view mercurial/pure/parsers.py @ 32979:66117dae87f9

patch: rewrite reversehunks (issue5337)

The old reversehunks code accesses "crecord.uihunk._hunk", which is the raw
recordhunk without crecord selection information, therefore "revert -i"
cannot revert individual lines, aka. issue5337.

The patch rewrites related logic to return the right reverse hunk for
revert. Namely,

 1. "fromline" and "toline" are correctly swapped [1]
 2. crecord.uihunk generates a correct reverse hunk [2]

Besides, reversehunks(hunks) will no longer modify its input "hunks", which
is more expected.

[1]: To explain why "fromline" and "toline" need to be swapped, take the
     following example:

  $ cat > a <<EOF
  > 1
  > 2
  > 3
  > 4
  > EOF

  $ cat > b <<EOF
  > 2
  > 3
  > 5
  > EOF

  $ diff a b
  1d0   <---- "1" is "fromline" and "0" is "toline"
  < 1         and they are swapped if diff from the reversed direction
  4c3             |
  < 4             |
  ---             |
  > 5             |
                  |
  $ diff b a      |
  0a1   <---------+
  > 1
  3c4   <---- also "4c3" gets swapped to "3c4"
  < 5
  ---
  > 4

[2]: This is a bit tricky.

For example, given a file which is empty in working parent but has 3 lines
in working copy, and the user selection:

    select hunk to discard
    [x] +1
    [ ] +2
    [x] +3

The user intent is to drop "1" and "3" in working copy but keep "2", so the
reverse patch would be something like:

        -1
         2 (2 is a "context line")
        -3

We cannot just take all selected lines and swap "-" and "+", which will be:

        -1
        -3

That patch won't apply because of "2". So the correct way is to insert "2"
as a "context line" by inserting it first then deleting it:

        -2
        +2

Therefore, the correct revert patch is:

        -1
        -2
        +2
        -3

It could be reordered to look more like a common diff hunk:

        -1
        -2
        -3
        +2

Note: It's possible to return multiple hunks so there won't be lines like
"-2", "+2". But the current implementation is much simpler.

For deletions, like the working parent has "1\n2\n3\n" and it was changed to
empty in working copy:

    select hunk to discard
    [x] -1
    [ ] -2
    [x] -3

The user intent is to drop the deletion of 1 and 3 (in other words, keep
those lines), but still delete "2".

The reverse patch is meant to be applied to working copy which is empty.
So the patch would be:

        +1
        +3

That is to say, there is no need to special handle the unselected "2" like
the above insertion case.

# parsers.py - Python implementation of parsers.c
#
# 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

import struct
import zlib

from ..node import nullid
from .. import pycompat
stringio = pycompat.stringio


_pack = struct.pack
_unpack = struct.unpack
_compress = zlib.compress
_decompress = zlib.decompress

# Some code below makes tuples directly because it's more convenient. However,
# code outside this module should always use dirstatetuple.
def dirstatetuple(*x):
    # x is a tuple
    return x

indexformatng = ">Qiiiiii20s12x"
indexfirst = struct.calcsize('Q')
sizeint = struct.calcsize('i')
indexsize = struct.calcsize(indexformatng)

def gettype(q):
    return int(q & 0xFFFF)

def offset_type(offset, type):
    return int(int(offset) << 16 | type)

class BaseIndexObject(object):
    def __len__(self):
        return self._lgt + len(self._extra) + 1

    def insert(self, i, tup):
        assert i == -1
        self._extra.append(tup)

    def _fix_index(self, i):
        if not isinstance(i, int):
            raise TypeError("expecting int indexes")
        if i < 0:
            i = len(self) + i
        if i < 0 or i >= len(self):
            raise IndexError
        return i

    def __getitem__(self, i):
        i = self._fix_index(i)
        if i == len(self) - 1:
            return (0, 0, 0, -1, -1, -1, -1, nullid)
        if i >= self._lgt:
            return self._extra[i - self._lgt]
        index = self._calculate_index(i)
        r = struct.unpack(indexformatng, self._data[index:index + indexsize])
        if i == 0:
            e = list(r)
            type = gettype(e[0])
            e[0] = offset_type(0, type)
            return tuple(e)
        return r

class IndexObject(BaseIndexObject):
    def __init__(self, data):
        assert len(data) % indexsize == 0
        self._data = data
        self._lgt = len(data) // indexsize
        self._extra = []

    def _calculate_index(self, i):
        return i * indexsize

    def __delitem__(self, i):
        if not isinstance(i, slice) or not i.stop == -1 or not i.step is None:
            raise ValueError("deleting slices only supports a:-1 with step 1")
        i = self._fix_index(i.start)
        if i < self._lgt:
            self._data = self._data[:i * indexsize]
            self._lgt = i
            self._extra = []
        else:
            self._extra = self._extra[:i - self._lgt]

class InlinedIndexObject(BaseIndexObject):
    def __init__(self, data, inline=0):
        self._data = data
        self._lgt = self._inline_scan(None)
        self._inline_scan(self._lgt)
        self._extra = []

    def _inline_scan(self, lgt):
        off = 0
        if lgt is not None:
            self._offsets = [0] * lgt
        count = 0
        while off <= len(self._data) - indexsize:
            s, = struct.unpack('>i',
                self._data[off + indexfirst:off + sizeint + indexfirst])
            if lgt is not None:
                self._offsets[count] = off
            count += 1
            off += indexsize + s
        if off != len(self._data):
            raise ValueError("corrupted data")
        return count

    def __delitem__(self, i):
        if not isinstance(i, slice) or not i.stop == -1 or not i.step is None:
            raise ValueError("deleting slices only supports a:-1 with step 1")
        i = self._fix_index(i.start)
        if i < self._lgt:
            self._offsets = self._offsets[:i]
            self._lgt = i
            self._extra = []
        else:
            self._extra = self._extra[:i - self._lgt]

    def _calculate_index(self, i):
        return self._offsets[i]

def parse_index2(data, inline):
    if not inline:
        return IndexObject(data), None
    return InlinedIndexObject(data, inline), (0, data)

def parse_dirstate(dmap, copymap, st):
    parents = [st[:20], st[20: 40]]
    # dereference fields so they will be local in loop
    format = ">cllll"
    e_size = struct.calcsize(format)
    pos1 = 40
    l = len(st)

    # the inner loop
    while pos1 < l:
        pos2 = pos1 + e_size
        e = _unpack(">cllll", st[pos1:pos2]) # a literal here is faster
        pos1 = pos2 + e[4]
        f = st[pos2:pos1]
        if '\0' in f:
            f, c = f.split('\0')
            copymap[f] = c
        dmap[f] = e[:4]
    return parents

def pack_dirstate(dmap, copymap, pl, now):
    now = int(now)
    cs = stringio()
    write = cs.write
    write("".join(pl))
    for f, e in dmap.iteritems():
        if e[0] == 'n' and e[3] == now:
            # The file was last modified "simultaneously" with the current
            # write to dirstate (i.e. within the same second for file-
            # systems with a granularity of 1 sec). This commonly happens
            # for at least a couple of files on 'update'.
            # The user could change the file without changing its size
            # within the same second. Invalidate the file's mtime in
            # dirstate, forcing future 'status' calls to compare the
            # contents of the file if the size is the same. This prevents
            # mistakenly treating such files as clean.
            e = dirstatetuple(e[0], e[1], e[2], -1)
            dmap[f] = e

        if f in copymap:
            f = "%s\0%s" % (f, copymap[f])
        e = _pack(">cllll", e[0], e[1], e[2], e[3], len(f))
        write(e)
        write(f)
    return cs.getvalue()