mercurial/cext/charencode.h

copies: choose target directory based on longest match

If one side of a merge renames `dir1/` to `dir2/` and the subdirectory
`dir1/subdir1/` to `dir2/subdir2/`, and the other side of the merge
adds a file in `dir1/subdir1/`, we should clearly move that into
`dir2/subdir2/`. We already detect the directories correctly before
this patch, but we iterate over them in arbitrary order. That results
in the new file sometimes ending up in `dir2/subdir1/` instead. This
patch fixes it by iterating over the source directories by visiting
subdirectories first. That's achieved by simply iterating over them in
reverse lexicographical order.

Without the fix, the test case still passes on Python 2 but fails on
Python 3. It depends on the iteration order of the dict. I did not
look into how it's built up and why it behaved differently before the
fix. I could probably have gotten it to fail on Python 2 as well by
choosing different directory names.

Differential Revision: https://phab.mercurial-scm.org/D10115

/*
 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_ */