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

Don't detect BlockSpace elements as first element of a page.

Browse Source 
Skip over hrefs that are in weird encodings.
This commit is contained in:
Kovid Goyal 2007-05-12 02:52:26 +00:00
parent 76c0aeb57c
commit 69f20f634d
1 changed files with 18 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
src/libprs500/lrf/html/convert_from.py
View File

@ -400,6 +400,10 @@ class HTMLConverter(object):
return prop return prop
def parse_file(self): def parse_file(self):
def get_valid_block(page):
for item in page.contents:
if isinstance(item, (TextBlock, ImageBlock, RuledLine)):
return item
previous = self.book.last_page() previous = self.book.last_page()
self.current_page = self.book.create_page() self.current_page = self.book.create_page()
self.current_block = self.book.create_text_block() self.current_block = self.book.create_text_block()
@ -418,7 +422,7 @@ class HTMLConverter(object):
if not self.top.parent: if not self.top.parent:
if not previous: if not previous:
self.top = self.book.pages()[0].contents[0] self.top = get_valid_block(self.book.pages()[0])
else: else:
found = False found = False
for page in self.book.pages(): for page in self.book.pages():
@ -426,7 +430,9 @@ class HTMLConverter(object):
found = True found = True
continue continue
if found: if found:
self.top = page.contents[0] self.top = get_valid_block(page)
if not self.top:
continue
break break
if not self.top.parent: if not self.top.parent:
raise ConversionError, 'Could not parse ' + self.file_name raise ConversionError, 'Could not parse ' + self.file_name
@ -455,7 +461,7 @@ class HTMLConverter(object):
ans, found, page = None, False, bs.parent ans, found, page = None, False, bs.parent
for item in page.contents: for item in page.contents:
if found: if found:
if isinstance(item, (TextBlock, ImageBlock)): if isinstance(item, (TextBlock, RuledLine, ImageBlock)):
ans = item ans = item
break break
if item == bs: if item == bs:
@ -464,7 +470,7 @@ class HTMLConverter(object):
if not ans: if not ans:
for i in range(len(page.contents)-1, -1, -1): for i in range(len(page.contents)-1, -1, -1):
if isinstance(page.contents[i], (TextBlock, ImageBlock)): if isinstance(page.contents[i], (TextBlock, RuledLine, ImageBlock)):
ans = page.contents[i] ans = page.contents[i]
break break
@ -497,8 +503,11 @@ class HTMLConverter(object):
cb = CharButton(jb, text=self.get_text(tag)) cb = CharButton(jb, text=self.get_text(tag))
para.contents = [] para.contents = []
para.append(cb) para.append(cb)
elif self.link_level < self.max_link_levels: elif self.link_level < self.max_link_levels:
if not os.access(path, os.R_OK): try: # os.access raises Exceptions in path has null bytes
if not os.access(path.encode('utf8', 'replace'), os.R_OK):
raise Exception()
except Exception:
if self.verbose: if self.verbose:
print "Skipping", link print "Skipping", link
continue continue
@ -641,10 +650,12 @@ class HTMLConverter(object):
if test.startswith('margin') or test.startswith('text') or \ if test.startswith('margin') or test.startswith('text') or \
'padding' in test or 'border' in test or 'page-break' in test \ 'padding' in test or 'border' in test or 'page-break' in test \
or test.startswith('mso') or test.startswith('background')\ or test.startswith('mso') or test.startswith('background')\
or test in ['color', 'display', \ or test.startswith('line') or test in ['color', 'display', \
'letter-spacing', 'letter-spacing',
'font-variant']: 'font-variant']:
css.pop(key) css.pop(key)
if self.verbose:
print 'Ignoring CSS key:', key
return css return css
def end_current_para(self): def end_current_para(self):
@ -730,7 +741,6 @@ class HTMLConverter(object):
else: else:
target = BlockSpace() target = BlockSpace()
self.current_page.append(target) self.current_page.append(target)
self.targets[tag['name']] = target self.targets[tag['name']] = target
elif tag.has_key('href') and not self.link_exclude.match(tag['href']): elif tag.has_key('href') and not self.link_exclude.match(tag['href']):
purl = urlparse(tag['href']) purl = urlparse(tag['href'])