68 lines
1.9 KiB
Python
68 lines
1.9 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Pretty-print a JSON Lines (.jsonl) file.
|
|
|
|
Usage
|
|
-----
|
|
python scripts/jsonl_pretty_print.py path/to/file.jsonl [--indent 2]
|
|
|
|
The script reads each line, parses it as JSON, and writes a
|
|
human-readable representation to stdout. Redirect or pipe as needed.
|
|
|
|
Example
|
|
-------
|
|
python scripts/jsonl_pretty_print.py data.jsonl --indent 4 > pretty.json
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
|
|
def parse_args() -> argparse.Namespace:
|
|
parser = argparse.ArgumentParser(description="Pretty-print a .jsonl file.")
|
|
parser.add_argument(
|
|
"jsonl_path",
|
|
type=Path,
|
|
help="Path to the input .jsonl file",
|
|
)
|
|
parser.add_argument(
|
|
"--indent",
|
|
type=int,
|
|
default=2,
|
|
help="Number of spaces to indent (default: 2)",
|
|
)
|
|
return parser.parse_args()
|
|
|
|
|
|
def pretty_print_jsonl(path: Path, indent: int) -> None:
|
|
if not path.exists():
|
|
sys.exit(f"Error: {path} does not exist")
|
|
|
|
with path.open("r", encoding="utf-8") as fp:
|
|
for idx, line in enumerate(fp, start=1):
|
|
line = line.strip()
|
|
if not line:
|
|
continue # skip empty lines
|
|
try:
|
|
obj = json.loads(line)
|
|
except json.JSONDecodeError as exc:
|
|
sys.exit(f"JSON decode error on line {idx}: {exc}") # fail fast
|
|
# Build pretty JSON string, convert literal "\n" sequences to real newlines,
|
|
# and emit a blank line between records for readability.
|
|
pretty = json.dumps(obj, indent=indent, ensure_ascii=False, sort_keys=True)
|
|
pretty = pretty.replace("\\n", "\n")
|
|
sys.stdout.write(pretty)
|
|
sys.stdout.write("\n\n")
|
|
|
|
|
|
def main() -> None:
|
|
args = parse_args()
|
|
pretty_print_jsonl(args.jsonl_path, args.indent)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|