Convert mwscrape's CouchDB dump json into PyGlossary's Tabfile

dump-json-to-tabfile.py

import os
import sys
import json
from pyglossary.text_utils import joinByBar, escapeNTB

filename = sys.argv[1]

with open(filename, encoding="utf-8") as file, open(filename+".txt", "w", encoding="utf-8") as outFile:
    for toplevelLine in file:
        for item in json.loads(toplevelLine):
            if "parse" not in item:
                # print(f"No 'parse' in {item}")
                continue
            parse = item["parse"]
            defi = parse["text"]["*"]
            terms = [parse["title"]]
            if "aliases" in item:
                for alias in item["aliases"]:
                    if not alias:
                        continue
                    if len(alias) == 2:
                        alt = alias[1] 
                    else:
                        alt = alias[0]
                    terms.append(alt)
                    assert "\n" not in alt, alt
            termsEscaped = [escapeNTB(term) for term in terms]
            outFile.write(joinByBar(termsEscaped) + "\t" + escapeNTB(defi) + "\n")