/*
 * unistr.c - Unicode string handling. Part of the Linux-NTFS project.
 *
 * Copyright (c) 2000,2001 Anton Altaparmakov.
 *
 * This program/include file is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as published
 * by the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program/include file is distributed in the hope that it will be 
 * useful, but WITHOUT ANY WARRANTY; without even the implied warranty 
 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program (in the main directory of the Linux-NTFS 
 * distribution in the file COPYING); if not, write to the Free Software
 * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include <linux/string.h>
#include <asm/byteorder.h>

#include "unistr.h"
#include "macros.h"

/*
 * This is used by the name collation functions to quickly determine what
 * characters are (in)valid.
 */
const __u8 legal_ansi_char_array[0x40] = {
	0x00, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,

	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,

	0x17, 0x07, 0x18, 0x17, 0x17, 0x17, 0x17, 0x17,
	0x17, 0x17, 0x18, 0x16, 0x16, 0x17, 0x07, 0x00,

	0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17,
	0x17, 0x17, 0x04, 0x16, 0x18, 0x16, 0x18, 0x18,
};

/**
 * ntfs_are_names_equal - compare two Unicode names for equality
 * @s1:			name to compare to @s2
 * @s1_len:		length in Unicode characters of @s1
 * @s2:			name to compare to @s1
 * @s2_len:		length in Unicode characters of @s2
 * @ic:			ignore case bool
 * @upcase:		upcase table (only if @ic == IGNORE_CASE)
 * @upcase_size:	length in Unicode characters of @upcase (if present)
 *
 * Compare the names @s1 and @s2 and return TRUE (1) if the names are
 * identical, or FALSE (0) if they are not identical. If @ic is IGNORE_CASE,
 * the @upcase table is used to performa a case insensitive comparison.
 */
int ntfs_are_names_equal(wchar_t *s1, size_t s1_len,
		     wchar_t *s2, size_t s2_len, int ic,
		     wchar_t *upcase, __u32 upcase_size)
{
	if (s1_len != s2_len)
		return 0;
	if (!ic)
		return memcmp(s1, s2, s1_len << 1) ? 0: 1;
	return ntfs_wcsncasecmp(s1, s2, s1_len, upcase, upcase_size) ? 0: 1;
}

/**
 * ntfs_collate_names - collate two Unicode names
 * @upcase:	upcase table (ignored if @ic is CASE_SENSITIVE)
 * @upcase_len:	upcase table size (ignored if @ic is CASE_SENSITIVE)
 * @name1:	first Unicode name to compare
 * @name2:	second Unicode name to compare
 * @ic:         either CASE_SENSITIVE or IGNORE_CASE
 * @err_val:	if @name1 contains an invalid character return this value
 *
 * ntfs_collate_names collates two Unicode names and returns:
 * 
 *  -1 if the first name collates before the second one,
 *   0 if the names match,
 *   1 if the second name collates before the first one, or
 * @ec if an invalid character is encountered in @name1 during the comparison.
 *
 * The following characters are considered invalid: '"', '*', '<', '>' and '?'.
 */
int ntfs_collate_names(wchar_t *upcase, __u32 upcase_len,
		       wchar_t *name1, __u32 name1_len,
		       wchar_t *name2, __u32 name2_len,
		       int ic, int err_val)
{
	__u32 cnt, min_len;
	wchar_t c1, c2;

	min_len = name1_len;
	if (min_len > name2_len)
		min_len = name2_len;
	for (cnt = 0; cnt < min_len; ++cnt) {
		c1 = le16_to_cpu(*name1++);
		c2 = le16_to_cpu(*name2++);
		if (ic) {
			if (c1 < upcase_len)
				c1 = le16_to_cpu(upcase[c1]);
			if (c2 < upcase_len)
				c2 = le16_to_cpu(upcase[c2]);
		}
		if (c1 < 64 && legal_ansi_char_array[c1] & 8)
			return err_val;
		if (c1 < c2)
			return -1;
		if (c1 > c2)
			return 1;
		++name1;
		++name2;
	}
	if (name1_len < name2_len)
		return -1;
	if (name1_len == name2_len)
		return 0;
	/* name1_len > name2_len */
	c1 = le16_to_cpu(*name1);
	if (c1 < 64 && legal_ansi_char_array[c1] & 8)
		return err_val;
	return 1;
}

/**
 * ntfs_wcsncasecmp - compare two little endian Unicode strings, ignoring case
 * @s1:			first string
 * @s2:			second string
 * @n:			maximum unicode characters to compare
 * @upcase:		upcase table
 * @upcase_size:	upcase table size in Unicode characters
 *
 * Compare the first @n characters of the Unicode strings @s1 and @s2,
 * ignoring case. The strings in little endian format and appropriate
 * le16_to_cpu() conversion is performed on non-little endian machines.
 * 
 * Each character is uppercased using the @upcase table before the comparison.
 *
 * The function returns an integer less than, equal to, or greater than zero
 * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
 * to be less than, to match, or be greater than @s2.
 */
int ntfs_wcsncasecmp(wchar_t *s1, wchar_t *s2, size_t n,
		     wchar_t *upcase, __u32 upcase_size)
{
	wchar_t c1, c2;
	size_t i;

	for (i = 0; i < n; ++i) {
		if ((c1 = le16_to_cpu(s1[i])) < upcase_size)
			c1 = le16_to_cpu(upcase[c1]);
		if ((c2 = le16_to_cpu(s2[i])) < upcase_size)
			c2 = le16_to_cpu(upcase[c2]);
		if (c1 < c2)
			return -1;
		if (c1 > c2)
			return 1;
		if (!c1)
			break;
	}
	return 0;
}