Fix macro-hygiene defects in htsstrings.h (dup define, double-eval)

StringSubRW was defined twice (the second under a redundant comment); drop
the duplicate. StringCatN and StringSetLength each evaluated their SIZE
argument twice, so a side-effecting argument would run twice and a wrapping
expression could clamp inconsistently. Capture SIZE once into a local, the
way StringCopyN already does. StringSetLength keeps a signed local so the
"negative means strlen(buffer_)" contract is preserved.

No current call site passes a side-effecting SIZE, so the change is
behavior-preserving; the strsafe self-test now passes a (counter++, V)
argument and asserts a single evaluation, which fails on the old macros.

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

src/htscore.c

@@ -406,40 +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;
-}
+
+#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) {
@@ -2055,8 +2044,7 @@ 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

@@ -362,14 +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);
-
 int filters_init(char ***ptrfilters, int maxfilter, int filterinc);
 
 int fspc(httrackp * opt, FILE * fp, const char *type);
@@ -478,8 +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_; \
@@ -92,22 +91,17 @@ 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)
 
-/* clang-format off: an edit realigns all backslashes, churning the macro. */
-/* clang-format off */
 #define HT_ADD_END { \
   int ok=0;\
   if (TypedArraySize(output_buffer) != 0) { \
@@ -129,7 +123,6 @@ Please visit our Website: http://www.httrack.com
       } else {\
         ok=0;\
       } \
-      freet(mbuff);\
     }\
     if (!ok) { \
       file_notify(opt,urladr(), urlfil(), savename(), 1, 1, r->notmodified); \
@@ -172,9 +165,32 @@ Please visit our Website: http://www.httrack.com
   } \
   TypedArrayFree(output_buffer); \
 }
-/* clang-format on */
 #define HT_ADD_FOP
 
+// 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(); \
   /* */ \
@@ -201,9 +217,6 @@ Please visit our Website: http://www.httrack.com
   HTS_UNUSED TStamp makestat_time = stre->makestat_time; \
   HTS_UNUSED FILE* makestat_fp = stre->makestat_fp
 
-/* clang-format off: an edit realigns all backslashes, churning the macro. */
-/* clang-format off */
-/* Load-once: re-reading resets makestat_time (mutated locally, never SAVEd). */
 #define ENGINE_SET_CONTEXT() \
   ENGINE_SET_CONTEXT_BASE(); \
   /* */ \
@@ -214,8 +227,9 @@ Please visit our Website: http://www.httrack.com
   makeindex_fp = *stre->makeindex_fp_; \
   makeindex_links = *stre->makeindex_links_; \
   /* */ \
-  stat_fragment = *stre->stat_fragment_
-/* clang-format on */
+  stat_fragment = *stre->stat_fragment_; \
+  makestat_time = stre->makestat_time; \
+  makestat_fp = stre->makestat_fp
 
 #define ENGINE_LOAD_CONTEXT() \
   ENGINE_DEFINE_CONTEXT()
@@ -695,9 +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)
         }

src/htsselftest.c

@@ -1340,134 +1340,6 @@ static int st_urlhack(httrackp *opt, int argc, char **argv) {
   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);
@@ -1784,12 +1656,6 @@ 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},

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/Makefile.am

@@ -36,9 +36,6 @@ 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 \