view mercurial/bdiff.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_BDIFF_H_
#define _HG_BDIFF_H_

#include "compat.h"

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);

#endif