Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Move TOC creation into its own module

Browse Source
This commit is contained in:
Kovid Goyal 2013-06-15 10:46:03 +05:30
parent 8bc65df29a
commit ba0639c681
2 changed files with 62 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
src/calibre/ebooks/docx/to_html.py
View File

@ -25,9 +25,8 @@ from calibre.ebooks.docx.tables import Tables
from calibre.ebooks.docx.footnotes import Footnotes from calibre.ebooks.docx.footnotes import Footnotes
from calibre.ebooks.docx.cleanup import cleanup_markup from calibre.ebooks.docx.cleanup import cleanup_markup
from calibre.ebooks.docx.theme import Theme from calibre.ebooks.docx.theme import Theme
from calibre.ebooks.docx.toc import create_toc
from calibre.ebooks.metadata.opf2 import OPFCreator from calibre.ebooks.metadata.opf2 import OPFCreator
from calibre.ebooks.metadata.toc import TOC
from calibre.ebooks.oeb.polish.toc import elem_to_toc_text
from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1 from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
class Text: class Text:
@ -267,48 +266,8 @@ class Convert(object):
self.styles.resolve_numbering(numbering) self.styles.resolve_numbering(numbering)
def create_toc(self):
' Create a TOC from headings in the document '
root = self.body
headings = ('h1', 'h2', 'h3')
tocroot = TOC()
xpaths = [XPath('//%s' % x) for x in headings]
level_prev = {i+1:None for i in xrange(len(xpaths))}
level_prev[0] = tocroot
level_item_map = {i+1:frozenset(xp(root)) for i, xp in enumerate(xpaths)}
item_level_map = {e:i for i, elems in level_item_map.iteritems() for e in elems}
self.idcount = 0
def ensure_id(elem):
ans = elem.get('id', None)
if not ans:
self.idcount += 1
ans = 'toc_id_%d' % self.idcount
elem.set('id', ans)
return ans
for item in descendants(root, *headings):
lvl = plvl = item_level_map.get(item, None)
if lvl is None:
continue
parent = None
while parent is None:
plvl -= 1
parent = level_prev[plvl]
lvl = plvl + 1
elem_id = ensure_id(item)
text = elem_to_toc_text(item)
toc = parent.add_item('index.html', elem_id, text)
level_prev[lvl] = toc
for i in xrange(lvl+1, len(xpaths)+1):
level_prev[i] = None
if len(tuple(tocroot.flat())) > 1:
return tocroot
def write(self): def write(self):
toc = self.create_toc() toc = create_toc(self.body)
raw = html.tostring(self.html, encoding='utf-8', doctype='<!DOCTYPE html>') raw = html.tostring(self.html, encoding='utf-8', doctype='<!DOCTYPE html>')
with open(os.path.join(self.dest_dir, 'index.html'), 'wb') as f: with open(os.path.join(self.dest_dir, 'index.html'), 'wb') as f:
f.write(raw) f.write(raw)

60
src/calibre/ebooks/docx/toc.py Normal file
View File

@ -0,0 +1,60 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
from calibre.ebooks.docx.names import XPath, descendants
from calibre.ebooks.metadata.toc import TOC
from calibre.ebooks.oeb.polish.toc import elem_to_toc_text
class Count(object):
__slots__ = ('val',)
def __init__(self):
self.val = 0
def create_toc(body):
' Create a TOC from headings in the document '
headings = ('h1', 'h2', 'h3')
tocroot = TOC()
xpaths = [XPath('//%s' % x) for x in headings]
level_prev = {i+1:None for i in xrange(len(xpaths))}
level_prev[0] = tocroot
level_item_map = {i+1:frozenset(xp(body)) for i, xp in enumerate(xpaths)}
item_level_map = {e:i for i, elems in level_item_map.iteritems() for e in elems}
idcount = Count()
def ensure_id(elem):
ans = elem.get('id', None)
if not ans:
idcount.val += 1
ans = 'toc_id_%d' % idcount.val
elem.set('id', ans)
return ans
for item in descendants(body, *headings):
lvl = plvl = item_level_map.get(item, None)
if lvl is None:
continue
parent = None
while parent is None:
plvl -= 1
parent = level_prev[plvl]
lvl = plvl + 1
elem_id = ensure_id(item)
text = elem_to_toc_text(item)
toc = parent.add_item('index.html', elem_id, text)
level_prev[lvl] = toc
for i in xrange(lvl+1, len(xpaths)+1):
level_prev[i] = None
if len(tuple(tocroot.flat())) > 1:
return tocroot