Rename lang_name to lang

src/wiktextract/extractor/de/models.py

@@ -20,7 +20,7 @@ class Translation(BaseModelWrap):
         default=None,
         description="Wiktionary language code of the translation term",
     )
-    lang_name: Optional[str] = Field(
+    lang: Optional[str] = Field(
         default=None, description="Localized language name"
     )
     uncertain: Optional[bool] = Field(
@@ -151,9 +151,7 @@ class Sound(BaseModelWrap):
     lang_code: list[str] = Field(
         default=[], description="Wiktionary language code"
     )
-    lang_name: list[str] = Field(
-        default=[], description="Localized language name"
-    )
+    lang: list[str] = Field(default=[], description="Localized language name")
     # roman: list[str] = Field(
     #     default=[], description="Translitaration to Roman characters"
     # )
@@ -179,7 +177,7 @@ class WordEntry(BaseModelWrap):
     lang_code: str = Field(
         description="Wiktionary language code", examples=["es"]
     )
-    lang_name: str = Field(
+    lang: str = Field(
         description="Localized language name of the word", examples=["español"]
     )
     senses: Optional[list[Sense]] = []

src/wiktextract/extractor/de/page.py

@@ -272,15 +272,15 @@ def parse_page(
     for level2_node in tree.find_child(NodeKind.LEVEL2):
         for subtitle_template in level2_node.find_content(NodeKind.TEMPLATE):
             # The language sections are marked with
-            # == <title> ({{Sprache|<lang_name>}}) ==
-            # where <title> is the title of the page and <lang_name> is the
+            # == <title> ({{Sprache|<lang>}}) ==
+            # where <title> is the title of the page and <lang> is the
             # German name of the language of the section.
             if subtitle_template.template_name == "Sprache":
-                lang_name = subtitle_template.template_parameters.get(1)
-                lang_code = name_to_code(lang_name, "de")
+                lang = subtitle_template.template_parameters.get(1)
+                lang_code = name_to_code(lang, "de")
                 if lang_code == "":
                     wxr.wtp.warning(
-                        f"Unknown language: {lang_name}",
+                        f"Unknown language: {lang}",
                         sortid="extractor/de/page/parse_page/76",
                     )
                 if (
@@ -290,7 +290,7 @@ def parse_page(
                     continue
 
                 base_data = WordEntry(
-                    lang_name=lang_name, lang_code=lang_code, word=wxr.wtp.title
+                    lang=lang, lang_code=lang_code, word=wxr.wtp.title
                 )
                 parse_section(wxr, page_data, base_data, level2_node.children)
 

src/wiktextract/extractor/de/pronunciation.py

@@ -99,14 +99,14 @@ def process_lautschrift_template(
 
     lang_code = template_parameters.get("spr")
     if lang_code:
-        lang_name = code_to_name(lang_code, "de")
+        lang = code_to_name(lang_code, "de")
         add_sound_data_without_appending_to_existing_properties(
             wxr,
             sound_data,
             {
                 "ipa": [ipa],
                 "lang_code": lang_code,
-                "lang_name": lang_name,
+                "lang": lang,
             },
         )
     else:

src/wiktextract/extractor/de/translation.py

@@ -103,10 +103,10 @@ def process_translation_list(
 
             lang_code = node.template_parameters.get(1)
             translation_data.lang_code = lang_code
-            translation_data.lang_name = code_to_name(lang_code, "de")
-            if translation_data.lang_name == "":
+            translation_data.lang = code_to_name(lang_code, "de")
+            if translation_data.lang == "":
                 wxr.wtp.debug(
-                    f"Unknown language code: {translation_data.lang_name}",
+                    f"Unknown language code: {translation_data.lang}",
                     sortid="extractor/de/translation/process_translation_list/70",
                 )
             if node.template_name[-1] == "?":

src/wiktextract/extractor/es/models.py

@@ -156,7 +156,7 @@ class WordEntry(BaseModelWrap):
     lang_code: str = Field(
         description="Wiktionary language code", examples=["es"]
     )
-    lang_name: str = Field(
+    lang: str = Field(
         description="Localized language name of the word", examples=["español"]
     )
     senses: Optional[list[Sense]] = []

src/wiktextract/extractor/es/page.py

@@ -4,6 +4,7 @@
 
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import WikiNodeChildrenList
+
 from wiktextract.extractor.es.etymology import process_etymology_block
 from wiktextract.extractor.es.example import extract_example
 from wiktextract.extractor.es.gloss import extract_gloss
@@ -368,10 +369,10 @@ def parse_page(
                 ):
                     continue
 
-                lang_name = clean_node(wxr, categories, subtitle_template)
-                wxr.wtp.start_section(lang_name)
+                lang = clean_node(wxr, categories, subtitle_template)
+                wxr.wtp.start_section(lang)
                 base_data = WordEntry(
-                    lang_name=lang_name, lang_code=lang_code, word=wxr.wtp.title
+                    lang=lang, lang_code=lang_code, word=wxr.wtp.title
                 )
                 base_data.categories.extend(categories["categories"])
                 parse_entries(wxr, page_data, base_data, level2_node)

src/wiktextract/extractor/ru/models.py

@@ -12,7 +12,7 @@ class Translation(BaseModelWrap):
     lang_code: str = Field(
         description="Wiktionary language code of the translation term"
     )
-    lang_name: str = Field(
+    lang: str = Field(
         description="Localized language name of the translation term"
     )
     sense: Optional[str] = Field(
@@ -112,7 +112,7 @@ class WordEntry(BaseModelWrap):
     lang_code: str = Field(
         description="Wiktionary language code", examples=["ru"]
     )
-    lang_name: str = Field(
+    lang: str = Field(
         description="Localized language name of the word", examples=["Русский"]
     )
     categories: list[str] = Field(

src/wiktextract/extractor/ru/page.py

@@ -202,11 +202,11 @@ def parse_page(
 
             categories = {"categories": []}
 
-            lang_name = clean_node(wxr, categories, subtitle_template)
-            wxr.wtp.start_section(lang_name)
+            lang = clean_node(wxr, categories, subtitle_template)
+            wxr.wtp.start_section(lang)
 
             base_data = WordEntry(
-                lang_name=lang_name, lang_code=lang_code, word=wxr.wtp.title
+                lang=lang, lang_code=lang_code, word=wxr.wtp.title
             )
             base_data.categories.extend(categories["categories"])
 

src/wiktextract/extractor/ru/translation.py

@@ -20,7 +20,7 @@ def extract_translations(
             for key, raw_value in template_node.template_parameters.items():
                 if isinstance(key, str):
                     lang_code = key
-                    lang_name = code_to_name(lang_code, "ru")
+                    lang = code_to_name(lang_code, "ru")
 
                     for value_node in (
                         raw_value
@@ -36,7 +36,7 @@ def extract_translations(
                                 word_entry.translations.append(
                                     Translation(
                                         lang_code=lang_code,
-                                        lang_name=lang_name,
+                                        lang=lang,
                                         word=word,
                                         sense=sense if sense else None,
                                     )

tests/test_de_example.py

@@ -20,7 +20,7 @@ def tearDown(self) -> None:
         self.wxr.wtp.close_db_conn()
 
     def get_default_page_data(self) -> list[WordEntry]:
-        return [WordEntry(word="Beispiel", lang_code="de", lang_name="Deutsch")]
+        return [WordEntry(word="Beispiel", lang_code="de", lang="Deutsch")]
 
     def test_de_extract_examples(self):
         self.wxr.wtp.start_page("")

tests/test_de_gloss.py

@@ -28,7 +28,7 @@ def tearDown(self) -> None:
         self.wxr.wtp.close_db_conn()
 
     def get_default_word_entry(self):
-        return WordEntry(lang_code="de", lang_name="Deutsch", word="Beispiel")
+        return WordEntry(lang_code="de", lang="Deutsch", word="Beispiel")
 
     def test_de_extract_glosses(self):
         self.wxr.wtp.start_page("")

tests/test_de_linkages.py

@@ -20,7 +20,7 @@ def tearDown(self) -> None:
         self.wxr.wtp.close_db_conn()
 
     def get_default_word_entry(self) -> WordEntry:
-        return WordEntry(word="Beispiel", lang_code="de", lang_name="Deutsch")
+        return WordEntry(word="Beispiel", lang_code="de", lang="Deutsch")
 
     def test_de_extract_linkages(self):
         test_cases = [
@@ -105,7 +105,7 @@ def test_de_extract_linkages(self):
                 self.assertEqual(
                     word_entry.model_dump(
                         exclude_defaults=True,
-                        exclude={"word", "lang_code", "lang_name"},
+                        exclude={"word", "lang_code", "lang"},
                     ),
                     case["expected"],
                 )

tests/test_de_page.py

@@ -29,7 +29,7 @@ def tearDown(self) -> None:
         self.wxr.wtp.close_db_conn()
 
     def get_default_base_data(self):
-        return WordEntry(lang_code="de", lang_name="Deutsch", word="Beispiel")
+        return WordEntry(lang_code="de", lang="Deutsch", word="Beispiel")
 
     def test_de_parse_page(self):
         self.wxr.wtp.add_page("Vorlage:Sprache", 10, "")
@@ -45,7 +45,7 @@ def test_de_parse_page(self):
             lst,
             [
                 {
-                    "lang_name": "Deutsch",
+                    "lang": "Deutsch",
                     "lang_code": "de",
                     "word": "Beispiel",
                     "pos": "noun",
@@ -71,7 +71,7 @@ def test_de_parse_page_skipping_head_templates(self):
             lst,
             [
                 {
-                    "lang_name": "Deutsch",
+                    "lang": "Deutsch",
                     "lang_code": "de",
                     "word": "Beispiel",
                     "pos": "noun",
@@ -104,7 +104,7 @@ def test_de_parse_section(self):
                 {
                     "word": "Beispiel",
                     "lang_code": "de",
-                    "lang_name": "Deutsch",
+                    "lang": "Deutsch",
                     "pos": "adj",
                     "senses": [
                         {
@@ -118,7 +118,7 @@ def test_de_parse_section(self):
                     "word": "Beispiel",
                     "lang_code": "de",
                     "pos": "adv",
-                    "lang_name": "Deutsch",
+                    "lang": "Deutsch",
                     "senses": [
                         {
                             "glosses": ["gloss1"],
@@ -131,7 +131,7 @@ def test_de_parse_section(self):
                     "word": "Beispiel",
                     "lang_code": "de",
                     "pos": "verb",
-                    "lang_name": "Deutsch",
+                    "lang": "Deutsch",
                     "senses": [
                         {
                             "glosses": ["gloss2"],
@@ -144,7 +144,7 @@ def test_de_parse_section(self):
                     "word": "Beispiel",
                     "lang_code": "de",
                     "pos": "noun",
-                    "lang_name": "Deutsch",
+                    "lang": "Deutsch",
                     "senses": [
                         {
                             "glosses": ["gloss3"],

tests/test_de_pronunciation.py

@@ -4,8 +4,10 @@
 
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.de.models import Sound
-from wiktextract.extractor.de.pronunciation import (process_hoerbeispiele,
-                                                    process_ipa)
+from wiktextract.extractor.de.pronunciation import (
+    process_hoerbeispiele,
+    process_ipa,
+)
 from wiktextract.wxr_context import WiktextractContext
 
 
@@ -35,7 +37,7 @@ def test_de_process_ipa(self):
                 "expected": [
                     {
                         "ipa": ["ipa1"],
-                        "lang_name": ["Deutsch"],
+                        "lang": ["Deutsch"],
                         "lang_code": ["de"],
                     }
                 ],
@@ -46,7 +48,7 @@ def test_de_process_ipa(self):
                     {"ipa": ["ipa1", "ipa2"]},
                     {
                         "ipa": ["ipa3"],
-                        "lang_name": ["Deutsch"],
+                        "lang": ["Deutsch"],
                         "lang_code": ["de"],
                     },
                 ],