Merge pull request #737 from xxyzz/pl

[pl] translate some tags and topics data start with "a" and b"

src/wiktextract/extractor/pl/pos.py

@@ -5,10 +5,12 @@
 from ...page import clean_node
 from ...wxr_context import WiktextractContext
 from .models import Sense, WordEntry
+from .tags import translate_raw_tags
 
 POS_DATA = {
     "rzeczownik": {"pos": "noun"},
     "czasownik": {"pos": "verb"},
+    "przyimek": {"pos": "prep"},
     "przymiotnik": {"pos": "adj"},
     "przyrostek": {"pos": "suffix", "tags": ["morpheme"]},
     "wrostek": {"pos": "infix", "tags": ["morpheme"]},
@@ -19,11 +21,13 @@
     "spójnik": {"pos": "conj"},
     "określnik": {"pos": "det"},
     "międzyrostek": {"pos": "interfix", "tags": ["morpheme"]},
+    "morfem": {"pos": "unknown", "tags": ["morpheme"]},
     "wykrzyknik": {"pos": "intj"},
     "symbol": {"pos": "symbol"},
     "liczebnik": {"pos": "num"},
     "partykuła": {"pos": "particle"},
     "skrótowiec": {"pos": "abbrev", "tags": ["abbreviation"]},
+    "zaimek": {"pos": "pron"},
 }
 
 
@@ -83,4 +87,5 @@ def process_gloss_list_item(
         sense.raw_tags = raw_tags
         sense.sense_index = sense_index
         sense.glosses.append(gloss_text)
+        translate_raw_tags(sense)
         word_entry.senses.append(sense)

src/wiktextract/extractor/pl/tags.py

@@ -0,0 +1,62 @@
+from .models import WordEntry
+
+# Help:Abbreviations used in Wiktionary
+# https://pl.wiktionary.org/wiki/Pomoc:Skróty_używane_w_Wikisłowniku
+# Category:Shortcut templates
+# https://pl.wiktionary.org/wiki/Kategoria:Szablony_skrótów
+TAGS = {
+    "abl.": "ablative",
+    # "akust.": "",
+    "aor.": "aorist",
+    "bezok.": "infinitive",
+    "bezosob.": "impersonal",
+    "bibl.": "Biblical",
+    "blm": "no-plural",
+    "blp": "no-singulative",
+    "Bm": "Bokmål",
+    "bośn.": "Bosnian",
+    "brytań.": "British",
+    "bułg.": "Bulgarian",
+    "bwr.": "Bavarian",
+}
+
+TOPICS = {
+    "adm.": "administration",
+    "agrot.": "agrotechnology",
+    "alch.": "alchemy",
+    "anat.": "anatomy",
+    "antrop.": "anthropology",
+    "arachn.": "arachnology",
+    "archit.": "architecture",
+    "archeol.": "archeology",
+    "astr.": "astronomy",
+    "astrol.": "astrology",
+    "astronaut.": "astronautics",
+    "bank.": "banking",
+    # "bibliot.": "",
+    "biochem.": "biochemistry",
+    "biol.": "biology",
+    # "biur.": "",
+    "bot.": "botany",
+    "bud.": "construction",
+}
+
+
+def translate_raw_tags(data: WordEntry) -> None:
+    raw_tags = []
+    for raw_tag in data.raw_tags:
+        if raw_tag in TAGS and hasattr(data, "tags"):
+            tag = TAGS[raw_tag]
+            if isinstance(tag, str):
+                data.tags.append(tag)
+            elif isinstance(tag, list):
+                data.tags.extend(tag)
+        elif raw_tag in TOPICS and hasattr(data, "topics"):
+            topic = TOPICS[raw_tag]
+            if isinstance(topic, str):
+                data.topics.append(topic)
+            elif isinstance(topic, list):
+                data.topics.extend(topic)
+        else:
+            raw_tags.append(raw_tag)
+    data.raw_tags = raw_tags