revlog: break up compression of large deltas
Python's zlib apparently makes an internal copy of strings passed to
compress(). To avoid this, compress strings 1M at a time, then join
them at the end if the result would be smaller than the original.
For initial commits of large but compressible files, this cuts peak
memory usage nearly in half.
#!/usr/bin/env python
import sys
from mercurial import bdiff, mpatch
def test1(a, b):
d = bdiff.bdiff(a, b)
c = a
if d:
c = mpatch.patches(a, [d])
if c != b:
print "***", `a`, `b`
print "bad:"
print `c`[:200]
print `d`
def test(a, b):
print "***", `a`, `b`
test1(a, b)
test1(b, a)
test("a\nc\n\n\n\n", "a\nb\n\n\n")
test("a\nb\nc\n", "a\nc\n")
test("", "")
test("a\nb\nc", "a\nb\nc")
test("a\nb\nc\nd\n", "a\nd\n")
test("a\nb\nc\nd\n", "a\nc\ne\n")
test("a\nb\nc\n", "a\nc\n")
test("a\n", "c\na\nb\n")
test("a\n", "")
test("a\n", "b\nc\n")
test("a\n", "c\na\n")
test("", "adjfkjdjksdhfksj")
test("", "ab")
test("", "abc")
test("a", "a")
test("ab", "ab")
test("abc", "abc")
test("a\n", "a\n")
test("a\nb", "a\nb")
print "done"