diff options
Diffstat (limited to 'generic/tclUtf.c')
| -rw-r--r-- | generic/tclUtf.c | 84 |
1 files changed, 1 insertions, 83 deletions
diff --git a/generic/tclUtf.c b/generic/tclUtf.c index 64ee0a8..3741d70 100644 --- a/generic/tclUtf.c +++ b/generic/tclUtf.c @@ -209,30 +209,6 @@ Tcl_UniCharToUtf( return 2; } if (ch <= 0xFFFF) { -#if TCL_UTF_MAX == 4 - if ((ch & 0xF800) == 0xD800) { - if (ch & 0x0400) { - /* Low surrogate */ - if (((buf[0] & 0xF8) == 0xF0) && ((buf[1] & 0xC0) == 0x80) - && ((buf[2] & 0xCF) == 0)) { - /* Previous Tcl_UniChar was a High surrogate, so combine */ - buf[3] = (char) ((ch & 0x3F) | 0x80); - buf[2] |= (char) (((ch >> 6) & 0x0F) | 0x80); - return 4; - } - /* Previous Tcl_UniChar was not a High surrogate, so just output */ - } else { - /* High surrogate */ - ch += 0x40; - /* Fill buffer with specific 3-byte (invalid) byte combination, - so following Low surrogate can recognize it and combine */ - buf[2] = (char) ((ch << 4) & 0x30); - buf[1] = (char) (((ch >> 2) & 0x3F) | 0x80); - buf[0] = (char) (((ch >> 8) & 0x07) | 0xF0); - return 0; - } - } -#endif goto three; } @@ -321,15 +297,6 @@ Tcl_UniCharToUtfDString( * Tcl_UtfCharComplete() before calling this routine to ensure that * enough bytes remain in the string. * - * If TCL_UTF_MAX == 4, special handling of Surrogate pairs is done: - * For any UTF-8 string containing a character outside of the BMP, the - * first call to this function will fill *chPtr with the high surrogate - * and generate a return value of 0. Calling Tcl_UtfToUniChar again - * will produce the low surrogate and a return value of 4. Because *chPtr - * is used to remember whether the high surrogate is already produced, it - * is recommended to initialize the variable it points to as 0 before - * the first call to Tcl_UtfToUniChar is done. - * * Results: * *chPtr is filled with the Tcl_UniChar, and the return value is the * number of bytes from the UTF-8 string that were consumed. @@ -402,34 +369,15 @@ Tcl_UtfToUniChar( /* * Four-byte-character lead byte followed by three trail bytes. */ -#if TCL_UTF_MAX == 4 - Tcl_UniChar surrogate; - - byte = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12) - | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F)) - 0x10000; - surrogate = (Tcl_UniChar) (0xD800 + (byte >> 10)); - if (byte & 0x100000) { - /* out of range, < 0x10000 or > 0x10ffff */ - } else if (*chPtr != surrogate) { - /* produce high surrogate, but don't advance source pointer */ - *chPtr = surrogate; - return 0; - } else { - /* produce low surrogate, and advance source pointer */ - *chPtr = (Tcl_UniChar) (0xDC00 | (byte & 0x3FF)); - return 4; - } -#else *chPtr = (Tcl_UniChar) (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12) | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F)); if ((unsigned)(*chPtr - 0x10000) <= 0xFFFFF) { return 4; } -#endif } /* - * A four-byte-character lead-byte not followed by two trail-bytes + * A four-byte-character lead-byte not followed by three trail-bytes * represents itself. */ } @@ -1230,16 +1178,6 @@ Tcl_UtfNcmp( cs += TclUtfToUniChar(cs, &ch1); ct += TclUtfToUniChar(ct, &ch2); if (ch1 != ch2) { -#if TCL_UTF_MAX == 4 - /* Surrogates always report higher than non-surrogates */ - if (((ch1 & 0xFC00) == 0xD800)) { - if ((ch2 & 0xFC00) != 0xD800) { - return ch1; - } - } else if ((ch2 & 0xFC00) == 0xD800) { - return -ch2; - } -#endif return (ch1 - ch2); } } @@ -1280,16 +1218,6 @@ Tcl_UtfNcasecmp( cs += TclUtfToUniChar(cs, &ch1); ct += TclUtfToUniChar(ct, &ch2); if (ch1 != ch2) { -#if TCL_UTF_MAX == 4 - /* Surrogates always report higher than non-surrogates */ - if (((ch1 & 0xFC00) == 0xD800)) { - if ((ch2 & 0xFC00) != 0xD800) { - return ch1; - } - } else if ((ch2 & 0xFC00) == 0xD800) { - return -ch2; - } -#endif ch1 = Tcl_UniCharToLower(ch1); ch2 = Tcl_UniCharToLower(ch2); if (ch1 != ch2) { @@ -1329,16 +1257,6 @@ TclUtfCasecmp( cs += TclUtfToUniChar(cs, &ch1); ct += TclUtfToUniChar(ct, &ch2); if (ch1 != ch2) { -#if TCL_UTF_MAX == 4 - /* Surrogates always report higher than non-surrogates */ - if (((ch1 & 0xFC00) == 0xD800)) { - if ((ch2 & 0xFC00) != 0xD800) { - return ch1; - } - } else if ((ch2 & 0xFC00) == 0xD800) { - return -ch2; - } -#endif ch1 = Tcl_UniCharToLower(ch1); ch2 = Tcl_UniCharToLower(ch2); if (ch1 != ch2) { |