Use fontconfig utf8 functions

1 files changed, 20 insertions, 134 deletions

diff --git a/st.c b/st.c
index ed2f887..2ad5942 100644
--- a/st.c
+++ b/st.c
@@ -140,11 +140,6 @@ enum selection_type {
 	SEL_RECTANGULAR = 2
 };
 
-/* bit macro */
-#undef B0
-enum { B0 = 1, B1 = 2, B2 = 4, B3 = 8, B4 = 16, B5 = 32, B6 = 64, B7 = 128
-};
-
 typedef unsigned char uchar;
 typedef unsigned int uint;
 typedef unsigned long ulong;
@@ -440,126 +435,10 @@ static void *xcalloc(size_t nmemb, size_t size)
 	return p;
 }
 
-static int utf8decode(char *s, long *u)
-{
-	uchar c;
-	int i, n, rtn;
-
-	rtn = 1;
-	c = *s;
-	if (~c & B7) {		/* 0xxxxxxx */
-		*u = c;
-		return rtn;
-	} else if ((c & (B7 | B6 | B5)) == (B7 | B6)) {	/* 110xxxxx */
-		*u = c & (B4 | B3 | B2 | B1 | B0);
-		n = 1;
-	} else if ((c & (B7 | B6 | B5 | B4)) == (B7 | B6 | B5)) {	/* 1110xxxx */
-		*u = c & (B3 | B2 | B1 | B0);
-		n = 2;
-	} else if ((c & (B7 | B6 | B5 | B4 | B3)) == (B7 | B6 | B5 | B4)) {	/* 11110xxx */
-		*u = c & (B2 | B1 | B0);
-		n = 3;
-	} else {
-		goto invalid;
-	}
-
-	for (i = n, ++s; i > 0; --i, ++rtn, ++s) {
-		c = *s;
-		if ((c & (B7 | B6)) != B7)	/* 10xxxxxx */
-			goto invalid;
-		*u <<= 6;
-		*u |= c & (B5 | B4 | B3 | B2 | B1 | B0);
-	}
-
-	if ((n == 1 && *u < 0x80) ||
-	    (n == 2 && *u < 0x800) ||
-	    (n == 3 && *u < 0x10000) || (*u >= 0xD800 && *u <= 0xDFFF)) {
-		goto invalid;
-	}
-
-	return rtn;
-      invalid:
-	*u = 0xFFFD;
-
-	return rtn;
-}
-
-static int utf8encode(long *u, char *s)
-{
-	uchar *sp;
-	ulong uc;
-	int i, n;
-
-	sp = (uchar *) s;
-	uc = *u;
-	if (uc < 0x80) {
-		*sp = uc;	/* 0xxxxxxx */
-		return 1;
-	} else if (*u < 0x800) {
-		*sp = (uc >> 6) | (B7 | B6);	/* 110xxxxx */
-		n = 1;
-	} else if (uc < 0x10000) {
-		*sp = (uc >> 12) | (B7 | B6 | B5);	/* 1110xxxx */
-		n = 2;
-	} else if (uc <= 0x10FFFF) {
-		*sp = (uc >> 18) | (B7 | B6 | B5 | B4);	/* 11110xxx */
-		n = 3;
-	} else {
-		goto invalid;
-	}
-
-	for (i = n, ++sp; i > 0; --i, ++sp)
-		*sp = ((uc >> 6 * (i - 1)) & (B5 | B4 | B3 | B2 | B1 | B0)) | B7;	/* 10xxxxxx */
-
-	return n + 1;
-      invalid:
-	/* U+FFFD */
-	*s++ = '\xEF';
-	*s++ = '\xBF';
-	*s = '\xBD';
-
-	return 3;
-}
-
-/* use this if your buffer is less than UTF_SIZ, it returns 1 if you can decode
-   UTF-8 otherwise return 0 */
-static int isfullutf8(char *s, int b)
-{
-	uchar *c1, *c2, *c3;
-
-	c1 = (uchar *) s;
-	c2 = (uchar *)++ s;
-	c3 = (uchar *)++ s;
-	if (b < 1) {
-		return 0;
-	} else if ((*c1 & (B7 | B6 | B5)) == (B7 | B6) && b == 1) {
-		return 0;
-	} else if ((*c1 & (B7 | B6 | B5 | B4)) == (B7 | B6 | B5) &&
-		   ((b == 1) || ((b == 2) && (*c2 & (B7 | B6)) == B7))) {
-		return 0;
-	} else if ((*c1 & (B7 | B6 | B5 | B4 | B3)) == (B7 | B6 | B5 | B4)
-		   && ((b == 1) || ((b == 2) && (*c2 & (B7 | B6)) == B7)
-		       || ((b == 3) && (*c2 & (B7 | B6)) == B7
-			   && (*c3 & (B7 | B6)) == B7))) {
-		return 0;
-	} else {
-		return 1;
-	}
-}
-
 static int utf8size(char *s)
 {
-	uchar c = *s;
-
-	if (~c & B7) {
-		return 1;
-	} else if ((c & (B7 | B6 | B5)) == (B7 | B6)) {
-		return 2;
-	} else if ((c & (B7 | B6 | B5 | B4)) == (B7 | B6 | B5)) {
-		return 3;
-	} else {
-		return 4;
-	}
+	unsigned ucs;
+	return FcUtf8ToUcs4((unsigned char *) s, &ucs, UTF_SIZ);
 }
 
 static ushort sixd_to_16bit(int x)
@@ -896,7 +775,7 @@ void xdraws(char *s, Glyph base, int x, int y, int charlen, int bytelen)
 	int frp, frcflags;
 	int u8fl, u8fblen, u8cblen, doesexist;
 	char *u8c, *u8fs;
-	long u8char;
+	unsigned u8char;
 	Font *font = &dc.font;
 	FcResult fcres;
 	FcPattern *fcpattern, *fontpattern;
@@ -1000,7 +879,8 @@ void xdraws(char *s, Glyph base, int x, int y, int charlen, int bytelen)
 		u8fl = 0;
 		for (;;) {
 			u8c = s;
-			u8cblen = utf8decode(s, &u8char);
+			u8cblen = FcUtf8ToUcs4((unsigned char *) s,
+					       &u8char, UTF_SIZ);
 			s += u8cblen;
 			bytelen -= u8cblen;
 
@@ -2395,12 +2275,9 @@ static void kpress(XEvent *ev)
 
 static void ttyread(void)
 {
-	static char buf[BUFSIZ];
+	static unsigned char buf[BUFSIZ];
 	static int buflen = 0;
-	char *ptr;
-	char s[UTF_SIZ];
-	int charsize;		/* size of utf8 char in bytes */
-	long utf8c;
+	unsigned char *ptr;
 	int ret;
 
 	/* append read bytes to unprocessed bytes */
@@ -2410,10 +2287,19 @@ static void ttyread(void)
 	/* process every complete utf8 char */
 	buflen += ret;
 	ptr = buf;
-	while (buflen >= UTF_SIZ || isfullutf8(ptr, buflen)) {
-		charsize = utf8decode(ptr, &utf8c);
-		utf8encode(&utf8c, s);
-		tputc(s, charsize);
+
+	while (buflen) {
+		unsigned ucs;
+		int charsize = FcUtf8ToUcs4(ptr, &ucs, buflen);
+		if (charsize < 0) {
+			charsize = 1;
+			ucs = *ptr;
+		}
+
+		if (charsize > buflen)
+			break;
+
+		tputc((char *) ptr, charsize);
 		ptr += charsize;
 		buflen -= charsize;
 	}