mirror of
https://github.com/xroche/httrack.git
synced 2026-07-11 19:36:52 +03:00
Compare commits
2 Commits
ci-paralle
...
llint-int6
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
8e2e4e7d34 | ||
|
|
42c5e71f36 |
32
.github/workflows/ci.yml
vendored
32
.github/workflows/ci.yml
vendored
@@ -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"$jobs"
|
||||
run: make check
|
||||
|
||||
- name: Print the test log on failure
|
||||
if: failure()
|
||||
|
||||
15
AGENTS.md
15
AGENTS.md
@@ -6,19 +6,8 @@ the operational checklist: toolchain, invariants, and how to ship a change.
|
||||
## Build & test
|
||||
- Fresh clone first: `git submodule update --init src/coucal`
|
||||
- `./bootstrap` (regenerates `configure` via `autoreconf`; needs autoconf,
|
||||
automake, libtool), then `bash configure && make -j"$(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
|
||||
|
||||
@@ -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' \
|
||||
|
||||
@@ -8,6 +8,4 @@ set -euo pipefail
|
||||
bash "$top_srcdir/tests/local-crawl.sh" --rerun \
|
||||
--found 'errmask/keep.dat' \
|
||||
--file-min-bytes 'errmask/keep.dat' 1024 \
|
||||
--file-matches 'errmask/keep.dat' '^KEEP' \
|
||||
--file-not-matches 'errmask/keep.dat' 'error 403' \
|
||||
httrack 'BASEURL/errmask/index.html'
|
||||
|
||||
@@ -14,13 +14,11 @@
|
||||
# Usage:
|
||||
# bash local-crawl.sh [--tls] [--root DIR] [--cookie NAME=VALUE ...] \
|
||||
# [--rerun-args 'ARGS'] \
|
||||
# --errors N --errors-content N --files N --found PATH ... --directory PATH ... \
|
||||
# --errors N --files N --found PATH ... --directory PATH ... \
|
||||
# --log-found REGEX ... --log-not-found REGEX ... \
|
||||
# --file-matches PATH REGEX ... --file-not-matches PATH REGEX ... \
|
||||
# --file-min-bytes PATH N --max-mirror-bytes N \
|
||||
# httrack BASEURL/some/path [httrack-args...]
|
||||
# --errors counts every "Error:" log line; --errors-content drops transient
|
||||
# network failures (codes -2..-6) that flake on busy loopback under -c8.
|
||||
# --log-found/--log-not-found grep (ERE) the crawl's hts-log.txt.
|
||||
# --max/--min-mirror-bytes bound the mirrored content bytes (host root).
|
||||
# --file-matches/--file-not-matches grep (ERE) a mirrored file (PATH under the
|
||||
@@ -133,7 +131,7 @@ while test "$pos" -lt "$nargs"; do
|
||||
pos=$((pos + 1))
|
||||
rerun_args="${args[$pos]}"
|
||||
;;
|
||||
--errors | --errors-content | --files)
|
||||
--errors | --files)
|
||||
audit+=("${args[$pos]}" "${args[$((pos + 1))]}")
|
||||
pos=$((pos + 1))
|
||||
;;
|
||||
@@ -336,14 +334,6 @@ while test "$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" |
|
||||
|
||||
Reference in New Issue
Block a user