Fix one-byte fil[] overflow in ident_url_absolute on hostless ?-URLs

OSS-Fuzz caught an abort in ident_url_absolute: strncat_safe_'s bounds
check fired on a one-byte overflow of the 2048-byte fil[] path buffer.
URLs of 2048 bytes or more are rejected up front, so the path suffix is
at most 2047 bytes; but when it has no leading slash, one is prepended
before the copy, pushing the result to exactly 2048. A hostless URL
starting with '?' and 2047 bytes long reaches that copy before the
empty-host check at the end rejects it. Subtract the possible slash from
the limit and return -1 for those inputs, leaving valid URLs untouched.

The identabs self-test feeds the 2047-byte trigger and asserts a clean
-1, plus two valid URLs still parse.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

src/htslib.c

@@ -2575,6 +2575,11 @@ int ident_url_absolute(const char *url, lien_adrfil *adrfil) {
     // recopier adrfil->adresse www..
     strncatbuff(adrfil->adr, p, ((int) (q - p)));
     // *( adrfil->adr+( ((int) q) - ((int) p) ) )=0;  // faut arrêter la fumette!
+
+    // fil[] holds the path plus a possible leading '/' the top strlen() misses.
+    if (strlen(q) >= sizeof(adrfil->fil) - (q[0] != '/' ? 1 : 0))
+      return -1;
+
     // recopier chemin /pub/..
     if (q[0] != '/')            // page par défaut (/)
       strcatbuff(adrfil->fil, "/");

src/htsselftest.c

@@ -1266,6 +1266,30 @@ static int st_identurl(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* Regression for the one-byte fil[] overflow: a 2047-byte hostless "?"-URL used
+   to abort in strncat_safe_ when the missing leading '/' pushed fil to 2048. */
+static int st_identabs(httrackp *opt, int argc, char **argv) {
+  lien_adrfil af;
+  const size_t len =
+      sizeof(af.fil) - 1; /* 2047: max URL the top guard admits */
+  char *url = malloct(len + 1);
+
+  (void) opt;
+  (void) argc;
+  (void) argv;
+  url[0] = '?';
+  memset(url + 1, 'a', len - 1);
+  url[len] = '\0';
+  assertf(ident_url_absolute(url, &af) == -1);
+  freet(url);
+  /* valid URLs still parse, so the guard is not over-rejecting */
+  assertf(ident_url_absolute("http://www.example.com/a/b/c.html?x=1", &af) ==
+          0);
+  assertf(ident_url_absolute("www.foo.com?bar=1", &af) == 0);
+  printf("identabs self-test OK\n");
+  return 0;
+}
+
 /* Extra args are key=value: adr= cdispo= statuscode= status= strip= urlhack=
    no-www= no-slash= no-query= n83= type=, plus repeatable prior=adr|fil|sav
    registering an already-crawled link (dedup/collision paths). */
@@ -2567,6 +2591,8 @@ static const struct selftest_entry {
     {"resolve", "<link> <adr> <fil>", "resolve a link against an origin",
      st_resolve},
     {"identurl", "<url>", "split an absolute URL into (adr, fil)", st_identurl},
+    {"identabs", "", "ident_url_absolute one-byte fil[] overflow self-test",
+     st_identabs},
     {"header", "<raw-header-line> ...", "response header-line parsing",
      st_header},
     {"headerlong", "[header-name:]",

tests/01_engine-identabs.test

@@ -0,0 +1,8 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# A 2047-byte hostless "?"-URL used to overflow fil[] by one byte and abort in
+# strncat_safe_; the guard now returns -1 while valid URLs still parse.
+test "$(httrack -O /dev/null -#test=identabs)" == "identabs self-test OK" || exit 1

tests/Makefile.am

@@ -44,6 +44,7 @@ TESTS = \
 	01_engine-header.test \
 	01_engine-idna.test \
 	01_engine-identurl.test \
+	01_engine-identabs.test \
 	01_engine-escape-room.test \
 	01_engine-inplace-escape.test \
 	01_engine-java.test \