def get_or_add_periodical(mods, client, record_constants):
"""Takes a MODS etree and gets ors adds a Periodical
Periodical model uses the proposal at
http://www.w3.org/community/schemabibex/ to add support for recurring
resources in the MongoDatastore
Args:
mods: MODS XML etree
client: Mongo DB Client
record_constants: Dictionary of Record constants
Returns:
ObjectId: Mongo DB ObjectId for the schema.org Thesis
"""
schema_org = client.schema_org
bibframe = client.bibframe
title = mods.find("{{{0}}}titleInfo/{{{0}}}title".format(MODS_NS))
existing_periodical = schema_org.CreativeWork.find_one(
{"@type": 'Periodical',
"headline": title.text})
if existing_periodical is not None:
return existing_periodical.get('_id')
base_mods = add_base(mods, client, record_constants)
periodical = CreativeWork(**base_mods)
periodical_dict = periodical.as_dict()
periodical_dict['@type'] = 'Periodical'
periodical_id = schema_org.CreativeWork.insert(periodical_dict)
return periodical_id
def get_or_add_periodical(mods, client, record_constants):
"""Takes a MODS etree and gets ors adds a Periodical
Periodical model uses the proposal at
http://www.w3.org/community/schemabibex/ to add support for recurring
resources in the MongoDatastore
Args:
mods: MODS XML etree
client: Mongo DB Client
record_constants: Dictionary of Record constants
Returns:
ObjectId: Mongo DB ObjectId for the schema.org Thesis
"""
schema_org = client.schema_org
bibframe = client.bibframe
title = mods.find("{{{0}}}titleInfo/{{{0}}}title".format(MODS_NS))
existing_periodical = schema_org.CreativeWork.find_one({
"@type":
'Periodical',
"headline":
title.text
})
if existing_periodical is not None:
return existing_periodical.get('_id')
base_mods = add_base(mods, client, record_constants)
periodical = CreativeWork(**base_mods)
periodical_dict = periodical.as_dict()
periodical_dict['@type'] = 'Periodical'
periodical_id = schema_org.CreativeWork.insert(periodical_dict)
return periodical_id
def add_publication_volume(mods, client, volume, record_constants):
schema_org = client.schema_org
bibframe = client.bibframe
base_mods = add_base(mods, client, record_constants)
publication_volume = CreativeWork(**base_mods)
setattr(publication_volume, 'volumeNumber', volume)
pub_volume_dict = publication_volume.as_dict()
pub_volume_dict['@type'] = 'PublicationVolume'
pub_volume_id = schema_org.CreativeWork.insert(pub_volume_dict)
return pub_volume_id
def add_publication_volume(mods, client, volume, record_constants):
schema_org = client.schema_org
bibframe = client.bibframe
base_mods = add_base(mods, client, record_constants)
publication_volume = CreativeWork(**base_mods)
setattr(publication_volume, 'volumeNumber', volume)
pub_volume_dict = publication_volume.as_dict()
pub_volume_dict['@type'] = 'PublicationVolume'
pub_volume_id = schema_org.CreativeWork.insert(pub_volume_dict)
return pub_volume_id
def add_publication_issue(mods, client, issue_number, record_constants):
schema_org = client.schema_org
bibframe = client.bibframe
base_mods = add_base(mods, client, record_constants)
publication_issue = CreativeWork(**base_mods)
setattr(publication_issue, 'issueNumber', issue_number)
pub_issue_dict = publication_issue.as_dict()
pub_issue_dict['@type'] = 'PublicationIssue'
pub_issue_id = schema_org.CreativeWork.insert(pub_issue_dict)
return pub_issue_id
def add_publication_issue(mods, client, issue_number, record_constants):
schema_org = client.schema_org
bibframe = client.bibframe
base_mods = add_base(mods, client, record_constants)
publication_issue = CreativeWork(**base_mods)
setattr(publication_issue, 'issueNumber', issue_number)
pub_issue_dict = publication_issue.as_dict()
pub_issue_dict['@type'] = 'PublicationIssue'
pub_issue_id = schema_org.CreativeWork.insert(pub_issue_dict)
return pub_issue_id
def add_thesis(mods, client, record_constants):
"""Takes a MODS etree and adds a Thesis to the Mongo Datastore
Function takes a MODS etree and based on mods:genre value, creates a
custom Thesis Schema.org class that is descendent from schema:CreativeWork
Args:
mods: MODS XML etree
client: Mongo DB Client
Returns:
ObjectId: Mongo DB ObjectId for the schema.org Thesis
"""
schema_org = client.schema_org
bibframe = client.bibframe
base_mods = add_base(mods, client, record_constants)
thesis = CreativeWork(**base_mods)
thesis.genre = 'thesis'
if thesis.copyrightHolder is None:
thesis.copyrightHolder = []
thesis.copyrightHolder.extend(base_mods['creator'])
bf_text = bf_models.Text(recordInfo=generate_record_info(
record_constants['source'],
record_constants['msg']),
title=base_mods.get('headline'))
for name in mods.findall("{{{0}}}name".format(MODS_NS)):
name_type = name.attrib.get('type')
role = name.find("{{{0}}}role/{{{0}}}roleTerm".format(MODS_NS))
if name_type == 'corporate':
org_name = name.find("{{{}}}namePart".format(MODS_NS))
org_id = get_or_add_organization(
org_name.text,
client, record_constants)
if org_id is not None and role is not None:
if role.text == 'sponsor':
thesis.sourceOrganization = str(org_id)
if thesis.publisher:
publisher = schema_org.Organization.find_one(
{'_id': ObjectId(thesis.publisher)})
if publisher.get('department') is None:
publisher['department'] = []
if not str(org_id) in publisher.get('department'):
publisher['department'].append(str(org_id))
schema_org.Organization.update(
{'_id': publisher.get('_id')},
{ '$set': {"department": publisher['department']
}})
if thesis.publisher:
bf_organization = bibframe.Organization.find_one(
{"relatedTo": thesis.publisher},
{"_id": 1})
bf_text.dissertationInstitution = str(bf_organization.get('_id'))
for note in mods.findall("{{{0}}}note".format(MODS_NS)):
if note.attrib.get('type') == 'thesis' and \
note.attrib.get('displayLabel') == "Degree Name":
bf_text.dissertationDegree = note.text
thesis_id = schema_org.CreativeWork.insert(thesis.as_dict())
bf_text.relatedTo = [thesis_id,]
bf_text_id = bibframe.Work.insert(bf_text.as_dict())
schema_org.CreativeWork.update({"_id": thesis_id},
{"$set": {'sameAs': [str(bf_text_id)]}})
return thesis_id
def insert_mods(mods_xml, client):
"""Inserts a MODS XML datastream to MongoDB schema_org and bibframe
collections.
Args:
mods_xml: Raw MODS XML
client: Mongo Client
Returns:
None
Raises:
None
"""
mods = etree.XML(mods_xml)
genre = mods.find("{{{0}}}genre".format(mods2ds.MODS_NS))
if genre is None:
# Try genre subject
genre = mods.find("{{{0}}}subject/{{{0}}}genre".format(mods2ds.MODS_NS))
if genre is not None and genre.text is not None:
if ['audio recording',
'interview',
'personal narratives'].count(genre.text.lower()) > 0:
return mods2ds.get_or_add_audio(mods, client, RECORD_CONSTANTS)
if ['newspaper', 'periodical'].count(genre.text.lower()) > 0:
return mods2ds.get_or_add_periodical(mods, client, RECORD_CONSTANTS)
if genre.text.lower().startswith('history'):
return mods2ds.get_or_add_article(mods, client, RECORD_CONSTANTS)
if genre.text.lower().startswith('photo'):
return mods2ds.get_or_add_photograph(mods, client, RECORD_CONSTANTS)
if genre.text.lower().startswith('pict'):
return mods2ds.get_or_add_photograph(mods, client, RECORD_CONSTANTS)
if genre.text.lower().startswith('thes') or \
genre.text.lower().startswith('essay'):
return mods2ds.add_thesis(mods, client, RECORD_CONSTANTS)
if genre.text.lower().startswith('videorecord'):
return mods2ds.get_or_add_video(mods, client, RECORD_CONSTANTS)
# Next try using type_of_resource value to guess type
type_of_resource = mods.find(
"{{{0}}}typeOfResource".format(mods2ds.MODS_NS))
if type_of_resource is not None and type_of_resource.text is not None:
if type_of_resource.text.startswith('sound'):
return mods2ds.get_or_add_audio(mods, client, RECORD_CONSTANTS)
if type_of_resource.text.startswith('still image'):
return mods2ds.get_or_add_photograph(mods, client, RECORD_CONSTANTS)
if type_of_resource.text.startswith("text"):
series = mods.find(
"{{{0}}}relatedItem[@type='series']/{{{0}}}titleInfo/{{{0}}}title".format(
mods2ds.MODS_NS))
if series is not None and series.text is not None:
series_id = add_series(series, client)
article_id = mods2ds.get_or_add_article(mods, client, RECORD_CONSTANTS)
client.schema_org.CreativeWork.update(
{"_id": article_id},
{"$set": {"isPartOf": str(series_id)}})
return article_id
# No matches, create a generic CreativeWork
work = CreativeWork(**mods2ds.add_base(mods, client, RECORD_CONSTANTS))
work_id = client.schema_org.CreativeWork.insert(work.as_dict())
return work_id
def add_thesis(mods, client, record_constants):
"""Takes a MODS etree and adds a Thesis to the Mongo Datastore
Function takes a MODS etree and based on mods:genre value, creates a
custom Thesis Schema.org class that is descendent from schema:CreativeWork
Args:
mods: MODS XML etree
client: Mongo DB Client
Returns:
ObjectId: Mongo DB ObjectId for the schema.org Thesis
"""
schema_org = client.schema_org
bibframe = client.bibframe
base_mods = add_base(mods, client, record_constants)
thesis = CreativeWork(**base_mods)
thesis.genre = 'thesis'
if thesis.copyrightHolder is None:
thesis.copyrightHolder = []
thesis.copyrightHolder.extend(base_mods['creator'])
bf_text = bf_models.Text(recordInfo=generate_record_info(
record_constants['source'], record_constants['msg']),
title=base_mods.get('headline'))
for name in mods.findall("{{{0}}}name".format(MODS_NS)):
name_type = name.attrib.get('type')
role = name.find("{{{0}}}role/{{{0}}}roleTerm".format(MODS_NS))
if name_type == 'corporate':
org_name = name.find("{{{}}}namePart".format(MODS_NS))
org_id = get_or_add_organization(org_name.text, client,
record_constants)
if org_id is not None and role is not None:
if role.text == 'sponsor':
thesis.sourceOrganization = str(org_id)
if thesis.publisher:
publisher = schema_org.Organization.find_one(
{'_id': ObjectId(thesis.publisher)})
if publisher.get('department') is None:
publisher['department'] = []
if not str(org_id) in publisher.get('department'):
publisher['department'].append(str(org_id))
schema_org.Organization.update(
{'_id': publisher.get('_id')}, {
'$set': {
"department": publisher['department']
}
})
if thesis.publisher:
bf_organization = bibframe.Organization.find_one(
{"relatedTo": thesis.publisher}, {"_id": 1})
bf_text.dissertationInstitution = str(bf_organization.get('_id'))
for note in mods.findall("{{{0}}}note".format(MODS_NS)):
if note.attrib.get('type') == 'thesis' and \
note.attrib.get('displayLabel') == "Degree Name":
bf_text.dissertationDegree = note.text
thesis_id = schema_org.CreativeWork.insert(thesis.as_dict())
bf_text.relatedTo = [
thesis_id,
]
bf_text_id = bibframe.Work.insert(bf_text.as_dict())
schema_org.CreativeWork.update({"_id": thesis_id},
{"$set": {
'sameAs': [str(bf_text_id)]
}})
return thesis_id