Skip to content

Update parse.py with python3 #39

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update parse.py with python3 #39

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 11 additions & 11 deletions parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,9 +81,9 @@ def parse_def(text, definition):


def parse_defs(detail):
detail = re.sub(ur'(\(.{1}\))\[([^倫]{1})\]([^\b\r\n])',r'[\2]\n\1\3', detail)
detail = re.sub(ur'([^\b\n\r])\[([^倫]{1})\]',r'\1\n[\2]', detail)
detail = re.sub(ur'\[([^倫]{1})\]([^\b\r\n])',r'[\1]\n\2', detail)
detail = re.sub(r'(\(.{1}\))\[([^倫]{1})\]([^\b\r\n])',r'[\2]\n\1\3', detail)
detail = re.sub(r'([^\b\n\r])\[([^倫]{1})\]',r'\1\n[\2]', detail)
detail = re.sub(r'\[([^倫]{1})\]([^\b\r\n])',r'[\1]\n\2', detail)
lines = detail.splitlines()
definitions = []
pos = ''
Expand All @@ -92,7 +92,7 @@ def parse_defs(detail):
if not item:
continue
logging.debug('def_item=%s' % item)
m = re.match(ur'\[(.*)\]', item)
m = re.match(r'\[(.*)\]', item)
if m and m.group(1):
pos = m.group(1)
continue
Expand All @@ -111,7 +111,7 @@ def parse_defs(detail):

def associate_to_defs(key, text, defs):
while text:
m = re.match(ur'^((?:\d+\.)*)(.*)', text)
m = re.match(r'^((?:\d+\.)*)(.*)', text)
if not m:
logging.error('bad syntax %s: %s' % (key, text))
return
Expand All @@ -121,10 +121,10 @@ def associate_to_defs(key, text, defs):
if m.group(1) == '':
defs[0][key] = v
else:
for num in re.findall(ur'(\d+)\.', m.group(1)):
for num in re.findall(r'(\d+)\.', m.group(1)):
idx = int(num)
for d in defs:
m1 = re.match(ur'^(\d+)\.(.*)', d['def'])
m1 = re.match(r'^(\d+)\.(.*)', d['def'])
if m1 and m1.group(1):
defIndex = int(m1.group(1))
if idx == defIndex:
Expand Down Expand Up @@ -152,7 +152,7 @@ def parse_heteronym(cells):
heteronym['definitions'] += parse_defs(cells[11].value)

for item in heteronym['definitions']:
item['def'] = re.sub(ur'^\d+\.(.*)', ur'\1', item['def'])
item['def'] = re.sub(r'^\d+\.(.*)', r'\1', item['def'])

basic = dict(
stroke_count=int(cells[5].value),
Expand Down Expand Up @@ -257,16 +257,16 @@ def post_processing():
if not h.get('bopomofo'):
continue
for k in ('bopomofo', 'pinyin'):
if re.match(ur'^\([一二三四五六七八九十]\)', h[k]):
h[k] = re.sub(ur'^\([一二三四五六七八九十]\)', '', h[k])
if re.match(r'^\([一二三四五六七八九十]\)', h[k]):
h[k] = re.sub(r'^\([一二三四五六七八九十]\)', '', h[k])
known_bpmf.add(h['bopomofo'])

# remove <1> from definition
for h in hs:
defs = h['definitions']
defs_new = []
for d in defs:
m = re.match(ur'^(\([一二三四五六七八九十]\))(.+)', d['def'])
m = re.match(r'^(\([一二三四五六七八九十]\))(.+)', d['def'])
if m and re.search(re_bpmf, m.group(2)):
# TODO verify consistency
continue
Expand Down