Merge pull request #1006 from xxyzz/zh

[de, zh] add "pos_title" field

src/wiktextract/extractor/de/models.py

@@ -136,6 +136,7 @@ class WordEntry(BaseModelWrap):
 
     word: str = Field(description="word string")
     pos: str = Field(default="", description="Part of speech type")
+    pos_title: str = ""
     other_pos: list[str] = []
     # pos_title: str = Field(default=None, description="Original POS title")
     lang_code: str = Field(

src/wiktextract/extractor/de/page.py

@@ -131,9 +131,12 @@ def process_pos_section(
     level_node: LevelNode,
 ) -> None:
     pos_data_list = []
+    pos_title = ""
     for template_node in level_node.find_content(NodeKind.TEMPLATE):
         if template_node.template_name == "Wortart":
             pos_argument = template_node.template_parameters.get(1, "").strip()
+            if pos_title == "":
+                pos_title = pos_argument
             if pos_argument in IGNORE_POS:
                 continue
             elif pos_argument in FORM_POS:
@@ -169,6 +172,7 @@ def process_pos_section(
                 page_data[-1].tags.append(tag)
         if pos_index == 0:
             page_data[-1].pos = pos
+            page_data[-1].pos_title = pos_title
         elif pos != page_data[-1].pos and pos not in page_data[-1].other_pos:
             page_data[-1].other_pos.append(pos)
 

src/wiktextract/extractor/zh/models.py

@@ -134,6 +134,7 @@ class WordEntry(ChineseBaseModel):
     lang_code: str = Field(description="Wiktionary language code")
     lang: str = Field(description="Localized language name")
     pos: str = Field(description="Part of speech type")
+    pos_title: str = ""
     etymology_text: str = ""
     etymology_examples: list[Example] = []
     senses: list[Sense] = Field(default=[], description="Sense list")

src/wiktextract/extractor/zh/page.py

@@ -116,12 +116,13 @@ def process_pos_block(
     page_data: list[WordEntry],
     base_data: WordEntry,
     level_node: LevelNode,
-    pos_text: str,
+    pos_title: str,
 ):
-    pos_data = POS_TITLES[pos_text]
+    pos_data = POS_TITLES[pos_title]
     pos_type = pos_data["pos"]
     base_data.pos = pos_type
     page_data.append(base_data.model_copy(deep=True))
+    page_data[-1].pos_title = pos_title
     page_data[-1].tags.extend(pos_data.get("tags", []))
     for index, child in enumerate(level_node.filter_empty_str_child()):
         if isinstance(child, WikiNode):

tests/test_de_gloss.py

@@ -259,6 +259,7 @@ def test_form_of(self):
                     "lang": "Deutsch",
                     "lang_code": "de",
                     "pos": "adj",
+                    "pos_title": "Deklinierte Form",
                     "senses": [
                         {
                             "form_of": [{"word": "konjugiert"}],
@@ -300,6 +301,7 @@ def test_no_bedeutungen_section(self):
                     "lang": "Litauisch",
                     "lang_code": "lt",
                     "pos": "unknown",
+                    "pos_title": "Deklinierte Form",
                     "senses": [
                         {
                             "form_of": [{"word": "abakas"}],
@@ -330,6 +332,7 @@ def test_grammatische_merkmale_no_form_of_pos_title(self):
                     "lang": "Latein",
                     "lang_code": "la",
                     "pos": "verb",
+                    "pos_title": "Infinitiv",
                     "senses": [
                         {
                             "form_of": [{"word": "abire"}],
@@ -363,6 +366,7 @@ def test_no_gloss_list(self):
                     "lang": "Interlingua",
                     "lang_code": "ia",
                     "pos": "unknown",
+                    "pos_title": "Konjugierte Form",
                     "senses": [
                         {"glosses": ["Indikativ Präsens Aktiv des Verbs amar"]}
                     ],
@@ -390,6 +394,7 @@ def test_unordered_list(self):
                     "lang": "Prußisch",
                     "lang_code": "prg",
                     "pos": "prep",
+                    "pos_title": "Präposition",
                     "senses": [{"glosses": ["Nebenform der Präposition esse"]}],
                     "word": "assa",
                 }
@@ -413,6 +418,7 @@ def test_description_list_plus_unordered_list(self):
                     "lang": "Polnisch",
                     "lang_code": "pl",
                     "pos": "noun",
+                    "pos_title": "Deklinierte Form",
                     "senses": [
                         {
                             "form_of": [{"word": "auto"}],

tests/test_de_page.py

@@ -42,6 +42,7 @@ def test_de_parse_page(self):
                     "lang_code": "de",
                     "word": "Beispiel",
                     "pos": "noun",
+                    "pos_title": "Substantiv",
                     "senses": [{"tags": ["no-gloss"]}],
                 }
             ],
@@ -69,6 +70,7 @@ def test_de_parse_page_skipping_head_templates(self):
                     "lang_code": "de",
                     "word": "Beispiel",
                     "pos": "noun",
+                    "pos_title": "Substantiv",
                     "senses": [{"tags": ["no-gloss"]}],
                 }
             ],
@@ -91,6 +93,7 @@ def test_multiple_pos(self):
                     "lang": "Deutsch",
                     "lang_code": "de",
                     "pos": "noun",
+                    "pos_title": "Substantiv",
                     "other_pos": ["name"],
                     "senses": [
                         {

tests/test_zh_gloss.py

@@ -161,6 +161,7 @@ def test_gloss_text_only_page(self):
                         "lang": "漢語",
                         "lang_code": "zh",
                         "pos": "unknown",
+                        "pos_title": "釋義",
                         "senses": [
                             {
                                 "glosses": [
@@ -318,6 +319,7 @@ def test_inflection_of_template(self):
                     "lang": "冰島語",
                     "lang_code": "is",
                     "pos": "noun",
+                    "pos_title": "名詞",
                     "senses": [
                         {
                             "form_of": [{"word": "lindi"}],
@@ -544,6 +546,7 @@ def test_erhua(self):
                     "lang": "漢語",
                     "lang_code": "zh",
                     "pos": "adv",
+                    "pos_title": "副詞",
                     "senses": [
                         {
                             "categories": ["官話漢語", "官話兒化詞"],

tests/test_zh_linkage.py

@@ -129,6 +129,7 @@ def test_linkage_above_pos(self):
                     "lang": "英語",
                     "lang_code": "en",
                     "pos": "name",
+                    "pos_title": "專有名詞",
                     "senses": [{"glosses": ["偵探漫畫"]}],
                     "synonyms": [{"word": "Tec"}],
                     "word": "'Tec",
@@ -268,13 +269,15 @@ def test_level_3_linkage_section(self):
                     "lang": "漢語",
                     "lang_code": "zh",
                     "pos": "noun",
+                    "pos_title": "名詞",
                     "senses": [{"glosses": ["愚昧的人民"]}],
                     "word": "愚民",
                 },
                 {
                     "lang": "漢語",
                     "lang_code": "zh",
                     "pos": "verb",
+                    "pos_title": "動詞",
                     "descendants": [
                         {
                             "lang_code": "ja",

tests/test_zh_pronunciation.py

@@ -147,6 +147,7 @@ def test_level3_pron_level3_pos(self):
                     "lang": "漢語",
                     "lang_code": "zh",
                     "pos": "verb",
+                    "pos_title": "動詞",
                     "senses": [{"glosses": ["塞住耳朵"]}],
                     "sounds": [
                         {"zh_pron": "chōng'ěr", "tags": ["Mandarin", "Pinyin"]}
@@ -162,6 +163,7 @@ def test_level3_pron_level3_pos(self):
                     "lang": "漢語",
                     "lang_code": "zh",
                     "pos": "noun",
+                    "pos_title": "名詞",
                     "senses": [
                         {"glosses": ["古冠冕旁的瑱玉，因其下垂及耳，而得名"]}
                     ],
@@ -222,6 +224,7 @@ def test_level3_pron_level4_pos(self):
                     "lang": "漢語",
                     "lang_code": "zh",
                     "pos": "noun",
+                    "pos_title": "名詞",
                     "senses": [{"glosses": ["眾人，某個範圍中所有的人"]}],
                     "sounds": [
                         {
@@ -235,6 +238,7 @@ def test_level3_pron_level4_pos(self):
                     "lang": "漢語",
                     "lang_code": "zh",
                     "pos": "noun",
+                    "pos_title": "名詞",
                     "senses": [{"glosses": ["卿大夫之家"]}],
                     "sounds": [
                         {"zh_pron": "dàjiā", "tags": ["Mandarin", "Pinyin"]}
@@ -245,6 +249,7 @@ def test_level3_pron_level4_pos(self):
                     "lang": "漢語",
                     "lang_code": "zh",
                     "pos": "noun",
+                    "pos_title": "名詞",
                     "senses": [{"glosses": ["對女子的尊稱"]}],
                     "sounds": [
                         {"zh_pron": "dàgū", "tags": ["Mandarin", "Pinyin"]}