Remove unused code for Chinese Wiktionary from English extractor

tatuylonen · Nov 28, 2023 · 73c0aec · 73c0aec
1 parent ba2492e
commit 73c0aec
Show file tree

Hide file tree

Showing 2 changed files with 0 additions and 31 deletions.
diff --git a/src/wiktextract/config.py b/src/wiktextract/config.py
@@ -48,9 +48,6 @@ class WiktionaryConfig:
         "POS_TYPES",
         "OTHER_SUBTITLES",
         "ZH_PRON_TAGS",
-        "FR_FORM_TABLES",
-        "DE_FORM_TABLES",
-        "FORM_OF_TEMPLATES",
         "analyze_templates",
         "extract_thesaurus_pages",
     )
@@ -112,10 +109,6 @@ def __init__(
         self.data_folder = files("wiktextract") / "data" / dump_file_lang_code
         self.init_subtitles()
         self.set_attr_from_json("ZH_PRON_TAGS", "zh_pron_tags.json")
-        if dump_file_lang_code == "zh":
-            self.set_attr_from_json(
-                "FORM_OF_TEMPLATES", "form_of_templates.json"
-            )
         self.analyze_templates = True  # find templates that need pre-expand
         self.extract_thesaurus_pages = True
         self.load_edition_settings()

diff --git a/src/wiktextract/extractor/en/page.py b/src/wiktextract/extractor/en/page.py
@@ -1470,9 +1470,6 @@ def sense_template_fn(
                 v = v.strip()
                 if v and "<" not in v:
                     gloss_template_args.add(v)
-            if wxr.config.dump_file_lang_code == "zh":
-                add_form_of_tags(wxr, name,
-                                 wxr.config.FORM_OF_TEMPLATES, sense_base)
             return None
 
         def extract_link_texts(item):
@@ -3596,24 +3593,3 @@ def multitrans_post_fn(name, ht, text):
                              )
             x["original_title"] = word
     return ret
-
-
-def add_form_of_tags(wxr, template_name, form_of_templates, sense_data):
-    # https://en.wiktionary.org/wiki/Category:Form-of_templates
-    if template_name in form_of_templates:
-        data_append(sense_data, "tags", "form-of")
-
-        if template_name in ("abbreviation of", "abbr of"):
-            data_append(sense_data, "tags", "abbreviation")
-        elif template_name.startswith(("alt ", "alternative")):
-            data_append(sense_data, "tags", "alt-of")
-        elif template_name.startswith(("female", "feminine")):
-            data_append(sense_data, "tags", "feminine")
-        elif template_name == "initialism of":
-            data_extend(sense_data, "tags", ["abbreviation", "initialism"])
-        elif template_name.startswith("masculine"):
-            data_append(sense_data, "tags", "masculine")
-        elif template_name.startswith("misspelling"):
-            data_append(sense_data, "tags", "misspelling")
-        elif template_name.startswith(("obsolete", "obs ")):
-            data_append(sense_data, "tags", "obsolete")