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

PML Output: Don't write \Cn tags when we are within a heading. Put images in DropBook required image subfolder. Remove \Cn tags written inside of \x and \Xn tags.

Browse Source
This commit is contained in:
Kovid Goyal 2011-02-17 07:40:36 -07:00
commit fc314b2a9b
3 changed files with 15 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/calibre/ebooks/pml/input.py
View File

@ -1,4 +1,3 @@
import os.path
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'

5
src/calibre/ebooks/pml/output.py
View File

@ -50,7 +50,10 @@ class PMLOutput(OutputFormatPlugin):
with open(os.path.join(tdir, 'index.pml'), 'wb') as out:
out.write(pml.encode(opts.pml_output_encoding, 'replace'))
self.write_images(oeb_book.manifest, pmlmlizer.image_hrefs, tdir, opts)
img_path = os.path.join(tdir, 'index_img')
if not os.path.exists(img_path):
os.makedirs(img_path)
self.write_images(oeb_book.manifest, pmlmlizer.image_hrefs, img_path, opts)
log.debug('Compressing output...')
pmlz = ZipFile(output_path, 'w')

14
src/calibre/ebooks/pml/pmlml.py
View File

@ -180,6 +180,9 @@ class PMLMLizer(object):
links = set(re.findall(r'(?<=\\q="#).+?(?=")', text))
for unused in anchors.difference(links):
text = text.replace('\\Q="%s"' % unused, '')
# Remove \Cn tags that are within \x and \Xn tags
text = re.sub(ur'(?msu)(?P<t>\\(x|X[0-4]))(?P<a>.*?)(?P<c>\\C[0-4]\s*=\s*"[^"]*")(?P<b>.*?)(?P=t)', '\g<t>\g<a>\g<b>\g<t>', text)
# Replace bad characters.
text = text.replace(u'\xc2', '')
@ -255,7 +258,12 @@ class PMLMLizer(object):
# TOC markers.
toc_name = elem.attrib.get('name', None)
toc_id = elem.attrib.get('id', None)
if (toc_id or toc_name) and tag not in ('h1', 'h2','h3','h4','h5','h6',):
# Only write the TOC marker if the tag isn't a heading and we aren't in one.
if (toc_id or toc_name) and tag not in ('h1', 'h2','h3','h4','h5','h6') and \
'x' not in tag_stack+tags and 'X0' not in tag_stack+tags and \
'X1' not in tag_stack+tags and 'X2' not in tag_stack+tags and \
'X3' not in tag_stack+tags and 'X4' not in tag_stack+tags:
toc_page = page.href
if self.toc.get(toc_page, None):
for toc_x in (toc_name, toc_id):
@ -264,8 +272,8 @@ class PMLMLizer(object):
toc_depth = max(min(toc_depth, 4), 0)
text.append('\\C%s="%s"' % (toc_depth, toc_title))
# Process style information that needs holds a single tag
# Commented out because every page in an OEB book starts with this style
# Process style information that needs holds a single tag.
# Commented out because every page in an OEB book starts with this style.
if style['page-break-before'] == 'always':
text.append('\\p')