def info(self):
if not hasattr(self, '_info'):
from librarian import dcparser
from librarian import picture
info = dcparser.parse(self.xml_file.path, picture.PictureInfo)
self._info = info
return self._info
def info(self):
if not hasattr(self, '_info'):
from librarian import dcparser
from librarian import picture
info = dcparser.parse(self.xml_file.path, picture.PictureInfo)
self._info = info
return self._info
def from_xml_file(cls, xml_file, **kwargs):
# use librarian to parse meta-data
book_info = dcparser.parse(xml_file)
if not isinstance(xml_file, File):
xml_file = File(open(xml_file))
try:
return cls.from_text_and_meta(xml_file, book_info, **kwargs)
finally:
xml_file.close()
def from_xml_file(cls, xml_file, **kwargs):
from django.core.files import File
from librarian import dcparser
# use librarian to parse meta-data
book_info = dcparser.parse(xml_file)
if not isinstance(xml_file, File):
xml_file = File(open(xml_file))
try:
return cls.from_text_and_meta(xml_file, book_info, **kwargs)
finally:
xml_file.close()
def extract_metadata(self, book, book_info=None, dc_only=None):
"""
Extract metadata from book and returns a map of fields keyed by fieldname
"""
fields = {}
if book_info is None:
book_info = dcparser.parse(open(book.xml_file.path))
fields["slug"] = book.slug
fields["tags"] = [t.name for t in book.tags]
fields["is_book"] = True
# validator, name
for field in dcparser.BookInfo.FIELDS:
if dc_only and field.name not in dc_only:
continue
if hasattr(book_info, field.name):
if not getattr(book_info, field.name):
continue
# since no type information is available, we use validator
type_indicator = field.validator
if type_indicator == dcparser.as_unicode:
s = getattr(book_info, field.name)
if field.multiple:
s = ", ".join(s)
fields[field.name] = s
elif type_indicator == dcparser.as_person:
p = getattr(book_info, field.name)
if isinstance(p, dcparser.Person):
persons = unicode(p)
else:
persons = ", ".join(map(unicode, p))
fields[field.name] = persons
elif type_indicator == dcparser.as_date:
dt = getattr(book_info, field.name)
fields[field.name] = dt
# get published date
pd = None
if hasattr(book_info, "source_name") and book_info.source_name:
match = self.published_date_re.search(book_info.source_name)
if match is not None:
pd = str(match.groups()[0])
if not pd:
pd = ""
fields["published_date"] = pd
return fields
def extract_metadata(self, book, book_info=None, dc_only=None):
"""
Extract metadata from book and returns a map of fields keyed by fieldname
"""
fields = {}
if book_info is None:
book_info = dcparser.parse(open(book.xml_file.path))
fields['slug'] = book.slug
fields['tags'] = [t.name for t in book.tags]
fields['is_book'] = True
# validator, name
for field in dcparser.BookInfo.FIELDS:
if dc_only and field.name not in dc_only:
continue
if hasattr(book_info, field.name):
if not getattr(book_info, field.name):
continue
# since no type information is available, we use validator
type_indicator = field.validator
if type_indicator == dcparser.as_unicode:
s = getattr(book_info, field.name)
if field.multiple:
s = ', '.join(s)
fields[field.name] = s
elif type_indicator == dcparser.as_person:
p = getattr(book_info, field.name)
if isinstance(p, dcparser.Person):
persons = unicode(p)
else:
persons = ', '.join(map(unicode, p))
fields[field.name] = persons
elif type_indicator == dcparser.as_date:
dt = getattr(book_info, field.name)
fields[field.name] = dt
# get published date
pd = None
if hasattr(book_info, 'source_name') and book_info.source_name:
match = self.published_date_re.search(book_info.source_name)
if match is not None:
pd = str(match.groups()[0])
if not pd:
pd = ""
fields["published_date"] = pd
return fields
def rebuild_extra_info(apps, schema_editor):
Picture = apps.get_model("picture", "Picture")
from librarian.picture import PictureInfo
from librarian import dcparser
for pic in Picture.objects.all():
info = dcparser.parse(pic.xml_file.path, PictureInfo)
pic.extra_info = info.to_dict()
areas_json = pic.areas_json
for field in areas_json[u'things'].values():
field[u'object'] = field[u'object'].capitalize()
pic.areas_json = areas_json
html_text = unicode(render_to_string('picture/picture_info.html', {
'things': pic.areas_json['things'],
'themes': pic.areas_json['themes'],
}))
pic.html_file.save("%s.html" % pic.slug, ContentFile(html_text))
pic.save()
def check_load(xml_file):
pi = dcparser.parse(xml_file, picture.PictureInfo)
assert pi is not None
assert isinstance(pi, picture.PictureInfo)
def check_load(xml_file):
pi = dcparser.parse(xml_file, picture.PictureInfo)
assert pi is not None
assert isinstance(pi, picture.PictureInfo)
