X-Git-Url: https://git.draconx.ca/gitweb/gob-dx.git/blobdiff_plain/4ebed70c2119e843ce48ae4fa6076475d2100693..7f1f40bee65a4a3d3947ad8c50b535ea0754f629:/src/gob-strcase.c diff --git a/src/gob-strcase.c b/src/gob-strcase.c new file mode 100644 index 0000000..87c59a6 --- /dev/null +++ b/src/gob-strcase.c @@ -0,0 +1,176 @@ +/* c-strcasecmp.c -- case insensitive string comparator in C locale + Copyright (C) 1998-1999, 2005-2006, 2009-2021 Free Software Foundation, Inc. + + Character handling in C locale. + Copyright (C) 2000-2003, 2006, 2008-2021 Free Software Foundation, Inc. + + Stripped down copy of gnulib c-ctype and c-strcasecmp modules for + conditional fallback use. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, see . */ + +#include +#include + +#undef HAVE_G_ASCII_STRCASECMP +#include "util.h" + +/* The functions defined in this file assume the "C" locale and a character + set without diacritics (ASCII-US or EBCDIC-US or something like that). + Even if the "C" locale on a particular system is an extension of the ASCII + character set (like on BeOS, where it is UTF-8, or on AmigaOS, where it + is ISO-8859-1), the functions in this file recognize only the ASCII + characters. */ + +#if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \ + && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \ + && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \ + && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \ + && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \ + && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \ + && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \ + && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \ + && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \ + && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \ + && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \ + && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \ + && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \ + && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \ + && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \ + && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \ + && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \ + && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \ + && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \ + && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \ + && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \ + && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \ + && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126) +/* The character set is ASCII or one of its variants or extensions, not EBCDIC. + Testing the value of '\n' and '\r' is not relevant. */ +# define C_CTYPE_ASCII 1 +#elif ! (' ' == '\x40' && '0' == '\xf0' \ + && 'A' == '\xc1' && 'J' == '\xd1' && 'S' == '\xe2' \ + && 'a' == '\x81' && 'j' == '\x91' && 's' == '\xa2') +# error "Only ASCII and EBCDIC are supported" +#endif + +#if 'A' < 0 +# error "EBCDIC and char is signed -- not supported" +#endif + +/* Cases for lowercase hex letters, and lowercase letters, all offset by N. */ + +#define C_CTYPE_LOWER_A_THRU_F_N(N) \ + case 'a' + (N): case 'b' + (N): case 'c' + (N): case 'd' + (N): \ + case 'e' + (N): case 'f' + (N) +#define C_CTYPE_LOWER_N(N) \ + C_CTYPE_LOWER_A_THRU_F_N(N): \ + case 'g' + (N): case 'h' + (N): case 'i' + (N): case 'j' + (N): \ + case 'k' + (N): case 'l' + (N): case 'm' + (N): case 'n' + (N): \ + case 'o' + (N): case 'p' + (N): case 'q' + (N): case 'r' + (N): \ + case 's' + (N): case 't' + (N): case 'u' + (N): case 'v' + (N): \ + case 'w' + (N): case 'x' + (N): case 'y' + (N): case 'z' + (N) + +#define C_CTYPE_LOWER C_CTYPE_LOWER_N(0) +#define C_CTYPE_UPPER C_CTYPE_LOWER_N ('A' - 'a') + + +/* Function definitions. */ + +/* Unlike the functions in , which require an argument in the range + of the 'unsigned char' type, the functions here operate on values that are + in the 'unsigned char' range or in the 'char' range. In other words, + when you have a 'char' value, you need to cast it before using it as + argument to a function: + + const char *s = ...; + if (isalpha ((unsigned char) *s)) ... + + but you don't need to cast it for the functions defined in this file: + + const char *s = ...; + if (c_isalpha (*s)) ... + */ + +static int c_tolower(int c) +{ + switch (c) { + C_CTYPE_UPPER: + return c - 'A' + 'a'; + default: + return c; + } +} + +static int c_toupper(int c) +{ + switch (c) { + C_CTYPE_LOWER: + return c - 'a' + 'A'; + default: + return c; + } +} + +char *gob_strup(char *str) +{ + char *s; + + for (s = str; *s; s++) + *s = c_toupper(*s); + + return str; +} + +char *gob_strdown(char *str) +{ + char *s; + + for (s = str; *s; s++) + *s = c_tolower(*s); + + return str; +} + +int gob_strcasecmp(const char *s1, const char *s2) +{ + register const unsigned char *p1 = (const unsigned char *)s1; + register const unsigned char *p2 = (const unsigned char *)s2; + unsigned char c1, c2; + + if (p1 == p2) + return 0; + + do { + c1 = c_tolower (*p1); + c2 = c_tolower (*p2); + + if (c1 == '\0') + break; + + ++p1; + ++p2; + } while (c1 == c2); + + if (UCHAR_MAX <= INT_MAX) { + return c1 - c2; + } else { + /* + * On machines where 'char' and 'int' are types of the + * same size, the difference of two 'unsigned char' values + * - including the sign bit - doesn't fit in an 'int'. + */ + return _GL_CMP (c1, c2); + } +}