python - 基于用户字符串循环文件中的标记

Question

我有以下用于检查版权标记的代码。我目前只检查 userstring1。现在我想检查多个用户字符串。修改以下代码的最佳方法是什么：

• 检查所有正在检查的文件是否有所有用户字符串

• 打印匹配任何字符串的每个文件的文件名

  import os
  import sys
  import fnmatch
  
  userstring1="Copyright (c) 2012 Company, Inc\nAll Rights Reserved.\nCompany Confidential and Proprietary."
  userstring2="Copyright (c) 2011-2013 Company, Inc\nAll Rights Reserved.\nCompany Confidential and Proprietary."
  #print len(sys.argv)
  #print sys.argv[1]
  if len(sys.argv) < 2:
      sys.exit('Usage: check_copyright.py <build directory>')
  '''
  for r,d,f in os.walk(sys.argv[1]):
      for files in f:
          userlines = userstring.split('\n') # Separate the string into lines
          with open(os.path.join(r, files), "r") as file:
  '''
  for path,dirs,files in os.walk(sys.argv[1]):
      for fname in files:
          userlines = userstring1.split('\n') # Separate the string into lines 
          # Test the filename for particular pattern matches.
          for pat in ['*.cpp','*.c','*.h']:
              if fnmatch.fnmatch(fname,pat):
                  fullname = os.path.join(path,fname)
                  with open(fullname) as file:
                      match = 0
                      for line in file:
                          if userlines[match] in line: # Check if the line at index `m` is in the user lines
                              match += 1 # Next time check the following line
                          elif match > 0: # If there was no match, reset the counter
                              match = 0
                          if match >= len(userlines): # If 3 consecutive lines match, then you found a match
                              break
                      if match == len(userlines): # print if you found a match
                          print "MATCH"
                          print match
                          print "LENGTH userlines"
                          print len(userlines)
                      print fullname
  

Answer 1

我还没有测试过，但我所做的只是把你的代码放在一个函数中，然后循环每个用户名。

import os
import sys
import fnmatch


if len(sys.argv) < 2:
    sys.exit('Usage: check_copyright.py <build directory>')

userstring1="Copyright (c) 2012 Company, Inc\nAll Rights Reserved.\nCompany Confidential and Proprietary."
userstring2="Copyright (c) 2011-2013 Company, Inc\nAll Rights Reserved.\nCompany Confidential and Proprietary."


for path,dirs,files in os.walk(sys.argv[1]):
    for fname in files:
        for userstring in [userstring1, userstring2]:
            test(userstring, path, dirs, fname)

def test(userstring, path, dirs, fname):
    userlines = userstring.split('\n')
    for pat in ['*.cpp','*.c','*.h']:
        if fnmatch.fnmatch(fname,pat):
            fullname = os.path.join(path,fname)
            with open(fullname) as file:
                match = 0
                for line in file:
                    if userlines[match] in line: # Check if the line at index `m` is in the user lines
                        match += 1 # Next time check the following line
                    elif match > 0: # If there was no match, reset the counter
                        match = 0
                    if match >= len(userlines): # If 3 consecutive lines match, then you found a match
                        break
                if match == len(userlines): # print if you found a match
                    print "MATCH"
                    print match
                    print "LENGTH userlines"
                    print len(userlines)
                    print fullname