def write_csv(filename, entries):
uw = UnicodeWriter(open(filename, 'w'))
N = len(entries)
sys.stderr.write(HIDE_CURSOR)
for j, e in enumerate(e for e in entries
if e.volume([1, 2]) or e.civil_equivalent.startswith(u'!')):
note = u'Поиск похожих примеров [ %s%% ] %s\r' % (
int(j / float(N) * 100), e.civil_equivalent + ERASE_LINEEND)
sys.stderr.write(note.encode('utf-8'))
ecolumn = e.civil_equivalent + {1: u'¹', 2: u'²'}.get(e.homonym_order, u'')
all_examples = e.all_examples()
example_matches = []
for i in range(len(all_examples) - 1):
ex1, ex2 = all_examples[i:i+2]
if levenshtein_distance(ex1.ts_example, ex2.ts_example) < MAX_DISTANCE:
example_matches.append((ex1, ex2))
if example_matches:
uw.writerow((ecolumn, '', ''))
for match in example_matches:
uw.writerow(('', match[0].example, match[0].address_text))
uw.writerow(('', match[1].example, match[1].address_text))
uw.writerow(('','',''))
sys.stderr.write(ERASE_LINE + SHOW_CURSOR)
uw.stream.close()
def write_csv(filename, examples):
uw = UnicodeWriter(open(filename, 'w'))
NON_MARK_CHARS = ur'[\s\ \u00A0,0-9\.;:\-\u2011\!\(\)\[\]\?—–«»…]+'
register = {}
for e in (e for e in examples if e.host_entry.volume(1)):
for mark in re.split(NON_MARK_CHARS, e.address_text):
if mark in register:
register[mark] = (register[mark][0] + 1, e)
else:
register[mark] = (1, e)
for mark, (number, e) in sorted(register.items()):
row = (
mark,
str(number),
e.address_text,
str(e.id),
e.host_entry.civil_equivalent,
)
uw.writerow(row)
uw.stream.close()
def write_csv(filename, entries):
uw = UnicodeWriter(open(filename, 'w'))
for e in (e for e in entries if e.first_volume):
ecolumn = e.civil_equivalent + {1: u'¹', 2: u'²'}.get(e.homonym_order, u'')
for m in list(e.meanings) + list(e.metaph_meanings):
meaning = m.meaning.strip()
gloss = m.gloss.strip()
if meaning or gloss:
uw.writerow((str(m.id), ecolumn, u'%s ⏹ %s' % (meaning, gloss)))
if ecolumn:
ecolumn = u''
for cm in m.child_meanings:
meaning = cm.meaning.strip()
gloss = cm.gloss.strip()
if meaning or gloss:
row = (str(cm.id), ecolumn, u'• %s ⏹ %s' % (meaning, gloss))
uw.writerow(row)
if ecolumn:
ecolumn = u''
uw.stream.close()
#!/usr/bin/env python
# coding: utf-8
import os
import sys
import django
sys.path.append(
os.path.dirname(os.path.dirname(
os.path.abspath(__file__))))
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'slavdict.settings')
django.setup()
from slavdict.dictionary.models import CollocationGroup
from slavdict.unicode_csv import UnicodeWriter
uw = UnicodeWriter(open('cg_meanings.csv', 'w'))
for cg in (cg for cg in CollocationGroup.objects.all()
if cg.host_entry.first_volume):
cgcolumn = u'; '.join(c.collocation for c in cg.collocations)
for m in list(cg.meanings) + list(cg.metaph_meanings):
meaning = m.meaning.strip()
gloss = m.gloss.strip()
if meaning or gloss:
uw.writerow((str(m.id), cgcolumn, u'%s ⏹ %s' % (meaning, gloss)))
if cgcolumn:
cgcolumn = u''
