diff options
Diffstat (limited to 'fw/fe310/eos/unicode.c')
-rw-r--r-- | fw/fe310/eos/unicode.c | 70 |
1 files changed, 43 insertions, 27 deletions
diff --git a/fw/fe310/eos/unicode.c b/fw/fe310/eos/unicode.c index 29100c7..d660247 100644 --- a/fw/fe310/eos/unicode.c +++ b/fw/fe310/eos/unicode.c @@ -1,6 +1,6 @@ #include "unicode.h" -int utf8_enc(utf32_t ch, utf8_t *str) { +int utf8_enc(ucp_t ch, utf8_t *str) { if (ch <= 0x7f) { str[0] = ch; return 1; @@ -25,30 +25,30 @@ int utf8_enc(utf32_t ch, utf8_t *str) { } } -int utf8_dec(utf8_t *str, utf32_t *ch) { +int utf8_dec(utf8_t *str, ucp_t *ch) { if ((str[0] & 0x80) == 0x00) { *ch = str[0]; return 1; } else if ((str[0] & 0xe0) == 0xc0) { if ((str[1] & 0xc0) != 0x80) return UTF_ERR; - *ch = (utf32_t)(str[0] & 0x1f) << 6; - *ch |= (utf32_t)(str[1] & 0x3f); + *ch = (ucp_t)(str[0] & 0x1f) << 6; + *ch |= (ucp_t)(str[1] & 0x3f); if (*ch < 0x80) return UTF_ERR; return 2; } else if ((str[0] & 0xf0) == 0xe0) { if (((str[1] & 0xc0) != 0x80) || ((str[2] & 0xc0) != 0x80)) return UTF_ERR; - *ch = (utf32_t)(str[0] & 0x0f) << 12; - *ch |= (utf32_t)(str[1] & 0x3f) << 6; - *ch |= (utf32_t)(str[2] & 0x3f); + *ch = (ucp_t)(str[0] & 0x0f) << 12; + *ch |= (ucp_t)(str[1] & 0x3f) << 6; + *ch |= (ucp_t)(str[2] & 0x3f); if ((*ch >= 0xd800) && (*ch <= 0xdfff)) return UTF_ERR; if (*ch < 0x800) return UTF_ERR; return 3; } else if ((str[0] & 0xf8) == 0xf0) { if (((str[1] & 0xc0) != 0x80) || ((str[2] & 0xc0) != 0x80) || ((str[3] & 0xc0) != 0x80)) return UTF_ERR; - *ch = (utf32_t)(str[0] & 0x07) << 18; - *ch |= (utf32_t)(str[1] & 0x0f) << 12; - *ch |= (utf32_t)(str[2] & 0x3f) << 6; - *ch |= (utf32_t)(str[3] & 0x3f); + *ch = (ucp_t)(str[0] & 0x07) << 18; + *ch |= (ucp_t)(str[1] & 0x0f) << 12; + *ch |= (ucp_t)(str[2] & 0x3f) << 6; + *ch |= (ucp_t)(str[3] & 0x3f); if (*ch < 0x010000) return UTF_ERR; if (*ch > 0x10ffff) return UTF_ERR; return 4; @@ -57,16 +57,25 @@ int utf8_dec(utf8_t *str, utf32_t *ch) { } } -int utf8_len(utf8_t *str) { - if ((*str & 0xf8) == 0xf0) return 4; - if ((*str & 0xf0) == 0xe0) return 3; - if ((*str & 0xe0) == 0xc0) return 2; +int utf8_len_ch(ucp_t ch) { + if (ch <= 0x7f) return 1; + if (ch <= 0x7ff) return 2; + if (ch <= 0xffff) return 3; + if (ch <= 0x10ffff) return 4; + + return UTF_ERR; +} + +int utf8_len_str(utf8_t *str) { if ((*str & 0x80) == 0x00) return 1; + if ((*str & 0xe0) == 0xc0) return 2; + if ((*str & 0xf0) == 0xe0) return 3; + if ((*str & 0xf8) == 0xf0) return 4; return UTF_ERR; } -int utf8_seek(utf8_t *str, int off, utf32_t *ch) { +int utf8_seek(utf8_t *str, int off, ucp_t *ch) { int i; int len = 0; @@ -93,15 +102,16 @@ int utf8_seek(utf8_t *str, int off, utf32_t *ch) { return len; } -int utf8_verify(utf8_t *str, int str_size, int *str_len) { - utf32_t ch; - uint8_t ch_l; - int len = 0; +int utf8_verify(utf8_t *str, size_t str_size, size_t *str_len) { + ucp_t ch; + size_t len = 0; + int ch_l, rv; while (len < str_size) { if (str_size - len < 4) { - int _len = utf8_len(str + len); - if ((_len == UTF_ERR) || ((str_size - len) < _len)) break; + rv = utf8_len_str(str + len); + if (rv < 0) break; + if (str_size - len < rv) break; } ch_l = utf8_dec(str + len, &ch); if (ch_l > 0) { @@ -119,7 +129,7 @@ int utf8_verify(utf8_t *str, int str_size, int *str_len) { return UTF_ERR; } -int utf16_enc(utf32_t ch, uint8_t *str) { +int utf16_enc(ucp_t ch, utf16_t *str) { if (ch <= 0xffff) { if ((ch >= 0xd800) && (ch <= 0xdfff)) return UTF_ERR; str[0] = ch >> 8; @@ -142,7 +152,7 @@ int utf16_enc(utf32_t ch, uint8_t *str) { } } -int utf16_dec(uint8_t *str, utf32_t *ch) { +int utf16_dec(utf16_t *str, ucp_t *ch) { *ch = (str[0] << 8) | str[1]; if ((*ch >= 0xd800) && (*ch <= 0xdfff)) { uint16_t hi = *ch; @@ -158,15 +168,21 @@ int utf16_dec(uint8_t *str, utf32_t *ch) { } } -int utf16_len(uint8_t *str) { +int utf16_len_ch(ucp_t ch) { + if (ch <= 0xffff) return 2; + if (ch <= 0x10ffff) return 4; + + return UTF_ERR; +} + +int utf16_len_str(utf16_t *str) { uint16_t ch = (str[0] << 8) | str[1]; - if ((ch >= 0xdc00) && (ch <= 0xdfff)) return UTF_ERR; if ((ch >= 0xd800) && (ch <= 0xdfff)) return 4; return 2; } -int utf16_seek(uint8_t *str, int off, utf32_t *ch) { +int utf16_seek(utf16_t *str, int off, ucp_t *ch) { int i; int len = 0; uint16_t cu; |