Files
douyin_guaji-main/tools/scan_coords.py
T

98 lines
2.8 KiB
Python

"""
扫描仓库中疑似硬编码坐标/ROI 的脚本。
输出 CSV 到 `tools/coords_report.csv`。
用法:
python tools/scan_coords.py
原理: 使用简单正则匹配形如 (123, 456) 或 (100, 200, 300, 400) 的元组/列表。
"""
from pathlib import Path
import re
import csv
ROOT = Path(__file__).resolve().parents[1]
OUT_CSV = ROOT / "tools" / "coords_report.csv"
IGNORE_DIRS = {".git", "__pycache__", ".venv", "venv", "dist", "build"}
# 常见坐标/ROI 正则(宽松)
PATTERNS = [
re.compile(r"\(\s*\d{1,4}\s*,\s*\d{1,4}\s*\)"), # (123, 456)
re.compile(r"\[\s*\d{1,4}\s*,\s*\d{1,4}\s*\]"), # [123, 456]
re.compile(
r"\(\s*\d{1,4}\s*,\s*\d{1,4}\s*,\s*\d{1,4}\s*,\s*\d{1,4}\s*\)"
), # (x1,y1,x2,y2)
re.compile(
r"\[\s*\d{1,4}\s*,\s*\d{1,4}\s*,\s*\d{1,4}\s*,\s*\d{1,4}\s*\]"
), # [x1,y1,x2,y2]
]
# 额外关键词匹配(ROI 变量名等)
KEYWORD_PATTERNS = [
re.compile(p, re.IGNORECASE)
for p in [
r"coords?",
r"roi",
r"rect",
r"left_up",
r"right_down",
r"crop",
r"cut_pic",
r"x1",
r"y1",
r"fudai_x",
]
]
def scan_file(path: Path):
results = []
try:
text = path.read_text(encoding="utf-8")
except Exception:
return results
lines = text.splitlines()
for i, line in enumerate(lines, start=1):
for pat in PATTERNS:
for m in pat.finditer(line):
# capture some context
ctx = line.strip()
results.append((str(path.relative_to(ROOT)), i, m.group(0), ctx))
# 额外按关键词收集可能的 ROI 定义行
if any(k.search(line) for k in KEYWORD_PATTERNS):
# avoid duplicates: only add if it contains a digit
if re.search(r"\d{2,4}", line):
results.append(
(str(path.relative_to(ROOT)), i, "[keyword_match]", line.strip())
)
return results
def main():
rows = []
for f in ROOT.rglob("*"):
if f.is_dir():
if f.name in IGNORE_DIRS:
continue
else:
continue
if f.suffix in {".py", ".pyx", ".txt", ".md", ".json", ".yaml", ".yml", ".cfg"}:
if any(part in IGNORE_DIRS for part in f.parts):
continue
hits = scan_file(f)
rows.extend(hits)
OUT_CSV.parent.mkdir(parents=True, exist_ok=True)
with OUT_CSV.open("w", encoding="utf-8", newline="") as csvf:
writer = csv.writer(csvf)
writer.writerow(["file", "line", "match", "context"])
for r in rows:
writer.writerow(r)
print(f"扫描完成,发现 {len(rows)} 条疑似坐标/ROI 行,输出到: {OUT_CSV}")
if __name__ == "__main__":
main()