Collapse the 5 inplace_escape_* bodies into one shared helper (#464)

DECLARE_INPLACE_ESCAPE_VERSION stamped five byte-identical function
bodies, one per escaper. Move the body into a single static
inplace_escape() helper parameterized by a function pointer to the
underlying escape_*(); the five HTSEXT_API inplace_escape_* symbols
stay as thin wrappers, so the exported ABI is unchanged.

A new -#test=inplace-escape self-test asserts each inplace_escape_*()
equals its escape_*() applied to a copy across several samples
(including a >255-byte one to hit the helper's malloct path), guarding
the refactor.

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

src/htscore.c

@@ -406,29 +406,40 @@ void hts_invalidate_link(httrackp * opt, int lpos) {
   opt->liens[lpos]->pass2 = -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)
+// 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;
+}
 
 /* does it look like XML ? (SVG et al.) */
 static int look_like_xml(const char *s) {
@@ -2044,7 +2055,8 @@ int httpmirror(char *url1, httrackp * opt) {
   /*
      Ensure the index is being closed
    */
-  HT_INDEX_END;
+  hts_finish_makeindex(opt, &makeindex_done, &makeindex_fp, makeindex_links,
+                       makeindex_firstlink, template_footer, "", "");
 
   /* 
      updating-a-remotely-deteted-website hack

src/htscore.h

@@ -362,6 +362,14 @@ 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);

src/htslib.c

@@ -4131,25 +4131,33 @@ DECLARE_APPEND_ESCAPE_VERSION(escape_uri)
 
 #undef DECLARE_APPEND_ESCAPE_VERSION
 
-// 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) { \
-  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; \
+// 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).
+#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);                                   \
+  }
+
 DECLARE_INPLACE_ESCAPE_VERSION(escape_in_url)
 DECLARE_INPLACE_ESCAPE_VERSION(escape_spc_url)
 DECLARE_INPLACE_ESCAPE_VERSION(escape_uri_utf)

src/htsparse.c

@@ -167,30 +167,6 @@ Please visit our Website: http://www.httrack.com
 }
 #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(); \
   /* */ \
@@ -709,7 +685,9 @@ int htsparse(htsmoduleStruct * str, htsmoduleStructExtended * stre) {
               }
 
             } else if (heap(ptr)->depth < opt->depth) {        // on a sauté level1+1 et level1
-              HT_INDEX_END;
+              hts_finish_makeindex(opt, &makeindex_done, &makeindex_fp,
+                                   makeindex_links, makeindex_firstlink,
+                                   template_footer, "primary", "primary");
             }
           }                     // if (opt->makeindex)
         }

src/htsselftest.c

@@ -524,6 +524,41 @@ 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;
 }
 
@@ -1305,6 +1340,90 @@ 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;
+}
+
 /* 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);
@@ -1621,6 +1740,10 @@ 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},
     {"status", "", "HTTP status code -> reason phrase self-test", st_status},
     {"acceptencoding", "[dir]",
      "Accept-Encoding advertises gzip+deflate, both decode", st_acceptencoding},

src/htsstrings.h

@@ -121,9 +121,6 @@ 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])
 
@@ -191,8 +188,9 @@ HTS_STATIC char *StringBuffN_(String *blk, int size) {
     asserts SIZE fits the existing content; does not (re)allocate. **/
 #define StringSetLength(BLK, SIZE)                                             \
   do {                                                                         \
-    if (SIZE >= 0) {                                                           \
-      (BLK).length_ = SIZE;                                                    \
+    const int len__ = (SIZE); /* signed: negative means strlen(buffer_) */     \
+    if (len__ >= 0) {                                                          \
+      (BLK).length_ = len__;                                                   \
     } else {                                                                   \
       (BLK).length_ = strlen((BLK).buffer_);                                   \
     }                                                                          \
@@ -308,10 +306,11 @@ 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__ > (SIZE)) {                                                   \
-        size__ = (SIZE);                                                       \
+      if (size__ > usize__) {                                                  \
+        size__ = usize__;                                                      \
       }                                                                        \
       StringMemcat(BLK, str__, size__);                                        \
     }                                                                          \

tests/01_engine-inplace-escape.test

@@ -0,0 +1,7 @@
+#!/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

@@ -0,0 +1,12 @@
+#!/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/19_local-connect-fallback.test

@@ -20,6 +20,14 @@ 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/Makefile.am

@@ -36,6 +36,8 @@ TESTS = \
 	01_engine-filter.test \
 	01_engine-hashtable.test \
 	01_engine-idna.test \
+	01_engine-inplace-escape.test \
+	01_engine-makeindex.test \
 	01_engine-mime.test \
 	01_engine-parse.test \
 	01_engine-pause.test \