GitHub/gf-rgl
1
0
Fork 1
mirror of https://github.com/GrammaticalFramework/gf-rgl.git synced 2026-05-27 17:08:54 -06:00
Code Issues Packages Projects Releases Wiki Activity

Hrv: generating morpholex from wiktionary, in progress

Browse Source
This commit is contained in:
Aarne Ranta
2022-10-11 17:43:36 +02:00
parent 14351f2767
commit 8755f9da65
1 changed files with 25 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
src/croatian/wiktionary/extract.py
View File

@@ -210,10 +210,22 @@ def translations(mylang, reflang, lines):
})+'\n') })+'\n')
# write GF lexical entry # write GF lexical entry
def print_gf_code(data): def print_gf_code(data, i):
def prrec(fs, lemma): lemma = list(data.keys())[0]
if fs.get('status') == 'NOFORMS': if any([c in cyrillic for c in lemma]):
return
cats = {
'name': ('PN', 7),
'noun': ('N', 11),
'adj': ('A', 12),
'verb': ('V', 12)
}
pos = data[lemma]['pos']
def prrec(fs, lemma, expected):
if fs.get('status') == 'NOFORMS' or len(fs) != expected:
return '"' + lemma + '"' return '"' + lemma + '"'
else: else:
s = '{' s = '{'
@@ -221,18 +233,13 @@ def print_gf_code(data):
s += f + ' = ' + '"' + str(fs[f]) + '"' + ' ; ' s += f + ' = ' + '"' + str(fs[f]) + '"' + ' ; '
return s[:-3] + '}' # removing last ; return s[:-3] + '}' # removing last ;
cats = {'noun': 'N', 'adv': 'Adv', 'adj': 'A', 'verb': 'V'} if pos in cats:
cat, expected = cats[pos]
lemma = list(data.keys())[0] fun = "'" + lemma + '_' + str(i) + '_' + cat + "'"
if len(data[lemma]['forms']) == expected:
if any([c in cyrillic for c in lemma]): print(' '.join(['fun', fun, ':', cat, ';']))
return print(' '.join(['lin', fun, '=',
'mk'+cat, prrec(data[lemma]['forms'], lemma, expected),';']))
if data[lemma]['pos'] in cats:
cat = cats[data[lemma]['pos']]
fun = lemma + '_' + cat
print(' '.join(['fun', fun, ':', cat, ';']))
print(' '.join(['lin', fun, '=', 'mk'+cat, prrec(data[lemma]['forms'], lemma),';']))
else: else:
pass pass
@@ -248,9 +255,9 @@ def main():
if mode == 'gf': if mode == 'gf':
with open(MORPHO_FINAL_FILE, "r", encoding="utf-8") as lines: with open(MORPHO_FINAL_FILE, "r", encoding="utf-8") as lines:
for line in lines: for line, i in zip(lines, range(100000)):
data = json.loads(line) data = json.loads(line)
print_gf_code(data) print_gf_code(data, i)
with open(WIKTIONARY_FILE, "r", encoding="utf-8") as lines: with open(WIKTIONARY_FILE, "r", encoding="utf-8") as lines:
if mode == 'trans': if mode == 'trans':