Merge pull request #807 from xxyzz/de

[de] fix `IndexError` exception and add some title templates

src/wiktextract/data/overrides/de.json

@@ -1,9 +1,19 @@
 {
+  "Vorlage:Abgeleitete Symbole": {
+    "body": "====Abgeleitete Symbole====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Abkürzungen": {
     "body": "==== Abkürzungen ====",
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Ähnlichkeiten": {
+    "body": "====Ähnliche Wörter====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Alternative Schreibweisen": {
     "body": "==== Alternative Schreibweisen ====",
     "namespace_id": 10,
@@ -44,6 +54,16 @@
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Erbwörter": {
+    "body": "====Erbwörter====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
+  "Vorlage:Geflügelte Worte": {
+    "body": "====Geflügelte Worte====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Gegenwörter": {
     "body": "==== Gegenwörter ====",
     "namespace_id": 10,
@@ -54,31 +74,81 @@
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Hanja": {
+    "body": "====Hanja====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Herkunft": {
     "body": "==== Herkunft ====",
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Heteronyme": {
+    "body": "====Heteronyme====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Holonyme": {
     "body": "==== Holonyme ====",
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:in arabischer Schrift": {
+    "body": "====In arabischer Schrift====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
+  "Vorlage:in hebräischer Schrift": {
+    "body": "====In hebräischer Schrift====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
+  "Vorlage:in kanadischer Silbenschrift": {
+    "body": "====In kanadischer Silbenschrift====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
+  "Vorlage:in kyrillischer Schrift": {
+    "body": "====In kyrillischer Schrift====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
+  "Vorlage:in lateinischer Schrift": {
+    "body": "====In lateinischer Schrift====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Koseformen": {
     "body": "==== Koseformen ====",
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Kurzformen": {
+    "body": "====Kurzformen====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Lesungen": {
     "body": "==== Lesungen ====",
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Männliche Namensvarianten": {
+    "body": "====Männliche Namensvarianten====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Männliche Wortformen": {
     "body": "==== Männliche Wortformen ====",
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Meronyme": {
+    "body": "====Meronyme====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Namensvarianten": {
     "body": "==== Namensvarianten ====",
     "namespace_id": 10,
@@ -129,11 +199,21 @@
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Sinnverwandte Redewendungen": {
+    "body": "====Sinnverwandte Redewendungen====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Sinnverwandte Wörter": {
     "body": "==== Sinnverwandte Wörter ====",
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Sinnverwandte Zeichen": {
+    "body": "====Sinnverwandte Zeichen====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Sprichwörter": {
     "body": "==== Sprichwörter ====",
     "namespace_id": 10,
@@ -159,6 +239,16 @@
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Verballhornung": {
+    "body": "====Verballhornungen====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
+  "Vorlage:Vergrößerungsformen": {
+    "body": "====Vergrößerungsformen====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Verkleinerungsformen": {
     "body": "==== Verkleinerungsformen ====",
     "namespace_id": 10,
@@ -169,6 +259,11 @@
     "namespace_id": 10,
     "need_pre_expand": true
   },
+  "Vorlage:Weibliche Namensvarianten": {
+    "body": "====Weibliche Namensvarianten====",
+    "namespace_id": 10,
+    "need_pre_expand": true
+  },
   "Vorlage:Weibliche Wortformen": {
     "body": "==== Weibliche Wortformen ====",
     "namespace_id": 10,

src/wiktextract/extractor/de/linkage.py

@@ -48,6 +48,17 @@ def process_linkage_list_item(
             raw_tag = clean_node(wxr, None, child)
             if raw_tag.endswith(":"):
                 raw_tags.append(raw_tag.strip(": "))
+            else:
+                for link_node in child.find_child(NodeKind.LINK):
+                    link_text = clean_node(wxr, None, link_node)
+                    if link_text != "":
+                        linkage = Linkage(
+                            word=link_text,
+                            sense_index=sense_idx,
+                            raw_tags=raw_tags,
+                        )
+                        translate_raw_tags(linkage)
+                        linkage_list.append(linkage)
         elif isinstance(child, TemplateNode) and child.template_name.endswith(
             "."
         ):
@@ -67,7 +78,7 @@ def process_linkage_list_item(
                 translate_raw_tags(linkage)
                 linkage_list.append(linkage)
 
-    if len(note_nodes) > 0:
+    if len(note_nodes) > 0 and len(linkage_list) > 0:
         linkage_list[-1].note = clean_node(wxr, None, note_nodes).strip(
             "–—―‒- "
         )

src/wiktextract/extractor/de/models.py

@@ -177,3 +177,4 @@ class WordEntry(BaseModelWrap):
     redirects: list[str] = []
     etymology_text: str = ""
     forms: list[Form] = []
+    meronyms: list[Linkage] = []

src/wiktextract/extractor/de/page.py

@@ -39,6 +39,8 @@ def parse_section(
     # Page structure: https://de.wiktionary.org/wiki/Hilfe:Formatvorlage
     # Level 3 headings are used to start POS sections like
     # === {{Wortart|Verb|Deutsch}} ===
+    # title templates:
+    # https://de.wiktionary.org/wiki/Kategorie:Wiktionary:Textbausteine
     if level_node.kind == NodeKind.LEVEL3:
         process_pos_section(wxr, page_data, base_data, level_node)
     # Level 4 headings were introduced by overriding the default templates.

src/wiktextract/extractor/de/section_titles.py

@@ -91,19 +91,30 @@
     "Holonyme": "holonyms",
     "Oberbegriffe": "hypernyms",
     "Redewendungen": "expressions",
+    "Sinnverwandte Redewendungen": "synonyms",
     "Sinnverwandte Wörter": "coordinate_terms",
+    "Sinnverwandte Zeichen": "synonyms",
     "Sprichwörter": "proverbs",
     "Synonyme": "synonyms",
     "Unterbegriffe": "hyponyms",
     "Wortbildungen": "derived",
+    "Abgeleitete Symbole": "derived",
+    "Geflügelte Worte": "proverbs",
+    "Meronyme": "meronyms",
 }
 
 FORM_TITLES = {
     "Nebenformen": ["variant"],
+    "Namensvarianten": ["variant"],
     "Weibliche Wortformen": ["feminine"],
+    "Weibliche Namensvarianten": ["feminine"],
     "Männliche Wortformen": ["masculine"],
     "Verkleinerungsformen": ["diminutive"],
     "Vergrößerungsformen": ["augmentative"],
     "Kurzformen": ["abbreviation"],
     "Koseformen": ["affective"],
+    "Hanja": ["hanja"],
+    "Männliche Namensvarianten": ["masculine"],
+    "Nicht mehr gültige Schreibweisen": ["obsolete"],
+    "Symbole": ["symbol"],
 }

tests/test_de_linkages.py

@@ -118,3 +118,24 @@ def test_tag_template(self):
                 },
             ],
         )
+
+    def test_link_in_italic_node(self):
+        self.wxr.wtp.start_page("Abendland")
+        root = self.wxr.wtp.parse("""====Redewendungen====
+:[1] ''[[Morgenland und Abendland]]'' -""")
+        word_entry = WordEntry(
+            word="Abendland",
+            lang_code="de",
+            lang="Deutsch",
+            senses=[Sense(sense_index="1")],
+        )
+        extract_linkages(self.wxr, word_entry, root.children[0], "expressions")
+        self.assertEqual(
+            [
+                d.model_dump(exclude_defaults=True)
+                for d in word_entry.expressions
+            ],
+            [
+                {"word": "Morgenland und Abendland", "sense_index": "1"},
+            ],
+        )