Echo/fcb_photo_review
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

统一引号格式，优化架构排布

Browse Source
This commit is contained in:
liuyebo
2024-09-26 15:16:57 +08:00
parent ff9d612e67
commit c5a03ad16f
22 changed files with 143 additions and 302 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
util/common_util.py
View File

@@ -62,9 +62,9 @@ def delete_temp_file(temp_files):
for file in temp_files:
try:
os.remove(file)
logging.info(f"临时文件 {file} 已删除")
logging.info(f'临时文件 {file} 已删除')
except Exception as e:
logging.warning(f"删除临时文件 {file} 时出错: {e}")
logging.warning(f'删除临时文件 {file} 时出错: {e}')
def zoom_rectangle(rectangle, ratio):
@@ -83,40 +83,40 @@ def zoom_rectangle(rectangle, ratio):
def chinese_to_money_unit(chinese):
if chinese in ["拾", "十"]:
if chinese in ['拾', '十']:
return 10, False
elif chinese in ["佰", "百"]:
elif chinese in ['佰', '百']:
return 100, False
elif chinese in ["仟", "千"]:
elif chinese in ['仟', '千']:
return 1000, False
elif chinese == "万":
elif chinese == '万':
return 10000, True
elif chinese == "亿":
elif chinese == '亿':
return 100000000, True
else:
return None, False
def chinese_char_to_number(chinese):
if chinese == "零":
if chinese == '零':
return 0
elif chinese in ["一", "壹"]:
elif chinese in ['一', '壹']:
return 1
elif chinese in ["二", "贰"]:
elif chinese in ['二', '贰']:
return 2
elif chinese in ["三", "叁"]:
elif chinese in ['三', '叁']:
return 3
elif chinese in ["四", "肆"]:
elif chinese in ['四', '肆']:
return 4
elif chinese in ["五", "伍"]:
elif chinese in ['五', '伍']:
return 5
elif chinese in ["六", "陆"]:
elif chinese in ['六', '陆']:
return 6
elif chinese in ["七", "柒"]:
elif chinese in ['七', '柒']:
return 7
elif chinese in ["八", "捌"]:
elif chinese in ['八', '捌']:
return 8
elif chinese in ["九", "玖"]:
elif chinese in ['九', '玖']:
return 9
else:
return -1
@@ -137,12 +137,12 @@ def chinese_to_number(chinese):
section += number * (unit[0] / 10)
unit = [None, False]
elif number > 0:
raise ValueError(f"{chinese} has bad number '{chinese[i - 1]}{c}' at: {i}")
raise ValueError(f"'{chinese} has bad number '{chinese[i - 1]}{c}' at: {i}'")
number = num
else:
unit = chinese_to_money_unit(c)
if unit[0] is None:
raise ValueError(f"{chinese} has unknown unit '{c}' at: {i}")
raise ValueError(f"'{chinese} has unknown unit '{c}' at: {i}'")
if unit[1]:
section = (section + number) * unit[0]
result += section
@@ -163,14 +163,14 @@ def chinese_to_number(chinese):
def chinese_money_to_number(chinese_money_amount):
if string_util.blank(chinese_money_amount):
return None
yi = chinese_money_amount.find("元")
yi = chinese_money_amount.find('元')
if yi == -1:
yi = chinese_money_amount.find("圆")
ji = chinese_money_amount.find("角")
fi = chinese_money_amount.find("分")
yi = chinese_money_amount.find('圆')
ji = chinese_money_amount.find('角')
fi = chinese_money_amount.find('分')
if yi == -1 and ji == -1 and fi == -1:
raise ValueError(f"无法解析: {chinese_money_amount}")
raise ValueError(f'无法解析: {chinese_money_amount}')
y_str = None
if yi > 0:

84
util/data_util.py
View File

@@ -8,20 +8,20 @@ from util import common_util
# 处理金额类数据
def handle_decimal(string):
if not string:
return ""
return ''
string = re.sub(r'[^0-9.]', '', string)
if not string:
return ""
if "." not in string:
return ''
if '.' not in string:
if len(string) > 2:
result = string[:-2] + "." + string[-2:]
result = string[:-2] + '.' + string[-2:]
else:
result = string
else:
front, back = string.rsplit('.', 1)
front = front.replace(".", "")
front = front.replace('.', '')
if back:
back = "." + back[:2]
back = '.' + back[:2]
result = front + back
return result[:16]
@@ -32,7 +32,7 @@ def parse_money(capital_num, num):
money = common_util.chinese_money_to_number(capital_num)
return capital_num, money
except Exception as e:
logging.warning("大写金额解析失败", exc_info=e)
logging.warning('大写金额解析失败', exc_info=e)
return num, handle_decimal(num)
@@ -40,17 +40,17 @@ def parse_money(capital_num, num):
# 处理日期类数据
def handle_date(string):
if not string:
return ""
return ''
string = string.replace("年", "-").replace("月", "-").replace("日", "").replace("/", "-").replace(".", "-")
string = string.replace('年', '-').replace('月', '-').replace('日', '').replace('/', '-').replace('.', '-')
string = re.sub(r'[^0-9-]', '', string)
string = string.strip("-")
if "-" in string:
dash_count = string.count("-")
string = string.strip('-')
if '-' in string:
dash_count = string.count('-')
if dash_count > 2:
third_dash_index = string.find("-", string.find("-", string.find("-") + 1) + 1)
third_dash_index = string.find('-', string.find('-', string.find('-') + 1) + 1)
string = string[:third_dash_index]
day = string[string.rindex("-") + 1:]
day = string[string.rindex('-') + 1:]
if len(day) > 2:
string = string[:2 - len(day)]
else:
@@ -58,7 +58,7 @@ def handle_date(string):
string = string[:8]
if len(string) < 6:
return ""
return ''
# 定义可能的日期格式
formats = [
@@ -78,23 +78,23 @@ def handle_date(string):
date = datetime.strptime(string, fmt)
# 限定日期的年份范围
if 2000 < date.year < 2100:
return date.strftime("%Y-%m-%d")
return date.strftime('%Y-%m-%d')
continue
except ValueError:
continue
return ""
return ''
def handle_hospital(string):
if not string:
return ""
return ''
return string[:255]
def handle_department(string):
if not string:
return ""
return ''
return string[:255]
@@ -103,12 +103,12 @@ def parse_department(string):
if not string:
return result
string = string.replace(")", "").replace("）", "").replace("(", " ").replace("（", " ") # 去除括号
string = string.replace(')', '').replace('）', '').replace('(', ' ').replace('（', ' ') # 去除括号
string = re.sub(r'[^⺀-鿿 ]', '', string) # 去除非汉字字符，除了空格
string = re.sub(r'[一二三四五六七八九十]', '', string) # 去除中文数字
string = string.replace("病区", "").replace("病", "") # 去除常见的无意义词
string = string.replace("科", " ") # 分离科室
departments = string.strip().split(" ")
string = string.replace('病区', '').replace('病', '') # 去除常见的无意义词
string = string.replace('科', ' ') # 分离科室
departments = string.strip().split(' ')
for department in departments:
if department:
result.append(department)
@@ -118,33 +118,33 @@ def parse_department(string):
# 处理姓名类数据
def handle_name(string):
if not string:
return ""
return ''
return re.sub(r'[^⺀-鿿·]', '', string)[:30]
# 处理医保类型数据
def handle_insurance_type(string):
if not string:
return ""
worker_insurance_keys = ["社保", "城保", "职", "退休"]
villager_insurance_keys = ["农保", "居民"]
migrant_worker_insurance_keys = ["农民工"]
no_insurance_keys = ["自费", "全费"]
return ''
worker_insurance_keys = ['社保', '城保', '职', '退休']
villager_insurance_keys = ['农保', '居民']
migrant_worker_insurance_keys = ['农民工']
no_insurance_keys = ['自费', '全费']
if any(key in string for key in worker_insurance_keys):
return "职工医保"
return '职工医保'
if any(key in string for key in villager_insurance_keys):
return "居民医保"
return '居民医保'
if any(key in string for key in migrant_worker_insurance_keys):
return "农民工医保"
return '农民工医保'
if any(key in string for key in no_insurance_keys):
return "无医保"
return "其他"
return '无医保'
return '其他'
# 处理原始数据
def handle_original_data(string):
if not string:
return ""
return ''
# 防止过长存入数据库失败
return string[:255]
@@ -152,7 +152,7 @@ def handle_original_data(string):
# 处理id类数据
def handle_id(string):
if not string:
return ""
return ''
# 防止过长存入数据库失败
return string[:50]
@@ -160,8 +160,8 @@ def handle_id(string):
# 处理年龄类数据
def handle_age(string):
if not string:
return ""
string = string.split("岁")[0]
return ''
string = string.split('岁')[0]
num = re.sub(r'\D', '', string)
return num[-3:]
@@ -173,8 +173,8 @@ def parse_hospital(string):
return result
string = common_util.traditional_to_simple_chinese(string)
string_without_brackets = string.replace(")", "").replace("）", "").replace("(", " ").replace("（", " ")
string_without_company = string_without_brackets.replace("有限公司", "")
split_hospitals = string_without_company.replace("医院", "医院 ")
result += split_hospitals.strip().split(" ")
string_without_brackets = string.replace(')', '').replace('）', '').replace('(', ' ').replace('（', ' ')
string_without_company = string_without_brackets.replace('有限公司', '')
split_hospitals = string_without_company.replace('医院', '医院 ')
result += split_hospitals.strip().split(' ')
return result

2
util/html_util.py
View File

@@ -15,7 +15,7 @@ def get_jsczt_id_base(url):
if response.status_code != 200:
raise Exception(f'请求江苏省财政票据失败！状态码: {response.status_code}')
soup = BeautifulSoup(response.text, 'html.parser')
hidden_input = soup.find('input', {'name': "idBase"})
hidden_input = soup.find('input', {'name': 'idBase'})
if hidden_input:
# 获取隐藏字段的值
value = hidden_input.get('value')

28
util/image_util.py
View File

@@ -13,14 +13,14 @@ from log import PROJECT_ROOT
@retry(stop=stop_after_attempt(3), wait=wait_random(1, 3), reraise=True,
after=lambda x: logging.warning("获取图片失败！"))
after=lambda x: logging.warning('获取图片失败！'))
def read(image_path):
"""
从网络或本地读取图片
:param image_path: 网络或本地路径
:return: NumPy数组形式的图片
"""
if image_path.startswith("http"):
if image_path.startswith('http'):
# 发送HTTP请求并获取图像数据
resp = urllib.request.urlopen(image_path, timeout=60)
# 将数据读取为字节流
@@ -76,35 +76,35 @@ def split(image, ratio=1.414, overlap=0.05, x_compensation=3):
for i in range(math.ceil(height / step)):
offset = round(step * i)
cropped_img = capture(image, [0, offset, width, offset + new_img_height])
split_result.append({"img": cropped_img, "x_offset": 0, "y_offset": offset})
split_result.append({'img': cropped_img, 'x_offset': 0, 'y_offset': offset})
elif wh_ratio > ratio: # 横向过长
new_img_width = height * ratio
step = height * (ratio - overlap * x_compensation) # 一般文字是横向的，所以横向截取时增大重叠部分
for i in range(math.ceil(width / step)):
offset = round(step * i)
cropped_img = capture(image, [offset, 0, offset + new_img_width, width])
split_result.append({"img": cropped_img, "x_offset": offset, "y_offset": 0})
split_result.append({'img': cropped_img, 'x_offset': offset, 'y_offset': 0})
else:
split_result.append({"img": image, "x_offset": 0, "y_offset": 0})
split_result.append({'img': image, 'x_offset': 0, 'y_offset': 0})
return split_result
def parse_rotation_angles(image):
"""
判断图片旋转角度，逆时针旋转该角度后为正。可能值["0", "90", "180", "270"]
判断图片旋转角度，逆时针旋转该角度后为正。可能值['0', '90', '180', '270']
:param image: 图片NumPy数组或文件路径
:return: 最有可能的两个角度
"""
angles = ['0', '90']
model = PaddleClas(model_name="text_image_orientation")
model = PaddleClas(model_name='text_image_orientation')
clas_result = model.predict(input_data=image)
try:
clas_result = next(clas_result)[0]
if clas_result["scores"][0] < 0.5:
if clas_result['scores'][0] < 0.5:
return angles
angles = clas_result["label_names"]
angles = clas_result['label_names']
except Exception as e:
logging.error("获取图片旋转角度失败", exc_info=e)
logging.error('获取图片旋转角度失败', exc_info=e)
return angles
@@ -201,25 +201,25 @@ def expand_to_a4_size(image):
if hw_ratio >= 1.42:
exp_w = int(height / 1.414 - width)
x_offset = int(exp_w / 2)
exp_img = numpy.zeros((height, x_offset, 3), dtype="uint8")
exp_img = numpy.zeros((height, x_offset, 3), dtype='uint8')
exp_img.fill(255)
image = numpy.hstack([exp_img, image, exp_img])
elif 1 <= hw_ratio <= 1.40:
exp_h = int(width * 1.414 - height)
y_offset = int(exp_h / 2)
exp_img = numpy.zeros((y_offset, width, 3), dtype="uint8")
exp_img = numpy.zeros((y_offset, width, 3), dtype='uint8')
exp_img.fill(255)
image = numpy.vstack([exp_img, image, exp_img])
elif 0.72 <= hw_ratio < 1:
exp_w = int(height * 1.414 - width)
x_offset = int(exp_w / 2)
exp_img = numpy.zeros((height, x_offset, 3), dtype="uint8")
exp_img = numpy.zeros((height, x_offset, 3), dtype='uint8')
exp_img.fill(255)
image = numpy.hstack([exp_img, image, exp_img])
elif hw_ratio <= 0.7:
exp_h = int(width / 1.414 - height)
y_offset = int(exp_h / 2)
exp_img = numpy.zeros((y_offset, width, 3), dtype="uint8")
exp_img = numpy.zeros((y_offset, width, 3), dtype='uint8')
exp_img.fill(255)
image = numpy.vstack([exp_img, image, exp_img])
return image, x_offset, y_offset