view mercurial/diffhelper.py @ 43813:5a9e2ae9899b

fuzz: use a more standard approach to allow local builds of fuzzers

This is taken from the (improved since we started fuzzing) guide on ideal
integrations. Rather than have our own wonky targets for building outside the
fuzzer universe, we have a driver program we carry along and use when we're
not using LibFuzzer. This will let us jettison a fair amount of goo.

contrib/fuzz/standalone_fuzz_target_runner.cc is
https://github.com/google/oss-fuzz/ file
projects/example/my-api-repo/standalone from git revision
c4579d9358a73ea5dbcc99cb985de1f2bf76dcf7, reformatted with out
clang-format settings and a no-check-code comment added. It allows
running a single test input through a fuzzer, rather than performing
ongoing fuzzing as libfuzzer would.

contrib/fuzz/FuzzedDataProvider.h is
https://github.com/llvm/llvm-project/ file
/compiler-rt/include/fuzzer/FuzzedDataProvider.h from git revision
a44ef027ebca1598892ea9b104d6189aeb3bc2f0, reformatted with our
clang-format settings and a no-check-code comment added. We can
discard this if we instead want to add an hghave check for a new
enough llvm that includes FuzzedDataProvder.h in the fuzzer headers.

Differential Revision: https://phab.mercurial-scm.org/D7564

# diffhelper.py - helper routines for patch
#
# Copyright 2009 Matt Mackall <[e-mail]> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

from .i18n import _

from . import (
    error,
    pycompat,
)


def addlines(fp, hunk, lena, lenb, a, b):
    """Read lines from fp into the hunk

    The hunk is parsed into two arrays, a and b. a gets the old state of
    the text, b gets the new state. The control char from the hunk is saved
    when inserting into a, but not b (for performance while deleting files.)
    """
    while True:
        todoa = lena - len(a)
        todob = lenb - len(b)
        num = max(todoa, todob)
        if num == 0:
            break
        for i in pycompat.xrange(num):
            s = fp.readline()
            if not s:
                raise error.ParseError(_(b'incomplete hunk'))
            if s == b"\\ No newline at end of file\n":
                fixnewline(hunk, a, b)
                continue
            if s == b'\n' or s == b'\r\n':
                # Some patches may be missing the control char
                # on empty lines. Supply a leading space.
                s = b' ' + s
            hunk.append(s)
            if s.startswith(b'+'):
                b.append(s[1:])
            elif s.startswith(b'-'):
                a.append(s)
            else:
                b.append(s[1:])
                a.append(s)


def fixnewline(hunk, a, b):
    """Fix up the last lines of a and b when the patch has no newline at EOF"""
    l = hunk[-1]
    # tolerate CRLF in last line
    if l.endswith(b'\r\n'):
        hline = l[:-2]
    else:
        hline = l[:-1]

    if hline.startswith((b' ', b'+')):
        b[-1] = hline[1:]
    if hline.startswith((b' ', b'-')):
        a[-1] = hline
    hunk[-1] = hline


def testhunk(a, b, bstart):
    """Compare the lines in a with the lines in b

    a is assumed to have a control char at the start of each line, this char
    is ignored in the compare.
    """
    alen = len(a)
    blen = len(b)
    if alen > blen - bstart or bstart < 0:
        return False
    for i in pycompat.xrange(alen):
        if a[i][1:] != b[i + bstart]:
            return False
    return True