def get_rml_relationships(rml):
""" relationship -> relationships """
result = {}
rml_relationships = rml.findall(xmletree.prefixtag("rml", "relationship"))
if rml_relationships is not None:
relationships = []
for rml_relationship in rml_relationships:
if rml_relationship is not None:
# name -> agent.name
name = get_rml_element_text(rml_relationship, "name")
relationship = creator_service.formatted_name_to_creator(name, constants.REC_CLASS_PERSON, None)
if relationship is None:
relationship = {}
relationship["agent"] = Person()
# identifier -> agent.rec_id & agent.identifiers
relationship["agent"].update(get_rml_identifiers(rml_relationship))
# relationType -> relation_type
relationship.update(get_rml_element_text_and_set_key(rml_relationship, "relationType", "relation_type"))
# descriptions -> descriptions
relationship.update(get_rml_textlangs_and_set_key(rml_relationship, "description", "descriptions"))
if relationship is not None:
relationships.append(relationship)
if relationships:
result["relationships"] = relationships
return result
def endnote_authors_to_creators(authors, creator_type="person", role="aut"):
creators = []
for author in authors.splitlines():
creator = creator_service.formatted_name_to_creator(author, creator_type, role)
if creator:
creators.append(creator)
return creators
def endnote_authors_to_creators(authors, creator_type="person", role="aut"):
creators = []
for author in authors.splitlines():
creator = creator_service.formatted_name_to_creator(
author, creator_type, role)
if creator:
creators.append(creator)
return creators
def extract_creators(entry, key, role):
#logging.debug("extract_creators")
if key in entry.persons:
#logging.debug("key: {}".format(key))
creators = []
authors = entry.persons[key]
for author in authors:
formatted_name = unicode(author).encode('utf-8')
formatted_name = replace_special_characters(formatted_name)
creator = creator_service.formatted_name_to_creator(formatted_name, constants.REC_CLASS_PERSON, role)
creators.append(creator)
return creators
else:
return None
def get_rml_teachings(rml):
""" teaching -> teachings """
result = {}
rml_teachings = rml.findall(xmletree.prefixtag("rml", "teaching"))
if rml_teachings is not None:
teachings = []
for rml_teaching in rml_teachings:
if rml_teaching is not None:
teaching = {}
# dateBegin -> date_begin
teaching.update(get_rml_element_text_and_set_key(rml_teaching, "dateBegin", "date_begin"))
# dateEnd -> date_end
teaching.update(get_rml_element_text_and_set_key(rml_teaching, "dateEnd", "date_end"))
# description -> descriptions[i]
teaching.update(get_rml_textlangs_and_set_key(rml_teaching, "description", "descriptions"))
# level -> level
teaching.update(get_rml_element_text_and_set_key(rml_teaching, "level", "level"))
# title -> title
teaching.update(get_rml_element_text_and_set_key(rml_teaching, "title", "title"))
# creators
# name -> creators[0].agent.name
name = get_rml_element_text(rml_teaching, "name")
creator = creator_service.formatted_name_to_creator(name, constants.REC_CLASS_ORGUNIT, "dgg")
if creator is None:
creator = Creator()
creator["agent"] = Orgunit()
creator["roles"] = "dgg"
# identifiers -> creators[0].agent.rec_id or creators[0].agent.identifiers
creator["agent"].update(get_rml_identifiers(rml_teaching))
if "name" in creator["agent"] or "rec_id" in creator["agent"] or "identifiers" in creator["agent"]:
teaching["creators"] = [creator]
if teaching is not None:
teachings.append(teaching)
if teachings:
result["teachings"] = teachings
return result
def get_rml_degrees(rml):
""" degree -> degrees """
result = {}
rml_degrees = rml.findall(xmletree.prefixtag("rml", "degree"))
if rml_degrees is not None:
degrees = []
for rml_degree in rml_degrees:
if rml_degree is not None:
degree = {}
# dateBegin -> date_begin
degree.update(get_rml_element_text_and_set_key(rml_degree, "dateBegin", "date_begin"))
# dateEnd -> date_end
degree.update(get_rml_element_text_and_set_key(rml_degree, "dateEnd", "date_end"))
# description -> descriptions
degree.update(get_rml_textlangs_and_set_key(rml_degree, "description", "descriptions"))
# level -> level
degree.update(get_rml_element_text_and_set_key(rml_degree, "level", "level"))
# title -> title
degree.update(get_rml_element_text_and_set_key(rml_degree, "title", "title"))
# creators
# name -> creators[0].agent.name
name = get_rml_element_text(rml_degree, "name")
creator = creator_service.formatted_name_to_creator(name, constants.REC_CLASS_ORGUNIT, "dgg")
if creator is None:
creator = Creator()
creator["agent"] = Orgunit()
creator["roles"] = ["dgg"]
# identifiers -> creators[0].agent.rec_id or creators[0].agent.identifiers
creator["agent"].update(get_rml_identifiers(rml_degree))
if "name" in creator["agent"] or "rec_id" in creator["agent"] or "identifiers" in creator["agent"]:
degree["creators"] = [creator]
if degree is not None:
degrees.append(degree)
if degrees:
result["degrees"] = degrees
return result
def get_rml_call(rml):
""" call -> call """
result = {}
rml_call = rml.find(xmletree.prefixtag("rml", "call"))
if rml_call is not None:
call = Call()
# funding -> funding
rml_funding = rml_call.find(xmletree.prefixtag("rml", "funding"))
if rml_funding is not None:
# name -> agent.name
name = get_rml_element_text(rml_funding, "name")
funding = creator_service.formatted_name_to_creator(name, constants.REC_CLASS_ORGUNIT, None)
if funding is None:
funding = Creator()
funding["agent"] = Orgunit()
# identifier -> agent.rec_id & agent.identifiers
funding["agent"].update(get_rml_identifiers(rml_funding))
# programme -> programme
funding.update(get_rml_element_text_and_set_key(rml_funding, "programme", "programme"))
# scheme -> scheme
funding.update(get_rml_element_text_and_set_key(rml_funding, "scheme", "scheme"))
# contribution -> contribution
funding.update(get_rml_money_and_set_key(rml_funding, "contribution", "contribution"))
if funding:
call["funding"] = funding
# identifier -> rec_id
call.update(get_rml_element_text_and_set_key(rml_call, "identifier", "rec_id"))
# title -> title
call.update(get_rml_element_text_and_set_key(rml_call, "title", "title"))
# year -> date_issued
call.update(get_rml_element_text_and_set_key(rml_call, "year", "date_issued"))
if call:
result["call"] = call
return result
def get_rml_participants(rml):
""" participant -> creators """
result = {}
rml_participants = rml.findall(xmletree.prefixtag("rml", "participant"))
if rml_participants is not None:
creators = []
for rml_participant in rml_participants:
if rml_participant is not None:
creator_name = get_rml_element_text(rml_participant, "name")
if creator_name:
creator_rec_class = xmletree.get_element_attribute(rml_participant, "entityType")
if creator_rec_class:
creator_rec_class = creator_rec_class.title()
creator = creator_service.formatted_name_to_creator(creator_name, creator_rec_class, None)
if creator:
creators.append(creator)
if creators:
result["creators"] = creators
return result
def convert_creators(sum_doc, sum_authors_key, sum_affiliations_key, creator_type, role):
creators = []
if sum_authors_key in sum_doc:
sum_authors = sum_doc[sum_authors_key]
if sum_authors:
affiliations_dict = {}
if sum_affiliations_key in sum_doc:
sum_affiliations = sum_doc[sum_affiliations_key]
if sum_affiliations:
for index, affiliation in enumerate(sum_affiliations):
affiliations_dict[index + 1] = affiliation
for author in sum_authors:
creator = Creator()
if "surname" in author and "givenname" in author:
person = Person()
person.set_key_if_not_none("name_family", author["surname"])
person.set_key_if_not_none("name_given", author["givenname"])
creator["agent"] = person
if role:
creator["roles"] = [role]
else:
formatted_name = ""
if "fullname" in author:
formatted_name = author["fullname"]
elif "name" in author:
formatted_name = author["name"]
creator = creator_service.formatted_name_to_creator(formatted_name, creator_type, role)
if "sequence" in author and author["sequence"] in affiliations_dict:
creator["affiliation"] = affiliations_dict[author["sequence"]]
# todo : location dans le cas des DissertationSchool_xml
if creator:
creators.append(creator)
return creators
def csv_dict_reader_to_metasjon(csv_row, input_format, source, rec_id_prefix):
document = Document()
if source:
document["rec_source"] = source
if input_format == constants.FORMAT_CSV_SITPOL:
#logging.debug("csv_dict_reader_to_metasjon type(csv_row): {}".format(type(csv_row)))
#print csv_row
document["title"] = csv_row["title"]
classifications_sitpol = [x.strip() for x in csv_row["classifications_sitpol"].split(";") if x.strip()]
if classifications_sitpol:
document["classifications_sitpol"] = classifications_sitpol
classifications_ddc = [x.strip() for x in csv_row["classifications_ddc"].split(";") if x.strip()]
if classifications_ddc:
document["classifications_ddc"] = classifications_ddc
formatted_names = [x.strip() for x in csv_row["creators@role=pbl"].split(";") if x.strip()]
if formatted_names:
#logging.debug("formatted_names: {}".format(formatted_names))
creators = []
for formatted_name in formatted_names:
if formatted_name:
creator = creator_service.formatted_name_to_creator(formatted_name, None, "pbl")
if creator:
creators.append(creator)
if creators:
document["creators"] = creators
document["date_last_accessed"] = datetime.now().isoformat()
document["descriptions"] = [{"language":"fr", "value":csv_row["descriptions@lang=fr"]}]
keywords_fr = [x.strip() for x in csv_row["keywords@lang=fr"].split(";") if x.strip()]
keywords_en = [x.strip() for x in csv_row["keywords@lang=en"].split(";") if x.strip()]
keywords = {}
if keywords_fr:
keywords["fr"] = keywords_fr
if keywords_en:
keywords["en"] = keywords_en
if keywords:
document["keywords"] = keywords
document["languages"] = [x.strip() for x in csv_row["languages"].split(";") if x.strip()]
note = csv_row["notes@lang=fr"]
if note:
document["notes"] = note
document["publication_countries"] = [x.strip() for x in csv_row["publication_countries"].split(";") if x.strip()]
if "rec_created_user" in csv_row:
document["rec_created_user"] = csv_row["rec_created_user"]
document["rec_type_cerimes"] = csv_row["rec_type_cerimes"]
specific_agents = [x.strip() for x in csv_row["specific_agents"].split(";") if x.strip()]
if specific_agents:
document["specific_agents"] = specific_agents
document["specific_actor_type"] = csv_row["specific_actor_type"]
document["target_audiences_cerimes"] = csv_row["target_audiences_cerimes"]
document["url"] = csv_row["url"]
document["rec_type"] = constants.DOC_TYPE_WEBENTITY
document["webentity_type"] = csv_row["webentity_type"]
elif input_format == constants.FORMAT_CSV_METAJSON:
document["rec_type"] = "DatasetQuali"
creators = []
if "Laboratoire d'inventaire" in csv_row:
creators.append(creator_service.formatted_name_to_creator(csv_row["Laboratoire d'inventaire"], constants.REC_CLASS_ORGUNIT, "dpt"))
document["title"] = csv_row["Titre de l'enquete"]
if "Sujet(s) de l'enquete" in csv_row:
document["keywords"] = [x.strip() for x in csv_row["Sujet(s) de l'enquete"].split("\n") if x.strip()]
if "Nom Auteur 1" in csv_row:
name_familly = csv_row["Nom Auteur 1"]
name_given = affiliation = ""
if "Prenom Auteur 1" in csv_row:
name_given = csv_row["Prenom Auteur 1"]
if "Affiliation Auteur 1" in csv_row:
affiliation = csv_row["Affiliation Auteur 1"]
document["creators"] = creators
else:
logging.error("Unknown input_format: {}".format(input_format))
logging.info(jsonbson.dumps_json(document, True))
return document
def ris_txt_lines_to_metajson_list(txt_lines, source, rec_id_prefix,
only_first_record):
document = None
ris_type = None
rec_type = None
is_part_of_rec_type = None
previous_key = None
previous_value = None
for line in txt_lines:
if line:
line = line.rstrip('\r\n')
#logging.debug("line: {}".format(line))
# multi line management
if previous_key:
key = previous_key
value = previous_value + line
previous_key = None
previous_value = None
else:
key = line[:2].strip()
value = line[6:].strip()
if value.endswith("/") and key not in ["Y1", "PY"]:
#logging.debug("multi line")
previous_key = key
previous_value = value.rstrip('/')
continue
if key is None or len(key) == 0:
# empty line -> continue
#logging.debug("empty line")
continue
elif key == RIS_KEY_BEGIN:
# record begin with document type -> create document
# init
document = Document()
is_part_of_rec_type = None
if source:
document["rec_source"] = source
ris_type = value
rec_type = ris_document_type_to_metajson_document_type[
ris_type]
document["rec_type"] = rec_type
if ris_type in ris_document_type_to_metajson_document_is_part_of_type:
is_part_of_rec_type = ris_document_type_to_metajson_document_is_part_of_type[
ris_type]
is_part_of = Document()
is_part_of["rec_type"] = is_part_of_rec_type
document["is_part_ofs"] = [is_part_of]
elif key == RIS_KEY_END:
# record end -> return the result
# verify the is_part_ofs[0]["title"]
if "is_part_ofs" in document and "title" not in document[
"is_part_ofs"][0] and "title_abbreviateds" in document[
"is_part_ofs"][0]:
document["is_part_ofs"][0]["title"] = document[
"is_part_ofs"][0]["title_abbreviateds"][0]["title"]
del document["is_part_ofs"][0]["title_abbreviateds"]
logging.info("# RIS type: {}".format(ris_type))
metajson_service.pretty_print_document(document)
yield document
else:
# process key value
#logging.debug("key: {}; value: {}".format(key, value))
if key == "ID":
document["rec_id"] = value
elif key in [
"T1", "TI", "CT"
] or (key == "BT"
and ris_type in [RIS_TYPE_BOOK, RIS_TYPE_UNPB]):
# Title Primary -> title
document["title"] = value
elif key in [
"JF", "JO"
] or (key == "BT"
and ris_type not in [RIS_TYPE_BOOK, RIS_TYPE_UNPB]):
# Title Secondary -> is_part_of["title"]
document.add_is_part_of_title(value)
elif key in ["JA", "J1", "J2", "T2"]:
# Title Secondary -> is_part_of["title_abbreviateds"][O]["title"]
document.add_is_part_of_title_abbreviated(value)
elif key == "T3":
# Title Series
document.add_series_title(value)
elif key in ["A1", "AU"]:
document.add_creator(
creator_service.formatted_name_to_creator(
value, None, "aut"))
elif key in ["A2", "ED"]:
if is_part_of_rec_type:
document.add_is_part_of_creator(
creator_service.formatted_name_to_creator(
value, None, "edt"))
else:
document.add_creator(
creator_service.formatted_name_to_creator(
value, None, "edt"))
elif key == "A3":
document.add_series_creator(
creator_service.formatted_name_to_creator(
value, None, "aut"))
elif key == "A4":
document.add_creator(
creator_service.formatted_name_to_creator(
value, None, "ctb"))
elif key in ["PY", "Y1", "DA"]:
index_slash = value.find("/")
if index_slash != -1:
# YYYY/MM/DD/other info (like season)
# todo
document["date_issued"] = value.strip("/")
else:
document["date_issued"] = value
elif key == "SP":
document["part_page_begin"] = value
elif key == "EP":
document["part_page_end"] = value
elif key == "VL":
document["part_volume"] = value
elif key in ["IS", "CP"]:
document["part_issue"] = value
elif key in ["AB", "N2"]:
document["descriptions"] = [{
"language": "und",
"value": value
}]
elif key == "N1":
document["notes"] = [{"language": "und", "value": value}]
elif key == "PB":
document.add_item_to_key(value, "publishers")
elif key == "CY":
document.add_item_to_key(value, "publication_places")
elif key == "RP":
document["publication_status"] = value
elif key == "ET":
document["edition"] = value
elif key == "UR":
resource = Resource()
resource["url"] = value
document.add_item_to_key(resource, "resources")
elif key == "AN":
# Accession Number
identifier = metajson_service.create_identifier(
"accessionnumber", value)
document.add_identifier(identifier)
elif key == "CN":
# Call Number
identifier = metajson_service.create_identifier(
"callnumber", value)
document.add_identifier(identifier)
elif key == "DO":
# DOI
identifier = metajson_service.create_identifier(
"doi", value)
document.add_identifier(identifier)
elif key == "SN":
# ISBN or ISSN ?
id_type = None
if rec_type in [
constants.DOC_TYPE_JOURNALARTICLE,
constants.DOC_TYPE_MAGAZINEARTICLE,
constants.DOC_TYPE_NEWSPAPERARTICLE,
constants.DOC_TYPE_JOURNAL
]:
id_type = "issn"
else:
id_type = "isbn"
identifier = metajson_service.create_identifier(
id_type, value)
if is_part_of_rec_type is None:
document.add_identifier(identifier)
else:
document["is_part_ofs"][0].add_identifier(identifier)
elif key == "CA":
document["caption"] = value
elif key == "DB":
# Name of Database -> rec_source ?
document["rec_source"] = value
elif key == "DP":
# NDatabase Provider -> rec_source ?
document["rec_source"] = value
elif key == "KW":
if "keywords" not in document:
document["keywords"] = {"und": []}
document["keywords"]["und"].append(value)
else:
logging.debug("Not managed key: {} with value: {}".format(
key, value))
def endnotexml_record_to_metajson(record, source, rec_id_prefix):
document = Document()
# TODO
# translated_creators: /contributors/translated-authors/author/style
# auth_address: /auth-address/style
# label: /label/style
# custom1
# Extract endnote properties
rec_id = record.find("rec-number").text
endnote_type = record.find("ref-type").text
rec_type = endnote_record_type_to_metajson_document_type[endnote_type]
primary_creators = extract_creators(None, "aut", record,
"./contributors/authors/author/style")
secondary_creators = extract_creators(
None, "pbd", record, "./contributors/secondary-authors/author/style")
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION]:
tertiary_creators = extract_creators(
None, "pbd", record,
"./contributors/tertiary-authors/author/style")
elif endnote_type == TYPE_THESIS:
tertiary_creators = extract_creators(
None, "ths", record,
"./contributors/tertiary-authors/author/style")
elif endnote_type == TYPE_FILM_OR_BROADCAST:
tertiary_creators = extract_creators(
None, "pro", record,
"./contributors/tertiary-authors/author/style")
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION]:
subsidiary_creators = extract_creators(
None, "trl", record,
"./contributors/subsidiary-authors/author/style")
elif endnote_type == TYPE_FILM_OR_BROADCAST:
subsidiary_creators = extract_creators(
None, "act", record,
"./contributors/subsidiary-authors/author/style")
translated_creators = extract_creators(
None, "trl", record, "./contributors/translated-authors/author/style")
auth_address = extract_text(record, "./auth-address/style")
title = extract_text(record, "./titles/title/style")
title_secondary = extract_text(record, "./titles/secondary-title/style")
title_tertiary = extract_text(record, "./titles/tertiary-title/style")
title_alternative = extract_text(record, "./titles/alt-title/style")
title_abbreviated = extract_text(record, "./titles/short-title/style")
title_translated = extract_text(record, "./titles/translated-title/style")
pages = extract_text(record, "./pages/style")
part_volume = extract_text(record, "./volume/style")
part_number = extract_text(record, "./number/style")
extent_volumes = extract_text(record, "./num-vols/style")
edition = extract_text(record, "./edition/style")
part_section = extract_text(record, "./section/style")
reprint_edition = extract_text(record, "./reprint-edition/style")
keywords = extract_text(record, "./keywords/keyword/style")
date_year = extract_text(record, "./dates/year/style")
date_pub = extract_text(record, "./dates/pub-dates/date/style")
publication_places_formatted = extract_text(record, "./pub-location/style")
publishers_formatted = extract_text(record, "./publisher/style")
orig_pub = extract_text(record, "./orig-pub/style")
isbn_or_issn = extract_text(record, "./isbn/style")
accessionnumber = extract_text(record, "./accession-num/style")
callnumber = extract_text(record, "./call-num/style")
if endnote_type == TYPE_WEB_PAGE:
abstract = extract_text(record, "./pages/style")
else:
abstract = extract_text(record, "./abstract/style")
label = extract_text(record, "./label/style")
caption = extract_text(record, "./caption/style")
note = extract_text(record, "./notes/style")
reviewed_item = extract_text(record, "./reviewed-item/style")
rec_type_description = extract_text(record, "./work-type/style")
url = extract_text(record, "./urls/related-urls/url/style")
custom1 = extract_text(record, "./custom1/style")
custom2 = extract_text(record, "./custom2/style")
custom3 = extract_text(record, "./custom3/style")
custom4 = extract_text(record, "./custom4/style")
custom5 = extract_text(record, "./custom5/style")
custom6 = extract_text(record, "./custom6/style")
custom7 = extract_text(record, "./custom7/style")
doi = extract_text(record, "./electronic-resource-num/style")
remote_database_name = extract_text(record, "./remote-database-name/style")
remote_database_provider = extract_text(
record, "./remote-database-provider/style")
research_notes = extract_text(record, "./research-notes/style")
language = extract_text(record, "./language/style")
access_date = extract_text(record, "./access-date/style")
# rec_id, rec_source
document["rec_id"] = rec_id
if source:
document["rec_source"] = source
# publishers_formatted, publication_places_formatted
publishers = None
publication_places = None
if publishers_formatted:
publishers = publishers_formatted.split("\r")
if publication_places_formatted:
publication_places = publication_places_formatted.split("\r")
# type, is_part_of.type, is_part_of.is_part_of.type
try:
is_part_of_type = endnote_record_type_to_metajson_document_is_part_of_type[
endnote_type]
except:
is_part_of_type = None
is_part_of_is_part_of_type = None
if title_secondary is not None:
if endnote_type == TYPE_FIGURE:
# how to determine the is_part_of type ?
# if there is a volume or an issue number, it's a JournalArticle, else it's a Book or BookPart
if part_volume is not None or part_number is not None:
is_part_of_type = constants.DOC_TYPE_JOURNALARTICLE
is_part_of_is_part_of_type = constants.DOC_TYPE_JOURNAL
else:
if title_translated is not None:
is_part_of_type = constants.DOC_TYPE_BOOKPART
is_part_of_is_part_of_type = constants.DOC_TYPE_BOOK
else:
is_part_of_type = constants.DOC_TYPE_BOOK
elif endnote_type == TYPE_FILM_OR_BROADCAST:
rec_type = constants.DOC_TYPE_VIDEOPART
is_part_of_type = constants.DOC_TYPE_VIDEORECORDING
document["rec_type"] = rec_type
document.set_key_if_not_none("rec_type_description", rec_type_description)
# issn or isbn ?
if is_part_of_type in [
constants.DOC_TYPE_JOURNAL, constants.DOC_TYPE_NEWSPAPER,
constants.DOC_TYPE_MAGAZINE
]:
isbn_or_issn_type = "issn"
else:
isbn_or_issn_type = "isbn"
# is_part_of, is_part_of.is_part_of
if is_part_of_type is not None and title_secondary:
is_part_of = Document()
is_part_of.set_key_if_not_none("rec_type", is_part_of_type)
is_part_of.set_key_if_not_none("title", title_secondary)
if is_part_of_is_part_of_type is not None:
# is_part_of in case of is_part_of.is_part_of
# creators with role aut
is_part_of.add_creators(
creator_service.change_contibutors_role(
secondary_creators, "aut"))
# is_part_of.is_part_of
is_part_of_is_part_of = Document()
is_part_of_is_part_of.set_key_if_not_none(
"rec_type", is_part_of_is_part_of_type)
is_part_of_is_part_of.set_key_if_not_none("title",
title_translated)
# creators with role pbd
is_part_of_is_part_of.add_creators(
creator_service.change_contibutors_role(
translated_creators, "pbd"))
#is_part_of_is_part_of.set_key_if_not_none("date_issued",date_year)
is_part_of_is_part_of.set_key_if_not_none("publishers", publishers)
is_part_of_is_part_of.set_key_if_not_none("publication_places",
publication_places)
if isbn_or_issn:
is_part_of["identifiers"] = [
metajson_service.create_identifier(isbn_or_issn_type,
isbn_or_issn)
]
is_part_of.add_items_to_key([is_part_of_is_part_of], "is_part_ofs")
else:
# is_part_of in case of no is_part_of.is_part_of
# creators with role edt
is_part_of.add_creators(secondary_creators)
#is_part_of.set_key_if_not_none("date_issued",date_year)
is_part_of.set_key_if_not_none("publishers", publishers)
is_part_of.set_key_if_not_none("publication_places",
publication_places)
if isbn_or_issn:
is_part_of["identifiers"] = [
metajson_service.create_identifier(isbn_or_issn_type,
isbn_or_issn)
]
if "title" in is_part_of and is_part_of["title"]:
document.add_items_to_key([is_part_of], "is_part_ofs")
else:
if isbn_or_issn:
document["identifiers"] = [
metajson_service.create_identifier(isbn_or_issn_type,
isbn_or_issn)
]
if publishers:
if endnote_type == TYPE_THESIS:
document.add_creators([
creator_service.formatted_name_to_creator(
publishers[0], "orgunit", "dgg")
])
elif endnote_type == TYPE_FILM_OR_BROADCAST:
document.add_creators([
creator_service.formatted_name_to_creator(
publishers[0], "orgunit", "dst")
])
else:
document.set_key_if_not_none("publishers", publishers)
document.set_key_if_not_none("publication_places", publication_places)
# seriess[]
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION]:
series = Document()
series["rec_type"] = constants.DOC_TYPE_SERIES
if endnote_type == TYPE_BOOK and title_secondary:
series.set_key_if_not_none("title", title_secondary)
series.add_creators(secondary_creators)
series.set_key_if_not_none("part_volume", part_number)
if endnote_type == TYPE_BOOK_SECTION and title_tertiary:
series.set_key_if_not_none("title", title_tertiary)
series.add_creators(tertiary_creators)
series.set_key_if_not_none("part_volume", part_number)
if "title" in series and len(series) > 2:
document.add_items_to_key([series], "seriess")
# originals[]
if (reprint_edition or title_translated or orig_pub) and endnote_type in [
TYPE_BOOK, TYPE_BOOK_SECTION, TYPE_JOURNAL_ARTICLE,
TYPE_FILM_OR_BROADCAST
]:
original_title = None
original_is_part_of = None
if reprint_edition:
original_title = reprint_edition
if title_translated and is_part_of_is_part_of_type is None:
original_title = title_translated
if orig_pub:
if is_part_of_type is not None:
original_is_part_of = Document()
original_is_part_of["rec_type"] = is_part_of_type
original_is_part_of["title"] = orig_pub
else:
original_title = orig_pub
if original_title:
original = Document()
original["rec_type"] = rec_type
original.set_key_if_not_none("title", original_title)
original.add_item_to_key(original_is_part_of, "is_part_ofs")
document.add_item_to_key(original, "originals")
# is_review_ofs[]
if reviewed_item and endnote_type in [
TYPE_BOOK_SECTION, TYPE_JOURNAL_ARTICLE
]:
is_review_ofs = Document()
is_review_ofs.set_key_if_not_none("title", reviewed_item)
is_review_ofs.set_key_if_not_none("rec_type", "Book")
document.add_items_to_key([is_review_ofs], "is_review_ofs")
# descriptions[0].value
if abstract:
document["descriptions"] = [{"value": abstract, "language": "und"}]
# archive
if endnote_type == TYPE_FIGURE and remote_database_provider:
archive = Document()
archive["title"] = remote_database_provider
document.add_items_to_key([archive], "archive")
# caption
document.set_key_if_not_none("caption", caption)
# creators[]
document.add_creators(primary_creators)
if endnote_type in [TYPE_BOOK, TYPE_THESIS, TYPE_FILM_OR_BROADCAST]:
document.add_creators(tertiary_creators)
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION, TYPE_FILM_OR_BROADCAST]:
document.add_creators(subsidiary_creators)
if custom4:
document.add_creators(
endnote_authors_to_creators(custom4, "person", "rev"))
if endnote_type == TYPE_FIGURE and remote_database_name:
document.add_creators(
endnote_authors_to_creators(remote_database_name, None, "cph"))
# edition
if endnote_type in [
TYPE_BOOK, TYPE_BOOK_SECTION, TYPE_FILM_OR_BROADCAST, TYPE_WEB_PAGE
] and edition:
document["edition"] = edition
# extent_pages, extent_volumes
if endnote_type in [TYPE_BOOK, TYPE_THESIS] and pages:
document["extent_pages"] = pages.replace("p.", "").strip()
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION] and extent_volumes:
document["extent_volumes"] = extent_volumes
# date_issued, date_issued_first
if date_year:
date_issued = ""
date_issued_first = ""
orig_index_begin = date_year.find("[")
orig_index_end = date_year.find("]")
if orig_index_begin != -1 and orig_index_end != -1:
date_issued_first = date_year[orig_index_begin + 1:orig_index_end]
date_issued = date_year.replace("[" + date_issued_first + "]",
"").strip()
else:
date_issued = date_year.strip()
if "is_part_ofs" in document:
if document["is_part_ofs"][0][
"rec_type"] == constants.DOC_TYPE_BOOK:
document["is_part_ofs"][0].set_key_if_not_none(
"date_issued", date_issued)
document["is_part_ofs"][0].set_key_if_not_none(
"date_issued_first", date_issued_first)
elif "is_part_ofs" in document["is_part_ofs"][0] and document[
"is_part_ofs"][0]["is_part_ofs"][0][
"rec_type"] == constants.DOC_TYPE_BOOK:
document["is_part_ofs"][0]["is_part_ofs"][
0].set_key_if_not_none("date_issued", date_issued)
document["is_part_ofs"][0]["is_part_ofs"][
0].set_key_if_not_none("date_issued_first",
date_issued_first)
else:
document.set_key_if_not_none("date_issued_first",
date_issued_first)
if rec_type in unpublished_types:
document.set_key_if_not_none("date_created", date_issued)
else:
document.set_key_if_not_none("date_issued", date_issued)
else:
document.set_key_if_not_none("date_issued_first",
date_issued_first)
if rec_type in unpublished_types:
document.set_key_if_not_none("date_created", date_issued)
else:
document.set_key_if_not_none("date_issued", date_issued)
# identifiers[]
identifiers = []
if accessionnumber:
identifiers.append(
metajson_service.create_identifier("accessionnumber",
accessionnumber))
if callnumber:
identifiers.append(
metajson_service.create_identifier("callnumber", callnumber))
if doi:
identifiers.append(metajson_service.create_identifier("doi", doi))
if identifiers:
document["identifiers"] = identifiers
# language
if language:
rfc5646 = language_service.convert_unknown_format_to_rfc5646(language)
if rfc5646:
document["languages"] = [rfc5646]
# note
if endnote_import_note and note:
document.set_key_with_value_type_in_list("notes", note, "general")
if endnote_import_research_note and research_notes:
document.set_key_with_value_type_in_list("notes", research_notes,
"user")
# part_page_begin & part_page_end
if endnote_type in [TYPE_BOOK_SECTION, TYPE_FIGURE, TYPE_JOURNAL_ARTICLE
] and pages:
hyphen_index = pages.find("-")
if hyphen_index == -1:
document["part_page_begin"] = pages.replace("p.", "").strip()
else:
document["part_page_begin"] = pages[:hyphen_index].replace(
"p.", "").strip()
document["part_page_end"] = pages[hyphen_index + 1:].replace(
"p.", "").strip()
if endnote_type in [TYPE_JOURNAL_ARTICLE]:
document.set_key_if_not_none("part_issue", part_number)
elif endnote_type in [TYPE_FIGURE]:
document.set_key_if_not_none("part_number", part_number)
document.set_key_if_not_none("part_section", part_section)
document.set_key_if_not_none("part_volume", part_volume)
# resources[0]
if url is not None:
resource = Resource()
resource["rec_type"] = "ResourceRemote"
resource.set_key_if_not_none("url", url)
if endnote_type == TYPE_WEB_PAGE:
resource.set_key_if_not_none("date_last_accessed", part_number)
else:
resource.set_key_if_not_none("date_last_accessed", access_date)
document["resources"] = [resource]
# subjects[]
if endnote_import_keywords and keywords:
for keyword in keywords.split():
document.set_key_with_value_type_in_list("subjects", keyword,
"topic")
# title, title_alternative, title_abbreviated, title_translated
document["title"] = title
if title_alternative:
document["title_alternatives"] = [{"title": title_alternative}]
if title_abbreviated:
document["title_abbreviateds"] = [{"title": title_abbreviated}]
#logging.debug("# endnote_type: {}".format(endnote_type))
metajson_service.pretty_print_document(document)
return document
def endnotexml_record_to_metajson(record, source, rec_id_prefix):
document = Document()
# TODO
# translated_creators: /contributors/translated-authors/author/style
# auth_address: /auth-address/style
# label: /label/style
# custom1
# Extract endnote properties
rec_id = record.find("rec-number").text
endnote_type = record.find("ref-type").text
rec_type = endnote_record_type_to_metajson_document_type[endnote_type]
primary_creators = extract_creators(None, "aut", record, "./contributors/authors/author/style")
secondary_creators = extract_creators(None, "pbd", record, "./contributors/secondary-authors/author/style")
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION]:
tertiary_creators = extract_creators(None, "pbd", record, "./contributors/tertiary-authors/author/style")
elif endnote_type == TYPE_THESIS:
tertiary_creators = extract_creators(None, "ths", record, "./contributors/tertiary-authors/author/style")
elif endnote_type == TYPE_FILM_OR_BROADCAST:
tertiary_creators = extract_creators(None, "pro", record, "./contributors/tertiary-authors/author/style")
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION]:
subsidiary_creators = extract_creators(None, "trl", record, "./contributors/subsidiary-authors/author/style")
elif endnote_type == TYPE_FILM_OR_BROADCAST:
subsidiary_creators = extract_creators(None, "act", record, "./contributors/subsidiary-authors/author/style")
translated_creators = extract_creators(None, "trl", record, "./contributors/translated-authors/author/style")
auth_address = extract_text(record, "./auth-address/style")
title = extract_text(record, "./titles/title/style")
title_secondary = extract_text(record, "./titles/secondary-title/style")
title_tertiary = extract_text(record, "./titles/tertiary-title/style")
title_alternative = extract_text(record, "./titles/alt-title/style")
title_abbreviated = extract_text(record, "./titles/short-title/style")
title_translated = extract_text(record, "./titles/translated-title/style")
pages = extract_text(record, "./pages/style")
part_volume = extract_text(record, "./volume/style")
part_number = extract_text(record, "./number/style")
extent_volumes = extract_text(record, "./num-vols/style")
edition = extract_text(record, "./edition/style")
part_section = extract_text(record, "./section/style")
reprint_edition = extract_text(record, "./reprint-edition/style")
keywords = extract_text(record, "./keywords/keyword/style")
date_year = extract_text(record, "./dates/year/style")
date_pub = extract_text(record, "./dates/pub-dates/date/style")
publication_places_formatted = extract_text(record, "./pub-location/style")
publishers_formatted = extract_text(record, "./publisher/style")
orig_pub = extract_text(record, "./orig-pub/style")
isbn_or_issn = extract_text(record, "./isbn/style")
accessionnumber = extract_text(record, "./accession-num/style")
callnumber = extract_text(record, "./call-num/style")
if endnote_type == TYPE_WEB_PAGE:
abstract = extract_text(record, "./pages/style")
else:
abstract = extract_text(record, "./abstract/style")
label = extract_text(record, "./label/style")
caption = extract_text(record, "./caption/style")
note = extract_text(record, "./notes/style")
reviewed_item = extract_text(record, "./reviewed-item/style")
rec_type_description = extract_text(record, "./work-type/style")
url = extract_text(record, "./urls/related-urls/url/style")
custom1 = extract_text(record, "./custom1/style")
custom2 = extract_text(record, "./custom2/style")
custom3 = extract_text(record, "./custom3/style")
custom4 = extract_text(record, "./custom4/style")
custom5 = extract_text(record, "./custom5/style")
custom6 = extract_text(record, "./custom6/style")
custom7 = extract_text(record, "./custom7/style")
doi = extract_text(record, "./electronic-resource-num/style")
remote_database_name = extract_text(record, "./remote-database-name/style")
remote_database_provider = extract_text(record, "./remote-database-provider/style")
research_notes = extract_text(record, "./research-notes/style")
language = extract_text(record, "./language/style")
access_date = extract_text(record, "./access-date/style")
# rec_id, rec_source
document["rec_id"] = rec_id
if source:
document["rec_source"] = source
# publishers_formatted, publication_places_formatted
publishers = None
publication_places = None
if publishers_formatted:
publishers = publishers_formatted.split("\r")
if publication_places_formatted:
publication_places = publication_places_formatted.split("\r")
# type, is_part_of.type, is_part_of.is_part_of.type
try:
is_part_of_type = endnote_record_type_to_metajson_document_is_part_of_type[endnote_type]
except:
is_part_of_type = None
is_part_of_is_part_of_type = None
if title_secondary is not None:
if endnote_type == TYPE_FIGURE:
# how to determine the is_part_of type ?
# if there is a volume or an issue number, it's a JournalArticle, else it's a Book or BookPart
if part_volume is not None or part_number is not None:
is_part_of_type = constants.DOC_TYPE_JOURNALARTICLE
is_part_of_is_part_of_type = constants.DOC_TYPE_JOURNAL
else:
if title_translated is not None:
is_part_of_type = constants.DOC_TYPE_BOOKPART
is_part_of_is_part_of_type = constants.DOC_TYPE_BOOK
else:
is_part_of_type = constants.DOC_TYPE_BOOK
elif endnote_type == TYPE_FILM_OR_BROADCAST:
rec_type = constants.DOC_TYPE_VIDEOPART
is_part_of_type = constants.DOC_TYPE_VIDEORECORDING
document["rec_type"] = rec_type
document.set_key_if_not_none("rec_type_description", rec_type_description)
# issn or isbn ?
if is_part_of_type in [constants.DOC_TYPE_JOURNAL, constants.DOC_TYPE_NEWSPAPER, constants.DOC_TYPE_MAGAZINE]:
isbn_or_issn_type = "issn"
else:
isbn_or_issn_type = "isbn"
# is_part_of, is_part_of.is_part_of
if is_part_of_type is not None and title_secondary:
is_part_of = Document()
is_part_of.set_key_if_not_none("rec_type", is_part_of_type)
is_part_of.set_key_if_not_none("title", title_secondary)
if is_part_of_is_part_of_type is not None:
# is_part_of in case of is_part_of.is_part_of
# creators with role aut
is_part_of.add_creators(creator_service.change_contibutors_role(secondary_creators, "aut"))
# is_part_of.is_part_of
is_part_of_is_part_of = Document()
is_part_of_is_part_of.set_key_if_not_none("rec_type", is_part_of_is_part_of_type)
is_part_of_is_part_of.set_key_if_not_none("title", title_translated)
# creators with role pbd
is_part_of_is_part_of.add_creators(creator_service.change_contibutors_role(translated_creators, "pbd"))
#is_part_of_is_part_of.set_key_if_not_none("date_issued",date_year)
is_part_of_is_part_of.set_key_if_not_none("publishers", publishers)
is_part_of_is_part_of.set_key_if_not_none("publication_places", publication_places)
if isbn_or_issn:
is_part_of["identifiers"] = [metajson_service.create_identifier(isbn_or_issn_type, isbn_or_issn)]
is_part_of.add_items_to_key([is_part_of_is_part_of], "is_part_ofs")
else:
# is_part_of in case of no is_part_of.is_part_of
# creators with role edt
is_part_of.add_creators(secondary_creators)
#is_part_of.set_key_if_not_none("date_issued",date_year)
is_part_of.set_key_if_not_none("publishers", publishers)
is_part_of.set_key_if_not_none("publication_places", publication_places)
if isbn_or_issn:
is_part_of["identifiers"] = [metajson_service.create_identifier(isbn_or_issn_type, isbn_or_issn)]
if "title" in is_part_of and is_part_of["title"]:
document.add_items_to_key([is_part_of], "is_part_ofs")
else:
if isbn_or_issn:
document["identifiers"] = [metajson_service.create_identifier(isbn_or_issn_type, isbn_or_issn)]
if publishers:
if endnote_type == TYPE_THESIS:
document.add_creators([creator_service.formatted_name_to_creator(publishers[0], "orgunit", "dgg")])
elif endnote_type == TYPE_FILM_OR_BROADCAST:
document.add_creators([creator_service.formatted_name_to_creator(publishers[0], "orgunit", "dst")])
else:
document.set_key_if_not_none("publishers", publishers)
document.set_key_if_not_none("publication_places", publication_places)
# seriess[]
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION]:
series = Document()
series["rec_type"] = constants.DOC_TYPE_SERIES
if endnote_type == TYPE_BOOK and title_secondary:
series.set_key_if_not_none("title", title_secondary)
series.add_creators(secondary_creators)
series.set_key_if_not_none("part_volume", part_number)
if endnote_type == TYPE_BOOK_SECTION and title_tertiary:
series.set_key_if_not_none("title", title_tertiary)
series.add_creators(tertiary_creators)
series.set_key_if_not_none("part_volume", part_number)
if "title" in series and len(series) > 2:
document.add_items_to_key([series], "seriess")
# originals[]
if (reprint_edition or title_translated or orig_pub) and endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION, TYPE_JOURNAL_ARTICLE, TYPE_FILM_OR_BROADCAST]:
original_title = None
original_is_part_of = None
if reprint_edition:
original_title = reprint_edition
if title_translated and is_part_of_is_part_of_type is None:
original_title = title_translated
if orig_pub:
if is_part_of_type is not None:
original_is_part_of = Document()
original_is_part_of["rec_type"] = is_part_of_type
original_is_part_of["title"] = orig_pub
else:
original_title = orig_pub
if original_title:
original = Document()
original["rec_type"] = rec_type
original.set_key_if_not_none("title", original_title)
original.add_item_to_key(original_is_part_of, "is_part_ofs")
document.add_item_to_key(original, "originals")
# is_review_ofs[]
if reviewed_item and endnote_type in [TYPE_BOOK_SECTION, TYPE_JOURNAL_ARTICLE]:
is_review_ofs = Document()
is_review_ofs.set_key_if_not_none("title", reviewed_item)
is_review_ofs.set_key_if_not_none("rec_type", "Book")
document.add_items_to_key([is_review_ofs], "is_review_ofs")
# descriptions[0].value
if abstract:
document["descriptions"] = [{"value": abstract, "language": "und"}]
# archive
if endnote_type == TYPE_FIGURE and remote_database_provider:
archive = Document()
archive["title"] = remote_database_provider
document.add_items_to_key([archive], "archive")
# caption
document.set_key_if_not_none("caption", caption)
# creators[]
document.add_creators(primary_creators)
if endnote_type in [TYPE_BOOK, TYPE_THESIS, TYPE_FILM_OR_BROADCAST]:
document.add_creators(tertiary_creators)
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION, TYPE_FILM_OR_BROADCAST]:
document.add_creators(subsidiary_creators)
if custom4:
document.add_creators(endnote_authors_to_creators(custom4, "person", "rev"))
if endnote_type == TYPE_FIGURE and remote_database_name:
document.add_creators(endnote_authors_to_creators(remote_database_name, None, "cph"))
# edition
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION, TYPE_FILM_OR_BROADCAST, TYPE_WEB_PAGE] and edition:
document["edition"] = edition
# extent_pages, extent_volumes
if endnote_type in [TYPE_BOOK, TYPE_THESIS] and pages:
document["extent_pages"] = pages.replace("p.", "").strip()
if endnote_type in [TYPE_BOOK, TYPE_BOOK_SECTION] and extent_volumes:
document["extent_volumes"] = extent_volumes
# date_issued, date_issued_first
if date_year:
date_issued = ""
date_issued_first = ""
orig_index_begin = date_year.find("[")
orig_index_end = date_year.find("]")
if orig_index_begin != -1 and orig_index_end != -1:
date_issued_first = date_year[orig_index_begin + 1: orig_index_end]
date_issued = date_year.replace("[" + date_issued_first + "]", "").strip()
else:
date_issued = date_year.strip()
if "is_part_ofs" in document:
if document["is_part_ofs"][0]["rec_type"] == constants.DOC_TYPE_BOOK:
document["is_part_ofs"][0].set_key_if_not_none("date_issued", date_issued)
document["is_part_ofs"][0].set_key_if_not_none("date_issued_first", date_issued_first)
elif "is_part_ofs" in document["is_part_ofs"][0] and document["is_part_ofs"][0]["is_part_ofs"][0]["rec_type"] == constants.DOC_TYPE_BOOK:
document["is_part_ofs"][0]["is_part_ofs"][0].set_key_if_not_none("date_issued", date_issued)
document["is_part_ofs"][0]["is_part_ofs"][0].set_key_if_not_none("date_issued_first", date_issued_first)
else:
document.set_key_if_not_none("date_issued_first", date_issued_first)
if rec_type in unpublished_types:
document.set_key_if_not_none("date_created", date_issued)
else:
document.set_key_if_not_none("date_issued", date_issued)
else:
document.set_key_if_not_none("date_issued_first", date_issued_first)
if rec_type in unpublished_types:
document.set_key_if_not_none("date_created", date_issued)
else:
document.set_key_if_not_none("date_issued", date_issued)
# identifiers[]
identifiers = []
if accessionnumber:
identifiers.append(metajson_service.create_identifier("accessionnumber", accessionnumber))
if callnumber:
identifiers.append(metajson_service.create_identifier("callnumber", callnumber))
if doi:
identifiers.append(metajson_service.create_identifier("doi", doi))
if identifiers:
document["identifiers"] = identifiers
# language
if language:
rfc5646 = language_service.convert_unknown_format_to_rfc5646(language)
if rfc5646:
document["languages"] = [rfc5646]
# note
if endnote_import_note and note:
document.set_key_with_value_type_in_list("notes", note, "general")
if endnote_import_research_note and research_notes:
document.set_key_with_value_type_in_list("notes", research_notes, "user")
# part_page_begin & part_page_end
if endnote_type in [TYPE_BOOK_SECTION, TYPE_FIGURE, TYPE_JOURNAL_ARTICLE] and pages:
hyphen_index = pages.find("-")
if hyphen_index == -1:
document["part_page_begin"] = pages.replace("p.", "").strip()
else:
document["part_page_begin"] = pages[:hyphen_index].replace("p.", "").strip()
document["part_page_end"] = pages[hyphen_index+1:].replace("p.", "").strip()
if endnote_type in [TYPE_JOURNAL_ARTICLE]:
document.set_key_if_not_none("part_issue", part_number)
elif endnote_type in [TYPE_FIGURE]:
document.set_key_if_not_none("part_number", part_number)
document.set_key_if_not_none("part_section", part_section)
document.set_key_if_not_none("part_volume", part_volume)
# resources[0]
if url is not None:
resource = Resource()
resource["rec_type"] = "ResourceRemote"
resource.set_key_if_not_none("url", url)
if endnote_type == TYPE_WEB_PAGE:
resource.set_key_if_not_none("date_last_accessed", part_number)
else:
resource.set_key_if_not_none("date_last_accessed", access_date)
document["resources"] = [resource]
# subjects[]
if endnote_import_keywords and keywords:
for keyword in keywords.split():
document.set_key_with_value_type_in_list("subjects", keyword, "topic")
# title, title_alternative, title_abbreviated, title_translated
document["title"] = title
if title_alternative:
document["title_alternatives"] = [{"title": title_alternative}]
if title_abbreviated:
document["title_abbreviateds"] = [{"title": title_abbreviated}]
#logging.debug("# endnote_type: {}".format(endnote_type))
metajson_service.pretty_print_document(document)
return document
def ris_txt_lines_to_metajson_list(txt_lines, source, rec_id_prefix, only_first_record):
document = None
ris_type = None
rec_type = None
is_part_of_rec_type = None
previous_key = None
previous_value = None
for line in txt_lines:
if line:
line = line.rstrip('\r\n')
#logging.debug("line: {}".format(line))
# multi line management
if previous_key:
key = previous_key
value = previous_value + line
previous_key = None
previous_value = None
else:
key = line[:2].strip()
value = line[6:].strip()
if value.endswith("/") and key not in ["Y1", "PY"]:
#logging.debug("multi line")
previous_key = key
previous_value = value.rstrip('/')
continue
if key is None or len(key) == 0:
# empty line -> continue
#logging.debug("empty line")
continue
elif key == RIS_KEY_BEGIN:
# record begin with document type -> create document
# init
document = Document()
is_part_of_rec_type = None
if source:
document["rec_source"] = source
ris_type = value
rec_type = ris_document_type_to_metajson_document_type[ris_type]
document["rec_type"] = rec_type
if ris_type in ris_document_type_to_metajson_document_is_part_of_type:
is_part_of_rec_type = ris_document_type_to_metajson_document_is_part_of_type[ris_type]
is_part_of = Document()
is_part_of["rec_type"] = is_part_of_rec_type
document["is_part_ofs"] = [is_part_of]
elif key == RIS_KEY_END:
# record end -> return the result
# verify the is_part_ofs[0]["title"]
if "is_part_ofs" in document and "title" not in document["is_part_ofs"][0] and "title_abbreviateds" in document["is_part_ofs"][0]:
document["is_part_ofs"][0]["title"] = document["is_part_ofs"][0]["title_abbreviateds"][0]["title"]
del document["is_part_ofs"][0]["title_abbreviateds"]
logging.info("# RIS type: {}".format(ris_type))
metajson_service.pretty_print_document(document)
yield document
else:
# process key value
#logging.debug("key: {}; value: {}".format(key, value))
if key == "ID":
document["rec_id"] = value
elif key in ["T1", "TI", "CT"] or (key == "BT" and ris_type in [RIS_TYPE_BOOK, RIS_TYPE_UNPB]):
# Title Primary -> title
document["title"] = value
elif key in ["JF", "JO"] or (key == "BT" and ris_type not in [RIS_TYPE_BOOK, RIS_TYPE_UNPB]):
# Title Secondary -> is_part_of["title"]
document.add_is_part_of_title(value)
elif key in ["JA", "J1", "J2", "T2"]:
# Title Secondary -> is_part_of["title_abbreviateds"][O]["title"]
document.add_is_part_of_title_abbreviated(value)
elif key == "T3":
# Title Series
document.add_series_title(value)
elif key in ["A1", "AU"]:
document.add_creator(creator_service.formatted_name_to_creator(value, None, "aut"))
elif key in ["A2", "ED"]:
if is_part_of_rec_type:
document.add_is_part_of_creator(creator_service.formatted_name_to_creator(value, None, "edt"))
else:
document.add_creator(creator_service.formatted_name_to_creator(value, None, "edt"))
elif key == "A3":
document.add_series_creator(creator_service.formatted_name_to_creator(value, None, "aut"))
elif key == "A4":
document.add_creator(creator_service.formatted_name_to_creator(value, None, "ctb"))
elif key in ["PY", "Y1", "DA"]:
index_slash = value.find("/")
if index_slash != -1:
# YYYY/MM/DD/other info (like season)
# todo
document["date_issued"] = value.strip("/")
else:
document["date_issued"] = value
elif key == "SP":
document["part_page_begin"] = value
elif key == "EP":
document["part_page_end"] = value
elif key == "VL":
document["part_volume"] = value
elif key in ["IS", "CP"]:
document["part_issue"] = value
elif key in ["AB", "N2"]:
document["descriptions"] = [{"language": "und", "value": value}]
elif key == "N1":
document["notes"] = [{"language": "und", "value": value}]
elif key == "PB":
document.add_item_to_key(value, "publishers")
elif key == "CY":
document.add_item_to_key(value, "publication_places")
elif key == "RP":
document["publication_status"] = value
elif key == "ET":
document["edition"] = value
elif key == "UR":
resource = Resource()
resource["url"] = value
document.add_item_to_key(resource, "resources")
elif key == "AN":
# Accession Number
identifier = metajson_service.create_identifier("accessionnumber", value)
document.add_identifier(identifier)
elif key == "CN":
# Call Number
identifier = metajson_service.create_identifier("callnumber", value)
document.add_identifier(identifier)
elif key == "DO":
# DOI
identifier = metajson_service.create_identifier("doi", value)
document.add_identifier(identifier)
elif key == "SN":
# ISBN or ISSN ?
id_type = None
if rec_type in [constants.DOC_TYPE_JOURNALARTICLE, constants.DOC_TYPE_MAGAZINEARTICLE, constants.DOC_TYPE_NEWSPAPERARTICLE, constants.DOC_TYPE_JOURNAL]:
id_type = "issn"
else:
id_type = "isbn"
identifier = metajson_service.create_identifier(id_type, value)
if is_part_of_rec_type is None:
document.add_identifier(identifier)
else:
document["is_part_ofs"][0].add_identifier(identifier)
elif key == "CA":
document["caption"] = value
elif key == "DB":
# Name of Database -> rec_source ?
document["rec_source"] = value
elif key == "DP":
# NDatabase Provider -> rec_source ?
document["rec_source"] = value
elif key == "KW":
if "keywords" not in document:
document["keywords"] = {"und": []}
document["keywords"]["und"].append(value)
else:
logging.debug("Not managed key: {} with value: {}".format(key, value))
