Source Code for Module docs.latex.find_replicate_titles

  1  #! /usr/bin/env python 
  2   
  3  ############################################################################### 
  4  #                                                                             # 
  5  # Copyright (C) 2015 Edward d'Auvergne                                        # 
  6  #                                                                             # 
  7  # This file is part of the program relax (http://www.nmr-relax.com).          # 
  8  #                                                                             # 
  9  # This program is free software: you can redistribute it and/or modify        # 
 10  # it under the terms of the GNU General Public License as published by        # 
 11  # the Free Software Foundation, either version 3 of the License, or           # 
 12  # (at your option) any later version.                                         # 
 13  #                                                                             # 
 14  # This program is distributed in the hope that it will be useful,             # 
 15  # but WITHOUT ANY WARRANTY; without even the implied warranty of              # 
 16  # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the               # 
 17  # GNU General Public License for more details.                                # 
 18  #                                                                             # 
 19  # You should have received a copy of the GNU General Public License           # 
 20  # along with relax; if not, write to the Free Software                        # 
 21  #                                                                             # 
 22  ############################################################################### 
 23   
 24  # Python module imports. 
 25  from os import getcwd, path, walk 
 26  from re import search 
 27  import sys 
 28   
 29   
 30 -class Replicated_titles: 
 31      """Class used to find replicated titles in the LaTeX sources.""" 
 32   
 33 -    def __init__(self): 
 34          """Set up the required data structures.""" 
 35   
 36          # The data structure for holding the unique title names. 
 37          self.titles = [] 
 38   
 39          # The replicate count structure. 
 40          self.replicate = {} 
 41   
 42   
 43 -    def find(self): 
 44          """Find the replicates.""" 
 45   
 46          # Reset the data structures if necessary. 
 47          if len(self.titles): 
 48              self.titles = [] 
 49              self.replicate = {} 
 50   
 51          # Walk through the directories. 
 52          for root, dirs, files in walk(getcwd()): 
 53              # Loop over the files in the current directory. 
 54              for file_name in files: 
 55                  # Skip non-LaTeX files. 
 56                  if not search("tex$", file_name): 
 57                      continue 
 58   
 59                  # Skip files not in 'docs/latex'. 
 60                  if not search(path.join('docs', 'latex'), root): 
 61                      continue 
 62   
 63                  # The full path. 
 64                  file_path = path.join(root, file_name) 
 65   
 66                  # Read the contents of the file. 
 67                  file = open(file_path) 
 68                  lines = file.readlines() 
 69                  file.close() 
 70   
 71                  # Loop over the file contents. 
 72                  for line in lines: 
 73                      # Skip everything that is not a chapter or section. 
 74                      if not (search("\\\\chapter", line) or search("\\\\section", line) or search("\\\\subsection", line)): 
 75                          continue 
 76   
 77                      # Strip off the newline character. 
 78                      line = line.replace('\n', '') 
 79   
 80                      # Strip off any label. 
 81                      if search(' \\\\label', line): 
 82                          line = line[:line.index(' \label')] 
 83   
 84                      # Extract the short title string, if it exists. 
 85                      if '[' in line: 
 86                          title = line[line.index('[')+1:line.index(']')] 
 87   
 88                      # Extract the full title string by finding the first '{' and chop off the final '}'. 
 89                      else: 
 90                          title = line[line.index('{')+1:-1] 
 91   
 92                      # Is the title new? 
 93                      if not title in self.titles: 
 94                          self.titles.append(title) 
 95   
 96                      # Replicate! 
 97                      else: 
 98                          # No replicates yet, so 2 identical titles exist. 
 99                          if not title in self.replicate: 
100                              self.replicate[title] = 2 
101   
102                          # At least two identical titles exist, so increment the counter. 
103                          else: 
104                              self.replicate[title] += 1 
105   
106          # Final printout. 
107          if len(self.replicate): 
108              # The replicate titles. 
109              print("%-80s %-10s" % ("Title", "Count")) 
110              for title in self.replicate: 
111                  print("%-80s %10i" % (title, self.replicate[title])) 
112   
113              # Return a status that replicates have been found. 
114              return True 
115   
116          # No replicates. 
117          return False 
118   
119   
120   
121  if __name__ == "__main__": 
122      repli = Replicated_titles() 
123      if repli.find(): 
124          sys.exit(1) 
125      else: 
126          sys.exit(0) 
127