mirror of
https://github.com/xroche/httrack.git
synced 2026-06-29 05:26:32 +03:00
Compare commits
1 Commits
debian-3.4
...
fix/urlhac
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
600001b282 |
44
.github/workflows/ci.yml
vendored
44
.github/workflows/ci.yml
vendored
@@ -61,50 +61,6 @@ jobs:
|
||||
if: failure()
|
||||
run: cat tests/test-suite.log 2>/dev/null || true
|
||||
|
||||
# Reproduce the Debian buildds: they build in a minimal chroot with no
|
||||
# python3, so the local-server tests must SKIP (exit 77), not fail. GitHub
|
||||
# runners ship python3, so every other job hides this path; here we remove it
|
||||
# before `make check`. This is the guard that would have caught the 3.49.10-1
|
||||
# FTBFS (28_local-pause failed instead of skipping when python3 was absent).
|
||||
buildd-no-python3:
|
||||
name: build (no python3, Debian buildd)
|
||||
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 autoconf automake libtool autoconf-archive \
|
||||
zlib1g-dev libssl-dev
|
||||
|
||||
- name: Configure
|
||||
run: |
|
||||
set -euo pipefail
|
||||
autoreconf -fi
|
||||
./configure
|
||||
|
||||
- name: Build
|
||||
run: make -j"$(nproc)"
|
||||
|
||||
- name: Test without python3
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# Hide every python3* so `command -v python3` fails like it does in the
|
||||
# buildd chroot; masking with /bin/false would still resolve.
|
||||
sudo find /usr/bin /usr/local/bin -maxdepth 1 -name 'python3*' \
|
||||
-exec mv {} {}.hidden \;
|
||||
! command -v python3
|
||||
make check
|
||||
|
||||
- name: Print the test log on failure
|
||||
if: failure()
|
||||
run: cat tests/test-suite.log 2>/dev/null || true
|
||||
|
||||
# Portability: build and test on macOS (Darwin/clang) on a native runner --
|
||||
# no VM. The tree has no __APPLE__ branches, so Darwin exercises the
|
||||
# generic-Unix path on a second libc and kernel. brew's openssl@3 is keg-only,
|
||||
|
||||
@@ -39,10 +39,6 @@ Welcome, and nothing to disclose. Two rules:
|
||||
|
||||
The sign-off covers AI-assisted code too.
|
||||
|
||||
## Translations
|
||||
|
||||
Interface strings live in [`lang/`](lang/). See [lang/README.md](lang/README.md) for the file format and how to add or update a language.
|
||||
|
||||
## Bugs
|
||||
|
||||
Open an issue with the version, OS, command used, and expected vs actual result.
|
||||
|
||||
10
configure.ac
10
configure.ac
@@ -1,6 +1,6 @@
|
||||
AC_PREREQ([2.71])
|
||||
|
||||
AC_INIT([httrack], [3.49.10], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
|
||||
AC_INIT([httrack], [3.49.9], [roche+packaging@httrack.com], [httrack], [http://www.httrack.com/])
|
||||
AC_COPYRIGHT([
|
||||
HTTrack Website Copier, Offline Browser for Windows and Unix
|
||||
Copyright (C) 1998-2015 Xavier Roche and other contributors
|
||||
@@ -29,10 +29,10 @@ AC_CONFIG_SRCDIR(src/httrack.c)
|
||||
AC_CONFIG_MACRO_DIR([m4])
|
||||
AC_CONFIG_HEADERS(config.h)
|
||||
AM_INIT_AUTOMAKE([subdir-objects])
|
||||
# 3:2:0: 3.49.10 only appends tail fields to the options struct (no existing
|
||||
# symbol or offset changed vs 3.49.9), so it stays soname .so.3; bump revision.
|
||||
# (3:0:0 was the htsblk mime-buffer widening, the ABI break that moved .so.2 -> .so.3.)
|
||||
VERSION_INFO="3:2:0"
|
||||
# 3:1:0: 3.49.9 changed code but not the exported interface vs 3.49.8 (same 164
|
||||
# symbols, no struct-layout change), so bump revision only. (3:0:0 was the htsblk
|
||||
# mime-buffer widening, an ABI break that moved the soname .so.2 -> .so.3.)
|
||||
VERSION_INFO="3:1:0"
|
||||
AM_MAINTAINER_MODE
|
||||
AC_USE_SYSTEM_EXTENSIONS
|
||||
|
||||
|
||||
22
debian/changelog
vendored
22
debian/changelog
vendored
@@ -1,25 +1,3 @@
|
||||
httrack (3.49.10-2) unstable; urgency=medium
|
||||
|
||||
* Fix FTBFS: tests/28_local-pause failed instead of skipping when python3 is
|
||||
absent (the local-server tests need python3, which the buildds lack). Add
|
||||
patches/skip-local-pause-test-without-python3.patch to guard the test on
|
||||
python3 up front, like its siblings, so it skips cleanly.
|
||||
|
||||
-- Xavier Roche <xavier@debian.org> Sun, 28 Jun 2026 20:18:46 +0200
|
||||
|
||||
httrack (3.49.10-1) unstable; urgency=medium
|
||||
|
||||
* New upstream release: new download-pacing and URL-handling options plus a
|
||||
batch of crawl and robustness fixes (full list in history.txt).
|
||||
* Rewrite debian/copyright in machine-readable DEP-5 format, crediting the
|
||||
bundled minizip, md5 and coucal sources (#415).
|
||||
* Lead the webhttrack browser dependency with chromium so httrack is not
|
||||
dragged into the firefox-esr autoremoval cascade (#436).
|
||||
* Override the embedded-library lint for the bundled minizip (#419).
|
||||
* Bump Standards-Version to 4.7.4 (no changes required).
|
||||
|
||||
-- Xavier Roche <xavier@debian.org> Sun, 28 Jun 2026 14:01:53 +0200
|
||||
|
||||
httrack (3.49.9-1) unstable; urgency=medium
|
||||
|
||||
* New upstream release: Content-Type and file-type detection fixes (trust a
|
||||
|
||||
4
debian/control
vendored
4
debian/control
vendored
@@ -2,7 +2,7 @@ Source: httrack
|
||||
Section: web
|
||||
Priority: optional
|
||||
Maintainer: Xavier Roche <roche@httrack.com>
|
||||
Standards-Version: 4.7.4
|
||||
Standards-Version: 4.7.0
|
||||
Build-Depends: debhelper-compat (= 13), autoconf, autoconf-archive, automake, libtool, zlib1g-dev, libssl-dev
|
||||
Rules-Requires-Root: no
|
||||
Homepage: http://www.httrack.com
|
||||
@@ -30,7 +30,7 @@ Description: Copy websites to your computer (Offline browser)
|
||||
Package: webhttrack
|
||||
Architecture: any
|
||||
Multi-Arch: foreign
|
||||
Depends: ${misc:Depends}, ${shlibs:Depends}, webhttrack-common, sensible-utils, chromium | firefox-esr | www-browser
|
||||
Depends: ${misc:Depends}, ${shlibs:Depends}, webhttrack-common, sensible-utils, firefox-esr | chromium | www-browser
|
||||
Replaces: webhttrack-common (<< 3.43.9-2)
|
||||
Breaks: webhttrack-common (<< 3.43.9-2)
|
||||
Suggests: httrack, httrack-doc
|
||||
|
||||
1
debian/patches/series
vendored
1
debian/patches/series
vendored
@@ -1 +0,0 @@
|
||||
skip-local-pause-test-without-python3.patch
|
||||
@@ -1,29 +0,0 @@
|
||||
Description: skip 28_local-pause when python3 is absent (fixes FTBFS on buildds)
|
||||
The local-server tests skip (exit 77) when python3 is missing, but
|
||||
28_local-pause wrapped local-crawl.sh in a command substitution that swallowed
|
||||
that skip. On the python3-less buildd chroot the test then ran serverless, both
|
||||
crawls finished in 0s, and the 0s delta was reported as a failure. Guard the
|
||||
test on python3 up front, like its siblings, so it skips cleanly.
|
||||
Author: Xavier Roche <roche@httrack.com>
|
||||
Origin: upstream, https://github.com/xroche/httrack/pull/445
|
||||
Applied-Upstream: https://github.com/xroche/httrack/commit/45279d7
|
||||
Forwarded: not-needed
|
||||
Last-Update: 2026-06-28
|
||||
diff --git a/tests/28_local-pause.test b/tests/28_local-pause.test
|
||||
index 8505a75..add95d1 100755
|
||||
--- a/tests/28_local-pause.test
|
||||
+++ b/tests/28_local-pause.test
|
||||
@@ -9,6 +9,13 @@ set -e
|
||||
|
||||
: "${top_srcdir:=..}"
|
||||
|
||||
+# python3 runs the local server (mirror local-crawl.sh); skip when absent, else
|
||||
+# run() swallows its exit-77 and the serverless 0s/0s crawl looks like a fail.
|
||||
+command -v python3 >/dev/null || {
|
||||
+ echo "python3 not found; skipping local crawl tests"
|
||||
+ exit 77
|
||||
+}
|
||||
+
|
||||
run() { # echoes the wall-clock seconds of one crawl
|
||||
local t0 t1
|
||||
t0=$(date +%s)
|
||||
20
history.txt
20
history.txt
@@ -4,25 +4,7 @@ HTTrack Website Copier release history:
|
||||
|
||||
This file lists all changes and fixes that have been made for HTTrack
|
||||
|
||||
3.49-10
|
||||
+ New: --cookies-file to preload a Netscape cookies.txt before crawling (#215)
|
||||
+ New: --pause to space out file downloads by a random delay (#185)
|
||||
+ New: --strip-query to drop selected query keys from the dedup naming (#112)
|
||||
+ Changed: split the -%u URL hacks into independent --keep-www-prefix, --keep-double-slashes and --keep-query-order toggles (#271)
|
||||
+ Fixed: follow a redirect Location after dropping its #fragment, instead of requesting the fragment and polluting the saved name (#204)
|
||||
+ Fixed: escaped brackets inside a *[...] filter character class (#148)
|
||||
+ Fixed: honor the server's Content-Range when resuming a partial download, instead of appending overlapping bytes (#198)
|
||||
+ Fixed: abort the download as soon as the response type is excluded by -mime:, instead of fetching then discarding the body (#58)
|
||||
+ Fixed: keep size-based filter rules neutral until the file size is known (#143)
|
||||
+ Fixed: stop the mirror with a clean fatal error on a cache write failure, instead of crashing (#174, #219)
|
||||
+ Fixed: stop the 412/416 partial re-get loop on --continue and --update (#206)
|
||||
+ Fixed: keep an unrecognized URL tail instead of mangling it to .html (#115)
|
||||
+ Fixed: honor --tolerant (-%B) on a broken Content-Length, and fix an out-of-bounds read it exposed (#32, #41)
|
||||
+ Fixed: fall back to the next resolved address when a connection fails or stalls, instead of hanging on a dead IPv6 address
|
||||
+ Fixed: report why a -%L URL list could not be loaded (#49)
|
||||
+ Changed: multiple internal hardening, build and CI improvements
|
||||
|
||||
.49-9
|
||||
3.49-9
|
||||
+ Fixed: file-type detection from the Content-Type header: trust a declared type over a binary URL extension, honor --assume under the delayed type check, and keep a known extension against a bogus or empty Content-Type (#267, #29, #56)
|
||||
+ Fixed: an uninitialized-buffer read when the Content-Type is empty (#411)
|
||||
+ Fixed: restored C++ source-compatibility of the installed headers so reverse dependencies (httraqt) build again (#413)
|
||||
|
||||
@@ -247,7 +247,7 @@ See also: The <a href="faq.html#VF1">FAQ</a><br>
|
||||
<td>the \ character</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td nowrap><tt>*[\[,\]]</tt></td>
|
||||
<td nowrap><tt>*[\[\]]</tt></td>
|
||||
<td>the [ or ] character</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
||||
@@ -295,7 +295,7 @@ Max Depth
|
||||
Maximum external depth:
|
||||
Maximum external depth:
|
||||
Filters (refuse/accept links) :
|
||||
Filters (refuse/accept links):
|
||||
Filters (refuse/accept links) :
|
||||
Paths
|
||||
Paths
|
||||
Save prefs
|
||||
|
||||
@@ -1,37 +0,0 @@
|
||||
# Translating HTTrack
|
||||
|
||||
Interface strings live here, one `.txt` file per language. `English.txt` is the reference: every other file maps each English string to its translation.
|
||||
|
||||
## File format
|
||||
|
||||
Plain text, entries in consecutive pairs of lines:
|
||||
|
||||
```
|
||||
<English string>
|
||||
<translation>
|
||||
```
|
||||
|
||||
The first line of a pair is the lookup key and must stay identical to the one in `English.txt`; translate only the second line. Missing entries fall back to the English text at runtime, so a partial translation works.
|
||||
|
||||
Preserve any `\r\n`, `\t` and `printf` placeholders (`%s`, `%d`, ...) in the translation.
|
||||
|
||||
A few `LANGUAGE_*` entries at the top describe the file itself:
|
||||
|
||||
| Key | Meaning |
|
||||
| --- | --- |
|
||||
| `LANGUAGE_NAME` | Name shown in the language picker, in its own language (`Deutsch`, not `German`) |
|
||||
| `LANGUAGE_ISO` | ISO 639 code, with region if needed (`de`, `pt_BR`) |
|
||||
| `LANGUAGE_CHARSET` | Encoding the file is saved in (`ISO-8859-1`, `windows-1251`, `UTF-8`, ...) |
|
||||
| `LANGUAGE_AUTHOR` | Your name and contact |
|
||||
| `LANGUAGE_WINDOWSID` | Windows locale name used by WinHTTrack (`German (Standard)`) |
|
||||
|
||||
Save the file in exactly its declared `LANGUAGE_CHARSET`; an editor that rewrites it as UTF-8 will corrupt the non-ASCII bytes.
|
||||
|
||||
## Adding or updating a language
|
||||
|
||||
1. Copy `English.txt` to `<Language>.txt`, or edit the existing file.
|
||||
2. Translate each second line; leave the English keys untouched.
|
||||
3. Fill in the `LANGUAGE_*` header for a new file.
|
||||
4. Open a pull request, or attach the file to a GitHub issue.
|
||||
|
||||
When new strings land in `English.txt` they show up untranslated (as English) until a translator fills them in.
|
||||
@@ -24,7 +24,6 @@ httrack \- offline browser : copy websites to a local directory
|
||||
[ \fB\-EN, \-\-max\-time[=N]\fR ]
|
||||
[ \fB\-AN, \-\-max\-rate[=N]\fR ]
|
||||
[ \fB\-%cN, \-\-connection\-per\-second[=N]\fR ]
|
||||
[ \fB\-%G, \-\-pause\fR ]
|
||||
[ \fB\-GN, \-\-max\-pause[=N]\fR ]
|
||||
[ \fB\-cN, \-\-sockets[=N]\fR ]
|
||||
[ \fB\-TN, \-\-timeout[=N]\fR ]
|
||||
@@ -50,7 +49,6 @@ httrack \- offline browser : copy websites to a local directory
|
||||
[ \fB\-%p, \-\-preserve\fR ]
|
||||
[ \fB\-%T, \-\-utf8\-conversion\fR ]
|
||||
[ \fB\-bN, \-\-cookies[=N]\fR ]
|
||||
[ \fB\-%K, \-\-cookies\-file\fR ]
|
||||
[ \fB\-u, \-\-check\-type[=N]\fR ]
|
||||
[ \fB\-j, \-\-parse\-java[=N]\fR ]
|
||||
[ \fB\-sN, \-\-robots[=N]\fR ]
|
||||
@@ -156,8 +154,6 @@ maximum mirror time in seconds (60=1 minute, 3600=1 hour) (\-\-max\-time[=N])
|
||||
maximum transfer rate in bytes/seconds (1000=1KB/s max) (\-\-max\-rate[=N])
|
||||
.IP \-%cN
|
||||
maximum number of connections/seconds (*%c10) (\-\-connection\-per\-second[=N])
|
||||
.IP \-%G
|
||||
random pause of MIN[:MAX] seconds between files (e.g. %G5:10) (\-\-pause <param>)
|
||||
.IP \-GN
|
||||
pause transfer if N bytes reached, and wait until lock file is deleted (\-\-max\-pause[=N])
|
||||
.SS Flow control:
|
||||
@@ -216,8 +212,6 @@ links conversion to UTF\-8 (\-\-utf8\-conversion)
|
||||
.SS Spider options:
|
||||
.IP \-bN
|
||||
accept cookies in cookies.txt (0=do not accept,* 1=accept) (\-\-cookies[=N])
|
||||
.IP \-%K
|
||||
load extra cookies from a Netscape cookies.txt (\-\-cookies\-file <param>)
|
||||
.IP \-u
|
||||
check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always) (\-\-check\-type[=N])
|
||||
.IP \-j
|
||||
|
||||
@@ -112,10 +112,6 @@ const char *hts_optalias[][4] = {
|
||||
{"include-query-string", "-%q", "single", ""},
|
||||
{"strip-query", "-%g", "param1",
|
||||
"strip [host/pattern=]key1,key2,... from URLs"},
|
||||
{"cookies-file", "-%K", "param1",
|
||||
"load extra cookies from a Netscape cookies.txt"},
|
||||
{"pause", "-%G", "param1",
|
||||
"random pause of MIN[:MAX] seconds between files"},
|
||||
{"generate-errors", "-o", "single", ""},
|
||||
{"do-not-generate-errors", "-o0", "single", ""},
|
||||
{"purge-old", "-X", "param", ""},
|
||||
|
||||
@@ -3,12 +3,12 @@
|
||||
|
||||
# Change this to download files
|
||||
if false; then
|
||||
echo "mget https://www.unicode.org/Public/MAPPINGS/ISO8859/8859-*.TXT" | lftp
|
||||
echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP*.TXT" | lftp
|
||||
echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP*.TXT" | lftp
|
||||
echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP*.TXT" | lftp
|
||||
echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/CP*.TXT" | lftp
|
||||
echo "mget https://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8*.TXT" | lftp
|
||||
echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/ISO8859/8859-*.TXT" | lftp
|
||||
echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP*.TXT" | lftp
|
||||
echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP*.TXT" | lftp
|
||||
echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP*.TXT" | lftp
|
||||
echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/CP*.TXT" | lftp
|
||||
echo "mget ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8*.TXT" | lftp
|
||||
rm -f CP932.TXT CP936.TXT CP949.TXT CP950.TXT
|
||||
fi
|
||||
|
||||
|
||||
@@ -35,7 +35,6 @@ Please visit our Website: http://www.httrack.com
|
||||
|
||||
#include <fcntl.h>
|
||||
#include <ctype.h>
|
||||
#include <stdint.h> /* uint64_t for the pause mixer (already a hard dep via md5.h) */
|
||||
|
||||
/* File defs */
|
||||
#include "htscore.h"
|
||||
@@ -524,12 +523,9 @@ int httpmirror(char *url1, httrackp * opt) {
|
||||
opt->cookie = &cookie;
|
||||
cookie.max_len = 30000; // max len
|
||||
strcpybuff(cookie.data, "");
|
||||
// Load the mirror's cookies.txt, then the one in the current directory
|
||||
// Charger cookies.txt par défaut ou cookies.txt du miroir
|
||||
cookie_load(opt->cookie, StringBuff(opt->path_log), "cookies.txt");
|
||||
cookie_load(opt->cookie, "", "cookies.txt");
|
||||
// A user-supplied cookie file is merged last so it wins on conflicts
|
||||
if (strnotempty(StringBuff(opt->cookies_file)))
|
||||
cookie_load(opt->cookie, "", StringBuff(opt->cookies_file));
|
||||
} else
|
||||
opt->cookie = NULL;
|
||||
|
||||
@@ -3315,21 +3311,6 @@ HTS_INLINE int back_fillmax(struct_back * sback, httrackp * opt,
|
||||
return -1; /* plus de place */
|
||||
}
|
||||
|
||||
/* Seed-derived: stable within a gap, rerolls per launch; a per-call rand()
|
||||
would bias the delay toward min_ms (see header). Jitter, not crypto. */
|
||||
int hts_pause_target_ms(TStamp seed, int min_ms, int max_ms) {
|
||||
uint64_t z = (uint64_t) seed;
|
||||
|
||||
if (max_ms <= min_ms)
|
||||
return min_ms;
|
||||
/* SplitMix64 finalizer: scrambles the low-entropy ms timestamp. */
|
||||
z += 0x9E3779B97F4A7C15ULL;
|
||||
z = (z ^ (z >> 30)) * 0xBF58476D1CE4E5B9ULL;
|
||||
z = (z ^ (z >> 27)) * 0x94D049BB133111EBULL;
|
||||
z ^= z >> 31;
|
||||
return min_ms + (int) (z % (uint64_t) (max_ms - min_ms + 1));
|
||||
}
|
||||
|
||||
int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt) {
|
||||
int n = opt->maxsoc - back_nsoc(sback);
|
||||
|
||||
@@ -3350,18 +3331,6 @@ int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt) {
|
||||
}
|
||||
}
|
||||
|
||||
// #185 randomized inter-file pause: non-blocking, one launch per gap
|
||||
if (n > 0 && opt->pause_max_ms > 0 && HTS_STAT.last_connect > 0) {
|
||||
TStamp opTime =
|
||||
HTS_STAT.last_request ? HTS_STAT.last_request : HTS_STAT.last_connect;
|
||||
TStamp lap = mtime_local() - opTime;
|
||||
|
||||
if (lap < hts_pause_target_ms(opTime, opt->pause_min_ms, opt->pause_max_ms))
|
||||
n = 0;
|
||||
else
|
||||
n = 1;
|
||||
}
|
||||
|
||||
return n;
|
||||
}
|
||||
|
||||
@@ -3773,14 +3742,6 @@ HTSEXT_API int copy_htsopt(const httrackp * from, httrackp * to) {
|
||||
if (StringNotEmpty(from->strip_query))
|
||||
StringCopyS(to->strip_query, from->strip_query);
|
||||
|
||||
if (StringNotEmpty(from->cookies_file))
|
||||
StringCopyS(to->cookies_file, from->cookies_file);
|
||||
|
||||
if (from->pause_max_ms > 0) {
|
||||
to->pause_min_ms = from->pause_min_ms;
|
||||
to->pause_max_ms = from->pause_max_ms;
|
||||
}
|
||||
|
||||
if (from->retry > -1)
|
||||
to->retry = from->retry;
|
||||
|
||||
|
||||
@@ -418,10 +418,6 @@ int back_pluggable_sockets(struct_back * sback, httrackp * opt);
|
||||
|
||||
int back_pluggable_sockets_strict(struct_back * sback, httrackp * opt);
|
||||
|
||||
/* Randomized inter-file pause target in [min_ms,max_ms] (#185), derived from a
|
||||
timestamp seed so it is stable within one gap and rerolls per launch. */
|
||||
int hts_pause_target_ms(TStamp seed, int min_ms, int max_ms);
|
||||
|
||||
/* Schedule more links from the heap into free slots. Returns the number queued,
|
||||
or <=0 if none could be added (no free slot / paused / stopped). */
|
||||
int back_fill(struct_back * sback, httrackp * opt, cache_back * cache,
|
||||
|
||||
@@ -1976,51 +1976,6 @@ static int hts_main_internal(int argc, char **argv, httrackp * opt) {
|
||||
StringCat(opt->strip_query, argv[na]);
|
||||
}
|
||||
break;
|
||||
case 'K': // cookies-file: extra Netscape cookies.txt to preload
|
||||
if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
|
||||
HTS_PANIC_PRINTF(
|
||||
"Option cookies-file needs a blank space and "
|
||||
"a cookies.txt path");
|
||||
printf("Example: --cookies-file \"/home/me/cookies.txt\"\n");
|
||||
htsmain_free();
|
||||
return -1;
|
||||
} else {
|
||||
na++;
|
||||
if (strlen(argv[na]) >= 1024) {
|
||||
HTS_PANIC_PRINTF("Cookie file path too long");
|
||||
htsmain_free();
|
||||
return -1;
|
||||
}
|
||||
StringCopy(opt->cookies_file, argv[na]);
|
||||
}
|
||||
break;
|
||||
case 'G': // pause: randomized inter-file delay MIN[:MAX] seconds
|
||||
if ((na + 1 >= argc) || (argv[na + 1][0] == '-')) {
|
||||
HTS_PANIC_PRINTF("Option pause needs a blank space and a "
|
||||
"delay in seconds (MIN[:MAX])");
|
||||
printf("Example: --pause 5:10\n");
|
||||
htsmain_free();
|
||||
return -1;
|
||||
} else {
|
||||
double pmin = 0, pmax = 0;
|
||||
int nf;
|
||||
|
||||
na++;
|
||||
nf = sscanf(argv[na], "%lf:%lf", &pmin, &pmax);
|
||||
if (nf < 2)
|
||||
pmax = pmin; /* a single value means a fixed delay */
|
||||
/* positive-form bounds: NaN fails every comparison, so this
|
||||
rejects it before the undefined (int)(NaN*1000) cast */
|
||||
if (nf < 1 || !(pmin >= 0 && pmax >= pmin && pmax <= 86400)) {
|
||||
HTS_PANIC_PRINTF("Invalid --pause range (expected "
|
||||
"MIN[:MAX] seconds, 0<=MIN<=MAX<=86400)");
|
||||
htsmain_free();
|
||||
return -1;
|
||||
}
|
||||
opt->pause_min_ms = (int) (pmin * 1000.0);
|
||||
opt->pause_max_ms = (int) (pmax * 1000.0);
|
||||
}
|
||||
break;
|
||||
case 't': /* do not change type (ending) of filenames according to the MIME type */
|
||||
opt->no_type_change = 1;
|
||||
if (*(com+1)=='0') { opt->no_type_change = 0; com++; }
|
||||
|
||||
@@ -30,14 +30,12 @@ Please visit our Website: http://www.httrack.com
|
||||
/* Author: Xavier Roche */
|
||||
/* ------------------------------------------------------------ */
|
||||
|
||||
#include <stdint.h>
|
||||
|
||||
#include "htscharset.h"
|
||||
#include "htsencoding.h"
|
||||
#include "htssafe.h"
|
||||
|
||||
/* static int decode_entity(const uint64_t hash, const size_t len);
|
||||
*/
|
||||
/* static int decode_entity(const unsigned int hash, const size_t len);
|
||||
*/
|
||||
#include "htsentities.h"
|
||||
|
||||
/* hexadecimal conversion */
|
||||
@@ -52,31 +50,30 @@ static int get_hex_value(char c) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
/* 64-bit FNV-1a; must match htsentities.sh, which keys the entity table on it.
|
||||
*/
|
||||
#define HASH_INIT 0xcbf29ce484222325ULL
|
||||
#define HASH_PRIME 0x100000001b3ULL
|
||||
#define HASH_ADD(HASH, C) \
|
||||
do { \
|
||||
(HASH) ^= (unsigned char) (C); \
|
||||
(HASH) *= HASH_PRIME; \
|
||||
} while (0)
|
||||
/* Numerical Recipes,
|
||||
see <http://en.wikipedia.org/wiki/Linear_congruential_generator> */
|
||||
#define HASH_PRIME ( 1664525 )
|
||||
#define HASH_CONST ( 1013904223 )
|
||||
#define HASH_ADD(HASH, C) do { \
|
||||
(HASH) *= HASH_PRIME; \
|
||||
(HASH) += HASH_CONST; \
|
||||
(HASH) += (C); \
|
||||
} while(0)
|
||||
|
||||
int hts_unescapeEntitiesWithCharset(const char *src, char *dest, const size_t max, const char *charset) {
|
||||
size_t i, j, ampStart, ampStartDest;
|
||||
int uc;
|
||||
int hex;
|
||||
uint64_t hash;
|
||||
unsigned int hash;
|
||||
|
||||
assertf(max != 0);
|
||||
for (i = 0, j = 0, ampStart = (size_t) -1, ampStartDest = 0, uc = -1, hex = 0,
|
||||
hash = HASH_INIT;
|
||||
src[i] != '\0'; i++) {
|
||||
for(i = 0, j = 0, ampStart = (size_t) -1, ampStartDest = 0,
|
||||
uc = -1, hex = 0, hash = 0 ; src[i] != '\0' ; i++) {
|
||||
/* start of entity */
|
||||
if (src[i] == '&') {
|
||||
ampStart = i;
|
||||
ampStartDest = j;
|
||||
hash = HASH_INIT;
|
||||
hash = 0;
|
||||
uc = -1;
|
||||
}
|
||||
/* inside a potential entity */
|
||||
@@ -177,11 +174,14 @@ int hts_unescapeEntitiesWithCharset(const char *src, char *dest, const size_t ma
|
||||
}
|
||||
/* alphanumerical entity */
|
||||
else {
|
||||
/* alphanum, capped at the longest name
|
||||
* '∳' (31) */
|
||||
if (i <= ampStart + 31 && ((src[i] >= '0' && src[i] <= '9') ||
|
||||
(src[i] >= 'A' && src[i] <= 'Z') ||
|
||||
(src[i] >= 'a' && src[i] <= 'z'))) {
|
||||
/* alphanum and not too far ('ϑ' is the longest) */
|
||||
if (i <= ampStart + 10 &&
|
||||
(
|
||||
(src[i] >= '0' && src[i] <= '9')
|
||||
|| (src[i] >= 'A' && src[i] <= 'Z')
|
||||
|| (src[i] >= 'a' && src[i] <= 'z')
|
||||
)
|
||||
) {
|
||||
/* compute hash */
|
||||
HASH_ADD(hash, (unsigned char) src[i]);
|
||||
} else {
|
||||
|
||||
13612
src/htsentities.h
13612
src/htsentities.h
File diff suppressed because it is too large
Load Diff
@@ -1,92 +1,75 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
# Regenerate htsentities.h from the WHATWG named character references.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
src=entities.json
|
||||
url=https://html.spec.whatwg.org/entities.json
|
||||
src=html40.txt
|
||||
url=http://www.w3.org/TR/1998/REC-html40-19980424/html40.txt
|
||||
dest=htsentities.h
|
||||
|
||||
# 64-bit FNV-1a of $1, printed as a C constant. Must match the hash in
|
||||
# htsencoding.c. The offset basis is stored as its wrapped (signed) bit pattern;
|
||||
# bash arithmetic is 64-bit two's complement, so the result is bit-exact.
|
||||
fnv1a() {
|
||||
local s=$1 i c h=$((0xcbf29ce484222325))
|
||||
for ((i = 0; i < ${#s}; i++)); do
|
||||
printf -v c '%d' "'${s:i:1}"
|
||||
h=$(((h ^ (c & 0xff)) * 0x100000001b3))
|
||||
done
|
||||
printf '0x%016xULL' "$h"
|
||||
}
|
||||
(
|
||||
cat <<EOF
|
||||
/*
|
||||
-- ${dest} --
|
||||
FILE GENERATED BY $0, DO NOT MODIFY
|
||||
|
||||
if [ ! -f "$src" ]; then
|
||||
curl -fsS "$url" -o "$src"
|
||||
fi
|
||||
We compute the LCG hash
|
||||
(see <http://en.wikipedia.org/wiki/Linear_congruential_generator>)
|
||||
for each entity. We should in theory check using strncmp() that we
|
||||
actually have the correct entity, but this is actually statistically
|
||||
not needed.
|
||||
|
||||
# Keep ';'-terminated single-codepoint names; the ~93 multi-codepoint refs can't
|
||||
# fit decode_entity's single-codepoint return and are skipped (left verbatim).
|
||||
pairs=$(jq -r '
|
||||
to_entries
|
||||
| map(select((.key | endswith(";")) and (.value.codepoints | length == 1)))
|
||||
| sort_by(.key)
|
||||
| .[] | "\(.key | ltrimstr("&") | rtrimstr(";"))\t\(.value.codepoints[0])"' "$src")
|
||||
We may want to do better, but we expect the hash function to be uniform, and
|
||||
let the compiler be smart enough to optimize the switch (for example by
|
||||
checking in log2() intervals)
|
||||
|
||||
This code has been generated using the evil $0 script.
|
||||
*/
|
||||
|
||||
# Skipped multi-codepoint names, kept to prove none aliases an emitted hash.
|
||||
skipped=$(jq -r '
|
||||
to_entries
|
||||
| map(select((.key | endswith(";")) and (.value.codepoints | length > 1)))
|
||||
| .[] | .key | ltrimstr("&") | rtrimstr(";")' "$src")
|
||||
|
||||
cases=""
|
||||
emit_hashes=""
|
||||
while IFS=$'\t' read -r name cp; do
|
||||
hash=$(fnv1a "$name")
|
||||
cases+=" /* $name */"$'\n'
|
||||
cases+=" case $hash:"$'\n'
|
||||
cases+=" if (len == ${#name}) {"$'\n'
|
||||
cases+=" return $cp;"$'\n'
|
||||
cases+=" }"$'\n'
|
||||
cases+=" break;"$'\n'
|
||||
emit_hashes+="$hash"$'\n'
|
||||
done <<<"$pairs"
|
||||
|
||||
skip_hashes=""
|
||||
while IFS= read -r name; do
|
||||
[ -n "$name" ] && skip_hashes+="$(fnv1a "$name")"$'\n'
|
||||
done <<<"$skipped"
|
||||
|
||||
# The switch keys on the hash alone, so the dispatch is correct only while every
|
||||
# emitted name hashes uniquely; prove it here, no runtime name compare needed.
|
||||
dups=$(printf '%s' "$emit_hashes" | sort | uniq -d || true)
|
||||
if [ -n "$dups" ]; then
|
||||
echo "FATAL: two entity names share a hash (duplicate switch case); change the hash:" >&2
|
||||
echo "$dups" >&2
|
||||
exit 1
|
||||
fi
|
||||
# A skipped name colliding with an emitted hash would mis-decode instead of
|
||||
# staying verbatim; forbid that too.
|
||||
aliased=$(comm -12 <(printf '%s' "$emit_hashes" | sort -u) <(printf '%s' "$skip_hashes" | sort -u) || true)
|
||||
if [ -n "$aliased" ]; then
|
||||
echo "FATAL: a skipped multi-codepoint name aliases an emitted hash:" >&2
|
||||
echo "$aliased" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
cat >"$dest" <<EOF
|
||||
/* GENERATED by $0 from the WHATWG named character references
|
||||
(${url}). DO NOT EDIT.
|
||||
Dispatch keys on a 64-bit FNV-1a hash of the entity name; the generator
|
||||
aborts on any hash collision, so no runtime name compare is needed. */
|
||||
|
||||
#include <stdint.h>
|
||||
|
||||
static int decode_entity(const uint64_t hash, const size_t len) {
|
||||
static int decode_entity(const unsigned int hash, const size_t len) {
|
||||
switch(hash) {
|
||||
${cases} }
|
||||
EOF
|
||||
(
|
||||
if test -f ${src}; then
|
||||
cat ${src}
|
||||
else
|
||||
GET "${url}"
|
||||
fi
|
||||
) |
|
||||
grep -E '^<!ENTITY [a-zA-Z0-9_]' |
|
||||
sed \
|
||||
-e 's/<!ENTITY //' -e "s/[[:space:]][[:space:]]*/ /g" \
|
||||
-e 's/-->$//' \
|
||||
-e 's/\([^ ]*\) CDATA "&#\([^\"]*\);" -- \(.*\)/\1 \2 \3/' |
|
||||
(
|
||||
read -r A
|
||||
while test -n "$A"; do
|
||||
ent="${A%% *}"
|
||||
code=$(echo "$A" | cut -f2 -d' ')
|
||||
# compute hash
|
||||
hash=0
|
||||
i=0
|
||||
a=1664525
|
||||
c=1013904223
|
||||
m="$((1 << 32))"
|
||||
while test "$i" -lt ${#ent}; do
|
||||
d="$(echo -n "${ent:${i}:1}" | hexdump -v -e '/1 "%d"')"
|
||||
hash="$((((hash * a) % (m) + d + c) % (m)))"
|
||||
i=$((i + 1))
|
||||
done
|
||||
echo -e " /* $A */"
|
||||
echo -e " case ${hash}u:"
|
||||
echo -e " if (len == ${#ent} /* && strncmp(ent, \"${ent}\") == 0 */) {"
|
||||
echo -e " return ${code};"
|
||||
echo -e " }"
|
||||
echo -e " break;"
|
||||
|
||||
# next
|
||||
read -r A
|
||||
done
|
||||
)
|
||||
cat <<EOF
|
||||
}
|
||||
/* unknown */
|
||||
return -1;
|
||||
}
|
||||
EOF
|
||||
|
||||
echo "wrote $dest ($(grep -c '^ case ' "$dest") entities)" >&2
|
||||
) >${dest}
|
||||
|
||||
@@ -193,12 +193,7 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * s
|
||||
int len = (int) strlen(joker);
|
||||
|
||||
while((joker[i] != RIGHT) && (joker[i]) && (i < len)) {
|
||||
// '\' escapes the next char as a literal member, e.g. *[\[\]]
|
||||
if (joker[i] == '\\' && joker[i + 1] != '\0') {
|
||||
i++;
|
||||
pass[(int) (unsigned char) joker[i]] = 1;
|
||||
i++;
|
||||
} else if ((joker[i] == '<') || (joker[i] == '>')) { // *[<10]
|
||||
if ((joker[i] == '<') || (joker[i] == '>')) { // *[<10]
|
||||
int lsize = 0;
|
||||
int lverdict;
|
||||
|
||||
@@ -226,9 +221,7 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * s
|
||||
while(isdigit((unsigned char) joker[i]))
|
||||
i++;
|
||||
}
|
||||
} else if (joker[i + 1] == '-' && joker[i + 2] != '\0') {
|
||||
// range *[A-Z]; the '\0' guard rejects a truncated *[a- (else
|
||||
// i+=3 overshoots the NUL)
|
||||
} else if (joker[i + 1] == '-') { // 2 car, ex: *[A-Z]
|
||||
if ((int) (unsigned char) joker[i + 2] >
|
||||
(int) (unsigned char) joker[i]) {
|
||||
int j;
|
||||
@@ -240,7 +233,10 @@ HTS_INLINE const char *strjoker(const char *chaine, const char *joker, LLint * s
|
||||
}
|
||||
// else err=1;
|
||||
i += 3;
|
||||
} else { // 1 car, ex: *[ ]
|
||||
} else { // 1 car, ex: *[ ]
|
||||
if (joker[i + 2] == '\\' && joker[i + 3] != 0) { // escaped char, such as *[\[] or *[\]]
|
||||
i++;
|
||||
}
|
||||
pass[(int) (unsigned char) joker[i]] = 1;
|
||||
i++;
|
||||
}
|
||||
|
||||
@@ -43,8 +43,8 @@ Please visit our Website: http://www.httrack.com
|
||||
configure.ac, decoupled from these). VERSION is the display form, VERSIONID
|
||||
the dotted numeric form, AFF_VERSION the short form shown in footers,
|
||||
LIB_VERSION the data/cache format generation. */
|
||||
#define HTTRACK_VERSION "3.49-10"
|
||||
#define HTTRACK_VERSIONID "3.49.10"
|
||||
#define HTTRACK_VERSION "3.49-9"
|
||||
#define HTTRACK_VERSIONID "3.49.9"
|
||||
#define HTTRACK_AFF_VERSION "3.x"
|
||||
#define HTTRACK_LIB_VERSION "2.0"
|
||||
|
||||
|
||||
@@ -521,7 +521,6 @@ void help(const char *app, int more) {
|
||||
infomsg(" EN maximum mirror time in seconds (60=1 minute, 3600=1 hour)");
|
||||
infomsg(" AN maximum transfer rate in bytes/seconds (1000=1KB/s max)");
|
||||
infomsg(" %cN maximum number of connections/seconds (*%c10)");
|
||||
infomsg(" %G random pause of MIN[:MAX] seconds between files (e.g. %G5:10)");
|
||||
infomsg
|
||||
(" GN pause transfer if N bytes reached, and wait until lock file is deleted");
|
||||
infomsg("");
|
||||
@@ -573,7 +572,6 @@ void help(const char *app, int more) {
|
||||
infomsg("");
|
||||
infomsg("Spider options:");
|
||||
infomsg(" bN accept cookies in cookies.txt (0=do not accept,* 1=accept)");
|
||||
infomsg(" %K load extra cookies from a Netscape cookies.txt");
|
||||
infomsg
|
||||
(" u check document type if unknown (cgi,asp..) (u0 don't check, * u1 check but /, u2 check always)");
|
||||
infomsg
|
||||
|
||||
@@ -6045,9 +6045,6 @@ HTSEXT_API httrackp *hts_create_opt(void) {
|
||||
opt->no_query_dedup = HTS_FALSE;
|
||||
StringCopy(opt->footer, HTS_DEFAULT_FOOTER);
|
||||
StringCopy(opt->strip_query, "");
|
||||
StringCopy(opt->cookies_file, "");
|
||||
opt->pause_min_ms = 0;
|
||||
opt->pause_max_ms = 0;
|
||||
opt->ftp_proxy = HTS_TRUE;
|
||||
opt->convert_utf8 = HTS_TRUE;
|
||||
StringCopy(opt->filelist, "");
|
||||
@@ -6193,7 +6190,6 @@ HTSEXT_API void hts_free_opt(httrackp * opt) {
|
||||
StringFree(opt->footer);
|
||||
StringFree(opt->mod_blacklist);
|
||||
StringFree(opt->strip_query);
|
||||
StringFree(opt->cookies_file);
|
||||
|
||||
StringFree(opt->path_html);
|
||||
StringFree(opt->path_html_utf8);
|
||||
|
||||
@@ -535,10 +535,6 @@ struct httrackp {
|
||||
no_www_dedup; /**< with urlhack, keep www.host distinct from host */
|
||||
hts_boolean no_slash_dedup; /**< with urlhack, keep redundant // in paths */
|
||||
hts_boolean no_query_dedup; /**< with urlhack, keep query-argument order */
|
||||
String cookies_file; /**< extra Netscape cookies.txt to preload
|
||||
(--cookies-file) */
|
||||
int pause_min_ms; /**< inter-file pause lower bound, ms (0=off, #185) */
|
||||
int pause_max_ms; /**< inter-file pause upper bound, ms */
|
||||
};
|
||||
|
||||
/* Running statistics for a mirror. */
|
||||
|
||||
@@ -302,14 +302,6 @@ static HTS_INLINE char html_prevc(const char *html, const char *start) {
|
||||
return html > start ? html[-1] : ' ';
|
||||
}
|
||||
|
||||
/* Drop a redirect Location's #fragment: a UA anchor, never part of the fetched
|
||||
* resource (#204). */
|
||||
static void url_drop_fragment(char *const url) {
|
||||
char *const frag = strchr(url, '#');
|
||||
if (frag != NULL)
|
||||
*frag = '\0';
|
||||
}
|
||||
|
||||
/* True if [s, s+len) is exactly an HTTP method token (XHR.open's first
|
||||
argument is a method, not a URL: #218). Case-insensitive. */
|
||||
static int is_http_method(const char *s, size_t len) {
|
||||
@@ -3604,7 +3596,6 @@ int hts_mirror_check_moved(htsmoduleStruct * str,
|
||||
//
|
||||
|
||||
strcpybuff(mov_url, r->location);
|
||||
url_drop_fragment(mov_url);
|
||||
|
||||
// url qque -> adresse+fichier
|
||||
if ((reponse =
|
||||
@@ -4812,7 +4803,6 @@ int hts_wait_delayed(htsmoduleStruct * str, lien_adrfilsave *afs,
|
||||
|
||||
mov_url[0] = '\0';
|
||||
strcpybuff(mov_url, back[b].r.location); // copier URL
|
||||
url_drop_fragment(mov_url);
|
||||
|
||||
/* Remove (temporarily created) file if it was created */
|
||||
UNLINK(fconv(OPT_GET_BUFF(opt), OPT_GET_BUFF_SIZE(opt), back[b].url_sav));
|
||||
|
||||
@@ -512,21 +512,15 @@ static int string_safety_selftests(void) {
|
||||
/* ------------------------------------------------------------ */
|
||||
|
||||
static int st_filter(httrackp *opt, int argc, char **argv) {
|
||||
char *str, *pat;
|
||||
int matched;
|
||||
|
||||
(void) opt;
|
||||
if (argc < 2) {
|
||||
fprintf(stderr, "filter: needs a filter pattern and a string\n");
|
||||
return 1;
|
||||
}
|
||||
/* exact-size heap copies so a sanitizer traps any over-read of the pattern */
|
||||
str = strdupt(argv[1]);
|
||||
pat = strdupt(argv[0]);
|
||||
matched = strjoker(str, pat, NULL, NULL) != NULL;
|
||||
printf("%s does %s %s\n", argv[1], matched ? "match" : "NOT match", argv[0]);
|
||||
freet(str);
|
||||
freet(pat);
|
||||
if (strjoker(argv[1], argv[0], NULL, NULL))
|
||||
printf("%s does match %s\n", argv[1], argv[0]);
|
||||
else
|
||||
printf("%s does NOT match %s\n", argv[1], argv[0]);
|
||||
return 0;
|
||||
}
|
||||
|
||||
@@ -905,71 +899,12 @@ static int st_copyopt(httrackp *opt, int argc, char **argv) {
|
||||
if (to->parseall != HTS_TRUE)
|
||||
err = 1;
|
||||
|
||||
/* String field: a non-empty source deep-copies across, an empty source
|
||||
leaves the target intact (StringNotEmpty guard). Covers the exported
|
||||
copy_htsopt String path that no crawl test reaches. */
|
||||
StringCopy(from->cookies_file, "/tmp/jar.txt");
|
||||
StringCopy(to->cookies_file, "");
|
||||
copy_htsopt(from, to);
|
||||
if (strcmp(StringBuff(to->cookies_file), "/tmp/jar.txt") != 0)
|
||||
err = 1;
|
||||
StringCopy(from->cookies_file, "");
|
||||
copy_htsopt(from, to);
|
||||
if (strcmp(StringBuff(to->cookies_file), "/tmp/jar.txt") != 0)
|
||||
err = 1;
|
||||
|
||||
/* #185 pause pair: copied when enabled (max>0), the 0 sentinel skips */
|
||||
from->pause_min_ms = 5000;
|
||||
from->pause_max_ms = 10000;
|
||||
to->pause_min_ms = to->pause_max_ms = 0;
|
||||
copy_htsopt(from, to);
|
||||
if (to->pause_min_ms != 5000 || to->pause_max_ms != 10000)
|
||||
err = 1;
|
||||
from->pause_min_ms = from->pause_max_ms = 0;
|
||||
copy_htsopt(from, to);
|
||||
if (to->pause_min_ms != 5000 || to->pause_max_ms != 10000)
|
||||
err = 1;
|
||||
|
||||
hts_free_opt(from);
|
||||
hts_free_opt(to);
|
||||
printf("copy-htsopt: %s\n", err ? "FAIL" : "OK");
|
||||
return err;
|
||||
}
|
||||
|
||||
static int st_pause(httrackp *opt, int argc, char **argv) {
|
||||
int err = 0, i, seen_low = 0, seen_high = 0;
|
||||
|
||||
(void) opt;
|
||||
(void) argc;
|
||||
(void) argv;
|
||||
/* Consecutive-ms seeds (production shape: launch timestamps a few ms apart)
|
||||
must stay in range and spread, not collapse to a bound -- worst case for a
|
||||
weak low-bit mixer. */
|
||||
for (i = 0; i < 10000; i++) {
|
||||
int t = hts_pause_target_ms((TStamp) (1719500000000LL + i), 5000, 10000);
|
||||
|
||||
if (t < 5000 || t > 10000)
|
||||
err = 1;
|
||||
seen_low |= (t < 6000);
|
||||
seen_high |= (t > 9000);
|
||||
}
|
||||
if (!seen_low || !seen_high)
|
||||
err = 1;
|
||||
if (hts_pause_target_ms(12345, 8000, 8000) != 8000) /* equal bounds = fixed */
|
||||
err = 1;
|
||||
/* deterministic: a seed yields the same target even after an intervening call
|
||||
with another seed (no global PRNG state to perturb it) */
|
||||
{
|
||||
int a = hts_pause_target_ms(99, 5000, 10000);
|
||||
|
||||
(void) hts_pause_target_ms(54321, 5000, 10000);
|
||||
if (hts_pause_target_ms(99, 5000, 10000) != a)
|
||||
err = 1;
|
||||
}
|
||||
printf("pause: %s\n", err ? "FAIL" : "OK");
|
||||
return err;
|
||||
}
|
||||
|
||||
static int st_relative(httrackp *opt, int argc, char **argv) {
|
||||
char s[HTS_URLMAXSIZE * 2];
|
||||
|
||||
@@ -1316,7 +1251,6 @@ static const struct selftest_entry {
|
||||
{"strsafe", "[overflow|overflow-buff [str]]", "bounded string-op self-test",
|
||||
st_strsafe},
|
||||
{"copyopt", "", "copy_htsopt option-copy self-test", st_copyopt},
|
||||
{"pause", "", "randomized inter-file pause target self-test", st_pause},
|
||||
{"relative", "<link> <curr-file>", "relative link between two paths",
|
||||
st_relative},
|
||||
{"resolve", "<link> <adr> <fil>", "resolve a link against an origin",
|
||||
|
||||
@@ -90,16 +90,4 @@ refused "dangling-quote argument not refused cleanly"
|
||||
run_only "$tmp/q-lone" '"'
|
||||
refused "lone-quote argument not refused cleanly"
|
||||
|
||||
# --pause (#185): valid MIN[:MAX] accepted; malformed, reversed, over-range and
|
||||
# non-finite values refused cleanly. NaN defeats naive `<`/`>` checks (it
|
||||
# compares false to everything), so it must not slip through to the int cast.
|
||||
run "$tmp/pause-ok" --pause 0.2:0.4
|
||||
accepted "$tmp/pause-ok" "#185: valid --pause range rejected"
|
||||
run "$tmp/pause-fix" --pause 0.2
|
||||
accepted "$tmp/pause-fix" "#185: valid fixed --pause rejected"
|
||||
for bad in nan nan:5 5:nan inf 10:5 99999; do
|
||||
run "$tmp/pause-bad" --pause "$bad"
|
||||
refused "#185: invalid --pause '$bad' not refused cleanly"
|
||||
done
|
||||
|
||||
exit 0
|
||||
|
||||
@@ -18,21 +18,6 @@ ent '&' '&'
|
||||
ent '<>' '<>'
|
||||
ent 'é' 'é'
|
||||
|
||||
# HTML5 names from the WHATWG set
|
||||
ent '…' '…'
|
||||
ent '⋃' '⋃'
|
||||
# longest name (31 chars) exercises the name-length cap
|
||||
ent '∳' '∳'
|
||||
# astral codepoint -> 4-byte UTF-8
|
||||
ent '𝔸' '𝔸'
|
||||
# multi-codepoint refs are skipped at generation, so left verbatim
|
||||
ent 'fj' 'fj'
|
||||
|
||||
# common HTML4 names still decode (regression guard against accidental drops)
|
||||
ent '©®™' '©®™'
|
||||
ent '—–' '—–'
|
||||
ent 'αβ' 'αβ'
|
||||
|
||||
# numeric: decimal and hex
|
||||
ent 'AB' 'AB'
|
||||
ent 'A' 'A'
|
||||
|
||||
@@ -50,54 +50,27 @@ match '*foo*bar' 'foozbar'
|
||||
# '?' is the query-string marker, not a single-char wildcard
|
||||
nomatch 'a?c' 'abc'
|
||||
|
||||
# Inside a class, backslash escapes the next char as a literal member (#148):
|
||||
# '\X' matches X only (not '\'), and an escaped ']' is a member, not the terminator.
|
||||
# backslash escapes a metacharacter inside a class so it is matched literally.
|
||||
# Quirk: the decoder also adds the backslash itself to the set, so '\X' matches
|
||||
# both X and '\'. These assertions pin that behavior.
|
||||
match '*[\*]' '*'
|
||||
nomatch '*[\*]' "\\"
|
||||
match '*[\*]' "\\"
|
||||
nomatch '*[\*]' 'a'
|
||||
match '*[\\]' "\\"
|
||||
nomatch '*[\\]' '*'
|
||||
nomatch '*[\\]' 'a'
|
||||
match '*[\[]' '['
|
||||
nomatch '*[\[]' "\\"
|
||||
match '*[\]]' ']'
|
||||
nomatch '*[\]]' "\\"
|
||||
match '*[\[]' "\\"
|
||||
nomatch '*[\[]' 'a'
|
||||
|
||||
# '*[\[\]]' is "the [ or ] character", as the filter guide documents.
|
||||
match '*[\[\]]' '['
|
||||
match '*[\[\]]' ']'
|
||||
nomatch '*[\[\]]' 'a'
|
||||
match '*[\[,\]]' '[' # comma between members is optional
|
||||
match '*[\[,\]]' ']'
|
||||
match '*[a,\[]' 'a' # an escaped member no longer eats the preceding one
|
||||
match '*[a,\[]' '['
|
||||
|
||||
# Escape is decoded before the range/separator/size checks, so '\-' '\,' '\<'
|
||||
# are literal members, not operators.
|
||||
match '*[a\-z]' 'a'
|
||||
match '*[a\-z]' 'z'
|
||||
nomatch '*[a\-z]' 'b' # not the a..z range
|
||||
match '*[\,]' ','
|
||||
nomatch '*[\,]' "\\" # the escape must not leak '\' into the class
|
||||
match '*[\<]' '<'
|
||||
nomatch '*[\<]' "\\"
|
||||
match '*[\[,\],a]' '['
|
||||
match '*[\[,\],a]' ']'
|
||||
match '*[\[,\],a]' 'a'
|
||||
|
||||
# A truncated range '*[a-' is the literal members {a,-}; the parser must not
|
||||
# read past the end decoding it (was a 1-byte heap over-read in the range arm).
|
||||
match '*[a-' 'a'
|
||||
nomatch '*[a-' 'b'
|
||||
|
||||
# *(...) matches exactly one char from the class; *[...] matches a run.
|
||||
match '*(a,b)' 'a'
|
||||
nomatch '*(a,b)' 'aa'
|
||||
nomatch '*(a,b)' 'c'
|
||||
|
||||
# documented composite filters (filters.html)
|
||||
match 'www.*[path].com/*[path].zip' 'www.foo.com/a/b.zip'
|
||||
nomatch 'www.*[path].com/*[path].zip' 'www.foo.com/a/b.tar'
|
||||
match '*.html*[]' 'page.html'
|
||||
nomatch '*.html*[]' 'page.html?x=1' # *[] forbids the trailing query
|
||||
# A literal ']' cannot be a class member: the class parser stops at the first
|
||||
# ']', escaped or not. So '*[\[\]]' does NOT mean "the [ or ] character" as the
|
||||
# filter guide claims (GitHub #148); it parses as the class {'[','\'} followed
|
||||
# by a trailing literal ']'. These assertions document the current (buggy)
|
||||
# behavior so any future matcher fix is a deliberate, visible change.
|
||||
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
|
||||
|
||||
@@ -1,15 +0,0 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
# --pause (#185): the inter-file pause target must stay in [min,max] and spread
|
||||
# across it (a per-call rand() would collapse it toward min). Driven by the
|
||||
# in-process 'httrack -#test=pause' test. POSIX-portable ($(BASH) is /bin/sh on macOS).
|
||||
|
||||
set -eu
|
||||
|
||||
# 'run' is an ignored placeholder argument.
|
||||
out=$(httrack -#test=pause run)
|
||||
|
||||
test "$out" = "pause: OK" || {
|
||||
echo "expected 'pause: OK', got: $out" >&2
|
||||
exit 1
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
# End-to-end --cookies-file (#215): /gated/secret.php needs a cookie no page
|
||||
# ever Set-Cookies, so it is reachable only when the option preloads it from a
|
||||
# Netscape cookies.txt. Locks the CLI->opt->cookie_load->wire plumbing.
|
||||
|
||||
set -e
|
||||
|
||||
: "${top_srcdir:=..}"
|
||||
|
||||
# preloaded cookie -> secret page is served. -o0 means a 500 leaves no file, so
|
||||
# --found/--files only hold when the secret is genuinely fetched (200).
|
||||
bash "$top_srcdir/tests/local-crawl.sh" --cookie 'session=opensesame' \
|
||||
--errors 0 --files 2 \
|
||||
--found 'gated/index.html' --found 'gated/secret.html' \
|
||||
httrack 'BASEURL/gated/index.php' -o0
|
||||
|
||||
# control: without the cookie the secret 500s; -o0 suppresses the error page so
|
||||
# its absence is real (error + missing file)
|
||||
bash "$top_srcdir/tests/local-crawl.sh" --errors 1 \
|
||||
--found 'gated/index.html' --not-found 'gated/secret.html' \
|
||||
httrack 'BASEURL/gated/index.php' -o0
|
||||
@@ -1,36 +0,0 @@
|
||||
#!/bin/bash
|
||||
#
|
||||
# --pause (#185): a fixed inter-file delay must slow a multi-file crawl. Measure
|
||||
# the same crawl with and without --pause and compare: the harness overhead
|
||||
# cancels, leaving only the pause. Integer seconds keep it portable (BSD date
|
||||
# has no %N); a lower bound is not timing-flaky since a pause only adds time.
|
||||
|
||||
set -e
|
||||
|
||||
: "${top_srcdir:=..}"
|
||||
|
||||
# python3 runs the local server (mirror local-crawl.sh); skip when absent, else
|
||||
# run() swallows its exit-77 and the serverless 0s/0s crawl looks like a fail.
|
||||
command -v python3 >/dev/null || {
|
||||
echo "python3 not found; skipping local crawl tests"
|
||||
exit 77
|
||||
}
|
||||
|
||||
run() { # echoes the wall-clock seconds of one crawl
|
||||
local t0 t1
|
||||
t0=$(date +%s)
|
||||
bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
|
||||
httrack 'BASEURL/types/index.html' -c1 "$@" >/dev/null 2>&1
|
||||
t1=$(date +%s)
|
||||
echo $((t1 - t0))
|
||||
}
|
||||
|
||||
base=$(run)
|
||||
paused=$(run --pause 0.5)
|
||||
delta=$((paused - base))
|
||||
|
||||
echo "crawl: ${base}s, with --pause 0.5: ${paused}s (delta ${delta}s)"
|
||||
if [ "$delta" -lt 2 ]; then
|
||||
echo "FAIL: --pause did not delay the crawl (delta ${delta}s)" >&2
|
||||
exit 1
|
||||
fi
|
||||
@@ -1,11 +0,0 @@
|
||||
#!/bin/bash
|
||||
# Issue #204: a 302 Location with a #fragment must drop the fragment before the
|
||||
# target is fetched. The server is strict (400 on a '#' in the request-target),
|
||||
# so a leaked fragment logs an error and the target is never saved.
|
||||
set -e
|
||||
|
||||
: "${top_srcdir:=..}"
|
||||
|
||||
bash "$top_srcdir/tests/local-crawl.sh" --errors 0 \
|
||||
--found 'redir/target.html' \
|
||||
httrack 'BASEURL/redir/index.html'
|
||||
@@ -41,7 +41,6 @@ TESTS = \
|
||||
01_engine-idna.test \
|
||||
01_engine-mime.test \
|
||||
01_engine-parse.test \
|
||||
01_engine-pause.test \
|
||||
01_engine-rcfile.test \
|
||||
01_engine-relative.test \
|
||||
01_engine-savename.test \
|
||||
@@ -73,9 +72,6 @@ TESTS = \
|
||||
23_local-errpage.test \
|
||||
24_local-resume-overlap.test \
|
||||
25_local-mime-exclude.test \
|
||||
26_local-strip-query.test \
|
||||
27_local-cookies-file.test \
|
||||
28_local-pause.test \
|
||||
29_local-redirect-fragment.test
|
||||
26_local-strip-query.test
|
||||
|
||||
CLEANFILES = check-network_sh.cache
|
||||
|
||||
@@ -12,14 +12,11 @@
|
||||
# the mirror directory name.
|
||||
#
|
||||
# Usage:
|
||||
# bash local-crawl.sh [--tls] [--root DIR] [--cookie NAME=VALUE ...] \
|
||||
# bash local-crawl.sh [--tls] [--root DIR] \
|
||||
# --errors N --files N --found PATH ... --directory PATH ... \
|
||||
# --log-found REGEX ... --log-not-found REGEX ... \
|
||||
# httrack BASEURL/some/path [httrack-args...]
|
||||
# --log-found/--log-not-found grep (ERE) the crawl's hts-log.txt.
|
||||
# --cookie writes a Netscape cookies.txt (scoped to the discovered host:port,
|
||||
# which the ephemeral port forces into the cookie domain) and passes it to
|
||||
# httrack via --cookies-file, to exercise preloaded cookies.
|
||||
|
||||
set -u
|
||||
|
||||
@@ -88,7 +85,6 @@ tmpdir=$(mktemp -d "${tmptopdir}/httrack_local.XXXXXX") || die "could not create
|
||||
|
||||
# --- parse leading control flags --------------------------------------------
|
||||
declare -a audit=()
|
||||
declare -a cookies=()
|
||||
scheme=http
|
||||
pos=0
|
||||
args=("$@")
|
||||
@@ -109,10 +105,6 @@ while test "$pos" -lt "$nargs"; do
|
||||
pos=$((pos + 1))
|
||||
root="${args[$pos]}"
|
||||
;;
|
||||
--cookie)
|
||||
pos=$((pos + 1))
|
||||
cookies+=("${args[$pos]}")
|
||||
;;
|
||||
--errors | --files)
|
||||
audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
|
||||
pos=$((pos + 1))
|
||||
@@ -166,17 +158,6 @@ while test "$pos" -lt "$nargs"; do
|
||||
pos=$((pos + 1))
|
||||
done
|
||||
|
||||
# --- materialize any --cookie entries into a cookies.txt ---------------------
|
||||
if test "${#cookies[@]}" -gt 0; then
|
||||
jar="${tmpdir}/cookies.txt"
|
||||
: >"$jar"
|
||||
for spec in "${cookies[@]}"; do
|
||||
printf '127.0.0.1:%s\tTRUE\t/\tFALSE\t1999999999\t%s\t%s\n' \
|
||||
"$port" "${spec%%=*}" "${spec#*=}" >>"$jar"
|
||||
done
|
||||
hts+=(--cookies-file "$jar")
|
||||
fi
|
||||
|
||||
# --- run httrack -------------------------------------------------------------
|
||||
which httrack >/dev/null || die "could not find httrack"
|
||||
ver=$(httrack -O /dev/null --version | sed -e 's/HTTrack version //')
|
||||
|
||||
@@ -110,19 +110,6 @@ class Handler(SimpleHTTPRequestHandler):
|
||||
return self.fail_cookie("badger")
|
||||
self.send_html("\tThis is a test.")
|
||||
|
||||
# --cookies-file (#215): the secret page needs a cookie no page ever sets,
|
||||
# so it is reachable only when --cookies-file preloads it.
|
||||
GATE_COOKIE = ("session", "opensesame")
|
||||
|
||||
def route_gated_index(self):
|
||||
self.send_html('\tThis is a <a href="secret.php">link</a>')
|
||||
|
||||
def route_gated_secret(self):
|
||||
name, value = self.GATE_COOKIE
|
||||
if self.request_cookies().get(name) != value:
|
||||
return self.fail_cookie(name)
|
||||
self.send_html("\tThis is the secret.")
|
||||
|
||||
def route_robots(self):
|
||||
body = b"User-agent: *\nDisallow:\n"
|
||||
self.send_response(200)
|
||||
@@ -354,27 +341,10 @@ class Handler(SimpleHTTPRequestHandler):
|
||||
if self.command != "HEAD":
|
||||
self.wfile.write(body)
|
||||
|
||||
# 302 whose Location carries a #fragment (#204): the fragment is a UA anchor
|
||||
# that must be dropped before the target is fetched. A leaked '#' reaches the
|
||||
# strict-server guard below and 400s.
|
||||
def route_redir_index(self):
|
||||
self.send_html('\t<a href="go.php">go</a>')
|
||||
|
||||
def route_redir_go(self):
|
||||
self.send_response(302, "Found")
|
||||
self.send_header("Location", "target.html#section")
|
||||
self.send_header("Content-Length", "0")
|
||||
self.end_headers()
|
||||
|
||||
def route_redir_target(self):
|
||||
self.send_raw(b"<html><body>redirect target</body></html>\n", "text/html")
|
||||
|
||||
ROUTES = {
|
||||
"/cookies/entrance.php": route_entrance,
|
||||
"/cookies/second.php": route_second,
|
||||
"/cookies/third.php": route_third,
|
||||
"/gated/index.php": route_gated_index,
|
||||
"/gated/secret.php": route_gated_secret,
|
||||
"/robots.txt": route_robots,
|
||||
"/types/index.html": route_types_index,
|
||||
"/types/control.php": route_types,
|
||||
@@ -406,23 +376,10 @@ class Handler(SimpleHTTPRequestHandler):
|
||||
"/mimex/index.html": route_mimex_index,
|
||||
"/mimex/blob.pdf": route_mimex_blob,
|
||||
"/mimex/real.html": route_mimex_real,
|
||||
"/redir/index.html": route_redir_index,
|
||||
"/redir/go.php": route_redir_go,
|
||||
"/redir/target.html": route_redir_target,
|
||||
}
|
||||
|
||||
# --- dispatch ----------------------------------------------------------
|
||||
|
||||
def reject_fragment(self):
|
||||
# Strict server: a '#' in the request-target is the client failing to
|
||||
# drop a fragment (#204). RFC 3986 forbids it on the wire; answer 400.
|
||||
if "#" in self.path:
|
||||
self.send_response(400, "Bad Request")
|
||||
self.send_header("Content-Length", "0")
|
||||
self.end_headers()
|
||||
return True
|
||||
return False
|
||||
|
||||
def dispatch(self):
|
||||
self._set_cookies = []
|
||||
path = urlsplit(self.path).path
|
||||
@@ -434,14 +391,10 @@ class Handler(SimpleHTTPRequestHandler):
|
||||
return False
|
||||
|
||||
def do_GET(self):
|
||||
if self.reject_fragment():
|
||||
return
|
||||
if not self.dispatch():
|
||||
super().do_GET()
|
||||
|
||||
def do_HEAD(self):
|
||||
if self.reject_fragment():
|
||||
return
|
||||
if not self.dispatch():
|
||||
super().do_HEAD()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user