Add --strip-query to drop query keys from dedup naming (#112) (#434)

Two URLs that differ only in tracking or session query parameters
(?utm_source=x versus ?utm_source=y) were saved as separate files, and a
single CGI could fan out into thousands of near-duplicate pages.
fil_normalized already sorted query args, so reordered parameters dedup,
but there was no way to drop a named key.

--strip-query "[host/pattern=]key1,key2,..." (repeatable) removes the
listed keys when computing the dedup key and the saved name. The fetched
URL is untouched, so a required sid= is still sent on the wire; only the
local namespace collapses. Patterns match the normalized host/path with
the +/- filter glob (strjoker), last match wins as in the filter list,
and stripping is decoupled from urlhack (-%u) so it never silently
no-ops with -%u0.

It all funnels through one chokepoint, fil_normalized: an internal
fil_normalized_filtered() strips then delegates, and hts_query_strip_keys
resolves the per-URL key list. The strip pass walks every query field,
including empty and trailing ones, so its output is a fixpoint under the
read path's second normalization (otherwise dedup silently misses).
Exported ABI is unchanged; the strip_query field is appended at the tail
of httrackp. Covered by a -#test=stripquery self-test (degenerate queries
like a=&b&c== and a 50-case idempotency fixpoint) and an end-to-end dedup
crawl test.

Closes #112

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

.github/workflows/ci.yml

@@ -188,6 +188,51 @@ jobs:
         if: failure()
         run: cat tests/test-suite.log 2>/dev/null || true
 
+  # MemorySanitizer catches reads of uninitialized memory (#143's stack-garbage
+  # size filter) that ASan/UBSan miss. It flags any byte an uninstrumented lib
+  # wrote, so the job stays in our own code: offline self-tests only, no openssl
+  # (--disable-https), no zlib cache tests, static (the runtime is not in .so's).
+  msan:
+    name: msan (MemorySanitizer, clang)
+    runs-on: ubuntu-24.04
+    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 clang autoconf automake libtool autoconf-archive \
+            zlib1g-dev
+
+      - name: Configure (MSan, static, no https)
+        run: |
+          set -euo pipefail
+          autoreconf -fi
+          ./configure CC=clang \
+            CFLAGS="-fsanitize=memory -fsanitize-memory-track-origins=2 -fno-sanitize-recover=all -g -O1 -fno-omit-frame-pointer" \
+            LDFLAGS="-fsanitize=memory" \
+            --disable-https --disable-shared --enable-static
+
+      - name: Build
+        run: make -j"$(nproc)"
+
+      - name: Test (offline self-tests under MSan)
+        env:
+          MSAN_OPTIONS: abort_on_error=1:halt_on_error=1
+        run: |
+          set -euo pipefail
+          # Engine self-tests only; the cache trio pulls in uninstrumented zlib.
+          tests="$(cd tests && ls 01_engine-*.test | grep -v -- '-cache' | tr '\n' ' ')"
+          make check TESTS="$tests"
+
+      - name: Print the test log on failure
+        if: failure()
+        run: cat tests/test-suite.log 2>/dev/null || true
+
   # Optional-dependency build: compile and test with HTTPS/OpenSSL disabled --
   # the configuration users on minimal systems build, and one libssl is not even
   # installed here so configure cannot silently re-enable it. The matrix above

AGENTS.md

@@ -33,8 +33,9 @@ the operational checklist: toolchain, invariants, and how to ship a change.
 - Be terse. Comment the why, in English; translate French comments you touch.
 - Strip AI tells from prose (em-dash overuse, rule-of-three, filler, vague
   attributions). Ref: Wikipedia "Signs of AI writing". Claude Code: `/humanizer`.
-- Behavior change → add a test. Fast path: a hidden `httrack -#N` debug
-  subcommand (`htscoremain.c`) driven by a `tests/NN_*.test`, over a slow crawl.
+- Behavior change → add a test. Fast path: a hidden `httrack -#test=NAME` engine
+  self-test (registry in `htsselftest.c`; `-#test` lists them) driven by a
+  `tests/NN_*.test`, over a slow crawl.
 
 ## Review your change adversarially (strongly suggested)
 Before pushing, and when reviewing others, don't skim for bugs:

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 "13 June 2026" "httrack website copier"
+.TH httrack 1 "27 June 2026" "httrack website copier"
 .SH NAME
 httrack \- offline browser : copy websites to a local directory
 .SH SYNOPSIS
@@ -43,6 +43,7 @@ httrack \- offline browser : copy websites to a local directory
 [ \fB\-x, \-\-replace\-external\fR ]
 [ \fB\-%x, \-\-disable\-passwords\fR ]
 [ \fB\-%q, \-\-include\-query\-string\fR ]
+[ \fB\-%g, \-\-strip\-query\fR ]
 [ \fB\-o, \-\-generate\-errors\fR ]
 [ \fB\-X, \-\-purge\-old[=N]\fR ]
 [ \fB\-%p, \-\-preserve\fR ]
@@ -198,6 +199,8 @@ replace external html links by error pages (\-\-replace\-external)
 do not include any password for external password protected websites (%x0 include) (\-\-disable\-passwords)
 .IP \-%q
 *include query string for local files (useless, for information purpose only) (%q0 don't include) (\-\-include\-query\-string)
+.IP \-%g
+strip query keys for dedup ([host/pattern=]key1,key2,...) (\-\-strip\-query <param>)
 .IP \-o
 *generate output html file in case of error (404..) (o0 don't generate) (\-\-generate\-errors)
 .IP \-X
@@ -313,12 +316,8 @@ debug HTTP headers in logfile (\-\-debug\-headers)
 .SS Guru options: (do NOT use if possible)
 .IP \-#X
 *use optimized engine (limited memory boundary checks) (\-\-fast\-engine)
-.IP \-#0
-filter test (\-#0 '*.gif' 'www.bar.com/foo.gif') (\-\-debug\-testfilters <param>)
-.IP \-#1
-simplify test (\-#1 ./foo/bar/../foobar)
-.IP \-#2
-type test (\-#2 /foo/bar.php)
+.IP \-#test
+list engine self\-tests (run one with \-#test=NAME [args])
 .IP \-#C
 cache list (\-#C '*.com/spider*.gif' (\-\-debug\-cache <param>)
 .IP \-#R

src/Makefile.am

@@ -56,7 +56,7 @@ whttrackrundir = $(bindir)
 whttrackrun_SCRIPTS = webhttrack
 
 libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
-	htscache_selftest.c htsdns_selftest.c \
+	htscache_selftest.c htsdns_selftest.c htsselftest.c \
 	htscatchurl.c htsfilters.c htsftp.c htshash.c coucal/coucal.c \
 	htshelp.c htslib.c htscoremain.c \
 	htsname.c htsrobots.c htstools.c htswizard.c \
@@ -66,7 +66,7 @@ libhttrack_la_SOURCES =  htscore.c htsparse.c htsback.c htscache.c \
 	md5.c \
 	minizip/ioapi.c minizip/mztools.c minizip/unzip.c minizip/zip.c \
 	hts-indextmpl.h htsalias.h htsback.h htsbase.h htssafe.h \
-	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htscatchurl.h  \
+	htsbasenet.h htsbauth.h htscache.h htscache_selftest.h htsdns_selftest.h htsselftest.h htscatchurl.h  \
 	htsconfig.h htscore.h htsparse.h htscoremain.h htsdefines.h  \
 	htsfilters.h htsftp.h htsglobal.h htshash.h coucal/coucal.h \
 	htshelp.h htsindex.h htslib.h htsmd5.h \

src/htsalias.c

@@ -60,6 +60,9 @@ Please visit our Website: http://www.httrack.com
   param1 : this option must be alone, and needs one distinct parameter (-P <path>)
   param0 : this option must be alone, but the parameter should be put together (+*.gif)
 */
+/* clang-format off: hand-aligned table; clang-format reflows the whole
+   initializer (2->4 space) on any edit, churning every untouched row. */
+/* clang-format off */
 const char *hts_optalias[][4] = {
   /*   {"","","",""}, */
   {"path", "-O", "param1", "output path"},
@@ -107,6 +110,8 @@ const char *hts_optalias[][4] = {
   {"disable-passwords", "-%x", "single", ""}, {"disable-password", "-%x",
                                                "single", ""},
   {"include-query-string", "-%q", "single", ""},
+  {"strip-query", "-%g", "param1",
+   "strip [host/pattern=]key1,key2,... from URLs"},
   {"generate-errors", "-o", "single", ""},
   {"do-not-generate-errors", "-o0", "single", ""},
   {"purge-old", "-X", "param", ""},
@@ -241,6 +246,7 @@ const char *hts_optalias[][4] = {
 
   {"", "", "", ""}
 };
+/* clang-format on */
 
 /* 
   Check for alias in command-line 

src/htsback.c

@@ -57,7 +57,10 @@ Please visit our Website: http://www.httrack.com
 // DOS
 #include <process.h>            /* _beginthread, _endthread */
 #endif
+#include <io.h> /* _chsize_s */
+#define HTS_FTRUNCATE(fp, sz) _chsize_s(_fileno(fp), (sz))
 #else
+#define HTS_FTRUNCATE(fp, sz) ftruncate(fileno(fp), (sz))
 #endif
 
 #define VT_CLREOL       "\33[K"
@@ -3763,7 +3766,27 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     }
 #endif
 /********** **************************** ********** */
-                  } else {      // il faut aller le chercher
+                  }
+                  // MIME type excluded by a -mime: filter: abort, don't fetch
+                  // the body (#58)
+                  else if (HTTP_IS_OK(back[i].r.statuscode) &&
+                           !back[i].testmode &&
+                           strnotempty(back[i].r.contenttype) &&
+                           hts_acceptmime(opt, 0, back[i].url_adr,
+                                          back[i].url_fil,
+                                          back[i].r.contenttype) == 1) {
+                    deletehttp(&back[i].r);
+                    back[i].r.soc = INVALID_SOCKET;
+                    back[i].status = STATUS_READY;
+                    back_set_finished(sback, i);
+                    back[i].r.statuscode = STATUSCODE_EXCLUDED;
+                    strcpybuff(back[i].r.msg, "Excluded by MIME type filter");
+                    hts_log_print(
+                        opt, LOG_NOTICE,
+                        "File excluded by MIME type filter (%s): %s%s",
+                        back[i].r.contenttype, back[i].url_adr,
+                        back[i].url_fil);
+                  } else { // il faut aller le chercher
 
                     // effacer buffer (requète)
                     if (!noFreebuff) {
@@ -3774,35 +3797,70 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                     // xxc SI CHUNK VERIFIER QUE CA MARCHE??
                     if (back[i].r.statuscode == 206) {  // on nous envoie un morceau (la fin) coz une partie sur disque!
                       off_t sz = fsize_utf8(back[i].url_sav);
+                      /* RFC 7233: resume at the server's Content-Range start,
+                         not the offset we requested; a server may resume
+                         earlier and appending the overlap duplicates bytes
+                         (#198). */
+                      const LLint resume = back[i].r.crange_start;
+                      const hts_boolean range_ok =
+                          back[i].r.crange > 0 && resume >= 0 &&
+                          resume <= (LLint) sz &&
+                          back[i].r.crange_end + 1 == back[i].r.crange &&
+                          (back[i].r.totalsize < 0 ||
+                           back[i].r.totalsize ==
+                               back[i].r.crange_end - resume + 1);
 
 #if HDEBUG
                       printf("partial content: " LLintP " on disk..\n",
                              (LLint) sz);
 #endif
-                      if (sz >= 0) {
+                      if (sz >= 0 && range_ok) {
                         if (!is_hypertext_mime(opt, back[i].r.contenttype, back[i].url_sav)) {  // pas HTML
                           if (opt->getmode & HTS_GETMODE_NONHTML) {
                             filenote(&opt->state.strc, back[i].url_sav, NULL);  // noter fichier comme connu
                             file_notify(opt, back[i].url_adr, back[i].url_fil,
                                         back[i].url_sav, 0, 1,
                                         back[i].r.notmodified);
-                            back[i].r.out = FOPEN(fconv(catbuff, sizeof(catbuff), back[i].url_sav), "ab");       // append
+                            back[i].r.out =
+                                FOPEN(fconv(catbuff, sizeof(catbuff),
+                                            back[i].url_sav),
+                                      "r+b"); // resume in place
                             if (back[i].r.out && opt->cache != 0) {
-                              back[i].r.is_write = 1;   // écrire
-                              back[i].r.size = sz;      // déja écrit
-                              back[i].r.statuscode = HTTP_OK;   // Forcer 'OK'
+                              back[i].r.is_write = 1;
+                              back[i].r.size = resume; // bytes already on disk
+                              back[i].r.statuscode = HTTP_OK; // force 'OK'
                               if (back[i].r.totalsize >= 0)
-                                back[i].r.totalsize += sz;      // plus en fait
-                              fseek(back[i].r.out, 0, SEEK_END);        // à la fin
-                              /* create a temporary reference file in case of broken mirror */
-                              if (back_serialize_ref(opt, &back[i]) != 0) {
-                                hts_log_print(opt, LOG_WARNING,
-                                              "Could not create temporary reference file for %s%s",
-                                              back[i].url_adr, back[i].url_fil);
-                              }
+                                back[i].r.totalsize += resume; // -> full size
+                              // drop bytes past the resume point; a silent
+                              // failure could leave a stale tail, so on error
+                              // drop the partial and refetch the whole file
+                              if (HTS_FTRUNCATE(back[i].r.out,
+                                                (off_t) resume) != 0) {
+                                fclose(back[i].r.out);
+                                back[i].r.out = NULL;
+                                url_savename_refname_remove(
+                                    opt, back[i].url_adr, back[i].url_fil);
+                                UNLINK(back[i].url_sav);
+                                back[i].status = STATUS_READY;
+                                back_set_finished(sback, i);
+                                strcpybuff(back[i].r.msg,
+                                           "Can not truncate partial file, "
+                                           "restarting");
+                              } else {
+                                fseeko(back[i].r.out, (off_t) resume, SEEK_SET);
+                                /* create a temporary reference file in case of
+                                 * broken mirror */
+                                if (back_serialize_ref(opt, &back[i]) != 0) {
+                                  hts_log_print(opt, LOG_WARNING,
+                                                "Could not create temporary "
+                                                "reference file for %s%s",
+                                                back[i].url_adr,
+                                                back[i].url_fil);
+                                }
 #if HDEBUG
-                              printf("continue interrupted file\n");
+                                printf("continue interrupted file\n");
 #endif
+                              }
                             } else {    // On est dans la m**
                               back[i].status = STATUS_READY;    // terminé (voir plus loin)
                               back_set_finished(sback, i);
@@ -3814,17 +3872,18 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                           FILE *fp =
                             FOPEN(fconv(catbuff, sizeof(catbuff), back[i].url_sav), "rb");
                           if (fp) {
-                            LLint alloc_mem = sz + 1;
+                            LLint alloc_mem = resume + 1;
 
                             if (back[i].r.totalsize >= 0)
                               alloc_mem += back[i].r.totalsize; // AJOUTER RESTANT!
                             if (deleteaddr(&back[i].r)
                                 && (back[i].r.adr =
                                     (char *) malloct((size_t) alloc_mem))) {
-                              back[i].r.size = sz;
+                              back[i].r.size = resume;
                               if (back[i].r.totalsize >= 0)
-                                back[i].r.totalsize += sz;      // plus en fait
-                              if ((fread(back[i].r.adr, 1, sz, fp)) != sz) {
+                                back[i].r.totalsize += resume; // -> full size
+                              if ((fread(back[i].r.adr, 1, (size_t) resume,
+                                         fp)) != (size_t) resume) {
                                 back[i].status = STATUS_READY;  // terminé (voir plus loin)
                                 back_set_finished(sback, i);
                                 strcpybuff(back[i].r.msg,
@@ -3842,14 +3901,30 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                          "No memory for partial file");
                             }
                             fclose(fp);
-                          } else {      // Argh.. 
+                          } else {                              // open failed
                             back[i].status = STATUS_READY;      // terminé (voir plus loin)
                             back_set_finished(sback, i);
                             strcpybuff(back[i].r.msg,
                                        "Can not open partial file");
                           }
                         }
-                      } else {  // Non trouvé??
+                      } else if (sz >=
+                                 0) { // unusable range -> restart whole file
+                        hts_log_print(opt, LOG_WARNING,
+                                      "Unusable partial-content range for %s%s "
+                                      "(have " LLintP " bytes, got " LLintP
+                                      "-" LLintP "/" LLintP "), restarting",
+                                      back[i].url_adr, back[i].url_fil,
+                                      (LLint) sz, back[i].r.crange_start,
+                                      back[i].r.crange_end, back[i].r.crange);
+                        url_savename_refname_remove(opt, back[i].url_adr,
+                                                    back[i].url_fil);
+                        UNLINK(back[i].url_sav);
+                        back[i].status = STATUS_READY;
+                        back_set_finished(sback, i);
+                        strcpybuff(back[i].r.msg,
+                                   "Unusable partial content, restarting");
+                      } else {                          // partial not found
                         back[i].status = STATUS_READY;  // terminé (voir plus loin)
                         back_set_finished(sback, i);
                         strcpybuff(back[i].r.msg, "Can not find partial file");
@@ -3930,7 +4005,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
 
                       }
                     }
-
                   }
 
                   /*} */

src/htsbasenet.h

@@ -146,7 +146,8 @@ typedef enum BackStatusCode {
   STATUSCODE_NON_FATAL = -5,
   STATUSCODE_SSL_HANDSHAKE = -6,
   STATUSCODE_TOO_BIG = -7,
-  STATUSCODE_TEST_OK = -10
+  STATUSCODE_TEST_OK = -10,
+  STATUSCODE_EXCLUDED = -11 /* aborted: MIME excluded by a -mime: filter */
 } BackStatusCode;
 
 /** HTTrack status ('status' member of of 'lien_back') **/

src/htscore.c

@@ -736,26 +736,39 @@ int httpmirror(char *url1, httrackp * opt) {
     /* OPTIMIZED for fast load */
     if (StringNotEmpty(opt->filelist)) {
       char *filelist_buff = NULL;
-      const size_t filelist_sz = off_t_to_size_t(fsize(StringBuff(opt->filelist)));
+      size_t filelist_sz = 0;
+      const char *filelist_err = NULL; /* failure reason, NULL on success */
+      const off_t fs = fsize(StringBuff(opt->filelist));
 
-      if (filelist_sz != (size_t) -1) {
+      if (fs < 0) {
+        /* fsize() hides the cause; redo stat() for a precise errno (#49) */
+        struct stat st;
+        filelist_err = stat(StringBuff(opt->filelist), &st) != 0
+                           ? strerror(errno)
+                           : "not a regular file";
+      } else if ((filelist_sz = off_t_to_size_t(fs)) == (size_t) -1) {
+        filelist_err = "file too large";
+        filelist_sz = 0;
+      } else {
         FILE *fp = fopen(StringBuff(opt->filelist), "rb");
 
-        if (fp) {
+        if (fp == NULL) {
+          filelist_err = strerror(errno);
+        } else {
           filelist_buff = malloct(filelist_sz + 1);
-          if (filelist_buff) {
-            if (fread(filelist_buff, 1, filelist_sz, fp) != filelist_sz) {
-              freet(filelist_buff);
-              filelist_buff = NULL;
-            } else {
-              *(filelist_buff + filelist_sz) = '\0';
-            }
+          if (filelist_buff == NULL) {
+            filelist_err = "out of memory";
+          } else if (fread(filelist_buff, 1, filelist_sz, fp) != filelist_sz) {
+            freet(filelist_buff);
+            filelist_err = "read error";
+          } else {
+            filelist_buff[filelist_sz] = '\0';
           }
           fclose(fp);
         }
       }
 
-      if (filelist_buff) {
+      if (filelist_buff != NULL) {
         int filelist_ptr = 0;
         int n = 0;
         char BIGSTK line[HTS_URLMAXSIZE * 2];
@@ -780,8 +793,8 @@ int httpmirror(char *url1, httrackp * opt) {
         // Free buffer
         freet(filelist_buff);
       } else {
-        hts_log_print(opt, LOG_ERROR, "Could not include URL list: %s",
-                      StringBuff(opt->filelist));
+        hts_log_print(opt, LOG_ERROR, "Could not include URL list \"%s\": %s",
+                      StringBuff(opt->filelist), filelist_err);
       }
     }
 
@@ -3726,6 +3739,9 @@ HTSEXT_API int copy_htsopt(const httrackp * from, httrackp * to) {
   if (StringNotEmpty(from->user_agent))
     StringCopyS(to->user_agent, from->user_agent);
 
+  if (StringNotEmpty(from->strip_query))
+    StringCopyS(to->strip_query, from->strip_query);
+
   if (from->retry > -1)
     to->retry = from->retry;
 

src/htscore.h

@@ -236,6 +236,8 @@ struct hash_struct {
   coucal former_adrfil;
   /* scratch buffers reused across lookups (not reentrant) */
   int normalized;
+  /* query-strip keys (not owned); set from opt->strip_query at hash_init */
+  const char *strip_query;
   char normfil[HTS_URLMAXSIZE * 2];
   char normfil2[HTS_URLMAXSIZE * 2];
   char catbuff[CATBUFF_SIZE];
@@ -364,6 +366,17 @@ int fspc(httrackp * opt, FILE * fp, const char *type);
 
 char *next_token(char *p, int flag);
 
+/* Like fil_normalized(), but first drops query keys in STRIP (comma-separated,
+   "*" = all); STRIP NULL/empty behaves exactly like fil_normalized(). */
+char *fil_normalized_filtered(const char *source, char *dest,
+                              const char *strip);
+
+/* For URL ADR/FIL, return (in DEST) the comma keylist to strip from the
+   '\n'-separated "[pattern=]keys" RULES (patterns matched on host/path via
+   strjoker, last wins); NULL if none match. Feeds fil_normalized_filtered(). */
+const char *hts_query_strip_keys(const char *rules, const char *adr,
+                                 const char *fil, char *dest, size_t destsize);
+
 /* Read a whole file into a freshly malloc'd, NUL-terminated buffer; the caller
    owns it and must release it with freet(). Return NULL on missing/unreadable
    file (readfile_or substitutes defaultdata instead). The byte content is NOT

src/htsfilters.c

@@ -76,7 +76,8 @@ int fa_strjoker(int type, char **filters, int nfil, const char *nom, LLint * siz
     }
     if (size)
       sz = *size;
-    if (strjoker(nom, filters[i] + filteroffs, &sz, size_flag)) {       // reconnu
+    /* size unknown (scan time): no size pointer => size tests stay neutral */
+    if (strjoker(nom, filters[i] + filteroffs, size ? &sz : NULL, size_flag)) {
       if (size)
         if (sz != *size)
           sizelimit = sz;

src/htshash.c

@@ -117,10 +117,17 @@ static coucal_hashkeys key_adrfil_hashes_generic(void *arg,
 
   // copy link
   assertf(fil != NULL);
-  if (hash->normalized) {
-    fil_normalized(fil, &hash->normfil[strlen(hash->normfil)]);
-  } else {
-    strcpy(&hash->normfil[strlen(hash->normfil)], fil);
+  {
+    /* resolve the per-URL strip keys; strip applies even when urlhack is off */
+    char BIGSTK keybuf[HTS_URLMAXSIZE];
+    const char *const keys = hts_query_strip_keys(hash->strip_query, adr, fil,
+                                                  keybuf, sizeof(keybuf));
+
+    if (hash->normalized || keys != NULL) {
+      fil_normalized_filtered(fil, &hash->normfil[strlen(hash->normfil)], keys);
+    } else {
+      strcpy(&hash->normfil[strlen(hash->normfil)], fil);
+    }
   }
 
   // hash
@@ -161,12 +168,20 @@ static int key_adrfil_equals_generic(void *arg,
   }
 
   // now compare pathes
-  if (normalized) {
-    fil_normalized(a_fil, hash->normfil);
-    fil_normalized(b_fil, hash->normfil2);
-    return strcmp(hash->normfil, hash->normfil2) == 0;
-  } else {
-    return strcmp(a_fil, b_fil) == 0;
+  {
+    char BIGSTK ka[HTS_URLMAXSIZE], kb[HTS_URLMAXSIZE];
+    const char *const keysa =
+        hts_query_strip_keys(hash->strip_query, a_adr, a_fil, ka, sizeof(ka));
+    const char *const keysb =
+        hts_query_strip_keys(hash->strip_query, b_adr, b_fil, kb, sizeof(kb));
+
+    if (normalized || keysa != NULL || keysb != NULL) {
+      fil_normalized_filtered(a_fil, hash->normfil, keysa);
+      fil_normalized_filtered(b_fil, hash->normfil2, keysb);
+      return strcmp(hash->normfil, hash->normfil2) == 0;
+    } else {
+      return strcmp(a_fil, b_fil) == 0;
+    }
   }
 }
 
@@ -227,6 +242,9 @@ void hash_init(httrackp *opt, hash_struct * hash, int normalized) {
   hash->adrfil = coucal_new(0);
   hash->former_adrfil = coucal_new(0);
   hash->normalized = normalized;
+  /* snapshot the query-strip list (not owned; valid for the hash lifetime) */
+  hash->strip_query =
+      StringNotEmpty(opt->strip_query) ? StringBuff(opt->strip_query) : NULL;
 
   hts_set_hash_handler(hash->sav, opt);
   hts_set_hash_handler(hash->adrfil, opt);

src/htshelp.c

@@ -563,6 +563,7 @@ void help(const char *app, int more) {
     (" %x  do not include any password for external password protected websites (%x0 include)");
   infomsg
     (" %q *include query string for local files (useless, for information purpose only) (%q0 don't include)");
+  infomsg(" %g  strip query keys for dedup ([host/pattern=]key1,key2,...)");
   infomsg
     ("  o *generate output html file in case of error (404..) (o0 don't generate)");
   infomsg("  X *purge old files after update (X0 keep delete)");
@@ -646,9 +647,7 @@ void help(const char *app, int more) {
   infomsg("");
   infomsg("Guru options: (do NOT use if possible)");
   infomsg(" #X *use optimized engine (limited memory boundary checks)");
-  infomsg(" #0  filter test (-#0 '*.gif' 'www.bar.com/foo.gif')");
-  infomsg(" #1  simplify test (-#1 ./foo/bar/../foobar)");
-  infomsg(" #2  type test (-#2 /foo/bar.php)");
+  infomsg(" #test  list engine self-tests (run one with -#test=NAME [args])");
   infomsg(" #C  cache list (-#C '*.com/spider*.gif'");
   infomsg(" #R  cache repair (damaged cache)");
   infomsg(" #d  debug parser");

src/htslib.c

@@ -3681,6 +3681,142 @@ HTSEXT_API char *fil_normalized(const char *source, char *dest) {
   return dest;
 }
 
+/* Is query key ARG[0..keylen) in the comma-separated STRIP list? "*" = all;
+   case-sensitive, space-trimmed tokens. */
+static int hts_query_key_stripped(const char *arg, size_t keylen,
+                                  const char *strip) {
+  const char *p = strip;
+
+  while (*p != '\0') {
+    const char *start = p;
+    size_t toklen;
+
+    while (*p != '\0' && *p != ',')
+      p++;
+    toklen = (size_t) (p - start);
+    while (toklen > 0 && *start == ' ') {
+      start++;
+      toklen--;
+    }
+    while (toklen > 0 && start[toklen - 1] == ' ')
+      toklen--;
+    if (toklen == 1 && start[0] == '*')
+      return 1;
+    if (toklen == keylen && strncmp(start, arg, keylen) == 0)
+      return 1;
+    if (*p == ',')
+      p++;
+  }
+  return 0;
+}
+
+/* see htscore.h */
+char *fil_normalized_filtered(const char *source, char *dest,
+                              const char *strip) {
+  const char *query;
+  char BIGSTK tmp[HTS_URLMAXSIZE * 2];
+  htsbuff cb;
+  int wrote = 0;
+
+  /* No strip list, or no query: plain normalization. */
+  if (strip == NULL || *strip == '\0' ||
+      (query = strchr(source, '?')) == NULL) {
+    return fil_normalized(source, dest);
+  }
+
+  /* Copy the path, re-emit kept query args, let fil_normalized() sort. Walk
+     every field incl. empty/trailing ("a&","?&&") so the result is a fixpoint
+     (the read re-normalizes it; a dropped empty arg would miss dedup). */
+  cb = htsbuff_ptr(tmp, sizeof(tmp));
+  htsbuff_catn(&cb, source, (size_t) (query - source));
+  for (query++;;) {
+    const char *const arg = query;
+    const char *eq = NULL;
+    size_t keylen, arglen;
+
+    while (*query != '\0' && *query != '&') {
+      if (eq == NULL && *query == '=')
+        eq = query;
+      query++;
+    }
+    arglen = (size_t) (query - arg);
+    keylen = eq != NULL ? (size_t) (eq - arg) : arglen;
+    if (!hts_query_key_stripped(arg, keylen, strip)) {
+      htsbuff_catc(&cb, wrote ? '&' : '?');
+      htsbuff_catn(&cb, arg, arglen);
+      wrote = 1;
+    }
+    if (*query == '\0')
+      break;
+    query++;
+  }
+  return fil_normalized(tmp, dest);
+}
+
+/* see htscore.h */
+const char *hts_query_strip_keys(const char *rules, const char *adr,
+                                 const char *fil, char *dest, size_t destsize) {
+  const char *p, *q;
+  const char *result = NULL;
+  char BIGSTK url[HTS_URLMAXSIZE * 2];
+
+  if (rules == NULL || *rules == '\0' || destsize == 0)
+    return NULL;
+
+  /* Match string = normalized host/path, query removed. jump_normalized_const
+     collapses www+scheme/auth so read and write (double-normalized) agree;
+     query excluded keeps the decision on host/path only. */
+  url[0] = '\0';
+  strcatbuff(url, jump_normalized_const(adr));
+  if (fil[0] != '/')
+    strcatbuff(url, "/");
+  q = strchr(fil, '?');
+  if (q != NULL)
+    strncatbuff(url, fil, (int) (q - fil));
+  else
+    strcatbuff(url, fil);
+
+  /* Walk the '\n' entries; last match wins (like the +/- filter eval). Each is
+     "pattern=keys"; no '=' is the bare form, pattern "*". */
+  for (p = rules; *p != '\0';) {
+    const char *const line = p;
+    const char *eol, *eq, *keys;
+    char BIGSTK pat[HTS_URLMAXSIZE * 2];
+
+    while (*p != '\0' && *p != '\n')
+      p++;
+    eol = p;
+    if (*p == '\n')
+      p++;
+    if (eol == line)
+      continue;
+    eq = memchr(line, '=', (size_t) (eol - line));
+    if (eq != NULL) {
+      size_t patlen = (size_t) (eq - line);
+
+      if (patlen >= sizeof(pat))
+        patlen = sizeof(pat) - 1;
+      memcpy(pat, line, patlen);
+      pat[patlen] = '\0';
+      keys = eq + 1;
+    } else {
+      pat[0] = '*';
+      pat[1] = '\0';
+      keys = line;
+    }
+    if (strjoker(url, pat, NULL, NULL) != NULL) {
+      size_t klen = (size_t) (eol - keys);
+
+      if (klen >= destsize)
+        klen = destsize - 1;
+      memcpy(dest, keys, klen);
+      dest[klen] = '\0';
+      result = dest;
+    }
+  }
+  return result;
+}
+
 #define endwith(a) ( (len >= (sizeof(a)-1)) ? ( strncmp(dest, a+len-(sizeof(a)-1), sizeof(a)-1) == 0 ) : 0 );
 HTSEXT_API char *adr_normalized_sized(const char *source, char *dest,
                                       size_t destsize) {
@@ -5891,6 +6027,7 @@ HTSEXT_API httrackp *hts_create_opt(void) {
   opt->sizehack = HTS_FALSE;
   opt->urlhack = HTS_TRUE;
   StringCopy(opt->footer, HTS_DEFAULT_FOOTER);
+  StringCopy(opt->strip_query, "");
   opt->ftp_proxy = HTS_TRUE;
   opt->convert_utf8 = HTS_TRUE;
   StringCopy(opt->filelist, "");
@@ -6035,6 +6172,7 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
     StringFree(opt->urllist);
     StringFree(opt->footer);
     StringFree(opt->mod_blacklist);
+    StringFree(opt->strip_query);
 
     StringFree(opt->path_html);
     StringFree(opt->path_html_utf8);

src/htsname.c

@@ -198,6 +198,13 @@ int url_savename(lien_adrfilsave *const afs,
   // copy of fil, used for lookups (see urlhack)
   const char *normadr = adr;
   const char *normfil = fil_complete;
+  /* query keys to strip for this URL (NULL = none); decoupled from urlhack */
+  char BIGSTK stripkeys[HTS_URLMAXSIZE];
+  const char *const strip =
+      StringNotEmpty(opt->strip_query)
+          ? hts_query_strip_keys(StringBuff(opt->strip_query), adr,
+                                 fil_complete, stripkeys, sizeof(stripkeys))
+          : NULL;
   const char *const print_adr = jump_protocol_const(adr);
   const char *start_pos = NULL, *nom_pos = NULL, *dot_pos = NULL;     // Position nom et point
 
@@ -232,7 +239,7 @@ int url_savename(lien_adrfilsave *const afs,
   if (opt->urlhack) {
     // copy of adr (without protocol), used for lookups (see urlhack)
     normadr = adr_normalized_sized(adr, normadr_, sizeof(normadr_));
-    normfil = fil_normalized(fil_complete, normfil_);
+    normfil = fil_normalized_filtered(fil_complete, normfil_, strip);
   } else {
     if (link_has_authority(adr_complete)) {     // https or other protocols : in "http/" subfolder
       char *pos = strchr(adr_complete, ':');
@@ -245,6 +252,9 @@ int url_savename(lien_adrfilsave *const afs,
         normadr = normadr_;
       }
     }
+    // strip still applies with urlhack off (host left untouched)
+    if (strip != NULL)
+      normfil = fil_normalized_filtered(fil_complete, normfil_, strip);
   }
 
   // à afficher sans ftp://

src/htsopt.h

@@ -529,6 +529,8 @@ struct httrackp {
   htslibhandles libHandles; /**< loaded external module handles */
   //
   htsoptstate state; /**< embedded live engine state */
+  String strip_query; /**< query keys to drop when deduping URLs (-strip-query);
+                           appended at the tail to keep field offsets stable */
 };
 
 /* Running statistics for a mirror. */

src/htsselftest.h

@@ -0,0 +1,52 @@
+/* ------------------------------------------------------------ */
+/*
+HTTrack Website Copier, Offline Browser for Windows and Unix
+Copyright (C) 2026 Xavier Roche and other contributors
+
+SPDX-License-Identifier: GPL-3.0-or-later
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Ethical use: we kindly ask that you NOT use this software to harvest email
+addresses or to collect any other private information about people. Doing so
+would dishonor our work and waste the many hours we have spent on it.
+
+Please visit our Website: http://www.httrack.com
+*/
+
+/* ------------------------------------------------------------ */
+/* File: htsselftest.h                                          */
+/*       named dispatch for the hidden engine self-tests        */
+/* Author: Xavier Roche                                         */
+/* ------------------------------------------------------------ */
+
+#ifndef HTSSELFTEST_DEFH
+#define HTSSELFTEST_DEFH
+
+#ifdef HTS_INTERNAL_BYTECODE
+
+#ifndef HTS_DEF_FWSTRUCT_httrackp
+#define HTS_DEF_FWSTRUCT_httrackp
+typedef struct httrackp httrackp;
+#endif
+
+/* Run engine self-test `name` over the positional args argv[0..argc-1], or list
+   the available tests when name is NULL, empty, or "list". Prints the result;
+   returns the process exit code (0 == success). The caller owns option cleanup.
+   Reached through the hidden `httrack -#test[=NAME ...]` subcommand. */
+int hts_selftest(httrackp *opt, const char *name, int argc, char **argv);
+
+#endif
+
+#endif

tests/01_engine-cache-golden.test

@@ -4,7 +4,7 @@
 # POSIX /bin/sh on some platforms (e.g. macOS), so avoid bashisms and GNU-only
 # tool flags despite the #!/bin/bash above.
 
-# Golden cache-format regression test (driven by 'httrack -#B <dir>').
+# Golden cache-format regression test (driven by 'httrack -#test=cache-golden <dir>').
 #
 # 01_engine-cache.test writes the cache with the same build it reads back (a
 # round-trip), so it cannot catch a read-path or ZIP-format regression where
@@ -13,7 +13,7 @@
 # byte-exact.
 #
 # Regenerate the fixture after a deliberate format change with
-# 'httrack -#B <dir> regen', then copy <dir>/hts-cache/new.zip over the
+# 'httrack -#test=cache-golden <dir> regen', then copy <dir>/hts-cache/new.zip over the
 # committed file.
 
 set -eu
@@ -37,11 +37,11 @@ trap 'rm -rf "$dir"' EXIT
 mkdir -p "$dir/hts-cache"
 cp "$fixture/hts-cache/new.zip" "$dir/hts-cache/new.zip"
 
-out=$(httrack -#B "$dir")
+out=$(httrack -#test=cache-golden "$dir")
 
 # Match the exact success line: the read must have found and verified every
-# entry, not merely failed to enter the mode (a bad -#B falls through to the
-# usage screen, which also exits non-zero but never prints this).
+# entry, not merely failed to enter the mode (a renamed/removed test prints the
+# registry to stderr, which also exits non-zero but never prints this).
 test "$out" = "cache-golden: OK" || {
     echo "expected 'cache-golden: OK', got: $out" >&2
     exit 1

tests/01_engine-cache-writefail.test

@@ -4,20 +4,20 @@
 # POSIX /bin/sh on some platforms (e.g. macOS), so avoid bashisms and GNU-only
 # tool flags despite the #!/bin/bash above.
 
-# Cache write-failure handling (httrack -#W <dir>). #174/#219.
+# Cache write-failure handling (httrack -#test=cache-writefail <dir>). #174/#219.
 # A failing new.zip write (disk full) used to crash the process via assertf; it
 # must instead stop the mirror with a fatal error (exit_xh=-1), no crash. The
-# self-test asserts that; reverting the fix makes -#W abort (SIGABRT) and fail.
+# self-test asserts that; reverting the fix makes -#test=cache-writefail abort (SIGABRT) and fail.
 
 set -eu
 
 dir=$(mktemp -d)
 trap 'rm -rf "$dir"' EXIT
 
-out=$(httrack -#W "$dir")
+out=$(httrack -#test=cache-writefail "$dir")
 
-# Match the exact success line (error logs also go to stdout); a bad -#W falls
-# through to the usage screen, which exits non-zero but never prints this.
+# Match the exact success line (error logs also go to stdout); a renamed/removed
+# test prints the registry to stderr, which exits non-zero but never prints this.
 printf '%s\n' "$out" | grep -qx "cache-writefail: OK" || {
     echo "expected 'cache-writefail: OK', got: $out" >&2
     exit 1

tests/01_engine-cache.test

@@ -4,7 +4,7 @@
 # POSIX /bin/sh on some platforms (e.g. macOS), so avoid bashisms and GNU-only
 # tool flags despite the #!/bin/bash above.
 
-# Cache create/read/update logic (driven by 'httrack -#A <dir>').
+# Cache create/read/update logic (driven by 'httrack -#test=cache <dir>').
 #
 # The in-process self-test stores several hand-crafted edge entries (normal
 # HTML, an empty redirect with a near-limit location, a non-HTML body kept via
@@ -20,13 +20,13 @@ set -eu
 dir=$(mktemp -d)
 trap 'rm -rf "$dir"' EXIT
 
-# Like the other -# debug modes, a trailing token (the working directory) is
-# required; a bare '-#A' falls through to the usage screen.
-out=$(httrack -#A "$dir")
+# The working directory is a required argument; without it the test prints a
+# usage line to stderr and returns non-zero.
+out=$(httrack -#test=cache "$dir")
 
 # Match the exact success line, so the test cannot pass for an unrelated reason
-# (e.g. the -#A mode being gone and falling through to the usage screen, which
-# also exits non-zero but never prints this).
+# (e.g. the cache test being gone, which prints the registry to stderr but
+# never prints this line).
 test "$out" = "cache-selftest: OK" || {
     echo "expected 'cache-selftest: OK', got: $out" >&2
     exit 1

tests/01_engine-charset.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # charset -> UTF-8 conversion (hts_convertStringToUTF8).
-# -#3 <charset> <string> prints the string re-decoded from <charset> as UTF-8.
+# -#test=charset <charset> <string> prints the string re-decoded from <charset> as UTF-8.
 conv() {
-    test "$(httrack -O /dev/null -#3 "$1" "$2")" == "$3" || exit 1
+    test "$(httrack -O /dev/null -#test=charset "$1" "$2")" == "$3" || exit 1
 }
 # crash probe: malformed input must exit cleanly, not abort.
 runs() {
-    httrack -O /dev/null -#3 "$1" "$2" >/dev/null 2>&1 || exit 1
+    httrack -O /dev/null -#test=charset "$1" "$2" >/dev/null 2>&1 || exit 1
 }
 
 # the source bytes below are UTF-8 (this file is UTF-8); "café" is 0x63 61 66 C3 A9.
@@ -31,7 +31,7 @@ conv 'us-ascii' 'hello' 'hello'
 # unknown charset: ASCII passes through unchanged, but non-ASCII input cannot be
 # decoded and yields empty output (an error is printed to stderr).
 conv 'no-such-charset-xyz' 'abc' 'abc'
-test "$(httrack -O /dev/null -#3 'no-such-charset-xyz' 'café' 2>/dev/null)" == "" || exit 1
+test "$(httrack -O /dev/null -#test=charset 'no-such-charset-xyz' 'café' 2>/dev/null)" == "" || exit 1
 
 # malformed UTF-8 (lone continuation byte, truncated lead byte) must not crash
 runs 'utf-8' $'\x80'

tests/01_engine-cookies.test

@@ -1,14 +1,15 @@
 #!/bin/bash
 #
 # Issue #151 guard: the request Cookie header must be bare RFC 6265 name=value
-# pairs, no $Version/$Path attributes. Driven by the 'httrack -#Q' selftest.
+# pairs, no $Version/$Path attributes. Driven by the 'httrack -#test=cookies' selftest.
 
 set -eu
 
-# A trailing token is required; a bare '-#Q' falls through to the usage screen.
-out=$(httrack -#Q run)
+# 'run' is an ignored placeholder argument.
+out=$(httrack -#test=cookies run)
 
-# Exact-match the success line so a fall-through to usage can't pass the test.
+# Exact-match the success line so a renamed/removed test (it prints the registry
+# to stderr) can't pass.
 test "$out" = "cookie-header: OK" || {
     echo "expected 'cookie-header: OK', got: $out" >&2
     exit 1

tests/01_engine-copyopt.test

@@ -2,15 +2,16 @@
 #
 # Regression guard for the unsigned-enum sentinel trap: copy_htsopt's
 # `if (from->X > -1)` guard is always false for unsigned hts_boolean fields, so
-# they silently stop being copied. Driven by the in-process 'httrack -#9' test.
+# they silently stop being copied. Driven by the in-process 'httrack -#test=copyopt' test.
 # Keep POSIX-portable (harness runs it via $(BASH), a plain /bin/sh on macOS).
 
 set -eu
 
-# A trailing token is required; a bare '-#9' falls through to the usage screen.
-out=$(httrack -#9 run)
+# 'run' is an ignored placeholder argument.
+out=$(httrack -#test=copyopt run)
 
-# Exact-match the success line so a fall-through to usage can't pass the test.
+# Exact-match the success line so a renamed/removed test (it prints the registry
+# to stderr) can't pass.
 test "$out" = "copy-htsopt: OK" || {
     echo "expected 'copy-htsopt: OK', got: $out" >&2
     exit 1

tests/01_engine-dns.test

@@ -5,9 +5,8 @@ set -euo pipefail
 
 # DNS resolver/cache self-test: a mock getaddrinfo (no network) checks address
 # family, single-address selection, the -@i4/-@i6 family filter, and cache reuse.
-# The trailing token is required, like the other -# selftests, so a bare command
-# line isn't treated as "no arguments" and routed to the usage screen.
-out=$(httrack -#D run)
+# 'run' is an ignored placeholder argument.
+out=$(httrack -#test=dns run)
 
 test "$out" = "dns-selftest: OK" || {
     echo "expected 'dns-selftest: OK', got: $out" >&2

tests/01_engine-entities.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # HTML entity unescaping (hts_unescapeEntitiesWithCharset).
-# -#6 <string> prints the string with entities decoded (UTF-8 output).
+# -#test=entities <string> prints the string with entities decoded (UTF-8 output).
 ent() {
-    test "$(httrack -O /dev/null -#6 "$1")" == "$2" || exit 1
+    test "$(httrack -O /dev/null -#test=entities "$1")" == "$2" || exit 1
 }
 # crash probe: malformed input must exit cleanly, not abort.
 runs() {
-    httrack -O /dev/null -#6 "$1" >/dev/null 2>&1 || exit 1
+    httrack -O /dev/null -#test=entities "$1" >/dev/null 2>&1 || exit 1
 }
 
 # named entities

tests/01_engine-filelist.test

@@ -0,0 +1,65 @@
+#!/bin/bash
+#
+# -%L URL-list loading (#49): a readable list is honored; an unusable one fails
+# with the reason (errno / not-a-regular-file), not a bare "Could not include
+# URL list". Offline: file:// fixture, no server. Asserts on httrack's own
+# strings and the message shape, so it is locale-independent.
+
+set -euo pipefail
+
+tmp=$(mktemp -d "${TMPDIR:-/tmp}/httrack_filelist.XXXXXX") || exit 1
+trap 'rm -rf "$tmp"' EXIT HUP INT QUIT PIPE TERM
+
+echo '<html><body>hi</body></html>' >"$tmp/index.html"
+
+# run httrack with the given -%L target; structured log lands in $out/hts-log.txt
+run() {
+    local out="$1" list="$2"
+    rm -rf "$out"
+    mkdir -p "$out"
+    httrack -O "$out" --quiet -n "-%L" "$list" >"$out/.stdout" 2>&1 || true
+    LOG="$out/hts-log.txt"
+}
+
+fail() {
+    echo "FAIL: $1"
+    cat "$LOG"
+    exit 1
+}
+loghas() {
+    grep -Eq "$1" "$LOG" || fail "expected /$1/ in $LOG"
+}
+lognot() {
+    if grep -Eq "$1" "$LOG"; then fail "unexpected /$1/ in $LOG"; fi
+}
+
+# readable list: its one URL is loaded and counted (count must be non-zero)
+printf 'file://%s/index.html\n' "$tmp" >"$tmp/urls.txt"
+run "$tmp/ok" "$tmp/urls.txt"
+loghas '[1-9][0-9]* links added from'
+
+# missing file: quoted name + a non-empty reason, never the old reasonless
+# "Could not include URL list: <name>". The reason is the stat() errno, not the
+# directory fallback literal (guards against dropping the errno lookup).
+run "$tmp/miss" "$tmp/nope.txt"
+loghas 'Could not include URL list "[^"]+": .+'
+lognot 'Could not include URL list: '
+lognot 'not a regular file'
+
+# a directory is rejected with our own reason (locale-independent)
+mkdir -p "$tmp/adir"
+run "$tmp/dir" "$tmp/adir"
+loghas 'Could not include URL list "[^"]+": not a regular file'
+
+# unreadable regular file: the fopen() errno arm fires, distinct from the
+# directory branch. Root bypasses mode 000, so skip it there.
+if test "$(id -u)" -ne 0; then
+    : >"$tmp/noperm.txt"
+    chmod 000 "$tmp/noperm.txt"
+    run "$tmp/perm" "$tmp/noperm.txt"
+    chmod 644 "$tmp/noperm.txt"
+    loghas 'Could not include URL list "[^"]+": .+'
+    lognot 'not a regular file'
+fi
+
+exit 0

tests/01_engine-filter.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # wildcard filter engine (strjoker), the core of +/- include/exclude rules.
-# -#0 <filter> <string> prints "<string> does match <filter>" or "... does NOT match ...".
+# -#test=filter <filter> <string> prints "<string> does match <filter>" or "... does NOT match ...".
 
 match() {
-    test "$(httrack -O /dev/null -#0 "$1" "$2")" == "$2 does match $1" || exit 1
+    test "$(httrack -O /dev/null -#test=filter "$1" "$2")" == "$2 does match $1" || exit 1
 }
 nomatch() {
-    test "$(httrack -O /dev/null -#0 "$1" "$2")" == "$2 does NOT match $1" || exit 1
+    test "$(httrack -O /dev/null -#test=filter "$1" "$2")" == "$2 does NOT match $1" || exit 1
 }
 
 # bare star matches everything
@@ -71,3 +71,27 @@ nomatch '*[\[\]]' '[' # not matched, despite the docs
 match '*[\[\]]' ']'   # only via the empty class-match + trailing ']'
 match '*[\[\]]' '[]'  # one of {'[','\'} then the trailing ']'
 nomatch '*[\[\]]' '[]x'
+
+# Size-based rules (-#test=filtersize <size> <string> <filter...>): a negative size
+# means the size is still unknown (scan time). A size exclusion must stay neutral
+# then, so the file is fetched and only cancelled once its size is known (#143).
+fsize() {
+    local want="$1"
+    shift
+    test "$(httrack -O /dev/null -#test=filtersize "$@")" == "$want" || exit 1
+}
+fsize 'verdict=allowed size_flag=0' -1 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'   # scan time: keep
+fsize 'verdict=forbidden size_flag=1' 5 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'  # <10KB: cancel
+fsize 'verdict=allowed size_flag=1' 20 foo.jpg -* '+*.jpg' '-*.jpg*[<10]'   # >=10KB: keep
+fsize 'verdict=forbidden size_flag=0' -1 foo.txt -* '+*.jpg' '-*.jpg*[<10]' # not a jpg
+# the '>' operator is just as neutral at scan time, and fires once size is known
+fsize 'verdict=allowed size_flag=0' -1 foo.jpg -* '+*.jpg' '-*.jpg*[>10]'   # scan time: keep
+fsize 'verdict=forbidden size_flag=1' 20 foo.jpg -* '+*.jpg' '-*.jpg*[>10]' # >10KB: cancel
+
+# [name]/[file]/[path] never span '?' mid-string; a trailing query is still
+# tolerated by the global '?' rule (same as plain *.aspx), not the class (#144).
+nomatch '*[path]/end' 'a?b/end'
+nomatch '*[file]end' 'foo?xend'
+nomatch '*[name]X' 'abc?X'
+match '*[file]' 'foo?x=1' # trailing query: tolerated, as for *.aspx
+match '*.aspx' 'page.aspx?y=2'

tests/01_engine-hashtable.test

@@ -3,5 +3,7 @@
 
 set -euo pipefail
 
-# httrack internal hashtable autotest on 100K keys
-httrack -#7 100000
+# httrack internal hashtable autotest on 100K keys. Assert the success line (on
+# stderr) so a misrouted registry entry can't pass on exit code alone.
+out=$(httrack -#test=hashtable 100000 2>&1)
+printf '%s\n' "$out" | grep -q "all hashtable tests were successful!" || exit 1

tests/01_engine-idna.test

@@ -3,13 +3,13 @@
 
 set -euo pipefail
 
-# IDNA / punycode encode (-#4) and decode (-#5). This code has a CVE history,
+# IDNA / punycode encode (-#test=idna-encode) and decode (-#test=idna-decode). This code has a CVE history,
 # so the edge cases below cover passthrough, round-trips, and malformed input.
 
-enc() { test "$(httrack -O /dev/null -#4 "$1")" == "$2" || exit 1; }
-dec() { test "$(httrack -O /dev/null -#5 "$1")" == "$2" || exit 1; }
+enc() { test "$(httrack -O /dev/null -#test=idna-encode "$1")" == "$2" || exit 1; }
+dec() { test "$(httrack -O /dev/null -#test=idna-decode "$1")" == "$2" || exit 1; }
 # crash probe: malformed ACE input must exit cleanly, not abort.
-runs() { httrack -O /dev/null -#5 "$1" >/dev/null 2>&1 || exit 1; }
+runs() { httrack -O /dev/null -#test=idna-decode "$1" >/dev/null 2>&1 || exit 1; }
 
 # encode
 enc 'www.café.com' 'www.xn--caf-dma.com'

tests/01_engine-mime.test

@@ -4,13 +4,13 @@
 set -euo pipefail
 
 # MIME type guessing from extension (get_httptype / give_mimext).
-# -#2 <path> prints "<path> is '<mime>'" then "and its local type is '.<ext>'".
+# -#test=mime <path> prints "<path> is '<mime>'" then "and its local type is '.<ext>'".
 
 mime() {
-    test "$(httrack -O /dev/null -#2 "$1" | head -1)" == "$1 is '$2'" || exit 1
+    test "$(httrack -O /dev/null -#test=mime "$1" | head -1)" == "$1 is '$2'" || exit 1
 }
 unknown() {
-    test "$(httrack -O /dev/null -#2 "$1" | head -1)" == "$1 is of an unknown MIME type" || exit 1
+    test "$(httrack -O /dev/null -#test=mime "$1" | head -1)" == "$1 is of an unknown MIME type" || exit 1
 }
 
 mime '/a/b.html' 'text/html'

tests/01_engine-relative.test

@@ -8,7 +8,7 @@ set -euo pipefail
 # relative path from <curr>'s directory to <link>
 rel() {
     local got
-    got=$(httrack -O /dev/null -#l "$1" "$2")
+    got=$(httrack -O /dev/null -#test=relative "$1" "$2")
     test "$got" == "relative=$3" ||
         {
             echo "FAIL rel($1, $2): got '$got' want 'relative=$3'"
@@ -19,7 +19,7 @@ rel() {
 # resolve <link> against origin <adr>/<fil> -> adr=.. fil=..
 ident() {
     local got
-    got=$(httrack -O /dev/null -#i "$1" "$2" "$3")
+    got=$(httrack -O /dev/null -#test=resolve "$1" "$2" "$3")
     test "$got" == "$4" ||
         {
             echo "FAIL ident($1, $2, $3): got '$got' want '$4'"

tests/01_engine-savename.test

@@ -3,11 +3,11 @@
 
 set -euo pipefail
 
-# Local save-name extension resolution (url_savename via -#N <fil> <content-type>).
+# Local save-name extension resolution (url_savename via -#test=savename <fil> <content-type>).
 # Asserts on the basename of "savename: <path>".
 
 name() {
-    out="$(httrack -O /dev/null -#N "$1" "$2" | sed -n 's/^savename: //p')"
+    out="$(httrack -O /dev/null -#test=savename "$1" "$2" | sed -n 's/^savename: //p')"
     test "${out##*/}" == "$3" || {
         echo "FAIL: '$1' '$2' -> '$out' (want '$3')"
         exit 1

tests/01_engine-selftest-dispatch.test

@@ -0,0 +1,17 @@
+#!/bin/bash
+#
+# The -#test dispatch itself: a bare -#test lists the registry, and an unknown
+# name errors (non-zero, diagnostic) instead of silently passing.
+
+set -eu
+
+# Bare -#test lists known tests (printed to stderr).
+list=$(httrack -#test 2>&1)
+printf '%s\n' "$list" | grep -q "filter" || exit 1
+printf '%s\n' "$list" | grep -q "cache-writefail" || exit 1
+
+# Unknown name: non-zero exit + diagnostic, and no test result line.
+rc=0
+err=$(httrack -#test=bogus 2>&1) || rc=$?
+test "$rc" -ne 0 || exit 1
+printf '%s\n' "$err" | grep -q "Unknown self-test" || exit 1

tests/01_engine-simplify.test

@@ -5,7 +5,7 @@ set -euo pipefail
 
 # path simplify engine (fil_simplifie): collapses ./ and ../ segments.
 simp() {
-    test "$(httrack -O /dev/null -#1 "$1")" == "simplified=$2" || exit 1
+    test "$(httrack -O /dev/null -#test=simplify "$1")" == "simplified=$2" || exit 1
 }
 
 simp './foo/bar/' 'foo/bar/'

tests/01_engine-stripquery.test

@@ -0,0 +1,8 @@
+#!/bin/bash
+#
+
+set -euo pipefail
+
+# --strip-query: pattern-scoped query-key stripping for dedup. All assertions
+# live in the engine self-test (hts_query_strip_keys + fil_normalized_filtered).
+httrack -O /dev/null -#test=stripquery | grep -q "strip-query self-test OK"

tests/01_engine-strsafe.test

@@ -3,23 +3,22 @@
 
 set -euo pipefail
 
-# htssafe.h bounded string operations (driven by 'httrack -#8').
+# htssafe.h bounded string operations (driven by 'httrack -#test=strsafe').
 
 # Success path: every bounded op (strcpybuff/strcatbuff/strncatbuff/strlcpybuff)
-# must behave correctly. Like the other -# debug modes, a trailing token is
-# required (a bare '-#8' falls through to the usage screen).
+# must behave correctly. 'run' selects the success path (vs the overflow modes).
 rc=0
-out=$(httrack -#8 run) || rc=$?
+out=$(httrack -#test=strsafe run) || rc=$?
 test "$rc" -eq 0 || exit 1
 test "$out" == "strsafe: OK" || exit 1
 
 # Overflow path: an over-capacity write into a sized buffer must be caught by
 # the bounded macro and abort the process, not be silently truncated/completed.
 # Assert the htssafe abort signature specifically, so the test cannot pass for
-# an unrelated reason (e.g. the -#8 mode being gone and falling through to the
-# usage screen, which also exits non-zero).
+# an unrelated reason (e.g. the strsafe test being gone, which prints the
+# registry to stderr and also exits non-zero).
 # the bounded macro aborts (non-zero exit), so don't let set -e trip on it
-err=$(httrack -#8 overflow "this string is far too long for the buffer" 2>&1) || true
+err=$(httrack -#test=strsafe overflow "this string is far too long for the buffer" 2>&1) || true
 case "$err" in
 *"strsafe: NOT aborted"*)
     echo "over-capacity write was NOT caught" >&2
@@ -36,7 +35,7 @@ esac
 # capacity (4 bytes into a 4-byte buffer), so this also pins the boundary: a
 # '<=' off-by-one in the capacity check would let it through (and print "NOT
 # aborted"). Match the specific htsbuff abort message, not just any assert.
-err=$(httrack -#8 overflow-buff "abcd" 2>&1) || true
+err=$(httrack -#test=strsafe overflow-buff "abcd" 2>&1) || true
 case "$err" in
 *"strsafe: NOT aborted"*)
     echo "htsbuff over-capacity write was NOT caught" >&2

tests/24_local-resume-overlap.test

@@ -0,0 +1,109 @@
+#!/bin/bash
+# Issue #198: on a resumed download the server may answer the Range with a 206
+# that starts *before* the offset we asked for (block-aligned ranges). httrack
+# must honor the returned Content-Range, not blindly append, or the overlap
+# bytes get duplicated and the file grows (corrupt PDFs). Pass 1 interrupts
+# flaky.bin mid-body (partial + temp-ref); pass 2 resumes against a 206 that
+# backs up 8 bytes. The result must equal the same bytes fetched whole (full.bin).
+set -eu
+
+: "${top_srcdir:=..}"
+testdir=$(cd "$(dirname "$0")" && pwd)
+server="${testdir}/local-server.py"
+
+command -v python3 >/dev/null || ! echo "python3 not found; skipping" || exit 77
+
+tmpdir=$(mktemp -d "${TMPDIR:-/tmp}/httrack_198.XXXXXX") || exit 1
+serverpid=
+crawlpid=
+cleanup() {
+    if test -n "$crawlpid"; then kill -9 "$crawlpid" 2>/dev/null || true; fi
+    if test -n "$serverpid"; then
+        kill "$serverpid" 2>/dev/null || true
+        wait "$serverpid" 2>/dev/null || true
+    fi
+    rm -rf "$tmpdir"
+}
+trap cleanup EXIT HUP INT QUIT PIPE TERM
+
+# OVERLAP_COUNTER gets a byte per flaky.bin request so pass 1 knows when to interrupt.
+serverlog="${tmpdir}/server.log"
+counter="${tmpdir}/hits"
+resumed="${tmpdir}/resumed" # gets a byte when the server serves a resume 206
+OVERLAP_COUNTER="$counter" OVERLAP_RESUMED="$resumed" \
+    python3 "$server" --root "${testdir}/server-root" \
+    >"$serverlog" 2>&1 &
+serverpid=$!
+port=
+for _ in $(seq 1 50); do
+    line=$(head -n1 "$serverlog" 2>/dev/null)
+    if test "${line%% *}" == "PORT"; then
+        port="${line#PORT }"
+        break
+    fi
+    kill -0 "$serverpid" 2>/dev/null || {
+        echo "server exited early: $(cat "$serverlog")"
+        exit 1
+    }
+    sleep 0.1
+done
+test -n "$port" || {
+    echo "could not discover server port"
+    exit 1
+}
+base="http://127.0.0.1:${port}"
+
+which httrack >/dev/null || {
+    echo "could not find httrack"
+    exit 1
+}
+out="${tmpdir}/crawl"
+common=(-O "$out" --quiet --disable-security-limits --robots=0 --timeout=30 --retries=0 -c1)
+refdir="${out}/hts-cache/ref"
+
+# pass 1: interrupt once flaky.bin's prefix is streaming (partial + temp-ref).
+printf '[pass 1: interrupt flaky.bin] ..\t'
+httrack "${common[@]}" "${base}/overlap/index.html" >"${tmpdir}/log1" 2>&1 &
+crawlpid=$!
+for _ in $(seq 1 300); do
+    test -s "$counter" && break
+    kill -0 "$crawlpid" 2>/dev/null || break
+    sleep 0.1
+done
+sleep 0.5
+kill -TERM "$crawlpid" 2>/dev/null || true
+wait "$crawlpid" 2>/dev/null || true
+crawlpid=
+test -n "$(find "$refdir" -name '*.ref' 2>/dev/null)" || {
+    echo "FAIL: no temp-ref survived pass 1; cannot drive the resume"
+    exit 1
+}
+echo "OK (temp-ref present)"
+
+# pass 2: --continue -> resume Range -> 206 that starts 8 bytes early.
+printf '[pass 2: resume flaky.bin] ..\t'
+httrack "${common[@]}" --continue "${base}/overlap/index.html" >"${tmpdir}/log2" 2>&1 || true
+echo "OK"
+
+# Guard against a silent full re-download: the byte-compare below only tests the
+# fix if pass 2 actually went through the resume Range -> 206 path.
+printf '[resume path was exercised] ..\t'
+if ! test -s "$resumed"; then
+    echo "FAIL: pass 2 never triggered a resume 206; the overlap fix was not exercised"
+    exit 1
+fi
+echo "OK"
+
+printf '[resumed file is not corrupted] ..\t'
+dir=$(find "$out" -maxdepth 1 -type d -name '127.0.0.1*' | head -1)
+flaky="${dir}/overlap/flaky.bin"
+full="${dir}/overlap/full.bin"
+if ! test -f "$flaky" || ! test -f "$full"; then
+    echo "FAIL: flaky.bin or full.bin missing after pass 2"
+    exit 1
+fi
+if ! cmp -s "$flaky" "$full"; then
+    echo "FAIL: resumed flaky.bin ($(wc -c <"$flaky")) != full.bin ($(wc -c <"$full")); overlap duplicated"
+    exit 1
+fi
+echo "OK ($(wc -c <"$flaky") bytes, byte-identical)"

tests/25_local-mime-exclude.test

@@ -0,0 +1,16 @@
+#!/bin/bash
+#
+# A -mime: exclusion must abort the transfer on the response Content-Type, not
+# fetch the whole 1 MB body then discard it (#58). The bytes-received guard is
+# the real one: the file is absent either way, but only the fix keeps the count
+# tiny (header only) instead of pulling the body. Match it positively (a small,
+# <=4-digit count) so a vanished/reworded summary line fails rather than passes.
+
+: "${top_srcdir:=..}"
+
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
+    --found 'mimex/real.html' \
+    --not-found 'mimex/blob.pdf' \
+    --log-found 'excluded by MIME type filter' \
+    --log-found '\[[0-9]{1,4} bytes received' \
+    httrack 'BASEURL/mimex/index.html' '-mime:application/pdf'

tests/26_local-strip-query.test

@@ -0,0 +1,18 @@
+#!/bin/bash
+#
+# End-to-end --strip-query (#112): two links to one resource differing only by
+# ?utm_source dedup to a single saved file (2 files written: index + resource);
+# the control crawl without the option keeps both variants (3 files). Locks the
+# CLI->opt->hash plumbing the engine self-test can't reach.
+
+set -e
+
+: "${top_srcdir:=..}"
+
+# stripped: the two ?utm_source variants collapse to one resource
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 --files 2 \
+    httrack 'BASEURL/stripquery/index.html' --strip-query 'utm_source'
+
+# control: no stripping -> both query-named variants are saved
+bash "$top_srcdir/tests/local-crawl.sh" --errors 0 --files 3 \
+    httrack 'BASEURL/stripquery/index.html'

tests/Makefile.am

@@ -5,6 +5,7 @@ EXTRA_DIST = $(TESTS) crawl-test.sh run-all-tests.sh check-network.sh \
 	proxy-https-server.py \
 	local-crawl.sh local-server.py server.crt server.key \
 	server-root/simple/basic.html server-root/simple/link.html \
+	server-root/stripquery/index.html server-root/stripquery/a.html \
 	fixtures/cache-golden/hts-cache/new.zip
 
 TESTS_ENVIRONMENT =
@@ -34,6 +35,7 @@ TESTS = \
 	01_engine-dns.test \
 	01_engine-doitlog.test \
 	01_engine-entities.test \
+	01_engine-filelist.test \
 	01_engine-filter.test \
 	01_engine-hashtable.test \
 	01_engine-idna.test \
@@ -42,7 +44,9 @@ TESTS = \
 	01_engine-rcfile.test \
 	01_engine-relative.test \
 	01_engine-savename.test \
+	01_engine-selftest-dispatch.test \
 	01_engine-simplify.test \
+	01_engine-stripquery.test \
 	01_engine-strsafe.test \
 	02_manpage-regen.test \
 	02_update-cache.test \
@@ -64,6 +68,9 @@ TESTS = \
 	20_local-resume-loop.test \
 	21_local-intl-update.test \
 	22_local-broken-size.test \
-	23_local-errpage.test
+	23_local-errpage.test \
+	24_local-resume-overlap.test \
+	25_local-mime-exclude.test \
+	26_local-strip-query.test
 
 CLEANFILES = check-network_sh.cache

tests/local-server.py

@@ -177,6 +177,24 @@ class Handler(SimpleHTTPRequestHandler):
         body, ctype = self.TYPE_MATRIX[path]
         self.send_raw(body, ctype)
 
+    # --- MIME-type exclusion abort (issue #58) -----------------------------
+    # A -mime:application/pdf filter must abort the transfer once the header
+    # arrives, not download the whole body and discard it.
+    def route_mimex_index(self):
+        self.send_html(
+            '\t<a href="blob.pdf">pdf</a>\n' '\t<a href="real.html">real</a>\n'
+        )
+
+    # 1 MB body: the fix aborts after the header, so httrack's "bytes received"
+    # stays tiny; without it the engine reads the body and the count jumps.
+    MIMEX_BLOB = b"%PDF-1.4\n" + b"\x00" * (1024 * 1024)
+
+    def route_mimex_blob(self):
+        self.send_raw(self.MIMEX_BLOB, "application/pdf")
+
+    def route_mimex_real(self):
+        self.send_raw(b"<html><body>real</body></html>", "text/html")
+
     # --- special chars in URLs across an update (issue #157) ---------------
     # A dotless, accented basename served as text/html (MediaWiki style). The
     # name the first crawl picks (.html) must survive the update pass.
@@ -225,6 +243,71 @@ class Handler(SimpleHTTPRequestHandler):
         self.send_header("Content-Length", "0")
         self.end_headers()
 
+    # 206 resume must honor the server's Content-Range, not the offset we asked
+    # for (#198): a server resuming a few bytes *before* the request must not
+    # leave httrack duplicating the overlap onto the partial. flaky.bin
+    # interrupts once then resumes OVERLAP_EARLY bytes early; full.bin serves
+    # the identical bytes in one shot, so the test can compare the two.
+    OVERLAP_BLOB = b"%PDF-1.4\n" + bytes((i * 37 + 11) % 256 for i in range(8000))
+    OVERLAP_EARLY = 8
+    OVERLAP_PREFIX_LEN = 4000  # flushed before the stall
+    _overlap_started = False
+
+    def route_overlap_index(self):
+        self.send_html('\t<a href="flaky.bin">flaky</a>\n\t<a href="full.bin">full</a>')
+
+    def route_overlap_full(self):
+        self.send_raw(self.OVERLAP_BLOB, "application/octet-stream")
+
+    def route_overlap(self):
+        counter = os.environ.get("OVERLAP_COUNTER")
+        if counter:
+            with open(counter, "a") as fp:
+                fp.write("x")
+        blob = self.OVERLAP_BLOB
+        rng = self.headers.get("Range")
+        # First GET: stream a prefix then stall, so the crawl can be interrupted
+        # mid-body (partial + temp-ref on disk).
+        if rng is None and not Handler._overlap_started:
+            Handler._overlap_started = True
+            self.send_response(200)
+            self.send_header("Content-Type", "application/octet-stream")
+            self.send_header("Content-Length", str(len(blob)))
+            self.send_header("Accept-Ranges", "bytes")
+            self.end_headers()
+            if self.command != "HEAD":
+                self.wfile.write(blob[: self.OVERLAP_PREFIX_LEN])
+                self.wfile.flush()
+                try:
+                    while True:
+                        time.sleep(3600)
+                except OSError:
+                    pass
+            return
+        if rng is None:  # no resume request: serve the whole file
+            return self.route_overlap_full()
+        # Resume: honor the Range, but back up OVERLAP_EARLY bytes.
+        start = (
+            int(rng[len("bytes=") :].split("-")[0]) if rng.startswith("bytes=") else 0
+        )
+        start = max(0, start - self.OVERLAP_EARLY)
+        # Signal that the resume Range -> 206 path actually fired, so the test
+        # can prove it was exercised (not a silent full re-download).
+        resumed = os.environ.get("OVERLAP_RESUMED")
+        if resumed:
+            with open(resumed, "a") as fp:
+                fp.write("x")
+        part = blob[start:]
+        self.send_response(206, "Partial Content")
+        self.send_header("Content-Type", "application/octet-stream")
+        self.send_header("Content-Length", str(len(part)))
+        self.send_header(
+            "Content-Range", "bytes %d-%d/%d" % (start, len(blob) - 1, len(blob))
+        )
+        self.end_headers()
+        if self.command != "HEAD":
+            self.wfile.write(part)
+
     # error pages / 0-byte files (#17): -o0 ("no error pages") must keep 4xx/5xx
     # bodies off disk; a genuine 0-byte 200 is a valid file and stays.
     def route_errpage_index(self):
@@ -281,12 +364,18 @@ class Handler(SimpleHTTPRequestHandler):
         "/intl/" + INTL_NAME: route_intl_page,
         "/resume/index.html": route_resume_index,
         "/resume/blob.txt": route_resume,
+        "/overlap/index.html": route_overlap_index,
+        "/overlap/flaky.bin": route_overlap,
+        "/overlap/full.bin": route_overlap_full,
         "/size/index.html": route_size_index,
         "/size/oversize.bin": route_size_oversize,
         "/errpage/index.html": route_errpage_index,
         "/errpage/good.html": route_errpage_good,
         "/errpage/missing.html": route_errpage_missing,
         "/errpage/empty.html": route_errpage_empty,
+        "/mimex/index.html": route_mimex_index,
+        "/mimex/blob.pdf": route_mimex_blob,
+        "/mimex/real.html": route_mimex_real,
     }
 
     # --- dispatch ----------------------------------------------------------

tests/server-root/stripquery/a.html

@@ -0,0 +1 @@
+<html><body>resource A</body></html>

tests/server-root/stripquery/index.html

@@ -0,0 +1,5 @@
+<html><body>
+Two links to one resource, differing only by a tracking parameter.
+<a href="a.html?utm_source=x">x</a>
+<a href="a.html?utm_source=y">y</a>
+</body></html>