Merge pull request #451 from xxyzz/lang

Change "lang_name" field to "lang" in fr and zh extractor

src/wiktextract/extractor/fr/conjugation.py

@@ -16,7 +16,7 @@ def extract_conjugation(wxr: WiktextractContext, entry: WordEntry) -> None:
     """
     conj_ns = wxr.wtp.NAMESPACE_DATA["Conjugaison"]
     conj_page_title = (
-        f"{conj_ns['name']}:{entry.lang_name.lower()}/{entry.word}"
+        f"{conj_ns['name']}:{entry.lang.lower()}/{entry.word}"
     )
     conj_page = wxr.wtp.get_page_body(conj_page_title, conj_ns["id"])
     if conj_page is None:

src/wiktextract/extractor/fr/linkage.py

@@ -44,7 +44,7 @@ def process_derives_autres_list(
             ):
                 word = clean_node(wxr, None, node)
                 page_data[-1].derived.append(
-                    Linkage(lang_code=lang_code, lang_name=lang_name, word=word)
+                    Linkage(lang_code=lang_code, lang=lang_name, word=word)
                 )
 
 

src/wiktextract/extractor/fr/models.py

@@ -45,7 +45,7 @@ class Translation(FrenchBaseModel):
     lang_code: str = Field(
         "", description="Wiktionary language code of the translation term"
     )
-    lang_name: str = Field("", description="Translation language name")
+    lang: str = Field("", description="Translation language name")
     word: str = Field("", description="Translation term")
     sense: str = Field("", description="Translation gloss")
     sense_index: int = Field(
@@ -68,7 +68,7 @@ class Linkage(FrenchBaseModel):
     sense_index: int = Field(
         0, ge=0, description="Number of the definition, start from 1"
     )
-    lang_name: str = Field("", description="Localized language name")
+    lang: str = Field("", description="Localized language name")
     lang_code: str = Field("", description="Wiktionary language code")
 
 
@@ -84,7 +84,7 @@ class WordEntry(FrenchBaseModel):
 
     word: str = Field(description="Word string")
     lang_code: str = Field(description="Wiktionary language code")
-    lang_name: str = Field(description="Localized language name")
+    lang: str = Field(description="Localized language name")
     pos: str = Field("", description="Part of speech type")
     pos_title: str = Field(
         "", description="Original POS title for matching etymology texts"

src/wiktextract/extractor/fr/page.py

@@ -190,7 +190,7 @@ def parse_page(
                 base_data = WordEntry(
                     word=wxr.wtp.title,
                     lang_code=lang_code,
-                    lang_name=lang_name,
+                    lang=lang_name,
                     categories=categories.get("categories", []),
                 )
                 etymology_data: Optional[EtymologyData] = None

src/wiktextract/extractor/fr/translation.py

@@ -89,7 +89,7 @@ def process_translation_templates(
         base_translation_data.lang_code = template_node.template_parameters.get(
             1
         )
-        base_translation_data.lang_name = clean_node(
+        base_translation_data.lang = clean_node(
             wxr, page_data[-1], template_node
         )
     elif template_node.template_name.startswith("trad"):

src/wiktextract/extractor/zh/descendant.py

@@ -43,7 +43,7 @@ def extract_descendant_list_item(
         for child_index, child_node in enumerate(nodes_without_ruby):
             if isinstance(child_node, str) and child_node.endswith("："):
                 lang_name = child_node.strip(" ：")
-                descendant_data.lang_name = lang_name
+                descendant_data.lang = lang_name
             elif (
                 isinstance(child_node, WikiNode)
                 and child_node.kind == NodeKind.HTML
@@ -61,7 +61,7 @@ def extract_descendant_list_item(
                         if len(descendant_data.word) > 0:
                             parent_data.descendants.append(descendant_data)
                             descendant_data = Descendant(
-                                lang_code=lang_code, lang_name=lang_name
+                                lang_code=lang_code, lang=lang_name
                             )
                             if len(ruby_data) > 0:
                                 descendant_data.ruby = ruby_data

src/wiktextract/extractor/zh/linkage.py

@@ -120,7 +120,7 @@ def extract_linkages(
 
                 base_data = WordEntry(
                     lang_code=page_data[-1].lang_code,
-                    lang_name=page_data[-1].lang_name,
+                    lang=page_data[-1].lang,
                     word=page_data[-1].word,
                 )
                 parse_section(wxr, page_data, base_data, node)

src/wiktextract/extractor/zh/models.py

@@ -64,7 +64,7 @@ class Translation(ChineseBaseModel):
     lang_code: str = Field(
         "", description="Wiktionary language code of the translation term"
     )
-    lang_name: str = Field("", description="Translation language name")
+    lang: str = Field("", description="Translation language name")
     word: str = Field("", description="Translation term")
     sense: str = Field("", description="Translation gloss")
     tags: list[str] = []
@@ -83,8 +83,8 @@ class Linkage(ChineseBaseModel):
 
 
 class Descendant(ChineseBaseModel):
-    lang_code: str = Field("", description="Wiktionary language code of")
-    lang_name: str = Field("", description="Translation language name")
+    lang_code: str = Field("", description="Wiktionary language code")
+    lang: str = Field("", description="Language name")
     word: str = ""
     roman: str = ""
     tags: list[str] = []
@@ -97,7 +97,7 @@ class WordEntry(ChineseBaseModel):
 
     word: str = Field(description="Word string")
     lang_code: str = Field(description="Wiktionary language code")
-    lang_name: str = Field(description="Localized language name")
+    lang: str = Field(description="Localized language name")
     pos: str = Field("", description="Part of speech type")
     etymology_text: str = ""
     senses: list[Sense] = Field([], description="Sense list")

src/wiktextract/extractor/zh/page.py

@@ -226,7 +226,7 @@ def parse_page(
             continue
         wxr.wtp.start_section(lang_name)
         base_data = WordEntry(
-            word=wxr.wtp.title, lang_code=lang_code, lang_name=lang_name
+            word=wxr.wtp.title, lang_code=lang_code, lang=lang_name
         )
         base_data.categories = categories.get("categories", [])
         page_data.append(base_data.model_copy(deep=True))

src/wiktextract/extractor/zh/translation.py

@@ -102,7 +102,7 @@ def process_translation_list_item(
         tags, word = capture_text_in_parentheses(word_and_tags)
         tags = [tag for tag in tags if tag != lang_code]  # rm Wiktionary link
         translation_data = Translation(
-            lang_code=lang_code, lang_name=lang_text, word=word
+            lang_code=lang_code, lang=lang_text, word=word
         )
         tags_without_roman = []
         for tag in tags:

tests/test_fr_conj.py

@@ -67,7 +67,7 @@ def test_fr_conj_1(self):
 |}
 </div>""",
         )
-        entry = WordEntry(lang_code="fr", lang_name="Français", word="lancer")
+        entry = WordEntry(lang_code="fr", lang="Français", word="lancer")
         extract_conjugation(self.wxr, entry)
         self.assertEqual(
             [f.model_dump(exclude_defaults=True) for f in entry.forms],

tests/test_fr_etymology.py

@@ -54,14 +54,14 @@ def test_list_etymologies(self):
             WordEntry(
                 word="test",
                 lang_code="fr",
-                lang_name="Français",
+                lang="Français",
                 pos="noun",
                 pos_title="Nom commun 1",
             ),
             WordEntry(
                 word="test",
                 lang_code="fr",
-                lang_name="Français",
+                lang="Français",
                 pos="noun",
                 pos_title="Nom commun 2",
             ),
@@ -73,7 +73,7 @@ def test_list_etymologies(self):
                 {
                     "word": "test",
                     "lang_code": "fr",
-                    "lang_name": "Français",
+                    "lang": "Français",
                     "pos": "noun",
                     "pos_title": "Nom commun 1",
                     "etymology_texts": [
@@ -84,7 +84,7 @@ def test_list_etymologies(self):
                 {
                     "word": "test",
                     "lang_code": "fr",
-                    "lang_name": "Français",
+                    "lang": "Français",
                     "pos": "noun",
                     "pos_title": "Nom commun 2",
                     "etymology_texts": [
@@ -119,21 +119,21 @@ def test_indent_etymology_with_pos_template(self):
             WordEntry(
                 word="test",
                 lang_code="fr",
-                lang_name="Français",
+                lang="Français",
                 pos="noun",
                 pos_title="Nom commun 1",
             ),
             WordEntry(
                 word="test",
                 lang_code="fr",
-                lang_name="Français",
+                lang="Français",
                 pos="noun",
                 pos_title="Nom commun 2",
             ),
             WordEntry(
                 word="test",
                 lang_code="fr",
-                lang_name="Français",
+                lang="Français",
                 pos="intj",
                 pos_title="Interjection",
             ),
@@ -145,7 +145,7 @@ def test_indent_etymology_with_pos_template(self):
                 {
                     "word": "test",
                     "lang_code": "fr",
-                    "lang_name": "Français",
+                    "lang": "Français",
                     "pos": "noun",
                     "pos_title": "Nom commun 1",
                     "etymology_texts": [
@@ -155,7 +155,7 @@ def test_indent_etymology_with_pos_template(self):
                 {
                     "word": "test",
                     "lang_code": "fr",
-                    "lang_name": "Français",
+                    "lang": "Français",
                     "pos": "noun",
                     "pos_title": "Nom commun 2",
                     "etymology_texts": [
@@ -165,7 +165,7 @@ def test_indent_etymology_with_pos_template(self):
                 {
                     "word": "test",
                     "lang_code": "fr",
-                    "lang_name": "Français",
+                    "lang": "Français",
                     "pos": "intj",
                     "pos_title": "Interjection",
                     "etymology_texts": [

tests/test_fr_form_line.py

@@ -25,7 +25,7 @@ def test_ipa(self):
         self.wxr.wtp.add_page("Modèle:pron", 10, "\\bɔ̃.ʒuʁ\\")
         root = self.wxr.wtp.parse("'''bonjour''' {{pron|bɔ̃.ʒuʁ|fr}}")
         page_data = [
-            WordEntry(word="bonjour", lang_code="fr", lang_name="Français")
+            WordEntry(word="bonjour", lang_code="fr", lang="Français")
         ]
         extract_form_line(self.wxr, page_data, root.children)
         self.assertEqual(
@@ -38,7 +38,7 @@ def test_gender(self):
         self.wxr.wtp.add_page("Modèle:m", 10, "masculin")
         root = self.wxr.wtp.parse("'''bonjour''' {{m}}")
         page_data = [
-            WordEntry(word="bonjour", lang_code="fr", lang_name="Français")
+            WordEntry(word="bonjour", lang_code="fr", lang="Français")
         ]
         extract_form_line(self.wxr, page_data, root.children)
         self.assertEqual(page_data[-1].tags, ["masculin"])
@@ -50,7 +50,7 @@ def test_zh_mot(self):
         self.wxr.wtp.add_page("Modèle:pron", 10, body="\\ma̠˨˩˦\\")
         root = self.wxr.wtp.parse("{{zh-mot|马|mǎ}}")
         page_data = [
-            WordEntry(word="test", lang_code="fr", lang_name="Français")
+            WordEntry(word="test", lang_code="fr", lang="Français")
         ]
         process_zh_mot_template(self.wxr, root.children[0], page_data)
         self.assertEqual(
@@ -72,15 +72,15 @@ def test_ipa_location_tag(self):
             "{{pron|bas.kɛt.bol|fr}} {{FR|nocat=1}} ''ou'' {{pron|bas.kɛt.bɔl|fr}} {{FR|nocat=1}} ''ou'' {{pron|bas.kɛt.bɑl|fr}} {{CA|nocat=1}} {{m}}"
         )
         page_data = [
-            WordEntry(word="basket-ball", lang_code="fr", lang_name="Français")
+            WordEntry(word="basket-ball", lang_code="fr", lang="Français")
         ]
         extract_form_line(self.wxr, page_data, root.children)
         self.assertEqual(
             page_data[-1].model_dump(exclude_defaults=True),
             {
                 "word": "basket-ball",
                 "lang_code": "fr",
-                "lang_name": "Français",
+                "lang": "Français",
                 "tags": ["masculin"],
                 "sounds": [
                     {"ipa": "bas.kɛt.bol", "tags": ["France"]},
@@ -99,7 +99,7 @@ def test_template_in_pron_argument(self):
             "'''minéral argileux''' {{pron|mi.ne.ʁa.l{{liaison|fr}}aʁ.ʒi.lø|fr}}"
         )
         page_data = [
-            WordEntry(word="test", lang_code="fr", lang_name="Français")
+            WordEntry(word="test", lang_code="fr", lang="Français")
         ]
         extract_form_line(self.wxr, page_data, root.children)
         self.assertEqual(
@@ -118,15 +118,15 @@ def test_equiv_pour_template(self, mock_node_to_wikitext):
             "{{équiv-pour|un homme|auteur|2egenre=une personne non-binaire|2egenre1=autaire|2egenre2=auteurice|2egenre3=auteur·ice|lang=fr}}"
         )
         page_data = [
-            WordEntry(word="autrice", lang_code="fr", lang_name="Français")
+            WordEntry(word="autrice", lang_code="fr", lang="Français")
         ]
         extract_form_line(self.wxr, page_data, root.children)
         self.assertEqual(
             page_data[-1].model_dump(exclude_defaults=True),
             {
                 "word": "autrice",
                 "lang_code": "fr",
-                "lang_name": "Français",
+                "lang": "Français",
                 "forms": [
                     {
                         "form": "auteur",