action_maketokenizer.py   [plain text]

#!/usr/bin/python
#
# Copyright (C) 2009 Google Inc. All rights reserved.
# 
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
# 
#     * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#     * Redistributions in binary form must reproduce the above
# copyright notice, this list of conditions and the following disclaimer
# in the documentation and/or other materials provided with the
# distribution.
#     * Neither the name of Google Inc. nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
# 
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
# Copyright (c) 2009 The Chromium Authors. All rights reserved.
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.

# usage: action_maketokenizer.py OUTPUTS -- INPUTS
#
# Multiple INPUTS may be listed. The sections are separated by -- arguments.
#
# OUTPUTS must contain a single item: a path to tokenizer.cpp.
#
# INPUTS must contain exactly two items. The first item must be the path to
# maketokenizer. The second item must be the path to tokenizer.flex.


import os
import subprocess
import sys


def SplitArgsIntoSections(args):
    sections = []
    while len(args) > 0:
        if not '--' in args:
            # If there is no '--' left, everything remaining is an entire section.
            dashes = len(args)
        else:
            dashes = args.index('--')

        sections.append(args[:dashes])

        # Next time through the loop, look at everything after this '--'.
        if dashes + 1 == len(args):
            # If the '--' is at the end of the list, we won't come back through the
            # loop again. Add an empty section now corresponding to the nothingness
            # following the final '--'.
            args = []
            sections.append(args)
        else:
            args = args[dashes + 1:]

    return sections


def main(args):
    sections = SplitArgsIntoSections(args[1:])
    assert len(sections) == 2
    (outputs, inputs) = sections

    assert len(outputs) == 1
    output = outputs[0]

    assert len(inputs) == 2
    maketokenizer = inputs[0]
    flexInput = inputs[1]

    # Do it. check_call is new in 2.5, so simulate its behavior with call and
    # assert.
    outfile = open(output, 'wb')
    p1 = subprocess.Popen(['flex', '-t', flexInput], stdout=subprocess.PIPE)
    p2 = subprocess.Popen(['perl', maketokenizer], stdin=p1.stdout, stdout=outfile)

    r1 = p1.wait()
    r2 = p2.wait()
    assert r1 == 0
    assert r2 == 0

    return 0


if __name__ == '__main__':
    sys.exit(main(sys.argv))