add hg and python

sys/lib/python/mercurial/pure/base85.py

@@ -0,0 +1,74 @@
+# base85.py: pure python base85 codec
+#
+# Copyright (C) 2009 Brendan Cully <brendan@kublai.com>
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2, incorporated herein by reference.
+
+import struct
+
+_b85chars = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ" \
+            "abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~"
+_b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]
+_b85dec = {}
+
+def _mkb85dec():
+    for i, c in enumerate(_b85chars):
+        _b85dec[c] = i
+
+def b85encode(text, pad=False):
+    """encode text in base85 format"""
+    l = len(text)
+    r = l % 4
+    if r:
+        text += '\0' * (4 - r)
+    longs = len(text) >> 2
+    words = struct.unpack('>%dL' % (longs), text)
+
+    out = ''.join(_b85chars[(word // 52200625) % 85] +
+                  _b85chars2[(word // 7225) % 7225] +
+                  _b85chars2[word % 7225]
+                  for word in words)
+
+    if pad:
+        return out
+
+    # Trim padding
+    olen = l % 4
+    if olen:
+        olen += 1
+    olen += l // 4 * 5
+    return out[:olen]
+
+def b85decode(text):
+    """decode base85-encoded text"""
+    if not _b85dec:
+        _mkb85dec()
+
+    l = len(text)
+    out = []
+    for i in range(0, len(text), 5):
+        chunk = text[i:i+5]
+        acc = 0
+        for j, c in enumerate(chunk):
+            try:
+                acc = acc * 85 + _b85dec[c]
+            except KeyError:
+                raise TypeError('Bad base85 character at byte %d' % (i + j))
+        if acc > 4294967295:
+            raise OverflowError('Base85 overflow in hunk starting at byte %d' % i)
+        out.append(acc)
+
+    # Pad final chunk if necessary
+    cl = l % 5
+    if cl:
+        acc *= 85 ** (5 - cl)
+        if cl > 1:
+            acc += 0xffffff >> (cl - 2) * 8
+        out[-1] = acc
+
+    out = struct.pack('>%dL' % (len(out)), *out)
+    if cl:
+        out = out[:-(5 - cl)]
+
+    return out

sys/lib/python/mercurial/pure/bdiff.py

@@ -0,0 +1,76 @@
+# bdiff.py - Python implementation of bdiff.c
+#
+# Copyright 2009 Matt Mackall <mpm@selenic.com> and others
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2, incorporated herein by reference.
+
+import struct, difflib
+
+def splitnewlines(text):
+    '''like str.splitlines, but only split on newlines.'''
+    lines = [l + '\n' for l in text.split('\n')]
+    if lines:
+        if lines[-1] == '\n':
+            lines.pop()
+        else:
+            lines[-1] = lines[-1][:-1]
+    return lines
+
+def _normalizeblocks(a, b, blocks):
+    prev = None
+    for curr in blocks:
+        if prev is None:
+            prev = curr
+            continue
+        shift = 0
+
+        a1, b1, l1 = prev
+        a1end = a1 + l1
+        b1end = b1 + l1
+
+        a2, b2, l2 = curr
+        a2end = a2 + l2
+        b2end = b2 + l2
+        if a1end == a2:
+            while a1end+shift < a2end and a[a1end+shift] == b[b1end+shift]:
+                shift += 1
+        elif b1end == b2:
+            while b1end+shift < b2end and a[a1end+shift] == b[b1end+shift]:
+                shift += 1
+        yield a1, b1, l1+shift
+        prev = a2+shift, b2+shift, l2-shift
+    yield prev
+
+def bdiff(a, b):
+    a = str(a).splitlines(True)
+    b = str(b).splitlines(True)
+
+    if not a:
+        s = "".join(b)
+        return s and (struct.pack(">lll", 0, 0, len(s)) + s)
+
+    bin = []
+    p = [0]
+    for i in a: p.append(p[-1] + len(i))
+
+    d = difflib.SequenceMatcher(None, a, b).get_matching_blocks()
+    d = _normalizeblocks(a, b, d)
+    la = 0
+    lb = 0
+    for am, bm, size in d:
+        s = "".join(b[lb:bm])
+        if am > la or s:
+            bin.append(struct.pack(">lll", p[la], p[am], len(s)) + s)
+        la = am + size
+        lb = bm + size
+
+    return "".join(bin)
+
+def blocks(a, b):
+    an = splitnewlines(a)
+    bn = splitnewlines(b)
+    d = difflib.SequenceMatcher(None, an, bn).get_matching_blocks()
+    d = _normalizeblocks(an, bn, d)
+    return [(i, i + n, j, j + n) for (i, j, n) in d]
+

sys/lib/python/mercurial/pure/diffhelpers.py

@@ -0,0 +1,56 @@
+# diffhelpers.py - pure Python implementation of diffhelpers.c
+#
+# Copyright 2009 Matt Mackall <mpm@selenic.com> and others
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2, incorporated herein by reference.
+
+def addlines(fp, hunk, lena, lenb, a, b):
+    while True:
+        todoa = lena - len(a)
+        todob = lenb - len(b)
+        num = max(todoa, todob)
+        if num == 0:
+            break
+        for i in xrange(num):
+            s = fp.readline()
+            c = s[0]
+            if s == "\\ No newline at end of file\n":
+                fix_newline(hunk, a, b)
+                continue
+            if c == "\n":
+                # Some patches may be missing the control char
+                # on empty lines. Supply a leading space.
+                s = " \n"
+            hunk.append(s)
+            if c == "+":
+                b.append(s[1:])
+            elif c == "-":
+                a.append(s)
+            else:
+                b.append(s[1:])
+                a.append(s)
+    return 0
+
+def fix_newline(hunk, a, b):
+    l = hunk[-1]
+    c = l[0]
+    hline = l[:-1]
+
+    if c == " " or c == "+":
+        b[-1] = l[1:-1]
+    if c == " " or c == "-":
+        a[-1] = hline
+    hunk[-1] = hline
+    return 0
+
+
+def testhunk(a, b, bstart):
+    alen = len(a)
+    blen = len(b)
+    if alen > blen - bstart:
+        return -1
+    for i in xrange(alen):
+        if a[i][1:] != b[i + bstart]:
+            return -1
+    return 0

sys/lib/python/mercurial/pure/mpatch.py

@@ -0,0 +1,116 @@
+# mpatch.py - Python implementation of mpatch.c
+#
+# Copyright 2009 Matt Mackall <mpm@selenic.com> and others
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2, incorporated herein by reference.
+
+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(0)
+            if f[0] > l: # do we need to split?
+                src.insert(0, (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 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 = new + frags                    # 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 Exception("patch cannot be decoded")
+
+    outlen += orig - last
+    return outlen

sys/lib/python/mercurial/pure/osutil.py

@@ -0,0 +1,52 @@
+# osutil.py - pure Python version of osutil.c
+#
+#  Copyright 2009 Matt Mackall <mpm@selenic.com> and others
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2, incorporated herein by reference.
+
+import os
+import stat as _stat
+
+posixfile = open
+
+def _mode_to_kind(mode):
+    if _stat.S_ISREG(mode): return _stat.S_IFREG
+    if _stat.S_ISDIR(mode): return _stat.S_IFDIR
+    if _stat.S_ISLNK(mode): return _stat.S_IFLNK
+    if _stat.S_ISBLK(mode): return _stat.S_IFBLK
+    if _stat.S_ISCHR(mode): return _stat.S_IFCHR
+    if _stat.S_ISFIFO(mode): return _stat.S_IFIFO
+    if _stat.S_ISSOCK(mode): return _stat.S_IFSOCK
+    return mode
+
+def listdir(path, stat=False, skip=None):
+    '''listdir(path, stat=False) -> list_of_tuples
+
+    Return a sorted list containing information about the entries
+    in the directory.
+
+    If stat is True, each element is a 3-tuple:
+
+      (name, type, stat object)
+
+    Otherwise, each element is a 2-tuple:
+
+      (name, type)
+    '''
+    result = []
+    prefix = path
+    if not prefix.endswith(os.sep):
+        prefix += os.sep
+    names = os.listdir(path)
+    names.sort()
+    for fn in names:
+        st = os.lstat(prefix + fn)
+        if fn == skip and _stat.S_ISDIR(st.st_mode):
+            return []
+        if stat:
+            result.append((fn, _mode_to_kind(st.st_mode), st))
+        else:
+            result.append((fn, _mode_to_kind(st.st_mode)))
+    return result
+

sys/lib/python/mercurial/pure/parsers.py

@@ -0,0 +1,90 @@
+# parsers.py - Python implementation of parsers.c
+#
+# Copyright 2009 Matt Mackall <mpm@selenic.com> and others
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2, incorporated herein by reference.
+
+from mercurial.node import bin, nullid, nullrev
+from mercurial import util
+import struct, zlib
+
+_pack = struct.pack
+_unpack = struct.unpack
+_compress = zlib.compress
+_decompress = zlib.decompress
+_sha = util.sha1
+
+def parse_manifest(mfdict, fdict, lines):
+    for l in lines.splitlines():
+        f, n = l.split('\0')
+        if len(n) > 40:
+            fdict[f] = n[40:]
+            mfdict[f] = bin(n[:40])
+        else:
+            mfdict[f] = bin(n)
+
+def parse_index(data, inline):
+    def gettype(q):
+        return int(q & 0xFFFF)
+
+    def offset_type(offset, type):
+        return long(long(offset) << 16 | type)
+
+    indexformatng = ">Qiiiiii20s12x"
+
+    s = struct.calcsize(indexformatng)
+    index = []
+    cache = None
+    nodemap = {nullid: nullrev}
+    n = off = 0
+    # if we're not using lazymap, always read the whole index
+    l = len(data) - s
+    append = index.append
+    if inline:
+        cache = (0, data)
+        while off <= l:
+            e = _unpack(indexformatng, data[off:off + s])
+            nodemap[e[7]] = n
+            append(e)
+            n += 1
+            if e[1] < 0:
+                break
+            off += e[1] + s
+    else:
+        while off <= l:
+            e = _unpack(indexformatng, data[off:off + s])
+            nodemap[e[7]] = n
+            append(e)
+            n += 1
+            off += s
+
+    e = list(index[0])
+    type = gettype(e[0])
+    e[0] = offset_type(0, type)
+    index[0] = tuple(e)
+
+    # add the magic null revision at -1
+    index.append((0, 0, 0, -1, -1, -1, -1, nullid))
+
+    return index, nodemap, cache
+
+def parse_dirstate(dmap, copymap, st):
+    parents = [st[:20], st[20: 40]]
+    # deref 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