Add --why to explain which filter rule accepts or rejects a URL

The top user-confusion class is filters silently not doing what their
author expects. --why <url>, given the rest of the crawl command line,
prints the deciding rule ("rejected by rule #2 (-*.zip)") or reports
that no rule matches, then exits without crawling. It reuses the real
option parsing and filter seeding end to end, and evaluates through the
new fa_strjoker_dual(), which also replaces the two hand-rolled copies
of the dual-form verdict merge in htswizard.c.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>

.github/workflows/codeql.yml

@@ -1,57 +0,0 @@
-# CodeQL static analysis (C). The security-extended suite covers the classes
-# this codebase actually fights: overflows, tainted-size allocs, format bugs.
-name: CodeQL
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-  schedule:
-    # Weekly re-scan of master so new/updated queries land without a push.
-    - cron: "17 4 * * 1"
-
-permissions:
-  contents: read
-
-concurrency:
-  group: codeql-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  analyze:
-    name: analyze (c-cpp)
-    runs-on: ubuntu-24.04
-    permissions:
-      contents: read
-      # Upload findings to the repo's code-scanning dashboard.
-      security-events: write
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Install build dependencies
-        run: |
-          set -euo pipefail
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends \
-            build-essential autoconf automake libtool autoconf-archive \
-            zlib1g-dev libssl-dev
-
-      - uses: github/codeql-action/init@v4
-        with:
-          languages: c-cpp
-          build-mode: manual
-          queries: security-extended
-
-      # Manual build: CodeQL traces the compiler, so build exactly what ships.
-      - name: Build
-        run: |
-          set -euo pipefail
-          autoreconf -fi
-          ./configure
-          make -j"$(nproc)"
-
-      - uses: github/codeql-action/analyze@v4
-        with:
-          category: "/language:c-cpp"

man/httrack.1

@@ -3,7 +3,7 @@
 .\"
 .\" This file is generated by man/makeman.sh; do not edit by hand.
 .\" SPDX-License-Identifier: GPL-3.0-or-later
-.TH httrack 1 "27 June 2026" "httrack website copier"
+.TH httrack 1 "07 July 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -51,6 +51,7 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-%T, \-\-utf8\-conversion\fR ]
 [ \fB\-bN, \-\-cookies[=N]\fR ]
 [ \fB\-%K, \-\-cookies\-file\fR ]
+[ \fB\-%Y, \-\-why\fR ]
 [ \fB\-u, \-\-check\-type[=N]\fR ]
 [ \fB\-j, \-\-parse\-java[=N]\fR ]
 [ \fB\-sN, \-\-robots[=N]\fR ]
@@ -218,6 +219,8 @@ links conversion to UTF\-8 (\-\-utf8\-conversion)
 accept cookies in cookies.txt (0=do not accept,* 1=accept) (\-\-cookies[=N])
 .IP \-%K
 load extra cookies from a Netscape cookies.txt (\-\-cookies\-file <param>)
+.IP \-%Y
+explain which filter rule accepts or rejects a URL, then exit (\-\-why <param>)
 .IP \-u
 check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always) (\-\-check\-type[=N])
 .IP \-j

src/htsalias.c

@@ -114,6 +114,8 @@ const char *hts_optalias[][4] = {
    "strip [host/pattern=]key1,key2,... from URLs"},
   {"cookies-file", "-%K", "param1",
    "load extra cookies from a Netscape cookies.txt"},
+  {"why", "-%Y", "param1",
+   "explain which filter rule accepts or rejects a URL, then exit"},
   {"pause", "-%G", "param1",
    "random pause of MIN[:MAX] seconds between files"},
   {"generate-errors", "-o", "single", ""},

src/htscore.c

@@ -846,6 +846,52 @@ int httpmirror(char *url1, httrackp * opt) {
       }
     }                           // while
 
+    /* --why: print which filter rule decides for this URL, then stop */
+    if (StringNotEmpty(opt->why_url)) {
+      char BIGSTK url[HTS_URLMAXSIZE * 2];
+      lien_adrfil af;
+
+      if (strstr(StringBuff(opt->why_url), ":/") == NULL)
+        snprintf(url, sizeof(url), "http://%s", StringBuff(opt->why_url));
+      else
+        strcpybuff(url, StringBuff(opt->why_url));
+      if (ident_url_absolute(url, &af) < 0) {
+        printf("--why: unable to parse URL %s" LF, StringBuff(opt->why_url));
+      } else {
+        char BIGSTK l[HTS_URLMAXSIZE * 2], lfull[HTS_URLMAXSIZE * 2];
+        int jok, jokDepth = 0;
+
+        /* the two forms the wizard tests */
+        strcpybuff(l, jump_identification_const(af.adr));
+        if (*af.fil != '/')
+          strcatbuff(l, "/");
+        strcatbuff(l, af.fil);
+        if (!link_has_authority(af.adr))
+          strcpybuff(lfull, "http://");
+        else
+          lfull[0] = '\0';
+        strcatbuff(lfull, af.adr);
+        if (*af.fil != '/')
+          strcatbuff(lfull, "/");
+        strcatbuff(lfull, af.fil);
+        jok = fa_strjoker_dual(/*url */ 0, filters, filptr, lfull, l, NULL,
+                               NULL, &jokDepth);
+        if (jok > 0)
+          printf("%s: accepted by rule #%d (%s)" LF, url, jokDepth + 1,
+                 filters[jokDepth]);
+        else if (jok < 0)
+          printf("%s: rejected by rule #%d (%s)" LF, url, jokDepth + 1,
+                 filters[jokDepth]);
+        else
+          printf("%s: no filter rule matches; the wizard decides "
+                 "(same-site links are followed by default)" LF,
+                 url);
+      }
+      freet(primary);
+      XH_extuninit;
+      return 1;
+    }
+
     /* load URL file list */
     /* OPTIMIZED for fast load */
     if (StringNotEmpty(opt->filelist)) {

src/htscoremain.c

@@ -1803,6 +1803,23 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
                   StringCopy(opt->cookies_file, argv[na]);
                 }
                 break;
+              case 'Y': // why: explain the filter verdict for a URL, no crawl
+                if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
+                  HTS_PANIC_PRINTF("Option why needs a blank space and a URL");
+                  printf(
+                      "Example: --why \"http://www.example.com/file.zip\"\n");
+                  htsmain_free();
+                  return -1;
+                } else {
+                  na++;
+                  if (strlen(argv[na]) >= HTS_URLMAXSIZE) {
+                    HTS_PANIC_PRINTF("why URL too long");
+                    htsmain_free();
+                    return -1;
+                  }
+                  StringCopy(opt->why_url, argv[na]);
+                }
+                break;
               case 'G': // pause: randomized inter-file delay MIN[:MAX] seconds
                 if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
                   HTS_PANIC_PRINTF("Option pause needs a blank space and a "

src/htsfilters.c

@@ -94,6 +94,32 @@ int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * siz
   return verdict;
 }
 
+int fa_strjoker_dual(int type, char **filters, int nfil, const char *nom1,
+                     const char *nom2, LLint *size, int *size_flag,
+                     int *depth) {
+  int depth1 = 0, depth2 = 0;
+  int flag1 = 0, flag2 = 0;
+  LLint sz1 = 0, sz2 = 0;
+  int jok1, jok2, use1;
+
+  if (size) {
+    sz1 = *size;
+    sz2 = *size;
+  }
+  jok1 = fa_strjoker(type, filters, nfil, nom1, size ? &sz1 : NULL,
+                     size_flag ? &flag1 : NULL, &depth1);
+  jok2 = fa_strjoker(type, filters, nfil, nom2, size ? &sz2 : NULL,
+                     size_flag ? &flag2 : NULL, &depth2);
+  use1 = jok2 == 0 || (jok1 != 0 && depth1 >= depth2);
+  if (size)
+    *size = use1 ? sz1 : sz2;
+  if (size_flag)
+    *size_flag = use1 ? flag1 : flag2;
+  if (depth)
+    *depth = use1 ? depth1 : depth2;
+  return use1 ? jok1 : jok2;
+}
+
 // supercomparateur joker (tm)
 // compare a et b (b=avec joker dedans), case insensitive [voir CI]
 // renvoi l'adresse de la première lettre de la chaine

src/htsfilters.h

@@ -41,6 +41,11 @@ Please visit our Website: http://www.httrack.com
 
 int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * size,
                 int *size_flag, int *depth);
+/* fa_strjoker() on both URL forms the engine builds (nom1 full, nom2 without
+   scheme); the match latest in the list wins, a "don't know" verdict defers.
+   Returns the merged verdict; the out-params carry the winner's values. */
+int fa_strjoker_dual(int type, char **filters, int nfil, const char *nom1,
+                     const char *nom2, LLint *size, int *size_flag, int *depth);
 HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * size,
                           int *size_flag);
 const char *strjokerfind(const char *chaine, const char *joker);

src/htshelp.c

@@ -543,6 +543,7 @@ void help(const char *app, int more) {
   infomsg("Spider options:");
   infomsg("  bN accept cookies in cookies.txt (0=do not accept,* 1=accept)");
   infomsg(" %K  load extra cookies from a Netscape cookies.txt");
+  infomsg(" %Y  explain which filter rule accepts or rejects a URL, then exit");
   infomsg
     ("  u  check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always)");
   infomsg

src/htslib.c

@@ -6006,6 +6006,7 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   StringCopy(opt->footer, HTS_DEFAULT_FOOTER);
   StringCopy(opt->strip_query, "");
   StringCopy(opt->cookies_file, "");
+  StringCopy(opt->why_url, "");
   opt->pause_min_ms = 0;
   opt->pause_max_ms = 0;
   opt->ftp_proxy = HTS_TRUE;
@@ -6153,6 +6154,7 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
     StringFree(opt->mod_blacklist);
     StringFree(opt->strip_query);
     StringFree(opt->cookies_file);
+    StringFree(opt->why_url);
 
     StringFree(opt->path_html);
     StringFree(opt->path_html_utf8);

src/htsopt.h

@@ -536,6 +536,8 @@ struct httrackp {
                                  (--cookies-file) */
   int pause_min_ms; /**< inter-file pause lower bound, ms (0=off, #185) */
   int pause_max_ms; /**< inter-file pause upper bound, ms */
+  String why_url;   /**< URL to diagnose (--why): print the deciding filter rule
+                         and exit without crawling */
 };
 
 /* Running statistics for a mirror. */

src/htsselftest.c

@@ -620,6 +620,26 @@ static int st_filtersize(httrackp *opt, int argc, char **argv) {
   return 0;
 }
 
+/* Merged two-form filter verdict via fa_strjoker_dual (see htsfilters.h). */
+static int st_filterdual(httrackp *opt, int argc, char **argv) {
+  int depth = -1, verdict;
+
+  (void) opt;
+  if (argc < 3) {
+    fprintf(stderr,
+            "filterdual: needs <string1> <string2> <filter> [filter...]\n");
+    return 1;
+  }
+  verdict = fa_strjoker_dual(0, &argv[2], argc - 2, argv[0], argv[1], NULL,
+                             NULL, &depth);
+  printf("verdict=%s rule=%d\n",
+         verdict > 0   ? "allowed"
+         : verdict < 0 ? "forbidden"
+                       : "unknown",
+         depth);
+  return 0;
+}
+
 static int st_simplify(httrackp *opt, int argc, char **argv) {
   (void) opt;
   if (argc < 1) {
@@ -2134,6 +2154,8 @@ static const struct selftest_entry {
     {"filtersize", "<size> <string> <filter>...",
      "size-aware filter verdict (negative size = unknown/scan time)",
      st_filtersize},
+    {"filterdual", "<string1> <string2> <filter>...",
+     "merged two-form filter verdict (fa_strjoker_dual)", st_filterdual},
     {"simplify", "<path>", "collapse ./ and ../ in a path", st_simplify},
     {"stripquery", "", "--strip-query pattern/key stripping self-test",
      st_stripquery},

src/htswizard.c

@@ -524,28 +524,11 @@ static int hts_acceptlink_(httrackp * opt, int ptr,
 
         // filters, 0=sait pas 1=ok -1=interdit
         {
-          int jokDepth1 = 0, jokDepth2 = 0;
-          int jok1 = 0, jok2 = 0;
+          int jokDepth = 0;
 
-          jok1 =
-            fa_strjoker( /*url */ 0, _FILTERS, *_FILTERS_PTR, lfull, NULL, NULL,
-                        &jokDepth1);
-          jok2 =
-            fa_strjoker( /*url */ 0, _FILTERS, *_FILTERS_PTR, l, NULL, NULL,
-                        &jokDepth2);
-          if (jok2 == 0) {      // #2 doesn't know
-            jok = jok1;         // then, use #1
-            mdepth = _FILTERS[jokDepth1];
-          } else if (jok1 == 0) {       // #1 doesn't know
-            jok = jok2;         // then, use #2
-            mdepth = _FILTERS[jokDepth2];
-          } else if (jokDepth1 >= jokDepth2) {  // #1 matching rule is "after" #2, then it is prioritary
-            jok = jok1;
-            mdepth = _FILTERS[jokDepth1];
-          } else {              // #2 matching rule is "after" #1, then it is prioritary
-            jok = jok2;
-            mdepth = _FILTERS[jokDepth2];
-          }
+          jok = fa_strjoker_dual(/*url */ 0, _FILTERS, *_FILTERS_PTR, lfull, l,
+                                 NULL, NULL, &jokDepth);
+          mdepth = _FILTERS[jokDepth];
         }
 
         if (jok == 1) {         // autorisé
@@ -965,34 +948,10 @@ int hts_testlinksize(httrackp * opt, const char *adr, const char *fil, LLint siz
 
       // filters, 0=sait pas 1=ok -1=interdit
       {
-        int jokDepth1 = 0, jokDepth2 = 0;
-        int jok1 = 0, jok2 = 0;
-        LLint sz1 = size, sz2 = size;
-        int size_flag1 = 0, size_flag2 = 0;
-
-        jok1 =
-          fa_strjoker( /*url */ 0, *opt->filters.filters, *opt->filters.filptr,
-                      lfull, &sz1, &size_flag1, &jokDepth1);
-        jok2 =
-          fa_strjoker( /*url */ 0, *opt->filters.filters, *opt->filters.filptr,
-                      l, &sz2, &size_flag2, &jokDepth2);
-        if (jok2 == 0) {        // #2 doesn't know
-          jok = jok1;           // then, use #1
-          sz = sz1;
-          size_flag = size_flag1;
-        } else if (jok1 == 0) { // #1 doesn't know
-          jok = jok2;           // then, use #2
-          sz = sz2;
-          size_flag = size_flag2;
-        } else if (jokDepth1 >= jokDepth2) {    // #1 matching rule is "after" #2, then it is prioritary
-          jok = jok1;
-          sz = sz1;
-          size_flag = size_flag1;
-        } else {                // #2 matching rule is "after" #1, then it is prioritary
-          jok = jok2;
-          sz = sz2;
-          size_flag = size_flag2;
-        }
+        sz = size;
+        jok = fa_strjoker_dual(/*url */ 0, *opt->filters.filters,
+                               *opt->filters.filptr, lfull, l, &sz, &size_flag,
+                               NULL);
       }
 
       // log

tests/01_engine-filterdual.test

@@ -0,0 +1,20 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# fa_strjoker_dual: merged verdict on the two URL forms the engine tests;
+# the match latest in the filter list wins, an unknown verdict defers.
+
+fdual() {
+    local want="$1"
+    shift
+    test "$(httrack -O /dev/null -#test=filterdual "$@")" == "$want" || exit 1
+}
+
+fdual 'verdict=unknown rule=0' zzz yyy '+a*'     # neither form matches
+fdual 'verdict=forbidden rule=0' aaa zzz '-a*'   # only form 1 matches
+fdual 'verdict=forbidden rule=0' zzz aaa '-a*'   # only form 2 matches
+fdual 'verdict=forbidden rule=1' a b '+a*' '-b*' # later rule wins (form 2)
+fdual 'verdict=forbidden rule=1' b a '+a*' '-b*' # later rule wins (form 1)
+fdual 'verdict=allowed rule=0' a aa '+a*'        # tie: form 1 wins

tests/40_local-why.test

@@ -0,0 +1,35 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# --why: report which +/- filter rule decides for a URL, without crawling.
+
+tmpdir="$(mktemp -d)"
+trap 'rm -rf "$tmpdir"' EXIT
+
+why() {
+    local want="$1" out
+    shift
+    out="$(httrack -O "$tmpdir/p" -q "$@" |
+        grep -E 'accepted|rejected|no filter|unable')"
+    test "$out" == "$want" || {
+        echo "want: $want"
+        echo "got : $out"
+        exit 1
+    }
+}
+
+base=http://www.example.com
+why "$base/x.zip: rejected by rule #2 (-*.zip)" \
+    --why "$base/x.zip" "$base/" '+*.png' '-*.zip'
+why "$base/a.png: accepted by rule #1 (+*.png)" \
+    --why "$base/a.png" "$base/" '+*.png' '-*.zip'
+why "$base/i.html: no filter rule matches; the wizard decides (same-site links are followed by default)" \
+    --why "$base/i.html" "$base/" '+*.png' '-*.zip'
+# scheme-less input gets the same http:// default as primary URLs
+why "$base/x.zip: rejected by rule #2 (-*.zip)" \
+    --why "www.example.com/x.zip" "$base/" '+*.png' '-*.zip'
+# the rule latest in the list decides
+why "$base/x.zip: accepted by rule #3 (+*x.zip)" \
+    --why "$base/x.zip" "$base/" '+*.png' '-*.zip' '+*x.zip'

tests/Makefile.am

@@ -35,6 +35,7 @@ TESTS = \
 	01_engine-entities.test \
 	01_engine-filelist.test \
 	01_engine-filter.test \
+	01_engine-filterdual.test \
 	01_engine-ftp-line.test \
 	01_engine-ftp-userpass.test \
 	01_engine-hashtable.test \
@@ -105,6 +106,7 @@ TESTS = \
 	36_local-bigcrawl.test \
 	37_local-cache-outage.test \
 	38_local-update-304.test \
-	39_local-delayed-cancel.test
+	39_local-delayed-cancel.test \
+	40_local-why.test
 
 CLEANFILES = check-network_sh.cache