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

RocketBook output: Fix images and anchors when dealing with mulit file and directory input.

Browse Source
This commit is contained in:
John Schember 2009-08-08 22:05:49 -04:00
parent 2961c75e5b
commit 556dc9a70a
3 changed files with 36 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -112,7 +112,6 @@ class PMLMLizer(object):
aid = self.link_hrefs[aid] aid = self.link_hrefs[aid]
return u'\\Q="%s"' % aid return u'\\Q="%s"' % aid
def clean_text(self, text): def clean_text(self, text):
# Remove excess spaces at beginning and end of lines # Remove excess spaces at beginning and end of lines
text = re.sub('(?m)^[ ]+', '', text) text = re.sub('(?m)^[ ]+', '', text)

51
src/calibre/ebooks/rb/rbml.py
View File

@ -45,6 +45,10 @@ LINK_TAGS = [
'a', 'a',
] ]
IMAGE_TAGS = [
'img',
]
STYLES = [ STYLES = [
('font-weight', {'bold' : 'b', 'bolder' : 'b'}), ('font-weight', {'bold' : 'b', 'bolder' : 'b'}),
('font-style', {'italic' : 'i'}), ('font-style', {'italic' : 'i'}),
@ -56,6 +60,7 @@ class RBMLizer(object):
def __init__(self, log, name_map={}): def __init__(self, log, name_map={}):
self.log = log self.log = log
self.name_map = name_map self.name_map = name_map
self.link_hrefs = {}
def extract_content(self, oeb_book, opts): def extract_content(self, oeb_book, opts):
self.log.info('Converting XHTML to RB markup...') self.log.info('Converting XHTML to RB markup...')
@ -65,6 +70,7 @@ class RBMLizer(object):
def mlize_spine(self): def mlize_spine(self):
self.link_hrefs = {}
output = u'<HTML><HEAD><TITLE></TITLE></HEAD><BODY>' output = u'<HTML><HEAD><TITLE></TITLE></HEAD><BODY>'
if 'titlepage' in self.oeb_book.guide: if 'titlepage' in self.oeb_book.guide:
self.log.debug('Generating cover page...') self.log.debug('Generating cover page...')
@ -72,19 +78,25 @@ class RBMLizer(object):
item = self.oeb_book.manifest.hrefs[href] item = self.oeb_book.manifest.hrefs[href]
if item.spine_position is None: if item.spine_position is None:
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile) stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.dump_text(item.data.find(XHTML('body')), stylizer) output += self.dump_text(item.data.find(XHTML('body')), stylizer, item)
for item in self.oeb_book.spine: for item in self.oeb_book.spine:
self.log.debug('Converting %s to RocketBook HTML...' % item.href) self.log.debug('Converting %s to RocketBook HTML...' % item.href)
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile) stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.add_page_anchor(item.href) output += self.add_page_anchor(item)
output += self.dump_text(item.data.find(XHTML('body')), stylizer) output += self.dump_text(item.data.find(XHTML('body')), stylizer, item)
output += u'</BODY></HTML>' output += u'</BODY></HTML>'
output = self.clean_text(output) output = self.clean_text(output)
return output return output
def add_page_anchor(self, href): def add_page_anchor(self, page):
href = os.path.splitext(os.path.basename(href))[0] return self.get_anchor(page, '')
return u'<A NAME="%s"></A>' % href
def get_anchor(self, page, aid):
aid = '%s#%s' % (page.href, aid)
if aid not in self.link_hrefs.keys():
self.link_hrefs[aid] = 'calibre_link-%s' % len(self.link_hrefs.keys())
aid = self.link_hrefs[aid]
return u'<A NAME="%s"></A>' % aid
def clean_text(self, text): def clean_text(self, text):
# Remove anchors that do not have links # Remove anchors that do not have links
@ -95,7 +107,7 @@ class RBMLizer(object):
return text return text
def dump_text(self, elem, stylizer, tag_stack=[]): def dump_text(self, elem, stylizer, page, tag_stack=[]):
if not isinstance(elem.tag, basestring) \ if not isinstance(elem.tag, basestring) \
or namespace(elem.tag) != XHTML_NS: or namespace(elem.tag) != XHTML_NS:
return u'' return u''
@ -112,10 +124,11 @@ class RBMLizer(object):
# Process tags that need special processing and that do not have inner # Process tags that need special processing and that do not have inner
# text. Usually these require an argument # text. Usually these require an argument
if tag == 'img': if tag in IMAGE_TAGS:
src = os.path.basename(elem.get('src')) if elem.attrib.get('src', None):
name = self.name_map.get(src, src) if page.abshref(elem.attrib['src']) not in self.name_map.keys():
text += '<IMG SRC="%s">' % name self.name_map[page.abshref(elem.attrib['src'])] = unique_name('%s' % len(self.image_hrefs.keys()), self.image_hrefs.keys(), self.name_map.keys())
text += '<IMG SRC="%s">' % self.name_map[page.abshref(elem.attrib['src'])]
rb_tag = tag.upper() if tag in TAGS else None rb_tag = tag.upper() if tag in TAGS else None
if rb_tag: if rb_tag:
@ -123,21 +136,25 @@ class RBMLizer(object):
text += '<%s>' % rb_tag text += '<%s>' % rb_tag
tag_stack.append(rb_tag) tag_stack.append(rb_tag)
# Anchors links
if tag in LINK_TAGS: if tag in LINK_TAGS:
href = elem.get('href') href = elem.get('href')
if href: if href:
href = page.abshref(href)
if '://' not in href: if '://' not in href:
if '#' in href: if '#' not in href:
href = href.partition('#')[2] href += '#'
href = os.path.splitext(os.path.basename(href))[0] if href not in self.link_hrefs.keys():
self.link_hrefs[href] = 'calibre_link-%s' % len(self.link_hrefs.keys())
href = self.link_hrefs[href]
text += '<A HREF="#%s">' % href
tag_count += 1 tag_count += 1
text += '<A HREF="#%s">' % href
tag_stack.append('A') tag_stack.append('A')
# Anchor ids # Anchor ids
id_name = elem.get('id') id_name = elem.get('id')
if id_name: if id_name:
text += '<A NAME="%s"></A>' % os.path.splitext(id_name)[0] text += self.get_anchor(page, id_name)
# Processes style information # Processes style information
for s in STYLES: for s in STYLES:
@ -153,7 +170,7 @@ class RBMLizer(object):
text += prepare_string_for_xml(elem.text) text += prepare_string_for_xml(elem.text)
for item in elem: for item in elem:
text += self.dump_text(item, stylizer, tag_stack) text += self.dump_text(item, stylizer, page, tag_stack)
close_tag_list = [] close_tag_list = []
for i in range(0, tag_count): for i in range(0, tag_count):

4
src/calibre/ebooks/rb/writer.py
View File

@ -125,10 +125,10 @@ class RBWriter(object):
im.save(data, 'PNG') im.save(data, 'PNG')
data = data.getvalue() data = data.getvalue()
name = '%s.png' % os.path.splitext(os.path.basename(item.href))[0] name = '%s.png' % len(used_names)
name = unique_name(name, used_names) name = unique_name(name, used_names)
used_names.append(name) used_names.append(name)
self.name_map[os.path.basename(item.href)] = name self.name_map[item.href] = name
images.append((name, data)) images.append((name, data))
except Exception as e: except Exception as e: