Add support for parsing output

This commit is contained in:
2026-01-09 13:41:44 +01:00
parent 9fe538014e
commit 7fbe57c05d

View File

@@ -1,8 +1,70 @@
import morfeusz2
from conmorfeusz import concraft
from typing import Dict, List
_TAG_SPECS: Dict[str, List[str]] = {
"adv": ["degree"],
"imps": ["aspect"],
"inf": ["aspect"],
"pant": ["aspect"],
"pcon": ["aspect"],
"qub": ["vocalicity"],
"prep": ["case", "vocalicity"],
"siebie": ["case"],
"subst": ["number", "case", "gender"],
"depr": ["number", "case", "gender"],
"ger": ["number", "case", "gender", "aspect", "negation"],
"ppron12": ["number", "case", "gender", "person", "accentability"],
"ppron3": [
"number",
"case",
"gender",
"person",
"accentability",
"postprepositionality",
],
"num": ["number", "case", "gender", "accommodability"],
"numcol": ["number", "case", "gender", "accommodability"],
"adj": ["number", "case", "gender", "degree"],
"pact": ["number", "case", "gender", "aspect", "negation"],
"ppas": ["number", "case", "gender", "aspect", "negation"],
"winien": ["number", "gender", "aspect"],
"praet": ["number", "gender", "aspect", "agglutination"],
"bedzie": ["number", "person", "aspect"],
"fin": ["number", "person", "aspect"],
"impt": ["number", "person", "aspect"],
"aglt": ["number", "person", "aspect", "vocalicity"],
}
def parse_tags(tags: str) -> Dict[str, str | None]:
type_, *rest = tags.split(":")
fields = _TAG_SPECS.get(type_, [])
padded_values = rest + [None] * (len(fields) - len(rest))
parsed = {field: value for field, value in zip(fields, padded_values)}
return {"type": type_, **parsed}
def entry_to_dict(entry):
start, end, morf, prob, eos, disamb = entry
segment, lemma, tags, frequency, qualifiers = morf
return {
"start": start,
"end": end,
"segment": segment,
"lemma": lemma,
"tags": parse_tags(tags),
"frequency": frequency,
"qualifiers": qualifiers,
"prob": float(prob),
"eos": eos == "eos",
"disamb": disamb == "disamb"
}
def analyse(text):
morf = morfeusz2.Morfeusz(expand_tags=True)
conc = concraft.Concraft()
analysis = morf.analyse(text)
return conc.disamb(analysis)
return [entry_to_dict(e) for e in conc.disamb(analysis) if len(e) == 6]