FreeCalypso > hg > freecalypso-tools

annotate uptools/libcoding/utf8_decode.c @ 650:bf840c984113

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
fc-xram reworked to use the new binary protocol
author Mychaela Falconia <falcon@freecalypso.org>
date Mon, 02 Mar 2020 03:21:41 +0000
parents ec0d6d58e043
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
354
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
1 /*
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
2 * This library module implements a function that converts text input
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
3 * from UTF-8 to ISO 8859-1, rejecting any input Unicode characters
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
4 * that aren't in the 8859-1 range. The conversion in done in place.
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
5 */
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
6
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
7 #include <sys/types.h>
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
8
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
9 utf8_to_latin1(buf)
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
10 u_char *buf;
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
11 {
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
12 u_char *ip = buf, *op = buf;
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
13 int c, c2;
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
14
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
15 while (c = *ip++) {
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
16 if (c < 0x80) {
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
17 *op++ = c;
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
18 continue;
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
19 }
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
20 if (c != 0xC2 && c != 0xC3)
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
21 return(-1);
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
22 c2 = *ip++;
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
23 if (c2 < 0x80 || c2 > 0xBF)
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
24 return(-1);
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
25 *op++ = ((c & 3) << 6) | (c2 & 0x3F);
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
26 }
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
27 *op = '\0';
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
28 return(0);
ec0d6d58e043 uptools/libcoding: UTF-8 input conversion to 8859-1 implemented
Mychaela Falconia <falcon@freecalypso.org>
parents:
diff changeset
29 }