From c57cd5008b84f0e87cca55b84450e4c92c3d2c8f Mon Sep 17 00:00:00 2001
From: EliotJones <elioty@hotmail.co.uk>
Date: Sat, 13 Sep 2025 16:20:01 +0200
Subject: [PATCH] read last line of ignore file

- do not cancel other matrix jobs if one test fails
- read all lines of the ignore list even if it doesn't end with a newline
- add ignore list for 0008 and 0009
---
 .github/workflows/run_common_crawl_tests.yml |  3 ++-
 tools/common-crawl-ignore.txt                | 11 ++++++++++-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/run_common_crawl_tests.yml b/.github/workflows/run_common_crawl_tests.yml
index 5e7ccdc1..244dce42 100644
--- a/.github/workflows/run_common_crawl_tests.yml
+++ b/.github/workflows/run_common_crawl_tests.yml
@@ -10,6 +10,7 @@ jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         pair: ["0000-0001", "0002-0003", "0004-0005", "0006-0007"]
 
@@ -45,7 +46,7 @@ jobs:
 
       - name: Remove unwanted test files
         run: |
-          while read f; do
+          while read f || [ -n "$f" ]; do
             full="corpus/extracted/$f"
             if [ -f "$full" ]; then
               echo "Removing $full"
diff --git a/tools/common-crawl-ignore.txt b/tools/common-crawl-ignore.txt
index dc58bfbd..5d7f95b3 100644
--- a/tools/common-crawl-ignore.txt
+++ b/tools/common-crawl-ignore.txt
@@ -37,4 +37,13 @@
 0006766.pdf
 0006844.pdf
 0007159.pdf
-0007559.pdf
\ No newline at end of file
+0007559.pdf
+0008404.pdf
+0008443.pdf
+0008674.pdf
+0008978.pdf
+0009290.pdf
+0009309.pdf
+0009464.pdf
+0009706.pdf
+0009944.pdf
\ No newline at end of file