Add default ZIM tags based on Kiwix convention

Author: benoit74

CHANGELOG.md

@@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Add map scale control (metric units) to display real-world distances at current zoom level (#46)
 - Toggle map scale units between metric and imperial when clicking the scale control (#77)
+- Add default ZIM tags based on Kiwix convention (#76)
 
 ### Fixed
 

scraper/src/maps2zim/zimconfig.py

@@ -2,6 +2,14 @@
 
 from maps2zim.errors import InvalidFormatError
 
+DEFAULT_TAGS: list[str] = [
+    "_sw:no",
+    "_ftindex:yes",
+    "_pictures:yes",
+    "_videos:no",
+    "_details:yes",
+]
+
 
 class ZimConfig(BaseModel):
     """Common configuration for building ZIM files."""
@@ -43,6 +51,13 @@ def fmt(string: str) -> str:
                     f"valid placeholders are: {valid_placeholders}"
                 ) from e
 
+        formatted_tags = [fmt(tag) for tag in self.tags] if self.tags else []
+        # Build a dict of tag key -> tag value from default tags, then override
+        # with user-provided tags (key is the part before the colon).
+        merged: dict[str, str] = {}
+        for tag in DEFAULT_TAGS + formatted_tags:
+            key = tag.split(":")[0] if ":" in tag else tag
+            merged[key] = tag
         return ZimConfig(
             secondary_color=self.secondary_color,
             file_name=fmt(self.file_name),
@@ -54,5 +69,5 @@ def fmt(string: str) -> str:
             long_description=(
                 fmt(self.long_description) if self.long_description else None
             ),
-            tags=[fmt(tag) for tag in self.tags] if self.tags else [],
+            tags=list(merged.values()),
         )

scraper/tests/test_zimconfig.py

@@ -0,0 +1,78 @@
+import pytest
+
+from maps2zim.errors import InvalidFormatError
+from maps2zim.zimconfig import DEFAULT_TAGS, ZimConfig
+
+
+def make_config(tags: list[str] | None = None) -> ZimConfig:
+    return ZimConfig(
+        file_name="test_{region}",
+        name="test_{region}",
+        title="Test {region}",
+        publisher="Publisher",
+        creator="Creator",
+        description="Desc {region}",
+        long_description=None,
+        tags=tags,
+        secondary_color="#FFFFFF",
+    )
+
+
+PLACEHOLDERS = {"region": "world"}
+
+
+def test_format_includes_default_tags_when_no_tags():
+    config = make_config(tags=None)
+    result = config.format(PLACEHOLDERS)
+    assert result.tags == DEFAULT_TAGS
+
+
+def test_format_default_tags_overridden_by_user_tag():
+    config = make_config(tags=["_videos:yes"])
+    result = config.format(PLACEHOLDERS)
+    assert result.tags is not None
+    # _videos:no from defaults should be replaced by _videos:yes
+    assert "_videos:yes" in result.tags
+    assert "_videos:no" not in result.tags
+
+
+def test_format_all_default_tags_present_with_override():
+    config = make_config(tags=["_videos:yes"])
+    result = config.format(PLACEHOLDERS)
+    assert result.tags is not None
+    for default_tag in DEFAULT_TAGS:
+        key = default_tag.split(":")[0]
+        assert any(t.startswith(key + ":") for t in result.tags)
+
+
+def test_format_extra_user_tag_added():
+    config = make_config(tags=["custom_tag"])
+    result = config.format(PLACEHOLDERS)
+    assert result.tags is not None
+    assert "custom_tag" in result.tags
+    # All defaults still present
+    for default_tag in DEFAULT_TAGS:
+        assert default_tag in result.tags
+
+
+def test_format_multiple_overrides():
+    config = make_config(tags=["_videos:yes", "_pictures:no"])
+    result = config.format(PLACEHOLDERS)
+    assert result.tags is not None
+    assert "_videos:yes" in result.tags
+    assert "_videos:no" not in result.tags
+    assert "_pictures:no" in result.tags
+    assert "_pictures:yes" not in result.tags
+
+
+def test_format_tags_with_placeholder():
+    config = make_config(tags=["region_{region}"])
+    result = config.format(PLACEHOLDERS)
+    assert result.tags is not None
+    assert "region_world" in result.tags
+
+
+def test_format_invalid_placeholder_raises():
+    config = make_config(tags=["_{bad_key}:yes"])
+    with pytest.raises(InvalidFormatError):
+        config.format(PLACEHOLDERS)