判断文件是fastq格式_20211207

最新推荐文章于 2024-06-14 09:50:01 发布

lj_learn

最新推荐文章于 2024-06-14 09:50:01 发布

阅读量367

点赞数 9

文章标签： python 数据库开发语言

本文链接：https://blog.csdn.net/m0_50542529/article/details/135083754

版权

import os
import pandas as pd
import getopt
import sys
import Levenshtein
import urllib.request
# def get(path):
file1 = r"File\2021-10\testfq.fastq"
df1 = pd.read_csv(file1, sep='\t',header=None)
print(df1)

list1=[i for i in range(len(df1)) if i % 4==0] #取0，4，8
# print(type(x),x)

list2=map(lambda x:x+1,list1) #都加1，参考https://blog.csdn.net/XianZhe_/article/details/107795700
list2_1=map(lambda x:x+1,list1)

list3=[i+2 for i in list1]

list4=[i+3 for i in list1]

# def is_ascii(s):
#     return all(ord(c) < 128 for c in s)
#
# str1='CC>ICCCBI1C:CDCICHB+ACCCECG'
# is_ascii(str1)
list5=['A','T','C','G']

list6=[]
list7=[]

if len(df1) !=0 and len(df1) % 4==0:
    for i in list1:
        if str(df1.iloc[i,0])[0]=="@":
            # continue
            # print(str(df1.iloc[i, 0])[0])
            if  Levenshtein.ratio(str(df1.iloc[0,0])[0], str(df1.iloc[i,0])[0]) ==1.0 :# https://blog.csdn.net/Guo_Python/article/details/110229037
                continue
            else :
                print("不是fastq，第1行,第5行等的第一个字符不相等")
                exit()
        else:
            print("不是fastq，第一行不是@")
            exit()
    for m in list4:
        if str(df1.iloc[m,0]).isascii() == True:    # 判断是不是ascii码：https://blog.csdn.net/qq_41961087/article/details/107703076；https://blog.csdn.net/jacke121/article/details/85016331
            # print("是ascii编码")
            continue
            # print(str(df1.iloc[m, 0])[0])
        else:
            print("不是fastq，不是ascii编码")
            exit()
    for x in list3:
        if str(df1.iloc[x,0])[0]=="+":
            continue
        else:
            print("不是fastq，第三行不是+")
            exit()
    for x in list2:
        for i in range(len(str(df1.iloc[x,0]))):
            if str(df1.iloc[x,0])[i] in list5:
                # print('正确')
                continue
            else:
                print("不是fastq，序列有别的字符")
                exit()
    for l in list2_1:
        list6.append(len(str(df1.iloc[l,0])))
        # print(list6)
            # continue
        # else:
        #     print("不是fastq，序列有别的字符")
        #     exit()
        if len(set(list6))==1:
            # continue
            list7.append(len(str(df1.iloc[l+2,0])))
            if len(set(list7))==1:
                if set(list6)==set(list7):
                    continue
                else :
                    print("不是fastq，第二和第四行长度不等")
                    exit()
            else :
                print("不是fastq，第四行长度不等")
                exit()
        else:
            print("不是fastq，第二行长度不等")
            exit()

    print("是fastq文件")
else:
    print("不是fastq文件，序列残缺，不是4的整数倍")

sequence_number=len(df1)
print('有'+str(int(len(df1)/4))+'条序列')

# print(list6)

arg = getopt.getopt(sys.argv[1:],'-h',['help'])