Spaces:
Running
Running
| from collections import OrderedDict | |
| import pymarc | |
| def get_record_values(record, location): | |
| split = location.split("$") | |
| if len(split) == 1: | |
| tag = split[0] | |
| code = None | |
| elif len(split) == 2: | |
| tag, code = split | |
| else: | |
| raise ValueError("Invalid location") | |
| # Find fields matching tag | |
| fields = record.get_fields(tag) | |
| results = [] | |
| for current_value in fields: | |
| if current_value is not None: | |
| if code is not None: | |
| values = current_value.get_subfields(code) | |
| results.extend(values) | |
| elif isinstance(current_value, pymarc.Field): | |
| results.append(current_value.value()) | |
| return " ".join(results) | |
| def record_dict(record): | |
| d = OrderedDict() | |
| # Dump every field value into a string | |
| d["raw"] = " ".join([f.value() for f in record.fields]) | |
| d["cid"] = get_record_values(record, "CID") | |
| d["id"] = get_record_values(record, "001") | |
| fixed_data = get_record_values(record, "008") | |
| d["pub_date"] = fixed_data[7:11] | |
| d["pub_place"] = fixed_data[15:18] | |
| d["language"] = fixed_data[35:38] | |
| d["title_a"] = get_record_values(record, "245$a") | |
| d["title_b"] = get_record_values(record, "245$b") | |
| d["title_c"] = get_record_values(record, "245$c") | |
| d["title_p"] = get_record_values(record, "245$p") | |
| d["title"] = " ".join([d["title_a"], d["title_b"], d["title_p"]]) | |
| d["title_variation_a"] = get_record_values(record, "246$a") | |
| d["title_variation_b"] = get_record_values(record, "246$b") | |
| d["subject_headings"] = " ".join( | |
| get_record_values(record, "650$a") + get_record_values(record, "650$x") | |
| ) | |
| d["author_names"] = " ".join( | |
| [get_record_values(record, "100$a"), get_record_values(record, "700$a")] | |
| ) | |
| d["corporate_names"] = " ".join( | |
| [get_record_values(record, "110$a"), get_record_values(record, "710$a")] | |
| ) | |
| d["meeting_names"] = " ".join( | |
| [get_record_values(record, "111$a"), get_record_values(record, "711$a")] | |
| ) | |
| d["publisher"] = record.publisher or "" | |
| d["pagination"] = get_record_values(record, "300$a") | |
| d["dimensions"] = get_record_values(record, "300$c") | |
| return d | |
| def load_records(path): | |
| records = [] | |
| extension = path.split(".")[-1] | |
| if extension == "mrc" or extension == "marc": | |
| with open(path, "rb") as marcfile: | |
| reader = pymarc.MARCReader(marcfile) | |
| records.extend(list(reader)) | |
| elif extension == "json": | |
| with open(path, "r") as jsonfile: | |
| for line in jsonfile: | |
| record = pymarc.parse_json_to_array(line)[0] | |
| records.append(record) | |
| else: | |
| raise ValueError(f"Unsupported file extension: {extension}") | |
| return records | |