PYTHON文本处理指南之日志LOG解析

处理特定字段的内容，并指指定条件输出。

注意代码中用一个方法列表，并且将方法参数延后传递。

GOOGLE作过PYTHON代码的水平，就是不一样呀。

希望能学到这种通用的技巧。

只是，英文PDF看起来有难度，并且印刷代码还有错误。

有识之士能出个中文版么？现在只好硬头皮看下去。

#!/usr/bin/python
import sys
from optparse import OptionParser

class LogProcessor(object):
    '''
    Process a combined log format.

    This processor handles log files in a combined format,
    objects that act on the results are passed in to
    the init method as a series of methods.
    '''
    def __init__(self, call_chain=None):
        """
        Setup parser
        Save the call chain. Each time we process a log ,
        we'll run the list of callbacks with the processed
        log results.
        """
        if call_chain is None:
            call_chain = []
        self._call_chain = call_chain
    def split(self, line):
            """
            Split a log file.
            Initially,we just want size and requested file name . so
            we'll split on spaces and pull the data out.
            """
            parts = line.split()

            return {
                'size': 0 if parts[9] == '-' else int(parts[9]),
                'file_requested': parts[6]
            }
    def parse(self, handle):
            """
            Parses the log file.
            Returns a dictionary composed of log entry values
            for easy data summation
            """
            for line in handle:
                fields = self.split(line)
                for func in self._call_chain:
                   func(fields)

class MaxSizeHandler(object):
    """
    Check a file's size.
    """
    def __init__(self, size):
        self.size = size
    def process(self, fields):
        """
        Looks at each line individually.
        Looks at each parsed log line individually and
        performs a size calculation. If it's bigger than
        our self.size, we just print a warning.
        """
        if fields['size'] > self.size:
            #print ('Warning: %s exceeds $d bytes (%s) !' % (fields['file_requested'], str(self.size), fields['size']))
            print ('Warning: {0} exceeds {1} bytes {2} !'.format (fields['file_requested'], str(self.size), fields['size']))
if __name__ == '__main__':
    parser = OptionParser()
    parser.add_option('-s', '--size', dest = "size",
                      help = "Maximum File Size Allowed",
                      default = 0, type = "int")
    opts,args = parser.parse_args()
    call_chain = []

    size_check = MaxSizeHandler(opts.size)
    call_chain.append(size_check.process)
    processor = LogProcessor(call_chain)
    processor.parse(sys.stdin)