diff options
Diffstat (limited to 'src/utf8.c')
| -rw-r--r-- | src/utf8.c | 193 |
1 files changed, 87 insertions, 106 deletions
@@ -1,4 +1,4 @@ -/* +/* * utf8.c: * * Copyright (c) 2008 James McKenzie <james@fishsoup.dhs.org>, @@ -8,8 +8,11 @@ static char rcsid[] = "$Id$"; -/* +/* * $Log$ + * Revision 1.14 2008/03/07 12:37:04 james + * *** empty log message *** + * * Revision 1.13 2008/03/06 16:49:39 james * *** empty log message *** * @@ -61,25 +64,24 @@ utf8_flush (Context * c) int i; int err = 0; - switch (u->utf_ptr) - { - case 1: - log_f (c->l, "<invalid utf-8 sequence: \\%03o>", u->utf_buf[0]); - break; - case 2: - log_f (c->l, "<invalid utf-8 sequence: \\%03o \\%03o>", - u->utf_buf[0], u->utf_buf[1]); - break; - case 3: - log_f (c->l, "<invalid utf-8 sequence: \\%03o \\%03o \\%03o>", - u->utf_buf[0], u->utf_buf[1], u->utf_buf[2]); - break; - case 4: - log_f (c->l, - "<invalid utf-8 sequence: \\%03o \\%03o \\%03o \\%03o>", - u->utf_buf[0], u->utf_buf[1], u->utf_buf[2], u->utf_buf[3]); - break; - } + switch (u->utf_ptr) { + case 1: + log_f (c->l, "<invalid utf-8 sequence: \\%03o>", u->utf_buf[0]); + break; + case 2: + log_f (c->l, "<invalid utf-8 sequence: \\%03o \\%03o>", + u->utf_buf[0], u->utf_buf[1]); + break; + case 3: + log_f (c->l, "<invalid utf-8 sequence: \\%03o \\%03o \\%03o>", + u->utf_buf[0], u->utf_buf[1], u->utf_buf[2]); + break; + case 4: + log_f (c->l, + "<invalid utf-8 sequence: \\%03o \\%03o \\%03o \\%03o>", + u->utf_buf[0], u->utf_buf[1], u->utf_buf[2], u->utf_buf[3]); + break; + } for (i = 0; i < u->utf_ptr; ++i) err += vt102_parse_char (c, u->utf_buf[i]); @@ -97,68 +99,54 @@ utf8_parse (Context * c, uint32_t ch) UTF8 *u = c->u; int err = 0; - if (ch == SYM_CHAR_RESET) - { - u->in_utf8 = 0; + if (ch == SYM_CHAR_RESET) { + u->in_utf8 = 0; + err += vt102_parse_char (c, ch); + return err; + } + + if (!u->in_utf8) { + /* FIXME: for the moment we bodge utf8 support - need to do */ + /* L->R and R->L and double width characters */ + if (ch == 0xb9) // FIXME - OTHER 8 bit control chars + { /* CSI, not a valid utf8 start char */ + err += vt102_parse_char (c, ch); + } else if ((ch & 0xe0) == 0xc0) { /* Start of two byte unicode sequence */ + u->in_utf8 = 1; + u->utf_ptr = 0; + u->utf_buf[u->utf_ptr++] = ch; + u->ch = (ch & 0x1f) << 6; + u->sh = 0; + } else if ((ch & 0xf0) == 0xe0) { /* Start of three byte unicode sequence + */ + u->in_utf8 = 2; + u->utf_ptr = 0; + u->utf_buf[u->utf_ptr++] = ch; + u->ch = (ch & 0x0f) << 12; + u->sh = 6; + } else if ((ch & 0xf8) == 0xf0) { + u->in_utf8 = 3; + u->utf_ptr = 0; + u->utf_buf[u->utf_ptr++] = ch; + u->ch = (ch & 0x07) << 18; + u->sh = 12; + } else { err += vt102_parse_char (c, ch); - return err; - } - - if (!u->in_utf8) - { - /*FIXME: for the moment we bodge utf8 support - need to do */ - /* L->R and R->L and double width characters */ - if (ch == 0xb9) //FIXME - OTHER 8 bit control chars - { /*CSI, not a valid utf8 start char */ - err += vt102_parse_char (c, ch); - } - else if ((ch & 0xe0) == 0xc0) - { /*Start of two byte unicode sequence */ - u->in_utf8 = 1; - u->utf_ptr = 0; - u->utf_buf[u->utf_ptr++] = ch; - u->ch = (ch & 0x1f) << 6; - u->sh = 0; - } - else if ((ch & 0xf0) == 0xe0) - { /*Start of three byte unicode sequence */ - u->in_utf8 = 2; - u->utf_ptr = 0; - u->utf_buf[u->utf_ptr++] = ch; - u->ch = (ch & 0x0f) << 12; - u->sh = 6; - } - else if ((ch & 0xf8) == 0xf0) - { - u->in_utf8 = 3; - u->utf_ptr = 0; - u->utf_buf[u->utf_ptr++] = ch; - u->ch = (ch & 0x07) << 18; - u->sh = 12; - } - else - { - err += vt102_parse_char (c, ch); - } } - else - { - if ((ch & 0xc0) != 0x80) - { - err += utf8_flush (c); - err += vt102_parse_char (c, ch); - } - else - { - u->utf_buf[u->utf_ptr++] = ch; - u->ch |= (ch & 0x3f) << u->sh; - u->sh -= 6; - u->in_utf8--; - - if (!u->in_utf8) - err += vt102_parse_char (c, u->ch); - } + } else { + if ((ch & 0xc0) != 0x80) { + err += utf8_flush (c); + err += vt102_parse_char (c, ch); + } else { + u->utf_buf[u->utf_ptr++] = ch; + u->ch |= (ch & 0x3f) << u->sh; + u->sh -= 6; + u->in_utf8--; + + if (!u->in_utf8) + err += vt102_parse_char (c, u->ch); } + } return err; } @@ -179,32 +167,25 @@ int utf8_encode (char *ptr, int ch) { - if (ch < 0x80) - { - ptr[0] = ch; - return 1; - } - else if (ch < 0x800) - { - ptr[0] = 0xc0 | (ch >> 6); - ptr[1] = 0x80 | (ch & 0x3f); - return 2; - } - else if (ch < 0x10000) - { - ptr[0] = 0xe0 | (ch >> 12); - ptr[1] = 0x80 | ((ch >> 6) & 0x3f); - ptr[2] = 0x80 | (ch & 0x3f); - return 3; - } - else if (ch < 0x1fffff) - { - ptr[0] = 0xf0 | (ch >> 18); - ptr[1] = 0x80 | ((ch >> 12) & 0x3f); - ptr[2] = 0x80 | ((ch >> 6) & 0x3f); - ptr[3] = 0x80 | (ch & 0x3f); - return 4; - } + if (ch < 0x80) { + ptr[0] = ch; + return 1; + } else if (ch < 0x800) { + ptr[0] = 0xc0 | (ch >> 6); + ptr[1] = 0x80 | (ch & 0x3f); + return 2; + } else if (ch < 0x10000) { + ptr[0] = 0xe0 | (ch >> 12); + ptr[1] = 0x80 | ((ch >> 6) & 0x3f); + ptr[2] = 0x80 | (ch & 0x3f); + return 3; + } else if (ch < 0x1fffff) { + ptr[0] = 0xf0 | (ch >> 18); + ptr[1] = 0x80 | ((ch >> 12) & 0x3f); + ptr[2] = 0x80 | ((ch >> 6) & 0x3f); + ptr[3] = 0x80 | (ch & 0x3f); + return 4; + } return 0; } |