python搜索文件并进行内容替换的类的实现方法实例

python搜索文件并进行内容替换的类是如何来实现的呢?下面的内容将会通过具体的实例来演示python搜索文件并进行内容替换的类的实现方法及相关技巧:

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:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
#!/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 ("-", "+", "&#63;"):
        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 (.*&#63;) %}'),
    #replace_string = "{% url '\g<1>' %}",
    search_only=True, # Display only the difference
#    search_only   = False, # write the new content
    file_filter=("*.py",), # fnmatch-Filter
  )

python搜索文件并进行内容替换的类就是这样,欢迎大家参考。。。。

Sidebar