surname = parts[0]
names = []
elif len(parts) != 2:
- raise ValueError("Invalid person name. There should be at most one comma: \"%s\"." % text)
+ raise ValueError("Invalid person name. There should be at most one comma: \"%s\"." % text.encode('utf-8'))
else:
surname = parts[0]
if len(parts[1]) == 0:
# there is no non-whitespace data after the comma
raise ValueError("Found a comma, but no names given: \"%s\" -> %r." % (text, parts))
- names = [name for name in parts[1].split() if len(name)] # all non-whitespace tokens
+ names = parts[1].split()
return cls(surname, *names)
def readable(self):
Field(DCNS('type'), 'type', required=False, multiple=True),
Field(DCNS('contributor.editor'), 'editors',
- as_person, salias='editor', multiple=True, default=[]),
+ as_person, salias='editor', multiple=True, required=False),
Field(DCNS('contributor.technical_editor'), 'technical_editors',
- as_person, salias='technical_editor', multiple=True, default=[]),
- Field(DCNS('contributor.funding'), 'funders', salias='funder', multiple=True, default=[]),
+ as_person, salias='technical_editor', multiple=True, required=False),
+ Field(DCNS('contributor.funding'), 'funders', salias='funder', multiple=True, required=False),
Field(DCNS('contributor.thanks'), 'thanks', required=False),
Field(DCNS('date'), 'created_at'),
Field(DCNS('date.pd'), 'released_to_public_domain_at', as_date, required=False),
- Field(DCNS('publisher'), 'publisher'),
+ Field(DCNS('publisher'), 'publisher', multiple=True),
Field(DCNS('language'), 'language'),
Field(DCNS('description'), 'description', required=False),
Field(DCNS('rights.license'), 'license', required=False),
Field(DCNS('rights'), 'license_description'),
- Field(PLMETNS('digitisationSponsor'), 'sponsors', multiple=True, default=[]),
+ Field(PLMETNS('digitisationSponsor'), 'sponsors', multiple=True, required=False),
Field(WLNS('digitisationSponsorNote'), 'sponsor_note', required=False),
Field(WLNS('developmentStage'), 'stage', required=False),
)
text = text.decode('utf-8')
val = TextPlus(text)
val.lang = e.attrib.get(XMLNS('lang'), lang)
+ if e.tag == 'meta':
+ meta_id = e.attrib.get('id')
+ if meta_id and meta_id.endswith('-id'):
+ field_dict[meta_id] = [val.replace('ISBN-', 'ISBN ')]
else:
val = e.text
fv.append(val)
Field(DCNS('subject.period'), 'epochs', salias='epoch', multiple=True, required=False),
Field(DCNS('subject.type'), 'kinds', salias='kind', multiple=True, required=False),
Field(DCNS('subject.genre'), 'genres', salias='genre', multiple=True, required=False),
-
+
+ Field(DCNS('subject.location'), 'location', required=False),
+
Field(DCNS('contributor.translator'), 'translators',
- as_person, salias='translator', multiple=True, default=[]),
+ as_person, salias='translator', multiple=True, required=False),
Field(DCNS('relation.hasPart'), 'parts', WLURI, strict=as_wluri_strict, multiple=True, required=False),
Field(DCNS('relation.isVariantOf'), 'variant_of', WLURI, strict=as_wluri_strict, required=False),
# WLCover-specific.
Field(WLNS('coverBarColor'), 'cover_bar_color', required=False),
Field(WLNS('coverBoxPosition'), 'cover_box_position', required=False),
+ Field(WLNS('coverClass'), 'cover_class', default=['default']),
+ Field('pdf-id', 'isbn_pdf', required=False),
+ Field('epub-id', 'isbn_epub', required=False),
+ Field('mobi-id', 'isbn_mobi', required=False),
+ Field('txt-id', 'isbn_txt', required=False),
+ Field('html-id', 'isbn_html', required=False),
)