mercurial/pure/charencode.py

wireprotov2: send linknodes to emitfilerevisions()

Previously, linknodes were calculated within emitfilerevisions() by
using filectx.introrev(), which would always use the linkrev/linknode
as recorded by storage. This is wrong for cases where the receiver
doesn't have the changeset the linknode refers to.

This commit changes the logic for linknode emission so the mapping
of filenode to linknode is computed by the caller and passed into
emitfilerevisions().

As part of the change, linknodes for "filesdata" in the
haveparents=False case are now correct: the existing code performed a
manifest walk and it was trivial to plug in the correct linknode.

However, behavior for the haveparents=True case is still wrong
because it relies on filtering linkrevs against the outgoing set in
order to determine what to send. This will be fixed in a subsequent
commit.

The change test test-wireproto-exchangev2-shallow.t is a bit wonky.
The test repo has 6 revisions. The changed test is performing a shallow
clone with depth=1. So, only file data for revision 5 is present
locally. So, the new behavior of associating the linknode with
revision 5 for every file revision seems correct. Of course, when
backfilling old revisions, we'll want to update the linknode. But
this problem requires wire protocol support and we'll cross that
bridge later.

Differential Revision: https://phab.mercurial-scm.org/D5405

# charencode.py - miscellaneous character encoding
#
#  Copyright 2005-2009 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

import array

from .. import (
    pycompat,
)

def isasciistr(s):
    try:
        s.decode('ascii')
        return True
    except UnicodeDecodeError:
        return False

def asciilower(s):
    '''convert a string to lowercase if ASCII

    Raises UnicodeDecodeError if non-ASCII characters are found.'''
    s.decode('ascii')
    return s.lower()

def asciiupper(s):
    '''convert a string to uppercase if ASCII

    Raises UnicodeDecodeError if non-ASCII characters are found.'''
    s.decode('ascii')
    return s.upper()

_jsonmap = []
_jsonmap.extend("\\u%04x" % x for x in range(32))
_jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))
_jsonmap.append('\\u007f')
_jsonmap[0x09] = '\\t'
_jsonmap[0x0a] = '\\n'
_jsonmap[0x22] = '\\"'
_jsonmap[0x5c] = '\\\\'
_jsonmap[0x08] = '\\b'
_jsonmap[0x0c] = '\\f'
_jsonmap[0x0d] = '\\r'
_paranoidjsonmap = _jsonmap[:]
_paranoidjsonmap[0x3c] = '\\u003c'  # '<' (e.g. escape "</script>")
_paranoidjsonmap[0x3e] = '\\u003e'  # '>'
_jsonmap.extend(pycompat.bytechr(x) for x in range(128, 256))

def jsonescapeu8fast(u8chars, paranoid):
    """Convert a UTF-8 byte string to JSON-escaped form (fast path)

    Raises ValueError if non-ASCII characters have to be escaped.
    """
    if paranoid:
        jm = _paranoidjsonmap
    else:
        jm = _jsonmap
    try:
        return ''.join(jm[x] for x in bytearray(u8chars))
    except IndexError:
        raise ValueError

if pycompat.ispy3:
    _utf8strict = r'surrogatepass'
else:
    _utf8strict = r'strict'

def jsonescapeu8fallback(u8chars, paranoid):
    """Convert a UTF-8 byte string to JSON-escaped form (slow path)

    Escapes all non-ASCII characters no matter if paranoid is False.
    """
    if paranoid:
        jm = _paranoidjsonmap
    else:
        jm = _jsonmap
    # non-BMP char is represented as UTF-16 surrogate pair
    u16b = u8chars.decode('utf-8', _utf8strict).encode('utf-16', _utf8strict)
    u16codes = array.array(r'H', u16b)
    u16codes.pop(0)  # drop BOM
    return ''.join(jm[x] if x < 128 else '\\u%04x' % x for x in u16codes)