setup_bdiff_cffi.py

bundle2: only emit compressed chunks if they have data

This is similar to 58467204cac0. Not all calls into the compressor
return compressed data, as the compressor may buffer compressed
output internally. It is cheaper to check for empty chunks than to
send empty chunks through the generator.

When generating a gzip-v2 bundle of the mozilla-unified repo, this
change results in 50,093 empty chunks not being sent through the
generator (out of 1,902,996 total input chunks).

from __future__ import absolute_import

import cffi
import os

ffi = cffi.FFI()
ffi.set_source("_bdiff_cffi",
    open(os.path.join(os.path.join(os.path.dirname(__file__), 'mercurial'),
        'bdiff.c')).read(), include_dirs=['mercurial'])
ffi.cdef("""
struct bdiff_line {
    int hash, n, e;
    ssize_t len;
    const char *l;
};

struct bdiff_hunk;
struct bdiff_hunk {
    int a1, a2, b1, b2;
    struct bdiff_hunk *next;
};

int bdiff_splitlines(const char *a, ssize_t len, struct bdiff_line **lr);
int bdiff_diff(struct bdiff_line *a, int an, struct bdiff_line *b, int bn,
    struct bdiff_hunk *base);
void bdiff_freehunks(struct bdiff_hunk *l);
void free(void*);
""")

if __name__ == '__main__':
    ffi.compile()