Python 3.2 文件 I/O。 根据预设的大小限制生成和拆分文件。 如何？

Question

我正在处理一些生成给定字符集的所有排列的代码。 尽管我的代码在 Python 2.7 中工作，但由于字符串中的许多更改，它不再在 Python 3.x 中工作。 我想适应，因为我是 Python 新手，我希望你能给我一点推动。 =)

我的问题是，当 Python 生成您选择的单词列表时，输出文件大小会相应增加。 我想让你告诉我如何让这个脚本检查预设的文件大小，如果达到，打开一个新文件并继续写入排列。

例子：

numeric_lowercase.000001
numeric_lowercase.000002
numeric_lowercase.000003

请记住，我已经查看了站点上的大多数示例，但它们不适用于 Python 3.2。

到目前为止，这是我的 Python 3.2 工作代码：

import itertools
import subprocess
import os
from string import digits, ascii_lowercase, ascii_uppercase, punctuation

if os.name == 'nt':
    def clear_console():
        subprocess.call("cls", shell=True)
        return
else:
    def clear_console():
        subprocess.call("clear", shell=True)
        return

def generate_phone_numbers(area_code):
    f = open('phones.txt', 'w')
    for i in range(2010000, 9999999):
        f.write(area_code + str(i) + '\n')

def generate_wordlist(lst_chars, min_digit, max_digit, lst_name):
    f = open(lst_name, 'w')
    for curr_length in range(min_digit, max_digit + 1):
        for curr_digit in itertools.product(lst_chars, repeat=curr_length):
            f.write(''.join(curr_digit) + '\n')

print ('')
print ('  wgen - Menu')

choice = 0

while int(choice) not in range(1,6):
    clear_console()
    choice = input('''
  1. Phone numbers for a given area code.
  2. Numbers.
  3. Numbers + Lowercase.
  4. Numbers + Lowercase + Uppercase.
  5. Numbers + Lowercase + Uppercase + Punctuation.

  Enter Option: ''')

print ('')

choice = int(choice)

if choice == 1:
    area_code = input('''
  Please enter Area Code: ''')
    area_code = str(area_code)
    area_code = area_code.strip()
    if len(area_code) == 3:
        print ('')
        print ('  Generating phone numbers for area code ' + area_code + '.')
        print ('  Please wait...')
        generate_phone_numbers(area_code)

if choice == 2:
    min_digit = input('  What is the minimum size of the word? ')
    min_digit = int(min_digit)
    print ('')
    max_digit = input('  What is the maximum size of the word? ')
    max_digit = int(max_digit)
    chars = digits
    lst_name = 'numeric.txt'
    print ('')
    print ('  Generating numbers between ' + str(min_digit) + ' and ' + str(max_digit) + ' digits.')
    print ('  Please wait...')
    generate_wordlist(chars, min_digit, max_digit, lst_name)

if choice == 3:
    min_digit = input('  What is the minimum size of the word? ')
    min_digit = int(min_digit)
    print ('')
    max_digit = input('  What is the maximum size of the word? ')
    max_digit = int(max_digit)
    chars = digits + ascii_lowercase
    lst_name = 'numeric_lowercase.txt'
    print ('')
    print ('  Generating numbers & lowercase between ' + str(min_digit) + ' and ' + str(max_digit) + ' digits.')
    print ('  Please wait...')
    generate_wordlist(chars, min_digit, max_digit, lst_name)

if choice == 4:
    min_digit = input('  What is the minimum size of the word? ')
    min_digit = int(min_digit)
    print ('')
    max_digit = input('  What is the maximum size of the word? ')
    max_digit = int(max_digit)
    chars = digits + ascii_lowercase + ascii_uppercase
    lst_name = 'numeric_lowercase_uppercase.txt'
    print ('')
    print ('  Generating numbers, lowercase & uppercase between ' + str(min_digit) + ' and ' + str(max_digit) + ' digits.')
    print ('  Please wait...')
    generate_wordlist(chars, min_digit, max_digit, lst_name)

if choice == 5:
    min_digit = input('  What is the minimum size of the word? ')
    min_digit = int(min_digit)
    print ('')
    max_digit = input('  What is the maximum size of the word? ')
    max_digit = int(max_digit)
    chars = punctuation
    lst_name = 'numeric_lowercase_uppercase_punctuation.txt'
    print ('')
    print ('  Generating numbers, lowercase, uppercase & punctuation between ' + str(min_digit) + ' and ' + str(max_digit) + ' digits.')
    print ('  Please wait...')
    generate_wordlist(chars, min_digit, max_digit, lst_name)

Answer 1

我认为最好的解决方案是编写一个像文件一样的类，但提供分块功能。 您的程序只是写入此对象，就好像它是一个常规文件一样。

下面的实现不会拆分字符串（如果你调用f.write("this is a test")整个消息保证进入一个文件）并且它只会在超过限制时开始一个新的，所以文件将略大于块大小。 此行为全部在write()方法中，如果需要，可以更改。

class chunkyfile(object):
    def __init__(self, filename, chunksize=1000000, mode="w", encoding=None, 
                 extension="", start=0, digits=6):
        self.filename  = filename
        self.chunksize = chunksize
        self.chunkno   = start
        self.file      = None
        self.mode      = mode
        self.encoding  = encoding
        self.digits    = digits
        self.extension = ("." * bool(extension) * (not extension.startswith(".")) +
                          extension)
        self.softspace = 0       # for use with print

    def _nextfile(self):
        self.file and self.file.close()
        self.file = open(self.filename + str(self.chunkno).rjust(self.digits, "0") + 
                         self.extension, mode=self.mode, encoding=self.encoding)
        self.chunkno += 1

    def write(self, text):
        self.file and self.file.tell() > self.chunksize and self.close()
        self.file or self._nextfile()
        self.file.write(text)

    # convenience method, equivalent to print(... file=f)
    # requires Python 3.x or from __future__ import print in Py2
    def print(*objects, sep=" ", end="\n", flush=False):
        print(*objects, sep=sep, end=end, flush=flush, file=self)

    def writelines(self, lines):
        # do it a line at a time in case we need to split
        for line in lines: self.write(line)

    def flush(self):
        self.file and self.file.flush()

    def close(self):
        self.file = self.file and self.file.close()

    # support "with" statement
    def __enter__(self):
        return self

    def __exit__(self, e, value, tb):
        self.close()

# now use the file
with chunkyfile(r"C:\test", 10, extension="txt", encoding="utf8") as f:
    f.write("FINALLY ROBOTIC BEINGS RULE THE WORLD")
    f.write("The humans are dead")
    f.write("The humans are dead")
    f.write("We used poisonous gasses")
    f.write("And we poisoned their asses")

Answer 2

通过一些预先配置，您可以使用 stdlib 中的日志记录库中内置的 RotatingFileHandler。

import logging
from logging.handlers import RotatingFileHandler

log = logging.getLogger('myprog.stufflogger')
log.propagate = False #ensure that we don't mess with other logging

#configure RotatingFileHandler
handler = RotatingFileHandler('base_file_name.txt', maxBytes=1024*1024*20)
handler.setFormatter(logging.Formatter('%(message)s')
handler.terminator = '' # default is new line

log.addHandler(handler)


# you can now use any of the log methods to add the values

log.info('stuff')