[BACK]Return to unicode.h CVS log [TXT][DIR] Up to [cvs.NetBSD.org] / src / sys / fs

File: [cvs.NetBSD.org] / src / sys / fs / unicode.h (download)

Revision 1.7, Sun Apr 6 19:25:22 2014 UTC (9 years, 11 months ago) by jakllsch
Branch: MAIN
CVS Tags: yamt-pagecache-base9, tls-maxphys-base-20171202, tls-maxphys-base, tls-earlyentropy-base, thorpej-ifq-base, thorpej-ifq, thorpej-i2c-spi-conf2-base, thorpej-i2c-spi-conf2, thorpej-i2c-spi-conf-base, thorpej-i2c-spi-conf, thorpej-futex2-base, thorpej-futex2, thorpej-futex-base, thorpej-futex, thorpej-cfargs2-base, thorpej-cfargs2, thorpej-cfargs-base, thorpej-cfargs, thorpej-altq-separation-base, thorpej-altq-separation, rmind-smpnet-nbase, rmind-smpnet-base, prg-localcount2-base3, prg-localcount2-base2, prg-localcount2-base1, prg-localcount2-base, prg-localcount2, phil-wifi-base, phil-wifi-20200421, phil-wifi-20200411, phil-wifi-20200406, phil-wifi-20191119, phil-wifi-20190609, phil-wifi, pgoyette-localcount-base, pgoyette-localcount-20170426, pgoyette-localcount-20170320, pgoyette-localcount-20170107, pgoyette-localcount-20161104, pgoyette-localcount-20160806, pgoyette-localcount-20160726, pgoyette-localcount, pgoyette-compat-merge-20190127, pgoyette-compat-base, pgoyette-compat-20190127, pgoyette-compat-20190118, pgoyette-compat-1226, pgoyette-compat-1126, pgoyette-compat-1020, pgoyette-compat-0930, pgoyette-compat-0906, pgoyette-compat-0728, pgoyette-compat-0625, pgoyette-compat-0521, pgoyette-compat-0502, pgoyette-compat-0422, pgoyette-compat-0415, pgoyette-compat-0407, pgoyette-compat-0330, pgoyette-compat-0322, pgoyette-compat-0315, pgoyette-compat, perseant-stdc-iso10646-base, perseant-stdc-iso10646, nick-nhusb-base-20170825, nick-nhusb-base-20170204, nick-nhusb-base-20161204, nick-nhusb-base-20161004, nick-nhusb-base-20160907, nick-nhusb-base-20160529, nick-nhusb-base-20160422, nick-nhusb-base-20160319, nick-nhusb-base-20151226, nick-nhusb-base-20150921, nick-nhusb-base-20150606, nick-nhusb-base-20150406, nick-nhusb-base, nick-nhusb, netbsd-9-base, netbsd-9-3-RELEASE, netbsd-9-2-RELEASE, netbsd-9-1-RELEASE, netbsd-9-0-RELEASE, netbsd-9-0-RC2, netbsd-9-0-RC1, netbsd-9, netbsd-8-base, netbsd-8-2-RELEASE, netbsd-8-1-RELEASE, netbsd-8-1-RC1, netbsd-8-0-RELEASE, netbsd-8-0-RC2, netbsd-8-0-RC1, netbsd-8, netbsd-7-nhusb-base-20170116, netbsd-7-nhusb-base, netbsd-7-nhusb, netbsd-7-base, netbsd-7-2-RELEASE, netbsd-7-1-RELEASE, netbsd-7-1-RC2, netbsd-7-1-RC1, netbsd-7-1-2-RELEASE, netbsd-7-1-1-RELEASE, netbsd-7-1, netbsd-7-0-RELEASE, netbsd-7-0-RC3, netbsd-7-0-RC2, netbsd-7-0-RC1, netbsd-7-0-2-RELEASE, netbsd-7-0-1-RELEASE, netbsd-7-0, netbsd-7, netbsd-10-base, netbsd-10-0-RELEASE, netbsd-10-0-RC6, netbsd-10-0-RC5, netbsd-10-0-RC4, netbsd-10-0-RC3, netbsd-10-0-RC2, netbsd-10-0-RC1, netbsd-10, matt-nb8-mediatek-base, matt-nb8-mediatek, localcount-20160914, jdolecek-ncq-base, jdolecek-ncq, isaki-audio2-base, isaki-audio2, is-mlppp-base, is-mlppp, cjep_sun2x-base1, cjep_sun2x-base, cjep_sun2x, cjep_staticlib_x-base1, cjep_staticlib_x-base, cjep_staticlib_x, bouyer-xenpvh-base2, bouyer-xenpvh-base1, bouyer-xenpvh-base, bouyer-xenpvh, bouyer-sunxi-drm-base, bouyer-sunxi-drm, bouyer-socketcan-base1, bouyer-socketcan-base, bouyer-socketcan, ad-namecache-base3, ad-namecache-base2, ad-namecache-base1, ad-namecache-base, ad-namecache, HEAD
Changes since 1.6: +2 -2 lines

Use size_t instead of int for character count to avoid sign compare issues.

/* $NetBSD: unicode.h,v 1.7 2014/04/06 19:25:22 jakllsch Exp $ */

/*-
 * Copyright (c) 2001, 2004 The NetBSD Foundation, Inc.
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

/*-
 * Copyright (c) 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * Paul Borman at Krystal Technologies.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */

/*
 * Routines for handling Unicode encoded in UTF-8 form, code derived from
 * src/lib/libc/locale/utf2.c.
 */
static u_int16_t wget_utf8(const char **, size_t *) __unused;
static int wput_utf8(char *, size_t, u_int16_t) __unused;

/*
 * Read one UTF8-encoded character off the string, shift the string pointer
 * and return the character.
 */
static u_int16_t
wget_utf8(const char **str, size_t *sz)
{
	size_t c;
	u_int16_t rune = 0;
	const char *s = *str;
	static const int _utf_count[16] = {
		1, 1, 1, 1, 1, 1, 1, 1,
		0, 0, 0, 0, 2, 2, 3, 0,
	};

	/* must be called with at least one byte remaining */
	KASSERT(*sz > 0);

	c = _utf_count[(s[0] & 0xf0) >> 4];
	if (c == 0 || c > *sz) {
    decoding_error:
		/*
		 * The first character is in range 128-255 and doesn't
		 * mark valid a valid UTF-8 sequence. There is not much
		 * we can do with this, so handle by returning
		 * the first character as if it would be a correctly
		 * encoded ISO-8859-1 character.
		 */
		c = 1;
	}

	switch (c) {
	case 1:
		rune = s[0] & 0xff;
		break;
	case 2:
		if ((s[1] & 0xc0) != 0x80)
			goto decoding_error;
		rune = ((s[0] & 0x1F) << 6) | (s[1] & 0x3F);
		break;
	case 3:
		if ((s[1] & 0xC0) != 0x80 || (s[2] & 0xC0) != 0x80)
			goto decoding_error;
		rune = ((s[0] & 0x0F) << 12) | ((s[1] & 0x3F) << 6)
		    | (s[2] & 0x3F);
		break;
	}

	*str += c;
	*sz -= c;
	return rune;
}

/*
 * Encode wide character and write it to the string. 'n' specifies
 * how much buffer space remains in 's'. Returns number of bytes written
 * to the target string 's'.
 */
static int
wput_utf8(char *s, size_t n, u_int16_t wc)
{
	if (wc & 0xf800) {
		if (n < 3) {
			/* bound check failure */
			return 0;
		}

		s[0] = 0xE0 | (wc >> 12);
		s[1] = 0x80 | ((wc >> 6) & 0x3F);
		s[2] = 0x80 | ((wc) & 0x3F);
		return 3;
	} else if (wc & 0x0780) {
		if (n < 2) {
			/* bound check failure */
			return 0;
		}

		s[0] = 0xC0 | (wc >> 6);
		s[1] = 0x80 | ((wc) & 0x3F);
		return 2;
	} else {
		if (n < 1) {
			/* bound check failure */
			return 0;
		}

		s[0] = wc;
		return 1;
	}
}