view mercurial/pure/mpatch.py @ 25867:a74e9806d17d stable

highlight: produce correct markup when there's a blank line just before EOF

Due to how the colorized output from pygments was stripped of <pre> elements,
when there was an empty line at the end of a file, highlight extension produced
an incorrect markup (no closing tags from the fileline/annotateline template).
It wasn't usually noticeable, because browsers were smart enough to see where
the missing tags should've been, but in monoblue style it resulted in the last
line having twice the normal height.

Instead of awkwardly trying to strip outer <pre></pre> tags, let's make the
formatter with nowrap=True, which should do what we need in pygments since at
least 0.5 (2006-10-30).

Example from monoblue style:

Before:

    <div class="source">

<div style="font-family:monospace" class="parity0">
<pre><a class="linenr" href="#l1" id="l1">     1</a> </pre>
</div>
<div style="font-family:monospace" class="parity1">
<pre><a class="linenr" href="#l2" id="l2">     2</a>
    </div>

Now:

    <div class="source">

<div style="font-family:monospace" class="parity0">
<pre><a class="linenr" href="#l1" id="l1">     1</a> </pre>
</div>
<div style="font-family:monospace" class="parity1">
<pre><a class="linenr" href="#l2" id="l2">     2</a> </pre>
</div>
    </div>

(Notice the missing </pre></div> now in place)

# mpatch.py - Python implementation of mpatch.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.

import struct
try:
    from cStringIO import StringIO
except ImportError:
    from StringIO import StringIO

# This attempts to apply a series of patches in time proportional to
# the total size of the patches, rather than patches * len(text). This
# means rather than shuffling strings around, we shuffle around
# pointers to fragments with fragment lists.
#
# When the fragment lists get too long, we collapse them. To do this
# efficiently, we do all our operations inside a buffer created by
# mmap and simply use memmove. This avoids creating a bunch of large
# temporary string buffers.

def patches(a, bins):
    if not bins:
        return a

    plens = [len(x) for x in bins]
    pl = sum(plens)
    bl = len(a) + pl
    tl = bl + bl + pl # enough for the patches and two working texts
    b1, b2 = 0, bl

    if not tl:
        return a

    m = StringIO()
    def move(dest, src, count):
        """move count bytes from src to dest

        The file pointer is left at the end of dest.
        """
        m.seek(src)
        buf = m.read(count)
        m.seek(dest)
        m.write(buf)

    # load our original text
    m.write(a)
    frags = [(len(a), b1)]

    # copy all the patches into our segment so we can memmove from them
    pos = b2 + bl
    m.seek(pos)
    for p in bins: m.write(p)

    def pull(dst, src, l): # pull l bytes from src
        while l:
            f = src.pop()
            if f[0] > l: # do we need to split?
                src.append((f[0] - l, f[1] + l))
                dst.append((l, f[1]))
                return
            dst.append(f)
            l -= f[0]

    def collect(buf, list):
        start = buf
        for l, p in reversed(list):
            move(buf, p, l)
            buf += l
        return (buf - start, start)

    for plen in plens:
        # if our list gets too long, execute it
        if len(frags) > 128:
            b2, b1 = b1, b2
            frags = [collect(b1, frags)]

        new = []
        end = pos + plen
        last = 0
        while pos < end:
            m.seek(pos)
            p1, p2, l = struct.unpack(">lll", m.read(12))
            pull(new, frags, p1 - last) # what didn't change
            pull([], frags, p2 - p1)    # what got deleted
            new.append((l, pos + 12))   # what got added
            pos += l + 12
            last = p2
        frags.extend(reversed(new))     # what was left at the end

    t = collect(b2, frags)

    m.seek(t[1])
    return m.read(t[0])

def patchedsize(orig, delta):
    outlen, last, bin = 0, 0, 0
    binend = len(delta)
    data = 12

    while data <= binend:
        decode = delta[bin:bin + 12]
        start, end, length = struct.unpack(">lll", decode)
        if start > end:
            break
        bin = data + length
        data = bin + 12
        outlen += start - last
        last = end
        outlen += length

    if bin != binend:
        raise ValueError("patch cannot be decoded")

    outlen += orig - last
    return outlen