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

r1341

This commit is contained in:
Tim Bentley 2011-02-27 06:59:09 +00:00
parent d0520b739c ccfb472aa6
commit 60520315a7
2 changed files with 25 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
openlp/plugins/bibles/lib/http.py
View File

@ -35,7 +35,7 @@ import socket
import urllib
from HTMLParser import HTMLParseError
from BeautifulSoup import BeautifulSoup, NavigableString
from BeautifulSoup import BeautifulSoup, NavigableString, Tag
from openlp.core.lib import Receiver, translate
from openlp.core.lib.ui import critical_error_message_box
@ -221,21 +221,14 @@ class BGExtract(object):
crossrefs = soup.findAll(u'sup', u'xref')
if crossrefs:
[crossref.extract() for crossref in crossrefs]
headings = soup.findAll(u'h5')
if headings:
[heading.extract() for heading in headings]
cleanup = [(re.compile('\s+'), lambda match: ' ')]
verses = BeautifulSoup(str(soup), markupMassage=cleanup)
content = verses.find(u'div', u'result-text-style-normal')
if not content:
content = verses.find(u'div', u'result-text-style-rtl-serif')
if not content:
log.debug(u'No content found in the BibleGateway response.')
send_error_message(u'parse')
return None
verse_count = len(verses.findAll(u'sup', u'versenum'))
found_count = 0
verse_list = {}
while found_count < verse_count:
content = content.findNext(u'sup', u'versenum')
raw_verse_num = content.next
for verse in verses(u'sup', u'versenum'):
raw_verse_num = verse.next
clean_verse_num = 0
# Not all verses exist in all translations and may or may not be
# represented by a verse number. If they are not fine, if they are
@ -248,9 +241,22 @@ class BGExtract(object):
log.exception(u'Illegal verse number in %s %s %s:%s',
version, bookname, chapter, unicode(raw_verse_num))
if clean_verse_num:
raw_verse_text = raw_verse_num.next
verse_list[clean_verse_num] = unicode(raw_verse_text)
found_count += 1
verse_text = raw_verse_num.next
part = raw_verse_num.next.next
while not (isinstance(part, Tag) and part.attrMap and
part.attrMap[u'class'] == u'versenum'):
# While we are still in the same verse grab all the text.
if isinstance(part, NavigableString):
verse_text = verse_text + part
if isinstance(part.next, Tag) and part.next.name == u'div':
# Run out of verses so stop.
break
part = part.next
verse_list[clean_verse_num] = unicode(verse_text)
if not verse_list:
log.debug(u'No content found in the BibleGateway response.')
send_error_message(u'parse')
return None
return SearchResults(bookname, chapter, verse_list)

5
openlp/plugins/songs/lib/foilpresenterimport.py
View File

@ -314,14 +314,15 @@ class FoilPresenter(object):
i = 1
else:
i = 1
author_temp = []
for author in strings:
temp = re.split(u',(?=\D{2})|(?<=\D),|\/(?=\D{3,})|(?<=\D);',
author)
for tempx in temp:
author_temp.append(tempx)
for author in author_temp:
regex = u'^[\/,;\-\s]+|[\/,;\-\s]+$|'\
'\s*[0-9]{4}\s*[\-\/]?\s*([0-9]{4})?[\/,;\-\s]*$'
regex = u'^[\/,;\-\s\.]+|[\/,;\-\s\.]+$|'\
'\s*[0-9]{4}\s*[\-\/]?\s*([0-9]{4})?[\/,;\-\s\.]*$'
author = re.compile(regex).sub(u'', author)
author = re.compile(
u'[0-9]{1,2}\.\s?J(ahr)?h\.|um\s*$|vor\s*$').sub(u'',