openlp-core team mailing list archive

[Jon Tibble <meths@xxxxxxxxxxxxxx>]

Jon Tibble has proposed merging lp:~meths/openlp/trivialfixes into lp:openlp.

Requested reviews:
  OpenLP Core (openlp-core)

For more details, see:
https://code.launchpad.net/~meths/openlp/trivialfixes/+merge/47959

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.
-- 
https://code.launchpad.net/~meths/openlp/trivialfixes/+merge/47959
Your team OpenLP Core is requested to review the proposed merge of lp:~meths/openlp/trivialfixes into lp:openlp.

=== modified file 'openlp/plugins/bibles/lib/csvbible.py'
--- openlp/plugins/bibles/lib/csvbible.py	2011-01-27 16:55:49 +0000
+++ openlp/plugins/bibles/lib/csvbible.py	2011-01-31 02:48:54 +0000
@@ -50,14 +50,17 @@
         ...
         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 @@
             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')

=== modified file 'openlp/plugins/bibles/lib/http.py'
--- openlp/plugins/bibles/lib/http.py	2011-01-15 19:24:50 +0000
+++ openlp/plugins/bibles/lib/http.py	2011-01-31 02:48:54 +0000
@@ -210,7 +210,8 @@
         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 @@
         """
         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 @@
     ``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 @@
     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: