comparison mercurial/changelog.py @ 42116:caa067ee21dc

changelog: extract a _string_unescape() to mirror _string_escape()

We use our own _string_escape() to encode the "extras" field. Then we
use codecs.escape_decode() to escape it. But there's also a little
workaround for dealing with escaped text that looks like octal numbers
since the fix for
https://bz.mercurial-scm.org/show_bug.cgi?id=3156. This patch extracts
the call to codecs.escape_decode() along with the fix for octal
numbers and puts it in a _string_unescape(). It also updates the test
to check for the octal-number case from the aforementioned bug.

As you may have suspected, I want to be able to reuse this new
function later.

Differential Revision: https://phab.mercurial-scm.org/D6184

42115:27475ae67676

def _string_escape(text):
    """
    >>> from .pycompat import bytechr as chr
    >>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)}
    >>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)sab%(cr)scd%(bs)s%(nl)s" % d
    >>> s
    'ab\\ncd\\\\\\\\n\\x00ab\\rcd\\\\\\n'
    >>> res = _string_escape(s)
    >>> s == stringutil.unescapestr(res)
    True
    """
    # subset of the string_escape codec
    text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
    return text.replace('\0', '\\0')

def decodeextra(text):
    """
    >>> from .pycompat import bytechr as chr
    >>> sorted(decodeextra(encodeextra({b'foo': b'bar', b'baz': chr(0) + b'2'})

    [('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')]
    """
    extra = _defaultextra.copy()
    for l in text.split('\0'):
        if l:
            if '\\0' in l:
                # fix up \0 without getting into trouble with \\0
                l = l.replace('\\\\', '\\\\\n')
                l = l.replace('\\0', '\0')
                l = l.replace('\n', '')
            k, v = stringutil.unescapestr(l).split(':', 1)
            extra[k] = v
    return extra

def encodeextra(d):
    # keys must be sorted to produce a deterministic changelog entry

42116:caa067ee21dc

def _string_escape(text):
    """
    >>> from .pycompat import bytechr as chr
    >>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)}
    >>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)s12ab%(cr)scd%(bs)s%(nl)s" % d
    >>> s
    'ab\\ncd\\\\\\\\n\\x0012ab\\rcd\\\\\\n'
    >>> res = _string_escape(s)
    >>> s == _string_unescape(res)
    True
    """
    # subset of the string_escape codec
    text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
    return text.replace('\0', '\\0')

def _string_unescape(text):
    if '\\0' in text:
        # fix up \0 without getting into trouble with \\0
        text = text.replace('\\\\', '\\\\\n')
        text = text.replace('\\0', '\0')
        text = text.replace('\n', '')
    return stringutil.unescapestr(text)

def decodeextra(text):
    """
    >>> from .pycompat import bytechr as chr
    >>> sorted(decodeextra(encodeextra({b'foo': b'bar', b'baz': chr(0) + b'2'})

    [('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')]
    """
    extra = _defaultextra.copy()
    for l in text.split('\0'):
        if l:
            k, v = _string_unescape(l).split(':', 1)
            extra[k] = v
    return extra

def encodeextra(d):
    # keys must be sorted to produce a deterministic changelog entry