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

lrs2lrf: Handle missing style labels gracefully

Browse Source
This commit is contained in:
Kovid Goyal 2009-07-26 12:09:21 -06:00
parent 2c5d951139
commit a80d705049
2 changed files with 54 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

82
src/calibre/ebooks/lrf/lrs/convert_from.py
View File

@ -18,38 +18,38 @@ from calibre.ebooks.lrf.pylrs.pylrs import Book, PageStyle, TextStyle, \
from calibre.ebooks.chardet import xml_to_unicode from calibre.ebooks.chardet import xml_to_unicode
class LrsParser(object): class LrsParser(object):
SELF_CLOSING_TAGS = [i.lower() for i in ['CR', 'Plot', 'NoBR', 'Space', SELF_CLOSING_TAGS = [i.lower() for i in ['CR', 'Plot', 'NoBR', 'Space',
'PutObj', 'RuledLine', 'PutObj', 'RuledLine',
'Plot', 'SetDefault', 'BookSetting', 'RegistFont', 'Plot', 'SetDefault', 'BookSetting', 'RegistFont',
'PageStyle', 'TextStyle', 'BlockStyle', 'JumpTo', 'PageStyle', 'TextStyle', 'BlockStyle', 'JumpTo',
'ImageStream', 'Image']] 'ImageStream', 'Image']]
def __init__(self, stream, logger): def __init__(self, stream, logger):
self.logger = logger self.logger = logger
src = stream.read() src = stream.read()
self.soup = BeautifulStoneSoup(xml_to_unicode(src)[0], self.soup = BeautifulStoneSoup(xml_to_unicode(src)[0],
convertEntities=BeautifulStoneSoup.XML_ENTITIES, convertEntities=BeautifulStoneSoup.XML_ENTITIES,
selfClosingTags=self.SELF_CLOSING_TAGS) selfClosingTags=self.SELF_CLOSING_TAGS)
self.objects = {} self.objects = {}
for obj in self.soup.findAll(objid=True): for obj in self.soup.findAll(objid=True):
self.objects[obj['objid']] = obj self.objects[obj['objid']] = obj
self.parsed_objects = {} self.parsed_objects = {}
self.first_pass() self.first_pass()
self.second_pass() self.second_pass()
self.third_pass() self.third_pass()
self.fourth_pass() self.fourth_pass()
self.fifth_pass() self.fifth_pass()
def fifth_pass(self): def fifth_pass(self):
for tag in self.soup.findAll(['canvas', 'header', 'footer']): for tag in self.soup.findAll(['canvas', 'header', 'footer']):
canvas = self.parsed_objects[tag.get('objid')] canvas = self.parsed_objects[tag.get('objid')]
for po in tag.findAll('putobj'): for po in tag.findAll('putobj'):
canvas.put_object(self.parsed_objects[po.get('refobj')], canvas.put_object(self.parsed_objects[po.get('refobj')],
po.get('x1'), po.get('y1')) po.get('x1'), po.get('y1'))
@classmethod @classmethod
def attrs_to_dict(cls, tag, exclude=('objid',)): def attrs_to_dict(cls, tag, exclude=('objid',)):
result = {} result = {}
@ -58,7 +58,7 @@ class LrsParser(object):
continue continue
result[str(key)] = val result[str(key)] = val
return result return result
def text_tag_to_element(self, tag): def text_tag_to_element(self, tag):
map = { map = {
'span' : Span, 'span' : Span,
@ -77,7 +77,7 @@ class LrsParser(object):
settings = self.attrs_to_dict(tag) settings = self.attrs_to_dict(tag)
settings.pop('spanstyle', '') settings.pop('spanstyle', '')
return map[tag.name](**settings) return map[tag.name](**settings)
def process_text_element(self, tag, elem): def process_text_element(self, tag, elem):
for item in tag.contents: for item in tag.contents:
if isinstance(item, NavigableString): if isinstance(item, NavigableString):
@ -86,8 +86,8 @@ class LrsParser(object):
subelem = self.text_tag_to_element(item) subelem = self.text_tag_to_element(item)
elem.append(subelem) elem.append(subelem)
self.process_text_element(item, subelem) self.process_text_element(item, subelem)
def process_paragraph(self, tag): def process_paragraph(self, tag):
p = Paragraph() p = Paragraph()
contents = [i for i in tag.contents] contents = [i for i in tag.contents]
@ -104,7 +104,7 @@ class LrsParser(object):
p.append(elem) p.append(elem)
self.process_text_element(item, elem) self.process_text_element(item, elem)
return p return p
def process_text_block(self, tag): def process_text_block(self, tag):
tb = self.parsed_objects[tag.get('objid')] tb = self.parsed_objects[tag.get('objid')]
for item in tag.contents: for item in tag.contents:
@ -119,25 +119,25 @@ class LrsParser(object):
elem = self.text_tag_to_element(item) elem = self.text_tag_to_element(item)
self.process_text_element(item, elem) self.process_text_element(item, elem)
p.append(elem) p.append(elem)
def fourth_pass(self): def fourth_pass(self):
for tag in self.soup.findAll('page'): for tag in self.soup.findAll('page'):
page = self.parsed_objects[tag.get('objid')] page = self.parsed_objects[tag.get('objid')]
self.book.append(page) self.book.append(page)
for block_tag in tag.findAll(['canvas', 'imageblock', 'textblock', for block_tag in tag.findAll(['canvas', 'imageblock', 'textblock',
'ruledline', 'simpletextblock']): 'ruledline', 'simpletextblock']):
if block_tag.name == 'ruledline': if block_tag.name == 'ruledline':
page.append(RuledLine(**self.attrs_to_dict(block_tag))) page.append(RuledLine(**self.attrs_to_dict(block_tag)))
else: else:
page.append(self.parsed_objects[block_tag.get('objid')]) page.append(self.parsed_objects[block_tag.get('objid')])
for tag in self.soup.find('objects').findAll('button'): for tag in self.soup.find('objects').findAll('button'):
jt = tag.find('jumpto') jt = tag.find('jumpto')
tb = self.parsed_objects[jt.get('refobj')] tb = self.parsed_objects[jt.get('refobj')]
jb = JumpButton(tb) jb = JumpButton(tb)
self.book.append(jb) self.book.append(jb)
self.parsed_objects[tag.get('objid')] = jb self.parsed_objects[tag.get('objid')] = jb
for tag in self.soup.findAll(['textblock', 'simpletextblock']): for tag in self.soup.findAll(['textblock', 'simpletextblock']):
self.process_text_block(tag) self.process_text_block(tag)
toc = self.soup.find('toc') toc = self.soup.find('toc')
@ -145,11 +145,11 @@ class LrsParser(object):
for tag in toc.findAll('toclabel'): for tag in toc.findAll('toclabel'):
label = self.tag_to_string(tag) label = self.tag_to_string(tag)
self.book.addTocEntry(label, self.parsed_objects[tag.get('refobj')]) self.book.addTocEntry(label, self.parsed_objects[tag.get('refobj')])
def third_pass(self): def third_pass(self):
map = { map = {
'page' : (Page, ['pagestyle', 'evenfooterid', 'page' : (Page, ['pagestyle', 'evenfooterid',
'oddfooterid', 'evenheaderid', 'oddheaderid']), 'oddfooterid', 'evenheaderid', 'oddheaderid']),
'textblock' : (TextBlock, ['textstyle', 'blockstyle']), 'textblock' : (TextBlock, ['textstyle', 'blockstyle']),
'simpletextblock' : (TextBlock, ['textstyle', 'blockstyle']), 'simpletextblock' : (TextBlock, ['textstyle', 'blockstyle']),
@ -167,7 +167,7 @@ class LrsParser(object):
settings = self.attrs_to_dict(tag, map[tag.name][1]+['objid', 'objlabel']) settings = self.attrs_to_dict(tag, map[tag.name][1]+['objid', 'objlabel'])
for a in ('pagestyle', 'blockstyle', 'textstyle'): for a in ('pagestyle', 'blockstyle', 'textstyle'):
label = tag.get(a, False) label = tag.get(a, False)
if label: if label and label in self._style_labels:
_obj = self.parsed_objects[label] if \ _obj = self.parsed_objects[label] if \
self.parsed_objects.has_key(label) else \ self.parsed_objects.has_key(label) else \
self._style_labels[label] self._style_labels[label]
@ -181,9 +181,9 @@ class LrsParser(object):
if tag.has_key('canvaswidth'): if tag.has_key('canvaswidth'):
args += [tag.get('canvaswidth'), tag.get('canvasheight')] args += [tag.get('canvaswidth'), tag.get('canvasheight')]
self.parsed_objects[id] = map[tag.name][0](*args, **settings) self.parsed_objects[id] = map[tag.name][0](*args, **settings)
def second_pass(self): def second_pass(self):
map = { map = {
'pagestyle' : (PageStyle, ['stylelabel', 'evenheaderid', 'oddheaderid', 'evenfooterid', 'oddfooterid']), 'pagestyle' : (PageStyle, ['stylelabel', 'evenheaderid', 'oddheaderid', 'evenfooterid', 'oddfooterid']),
@ -207,8 +207,8 @@ class LrsParser(object):
self._style_labels[x] = self.parsed_objects[id] self._style_labels[x] = self.parsed_objects[id]
if tag.name == 'registfont': if tag.name == 'registfont':
self.book.append(self.parsed_objects[id]) self.book.append(self.parsed_objects[id])
@classmethod @classmethod
def tag_to_string(cls, tag): def tag_to_string(cls, tag):
''' '''
@ -226,20 +226,20 @@ class LrsParser(object):
res = cls.tag_to_string(item) res = cls.tag_to_string(item)
if res: if res:
strings.append(res) strings.append(res)
return u''.join(strings) return u''.join(strings)
def first_pass(self): def first_pass(self):
info = self.soup.find('bbebxylog').find('bookinformation').find('info') info = self.soup.find('bbebxylog').find('bookinformation').find('info')
bookinfo = info.find('bookinfo') bookinfo = info.find('bookinfo')
docinfo = info.find('docinfo') docinfo = info.find('docinfo')
def me(base, tagname): def me(base, tagname):
tag = base.find(tagname.lower()) tag = base.find(tagname.lower())
if tag is None: if tag is None:
return ('', '', '') return ('', '', '')
tag = (self.tag_to_string(tag), tag.get('reading') if tag.has_key('reading') else '') tag = (self.tag_to_string(tag), tag.get('reading') if tag.has_key('reading') else '')
return tag return tag
title = me(bookinfo, 'Title') title = me(bookinfo, 'Title')
author = me(bookinfo, 'Author') author = me(bookinfo, 'Author')
publisher = me(bookinfo, 'Publisher') publisher = me(bookinfo, 'Publisher')
@ -250,12 +250,12 @@ class LrsParser(object):
creator = me(docinfo, 'Creator')[0] creator = me(docinfo, 'Creator')[0]
producer = me(docinfo, 'Producer')[0] producer = me(docinfo, 'Producer')[0]
bookid = me(bookinfo, 'BookID')[0] bookid = me(bookinfo, 'BookID')[0]
sd = self.soup.find('setdefault') sd = self.soup.find('setdefault')
sd = StyleDefault(**self.attrs_to_dict(sd, ['page_tree_id', 'rubyalignandadjust'])) sd = StyleDefault(**self.attrs_to_dict(sd, ['page_tree_id', 'rubyalignandadjust']))
bs = self.soup.find('booksetting') bs = self.soup.find('booksetting')
bs = BookSetting(**self.attrs_to_dict(bs, [])) bs = BookSetting(**self.attrs_to_dict(bs, []))
settings = {} settings = {}
thumbnail = self.soup.find('cthumbnail') thumbnail = self.soup.find('cthumbnail')
if thumbnail is not None: if thumbnail is not None:
@ -264,23 +264,23 @@ class LrsParser(object):
settings['thumbnail'] = f settings['thumbnail'] = f
else: else:
print _('Could not read from thumbnail file:'), f print _('Could not read from thumbnail file:'), f
self.book = Book(title=title, author=author, publisher=publisher, self.book = Book(title=title, author=author, publisher=publisher,
category=category, classification=classification, category=category, classification=classification,
freetext=freetext, language=language, creator=creator, freetext=freetext, language=language, creator=creator,
producer=producer, bookid=bookid, setdefault=sd, producer=producer, bookid=bookid, setdefault=sd,
booksetting=bs, **settings) booksetting=bs, **settings)
for hdr in self.soup.findAll(['header', 'footer']): for hdr in self.soup.findAll(['header', 'footer']):
elem = Header if hdr.name == 'header' else Footer elem = Header if hdr.name == 'header' else Footer
self.parsed_objects[hdr.get('objid')] = elem(**self.attrs_to_dict(hdr)) self.parsed_objects[hdr.get('objid')] = elem(**self.attrs_to_dict(hdr))
def render(self, file, to_lrs=False): def render(self, file, to_lrs=False):
if to_lrs: if to_lrs:
self.book.renderLrs(file, 'utf-8') self.book.renderLrs(file, 'utf-8')
else: else:
self.book.renderLrf(file) self.book.renderLrf(file)
def option_parser(): def option_parser():
parser = OptionParser(usage=_('%prog [options] file.lrs\nCompile an LRS file into an LRF file.')) parser = OptionParser(usage=_('%prog [options] file.lrs\nCompile an LRS file into an LRF file.'))
@ -299,7 +299,7 @@ def main(args=sys.argv, logger=None):
level = logging.DEBUG if opts.verbose else logging.INFO level = logging.DEBUG if opts.verbose else logging.INFO
logger = logging.getLogger('lrs2lrf') logger = logging.getLogger('lrs2lrf')
setup_cli_handlers(logger, level) setup_cli_handlers(logger, level)
if len(args) != 2: if len(args) != 2:
parser.print_help() parser.print_help()
return 1 return 1
@ -310,7 +310,7 @@ def main(args=sys.argv, logger=None):
if opts.verbose: if opts.verbose:
import warnings import warnings
warnings.defaultaction = 'error' warnings.defaultaction = 'error'
logger.info('Parsing LRS file...') logger.info('Parsing LRS file...')
converter = LrsParser(open(args[1], 'rb'), logger) converter = LrsParser(open(args[1], 'rb'), logger)
logger.info('Writing to output file...') logger.info('Writing to output file...')
@ -320,4 +320,4 @@ def main(args=sys.argv, logger=None):
if __name__ == '__main__': if __name__ == '__main__':
sys.exit(main()) sys.exit(main())

14
src/calibre/utils/filenames.py
View File

@ -5,7 +5,19 @@ meaning as possible.
from calibre.ebooks.unidecode.unidecoder import Unidecoder from calibre.ebooks.unidecode.unidecoder import Unidecoder
from calibre import sanitize_file_name from calibre import sanitize_file_name
from calibre.constants import preferred_encoding
udc = Unidecoder() udc = Unidecoder()
def ascii_text(orig):
try:
ascii = udc.decode(orig)
except:
if isinstance(orig, unicode):
ascii = orig.encode('ascii', 'replace')
ascii = orig.decode(preferred_encoding,
'replace').encode('ascii', 'replace')
return ascii
def ascii_filename(orig): def ascii_filename(orig):
return sanitize_file_name(udc.decode(orig).replace('?', '_')) return sanitize_file_name(ascii_text(orig).replace('?', '_'))