clique / src /.ipynb_checkpoints /highlight_seeds_dot-checkpoint.py
qingy2024's picture
Upload folder using huggingface_hub
bf620c6 verified
#!/usr/bin/env python3
"""
highlight_seeds_dot.py
Highlight seed nodes (first cluster in a JSON seeds file) inside a GraphViz .dot file.
Usage
-----
python highlight_seeds_dot.py <input.dot> <seeds.json> <output.dot>
Every node listed in seeds.json[clusters][0]["seed_nodes"] will be rendered
[color="red", style="filled", fillcolor="red", fontcolor="white"]
and all its incident edges colored red.
The script prints *nothing* to stdout – it only writes the modified .dot file.
"""
from __future__ import annotations
import argparse
import json
import re
from pathlib import Path
def load_seeds(seeds_path: Path) -> set[int]:
"""Return the seed-node indices from the first cluster."""
with seeds_path.open("r", encoding="utf-8") as f:
data = json.load(f)
return {n - 1 for n in data["clusters"][0]["seed_nodes"]}
def highlight_dot(dot_path: Path, seeds: set[int], out_path: Path) -> None:
"""Read dot_path, highlight seeds and their edges, write to out_path."""
content = dot_path.read_text(encoding="utf-8")
# 1) highlight seed nodes
def node_replace(m: re.Match) -> str:
node_id = int(m.group(1))
if node_id in seeds:
return f'{m.group(0).rstrip(";")} [color="red", style="filled", fillcolor="red", fontcolor="white"];'
return m.group(0)
content = re.sub(rf'^\s*({"|".join(map(str, seeds))})\s*;', node_replace, content, flags=re.MULTILINE)
# 2) highlight edges incident to seeds
def edge_replace(m: re.Match) -> str:
u, v = int(m.group(1)), int(m.group(2))
if u in seeds or v in seeds:
return f'{m.group(0).rstrip(";")} [color="red"];'
return m.group(0)
content = re.sub(rf'^\s*({"|".join(map(str, seeds))})\s*--\s*(\d+)\s*;', edge_replace, content, flags=re.MULTILINE)
content = re.sub(rf'^\s*(\d+)\s*--\s*({"|".join(map(str, seeds))})\s*;', edge_replace, content, flags=re.MULTILINE)
out_path.parent.mkdir(parents=True, exist_ok=True)
out_path.write_text(content, encoding="utf-8")
def main() -> None:
parser = argparse.ArgumentParser(description=__doc__.strip(), formatter_class=argparse.RawTextHelpFormatter)
parser.add_argument("input_dot", type=str, help="Original GraphViz .dot file")
parser.add_argument("seeds_json", type=str, help="Seeds JSON file")
parser.add_argument("output_dot", type=str, help="Path to write highlighted .dot file")
args = parser.parse_args()
seeds = load_seeds(Path(args.seeds_json))
highlight_dot(Path(args.input_dot), seeds, Path(args.output_dot))
if __name__ == "__main__":
main()