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

Edit book: Fix errors when working on HTML files that parse as valid XML, but do not have the correct XHTML namespace.

Browse Source
This commit is contained in:
Kovid Goyal 2014-01-09 21:33:47 +05:30
parent 3918e3d679
commit e1901121ae
2 changed files with 26 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
src/calibre/ebooks/oeb/polish/check/parsing.py
View File

@ -11,12 +11,12 @@ import re
from lxml.etree import XMLParser, fromstring, XMLSyntaxError from lxml.etree import XMLParser, fromstring, XMLSyntaxError
import cssutils import cssutils
from calibre import force_unicode, human_readable from calibre import force_unicode, human_readable, prepare_string_for_xml
from calibre.ebooks.html_entities import html5_entities from calibre.ebooks.html_entities import html5_entities
from calibre.ebooks.oeb.polish.pretty import pretty_script_or_style as fix_style_tag from calibre.ebooks.oeb.polish.pretty import pretty_script_or_style as fix_style_tag
from calibre.ebooks.oeb.polish.utils import PositionFinder from calibre.ebooks.oeb.polish.utils import PositionFinder
from calibre.ebooks.oeb.polish.check.base import BaseError, WARN, ERROR, INFO from calibre.ebooks.oeb.polish.check.base import BaseError, WARN, ERROR, INFO
from calibre.ebooks.oeb.base import OEB_DOCS from calibre.ebooks.oeb.base import OEB_DOCS, XHTML_NS
HTML_ENTITTIES = frozenset(html5_entities) HTML_ENTITTIES = frozenset(html5_entities)
XML_ENTITIES = {'lt', 'gt', 'amp', 'apos', 'quot'} XML_ENTITIES = {'lt', 'gt', 'amp', 'apos', 'quot'}
@ -79,6 +79,24 @@ class BadEntity(BaseError):
def __init__(self, ent, name, lnum, col): def __init__(self, ent, name, lnum, col):
BaseError.__init__(self, _('Invalid entity: %s') % ent, name, lnum, col) BaseError.__init__(self, _('Invalid entity: %s') % ent, name, lnum, col)
class BadNamespace(BaseError):
INDIVIDUAL_FIX = _(
'Run fix HTML on this file, which will automatically insert the correct namespace')
def __init__(self, name, namespace):
BaseError.__init__(self, _('Invalid or missing namespace'), name)
self.HELP = prepare_string_for_xml(_(
'This file has {0}. Its namespace must be {1}. Se the namespace by defining the xmlns'
' attribute on the <html> element, like this <html xmlns="{1}">').format(
(_('incorrect namespace %s') % namespace) if namespace else _('no namespace'),
XHTML_NS))
def __call__(self, container):
container.parsed(self.name)
container.dirty(self.name)
return True
class EntitityProcessor(object): class EntitityProcessor(object):
@ -138,7 +156,7 @@ def check_xml_parsing(name, mt, raw):
errors.append(BadEntity(ent, name, lnum, col)) errors.append(BadEntity(ent, name, lnum, col))
try: try:
fromstring(eraw, parser=parser) root = fromstring(eraw, parser=parser)
except XMLSyntaxError as err: except XMLSyntaxError as err:
try: try:
line, col = err.position line, col = err.position
@ -148,6 +166,9 @@ def check_xml_parsing(name, mt, raw):
except Exception as err: except Exception as err:
return errors + [errcls(err.message, name)] return errors + [errcls(err.message, name)]
if mt in OEB_DOCS and root.nsmap.get(root.prefix, None) != XHTML_NS:
errors.append(BadNamespace(name, root.nsmap.get(root.prefix, None)))
return errors return errors
class CSSError(BaseError): class CSSError(BaseError):

2
src/calibre/ebooks/oeb/polish/parsing.py
View File

@ -629,6 +629,8 @@ def parse(raw, decoder=None, log=None, line_numbers=True, linenumber_attribute=N
try: try:
parser = XMLParser(no_network=True) parser = XMLParser(no_network=True)
ans = fromstring(raw, parser=parser) ans = fromstring(raw, parser=parser)
if ans.tag != '{%s}html' % html_ns:
raise ValueError('Root tag is not <html> in the XHTML namespace')
if linenumber_attribute: if linenumber_attribute:
for elem in ans.iter(LxmlElement): for elem in ans.iter(LxmlElement):
if elem.sourceline is not None: if elem.sourceline is not None: