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

Another unicode bug squashed and improved <pre> handling

Browse Source
This commit is contained in:
Kovid Goyal 2007-06-29 15:42:11 +00:00
parent c6c84a45b5
commit e2a32e3198
2 changed files with 6 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/libprs500/__init__.py
View File

@ -13,7 +13,7 @@
## with this program; if not, write to the Free Software Foundation, Inc., ## with this program; if not, write to the Free Software Foundation, Inc.,
## 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. ## 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
''' E-book management software''' ''' E-book management software'''
__version__ = "0.3.61" __version__ = "0.3.62"
__docformat__ = "epytext" __docformat__ = "epytext"
__author__ = "Kovid Goyal <kovid@kovidgoyal.net>" __author__ = "Kovid Goyal <kovid@kovidgoyal.net>"
__appname__ = 'libprs500' __appname__ = 'libprs500'

12
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -215,8 +215,6 @@ class Span(_Span):
attrs.pop('fontfacename') attrs.pop('fontfacename')
_Span.__init__(self, text=src, **attrs) _Span.__init__(self, text=src, **attrs)
class HTMLConverter(object): class HTMLConverter(object):
SELECTOR_PAT = re.compile(r"([A-Za-z0-9\-\_\:\.]+[A-Za-z0-9\-\_\:\.\s\,]*)\s*\{([^\}]*)\}") SELECTOR_PAT = re.compile(r"([A-Za-z0-9\-\_\:\.]+[A-Za-z0-9\-\_\:\.\s\,]*)\s*\{([^\}]*)\}")
PAGE_BREAK_PAT = re.compile(r'page-break-(?:after|before)\s*:\s*(\w+)', re.IGNORECASE) PAGE_BREAK_PAT = re.compile(r'page-break-(?:after|before)\s*:\s*(\w+)', re.IGNORECASE)
@ -230,7 +228,7 @@ class HTMLConverter(object):
lambda match: match.group().replace('<!--', '').replace('-->', '')), lambda match: match.group().replace('<!--', '').replace('-->', '')),
# remove <p> tags from within <a> tags # remove <p> tags from within <a> tags
(re.compile(r'<a.*?>(.*?)</a\s*>', re.DOTALL|re.IGNORECASE), (re.compile(r'<a.*?>(.*?)</a\s*>', re.DOTALL|re.IGNORECASE),
lambda match: re.compile(r'<.*?p.*?>', re.IGNORECASE).sub('', match.group())), lambda match: re.compile(r'<\s*?p.*?>', re.IGNORECASE).sub('', match.group())),
] ]
# Fix Baen markup # Fix Baen markup
BAEN_SANCTIFY = [(re.compile(r'<\s*[Aa]\s+id="p[0-9]+"\s+name="p[0-9]+"\s*>\s*<\/[Aa]>'), BAEN_SANCTIFY = [(re.compile(r'<\s*[Aa]\s+id="p[0-9]+"\s+name="p[0-9]+"\s*>\s*<\/[Aa]>'),
@ -551,9 +549,9 @@ class HTMLConverter(object):
cwd = os.getcwd() cwd = os.getcwd()
for link in self.links: for link in self.links:
para, tag = link.para, link.tag para, tag = link.para, link.tag
text = self.get_text(tag) text = self.get_text(tag, 1000)
# Needed for TOC entries due to bug in LRF # Needed for TOC entries due to bug in LRF
ascii_text = text.decode('utf8', 'replace').encode('ascii', 'replace') ascii_text = text.encode('ascii', 'replace')
if not text: if not text:
text = 'Link' text = 'Link'
img = tag.find('img') img = tag.find('img')
@ -996,7 +994,7 @@ class HTMLConverter(object):
lines = src.split('\n') lines = src.split('\n')
for line in lines: for line in lines:
try: try:
self.current_para.append(Span(line, tag_css, self.memory, self.profile.dpi, self.fonts)) self.current_para.append(line)
self.current_para.CR() self.current_para.CR()
except ConversionError: except ConversionError:
pass pass
@ -1375,7 +1373,7 @@ def console_query(dirpath, candidate, docs):
def get_path(path, query=console_query): def get_path(path, query=console_query):
path = os.path.abspath(os.path.expanduser(path)) path = os.path.abspath(os.path.expanduser(path))
ext = os.path.splitext(path)[1][1:].lower() ext = os.path.splitext(path)[1][1:].lower()
if ext in ['htm', 'html', 'xhtml']: if ext in ['htm', 'html', 'xhtml', 'php']:
return None, path return None, path
dirpath = mkdtemp('','html2lrf') dirpath = mkdtemp('','html2lrf')
extract(path, dirpath) extract(path, dirpath)