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

RB output: Optimize string manipulation.

Browse Source
This commit is contained in:
John Schember 2009-09-02 18:34:41 -04:00
parent 7fc881735f
commit 7c9b132a7e
1 changed files with 26 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
src/calibre/ebooks/rb/rbml.py
View File

@ -71,12 +71,12 @@ class RBMLizer(object):
def mlize_spine(self): def mlize_spine(self):
self.link_hrefs = {} self.link_hrefs = {}
output = u'<HTML><HEAD><TITLE></TITLE></HEAD><BODY>' output = [u'<HTML><HEAD><TITLE></TITLE></HEAD><BODY>']
output += self.get_cover_page() output.append(self.get_cover_page())
output += u'ghji87yhjko0Caliblre-toc-placeholder-for-insertion-later8ujko0987yjk' output.append(u'ghji87yhjko0Caliblre-toc-placeholder-for-insertion-later8ujko0987yjk')
output += self.get_text() output.append(self.get_text())
output += u'</BODY></HTML>' output.append(u'</BODY></HTML>')
output = output.replace(u'ghji87yhjko0Caliblre-toc-placeholder-for-insertion-later8ujko0987yjk', self.get_toc()) output = ''.join(output).replace(u'ghji87yhjko0Caliblre-toc-placeholder-for-insertion-later8ujko0987yjk', self.get_toc())
output = self.clean_text(output) output = self.clean_text(output)
return output return output
@ -92,26 +92,26 @@ class RBMLizer(object):
return output return output
def get_toc(self): def get_toc(self):
toc = u'' toc = [u'']
if self.opts.inline_toc: if self.opts.inline_toc:
self.log.debug('Generating table of contents...') self.log.debug('Generating table of contents...')
toc += u'<H1>%s</H1><UL>\n' % _('Table of Contents:') toc.append(u'<H1>%s</H1><UL>\n' % _('Table of Contents:'))
for item in self.oeb_book.toc: for item in self.oeb_book.toc:
if item.href in self.link_hrefs.keys(): if item.href in self.link_hrefs.keys():
toc += '<LI><A HREF="#%s">%s</A></LI>\n' % (self.link_hrefs[item.href], item.title) toc.append('<LI><A HREF="#%s">%s</A></LI>\n' % (self.link_hrefs[item.href], item.title))
else: else:
self.oeb.warn('Ignoring toc item: %s not found in document.' % item) self.oeb.warn('Ignoring toc item: %s not found in document.' % item)
toc += '</UL>' toc.append('</UL>')
return toc return ''.join(toc)
def get_text(self): def get_text(self):
output = u'' output = [u'']
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) output.append(self.add_page_anchor(item))
output += self.dump_text(item.data.find(XHTML('body')), stylizer, item) output += self.dump_text(item.data.find(XHTML('body')), stylizer, item)
return output return ''.join(output)
def add_page_anchor(self, page): def add_page_anchor(self, page):
return self.get_anchor(page, '') return self.get_anchor(page, '')
@ -135,14 +135,14 @@ class RBMLizer(object):
def dump_text(self, elem, stylizer, page, 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'']
text = u'' text = [u'']
style = stylizer.style(elem) style = stylizer.style(elem)
if style['display'] in ('none', 'oeb-page-head', 'oeb-page-foot') \ if style['display'] in ('none', 'oeb-page-head', 'oeb-page-foot') \
or style['visibility'] == 'hidden': or style['visibility'] == 'hidden':
return u'' return [u'']
tag = barename(elem.tag) tag = barename(elem.tag)
tag_count = 0 tag_count = 0
@ -153,12 +153,12 @@ class RBMLizer(object):
if elem.attrib.get('src', None): if elem.attrib.get('src', None):
if page.abshref(elem.attrib['src']) not in self.name_map.keys(): if page.abshref(elem.attrib['src']) not in self.name_map.keys():
self.name_map[page.abshref(elem.attrib['src'])] = unique_name('%s' % len(self.image_hrefs.keys()), self.image_hrefs.keys(), self.name_map.keys()) 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'])] text.append('<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:
tag_count += 1 tag_count += 1
text += '<%s>' % rb_tag text.append('<%s>' % rb_tag)
tag_stack.append(rb_tag) tag_stack.append(rb_tag)
# Anchors links # Anchors links
@ -172,14 +172,14 @@ class RBMLizer(object):
if href not in self.link_hrefs.keys(): if href not in self.link_hrefs.keys():
self.link_hrefs[href] = 'calibre_link-%s' % len(self.link_hrefs.keys()) self.link_hrefs[href] = 'calibre_link-%s' % len(self.link_hrefs.keys())
href = self.link_hrefs[href] href = self.link_hrefs[href]
text += '<A HREF="#%s">' % href text.append('<A HREF="#%s">' % href)
tag_count += 1 tag_count += 1
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 += self.get_anchor(page, id_name) text.append(self.get_anchor(page, id_name))
# Processes style information # Processes style information
for s in STYLES: for s in STYLES:
@ -187,12 +187,12 @@ class RBMLizer(object):
if style_tag: if style_tag:
style_tag = style_tag.upper() style_tag = style_tag.upper()
tag_count += 1 tag_count += 1
text += '<%s>' % style_tag text.append('<%s>' % style_tag)
tag_stack.append(style_tag) tag_stack.append(style_tag)
# Proccess tags that contain text. # Proccess tags that contain text.
if hasattr(elem, 'text') and elem.text != None and elem.text.strip() != '': if hasattr(elem, 'text') and elem.text != None and elem.text.strip() != '':
text += prepare_string_for_xml(elem.text) text.append(prepare_string_for_xml(elem.text))
for item in elem: for item in elem:
text += self.dump_text(item, stylizer, page, tag_stack) text += self.dump_text(item, stylizer, page, tag_stack)
@ -204,14 +204,14 @@ class RBMLizer(object):
text += self.close_tags(close_tag_list) text += self.close_tags(close_tag_list)
if hasattr(elem, 'tail') and elem.tail != None and elem.tail.strip() != '': if hasattr(elem, 'tail') and elem.tail != None and elem.tail.strip() != '':
text += prepare_string_for_xml(elem.tail) text.append(prepare_string_for_xml(elem.tail))
return text return text
def close_tags(self, tags): def close_tags(self, tags):
text = u'' text = [u'']
for i in range(0, len(tags)): for i in range(0, len(tags)):
tag = tags.pop() tag = tags.pop()
text += '</%s>' % tag text.append('</%s>' % tag)
return text return text