raoul/openlp
1
0
Fork 0
forked from openlp/openlp
Code Issues Pull Requests Projects Releases Wiki Activity

changes from review (cosmetic & regex performance)

Browse Source
This commit is contained in:
Benny 2011-07-05 12:50:55 +02:00
parent ae8ac35d2c
commit 6436b05240
1 changed files with 30 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
openlp/plugins/songs/lib/ewimport.py
View File

@ -39,18 +39,25 @@ from openlp.plugins.songs.lib import VerseType
from openlp.plugins.songs.lib import retrieve_windows_encoding from openlp.plugins.songs.lib import retrieve_windows_encoding
from songimport import SongImport from songimport import SongImport
RTF_STRIPPING_REGEX = re.compile(r'\{\\tx[^}]*\}')
# regex: at least two newlines, can have spaces between them
SLIDE_BREAK_REGEX = re.compile(r'\n *?\n[\n ]*')
NUMBER_REGEX = re.compile(r'[0-9]+')
NOTE_REGEX = re.compile(r'\(.*?\)')
def strip_rtf(blob, encoding): def strip_rtf(blob, encoding):
depth = 0 depth = 0
control = False control = False
clear_text = [] clear_text = []
control_word = [] control_word = []
# workaround for \tx bug: remove one pair of curly braces if \tx is encountered # workaround for \tx bug: remove one pair of curly braces
p = re.compile(r'\{\\tx[^}]*\}') # if \tx is encountered
m = p.search(blob) match = RTF_STRIPPING_REGEX.search(blob)
if m: if match:
# start and end indices of match are curly braces - filter them out # start and end indices of match are curly braces - filter them out
blob = ''.join([blob[i] for i in xrange(len(blob)) if i != m.start() and i !=m.end()]) blob = ''.join([blob[i] for i in xrange(len(blob))
if i != match.start() and i !=match.end()])
for c in blob: for c in blob:
if control: if control:
@ -267,17 +274,16 @@ class EasyWorshipSongImport(SongImport):
self.add_author(author_name.strip()) self.add_author(author_name.strip())
if words: if words:
# Format the lyrics # Format the lyrics
words = strip_rtf(words, self.encoding) # TODO: convert rtf to display tags? words = strip_rtf(words, self.encoding)
# regex: at least two newlines, with zero or more space characters between them
p = re.compile(r'\n *?\n[\n ]*')
verse_type = VerseType.Tags[VerseType.Verse] verse_type = VerseType.Tags[VerseType.Verse]
for verse in p.split(words): for verse in SLIDE_BREAK_REGEX.split(words):
verse = verse.strip() verse = verse.strip()
if len(verse) == 0: if len(verse) == 0:
continue continue
verse_split = verse.split(u'\n', 1) verse_split = verse.split(u'\n', 1)
first_line_is_tag = False first_line_is_tag = False
# ew tags: verse, chorus, pre-chorus, bridge, tag, intro, ending, slide # EW tags: verse, chorus, pre-chorus, bridge, tag,
# intro, ending, slide
for type in VerseType.Names+['tag', 'slide']: for type in VerseType.Names+['tag', 'slide']:
type = type.lower() type = type.lower()
ew_tag = verse_split[0].strip().lower() ew_tag = verse_split[0].strip().lower()
@ -287,27 +293,27 @@ class EasyWorshipSongImport(SongImport):
verse_type = VerseType.Tags[VerseType.Other] verse_type = VerseType.Tags[VerseType.Other]
first_line_is_tag = True first_line_is_tag = True
number_found = False number_found = False
if len(ew_tag) > len(type): # tag is followed by number and/or note # check if tag is followed by number and/or note
p = re.compile(r'[0-9]+') if len(ew_tag) > len(type):
m = re.search(p, ew_tag) match = NUMBER_REGEX.search(ew_tag)
if m: if match:
number = m.group() number = match.group()
verse_type +=number verse_type +=number
number_found = True number_found = True
match = NOTE_REGEX.search(ew_tag)
p = re.compile(r'\(.*?\)') if match:
m = re.search(p, ew_tag) self.comments += ew_tag + u'\n'
if m:
self.comments += ew_tag+'\n'
if not number_found: if not number_found:
verse_type += '1' verse_type += u'1'
break break
self.add_verse( self.add_verse(
verse_split[-1].strip() if first_line_is_tag else verse, verse_split[-1].strip() if first_line_is_tag else verse,
verse_type) verse_type)
if len(self.comments) > 5: if len(self.comments) > 5:
self.comments += unicode(translate('SongsPlugin.EasyWorshipSongImport', self.comments += unicode(
'\n[above are Song Tags with notes imported from EasyWorship]')) translate('SongsPlugin.EasyWorshipSongImport',
'\n[above are Song Tags with notes imported from \
EasyWorship]'))
if self.stop_import_flag: if self.stop_import_flag:
break break
if not self.finish(): if not self.finish():