[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Bug-gnulib] addition: c-ctype.h, c-ctype.c
From: |
Bruno Haible |
Subject: |
[Bug-gnulib] addition: c-ctype.h, c-ctype.c |
Date: |
Mon, 27 Jan 2003 21:18:46 +0100 (CET) |
Hi,
The c-ctype module provides the equivalent of <ctype.h> for the C
locale, using ASCII characters only. It is useful for some limited
areas where locale dependency is not desired but speed is wanted,
e.g. when parsing a file (assembler, Emacs Lisp etc).
The module's functions, except c_isascii, should also work on EBCDIC
hosts, but the compiled code will be less efficient than for ASCII.
gcc's libiberty contains a similar file, called safe-ctype.h but I
don't want to use this because:
- "safe-ctype" is a misnomer - there is nothing unsafe about using
<ctype.h>,
- safe-ctype.h and ctype.h may not be used simultaneously,
- safe-ctype.h defines ISPRINT etc. which usually denote the
locale aware isprint function, which some 8-bit-clean fixup,
- The functions is safe-ctype.h don't support the EOF argument,
unlike <ctype.h> and c-ctype.h.
Any objections?
Bruno
=============================== c-ctype.h ===============================
/* Character handling in C locale.
These functions work like the corresponding functions in <ctype.h>,
except that they have the C (POSIX) locale hardwired, whereas the
<ctype.h> functions' behaviour depends on the current locale set via
setlocale.
Copyright (C) 2000-2002 Free Software Foundation, Inc.
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 of the License, 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, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
#ifndef C_CTYPE_H
#define C_CTYPE_H
#include <stdbool.h>
/* Check whether the ASCII optimizations apply. */
#if ('0' <= '9') \
&& ('0' + 1 == '1') && ('1' + 1 == '2') && ('2' + 1 == '3') \
&& ('3' + 1 == '4') && ('4' + 1 == '5') && ('5' + 1 == '6') \
&& ('6' + 1 == '7') && ('7' + 1 == '8') && ('8' + 1 == '9')
#define C_CTYPE_CONSECUTIVE_DIGITS 1
#endif
#if ('A' <= 'Z') \
&& ('A' + 1 == 'B') && ('B' + 1 == 'C') && ('C' + 1 == 'D') \
&& ('D' + 1 == 'E') && ('E' + 1 == 'F') && ('F' + 1 == 'G') \
&& ('G' + 1 == 'H') && ('H' + 1 == 'I') && ('I' + 1 == 'J') \
&& ('J' + 1 == 'K') && ('K' + 1 == 'L') && ('L' + 1 == 'M') \
&& ('M' + 1 == 'N') && ('N' + 1 == 'O') && ('O' + 1 == 'P') \
&& ('P' + 1 == 'Q') && ('Q' + 1 == 'R') && ('R' + 1 == 'S') \
&& ('S' + 1 == 'T') && ('T' + 1 == 'U') && ('U' + 1 == 'V') \
&& ('V' + 1 == 'W') && ('W' + 1 == 'X') && ('X' + 1 == 'Y') \
&& ('Y' + 1 == 'Z')
#define C_CTYPE_CONSECUTIVE_UPPERCASE 1
#endif
#if ('a' <= 'z') \
&& ('a' + 1 == 'b') && ('b' + 1 == 'c') && ('c' + 1 == 'd') \
&& ('d' + 1 == 'e') && ('e' + 1 == 'f') && ('f' + 1 == 'g') \
&& ('g' + 1 == 'h') && ('h' + 1 == 'i') && ('i' + 1 == 'j') \
&& ('j' + 1 == 'k') && ('k' + 1 == 'l') && ('l' + 1 == 'm') \
&& ('m' + 1 == 'n') && ('n' + 1 == 'o') && ('o' + 1 == 'p') \
&& ('p' + 1 == 'q') && ('q' + 1 == 'r') && ('r' + 1 == 's') \
&& ('s' + 1 == 't') && ('t' + 1 == 'u') && ('u' + 1 == 'v') \
&& ('v' + 1 == 'w') && ('w' + 1 == 'x') && ('x' + 1 == 'y') \
&& ('y' + 1 == 'z')
#define C_CTYPE_CONSECUTIVE_LOWERCASE 1
#endif
#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 ISO-646, not EBCDIC. */
#define C_CTYPE_ASCII 1
#endif
/* Function declarations. */
extern bool c_isascii (int c); /* not locale dependent */
extern bool c_isalnum (int c);
extern bool c_isalpha (int c);
extern bool c_isblank (int c);
extern bool c_iscntrl (int c);
extern bool c_isdigit (int c);
extern bool c_islower (int c);
extern bool c_isgraph (int c);
extern bool c_isprint (int c);
extern bool c_ispunct (int c);
extern bool c_isspace (int c);
extern bool c_isupper (int c);
extern bool c_isxdigit (int c);
extern int c_tolower (int c);
extern int c_toupper (int c);
#if defined __GNUC__ && defined __OPTIMIZE__ && !defined __OPTIMIZE_SIZE__
/* ASCII optimizations. */
#define c_isascii(c) \
({ int __c = (c); \
((__c & ~0x7f) == 0); \
})
#if C_CTYPE_CONSECUTIVE_DIGITS \
&& C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
#define c_isalnum(c) \
({ int __c = (c); \
((__c >= '0' && __c <= '9') \
|| (__c >= 'A' && __c <= 'Z') \
|| (__c >= 'a' && __c <= 'z')); \
})
#endif
#if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
#define c_isalpha(c) \
({ int __c = (c); \
((__c >= 'A' && __c <= 'Z') || (__c >= 'a' && __c <= 'z')); \
})
#endif
#define c_isblank(c) \
({ int __c = (c); \
(__c == ' ' || __c == '\t'); \
})
#if C_CTYPE_ASCII
#define c_iscntrl(c) \
({ int __c = (c); \
((__c & ~0x1f) == 0 || __c == 0x7f); \
})
#endif
#if C_CTYPE_CONSECUTIVE_DIGITS
#define c_isdigit(c) \
({ int __c = (c); \
(__c >= '0' && __c <= '9'); \
})
#endif
#if C_CTYPE_CONSECUTIVE_LOWERCASE
#define c_islower(c) \
({ int __c = (c); \
(__c >= 'a' && __c <= 'z'); \
})
#endif
#if C_CTYPE_ASCII
#define c_isgraph(c) \
({ int __c = (c); \
(__c >= '!' && __c <= '~'); \
})
#endif
#if C_CTYPE_ASCII
#define c_isprint(c) \
({ int __c = (c); \
(__c >= ' ' && __c <= '~'); \
})
#endif
#if C_CTYPE_ASCII
#define c_ispunct(c) \
({ int _c = (c); \
(c_isgraph (_c) && ! c_isalnum (_c)); \
})
#endif
#define c_isspace(c) \
({ int __c = (c); \
(__c == ' ' || __c == '\t' \
|| __c == '\n' || __c == '\v' || __c == '\f' || __c == '\r'); \
})
#if C_CTYPE_CONSECUTIVE_UPPERCASE
#define c_isupper(c) \
({ int __c = (c); \
(__c >= 'A' && __c <= 'Z'); \
})
#endif
#if C_CTYPE_CONSECUTIVE_DIGITS \
&& C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
#define c_isxdigit(c) \
({ int __c = (c); \
((__c >= '0' && __c <= '9') \
|| (__c >= 'A' && __c <= 'F') \
|| (__c >= 'a' && __c <= 'f')); \
})
#endif
#if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
#define c_tolower(c) \
({ int __c = (c); \
(__c >= 'A' && __c <= 'Z' ? __c - 'A' + 'a' : __c); \
})
#define c_toupper(c) \
({ int __c = (c); \
(__c >= 'a' && __c <= 'z' ? __c - 'a' + 'A' : __c); \
})
#endif
#endif /* optimizing for speed */
#endif /* C_CTYPE_H */
=============================== c-ctype.c ===============================
/* Character handling in C locale.
Copyright 2000-2002 Free Software Foundation, Inc.
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 of the License, 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, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */
/* Specification. */
#include "c-ctype.h"
#undef c_isalnum
#undef c_isalpha
#undef c_isascii
#undef c_isblank
#undef c_iscntrl
#undef c_isdigit
#undef c_islower
#undef c_isgraph
#undef c_isprint
#undef c_ispunct
#undef c_isspace
#undef c_isupper
#undef c_isxdigit
#undef c_tolower
#undef c_toupper
/* The function isascii is not locale dependent. Its use in EBCDIC is
questionable. */
bool
c_isascii (int c)
{
return ((c & ~0x7f) == 0);
}
bool
c_isalnum (int c)
{
#if C_CTYPE_CONSECUTIVE_DIGITS \
&& C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
return ((c >= '0' && c <= '9')
|| (c >= 'A' && c <= 'Z')
|| (c >= 'a' && c <= 'z'));
#else
switch (c)
{
case '0': case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9':
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
return 1;
default:
return 0;
}
#endif
}
bool
c_isalpha (int c)
{
#if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
return ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'));
#else
switch (c)
{
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
return 1;
default:
return 0;
}
#endif
}
bool
c_isblank (int c)
{
return (c == ' ' || c == '\t');
}
bool
c_iscntrl (int c)
{
#if C_CTYPE_ASCII
return ((c & ~0x1f) == 0 || c == 0x7f);
#else
switch (c)
{
case ' ': case '!': case '"': case '#': case '$': case '%':
case '&': case '\'': case '(': case ')': case '*': case '+':
case ',': case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9':
case ':': case ';': case '<': case '=': case '>': case '?':
case '@':
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case '[': case '\\': case ']': case '^': case '_': case '`':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
case '{': case '|': case '}': case '~':
return 0;
default:
return 1;
}
#endif
}
bool
c_isdigit (int c)
{
#if C_CTYPE_CONSECUTIVE_DIGITS
return (c >= '0' && c <= '9');
#else
switch (c)
{
case '0': case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9':
return 1;
default:
return 0;
}
#endif
}
bool
c_islower (int c)
{
#if C_CTYPE_CONSECUTIVE_LOWERCASE
return (c >= 'a' && c <= 'z');
#else
switch (c)
{
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
return 1;
default:
return 0;
}
#endif
}
bool
c_isgraph (int c)
{
#if C_CTYPE_ASCII
return (c >= '!' && c <= '~');
#else
switch (c)
{
case '!': case '"': case '#': case '$': case '%': case '&':
case '\'': case '(': case ')': case '*': case '+': case ',':
case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9':
case ':': case ';': case '<': case '=': case '>': case '?':
case '@':
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case '[': case '\\': case ']': case '^': case '_': case '`':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
case '{': case '|': case '}': case '~':
return 1;
default:
return 0;
}
#endif
}
bool
c_isprint (int c)
{
#if C_CTYPE_ASCII
return (c >= ' ' && c <= '~');
#else
switch (c)
{
case ' ': case '!': case '"': case '#': case '$': case '%':
case '&': case '\'': case '(': case ')': case '*': case '+':
case ',': case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9':
case ':': case ';': case '<': case '=': case '>': case '?':
case '@':
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case '[': case '\\': case ']': case '^': case '_': case '`':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
case '{': case '|': case '}': case '~':
return 1;
default:
return 0;
}
#endif
}
bool
c_ispunct (int c)
{
#if C_CTYPE_ASCII
return ((c >= '!' && c <= '~')
&& !((c >= '0' && c <= '9')
|| (c >= 'A' && c <= 'Z')
|| (c >= 'a' && c <= 'z')));
#else
switch (c)
{
case '!': case '"': case '#': case '$': case '%': case '&':
case '\'': case '(': case ')': case '*': case '+': case ',':
case '-': case '.': case '/':
case ':': case ';': case '<': case '=': case '>': case '?':
case '@':
case '[': case '\\': case ']': case '^': case '_': case '`':
case '{': case '|': case '}': case '~':
return 1;
default:
return 0;
}
#endif
}
bool
c_isspace (int c)
{
return (c == ' ' || c == '\t'
|| c == '\n' || c == '\v' || c == '\f' || c == '\r');
}
bool
c_isupper (int c)
{
#if C_CTYPE_CONSECUTIVE_UPPERCASE
return (c >= 'A' && c <= 'Z');
#else
switch (c)
{
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
return 1;
default:
return 0;
}
#endif
}
bool
c_isxdigit (int c)
{
#if C_CTYPE_CONSECUTIVE_DIGITS \
&& C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
return ((c >= '0' && c <= '9')
|| (c >= 'A' && c <= 'F')
|| (c >= 'a' && c <= 'f'));
#else
switch (c)
{
case '0': case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9':
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
return 1;
default:
return 0;
}
#endif
}
int
c_tolower (int c)
{
#if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
return (c >= 'A' && c <= 'Z' ? c - 'A' + 'a' : c);
#else
switch (c)
{
case 'A': return 'a';
case 'B': return 'b';
case 'C': return 'c';
case 'D': return 'd';
case 'E': return 'e';
case 'F': return 'f';
case 'G': return 'g';
case 'H': return 'h';
case 'I': return 'i';
case 'J': return 'j';
case 'K': return 'k';
case 'L': return 'l';
case 'M': return 'm';
case 'N': return 'n';
case 'O': return 'o';
case 'P': return 'p';
case 'Q': return 'q';
case 'R': return 'r';
case 'S': return 's';
case 'T': return 't';
case 'U': return 'u';
case 'V': return 'v';
case 'W': return 'w';
case 'X': return 'x';
case 'Y': return 'y';
case 'Z': return 'z';
default: return c;
}
#endif
}
int
c_toupper (int c)
{
#if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
return (c >= 'a' && c <= 'z' ? c - 'a' + 'A' : c);
#else
switch (c)
{
case 'a': return 'A';
case 'b': return 'B';
case 'c': return 'C';
case 'd': return 'D';
case 'e': return 'E';
case 'f': return 'F';
case 'g': return 'G';
case 'h': return 'H';
case 'i': return 'I';
case 'j': return 'J';
case 'k': return 'K';
case 'l': return 'L';
case 'm': return 'M';
case 'n': return 'N';
case 'o': return 'O';
case 'p': return 'P';
case 'q': return 'Q';
case 'r': return 'R';
case 's': return 'S';
case 't': return 'T';
case 'u': return 'U';
case 'v': return 'V';
case 'w': return 'W';
case 'x': return 'X';
case 'y': return 'Y';
case 'z': return 'Z';
default: return c;
}
#endif
}
- [Bug-gnulib] addition: c-ctype.h, c-ctype.c,
Bruno Haible <=
- Re: [Bug-gnulib] addition: c-ctype.h, c-ctype.c, Paul Eggert, 2003/01/27
- Re: [Bug-gnulib] addition: c-ctype.h, c-ctype.c, Bruno Haible, 2003/01/28
- Re: [Bug-gnulib] addition: c-ctype.h, c-ctype.c, Paul Eggert, 2003/01/28
- Re: [Bug-gnulib] addition: c-ctype.h, c-ctype.c, Bruno Haible, 2003/01/28
- Re: [Bug-gnulib] addition: c-ctype.h, c-ctype.c, Paul Eggert, 2003/01/28
- Re: [Bug-gnulib] addition: c-ctype.h, c-ctype.c, Bruno Haible, 2003/01/29