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

KF8 Input: Handle images referenced via CSS url in the style attribute of a tag

Browse Source
This commit is contained in:
Kovid Goyal 2012-04-26 11:05:05 +05:30
parent a883b577a6
commit 68e26b945c
1 changed files with 30 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
src/calibre/ebooks/mobi/reader/markup.py
View File

@ -223,15 +223,15 @@ def insert_images_into_markup(parts, resource_map, log):
# Handle any embedded raster images links in the xhtml text # Handle any embedded raster images links in the xhtml text
# kindle:embed:XXXX?mime=image/gif (png, jpeg, etc) (used for images) # kindle:embed:XXXX?mime=image/gif (png, jpeg, etc) (used for images)
img_pattern = re.compile(r'''(<[img\s|image\s][^>]*>)''', re.IGNORECASE) img_pattern = re.compile(r'''(<[img\s|image\s][^>]*>)''', re.IGNORECASE)
img_index_pattern = re.compile(r'''['"]kindle:embed:([0-9|A-V]+)[^'"]*['"]''') img_index_pattern = re.compile(r'''[('"]kindle:embed:([0-9|A-V]+)[^')"]*[)'"]''')
style_pattern = re.compile(r'''(<[a-zA-Z0-9]+\s[^>]*style\s*=\s*[^>]*>)''',
re.IGNORECASE)
for i in xrange(len(parts)): for i in xrange(len(parts)):
part = parts[i] part = parts[i]
#[partnum, dir, filename, beg, end, aidtext] = self.k8proc.partinfo[i]
# links to raster image files
# image_pattern
srcpieces = img_pattern.split(part) srcpieces = img_pattern.split(part)
for j in range(1, len(srcpieces), 2): for j in xrange(1, len(srcpieces), 2):
tag = srcpieces[j] tag = srcpieces[j]
if tag.startswith('<im'): if tag.startswith('<im'):
for m in img_index_pattern.finditer(tag): for m in img_index_pattern.finditer(tag):
@ -248,6 +248,30 @@ def insert_images_into_markup(parts, resource_map, log):
# store away modified version # store away modified version
parts[i] = part parts[i] = part
# Replace urls used in style attributes
for i in xrange(len(parts)):
part = parts[i]
srcpieces = style_pattern.split(part)
for j in xrange(1, len(srcpieces), 2):
tag = srcpieces[j]
if 'kindle:embed' in tag:
for m in img_index_pattern.finditer(tag):
num = int(m.group(1), 32)
href = resource_map[num-1]
osep = m.group()[0]
csep = m.group()[-1]
if href:
replacement = '%s%s%s'%(osep, '../' + href, csep)
tag = img_index_pattern.sub(replacement, tag, 1)
else:
log.warn('Referenced image %s was not recognized as '
'a valid image in %s' % (num, tag))
srcpieces[j] = tag
part = "".join(srcpieces)
# store away modified version
parts[i] = part
def upshift_markup(parts): def upshift_markup(parts):
tag_pattern = re.compile(r'''(<(?:svg)[^>]*>)''', re.IGNORECASE) tag_pattern = re.compile(r'''(<(?:svg)[^>]*>)''', re.IGNORECASE)