djangoldp-ds4go 1.0.0__tar.gz → 1.0.2__tar.gz

{djangoldp_ds4go-1.0.0 → djangoldp_ds4go-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: djangoldp_ds4go
-Version: 1.0.0
+Version: 1.0.2
 Summary: djangoldp package for dataspace interoperability framework
 Home-page: https://git.startinblox.com/djangoldp-packages/djangoldp-ds4go
 Author: Startin'blox

djangoldp_ds4go-1.0.2/README.md

@@ -0,0 +1,59 @@
+# DjangoLDP DS4GO
+
+This is a Django package for the DS4GO ecosystem, providing models and tools for fact-checking applications.
+
+See [DSIF](https://dsif.eu/).
+
+## Configuration
+
+Add `djangoldp_ds4go` to your `INSTALLED_APPS` and configure internationalization settings:
+
+```yaml
+dependencies:
+  - djangoldp-account
+  - django-webidoidc-provider
+  - djangoldp-i18n
+  - djangoldp-ds4go
+  # ...
+
+ldppackages:
+  - rest_framework
+  - oidc_provider
+  - djangoldp_account
+  - djangoldp_i18n
+  - djangoldp_ds4go
+  # ...
+
+# [...]
+
+server:
+  # [...] # See djangoldp configuration for other settings
+
+  USE_I18N: True
+  # Your application default language, will be served if no header are provided
+  LANGUAGE_CODE: fr
+  # Your application fallback language, will be served when a requested language is not available
+  MODELTRANSLATION_DEFAULT_LANGUAGE: fr
+  # Priority order. Ensure that every language is listed here to avoid empty translations
+  MODELTRANSLATION_FALLBACK_LANGUAGES:
+    - fr
+    - en
+    - es
+  # A list of all supported languages, you **must** make a migration afterwise
+  LANGUAGES:
+    - ['fr', 'Français']
+    - ['en', 'English']
+    - ['es', 'Español']
+```
+
+Run `python manage.py makemigrations` and `python manage.py migrate` after updating language settings.
+
+## Importing RSS Data
+
+Import fact-check data from RSS feeds using the management command:
+
+```bash
+python manage.py import_rss --rss_file="path/to/rss.xml"
+```
+
+This command parses RSS XML to create or update facts, handling translations based on the feed language, creating category hierarchies, and importing media metadata.

djangoldp_ds4go-1.0.2/djangoldp_ds4go/__init__.py

@@ -0,0 +1 @@
+__version__ = '1.0.2'

djangoldp_ds4go-1.0.2/djangoldp_ds4go/management/commands/import_rss.py

@@ -0,0 +1,126 @@
+import json
+
+from defusedxml.ElementTree import parse
+from django.core.management.base import BaseCommand
+
+from djangoldp_ds4go.models import Category, Fact, Media
+
+
+class Command(BaseCommand):
+    help = "Import facts from RSS file"
+
+    def add_arguments(self, parser):
+        parser.add_argument("--rss_file", type=str, help="Path to the RSS file")
+
+    def handle(self, *args, **options):
+        rss_file = options["rss_file"]
+        tree = parse(rss_file)
+        root = tree.getroot()
+        ns = {
+            "schema": "https://schema.org/",
+            "media": "http://search.yahoo.com/mrss/",
+            "content": "http://purl.org/rss/1.0/modules/content/",
+        }
+        channel = root.find("channel")
+        language_elem = channel.find("language")
+        language = language_elem.text if language_elem is not None else "fr"
+
+        for item in channel.findall("item"):
+            guid = item.find("guid").text
+            existing_fact = Fact.objects.filter(rss_guid=guid).first()
+            title = item.find("title").text
+            link = item.find("link").text
+            review_elem = item.find("schema:review", ns)
+
+            try:
+                review = json.loads(review_elem.text) if review_elem is not None else {}
+            except json.JSONDecodeError:
+                review = {}
+                self.stderr.write(self.style.WARNING("Failed to parse review for item with guid %s. Ignoring." % (guid)))
+
+            description = item.find("description").text
+            content_elem = item.find("content:encoded", ns)
+            content = content_elem.text if content_elem is not None else ""
+            author = item.find("author").text if item.find("author") is not None else ""
+            enclosure_url = None
+            enclosure = item.find("enclosure")
+
+            if enclosure is not None:
+                enclosure_url = enclosure.get("url")
+
+            if existing_fact:
+                fact = existing_fact
+                self.stdout.write(f"Updating existing fact with guid {guid}")
+            else:
+                fact = Fact.objects.create(
+                    rss_guid=guid,
+                    link=link,
+                    review=review,
+                )
+                self.stdout.write(f"Creating new fact: {title}")
+
+            # Set translated fields
+            setattr(fact, f"name_{language}", title)
+            setattr(fact, f"description_{language}", description)
+            setattr(fact, f"content_{language}", content)
+            setattr(fact, f"author_{language}", author)
+
+            if enclosure_url:
+                setattr(fact, f"enclosure_{language}", enclosure_url)
+
+            fact.save()
+
+            # Categories
+            categories = item.findall("category")
+            for cat_elem in categories:
+                cat_name = cat_elem.text
+                category = self.get_or_create_category(cat_name, language)
+                fact.categories.add(category)
+
+            # Medias
+            for media_elem in item.findall("media:content", ns):
+                url = media_elem.get("url")
+                file_size = int(media_elem.get("fileSize", 0))
+                width = int(media_elem.get("width", 0))
+                height = int(media_elem.get("height", 0))
+                file_type = media_elem.get("type")
+                desc = media_elem.find("media:description", ns)
+                description = desc.text if desc is not None else ""
+                existing_media = Media.objects.filter(
+                    url=url, related_fact=fact
+                ).first()
+
+                if existing_media:
+                    setattr(existing_media, f"description_{language}", description)
+                    existing_media.save()
+                else:
+                    media = Media.objects.create(
+                        url=url,
+                        file_size=file_size,
+                        width=width,
+                        height=height,
+                        file_type=file_type,
+                        related_fact=fact,
+                    )
+                    setattr(media, f"description_{language}", description)
+                    media.save()
+
+            self.stdout.write(f"Processed fact: {title}")
+
+    def get_or_create_category(self, cat_name, language):
+        parts = cat_name.split("/")
+        current_parent = None
+
+        for part in parts:
+            part = part.strip()
+            category, created = Category.objects.get_or_create(
+                name=part,
+                parent_category=current_parent,
+            )
+            # FIXME: I don't know how to handle i18n here as these are strings: "Media Topic" could be "Totoro" in another lang?
+            # if created or not getattr(category, f"name_{language}", None):
+            #     setattr(category, f"name_{language}", part)
+            #     category.save()
+            current_parent = category
+
+        return current_parent

{djangoldp_ds4go-1.0.0 → djangoldp_ds4go-1.0.2}/djangoldp_ds4go/models/category.py

@@ -14,6 +14,7 @@ class Category(baseNamedModel):
     class Meta(baseNamedModel.Meta):
         verbose_name = _("Category")
         verbose_name_plural = _("Categories")
+        container_path = "categories"
 
         rdf_type = "ds4go:Category"
         serializer_fields = baseNamedModel.Meta.serializer_fields + [

{djangoldp_ds4go-1.0.0 → djangoldp_ds4go-1.0.2}/djangoldp_ds4go/models/fact.py

@@ -26,6 +26,7 @@ class Fact(baseNamedModel):
     enclosure = fields.LDPUrlField(blank=True, null=True, verbose_name=_("Enclosure"))
 
     class Meta(baseNamedModel.Meta):
+        depth = 1
         verbose_name = _("Fact")
         verbose_name_plural = _("Facts")
 
@@ -41,6 +42,6 @@ class Fact(baseNamedModel):
             "review",
         ]
 
-        nested_fields = baseNamedModel.Meta.nested_fields + ["medias"]
+        nested_fields = baseNamedModel.Meta.nested_fields + ["categories", "medias"]
 
         view_set = I18nLDPViewSet

{djangoldp_ds4go-1.0.0 → djangoldp_ds4go-1.0.2}/djangoldp_ds4go.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: djangoldp_ds4go
-Version: 1.0.0
+Version: 1.0.2
 Summary: djangoldp package for dataspace interoperability framework
 Home-page: https://git.startinblox.com/djangoldp-packages/djangoldp-ds4go
 Author: Startin'blox

{djangoldp_ds4go-1.0.0 → djangoldp_ds4go-1.0.2}/djangoldp_ds4go.egg-info/SOURCES.txt

@@ -10,6 +10,9 @@ djangoldp_ds4go.egg-info/SOURCES.txt
 djangoldp_ds4go.egg-info/dependency_links.txt
 djangoldp_ds4go.egg-info/requires.txt
 djangoldp_ds4go.egg-info/top_level.txt
+djangoldp_ds4go/management/__init__.py
+djangoldp_ds4go/management/commands/__init__.py
+djangoldp_ds4go/management/commands/import_rss.py
 djangoldp_ds4go/migrations/0001_initial.py
 djangoldp_ds4go/migrations/0002_djangoldp_i18n.py
 djangoldp_ds4go/migrations/__init__.py

djangoldp_ds4go-1.0.0/README.md

@@ -1,20 +0,0 @@
-# DjangoLDP DS4GO
-
-This is a Django project for DS4GO ecosystem.
-
-See [DS4GO](https://dsif.eu/).
-
-## Server settings
-
-```yaml
-  USE_I18N: True
-  # Your application default language, will be served if no header are provided
-  LANGUAGE_CODE: fr
-  # Your application fallback language, will be served when a translation is not available
-  MODELTRANSLATION_DEFAULT_LANGUAGE: fr
-  # A list of all supported languages, you **must** make a migration afterwise
-  LANGUAGES:
-    - ['fr', 'Français']
-    - ['en', 'English']
-    - ['es', 'Español']
-```

djangoldp_ds4go-1.0.0/djangoldp_ds4go/__init__.py

@@ -1 +0,0 @@
-__version__ = '1.0.0'