Question

我正在尝试使用Heapq Merge合并一堆填充了排序整数的临时文件并写入输出文件。函数中的生成器返回值。 heapq.merge（）看起来很好。程序构建但没有任何内容写入TestWriteOutput.txt文件。我尝试在打开文件的行之后写入输出文件（outf），但没有任何内容写入。 TestWriteOutput.txt已创建，但为空。

import os
import sys
import array
import tempfile
import heapq

cwd = os.getcwd()
print "Current Directory: %s" % cwd


#generator function to return one integer at a time from the tempfile    
to a list

def numInFile(f): 
    while True:
        #set input buffer to read 8KB
        input_buffer = [int(x) for x in f.read(1024*2).split(',') if 
        x.strip().isdigit()]
        #convert list of string values into integers
        int_buffer = map(int, input_buffer)
        f.seek(0) #reset flag
        if not input_buffer:
            break
        for number in int_buffer: 
            yield number #returns one number at a time and appends to 
                           iterator



with open('age.txt', 'r+') as inf:
    with open('TestWriteOutput.txt', 'w+') as outf:
        outf.write('some test data')
        outf.write('some more data')
        #iterator for heapq merge 
        sorted_list =[]
        while True:
            a = [int(x) for x in inf.read(20000).split(',') if 
                x.strip().isdigit()]
            int_a = map(int, a)
            if not a:
                break
            f = tempfile.TemporaryFile()
            #sort and write to temp file
            outf_array = sorted(int_a)
            #####print outf_array
            f.write(str(outf_array))
            f.seek(0)
            sorted_list.append(numInFile(f))



        write_to_file = array.array('i')

        #heapq merge function merges multiple ordered lists into a 
          single list
        for x in heapq.merge(*sorted_list): 
            out_buffer = 1024*4
            write_to_file.append(x)
            if len(write_to_file) >= out_buffer: 
                write_to_file.tofile(outf)
                del write_to_file[:]
        if write_to_file:
            write_to_file.tofile(outf)

Answer 1

问题是在numInFile函数中，您将在每次迭代中将文件指针重置回文件的开头。这使numInFile成为取之不尽的发电机。

如果我将numInFile更改为：

def numInFile(f): 
    while True:
        #set input buffer to read 8KB
        input_buffer = [int(x) for x in f.read(1024*2).split(',') if 
        x.strip().isdigit()]
        #convert list of string values into integers
        int_buffer = map(int, input_buffer)
        if not input_buffer:
            break
        for number in int_buffer: 
            yield number #returns one number at a time and appends to iterator

并删除对输出文件的测试写入，程序成功完成。

>>> import array
>>> with open('TestWriteOutput.txt') as f:
...     arr = array.array('i')
...     arr.fromfile(f, 64)
... 
>>> arr
array('i', [3, 3, 4, 5, 6, 6, 8, 8, 8, 8, 10, 11, 12, 12, 13, 17, 21, 25, 29, 30, 36, 37, 38, 39, 40, 44, 44, 46, 50, 50, 50, 52, 53, 53, 55, 56, 57, 59, 62, 63, 63, 64, 64, 65, 65, 66, 67, 68, 69, 70, 72, 73, 73, 74, 75, 75, 75, 75, 75, 76, 76, 77, 78, 79])

python heapq merge sort无法写入输出文件

1 个答案: