GitHub CI

.github/workflows/ubuntu.yml

@@ -0,0 +1,40 @@
+name: Ubuntu
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        submodules: recursive
+    - name: dependencies
+      run: sudo apt-get install -y build-essential libboost-test-dev libboost-program-options-dev cmake zlib1g-dev libbz2-dev liblzma-dev libicu-dev uchardet libuchardet-dev libzip-dev wget
+    - name: cmake
+      run: |
+        cmake -E make_directory build
+        cd build
+        cmake ..
+    - name: Compile
+      working-directory: build
+      run: cmake --build . -j2
+    - name: Unit Tests
+      working-directory: build
+      run: ctest -j2
+    - name: Regression Tests
+      working-directory: tests
+      run: |
+        ../build/bin/warc2text \
+          -f url,text,mime,html \
+          -o output \
+          hello-world.warc.gz
+        # ../build/bin/warc2text \
+        #  --json \
+        # hello-world.warc.gz > hello-world.json
+        shasum -c checksums.txt

tests/checksums.txt

@@ -0,0 +1,5 @@
+28d6c5e68f9e8c3275015ff1bd082fce3382441a  hello-world.json
+84a4f15ca77e1aafe8f33e5b94c6010e23cdf15b  output/en/html.gz
+8baa00c2a8c791da25c52a638711fc1692ef266f  output/en/mime.gz
+9728d8b84aca564f9f1907825711926b69e83028  output/en/text.gz
+5a6bead02cc1b50ca216665a71146420d6c8bb55  output/en/url.gz

tests/hello-world.json.expected

@@ -0,0 +1 @@
+{"f":"./hello-world.warc.gz","o":907,"s":723,"rs":11,"ps":12,"l":"en","u":"http://iipc.github.io/warc-specifications/primers/web-archive-formats/hello-world.txt","c":"text/plain","ts":"2015-07-08T21:55:13Z","p":"Hello World\n"}