Home | History | Annotate | Download | only in scripts 
      1 # Copyright (C) 2013 Google Inc. All rights reserved.
      2 #
      3 # Redistribution and use in source and binary forms, with or without
      4 # modification, are permitted provided that the following conditions are
      5 # met:
      6 #
      7 #     * Redistributions of source code must retain the above copyright
      8 # notice, this list of conditions and the following disclaimer.
      9 #     * Redistributions in binary form must reproduce the above
     10 # copyright notice, this list of conditions and the following disclaimer
     11 # in the documentation and/or other materials provided with the
     12 # distribution.
     13 #     * Neither the name of Google Inc. nor the names of its
     14 # contributors may be used to endorse or promote products derived from
     15 # this software without specific prior written permission.
     16 #
     17 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
     18 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
     19 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
     20 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
     21 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     22 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     23 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
     24 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
     25 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
     26 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
     27 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
     28 
     29 """Lexer for Blink IDL.
     30 
     31 The lexer uses the PLY (Python Lex-Yacc) library to build a tokenizer which
     32 understands the Blink dialect of Web IDL and produces a token stream suitable
     33 for the Blink IDL parser.
     34 
     35 Blink IDL is identical to Web IDL at the token level, but the base lexer
     36 does not discard comments. We need to override (and not include comments in
     37 the token stream), as otherwise comments must be explicitly included in the
     38 phrase grammar of the parser.
     39 
     40 FIXME: Change base lexer to discard comments, and simply used the base
     41 lexer, eliminating this separate lexer.
     42 
     43 Web IDL:
     44     http://www.w3.org/TR/WebIDL/
     45 Web IDL Grammar:
     46     http://www.w3.org/TR/WebIDL/#idl-grammar
     47 PLY:
     48     http://www.dabeaz.com/ply/
     49 
     50 Design doc:
     51 http://www.chromium.org/developers/design-documents/idl-compiler#TOC-Front-end
     52 """
     53 
     54 # Disable attribute validation, as lint can't import parent class to check
     55 # pylint: disable=E1101
     56 
     57 import os.path
     58 import sys
     59 
     60 # PLY is in Chromium src/third_party/ply
     61 module_path, module_name = os.path.split(__file__)
     62 third_party = os.path.join(module_path, os.pardir, os.pardir, os.pardir, os.pardir)
     63 # Insert at front to override system libraries, and after path[0] == script dir
     64 sys.path.insert(1, third_party)
     65 from ply import lex
     66 
     67 # Base lexer is in Chromium src/tools/idl_parser
     68 tools_dir = os.path.join(third_party, os.pardir, 'tools')
     69 sys.path.append(tools_dir)
     70 from idl_parser.idl_lexer import IDLLexer
     71 
     72 REMOVE_TOKENS = ['COMMENT']
     73 
     74 
     75 class BlinkIDLLexer(IDLLexer):
     76     # ignore comments
     77     def t_COMMENT(self, t):
     78         r'(/\*(.|\n)*?\*/)|(//.*(\n[ \t]*//.*)*)'
     79         self.AddLines(t.value.count('\n'))
     80 
     81     # Analogs to _AddToken/_AddTokens in base lexer
     82     # Needed to remove COMMENT token, since comments ignored
     83     def _RemoveToken(self, token):
     84         if token in self.tokens:
     85             self.tokens.remove(token)
     86 
     87     def _RemoveTokens(self, tokens):
     88         for token in tokens:
     89             self._RemoveToken(token)
     90 
     91     def __init__(self, debug=False, optimize=True, outputdir=None):
     92         if debug:
     93             # Turn off optimization and caching to help debugging
     94             optimize = False
     95             outputdir = None
     96         if outputdir:
     97             # Need outputdir in path because lex imports the cached lex table
     98             # as a Python module
     99             sys.path.append(outputdir)
    100 
    101         IDLLexer.__init__(self)
    102         # Overrides to parent class
    103         self._RemoveTokens(REMOVE_TOKENS)
    104         # Optimized mode substantially decreases startup time (by disabling
    105         # error checking), and also allows use of Python's optimized mode.
    106         # See: Optimized Mode
    107         # http://www.dabeaz.com/ply/ply.html#ply_nn15
    108         self._lexobj = lex.lex(object=self,
    109                                debug=debug,
    110                                optimize=optimize,
    111                                outputdir=outputdir)
    112 
    113 
    114 ################################################################################
    115 
    116 def main(argv):
    117     # If file itself executed, build and cache lex table
    118     try:
    119         outputdir = argv[1]
    120     except IndexError as err:
    121         print 'Usage: %s OUTPUT_DIR' % argv[0]
    122         return 1
    123     lexer = BlinkIDLLexer(outputdir=outputdir)
    124 
    125 
    126 if __name__ == '__main__':
    127     sys.exit(main(sys.argv))
    128