Replace duplicated HT_INDEX_END macro with a shared function

The macro that closes the makeindex index.html (footer, optional refresh meta, then the user "primary" command) was copy-pasted into htsparse.c and htscore.c, flagged by a `// COPY IN HTSCORE.C` comment and drifting in whitespace. Collapse both into hts_finish_makeindex() in htscore.c, declared in htscore.h.

The two copies were not byte-identical: the final usercommand() call passed "primary","primary" from htsparse.c but "","" from htscore.c. The helper takes those as adr/fil parameters so each call site keeps its exact behavior.

Add a -#test=makeindex self-test (driven by 01_engine-makeindex.test) that drives the function offline and asserts the footer is written, the refresh meta appears only for a single first link, and *fp/*done are updated.

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

src/htscore.h

@@ -478,8 +478,4 @@ 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); \
@@ -172,7 +165,6 @@ Please visit our Website: http://www.httrack.com
   } \
   TypedArrayFree(output_buffer); \
 }
-/* clang-format on */
 #define HT_ADD_FOP
 
 #define ENGINE_DEFINE_CONTEXT() \
@@ -201,9 +193,6 @@ 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 +203,9 @@ 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()

src/htsselftest.c

@@ -524,41 +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;
 }
 
@@ -1389,85 +1354,6 @@ static int st_makeindex(httrackp *opt, int argc, char **argv) {
   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);
@@ -1786,10 +1672,6 @@ static const struct selftest_entry {
     {"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},

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/Makefile.am

@@ -36,8 +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 \