Spaces:
Running
Running
File size: 1,493 Bytes
d2b9031 49e25d2 ff86828 d2b9031 49e25d2 9abfad3 49e25d2 9abfad3 ff86828 49e25d2 ff86828 9faad6b 9abfad3 9faad6b 9abfad3 9faad6b ff86828 9abfad3 7773ef1 ff86828 7773ef1 49e25d2 72dd3ca ff86828 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 |
import gradio as gr
import pandas as pd
import requests
from io import BytesIO
def convert_parquet_to_jsonl(parquet_file=None, parquet_url=None):
# Read Parquet from file or URL
if parquet_file is not None:
df = pd.read_parquet(parquet_file.name)
elif parquet_url is not None:
response = requests.get(parquet_url)
response.raise_for_status()
df = pd.read_parquet(BytesIO(response.content))
else:
raise ValueError("Either parquet_file or parquet_url must be provided")
# Clean string columns to replace invalid UTF-8 sequences
for col in df.select_dtypes(include=["object"]).columns:
df[col] = df[col].apply(
lambda x: x.encode("utf-8", errors="replace").decode("utf-8", errors="replace") if isinstance(x, str) else x
)
# Convert to JSON Lines
jsonl_data = df.to_json(orient="records", lines=True)
# Write the output to a file using UTF-8 encoding explicitly
output_file_path = "output.jsonl"
with open(output_file_path, "w", encoding="utf-8") as f:
f.write(jsonl_data)
return output_file_path
demo = gr.Interface(
fn=convert_parquet_to_jsonl,
inputs=[gr.File(label="Parquet File"), gr.Textbox(label="Parquet File URL")],
outputs=[gr.File(label="JSONL Output")],
title="Parquet to JSONL Converter",
description="Convert a Parquet file to JSONL format from a downloadable link or file upload"
)
if __name__ == "__main__":
demo.launch()
|