Advertise deflate in Accept-Encoding and decode it

The request Accept-Encoding offered only gzip even though the response
parser already recognized deflate/x-deflate. But the actual decode path
(hts_zunpack) used zlib's gzread, which only inflates gzip and copies any
deflate body through verbatim, so a deflate response would have been
written out still compressed. Advertising deflate without fixing that
would corrupt files.

Rewrite hts_zunpack to inflate via inflateInit2 with format detection:
gzip and zlib (RFC1950) auto-detect with +32 windowBits, everything else
is treated as raw deflate (RFC1951). Then add deflate to the advertised
list through a small hts_acceptencoding() helper shared with the test.

A new -#test=acceptencoding self-test asserts the advertised header
carries both gzip and deflate, and round-trips gzip, zlib and raw-deflate
bodies through hts_zunpack on disk. Both halves fail on the old binary.

Brotli is intentionally out of scope (new dependency, larger change).

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

debian/control

@@ -1,8 +1,9 @@
 Source: httrack
 Section: web
+Priority: optional
 Maintainer: Xavier Roche <roche@httrack.com>
 Standards-Version: 4.7.4
-Build-Depends: debhelper-compat (= 14), autoconf, autoconf-archive, automake, libtool, zlib1g-dev, libssl-dev
+Build-Depends: debhelper-compat (= 13), autoconf, autoconf-archive, automake, libtool, zlib1g-dev, libssl-dev
 Rules-Requires-Root: no
 Homepage: http://www.httrack.com
 Vcs-Git: https://github.com/xroche/httrack.git

debian/source/lintian-overrides

@@ -1,6 +1,4 @@
-# Maintainer uploads sign the changelog as xavier@debian.org while the control
-# Maintainer is roche@httrack.com; lintian reads the address mismatch as an NMU.
-httrack source: no-nmu-in-changelog
+httrack source: changelog-should-mention-nmu
 httrack source: source-nmu-has-incorrect-version-number
 
 # The bundled HTML pages are the genuine upstream documentation taken from

debian/upstream/metadata

@@ -1,6 +0,0 @@
----
-Repository: https://github.com/xroche/httrack.git
-Repository-Browse: https://github.com/xroche/httrack
-Bug-Database: https://github.com/xroche/httrack/issues
-Bug-Submit: https://github.com/xroche/httrack/issues/new
-Contact: Xavier Roche <roche@httrack.com>

src/htscore.c

@@ -406,106 +406,29 @@ void hts_invalidate_link(httrackp * opt, int lpos) {
   opt->liens[lpos]->pass2 = -1;
 }
 
-// Write the makeindex footer (refresh meta when makeindex_links==1), close
-// the file, then run usercommand.
-void hts_finish_makeindex(httrackp *opt, int *makeindex_done,
-                          FILE **makeindex_fp, int makeindex_links,
-                          const char *makeindex_firstlink,
-                          const char *template_footer, const char *adr,
-                          const char *fil) {
-  if (!*makeindex_done) {
-    if (*makeindex_fp) {
-      char BIGSTK tempo[1024];
-      if (makeindex_links == 1) {
-        char BIGSTK link_escaped[HTS_URLMAXSIZE * 2];
-        escape_uri_utf(makeindex_firstlink, link_escaped, sizeof(link_escaped));
-        snprintf(tempo, sizeof(tempo),
-                 "<meta HTTP-EQUIV=\"Refresh\" CONTENT=\"0; URL=%s\">" CRLF,
-                 link_escaped);
-      } else
-        tempo[0] = '\0';
-      hts_template_format(*makeindex_fp, template_footer,
-                          "<!-- Mirror and index made by HTTrack Website "
-                          "Copier/" HTTRACK_VERSION " " HTTRACK_AFF_AUTHORS
-                          " -->",
-                          tempo, /* EOF */ NULL);
-      fflush(*makeindex_fp);
-      fclose(*makeindex_fp);
-      *makeindex_fp = NULL;
-      usercommand(opt, 0, NULL,
-                  fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),
-                          StringBuff(opt->path_html_utf8), "index.html"),
-                  adr, fil);
-    }
-  }
-  *makeindex_done = 1;
-}
 
-/* Flush the parsed HTML output buffer to disk, skipping the rewrite when the
- * on-disk MD5 is unchanged. */
-void hts_finish_html_file(httrackp *opt, cache_back *cache, htsblk *r,
-                          FILE **fp, const char *ht_buff, size_t ht_len,
-                          const char *adr, const char *fil, const char *save) {
-  char digest[32 + 2];
-  off_t fsize_old =
-      fsize(fconv(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), save));
-  int ok = 0;
-
-  digest[0] = '\0';
-  domd5mem(ht_buff, ht_len, digest, 1);
-  if (fsize_old == (off_t) ht_len) {
-    int mlen = 0;
-    char *mbuff;
-
-    cache_readdata(cache, "//[HTML-MD5]//", save, &mbuff, &mlen);
-    if (mlen)
-      mbuff[mlen] = '\0';
-    if ((mlen == 32) && (strcmp(((mbuff != NULL) ? mbuff : ""), digest) == 0)) {
-      ok = 1;
-      hts_log_print(opt, LOG_DEBUG, "File not re-written (md5): %s", save);
-    }
-    freet(mbuff);
-  }
-  if (!ok) {
-    file_notify(opt, adr, fil, save, 1, 1, r->notmodified);
-    *fp = filecreate(&opt->state.strc, save);
-    if (*fp) {
-      if (ht_len > 0 && fwrite(ht_buff, 1, ht_len, *fp) != ht_len) {
-        int fcheck = check_fatal_io_errno();
-
-        if (fcheck)
-          opt->state.exit_xh = -1;
-        if (opt->log) {
-          hts_log_print(opt, LOG_ERROR | LOG_ERRNO,
-                        "Unable to write HTML file %s", save);
-          if (fcheck)
-            hts_log_print(opt, LOG_ERROR, "* * Fatal write error, giving up");
-        }
-      }
-      fclose(*fp);
-      *fp = NULL;
-      if (strnotempty(r->lastmodified))
-        set_filetime_rfc822(save, r->lastmodified);
-    } else {
-      int fcheck = check_fatal_io_errno();
-
-      if (fcheck) {
-        hts_log_print(opt, LOG_ERROR,
-                      "Mirror aborted: disk full or filesystem problems");
-        opt->state.exit_xh = -1;
-      }
-      hts_log_print(opt, LOG_ERROR | LOG_ERRNO, "Unable to save file %s", save);
-      if (fcheck)
-        hts_log_print(opt, LOG_ERROR, "* * Fatal write error, giving up");
-    }
-  } else {
-    file_notify(opt, adr, fil, save, 0, 0, r->notmodified);
-    filenote(&opt->state.strc, save, NULL);
-  }
-  if (cache->ndx)
-    cache_writedata(cache->ndx, cache->dat, "//[HTML-MD5]//", save, digest,
-                    (int) strlen(digest));
-}
+#define HT_INDEX_END do { \
+if (!makeindex_done) { \
+if (makeindex_fp) { \
+  char BIGSTK tempo[1024]; \
+  if (makeindex_links == 1) { \
+    char BIGSTK link_escaped[HTS_URLMAXSIZE*2]; \
+    escape_uri_utf(makeindex_firstlink, link_escaped, sizeof(link_escaped)); \
+    snprintf(tempo,sizeof(tempo),"<meta HTTP-EQUIV=\"Refresh\" CONTENT=\"0; URL=%s\">"CRLF, link_escaped); \
+  } else \
+    tempo[0]='\0'; \
+    hts_template_format(makeindex_fp,template_footer, \
+    "<!-- Mirror and index made by HTTrack Website Copier/"HTTRACK_VERSION" "HTTRACK_AFF_AUTHORS" -->", \
+    tempo, /* EOF */ NULL \
+    ); \
+  fflush(makeindex_fp); \
+  fclose(makeindex_fp);  /* à ne pas oublier sinon on passe une nuit blanche */  \
+  makeindex_fp=NULL; \
+  usercommand(opt,0,NULL,fconcat(OPT_GET_BUFF(opt),OPT_GET_BUFF_SIZE(opt),StringBuff(opt->path_html_utf8),"index.html"),"","");  \
+} \
+} \
+makeindex_done=1;    /* ok c'est fait */  \
+} while(0)
 
 /* does it look like XML ? (SVG et al.) */
 static int look_like_xml(const char *s) {
@@ -1873,18 +1796,90 @@ int httpmirror(char *url1, httrackp * opt) {
         if (strnotempty(savename()) == 0) {       // pas de chemin de sauvegarde
           if (strcmp(urlfil(), "/robots.txt") == 0) {     // robots.txt
             if (r.adr) {
+              int bptr = 0;
+              char BIGSTK line[1024];
+              char BIGSTK buff[8192];
               char BIGSTK infobuff[8192];
-#ifdef IGNORE_RESTRICTIVE_ROBOTS
-              hts_boolean keep_root = (opt->robots >= HTS_ROBOTS_ALWAYS_STRICT)
-                                          ? HTS_TRUE
-                                          : HTS_FALSE;
-#else
-              hts_boolean keep_root = HTS_TRUE;
-#endif
+              int record = 0;
 
-              robots_parse(&robots, urladr(), r.adr, r.size, infobuff,
-                           sizeof(infobuff), keep_root);
-              if (strnotempty(infobuff)) {
+              line[0] = '\0';
+              buff[0] = '\0';
+              infobuff[0] = '\0';
+              //
+#if DEBUG_ROBOTS
+              printf("robots.txt dump:\n%s\n", r.adr);
+#endif
+              do {
+                char *comm;
+                int llen;
+
+                bptr += binput(r.adr + bptr, line, sizeof(line) - 2);
+                /* strip comment */
+                comm = strchr(line, '#');
+                if (comm != NULL) {
+                  *comm = '\0';
+                }
+                /* strip spaces */
+                llen = (int) strlen(line);
+                while(llen > 0 && is_realspace(line[llen - 1])) {
+                  line[llen - 1] = '\0';
+                  llen--;
+                }
+                if (strfield(line, "user-agent:")) {
+                  char *a;
+
+                  a = line + 11;
+                  while(is_realspace(*a))
+                    a++;        // sauter espace(s)
+                  if (*a == '*') {
+                    if (record != 2)
+                      record = 1;       // c pour nous
+                  } else if (strfield(a, "httrack") || strfield(a, "winhttrack")
+                             || strfield(a, "webhttrack")) {
+                    buff[0] = '\0';     // re-enregistrer
+                    infobuff[0] = '\0';
+                    record = 2; // locked
+#if DEBUG_ROBOTS
+                    printf("explicit disallow for httrack\n");
+#endif
+                  } else
+                    record = 0;
+                } else if (record) {
+                  if (strfield(line, "disallow:")) {
+                    char *a = line + 9;
+
+                    while(is_realspace(*a))
+                      a++;      // sauter espace(s)
+                    if (strnotempty(a)) {
+#ifdef IGNORE_RESTRICTIVE_ROBOTS
+                      if (strcmp(a, "/") != 0 ||
+                          opt->robots >= HTS_ROBOTS_ALWAYS_STRICT)
+#endif
+                      { /* ignoring disallow: / */
+                        if ((strlen(buff) + strlen(a) + 8) < sizeof(buff)) {
+                          strcatbuff(buff, a);
+                          strcatbuff(buff, "\n");
+                          if ((strlen(infobuff) + strlen(a) + 8) <
+                              sizeof(infobuff)) {
+                            if (strnotempty(infobuff))
+                              strcatbuff(infobuff, ", ");
+                            strcatbuff(infobuff, a);
+                          }
+                        }
+                      }
+#ifdef IGNORE_RESTRICTIVE_ROBOTS
+                      else {
+                        hts_log_print(opt, LOG_NOTICE,
+                                      "Note: %s robots.txt rules are too restrictive, ignoring /",
+                                      urladr());
+                      }
+#endif
+                    }
+                  }
+                }
+              } while((bptr < r.size) && (strlen(buff) < (sizeof(buff) - 32)));
+              if (strnotempty(buff)) {
+                checkrobots_set(&robots, urladr(), buff);
                 hts_log_print(opt, LOG_INFO,
                               "Note: robots.txt forbidden links for %s are: %s",
                               urladr(), infobuff);
@@ -2121,8 +2116,7 @@ int httpmirror(char *url1, httrackp * opt) {
   /*
      Ensure the index is being closed
    */
-  hts_finish_makeindex(opt, &makeindex_done, &makeindex_fp, makeindex_links,
-                       makeindex_firstlink, template_footer, "", "");
+  HT_INDEX_END;
 
   /* 
      updating-a-remotely-deteted-website hack

src/htscore.h

@@ -362,20 +362,6 @@ void usercommand(httrackp * opt, int exe, const char *cmd, const char *file,
 
 void usercommand_exe(const char *cmd, const char *file);
 
-// Finish the makeindex index.html (footer + refresh meta), run usercommand.
-// Updates *makeindex_done/*makeindex_fp in place; adr/fil are the mode strings.
-void hts_finish_makeindex(httrackp *opt, int *makeindex_done,
-                          FILE **makeindex_fp, int makeindex_links,
-                          const char *makeindex_firstlink,
-                          const char *template_footer, const char *adr,
-                          const char *fil);
-
-// Flush ht_buff[0..ht_len] to save on disk (skip if MD5 unchanged); *fp
-// closed+NULLed on write. Precondition: ht_len>0.
-void hts_finish_html_file(httrackp *opt, cache_back *cache, htsblk *r,
-                          FILE **fp, const char *ht_buff, size_t ht_len,
-                          const char *adr, const char *fil, const char *save);
-
 int filters_init(char ***ptrfilters, int maxfilter, int filterinc);
 
 int fspc(httrackp * opt, FILE * fp, const char *type);
@@ -484,8 +470,4 @@ void voidf(void);
 /* HTML marker comment marking where the top index is spliced. */
 #define HTS_TOPINDEX "TOP_INDEX_HTTRACK"
 
-/* Worst-case byte expansion HT_ADD_HTMLESCAPED* must reserve per escaper. */
-#define HTS_HTMLESCAPE_MAXEXP 5      /* escape_for_html_print: '&'->"&" */
-#define HTS_HTMLESCAPE_FULL_MAXEXP 6 /* _full: high byte->"&#xHH;" */
-
 #endif

src/htslib.c

@@ -4131,32 +4131,24 @@ DECLARE_APPEND_ESCAPE_VERSION(escape_uri)
 
 #undef DECLARE_APPEND_ESCAPE_VERSION
 
-// In-place escaping: copy dest aside, then escape that copy back into dest.
-typedef size_t (*escape_fn_t)(const char *src, char *dest, size_t size);
-
-static size_t inplace_escape(char *const dest, const size_t size,
-                             escape_fn_t escape) {
-  char buffer[256];
-  const size_t len = strnlen(dest, size);
-  const int in_buffer = len + 1 < sizeof(buffer);
-  char *src = in_buffer ? buffer : malloct(len + 1);
-  size_t ret;
-  assertf(src != NULL);
-  assertf(len < size);
-  memcpy(src, dest, len + 1);
-  ret = escape(src, dest, size);
-  if (!in_buffer) {
-    freet(src);
-  }
-  return ret;
-}
-
-// Thin exported wrappers binding inplace_escape() to each escaper (ABI).
+// Same as above, but in-place
 #undef DECLARE_INPLACE_ESCAPE_VERSION
-#define DECLARE_INPLACE_ESCAPE_VERSION(NAME)                                   \
-  HTSEXT_API size_t inplace_##NAME(char *const dest, const size_t size) {      \
-    return inplace_escape(dest, size, NAME);                                   \
-  }
+#define DECLARE_INPLACE_ESCAPE_VERSION(NAME) \
+HTSEXT_API size_t inplace_ ##NAME(char *const dest, const size_t size) { \
+  char buffer[256]; \
+  const size_t len = strnlen(dest, size); \
+  const int in_buffer = len + 1 < sizeof(buffer); \
+  char *src = in_buffer ? buffer : malloct(len + 1); \
+  size_t ret; \
+  assertf(src != NULL); \
+  assertf(len < size); \
+  memcpy(src, dest, len + 1); \
+  ret = NAME(src, dest, size); \
+  if (!in_buffer) { \
+    freet(src); \
+  } \
+  return ret; \
+}
 
 DECLARE_INPLACE_ESCAPE_VERSION(escape_in_url)
 DECLARE_INPLACE_ESCAPE_VERSION(escape_spc_url)

src/htsparse.c

@@ -77,14 +77,13 @@ Please visit our Website: http://www.httrack.com
 /** Append to the output buffer the string 'A'. **/
 #define HT_ADD(A) TypedArrayAppend(output_buffer, A, strlen(A))
 
-/* clang-format off: an edit realigns all backslashes, churning the macro. */
-/* clang-format off */
-/** Append 'A' to the output buffer, html-escaped; FACTOR = max byte expansion. **/
-#define HT_ADD_HTMLESCAPED_ANY(A, FUNCTION, FACTOR) do { \
+/** Append to the output buffer the string 'A', html-escaped. **/
+#define HT_ADD_HTMLESCAPED_ANY(A, FUNCTION) do { \
   if ((opt->getmode & 1) != 0 && ptr>0) { \
     const char *const str_ = (A); \
     size_t size_; \
-    TypedArrayEnsureRoom(output_buffer, strlen(str_) * (FACTOR) + 1024); \
+    /* & is the maximum expansion */ \
+    TypedArrayEnsureRoom(output_buffer, strlen(str_) * 5 + 1024); \
     size_ = FUNCTION(str_, &TypedArrayTail(output_buffer), \
                      TypedArrayRoom(output_buffer)); \
     TypedArraySize(output_buffer) += size_; \
@@ -92,113 +91,188 @@ Please visit our Website: http://www.httrack.com
 } while(0)
 
 /** Append to the output buffer the string 'A', html-escaped for &. **/
-#define HT_ADD_HTMLESCAPED(A) \
-  HT_ADD_HTMLESCAPED_ANY(A, escape_for_html_print, HTS_HTMLESCAPE_MAXEXP)
+#define HT_ADD_HTMLESCAPED(A) HT_ADD_HTMLESCAPED_ANY(A, escape_for_html_print)
 
 /**
- * Append to the output buffer the string 'A', html-escaped for & and
+ * Append to the output buffer the string 'A', html-escaped for & and 
  * high chars.
  **/
-#define HT_ADD_HTMLESCAPED_FULL(A) \
-  HT_ADD_HTMLESCAPED_ANY(A, escape_for_html_print_full, HTS_HTMLESCAPE_FULL_MAXEXP)
-/* clang-format on */
+#define HT_ADD_HTMLESCAPED_FULL(A) HT_ADD_HTMLESCAPED_ANY(A, escape_for_html_print_full)
 
 // does nothing
 #define XH_uninit do {} while(0)
 
+#define HT_ADD_END { \
+  int ok=0;\
+  if (TypedArraySize(output_buffer) != 0) { \
+    const size_t ht_len = TypedArraySize(output_buffer); \
+    const char *const ht_buff = TypedArrayElts(output_buffer); \
+    char digest[32+2];\
+    off_t fsize_old = fsize(fconv(OPT_GET_BUFF(opt),OPT_GET_BUFF_SIZE(opt),savename()));\
+    digest[0] = '\0';\
+    domd5mem(TypedArrayElts(output_buffer), ht_len, digest, 1);\
+    if (fsize_old == (off_t) ht_len) { \
+      int mlen = 0;\
+      char* mbuff;\
+      cache_readdata(cache,"//[HTML-MD5]//",savename(),&mbuff,&mlen);\
+      if (mlen) \
+        mbuff[mlen]='\0';\
+      if ((mlen == 32) && (strcmp(((mbuff!=NULL)?mbuff:""),digest)==0)) {\
+        ok=1;\
+        hts_log_print(opt, LOG_DEBUG, "File not re-written (md5): %s",savename());\
+      } else {\
+        ok=0;\
+      } \
+    }\
+    if (!ok) { \
+      file_notify(opt,urladr(), urlfil(), savename(), 1, 1, r->notmodified); \
+      fp=filecreate(&opt->state.strc, savename()); \
+      if (fp) { \
+        if (ht_len>0) {\
+        if (fwrite(ht_buff,1,ht_len,fp) != ht_len) { \
+          int fcheck;\
+          if ((fcheck=check_fatal_io_errno())) {\
+            opt->state.exit_xh=-1;\
+          }\
+          if (opt->log) {   \
+            hts_log_print(opt, LOG_ERROR | LOG_ERRNO, "Unable to write HTML file %s", savename());\
+            if (fcheck) {\
+              hts_log_print(opt, LOG_ERROR, "* * Fatal write error, giving up");\
+            }\
+          }\
+        }\
+        }\
+        fclose(fp); fp=NULL; \
+        if (strnotempty(r->lastmodified)) \
+        set_filetime_rfc822(savename(),r->lastmodified); \
+      } else {\
+        int fcheck;\
+        if ((fcheck=check_fatal_io_errno())) {\
+  				hts_log_print(opt, LOG_ERROR, "Mirror aborted: disk full or filesystem problems"); \
+          opt->state.exit_xh=-1;\
+        }\
+        hts_log_print(opt, LOG_ERROR | LOG_ERRNO, "Unable to save file %s", savename());\
+        if (fcheck) {\
+          hts_log_print(opt, LOG_ERROR, "* * Fatal write error, giving up");\
+        }\
+      }\
+    } else {\
+      file_notify(opt,urladr(), urlfil(), savename(), 0, 0, r->notmodified); \
+      filenote(&opt->state.strc, savename(),NULL); \
+    }\
+    if (cache->ndx)\
+      cache_writedata(cache->ndx,cache->dat,"//[HTML-MD5]//",savename(),digest,(int)strlen(digest));\
+  } \
+  TypedArrayFree(output_buffer); \
+}
 #define HT_ADD_FOP
 
-/* Mutable extended-context fields: one source of truth so the DEFINE/SET/SAVE
-   load and store lists can't drift apart. */
-/* clang-format off */
-#define ENGINE_MUTABLE_FIELDS(X) \
-  X(int, error, stre->error_) \
-  X(int, store_errpage, stre->store_errpage_) \
-  X(int, makeindex_done, stre->makeindex_done_) \
-  X(FILE *, makeindex_fp, stre->makeindex_fp_) \
-  X(int, makeindex_links, stre->makeindex_links_) \
-  X(LLint, stat_fragment, stre->stat_fragment_)
-
-#define ENGINE_FIELD_DECLARE(type, name, src) type name = *(src);
-#define ENGINE_FIELD_LOAD(type, name, src) name = *(src);
-#define ENGINE_FIELD_STORE(type, name, src) *(src) = name;
+// COPY IN HTSCORE.C
+#define HT_INDEX_END do { \
+  if (!makeindex_done) { \
+  if (makeindex_fp) { \
+  char BIGSTK tempo[1024]; \
+  if (makeindex_links == 1) { \
+  char BIGSTK link_escaped[HTS_URLMAXSIZE*2]; \
+  escape_uri_utf(makeindex_firstlink, link_escaped, sizeof(link_escaped)); \
+  snprintf(tempo,sizeof(tempo),"<meta HTTP-EQUIV=\"Refresh\" CONTENT=\"0; URL=%s\">"CRLF,link_escaped); \
+  } else \
+  tempo[0]='\0'; \
+  hts_template_format(makeindex_fp,template_footer, \
+  "<!-- Mirror and index made by HTTrack Website Copier/"HTTRACK_VERSION" "HTTRACK_AFF_AUTHORS" -->", \
+  tempo, /* EOF */ NULL \
+  ); \
+  fflush(makeindex_fp); \
+  fclose(makeindex_fp);  /* à ne pas oublier sinon on passe une nuit blanche */  \
+  makeindex_fp=NULL; \
+  usercommand(opt,0,NULL,fconcat(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt),  StringBuff(opt->path_html_utf8),"index.html"),"primary","primary");  \
+  } \
+  } \
+  makeindex_done=1;    /* ok c'est fait */  \
+} while(0)
 
 #define ENGINE_DEFINE_CONTEXT() \
   ENGINE_DEFINE_CONTEXT_BASE(); \
+  /* */ \
   htsblk* const r HTS_UNUSED = stre->r_; \
   hash_struct* const hash HTS_UNUSED = stre->hash_; \
   char* const codebase HTS_UNUSED = stre->codebase; \
   char* const base HTS_UNUSED = stre->base; \
+  /* */ \
   const char * const template_header HTS_UNUSED = stre->template_header_; \
   const char * const template_body HTS_UNUSED = stre->template_body_; \
   const char * const template_footer HTS_UNUSED = stre->template_footer_; \
+  /* */ \
   HTS_UNUSED char* const makeindex_firstlink = stre->makeindex_firstlink_; \
-  ENGINE_MUTABLE_FIELDS(ENGINE_FIELD_DECLARE) \
-  /* load-once (kept out of SET/SAVE): re-reading would reset the throttle */ \
+  /* */ \
+  /* */ \
+  int error = * stre->error_; \
+  int store_errpage = * stre->store_errpage_; \
+  /* */ \
+  int makeindex_done = *stre->makeindex_done_; \
+  FILE* makeindex_fp = *stre->makeindex_fp_; \
+  int makeindex_links = *stre->makeindex_links_; \
+  /* */ \
+  LLint stat_fragment = *stre->stat_fragment_; \
   HTS_UNUSED TStamp makestat_time = stre->makestat_time; \
   HTS_UNUSED FILE* makestat_fp = stre->makestat_fp
 
 #define ENGINE_SET_CONTEXT() \
   ENGINE_SET_CONTEXT_BASE(); \
-  ENGINE_MUTABLE_FIELDS(ENGINE_FIELD_LOAD)
+  /* */ \
+  error = * stre->error_; \
+  store_errpage = * stre->store_errpage_; \
+  /* */ \
+  makeindex_done = *stre->makeindex_done_; \
+  makeindex_fp = *stre->makeindex_fp_; \
+  makeindex_links = *stre->makeindex_links_; \
+  /* */ \
+  stat_fragment = *stre->stat_fragment_; \
+  makestat_time = stre->makestat_time; \
+  makestat_fp = stre->makestat_fp
 
 #define ENGINE_LOAD_CONTEXT() \
   ENGINE_DEFINE_CONTEXT()
 
 #define ENGINE_SAVE_CONTEXT() \
   ENGINE_SAVE_CONTEXT_BASE(); \
-  ENGINE_MUTABLE_FIELDS(ENGINE_FIELD_STORE)
-/* clang-format on */
+  /* */ \
+  * stre->error_ = error; \
+  * stre->store_errpage_ = store_errpage; \
+  /* */ \
+  *stre->makeindex_done_ = makeindex_done; \
+  *stre->makeindex_fp_ = makeindex_fp; \
+  *stre->makeindex_links_ = makeindex_links; \
+  /* */ \
+  *stre->stat_fragment_ = stat_fragment
 
+#define _FILTERS     (*opt->filters.filters)
+#define _FILTERS_PTR (opt->filters.filptr)
 #define _ROBOTS      ((robots_wizard*)opt->robotsptr)
 
-/* JS-detection automaton states; INSCRIPT_DEFAULT is the synthetic "any other
-   char" column of the transition table. */
-typedef enum {
-  INSCRIPT_START = 0,
-  INSCRIPT_ANTISLASH,
-  INSCRIPT_INQUOTE,
-  INSCRIPT_INQUOTE2,
-  INSCRIPT_SLASH,
-  INSCRIPT_SLASHSLASH,
-  INSCRIPT_COMMENT,
-  INSCRIPT_COMMENT2,
-  INSCRIPT_ANTISLASH_IN_QUOTE,
-  INSCRIPT_ANTISLASH_IN_QUOTE2,
-  INSCRIPT_DEFAULT = 256
-} INSCRIPT;
+/* Apply current *adr character for the script automate */
+#define AUTOMATE_LOOKUP_CURRENT_ADR() do { \
+  if (inscript) { \
+  int new_state_pos; \
+  new_state_pos=inscript_state[inscript_state_pos][(unsigned char)*html]; \
+  if (new_state_pos < 0) { \
+  new_state_pos=inscript_state[inscript_state_pos][INSCRIPT_DEFAULT]; \
+  } \
+  assertf(new_state_pos >= 0); \
+  assertf(new_state_pos*sizeof(inscript_state[0]) < sizeof(inscript_state)); \
+  inscript_state_pos=new_state_pos; \
+  } \
+} while(0)
 
-#define INSCRIPT_NSTATES 10 /* rows in the transition table */
-
-/* Live view of the parser's automaton locals, set up once so the helpers below
-   can drive it without capturing them by lexical scope. */
-typedef struct {
-  const int *inscript;             /* nonzero while inside a script body */
-  const signed char (*table)[257]; /* [INSCRIPT_NSTATES][257] transitions */
-  INSCRIPT *pos;                   /* current state */
-  const char **html;               /* parse cursor */
-} script_automate;
-
-/* Feed the current *html byte to the automaton. No-op outside a script body. */
-static void hts_automate_lookup(const script_automate *aut) {
-  if (*aut->inscript) {
-    int next = aut->table[*aut->pos][(unsigned char) **aut->html];
-    if (next < 0) {
-      next = aut->table[*aut->pos][INSCRIPT_DEFAULT];
-    }
-    assertf(next >= 0 && next < INSCRIPT_NSTATES);
-    *aut->pos = (INSCRIPT) next;
-  }
-}
-
-/* Advance the cursor by 'steps' bytes, feeding each to the automaton. */
-static void hts_automate_increment(const script_automate *aut, int steps) {
-  while (steps > 0) {
-    (*aut->html)++;
-    hts_automate_lookup(aut);
-    steps--;
-  }
-}
+/* Increment current pointer to 'steps' characters, modifying automate if necessary */
+#define INCREMENT_CURRENT_ADR(steps) do { \
+  int steps__ = (int) ( steps ); \
+  while(steps__ > 0) { \
+  html++; \
+  AUTOMATE_LOOKUP_CURRENT_ADR(); \
+  steps__ --; \
+  } \
+} while(0)
 
 /* Percent-encode the angle brackets of a string so it is safe to embed inside
    an HTML comment (the default footer) or any other HTML context. A URL holding
@@ -343,7 +417,20 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
       int incomment = 0;        // dans un <!--
       int inscript = 0;         // dans un scipt pour applets javascript)
       int inscript_locked = 0;  // in locked script (ie. js file)
-      signed char inscript_state[INSCRIPT_NSTATES][257];
+      signed char inscript_state[10][257];
+      typedef enum {
+        INSCRIPT_START = 0,
+        INSCRIPT_ANTISLASH,
+        INSCRIPT_INQUOTE,
+        INSCRIPT_INQUOTE2,
+        INSCRIPT_SLASH,
+        INSCRIPT_SLASHSLASH,
+        INSCRIPT_COMMENT,
+        INSCRIPT_COMMENT2,
+        INSCRIPT_ANTISLASH_IN_QUOTE,
+        INSCRIPT_ANTISLASH_IN_QUOTE2,
+        INSCRIPT_DEFAULT = 256
+      } INSCRIPT;
       INSCRIPT inscript_state_pos = INSCRIPT_START;
       const char *inscript_name = NULL;       // script tag name
       int inscript_tag = 0;     // on est dans un <body onLoad="... terminé par >
@@ -404,8 +491,6 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
       inscript_state[INSCRIPT_COMMENT2]['*'] = INSCRIPT_COMMENT2;
       inscript_state[INSCRIPT_ANTISLASH_IN_QUOTE][INSCRIPT_DEFAULT] = INSCRIPT_INQUOTE; /* #8: escape in '' */
       inscript_state[INSCRIPT_ANTISLASH_IN_QUOTE2][INSCRIPT_DEFAULT] = INSCRIPT_INQUOTE2;       /* #9: escape in "" */
-      const script_automate saut = {&inscript, inscript_state,
-                                    &inscript_state_pos, &html};
 
       /* Primary list or URLs */
       if (ptr == 0) {
@@ -624,9 +709,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
               }
 
             } else if (heap(ptr)->depth < opt->depth) {        // on a sauté level1+1 et level1
-              hts_finish_makeindex(opt, &makeindex_done, &makeindex_fp,
-                                   makeindex_links, makeindex_firstlink,
-                                   template_footer, "primary", "primary");
+              HT_INDEX_END;
             }
           }                     // if (opt->makeindex)
         }
@@ -844,7 +927,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
             }
 
             /* automate */
-            hts_automate_lookup(&saut);
+            AUTOMATE_LOOKUP_CURRENT_ADR();
 
             // Note:
             // Certaines pages ne respectent pas le html
@@ -1760,7 +1843,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
             }
             // sauter espaces
             // adr+=p;
-            hts_automate_increment(&saut, p);
+            INCREMENT_CURRENT_ADR(p);
             while((is_space(*html)
                    || (inscriptgen && html[0] == '\\' && is_space(html[1])
                    )
@@ -1775,7 +1858,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                 }
               // puis quitter
               // html++;    // sauter les espaces, "" et cie
-              hts_automate_increment(&saut, 1);
+              INCREMENT_CURRENT_ADR(1);
             }
 
             /* Stop at \n (LF) if primary links or link lists */
@@ -1790,7 +1873,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
               if (*html == '\\') {
                 if ((*(html + 1) == '\'') || (*(html + 1) == '"')) {      // \" ou \'
                   // html+=2;    // sauter
-                  hts_automate_increment(&saut, 2);
+                  INCREMENT_CURRENT_ADR(2);
                 }
               }
             }
@@ -1838,7 +1921,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
             if (srcset_p) {
               while(html < r->adr + r->size
                     && (is_realspace(*html) || *html == ','))
-                hts_automate_increment(&saut, 1);
+                INCREMENT_CURRENT_ADR(1);
             }
             eadr = html;
 
@@ -3298,7 +3381,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
 
             assertf(eadr - html >= 0);   // Should not go back
             if (eadr > html) {
-              hts_automate_increment(&saut, (int) (eadr - 1 - html));
+              INCREMENT_CURRENT_ADR(eadr - 1 - html);
             }
             // adr=eadr-1;  // ** sauter
 
@@ -3317,8 +3400,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                   q++;          // skip whitespace and empty candidates
                 if (q < endp && *q != '\0' && *q != ',' && *q != quote
                     && *q != '<' && *q != '>' && (unsigned char) *q >= 32) {
-                  hts_automate_increment(
-                      &saut, (int) (q - html)); // keep the automate in sync
+                  INCREMENT_CURRENT_ADR(q - html);   // keep the automate in sync
                   ok = 1;
                   goto srcset_next;
                 }
@@ -3458,12 +3540,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
         }
 
         /* Flush and save to disk */
-        if (TypedArraySize(output_buffer) != 0) {
-          hts_finish_html_file(
-              opt, cache, r, &fp, TypedArrayElts(output_buffer),
-              TypedArraySize(output_buffer), urladr(), urlfil(), savename());
-        }
-        TypedArrayFree(output_buffer);
+        HT_ADD_END;             // achever
       }
       //
       //
@@ -3488,24 +3565,6 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
   return 0;
 }
 
-/* Mirror the savename to tell whether a redirect saves to the same file (#159);
- * contract in htsparse.h. */
-hts_boolean hts_redirect_same_savefile(httrackp *opt, const char *cur_adr,
-                                       const char *cur_fil,
-                                       const char *moved_adr,
-                                       const char *moved_fil) {
-  const int norm_slash = opt->urlhack && !opt->no_slash_dedup;
-  const int norm_query = opt->urlhack && !opt->no_query_dedup;
-  char BIGSTK n_fil[HTS_URLMAXSIZE * 2], pn_fil[HTS_URLMAXSIZE * 2];
-
-  if (strcasecmp(jump_identification_const(moved_adr),
-                 jump_identification_const(cur_adr)) != 0)
-    return HTS_FALSE;
-  fil_normalized_filtered_ex(moved_fil, n_fil, NULL, norm_slash, norm_query);
-  fil_normalized_filtered_ex(cur_fil, pn_fil, NULL, norm_slash, norm_query);
-  return strcasecmp(n_fil, pn_fil) == 0;
-}
-
 /*
 Check 301, 302, .. statuscodes (moved)
 */
@@ -3551,9 +3610,36 @@ int hts_mirror_check_moved(htsmoduleStruct * str,
         if ((reponse =
              ident_url_relatif(mov_url, urladr(), urlfil(), moved)) >= 0) {
           int set_prio_to = 0;  // pas de priotité fixéd par wizard
-          // A same-file alias redirect must be followed, not stubbed (#159).
-          const hts_boolean same_savefile = hts_redirect_same_savefile(
-              opt, urladr(), urlfil(), moved->adr, moved->fil);
+
+          // check whether URLHack is harmless or not (per the effective
+          // sub-flags)
+          if (opt->urlhack && (!opt->no_www_dedup || !opt->no_slash_dedup ||
+                               !opt->no_query_dedup)) {
+            const int norm_host = !opt->no_www_dedup;
+            const int norm_slash = !opt->no_slash_dedup;
+            const int norm_query = !opt->no_query_dedup;
+            char BIGSTK n_adr[HTS_URLMAXSIZE * 2], n_fil[HTS_URLMAXSIZE * 2];
+            char BIGSTK pn_adr[HTS_URLMAXSIZE * 2], pn_fil[HTS_URLMAXSIZE * 2];
+
+            strlcpybuff(n_adr,
+                        norm_host ? jump_normalized_const(moved->adr)
+                                  : jump_identification_const(moved->adr),
+                        sizeof(n_adr));
+            strlcpybuff(pn_adr,
+                        norm_host ? jump_normalized_const(urladr())
+                                  : jump_identification_const(urladr()),
+                        sizeof(pn_adr));
+            fil_normalized_filtered_ex(moved->fil, n_fil, NULL, norm_slash,
+                                       norm_query);
+            fil_normalized_filtered_ex(urlfil(), pn_fil, NULL, norm_slash,
+                                       norm_query);
+            if (strcasecmp(n_adr, pn_adr) == 0
+                && strcasecmp(n_fil, pn_fil) == 0) {
+              hts_log_print(opt, LOG_WARNING,
+                            "Redirected link is identical because of 'URL Hack' option: %s%s and %s%s",
+                            urladr(), urlfil(), moved->adr, moved->fil);
+            }
+          }
           //if (ident_url_absolute(mov_url,moved->adr,moved->fil)!=-1) {    // ok URL reconnue
           // c'est (en gros) la même URL..
           // si c'est un problème de casse dans le host c'est que le serveur est buggé
@@ -3581,17 +3667,7 @@ int hts_mirror_check_moved(htsmoduleStruct * str,
                 hts_log_print(opt, LOG_DEBUG, "moved link accepted: %s%s",
                               moved->adr, moved->fil);
               }
-            } else if (same_savefile) {
-              // A stub would point at itself; follow the redirect instead.
-              if (hts_acceptlink(opt, ptr, moved->adr, moved->fil, NULL, NULL,
-                                 &set_prio_to, NULL) != 1) {
-                get_it = 1;
-                hts_log_print(opt, LOG_WARNING,
-                              "Redirect to a same-file alias, fetching real "
-                              "content: %s%s -> %s%s",
-                              urladr(), urlfil(), moved->adr, moved->fil);
-              }
-            } /* sinon traité normalement */
+            }                   /* sinon traité normalement */
           }
 
           //if ((strfield2(moved->adr,urladr())!=0) && (strfield2(moved->fil,urlfil())!=0)) {  // identique à casse près
@@ -3614,11 +3690,7 @@ int hts_mirror_check_moved(htsmoduleStruct * str,
                    heap(heap(ptr)->precedent)->adr,
                    heap(heap(ptr)->precedent)->fil, opt,
                    sback, cache, hash, ptr, numero_passe, NULL) != -1) {
-                // Same-file alias: the reserved name is the invalidated source,
-                // so record anyway.
-                if (same_savefile ||
-                    hash_read(hash, savedmoved.save, NULL,
-                              HASH_STRUCT_FILENAME) < 0) { // n'existe pas déja
+                if (hash_read(hash, savedmoved.save, NULL, HASH_STRUCT_FILENAME) < 0) {   // n'existe pas déja
                   // enregistrer lien avec SAV IDENTIQUE
                   if (hts_record_link(opt, moved->adr, moved->fil, heap(ptr)->sav, "", "", NULL)) {
                     // mode test?
@@ -3642,6 +3714,7 @@ int hts_mirror_check_moved(htsmoduleStruct * str,
                                 "moving %s to an existing file %s",
                                 heap(ptr)->fil, urlfil());
                 }
+
               }
             }
 

src/htsparse.h

@@ -116,19 +116,6 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre);
 int hts_mirror_check_moved(htsmoduleStruct * str,
                            htsmoduleStructExtended * stre);
 
-/*
-  Non-zero if a redirect (cur_adr,cur_fil)->(moved_adr,moved_fil) saves to the
-  same local file, so it must be followed rather than turned into a
-  self-pointing "moved" stub (#159). Mirrors the savename: scheme+userinfo
-  stripped, www kept (www dedup is the crawl layer's job), path
-  slash/query-normalized per the URL-hack flags. Not hash_url_equals: that keys
-  on the dedup hash, which folds www and never collapses http<->https.
-*/
-hts_boolean hts_redirect_same_savefile(httrackp *opt, const char *cur_adr,
-                                       const char *cur_fil,
-                                       const char *moved_adr,
-                                       const char *moved_fil);
-
 /*
   Process user intercations: pause, add link, delete link..
 */

src/htsrobots.c

@@ -44,84 +44,28 @@ Please visit our Website: http://www.httrack.com
 
 // -- robots --
 
-/* RFC 9309 path-prefix match; '*' any run, '$' anchors end; linear. */
-static hts_boolean robots_pattern_match(const char *pattern, const char *path) {
-  size_t patlen = strlen(pattern);
-  hts_boolean anchored = HTS_FALSE;
-  const char *p, *pend, *s;
-  const char *star = NULL, *star_s = NULL;
-
-  if (patlen > 0 && pattern[patlen - 1] == '$') {
-    anchored = HTS_TRUE;
-    patlen--;
-  }
-  p = pattern;
-  pend = pattern + patlen;
-  s = path;
-  while (*s != '\0') {
-    if (p == pend) {
-      if (!anchored)
-        return HTS_TRUE;  // prefix matched
-      if (star != NULL) { // anchored: '*' must eat the rest
-        p = star + 1;
-        s = ++star_s;
-        continue;
-      }
-      return HTS_FALSE;
-    }
-    if (*p == '*') {
-      star = p++;
-      star_s = s;
-    } else if (*p == *s) {
-      p++;
-      s++;
-    } else if (star != NULL) {
-      p = star + 1;
-      s = ++star_s;
-    } else {
-      return HTS_FALSE;
-    }
-  }
-  while (p < pend && *p == '*')
-    p++;
-  return (p == pend) ? HTS_TRUE : HTS_FALSE;
-}
-
 // fil="" : vérifier si règle déja enregistrée
 int checkrobots(robots_wizard * robots, const char *adr, const char *fil) {
   while(robots) {
     if (strfield2(robots->adr, adr)) {
       if (fil[0]) {
-        /* RFC 9309: longest pattern wins, Allow beats Disallow on ties. */
         int ptr = 0;
-        char line[HTS_ROBOTS_TOKEN_SIZE];
-        size_t toklen = strlen(robots->token);
-        size_t best_len = 0;
-        hts_boolean matched = HTS_FALSE;
-        hts_boolean best_allow = HTS_FALSE;
+        char line[250];
 
-        while (ptr < (int) toklen) {
-          ptr += binput(robots->token + ptr, line, sizeof(line) - 1);
-          if (line[0] != 'A' && line[0] != 'D')
-            continue;
-          {
-            const hts_boolean is_allow =
-                (line[0] == 'A') ? HTS_TRUE : HTS_FALSE;
-            const char *pat = line + 1;
-
-            if (robots_pattern_match(pat, fil)) {
-              const size_t len = strlen(pat);
-
-              if (!matched || len > best_len || (len == best_len && is_allow)) {
-                matched = HTS_TRUE;
-                best_len = len;
-                best_allow = is_allow;
+        if (strnotempty(robots->token)) {
+          do {
+            ptr += binput(robots->token + ptr, line, 200);
+            if (line[0] == '/') {       // absolu
+              if (strfield(fil, line)) {        // commence avec ligne
+                return -1;      // interdit
+              }
+            } else {            // relatif
+              if (strstrcase(fil, line)) {
+                return -1;
               }
             }
-          }
+          } while((strnotempty(line)) && (ptr < (int) strlen(robots->token)));
         }
-        if (matched && !best_allow)
-          return -1; // forbidden
       } else {
         return -1;
       }
@@ -130,93 +74,6 @@ int checkrobots(robots_wizard * robots, const char *adr, const char *fil) {
   }
   return 0;
 }
-
-/* Append "<marker><pattern>\n" to the bounded rule blob if it fits. */
-static void robots_blob_add(char *blob, size_t blobsize, char marker,
-                            const char *pat) {
-  const size_t used = strlen(blob);
-  const size_t need = strlen(pat) + 2; // marker + '\n'
-
-  if (need < blobsize - used) { // overflow-safe: used <= blobsize-1
-    blob[used] = marker;
-    blob[used + 1] = '\0';
-    strlcatbuff(blob, pat, blobsize);
-    strlcatbuff(blob, "\n", blobsize);
-  }
-}
-
-void robots_parse(robots_wizard *robots, const char *adr, const char *body,
-                  size_t bodysize, char *info, size_t infosize,
-                  hts_boolean keep_root_disallow) {
-  size_t bptr = 0;
-  int record = 0;
-  char BIGSTK line[1024];
-  char BIGSTK blob[HTS_ROBOTS_TOKEN_SIZE];
-
-  blob[0] = '\0';
-  if (info != NULL && infosize > 0)
-    info[0] = '\0';
-#if DEBUG_ROBOTS
-  printf("robots.txt dump:\n%s\n", body);
-#endif
-  while (bptr < bodysize) {
-    char *comm;
-    int llen;
-
-    bptr += binput(body + bptr, line, sizeof(line) - 2);
-    comm = strchr(line, '#'); // strip comment
-    if (comm != NULL)
-      *comm = '\0';
-    llen = (int) strlen(line); // strip trailing spaces
-    while (llen > 0 && is_realspace(line[llen - 1])) {
-      line[llen - 1] = '\0';
-      llen--;
-    }
-    if (strfield(line, "user-agent:")) {
-      char *a = line + 11;
-
-      while (is_realspace(*a))
-        a++;
-      if (*a == '*') {
-        if (record != 2)
-          record = 1; // generic group applies to us
-      } else if (strfield(a, "httrack") || strfield(a, "winhttrack") ||
-                 strfield(a, "webhttrack")) {
-        blob[0] = '\0'; // explicit group: restart capture
-        if (info != NULL && infosize > 0)
-          info[0] = '\0';
-        record = 2; // locked to the httrack group
-      } else
-        record = 0;
-    } else if (record) {
-      hts_boolean is_allow = strfield(line, "allow:");
-      hts_boolean is_disallow = !is_allow && strfield(line, "disallow:");
-
-      if (is_allow || is_disallow) {
-        char *a = line + (is_allow ? 6 : 9);
-
-        while (is_realspace(*a))
-          a++;
-        if (strnotempty(a)) {
-          if (is_disallow && !keep_root_disallow && strcmp(a, "/") == 0) {
-            // dropped: site-wide disallow ignored by option
-          } else {
-            robots_blob_add(blob, sizeof(blob), is_allow ? 'A' : 'D', a);
-            if (is_disallow && info != NULL &&
-                strlen(a) + 2 < infosize - strlen(info)) {
-              if (strnotempty(info))
-                strlcatbuff(info, ", ", infosize);
-              strlcatbuff(info, a, infosize);
-            }
-          }
-        }
-      }
-    }
-  }
-  if (strnotempty(blob))
-    checkrobots_set(robots, adr, blob);
-}
-
 int checkrobots_set(robots_wizard * robots, const char *adr, const char *data) {
   if (((int) strlen(adr)) >= sizeof(robots->adr) - 2)
     return 0;

src/htsrobots.h

@@ -39,27 +39,17 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DEF_FWSTRUCT_robots_wizard
 typedef struct robots_wizard robots_wizard;
 #endif
-
-/* Per-host blob: one rule per line, first byte 'A'/'D' then path pattern. */
-#define HTS_ROBOTS_TOKEN_SIZE 4096
-
 struct robots_wizard {
   char adr[128];
-  char token[HTS_ROBOTS_TOKEN_SIZE];
+  char token[4096];
   struct robots_wizard *next;
 };
 
 /* Library internal definictions */
 #ifdef HTS_INTERNAL_BYTECODE
-/* -1 if `fil` disallowed for `adr` (RFC 9309); empty: -1 if rules exist. */
 int checkrobots(robots_wizard * robots, const char *adr, const char *fil);
 void checkrobots_free(robots_wizard * robots);
 int checkrobots_set(robots_wizard * robots, const char *adr, const char *data);
-/* Parse robots.txt `body` for `adr`, storing the HTTrack group's rules; `info`
-   gets a disallow summary, `keep_root_disallow` FALSE drops "Disallow: /". */
-void robots_parse(robots_wizard *robots, const char *adr, const char *body,
-                  size_t bodysize, char *info, size_t infosize,
-                  hts_boolean keep_root_disallow);
 #endif
 
 #endif

src/htsselftest.c

@@ -45,7 +45,6 @@ Please visit our Website: http://www.httrack.com
 #include "htscore.h"
 #include "htsdefines.h"
 #include "htslib.h"
-#include "htsparse.h"
 #include "htscache_selftest.h"
 #include "htsdns_selftest.h"
 #include "htscharset.h"
@@ -525,41 +524,6 @@ static int string_safety_selftests(void) {
       return 1;
   }
 
-  /* StringCatN/StringSetLength must eval SIZE once: (n_eval++, V) leaves
-     n_eval == 2 on a double-eval macro. */
-  {
-    String s = STRING_EMPTY;
-    int n_eval = 0;
-
-    StringCat(s, "hello");
-    StringCatN(s, "world", (n_eval++, 3)); /* strlen>SIZE so the clamp runs */
-    if (n_eval != 1 || strcmp(StringBuff(s), "hellowor") != 0) {
-      StringFree(s);
-      return 1;
-    }
-
-    n_eval = 0;
-    StringSetLength(s, (n_eval++, 5));
-    if (n_eval != 1 || StringLength(s) != 5) {
-      StringFree(s);
-      return 1;
-    }
-    StringFree(s);
-  }
-
-  /* StringSubRW still reads/writes after dropping its duplicate definition. */
-  {
-    String s = STRING_EMPTY;
-
-    StringCat(s, "abc");
-    StringSubRW(s, 1) = 'X';
-    if (StringSub(s, 1) != 'X' || strcmp(StringBuff(s), "aXc") != 0) {
-      StringFree(s);
-      return 1;
-    }
-    StringFree(s);
-  }
-
   return 0;
 }
 
@@ -1341,165 +1305,6 @@ static int st_urlhack(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-/* #159: hts_redirect_same_savefile decides whether a redirect is a same-file
- * alias. */
-static int st_redirect_samefile(httrackp *opt, int argc, char **argv) {
-  (void) argc;
-  (void) argv;
-#define SAME(aa, fa, ab, fb) hts_redirect_same_savefile(opt, aa, fa, ab, fb)
-  /* scheme and userinfo collapse (the #159 case); a different path does not */
-  assertf(SAME("http://foo.com", "/a/b", "https://foo.com", "/a/b"));
-  assertf(SAME("http://user@foo.com", "/a", "http://foo.com", "/a"));
-  assertf(!SAME("http://foo.com", "/a", "http://foo.com", "/b"));
-  /* www stays distinct here; the crawl's dedup layer folds www, not this helper
-   */
-  opt->urlhack = HTS_TRUE;
-  opt->no_www_dedup = opt->no_slash_dedup = opt->no_query_dedup = HTS_FALSE;
-  assertf(!SAME("http://www.foo.com", "/a", "http://foo.com", "/a"));
-  /* slash/query fold only when the dedup flag is on */
-  assertf(SAME("https://foo.com", "/a//b", "http://foo.com", "/a/b"));
-  assertf(
-      SAME("https://foo.com", "/p?b=2&a=1", "http://foo.com", "/p?a=1&b=2"));
-  opt->no_slash_dedup = opt->no_query_dedup = HTS_TRUE;
-  assertf(!SAME("https://foo.com", "/a//b", "http://foo.com", "/a/b"));
-  assertf(
-      !SAME("https://foo.com", "/p?b=2&a=1", "http://foo.com", "/p?a=1&b=2"));
-  /* but a pure scheme alias still collapses regardless of dedup opt-outs */
-  assertf(SAME("http://foo.com", "/a/b", "https://foo.com", "/a/b"));
-  opt->no_slash_dedup = opt->no_query_dedup = HTS_FALSE;
-#undef SAME
-  printf("redirect-samefile self-test OK\n");
-  return 0;
-}
-
-// hts_finish_makeindex writes the footer, emits the refresh meta only when
-// makeindex_links==1, and clears *fp / sets *done. argv[0] is a writable dir.
-static int st_makeindex(httrackp *opt, int argc, char **argv) {
-  char path[HTS_URLMAXSIZE];
-  char buf[4096];
-  FILE *fp;
-  size_t n;
-  int done;
-
-  assertf(argc >= 1);
-  snprintf(path, sizeof(path), "%s/index.html", argv[0]);
-
-  /* single first link: footer + a refresh meta carrying the escaped URL */
-  done = 0;
-  fp = fopen(path, "wb");
-  assertf(fp != NULL);
-  hts_finish_makeindex(opt, &done, &fp, 1, "http://example.com/a b", "%s%s", "",
-                       "");
-  assertf(fp == NULL); /* the function closed and cleared it */
-  assertf(done != 0);
-  fp = fopen(path, "rb");
-  assertf(fp != NULL);
-  n = fread(buf, 1, sizeof(buf) - 1, fp);
-  fclose(fp);
-  buf[n] = '\0';
-  assertf(strstr(buf, "Mirror and index made by HTTrack") != NULL);
-  assertf(strstr(buf, "Refresh") != NULL);
-  assertf(strstr(buf, "example.com") != NULL);
-
-  /* no single link: footer only, no refresh meta */
-  done = 0;
-  fp = fopen(path, "wb");
-  assertf(fp != NULL);
-  hts_finish_makeindex(opt, &done, &fp, 0, NULL, "%s%s", "", "");
-  assertf(fp == NULL);
-  assertf(done != 0);
-  fp = fopen(path, "rb");
-  assertf(fp != NULL);
-  n = fread(buf, 1, sizeof(buf) - 1, fp);
-  fclose(fp);
-  buf[n] = '\0';
-  assertf(strstr(buf, "Mirror and index made by HTTrack") != NULL);
-  assertf(strstr(buf, "Refresh") == NULL);
-
-  UNLINK(path);
-  printf("makeindex self-test OK\n");
-  return 0;
-}
-
-/* Each inplace_escape_*() must equal escape_*() on a copy. */
-static int st_inplace_escape(httrackp *opt, int argc, char **argv) {
-  /* >255 bytes forces the helper's malloct path, not the stack buffer */
-  static char longstr[600];
-  static const char *const samples[] = {
-      "",          "abc",           "a b/c?d=e&f", "h\x8ello w\x94rld",
-      "a%b\"c<d>", "/path to/file", longstr};
-  static size_t (*const inplace[])(char *, size_t) = {
-      inplace_escape_in_url, inplace_escape_spc_url, inplace_escape_uri_utf,
-      inplace_escape_check_url, inplace_escape_uri};
-  static size_t (*const plain[])(const char *, char *, size_t) = {
-      escape_in_url, escape_spc_url, escape_uri_utf, escape_check_url,
-      escape_uri};
-  size_t i, f;
-
-  (void) opt;
-  (void) argc;
-  (void) argv;
-
-  memset(longstr, 'a', sizeof(longstr) - 1);
-  for (f = 0; f < sizeof(inplace) / sizeof(inplace[0]); f++) {
-    for (i = 0; i < sizeof(samples) / sizeof(samples[0]); i++) {
-      char ref[4096], work[4096];
-      size_t rret, iret;
-      rret = plain[f](samples[i], ref, sizeof(ref));
-      strcpybuff(work, samples[i]);
-      iret = inplace[f](work, sizeof(work));
-      assertf(iret == rret);
-      assertf(strcmp(work, ref) == 0);
-    }
-  }
-  printf("inplace-escape self-test OK\n");
-  return 0;
-}
-
-/* Pin HTS_HTMLESCAPE*_MAXEXP to each escaper's true max byte expansion. */
-static int st_escape_room(httrackp *opt, int argc, char **argv) {
-  /* N > 1023: where 6n outgrows the old 5n+1024 reservation */
-  enum { N = 2000 };
-
-  char *src = malloct(N + 1);
-  char *dst;
-  size_t room, got;
-  (void) opt;
-  (void) argc;
-  (void) argv;
-
-  /* _full worst case: a high byte expands to "&#xHH;" (6 bytes) */
-  memset(src, 0xE9, N);
-  src[N] = '\0';
-  room = (size_t) N * HTS_HTMLESCAPE_FULL_MAXEXP + 1024;
-  dst = malloct(room);
-  got = escape_for_html_print_full(src, dst, room);
-  assertf(got == (size_t) N * HTS_HTMLESCAPE_FULL_MAXEXP);
-  assertf(strlen(dst) == got);
-  freet(dst);
-
-  /* one factor short overflows (returns size), truncating the page: the bug */
-  room = (size_t) N * (HTS_HTMLESCAPE_FULL_MAXEXP - 1) + 1024;
-  dst = malloct(room);
-  got = escape_for_html_print_full(src, dst, room);
-  assertf(got == room);
-  freet(dst);
-
-  /* plain escaper worst case: '&' -> "&amp;" (5); high bytes stay verbatim */
-  memset(src, '&', N);
-  src[N] = '\0';
-  room = (size_t) N * HTS_HTMLESCAPE_MAXEXP + 1024;
-  dst = malloct(room);
-  got = escape_for_html_print(src, dst, room);
-  assertf(got == (size_t) N * HTS_HTMLESCAPE_MAXEXP);
-  assertf(strlen(dst) == got);
-  freet(dst);
-
-  freet(src);
-  printf("escape-room self-test OK\n");
-  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);
@@ -1686,89 +1491,6 @@ static int st_acceptencoding(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
-/* Each call parses `txt` under a fresh host, then checkrobots() for `path`. */
-static int rb_decide(robots_wizard *r, const char *txt, const char *path) {
-  static int n = 0;
-  char host[64];
-
-  snprintf(host, sizeof(host), "h%d.example", n++);
-  robots_parse(r, host, txt, strlen(txt), NULL, 0, HTS_TRUE);
-  return checkrobots(r, host, path);
-}
-
-static int st_robots(httrackp *opt, int argc, char **argv) {
-  robots_wizard robots;
-  (void) opt;
-  (void) argc;
-  (void) argv;
-  memset(&robots, 0, sizeof(robots));
-
-  /* Longer Allow re-opens subtree under Disallow: / (old matcher couldn't). */
-  {
-    const char *txt = "User-agent: *\nDisallow: /\nAllow: /public/\n";
-
-    assertf(rb_decide(&robots, txt, "/public/x") == 0); /* allowed */
-    assertf(rb_decide(&robots, txt, "/private") == -1); /* denied */
-    assertf(rb_decide(&robots, txt, "/") == -1);        /* denied */
-  }
-
-  /* Equal-length match: Allow wins the tie over Disallow. */
-  {
-    const char *txt = "User-agent: *\nDisallow: /foo\nAllow: /foo\n";
-
-    assertf(rb_decide(&robots, txt, "/foo/bar") == 0);
-  }
-
-  /* Longest match wins even when it is not the last rule. */
-  {
-    assertf(rb_decide(&robots, "User-agent: *\nDisallow: /a/b\nAllow: /a\n",
-                      "/a/b/c") == -1);
-    assertf(rb_decide(&robots, "User-agent: *\nAllow: /a/b\nDisallow: /a\n",
-                      "/a/b/c") == 0);
-  }
-
-  /* '*' matches any run of characters. */
-  {
-    const char *txt = "User-agent: *\nDisallow: /*.php\n";
-
-    assertf(rb_decide(&robots, txt, "/a/b/index.php") == -1);
-    assertf(rb_decide(&robots, txt, "/a/b/index.html") == 0);
-  }
-
-  /* Trailing '$' anchors the end of the path. */
-  {
-    const char *txt = "User-agent: *\nDisallow: /a$\n";
-
-    assertf(rb_decide(&robots, txt, "/a") == -1);
-    assertf(rb_decide(&robots, txt, "/ab") == 0);
-    assertf(rb_decide(&robots, txt, "/a/b") == 0);
-  }
-
-  /* The httrack-specific group replaces the generic '*' group entirely. */
-  {
-    const char *txt = "User-agent: *\nDisallow: /everyone\n"
-                      "User-agent: httrack\nDisallow: /\n";
-
-    assertf(rb_decide(&robots, txt, "/anything") == -1);
-  }
-
-  /* Replace, not merge: the generic group does not bind the httrack group. */
-  {
-    const char *txt = "User-agent: *\nDisallow: /x\n"
-                      "User-agent: httrack\nDisallow: /y\n";
-
-    assertf(rb_decide(&robots, txt, "/x") == 0);
-    assertf(rb_decide(&robots, txt, "/y") == -1);
-  }
-
-  /* No rules: everything is allowed. */
-  assertf(rb_decide(&robots, "User-agent: *\nDisallow:\n", "/x") == 0);
-
-  checkrobots_free(&robots);
-  printf("robots self-test OK\n");
-  return 0;
-}
-
 /* ------------------------------------------------------------ */
 /* Registry: name -> handler, with a usage hint and a one-line description. */
 /* ------------------------------------------------------------ */
@@ -1789,8 +1511,6 @@ static const struct selftest_entry {
      st_stripquery},
     {"urlhack", "", "-%u url-hack sub-flag (www/slash/query) self-test",
      st_urlhack},
-    {"redirect-samefile", "", "same-file redirect detection self-test (#159)",
-     st_redirect_samefile},
     {"mime", "<filename>", "MIME type for a filename", st_mime},
     {"charset", "<charset> <string>",
      "convert a string to UTF-8 from a charset", st_charset},
@@ -1818,17 +1538,9 @@ static const struct selftest_entry {
     {"dns", "", "DNS resolver/cache self-test", st_dns},
     {"cookies", "", "cookie request-header self-test", st_cookies},
     {"useragent", "", "default User-Agent self-test", st_useragent},
-    {"makeindex", "[dir]", "hts_finish_makeindex footer/refresh self-test",
-     st_makeindex},
-    {"inplace-escape", "", "inplace_escape_* vs escape_* equivalence self-test",
-     st_inplace_escape},
-    {"escape-room", "", "HT_ADD_HTMLESCAPED* reservation-factor self-test",
-     st_escape_room},
     {"status", "", "HTTP status code -> reason phrase self-test", st_status},
     {"acceptencoding", "[dir]",
      "Accept-Encoding advertises gzip+deflate, both decode", st_acceptencoding},
-    {"robots", "", "robots.txt RFC 9309 Allow/Disallow precedence self-test",
-     st_robots},
 };
 
 static void list_selftests(void) {

src/htsstrings.h

@@ -121,6 +121,9 @@ struct String {
 /** Byte at POS (read/write). No bounds check; POS must be < StringLength. **/
 #define StringSubRW(BLK, POS) (StringBuffRW(BLK)[POS])
 
+/** Subcharacter (read/write) **/
+#define StringSubRW(BLK, POS) (StringBuffRW(BLK)[POS])
+
 /** Byte POS positions from the end (read). POS==1 is the last byte. **/
 #define StringRight(BLK, POS) (StringBuff(BLK)[StringLength(BLK) - POS])
 
@@ -188,9 +191,8 @@ HTS_STATIC char *StringBuffN_(String *blk, int size) {
     asserts SIZE fits the existing content; does not (re)allocate. **/
 #define StringSetLength(BLK, SIZE)                                             \
   do {                                                                         \
-    const int len__ = (SIZE); /* signed: negative means strlen(buffer_) */     \
-    if (len__ >= 0) {                                                          \
-      (BLK).length_ = len__;                                                   \
+    if (SIZE >= 0) {                                                           \
+      (BLK).length_ = SIZE;                                                    \
     } else {                                                                   \
       (BLK).length_ = strlen((BLK).buffer_);                                   \
     }                                                                          \
@@ -306,11 +308,10 @@ HTS_STATIC void StringAttach(String *blk, char **str) {
 #define StringCatN(BLK, STR, SIZE)                                             \
   do {                                                                         \
     const char *str__ = (STR);                                                 \
-    const size_t usize__ = (SIZE);                                             \
     if (str__ != NULL) {                                                       \
       size_t size__ = strlen(str__);                                           \
-      if (size__ > usize__) {                                                  \
-        size__ = usize__;                                                      \
+      if (size__ > (SIZE)) {                                                   \
+        size__ = (SIZE);                                                       \
       }                                                                        \
       StringMemcat(BLK, str__, size__);                                        \
     }                                                                          \

tests/01_engine-escape-room.test

@@ -1,7 +0,0 @@
-#!/bin/bash
-#
-
-set -euo pipefail
-
-# HT_ADD_HTMLESCAPED* must reserve the escaper's worst case (6 for _full).
-httrack -O /dev/null -#test=escape-room run | grep -q "escape-room self-test OK"

tests/01_engine-inplace-escape.test

@@ -1,7 +0,0 @@
-#!/bin/bash
-#
-
-set -euo pipefail
-
-# inplace_escape_*() must match escape_*() on a copy: guards the shared helper.
-httrack -O /dev/null -#test=inplace-escape run | grep -q "inplace-escape self-test OK"

tests/01_engine-makeindex.test

@@ -1,12 +0,0 @@
-#!/bin/bash
-#
-
-set -euo pipefail
-
-# hts_finish_makeindex writes the footer and gates the refresh meta on a single
-# first link (guards the macro->function extraction).
-dir=$(mktemp -d)
-trap 'rm -rf "$dir"' EXIT
-
-httrack -O /dev/null -#test=makeindex "$dir" run |
-    grep -q "makeindex self-test OK"

tests/01_engine-redirect.test

@@ -1,9 +0,0 @@
-#!/bin/bash
-#
-
-set -euo pipefail
-
-# #159: a redirect to a same-file alias (http<->https, user@host, ..) must be
-# followed through, not turned into a self-pointing "moved" stub. The decision
-# helper is exercised by the engine self-test.
-httrack -O /dev/null -#test=redirect-samefile run | grep -q "redirect-samefile self-test OK"

tests/01_engine-robots.test

@@ -1,7 +0,0 @@
-#!/bin/bash
-#
-
-set -euo pipefail
-
-# robots.txt RFC 9309 Allow/Disallow precedence (#452): longest match wins.
-httrack -O /dev/null -#test=robots run | grep -q "robots self-test OK"

tests/19_local-connect-fallback.test

@@ -20,14 +20,6 @@ if ! command -v python3 >/dev/null 2>&1; then
     echo "python3 missing, skipping"
     exit 77
 fi
-# The fixture needs a second loopback IP (dead 127.0.0.2 + live 127.0.0.1) for
-# the fallback to have a target; GNU/Hurd has only 127.0.0.1, so skip there.
-case "$(uname -s)" in
-GNU | GNU/*)
-    echo "GNU/Hurd: single loopback IP, connect-fallback fixture unbuildable, skipping"
-    exit 77
-    ;;
-esac
 
 server="$top_srcdir/tests/local-server.py"
 root="$top_srcdir/tests/server-root"

tests/30_local-fragment-link.test

@@ -1,13 +0,0 @@
-#!/bin/bash
-# Issue #279: an anchored link (target.html#sec, quoted or bare) fetches the
-# target with the fragment dropped (strict server 400s on a '#' in the request)
-# but keeps it in the rewritten local link so the anchor still works.
-set -e
-
-: "${top_srcdir:=..}"
-
-bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
-    --found 'fraglink/target.html' \
-    --file-matches 'fraglink/index.html' 'href=target\.html#sec' \
-    --file-matches 'fraglink/index.html' 'href="target\.html#sec2"' \
-    httrack 'BASEURL/fraglink/index.html'

tests/Makefile.am

@@ -6,7 +6,6 @@ EXTRA_DIST = $(TESTS) crawl-test.sh run-all-tests.sh check-network.sh \
 	local-crawl.sh local-server.py server.crt server.key \
 	server-root/simple/basic.html server-root/simple/link.html \
 	server-root/stripquery/index.html server-root/stripquery/a.html \
-	server-root/fraglink/index.html server-root/fraglink/target.html \
 	fixtures/cache-golden/hts-cache/new.zip
 
 TESTS_ENVIRONMENT =
@@ -37,16 +36,11 @@ TESTS = \
 	01_engine-filter.test \
 	01_engine-hashtable.test \
 	01_engine-idna.test \
-	01_engine-escape-room.test \
-	01_engine-inplace-escape.test \
-	01_engine-makeindex.test \
 	01_engine-mime.test \
 	01_engine-parse.test \
 	01_engine-pause.test \
 	01_engine-rcfile.test \
-	01_engine-redirect.test \
 	01_engine-relative.test \
-	01_engine-robots.test \
 	01_engine-savename.test \
 	01_engine-selftest-dispatch.test \
 	01_engine-simplify.test \
@@ -85,7 +79,6 @@ TESTS = \
 	26_local-strip-query.test \
 	27_local-cookies-file.test \
 	28_local-pause.test \
-	29_local-redirect-fragment.test \
-	30_local-fragment-link.test
+	29_local-redirect-fragment.test
 
 CLEANFILES = check-network_sh.cache

tests/local-crawl.sh

@@ -15,11 +15,8 @@
 #   bash local-crawl.sh [--tls] [--root DIR] [--cookie NAME=VALUE ...] \
 #       --errors N --files N --found PATH ... --directory PATH ... \
 #       --log-found REGEX ... --log-not-found REGEX ... \
-#       --file-matches PATH REGEX ... --file-not-matches PATH REGEX ... \
 #       httrack BASEURL/some/path [httrack-args...]
 # --log-found/--log-not-found grep (ERE) the crawl's hts-log.txt.
-# --file-matches/--file-not-matches grep (ERE) a mirrored file (PATH under the
-# host root), to assert rewritten link/content survived the crawl.
 # --cookie writes a Netscape cookies.txt (scoped to the discovered host:port,
 # which the ephemeral port forces into the cookie domain) and passes it to
 # httrack via --cookies-file, to exercise preloaded cookies.
@@ -124,10 +121,6 @@ while test "$pos" -lt "$nargs"; do
         audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
         pos=$((pos + 1))
         ;;
-    --file-matches | --file-not-matches)
-        audit+=("${args[$pos]}" "${args[$((pos + 1))]}" "${args[$((pos + 2))]}")
-        pos=$((pos + 2))
-        ;;
     httrack)
         pos=$((pos + 1))
         break
@@ -301,24 +294,6 @@ while test "$i" -lt "${#audit[@]}"; do
             exit 1
         else result "OK"; fi
         ;;
-    --file-matches)
-        path="${audit[$((i + 1))]}"
-        i=$((i + 2))
-        info "checking ${path} matches ${audit[$i]}"
-        if grep -aqE "${audit[$i]}" "${hostroot}/${path}"; then result "OK"; else
-            result "no match"
-            exit 1
-        fi
-        ;;
-    --file-not-matches)
-        path="${audit[$((i + 1))]}"
-        i=$((i + 2))
-        info "checking ${path} lacks ${audit[$i]}"
-        if grep -aqE "${audit[$i]}" "${hostroot}/${path}"; then
-            result "matched"
-            exit 1
-        else result "OK"; fi
-        ;;
     esac
     i=$((i + 1))
 done

tests/server-root/fraglink/index.html

@@ -1,4 +0,0 @@
-<html><body>
-<a href=target.html#sec>unquoted fragment link</a>
-<a href="target.html#sec2">quoted fragment link</a>
-</body></html>

tests/server-root/fraglink/target.html

@@ -1 +0,0 @@
-<html><body><a name="sec"></a><a name="sec2"></a>target</body></html>