config/check_js_opcode.py
author Henri Sivonen <hsivonen@hsivonen.fi>
Fri, 06 Jul 2018 10:44:43 +0300
changeset 489140 4ef0f163fdeb9afeddd87b37bfd987298c038542
parent 476323 da3c81f986fa63b42a2874b1791eddcdbfbe8424
child 503288 19a802e5b33298741d6efcc2e8374ae48f1e8b28
permissions -rw-r--r--
Bug 1402247 - Use encoding_rs for XPCOM string encoding conversions. r=Nika,erahm,froydnj. Correctness improvements: * UTF errors are handled safely per spec instead of dangerously truncating strings. * There are fewer converter implementations. Performance improvements: * The old code did exact buffer length math, which meant doing UTF math twice on each input string (once for length calculation and another time for conversion). Exact length math is more complicated when handling errors properly, which the old code didn't do. The new code does UTF math on the string content only once (when converting) but risks allocating more than once. There are heuristics in place to lower the probability of reallocation in cases where the double math avoidance isn't enough of a saving to absorb an allocation and memcpy. * Previously, in UTF-16 <-> UTF-8 conversions, an ASCII prefix was optimized but a single non-ASCII code point pessimized the rest of the string. The new code tries to get back on the fast ASCII path. * UTF-16 to Latin1 conversion guarantees less about handling of out-of-range input to eliminate an operation from the inner loop on x86/x86_64. * When assigning to a pre-existing string, the new code tries to reuse the old buffer instead of first releasing the old buffer and then allocating a new one. * When reallocating from the new code, the memcpy covers only the data that is part of the logical length of the old string instead of memcpying the whole capacity. (For old callers old excess memcpy behavior is preserved due to bogus callers. See bug 1472113.) * UTF-8 strings in XPConnect that are in the Latin1 range are passed to SpiderMonkey as Latin1. New features: * Conversion between UTF-8 and Latin1 is added in order to enable faster future interop between Rust code (or otherwise UTF-8-using code) and text node and SpiderMonkey code that uses Latin1. MozReview-Commit-ID: JaJuExfILM9

# vim: set ts=8 sts=4 et sw=4 tw=99:
# This Source Code Form is subject to the terms of the Mozilla Public
# License, v. 2.0. If a copy of the MPL was not distributed with this
# file, You can obtain one at http://mozilla.org/MPL/2.0/.

# ----------------------------------------------------------------------------
# This script checks bytecode documentation in js/src/vm/Opcodes.h
# ----------------------------------------------------------------------------

from __future__ import print_function

import os
import sys

scriptname = os.path.basename(__file__)
topsrcdir = os.path.dirname(os.path.dirname(__file__))


def log_pass(text):
    print('TEST-PASS | {} | {}'.format(scriptname, text))


def log_fail(text):
    print('TEST-UNEXPECTED-FAIL | {} | {}'.format(scriptname, text))


def check_opcode():
    sys.path.insert(0, os.path.join(topsrcdir, 'js', 'src', 'vm'))
    import opcode

    try:
        opcode.get_opcodes(topsrcdir)
    except Exception as e:
        log_fail(e.args[0])

    log_pass('ok')
    return True


def main():
    if not check_opcode():
        sys.exit(1)

    sys.exit(0)


if __name__ == '__main__':
    main()