jimallman · September 21, 2019 17:35
diff --git a/gather-curator-names.py b/gather-curator-names.py
 #!/usr/bin/env python3
 # Scan all nearby studies for unique '^ot:curatorName' values
 import os
 import json

 studies_found = 0
 unique_names = [ ]
 try:
    # look for "bundles" of studies with IDs ending in (e.g.) "99"
    for bundle_dirname in os.listdir('study'):
        print("  ", bundle_dirname)
        # look for individual study subdirectores in this bundle, e.g. 'ot_2199'
        for study_dirname in os.listdir('study/'+ bundle_dirname):
            print("    ", study_dirname, end=", ")
            # each study should have one Nexson (JSON) file with the same name
            full_path_to_nexson = 'study/'+ bundle_dirname +'/'+ study_dirname +'/'+ study_dirname +'.json'
            try:
                with open(full_path_to_nexson) as nexson_file:
                    data = json.load(nexson_file)
                    #print(data['nexml'].keys())
                    nexml = data['nexml']
                    study_version = nexml.get('@version', "NOT FOUND")
                    print("version: ", study_version, end=", ")
                    study_curators = nexml.get('^ot:curatorName', "NOT FOUND")
                    if type(study_curators) is not list:
                        study_curators = [study_curators]
                    print("^ot:curatorName: ", study_curators)
                    for curator_name in study_curators:
                        if curator_name not in unique_names:
                            unique_names.append(curator_name)
                studies_found += 1
            except:
                print("Nexson file broken or not found: ", full_path_to_nexson)
 except:
    print("Expected to find local dir 'study' with nested subdirectories! Are we in the right place?")
 print("====")

 print(studies_found, " studies found and scanned. ")
 print(len(unique_names), " unique names found. ")
 for found_name in unique_names:
    print("  ", found_name)

 # TODO: Write these to a file, consolidate all found names to Github userids and current name
	#!/usr/bin/env python3
	# Scan all nearby studies for unique '^ot:curatorName' values
	import os
	import json

	studies_found = 0
	unique_names = [ ]
	try:
	# look for "bundles" of studies with IDs ending in (e.g.) "99"
	for bundle_dirname in os.listdir('study'):
	print(" ", bundle_dirname)
	# look for individual study subdirectores in this bundle, e.g. 'ot_2199'
	for study_dirname in os.listdir('study/'+ bundle_dirname):
	print(" ", study_dirname, end=", ")
	# each study should have one Nexson (JSON) file with the same name
	full_path_to_nexson = 'study/'+ bundle_dirname +'/'+ study_dirname +'/'+ study_dirname +'.json'
	try:
	with open(full_path_to_nexson) as nexson_file:
	data = json.load(nexson_file)
	#print(data['nexml'].keys())
	nexml = data['nexml']
	study_version = nexml.get('@version', "NOT FOUND")
	print("version: ", study_version, end=", ")
	study_curators = nexml.get('^ot:curatorName', "NOT FOUND")
	if type(study_curators) is not list:
	study_curators = [study_curators]
	print("^ot:curatorName: ", study_curators)
	for curator_name in study_curators:
	if curator_name not in unique_names:
	unique_names.append(curator_name)
	studies_found += 1
	except:
	print("Nexson file broken or not found: ", full_path_to_nexson)
	except:
	print("Expected to find local dir 'study' with nested subdirectories! Are we in the right place?")
	print("====")

	print(studies_found, " studies found and scanned. ")
	print(len(unique_names), " unique names found. ")
	for found_name in unique_names:
	print(" ", found_name)

	# TODO: Write these to a file, consolidate all found names to Github userids and current name