def test():
base_dir = os.path.join(os.getcwd(), "data")
print "base_dir: {}".format(base_dir)
#query_string = "s.q=europe&s.cmd%5B%5D=addFacetValueFilters%28IsFullText%2Ctrue%29&s.fq%5B%5D=SourceType%3A%28%22Library+Catalog%22%29&s.fvf%5B%5D=ContentType%2CNewspaper+Article%2Ct&s.fvf%5B%5D=ContentType%2CBook+Review%2Ct&s.fvf%5B%5D=ContentType%2CDissertation%2Ct"
#query_string = "s.cmd=addFacetValueFilters(ContentType,Book+Review)&s.fvf%5B%5D=ContentType,Journal+Article,f&s.fvf%5B%5D=ContentType,Dissertation,t&s.fvf%5B%5D=IsFullText,true,f&s.fvf%5B%5D=ContentType,Newspaper+Article,t&s.q=europe"
#query_string = "s.cmd=addFacetValueFilters(ContentType,Journal+Article)&s.fvf=IsFullText,true,f&s.q=europe+federal"
#query_string = "s.fvf%5B%5D=ContentType%2CJournal+Article%2Cf&s.fvf%5B%5D=IsFullText%2Ctrue%2Cf&s.q=europe+federal&s.cmd=addFacetValueFilters(ContentType,Dissertation)%20removeFacetValueFilter(ContentType,Journal%20Article)"
#query_string = "s.fvf%5B%5D=ContentType%2CConference+Proceeding%2Cf&s.fvf%5B%5D=ContentType%2CData+Set%2Cf&s.fvf%5B%5D=IsFullText%2Ctrue%2Cf&s.fvf%5B%5D=ContentType%2CNewspaper+Article%2Cf&s.fvf%5B%5D=ContentType%2CTrade+Publication+Article%2Cf&s.ps=50&s.q=europe+federal&s.cmd=removeFacetValueFilter(ContentType,Newspaper%20Article)%20removeFacetValueFilter(ContentType,Trade%20Publication%20Article)%20removeFacetValueFilter(ContentType,Data%20Set)"
#query_string = "s.fvf%5B%5D=ContentType%2CConference+Proceeding%2Cf&s.fvf%5B%5D=IsFullText%2Ctrue%2Cf&s.ps=50&s.q=europe+federal&s.cmd=addFacetValueFilters(ContentType,Data+Set)"
query_string = "s.q=Organized+Crime+and+States"
# Thesis:
#query_string = "s.cmd=addFacetValueFilters(ContentType,Dissertation)&s.q=social"
# Video:
#query_string = "s.q=social&s.fvf%5B%5D=ContentType%2CVideo+Recording%2Cf"
# EditedBook
#query_string = "s.q=ouvrage+collectif&s.cmd=addFacetValueFilters(ContentType,Book+%2F+eBook)"
#query_string = "s.fvf%5B%5D=ContentType%2CConference+Proceeding%2Cf"
summon_response = summon.summon_query(query_string)
metajson_list = crosswalks_service.convert_json(
summon_response, constants.FORMAT_SUMMONJSON, "summon", False)
collection = metajson_service.create_collection("summon_test",
"Summon Test",
metajson_list)
print jsonbson.dumps_json(collection, True)
def convert_metajson_list_in_one_file(metajson_list, output_format):
if metajson_list:
if output_format == constants.FORMAT_METAJSON or output_format == constants.FORMAT_HTML:
yield metajson_service.create_collection(None, None, metajson_list)
elif output_format == constants.FORMAT_MODS:
yield mods_crosswalk.metajson_list_to_mods_xmletree(metajson_list)
elif output_format == constants.FORMAT_METS:
yield mets_crosswalk.metajson_list_to_mets_xmletree(metajson_list)
elif output_format == constants.FORMAT_REPEC:
yield repec_crosswalk.metajson_list_to_repec(metajson_list)
elif output_format == constants.FORMAT_CSV_METAJSON:
yield csv_crosswalk.metajson_list_to_csv_metajson(metajson_list)
else:
logging.error("convert_metajson_list ERROR Not managed format: {}".format(output_format))
def convert_metajson_list_in_one_file(metajson_list, output_format):
if metajson_list:
if output_format == constants.FORMAT_METAJSON or output_format == constants.FORMAT_HTML:
yield metajson_service.create_collection(None, None, metajson_list)
elif output_format == constants.FORMAT_MODS:
yield mods_crosswalk.metajson_list_to_mods_xmletree(metajson_list)
elif output_format == constants.FORMAT_METS:
yield mets_crosswalk.metajson_list_to_mets_xmletree(metajson_list)
elif output_format == constants.FORMAT_REPEC:
yield repec_crosswalk.metajson_list_to_repec(metajson_list)
elif output_format == constants.FORMAT_CSV_METAJSON:
yield csv_crosswalk.metajson_list_to_csv_metajson(metajson_list)
else:
logging.error("convert_metajson_list ERROR Not managed format: {}".format(output_format))
def parse_and_convert_file_list(input_file_path_list, input_format, output_format, source, rec_id_prefix, only_first_record, all_in_one_file):
""" Convert from a list of file path """
results = []
for input_file_path in input_file_path_list:
file_results = parse_and_convert_file(input_file_path, input_format, output_format, source, rec_id_prefix, only_first_record, False)
#logging.debug("parse_and_convert_file_list type(file_results): {}".format(type(file_results)))
if file_results:
results.extend(file_results)
if results:
if not all_in_one_file:
return results
else:
if output_format == constants.FORMAT_METAJSON or output_format == constants.FORMAT_HTML:
return metajson_service.create_collection(None, None, results)
elif output_format == constants.FORMAT_MODS:
return mods_crosswalk.create_mods_collection_xmletree(results)
else:
logging.error("parse_and_convert_file_list: ERROR Not managed format: {}".format(output_format))
def parse_and_convert_file_list(input_file_path_list, input_format, output_format, source, rec_id_prefix, only_first_record, all_in_one_file):
""" Convert from a list of file path """
results = []
for input_file_path in input_file_path_list:
file_results = parse_and_convert_file(input_file_path, input_format, output_format, source, rec_id_prefix, only_first_record, False)
#logging.debug("parse_and_convert_file_list type(file_results): {}".format(type(file_results)))
if file_results:
results.extend(file_results)
if results:
if not all_in_one_file:
return results
else:
if output_format == constants.FORMAT_METAJSON or output_format == constants.FORMAT_HTML:
return metajson_service.create_collection(None, None, results)
elif output_format == constants.FORMAT_MODS:
return mods_crosswalk.create_mods_collection_xmletree(results)
else:
logging.error("parse_and_convert_file_list: ERROR Not managed format: {}".format(output_format))
def test():
base_dir = os.path.join(os.getcwd(), "data")
print "base_dir: {}".format(base_dir)
#query_string = "s.q=europe&s.cmd%5B%5D=addFacetValueFilters%28IsFullText%2Ctrue%29&s.fq%5B%5D=SourceType%3A%28%22Library+Catalog%22%29&s.fvf%5B%5D=ContentType%2CNewspaper+Article%2Ct&s.fvf%5B%5D=ContentType%2CBook+Review%2Ct&s.fvf%5B%5D=ContentType%2CDissertation%2Ct"
#query_string = "s.cmd=addFacetValueFilters(ContentType,Book+Review)&s.fvf%5B%5D=ContentType,Journal+Article,f&s.fvf%5B%5D=ContentType,Dissertation,t&s.fvf%5B%5D=IsFullText,true,f&s.fvf%5B%5D=ContentType,Newspaper+Article,t&s.q=europe"
#query_string = "s.cmd=addFacetValueFilters(ContentType,Journal+Article)&s.fvf=IsFullText,true,f&s.q=europe+federal"
#query_string = "s.fvf%5B%5D=ContentType%2CJournal+Article%2Cf&s.fvf%5B%5D=IsFullText%2Ctrue%2Cf&s.q=europe+federal&s.cmd=addFacetValueFilters(ContentType,Dissertation)%20removeFacetValueFilter(ContentType,Journal%20Article)"
#query_string = "s.fvf%5B%5D=ContentType%2CConference+Proceeding%2Cf&s.fvf%5B%5D=ContentType%2CData+Set%2Cf&s.fvf%5B%5D=IsFullText%2Ctrue%2Cf&s.fvf%5B%5D=ContentType%2CNewspaper+Article%2Cf&s.fvf%5B%5D=ContentType%2CTrade+Publication+Article%2Cf&s.ps=50&s.q=europe+federal&s.cmd=removeFacetValueFilter(ContentType,Newspaper%20Article)%20removeFacetValueFilter(ContentType,Trade%20Publication%20Article)%20removeFacetValueFilter(ContentType,Data%20Set)"
#query_string = "s.fvf%5B%5D=ContentType%2CConference+Proceeding%2Cf&s.fvf%5B%5D=IsFullText%2Ctrue%2Cf&s.ps=50&s.q=europe+federal&s.cmd=addFacetValueFilters(ContentType,Data+Set)"
query_string = "s.q=Organized+Crime+and+States"
# Thesis:
#query_string = "s.cmd=addFacetValueFilters(ContentType,Dissertation)&s.q=social"
# Video:
#query_string = "s.q=social&s.fvf%5B%5D=ContentType%2CVideo+Recording%2Cf"
# EditedBook
#query_string = "s.q=ouvrage+collectif&s.cmd=addFacetValueFilters(ContentType,Book+%2F+eBook)"
#query_string = "s.fvf%5B%5D=ContentType%2CConference+Proceeding%2Cf"
summon_response = summon.summon_query(query_string)
metajson_list = crosswalks_service.convert_json(summon_response, constants.FORMAT_SUMMONJSON, "summon", False)
collection = metajson_service.create_collection("summon_test", "Summon Test", metajson_list)
print jsonbson.dumps_json(collection, True)
def write_metajson_collection(col_id, col_title, items, output_file_path):
if items:
#logging.debug("write_metajson_collection type(items): {}".format(type(items)))
collection = metajson_service.create_collection(col_id, col_title, items)
write_json(collection, output_file_path)
