Diff | Source/Git

Download diff

	4b825dc642cb6eb9a060e54bf8d69288fbee4904		cfad47cfa334b206c65f22086bcc5d63e6f70944
		1	#ifdef RCSID
		2	static char RCSid[] =
		3	"$Header: d:/cvsroot/tads/tads3/utf8.cpp,v 1.2 1999/05/17 02:52:29 MJRoberts Exp $";
		4	#endif
		5
		6	/*
		7	* Copyright (c) 1998, 2002 Michael J. Roberts. All Rights Reserved.
		8	*
		9	* Please see the accompanying license file, LICENSE.TXT, for information
		10	* on using and copying this software.
		11	*/
		12	/*
		13	Name
		14	utf8.cpp - UTF-8 implementation
		15	Function
		16
		17	Notes
		18
		19	Modified
		20	10/17/98 MJRoberts - Creation
		21	*/
		22
		23	#include "utf8.h"
		24
		25	/* ------------------------------------------------------------------------ */
		26	/*
		27	* encode a string of wide characters into the buffer
		28	*/
		29	size_t utf8_ptr::setwchars(const wchar_t *src, size_t src_count,
		30	size_t bufsiz)
		31	{
		32	size_t outbytes;
		33
		34	/* loop through the source and store the characters */
		35	for (outbytes = 0 ; src_count > 0 ; --src_count, ++src)
		36	{
		37	size_t curbytes;
		38
		39	/* figure out how many bytes we need for this character */
		40	curbytes = s_wchar_size(*src);
		41
		42	/* add it to the total output size */
		43	outbytes += curbytes;
		44
		45	/* if we have room, add it to the buffer */
		46	if (bufsiz >= curbytes)
		47	{
		48	/* store it */
		49	setch(*src);
		50
		51	/* deduct this space from the remaining buffer size */
		52	bufsiz -= outbytes;
		53	}
		54	else
		55	{
		56	/*
		57	* there's no room for this - make sure we don't store
		58	* anything more (since we might have room for a shorter
		59	* character later, but that would put a gap in the output
		60	* string - better to just truncate here)
		61	*/
		62	bufsiz = 0;
		63	}
		64	}
		65
		66	/* return the total output size used (or needed) */
		67	return outbytes;
		68	}
		69
		70	/* ------------------------------------------------------------------------ */
		71	/*
		72	* encode a null-terminated string of wide characters into the buffer
		73	*/
		74	size_t utf8_ptr::setwcharsz(const wchar_t *src, size_t bufsiz)
		75	{
		76	size_t outbytes;
		77
		78	/* loop through the source and store the characters */
		79	for (outbytes = 0 ; *src != 0 ; ++src)
		80	{
		81	size_t curbytes;
		82
		83	/* figure out how many bytes we need for this character */
		84	curbytes = s_wchar_size(*src);
		85
		86	/* add it to the total output size */
		87	outbytes += curbytes;
		88
		89	/* if we have room, add it to the buffer */
		90	if (bufsiz >= curbytes)
		91	{
		92	/* store it */
		93	setch(*src);
		94
		95	/* deduct this space from the remaining buffer size */
		96	bufsiz -= outbytes;
		97	}
		98	else
		99	{
		100	/*
		101	* there's no room for this - make sure we don't store
		102	* anything more (since we might have room for a shorter
		103	* character later, but that would put a gap in the output
		104	* string - better to just truncate here)
		105	*/
		106	bufsiz = 0;
		107	}
		108	}
		109
		110	/*
		111	* Add the null terminator, if there's room, but do not increment
		112	* our pointer - we want to leave our pointer pointing at the null
		113	* terminator. Include the null terminator's size (one byte) in the
		114	* result length (even if we don't have room to store it).
		115	*/
		116	++outbytes;
		117	if (bufsiz > 0)
		118	*p_ = '\0';
		119
		120	/* return the total output size used (or needed) */
		121	return outbytes;
		122	}
		123
		124	/* ------------------------------------------------------------------------ */
		125	/*
		126	* Compare this string to the given string
		127	*/
		128	int utf8_ptr::s_compare_to(const char *p1, size_t bytelen1,
		129	const char *p2, size_t bytelen2)
		130	{
		131	/* keep going until one or the other string runs out of bytes */
		132	while (bytelen1 != 0 && bytelen2 != 0)
		133	{
		134	wchar_t c1, c2;
		135	size_t siz1, siz2;
		136
		137	/* get the current character from each string */
		138	c1 = s_getch(p1);
		139	c2 = s_getch(p2);
		140
		141	/* compare them */
		142	if (c1 > c2)
		143	return 1;
		144	else if (c1 < c2)
		145	return -1;
		146
		147	/* get the size of each character */
		148	siz1 = s_charsize(*p1);
		149	siz2 = s_charsize(*p2);
		150
		151	/* decrement each counter by the byte size of this character */
		152	bytelen1 -= siz1;
		153	bytelen2 -= siz2;
		154
		155	/* advance to the next character in each string */
		156	p1 += siz1;
		157	p2 += siz2;
		158	}
		159
		160	/*
		161	* we didn't find any character differences, but one string is
		162	* longer than the other -- if they ran out at the same time,
		163	* they're identical; otherwise, the one that ran out first is the
		164	* lesser one
		165	*/
		166	if (bytelen2 != 0)
		167	{
		168	/* the first one ran out first, so the first one sorts earlier */
		169	return -1;
		170	}
		171	else if (bytelen1 != 0)
		172	{
		173	/* the second one ran out first, so the first one sort later */
		174	return 1;
		175	}
		176	else
		177	{
		178	/* they both ran out at the same time */
		179	return 0;
		180	}
		181	}
		182

FrobTADS

cfad47cfa3/tads3/utf8.cpp