Files
douyi_guaji_main/test_digit_ocr.py
T
Your Name 499002d3b1 fix: Clean up blank lines and enhance readability across multiple files
- Removed excessive blank lines from various markdown and Python files to improve readability and maintainability.
- Ensured consistent formatting across documentation and code files, enhancing overall project clarity.
- Updated logging mechanisms for better consistency and debugging support.
2025-12-26 21:59:54 +08:00

284 lines
10 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
测试数字OCR模块
使用debug_capture中的图片测试analyse_pic_digits函数
"""
import os
import sys
from pathlib import Path
# 添加项目根目录到路径
project_root = Path(__file__).parent
sys.path.insert(0, str(project_root))
from Underlying_Operations import underlying_operations
from douyin_utils import extract_prize_value_yuan
def test_digit_ocr():
"""测试数字OCR功能"""
print("=" * 60)
print("数字OCR模块测试")
print("=" * 60)
# 初始化OCR操作类
print("\n正在初始化OCR引擎...")
try:
ops = underlying_operations()
print(f"OCR引擎类型: {ops.ocr_type}")
print("OCR初始化成功!\n")
except Exception as e:
print(f"OCR初始化失败: {e}")
return False
# 测试图片路径 - 优先使用pic/ocr/fudai目录下的图片(这些是实际使用的图片)
fudai_dir = project_root / "pic" / "ocr" / "fudai"
debug_dir = project_root / "pic" / "debug_captures" / "2025-12-26"
# 查找测试图片
test_images = {
"福袋价值": None,
"福袋倒计时_分钟": None,
"福袋倒计时_秒": None,
}
print("正在查找测试图片...")
# 第一轮:优先使用pic/ocr/fudai目录下的图片(这些是实际使用的图片)
if fudai_dir.exists():
for file in fudai_dir.glob("*.png"):
filename = file.name
# 排除success图片,使用原始图片
if "success" not in filename:
if "福袋价值" in filename and "倒计时" not in filename and test_images["福袋价值"] is None:
test_images["福袋价值"] = file
elif "福袋倒计时_分钟" in filename and test_images["福袋倒计时_分钟"] is None:
test_images["福袋倒计时_分钟"] = file
elif "福袋倒计时_秒" in filename and test_images["福袋倒计时_秒"] is None:
test_images["福袋倒计时_秒"] = file
# 第二轮:如果没找到,使用debug_capture中的cut_pic图片
if debug_dir.exists():
for name in test_images.keys():
if test_images[name] is None:
for file in debug_dir.glob("*.png"):
filename = file.name
if "cut_pic" in filename and "before_ocr" in filename:
if name in filename:
test_images[name] = file
break
# 显示找到的图片
print("\n找到的测试图片:")
for name, path in test_images.items():
if path:
print(f" [OK] {name}: {path.name}")
else:
print(f" [X] {name}: 未找到")
# 测试数字OCR
print("\n" + "=" * 60)
print("开始测试数字OCR识别")
print("=" * 60)
results = {}
# 测试福袋价值
if test_images["福袋价值"]:
print(f"\n【测试1】福袋价值识别")
print(f"图片: {test_images['福袋价值'].name}")
try:
# 使用analyse_pic_digits识别
result = ops.analyse_pic_digits(
"test_福袋价值",
change_color=1,
pic_path=str(test_images["福袋价值"])
)
print(f"识别结果(数字OCR): '{result}'")
# 提取价值
value = extract_prize_value_yuan(result)
print(f"提取的价值: {value} 元")
results["福袋价值"] = {
"result": result,
"value": value,
"success": bool(result)
}
except Exception as e:
print(f"识别失败: {e}")
import traceback
traceback.print_exc()
results["福袋价值"] = {"error": str(e)}
# 测试倒计时分钟
if test_images["福袋倒计时_分钟"]:
print(f"\n【测试2】福袋倒计时分钟识别")
print(f"图片: {test_images['福袋倒计时_分钟'].name}")
try:
result = ops.analyse_pic_digits(
"test_福袋倒计时_分钟",
change_color=1,
pic_path=str(test_images["福袋倒计时_分钟"])
)
print(f"识别结果(数字OCR): '{result}'")
results["福袋倒计时_分钟"] = {
"result": result,
"success": bool(result)
}
except Exception as e:
print(f"识别失败: {e}")
import traceback
traceback.print_exc()
results["福袋倒计时_分钟"] = {"error": str(e)}
# 测试倒计时秒
if test_images["福袋倒计时_秒"]:
print(f"\n【测试3】福袋倒计时秒识别")
print(f"图片: {test_images['福袋倒计时_秒'].name}")
try:
result = ops.analyse_pic_digits(
"test_福袋倒计时_秒",
change_color=1,
pic_path=str(test_images["福袋倒计时_秒"])
)
print(f"识别结果(数字OCR): '{result}'")
results["福袋倒计时_秒"] = {
"result": result,
"success": bool(result)
}
except Exception as e:
print(f"识别失败: {e}")
import traceback
traceback.print_exc()
results["福袋倒计时_秒"] = {"error": str(e)}
# 对比测试:使用原来的analyse_pic_word
print("\n" + "=" * 60)
print("对比测试:使用原来的analyse_pic_word")
print("=" * 60)
comparison_results = {}
if test_images["福袋价值"]:
print(f"\n【对比测试1】福袋价值(使用analyse_pic_word)")
try:
result = ops.analyse_pic_word(
"test_福袋价值",
change_color=0,
pic_path=str(test_images["福袋价值"])
)
print(f"识别结果(完整OCR): '{result}'")
value = extract_prize_value_yuan(result)
print(f"提取的价值: {value} 元")
comparison_results["福袋价值"] = {"result": result, "value": value}
except Exception as e:
print(f"识别失败: {e}")
comparison_results["福袋价值"] = {"error": str(e)}
if test_images["福袋倒计时_分钟"]:
print(f"\n【对比测试2】福袋倒计时分钟(使用analyse_pic_word)")
try:
result = ops.analyse_pic_word(
"test_福袋倒计时_分钟",
change_color=0,
pic_path=str(test_images["福袋倒计时_分钟"])
)
print(f"识别结果(完整OCR): '{result}'")
comparison_results["福袋倒计时_分钟"] = {"result": result}
except Exception as e:
print(f"识别失败: {e}")
comparison_results["福袋倒计时_分钟"] = {"error": str(e)}
if test_images["福袋倒计时_秒"]:
print(f"\n【对比测试3】福袋倒计时秒(使用analyse_pic_word)")
try:
result = ops.analyse_pic_word(
"test_福袋倒计时_秒",
change_color=0,
pic_path=str(test_images["福袋倒计时_秒"])
)
print(f"识别结果(完整OCR): '{result}'")
comparison_results["福袋倒计时_秒"] = {"result": result}
except Exception as e:
print(f"识别失败: {e}")
comparison_results["福袋倒计时_秒"] = {"error": str(e)}
# 总结
print("\n" + "=" * 60)
print("测试总结")
print("=" * 60)
print("\n数字OCR结果:")
for name, result in results.items():
if "error" in result:
print(f" {name}: [ERROR] 错误 - {result['error']}")
elif result.get("success"):
print(f" {name}: [OK] 成功 - '{result.get('result', '')}'")
else:
print(f" {name}: [WARN] 未识别到数字")
print("\n完整OCR对比结果:")
for name, result in comparison_results.items():
if "error" in result:
print(f" {name}: [ERROR] 错误 - {result['error']}")
else:
print(f" {name}: '{result.get('result', '')}'")
# 检查是否有问题
print("\n" + "=" * 60)
print("问题检查")
print("=" * 60)
issues = []
# 检查数字OCR是否正常工作
for name, result in results.items():
if "error" in result:
issues.append(f"{name}: 数字OCR函数报错 - {result['error']}")
elif not result.get("success"):
issues.append(f"{name}: 数字OCR未识别到任何数字")
# 检查对比结果
for name in results.keys():
if name in comparison_results:
digit_result = results[name].get("result", "")
full_result = comparison_results[name].get("result", "")
if digit_result and full_result:
# 提取数字进行比较
import re
digit_digits = re.findall(r'\d+', digit_result)
full_digits = re.findall(r'\d+', full_result)
# 对于价值,比较提取的数值(忽略前导零)
if name == "福袋价值":
digit_value = results[name].get("value", 0.0)
full_value = comparison_results[name].get("value", 0.0)
if abs(digit_value - full_value) > 0.01:
issues.append(f"{name}: 数字OCR提取的价值({digit_value})和完整OCR提取的价值({full_value})不一致")
else:
# 对于倒计时,比较数字(忽略前导零)
digit_nums = [int(d) for d in digit_digits]
full_nums = [int(d) for d in full_digits]
if digit_nums != full_nums:
issues.append(f"{name}: 数字OCR({digit_result})和完整OCR({full_result})结果不一致")
if issues:
print("\n[WARN] 发现以下问题:")
for issue in issues:
print(f" - {issue}")
return False
else:
print("\n[OK] 所有测试通过,未发现问题!")
return True
if __name__ == "__main__":
success = test_digit_ocr()
sys.exit(0 if success else 1)