import os
import re
#检查xml文件和img文件是否匹配
img_path=r"D:\dataset\VOCdevkit\VOC2007\JPEGImages"
xml_path=r"D:\dataset\VOCdevkit\VOC2007\Annotations"
img=os.listdir(img_path)
print(len(img))
xml=os.listdir(xml_path)
if len(img)!=len(xml):
    print("img xml数量不一致")
else:
    print("img xml数量一致")
# for i in img:
#     new_xml=re.findall('(^IP\d{9})',i)
#     print(new_xml[0])
#     print(len(xml))
new_img=[(re.findall('(.*?).jpg',i))[0] for i in img]
new_xml=[(re.findall('(.*?).xml',i))[0] for i in xml]
if len(img)!=len(new_img):
    print("jpgtup图片数目不一致")
else:
    print("jpgtup图片数目一致")
if len(xml)!=len(new_xml):
    print("xml数目不一致")
else:
    print("xml数目一致")
# print(len(xml))
print(new_img[0:5])
# print(len(img))
print(new_xml[0:5])
xml1=set(new_xml)   #检查xml文件里面是否有重复的
for i in xml1:
    count=0
    for j in new_xml:
        if i==j:
            count+=1
    if count !=1:
        print(i+'is 出现'+str(count)+"次")
for i in new_xml:
    if i  not in new_img:
        print(i+"xml不在img图片中")
    # new_img.remove(i)
for i in new_img:
    if i  not in new_xml:
        print(i+"jpg不在xml文件中")
    # new_img.remove(i)
# xml=re.findall('(^IP\d{9})',xml[0])
print("fin")