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

DOCX: Performance improvement

Browse Source
This commit is contained in:
Kovid Goyal 2013-06-06 14:00:33 +05:30
parent 02a28056de
commit a210f681a7
2 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/calibre/ebooks/docx/names.py
View File

@ -83,11 +83,10 @@ def get(x, attr, default=None):
return x.attrib.get(expand(attr), default) return x.attrib.get(expand(attr), default)
def ancestor(elem, name): def ancestor(elem, name):
tag = expand(name) try:
while elem is not None: return XPath('ancestor::%s[1]' % name)(elem)[0]
elem = elem.getparent() except IndexError:
if getattr(elem, 'tag', None) == tag: return None
return elem
def generate_anchor(name, existing): def generate_anchor(name, existing):
x = y = 'id_' + re.sub(r'[^0-9a-zA-Z_]', '', ascii_text(name)).lstrip('_') x = y = 'id_' + re.sub(r'[^0-9a-zA-Z_]', '', ascii_text(name)).lstrip('_')

9
src/calibre/ebooks/docx/to_html.py
View File

@ -16,7 +16,7 @@ from lxml.html.builder import (
from calibre.ebooks.docx.container import DOCX, fromstring from calibre.ebooks.docx.container import DOCX, fromstring
from calibre.ebooks.docx.names import ( from calibre.ebooks.docx.names import (
XPath, is_tag, XML, STYLES, NUMBERING, FONTS, get, generate_anchor, XPath, is_tag, XML, STYLES, NUMBERING, FONTS, get, generate_anchor,
descendants, ancestor, FOOTNOTES, ENDNOTES, children) descendants, FOOTNOTES, ENDNOTES, children)
from calibre.ebooks.docx.styles import Styles, inherit, PageProperties from calibre.ebooks.docx.styles import Styles, inherit, PageProperties
from calibre.ebooks.docx.numbering import Numbering from calibre.ebooks.docx.numbering import Numbering
from calibre.ebooks.docx.fonts import Fonts from calibre.ebooks.docx.fonts import Fonts
@ -308,6 +308,7 @@ class Convert(object):
current_anchor = None current_anchor = None
current_hyperlink = None current_hyperlink = None
hl_xpath = XPath('ancestor::w:hyperlink[1]')
for x in descendants(p, 'w:r', 'w:bookmarkStart', 'w:hyperlink'): for x in descendants(p, 'w:r', 'w:bookmarkStart', 'w:hyperlink'):
if x.tag.endswith('}r'): if x.tag.endswith('}r'):
@ -316,10 +317,10 @@ class Convert(object):
(dest if len(dest) == 0 else span).set('id', current_anchor) (dest if len(dest) == 0 else span).set('id', current_anchor)
current_anchor = None current_anchor = None
if current_hyperlink is not None: if current_hyperlink is not None:
hl = ancestor(x, 'w:hyperlink') try:
if hl is not None: hl = hl_xpath(x)[0]
self.link_map[hl].append(span) self.link_map[hl].append(span)
else: except IndexError:
current_hyperlink = None current_hyperlink = None
dest.append(span) dest.append(span)
self.layers[p].append(x) self.layers[p].append(x)