Fast processing of a CouchDB json import file. Related to this: https://simeon-yan-iliev.medium.com/export-import-a-database-with-couchdb-74bfec3831bc

process_couchdb_json.py

#!/usr/bin/env python
import sys
import json

if len(sys.argv) != 2:
    exit()

print("{\"docs\": [")

with open(sys.argv[1]) as infile:
    next(infile)
    for line in infile:
        line = line.rstrip()
        if line.startswith("{\"id"):
            doc = json.loads(line.rstrip(","))
            # Instead of specific values, if all doc, we could simply remove _rev below
            struct = {"_id": doc["doc"]["_id"], "off": doc["doc"]["off"]}
            end = ""
            if line.endswith(","):
                end = ","
            print(json.dumps(struct) + end)