def __init__(self, name, eid, locs):
BaseError.__init__(self, _('Duplicate id: %s') % eid, name)
self.HELP = _(
'The id {0} is present on more than one element in {1}. This is'
' not allowed. Remove the id from all but one of the elements').format(eid, name)
self.all_locations = [(name, lnum, None) for lnum in sorted(locs)]
self.duplicate_id = eid
def __init__(self, msg, *args, **kwargs):
msg = msg or ''
BaseError.__init__(self, 'Parsing failed: ' + msg, *args, **kwargs)
m = mismatch_pat.search(msg)
if m is not None:
self.has_multiple_locations = True
self.all_locations = [(self.name, int(m.group(1)), None), (self.name, self.line, self.col)]
def __init__(self, link_source, link_dest, link_elem, fragment):
BaseError.__init__(self, _('Link points to a location not present in the target file'), link_source, line=link_elem.sourceline)
self.bad_href = link_elem.get('href')
self.HELP = _('The link "{0}" points to a location <i>{1}</i> in the file {2} that does not exist.'
' You should either remove the location so that the link points to the top of the file,'
' or change the link to point to the correct location.').format(
self.bad_href, fragment, link_dest)
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}. Set 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 __init__(self, font_name, css_name, name, line):
BaseError.__init__(self, _('The CSS font-family name {0} does not match the actual font name {1}').format(css_name, font_name), name, line)
self.HELP = _('The font family name specified in the CSS @font-face rule: "{0}" does'
' not match the font name inside the actual font file: "{1}". This can'
' cause problems in some viewers. You should change the CSS font name'
' to match the actual font name.').format(css_name, font_name)
self.INDIVIDUAL_FIX = _('Change the font name {0} to {1} everywhere').format(css_name, font_name)
self.font_name, self.css_name = font_name, css_name
def __init__(self, name, lnum, bad_idref=None, bad_mimetype=None):
if bad_idref is not None:
msg = _('The item identified as the Table of Contents (%s) does not exist') % bad_idref
self.HELP = _('There is no item with id="%s" in the manifest.') % bad_idref
else:
msg = _('The item identified as the Table of Contents has an incorrect media-type (%s)') % bad_mimetype
self.HELP = _('The media type for the table of contents must be %s') % guess_type('a.ncx')
BaseError.__init__(self, msg, name, lnum)
def __init__(self, name, line, eid):
BaseError.__init__(self, _('Invalid id: %s') % eid, name, line)
self.HELP = _(
'The id {0} is not a valid id. IDs must start with a letter ([A-Za-z]) and may be'
' followed by any number of letters, digits ([0-9]), hyphens ("-"), underscores ("_")'
', colons (":"), and periods ("."). This is to ensure maximum compatibility'
' with a wide range of devices.').format(eid)
self.invalid_id = eid
def __init__(self, link_source, link_dest, link_elem):
BaseError.__init__(self, _('Link points to a file that is not a text document'), link_source, line=link_elem.sourceline)
self.HELP = _('The link "{0}" points to a file <i>{1}</i> that is not a text (HTML) document.'
' Many ebook readers will be unable to follow such a link. You should'
' either remove the link or change it to point to a text document.'
' For example, if it points to an image, you can create small wrapper'
' document that contains the image and change the link to point to that.').format(
link_elem.get('href'), link_dest)
self.bad_href = link_elem.get('href')
def __init__(self, container, name, opf_mt, ext_mt):
self.opf_mt, self.ext_mt = opf_mt, ext_mt
self.file_name = name
BaseError.__init__(self, _('The file %s has a mimetype that does not match its extension') % name, container.opf_name)
ext = name.rpartition('.')[-1]
self.HELP = _('The file {0} has its mimetype specified as {1} in the OPF file.'
' The recommended mimetype for files with the extension "{2}" is {3}.'
' You should change either the file extension or the mimetype in the OPF.').format(
name, opf_mt, ext, ext_mt)
self.INDIVIDUAL_FIX = _('Change the mimetype for this file in the OPF to %s') % ext_mt
def __init__(self, name, eid, locs, for_spine=False):
loc = 'spine' if for_spine else 'manifest'
BaseError.__init__(self, _('Duplicate item in {0}: {1}').format(loc, eid), name)
self.HELP = _(
'The item {0} is present more than once in the {2} in {1}. This is'
' not allowed.').format(eid, name, loc)
self.all_locations = [(name, lnum, None) for lnum in sorted(locs)]
self.duplicate_href = eid
self.xpath = '/opf:package/opf:' + ('spine/opf:itemref[@idref]' if for_spine else 'manifest/opf:item[@href]')
self.attr = 'idref' if for_spine else 'href'
def __init__(self, name, enc):
BaseError.__init__(self, _("Non UTF-8 encoding declaration"), name)
self.HELP = (
_(
"This file has its encoding declared as %s. Some"
" reader software cannot handle non-UTF8 encoded files."
" You should change the encoding to UTF-8."
)
% enc
)
def __init__(self, name, iid, mt, lnum, opf_name):
BaseError.__init__(self, _('Incorrect media-type for spine item'), opf_name, lnum)
self.HELP = _(
'The item {0} present in the spine has the media-type {1}. '
' Most ebook software cannot handle non-HTML spine items. '
' If the item is actually HTML, you should change its media-type to {2}.'
' If it is not-HTML you should consider replacing it with an HTML item, as it'
' is unlikely to work in most readers.').format(name, mt, XHTML_MIME)
if iid is not None:
self.INDIVIDUAL_FIX = _('Change the media-type to %s') % XHTML_MIME
self.iid = iid
def __init__(self, name):
BaseError.__init__(self, _('Filename contains unsafe characters'), name)
qname = urlquote(name)
self.sname = make_filename_safe(name)
self.HELP = _(
'The filename {0} contains unsafe characters, that must be escaped, like'
' this {1}. This can cause problems with some e-book readers. To be'
' absolutely safe, use only the English alphabet [a-z], the numbers [0-9],'
' underscores and hyphens in your file names. While many other characters'
' are allowed, they may cause problems with some software.').format(name, qname)
self.INDIVIDUAL_FIX = _(
'Rename the file {0} to {1}').format(name, self.sname)
def __init__(self, name):
from calibre.utils.filenames import ascii_filename
BaseError.__init__(self, _('Filename contains unsafe characters'), name)
qname = urlquote(name)
def esc(n):
return ''.join(x if x in URL_SAFE else '_' for x in n)
self.sname = '/'.join(esc(ascii_filename(x)) for x in name.split('/'))
self.HELP = _(
'The filename {0} contains unsafe characters, that must be escaped, like'
' this {1}. This can cause problems with some ebook readers. To be'
' absolutely safe, use only the English alphabet [a-z], the numbers [0-9],'
' underscores and hyphens in your file names. While many other characters'
' are allowed, they may cause problems with some software.').format(name, qname)
self.INDIVIDUAL_FIX = _(
'Rename the file {0} to {1}').format(name, self.sname)
def __init__(self, level, msg, name, line, col):
self.level = level
prefix = 'CSS: '
BaseError.__init__(self, prefix + msg, name, line, col)
if level == WARN:
self.HELP = _('This CSS construct is not recognized. That means that it'
' most likely will not work on reader devices. Consider'
' replacing it with something else.')
else:
self.HELP = _('Some reader programs are very'
' finicky about CSS stylesheets and will ignore the whole'
' sheet if there is an error. These errors can often'
' be fixed automatically, however, automatic fixing will'
' typically remove unrecognized items, instead of correcting them.')
self.INDIVIDUAL_FIX = _('Try to fix parsing errors in this stylesheet automatically')
def __init__(self, container, name, opf_mt, ext_mt):
self.opf_mt, self.ext_mt = opf_mt, ext_mt
self.file_name = name
BaseError.__init__(
self, _("The file %s has a mimetype that does not match its extension") % name, container.opf_name
)
ext = name.rpartition(".")[-1]
self.HELP = _(
"The file {0} has its mimetype specified as {1} in the OPF file."
' The recommended mimetype for files with the extension "{2}" is {3}.'
" You should change either the file extension or the mimetype in the OPF."
).format(name, opf_mt, ext, ext_mt)
if opf_mt in OEB_DOCS and name in {n for n, l in container.spine_names}:
self.INDIVIDUAL_FIX = _("Change the file extension to .xhtml")
self.change_ext_to = "xhtml"
else:
self.INDIVIDUAL_FIX = _("Change the mimetype for this file in the OPF to %s") % ext_mt
self.change_ext_to = None
def __init__(self, container, name, opf_mt, ext_mt):
self.opf_mt, self.ext_mt = opf_mt, ext_mt
self.file_name = name
BaseError.__init__(
self,
_('The file %s has a mimetype that does not match its extension') %
name, container.opf_name)
ext = name.rpartition('.')[-1]
self.HELP = _(
'The file {0} has its mimetype specified as {1} in the OPF file.'
' The recommended mimetype for files with the extension "{2}" is {3}.'
' You should change either the file extension or the mimetype in the OPF.'
).format(name, opf_mt, ext, ext_mt)
if opf_mt in OEB_DOCS and name in {
n
for n, l in container.spine_names
}:
self.INDIVIDUAL_FIX = _('Change the file extension to .xhtml')
self.change_ext_to = 'xhtml'
else:
self.INDIVIDUAL_FIX = _(
'Change the mimetype for this file in the OPF to %s') % ext_mt
self.change_ext_to = None
def __init__(self, name, enc):
BaseError.__init__(self, _('Non UTF-8 encoding declaration'), name)
self.HELP = _('This file has its encoding declared as %s. Some'
' reader software cannot handle non-UTF8 encoded files.'
' You should change the encoding to UTF-8.') % enc
def __init__(self, name, item_id, lnum):
BaseError.__init__(self, _('Item in manifest has no href attribute'), name, lnum)
self.item_id = item_id
def __init__(self, ent, name, lnum, col):
BaseError.__init__(self, _('Invalid entity: %s') % ent, name, lnum, col)
def __init__(self, ent, name, lnum, col):
BaseError.__init__(self, _('Invalid entity: %s') % ent, name, lnum, col)
def __init__(self, name, enc):
BaseError.__init__(self, _('Non UTF-8 encoding declaration'), name)
self.HELP = _('This file has its encoding declared as %s. Some'
' reader software cannot handle non-UTF8 encoded files.'
' You should change the encoding to UTF-8.') % enc
def __init__(self, name, idref, lnum):
BaseError.__init__(self, _('idref="%s" points to unknown id') % idref, name, lnum)
self.HELP = xml(_(
'The idref="%s" points to an id that does not exist in the OPF') % idref)
def __init__(self, msg, *args, **kwargs):
BaseError.__init__(self, 'Invalid image: ' + msg, *args, **kwargs)
def __init__(self, name):
BaseError.__init__(self, _('The file %s is empty') % name, name)
def __init__(self, name):
BaseError.__init__(self, _('Parsing of %s failed, could not decode') % name, name)
def __init__(self, name, lnum):
BaseError.__init__(self, _('Empty identifier element'), name, lnum)
def __init__(self, name):
BaseError.__init__(self, _('The file %s is empty') % name, name)
def __init__(self, name, section_name):
BaseError.__init__(self, _('The <%s> section is missing from the OPF') % section_name, name)
self.HELP = xml(_(
'The <%s> section is required in the OPF file. You have to create one.') % section_name)
def __init__(self, name, href, lnum):
BaseError.__init__(self, _('Item (%s) in manifest is missing') % href, name, lnum)
self.bad_href = href
self.INDIVIDUAL_FIX = _('Remove the entry for %s from the manifest') % href
def __init__(self, name, lnum):
BaseError.__init__(self, _('Missing ToC in navigation document'), name, lnum)
def __init__(self, name, lnum, ncx_id):
BaseError.__init__(self, _('Missing reference to the NCX Table of Contents'), name, lnum)
self.ncx_id = ncx_id
def __init__(self, name, lnum, ncx_id):
BaseError.__init__(self, _('Missing reference to the NCX Table of Contents'), name, lnum)
self.ncx_id = ncx_id
def __init__(self, name, lines):
BaseError.__init__(self, _('Bare text in body tag'), name)
self.all_locations = [(name, l, None) for l in sorted(lines)]
def __init__(self, name):
BaseError.__init__(self, _('Named entities present'), name)
def __init__(self, name):
BaseError.__init__(self, _('Named entities present'), name)
def __init__(self, name, locs):
BaseError.__init__(self, _('There is more than one cover defined'),
name)
self.all_locations = [(name, lnum, None) for lnum in sorted(locs)]
def check_opf(container):
errors = []
opf_version = container.opf_version_parsed
if container.opf.tag != OPF('package'):
err = BaseError(_('The OPF does not have the correct root element'), container.opf_name, container.opf.sourceline)
err.HELP = xml(_(
'The opf must have the root element <package> in namespace {0}, like this: <package xmlns="{0}">')).format(OPF2_NS)
errors.append(err)
elif container.opf.get('version') is None and container.book_type == 'epub':
err = BaseError(_('The OPF does not have a version'), container.opf_name, container.opf.sourceline)
err.HELP = xml(_(
'The <package> tag in the OPF must have a version attribute. This is usually version="2.0" for EPUB2 and AZW3 and version="3.0" for EPUB3'))
errors.append(err)
for tag in ('metadata', 'manifest', 'spine'):
if not container.opf_xpath('/opf:package/opf:' + tag):
errors.append(MissingSection(container.opf_name, tag))
all_ids = set(container.opf_xpath('//*/@id'))
for elem in container.opf_xpath('//*[@idref]'):
if elem.get('idref') not in all_ids:
errors.append(IncorrectIdref(container.opf_name, elem.get('idref'), elem.sourceline))
nl_items = [elem.sourceline for elem in container.opf_xpath('//opf:spine/opf:itemref[@linear="no"]')]
if nl_items:
errors.append(NonLinearItems(container.opf_name, nl_items))
seen, dups = {}, {}
for item in container.opf_xpath('/opf:package/opf:manifest/opf:item'):
href = item.get('href', None)
if href is None:
errors.append(NoHref(container.opf_name, item.get('id', None), item.sourceline))
else:
hname = container.href_to_name(href, container.opf_name)
if not hname or not container.exists(hname):
errors.append(MissingHref(container.opf_name, href, item.sourceline))
if href in seen:
if href not in dups:
dups[href] = [seen[href]]
dups[href].append(item.sourceline)
else:
seen[href] = item.sourceline
errors.extend(DuplicateHref(container.opf_name, eid, locs) for eid, locs in dups.iteritems())
seen, dups = {}, {}
for item in container.opf_xpath('/opf:package/opf:spine/opf:itemref[@idref]'):
ref = item.get('idref')
if ref in seen:
if ref not in dups:
dups[ref] = [seen[ref]]
dups[ref].append(item.sourceline)
else:
seen[ref] = item.sourceline
errors.extend(DuplicateHref(container.opf_name, eid, locs, for_spine=True) for eid, locs in dups.iteritems())
spine = container.opf_xpath('/opf:package/opf:spine[@toc]')
if spine:
spine = spine[0]
mitems = [x for x in container.opf_xpath('/opf:package/opf:manifest/opf:item[@id]') if x.get('id') == spine.get('toc')]
if mitems:
mitem = mitems[0]
if mitem.get('media-type', '') != guess_type('a.ncx'):
errors.append(IncorrectToc(container.opf_name, mitem.sourceline, bad_mimetype=mitem.get('media-type')))
else:
errors.append(IncorrectToc(container.opf_name, spine.sourceline, bad_idref=spine.get('toc')))
else:
spine = container.opf_xpath('/opf:package/opf:spine')
if spine:
spine = spine[0]
ncx = container.manifest_type_map.get(guess_type('a.ncx'))
if ncx:
ncx_name = ncx[0]
rmap = {v:k for k, v in container.manifest_id_map.iteritems()}
ncx_id = rmap.get(ncx_name)
if ncx_id:
errors.append(MissingNCXRef(container.opf_name, spine.sourceline, ncx_id))
if opf_version.major > 2:
if find_existing_nav_toc(container) is None:
errors.append(MissingNav(container.opf_name, 0))
covers = container.opf_xpath('/opf:package/opf:metadata/opf:meta[@name="cover"]')
if len(covers) > 0:
if len(covers) > 1:
errors.append(MultipleCovers(container.opf_name, [c.sourceline for c in covers]))
manifest_ids = set(container.opf_xpath('/opf:package/opf:manifest/opf:item/@id'))
for cover in covers:
if cover.get('content', None) not in manifest_ids:
errors.append(IncorrectCover(container.opf_name, cover.sourceline, cover.get('content', '')))
raw = etree.tostring(cover)
try:
n, c = raw.index('name="'), raw.index('content="')
except ValueError:
n = c = -1
if n > -1 and c > -1 and n > c:
errors.append(NookCover(container.opf_name, cover.sourceline))
uid = container.opf.get('unique-identifier', None)
if uid is None or not container.opf_xpath('/opf:package/opf:metadata/dc:identifier[@id=%r]' % uid):
errors.append(NoUID(container.opf_name))
for item, name, linear in container.spine_iter:
mt = container.mime_map[name]
if mt != XHTML_MIME:
iid = item.get('idref', None)
lnum = None
if iid:
mitem = container.opf_xpath('/opf:package/opf:manifest/opf:item[@id=%r]' % iid)
if mitem:
lnum = mitem[0].sourceline
else:
iid = None
errors.append(BadSpineMime(name, iid, mt, lnum, container.opf_name))
return errors
def check_opf(container):
errors = []
if container.opf.tag != OPF('package'):
err = BaseError(_('The OPF does not have the correct root element'),
container.opf_name)
err.HELP = xml(
_('The opf must have the root element <package> in namespace {0}, like this: <package xmlns="{0}">'
)).format(OPF2_NS)
errors.append(err)
for tag in ('metadata', 'manifest', 'spine'):
if not container.opf_xpath('/opf:package/opf:' + tag):
errors.append(MissingSection(container.opf_name, tag))
all_ids = set(container.opf_xpath('//*/@id'))
for elem in container.opf_xpath('//*[@idref]'):
if elem.get('idref') not in all_ids:
errors.append(
IncorrectIdref(container.opf_name, elem.get('idref'),
elem.sourceline))
nl_items = [
elem.sourceline for elem in container.opf_xpath(
'//opf:spine/opf:itemref[@linear="no"]')
]
if nl_items:
errors.append(NonLinearItems(container.opf_name, nl_items))
seen, dups = {}, {}
for item in container.opf_xpath(
'/opf:package/opf:manifest/opf:item[@href]'):
href = item.get('href')
if not container.exists(
container.href_to_name(href, container.opf_name)):
errors.append(
MissingHref(container.opf_name, href, item.sourceline))
if href in seen:
if href not in dups:
dups[href] = [seen[href]]
dups[href].append(item.sourceline)
else:
seen[href] = item.sourceline
errors.extend(
DuplicateHref(container.opf_name, eid, locs)
for eid, locs in dups.iteritems())
seen, dups = {}, {}
for item in container.opf_xpath(
'/opf:package/opf:spine/opf:itemref[@idref]'):
ref = item.get('idref')
if ref in seen:
if ref not in dups:
dups[ref] = [seen[ref]]
dups[ref].append(item.sourceline)
else:
seen[ref] = item.sourceline
errors.extend(
DuplicateHref(container.opf_name, eid, locs, for_spine=True)
for eid, locs in dups.iteritems())
spine = container.opf_xpath('/opf:package/opf:spine[@toc]')
if spine:
spine = spine[0]
mitems = [
x for x in container.opf_xpath(
'/opf:package/opf:manifest/opf:item[@id]')
if x.get('id') == spine.get('toc')
]
if mitems:
mitem = mitems[0]
if mitem.get('media-type', '') != guess_type('a.ncx'):
errors.append(
IncorrectToc(container.opf_name,
mitem.sourceline,
bad_mimetype=mitem.get('media-type')))
else:
errors.append(
IncorrectToc(container.opf_name,
spine.sourceline,
bad_idref=spine.get('toc')))
covers = container.opf_xpath(
'/opf:package/opf:metadata/opf:meta[@name="cover"]')
if len(covers) > 0:
if len(covers) > 1:
errors.append(
MultipleCovers(container.opf_name,
[c.sourceline for c in covers]))
manifest_ids = set(
container.opf_xpath('/opf:package/opf:manifest/opf:item/@id'))
for cover in covers:
if cover.get('content', None) not in manifest_ids:
errors.append(
IncorrectCover(container.opf_name, cover.sourceline,
cover.get('content', '')))
raw = etree.tostring(cover)
try:
n, c = raw.index('name="'), raw.index('content="')
except ValueError:
n = c = -1
if n > -1 and c > -1 and n > c:
errors.append(NookCover(container.opf_name, cover.sourceline))
uid = container.opf.get('unique-identifier', None)
if uid is None or not container.opf_xpath(
'/opf:package/opf:metadata/dc:identifier[@id=%r]' % uid):
errors.append(NoUID(container.opf_name))
for item, name, linear in container.spine_iter:
mt = container.mime_map[name]
if mt != XHTML_MIME:
iid = item.get('idref', None)
lnum = None
if iid:
mitem = container.opf_xpath(
'/opf:package/opf:manifest/opf:item[@id=%r]' % iid)
if mitem:
lnum = mitem[0].sourceline
else:
iid = None
errors.append(BadSpineMime(name, iid, mt, lnum,
container.opf_name))
return errors
def __init__(self, name):
BaseError.__init__(self, _('File too large'), name)
def __init__(self, name, fs_type):
BaseError.__init__(self, _('The font {} is not allowed to be embedded').format(name), name)
self.HELP = _('The font has a flag in its metadata ({:09b}) set indicating that it is'
' not licensed for embedding. You can ignore this warning, if you are'
' sure you have permission to embed this font.').format(fs_type)
def __init__(self, name, lnum, cover):
BaseError.__init__(self, _('The meta cover tag points to an non-existent item'), name, lnum)
self.HELP = xml(_(
'The meta cover tag points to an item with id="%s" which does not exist in the manifest') % cover)
def __init__(self, name):
BaseError.__init__(self, _('File too large'), name)
def __init__(self, name):
BaseError.__init__(self, _('Parsing of %s failed, could not decode') % name, name)
def __init__(self, name, lnum):
BaseError.__init__(self, _('The meta cover tag has content before name'), name, lnum)
def __init__(self, name, lnum):
BaseError.__init__(self, _('Empty id attributes are invalid'), name, lnum)
self.HELP = xml(_(
'Empty ID attributes are invalid in OPF files.'))
def __init__(self, msg, *args, **kwargs):
BaseError.__init__(self, 'Parsing failed: ' + msg, *args, **kwargs)
def __init__(self, name, lines):
BaseError.__init__(self, _('Bare text in body tag'), name)
self.all_locations = [(name, l, None) for l in sorted(lines)]
def check_opf(container):
errors = []
opf_version = container.opf_version_parsed
if container.opf.tag != OPF('package'):
err = BaseError(_('The OPF does not have the correct root element'), container.opf_name, container.opf.sourceline)
err.HELP = xml(_(
'The opf must have the root element <package> in namespace {0}, like this: <package xmlns="{0}">')).format(OPF2_NS)
errors.append(err)
elif container.opf.get('version') is None and container.book_type == 'epub':
err = BaseError(_('The OPF does not have a version'), container.opf_name, container.opf.sourceline)
err.HELP = xml(_(
'The <package> tag in the OPF must have a version attribute. This is usually version="2.0" for EPUB2 and AZW3 and version="3.0" for EPUB3'))
errors.append(err)
for tag in ('metadata', 'manifest', 'spine'):
if not container.opf_xpath('/opf:package/opf:' + tag):
errors.append(MissingSection(container.opf_name, tag))
all_ids = set(container.opf_xpath('//*/@id'))
if '' in all_ids:
for empty_id_tag in container.opf_xpath('//*[@id=""]'):
errors.append(EmptyID(container.opf_name, empty_id_tag.sourceline))
all_ids.discard('')
for elem in container.opf_xpath('//*[@idref]'):
if elem.get('idref') not in all_ids:
errors.append(IncorrectIdref(container.opf_name, elem.get('idref'), elem.sourceline))
nl_items = [elem.sourceline for elem in container.opf_xpath('//opf:spine/opf:itemref[@linear="no"]')]
if nl_items:
errors.append(NonLinearItems(container.opf_name, nl_items))
seen, dups = {}, {}
for item in container.opf_xpath('/opf:package/opf:manifest/opf:item'):
href = item.get('href', None)
if href is None:
errors.append(NoHref(container.opf_name, item.get('id', None), item.sourceline))
else:
hname = container.href_to_name(href, container.opf_name)
if not hname or not container.exists(hname):
errors.append(MissingHref(container.opf_name, href, item.sourceline))
if href in seen:
if href not in dups:
dups[href] = [seen[href]]
dups[href].append(item.sourceline)
else:
seen[href] = item.sourceline
errors.extend(DuplicateHref(container.opf_name, eid, locs) for eid, locs in iteritems(dups))
seen, dups = {}, {}
for item in container.opf_xpath('/opf:package/opf:spine/opf:itemref[@idref]'):
ref = item.get('idref')
if ref in seen:
if ref not in dups:
dups[ref] = [seen[ref]]
dups[ref].append(item.sourceline)
else:
seen[ref] = item.sourceline
errors.extend(DuplicateHref(container.opf_name, eid, locs, for_spine=True) for eid, locs in iteritems(dups))
spine = container.opf_xpath('/opf:package/opf:spine[@toc]')
if spine:
spine = spine[0]
mitems = [x for x in container.opf_xpath('/opf:package/opf:manifest/opf:item[@id]') if x.get('id') == spine.get('toc')]
if mitems:
mitem = mitems[0]
if mitem.get('media-type', '') != guess_type('a.ncx'):
errors.append(IncorrectToc(container.opf_name, mitem.sourceline, bad_mimetype=mitem.get('media-type')))
else:
errors.append(IncorrectToc(container.opf_name, spine.sourceline, bad_idref=spine.get('toc')))
else:
spine = container.opf_xpath('/opf:package/opf:spine')
if spine:
spine = spine[0]
ncx = container.manifest_type_map.get(guess_type('a.ncx'))
if ncx:
ncx_name = ncx[0]
rmap = {v:k for k, v in iteritems(container.manifest_id_map)}
ncx_id = rmap.get(ncx_name)
if ncx_id:
errors.append(MissingNCXRef(container.opf_name, spine.sourceline, ncx_id))
if opf_version.major > 2:
existing_nav = find_existing_nav_toc(container)
if existing_nav is None:
errors.append(MissingNav(container.opf_name, 0))
else:
toc = parse_nav(container, existing_nav)
if len(toc) == 0:
errors.append(EmptyNav(existing_nav, 0))
covers = container.opf_xpath('/opf:package/opf:metadata/opf:meta[@name="cover"]')
if len(covers) > 0:
if len(covers) > 1:
errors.append(MultipleCovers(container.opf_name, [c.sourceline for c in covers]))
manifest_ids = set(container.opf_xpath('/opf:package/opf:manifest/opf:item/@id'))
for cover in covers:
if cover.get('content', None) not in manifest_ids:
errors.append(IncorrectCover(container.opf_name, cover.sourceline, cover.get('content', '')))
raw = etree.tostring(cover)
try:
n, c = raw.index(b'name="'), raw.index(b'content="')
except ValueError:
n = c = -1
if n > -1 and c > -1 and n > c:
errors.append(NookCover(container.opf_name, cover.sourceline))
uid = container.opf.get('unique-identifier', None)
if uid is None or not container.opf_xpath('/opf:package/opf:metadata/dc:identifier[@id=%r]' % uid):
errors.append(NoUID(container.opf_name))
for elem in container.opf_xpath('/opf:package/opf:metadata/dc:identifier'):
if not elem.text or not elem.text.strip():
errors.append(EmptyIdentifier(container.opf_name, elem.sourceline))
for item, name, linear in container.spine_iter:
mt = container.mime_map[name]
if mt != XHTML_MIME:
iid = item.get('idref', None)
lnum = None
if iid:
mitem = container.opf_xpath('/opf:package/opf:manifest/opf:item[@id=%r]' % iid)
if mitem:
lnum = mitem[0].sourceline
else:
iid = None
errors.append(BadSpineMime(name, iid, mt, lnum, container.opf_name))
return errors
def __init__(self, name, idref, lnum):
BaseError.__init__(self, _('idref="%s" points to unknown id') % idref, name, lnum)
self.HELP = xml(_(
'The idref="%s" points to an id that does not exist in the OPF') % idref)
def __init__(self, name, lnum, cover):
BaseError.__init__(self, _('The meta cover tag points to an non-existent item'), name, lnum)
self.HELP = xml(_(
'The meta cover tag points to an item with id="%s" which does not exist in the manifest') % cover)
def __init__(self, name, locs):
BaseError.__init__(self, _('Non-linear items in the spine'), name)
self.all_locations = [(name, x, None) for x in locs]
def __init__(self, name, item_id, lnum):
BaseError.__init__(self, _('Item in manifest has no href attribute'), name, lnum)
self.item_id = item_id
def __init__(self, name):
BaseError.__init__(self, _('The OPF has no unique identifier'), name)
def __init__(self, msg, *args, **kwargs):
BaseError.__init__(self, 'Invalid image: ' + msg, *args, **kwargs)
def __init__(self, name, lnum):
BaseError.__init__(self,
_('The meta cover tag has content before name'),
name, lnum)
def __init__(self, msg, *args, **kwargs):
BaseError.__init__(self, 'Parsing failed: ' + msg, *args, **kwargs)
m = mismatch_pat.search(msg)
if m is not None:
self.has_multiple_locations = True
self.all_locations = [(self.name, int(m.group(1)), None), (self.name, self.line, self.col)]