compile.py

   1 #! /usr/bin/python3
   2
   3 '''
   4 This module converts text differetial diagnosis files
   5 to a simplified modular file format that can be used
   6 by the program.
   7 '''
   8 '''
   9 Copyright (c) 2015 Agnibho Mondal
  10 All rights reserved
  11
  12 This file is part of DDStorm.
  13
  14 DDStorm is free software: you can redistribute it and/or modify
  15 it under the terms of the GNU General Public License as published by
  16 the Free Software Foundation, either version 3 of the License, or
  17 (at your option) any later version.
  18
  19 DDStorm is distributed in the hope that it will be useful,
  20 but WITHOUT ANY WARRANTY; without even the implied warranty of
  21 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  22 GNU General Public License for more details.
  23
  24 You should have received a copy of the GNU General Public License
  25 along with DDStorm.  If not, see <http://www.gnu.org/licenses/>.
  26 '''
  27
  28 import os
  29 import logging
  30 import re
  31 from operator import itemgetter
  32 from fnmatch import fnmatch
  33
  34 from conf import Conf
  35 from const import *
  36 from alias import Alias
  37
  38 logging.basicConfig(filename=LOG_FILE)
  39
  40 class Compile:
  41     '''
  42     This class creates a compiler for the DDStorm
  43     that compiles the text files containing list of
  44     differential diagnosis to simplified modular
  45     data files usable by the program.
  46     '''
  47
  48     def __init__(self, conf=False):
  49         '''
  50         The constructor optionally accepts a configuration.
  51         If none is provided it creates a default configuration.
  52
  53         Parameters:
  54         conf - A dictionary containing configuration options
  55         '''
  56         if(conf):
  57             self._conf=conf
  58         else:
  59             self._conf=Conf()
  60         self.clean=True
  61
  62     def compile(self):
  63         ''' Compile the text files to DDStorm modules. '''
  64         self.source=set()
  65         self.custom=set()
  66         self.alias=Alias(self._conf)
  67
  68         # Loop over library files and add *.txt files to source
  69         for path, subdirs, files in os.walk(self._conf.get("library_path")):
  70             for name in files:
  71                 if(fnmatch(name, "*.txt")):
  72                     self.source.add(os.path.join(path, name))
  73
  74         # Loop over custom files and add *.txt files to custom
  75         for path, subdirs, files in os.walk(self._conf.get("custom_path")):
  76             for name in files:
  77                 if(fnmatch(name, "*.txt")):
  78                     self.custom.add(os.path.join(path, name))
  79
  80         # Create module directory if not already present and delete all module files
  81         if(not os.path.isdir(self._conf.get("module_path"))):
  82             os.makedirs(self._conf.get("module_path"))
  83         for f in os.listdir(self._conf.get("module_path")):
  84             if(fnmatch(f, "*.module")):
  85                 os.unlink(self._conf.get("module_path")+f)
  86
  87         # Create a regex for calculating priority from filename
  88         self.priorityRegex=re.compile("(?<=\.)\d+$")
  89
  90         # First sort files by priority then compile them to module
  91         for src in self._sortPriority(self.source):
  92             self._makeModule(src)
  93         for src in self._sortPriority(self.custom):
  94             self._makeModule(src)
  95
  96     def _sortPriority(self, files):
  97         ''' Sort data files based on their priority settings. '''
  98         ls=[]
  99         # Loop over the files
 100         for addr in files:
 101             # Format the file name
 102             name=os.path.splitext(os.path.basename(addr))[0].lower().replace("_"," ").replace("-", " ")
 103             # Search for priority tag on file name
 104             m=re.search(self.priorityRegex, name)
 105             # Add to ls as (symptom name, priority number, file name) with default priority of 100
 106             if(m):
 107                 ls.append((name.replace("."+m.group(), ""), int(m.group()), addr))
 108             else:
 109                 ls.append((name, 100, addr))
 110         # Sort the file list, first by the symptom name, then by the priority number
 111         ls.sort(reverse=True)
 112         if(ls):
 113             return(list(zip(*ls))[2])
 114         else:
 115             return ls
 116
 117     def _makeModule(self, src):
 118         ''' Create application usable modules from data files. '''
 119         # Format the file name
 120         module=os.path.splitext(os.path.basename(src))[0].lower().replace("_"," ").replace("-", " ")
 121         # Remove the priority tag from file name
 122         m=re.search(self.priorityRegex, module)
 123         if(m):
 124             module=module.replace("."+m.group(), "")
 125         # Create the module file name
 126         modFile=self._conf.get("module_path")+module+".module"
 127         modFlag=False
 128         # Loop over both files, the source data file and the target module file
 129         with open(src, "r") as sf, open(modFile, "a") as tf:
 130             # Ignore lines starting with ! or #, + and - has special meaning, write other lines to module. Log the errors.
 131             for line in sf:
 132                 line=line.strip().split("#")[0]
 133                 if(len(line)==0):
 134                     pass
 135                 elif(line.startswith("!")):
 136                     pass
 137                 elif(line.startswith("#")):
 138                     pass
 139                 elif(line.startswith("+")):
 140                     modFlag=True
 141                 elif(line.startswith("-")):
 142                     modFlag=True
 143                 elif(line.replace(" ","").replace("-","").replace("_","").replace("'","").isalnum()):
 144                     print(self.alias.get(line).capitalize(), file=tf)
 145                 else:
 146                     self.clean=False
 147                     logging.warning("Syntax error in file '"+src+"': "+line)
 148         # Deal with special lines
 149         if(modFlag):
 150             modFlag=False
 151             with open(src, "r") as f:
 152                 for line in f:
 153                     line=line.strip().split("#")[0]
 154                     if(line[1:].replace(" ","").replace("-","").replace("_","").replace("'","").isalnum()):
 155                         # If line starts with + add it to the module file
 156                         if(line.startswith("+")):
 157                             with open(modFile, "r") as fn:
 158                                 text=fn.read()
 159                             with open(modFile, "w") as fn:
 160                                 print(self.alias.get(line[1:]).capitalize()+"\n"+text, file=fn)
 161                         # If line starts with - remove corresponding item from the module file
 162                         elif(line.startswith("-")):
 163                             with open(modFile, "r") as fn:
 164                                 text=fn.read()
 165                             text=text.replace(self.alias.get(line[1:]).capitalize()+"\n", "")
 166                             with open(modFile, "w") as fn:
 167                                 print(text, file=fn)
 168
 169     def is_clean(self):
 170             '''Report if compilation ended successfully'''
 171             return self.clean
 172
 173 def main():
 174     ''' Compile the data files into formatted module files '''
 175     c=Compile().compile()
 176
 177 if(__name__=="__main__"):
 178     main()