view mercurial/cext/charencode.h @ 45214:6063c1857d0a stable

exchange: backout changeset c26335fa4225

Changeset c26335fa4225 has good intends but introduce significant behavior
regressions for multiple important cases. In short there are many case where
push would have caught instability creation/propagation that are no longer
covered.  These behavior have been covered for many years and even if some
related case are not currently caught, the covered one should not be regressed.

The next four changesets introduce tests for some of these cases. However we
could produce many more tests cases since the area is wide and they are many
possible combination. (And we should cover them when getting back to this issue)

Since 5.5 is one week away, the most reasonable approach seems to back this out
while we devise a new way to move forward that preserve the current behavior,
catch more issues and also improves the situation that c26335fa4225 target.


In addition to the behavior change, c26335fa4225 also introduced output
changes. These output changes does not requires a backout per-se, but are part of
the same changeset. However they come with a couple of issues that also requires
attention:

1) the bulk of the error message have been shoehorned into a multiple line abort
message. This seems quite different from what we usually do. The abort message
should be a compact and efficient message, with extra details being issued as
normal error output beforehand. (with --verbose/--quiet) support.

2) the current output is unbounded, so if there is many (tens, hundreds,
thousands, …) of unstable/obsolete changeset involved in the push, the output
can quickly become a scary and un-usuable wall of text. So we need some
limitation here (same as we have with the remote head list that says A, B , C
and # others).

/*
 charencode.h - miscellaneous character encoding

 This software may be used and distributed according to the terms of
 the GNU General Public License, incorporated herein by reference.
*/

#ifndef _HG_CHARENCODE_H_
#define _HG_CHARENCODE_H_

#include <Python.h>
#include "compat.h"

/* This should be kept in sync with normcasespecs in encoding.py. */
enum normcase_spec {
	NORMCASE_LOWER = -1,
	NORMCASE_UPPER = 1,
	NORMCASE_OTHER = 0
};

PyObject *unhexlify(const char *str, Py_ssize_t len);
PyObject *isasciistr(PyObject *self, PyObject *args);
PyObject *asciilower(PyObject *self, PyObject *args);
PyObject *asciiupper(PyObject *self, PyObject *args);
PyObject *make_file_foldmap(PyObject *self, PyObject *args);
PyObject *jsonescapeu8fast(PyObject *self, PyObject *args);

/* clang-format off */
static const int8_t hextable[256] = {
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, /* 0-9 */
	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* A-F */
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* a-f */
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
/* clang-format on */

static inline int hexdigit(const char *p, Py_ssize_t off)
{
	int8_t val = hextable[(unsigned char)p[off]];

	if (val >= 0) {
		return val;
	}

	PyErr_SetString(PyExc_ValueError, "input contains non-hex character");
	return 0;
}

#endif /* _HG_CHARENCODE_H_ */