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 Input: When autodetecting the Table of Contents from headings, work even if the headings use numbering. Fixes #1834661 [Private bug](https://bugs.launchpad.net/calibre/+bug/1834661)

Browse Source
This commit is contained in:
Kovid Goyal 2019-06-29 12:16:42 +05:30
parent ce01b4c571
commit 0d9047cfa3
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 14 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/calibre/ebooks/docx/to_html.py
View File

@ -497,6 +497,7 @@ class Convert(object):
if m is not None: if m is not None:
n = min(6, max(1, int(m.group(1)))) n = min(6, max(1, int(m.group(1))))
dest.tag = 'h%d' % n dest.tag = 'h%d' % n
dest.set('data-heading-level', unicode_type(n))
if style.bidi is True: if style.bidi is True:
dest.set('dir', 'rtl') dest.set('dir', 'rtl')

22
src/calibre/ebooks/docx/toc.py
View File

@ -15,15 +15,15 @@ from calibre.ebooks.oeb.polish.toc import elem_to_toc_text
from polyglot.builtins import iteritems, range from polyglot.builtins import iteritems, range
def from_headings(body, log, namespace): def from_headings(body, log, namespace, num_levels=3):
' Create a TOC from headings in the document ' ' Create a TOC from headings in the document '
XPath, descendants = namespace.XPath, namespace.descendants
headings = ('h1', 'h2', 'h3')
tocroot = TOC() tocroot = TOC()
xpaths = [XPath('//%s' % x) for x in headings] all_heading_nodes = body.xpath('//*[@data-heading-level]')
level_prev = {i+1:None for i in range(len(xpaths))} level_prev = {i+1:None for i in range(num_levels)}
level_prev[0] = tocroot level_prev[0] = tocroot
level_item_map = {i+1:frozenset(xp(body)) for i, xp in enumerate(xpaths)} level_item_map = {i:frozenset(
x for x in all_heading_nodes if int(x.get('data-heading-level')) == i)
for i in range(1, num_levels+1)}
item_level_map = {e:i for i, elems in iteritems(level_item_map) for e in elems} item_level_map = {e:i for i, elems in iteritems(level_item_map) for e in elems}
idcount = count() idcount = count()
@ -35,7 +35,7 @@ def from_headings(body, log, namespace):
elem.set('id', ans) elem.set('id', ans)
return ans return ans
for item in descendants(body, *headings): for item in all_heading_nodes:
lvl = plvl = item_level_map.get(item, None) lvl = plvl = item_level_map.get(item, None)
if lvl is None: if lvl is None:
continue continue
@ -48,7 +48,7 @@ def from_headings(body, log, namespace):
text = elem_to_toc_text(item) text = elem_to_toc_text(item)
toc = parent.add_item('index.html', elem_id, text) toc = parent.add_item('index.html', elem_id, text)
level_prev[lvl] = toc level_prev[lvl] = toc
for i in range(lvl+1, len(xpaths)+1): for i in range(lvl+1, num_levels+1):
level_prev[i] = None level_prev[i] = None
if len(tuple(tocroot.flat())) > 1: if len(tuple(tocroot.flat())) > 1:
@ -136,4 +136,8 @@ def from_toc(docx, link_map, styles, object_map, log, namespace):
def create_toc(docx, body, link_map, styles, object_map, log, namespace): def create_toc(docx, body, link_map, styles, object_map, log, namespace):
return from_toc(docx, link_map, styles, object_map, log, namespace) or from_headings(body, log, namespace) ans = from_toc(docx, link_map, styles, object_map, log, namespace) or from_headings(body, log, namespace)
# Remove heading level attributes
for h in body.xpath('//*[@data-heading-level]'):
del h.attrib['data-heading-level']
return ans