X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/357027375ff8867f42ca34bcbfb5a78b5b185fc3..e15b74e6d8f736dfc8a6101e8b9c6583eebd7509:/src/oai/handlers.py diff --git a/src/oai/handlers.py b/src/oai/handlers.py index d9699f9fe..54a0a20bc 100644 --- a/src/oai/handlers.py +++ b/src/oai/handlers.py @@ -1,48 +1,50 @@ -# -*- coding: utf-8 -*- # This file is part of Wolnelektury, licensed under GNU Affero GPLv3 or later. # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. # -from oaipmh import server, common, metadata, error -from catalogue.models import Book, Tag -from api.models import Deleted -from api.handlers import WL_BASE -from librarian import WLURI -from django.contrib.contenttypes.models import ContentType from datetime import datetime from lxml import etree + from django.conf import settings +from django.contrib.contenttypes.models import ContentType from django.contrib.sites.models import Site from django.utils import timezone +from oaipmh import server, common, metadata, error + +from api.handlers import WL_BASE +from api.models import Deleted +from catalogue.models import Book +from librarian import WLURI -make_time_naive = lambda d: timezone.localtime(d).replace(tzinfo=None) +def make_time_naive(d): + return timezone.localtime(d).replace(tzinfo=None) WL_DC_READER_XPATH = '(.|*)/rdf:RDF/rdf:Description/%s/text()' wl_dc_reader = metadata.MetadataReader( fields={ - 'title': ('textList', WL_DC_READER_XPATH % 'dc:title'), - 'creator': ('textList', WL_DC_READER_XPATH % 'dc:creator'), - 'subject': ('textList', (WL_DC_READER_XPATH + ' | ' + WL_DC_READER_XPATH + ' | ' + WL_DC_READER_XPATH) % - ('dc:subject.period', 'dc:subject.type', 'dc:subject.genre')), - 'description': ('textList', WL_DC_READER_XPATH % 'dc:description'), - 'publisher': ('textList', WL_DC_READER_XPATH % 'dc:publisher'), - 'contributor': ('textList', (WL_DC_READER_XPATH + ' | ' + WL_DC_READER_XPATH + ' | ' + WL_DC_READER_XPATH) % - ('dc:contributor.editor', 'dc:contributor.translator', 'dc:contributor.technical_editor')), - 'date': ('textList', WL_DC_READER_XPATH % 'dc:date'), - 'type': ('textList', WL_DC_READER_XPATH % 'dc:type'), - 'format': ('textList', WL_DC_READER_XPATH % 'dc:format'), - 'identifier': ('textList', WL_DC_READER_XPATH % 'dc:identifier.url'), - 'source': ('textList', WL_DC_READER_XPATH % 'dc:source'), - 'language': ('textList', WL_DC_READER_XPATH % 'dc:language'), - #'isPartOf': ('textList', 'rdf:RDF/rdf:Description/dc:relation.isPartOf/text()'), - 'hasPart': ('textList', WL_DC_READER_XPATH % 'dc:relation.hasPart'), - # 'relation': ('textList', 'rdf:RDF/rdf:Description/dc:relation/text()'), - # 'coverage': ('textList', 'rdf:RDF/rdf:Description/dc:coverage/text()'), - 'rights': ('textList', WL_DC_READER_XPATH % 'dc:rights') + 'title': ('textList', WL_DC_READER_XPATH % 'dc:title'), + 'creator': ('textList', WL_DC_READER_XPATH % 'dc:creator'), + 'subject': ('textList', (WL_DC_READER_XPATH + ' | ' + WL_DC_READER_XPATH + ' | ' + WL_DC_READER_XPATH) % + ('dc:subject.period', 'dc:subject.type', 'dc:subject.genre')), + 'description': ('textList', WL_DC_READER_XPATH % 'dc:description'), + 'publisher': ('textList', WL_DC_READER_XPATH % 'dc:publisher'), + 'contributor': ('textList', (WL_DC_READER_XPATH + ' | ' + WL_DC_READER_XPATH + ' | ' + WL_DC_READER_XPATH) % + ('dc:contributor.editor', 'dc:contributor.translator', 'dc:contributor.technical_editor')), + 'date': ('textList', WL_DC_READER_XPATH % 'dc:date'), + 'type': ('textList', WL_DC_READER_XPATH % 'dc:type'), + 'format': ('textList', WL_DC_READER_XPATH % 'dc:format'), + 'identifier': ('textList', WL_DC_READER_XPATH % 'dc:identifier.url'), + 'source': ('textList', WL_DC_READER_XPATH % 'dc:source'), + 'language': ('textList', WL_DC_READER_XPATH % 'dc:language'), + # 'isPartOf': ('textList', 'rdf:RDF/rdf:Description/dc:relation.isPartOf/text()'), + 'hasPart': ('textList', WL_DC_READER_XPATH % 'dc:relation.hasPart'), + # 'relation': ('textList', 'rdf:RDF/rdf:Description/dc:relation/text()'), + # 'coverage': ('textList', 'rdf:RDF/rdf:Description/dc:coverage/text()'), + 'rights': ('textList', WL_DC_READER_XPATH % 'dc:rights') }, namespaces={ - 'dc': 'http://purl.org/dc/elements/1.1/', - 'rdf': 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'} + 'dc': 'http://purl.org/dc/elements/1.1/', + 'rdf': 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'} ) @@ -66,19 +68,20 @@ class Catalogue(common.ResumptionOAIPMH): year_zero = timezone.make_aware(datetime(1990, 1, 1, 0, 0, 0), timezone.utc) try: - earliest_change = \ - Book.objects.order_by('changed_at')[0].changed_at - except: earliest_change = year_zero + earliest_change = Book.objects.filter(findable=True, preview=False).order_by('changed_at')[0].changed_at + except IndexError: + earliest_change = year_zero try: earliest_delete = \ - Deleted.objects.exclude(slug__exact=u'').ordery_by('deleted_at')[0].deleted_at - except: earliest_delete = year_zero + Deleted.objects.exclude(slug__exact='').order_by('deleted_at')[0].deleted_at + except IndexError: + earliest_delete = year_zero - self.earliest_datestamp = earliest_change <= earliest_delete and \ - earliest_change or earliest_delete + self.earliest_datestamp = earliest_change if earliest_change <= earliest_delete else earliest_delete - def metadata(self, book): + @staticmethod + def metadata(book): try: xml = etree.parse(book.xml_file) finally: @@ -93,16 +96,18 @@ class Catalogue(common.ResumptionOAIPMH): meta = None identifier = self.slug_to_identifier(book.slug) if isinstance(book, Book): - # setSpec = map(self.tag_to_setspec, book.tags.filter(category__in=self.TAG_CATEGORIES)) - header = common.Header(identifier, make_time_naive(book.changed_at), [], False) + # setSpec = map(self.tag_to_setspec, book.tags.filter(category__in=self.TAG_CATEGORIES)) + header = common.Header(None, identifier, make_time_naive(book.changed_at), [], False) if not headers_only: - meta = common.Metadata(self.metadata(book)) + meta = common.Metadata(None, self.metadata(book)) about = None elif isinstance(book, Deleted): - header = common.Header(identifier, make_time_naive(book.deleted_at), [], True) + header = common.Header(None, identifier, make_time_naive(book.deleted_at), [], True) if not headers_only: - meta = common.Metadata({}) + meta = common.Metadata(None, {}) about = None + else: + raise TypeError('Unknown book class') if headers_only: return header return header, meta, about @@ -110,7 +115,7 @@ class Catalogue(common.ResumptionOAIPMH): def identify(self, **kw): ident = common.Identify( 'Wolne Lektury', # generate - '%s/oaipmh' % unicode(WL_BASE), # generate + '%s/oaipmh' % str(WL_BASE), # generate '2.0', # version [m[1] for m in settings.MANAGERS], # adminEmails make_time_naive(self.earliest_datestamp), # earliest datestamp of any change @@ -127,8 +132,8 @@ class Catalogue(common.ResumptionOAIPMH): raise error.NoSetHierarchyError("Wolne Lektury does not support sets.") # books = Book.tagged.with_all([tag]) else: - books = Book.objects.all() - deleted = Deleted.objects.exclude(slug__exact=u'') + books = Book.objects.filter(findable=True, preview=False) + deleted = Deleted.objects.exclude(slug__exact='') books = books.order_by('changed_at') deleted = deleted.order_by('deleted_at') @@ -140,25 +145,23 @@ class Catalogue(common.ResumptionOAIPMH): deleted = deleted.filter(deleted_at__lte=until) return list(books) + list(deleted) - @staticmethod - def tag_to_setspec(tag): - return "%s:%s" % (tag.category, tag.slug) - - @staticmethod - def setspec_to_tag(s): - if not s: return None - cs = s.split(':') - if len(cs) == 2: - if not cs[0] in Catalogue.TAG_CATEGORIES: - raise error.NoSetHierarchyError("No category part in set") - tag = Tag.objects.get(slug=cs[1], category=cs[0]) - return tag - raise error.NoSetHierarchyError("Setspec should have two components: category:slug") + # @staticmethod + # def tag_to_setspec(tag): + # return "%s:%s" % (tag.category, tag.slug) + + # @staticmethod + # def setspec_to_tag(s): + # if not s: return None + # cs = s.split(':') + # if len(cs) == 2: + # if not cs[0] in Catalogue.TAG_CATEGORIES: + # raise error.NoSetHierarchyError("No category part in set") + # tag = Tag.objects.get(slug=cs[1], category=cs[0]) + # return tag + # raise error.NoSetHierarchyError("Setspec should have two components: category:slug") def getRecord(self, **kw): - """ -Returns (header, metadata, about) for given record. - """ + """Returns (header, metadata, about) for given record.""" slug = self.identifier_to_slug(kw['identifier']) try: book = Book.objects.get(slug=slug) @@ -166,8 +169,7 @@ Returns (header, metadata, about) for given record. except Book.DoesNotExist: book_type = ContentType.objects.get_for_model(Book) try: - deleted_book = Deleted.objects.get(content_type=book_type, - slug=slug) + deleted_book = Deleted.objects.get(content_type=book_type, slug=slug) except: raise error.IdDoesNotExistError("No item for this identifier") return self.record_for_book(deleted_book) @@ -187,15 +189,13 @@ Returns (header, metadata, about) for given record. def listIdentifiers(self, **kw): self.validate_kw(kw) records = [self.record_for_book(book, headers_only=True) for - book in self.books(None, - kw.get('from_', None), - kw.get('until', None))] + book in self.books(None, kw.get('from_'), kw.get('until'))] return records, None def listRecords(self, **kw): """ -can get a resumptionToken kw. -returns result, token + can get a resumptionToken kw. + returns result, token """ self.validate_kw(kw) records = [self.record_for_book(book) for @@ -216,13 +216,13 @@ returns result, token if 'identifier' in kw: slug = self.identifier_to_slug(kw['identifier']) try: - b = Book.objects.get(slug=slug) + Book.objects.get(slug=slug) return formats - except: + except Book.DoesNotExist: try: - d = Deleted.objects.get(slug=slug) + Deleted.objects.get(slug=slug) return [] - except: + except Deleted.DoesNotExist: raise error.IdDoesNotExistError("This id does not exist") else: return formats