Merge pull request #1020 from openzim/devdocs

Add Devdocs offliner, category and warehouse path

Author: benoit74

dev/receiver/create-warehouse-paths.sh

@@ -6,6 +6,7 @@ mkdir -p \
     /jail/zim/freecodecamp \
     /jail/zim/gutenberg \
     /jail/zim/ifixit \
+    /jail/zim/devdocs \
     /jail/zim/mooc \
     /jail/zim/other \
     /jail/zim/phet \
@@ -28,6 +29,7 @@ chmod 777 \
     /jail/zim/freecodecamp \
     /jail/zim/gutenberg \
     /jail/zim/ifixit \
+    /jail/zim/devdocs \
     /jail/zim/mooc \
     /jail/zim/other \
     /jail/zim/phet \

dispatcher/backend/docs/openapi_v1.yaml

@@ -1915,6 +1915,7 @@ components:
         - wikihow
         - zimit
         - ifixit
+        - devdocs
       example:
         - mwoffliner
         - sotoki

dispatcher/backend/src/common/enum.py

@@ -113,6 +113,7 @@ class ScheduleCategory:
     wiktionary = "wiktionary"
     ifixit = "ifixit"
     freecodecamp = "freecodecamp"
+    devdocs = "devdocs"
 
     @classmethod
     def all(cls):
@@ -137,6 +138,7 @@ def all(cls):
             cls.wiktionary,
             cls.ifixit,
             cls.freecodecamp,
+            cls.devdocs,
         ]
 
     @classmethod
@@ -168,6 +170,7 @@ class DockerImageName:
     wikihow = "openzim/wikihow"
     ifixit = "openzim/ifixit"
     freecodecamp = "openzim/freecodecamp"
+    devdocs = "openzim/devdocs"
 
     @classmethod
     def all(cls) -> set:
@@ -185,6 +188,7 @@ def all(cls) -> set:
             cls.wikihow,
             cls.ifixit,
             cls.freecodecamp,
+            cls.devdocs,
         }
 
 
@@ -202,6 +206,7 @@ class Offliner:
     wikihow = "wikihow"
     ifixit = "ifixit"
     freecodecamp = "freecodecamp"
+    devdocs = "devdocs"
 
     @classmethod
     def all(cls):
@@ -219,6 +224,7 @@ def all(cls):
             cls.wikihow,
             cls.ifixit,
             cls.freecodecamp,
+            cls.devdocs,
         ]
 
     @classmethod
@@ -243,6 +249,7 @@ def get_image_name(cls, offliner):
             cls.wikihow: DockerImageName.wikihow,
             cls.ifixit: DockerImageName.ifixit,
             cls.freecodecamp: DockerImageName.freecodecamp,
+            cls.devdocs: DockerImageName.devdocs,
         }.get(offliner, "-")
 
 
@@ -264,10 +271,18 @@ class Platform:
     wikihow = "wikihow"
     ifixit = "ifixit"
     ted = "ted"
+    devdocs = "devdocs"
 
     @classmethod
     def all(cls) -> str:
-        return [cls.wikimedia, cls.youtube, cls.wikihow, cls.ifixit, cls.ted]
+        return [
+            cls.wikimedia,
+            cls.youtube,
+            cls.wikihow,
+            cls.ifixit,
+            cls.ted,
+            cls.devdocs,
+        ]
 
     @classmethod
     def get_max_per_worker_tasks_for(cls, platform) -> int:

dispatcher/backend/src/common/schemas/models.py

@@ -21,6 +21,7 @@
     validate_warehouse_path,
 )
 from common.schemas.offliners import (
+    DevDocsFlagsSchema,
     FreeCodeCampFlagsSchema,
     GutenbergFlagsSchema,
     IFixitFlagsSchema,
@@ -101,6 +102,7 @@ def get_offliner_schema(offliner):
             Offliner.wikihow: WikihowFlagsSchema,
             Offliner.ifixit: IFixitFlagsSchema,
             Offliner.freecodecamp: FreeCodeCampFlagsSchema,
+            Offliner.devdocs: DevDocsFlagsSchema,
         }.get(offliner, Schema)
 
     @validates_schema

dispatcher/backend/src/common/schemas/offliners/__init__.py

@@ -1,4 +1,5 @@
 from common.schemas import SerializableSchema
+from common.schemas.offliners.devdocs import DevDocsFlagsSchema
 from common.schemas.offliners.freecodecamp import FreeCodeCampFlagsSchema
 from common.schemas.offliners.gutenberg import GutenbergFlagsSchema
 from common.schemas.offliners.ifixit import IFixitFlagsSchema
@@ -16,6 +17,7 @@
 from common.schemas.offliners.zimit import ZimitFlagsSchema, ZimitFlagsSchemaRelaxed
 
 __all__ = (
+    "DevDocsFlagsSchema",
     "FreeCodeCampFlagsSchema",
     "GutenbergFlagsSchema",
     "IFixitFlagsSchema",

dispatcher/backend/src/common/schemas/offliners/devdocs.py

@@ -0,0 +1,139 @@
+from marshmallow import fields
+
+from common.schemas import SerializableSchema, String
+from common.schemas.fields import (
+    validate_output,
+    validate_zim_description,
+    validate_zim_longdescription,
+)
+
+
+class DevDocsFlagsSchema(SerializableSchema):
+    class Meta:
+        ordered = True
+
+    slug = String(
+        metadata={
+            "label": "Slug",
+            "description": "Fetch the provided Devdocs resource. "
+            "Slugs are the first path entry in the Devdocs URL. "
+            "For example, the slug for: `https://devdocs.io/gcc~12/` is `gcc~12`. "
+            "Mutually exclusive with `All` setting, set only one option. Either this"
+            "setting or `All` must be configured.",
+        },
+    )
+
+    all_flag = fields.Boolean(
+        truthy=[True],
+        falsy=[False],
+        metadata={
+            "label": "All",
+            "description": "Fetch all Devdocs resources, and produce one ZIM "
+            "per resource. Mutually exclusive with `Slug` setting, set only "
+            "one option. Either this setting or `Slug` must be configured.",
+        },
+        data_key="all",
+    )
+
+    skip_slug_regex = String(
+        metadata={
+            "label": "Skip slugs regex",
+            "description": "Skips slugs matching the given regular expression."
+            "Do not set to fetch all slugs. Only useful when `All` is set.",
+        },
+        data_key="skip-slug-regex",
+    )
+
+    file_name_format = String(
+        metadata={
+            "label": "ZIM filename",
+            "description": "ZIM filename. Do not input trailing `.zim`, it "
+            "will be automatically added. You can use placeholders, see "
+            "https://github.com/openzim/devdocs/blob/main/README.md. Defaults "
+            "to devdocs.io_en_{clean_slug}_{period}",
+        },
+        data_key="file-name-format",
+    )
+
+    name_format = String(
+        metadata={
+            "label": "ZIM name",
+            "description": "ZIM name. You can use placeholders, see "
+            "https://github.com/openzim/devdocs/blob/main/README.md. Defaults "
+            "to devdocs.io_en_{clean_slug}",
+        },
+        data_key="name-format",
+    )
+
+    title_format = String(
+        metadata={
+            "label": "ZIM title",
+            "description": "ZIM title. You can use placeholders, see "
+            "https://github.com/openzim/devdocs/blob/main/README.md. Defaults "
+            "to `{full_name} Docs`",
+        },
+        data_key="title-format",
+    )
+
+    description_format = String(
+        metadata={
+            "label": "ZIM description",
+            "description": "ZIM description. You can use placeholders, see "
+            "https://github.com/openzim/devdocs/blob/main/README.md. Defaults "
+            "to `{full_name} docs by DevDocs`",
+        },
+        data_key="description-format",
+        validate=validate_zim_description,
+    )
+
+    long_description_format = String(
+        metadata={
+            "label": "ZIM long description",
+            "description": "ZIM long description. You can use placeholders, see "
+            "https://github.com/openzim/devdocs/blob/main/README.md. Defaults to no "
+            "long description",
+        },
+        data_key="long-description-format",
+        validate=validate_zim_longdescription,
+    )
+
+    tags = String(
+        metadata={
+            "label": "ZIM Tags",
+            "description": "List of semi-colon-separated Tags for the ZIM file. "
+            " You can use placeholders, see "
+            "https://github.com/openzim/devdocs/blob/main/README.md. Defaults to"
+            "`devdocs;{slug_without_version}`",
+        }
+    )
+
+    creator = String(
+        metadata={
+            "label": "Creator",
+            "description": "Name of content creator. “DevDocs” otherwise",
+        },
+    )
+
+    publisher = String(
+        metadata={
+            "label": "Publisher",
+            "description": "Custom publisher name (ZIM metadata). “openZIM” otherwise",
+        },
+    )
+
+    output = String(
+        metadata={
+            "label": "Output folder",
+            "placeholder": "/output",
+            "description": "Output folder for ZIM file(s). Leave it as `/output`",
+        },
+        load_default="/output",
+        dump_default="/output",
+        validate=validate_output,
+    )
+
+    debug = fields.Boolean(
+        truthy=[True],
+        falsy=[False],
+        metadata={"label": "Debug", "description": "Enable verbose output"},
+    )

dispatcher/backend/src/utils/offliners.py

@@ -25,6 +25,7 @@
     Offliner.nautilus: od("nautiluszim", True, False),
     Offliner.zimit: od("zimit", True, "statsFilename"),
     Offliner.kolibri: od("kolibri2zim", True, False),
+    Offliner.devdocs: od("devdocs2zim", True, False),
 }
 
 

dispatcher/frontend-ui/src/constants.js

@@ -336,17 +336,17 @@ export default {
   cancelable_statuses: cancelable_statuses,
   running_statuses: running_statuses,
   contact_email: "contact@kiwix.org",
-  categories: ["freecodecamp", "gutenberg", "ifixit", "other", "phet", "psiram", "stack_exchange",
+  categories: ["devdocs", "freecodecamp", "gutenberg", "ifixit", "other", "phet", "psiram", "stack_exchange",
                "ted", "openedx", "vikidia", "wikibooks", "wikihow", "wikinews",
                "wikipedia", "wikiquote", "wikisource", "wikispecies", "wikiversity",
                "wikivoyage", "wiktionary"],  // list of categories for fileering
-  warehouse_paths: ["/freecodecamp", "/gutenberg", "/ifixit", "/other", "/phet", "/psiram", "/stack_exchange",
+  warehouse_paths: ["/devdocs", "/freecodecamp", "/gutenberg", "/ifixit", "/other", "/phet", "/psiram", "/stack_exchange",
                     "/ted", "/mooc", "/videos", "/vikidia", "/wikibooks", "/wikihow",
                     "/wikinews", "/wikipedia", "/wikiquote", "/wikisource",
                     "/wikiversity", "/wikivoyage", "/wiktionary", "/zimit",
                     "/.hidden/dev", "/.hidden/private", "/.hidden/endless",
                     "/.hidden/bard", "/.hidden/bsf", "/.hidden/custom_apps"],
-  offliners: ["mwoffliner", "youtube", "phet", "gutenberg", "sotoki", "nautilus", "ted", "openedx", "zimit", "kolibri", "wikihow", "ifixit", "freecodecamp"],
+  offliners: ["mwoffliner", "youtube", "phet", "gutenberg", "sotoki", "nautilus", "ted", "openedx", "zimit", "kolibri", "wikihow", "ifixit", "freecodecamp", "devdocs"],
   periodicities: ["manually", "monthly", "quarterly", "biannualy", "annually"],
   memory_values: [536870912, // 512MiB
                   1073741824,  // 1GiB

workers/app/common/constants.py

@@ -122,6 +122,7 @@
 OFFLINER_WIKIHOW = "wikihow"
 OFFLINER_IFIXIT = "ifixit"
 OFFLINER_FREECODECAMP = "freecodecamp"
+OFFLINER_DEVDOCS = "devdocs"
 
 ALL_OFFLINERS = [
     OFFLINER_MWOFFLINER,
@@ -137,6 +138,7 @@
     OFFLINER_WIKIHOW,
     OFFLINER_IFIXIT,
     OFFLINER_FREECODECAMP,
+    OFFLINER_DEVDOCS,
 ]
 SUPPORTED_OFFLINERS = [
     offliner
@@ -152,7 +154,7 @@
     OFFLINER_YOUTUBE,
 ]
 
-ALL_PLATFORMS = ["wikimedia", "youtube", "wikihow", "ifixit", "ted"]
+ALL_PLATFORMS = ["wikimedia", "youtube", "wikihow", "ifixit", "ted", "devdocs"]
 PLATFORMS_TASKS = {}
 for platform in ALL_PLATFORMS:
     name = f"PLATFORM_{platform}_MAX_TASKS"

workers/contrib/zimfarm.config.example

@@ -47,7 +47,7 @@ ZIMFARM_CPU="3"
 # Comma-separated list of offliners to run or `""` for all of them. If
 # you want to run `youtube` tasks, you need to be whitelisted, contact
 # us.
-ZIMFARM_OFFLINERS="mwoffliner,sotoki,gutenberg,phet,nautilus,ted,openedx,zimit,kolibri,wikihow,ifixit,freecodecamp"
+ZIMFARM_OFFLINERS="mwoffliner,sotoki,gutenberg,phet,nautilus,ted,openedx,zimit,kolibri,wikihow,ifixit,freecodecamp,devdocs"
 
 # Set to `"y"` to only run task specifically assigned to this worker
 # (`""` otherwise)
@@ -66,4 +66,5 @@ DISABLE_IPV6=""
 # PLATFORM_youtube_MAX_TASKS=2
 # PLATFORM_wikihow_MAX_TASKS=2
 # PLATFORM_ifixit_MAX_TASKS=2
+# PLATFORM_devdocs_MAX_TASKS=2
 # PLATFORM_ted_MAX_TASKS=2

workers/contrib/zimfarm.sh

@@ -197,6 +197,7 @@ function restart() {
         --env PLATFORM_youtube_MAX_TASKS=$PLATFORM_youtube_MAX_TASKS \
         --env PLATFORM_wikihow_MAX_TASKS=$PLATFORM_wikihow_MAX_TASKS \
         --env PLATFORM_ifixit_MAX_TASKS=$PLATFORM_ifixit_MAX_TASKS \
+        --env PLATFORM_devdocs_MAX_TASKS=$PLATFORM_devdocs_MAX_TASKS \
         --env PLATFORM_ted_MAX_TASKS=$PLATFORM_ted_MAX_TASKS \
         --env POLL_INTERVAL=$POLL_INTERVAL \
         --env DNSCACHE_IMAGE=$DNSCACHE_IMAGE \