set up offliner definitions

.github/workflows/update-zim-offliner-definition.yaml

@@ -0,0 +1,38 @@
+name: Update ZIMFarm Definitions
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - "offliner-definition.json"
+  release:
+    types: [published]
+
+jobs:
+  prepare-json:
+    runs-on: ubuntu-24.04
+    outputs:
+      offliner_definition: ${{ steps.read-json.outputs.offliner_definition }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - id: read-json
+        run: |
+          if [ ! -f "offliner-definition.json" ]; then
+            echo "File not found!" >&2
+            exit 1
+          fi
+          json=$(jq -c . offliner-definition.json)
+          echo "offliner_definition=$json" >> $GITHUB_OUTPUT
+  call-workflow:
+    needs: prepare-json
+    uses: openzim/overview/.github/workflows/update-zimfarm-offliner-definition.yaml@main
+    with:
+      version: ${{ github.event_name == 'release' && github.event.release.tag_name || 'dev' }}
+      offliner: ted
+      offliner_definition: ${{ needs.prepare-json.outputs.offliner_definition }}
+    secrets:
+      zimfarm_ci_secret: ${{ secrets.ZIMFARM_CI_SECRET }}

offliner-definition.json

@@ -0,0 +1,184 @@
+{
+  "offliner_id": "ted",
+  "stdOutput": true,
+  "stdStats": false,
+  "flags": {
+    "topics": {
+      "type": "string",
+      "required": false,
+      "title": "Topics",
+      "description": "Comma-separated list of topics to scrape; as given on ted.com/talks. Pass all for all topics. Exclusive with playlists and links, only one must be set."
+    },
+    "playlists": {
+      "type": "string",
+      "required": false,
+      "title": "TED Playlists",
+      "description": "Comma-separated list of TED playlist IDs to scrape. Pass all for all playlists. Exclusive with topics and links, only one must set."
+    },
+    "links": {
+      "type": "string",
+      "required": false,
+      "title": "Links",
+      "description": "Comma-separated TED talk URLs to scrape, each in the format: https://www.ted.com/talks/<talk_slug>. Exclusive with topics and playlists, only one must set.",
+      "customValidator": "validate_ted_links"
+    },
+    "languages": {
+      "type": "string",
+      "required": false,
+      "title": "Languages",
+      "description": "Comma-separated list of ISO-639-3 language codes to filter videos. Do not pass this parameter for all languages",
+      "pattern": "^[a-z]{3}(,[a-z]{3})*$",
+      "customValidator": "language_code"
+    },
+    "subtitles_enough": {
+      "type": "boolean",
+      "required": false,
+      "title": "Subtitles enough?",
+      "description": "Whether to include videos that have a subtitle in requested language(s) if audio is in another language"
+    },
+    "subtitles": {
+      "type": "string",
+      "required": false,
+      "title": "Subtitles Setting",
+      "description": "Language setting for subtitles. all: include all available subtitles, matching (default): only subtitles matching language(s), none: include no subtitle. Also accepts comma-separated list of language(s)"
+    },
+    "video_format": {
+      "type": "string-enum",
+      "required": false,
+      "title": "Video format",
+      "description": "Format to download/transcode video to. webm is smaller",
+      "choices": [
+        { "title": "WEBM", "value": "webm" },
+        { "title": "MP4", "value": "mp4" }
+      ]
+    },
+    "low_quality": {
+      "type": "boolean",
+      "required": false,
+      "title": "Low Quality",
+      "description": "Re-encode video using stronger compression"
+    },
+    "autoplay": {
+      "type": "boolean",
+      "required": false,
+      "title": "Autoplay videos",
+      "description": "Enable autoplay on videos. Behavior differs on platforms/browsers"
+    },
+    "name": {
+      "type": "string",
+      "required": true,
+      "title": "Name",
+      "description": "ZIM name. Used as identifier and filename (date will be appended)",
+      "pattern": "^([a-z0-9\\-\\.]+_)([a-z\\-]+_)([a-z0-9\\-\\.]+)$"
+    },
+    "title": {
+      "type": "string",
+      "required": false,
+      "title": "Title",
+      "description": "Custom title for your ZIM. Based on selection otherwise",
+      "minLength": 1,
+      "maxLength": 30
+    },
+    "description": {
+      "type": "string",
+      "required": false,
+      "title": "Description",
+      "description": "Custom description for your ZIM. Based on selection otherwise",
+      "minLength": 1,
+      "maxLength": 80
+    },
+    "long_description": {
+      "type": "string",
+      "required": false,
+      "title": "Long description",
+      "description": "Custom long description for your ZIM. Based on selection otherwise",
+      "minLength": 1,
+      "maxLength": 4000
+    },
+    "creator": {
+      "type": "string",
+      "required": false,
+      "title": "Content Creator",
+      "description": "Name of content creator. Defaults to TED"
+    },
+    "publisher": {
+      "type": "string",
+      "required": false,
+      "title": "Publisher",
+      "isPublisher": true,
+      "description": "Custom publisher name (ZIM metadata). \"openZIM\" otherwise"
+    },
+    "tags": {
+      "type": "string",
+      "required": false,
+      "title": "ZIM Tags",
+      "description": "List of comma-separated Tags for the ZIM file. category:ted, ted, and _videos:yes added automatically"
+    },
+    "optimization_cache": {
+      "type": "url",
+      "required": false,
+      "title": "Optimization Cache URL",
+      "description": "URL with credentials and bucket name to S3 Optimization Cache",
+      "secret": true
+    },
+    "use_any_optimized_version": {
+      "type": "boolean",
+      "required": false,
+      "title": "Use any optimized version",
+      "description": "Use the cached files if present, whatever the version"
+    },
+    "output": {
+      "type": "string",
+      "required": false,
+      "title": "Output folder",
+      "description": "Output folder for ZIM file(s). Leave it as `/output`",
+      "pattern": "^/output$"
+    },
+    "tmp_dir": {
+      "type": "string",
+      "required": false,
+      "title": "Temp folder",
+      "description": "Where to create temporay build folder. Leave it as `/output`",
+      "pattern": "^/output$"
+    },
+    "zim_file": {
+      "type": "string",
+      "required": false,
+      "title": "ZIM filename",
+      "description": "ZIM file name (based on ZIM name if not provided)",
+      "pattern": "^([a-z0-9\\-\\.]+_)([a-z\\-]+_)([a-z0-9\\-\\.]+_)([a-z0-9\\-\\.]+_|)([\\d]{4}-[\\d]{2}|\\{period\\}).zim$"
+    },
+    "debug": {
+      "type": "boolean",
+      "required": false,
+      "title": "Debug",
+      "description": "Enable verbose output"
+    },
+    "threads": {
+      "type": "integer",
+      "required": false,
+      "title": "Threads",
+      "description": "Number of parallel threads to use while downloading"
+    },
+    "locale": {
+      "type": "string",
+      "required": false,
+      "title": "Locale",
+      "description": "The locale to use for the translations in ZIM"
+    },
+    "language_threshold": {
+      "type": "integer",
+      "required": false,
+      "title": "Language Threshold",
+      "description": "Add language in ZIM metadata only if present in at least this percentage of videos. Number between 0 and 1. Defaults to 0.5: language must be used in 50% of videos to be considered as ZIM language.",
+      "min": 0,
+      "max": 1
+    }
+  },
+  "modelValidators": [
+    {
+      "name": "check_exclusive_fields",
+      "fields": ["links", "topics", "playlists"]
+    }
+  ]
+}