Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

FB2 Output: Remove extra line breaks and prettify XML markup

Browse Source
This commit is contained in:
Andrey Efremov 2019-10-06 13:07:17 +07:00
parent 6071352d67
commit 88159288a8
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
src/calibre/ebooks/fb2/fb2ml.py
View File

@ -78,7 +78,7 @@ class FB2MLizer(object):
# Clean up pargraph endings. # Clean up pargraph endings.
text = re.sub(r'(?miu)\s*</p>', '</p>', text) text = re.sub(r'(?miu)\s*</p>', '</p>', text)
# Put paragraphs following a paragraph on a separate line. # Put paragraphs following a paragraph on a separate line.
text = re.sub(r'(?miu)</p>\s*<p>', '</p>\n\n<p>', text) text = re.sub(r'(?miu)</p>\s*<p>', '</p>\n<p>', text)
# Remove empty title elements. # Remove empty title elements.
text = re.sub(r'(?miu)<title>\s*</title>', '', text) text = re.sub(r'(?miu)<title>\s*</title>', '', text)
@ -88,11 +88,11 @@ class FB2MLizer(object):
text = re.sub(r'(?miu)<section>\s*</section>', '', text) text = re.sub(r'(?miu)<section>\s*</section>', '', text)
# Clean up sections start and ends. # Clean up sections start and ends.
text = re.sub(r'(?miu)\s*</section>', '\n</section>', text) text = re.sub(r'(?miu)\s*</section>', '\n</section>', text)
text = re.sub(r'(?miu)</section>\s*', '</section>\n\n', text) text = re.sub(r'(?miu)</section>\s*', '</section>\n', text)
text = re.sub(r'(?miu)\s*<section>', '\n<section>', text) text = re.sub(r'(?miu)\s*<section>', '\n<section>', text)
text = re.sub(r'(?miu)<section>\s*', '<section>\n', text) text = re.sub(r'(?miu)<section>\s*', '<section>\n', text)
# Put sectnions followed by sections on a separate line. # Put sectnions followed by sections on a separate line.
text = re.sub(r'(?miu)</section>\s*<section>', '</section>\n\n<section>', text) text = re.sub(r'(?miu)</section>\s*<section>', '</section>\n<section>', text)
if self.opts.insert_blank_line: if self.opts.insert_blank_line:
text = re.sub(r'(?miu)</p>', '</p><empty-line />', text) text = re.sub(r'(?miu)</p>', '</p><empty-line />', text)
@ -223,7 +223,7 @@ class FB2MLizer(object):
</description>\n''') % metadata </description>\n''') % metadata
def fb2_footer(self): def fb2_footer(self):
return '\n</FictionBook>' return '</FictionBook>'
def get_cover(self): def get_cover(self):
from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
@ -291,7 +291,8 @@ class FB2MLizer(object):
text.append('</section>') text.append('</section>')
self.section_level -= 1 self.section_level -= 1
return ''.join(text) + '</body>' text.append('</body>')
return ''.join(text) + '\n'
def fb2mlize_images(self): def fb2mlize_images(self):
''' '''
@ -316,11 +317,11 @@ class FB2MLizer(object):
# Don't put the encoded image on a single line. # Don't put the encoded image on a single line.
step = 72 step = 72
data = '\n'.join(raw_data[i:i+step] for i in range(0, len(raw_data), step)) data = '\n'.join(raw_data[i:i+step] for i in range(0, len(raw_data), step))
images.append('<binary id="%s" content-type="%s">%s\n</binary>' % (self.image_hrefs[item.href], content_type, data)) images.append('<binary id="%s" content-type="%s">%s</binary>' % (self.image_hrefs[item.href], content_type, data))
except Exception as e: except Exception as e:
self.log.error('Error: Could not include file %s because ' self.log.error('Error: Could not include file %s because '
'%s.' % (item.href, e)) '%s.' % (item.href, e))
return ''.join(images) return '\n'.join(images) + '\n'
def create_flat_toc(self, nodes, level): def create_flat_toc(self, nodes, level):
for item in nodes: for item in nodes: