summaryrefslogtreecommitdiff
path: root/src/xutf8/utf8Utils.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/xutf8/utf8Utils.c')
-rw-r--r--src/xutf8/utf8Utils.c227
1 files changed, 111 insertions, 116 deletions
diff --git a/src/xutf8/utf8Utils.c b/src/xutf8/utf8Utils.c
index ad2bc83ff..846846c93 100644
--- a/src/xutf8/utf8Utils.c
+++ b/src/xutf8/utf8Utils.c
@@ -1,5 +1,4 @@
-/* "$Id$"
- *
+/*
* Author: Jean-Marc Lienher ( http://oksid.ch )
* Copyright 2000-2003 by O'ksi'D.
*
@@ -7,11 +6,11 @@
* the file "COPYING" which should have been included with this file. If this
* file is missing or damaged, see the license at:
*
- * http://www.fltk.org/COPYING.php
+ * https://www.fltk.org/COPYING.php
*
- * Please report all bugs and problems on the following page:
+ * Please see the following page on how to report bugs and issues:
*
- * http://www.fltk.org/str.php
+ * https://www.fltk.org/bugs.php
*/
/*
@@ -24,84 +23,84 @@
/*** NOTE : all functions are LIMITED to 24 bits Unicode values !!! ***/
-/*
- * Converts the first char of the UTF-8 string to an Unicode value
- * Returns the byte length of the converted UTF-8 char
- * Returns -1 if the UTF-8 string is not valid
+/*
+ * Converts the first char of the UTF-8 string to an Unicode value
+ * Returns the byte length of the converted UTF-8 char
+ * Returns -1 if the UTF-8 string is not valid
*/
int
XConvertUtf8ToUcs(const unsigned char *buf,
- int len,
- unsigned int *ucs) {
+ int len,
+ unsigned int *ucs) {
if (buf[0] & 0x80) {
if (buf[0] & 0x40) {
if (buf[0] & 0x20) {
- if (buf[0] & 0x10) {
- if (buf[0] & 0x08) {
- if (buf[0] & 0x04) {
- if (buf[0] & 0x02) {
- /* bad UTF-8 string */
- } else {
- /* 0x04000000 - 0x7FFFFFFF */
- }
- } else if (len > 4
- && (buf[1] & 0xC0) == 0x80
- && (buf[2] & 0xC0) == 0x80
- && (buf[3] & 0xC0) == 0x80
- && (buf[4] & 0xC0) == 0x80) {
- /* 0x00200000 - 0x03FFFFFF */
- *ucs = ((buf[0] & ~0xF8) << 24) +
- ((buf[1] & ~0x80) << 18) +
- ((buf[2] & ~0x80) << 12) +
- ((buf[3] & ~0x80) << 6) +
- (buf[4] & ~0x80);
- if (*ucs > 0x001FFFFF && *ucs < 0x01000000) return 5;
- }
- } else if (len > 3
- && (buf[1] & 0xC0) == 0x80
- && (buf[2] & 0xC0) == 0x80
- && (buf[3] & 0xC0) == 0x80) {
- /* 0x00010000 - 0x001FFFFF */
- *ucs = ((buf[0] & ~0xF0) << 18) +
- ((buf[1] & ~0x80) << 12) +
- ((buf[2] & ~0x80) << 6) +
- (buf[3] & ~0x80);
- if (*ucs > 0x0000FFFF) return 4;
- }
- } else if (len > 2
- && (buf[1] & 0xC0) == 0x80
- && (buf[2] & 0xC0) == 0x80) {
- /* 0x00000800 - 0x0000FFFF */
- *ucs = ((buf[0] & ~0xE0) << 12) +
- ((buf[1] & ~0x80) << 6) +
- (buf[2] & ~0x80);
- if (*ucs > 0x000007FF) return 3;
- }
+ if (buf[0] & 0x10) {
+ if (buf[0] & 0x08) {
+ if (buf[0] & 0x04) {
+ if (buf[0] & 0x02) {
+ /* bad UTF-8 string */
+ } else {
+ /* 0x04000000 - 0x7FFFFFFF */
+ }
+ } else if (len > 4
+ && (buf[1] & 0xC0) == 0x80
+ && (buf[2] & 0xC0) == 0x80
+ && (buf[3] & 0xC0) == 0x80
+ && (buf[4] & 0xC0) == 0x80) {
+ /* 0x00200000 - 0x03FFFFFF */
+ *ucs = ((buf[0] & ~0xF8) << 24) +
+ ((buf[1] & ~0x80) << 18) +
+ ((buf[2] & ~0x80) << 12) +
+ ((buf[3] & ~0x80) << 6) +
+ (buf[4] & ~0x80);
+ if (*ucs > 0x001FFFFF && *ucs < 0x01000000) return 5;
+ }
+ } else if (len > 3
+ && (buf[1] & 0xC0) == 0x80
+ && (buf[2] & 0xC0) == 0x80
+ && (buf[3] & 0xC0) == 0x80) {
+ /* 0x00010000 - 0x001FFFFF */
+ *ucs = ((buf[0] & ~0xF0) << 18) +
+ ((buf[1] & ~0x80) << 12) +
+ ((buf[2] & ~0x80) << 6) +
+ (buf[3] & ~0x80);
+ if (*ucs > 0x0000FFFF) return 4;
+ }
+ } else if (len > 2
+ && (buf[1] & 0xC0) == 0x80
+ && (buf[2] & 0xC0) == 0x80) {
+ /* 0x00000800 - 0x0000FFFF */
+ *ucs = ((buf[0] & ~0xE0) << 12) +
+ ((buf[1] & ~0x80) << 6) +
+ (buf[2] & ~0x80);
+ if (*ucs > 0x000007FF) return 3;
+ }
} else if (len > 1 && (buf[1] & 0xC0) == 0x80) {
- /* 0x00000080 - 0x000007FF */
- *ucs = ((buf[0] & ~0xC0) << 6) +
- (buf[1] & ~0x80);
- if (*ucs > 0x0000007F) return 2;
+ /* 0x00000080 - 0x000007FF */
+ *ucs = ((buf[0] & ~0xC0) << 6) +
+ (buf[1] & ~0x80);
+ if (*ucs > 0x0000007F) return 2;
}
}
} else if (len > 0) {
/* 0x00000000 - 0x0000007F */
*ucs = buf[0];
return 1;
- }
+ }
*ucs = (unsigned int) '?'; /* bad UTF-8 string */
return -1;
}
-/*
- * Converts an Unicode value to an UTF-8 string
- * NOTE : the buffer (buf) must be at least 5 bytes long !!!
+/*
+ * Converts an Unicode value to an UTF-8 string
+ * NOTE : the buffer (buf) must be at least 5 bytes long !!!
*/
-int
-XConvertUcsToUtf8(unsigned int ucs,
- char *buf) {
+int
+XConvertUcsToUtf8(unsigned int ucs,
+ char *buf) {
if (ucs < 0x000080) {
buf[0] = ucs;
@@ -110,7 +109,7 @@ XConvertUcsToUtf8(unsigned int ucs,
buf[0] = 0xC0 | (ucs >> 6);
buf[1] = 0x80 | (ucs & 0x3F);
return 2;
- } else if (ucs < 0x010000) {
+ } else if (ucs < 0x010000) {
buf[0] = 0xE0 | (ucs >> 12);
buf[1] = 0x80 | ((ucs >> 6) & 0x3F);
buf[2] = 0x80 | (ucs & 0x3F);
@@ -133,23 +132,23 @@ XConvertUcsToUtf8(unsigned int ucs,
return -1;
}
-/*
- * returns the byte length of the first UTF-8 char
- * (returns -1 if not valid)
+/*
+ * returns the byte length of the first UTF-8 char
+ * (returns -1 if not valid)
*/
int
XUtf8CharByteLen(const unsigned char *buf,
- int len) {
+ int len) {
unsigned int ucs;
return XConvertUtf8ToUcs(buf, len, &ucs);
}
/*
- * returns the quantity of Unicode chars in the UTF-8 string
+ * returns the quantity of Unicode chars in the UTF-8 string
*/
-int
-XCountUtf8Char(const unsigned char *buf,
- int len) {
+int
+XCountUtf8Char(const unsigned char *buf,
+ int len) {
int i = 0;
int nbc = 0;
@@ -162,66 +161,62 @@ XCountUtf8Char(const unsigned char *buf,
return nbc;
}
-/*
+/*
* Same as XConvertUtf8ToUcs but no sanity check is done.
*/
int
XFastConvertUtf8ToUcs(const unsigned char *buf,
- int len,
- unsigned int *ucs) {
+ int len,
+ unsigned int *ucs) {
if (buf[0] & 0x80) {
if (buf[0] & 0x40) {
if (buf[0] & 0x20) {
- if (buf[0] & 0x10) {
- if (buf[0] & 0x08) {
- if (buf[0] & 0x04) {
- if (buf[0] & 0x02) {
- /* bad UTF-8 string */
- } else {
- /* 0x04000000 - 0x7FFFFFFF */
- }
- } else if (len > 4) {
- /* 0x00200000 - 0x03FFFFFF */
- *ucs = ((buf[0] & ~0xF8) << 24) +
- ((buf[1] & ~0x80) << 18) +
- ((buf[2] & ~0x80) << 12) +
- ((buf[3] & ~0x80) << 6) +
- (buf[4] & ~0x80);
- return 5;
- }
- } else if (len > 3) {
- /* 0x00010000 - 0x001FFFFF */
- *ucs = ((buf[0] & ~0xF0) << 18) +
- ((buf[1] & ~0x80) << 12) +
- ((buf[2] & ~0x80) << 6) +
- (buf[3] & ~0x80);
- return 4;
- }
- } else if (len > 2) {
- /* 0x00000800 - 0x0000FFFF */
- *ucs = ((buf[0] & ~0xE0) << 12) +
- ((buf[1] & ~0x80) << 6) +
- (buf[2] & ~0x80);
- return 3;
- }
+ if (buf[0] & 0x10) {
+ if (buf[0] & 0x08) {
+ if (buf[0] & 0x04) {
+ if (buf[0] & 0x02) {
+ /* bad UTF-8 string */
+ } else {
+ /* 0x04000000 - 0x7FFFFFFF */
+ }
+ } else if (len > 4) {
+ /* 0x00200000 - 0x03FFFFFF */
+ *ucs = ((buf[0] & ~0xF8) << 24) +
+ ((buf[1] & ~0x80) << 18) +
+ ((buf[2] & ~0x80) << 12) +
+ ((buf[3] & ~0x80) << 6) +
+ (buf[4] & ~0x80);
+ return 5;
+ }
+ } else if (len > 3) {
+ /* 0x00010000 - 0x001FFFFF */
+ *ucs = ((buf[0] & ~0xF0) << 18) +
+ ((buf[1] & ~0x80) << 12) +
+ ((buf[2] & ~0x80) << 6) +
+ (buf[3] & ~0x80);
+ return 4;
+ }
+ } else if (len > 2) {
+ /* 0x00000800 - 0x0000FFFF */
+ *ucs = ((buf[0] & ~0xE0) << 12) +
+ ((buf[1] & ~0x80) << 6) +
+ (buf[2] & ~0x80);
+ return 3;
+ }
} else if (len > 1) {
- /* 0x00000080 - 0x000007FF */
- *ucs = ((buf[0] & ~0xC0) << 6) +
- (buf[1] & ~0x80);
- return 2;
+ /* 0x00000080 - 0x000007FF */
+ *ucs = ((buf[0] & ~0xC0) << 6) +
+ (buf[1] & ~0x80);
+ return 2;
}
}
} else if (len > 0) {
/* 0x00000000 - 0x0000007F */
*ucs = buf[0];
return 1;
- }
+ }
*ucs = (unsigned int) '?'; /* bad UTF-8 string */
return -1;
}
-
-/*
- * End of "$Id$".
- */
generated by cgit v1.2.3 (git 2.25.1) at 2026-02-08 08:12:37 +0000