view mercurial/mpatch.h @ 37947:3ea3c96ada54

encoding: introduce tagging type for non-lossy non-ASCII string

This fixes the weird behavior of toutf8b(), which would convert a local
string back to UTF-8 *only if* it was lossy in the system encoding.

Before b7b26e54e37a "encoding: avoid localstr when a string can be encoded
losslessly (issue2763)", all local strings were wrapped by the localstr
class. I think this would justify the round-trip behavior of toutf8b().

ASCII strings are special-cased, so the cost of wrapping with safelocalstr
is negligible.

  (with mercurial repo)
  $ export HGRCPATH=/dev/null HGPLAIN= HGENCODING=latin-1
  $ hg log --time --config experimental.evolution=all > /dev/null

  (original)
  time: real 11.340 secs (user 11.290+0.000 sys 0.060+0.000)
  time: real 11.390 secs (user 11.300+0.000 sys 0.080+0.000)
  time: real 11.430 secs (user 11.360+0.000 sys 0.070+0.000)

  (this patch)
  time: real 11.200 secs (user 11.100+0.000 sys 0.100+0.000)
  time: real 11.370 secs (user 11.300+0.000 sys 0.070+0.000)
  time: real 11.190 secs (user 11.130+0.000 sys 0.060+0.000)

#ifndef _HG_MPATCH_H_
#define _HG_MPATCH_H_

#define MPATCH_ERR_NO_MEM -3
#define MPATCH_ERR_CANNOT_BE_DECODED -2
#define MPATCH_ERR_INVALID_PATCH -1

struct mpatch_frag {
	int start, end, len;
	const char *data;
};

struct mpatch_flist {
	struct mpatch_frag *base, *head, *tail;
};

int mpatch_decode(const char *bin, ssize_t len, struct mpatch_flist **res);
ssize_t mpatch_calcsize(ssize_t len, struct mpatch_flist *l);
void mpatch_lfree(struct mpatch_flist *a);
int mpatch_apply(char *buf, const char *orig, ssize_t len,
                 struct mpatch_flist *l);
struct mpatch_flist *
mpatch_fold(void *bins, struct mpatch_flist *(*get_next_item)(void *, ssize_t),
            ssize_t start, ssize_t end);

#endif