Tcl Source Code: Diff

Differences From Artifact [38ed3dc4e0]:

File generic/tclUtf.c — part of check-in [cc4f7b61e2] at 2025-08-31 17:16:26 on branch main — Merge 9.0. Fix TIP #726 implementation, so all functions give the same answer as Tcl 9.0 for out-of-bound characters (user: jan.nijtmans size: 67324) [more...]

To Artifact [bf568b2520]:

File generic/tclUtf.c — part of check-in [1857668b9f] at 2025-08-31 20:03:32 on branch main — Oops, 21 bits, not 17 bits (user: jan.nijtmans size: 67337)

︙
1784 1785 1786 1787 1788 1789 1790 ~~1791~~ 1792 1793 1794 1795 1796 1797 1798	1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798	- +	/ int Tcl_UniCharToUpper( int ch) / Unicode character to convert. / { if (!UNICODE_OUT_OF_RANGE(ch)) { ~~ch = utf8proc_toupper(ch & 0x1FFFF);~~ ch = utf8proc_toupper(ch & 0x1FFFFF); } / Clear away extension bits, if any / return ch & 0x1FFFFF; } / *----------------------------------------------------------------------
︙
1811 1812 1813 1814 1815 1816 1817 ~~1818~~ 1819 1820 1821 1822 1823 1824 1825	1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825	- +	/ int Tcl_UniCharToLower( int ch) / Unicode character to convert. / { if (!UNICODE_OUT_OF_RANGE(ch)) { ~~ch = utf8proc_tolower(ch & 0x1FFFF);~~ ch = utf8proc_tolower(ch & 0x1FFFFF); } / Clear away extension bits, if any / return ch & 0x1FFFFF; } / *----------------------------------------------------------------------
︙
1838 1839 1840 1841 1842 1843 1844 ~~1845~~ 1846 1847 1848 1849 1850 1851 1852	1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852	- +	/ int Tcl_UniCharToTitle( int ch) / Unicode character to convert. / { if (!UNICODE_OUT_OF_RANGE(ch)) { ~~ch = utf8proc_totitle(ch & 0x1FFFF);~~ ch = utf8proc_totitle(ch & 0x1FFFFF); } / Clear away extension bits, if any / return ch & 0x1FFFFF; } / *----------------------------------------------------------------------
︙
2005 2006 2007 2008 2009 2010 2011 ~~2012~~ 2013 2014 2015 2016 2017 2018 2019	2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsAlnum( int ch) /* Unicode character to test. / { ~~return ((UTF8PROC_ALPHA_BITS\|UTF8PROC_DIGIT_BITS) >> utf8proc_category(ch & 0x1FFFF)) & 1;~~ return ((UTF8PROC_ALPHA_BITS\|UTF8PROC_DIGIT_BITS) >> utf8proc_category(ch & 0x1FFFFF)) & 1; } / ---------------------------------------------------------------------- * Tcl_UniCharIsAlpha -- *
︙
2028 2029 2030 2031 2032 2033 2034 ~~2035~~ 2036 2037 2038 2039 2040 2041 2042	2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsAlpha( int ch) /* Unicode character to test. / { ~~return (UTF8PROC_ALPHA_BITS >> utf8proc_category(ch & 0x1FFFF)) & 1;~~ return (UTF8PROC_ALPHA_BITS >> utf8proc_category(ch & 0x1FFFFF)) & 1; } / ---------------------------------------------------------------------- * Tcl_UniCharIsControl -- *
︙
2051 2052 2053 2054 2055 2056 2057 ~~2058~~ 2059 2060 2061 2062 2063 2064 2065	2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsControl( int ch) /* Unicode character to test. / { ~~return (UTF8PROC_CONTROL_BITS >> utf8proc_category(ch & 0x1FFFF)) & 1;~~ return (UTF8PROC_CONTROL_BITS >> utf8proc_category(ch & 0x1FFFFF)) & 1; } / ---------------------------------------------------------------------- * Tcl_UniCharIsDigit -- *
︙
2074 2075 2076 2077 2078 2079 2080 ~~2081~~ 2082 2083 2084 2085 2086 2087 2088	2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsDigit( int ch) /* Unicode character to test. / { ~~return (utf8proc_category(ch & 0x1FFFF) == UTF8PROC_CATEGORY_ND);~~ return (utf8proc_category(ch & 0x1FFFFF) == UTF8PROC_CATEGORY_ND); } / ---------------------------------------------------------------------- * Tcl_UniCharIsGraph -- *
︙
2097 2098 2099 2100 2101 2102 2103 ~~2104~~ 2105 2106 2107 2108 2109 2110 2111	2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsGraph( int ch) /* Unicode character to test. / { ~~return (UTF8PROC_GRAPH_BITS >> utf8proc_category(ch & 0x1FFFF)) & 1;~~ return (UTF8PROC_GRAPH_BITS >> utf8proc_category(ch & 0x1FFFFF)) & 1; } / ---------------------------------------------------------------------- * Tcl_UniCharIsLower -- *
︙
2120 2121 2122 2123 2124 2125 2126 ~~2127~~ 2128 2129 2130 2131 2132 2133 2134	2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsLower( int ch) /* Unicode character to test. / { ~~return (utf8proc_category(ch & 0x1FFFF) == UTF8PROC_CATEGORY_LL);~~ return (utf8proc_category(ch & 0x1FFFFF) == UTF8PROC_CATEGORY_LL); } / ---------------------------------------------------------------------- * Tcl_UniCharIsPrint -- *
︙
2143 2144 2145 2146 2147 2148 2149 ~~2150~~ 2151 2152 2153 2154 2155 2156 2157	2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsPrint( int ch) /* Unicode character to test. / { ~~return ((UTF8PROC_SPACE_BITS\|UTF8PROC_GRAPH_BITS) >> utf8proc_category(ch & 0x1FFFF)) & 1;~~ return ((UTF8PROC_SPACE_BITS\|UTF8PROC_GRAPH_BITS) >> utf8proc_category(ch & 0x1FFFFF)) & 1; } / ---------------------------------------------------------------------- * Tcl_UniCharIsPunct -- *
︙
2166 2167 2168 2169 2170 2171 2172 ~~2173~~ 2174 2175 2176 2177 2178 2179 2180	2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsPunct( int ch) /* Unicode character to test. / { ~~return (UTF8PROC_PUNCT_BITS >> utf8proc_category(ch & 0x1FFFF)) & 1;~~ return (UTF8PROC_PUNCT_BITS >> utf8proc_category(ch & 0x1FFFFF)) & 1; } / ---------------------------------------------------------------------- * Tcl_UniCharIsSpace -- *
︙
2229 2230 2231 2232 2233 2234 2235 ~~2236~~ 2237 2238 2239 2240 2241 2242 2243	2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsUpper( int ch) /* Unicode character to test. / { ~~return (utf8proc_category(ch & 0x1FFFF) == UTF8PROC_CATEGORY_LU);~~ return (utf8proc_category(ch & 0x1FFFFF) == UTF8PROC_CATEGORY_LU); } / ---------------------------------------------------------------------- * Tcl_UniCharIsWordChar -- *
︙
2252 2253 2254 2255 2256 2257 2258 ~~2259~~ 2260 2261 2262 2263 2264 2265 2266	2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266	- +	---------------------------------------------------------------------- / int Tcl_UniCharIsWordChar( int ch) /* Unicode character to test. / { ~~return (UTF8PROC_WORD_BITS >> utf8proc_category(ch & 0x1FFFF)) & 1;~~ return (UTF8PROC_WORD_BITS >> utf8proc_category(ch & 0x1FFFFF)) & 1; } / ---------------------------------------------------------------------- * TclUniCharCaseMatch -- *
︙