tests: group zlib-dependent self-tests under 01_zlib-*

The MSan job runs the offline 01_engine-* self-tests but must skip any that
exercise the system zlib: uninstrumented libz floods MemorySanitizer with
false positives (MSan can't see libz initialize its own internal state, so
every byte deflate/inflate produces reads as "uninitialized"). That was a
grep -v -- '-cache' exclusion, a list that would grow with each new zlib test.

Rename the three cache tests to a 01_zlib-* prefix so the MSan job selects
01_engine-* with no exclusion list. They still run in the normal suite and
under ASan+UBSan (full make check), where uninstrumented libz is fine. The
deflate Accept-Encoding test (PR #459) follows the same convention.

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

.github/workflows/ci.yml

@@ -61,6 +61,50 @@ jobs:
         if: failure()
         run: cat tests/test-suite.log 2>/dev/null || true
 
+  # Reproduce the Debian buildds: they build in a minimal chroot with no
+  # python3, so the local-server tests must SKIP (exit 77), not fail. GitHub
+  # runners ship python3, so every other job hides this path; here we remove it
+  # before `make check`. This is the guard that would have caught the 3.49.10-1
+  # FTBFS (28_local-pause failed instead of skipping when python3 was absent).
+  buildd-no-python3:
+    name: build (no python3, Debian buildd)
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+
+      - name: Install build dependencies
+        run: |
+          set -euo pipefail
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            build-essential autoconf automake libtool autoconf-archive \
+            zlib1g-dev libssl-dev
+
+      - name: Configure
+        run: |
+          set -euo pipefail
+          autoreconf -fi
+          ./configure
+
+      - name: Build
+        run: make -j"$(nproc)"
+
+      - name: Test without python3
+        run: |
+          set -euo pipefail
+          # Hide every python3* so `command -v python3` fails like it does in the
+          # buildd chroot; masking with /bin/false would still resolve.
+          sudo find /usr/bin /usr/local/bin -maxdepth 1 -name 'python3*' \
+            -exec mv {} {}.hidden \;
+          ! command -v python3
+          make check
+
+      - name: Print the test log on failure
+        if: failure()
+        run: cat tests/test-suite.log 2>/dev/null || true
+
   # Portability: build and test on macOS (Darwin/clang) on a native runner --
   # no VM. The tree has no __APPLE__ branches, so Darwin exercises the
   # generic-Unix path on a second libc and kernel. brew's openssl@3 is keg-only,
@@ -225,8 +269,9 @@ jobs:
           MSAN_OPTIONS: abort_on_error=1:halt_on_error=1
         run: |
           set -euo pipefail
-          # Engine self-tests only; the cache trio pulls in uninstrumented zlib.
-          tests="$(cd tests && ls 01_engine-*.test | grep -v -- '-cache' | tr '\n' ' ')"
+          # 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"
 
       - name: Print the test log on failure

src/htsbasenet.h

@@ -129,6 +129,8 @@ typedef enum HTTPStatusCode {
   HTTP_UNSUPPORTED_MEDIA_TYPE = 415,
   HTTP_REQUESTED_RANGE_NOT_SATISFIABLE = 416,
   HTTP_EXPECTATION_FAILED = 417,
+  HTTP_TOO_MANY_REQUESTS = 429,
+  HTTP_UNAVAILABLE_FOR_LEGAL_REASONS = 451,
   HTTP_INTERNAL_SERVER_ERROR = 500,
   HTTP_NOT_IMPLEMENTED = 501,
   HTTP_BAD_GATEWAY = 502,

src/htsbasiccharsets.sh

@@ -3,12 +3,12 @@
 
 # Change this to download files
 if false; then
-    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/ISO8859/8859-*.TXT" | lftp
-    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP*.TXT" | lftp
-    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP*.TXT" | lftp
-    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP*.TXT" | lftp
-    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/CP*.TXT" | lftp
-    echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8*.TXT" | lftp
+    echo "mget https://www.unicode.org/Public/MAPPINGS/ISO8859/8859-*.TXT" | lftp
+    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP*.TXT" | lftp
+    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP*.TXT" | lftp
+    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP*.TXT" | lftp
+    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/CP*.TXT" | lftp
+    echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8*.TXT" | lftp
     rm -f CP932.TXT CP936.TXT CP949.TXT CP950.TXT
 fi
 

src/htscatchurl.c

@@ -64,7 +64,7 @@ Please visit our Website: http://www.httrack.com
 // catch_url_init(&port,&return_host);
 HTSEXT_API T_SOC catch_url_init_std(int *port_prox, char *adr_prox) {
   T_SOC soc;
-  int try_to_listen_to[] = { 8080, 3128, 80, 81, 82, 8081, 3129, 31337, 0, -1 };
+  int try_to_listen_to[] = {8080, 3128, 80, 81, 82, 8081, 3129, 0, -1};
   int i = 0;
 
   do {

src/htsencoding.c

@@ -30,12 +30,14 @@ Please visit our Website: http://www.httrack.com
 /* Author: Xavier Roche                                         */
 /* ------------------------------------------------------------ */
 
+#include <stdint.h>
+
 #include "htscharset.h"
 #include "htsencoding.h"
 #include "htssafe.h"
 
-/* static int decode_entity(const unsigned int hash, const size_t len);
-*/
+/* static int decode_entity(const uint64_t hash, const size_t len);
+ */
 #include "htsentities.h"
 
 /* hexadecimal conversion */
@@ -50,30 +52,31 @@ static int get_hex_value(char c) {
     return -1;
 }
 
-/* Numerical Recipes,
-   see <http://en.wikipedia.org/wiki/Linear_congruential_generator> */
-#define HASH_PRIME ( 1664525 )
-#define HASH_CONST ( 1013904223 )
-#define HASH_ADD(HASH, C) do {                  \
-    (HASH) *= HASH_PRIME;                       \
-    (HASH) += HASH_CONST;                       \
-    (HASH) += (C);                              \
-  } while(0)
+/* 64-bit FNV-1a; must match htsentities.sh, which keys the entity table on it.
+ */
+#define HASH_INIT 0xcbf29ce484222325ULL
+#define HASH_PRIME 0x100000001b3ULL
+#define HASH_ADD(HASH, C)                                                      \
+  do {                                                                         \
+    (HASH) ^= (unsigned char) (C);                                             \
+    (HASH) *= HASH_PRIME;                                                      \
+  } while (0)
 
 int hts_unescapeEntitiesWithCharset(const char *src, char *dest, const size_t max, const char *charset) {
   size_t i, j, ampStart, ampStartDest;
   int uc;
   int hex;
-  unsigned int hash;
+  uint64_t hash;
 
   assertf(max != 0);
-  for(i = 0, j = 0, ampStart = (size_t) -1, ampStartDest = 0,
-        uc = -1, hex = 0, hash = 0 ; src[i] != '\0' ; i++) {
+  for (i = 0, j = 0, ampStart = (size_t) -1, ampStartDest = 0, uc = -1, hex = 0,
+      hash = HASH_INIT;
+       src[i] != '\0'; i++) {
     /* start of entity */
     if (src[i] == '&') {
       ampStart = i;
       ampStartDest = j;
-      hash = 0;
+      hash = HASH_INIT;
       uc = -1;
     }
     /* inside a potential entity */
@@ -174,14 +177,11 @@ int hts_unescapeEntitiesWithCharset(const char *src, char *dest, const size_t ma
       }
       /* alphanumerical entity */
       else {
-        /* alphanum and not too far ('&thetasym;' is the longest) */
-        if (i <= ampStart + 10 &&
-            (
-             (src[i] >= '0' && src[i] <= '9')
-             || (src[i] >= 'A' && src[i] <= 'Z')
-             || (src[i] >= 'a' && src[i] <= 'z')
-             )
-            ) {
+        /* alphanum, capped at the longest name
+         * '&CounterClockwiseContourIntegral;' (31) */
+        if (i <= ampStart + 31 && ((src[i] >= '0' && src[i] <= '9') ||
+                                   (src[i] >= 'A' && src[i] <= 'Z') ||
+                                   (src[i] >= 'a' && src[i] <= 'z'))) {
           /* compute hash */
           HASH_ADD(hash, (unsigned char) src[i]);
         } else {

src/htsentities.sh

@@ -1,75 +1,92 @@
 #!/bin/bash
 #
+# Regenerate htsentities.h from the WHATWG named character references.
 
-src=html40.txt
-url=http://www.w3.org/TR/1998/REC-html40-19980424/html40.txt
+set -euo pipefail
+
+src=entities.json
+url=https://html.spec.whatwg.org/entities.json
 dest=htsentities.h
 
-(
-    cat <<EOF
-/*
-  -- ${dest} --
-  FILE GENERATED BY $0, DO NOT MODIFY
+# 64-bit FNV-1a of $1, printed as a C constant. Must match the hash in
+# htsencoding.c. The offset basis is stored as its wrapped (signed) bit pattern;
+# bash arithmetic is 64-bit two's complement, so the result is bit-exact.
+fnv1a() {
+    local s=$1 i c h=$((0xcbf29ce484222325))
+    for ((i = 0; i < ${#s}; i++)); do
+        printf -v c '%d' "'${s:i:1}"
+        h=$(((h ^ (c & 0xff)) * 0x100000001b3))
+    done
+    printf '0x%016xULL' "$h"
+}
 
-  We compute the LCG hash
-  (see <http://en.wikipedia.org/wiki/Linear_congruential_generator>)
-  for each entity. We should in theory check using strncmp() that we
-  actually have the correct entity, but this is actually statistically
-  not needed.
+if [ ! -f "$src" ]; then
+    curl -fsS "$url" -o "$src"
+fi
 
-  We may want to do better, but we expect the hash function to be uniform, and
-  let the compiler be smart enough to optimize the switch (for example by
-  checking in log2() intervals)
-  
-  This code has been generated using the evil $0 script.
-*/
+# Keep ';'-terminated single-codepoint names; the ~93 multi-codepoint refs can't
+# fit decode_entity's single-codepoint return and are skipped (left verbatim).
+pairs=$(jq -r '
+    to_entries
+    | map(select((.key | endswith(";")) and (.value.codepoints | length == 1)))
+    | sort_by(.key)
+    | .[] | "\(.key | ltrimstr("&") | rtrimstr(";"))\t\(.value.codepoints[0])"' "$src")
 
-static int decode_entity(const unsigned int hash, const size_t len) {
+# Skipped multi-codepoint names, kept to prove none aliases an emitted hash.
+skipped=$(jq -r '
+    to_entries
+    | map(select((.key | endswith(";")) and (.value.codepoints | length > 1)))
+    | .[] | .key | ltrimstr("&") | rtrimstr(";")' "$src")
+
+cases=""
+emit_hashes=""
+while IFS=$'\t' read -r name cp; do
+    hash=$(fnv1a "$name")
+    cases+="    /* $name */"$'\n'
+    cases+="  case $hash:"$'\n'
+    cases+="    if (len == ${#name}) {"$'\n'
+    cases+="      return $cp;"$'\n'
+    cases+="    }"$'\n'
+    cases+="    break;"$'\n'
+    emit_hashes+="$hash"$'\n'
+done <<<"$pairs"
+
+skip_hashes=""
+while IFS= read -r name; do
+    [ -n "$name" ] && skip_hashes+="$(fnv1a "$name")"$'\n'
+done <<<"$skipped"
+
+# The switch keys on the hash alone, so the dispatch is correct only while every
+# emitted name hashes uniquely; prove it here, no runtime name compare needed.
+dups=$(printf '%s' "$emit_hashes" | sort | uniq -d || true)
+if [ -n "$dups" ]; then
+    echo "FATAL: two entity names share a hash (duplicate switch case); change the hash:" >&2
+    echo "$dups" >&2
+    exit 1
+fi
+# A skipped name colliding with an emitted hash would mis-decode instead of
+# staying verbatim; forbid that too.
+aliased=$(comm -12 <(printf '%s' "$emit_hashes" | sort -u) <(printf '%s' "$skip_hashes" | sort -u) || true)
+if [ -n "$aliased" ]; then
+    echo "FATAL: a skipped multi-codepoint name aliases an emitted hash:" >&2
+    echo "$aliased" >&2
+    exit 1
+fi
+
+cat >"$dest" <<EOF
+/* GENERATED by $0 from the WHATWG named character references
+   (${url}). DO NOT EDIT.
+   Dispatch keys on a 64-bit FNV-1a hash of the entity name; the generator
+   aborts on any hash collision, so no runtime name compare is needed. */
+
+#include <stdint.h>
+
+static int decode_entity(const uint64_t hash, const size_t len) {
   switch(hash) {
-EOF
-    (
-        if test -f ${src}; then
-            cat ${src}
-        else
-            GET "${url}"
-        fi
-    ) |
-        grep -E '^<!ENTITY [a-zA-Z0-9_]' |
-        sed \
-            -e 's/<!ENTITY //' -e "s/[[:space:]][[:space:]]*/ /g" \
-            -e 's/-->$//' \
-            -e 's/\([^ ]*\) CDATA "&#\([^\"]*\);" -- \(.*\)/\1 \2 \3/' |
-        (
-            read -r A
-            while test -n "$A"; do
-                ent="${A%% *}"
-                code=$(echo "$A" | cut -f2 -d' ')
-                # compute hash
-                hash=0
-                i=0
-                a=1664525
-                c=1013904223
-                m="$((1 << 32))"
-                while test "$i" -lt ${#ent}; do
-                    d="$(echo -n "${ent:${i}:1}" | hexdump -v -e '/1 "%d"')"
-                    hash="$((((hash * a) % (m) + d + c) % (m)))"
-                    i=$((i + 1))
-                done
-                echo -e "    /* $A */"
-                echo -e "  case ${hash}u:"
-                echo -e "    if (len == ${#ent} /* && strncmp(ent, \"${ent}\") == 0 */) {"
-                echo -e "      return ${code};"
-                echo -e "    }"
-                echo -e "    break;"
-
-                # next
-                read -r A
-            done
-        )
-    cat <<EOF
-  }
+${cases}  }
   /* unknown */
   return -1;
 }
 EOF
-) >${dest}
+
+echo "wrote $dest ($(grep -c '^  case ' "$dest") entities)" >&2

src/htsglobal.h

@@ -229,6 +229,10 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DEFAULT_FOOTER                                                     \
   "<!-- Mirrored from %s%s by HTTrack Website Copier/" HTTRACK_AFF_VERSION     \
   " " HTTRACK_AFF_AUTHORS ", %s -->"
+/* Honest crawler User-Agent; no fake OS/browser to go stale. */
+#define HTS_DEFAULT_USER_AGENT                                                 \
+  "Mozilla/5.0 (compatible; HTTrack/" HTTRACK_AFF_VERSION                      \
+  "; +https://www.httrack.com/)"
 #define HTTRACK_WEB "http://www.httrack.com"
 #define HTS_UPDATE_WEBSITE                                                     \
   "http://www.httrack.com/"                                                    \

src/htslib.c

@@ -563,6 +563,39 @@ const char *hts_mime[][2] = {
   {"", ""}
 };
 
+/* Modern web formats (post-2010), kept in their own table: appending to the
+   legacy hts_mime[] above makes clang-format reflow its whole initializer.
+   Scanned after hts_mime[], so it never shadows a legacy mapping. */
+static const char *hts_mime_modern[][2] = {
+    {"image/webp", "webp"},
+    {"image/avif", "avif"},
+    {"image/heic", "heic"},
+    {"font/woff", "woff"},
+    {"font/woff2", "woff2"},
+    {"font/ttf", "ttf"},
+    {"font/otf", "otf"},
+    {"application/json", "json"},
+    {"application/ld+json", "jsonld"},
+    {"application/manifest+json", "webmanifest"},
+    {"application/wasm", "wasm"},
+    {"text/javascript", "js"},
+    {"text/javascript", "mjs"},
+    {"text/markdown", "md"},
+    {"video/mp4", "mp4"},
+    {"video/webm", "webm"},
+    {"video/ogg", "ogv"},
+    {"video/mp2t", "ts"},
+    {"audio/mp4", "m4a"},
+    {"audio/aac", "aac"},
+    {"audio/ogg", "oga"},
+    {"audio/opus", "opus"},
+    {"audio/flac", "flac"},
+    {"audio/webm", "weba"},
+    {"application/x-7z-compressed", "7z"},
+    {"application/x-rar-compressed", "rar"},
+    {"application/zstd", "zst"},
+    {"", ""}};
+
 // Reserved (RFC2396)
 #define CIS(c,ch) ( ((unsigned char)(c)) == (ch) )
 #define CHAR_RESERVED(c)  ( CIS(c,';') \
@@ -1918,6 +1951,10 @@ HTSEXT_API const char *infostatuscode_const(int statuscode) {
     return "Requested Range Not Satisfiable";
   case 417:
     return "Expectation Failed";
+  case 429:
+    return "Too Many Requests";
+  case 451:
+    return "Unavailable For Legal Reasons";
   case 500:
     return "Internal Server Error";
   case 501:
@@ -4308,6 +4345,20 @@ void guess_httptype(httrackp * opt, char *s, const char *fil) {
   (void) get_httptype_sized(opt, s, HTS_MIMETYPE_SIZE, fil, 1);
 }
 
+// first match in a NUL-terminated {mime,ext} table. key selects the lookup
+// column (0=mime, 1=ext); returns the other column, or NULL if no row matches
+// (a "*" partner means the row carries no value).
+static const char *hts_mime_lookup(const char *(*table)[2], int key,
+                                   const char *needle) {
+  int j;
+
+  for (j = 0; strnotempty(table[j][1]); j++) {
+    if (strfield2(table[j][key], needle) && table[j][!key][0] != '*')
+      return table[j][!key];
+  }
+  return NULL;
+}
+
 // write the mime type for fil into s (capacity ssize)
 // flag: 1 to always return a type (the "application/..." / octet-stream
 // fallback) returns 1 if a type was written to s, 0 otherwise
@@ -4331,17 +4382,15 @@ HTSEXT_API hts_boolean get_httptype_sized(httrackp *opt, char *s, size_t ssize,
     while ((a > fil) && (*a != '.') && (*a != '/'))
       a--;
     if (a >= fil && *a == '.' && strlen(a) < 32) {
-      int j = 0;
+      const char *mime;
 
       a++;
-      while(strnotempty(hts_mime[j][1])) {
-        if (strfield2(hts_mime[j][1], a)) {
-          if (hts_mime[j][0][0] != '*') { // a match exists
-            strlcpybuff(s, hts_mime[j][0], ssize);
-            return 1;
-          }
-        }
-        j++;
+      mime = hts_mime_lookup(hts_mime, 1, a);
+      if (mime == NULL)
+        mime = hts_mime_lookup(hts_mime_modern, 1, a);
+      if (mime != NULL) {
+        strlcpybuff(s, mime, ssize);
+        return 1;
       }
 
       if (flag) {
@@ -4476,18 +4525,16 @@ int get_userhttptype(httrackp * opt, char *s, const char *fil) {
 // returns 1 if an extension was found (and written to s), 0 otherwise
 int give_mimext(char *s, size_t ssize, const char *st) {
   int ok = 0;
-  int j = 0;
+  const char *ext;
 
   st = hts_effective_mime(st); /* no declared type: derive an html ext */
   s[0] = '\0';
-  while((!ok) && (strnotempty(hts_mime[j][1]))) {
-    if (strfield2(hts_mime[j][0], st)) {
-      if (hts_mime[j][1][0] != '*') { // a match exists
-        strlcpybuff(s, hts_mime[j][1], ssize);
-        ok = 1;
-      }
-    }
-    j++;
+  ext = hts_mime_lookup(hts_mime, 0, st);
+  if (ext == NULL)
+    ext = hts_mime_lookup(hts_mime_modern, 0, st);
+  if (ext != NULL) {
+    strlcpybuff(s, ext, ssize);
+    ok = 1;
   }
   // wrap "x" mimetypes, such as:
   // application/x-mp3
@@ -5754,6 +5801,13 @@ HTSEXT_API int hts_init(void) {
       abortLog("unable to initialize TLS: SSL_CTX_new()");
       assertf("unable to initialize TLS" == NULL);
     }
+    /* Pin a TLS floor (no SSLv3/TLS1.0/1.1); no cert verify, by design. */
+#if OPENSSL_VERSION_NUMBER >= 0x10100000L
+    SSL_CTX_set_min_proto_version(openssl_ctx, TLS1_2_VERSION);
+#else
+    SSL_CTX_set_options(openssl_ctx, SSL_OP_NO_SSLv2 | SSL_OP_NO_SSLv3 |
+                                         SSL_OP_NO_TLSv1 | SSL_OP_NO_TLSv1_1);
+#endif
   }
 #endif
 
@@ -6005,8 +6059,7 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   opt->shell = HTS_FALSE;
   opt->proxy.active = 0;        // pas de proxy
   opt->user_agent_send = HTS_TRUE;
-  StringCopy(opt->user_agent,
-             "Mozilla/4.5 (compatible; HTTrack 3.0x; Windows 98)");
+  StringCopy(opt->user_agent, HTS_DEFAULT_USER_AGENT);
   StringCopy(opt->referer, "");
   StringCopy(opt->from, "");
   opt->savename_83 = HTS_SAVENAME_83_LONG; // long names by default

src/htsselftest.c

@@ -239,6 +239,14 @@ static void basic_selftests(void) {
     assertf(strcmp(ext, "html") == 0);
     assertf(give_mimext(ext, sizeof(ext), "no/such-mime-type") == 0);
     assertf(ext[0] == '\0');
+    // modern web formats -> extension. Avoid MIME types the
+    // application/<=4-char-subtype fallback could fabricate without a row.
+    assertf(give_mimext(ext, sizeof(ext), "image/webp") == 1);
+    assertf(strcmp(ext, "webp") == 0);
+    assertf(give_mimext(ext, sizeof(ext), "application/manifest+json") == 1);
+    assertf(strcmp(ext, "webmanifest") == 0);
+    assertf(give_mimext(ext, sizeof(ext), "font/woff2") == 1);
+    assertf(strcmp(ext, "woff2") == 0);
   }
   // convtolower(): lower-cases into the caller buffer (bounded by its size).
   {
@@ -293,6 +301,16 @@ static void basic_selftests(void) {
     assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
                                "x.gif", 0) == 1);
     assertf(strcmp(r.contenttype, "image/gif") == 0);
+    // modern extensions map back to their MIME type
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "x.webp", 0) == 1);
+    assertf(strcmp(r.contenttype, "image/webp") == 0);
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "app.wasm", 0) == 1);
+    assertf(strcmp(r.contenttype, "application/wasm") == 0);
+    assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
+                               "mod.mjs", 0) == 1);
+    assertf(strcmp(r.contenttype, "text/javascript") == 0);
     // no extension and flag==0: nothing written, returns 0
     assertf(get_httptype_sized(opt, r.contenttype, sizeof(r.contenttype),
                                "noextfile", 0) == 0);
@@ -1284,6 +1302,40 @@ static int st_urlhack(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* Default User-Agent: honest HTTrack token, no resurrected Windows 98. */
+static int st_useragent(httrackp *opt, int argc, char **argv) {
+  const char *ua = StringBuff(opt->user_agent);
+  (void) argc;
+  (void) argv;
+  assertf(ua != NULL);
+  assertf(strcmp(ua, HTS_DEFAULT_USER_AGENT) == 0);
+  /* Teeth independent of the macro: honest token + self-identifier, and no
+     legacy Mozilla/4.x fake-browser string (rejects the whole relic family). */
+  assertf(strstr(ua, "HTTrack/") != NULL);
+  assertf(strstr(ua, "+https://www.httrack.com/") != NULL);
+  assertf(strstr(ua, "Mozilla/4.") == NULL);
+  printf("useragent self-test OK: %s\n", ua);
+  return 0;
+}
+
+/* HTTP status code -> reason phrase, including the modern 429/451. */
+static int st_status(httrackp *opt, int argc, char **argv) {
+  const char *s;
+  (void) opt;
+  (void) argc;
+  (void) argv;
+  s = infostatuscode_const(429);
+  assertf(s != NULL && strcmp(s, "Too Many Requests") == 0);
+  s = infostatuscode_const(451);
+  assertf(s != NULL && strcmp(s, "Unavailable For Legal Reasons") == 0);
+  /* A spot-check of a long-standing code, and an unknown one. */
+  s = infostatuscode_const(404);
+  assertf(s != NULL && strcmp(s, "Not Found") == 0);
+  assertf(infostatuscode_const(799) == NULL);
+  printf("status self-test OK\n");
+  return 0;
+}
+
 /* ------------------------------------------------------------ */
 /* Registry: name -> handler, with a usage hint and a one-line description. */
 /* ------------------------------------------------------------ */
@@ -1330,6 +1382,8 @@ static const struct selftest_entry {
      st_cache_writefail},
     {"dns", "", "DNS resolver/cache self-test", st_dns},
     {"cookies", "", "cookie request-header self-test", st_cookies},
+    {"useragent", "", "default User-Agent self-test", st_useragent},
+    {"status", "", "HTTP status code -> reason phrase self-test", st_status},
 };
 
 static void list_selftests(void) {

src/htsserver.c

@@ -358,12 +358,12 @@ int smallserver(T_SOC soc, char *url, char *method, char *data, char *path) {
       {NULL, 0}
     };
     initStrElt initStr[] = {
-      {"user", "Mozilla/4.5 (compatible; HTTrack 3.0x; Windows 98)"},
-      {"footer",
-       "<!-- Mirrored from %s%s by HTTrack Website Copier/3.x [XR&CO'2014], %s -->"},
-      {"url2", "+*.png +*.gif +*.jpg +*.jpeg +*.css +*.js -ad.doubleclick.net/*"},
-      {NULL, NULL}
-    };
+        {"user", HTS_DEFAULT_USER_AGENT},
+        {"footer", "<!-- Mirrored from %s%s by HTTrack Website Copier/3.x "
+                   "[XR&CO'2014], %s -->"},
+        {"url2",
+         "+*.png +*.gif +*.jpg +*.jpeg +*.css +*.js -ad.doubleclick.net/*"},
+        {NULL, NULL}};
     int i = 0;
 
     for(i = 0; initInt[i].name; i++) {

src/htswizard.c

@@ -80,6 +80,10 @@ htspair_t hts_detect_embed[] = {
   {NULL, NULL}
 };
 
+/* HTML5 media siblings of <img src>: same near-link treatment (#451) */
+static const htspair_t hts_detect_embed_html5[] = {
+    {"source", "src"}, {"source", "srcset"}, {"track", "src"}, {NULL, NULL}};
+
 /* Internal */
 static int hts_acceptlink_(httrackp * opt, int ptr, const char *adr,
                            const char *fil, const char *tag,
@@ -136,6 +140,17 @@ static int cmp_token(const char *tag, const char *cmp) {
           && !isalnum((unsigned char) tag[p]));
 }
 
+/* TRUE if (tag, attribute) matches an embedded-asset pair in the table */
+static hts_boolean is_embed_pair(const htspair_t *table, const char *tag,
+                                 const char *attribute) {
+  int i;
+  for (i = 0; table[i].tag != NULL; i++) {
+    if (cmp_token(tag, table[i].tag) && cmp_token(attribute, table[i].attr))
+      return HTS_TRUE;
+  }
+  return HTS_FALSE;
+}
+
 static int hts_acceptlink_(httrackp * opt, int ptr,
                            const char *adr, const char *fil, const char *tag,
                            const char *attribute, int *set_prio_to,
@@ -163,15 +178,9 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
 
   /* Built-in known tags (<img src=..>, ..) */
   if (forbidden_url != 0 && opt->nearlink && tag != NULL && attribute != NULL) {
-    int i;
-
-    for(i = 0; hts_detect_embed[i].tag != NULL; i++) {
-      if (cmp_token(tag, hts_detect_embed[i].tag)
-          && cmp_token(attribute, hts_detect_embed[i].attr)
-        ) {
-        embedded_triggered = 1;
-        break;
-      }
+    if (is_embed_pair(hts_detect_embed, tag, attribute) ||
+        is_embed_pair(hts_detect_embed_html5, tag, attribute)) {
+      embedded_triggered = 1;
     }
   }
 

src/proxy/proxytrack.c

@@ -497,6 +497,12 @@ static const char *GetHttpMessage(int statuscode) {
   case 417:
     return "Expectation Failed";
     break;
+  case 429:
+    return "Too Many Requests";
+    break;
+  case 451:
+    return "Unavailable For Legal Reasons";
+    break;
   case 500:
     return "Internal Server Error";
     break;

tests/01_engine-entities.test

@@ -18,6 +18,21 @@ ent '&' '&'
 ent '&lt;&gt;' '<>'
 ent '&eacute;' 'é'
 
+# HTML5 names from the WHATWG set
+ent '&hellip;' '…'
+ent '&bigcup;' '⋃'
+# longest name (31 chars) exercises the name-length cap
+ent '&CounterClockwiseContourIntegral;' '∳'
+# astral codepoint -> 4-byte UTF-8
+ent '&Aopf;' '𝔸'
+# multi-codepoint refs are skipped at generation, so left verbatim
+ent '&fjlig;' '&fjlig;'
+
+# common HTML4 names still decode (regression guard against accidental drops)
+ent '&copy;&reg;&trade;' '©®™'
+ent '&mdash;&ndash;' '—–'
+ent '&alpha;&beta;' 'αβ'
+
 # numeric: decimal and hex
 ent '&#65;&#66;' 'AB'
 ent '&#x41;' 'A'

tests/01_engine-parse.test

@@ -323,4 +323,33 @@ grep -Fq 'href="ahref%20(4).gif"' "$saved9" ||
 ! grep -Eq '(src|href)="[^"]*%28' "$saved9" ||
     ! echo "FAIL #163: gate over-fired onto a non-url() attribute link" || exit 1
 
+# HTML5 <source>/<track> follow as embedded near-links past the -r2 depth boundary (#451).
+# img.gif positive control; plain.gif (bare <a href>) negative control proves the gate is selective.
+site10="$tmp/html5media"
+mkdir -p "$site10"
+for f in img ss plain; do gif "$site10/$f.gif"; done
+printf 'x' >"$site10/v.webm"
+printf 'x' >"$site10/subs.vtt"
+cat >"$site10/index.html" <<EOF
+<html><body><a href="leaf.html">leaf</a></body></html>
+EOF
+cat >"$site10/leaf.html" <<EOF
+<html><body>
+<img src="img.gif">
+<picture><source srcset="ss.gif 2x"></picture>
+<video><source src="v.webm"></video>
+<video><track src="subs.vtt"></video>
+<a href="plain.gif">plain link past the boundary</a>
+</body></html>
+EOF
+out10="$tmp/html5media-out"
+rm -rf "$out10"
+mkdir -p "$out10"
+httrack "file://$site10/index.html" -O "$out10" --quiet --near -r2 >"$out10/.log" 2>&1 || true
+found "img.gif" "$out10"
+found "ss.gif" "$out10"
+found "v.webm" "$out10"
+found "subs.vtt" "$out10"
+notfound "plain.gif" "$out10"
+
 exit 0

tests/01_engine-status.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# HTTP status -> reason phrase, including the modern 429/451 (#453).
+httrack -O /dev/null -#test=status run | grep -q "status self-test OK"

tests/01_engine-useragent.test

@@ -0,0 +1,7 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# Default User-Agent (#449): honest HTTrack token, no Windows 98 relic.
+httrack -O /dev/null -#test=useragent run | grep -q "useragent self-test OK"

tests/01_zlib-cache-golden.test

@@ -6,7 +6,7 @@
 
 # Golden cache-format regression test (driven by 'httrack -#test=cache-golden <dir>').
 #
-# 01_engine-cache.test writes the cache with the same build it reads back (a
+# 01_zlib-cache.test writes the cache with the same build it reads back (a
 # round-trip), so it cannot catch a read-path or ZIP-format regression where
 # writer and reader drift together. This reads a *committed* cache frozen by an
 # earlier build and asserts a fixed set of entries still decodes field- and

tests/28_local-pause.test

@@ -9,6 +9,13 @@ set -e
 
 : "${top_srcdir:=..}"
 
+# python3 runs the local server (mirror local-crawl.sh); skip when absent, else
+# run() swallows its exit-77 and the serverless 0s/0s crawl looks like a fail.
+command -v python3 >/dev/null || {
+    echo "python3 not found; skipping local crawl tests"
+    exit 77
+}
+
 run() { # echoes the wall-clock seconds of one crawl
     local t0 t1
     t0=$(date +%s)

tests/Makefile.am

@@ -1,4 +1,4 @@
-# Committed binary fixture read by 01_engine-cache-golden.test. List it
+# Committed binary fixture read by 01_zlib-cache-golden.test. List it
 # explicitly: automake does not expand wildcards in EXTRA_DIST, so a glob would
 # silently drop it from the dist tarball and break "make distcheck".
 EXTRA_DIST = $(TESTS) crawl-test.sh run-all-tests.sh check-network.sh \
@@ -25,9 +25,6 @@ TEST_EXTENSIONS = .test
 TEST_LOG_COMPILER = $(BASH)
 TESTS = \
 	00_runnable.test \
-	01_engine-cache.test \
-	01_engine-cache-golden.test \
-	01_engine-cache-writefail.test \
 	01_engine-charset.test \
 	01_engine-cmdline.test \
 	01_engine-cookies.test \
@@ -47,9 +44,14 @@ TESTS = \
 	01_engine-savename.test \
 	01_engine-selftest-dispatch.test \
 	01_engine-simplify.test \
+	01_engine-status.test \
 	01_engine-stripquery.test \
 	01_engine-strsafe.test \
 	01_engine-urlhack.test \
+	01_engine-useragent.test \
+	01_zlib-cache.test \
+	01_zlib-cache-golden.test \
+	01_zlib-cache-writefail.test \
 	02_manpage-regen.test \
 	02_update-cache.test \
 	10_crawl-simple.test \