Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

When parsing fields ignore unknown flags

Browse Source
This commit is contained in:
Kovid Goyal 2014-03-30 19:47:26 +05:30
parent 4bede79eae
commit b07752e389
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/calibre/ebooks/docx/fields.py
View File

@ -35,6 +35,7 @@ scanner = re.Scanner([
(r'\s+', None), (r'\s+', None),
], flags=re.DOTALL) ], flags=re.DOTALL)
null = object()
def parse_hyperlink(raw, log): def parse_hyperlink(raw, log):
ans = {} ans = {}
@ -43,7 +44,7 @@ def parse_hyperlink(raw, log):
for token, token_type in scanner.scan(raw)[0]: for token, token_type in scanner.scan(raw)[0]:
token = token.replace('\x01', '\\').replace('\x02', '"') token = token.replace('\x01', '\\').replace('\x02', '"')
if token_type is FLAG: if token_type is FLAG:
last_option = {'l':'anchor', 'm':'image-map', 'n':'target', 'o':'title', 't':'target'}.get(token[1], None) last_option = {'l':'anchor', 'm':'image-map', 'n':'target', 'o':'title', 't':'target'}.get(token[1], null)
if last_option is not None: if last_option is not None:
ans[last_option] = None ans[last_option] = None
elif token_type is WORD: elif token_type is WORD:
@ -52,6 +53,7 @@ def parse_hyperlink(raw, log):
else: else:
ans[last_option] = token ans[last_option] = token
last_option = None last_option = None
ans.pop(null, None)
return ans return ans
def parse_xe(raw, log): def parse_xe(raw, log):
@ -61,7 +63,7 @@ def parse_xe(raw, log):
for token, token_type in scanner.scan(raw)[0]: for token, token_type in scanner.scan(raw)[0]:
token = token.replace('\x01', '\\').replace('\x02', '"') token = token.replace('\x01', '\\').replace('\x02', '"')
if token_type is FLAG: if token_type is FLAG:
last_option = {'b':'bold', 'i':'italic', 'f':'entry_type', 'r':'page_range_bookmark', 't':'page_number_text', 'y':'yomi'}.get(token[1], None) last_option = {'b':'bold', 'i':'italic', 'f':'entry_type', 'r':'page_range_bookmark', 't':'page_number_text', 'y':'yomi'}.get(token[1], null)
if last_option is not None: if last_option is not None:
ans[last_option] = None ans[last_option] = None
elif token_type is WORD: elif token_type is WORD:
@ -70,6 +72,7 @@ def parse_xe(raw, log):
else: else:
ans[last_option] = token ans[last_option] = token
last_option = None last_option = None
ans.pop(null, None)
return ans return ans
class Fields(object): class Fields(object):
@ -142,6 +145,7 @@ def test_parse_fields():
ae(r'www.calibre-ebook.com', {'url':'www.calibre-ebook.com'}) ae(r'www.calibre-ebook.com', {'url':'www.calibre-ebook.com'})
ae(r'www.calibre-ebook.com \t target \o tt', {'url':'www.calibre-ebook.com', 'target':'target', 'title': 'tt'}) ae(r'www.calibre-ebook.com \t target \o tt', {'url':'www.calibre-ebook.com', 'target':'target', 'title': 'tt'})
ae(r'"c:\\Some Folder"', {'url': 'c:\\Some Folder'}) ae(r'"c:\\Some Folder"', {'url': 'c:\\Some Folder'})
ae(r'xxxx \y yyyy', {'url': 'xxxx'})
def test_xe(self): def test_xe(self):
ae = lambda x, y: self.assertEqual(parse_xe(x, None), y) ae = lambda x, y: self.assertEqual(parse_xe(x, None), y)