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

Fix handling of img in <a href> tags. Remove show-broken-links option.

Browse Source
This commit is contained in:
Kovid Goyal 2007-05-22 18:16:30 +00:00
parent 7056e35aff
commit 7329106b99
1 changed files with 9 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -247,7 +247,7 @@ class HTMLConverter(object):
chapter_regex=re.compile('chapter|book|appendix', re.IGNORECASE), chapter_regex=re.compile('chapter|book|appendix', re.IGNORECASE),
link_exclude=re.compile('$'), link_exclude=re.compile('$'),
page_break=re.compile('h[12]', re.IGNORECASE), page_break=re.compile('h[12]', re.IGNORECASE),
profile=PRS500_PROFILE, hide_broken_links=False, profile=PRS500_PROFILE,
disable_autorotation=False): disable_autorotation=False):
''' '''
Convert HTML file at C{path} and add it to C{book}. After creating Convert HTML file at C{path} and add it to C{book}. After creating
@ -283,7 +283,7 @@ class HTMLConverter(object):
tags if no page-breaks are found and no chapter headings tags if no page-breaks are found and no chapter headings
are detected. are detected.
@param profile: Defines the geometry of the display device @param profile: Defines the geometry of the display device
@param hide_broken_links: Don't display broken links @param disable_autorotation: Don't autorotate very wide images
''' '''
# Defaults for various formatting tags # Defaults for various formatting tags
self.css = dict( self.css = dict(
@ -330,7 +330,6 @@ class HTMLConverter(object):
self.book = book #: The Book object representing a BBeB book self.book = book #: The Book object representing a BBeB book
self.is_root = is_root #: Are we converting the root HTML file self.is_root = is_root #: Are we converting the root HTML file
self.lstrip_toggle = False #: If true the next add_text call will do an lstrip self.lstrip_toggle = False #: If true the next add_text call will do an lstrip
self.hide_broken_links = hide_broken_links
path = os.path.abspath(path) path = os.path.abspath(path)
os.chdir(os.path.dirname(path)) os.chdir(os.path.dirname(path))
self.file_name = os.path.basename(path) self.file_name = os.path.basename(path)
@ -486,6 +485,9 @@ class HTMLConverter(object):
if isinstance(c, NavigableString): if isinstance(c, NavigableString):
text += str(c) text += str(c)
elif isinstance(c, Tag): elif isinstance(c, Tag):
if c.name.lower() == 'img' and c.has_key('alt'):
text += c['alt']
return text
text += self.get_text(c) text += self.get_text(c)
return text return text
@ -545,9 +547,6 @@ class HTMLConverter(object):
text = img['alt'] text = img['alt']
except KeyError: except KeyError:
pass pass
if self.hide_broken_links:
para.contents = []
para.append(_Span(text=text))
purl = urlparse(link.tag['href']) purl = urlparse(link.tag['href'])
if purl[1]: # Not a link to a file on the local filesystem if purl[1]: # Not a link to a file on the local filesystem
continue continue
@ -584,7 +583,6 @@ class HTMLConverter(object):
chapter_regex=self.chapter_regex, chapter_regex=self.chapter_regex,
link_exclude=self.link_exclude, link_exclude=self.link_exclude,
page_break=self.page_break, page_break=self.page_break,
hide_broken_links=self.hide_broken_links,
disable_autorotation=self.disable_autorotation) disable_autorotation=self.disable_autorotation)
HTMLConverter.processed_files[path] = self.files[path] HTMLConverter.processed_files[path] = self.files[path]
except Exception: except Exception:
@ -911,7 +909,10 @@ class HTMLConverter(object):
['png', 'jpg', 'bmp', 'jpeg']: ['png', 'jpg', 'bmp', 'jpeg']:
self.process_image(path, tag_css) self.process_image(path, tag_css)
else: else:
self.add_text(self.get_text(tag), tag_css) text = self.get_text(tag)
if not text:
text = "Link"
self.add_text(text, tag_css)
self.links.append(HTMLConverter.Link(self.current_para.contents[-1], tag)) self.links.append(HTMLConverter.Link(self.current_para.contents[-1], tag))
elif tagname == 'img': elif tagname == 'img':
if tag.has_key('src') and os.access(unquote(tag['src']), os.R_OK): if tag.has_key('src') and os.access(unquote(tag['src']), os.R_OK):
@ -1163,7 +1164,6 @@ def process_file(path, options):
chapter_detection=options.chapter_detection, chapter_detection=options.chapter_detection,
chapter_regex=re.compile(options.chapter_regex, re.IGNORECASE), chapter_regex=re.compile(options.chapter_regex, re.IGNORECASE),
link_exclude=re.compile(le), page_break=pb, link_exclude=re.compile(le), page_break=pb,
hide_broken_links=not options.show_broken_links,
disable_autorotation=options.disable_autorotation) disable_autorotation=options.disable_autorotation)
conv.process_links() conv.process_links()
oname = options.output oname = options.output
@ -1270,12 +1270,6 @@ def parse_options(argv=None, cli=True):
prepro = parser.add_option_group('PREPROCESSING OPTIONS') prepro = parser.add_option_group('PREPROCESSING OPTIONS')
prepro.add_option('--baen', action='store_true', default=False, dest='baen', prepro.add_option('--baen', action='store_true', default=False, dest='baen',
help='''Preprocess Baen HTML files to improve generated LRF.''') help='''Preprocess Baen HTML files to improve generated LRF.''')
debug = None
for g in parser.option_groups:
if g.title == 'DEBUG OPTIONS':
debug = g
debug.add_option('--show-broken-links', dest='show_broken_links', action='store_true',
default=False, help='''Show the href of broken links in generated LRF''')
options, args = parser.parse_args(args=argv) options, args = parser.parse_args(args=argv)
if len(args) != 1: if len(args) != 1:
if cli: if cli: