def test_mods_add_topic_already_exists(self):
#if the topic already exists, just return and don't do anything
mods_obj = mods.make_mods()
mods_obj.title = 'title'
mods_obj.subjects.append(mods.Subject(topic='random'))
mods.add_topic(mods_obj, 'random')
self.assertEqual(len(mods_obj.subjects), 1)
self.assertEqual(mods_obj.subjects[0].topic, 'random')
def test_mods_add_topic_incompatible(self):
#if topic is there, but with different label or authority info, raise an exception
mods_obj = mods.make_mods()
mods_obj.title = 'title'
mods_obj.subjects.append(mods.Subject(topic='random', label='label1'))
with self.assertRaises(Exception) as cm:
mods.add_topic(mods_obj, 'random', label='label2')
self.assertEqual(str(cm.exception), 'mods object already has topic "random"')
def _initialize_mods( self, mods_id ):
""" Initialize empty self.mods element; also sets namespace reference.
Switching from previous straight etree.Element() build for better bdr compatibility going forward. """
MODS_NAMESPACE = 'http://www.loc.gov/mods/v3'
self.MODS = '{%s}' % MODS_NAMESPACE
bdrxml_mods_obj = mods.make_mods()
utf8_xml = bdrxml_mods_obj.serialize()
self.mods = etree.fromstring( utf8_xml )
return self.mods
def test_mods_add_topic_label_and_fast(self):
mods_obj = mods.make_mods()
mods_obj.title = 'title'
mods.add_topic(mods_obj, 'random', label='Label:', fast_uri='http://id.worldcat.org/fast/902025')
self.assertEqual(mods_obj.subjects[0].topic, 'random')
self.assertEqual(mods_obj.subjects[0].label, 'Label:')
self.assertEqual(mods_obj.subjects[0].value_uri, 'http://id.worldcat.org/fast/902025')
self.assertEqual(mods_obj.subjects[0].authority_uri, 'http://id.worldcat.org/fast')
self.assertEqual(mods_obj.subjects[0].authority, 'fast')
def __init__(self, encoding='utf-8', parent_mods=None):
self.dataSeparator = u'||'
self.encoding = encoding
self._parent_mods = parent_mods
#dict for keeping track of which fields we've cleared out the parent
# info for. So we can have multiple columns in the spreadsheet w/ the same field.
self._cleared_fields = {}
if parent_mods:
self._mods = parent_mods
else:
self._mods = mods.make_mods()
def test_mods_add_topic_partial(self):
#if topic is partially there, finish adding whatever's missing
mods_obj = mods.make_mods()
mods_obj.title = 'title'
mods_obj.subjects.append(mods.Subject(topic='random', label='label1'))
mods.add_topic(mods_obj, 'random', label='label1', fast_uri='http://id.worldcat.org/fast/902025')
self.assertEqual(len(mods_obj.subjects), 1)
s = mods_obj.subjects[0]
self.assertEqual(s.topic, 'random')
self.assertEqual(s.label, 'label1')
self.assertEqual(s.authority, 'fast')
self.assertEqual(s.authority_uri, 'http://id.worldcat.org/fast')
self.assertEqual(s.value_uri, 'http://id.worldcat.org/fast/902025')
def __init__(self, record_type, field_data, parent_mods=None):
self.dataSeparator = u'||'
self._parent_mods = parent_mods
#dict for keeping track of which fields we've cleared out the parent
# info for. So we can have multiple columns in the spreadsheet w/ the same field.
self._cleared_fields = {}
self._record_type = record_type
if record_type == 'dwc':
self._xml_obj = darwincore.make_simple_darwin_record_set()
self._xml_obj.create_simple_darwin_record()
else:
if parent_mods:
self._xml_obj = parent_mods
else:
self._xml_obj = mods.make_mods()
for field in field_data:
self.add_data(field['xml_path'], field['data'])
def __init__(self, record_type, field_data, parent_mods=None):
self.dataSeparator = u'||'
self._parent_mods = parent_mods
#dict for keeping track of which fields we've cleared out the parent
# info for. So we can have multiple columns in the spreadsheet w/ the same field.
self._cleared_fields = {}
self._record_type = record_type
if record_type == 'dwc':
self._xml_obj = darwincore.make_simple_darwin_record_set()
self._xml_obj.create_simple_darwin_record()
else:
if parent_mods:
self._xml_obj = parent_mods
else:
self._xml_obj = mods.make_mods()
for field in field_data:
self.add_data(field['xml_path'], field['data'])
def test_create(self):
mets = make_mets()
#mods
mods_section = make_mods()
mods_section.title = 'sample'
mets.create_mods()
mets.mods = mods_section
#dwc
dwc_section = make_simple_darwin_record_set()
dwc_section.create_simple_darwin_record()
dwc_section.simple_darwin_record.catalog_number = 'catalog number'
mets.create_dwc()
mets.dwc = dwc_section
#ir
mets.create_ir()
mets.ir.filename = 'sample.txt'
#filesec -> filegrp
mets.create_filesec()
fg = FileGrp()
fg.id = u'GID1'
fg.use = u'image-tiff'
fi = File()
fi.admid = u'TMD1'
fi.groupid = u'GRP1'
fi.id = u'FID1'
fi.MIMETYPE = u'image/tiff'
fi.loctype = u'URL'
fi.href = u'/the/path.tif'
fg.file.append( fi )
mets.filesec.filegrp.append( fg )
#structMap
mets.create_structmap() # not used but required for valid mets
#serialize
created_string = mets.serialize( pretty=True )
#load
loaded = load_xmlobject_from_string(created_string, BDRMets)
#test
self.assertEqual(loaded.mods.title, 'sample')
self.assertEqual(loaded.dwc.simple_darwin_record.catalog_number, 'catalog number')
self.assertEqual(loaded.ir.filename, 'sample.txt')
self.assertEqual( type(loaded.structmap), StructMap )
self.assertEqual( loaded.filesec.filegrp[0].file[0].node.items(), [('ADMID', 'TMD1'), ('GROUPID', 'GRP1'), ('ID', 'FID1')] )
def test_create(self):
import bdrxml
from bdrxml.foxml import make
from bdrxml import mods
from bdrxml.foxml import Datastream, DatastreamVersion, InlineMets
mets = make_mets()
#mods
mods_section = mods.make_mods()
mods_section.title = 'sample'
mets.create_mdwrap()
mets.mdwrap.id = 'MODS'
mets.mods = mods_section
#ir
mets.create_ir()
mets.ir.filename = 'sample.txt'
#filesec -> filegrp
mets.create_filesec()
fg = FileGrp()
fg.id = u'GID1'
fg.use = u'image-tiff'
fi = File()
fi.admid = u'TMD1'
fi.groupid = u'GRP1'
fi.id = u'FID1'
fi.MIMETYPE = u'image/tiff'
fi.loctype = u'URL'
fi.href = u'/the/path.tif'
fg.file.append( fi )
mets.filesec.filegrp.append( fg )
#structMap
mets.create_structmap() # not used but required for valid mets
#serialize
created_string = mets.serialize( pretty=True )
# print created_string
#load
loaded = load_xmlobject_from_string(created_string, BDRMets)
#test
self.assertEqual(loaded.mods.title, 'sample')
self.assertEqual(loaded.ir.filename, 'sample.txt')
self.assertEqual( type(loaded.structmap), bdrxml.mets.StructMap )
self.assertEqual( loaded.filesec.filegrp[0].file[0].node.items(), [('ADMID', 'TMD1'), ('GROUPID', 'GRP1'), ('ID', 'FID1')] )
def get_mods_obj(self, update=False):
if self._mods_obj:
#if we have mods already, and we're not updating, just return it
if not update:
return self._mods_obj
else: #no self._mods_obj
if update:
raise Exception('no mods obj - can\'t update')
self._mods_obj = mods.make_mods()
#at this point, we want to put the form data into the mods obj (could be update or new)
self._mods_obj.title_info_list = [] #clear out any old titles
title = mods.TitleInfo()
title.title = self._form_data['title']
if self._form_data['title_language']:
title.node.set('lang', self._form_data['title_language'])
self._mods_obj.title_info_list.append(title)
if self._form_data['english_title']:
english_title = mods.TitleInfo()
english_title.title = self._form_data['english_title']
english_title.node.set('lang', 'en')
self._mods_obj.title_info_list.append(english_title)
if self._form_data['genre']:
self._mods_obj.genres = [] #clear out any old genres
genre = mods.Genre(text=self._form_data['genre'].text)
genre.authority = 'aat'
self._mods_obj.genres.append(genre)
if self._form_data['abstract']:
if not self._mods_obj.abstract:
self._mods_obj.create_abstract()
self._mods_obj.abstract.text = self._form_data[
'abstract'] #overwrites old abstract if present
if self._form_data['impression_date']:
#clear out old dateOther data, or create originInfo if needed
if self._mods_obj.origin_info:
self._mods_obj.origin_info.other = []
else:
self._mods_obj.create_origin_info()
date_other = mods.DateOther(
date=self._form_data['impression_date'])
date_other.type = 'impression'
self._mods_obj.origin_info.other.append(date_other)
#clear out any old names:
# if this is a new object, there aren't any names anyway.
# if this is an update, either the new names will be put in, or they don't want any names.
self._mods_obj.names = []
for p in self._person_formset_data:
name = mods.Name()
np = mods.NamePart(text=p['person'].name)
name.name_parts.append(np)
role = mods.Role(text=p['role'].text)
name.roles.append(role)
href = '{%s}href' % app_settings.XLINK_NAMESPACE
name.node.set(href, p['person'].trp_id)
self._mods_obj.names.append(name)
#clear out old notes data, preserving any annotor info
self._mods_obj.notes = [
note for note in self._mods_obj.notes if note.type == 'resp'
]
for i in self._inscription_formset_data:
note = mods.Note(text=i['text'])
note.type = 'inscription'
note.label = i['location']
self._mods_obj.notes.append(note)
annotator_note = mods.Note(text=self._annotator)
annotator_note.type = 'resp'
self._mods_obj.notes.append(annotator_note)
return self._mods_obj
def test_mods_add_topic(self):
mods_obj = mods.make_mods()
mods_obj.title = 'title'
mods.add_topic(mods_obj, 'random')
self.assertEqual(mods_obj.subjects[0].topic, 'random')
def setUp(self):
#basic fox
self.mods = make_mods()
def __init__(self, thesis):
self.thesis = thesis
self.mods_obj = mods.make_mods()
self._map_to_mods()
def get_mods_obj(self, update=False):
if self._mods_obj:
# if we have mods already, and we're not updating, just return it
if not update:
return self._mods_obj
else: # no self._mods_obj
if update:
raise Exception("no mods obj - can't update")
self._mods_obj = mods.make_mods()
# at this point, we want to put the form data into the mods obj (could be update or new)
self._mods_obj.title_info_list = [] # clear out any old titles
title = mods.TitleInfo()
title.title = self._form_data["title"]
if self._form_data["title_language"]:
title.node.set("lang", self._form_data["title_language"])
self._mods_obj.title_info_list.append(title)
if self._form_data["english_title"]:
english_title = mods.TitleInfo()
english_title.title = self._form_data["english_title"]
english_title.node.set("lang", "en")
self._mods_obj.title_info_list.append(english_title)
if self._form_data["genre"]:
self._mods_obj.genres = [] # clear out any old genres
genre = mods.Genre(text=self._form_data["genre"].text)
genre.authority = "aat"
self._mods_obj.genres.append(genre)
if self._form_data["abstract"]:
if not self._mods_obj.abstract:
self._mods_obj.create_abstract()
self._mods_obj.abstract.text = self._form_data["abstract"] # overwrites old abstract if present
if self._form_data["impression_date"]:
# clear out old dateOther data, or create originInfo if needed
if self._mods_obj.origin_info:
self._mods_obj.origin_info.other = []
else:
self._mods_obj.create_origin_info()
date_other = mods.DateOther(date=self._form_data["impression_date"])
date_other.type = "impression"
self._mods_obj.origin_info.other.append(date_other)
# clear out any old names:
# if this is a new object, there aren't any names anyway.
# if this is an update, either the new names will be put in, or they don't want any names.
self._mods_obj.names = []
for p in self._person_formset_data:
name = mods.Name()
np = mods.NamePart(text=p["person"].name)
name.name_parts.append(np)
role = mods.Role(text=p["role"].text)
name.roles.append(role)
href = "{%s}href" % app_settings.XLINK_NAMESPACE
name.node.set(href, p["person"].trp_id)
self._mods_obj.names.append(name)
# clear out old notes data, preserving any annotor info
self._mods_obj.notes = [note for note in self._mods_obj.notes if note.type == "resp"]
for i in self._inscription_formset_data:
note = mods.Note(text=i["text"])
note.type = "inscription"
note.label = i["location"]
self._mods_obj.notes.append(note)
annotator_note = mods.Note(text=self._annotator)
annotator_note.type = "resp"
self._mods_obj.notes.append(annotator_note)
return self._mods_obj
def setUp(self):
#basic mods
self.mods = mods.make_mods()
def __init__(self, thesis):
self.thesis = thesis
self.mods_obj = mods.make_mods()
self._map_to_mods()
