Merge pull request #264 from openzim/use_warc2zim2

.github/workflows/docker_zimit2.yml

@@ -0,0 +1,31 @@
+name: Docker Zimit2
+
+on:
+  push:
+    branches:
+      - zimit2
+
+jobs:
+  build-and-push:
+    name: Deploy Docker Image
+    runs-on: ubuntu-22.04
+
+    steps:
+      - name: Retrieve source code
+        uses: actions/checkout@v3
+
+      - name: Build and push
+        uses: openzim/docker-publish-action@v10
+        with:
+          image-name: openzim/zimit
+          manual-tag: zimit2
+          restrict-to: openzim/zimit
+          registries: ghcr.io
+          credentials:
+            GHCRIO_USERNAME=${{ secrets.GHCR_USERNAME }}
+            GHCRIO_TOKEN=${{ secrets.GHCR_TOKEN }}
+          repo_description: auto
+          repo_overview: auto
+          platforms: |
+            linux/amd64
+            linux/arm64

CHANGELOG.md

@@ -10,8 +10,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
-- Adapt to new `warc2zim` code structure
-- Using `main` warc2zim ⚠️ change before releasing!
+- Use `warc2zim` version 2, which works without Service Worker anymore
+- Using `warc2zim2` warc2zim ⚠️ change before releasing!
+- Build temporary `zimit2` Docker image for testing ⚠️ remove before releasing!
 
 ### Added
 

Dockerfile

@@ -9,7 +9,7 @@ RUN apt-get update \
     # python setup (in venv not to conflict with browsertrix)
     && python3 -m venv /app/zimit \
     && /app/zimit/bin/python -m pip install --no-cache-dir 'requests==2.31.0' 'inotify==0.2.10' 'tld==0.13' \
-    'git+https://github.com/openzim/warc2zim@main#egg_name=warc2zim' \
+    'git+https://github.com/openzim/warc2zim@warc2zim2#egg_name=warc2zim' \
     # placeholder (default output location)
     && mkdir -p /output \
     # disable chrome upgrade

test/integration.py

@@ -6,9 +6,9 @@ import libzim.reader
 from warcio import ArchiveIterator
 
 
-def get_zim_article(zimfile, path):
+def get_zim_main_entry(zimfile):
     zim_fh = libzim.reader.Archive(zimfile)
-    return zim_fh.get_entry_by_path(path).get_item().content.tobytes()
+    return zim_fh.main_entry
 
 
 def test_is_file():
@@ -20,9 +20,9 @@ def test_zim_main_page():
     """Main page specified, http://isago.rskg.org/, was a redirect to https
     Ensure main page is the redirected page"""
 
-    assert b'"https://isago.rskg.org/"' in get_zim_article(
-        "/output/isago.zim", "A/index.html"
-    )
+    main_entry = get_zim_main_entry("/output/isago.zim")
+    assert main_entry.is_redirect
+    assert main_entry.get_redirect_entry().path == "isago.rskg.org/"
 
 
 def test_user_agent():