scripts/build/yyout2grammar.py

   1 #!@PYTHON@
   2 #
   3 #  yyout2grammar.py
   4
   5 # This file is part of LilyPond, the GNU music typesetter.
   6 #
   7 # Copyright (C) 2005 by Carl D. Sorensen <c_sorensen@byu.edu>
   8 #
   9 # LilyPond 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 # LilyPond 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 LilyPond.  If not, see <http://www.gnu.org/licenses/>.
  21
  22
  23 #  Convert from bison output file parser.output to
  24 #  Grammar and index.
  25 #  Drops all of the state information.
  26 #  Converts \\ to \
  27 #  Eliminates the @ variables created when {} is placed
  28 #        in the middle of a rule
  29 #  Eliminates all of the c-code stuff
  30 #  Wraps lines that are longer than 78 characters for improved
  31 #        formatting
  32 #
  33 # to create input file, run
  34 #   bison -v parser.yy
  35 # this will create a file parser.output
  36 # then run
  37 #   yyout2grammar.py parser.output your_output_file
  38 #
  39
  40 import sys
  41 import re
  42
  43 atre = re.compile('(@\d+):')
  44
  45 intro_re = re.compile (r'(.*[:|])\s')
  46 keyword_re = re.compile (r'(\S+)\s')
  47
  48 # strip extra backslashes that are inserted by the python
  49 # string handling routines
  50 def strip_backslash(input_string):
  51     i=input_string.find(r'"\\')
  52     while i > -1 :
  53         input_string = input_string[:i+1]+input_string[i+2:]
  54         i = input_string.find(r'"\\')
  55     return  input_string
  56
  57 #  write an output line, adjusting to make sure that max_line_length
  58 #  is not exceeded
  59 def write_line (output_line, output_file):
  60     max_line_length = 78
  61     indent_value = 3
  62     if len(output_line) > max_line_length:
  63         intro = intro_re.match(output_line)
  64         if intro:
  65             output_file.write(intro.group(1)+" ")
  66             indent_column = len(intro.group(1))
  67             output_line = output_line[indent_column:]
  68             keyword = keyword_re.search(output_line)
  69             while keyword:
  70                 output_file.write(strip_backslash(keyword.group(1))+" \n")
  71                 output_line = output_line[keyword.end(1):]
  72                 keyword = keyword_re.search(output_line)
  73                 if keyword:
  74                     output_file.write("".rjust(indent_column + indent_value))
  75     else:
  76         output_file.write(strip_backslash(output_line))
  77     return
  78
  79 write_me = True
  80
  81 if len(sys.argv)!=3:
  82     print "Usage: yyout2grammar.py parser_output_file grammar_file."
  83 else:
  84     in_name = sys.argv[1]
  85     out_name = sys.argv[2]
  86
  87     print "input file name",in_name
  88     print "output file name",out_name
  89     in_file = open(in_name,'r')
  90     out_file= open(out_name, 'w')
  91
  92     at_items=[]
  93     inline = in_file.readline()
  94
  95     ## skip header material from file
  96     while inline != '' and not(inline.startswith("Grammar")):
  97         inline = in_file.readline()
  98
  99     ## process the Grammar lines
 100     if inline != '':
 101         write_line(inline, out_file)
 102         inline = in_file.readline()
 103         while inline != '' and not(inline.startswith("Terminals")):
 104             i = inline.find("$accept:")
 105             if i>-1:
 106                 write_me = False
 107                 inline = in_file.readline()
 108             atfound = re.findall(atre,inline)
 109             if len(atfound) > 0:
 110                 at_items.extend(atfound)
 111                 #  print at_items
 112                 write_me = False
 113                 inline=in_file.readline()
 114             else:
 115                 for at_item in at_items:
 116                     i=inline.find(at_item)
 117                     ## remove @ item
 118                     if i >= 0:
 119                         inline=inline[:i] + inline[i+len(at_item):]
 120
 121             if write_me:
 122                 write_line(inline, out_file)
 123             inline = in_file.readline()
 124             write_me = True
 125     index_items = []
 126
 127     #  Write the Terminals header line and the following blank line
 128     write_line(inline, out_file)
 129     inline = in_file.readline()
 130     write_line(inline, out_file)
 131     inline = in_file.readline()
 132     while inline != '' and not(inline.startswith("Nonterminals")):
 133         i=inline.find('"\\\\')
 134         while i > -1 :
 135             inline = inline[:i+1]+inline[i+2:]
 136             i = inline.find('"\\\\')
 137         index_items.append(inline)
 138         inline = in_file.readline()
 139     index_items.sort(lambda x,y:cmp(x.lower(),y.lower()))
 140     for index_item in index_items:
 141         write_line (index_item, out_file)
 142     write_line ('\n', out_file)
 143
 144     # Write the Nonterminals header and the blank line
 145     write_line(inline, out_file)
 146     inline = in_file.readline()
 147     write_line(inline, out_file)
 148     index_items = []
 149     index_item=in_file.readline()
 150     inline=in_file.readline()
 151     while inline != '' and not(inline.startswith("state")):
 152         while inline.startswith("    "):
 153             index_item = index_item + inline
 154             inline = in_file.readline()
 155         if not(index_item.startswith("@")) and \
 156                not(index_item.startswith("$accept")):
 157             index_items.append(index_item)
 158         index_item = inline
 159         inline=in_file.readline()
 160     index_items.sort(lambda x,y:cmp(x.lower(),y.lower()))
 161     for index_item in index_items:
 162         write_line (index_item, out_file)