mirror of
https://github.com/lllin000/PaperForge.git
synced 2026-07-22 06:50:53 +00:00
288829bb5b
- RenderOutput dataclass with heading_events/emitted_block_events tracking - Stack-algorithm structure tree with own/subtree block IDs - Recursive body_units builder with role helper + token cap splitting - Schema v4: section_path_json, section_level, section_title, part_ordinal - Phase 4/5 reorder in ocr_rebuild.py and ocr.py - 12 new test cases for tree nesting, own_block_ids, rendered-order intervals
35 lines
1 KiB
Python
35 lines
1 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
|
|
def read_json(path: Path):
|
|
"""Read and parse a JSON file."""
|
|
return json.loads(path.read_text(encoding="utf-8"))
|
|
|
|
|
|
def write_json_atomic(path: Path, data) -> None:
|
|
"""Write JSON atomically using a temp file and replace."""
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
tmp = path.with_suffix(f"{path.suffix}.tmp")
|
|
tmp.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
|
|
tmp.replace(path)
|
|
|
|
|
|
def write_json(path: Path, data) -> None:
|
|
"""Write data as JSON, creating parent directories as needed."""
|
|
write_json_atomic(path, data)
|
|
|
|
|
|
def read_jsonl(path: Path) -> list[dict]:
|
|
"""Read a newline-delimited JSON file (one JSON object per line)."""
|
|
if not path.exists():
|
|
return []
|
|
rows: list[dict] = []
|
|
with open(path, encoding="utf-8") as f:
|
|
for line in f:
|
|
line = line.strip()
|
|
if line:
|
|
rows.append(json.loads(line))
|
|
return rows
|