htsparse: keep makestat_time out of ENGINE_SET_CONTEXT

makestat_time throttles the makestat/maketrack stats to once per minute:
the wait loop compares time_local() against it and, when it fires, writes
it back to the local. But the field is by-value in the extended context,
so it can't round-trip through ENGINE_SAVE_CONTEXT, while ENGINE_SET_CONTEXT
re-read it from the load-once baseline on every loop iteration. That reset
the local before the next compare, so under -%v / maketrack the throttle
never held and the stats line plus the full back-stack dump were emitted
every iteration.

Drop makestat_time (and the never-changing makestat_fp) from SET_CONTEXT;
they belong to the load-once set. Wrapped the macro in clang-format off/on
for the same backslash-realignment reason as HT_ADD_END.

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

src/htscore.h

@@ -478,4 +478,8 @@ 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. **/
+/* clang-format off: an edit realigns all backslashes, churning the macro. */
-#define HT_ADD_HTMLESCAPED_ANY(A, FUNCTION) do { \
+/* 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_) * (FACTOR) + 1024); \
-    TypedArrayEnsureRoom(output_buffer, strlen(str_) * 5 + 1024); \
     size_ = FUNCTION(str_, &TypedArrayTail(output_buffer), \
                      TypedArrayRoom(output_buffer)); \
     TypedArraySize(output_buffer) += size_; \
@@ -91,17 +92,22 @@ 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)
 
+/* 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) { \
@@ -123,6 +129,7 @@ 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); \
@@ -165,6 +172,7 @@ Please visit our Website: http://www.httrack.com
   } \
   TypedArrayFree(output_buffer); \
 }
+/* clang-format on */
 #define HT_ADD_FOP
 
 #define ENGINE_DEFINE_CONTEXT() \
@@ -193,6 +201,9 @@ 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(); \
   /* */ \
@@ -203,9 +214,8 @@ Please visit our Website: http://www.httrack.com
   makeindex_fp = *stre->makeindex_fp_; \
   makeindex_links = *stre->makeindex_links_; \
   /* */ \
-  stat_fragment = *stre->stat_fragment_; \
+  stat_fragment = *stre->stat_fragment_
-  makestat_time = stre->makestat_time; \
+/* clang-format on */
-  makestat_fp = stre->makestat_fp
 
 #define ENGINE_LOAD_CONTEXT() \
   ENGINE_DEFINE_CONTEXT()

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/Makefile.am

@@ -36,6 +36,7 @@ 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 \