python实现的用于搜索文件并进行内容替换的类实例

yipeiwu_com6年前Python基础

本文实例讲述了python实现的用于搜索文件并进行内容替换的类。分享给大家供大家参考。具体实现方法如下:

#!/usr/bin/python -O
# coding: UTF-8
"""
-replace string in files (recursive)
-display the difference.
v0.2
 - search_string can be a re.compile() object -> use re.sub for replacing
v0.1
 - initial version
  Useable by a small "client" script, e.g.:
-------------------------------------------------------------------------------
#!/usr/bin/python -O
# coding: UTF-8
import sys, re
#sys.path.insert(0,"/path/to/git/repro/") # Please change path
from replace_in_files import SearchAndReplace
SearchAndReplace(
  search_path = "/to/the/files/",
  # e.g.: simple string replace:
  search_string = 'the old string',
  replace_string = 'the new string',
  # e.g.: Regular expression replacing (used re.sub)
  #search_string = re.compile('{% url (.*?) %}'),
  #replace_string = "{% url '\g<1>' %}",
  search_only = True, # Display only the difference
  #search_only = False, # write the new content
  file_filter=("*.py",), # fnmatch-Filter
)
-------------------------------------------------------------------------------
:copyleft: 2009-2011 by Jens Diemer
"""
__author__ = "Jens Diemer"
__license__ = """GNU General Public License v3 or above -
 http://www.opensource.org/licenses/gpl-license.php"""
__url__ = "http://www.jensdiemer.de"
__version__ = "0.2"
import os, re, time, fnmatch, difflib
# FIXME: see http://stackoverflow.com/questions/4730121/cant-get-an-objects-class-name-in-python
RE_TYPE = type(re.compile(""))
class SearchAndReplace(object):
  def __init__(self, search_path, search_string, replace_string,
                    search_only=True, file_filter=("*.*",)):
    self.search_path = search_path
    self.search_string = search_string
    self.replace_string = replace_string
    self.search_only = search_only
    self.file_filter = file_filter
    assert isinstance(self.file_filter, (list, tuple))
    # FIXME: see http://stackoverflow.com/questions/4730121/cant-get-an-objects-class-name-in-python
    self.is_re = isinstance(self.search_string, RE_TYPE)
    print "Search '%s' in [%s]..." % (
      self.search_string, self.search_path
    )
    print "_" * 80
    time_begin = time.time()
    file_count = self.walk()
    print "_" * 80
    print "%s files searched in %0.2fsec." % (
      file_count, (time.time() - time_begin)
    )
  def walk(self):
    file_count = 0
    for root, dirlist, filelist in os.walk(self.search_path):
      if ".svn" in root:
        continue
      for filename in filelist:
        for file_filter in self.file_filter:
          if fnmatch.fnmatch(filename, file_filter):
            self.search_file(os.path.join(root, filename))
            file_count += 1
    return file_count
  def search_file(self, filepath):
    f = file(filepath, "r")
    old_content = f.read()
    f.close()
    if self.is_re or self.search_string in old_content:
      new_content = self.replace_content(old_content, filepath)
      if self.is_re and new_content == old_content:
        return
      print filepath
      self.display_plaintext_diff(old_content, new_content)
  def replace_content(self, old_content, filepath):
    if self.is_re:
      new_content = self.search_string.sub(self.replace_string, old_content)
      if new_content == old_content:
        return old_content
    else:
      new_content = old_content.replace(
        self.search_string, self.replace_string
      )
    if self.search_only != False:
      return new_content
    print "Write new content into %s..." % filepath,
    try:
      f = file(filepath, "w")
      f.write(new_content)
      f.close()
    except IOError, msg:
      print "Error:", msg
    else:
      print "OK"
    print
    return new_content
  def display_plaintext_diff(self, content1, content2):
    """
    Display a diff.
    """
    content1 = content1.splitlines()
    content2 = content2.splitlines()
    diff = difflib.Differ().compare(content1, content2)
    def is_diff_line(line):
      for char in ("-", "+", "?"):
        if line.startswith(char):
          return True
      return False
    print "line | text\n-------------------------------------------"
    old_line = ""
    in_block = False
    old_lineno = lineno = 0
    for line in diff:
      if line.startswith(" ") or line.startswith("+"):
        lineno += 1
      if old_lineno == lineno:
        display_line = "%4s | %s" % ("", line.rstrip())
      else:
        display_line = "%4s | %s" % (lineno, line.rstrip())
      if is_diff_line(line):
        if not in_block:
          print "..."
          # Display previous line
          print old_line
          in_block = True
        print display_line
      else:
        if in_block:
          # Display the next line aber a diff-block
          print display_line
        in_block = False
      old_line = display_line
      old_lineno = lineno
    print "..."
if __name__ == "__main__":
  SearchAndReplace(
    search_path=".",
    # e.g.: simple string replace:
    search_string='the old string',
    replace_string='the new string',
    # e.g.: Regular expression replacing (used re.sub)
    #search_string  = re.compile('{% url (.*?) %}'),
    #replace_string = "{% url '\g<1>' %}",
    search_only=True, # Display only the difference
#    search_only   = False, # write the new content
    file_filter=("*.py",), # fnmatch-Filter
  )

希望本文所述对大家的Python程序设计有所帮助。

相关文章

python networkx 根据图的权重画图实现

python networkx 根据图的权重画图实现

首先输入边和边的权重,随后画出节点位置,根据权重大小划分实边和虚边 #coding:utf-8 #!/usr/bin/env python """ An example using...

Python中Continue语句的用法的举例详解

Python中Continue语句的用法的举例详解

 Python continue语句返回while循环的开始。Continue语句拒绝在该循环的当前迭代中的其余语句执行并移动控制返回到循环的顶部(开始位置)。 continu...

Python 把序列转换为元组的函数tuple方法

tuple函数功能和list功能很相似,以序列为参数并把它转换为元组 >>> tuple([1,2,3]) (1, 2, 3) >>> tuple...

python Pandas库基础分析之时间序列的处理详解

前言 在使用Python进行数据分析时,经常会遇到时间日期格式处理和转换,特别是分析和挖掘与时间相关的数据,比如量化交易就是从历史数据中寻找股价的变化规律。Python中自带的处理时间的...

Python 如何提高元组的可读性

这篇文章主要介绍了Python 如何提高元组的可读性,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友可以参考下 假设学生系统中数据为固定格式:(名...