Making suru verb work again

This commit is contained in:
Alex Yatskov 2016-04-19 21:37:11 -07:00
parent b02ec434f5
commit 8c0ead7a3a
2 changed files with 32 additions and 27 deletions

View File

@ -41,7 +41,8 @@ class Dictionary {
results = results.concat( results = results.concat(
indices.map(index => { indices.map(index => {
const [e, r, t, ...g] = dict.defs[index]; const [e, r, t, ...g] = dict.defs[index];
return {id: index, expression: e, reading: r, glossary: g, tags: t.split(' ')}; const tags = Dictionary.fixupTags(t.split(' '));
return {id: index, expression: e, reading: r, glossary: g, tags: tags};
}) })
); );
} }
@ -62,4 +63,19 @@ class Dictionary {
return results; return results;
} }
static fixupTags(tags) {
const results = [];
for (const tag of tags) {
if (tag.startsWith('v5') && tag !== 'v5') {
results.push('v5');
} else if (tag.startsWith('vs-')) {
results.push('vs');
}
results.push(tag);
}
return results;
}
} }

View File

@ -112,21 +112,21 @@ PARSED_TAGS = {
'v4h': 'Yodan verb with "hu/fu" ending (archaic)', 'v4h': 'Yodan verb with "hu/fu" ending (archaic)',
'v4r': 'Yodan verb with "ru" ending (archaic)', 'v4r': 'Yodan verb with "ru" ending (archaic)',
'v5': 'Godan verb (not completely classified)', 'v5': 'Godan verb (not completely classified)',
# 'v5aru': 'Godan verb - -aru special class', 'v5aru': 'Godan verb - -aru special class',
# 'v5b': 'Godan verb with "bu" ending', 'v5b': 'Godan verb with "bu" ending',
# 'v5g': 'Godan verb with "gu" ending', 'v5g': 'Godan verb with "gu" ending',
# 'v5k': 'Godan verb with "ku" ending', 'v5k': 'Godan verb with "ku" ending',
# 'v5k-s': 'Godan verb - iku/yuku special class', 'v5k-s': 'Godan verb - iku/yuku special class',
# 'v5m': 'Godan verb with "mu" ending', 'v5m': 'Godan verb with "mu" ending',
# 'v5n': 'Godan verb with "nu" ending', 'v5n': 'Godan verb with "nu" ending',
# 'v5r': 'Godan verb with "ru" ending', 'v5r': 'Godan verb with "ru" ending',
# 'v5r-i': 'Godan verb with "ru" ending (irregular verb)', 'v5r-i': 'Godan verb with "ru" ending (irregular verb)',
# 'v5s': 'Godan verb with "su" ending', 'v5s': 'Godan verb with "su" ending',
# 'v5t': 'Godan verb with "tsu" ending', 'v5t': 'Godan verb with "tsu" ending',
# 'v5u': 'Godan verb with "u" ending', 'v5u': 'Godan verb with "u" ending',
# 'v5u-s': 'Godan verb with "u" ending (special class)', 'v5u-s': 'Godan verb with "u" ending (special class)',
# 'v5uru': 'Godan verb - uru old class verb (old form of Eru)', 'v5uru': 'Godan verb - uru old class verb (old form of Eru)',
# 'v5z': 'Godan verb with "zu" ending', 'v5z': 'Godan verb with "zu" ending',
'vi': 'intransitive verb', 'vi': 'intransitive verb',
'vk': 'kuru verb - special class', 'vk': 'kuru verb - special class',
'vn': 'irregular nu verb', 'vn': 'irregular nu verb',
@ -167,16 +167,6 @@ def parse_kanji_dic(path):
return results return results
def fixup_godan_verbs(tags):
results = []
for tag in tags:
if tag.startswith('v5'):
tag = 'v5'
results.append(tag)
return set(results)
def parse_edict(path): def parse_edict(path):
results = [] results = []
for line in load_definitions(path): for line in load_definitions(path):
@ -194,7 +184,6 @@ def parse_edict(path):
dfn_match = re.search(r'^((?:\((?:[\w\-\,\:]*)*\)\s*)*)(.*)$', dfn) dfn_match = re.search(r'^((?:\((?:[\w\-\,\:]*)*\)\s*)*)(.*)$', dfn)
tags_raw = set(filter(None, re.split(r'[\s\(\),]', dfn_match.group(1)))) tags_raw = set(filter(None, re.split(r'[\s\(\),]', dfn_match.group(1))))
tags_raw = fixup_godan_verbs(tags_raw)
tags_raw = tags_raw.intersection(set(PARSED_TAGS.keys())) tags_raw = tags_raw.intersection(set(PARSED_TAGS.keys()))
tags = tags.union(tags_raw) tags = tags.union(tags_raw)