Drop the per-request pre-resolve that slowed crawls on non-default ports (#181 )

back_solve() resolved the raw "host:port" authority once per backing request through check_hostname_dns() — an uncached getaddrinfo whose result was only logged (host_wait() is always synchronous now). The connect path already strips the port and resolves through the DNS cache, so this lookup was pure overhead. On resolvers that don't fail fast on the malformed "host:port" name (search-domain expansion, DNS timeouts) it added a per-request stall: the reported slowness. Mirrors on port 80, or with the port omitted, avoided the bad name and stayed fast. Remove back_solve() and its debug-only lookup; keep the synchronous host_wait() gate. Add a DNS self-test pinning that the cache/connect path resolves "host:port" as the bare host. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: Xavier Roche <roche@httrack.com>
2026-07-11 19:36:52 +03:00 · 2026-07-11 00:08:17 +02:00
19 changed files with 178 additions and 636 deletions
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -55,9 +55,7 @@ jobs:
        run: make -j"$(nproc)"

      - name: Test
-        run: |
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check

      - name: Print the test log on failure
        if: failure()
@@ -101,8 +99,7 @@ jobs:
          sudo find /usr/bin /usr/local/bin -maxdepth 1 -name 'python3*' \
            -exec mv {} {}.hidden \;
          ! command -v python3
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+          make check

      - name: Print the test log on failure
        if: failure()
@@ -136,15 +133,7 @@ jobs:
        run: make -j"$(sysctl -n hw.ncpu)"

      - name: Test
-        # bigcrawl's sustained -c8 crawl drops fetches on macOS's loopback when
-        # it competes with other crawls, flaking its exact file count (the #527
-        # macOS drop). Run everything else in parallel, then bigcrawl alone (its
-        # serial-safe condition). Linux tolerates the full parallel run.
-        run: |
-          jobs=$(( $(sysctl -n hw.ncpu) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          rest=$(cd tests && ls *.test | grep -v '^36_local-bigcrawl\.test$' | tr '\n' ' ')
-          make check -j"$jobs" TESTS="$rest"
-          make check TESTS=36_local-bigcrawl.test
+        run: make check

      - name: Print the test log on failure
        if: failure()
@@ -182,9 +171,7 @@ jobs:
        run: make -j"$(nproc)"

      - name: Test
-        run: |
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check

      - name: Print the test log on failure
        if: failure()
@@ -239,9 +226,7 @@ jobs:
        env:
          ASAN_OPTIONS: detect_leaks=0:abort_on_error=1:halt_on_error=1:strict_string_checks=1:malloc_fill_byte=202:max_malloc_fill_size=2147483647:free_fill_byte=203:max_free_fill_size=2147483647
          UBSAN_OPTIONS: print_stacktrace=1:halt_on_error=1
-        run: |
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check

      - name: Print the test log on failure
        if: failure()
@@ -287,8 +272,7 @@ jobs:
          # 01_engine-* only; zlib-dependent self-tests are named 01_zlib-* and
          # skipped here (uninstrumented libz floods MSan with false positives).
          tests="$(cd tests && ls 01_engine-*.test | tr '\n' ' ')"
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs" TESTS="$tests"
+          make check TESTS="$tests"

      - name: Print the test log on failure
        if: failure()
@@ -363,9 +347,7 @@ jobs:
        run: make -j"$(nproc)"

      - name: Test
-        run: |
-          jobs=$(( $(nproc) * 2 )); [ "$jobs" -le 16 ] || jobs=16
-          make check -j"$jobs"
+        run: make check

      - name: Print the test log on failure
        if: failure()
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -6,19 +6,8 @@ the operational checklist: toolchain, invariants, and how to ship a change.
 ## Build & test
 - Fresh clone first: `git submodule update --init src/coucal`
 - `./bootstrap` (regenerates `configure` via `autoreconf`; needs autoconf,
-  automake, libtool), then `bash configure && make -j"$(nproc)" && make check
-  -j"$(nproc)"`. Always pass `-j` to `make check`: the suite runs under
-  automake's parallel harness and each crawl test binds its own ephemeral-port
-  server, so `-j` never contends and a multi-minute serial run drops to
-  seconds. A new `.test` added to `$(TESTS)` is scheduled onto a free worker
-  automatically; only a test slower than the current longest raises the floor.
-  On a few-core Linux box, `-j` at 2x the core count is faster still: the tests
-  spend much of their wall time asleep (server trickles, httrack self-pacing),
-  so an idle core covers a sleeping one. CI uses `min(2*cores, 16)`. macOS runs
-  36_local-bigcrawl alone in a second pass: its sustained `-c8` crawl overloads
-  the macOS loopback when it competes with other crawls and flakes its exact
-  file count (Linux tolerates the full parallel run).
-  Or run `sh build.sh` to do bootstrap + configure + make in one shot.
+  automake, libtool), then `bash configure && make && make check`. Or run
+  `sh build.sh` to do bootstrap + configure + make in one shot.

 ## Hard invariants
 - **Generated autotools files are NOT in git.** `configure`, every
--- a/src/htsback.c
+++ b/src/htsback.c
@@ -68,15 +68,6 @@ static int slot_can_be_cached_on_disk(const lien_back * back);
 static int slot_can_be_cleaned(const lien_back * back);
 static int slot_can_be_finalized(httrackp * opt, const lien_back * back);

-/* Which hard quota, if any, is currently aborting the mirror. */
-typedef enum {
-  HTS_MIRROR_LIMIT_NONE = 0,
-  HTS_MIRROR_LIMIT_SIZE,
-  HTS_MIRROR_LIMIT_TIME,
-} hts_mirror_limit;
-
-static hts_mirror_limit back_mirror_limit(httrackp *opt);
-
 struct_back *back_new(httrackp *opt, int back_max) {
  int i;
  struct_back *sback = calloct(1, sizeof(struct_back));
@@ -533,22 +524,22 @@ int back_nsoc_overall(const struct_back * sback) {

 /* generate temporary file on lien_back */
 /* Note: utf-8 */
-static int create_back_tmpfile(httrackp *opt, lien_back *const back,
-                               const char *ext) {
+static int create_back_tmpfile(httrackp * opt, lien_back *const back) {
  // do not use tempnam() but a regular filename
  back->tmpfile_buffer[0] = '\0';
  if (back->url_sav != NULL && back->url_sav[0] != '\0') {
-    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.%s",
-             back->url_sav, ext);
+    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s.z", 
+             back->url_sav);
    back->tmpfile = back->tmpfile_buffer;
    if (structcheck(back->tmpfile) != 0) {
-      hts_log_print(opt, LOG_WARNING, "can not create directory to %s",
+      hts_log_print(opt, LOG_WARNING, "can not create directory to %s", 
                    back->tmpfile);
      return -1;
    }
  } else {
-    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer), "%s/tmp%d.%s",
-             StringBuff(opt->path_html_utf8), opt->state.tmpnameid++, ext);
+    snprintf(back->tmpfile_buffer, sizeof(back->tmpfile_buffer),
+             "%s/tmp%d.z", StringBuff(opt->path_html_utf8),
+             opt->state.tmpnameid++);
    back->tmpfile = back->tmpfile_buffer;
  }
  /* OK */
@@ -556,32 +547,6 @@ static int create_back_tmpfile(httrackp *opt, lien_back *const back,
  return 0;
 }

-/* Commit or restore a re-fetch backup (#77 follow-up): a re-fetch over an
-   existing file moved the good copy to back->tmpfile before truncating url_sav.
-   commit keeps the new file and drops the backup; else restore it so an aborted
-   transfer leaves the previous copy intact. Skips the zlib .z temp. */
-static void back_finalize_backup(httrackp *opt, lien_back *const back,
-                                 const hts_boolean commit) {
-  if (back->tmpfile == NULL || back->r.compressed)
-    return;
-  if (commit) {
-    (void) UNLINK(back->tmpfile); /* new copy is good; drop the backup */
-  } else {
-    if (back->r.out != NULL) {
-      fclose(back->r.out);
-      back->r.out = NULL;
-    }
-    (void) UNLINK(back->url_sav); /* drop the failed partial */
-    /* On rename failure keep the backup: it still holds the good copy, so
-       losing it would be worse than an orphaned temp. */
-    if (RENAME(back->tmpfile, back->url_sav) != 0)
-      hts_log_print(opt, LOG_WARNING | LOG_ERRNO,
-                    "could not restore %s; previous copy kept as %s",
-                    back->url_sav, back->tmpfile);
-  }
-  back->tmpfile = NULL;
-}
-
 // objet (lien) téléchargé ou transféré depuis le cache
 //
 // fermer les paramètres de transfert,
@@ -617,7 +582,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
                      LLintP " got " LLintP "): %s%s", back[p].r.totalsize,
                      back[p].r.size, back[p].url_adr, back[p].url_fil);
      }
-      back_finalize_backup(opt, &back[p], HTS_FALSE);
      return -1;
    }

@@ -636,7 +600,7 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
            // en mémoire -> passage sur disque
            if (!back[p].r.is_write) {
              // do not use tempnam() but a regular filename
-              if (create_back_tmpfile(opt, &back[p], "z") == 0) {
+              if (create_back_tmpfile(opt, &back[p]) == 0) {
                assertf(back[p].tmpfile != NULL);
                /* note: tmpfile is utf-8 */
                back[p].r.out = FOPEN(back[p].tmpfile, "wb");
@@ -709,9 +673,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
          }
        }
 #endif
-        /* Body fully received: keep the freshly written url_sav, drop the
-           backup of the previous copy. */
-        back_finalize_backup(opt, &back[p], HTS_TRUE);
        /* Write mode to disk */
        if (back[p].r.is_write && back[p].r.adr != NULL) {
          freet(back[p].r.adr);
@@ -940,9 +901,6 @@ int back_finalize(httrackp * opt, cache_back * cache, struct_back * sback,
      }
    }
  }
-  /* Aborted, error, or not ready: url_sav (if written) is broken; restore the
-     previous copy from the backup. */
-  back_finalize_backup(opt, &back[p], HTS_FALSE);
  return -1;
 }

@@ -2426,15 +2384,9 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
  back_clean(opt, cache, sback);
 #endif

-  /* Time/size limit exceeded past grace: abort in-flight transfers so no wait
-     loop starves (#481, #77). FTP slots stay, their thread owns the socket. */
+  /* Time limit exceeded past grace: abort in-flight transfers so no wait loop
+     starves (#481). FTP slots stay, their thread owns the socket. */
  if (!back_checkmirror(opt)) {
-    const hts_mirror_limit limit = back_mirror_limit(opt);
-    const char *const reason =
-        (limit == HTS_MIRROR_LIMIT_SIZE) ? "size limit" : "time limit";
-    const char *const slotmsg = (limit == HTS_MIRROR_LIMIT_SIZE)
-                                    ? "Mirror Size Limit"
-                                    : "Mirror Time Out";
    int aborted = 0;
    unsigned int i;

@@ -2448,15 +2400,15 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
        if (back[i].r.is_write && IS_DELAYED_EXT(back[i].url_sav))
          back_delayed_discard(opt, &back[i]);
        back[i].r.statuscode = STATUSCODE_TIMEOUT;
-        strcpybuff(back[i].r.msg, slotmsg);
+        strcpybuff(back[i].r.msg, "Mirror Time Out");
        back[i].status = STATUS_READY;
        back_set_finished(sback, i);
        aborted++;
      }
    }
    if (aborted > 0)
-      hts_log_print(opt, LOG_WARNING, "%s reached, %d transfer(s) aborted",
-                    reason, aborted);
+      hts_log_print(opt, LOG_WARNING,
+                    "time limit reached, %d transfer(s) aborted", aborted);
    return;
  }

@@ -2946,8 +2898,7 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                strfield(get_ext(catbuff, sizeof(catbuff), back[i].url_sav), "gz") == 0
                                && strfield(get_ext(catbuff, sizeof(catbuff), back[i].url_sav), "tgz") == 0
                              ) {
-                              if (create_back_tmpfile(opt, &back[i], "z") ==
-                                  0) {
+                              if (create_back_tmpfile(opt, &back[i]) == 0) {
                                assertf(back[i].tmpfile != NULL);
                                /* note: tmpfile is utf-8 */
                                if ((back[i].r.out =
@@ -2960,20 +2911,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                                          back[i].url_sav, 1, 1,
                                          back[i].r.notmodified);
                              back[i].r.compressed = 0;
-                              /* Re-fetch over an existing file (#77 follow-up):
-                                 move the good copy aside before truncating it
-                                 so an aborted transfer can restore it. url_sav
-                                 is still written normally (file list intact).
-                               */
-                              back[i].tmpfile = NULL;
-                              if (fexist_utf8(back[i].url_sav)) {
-                                if (create_back_tmpfile(opt, &back[i], "bak") !=
-                                        0 ||
-                                    RENAME(back[i].url_sav, back[i].tmpfile) !=
-                                        0) {
-                                  back[i].tmpfile = NULL;
-                                }
-                              }
                              if ((back[i].r.out =
                                   filecreate(&opt->state.strc,
                                              back[i].url_sav)) == NULL) {
@@ -3512,11 +3449,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                    continue;
                  }

-                  // The server really sent 304 here; the *-hacks below force
-                  // NOT_MODIFIED only after confirming the file is complete.
-                  const hts_boolean server_sent_304 =
-                      (back[i].r.statuscode == HTTP_NOT_MODIFIED);
-
                  /*
                     Solve "false" 416 problems
                   */
@@ -3545,20 +3477,22 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                  if (back[i].r.statuscode == 406) {    // 'Not Acceptable'
                    back[i].r.statuscode = HTTP_OK;
                  }
-                  // On update, keep the good copy on error (mask as 304); skip
-                  // resume paths so a stale-partial 416 still re-fetches.
-                  if (HTTP_IS_ERROR(back[i].r.statuscode) &&
-                      back[i].is_update && !back[i].testmode &&
-                      back[i].range_req_size == 0 && back[i].url_sav[0] &&
-                      fexist_utf8(back[i].url_sav)) {
-                    hts_log_print(opt, LOG_DEBUG,
-                                  "Error %d (%s) ignored on update, keeping "
-                                  "existing copy: %s%s",
-                                  back[i].r.statuscode, back[i].r.msg,
-                                  back[i].url_adr, back[i].url_fil);
-                    back[i].r.statuscode = HTTP_NOT_MODIFIED;
-                    deletehttp(&back[i].r);
-                    back[i].r.soc = INVALID_SOCKET;
+                  // 'do not erase already downloaded file'
+                  // on an updated file
+                  // with an error : consider a 304 error
+                  if (!opt->delete_old) {
+                    if (HTTP_IS_ERROR(back[i].r.statuscode) && back[i].is_update
+                        && !back[i].testmode) {
+                      if (back[i].url_sav[0] && fexist_utf8(back[i].url_sav)) {
+                        hts_log_print(opt, LOG_DEBUG,
+                                      "Error ignored %d (%s) because of 'no purge' option for %s%s",
+                                      back[i].r.statuscode, back[i].r.msg,
+                                      back[i].url_adr, back[i].url_fil);
+                        back[i].r.statuscode = HTTP_NOT_MODIFIED;
+                        deletehttp(&back[i].r);
+                        back[i].r.soc = INVALID_SOCKET;
+                      }
+                    }
                  }
                  // Various hacks to limit re-transfers when updating a mirror
                  // Force update if same size detected
@@ -3706,21 +3640,6 @@ void back_wait(struct_back * sback, httrackp * opt, cache_back * cache,
                    }
                  }

-                  // Out-of-protocol 304 to a Range resume: the file is still
-                  // partial, so drop it and refetch instead of trusting it.
-                  if (server_sent_304 && back[i].range_req_size > 0) {
-                    url_savename_refname_remove(opt, back[i].url_adr,
-                                                back[i].url_fil);
-                    UNLINK(back[i].url_sav);
-                    deletehttp(&back[i].r);
-                    back[i].r.soc = INVALID_SOCKET;
-                    back[i].r.statuscode = STATUSCODE_NON_FATAL;
-                    strcpybuff(back[i].r.msg,
-                               "Bogus 304 on resume, restarting");
-                    back[i].status = STATUS_READY;
-                    back_set_finished(sback, i);
-                  }
-
                  /* sinon, continuer */
                  /* if (back[i].r.soc!=INVALID_SOCKET) {   // ok récupérer body? */
                  // head: terminé
@@ -4194,46 +4113,38 @@ static int back_maxtime_grace(const int maxtime) {
  return maximum(5, minimum(30, maxtime / 10));
 }

-/* Bytes the smooth stop may overrun before in-flight transfers are aborted.
-   No floor (unlike the time grace): a size overrun should abort promptly. */
-static LLint back_maxsize_grace(const LLint maxsite) { return maxsite / 10; }
-
-/* Which cap has overrun its grace and must hard-stop the mirror (#77, #481).
-   -M measures received volume (HTS_TOTAL_RECV), not saved 200-only stat_bytes
-   which undercounts redirect/error-heavy crawls (#520). */
-static hts_mirror_limit back_mirror_limit(httrackp *opt) {
-  if (opt->maxsite > 0 && HTS_STAT.HTS_TOTAL_RECV >= opt->maxsite &&
-      HTS_STAT.HTS_TOTAL_RECV - opt->maxsite >=
-          back_maxsize_grace(opt->maxsite))
-    return HTS_MIRROR_LIMIT_SIZE;
+int back_checkmirror(httrackp * opt) {
+  // Check max size
+  if ((opt->maxsite > 0) && (HTS_STAT.stat_bytes >= opt->maxsite)) {
+    if (!opt->state.stop) {     /* not yet stopped */
+      hts_log_print(opt, LOG_ERROR,
+                    "More than " LLintP
+                    " bytes have been transferred.. giving up",
+                    (LLint) opt->maxsite);
+      /* cancel mirror smoothly */
+      hts_request_stop(opt, 0);
+    }
+    return 1;                   /* don'k break mirror too sharply for size limits, but stop requested */
+    /*return 0;
+     */
+  }
+  // Check max time
  if (opt->maxtime > 0) {
    const TStamp elapsed = time_local() - HTS_STAT.stat_timestart;

-    if (elapsed >= opt->maxtime &&
-        elapsed - opt->maxtime >= back_maxtime_grace(opt->maxtime))
-      return HTS_MIRROR_LIMIT_TIME;
+    if (elapsed >= opt->maxtime) {
+      if (!opt->state.stop) { /* not yet stopped */
+        hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
+                      opt->maxtime);
+        /* cancel mirror smoothly */
+        hts_request_stop(opt, 0);
+      }
+      /* smooth stop starved past the grace period: stop waiting (#481) */
+      if (elapsed - opt->maxtime >= back_maxtime_grace(opt->maxtime))
+        return 0;
+    }
  }
-  return HTS_MIRROR_LIMIT_NONE;
-}
-
-int back_checkmirror(httrackp *opt) {
-  /* request a smooth stop the first time each cap is reached */
-  if (opt->maxsite > 0 && HTS_STAT.HTS_TOTAL_RECV >= opt->maxsite &&
-      !opt->state.stop) {
-    hts_log_print(opt, LOG_ERROR,
-                  "More than " LLintP
-                  " bytes have been transferred.. giving up",
-                  (LLint) opt->maxsite);
-    hts_request_stop(opt, 0);
-  }
-  if (opt->maxtime > 0 && !opt->state.stop &&
-      (time_local() - HTS_STAT.stat_timestart) >= opt->maxtime) {
-    hts_log_print(opt, LOG_ERROR, "More than %d seconds passed.. giving up",
-                  opt->maxtime);
-    hts_request_stop(opt, 0);
-  }
-  /* hard stop once a cap overruns its grace (callers must stop waiting) */
-  return back_mirror_limit(opt) == HTS_MIRROR_LIMIT_NONE;
+  return 1;                     /* Ok, go on */
 }

 // octets transférés + add
--- a/src/htsback.h
+++ b/src/htsback.h
@@ -141,8 +141,8 @@ LLint back_transferred(LLint add, struct_back * sback);
 int host_wait(httrackp * opt, lien_back * sback);
 #endif
 int back_checksize(httrackp * opt, lien_back * eback, int check_only_totalsize);
-/* Enforce -M/-E quotas: smooth-stops when reached; returns 0 once the -M cap
-   or -E deadline overruns its grace period (callers must stop waiting). */
+/* Enforce -M/-E quotas: requests a smooth stop when reached; returns 0 once
+   the -E deadline overran its grace period (callers must stop waiting). */
 int back_checkmirror(httrackp * opt);

 #endif
--- a/src/htscore.c
+++ b/src/htscore.c
@@ -1904,11 +1904,8 @@ int httpmirror(char *url1, httrackp * opt) {
            }
          }

-          // ATTENTION C'EST ICI QU'ON SAUVE LE FICHIER!!
-          // An empty body must not overwrite the file when the transfer failed
-          // (statuscode <= 0, e.g. an -M hard-stop): it would truncate a good
-          // copy to 0 (#77 follow-up).
-          if (r.adr != NULL || (r.size == 0 && r.statuscode > 0)) {
+          // ATTENTION C'EST ICI QU'ON SAUVE LE FICHIER!!          
+          if (r.adr != NULL || r.size == 0) {
            file_notify(opt, urladr(), urlfil(), savename(), 1, 1, r.notmodified);
            if (filesave(opt, r.adr, (int) r.size, savename(), urladr(), urlfil()) !=
                0) {
@@ -1929,6 +1926,7 @@ int httpmirror(char *url1, httrackp * opt) {
               */
            }
          }
+
        }

        /* Parsing of other media types (java, ram..) */
--- a/src/htsglobal.h
+++ b/src/htsglobal.h
@@ -56,10 +56,6 @@ Please visit our Website: http://www.httrack.com
 // Platform detection (sizes, feature macros)
 #include "htsconfig.h"

-// Fixed-width integer types + PRI* format macros for the LLint/TStamp typedefs
-#include <stdint.h>
-#include <inttypes.h>
-
 // WIN32 types
 #ifdef _WIN32
 #ifndef SIZEOF_LONG
@@ -115,6 +111,29 @@ Please visit our Website: http://www.httrack.com
 #define HTS_DO_NOT_USE_UID
 #endif

+#ifndef HTS_LONGLONG
+#ifdef SIZEOF_LONG_LONG
+#if SIZEOF_LONG_LONG == 8
+#define HTS_LONGLONG 1
+#endif
+#endif
+
+#ifndef HTS_LONGLONG
+#ifdef __sun
+#define HTS_LONGLONG 0
+#endif
+#ifdef __osf__
+#define HTS_LONGLONG 0
+#endif
+#ifdef __linux
+#define HTS_LONGLONG 1
+#endif
+#ifdef _WIN32
+#define HTS_LONGLONG 1
+#endif
+#endif
+#endif
+
 #ifdef DLLIB
 #define HTS_DLOPEN 1
 #else
@@ -307,11 +326,59 @@ typedef int hts_tristate;
 #define HTS_DEPRECATED(msg)
 #endif

-/* LLint/TStamp: signed exact-width 64-bit; -1 is a sentinel engine-wide. */
-typedef int64_t LLint;
-typedef int64_t TStamp;
-/* Full printf conversion, '%' included (PRId64 has none): "X: " LLintP. */
-#define LLintP "%" PRId64
+#ifndef HTS_LONGLONG
+#ifdef HTS_NO_64_BIT
+#define HTS_LONGLONG 0
+#else
+#define HTS_LONGLONG 1
+#endif
+#endif
+
+/* Wide integer types, chosen per platform.
+   LLint:  signed 64-bit counter for byte counts and large sizes (falls back to
+           plain int where 64-bit is unavailable).
+   TStamp: timestamp/duration in the same width (a double in the no-64-bit
+           fallback).
+   LLintP: the printf conversion for an LLint. */
+#if HTS_LONGLONG
+#ifdef LLINT_FORMAT
+typedef LLINT_TYPE LLint;
+
+typedef LLINT_TYPE TStamp;
+
+#define LLintP LLINT_FORMAT
+#else
+
+#ifdef _WIN32
+typedef __int64 LLint;
+
+typedef __int64 TStamp;
+
+#define LLintP "%I64d"
+#elif (defined(_LP64) || defined(__x86_64__) || defined(__powerpc64__) ||      \
+       defined(__64BIT__))
+
+typedef long int LLint;
+
+typedef long int TStamp;
+
+#define LLintP "%ld"
+#else
+typedef long long int LLint;
+
+typedef long long int TStamp;
+
+#define LLintP "%lld"
+#endif
+
+#endif /* HTS_LONGLONG */
+
+#else
+typedef int LLint;
+
+#define LLintP "%d"
+typedef double TStamp;
+#endif

 /* Integer type for file offsets/sizes passed to the C library. Widens to
   LLint (with HTS_FSEEKO for fseeko/ftello) under large-file support, plain
--- a/src/htslib.c
+++ b/src/htslib.c
@@ -3038,11 +3038,12 @@ HTSEXT_API char *int2char(strc_int2bytes2 * strc, int n) {
 /* See http://physics.nist.gov/cuu/Units/binary.html */
 #define ToLLint(a) ((LLint)(a))
 #define ToLLintKiB (ToLLint(1024))
-#define ToLLintMiB (ToLLintKiB * ToLLintKiB)
-#define ToLLintGiB (ToLLintKiB * ToLLintKiB * ToLLintKiB)
-#define ToLLintTiB (ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB)
-#define ToLLintPiB                                                             \
-  (ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB * ToLLintKiB)
+#define ToLLintMiB (ToLLintKiB*ToLLintKiB)
+#ifdef HTS_LONGLONG
+#define ToLLintGiB (ToLLintKiB*ToLLintKiB*ToLLintKiB)
+#define ToLLintTiB (ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB)
+#define ToLLintPiB (ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB*ToLLintKiB)
+#endif
 HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
  if (n < ToLLintKiB) {
    sprintf(strc->buff1, "%d", (int) (LLint) n);
@@ -3051,7 +3052,9 @@ HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
    sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / ToLLintKiB)),
            (int) ((LLint) ((n % ToLLintKiB) * 100) / ToLLintKiB));
    strcpybuff(strc->buff2, "KiB");
-  } else if (n < ToLLintGiB) {
+  }
+#ifdef HTS_LONGLONG
+  else if (n < ToLLintGiB) {
    sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / (ToLLintMiB))),
            (int) ((LLint) (((n % (ToLLintMiB)) * 100) / (ToLLintMiB))));
    strcpybuff(strc->buff2, "MiB");
@@ -3068,6 +3071,13 @@ HTSEXT_API char **int2bytes2(strc_int2bytes2 * strc, LLint n) {
            (int) ((LLint) (((n % (ToLLintPiB)) * 100) / (ToLLintPiB))));
    strcpybuff(strc->buff2, "PiB");
  }
+#else
+  else {
+    sprintf(strc->buff1, "%d,%02d", (int) ((LLint) (n / (ToLLintMiB))),
+            (int) ((LLint) (((n % (ToLLintMiB)) * 100) / (ToLLintMiB))));
+    strcpybuff(strc->buff2, "MiB");
+  }
+#endif
  strc->buffadr[0] = strc->buff1;
  strc->buffadr[1] = strc->buff2;
  return strc->buffadr;
--- a/tests/19_local-connect-fallback.test
+++ b/tests/19_local-connect-fallback.test
@@ -66,12 +66,9 @@ test -n "$port" || {
 }

 out="$tmpdir/crawl"
-# macOS has only 127.0.0.1, so the dead 127.0.0.x connects block to the timeout
-# instead of refusing instantly (as on Linux); a small --timeout + --retries=0
-# bound the stall without changing what the fallback exercises.
 HTTRACK_DEBUG_RESOLVE="deadhost:127.0.0.2,127.0.0.1" \
    httrack "http://deadhost:$port/simple/basic.html" -O "$out" \
-    -c1 --robots=0 --timeout=5 --retries=0 --quiet -Z >"$tmpdir/log" 2>&1
+    -c1 --robots=0 --timeout=30 --quiet -Z >"$tmpdir/log" 2>&1

 log="$out/hts-log.txt"

@@ -95,12 +92,12 @@ test -f "$out/deadhost_$port/simple/basic.html" || {
    exit 1
 }

-# every address dead: the slot exhausts the list, then errors out (the harness
-# timeout would catch a hang/loop)
+# every address refused: the slot exhausts the list, then errors out (the
+# harness timeout would catch a hang/loop; refused connects are instant)
 out2="$tmpdir/crawl2"
 HTTRACK_DEBUG_RESOLVE="alldead:127.0.0.2,127.0.0.3" \
    httrack "http://alldead:$port/simple/basic.html" -O "$out2" \
-    -c1 --robots=0 --timeout=5 --retries=0 --quiet -Z >"$tmpdir/log2" 2>&1
+    -c1 --robots=0 --timeout=30 --quiet -Z >"$tmpdir/log2" 2>&1
 log2="$out2/hts-log.txt"

 grep -q "trying next address" "$log2" || {
--- a/tests/31_local-javaclass.test
+++ b/tests/31_local-javaclass.test
@@ -17,10 +17,7 @@ printf 'GIF89a' >"$tmproot/javaclass/hello.gif"
 printf '\xCA\xFE\xBA\xBE\x00\x00\x00\x32\x00\x02\x01\x00\x09hello.gif\x00\x00\x00\x00' \
    >"$tmproot/javaclass/Foo.class"

-# --log-found first: a plugin-load failure (wrong soname, shadowing system
-# libhtsjava) trips here on the banner suffix, not as an opaque "not found".
 bash "$top_srcdir/tests/local-crawl.sh" --root "$tmproot" --errors 0 \
-    --log-found '\+libhtsjava' \
    --found 'javaclass/Foo.class' \
    --found 'javaclass/hello.gif' \
    httrack 'BASEURL/javaclass/index.html'
--- a/tests/36_local-bigcrawl.test
+++ b/tests/36_local-bigcrawl.test
@@ -9,7 +9,7 @@ set -euo pipefail
 : "${top_srcdir:=..}"

 bash "$top_srcdir/tests/local-crawl.sh" --rerun \
-    --errors-content 4 --files 361 \
+    --errors 4 --files 361 \
    --found 'big/p/95.html' \
    --found 'big/a/d1/d2/d3/d4/d5/d6/d7/d8/deep.png' \
    --found 'big/a/f2-2x.png' \
--- a/tests/42_local-maxsize-slow.test
+++ b/tests/42_local-maxsize-slow.test
@@ -1,21 +0,0 @@
-#!/bin/bash
-#
-# -M byte cap under a slow server (#77): p0 overruns -M at once while p1..p3
-# trickle for a minute; the cap must abort the in-flight transfers, not wait
-# them out. Unfixed, the smooth stop drains the trickle at server pace.
-
-set -euo pipefail
-
-: "${top_srcdir:=..}"
-
-start=$(date +%s)
-bash "$top_srcdir/tests/local-crawl.sh" \
-    --log-found 'More than 400000 bytes have been transferred.. giving up' \
-    httrack 'BASEURL/bigtrickle/index.html' -M400000 -c4
-wall=$(($(date +%s) - start))
-# trickle runs 60s; a smooth-only stop waits it out, the hard stop lands near 8s.
-# Wall clock is the discriminating check: the log line above fires either way.
-if [ "$wall" -ge 30 ]; then
-    echo "crawl took ${wall}s, -M hard stop did not engage" >&2
-    exit 1
-fi
--- a/tests/43_local-update-truncate.test
+++ b/tests/43_local-update-truncate.test
@@ -1,24 +0,0 @@
-#!/bin/bash
-#
-# -M hard-abort must not destroy already-complete files (#77 follow-up).
-# Pass 1 mirrors bigtrunc fully. Pass 2 re-fetches under --update -M: fast.bin
-# overruns the cap, its abort tears down slow.bin's stalled re-fetch. Both were
-# complete on disk from pass 1, and both must survive the aborted update:
-#   - slow.bin's re-fetch is incomplete; the direct-to-disk write must not be
-#     left truncated (the previous copy is restored).
-#   - fast.bin fully arrives but is torn down; the aborted slot must not overwrite
-#     it with an empty body.
-# Unfixed, slow.bin is truncated and fast.bin is zeroed while the cache still
-# records them complete.
-
-set -euo pipefail
-
-: "${top_srcdir:=..}"
-
-bash "$top_srcdir/tests/local-crawl.sh" \
-    --rerun-args '--update -M400000' \
-    --log-found 'More than 400000 bytes have been transferred.. giving up' \
-    --found bigtrunc/slow.bin \
-    --file-min-bytes bigtrunc/slow.bin 655360 \
-    --file-min-bytes bigtrunc/fast.bin 655360 \
-    httrack 'BASEURL/bigtrunc/index.html' -c2
--- a/tests/44_local-update-errormask.test
+++ b/tests/44_local-update-errormask.test
@@ -1,13 +0,0 @@
-#!/bin/bash
-# Issue #176: on --update a page that 200'd on the first crawl but now 403s must
-# keep its good local copy, not be overwritten by the error body nor purged.
-set -euo pipefail
-
-: "${top_srcdir:=..}"
-
-bash "$top_srcdir/tests/local-crawl.sh" --rerun \
-    --found 'errmask/keep.dat' \
-    --file-min-bytes 'errmask/keep.dat' 1024 \
-    --file-matches 'errmask/keep.dat' '^KEEP' \
-    --file-not-matches 'errmask/keep.dat' 'error 403' \
-    httrack 'BASEURL/errmask/index.html'
--- a/tests/45_local-maxsize-recv.test
+++ b/tests/45_local-maxsize-recv.test
@@ -1,16 +0,0 @@
-#!/bin/bash
-#
-# -M caps received volume, not saved 200-only bytes (#520): links to large 404
-# bodies pump received >> saved; the cap must trip though little lands on disk.
-
-set -euo pipefail
-
-: "${top_srcdir:=..}"
-
-# The mirror bound is the load-bearing half: it fires while <100 KB is saved,
-# so the cap can only have tripped on received volume, not saved bytes (which
-# would exceed the cap and fetch all 16 links).
-bash "$top_srcdir/tests/local-crawl.sh" \
-    --log-found 'More than 500000 bytes have been transferred.. giving up' \
-    --max-mirror-bytes 100000 \
-    httrack 'BASEURL/maxrecv/index.html' -M500000 -c4
--- a/tests/46_local-update-304-resume.test
+++ b/tests/46_local-update-304-resume.test
@@ -1,118 +0,0 @@
-#!/bin/bash
-# C7: a server 304 answering a resume's Range request is out of protocol; httrack
-# must drop the partial and refetch, not finalize it as complete at the partial
-# byte count. Pass 1 leaves a partial + temp-ref; pass 2 resumes, gets a bogus
-# 304, and must recover the whole file.
-set -u
-
-: "${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_c7.XXXXXX") || exit 1
-serverpid=
-crawlpid=
-cleanup() {
-    test -n "$crawlpid" && kill -9 "$crawlpid" 2>/dev/null
-    if test -n "$serverpid"; then
-        kill "$serverpid" 2>/dev/null
-        wait "$serverpid" 2>/dev/null
-    fi
-    rm -rf "$tmpdir"
-}
-trap cleanup EXIT HUP INT QUIT PIPE TERM
-
-serverlog="${tmpdir}/server.log"
-counter="${tmpdir}/reqcount"
-mark="${tmpdir}/got304"
-RESUME304_COUNTER="$counter" RESUME304_MARK="$mark" python3 "$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="${tmpdir}/crawl"
-mkdir "$out"
-common=(-O "$out" --quiet --disable-security-limits --robots=0 --timeout=30 --retries=1 -c1)
-refdir="${out}/hts-cache/ref"
-
-# --- pass 1: crawl, interrupt once the blob download is underway -------------
-printf '[pass 1: interrupt mid-download] ..\t'
-httrack "${common[@]}" "${base}/resume304/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
-wait "$crawlpid" 2>/dev/null
-crawlpid=
-test -n "$(find "$refdir" -name '*.ref' 2>/dev/null)" || {
-    echo "FAIL: no temp-ref survived pass 1; cannot drive C7"
-    exit 1
-}
-echo "OK (temp-ref present)"
-before=$(wc -c <"$counter" 2>/dev/null || echo 0)
-
-# --- pass 2: --continue -> resume Range -> bogus 304 -> drop + refetch --------
-printf '[pass 2: resume gets 304, must refetch] ..\t'
-httrack "${common[@]}" --continue "${base}/resume304/index.html" >"${tmpdir}/log2" 2>&1
-echo "OK (terminated)"
-
-blob=$(find "$out" -name blob.bin 2>/dev/null | head -1)
-full=8200 # len(RESUME304_BODY) = len("C7DATA--") + 8192
-
-printf '[file recovered whole] ..\t'
-test -s "$blob" || {
-    echo "FAIL: blob.bin missing after the 304 resume (partial dropped, not refetched)"
-    exit 1
-}
-got=$(wc -c <"$blob")
-test "$got" -eq "$full" || {
-    echo "FAIL: blob.bin is ${got} bytes, expected ${full} (partial finalized as complete)"
-    exit 1
-}
-echo "OK (${got} bytes)"
-
-# Pass 2 must issue at least two requests: the resume (Range -> 304) and the
-# range-less refetch (-> 200). Exactly one means the partial was trusted.
-after=$(wc -c <"$counter" 2>/dev/null || echo 0)
-hits=$((after - before))
-printf '[resume then refetch] ..\t'
-test "$hits" -ge 2 || {
-    echo "FAIL: only ${hits} pass-2 request(s); the 304 was trusted, no refetch"
-    exit 1
-}
-echo "OK (${hits} requests)"
-
-# The recovery must go through the resume path: a Range request that drew the
-# bogus 304 (a fresh re-crawl sends no Range, so this marker stays empty).
-printf '[resume Range drew a 304] ..\t'
-test -s "$mark" || {
-    echo "FAIL: no Range request got a 304; the resume path was not exercised"
-    exit 1
-}
-echo "OK"
--- a/tests/Makefile.am
+++ b/tests/Makefile.am
@@ -110,11 +110,6 @@ TESTS = \
 	38_local-update-304.test \
 	39_local-delayed-cancel.test \
 	40_local-why.test \
-	41_local-utf8-link.test \
-	42_local-maxsize-slow.test \
-	43_local-update-truncate.test \
-	44_local-update-errormask.test \
-	45_local-maxsize-recv.test \
-	46_local-update-304-resume.test
+	41_local-utf8-link.test

 CLEANFILES = check-network_sh.cache
--- a/tests/crawl-test.sh
+++ b/tests/crawl-test.sh
@@ -105,7 +105,7 @@ function start-crawl {
    log="${tmp}/log"
    debug starting httrack -O "${tmp}" "${moreargs[@]}" "${@:pos}"
    info "running httrack ${*:pos}"
-    httrack -O "${tmp}" --user-agent="httrack $ver ut ($(uname -mrs))" "${moreargs[@]}" "${@:pos}" >"${log}" 2>&1 &
+    httrack -O "${tmp}" --user-agent="httrack $ver ut ($(uname -omrs))" "${moreargs[@]}" "${@:pos}" >"${log}" 2>&1 &
    crawlpid="$!"
    debug "started cralwer on pid $crawlpid"
    wait "$crawlpid"
--- a/tests/local-crawl.sh
+++ b/tests/local-crawl.sh
@@ -13,21 +13,15 @@
 #
 # Usage:
 #   bash local-crawl.sh [--tls] [--root DIR] [--cookie NAME=VALUE ...] \
-#       [--rerun-args 'ARGS'] \
-#       --errors N --errors-content N --files N --found PATH ... --directory PATH ... \
+#       --errors N --files N --found PATH ... --directory PATH ... \
 #       --log-found REGEX ... --log-not-found REGEX ... \
 #       --file-matches PATH REGEX ... --file-not-matches PATH REGEX ... \
-#       --file-min-bytes PATH N --max-mirror-bytes N \
+#       --max-mirror-bytes N \
 #       httrack BASEURL/some/path [httrack-args...]
-# --errors counts every "Error:" log line; --errors-content drops transient
-# network failures (codes -2..-6) that flake on busy loopback under -c8.
 # --log-found/--log-not-found grep (ERE) the crawl's hts-log.txt.
 # --max/--min-mirror-bytes bound the mirrored content bytes (host root).
 # --file-matches/--file-not-matches grep (ERE) a mirrored file (PATH under the
 # host root), to assert rewritten link/content survived the crawl.
-# --file-min-bytes asserts a mirrored file (PATH) is at least N bytes.
-# --rerun-args runs a second pass (same server and mirror dir) with the given
-# extra httrack args appended, e.g. an --update run under a cap.
 # --cookie writes a Netscape cookies.txt (scoped to the discovered host:port,
 # which the ephemeral port forces into the cookie domain) and passes it to
 # httrack via --cookies-file, to exercise preloaded cookies.
@@ -45,7 +39,6 @@ key="${testdir}/server.key"
 tls=
 verbose=
 rerun=
-rerun_args=
 rerun_dead=
 tmpdir=
 serverpid=
@@ -129,11 +122,7 @@ while test "$pos" -lt "$nargs"; do
        pos=$((pos + 1))
        cookies+=("${args[$pos]}")
        ;;
-    --rerun-args)
-        pos=$((pos + 1))
-        rerun_args="${args[$pos]}"
-        ;;
-    --errors | --errors-content | --files)
+    --errors | --files)
        audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
        pos=$((pos + 1))
        ;;
@@ -141,7 +130,7 @@ while test "$pos" -lt "$nargs"; do
        audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
        pos=$((pos + 1))
        ;;
-    --file-matches | --file-not-matches | --file-min-bytes)
+    --file-matches | --file-not-matches)
        audit+=("${args[$pos]}" "${args[$((pos + 1))]}" "${args[$((pos + 2))]}")
        pos=$((pos + 2))
        ;;
@@ -213,7 +202,7 @@ mkdir "$out" || die "could not create $out"
 declare -a moreargs=(--quiet --max-time=120 --timeout=30 --disable-security-limits --robots=0)
 log="${tmpdir}/log"
 info "running httrack ${hts[*]}"
-httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" "${moreargs[@]}" "${hts[@]}" >"$log" 2>&1 &
+httrack -O "$out" --user-agent="httrack $ver local ($(uname -omrs))" "${moreargs[@]}" "${hts[@]}" >"$log" 2>&1 &
 crawlpid=$!
 wait "$crawlpid"
 crawlres=$?
@@ -230,7 +219,7 @@ grep -iE "^[0-9:]*[[:space:]]Error:" "${out}/hts-log.txt" >&2
 # --- optional second pass: re-mirror into the same dir (cache/update path) ----
 if test -n "$rerun"; then
    info "re-running httrack (update pass)"
-    httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" \
+    httrack -O "$out" --user-agent="httrack $ver local ($(uname -omrs))" \
        "${moreargs[@]}" "${hts[@]}" >"${log}.2" 2>&1 &
    crawlpid=$!
    wait "$crawlpid"
@@ -252,25 +241,6 @@ if test -n "$rerun"; then
    fi
 fi

-# --- optional second pass with extra args (e.g. an --update run under a cap) ---
-# Same server and mirror dir as the first pass, so the second pass sees the
-# cache the first pass wrote. Used to exercise re-fetch/update behaviour.
-if test -n "$rerun_args"; then
-    read -ra extra <<<"$rerun_args"
-    info "re-running httrack with ${rerun_args}"
-    httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" \
-        "${moreargs[@]}" "${hts[@]}" "${extra[@]}" >"${log}.2" 2>&1 &
-    crawlpid=$!
-    wait "$crawlpid"
-    crawlres=$?
-    crawlpid=
-    test "$crawlres" -eq 0 || ! result "second pass exited $crawlres" || {
-        cat "${log}.2" >&2
-        exit 1
-    }
-    result "OK (second pass)"
-fi
-
 # --- optional dead pass: server stopped, the cache must survive the rollback --
 if test -n "$rerun_dead"; then
    zip="${out}/hts-cache/new.zip"
@@ -281,7 +251,7 @@ if test -n "$rerun_dead"; then
    wait "$serverpid" 2>/dev/null
    serverpid=
    info "re-running httrack against the stopped server"
-    httrack -O "$out" --user-agent="httrack $ver local ($(uname -mrs))" \
+    httrack -O "$out" --user-agent="httrack $ver local ($(uname -omrs))" \
        "${moreargs[@]}" "${hts[@]}" >"${log}.dead" 2>&1 &
    crawlpid=$!
    wait "$crawlpid" || true
@@ -336,14 +306,6 @@ while test "$i" -lt "${#audit[@]}"; do
        assert_equals "checking errors" "${audit[$i]}" \
            "$(grep -iEc "^[0-9:]*[[:space:]]Error:" "${out}/hts-log.txt")"
        ;;
-    --errors-content)
-        i=$((i + 1))
-        total=$(grep -icE "^[0-9:]*[[:space:]]Error:" "${out}/hts-log.txt")
-        # transient network failures (statuscode -2..-6) flake on busy loopback;
-        # the code parens are followed by " at link" or " after N retries at link"
-        transient=$(grep -cE '\(-[2-6]\) (at link|after )' "${out}/hts-log.txt" || true)
-        assert_equals "checking content errors" "${audit[$i]}" "$((total - transient))"
-        ;;
    --files)
        i=$((i + 1))
        nFiles=$(grep -E "^HTTrack Website Copier/[^ ]* mirror complete in " "${out}/hts-log.txt" |
@@ -426,16 +388,6 @@ while test "$i" -lt "${#audit[@]}"; do
            exit 1
        else result "OK"; fi
        ;;
-    --file-min-bytes)
-        path="${audit[$((i + 1))]}"
-        i=$((i + 2))
-        sz=$(wc -c <"${hostroot}/${path}" 2>/dev/null | tr -d '[:space:]')
-        info "checking ${path} size ${sz:-0} >= ${audit[$i]} bytes"
-        if test -n "$sz" && test "$sz" -ge "${audit[$i]}"; then result "OK"; else
-            result "file too small (or missing)"
-            exit 1
-        fi
-        ;;
    esac
    i=$((i + 1))
 done
--- a/tests/local-server.py
+++ b/tests/local-server.py
@@ -790,56 +790,6 @@ class Handler(SimpleHTTPRequestHandler):
        self.send_header("Content-Length", "0")
        self.end_headers()

-    # C7: stall the first GET (partial + temp-ref), then answer the resume's
-    # Range with a bogus 304; httrack must drop the partial and refetch.
-    RESUME304_BODY = b"C7DATA--" + bytes((i * 7 + 3) % 256 for i in range(8192))
-    _resume304_started = False
-
-    def route_resume304_index(self):
-        self.send_html('\t<a href="blob.bin">blob</a>')
-
-    def route_resume304(self):
-        counter = os.environ.get("RESUME304_COUNTER")
-        if counter:
-            with open(counter, "a") as fp:
-                fp.write("x")
-        rng = self.headers.get("Range")
-        if not Handler._resume304_started:
-            Handler._resume304_started = True
-            self.send_response(200)
-            self.send_header("Content-Type", "application/octet-stream")
-            self.send_header("Content-Length", str(len(self.RESUME304_BODY)))
-            self.send_header("Accept-Ranges", "bytes")
-            self.send_header("Last-Modified", BIG_LASTMOD)
-            self.send_header("ETag", '"c7"')
-            self.end_headers()
-            if self.command != "HEAD":
-                self.wfile.write(self.RESUME304_BODY[:4096])
-                self.wfile.flush()
-                try:
-                    while True:
-                        time.sleep(3600)
-                except OSError:
-                    pass
-            return
-        if rng is not None:  # resume request: bogus out-of-protocol 304
-            mark = os.environ.get("RESUME304_MARK")
-            if mark:
-                with open(mark, "a") as fp:
-                    fp.write("z")
-            self.send_response(304)
-            self.send_header("ETag", '"c7"')
-            self.send_header("Content-Length", "0")
-            self.end_headers()
-            return
-        # Range-less refetch after the partial is dropped: whole file.
-        self.send_response(200)
-        self.send_header("Content-Type", "application/octet-stream")
-        self.send_header("Content-Length", str(len(self.RESUME304_BODY)))
-        self.end_headers()
-        if self.command != "HEAD":
-            self.wfile.write(self.RESUME304_BODY)
-
    # 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
@@ -984,33 +934,6 @@ class Handler(SimpleHTTPRequestHandler):
    def route_mini304_page(self):
        self.big_send(b"<html><body>tiny cacheable page</body></html>\n", "text/html")

-    # --- /errmask/: issue #176 — a page that 200'd on the first crawl but 403s
-    # on the update fetch must keep its good copy, not be overwritten nor purged.
-    ERRMASK_GOOD = b"KEEP" + b"." * 1020  # 1024 B distinctive non-HTML body
-    ERRMASK_ERR = b"<html><body>error 403</body></html>\n"
-
-    def route_errmask_index(self):
-        self.send_html('\t<a href="keep.dat">keep</a>\n')
-
-    def route_errmask_keep(self):
-        # First crawl (no validator) gets the 1024 B body + Last-Modified; the
-        # update sends a conditional and gets a 403 error page.
-        if self.headers.get("If-Modified-Since") or self.headers.get("If-None-Match"):
-            self.send_response(403, "Forbidden")
-            self.send_header("Content-Type", "text/html")
-            self.send_header("Content-Length", str(len(self.ERRMASK_ERR)))
-            self.end_headers()
-            if self.command != "HEAD":
-                self.wfile.write(self.ERRMASK_ERR)
-            return
-        self.send_response(200)
-        self.send_header("Content-Type", "application/octet-stream")
-        self.send_header("Last-Modified", BIG_LASTMOD)
-        self.send_header("Content-Length", str(len(self.ERRMASK_GOOD)))
-        self.end_headers()
-        if self.command != "HEAD":
-            self.wfile.write(self.ERRMASK_GOOD)
-
    # --- delayed-type degenerate paths (issues #5/#107) --------------------
    def route_delayed_index(self):
        self.send_html(
@@ -1112,64 +1035,6 @@ class Handler(SimpleHTTPRequestHandler):
    def route_bigfile(self):
        self.send_raw(b"x" * self.BIGFILE_BYTES, "application/octet-stream")

-    # -M under a slow server (#77): p0 is a fast 640KB file that alone overruns
-    # -M; p1..p3 trickle for a minute. The cap must abort those in-flight
-    # transfers, not wait them out.
-    def route_bigtrickle_index(self):
-        self.send_html(
-            "".join('\t<a href="p%d.bin">p%d</a>\n' % (i, i) for i in range(4))
-        )
-
-    # -M hard-abort must not destroy an already-complete file (#77 follow-up).
-    # "fast.bin" alone overruns -M and completes; "slow.bin" transfers fully on
-    # its first fetch (initial mirror) but stalls on every later fetch (the
-    # --update re-fetch), so the -M abort tears it down mid-body. An engine that
-    # truncates the good local copy on the aborted re-fetch loses data.
-    slow_seen = 0
-
-    def route_bigtrunc_index(self):
-        self.send_html('\t<a href="fast.bin">fast</a>\n\t<a href="slow.bin">slow</a>\n')
-
-    def route_bigtrunc_slow(self):
-        self.send_response(200)
-        self.send_header("Content-Type", "application/octet-stream")
-        self.send_header("Content-Length", str(self.BIGFILE_BYTES))
-        self.end_headers()
-        if self.command == "HEAD":
-            return
-        # Count body fetches only, so a stray HEAD can't shift which pass stalls.
-        Handler.slow_seen += 1
-        first = Handler.slow_seen == 1
-        try:
-            if first:
-                self.wfile.write(b"x" * self.BIGFILE_BYTES)
-                self.wfile.flush()
-            else:
-                self.wfile.write(b"x" * 4096)
-                self.wfile.flush()
-                for _ in range(120):
-                    self.wfile.write(b"x")
-                    self.wfile.flush()
-                    time.sleep(1.0)
-        except OSError:
-            pass
-
-    # -M received-volume cap (#520): links to large 404 bodies. httrack receives
-    # each (HTS_TOTAL_RECV climbs) but saves none, so saved stays far below -M.
-    def route_maxrecv_index(self):
-        self.send_html(
-            "".join('\t<a href="r%d.bin">r%d</a>\n' % (i, i) for i in range(16))
-        )
-
-    def route_maxrecv_404(self):
-        body = b"x" * self.BIGFILE_BYTES
-        self.send_response(404, "Not Found")
-        self.send_header("Content-Type", "application/octet-stream")
-        self.send_header("Content-Length", str(len(body)))
-        self.end_headers()
-        if self.command != "HEAD":
-            self.wfile.write(body)
-
    ROUTES = {
        "/cookies/entrance.php": route_entrance,
        "/cookies/second.php": route_second,
@@ -1199,8 +1064,6 @@ class Handler(SimpleHTTPRequestHandler):
        "/intl/" + INTL_NAME: route_intl_page,
        "/resume/index.html": route_resume_index,
        "/resume/blob.txt": route_resume,
-        "/resume304/index.html": route_resume304_index,
-        "/resume304/blob.bin": route_resume304,
        "/overlap/index.html": route_overlap_index,
        "/overlap/flaky.bin": route_overlap,
        "/overlap/full.bin": route_overlap_full,
@@ -1244,14 +1107,6 @@ class Handler(SimpleHTTPRequestHandler):
        "/bigfiles/p5.bin": route_bigfile,
        "/bigfiles/p6.bin": route_bigfile,
        "/bigfiles/p7.bin": route_bigfile,
-        "/bigtrickle/index.html": route_bigtrickle_index,
-        "/bigtrickle/p0.bin": route_bigfile,
-        "/bigtrickle/p1.bin": route_trickle_page,
-        "/bigtrickle/p2.bin": route_trickle_page,
-        "/bigtrickle/p3.bin": route_trickle_page,
-        "/bigtrunc/index.html": route_bigtrunc_index,
-        "/bigtrunc/fast.bin": route_bigfile,
-        "/bigtrunc/slow.bin": route_bigtrunc_slow,
        "/delayed/noloc.php": route_delayed_noloc,
        "/delayed/selfloop.php": route_delayed_selfloop,
        "/delayed/redir.php": route_delayed_redir,
@@ -1272,25 +1127,6 @@ class Handler(SimpleHTTPRequestHandler):
        "/redir/target.html": route_redir_target,
        "/mini304/index.html": route_mini304_index,
        "/mini304/page.html": route_mini304_page,
-        "/errmask/index.html": route_errmask_index,
-        "/errmask/keep.dat": route_errmask_keep,
-        "/maxrecv/index.html": route_maxrecv_index,
-        "/maxrecv/r0.bin": route_maxrecv_404,
-        "/maxrecv/r1.bin": route_maxrecv_404,
-        "/maxrecv/r2.bin": route_maxrecv_404,
-        "/maxrecv/r3.bin": route_maxrecv_404,
-        "/maxrecv/r4.bin": route_maxrecv_404,
-        "/maxrecv/r5.bin": route_maxrecv_404,
-        "/maxrecv/r6.bin": route_maxrecv_404,
-        "/maxrecv/r7.bin": route_maxrecv_404,
-        "/maxrecv/r8.bin": route_maxrecv_404,
-        "/maxrecv/r9.bin": route_maxrecv_404,
-        "/maxrecv/r10.bin": route_maxrecv_404,
-        "/maxrecv/r11.bin": route_maxrecv_404,
-        "/maxrecv/r12.bin": route_maxrecv_404,
-        "/maxrecv/r13.bin": route_maxrecv_404,
-        "/maxrecv/r14.bin": route_maxrecv_404,
-        "/maxrecv/r15.bin": route_maxrecv_404,
    }

    # --- /big/ seeded pseudo-site ------------------------------------------