src/parser/prescc.sh

   1 # This file is part of NIT ( http://www.nitlanguage.org ).
   2 #
   3 # Copyright 2009 Jean Privat <jean@pryen.org>
   4 # Copyright 2009 Jean-Sebastien Gelinas <calestar@gmail.com>
   5 #
   6 # Licensed under the Apache License, Version 2.0 (the "License");
   7 # you may not use this file except in compliance with the License.
   8 # You may obtain a copy of the License at
   9 #
  10 #     http://www.apache.org/licenses/LICENSE-2.0
  11 #
  12 # Unless required by applicable law or agreed to in writing, software
  13 # distributed under the License is distributed on an "AS IS" BASIS,
  14 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  15 # See the License for the specific language governing permissions and
  16 # limitations under the License.
  17
  18 # prescc, a Sablecc preprocessor.
  19 #
  20 # Synopsis
  21 #
  22 #   Extends a sablecc grammar with parametrized productions.
  23 #
  24 # Description
  25 #
  26 #   A production named foo~bar~baz semantically correspond to a production foo with two boolean parameters bar and baz
  27 #   In fact foo is a family of 4 distinct productions: foo, foo_bar, foo_baz and foo_bar_baz
  28 #   In a parametrized production with a parameter ~xxx:
  29 #    * parameters (~xxx) are substituted with _xxx if the parameter is true and removed if the parameter is false
  30 #    * guarded alternatives (!xxx) are disabled if the parameter is true
  31 #
  32 # Limitations
  33 #
  34 #   prescc is badly implemented with shell, sed and perl and is not robust.
  35 #   Users must remember the following:
  36 #    * parametrized productions MUST be terminated with a line containing only a single semicolon (;)
  37 #    * parameters (~) and guards (!) in alternatives MUST correspond to a parameter of the enclosing production
  38 #    * if required, names in transformations MUST contain the full invocation name (with all parameters)
  39 #        foo bar_x~y~z_t baz {-> New p(foo, bar_x~y~z_t.q)}
  40 #    * guards do not understand grammar, they just remove the whole line
  41 #    * The AST MUST start with a line containing only "Abstract Syntax Tree"
  42 #
  43 # Example of the dangling else implementation:
  44 #
  45 #   stmt~withelse =
  46 #                'if' expr 'then' stmt_withelse 'else' stmt~withelse |
  47 #     !withelse  'if' expr 'then' stmt |
  48 #                nop
  49 #                ;
  50
  51
  52 case $# in
  53         2);;
  54         *) echo "Usage: prescc infile outfile"; exit
  55 esac
  56
  57
  58 infile=$1
  59 outfile=$2
  60 tmpfile=`mktemp "$2.XXXXXX"`
  61
  62 printf "/* This file is autogenerated, do not modify it */" > "$outfile"
  63 cat "$infile" >> "$outfile"
  64
  65 # The perl code is used to list all the available parameters in the extended grammar
  66 for token in `perl -ne 'if (/\~(\w+)/ && !$found{$1}) {print "$1\n"; $found{$1}=1}' "$infile"`
  67 do
  68         echo "Parameter ~$token"
  69         # first, sed starts from first line to the AST line and removes ~xxx and !xxx
  70         sed -n -e "
  71                 1,/^Abstract Syntax Tree/{
  72                         /^Abstract Syntax Tree/b
  73                         s/[\~!]$token//g
  74                         p
  75                 }
  76         " "$outfile" > "$tmpfile"
  77         # second, sed clones ~xxx parametrized productions, substitute ~xxx with _xxx and delete !xxx lines
  78         sed -n -e "
  79                 /\~$token/,/;/{
  80                         s/\~$token/_$token/g
  81                         /!$token/d
  82                         p
  83                 }
  84         " "$outfile" >> "$tmpfile"
  85         # third, sed continues fron AST line to last line and remove ~xxx and !xxx
  86         sed -n -e "
  87                 /^Abstract Syntax Tree/,\${
  88                         s/[\~!]$token//g
  89                         p
  90                 }
  91         " "$outfile" >> "$tmpfile"
  92         mv "$tmpfile" "$outfile"
  93 done
  94