -76,6 +76,9 @@ Please visit our Website: http://www.httrack.com
 // always direct-to-disk (0/1)
 #define HTS_DIRECTDISK_ALWAYS 1
 
+// fast cache (build hash table)
+#define HTS_FAST_CACHE 1
+
 // le > peut être considéré comme un tag de fermeture de commentaire (<!-- > est
 // valide)
 #define GT_ENDS_COMMENT 1

src/htscore.c

@@ -134,6 +134,10 @@ RUN_CALLBACK0(opt, end); \
     back_delete_all(opt, &cache, sback);                                       \
     back_free(&sback);                                                         \
     checkrobots_free(&robots);                                                 \
+    if (cache.use) {                                                           \
+      freet(cache.use);                                                        \
+      cache.use = NULL;                                                        \
+    }                                                                          \
     if (cache.zipOutput) {                                                     \
       zipClose(cache.zipOutput,                                                \
                "Created by HTTrack Website Copier/" HTTRACK_VERSION);          \

src/htscore.h

@@ -194,6 +194,7 @@ struct cache_back {
   int type;
   int ro;                   /**< read-only: no new cache is written */
 
+  char *use;                /**< in-memory list of cached adr+fil keys */
   FILE *lst;                /**< file list, used for purge */
   FILE *txt;                /**< human-readable file list (info) */
   char lastmodified[256];

src/htsfilters.c

@@ -48,7 +48,6 @@ Please visit our Website: http://www.httrack.com
 #include "htsbase.h"
 #include "htslib.h"
 #include <ctype.h>
-#include <stdint.h>
 /* END specific definitions */
 
 // à partir d'un tableau de {"+*.toto","-*.zip","+*.tata"} définit si nom est autorisé
@@ -121,81 +120,16 @@ int fa_strjoker_dual(int type, char **filters, int nfil, const char *nom1,
   return use1 ? jok1 : jok2;
 }
 
-/* Failure memo for the recursive matcher: one bit per (chaine, joker) offset
-   pair keeps star-heavy patterns polynomial instead of exponential (#501). */
-typedef struct strjoker_memo {
-  const char *chaine0, *joker0; /* offsets are relative to these bases */
-  size_t stride;                /* strlen(joker0) + 1 */
-  unsigned char *failed;        /* failed-pair bitmap; NULL: no memo */
-} strjoker_memo;
-
-static const char *strjoker_impl(const strjoker_memo *memo, const char *chaine,
-                                 const char *joker, LLint *size,
-                                 int *size_flag);
-
-/* A pair that failed once fails forever (*size is only written on the success
-   path), so record NULL results and cut the re-exploration. */
-static const char *strjoker_rec(const strjoker_memo *memo, const char *chaine,
-                                const char *joker, LLint *size,
-                                int *size_flag) {
-  size_t bit = 0;
-  const char *adr;
-
-  if (memo->failed) {
-    bit = (size_t) (chaine - memo->chaine0) * memo->stride +
-          (size_t) (joker - memo->joker0);
-    if (memo->failed[bit >> 3] & (unsigned char) (1u << (bit & 7)))
-      return NULL;
-  }
-  adr = strjoker_impl(memo, chaine, joker, size, size_flag);
-  if (adr == NULL && memo->failed)
-    memo->failed[bit >> 3] |= (unsigned char) (1u << (bit & 7));
-  return adr;
-}
-
-// wildcard comparator: match chaine against joker (pattern), case-insensitive
-// returns the address of the first matched letter past any leading joker
-// (ie. *[..]toto.. returns the address of toto within chaine), NULL on mismatch
+// supercomparateur joker (tm)
+// compare a et b (b=avec joker dedans), case insensitive [voir CI]
+// renvoi l'adresse de la première lettre de la chaine
+// (càd *[..]toto.. renvoi adresse de toto dans la chaine)
+// accepte les délires du genre www.*.*/ * / * truc*.*
+// cet algo est 'un peu' récursif mais ne consomme pas trop de tm
+// * = toute lettre
+// --?-- : spécifique à HTTrack et aux ?
 HTS_INLINE const char *strjoker(const char *chaine, const char *joker,
                                 LLint *size, int *size_flag) {
-  strjoker_memo memo = {chaine, joker, 0, NULL};
-  unsigned char stackbits[2048];
-  hts_boolean onheap = HTS_FALSE;
-  const char *adr;
-
-  if (chaine != NULL && joker != NULL) {
-    const size_t n1 = strlen(chaine) + 1;
-
-    memo.stride = strlen(joker) + 1;
-    if (n1 <= (SIZE_MAX - 7) / memo.stride) { // overflow-safe bitmap size
-      const size_t bytes = (n1 * memo.stride + 7) / 8;
-
-      if (bytes <= sizeof(stackbits)) {
-        memset(stackbits, 0, bytes);
-        memo.failed = stackbits;
-      } else {
-        memo.failed = (unsigned char *) calloct(bytes, 1);
-        onheap = memo.failed != NULL ? HTS_TRUE : HTS_FALSE;
-      }
-    }
-  }
-  adr = strjoker_rec(&memo, chaine, joker, size, size_flag);
-  if (onheap)
-    freet(memo.failed);
-  return adr;
-}
-
-/* Test-only oracle: the same matcher without the failure memo. */
-const char *strjoker_nomemo(const char *chaine, const char *joker, LLint *size,
-                            int *size_flag) {
-  const strjoker_memo memo = {chaine, joker, 0, NULL};
-
-  return strjoker_rec(&memo, chaine, joker, size, size_flag);
-}
-
-static const char *strjoker_impl(const strjoker_memo *memo, const char *chaine,
-                                 const char *joker, LLint *size,
-                                 int *size_flag) {
   if (strnotempty(joker) == 0) {        // fin de chaine joker
     if (strnotempty(chaine) == 0)       // fin aussi pour la chaine: ok
       return chaine;
@@ -369,7 +303,7 @@ static const char *strjoker_impl(const strjoker_memo *memo, const char *chaine,
 
       // tester sans le joker (pas ()+ mais ()*)
       if (!unique) {
-        if ((adr = strjoker_rec(memo, chaine, joker + jmp, size, size_flag))) {
+        if ((adr = strjoker(chaine, joker + jmp, size, size_flag))) {
           return adr;
         }
       }
@@ -381,8 +315,7 @@ static const char *strjoker_impl(const strjoker_memo *memo, const char *chaine,
         max = strnotempty(chaine) ? 1 : 0; /* empty chaine: no char to eat */
       while(i < (int) max) {
         if (pass[(int) (unsigned char) chaine[i]]) {    // caractère autorisé
-          if ((adr = strjoker_rec(memo, chaine + i + 1, joker + jmp, size,
-                                  size_flag))) {
+          if ((adr = strjoker(chaine + i + 1, joker + jmp, size, size_flag))) {
             return adr;
           }
           i++;
@@ -392,8 +325,7 @@ static const char *strjoker_impl(const strjoker_memo *memo, const char *chaine,
 
       // tester chaîne vide
       if (i != max + 2)         // avant c'est ok
-        if ((adr = strjoker_rec(memo, chaine + max, joker + jmp, size,
-                                size_flag)))
+        if ((adr = strjoker(chaine + max, joker + jmp, size, size_flag)))
           return adr;
 
       return NULL;              // perdu
@@ -415,7 +347,7 @@ static const char *strjoker_impl(const strjoker_memo *memo, const char *chaine,
       // comparaison ok?
       if (ok) {
         // continuer la comparaison.
-        if (strjoker_rec(memo, chaine + jmp, joker + jmp, size, size_flag))
+        if (strjoker(chaine + jmp, joker + jmp, size, size_flag))
           return chaine;        // retourner 1e lettre
       }
 

src/htsfilters.h

@@ -48,10 +48,6 @@ int fa_strjoker_dual(int type, char **filters, int nfil, const char *nom1,
                      const char *nom2, LLint *size, int *size_flag, int *depth);
 HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * size,
                           int *size_flag);
-/* strjoker() without the failure memo (exponential worst case); test-only
-   oracle for the memoized matcher. */
-const char *strjoker_nomemo(const char *chaine, const char *joker, LLint *size,
-                            int *size_flag);
 const char *strjokerfind(const char *chaine, const char *joker);
 #endif
 

src/htsglobal.h

@@ -43,8 +43,8 @@ Please visit our Website: http://www.httrack.com
    configure.ac, decoupled from these). VERSION is the display form, VERSIONID
    the dotted numeric form, AFF_VERSION the short form shown in footers,
    LIB_VERSION the data/cache format generation. */
-#define HTTRACK_VERSION "3.49-12"
-#define HTTRACK_VERSIONID "3.49.12"
+#define HTTRACK_VERSION "3.49-11"
+#define HTTRACK_VERSIONID "3.49.11"
 #define HTTRACK_AFF_VERSION "3.x"
 #define HTTRACK_LIB_VERSION "2.0"
 
@@ -422,10 +422,9 @@ typedef int T_SOC;
 #endif
 
 /* Permission bits for created folders and files (mkdir and chmod).
-   PROTECT_FOLDER/FILE are owner-only. With HTS_ACCESS set (the default) the
-   ACCESS_ modes also grant group/other read; otherwise they stay owner-only. */
+   PROTECT_FOLDER is owner-only. With HTS_ACCESS set (the default) the ACCESS_
+   modes also grant group/other read; otherwise they stay owner-only. */
 #define HTS_PROTECT_FOLDER (S_IRUSR | S_IWUSR | S_IXUSR)
-#define HTS_PROTECT_FILE (S_IRUSR | S_IWUSR)
 
 #if HTS_ACCESS
 #define HTS_ACCESS_FILE (S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH)

src/htsparse.c

@@ -2007,7 +2007,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
 
                 /* Unescape/escape %20 and other   */
                 {
-                  // NULL when UTF-8 conversion is off (-%T0)
+                  // Note: always true (iso-8859-1 as default)
                   const char *const charset = str->page_charset_;
                   const int hasCharset = charset != NULL 
                     && *charset != '\0';
@@ -2030,12 +2030,11 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
 
                   // Force to encode non-printable chars (should never happend)
                   escape_remove_control(lien);
-
-                  // charset conversion for the URI filename (not the query
-                  // string), unless the bytes already are valid UTF-8:
-                  // converting those would double-encode them (#180)
-                  if (hasCharset && !hts_isCharsetUTF8(charset) &&
-                      !hts_isStringUTF8(lien, strlen(lien))) {
+                  
+                  // charset conversion for the URI filename, 
+                  // and not already UTF-8
+                  // (note: not for the query string!)
+                  if (hasCharset && !hts_isCharsetUTF8(charset)) {
                     char *const s = hts_convertStringToUTF8(lien, strlen(lien), charset);
                     if (s != NULL) {
                       hts_log_print(opt, LOG_DEBUG,

src/htsselftest.c

@@ -621,105 +621,6 @@ static int st_filtersize(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-/* Mime-type filter verdict via fa_strjoker(type=1): only mime: rules apply. */
-static int st_filtermime(httrackp *opt, int argc, char **argv) {
-  int verdict;
-
-  (void) opt;
-  if (argc < 2) {
-    fprintf(stderr, "filtermime: needs <mime> <filter> [filter...]\n");
-    return 1;
-  }
-  verdict = fa_strjoker(1, &argv[1], argc - 1, argv[0], NULL, NULL, NULL);
-  printf("verdict=%s\n", verdict > 0   ? "allowed"
-                         : verdict < 0 ? "forbidden"
-                                       : "unknown");
-  return 0;
-}
-
-/* SplitMix64: deterministic, platform-independent case generator. */
-static uint64_t st_mix64(uint64_t *state) {
-  uint64_t z = (*state += UINT64_C(0x9E3779B97F4A7C15));
-
-  z = (z ^ (z >> 30)) * UINT64_C(0xBF58476D1CE4B5B9);
-  z = (z ^ (z >> 27)) * UINT64_C(0x94D049BB133111EB);
-  return z ^ (z >> 31);
-}
-
-/* Differential test: memoized strjoker vs the no-memo oracle on seeded random
-   pattern/subject/size cases must agree on result, *size and *size_flag. */
-static int st_filtermemo(httrackp *opt, int argc, char **argv) {
-  static const char *const pieces[] = {
-      "a",       "b",        "A",    "c",      ".",       "/",
-      "?",       "*",        "*[a]", "*[ab]",  "*[a-c]",  "*[A-Z]",
-      "*[<5]",   "*[>5]",    "*(a)", "*(a,b)", "*[file]", "*[path]",
-      "*[name]", "*[param]", "*[]",  "*[\\a]", "*[a-"};
-  static const char subject_chars[] = "abAc./?";
-  uint64_t rng = UINT64_C(0x501);
-  int iters = 20000, matched = 0, unmatched = 0;
-  int it;
-
-  (void) opt;
-  if (argc >= 1)
-    sscanf(argv[0], "%d", &iters);
-  for (it = 0; it < iters; it++) {
-    char pat[64], str[16];
-    size_t pl = 0;
-    const int npieces = (int) (st_mix64(&rng) % 5);
-    const int slen = (int) (st_mix64(&rng) % 13);
-    const int szsel = (int) (st_mix64(&rng) % 4); /* none/unknown/3/20 */
-    LLint sz1, sz2, off1, off2;
-    int i, flag1 = 0, flag2 = 0;
-    char *hpat, *hstr;
-    const char *adr;
-
-    for (i = 0; i < npieces; i++) {
-      const char *p =
-          pieces[st_mix64(&rng) % (sizeof(pieces) / sizeof(pieces[0]))];
-      const size_t len = strlen(p);
-
-      if (len >= sizeof(pat) - pl)
-        break;
-      memcpy(pat + pl, p, len);
-      pl += len;
-    }
-    pat[pl] = '\0';
-    for (i = 0; i < slen; i++)
-      str[i] = subject_chars[st_mix64(&rng) % (sizeof(subject_chars) - 1)];
-    str[slen] = '\0';
-    sz1 = sz2 = (szsel <= 1) ? -1 : (szsel == 2) ? 3 : 20;
-    /* exact-size heap copies per run so a sanitizer traps any over-read */
-    hpat = strdupt(pat);
-    hstr = strdupt(str);
-    adr = strjoker(hstr, hpat, szsel ? &sz1 : NULL, szsel ? &flag1 : NULL);
-    off1 = adr != NULL ? (LLint) (adr - hstr) : -1;
-    freet(hpat);
-    freet(hstr);
-    hpat = strdupt(pat);
-    hstr = strdupt(str);
-    adr =
-        strjoker_nomemo(hstr, hpat, szsel ? &sz2 : NULL, szsel ? &flag2 : NULL);
-    off2 = adr != NULL ? (LLint) (adr - hstr) : -1;
-    freet(hpat);
-    freet(hstr);
-    if (off1 != off2 || sz1 != sz2 || flag1 != flag2) {
-      printf("filtermemo MISMATCH pat=[%s] str=[%s] szsel=%d: "
-             "off %d/%d size %d/%d flag %d/%d\n",
-             pat, str, szsel, (int) off1, (int) off2, (int) sz1, (int) sz2,
-             flag1, flag2);
-      return 1;
-    }
-    if (off1 >= 0)
-      matched++;
-    else
-      unmatched++;
-  }
-  /* both polarities must actually occur or the test proves nothing */
-  assertf(matched > 0 && unmatched > 0);
-  printf("filtermemo: %d cases OK\n", iters);
-  return 0;
-}
-
 /* Merged two-form filter verdict via fa_strjoker_dual (see htsfilters.h). */
 static int st_filterdual(httrackp *opt, int argc, char **argv) {
   int depth = -1, verdict;
@@ -788,30 +689,6 @@ static int st_charset(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-static int st_metacharset(httrackp *opt, int argc, char **argv) {
-  char *s;
-
-  (void) opt;
-  if (argc < 1) {
-    fprintf(stderr, "metacharset: needs an html string\n");
-    return 1;
-  }
-  s = hts_getCharsetFromMeta(argv[0], strlen(argv[0]));
-  printf("%s\n", s != NULL ? s : "(none)");
-  freet(s);
-  return 0;
-}
-
-static int st_isutf8(httrackp *opt, int argc, char **argv) {
-  (void) opt;
-  if (argc < 1) {
-    fprintf(stderr, "isutf8: needs a string\n");
-    return 1;
-  }
-  printf("%d\n", hts_isStringUTF8(argv[0], strlen(argv[0])) ? 1 : 0);
-  return 0;
-}
-
 static int st_idna_encode(httrackp *opt, int argc, char **argv) {
   char *s;
 
@@ -1686,26 +1563,6 @@ static int st_cookies(httrackp *opt, int argc, char **argv) {
     err = 1;
   if (strstr(hdr, "junk") != NULL) // wrong-domain cookie leaked
     err = 1;
-#ifndef _WIN32
-  /* the jar holds live session cookies: cookie_save must keep it 0600 */
-  {
-    const char *jar = "st-cookies-jar.txt";
-    struct stat st;
-
-    (void) UNLINK(jar);
-    assertf(cookie_save(&cookie, jar) == 0);
-    assertf(stat(jar, &st) == 0);
-    assertf((st.st_mode & 07777) == HTS_PROTECT_FILE);
-    assertf(st.st_size > 0); /* mode-only checks would pass an empty jar */
-    /* a pre-existing world-readable jar must be tightened, not kept */
-    assertf(chmod(jar, 0644) == 0);
-    assertf(cookie_save(&cookie, jar) == 0);
-    assertf(stat(jar, &st) == 0);
-    assertf((st.st_mode & 07777) == HTS_PROTECT_FILE);
-    assertf(st.st_size > 0);
-    (void) UNLINK(jar);
-  }
-#endif
   printf("cookie-header: %s\n", err ? "FAIL" : "OK");
   if (err)
     printf("  got: %s\n", hdr);
@@ -2147,19 +2004,6 @@ static int ae_write_collision(const char *path, const unsigned char *src,
   return ok ? 0 : 1;
 }
 
-/* Write src[0..len) to path as-is; 0 on success. */
-static int ae_write_raw(const char *path, const unsigned char *src,
-                        size_t len) {
-  FILE *const f = FOPEN(path, "wb");
-  int ok;
-
-  if (f == NULL)
-    return 1;
-  ok = fwrite(src, 1, len, f) == len;
-  fclose(f);
-  return ok ? 0 : 1;
-}
-
 /* Compare path's bytes to expect[0..len); 0 if equal. Streams (large files). */
 static int ae_check_decoded(const char *path, const unsigned char *expect,
                             size_t len) {
@@ -2227,46 +2071,6 @@ static int st_acceptencoding(httrackp *opt, int argc, char **argv) {
     assertf(ae_write_collision(inpath, body, 64) == 0);
     assertf(hts_zunpack(inpath, outpath) == 64);
     assertf(ae_check_decoded(outpath, body, 64) == 0);
-    /* Identity fallback (#47): a plain body mislabeled as compressed is kept
-       verbatim, small and multi-chunk (> one 8 KiB fread). */
-    assertf(ae_write_raw(inpath, small, slen) == 0);
-    assertf(hts_zunpack(inpath, outpath) == (int) slen);
-    assertf(ae_check_decoded(outpath, small, slen) == 0);
-    {
-      const size_t ilen = 16 * 1024;
-      unsigned char *idbody = malloct(ilen);
-
-      assertf(idbody != NULL);
-      for (i = 0; i < ilen; i++)
-        idbody[i] = small[i % slen];
-      assertf(ae_write_raw(inpath, idbody, ilen) == 0);
-      assertf(hts_zunpack(inpath, outpath) == (int) ilen);
-      assertf(ae_check_decoded(outpath, idbody, ilen) == 0);
-      freet(idbody);
-    }
-    /* Truncated gzip (CRC+ISIZE cut), zlib (ADLER32 cut) and raw deflate
-       must all still fail, not fall back to a verbatim copy. */
-    {
-      static const struct {
-        int wb;
-        size_t cut;
-      } tr[] = {{16 + MAX_WBITS, 8}, {MAX_WBITS, 4}, {-MAX_WBITS, 5}};
-
-      for (i = 0; i < sizeof(tr) / sizeof(tr[0]); i++) {
-        unsigned char z[512];
-        size_t zlen;
-        FILE *f;
-
-        assertf(ae_write_packed(inpath, tr[i].wb, small, slen) == 0);
-        f = FOPEN(inpath, "rb");
-        assertf(f != NULL);
-        zlen = fread(z, 1, sizeof(z), f);
-        fclose(f);
-        assertf(zlen > tr[i].cut && zlen < sizeof(z));
-        assertf(ae_write_raw(inpath, z, zlen - tr[i].cut) == 0);
-        assertf(hts_zunpack(inpath, outpath) < 0);
-      }
-    }
     freet(body);
   }
 #else
@@ -2455,10 +2259,6 @@ static const struct selftest_entry {
     {"filtersize", "<size> <string> <filter>...",
      "size-aware filter verdict (negative size = unknown/scan time)",
      st_filtersize},
-    {"filtermime", "<mime> <filter>...",
-     "mime-type filter verdict (fa_strjoker type=1)", st_filtermime},
-    {"filtermemo", "[iterations]",
-     "memoized vs unmemoized matcher differential", st_filtermemo},
     {"filterdual", "<string1> <string2> <filter>...",
      "merged two-form filter verdict (fa_strjoker_dual)", st_filterdual},
     {"simplify", "<path>", "collapse ./ and ../ in a path", st_simplify},
@@ -2471,9 +2271,6 @@ static const struct selftest_entry {
     {"mime", "<filename>", "MIME type for a filename", st_mime},
     {"charset", "<charset> <string>",
      "convert a string to UTF-8 from a charset", st_charset},
-    {"metacharset", "<html>", "extract the <meta> charset from an HTML page",
-     st_metacharset},
-    {"isutf8", "<string>", "is the string valid UTF-8 (1/0)", st_isutf8},
     {"idna-encode", "<host>", "encode a hostname to IDNA/punycode",
      st_idna_encode},
     {"idna-decode", "<host>", "decode an IDNA/punycode hostname",

src/htszlib.c

@@ -48,7 +48,6 @@ Please visit our Website: http://www.httrack.com
 
 /*
   Unpack file into a new file (gzip, zlib RFC1950 or raw deflate RFC1951).
-  A body provably in no deflate framing is copied verbatim (identity).
   Return value: size of the new file, or -1 if an error occurred
 */
 /* Note: utf-8 */
@@ -69,10 +68,6 @@ int hts_zunpack(char *filename, char *newfile) {
             ((inbuf[0] & 0x0f) == Z_DEFLATED &&
              (((unsigned) inbuf[0] << 8 | inbuf[1]) % 31) == 0)));
       int attempt;
-      /* not_deflate: the raw attempt hit a data error, so the body is in no
-         deflate framing at all. env_error: local I/O or memory failure. */
-      hts_boolean not_deflate = HTS_FALSE;
-      hts_boolean env_error = HTS_FALSE;
 
       /* deflate is ambiguous; on failure retry with the other windowBits */
       for (attempt = 0; attempt < 2 && ret < 0; attempt++) {
@@ -83,20 +78,15 @@ int hts_zunpack(char *filename, char *newfile) {
 
         if (attempt > 0) {
           /* rewind input; reopening fpout "wb" discards the partial output */
-          if (fseek(in, 0, SEEK_SET) != 0) {
-            env_error = HTS_TRUE;
+          if (fseek(in, 0, SEEK_SET) != 0)
             break;
-          }
           navail = fread(inbuf, 1, sizeof(inbuf), in);
         }
         fpout = FOPEN(fconv(catbuff, sizeof(catbuff), newfile), "wb");
-        if (fpout == NULL) {
-          env_error = HTS_TRUE;
+        if (fpout == NULL)
           break;
-        }
         memset(&strm, 0, sizeof(strm));
         if (inflateInit2(&strm, windowBits) != Z_OK) {
-          env_error = HTS_TRUE;
           fclose(fpout);
           break;
         }
@@ -118,17 +108,12 @@ int hts_zunpack(char *filename, char *newfile) {
               zerr = inflate(&strm, Z_NO_FLUSH);
               if (zerr == Z_NEED_DICT || zerr == Z_DATA_ERROR ||
                   zerr == Z_MEM_ERROR || zerr == Z_STREAM_ERROR) {
-                if (zerr == Z_MEM_ERROR || zerr == Z_STREAM_ERROR)
-                  env_error = HTS_TRUE;
-                else if (windowBits < 0)
-                  not_deflate = HTS_TRUE;
                 ok = HTS_FALSE;
                 break;
               }
               produced = sizeof(outbuf) - strm.avail_out;
               if (produced > 0 &&
                   fwrite(outbuf, 1, produced, fpout) != produced) {
-                env_error = HTS_TRUE;
                 ok = HTS_FALSE;
                 break;
               }
@@ -144,28 +129,6 @@ int hts_zunpack(char *filename, char *newfile) {
         inflateEnd(&strm);
         fclose(fpout);
       }
-      /* keep a mislabeled identity body verbatim only when provably not
-         deflate; truncation or a local failure must keep failing (#47) */
-      if (ret < 0 && !wrapped && not_deflate && !env_error && !ferror(in)) {
-        FILE *const fpout =
-            FOPEN(fconv(catbuff, sizeof(catbuff), newfile), "wb");
-
-        if (fpout != NULL && fseek(in, 0, SEEK_SET) == 0) {
-          int size = 0;
-
-          while ((navail = fread(inbuf, 1, sizeof(inbuf), in)) > 0) {
-            if (fwrite(inbuf, 1, navail, fpout) != navail) {
-              size = -1;
-              break;
-            }
-            size += (int) navail;
-          }
-          if (size >= 0 && !ferror(in))
-            ret = size;
-        }
-        if (fpout != NULL)
-          fclose(fpout);
-      }
       fclose(in);
     }
   }

tests/01_engine-charset.test

@@ -36,64 +36,3 @@ test "$(httrack -O /dev/null -#test=charset 'no-such-charset-xyz' 'café' 2>/dev
 # malformed UTF-8 (lone continuation byte, truncated lead byte) must not crash
 runs 'utf-8' $'\x80'
 runs 'utf-8' $'\xc3'
-
-# hts_getCharsetFromMeta: <meta> charset extraction, HTML5 and legacy forms.
-# -#test=metacharset <html> prints the charset, or "(none)".
-meta() {
-    test "$(httrack -O /dev/null -#test=metacharset "$1")" == "$2" || exit 1
-}
-
-# HTML5 form, quoting/spacing flavors
-meta '<meta charset="utf-8">' 'utf-8'
-meta "<meta charset='utf-8'>" 'utf-8'
-meta '<meta charset=utf-8>' 'utf-8'
-meta '<meta charset=utf-8 />' 'utf-8'
-meta '<meta charset=utf-8/>' 'utf-8'
-# charset labels are case-insensitive downstream; only require case-insensitive match
-test "$(httrack -O /dev/null -#test=metacharset '<META CHARSET=UTF-8>' | tr '[:upper:]' '[:lower:]')" == 'utf-8' || exit 1
-meta '<html><head><meta   charset = "utf-8"  ></head>' 'utf-8'
-
-# legacy http-equiv form, attributes in any order
-meta '<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">' 'iso-8859-1'
-meta '<meta content="text/html; charset=gb2312" http-equiv="content-type">' 'gb2312'
-meta '<meta http-equiv=Content-Type content="text/html;charset=euc-jp">' 'euc-jp'
-meta '<meta http-equiv="Content-Type" content="text/html; charset = koi8-r ">' 'koi8-r'
-meta '<meta http-equiv="Content-Type" content="text/html; charset=utf-8;">' 'utf-8'
-meta '<meta http-equiv=content-type content=text/html;charset=utf-8 />' 'utf-8'
-meta '<meta http-equiv=content-type content=text/html;charset=utf-8>' 'utf-8'
-
-# first resolvable meta wins; unrelated metas are skipped
-meta '<meta name="viewport" content="width=1"><meta charset="koi8-r">' 'koi8-r'
-meta '<meta charset="utf-8"><meta http-equiv="Content-Type" content="text/html; charset=gb2312">' 'utf-8'
-
-# duplicate attribute: first wins, as in browsers
-meta '<meta http-equiv="Content-Type" content="text/html; charset=big5" http-equiv="refresh">' 'big5'
-
-# negatives: wrong tag/attribute, empty value
-meta '<p>x</p>' '(none)'
-meta '<meta name="desc" content="charset=bogus">' '(none)'
-meta '<meta http-equiv="refresh" content="0; url=x.html">' '(none)'
-meta '<body charset="utf-8">' '(none)'
-meta '<meta charset="">' '(none)'
-
-# hostile truncations: no crash, no match
-meta '<meta charset="utf-8' '(none)'
-meta '<meta charset=' '(none)'
-meta '<meta ' '(none)'
-meta '<meta' '(none)'
-
-# hts_isStringUTF8: valid-UTF-8 probe (guards the #180 link conversion).
-utf8() {
-    test "$(httrack -O /dev/null -#test=isutf8 "$1")" == "$2" || exit 1
-}
-utf8 'plain' '1'
-utf8 'café' '1'
-utf8 '统计' '1'
-utf8 "$(printf 'caf\xe9')" '0'              # latin-1 accent
-utf8 "$(printf '\xc3')" '0'                 # truncated lead byte
-utf8 "$(printf '\xa9')" '0'                 # lone continuation byte
-utf8 "$(printf '\xf0\x9f\x98\x80')" '1'     # 4-byte emoji
-utf8 "$(printf '\xc0\xaf')" '0'             # overlong (latin-1 "À¯" must stay convertible)
-utf8 "$(printf '\xed\xa0\x80')" '0'         # UTF-16 surrogate
-utf8 "$(printf '\xf4\x90\x80\x80')" '0'     # above U+10FFFF
-utf8 "$(printf '\xf8\x88\x80\x80\x80')" '0' # legacy 5-byte form

tests/01_engine-filter.test

@@ -131,64 +131,3 @@ match '*.aspx' 'page.aspx?y=2'
 # empty subject against a unique-match allow-all pattern (heap over-read regress)
 nomatch_empty '*(('
 nomatch_empty '**(('
-
-# near-miss negatives: word order, exact tails, range boundaries, class case
-nomatch 'foo*bar' 'foobaz'
-nomatch '*foo*bar' 'barfoo' # both words present, wrong order
-nomatch '*.gif' 'a.gifx'    # trailing junk after the extension
-nomatch '*.gif' 'a.gi'
-nomatch '*[b-y]' 'a'
-nomatch '*[b-y]' 'z'
-nomatch '*[a-z].txt' 'B.txt' # classes are case-sensitive...
-match 'FoO*' 'foobar'        # ...literals are not
-
-# a star may match an empty run, but never skip a required literal
-match '*[0-9].gif' '.gif'
-nomatch '*[0-9].gif' 'x.gif'
-
-# a descending range *[c-a] is an empty class, not c..a reversed
-match '*[c-a]x' 'x'
-nomatch '*[c-a]x' 'cx'
-
-# *[param] is all-or-nothing on '?': spans everything after one, else nothing
-match 'a*[param]' 'a?x=1'
-nomatch 'a*[param]' 'ab?x=1'
-
-# the latest matching rule wins, regardless of sign
-fsize 'verdict=forbidden size_flag=0' -1 a.gif '+*.gif' '-*.gif'
-fsize 'verdict=allowed size_flag=0' -1 a.gif '-*.gif' '+*.gif'
-
-# a failed size test sets size_flag but leaves the rule unmatched
-fsize 'verdict=unknown size_flag=1' 5 foo.jpg '-*.jpg*[>10]'
-
-# mime filters (-#test=filtermime = fa_strjoker type=1): only mime: rules
-# apply to a mime type, and mime: rules never apply to a URL
-fmime() {
-    local want="$1"
-    shift
-    test "$(httrack -O /dev/null -#test=filtermime "$@")" == "verdict=$want" || exit 1
-}
-fmime allowed 'image/png' '+mime:image/*'
-fmime unknown 'text/html' '+mime:image/*'
-fmime forbidden 'image/png' '+mime:image/*' '-mime:image/png' # last wins
-fmime allowed 'image/png' '-mime:image/png' '+mime:image/*'
-fmime unknown 'image/png' '+image/*'                               # URL rule: skipped
-fsize 'verdict=unknown size_flag=0' -1 'image/png' '+mime:image/*' # and vice versa
-
-# memoized vs no-memo differential over seeded random patterns and subjects,
-# matching and non-matching (the self-test asserts both polarities occurred)
-test "$(httrack -O /dev/null -#test=filtermemo)" == "filtermemo: 20000 cases OK" || exit 1
-
-# star-heavy non-match must stay polynomial (#501); 400 chars also exercises
-# the heap-allocated memo. timeout (where available) turns a hang into a FAIL.
-with_timeout() {
-    if command -v timeout >/dev/null; then timeout 60 "$@"; else "$@"; fi
-}
-pat=$(printf '*[a]%.0s' $(seq 1 12))b
-subj=$(printf 'a%.0s' $(seq 1 400))
-test "$(with_timeout httrack -O /dev/null -#test=filter "$pat" "$subj")" == "$subj does NOT match $pat" || exit 1
-
-# a later star's class dead-end must re-extend the earlier star, not give up
-# (guards against a single-backtrack-point matcher rewrite)
-match '*[aX]X*[a]Y' 'aXaXaY'
-nomatch '*[aX]X*[a]Y' 'aXbXaY'

tests/11_crawl-international.test

@@ -22,9 +22,9 @@ bash crawl-test.sh \
     httrack http://ut.httrack.com/unicode-links/utf8.html
 
 bash crawl-test.sh \
-    --errors 2 --files 9 \
-    --found ut.httrack.com/unicode-links/café3860.html \
-    --found ut.httrack.com/unicode-links/café9fa8.html \
+    --errors 4 --files 7 \
+    --found ut.httrack.com/unicode-links/café3860.html \
+    --found ut.httrack.com/unicode-links/café9fa8.html \
     --found ut.httrack.com/unicode-links/café30f4.html \
     --found ut.httrack.com/unicode-links/café5e1f.html \
     --found ut.httrack.com/unicode-links/café7b30.html \

tests/36_local-bigcrawl.test

@@ -1,7 +1,7 @@
 #!/bin/bash
 #
 # Diverse seeded /big/ crawl: 12 pattern families, decoy absence, update pass
-# must 304-revalidate. 361 = 1 index + 96 pages + 192 imgs + 5 shared + 61
+# must 304-revalidate. 360 = 1 index + 96 pages + 192 imgs + 5 shared + 60
 # family + 6 singles; the 4 planted errors write -o1 pages, not counted.
 
 set -euo pipefail
@@ -9,7 +9,7 @@ set -euo pipefail
 : "${top_srcdir:=..}"
 
 bash "$top_srcdir/tests/local-crawl.sh" --rerun \
-    --errors 4 --files 361 \
+    --errors 4 --files 360 \
     --found 'big/p/95.html' \
     --found 'big/a/d1/d2/d3/d4/d5/d6/d7/d8/deep.png' \
     --found 'big/a/f2-2x.png' \
@@ -40,7 +40,6 @@ bash "$top_srcdir/tests/local-crawl.sh" --rerun \
     --not-found 'big/x/bj.jar' \
     --not-found 'big/x/is1.png' \
     --not-found 'big/x/concat.html' \
-    --file-matches 'big/f1/gzid.html' '<p>gzid</p>' \
     --file-matches 'big/p/2.html' 'srcset="\.\./a/f2-1x\.png 1x, \.\./a/f2-2x\.png 2x"' \
     --file-matches 'big/a/blk2.css' 'url\(blk2-bg\.png\)' \
     --file-matches 'big/p/5.html' "document\\.write\\('<a href=\"\\.\\./f5/dw\\.html\"" \

tests/41_local-utf8-link.test

@@ -1,21 +0,0 @@
-#!/bin/bash
-#
-# #180: raw non-ASCII hrefs must reach the wire UTF-8 percent-encoded whatever
-# the declared page charset; each PDF exists only at its exact UTF-8 path.
-
-set -euo pipefail
-: "${top_srcdir:=..}"
-
-bash "$top_srcdir/tests/local-crawl.sh" --errors 0 --rerun \
-    --found 'charset/header/统计大数据服务平台.pdf' \
-    --found 'charset/meta5/统计大数据服务平台.pdf' \
-    --found 'charset/metaeq/统计大数据服务平台.pdf' \
-    --found 'charset/none/统计大数据服务平台.pdf' \
-    --found 'charset/latin1hdr/统计大数据服务平台.pdf' \
-    --found 'charset/latin1real/café.pdf' \
-    --found 'charset/metalatin1/déjà.pdf' \
-    --found 'charset/latin1ovl/À¡x.pdf' \
-    --found 'charset/priority/nuée.pdf' \
-    --found 'charset/preenc/统计大数据服务平台.pdf' \
-    --found 'charset/bom/统计大数据服务平台.pdf' \
-    httrack 'BASEURL/charset/index.html'

tests/Makefile.am

@@ -109,7 +109,6 @@ TESTS = \
 	37_local-cache-outage.test \
 	38_local-update-304.test \
 	39_local-delayed-cancel.test \
-	40_local-why.test \
-	41_local-utf8-link.test
+	40_local-why.test
 
 CLEANFILES = check-network_sh.cache

tests/local-server.py

@@ -374,7 +374,6 @@ def big_index(port):
         '<img src="/big/a/d1/d2/d3/d4/d5/d6/d7/d8/deep.png">'
         '<a href="/big/f1/long.html?x=%s">long</a>'
         '<a href="/big/f1/gzok.html">gzok</a>'
-        '<a href="/big/f1/gzid.html">gzid</a>'
         '<a href="//127.0.0.1:%d/big/f1/protorel.html">protorel</a>'
         '<a href="http://127.0.0.1:%d/big/f1/abshost.html">abshost</a>'
         '<a href="/big/e/404.html">e404</a>'
@@ -400,7 +399,6 @@ BIG_SIMPLE_PAGES = {
     "/big/f1/dir/": "dir index",
     "/big/f1/long.html": "long",
     "/big/f1/gzok.html": "gzok",
-    "/big/f1/gzid.html": "gzid",
     "/big/f1/protorel.html": "protorel",
     "/big/f1/abshost.html": "abshost",
     "/big/f5/dw.html": "dw target",
@@ -662,97 +660,6 @@ class Handler(SimpleHTTPRequestHandler):
     def route_intl_page(self):
         self.send_raw(b"<html><body>accented page</body></html>\n", "text/html")
 
-    # Raw non-ASCII href matrix (#180): each variant declares the page charset
-    # differently; the PDF exists only at its exact UTF-8 path, so a
-    # mis-decoded link 404s.
-    CHARSET_CJK = "统计大数据服务平台.pdf"
-    # variant -> (index Content-Type, <head> bytes, href bytes, pdf name)
-    CHARSET_VARIANTS = {
-        "header": ("text/html; charset=utf-8", b"", CHARSET_CJK.encode(), CHARSET_CJK),
-        "meta5": (
-            "text/html",
-            b'<meta charset="utf-8">',
-            CHARSET_CJK.encode(),
-            CHARSET_CJK,
-        ),
-        "metaeq": (
-            "text/html",
-            b'<meta http-equiv="Content-Type" content="text/html; charset=utf-8">',
-            CHARSET_CJK.encode(),
-            CHARSET_CJK,
-        ),
-        "none": ("text/html", b"", CHARSET_CJK.encode(), CHARSET_CJK),
-        "latin1hdr": (
-            "text/html; charset=iso-8859-1",
-            b"",
-            CHARSET_CJK.encode(),
-            CHARSET_CJK,
-        ),
-        # genuine latin-1 href: the charset conversion must still apply
-        "latin1real": (
-            "text/html; charset=iso-8859-1",
-            b"",
-            "café.pdf".encode("latin-1"),
-            "café.pdf",
-        ),
-        # latin-1 declared by META only: the meta parser is load-bearing
-        "metalatin1": (
-            "text/html",
-            b'<meta charset="iso-8859-1">',
-            "déjà.pdf".encode("latin-1"),
-            "déjà.pdf",
-        ),
-        # latin-1 bytes that form an overlong UTF-8 shape: strict validation
-        # must still convert them
-        "latin1ovl": (
-            "text/html; charset=iso-8859-1",
-            b"",
-            "À¡x.pdf".encode("latin-1"),
-            "À¡x.pdf",
-        ),
-        # header wins over meta: latin-1 href only resolves if iso-8859-1 is kept
-        "priority": (
-            "text/html; charset=iso-8859-1",
-            b'<meta charset="utf-8">',
-            "nuée.pdf".encode("latin-1"),
-            "nuée.pdf",
-        ),
-        "preenc": ("text/html", b"", quote(CHARSET_CJK).encode(), CHARSET_CJK),
-        "bom": ("text/html", b"", CHARSET_CJK.encode(), CHARSET_CJK),
-    }
-
-    def route_charset(self):
-        path = unquote(urlsplit(self.path).path)
-        parts = path.split("/")
-        if path == "/charset/index.html":
-            self.send_html(
-                "".join(
-                    '\t<a href="%s/index.html">%s</a>\n' % (v, v)
-                    for v in self.CHARSET_VARIANTS
-                )
-            )
-            return
-        if len(parts) == 4 and parts[2] in self.CHARSET_VARIANTS:
-            ctype, head, href, pdf = self.CHARSET_VARIANTS[parts[2]]
-            if parts[3] == "index.html":
-                body = (
-                    b"<html><head>"
-                    + head
-                    + b'</head><body><a href="'
-                    + href
-                    + b'">doc</a></body></html>'
-                )
-                if parts[2] == "bom":
-                    body = b"\xef\xbb\xbf" + body
-                self.send_raw(body, ctype)
-                return
-            if parts[3] == pdf:
-                self.send_raw(self.FAKE_PDF, "application/pdf")
-                return
-        self.send_response(404)
-        self.send_header("Content-Length", "0")
-        self.end_headers()
-
     # 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
@@ -1172,13 +1079,6 @@ class Handler(SimpleHTTPRequestHandler):
                     "text/html",
                     extra=[("Content-Encoding", "gzip")],
                 )
-            elif path == "/big/f1/gzid.html":
-                # Plain body mislabeled as gzip: identity fallback keeps it (#47)
-                self.big_send(
-                    body,
-                    "text/html",
-                    extra=[("Content-Encoding", "gzip")],
-                )
             else:
                 self.big_send(body, "text/html")
         elif path == "/big/f1/list.html":
@@ -1294,9 +1194,6 @@ class Handler(SimpleHTTPRequestHandler):
         if path.startswith("/big/"):
             self.route_big()
             return True
-        if path.startswith("/charset/"):
-            self.route_charset()
-            return True
         # 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: