view tests/test-run-tests.py @ 36672:9e7b14caf67f

xdiff: remove patience and histogram diff algorithms

Patience diff is the normal diff algorithm, plus some greediness that
unconditionally matches common common unique lines.  That means it is easy to
construct cases to let it generate suboptimal result, like:

```
open('a', 'w').write('\n'.join(list('a' + 'x' * 300 + 'u' + 'x' * 700 + 'a\n')))
open('b', 'w').write('\n'.join(list('b' + 'x' * 700 + 'u' + 'x' * 300 + 'b\n')))
```

Patience diff has been advertised as being able to generate better results for
some C code changes. However, the more scientific way to do that is the
indention heuristic [1].

Since patience diff could generate suboptimal result more easily and its
"better" diff feature could be replaced by the new indention heuristic, let's
just remove it and its variant histogram diff to simplify the code.

[1]: https://github.com/git/git/commit/433860f3d0beb0c6f205290bd16cda413148f098

Test Plan:
`gcc -fPIC *.c --shared -o xdiff.so` still builds.

Differential Revision: https://phab.mercurial-scm.org/D2573

"""test line matching with some failing examples and some which warn

run-test.t only checks positive matches and can not see warnings
(both by design)
"""
from __future__ import absolute_import, print_function

import doctest
import os
import re
# this is hack to make sure no escape characters are inserted into the output
if 'TERM' in os.environ:
    del os.environ['TERM']
run_tests = __import__('run-tests')

def prn(ex):
    m = ex.args[0]
    if isinstance(m, str):
        print(m)
    else:
        print(m.decode('utf-8'))

def lm(expected, output):
    r"""check if output matches expected

    does it generally work?
        >>> lm(b'H*e (glob)\n', b'Here\n')
        True

    fail on bad test data
        >>> try: lm(b'a\n',b'a')
        ... except AssertionError as ex: print(ex)
        missing newline
        >>> try: lm(b'single backslash\n', b'single \backslash\n')
        ... except AssertionError as ex: prn(ex)
        single backslash or unknown char
    """
    assert (expected.endswith(b'\n')
            and output.endswith(b'\n')), 'missing newline'
    assert not re.search(br'[^ \w\\/\r\n()*?]', expected + output), \
           b'single backslash or unknown char'
    test = run_tests.TTest(b'test-run-test.t', b'.', b'.')
    match = test.linematch(expected, output)
    if isinstance(match, str):
        return 'special: ' + match
    elif isinstance(match, bytes):
        return 'special: ' + match.decode('utf-8')
    else:
        return bool(match) # do not return match object

def wintests():
    r"""test matching like running on windows

    enable windows matching on any os
        >>> _osaltsep = os.altsep
        >>> os.altsep = True
        >>> _osname = os.name
        >>> os.name = 'nt'

    valid match on windows
        >>> lm(b'g/a*/d (glob)\n', b'g\\abc/d\n')
        True

    direct matching, glob unnecessary
        >>> lm(b'g/b (glob)\n', b'g/b\n')
        'special: -glob'

    missing glob
        >>> lm(b'/g/c/d/fg\n', b'\\g\\c\\d/fg\n')
        True
        >>> lm(b'/g/c/d/fg\n', b'\\g\\c\\d\\fg\r\n')
        True

    restore os.altsep
        >>> os.altsep = _osaltsep
        >>> os.name = _osname
    """
    pass

def otherostests():
    r"""test matching like running on non-windows os

    disable windows matching on any os
        >>> _osaltsep = os.altsep
        >>> os.altsep = False
        >>> _osname = os.name
        >>> os.name = 'nt'

    backslash does not match slash
        >>> lm(b'h/a* (glob)\n', b'h\\ab\n')
        False

    direct matching glob can not be recognized
        >>> lm(b'h/b (glob)\n', b'h/b\n')
        True

    missing glob can not not be recognized
        >>> lm(b'/h/c/df/g/\n', b'\\h/c\\df/g\\\n')
        False

    restore os.altsep
        >>> os.altsep = _osaltsep
        >>> os.name = _osname
    """
    pass

if __name__ == '__main__':
    doctest.testmod()