Abort the download when the response MIME type is excluded by -mime: (#58)

A -mime: exclusion only took effect after the full body had been
downloaded and then discarded (leaving a .delayed temp behind), wasting
bandwidth. Honor it as soon as the response Content-Type arrives:
back_wait now aborts the transfer before the body when hts_acceptmime
forbids the declared type, finishing the slot with a new
STATUSCODE_EXCLUDED clean-skip status rather than fetching and dropping.

Covers the reported case (an HTML-looking URL served as application/pdf
past a +*.html include) and any -mime: match regardless of extension.

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

src/htsback.c

@@ -3766,7 +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) {
@@ -3985,7 +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') **/

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/Makefile.am

@@ -66,6 +66,7 @@ TESTS = \
 	21_local-intl-update.test \
 	22_local-broken-size.test \
 	23_local-errpage.test \
-	24_local-resume-overlap.test
+	24_local-resume-overlap.test \
+	25_local-mime-exclude.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.
@@ -355,6 +373,9 @@ class Handler(SimpleHTTPRequestHandler):
         "/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 ----------------------------------------------------------