tests: cover anchored-link (#frag) rewriting (#279) (#470)

An anchored hyperlink target.html#sec must fetch the target with the
fragment dropped yet keep the fragment in the rewritten local link so
the anchor still resolves. This already works; #279 is a stale
report from the Google Code era with no current repro.

Pin the behavior with a local-crawl test: the strict server 400s on a
'#' in the request-target (so a leaked fragment fails the fetch), and a
new --file-matches audit asserts the mirrored link keeps #sec/#sec2 for
both the unquoted and quoted forms.

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

debian/control

@@ -1,9 +1,8 @@
 Source: httrack
 Section: web
-Priority: optional
 Maintainer: Xavier Roche <roche@httrack.com>
 Standards-Version: 4.7.4
-Build-Depends: debhelper-compat (= 13), autoconf, autoconf-archive, automake, libtool, zlib1g-dev, libssl-dev
+Build-Depends: debhelper-compat (= 14), 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

@@ -1,4 +1,6 @@
-httrack source: changelog-should-mention-nmu
+# 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: source-nmu-has-incorrect-version-number
 
 # The bundled HTML pages are the genuine upstream documentation taken from

debian/upstream/metadata

@@ -0,0 +1,6 @@
+---
+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

@@ -441,6 +441,72 @@ void hts_finish_makeindex(httrackp *opt, int *makeindex_done,
   *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));
+}
+
 /* does it look like XML ? (SVG et al.) */
 static int look_like_xml(const char *s) {
   return strncmp(s, "<?xml", 5) == 0

src/htscore.h

@@ -370,6 +370,12 @@ void hts_finish_makeindex(httrackp *opt, int *makeindex_done,
                           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);
@@ -478,4 +484,8 @@ 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/htsparse.c

@@ -77,13 +77,14 @@ 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))
 
-/** Append to the output buffer the string 'A', html-escaped. **/
-#define HT_ADD_HTMLESCAPED_ANY(A, FUNCTION) do { \
+/* 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 { \
   if ((opt->getmode & 1) != 0 && ptr>0) { \
     const char *const str_ = (A); \
     size_t size_; \
-    /* & is the maximum expansion */ \
-    TypedArrayEnsureRoom(output_buffer, strlen(str_) * 5 + 1024); \
+    TypedArrayEnsureRoom(output_buffer, strlen(str_) * (FACTOR) + 1024); \
     size_ = FUNCTION(str_, &TypedArrayTail(output_buffer), \
                      TypedArrayRoom(output_buffer)); \
     TypedArraySize(output_buffer) += size_; \
@@ -91,164 +92,113 @@ 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)
+#define HT_ADD_HTMLESCAPED(A) \
+  HT_ADD_HTMLESCAPED_ANY(A, escape_for_html_print, HTS_HTMLESCAPE_MAXEXP)
 
 /**
- * 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)
+#define HT_ADD_HTMLESCAPED_FULL(A) \
+  HT_ADD_HTMLESCAPED_ANY(A, escape_for_html_print_full, HTS_HTMLESCAPE_FULL_MAXEXP)
+/* clang-format on */
 
 // 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;
+
 #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_; \
-  /* */ \
-  /* */ \
-  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_; \
+  ENGINE_MUTABLE_FIELDS(ENGINE_FIELD_DECLARE) \
+  /* load-once (kept out of SET/SAVE): re-reading would reset the throttle */ \
   HTS_UNUSED TStamp makestat_time = stre->makestat_time; \
   HTS_UNUSED FILE* makestat_fp = stre->makestat_fp
 
 #define ENGINE_SET_CONTEXT() \
   ENGINE_SET_CONTEXT_BASE(); \
-  /* */ \
-  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
+  ENGINE_MUTABLE_FIELDS(ENGINE_FIELD_LOAD)
 
 #define ENGINE_LOAD_CONTEXT() \
   ENGINE_DEFINE_CONTEXT()
 
 #define ENGINE_SAVE_CONTEXT() \
   ENGINE_SAVE_CONTEXT_BASE(); \
-  /* */ \
-  * 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
+  ENGINE_MUTABLE_FIELDS(ENGINE_FIELD_STORE)
+/* clang-format on */
 
-#define _FILTERS     (*opt->filters.filters)
-#define _FILTERS_PTR (opt->filters.filptr)
 #define _ROBOTS      ((robots_wizard*)opt->robotsptr)
 
-/* 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)
+/* 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;
 
-/* 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)
+#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--;
+  }
+}
 
 /* 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
@@ -393,20 +343,7 @@ 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[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;
+      signed char inscript_state[INSCRIPT_NSTATES][257];
       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 >
@@ -467,6 +404,8 @@ 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) {
@@ -905,7 +844,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
             }
 
             /* automate */
-            AUTOMATE_LOOKUP_CURRENT_ADR();
+            hts_automate_lookup(&saut);
 
             // Note:
             // Certaines pages ne respectent pas le html
@@ -1821,7 +1760,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
             }
             // sauter espaces
             // adr+=p;
-            INCREMENT_CURRENT_ADR(p);
+            hts_automate_increment(&saut, p);
             while((is_space(*html)
                    || (inscriptgen && html[0] == '\\' && is_space(html[1])
                    )
@@ -1836,7 +1775,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
                 }
               // puis quitter
               // html++;    // sauter les espaces, "" et cie
-              INCREMENT_CURRENT_ADR(1);
+              hts_automate_increment(&saut, 1);
             }
 
             /* Stop at \n (LF) if primary links or link lists */
@@ -1851,7 +1790,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
               if (*html == '\\') {
                 if ((*(html + 1) == '\'') || (*(html + 1) == '"')) {      // \" ou \'
                   // html+=2;    // sauter
-                  INCREMENT_CURRENT_ADR(2);
+                  hts_automate_increment(&saut, 2);
                 }
               }
             }
@@ -1899,7 +1838,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
             if (srcset_p) {
               while(html < r->adr + r->size
                     && (is_realspace(*html) || *html == ','))
-                INCREMENT_CURRENT_ADR(1);
+                hts_automate_increment(&saut, 1);
             }
             eadr = html;
 
@@ -3359,7 +3298,7 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
 
             assertf(eadr - html >= 0);   // Should not go back
             if (eadr > html) {
-              INCREMENT_CURRENT_ADR(eadr - 1 - html);
+              hts_automate_increment(&saut, (int) (eadr - 1 - html));
             }
             // adr=eadr-1;  // ** sauter
 
@@ -3378,7 +3317,8 @@ 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) {
-                  INCREMENT_CURRENT_ADR(q - html);   // keep the automate in sync
+                  hts_automate_increment(
+                      &saut, (int) (q - html)); // keep the automate in sync
                   ok = 1;
                   goto srcset_next;
                 }
@@ -3518,7 +3458,12 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
         }
 
         /* Flush and save to disk */
-        HT_ADD_END;             // achever
+        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);
       }
       //
       //

src/htsselftest.c

@@ -1424,6 +1424,50 @@ static int st_inplace_escape(httrackp *opt, int argc, char **argv) {
   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: '&' -> "&" (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);
@@ -1744,6 +1788,8 @@ static const struct selftest_entry {
      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},

tests/01_engine-escape-room.test

@@ -0,0 +1,7 @@
+#!/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/30_local-fragment-link.test

@@ -0,0 +1,13 @@
+#!/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

@@ -6,6 +6,7 @@ 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 =
@@ -36,6 +37,7 @@ 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 \
@@ -82,6 +84,7 @@ TESTS = \
 	26_local-strip-query.test \
 	27_local-cookies-file.test \
 	28_local-pause.test \
-	29_local-redirect-fragment.test
+	29_local-redirect-fragment.test \
+	30_local-fragment-link.test
 
 CLEANFILES = check-network_sh.cache

tests/local-crawl.sh

@@ -15,8 +15,11 @@
 #   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.
@@ -121,6 +124,10 @@ 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=$((pos + 1))
         break
@@ -294,6 +301,24 @@ while test "$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

@@ -0,0 +1,4 @@
+<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

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