Test 46: assert the resume's Range actually drew the 304

The size and request-count checks alone could pass a wrong-fix that silently
switched to a fresh re-crawl instead of handling the 304 on the resume path.
Mark when the server 304s a Range request and assert it fired, so recovery is
proven to go through the resume rather than around it.

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

src/htsback.c

@@ -3512,6 +3512,11 @@ 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
                    */
@@ -3701,6 +3706,21 @@ 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

tests/46_local-update-304-resume.test

@@ -0,0 +1,118 @@
+#!/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"

tests/Makefile.am

@@ -114,6 +114,7 @@ TESTS = \
 	42_local-maxsize-slow.test \
 	43_local-update-truncate.test \
 	44_local-update-errormask.test \
-	45_local-maxsize-recv.test
+	45_local-maxsize-recv.test \
+	46_local-update-304-resume.test
 
 CLEANFILES = check-network_sh.cache

tests/local-server.py

@@ -790,6 +790,56 @@ 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
@@ -1149,6 +1199,8 @@ 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,