Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

pep8

Browse Source
This commit is contained in:
Kovid Goyal 2013-05-12 14:38:21 +05:30
parent 32de3c16ea
commit ddbff0f23d
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/calibre/ebooks/oeb/parse_utils.py
View File

@ -44,8 +44,10 @@ META_XP = XPath('/h:html/h:head/h:meta[@http-equiv="Content-Type"]')
def merge_multiple_html_heads_and_bodies(root, log=None): def merge_multiple_html_heads_and_bodies(root, log=None):
heads, bodies = xpath(root, '//h:head'), xpath(root, '//h:body') heads, bodies = xpath(root, '//h:head'), xpath(root, '//h:body')
if not (len(heads) > 1 or len(bodies) > 1): return root if not (len(heads) > 1 or len(bodies) > 1):
for child in root: root.remove(child) return root
for child in root:
root.remove(child)
head = root.makeelement(XHTML('head')) head = root.makeelement(XHTML('head'))
body = root.makeelement(XHTML('body')) body = root.makeelement(XHTML('body'))
for h in heads: for h in heads:
@ -88,7 +90,7 @@ def html5_parse(data, max_nesting_depth=100):
# Check that the asinine HTML 5 algorithm did not result in a tree with # Check that the asinine HTML 5 algorithm did not result in a tree with
# insane nesting depths # insane nesting depths
for x in data.iterdescendants(): for x in data.iterdescendants():
if isinstance(x.tag, basestring) and len(x) is 0: # Leaf node if isinstance(x.tag, basestring) and len(x) is 0: # Leaf node
depth = node_depth(x) depth = node_depth(x)
if depth > max_nesting_depth: if depth > max_nesting_depth:
raise ValueError('html5lib resulted in a tree with nesting' raise ValueError('html5lib resulted in a tree with nesting'
@ -228,7 +230,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
if idx > -1: if idx > -1:
pre = data[:idx] pre = data[:idx]
data = data[idx:] data = data[idx:]
if '<!DOCTYPE' in pre: # Handle user defined entities if '<!DOCTYPE' in pre: # Handle user defined entities
user_entities = {} user_entities = {}
for match in re.finditer(r'<!ENTITY\s+(\S+)\s+([^>]+)', pre): for match in re.finditer(r'<!ENTITY\s+(\S+)\s+([^>]+)', pre):
val = match.group(2) val = match.group(2)
@ -368,8 +370,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
meta.getparent().remove(meta) meta.getparent().remove(meta)
meta = etree.SubElement(head, XHTML('meta'), meta = etree.SubElement(head, XHTML('meta'),
attrib={'http-equiv': 'Content-Type'}) attrib={'http-equiv': 'Content-Type'})
meta.set('content', 'text/html; charset=utf-8') # Ensure content is second meta.set('content', 'text/html; charset=utf-8') # Ensure content is second attribute
# attribute
# Ensure has a <body/> # Ensure has a <body/>
if not xpath(data, '/h:html/h:body'): if not xpath(data, '/h:html/h:body'):