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

Fix BG Chinese bible (Bug #706211) 

Fix CSV import to accept the same files V1 did and cater to "not quite" ASCII encoding generated by cp1252 files.

bzr-revno: 1255
Fixes: https://launchpad.net/bugs/706211
This commit is contained in:
Jon Tibble 2011-01-31 18:17:10 +00:00 committed by Tim Bentley
parent 5cb6fd12a6 250107073e
commit 90b1205e5b
2 changed files with 32 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
openlp/plugins/bibles/lib/csvbible.py
View File

@ -50,14 +50,17 @@ The format of the books file is:
...
40,2,Matthew,Matt
The format of the verses file is:
There are two acceptable formats of the verses file. They are:
<book_id>,<chapter_number>,<verse_number>,<verse_text>
or
<book_name>,<chapter_number>,<verse_number>,<verse_text>
For example:
1,1,1,"In the beginning God created the heaven and the earth."
1,1,2,"And the earth was without form, and void; and darkness...."
or
"Genesis",1,2,"And the earth was without form, and void; and...."
All CSV files are expected to use a comma (',') as the delimeter and double
quotes ('"') as the quote symbol.
@ -172,15 +175,22 @@ class CSVBible(BibleDB):
for line in verse_reader:
if self.stop_import_flag:
break
if book_ptr != book_list[int(line[0])]:
book = self.get_book(book_list[int(line[0])])
try:
line_book = book_list[int(line[0])]
except ValueError:
line_book = unicode(line[0], details['encoding'])
if book_ptr != line_book:
book = self.get_book(line_book)
book_ptr = book.name
self.wizard.incrementProgressBar(unicode(translate(
'BibleDB.Wizard', 'Importing verses from %s...',
'Importing verses from <book name>...')) % book.name)
self.session.commit()
self.create_verse(book.id, line[1], line[2],
unicode(line[3], details['encoding']))
try:
verse_text = unicode(line[3], details['encoding'])
except UnicodeError:
verse_text = unicode(line[3], u'cp1252')
self.create_verse(book.id, line[1], line[2], verse_text)
self.wizard.incrementProgressBar(translate('BibleDB.Wizard',
'Importing verses... done.'))
Receiver.send_message(u'openlp_process_events')

20
openlp/plugins/bibles/lib/http.py
View File

@ -210,7 +210,8 @@ class BGExtract(object):
cleaner = [(re.compile('&nbsp;|<br />|\'\+\''), lambda match: '')]
soup = get_soup_for_bible_ref(
u'http://www.biblegateway.com/passage/?%s' % url_params,
cleaner=cleaner)
pre_parse_regex=r'<meta name.*?/>', pre_parse_substitute='',
cleaner=cleaner)
if not soup:
return None
Receiver.send_message(u'openlp_process_events')
@ -499,7 +500,8 @@ class HTTPBible(BibleDB):
"""
return HTTPBooks.get_verse_count(book, chapter)
def get_soup_for_bible_ref(reference_url, header=None, cleaner=None):
def get_soup_for_bible_ref(reference_url, header=None, pre_parse_regex=None,
pre_parse_substitute=None, cleaner=None):
"""
Gets a webpage and returns a parsed and optionally cleaned soup or None.
@ -509,6 +511,13 @@ def get_soup_for_bible_ref(reference_url, header=None, cleaner=None):
``header``
An optional HTTP header to pass to the bible web server.
``pre_parse_regex``
A regular expression to run on the webpage. Allows manipulation of the
webpage before passing to BeautifulSoup for parsing.
``pre_parse_substitute``
The text to replace any matches to the regular expression with.
``cleaner``
An optional regex to use during webpage parsing.
"""
@ -518,12 +527,15 @@ def get_soup_for_bible_ref(reference_url, header=None, cleaner=None):
if not page:
send_error_message(u'download')
return None
page_source = page.read()
if pre_parse_regex and pre_parse_substitute is not None:
page_source = re.sub(pre_parse_regex, pre_parse_substitute, page_source)
soup = None
try:
if cleaner:
soup = BeautifulSoup(page, markupMassage=cleaner)
soup = BeautifulSoup(page_source, markupMassage=cleaner)
else:
soup = BeautifulSoup(page)
soup = BeautifulSoup(page_source)
except HTMLParseError:
log.exception(u'BeautifulSoup could not parse the bible page.')
if not soup: