- upgrade libidn

This commit is contained in:
giuseppenuc committed 2016-02-26 03:02:52 +01:00
1 parent 2b8d4ff66b
commit 9ef9394bd0
1015 files changed
+44748 -132401

No files matched your search

+395
View File
@@ -0,0 +1,395 @@
/* Character handling in C locale.
Copyright 2000-2003, 2006, 2009-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#define NO_C_CTYPE_MACROS
#include "c-ctype.h"
/* The function isascii is not locale dependent. Its use in EBCDIC is
questionable. */
bool
c_isascii (int c)
{
return (c >= 0x00 && c <= 0x7f);
}
bool
c_isalnum (int c)
{
#if C_CTYPE_CONSECUTIVE_DIGITS \
&& C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
#if C_CTYPE_ASCII
return ((c >= '0' && c <= '9')
|| ((c & ~0x20) >= 'A' && (c & ~0x20) <= 'Z'));
#else
return ((c >= '0' && c <= '9')
|| (c >= 'A' && c <= 'Z')
|| (c >= 'a' && c <= 'z'));
#endif
#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
#if C_CTYPE_ASCII
return ((c & ~0x20) >= 'A' && (c & ~0x20) <= 'Z');
#else
return ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'));
#endif
#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 '$': case '%':
case '&': case '\'': case '(': case ')': case '*': case '+':
case ',': case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4': case '5':
case '6': case '7': case '8': case '9':
case ':': case ';': case '<': case '=': case '>': case '?':
case '@':
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case '[': case '\\': case ']': case '^': case '_': case '`':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
case '{': case '|': case '}': case '~':
return 1;
default:
return 0;
}
#endif
}
bool
c_ispunct (int c)
{
#if C_CTYPE_ASCII
return ((c >= '!' && c <= '~')
&& !((c >= '0' && c <= '9')
|| ((c & ~0x20) >= 'A' && (c & ~0x20) <= 'Z')));
#else
switch (c)
{
case '!': case '"': case '#': case '$': 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
#if C_CTYPE_ASCII
return ((c >= '0' && c <= '9')
|| ((c & ~0x20) >= 'A' && (c & ~0x20) <= 'F'));
#else
return ((c >= '0' && c <= '9')
|| (c >= 'A' && c <= 'F')
|| (c >= 'a' && c <= 'f'));
#endif
#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
}
+295
View File
@@ -0,0 +1,295 @@
/* 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) 2000-2003, 2006, 2008-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#ifndef C_CTYPE_H
#define C_CTYPE_H
#include <stdbool.h>
#ifdef __cplusplus
extern "C" {
#endif
/* 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. */
/* Check whether the ASCII optimizations apply. */
/* ANSI C89 (and ISO C99 5.2.1.3 too) already guarantees that
'0', '1', ..., '9' have consecutive integer values. */
#define C_CTYPE_CONSECUTIVE_DIGITS 1
#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 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
#endif
/* Function declarations. */
/* Unlike the functions in <ctype.h>, 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 <ctype.h> 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)) ...
*/
extern bool c_isascii (int c) _GL_ATTRIBUTE_CONST; /* not locale dependent */
extern bool c_isalnum (int c) _GL_ATTRIBUTE_CONST;
extern bool c_isalpha (int c) _GL_ATTRIBUTE_CONST;
extern bool c_isblank (int c) _GL_ATTRIBUTE_CONST;
extern bool c_iscntrl (int c) _GL_ATTRIBUTE_CONST;
extern bool c_isdigit (int c) _GL_ATTRIBUTE_CONST;
extern bool c_islower (int c) _GL_ATTRIBUTE_CONST;
extern bool c_isgraph (int c) _GL_ATTRIBUTE_CONST;
extern bool c_isprint (int c) _GL_ATTRIBUTE_CONST;
extern bool c_ispunct (int c) _GL_ATTRIBUTE_CONST;
extern bool c_isspace (int c) _GL_ATTRIBUTE_CONST;
extern bool c_isupper (int c) _GL_ATTRIBUTE_CONST;
extern bool c_isxdigit (int c) _GL_ATTRIBUTE_CONST;
extern int c_tolower (int c) _GL_ATTRIBUTE_CONST;
extern int c_toupper (int c) _GL_ATTRIBUTE_CONST;
#if (defined __GNUC__ && !defined __STRICT_ANSI__ && defined __OPTIMIZE__ \
&& !defined __OPTIMIZE_SIZE__ && !defined NO_C_CTYPE_MACROS)
/* ASCII optimizations. */
#undef c_isascii
#define c_isascii(c) \
({ int __c = (c); \
(__c >= 0x00 && __c <= 0x7f); \
})
#if C_CTYPE_CONSECUTIVE_DIGITS \
&& C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
#if C_CTYPE_ASCII
#undef c_isalnum
#define c_isalnum(c) \
({ int __c = (c); \
((__c >= '0' && __c <= '9') \
|| ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'Z')); \
})
#else
#undef c_isalnum
#define c_isalnum(c) \
({ int __c = (c); \
((__c >= '0' && __c <= '9') \
|| (__c >= 'A' && __c <= 'Z') \
|| (__c >= 'a' && __c <= 'z')); \
})
#endif
#endif
#if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
#if C_CTYPE_ASCII
#undef c_isalpha
#define c_isalpha(c) \
({ int __c = (c); \
((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'Z'); \
})
#else
#undef c_isalpha
#define c_isalpha(c) \
({ int __c = (c); \
((__c >= 'A' && __c <= 'Z') || (__c >= 'a' && __c <= 'z')); \
})
#endif
#endif
#undef c_isblank
#define c_isblank(c) \
({ int __c = (c); \
(__c == ' ' || __c == '\t'); \
})
#if C_CTYPE_ASCII
#undef c_iscntrl
#define c_iscntrl(c) \
({ int __c = (c); \
((__c & ~0x1f) == 0 || __c == 0x7f); \
})
#endif
#if C_CTYPE_CONSECUTIVE_DIGITS
#undef c_isdigit
#define c_isdigit(c) \
({ int __c = (c); \
(__c >= '0' && __c <= '9'); \
})
#endif
#if C_CTYPE_CONSECUTIVE_LOWERCASE
#undef c_islower
#define c_islower(c) \
({ int __c = (c); \
(__c >= 'a' && __c <= 'z'); \
})
#endif
#if C_CTYPE_ASCII
#undef c_isgraph
#define c_isgraph(c) \
({ int __c = (c); \
(__c >= '!' && __c <= '~'); \
})
#endif
#if C_CTYPE_ASCII
#undef c_isprint
#define c_isprint(c) \
({ int __c = (c); \
(__c >= ' ' && __c <= '~'); \
})
#endif
#if C_CTYPE_ASCII
#undef c_ispunct
#define c_ispunct(c) \
({ int _c = (c); \
(c_isgraph (_c) && ! c_isalnum (_c)); \
})
#endif
#undef c_isspace
#define c_isspace(c) \
({ int __c = (c); \
(__c == ' ' || __c == '\t' \
|| __c == '\n' || __c == '\v' || __c == '\f' || __c == '\r'); \
})
#if C_CTYPE_CONSECUTIVE_UPPERCASE
#undef c_isupper
#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
#if C_CTYPE_ASCII
#undef c_isxdigit
#define c_isxdigit(c) \
({ int __c = (c); \
((__c >= '0' && __c <= '9') \
|| ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'F')); \
})
#else
#undef c_isxdigit
#define c_isxdigit(c) \
({ int __c = (c); \
((__c >= '0' && __c <= '9') \
|| (__c >= 'A' && __c <= 'F') \
|| (__c >= 'a' && __c <= 'f')); \
})
#endif
#endif
#if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
#undef c_tolower
#define c_tolower(c) \
({ int __c = (c); \
(__c >= 'A' && __c <= 'Z' ? __c - 'A' + 'a' : __c); \
})
#undef c_toupper
#define c_toupper(c) \
({ int __c = (c); \
(__c >= 'a' && __c <= 'z' ? __c - 'a' + 'A' : __c); \
})
#endif
#endif /* optimizing for speed */
#ifdef __cplusplus
}
#endif
#endif /* C_CTYPE_H */
+56
View File
@@ -0,0 +1,56 @@
/* Case-insensitive string comparison functions in C locale.
Copyright (C) 1995-1996, 2001, 2003, 2005, 2009-2015 Free Software
Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#ifndef C_STRCASE_H
#define C_STRCASE_H
#include <stddef.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. More precisely, one of the string arguments must be an ASCII
string; the other one can also contain non-ASCII characters (but then
the comparison result will be nonzero). */
#ifdef __cplusplus
extern "C" {
#endif
/* Compare strings S1 and S2, ignoring case, returning less than, equal to or
greater than zero if S1 is lexicographically less than, equal to or greater
than S2. */
extern int c_strcasecmp (const char *s1, const char *s2) _GL_ATTRIBUTE_PURE;
/* Compare no more than N characters of strings S1 and S2, ignoring case,
returning less than, equal to or greater than zero if S1 is
lexicographically less than, equal to or greater than S2. */
extern int c_strncasecmp (const char *s1, const char *s2, size_t n)
_GL_ATTRIBUTE_PURE;
#ifdef __cplusplus
}
#endif
#endif /* C_STRCASE_H */
+56
View File
@@ -0,0 +1,56 @@
/* c-strcasecmp.c -- case insensitive string comparator in C locale
Copyright (C) 1998-1999, 2005-2006, 2009-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "c-strcase.h"
#include <limits.h>
#include "c-ctype.h"
int
c_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 (c1 > c2 ? 1 : c1 < c2 ? -1 : 0);
}
+56
View File
@@ -0,0 +1,56 @@
/* c-strncasecmp.c -- case insensitive string comparator in C locale
Copyright (C) 1998-1999, 2005-2006, 2009-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "c-strcase.h"
#include <limits.h>
#include "c-ctype.h"
int
c_strncasecmp (const char *s1, const char *s2, size_t n)
{
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 || n == 0)
return 0;
do
{
c1 = c_tolower (*p1);
c2 = c_tolower (*p2);
if (--n == 0 || 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 (c1 > c2 ? 1 : c1 < c2 ? -1 : 0);
}
+110
View File
@@ -0,0 +1,110 @@
/* Convenience header for conditional use of GNU <libintl.h>.
Copyright (C) 1995-1998, 2000-2002, 2004-2006, 2009-2015 Free Software
Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License along
with this program; if not, see <http://www.gnu.org/licenses/>. */
#ifndef _LIBGETTEXT_H
#define _LIBGETTEXT_H 1
/* NLS can be disabled through the configure --disable-nls option. */
#if ENABLE_NLS
/* Get declarations of GNU message catalog functions. */
# include <libintl.h>
/* You can set the DEFAULT_TEXT_DOMAIN macro to specify the domain used by
the gettext() and ngettext() macros. This is an alternative to calling
textdomain(), and is useful for libraries. */
# ifdef DEFAULT_TEXT_DOMAIN
# undef gettext
# define gettext(Msgid) \
dgettext (DEFAULT_TEXT_DOMAIN, Msgid)
# undef ngettext
# define ngettext(Msgid1, Msgid2, N) \
dngettext (DEFAULT_TEXT_DOMAIN, Msgid1, Msgid2, N)
# endif
#else
/* Solaris /usr/include/locale.h includes /usr/include/libintl.h, which
chokes if dcgettext is defined as a macro. So include it now, to make
later inclusions of <locale.h> a NOP. We don't include <libintl.h>
as well because people using "gettext.h" will not include <libintl.h>,
and also including <libintl.h> would fail on SunOS 4, whereas <locale.h>
is OK. */
#if defined(__sun)
# include <locale.h>
#endif
/* Many header files from the libstdc++ coming with g++ 3.3 or newer include
<libintl.h>, which chokes if dcgettext is defined as a macro. So include
it now, to make later inclusions of <libintl.h> a NOP. */
#if defined(__cplusplus) && defined(__GNUG__) && (__GNUC__ >= 3)
# include <cstdlib>
# if (__GLIBC__ >= 2 && !defined __UCLIBC__) || _GLIBCXX_HAVE_LIBINTL_H
# include <libintl.h>
# endif
#endif
/* Disabled NLS.
The casts to 'const char *' serve the purpose of producing warnings
for invalid uses of the value returned from these functions.
On pre-ANSI systems without 'const', the config.h file is supposed to
contain "#define const". */
# undef gettext
# define gettext(Msgid) ((const char *) (Msgid))
# undef dgettext
# define dgettext(Domainname, Msgid) ((void) (Domainname), gettext (Msgid))
# undef dcgettext
# define dcgettext(Domainname, Msgid, Category) \
((void) (Category), dgettext (Domainname, Msgid))
# undef ngettext
# define ngettext(Msgid1, Msgid2, N) \
((N) == 1 \
? ((void) (Msgid2), (const char *) (Msgid1)) \
: ((void) (Msgid1), (const char *) (Msgid2)))
# undef dngettext
# define dngettext(Domainname, Msgid1, Msgid2, N) \
((void) (Domainname), ngettext (Msgid1, Msgid2, N))
# undef dcngettext
# define dcngettext(Domainname, Msgid1, Msgid2, N, Category) \
((void) (Category), dngettext (Domainname, Msgid1, Msgid2, N))
# undef textdomain
# define textdomain(Domainname) ((const char *) (Domainname))
# undef bindtextdomain
# define bindtextdomain(Domainname, Dirname) \
((void) (Domainname), (const char *) (Dirname))
# undef bind_textdomain_codeset
# define bind_textdomain_codeset(Domainname, Codeset) \
((void) (Domainname), (const char *) (Codeset))
#endif
/* Prefer gnulib's setlocale override over libintl's setlocale override. */
#ifdef GNULIB_defined_setlocale
# undef setlocale
# define setlocale rpl_setlocale
#endif
/* A pseudo function call that serves as a marker for the automated
extraction of messages, but does not call gettext(). The run-time
translation is done at a different place in the code.
The argument, String, should be a literal string. Concatenated strings
and other string expressions won't work.
The macro's expansion is not parenthesized, so that it is suitable as
initializer for static 'char[]' or 'const char[]' variables. */
#define gettext_noop(String) String
#endif /* _LIBGETTEXT_H */
+449
View File
@@ -0,0 +1,449 @@
/* Character set conversion.
Copyright (C) 1999-2001, 2007, 2009-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License along
with this program; if not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include <iconv.h>
#include <stddef.h>
#if REPLACE_ICONV_UTF
# include <errno.h>
# include <stdint.h>
# include <stdlib.h>
# include "unistr.h"
# ifndef uintptr_t
# define uintptr_t unsigned long
# endif
#endif
#if REPLACE_ICONV_UTF
/* UTF-{16,32}{BE,LE} converters taken from GNU libiconv 1.11. */
/* Return code if invalid. (xxx_mbtowc) */
# define RET_ILSEQ -1
/* Return code if no bytes were read. (xxx_mbtowc) */
# define RET_TOOFEW -2
/* Return code if invalid. (xxx_wctomb) */
# define RET_ILUNI -1
/* Return code if output buffer is too small. (xxx_wctomb, xxx_reset) */
# define RET_TOOSMALL -2
/*
* UTF-16BE
*/
/* Specification: RFC 2781 */
static int
utf16be_mbtowc (ucs4_t *pwc, const unsigned char *s, size_t n)
{
if (n >= 2)
{
ucs4_t wc = (s[0] << 8) + s[1];
if (wc >= 0xd800 && wc < 0xdc00)
{
if (n >= 4)
{
ucs4_t wc2 = (s[2] << 8) + s[3];
if (!(wc2 >= 0xdc00 && wc2 < 0xe000))
return RET_ILSEQ;
*pwc = 0x10000 + ((wc - 0xd800) << 10) + (wc2 - 0xdc00);
return 4;
}
}
else if (wc >= 0xdc00 && wc < 0xe000)
{
return RET_ILSEQ;
}
else
{
*pwc = wc;
return 2;
}
}
return RET_TOOFEW;
}
static int
utf16be_wctomb (unsigned char *r, ucs4_t wc, size_t n)
{
if (!(wc >= 0xd800 && wc < 0xe000))
{
if (wc < 0x10000)
{
if (n >= 2)
{
r[0] = (unsigned char) (wc >> 8);
r[1] = (unsigned char) wc;
return 2;
}
else
return RET_TOOSMALL;
}
else if (wc < 0x110000)
{
if (n >= 4)
{
ucs4_t wc1 = 0xd800 + ((wc - 0x10000) >> 10);
ucs4_t wc2 = 0xdc00 + ((wc - 0x10000) & 0x3ff);
r[0] = (unsigned char) (wc1 >> 8);
r[1] = (unsigned char) wc1;
r[2] = (unsigned char) (wc2 >> 8);
r[3] = (unsigned char) wc2;
return 4;
}
else
return RET_TOOSMALL;
}
}
return RET_ILUNI;
}
/*
* UTF-16LE
*/
/* Specification: RFC 2781 */
static int
utf16le_mbtowc (ucs4_t *pwc, const unsigned char *s, size_t n)
{
if (n >= 2)
{
ucs4_t wc = s[0] + (s[1] << 8);
if (wc >= 0xd800 && wc < 0xdc00)
{
if (n >= 4)
{
ucs4_t wc2 = s[2] + (s[3] << 8);
if (!(wc2 >= 0xdc00 && wc2 < 0xe000))
return RET_ILSEQ;
*pwc = 0x10000 + ((wc - 0xd800) << 10) + (wc2 - 0xdc00);
return 4;
}
}
else if (wc >= 0xdc00 && wc < 0xe000)
{
return RET_ILSEQ;
}
else
{
*pwc = wc;
return 2;
}
}
return RET_TOOFEW;
}
static int
utf16le_wctomb (unsigned char *r, ucs4_t wc, size_t n)
{
if (!(wc >= 0xd800 && wc < 0xe000))
{
if (wc < 0x10000)
{
if (n >= 2)
{
r[0] = (unsigned char) wc;
r[1] = (unsigned char) (wc >> 8);
return 2;
}
else
return RET_TOOSMALL;
}
else if (wc < 0x110000)
{
if (n >= 4)
{
ucs4_t wc1 = 0xd800 + ((wc - 0x10000) >> 10);
ucs4_t wc2 = 0xdc00 + ((wc - 0x10000) & 0x3ff);
r[0] = (unsigned char) wc1;
r[1] = (unsigned char) (wc1 >> 8);
r[2] = (unsigned char) wc2;
r[3] = (unsigned char) (wc2 >> 8);
return 4;
}
else
return RET_TOOSMALL;
}
}
return RET_ILUNI;
}
/*
* UTF-32BE
*/
/* Specification: Unicode 3.1 Standard Annex #19 */
static int
utf32be_mbtowc (ucs4_t *pwc, const unsigned char *s, size_t n)
{
if (n >= 4)
{
ucs4_t wc = (s[0] << 24) + (s[1] << 16) + (s[2] << 8) + s[3];
if (wc < 0x110000 && !(wc >= 0xd800 && wc < 0xe000))
{
*pwc = wc;
return 4;
}
else
return RET_ILSEQ;
}
return RET_TOOFEW;
}
static int
utf32be_wctomb (unsigned char *r, ucs4_t wc, size_t n)
{
if (wc < 0x110000 && !(wc >= 0xd800 && wc < 0xe000))
{
if (n >= 4)
{
r[0] = 0;
r[1] = (unsigned char) (wc >> 16);
r[2] = (unsigned char) (wc >> 8);
r[3] = (unsigned char) wc;
return 4;
}
else
return RET_TOOSMALL;
}
return RET_ILUNI;
}
/*
* UTF-32LE
*/
/* Specification: Unicode 3.1 Standard Annex #19 */
static int
utf32le_mbtowc (ucs4_t *pwc, const unsigned char *s, size_t n)
{
if (n >= 4)
{
ucs4_t wc = s[0] + (s[1] << 8) + (s[2] << 16) + (s[3] << 24);
if (wc < 0x110000 && !(wc >= 0xd800 && wc < 0xe000))
{
*pwc = wc;
return 4;
}
else
return RET_ILSEQ;
}
return RET_TOOFEW;
}
static int
utf32le_wctomb (unsigned char *r, ucs4_t wc, size_t n)
{
if (wc < 0x110000 && !(wc >= 0xd800 && wc < 0xe000))
{
if (n >= 4)
{
r[0] = (unsigned char) wc;
r[1] = (unsigned char) (wc >> 8);
r[2] = (unsigned char) (wc >> 16);
r[3] = 0;
return 4;
}
else
return RET_TOOSMALL;
}
return RET_ILUNI;
}
#endif
size_t
rpl_iconv (iconv_t cd,
ICONV_CONST char **inbuf, size_t *inbytesleft,
char **outbuf, size_t *outbytesleft)
#undef iconv
{
#if REPLACE_ICONV_UTF
switch ((uintptr_t) cd)
{
{
int (*xxx_wctomb) (unsigned char *, ucs4_t, size_t);
case (uintptr_t) _ICONV_UTF8_UTF16BE:
xxx_wctomb = utf16be_wctomb;
goto loop_from_utf8;
case (uintptr_t) _ICONV_UTF8_UTF16LE:
xxx_wctomb = utf16le_wctomb;
goto loop_from_utf8;
case (uintptr_t) _ICONV_UTF8_UTF32BE:
xxx_wctomb = utf32be_wctomb;
goto loop_from_utf8;
case (uintptr_t) _ICONV_UTF8_UTF32LE:
xxx_wctomb = utf32le_wctomb;
goto loop_from_utf8;
loop_from_utf8:
if (inbuf == NULL || *inbuf == NULL)
return 0;
{
ICONV_CONST char *inptr = *inbuf;
size_t inleft = *inbytesleft;
char *outptr = *outbuf;
size_t outleft = *outbytesleft;
size_t res = 0;
while (inleft > 0)
{
ucs4_t uc;
int m = u8_mbtoucr (&uc, (const uint8_t *) inptr, inleft);
if (m <= 0)
{
if (m == -1)
{
errno = EILSEQ;
res = (size_t)(-1);
break;
}
if (m == -2)
{
errno = EINVAL;
res = (size_t)(-1);
break;
}
abort ();
}
else
{
int n = xxx_wctomb ((uint8_t *) outptr, uc, outleft);
if (n < 0)
{
if (n == RET_ILUNI)
{
errno = EILSEQ;
res = (size_t)(-1);
break;
}
if (n == RET_TOOSMALL)
{
errno = E2BIG;
res = (size_t)(-1);
break;
}
abort ();
}
else
{
inptr += m;
inleft -= m;
outptr += n;
outleft -= n;
}
}
}
*inbuf = inptr;
*inbytesleft = inleft;
*outbuf = outptr;
*outbytesleft = outleft;
return res;
}
}
{
int (*xxx_mbtowc) (ucs4_t *, const unsigned char *, size_t);
case (uintptr_t) _ICONV_UTF16BE_UTF8:
xxx_mbtowc = utf16be_mbtowc;
goto loop_to_utf8;
case (uintptr_t) _ICONV_UTF16LE_UTF8:
xxx_mbtowc = utf16le_mbtowc;
goto loop_to_utf8;
case (uintptr_t) _ICONV_UTF32BE_UTF8:
xxx_mbtowc = utf32be_mbtowc;
goto loop_to_utf8;
case (uintptr_t) _ICONV_UTF32LE_UTF8:
xxx_mbtowc = utf32le_mbtowc;
goto loop_to_utf8;
loop_to_utf8:
if (inbuf == NULL || *inbuf == NULL)
return 0;
{
ICONV_CONST char *inptr = *inbuf;
size_t inleft = *inbytesleft;
char *outptr = *outbuf;
size_t outleft = *outbytesleft;
size_t res = 0;
while (inleft > 0)
{
ucs4_t uc;
int m = xxx_mbtowc (&uc, (const uint8_t *) inptr, inleft);
if (m <= 0)
{
if (m == RET_ILSEQ)
{
errno = EILSEQ;
res = (size_t)(-1);
break;
}
if (m == RET_TOOFEW)
{
errno = EINVAL;
res = (size_t)(-1);
break;
}
abort ();
}
else
{
int n = u8_uctomb ((uint8_t *) outptr, uc, outleft);
if (n < 0)
{
if (n == -1)
{
errno = EILSEQ;
res = (size_t)(-1);
break;
}
if (n == -2)
{
errno = E2BIG;
res = (size_t)(-1);
break;
}
abort ();
}
else
{
inptr += m;
inleft -= m;
outptr += n;
outleft -= n;
}
}
}
*inbuf = inptr;
*inbytesleft = inleft;
*outbuf = outptr;
*outbytesleft = outleft;
return res;
}
}
}
#endif
return iconv (cd, inbuf, inbytesleft, outbuf, outbytesleft);
}
+110
View File
@@ -0,0 +1,110 @@
/* A GNU-like <iconv.h>.
Copyright (C) 2007-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#ifndef _@GUARD_PREFIX@_ICONV_H
#if __GNUC__ >= 3
@PRAGMA_SYSTEM_HEADER@
#endif
@PRAGMA_COLUMNS@
/* The include_next requires a split double-inclusion guard. */
#@INCLUDE_NEXT@ @NEXT_ICONV_H@
#ifndef _@GUARD_PREFIX@_ICONV_H
#define _@GUARD_PREFIX@_ICONV_H
/* The definitions of _GL_FUNCDECL_RPL etc. are copied here. */
/* The definition of _GL_ARG_NONNULL is copied here. */
/* The definition of _GL_WARN_ON_USE is copied here. */
#if @GNULIB_ICONV@
# if @REPLACE_ICONV_OPEN@
/* An iconv_open wrapper that supports the IANA standardized encoding names
("ISO-8859-1" etc.) as far as possible. */
# if !(defined __cplusplus && defined GNULIB_NAMESPACE)
# define iconv_open rpl_iconv_open
# endif
_GL_FUNCDECL_RPL (iconv_open, iconv_t,
(const char *tocode, const char *fromcode)
_GL_ARG_NONNULL ((1, 2)));
_GL_CXXALIAS_RPL (iconv_open, iconv_t,
(const char *tocode, const char *fromcode));
# else
_GL_CXXALIAS_SYS (iconv_open, iconv_t,
(const char *tocode, const char *fromcode));
# endif
_GL_CXXALIASWARN (iconv_open);
#endif
#if @REPLACE_ICONV_UTF@
/* Special constants for supporting UTF-{16,32}{BE,LE} encodings.
Not public. */
# define _ICONV_UTF8_UTF16BE (iconv_t)(-161)
# define _ICONV_UTF8_UTF16LE (iconv_t)(-162)
# define _ICONV_UTF8_UTF32BE (iconv_t)(-163)
# define _ICONV_UTF8_UTF32LE (iconv_t)(-164)
# define _ICONV_UTF16BE_UTF8 (iconv_t)(-165)
# define _ICONV_UTF16LE_UTF8 (iconv_t)(-166)
# define _ICONV_UTF32BE_UTF8 (iconv_t)(-167)
# define _ICONV_UTF32LE_UTF8 (iconv_t)(-168)
#endif
#if @GNULIB_ICONV@
# if @REPLACE_ICONV@
# if !(defined __cplusplus && defined GNULIB_NAMESPACE)
# define iconv rpl_iconv
# endif
_GL_FUNCDECL_RPL (iconv, size_t,
(iconv_t cd,
@ICONV_CONST@ char **inbuf, size_t *inbytesleft,
char **outbuf, size_t *outbytesleft));
_GL_CXXALIAS_RPL (iconv, size_t,
(iconv_t cd,
@ICONV_CONST@ char **inbuf, size_t *inbytesleft,
char **outbuf, size_t *outbytesleft));
# else
_GL_CXXALIAS_SYS (iconv, size_t,
(iconv_t cd,
@ICONV_CONST@ char **inbuf, size_t *inbytesleft,
char **outbuf, size_t *outbytesleft));
# endif
_GL_CXXALIASWARN (iconv);
# ifndef ICONV_CONST
# define ICONV_CONST @ICONV_CONST@
# endif
#endif
#if @GNULIB_ICONV@
# if @REPLACE_ICONV@
# if !(defined __cplusplus && defined GNULIB_NAMESPACE)
# define iconv_close rpl_iconv_close
# endif
_GL_FUNCDECL_RPL (iconv_close, int, (iconv_t cd));
_GL_CXXALIAS_RPL (iconv_close, int, (iconv_t cd));
# else
_GL_CXXALIAS_SYS (iconv_close, int, (iconv_t cd));
# endif
_GL_CXXALIASWARN (iconv_close);
#endif
#endif /* _@GUARD_PREFIX@_ICONV_H */
#endif /* _@GUARD_PREFIX@_ICONV_H */
+46
View File
@@ -0,0 +1,46 @@
/* Character set conversion.
Copyright (C) 2007, 2009-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License along
with this program; if not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include <iconv.h>
#include <stdint.h>
#ifndef uintptr_t
# define uintptr_t unsigned long
#endif
int
rpl_iconv_close (iconv_t cd)
#undef iconv_close
{
#if REPLACE_ICONV_UTF
switch ((uintptr_t) cd)
{
case (uintptr_t) _ICONV_UTF8_UTF16BE:
case (uintptr_t) _ICONV_UTF8_UTF16LE:
case (uintptr_t) _ICONV_UTF8_UTF32BE:
case (uintptr_t) _ICONV_UTF8_UTF32LE:
case (uintptr_t) _ICONV_UTF16BE_UTF8:
case (uintptr_t) _ICONV_UTF16LE_UTF8:
case (uintptr_t) _ICONV_UTF32BE_UTF8:
case (uintptr_t) _ICONV_UTF32LE_UTF8:
return 0;
}
#endif
return iconv_close (cd);
}
+172
View File
@@ -0,0 +1,172 @@
/* Character set conversion.
Copyright (C) 2007, 2009-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License along
with this program; if not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include <iconv.h>
#include <errno.h>
#include <string.h>
#include "c-ctype.h"
#include "c-strcase.h"
#define SIZEOF(a) (sizeof(a) / sizeof(a[0]))
/* Namespace cleanliness. */
#define mapping_lookup rpl_iconv_open_mapping_lookup
/* The macro ICONV_FLAVOR is defined to one of these or undefined. */
#define ICONV_FLAVOR_AIX "iconv_open-aix.h"
#define ICONV_FLAVOR_HPUX "iconv_open-hpux.h"
#define ICONV_FLAVOR_IRIX "iconv_open-irix.h"
#define ICONV_FLAVOR_OSF "iconv_open-osf.h"
#define ICONV_FLAVOR_SOLARIS "iconv_open-solaris.h"
#ifdef ICONV_FLAVOR
# include ICONV_FLAVOR
#endif
iconv_t
rpl_iconv_open (const char *tocode, const char *fromcode)
#undef iconv_open
{
char fromcode_upper[32];
char tocode_upper[32];
char *fromcode_upper_end;
char *tocode_upper_end;
#if REPLACE_ICONV_UTF
/* Special handling of conversion between UTF-8 and UTF-{16,32}{BE,LE}.
Do this here, before calling the real iconv_open(), because OSF/1 5.1
iconv() to these encoding inserts a BOM, which is wrong.
We do not need to handle conversion between arbitrary encodings and
UTF-{16,32}{BE,LE}, because the 'striconveh' module implements two-step
conversion through UTF-8.
The _ICONV_* constants are chosen to be disjoint from any iconv_t
returned by the system's iconv_open() functions. Recall that iconv_t
is a scalar type. */
if (c_toupper (fromcode[0]) == 'U'
&& c_toupper (fromcode[1]) == 'T'
&& c_toupper (fromcode[2]) == 'F'
&& fromcode[3] == '-')
{
if (c_toupper (tocode[0]) == 'U'
&& c_toupper (tocode[1]) == 'T'
&& c_toupper (tocode[2]) == 'F'
&& tocode[3] == '-')
{
if (strcmp (fromcode + 4, "8") == 0)
{
if (c_strcasecmp (tocode + 4, "16BE") == 0)
return _ICONV_UTF8_UTF16BE;
if (c_strcasecmp (tocode + 4, "16LE") == 0)
return _ICONV_UTF8_UTF16LE;
if (c_strcasecmp (tocode + 4, "32BE") == 0)
return _ICONV_UTF8_UTF32BE;
if (c_strcasecmp (tocode + 4, "32LE") == 0)
return _ICONV_UTF8_UTF32LE;
}
else if (strcmp (tocode + 4, "8") == 0)
{
if (c_strcasecmp (fromcode + 4, "16BE") == 0)
return _ICONV_UTF16BE_UTF8;
if (c_strcasecmp (fromcode + 4, "16LE") == 0)
return _ICONV_UTF16LE_UTF8;
if (c_strcasecmp (fromcode + 4, "32BE") == 0)
return _ICONV_UTF32BE_UTF8;
if (c_strcasecmp (fromcode + 4, "32LE") == 0)
return _ICONV_UTF32LE_UTF8;
}
}
}
#endif
/* Do *not* add special support for 8-bit encodings like ASCII or ISO-8859-1
here. This would lead to programs that work in some locales (such as the
"C" or "en_US" locales) but do not work in East Asian locales. It is
better if programmers make their programs depend on GNU libiconv (except
on glibc systems), e.g. by using the AM_ICONV macro and documenting the
dependency in an INSTALL or DEPENDENCIES file. */
/* Try with the original names first.
This covers the case when fromcode or tocode is a lowercase encoding name
that is understood by the system's iconv_open but not listed in our
mappings table. */
{
iconv_t cd = iconv_open (tocode, fromcode);
if (cd != (iconv_t)(-1))
return cd;
}
/* Convert the encodings to upper case, because
1. in the arguments of iconv_open() on AIX, HP-UX, and OSF/1 the case
matters,
2. it makes searching in the table faster. */
{
const char *p = fromcode;
char *q = fromcode_upper;
while ((*q = c_toupper (*p)) != '\0')
{
p++;
q++;
if (q == &fromcode_upper[SIZEOF (fromcode_upper)])
{
errno = EINVAL;
return (iconv_t)(-1);
}
}
fromcode_upper_end = q;
}
{
const char *p = tocode;
char *q = tocode_upper;
while ((*q = c_toupper (*p)) != '\0')
{
p++;
q++;
if (q == &tocode_upper[SIZEOF (tocode_upper)])
{
errno = EINVAL;
return (iconv_t)(-1);
}
}
tocode_upper_end = q;
}
#ifdef ICONV_FLAVOR
/* Apply the mappings. */
{
const struct mapping *m =
mapping_lookup (fromcode_upper, fromcode_upper_end - fromcode_upper);
fromcode = (m != NULL ? m->vendor_name : fromcode_upper);
}
{
const struct mapping *m =
mapping_lookup (tocode_upper, tocode_upper_end - tocode_upper);
tocode = (m != NULL ? m->vendor_name : tocode_upper);
}
#else
fromcode = fromcode_upper;
tocode = tocode_upper;
#endif
return iconv_open (tocode, fromcode);
}
+132
View File
@@ -0,0 +1,132 @@
/* Copyright (C) 2001-2003, 2006-2015 Free Software Foundation, Inc.
Written by Bruno Haible <haible@clisp.cons.org>, 2001.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#ifndef _GL_STDBOOL_H
#define _GL_STDBOOL_H
/* ISO C 99 <stdbool.h> for platforms that lack it. */
/* Usage suggestions:
Programs that use <stdbool.h> should be aware of some limitations
and standards compliance issues.
Standards compliance:
- <stdbool.h> must be #included before 'bool', 'false', 'true'
can be used.
- You cannot assume that sizeof (bool) == 1.
- Programs should not undefine the macros bool, true, and false,
as C99 lists that as an "obsolescent feature".
Limitations of this substitute, when used in a C89 environment:
- <stdbool.h> must be #included before the '_Bool' type can be used.
- You cannot assume that _Bool is a typedef; it might be a macro.
- Bit-fields of type 'bool' are not supported. Portable code
should use 'unsigned int foo : 1;' rather than 'bool foo : 1;'.
- In C99, casts and automatic conversions to '_Bool' or 'bool' are
performed in such a way that every nonzero value gets converted
to 'true', and zero gets converted to 'false'. This doesn't work
with this substitute. With this substitute, only the values 0 and 1
give the expected result when converted to _Bool' or 'bool'.
- C99 allows the use of (_Bool)0.0 in constant expressions, but
this substitute cannot always provide this property.
Also, it is suggested that programs use 'bool' rather than '_Bool';
this isn't required, but 'bool' is more common. */
/* 7.16. Boolean type and values */
/* BeOS <sys/socket.h> already #defines false 0, true 1. We use the same
definitions below, but temporarily we have to #undef them. */
#if defined __BEOS__ && !defined __HAIKU__
# include <OS.h> /* defines bool but not _Bool */
# undef false
# undef true
#endif
#ifdef __cplusplus
# define _Bool bool
# define bool bool
#else
# if defined __BEOS__ && !defined __HAIKU__
/* A compiler known to have 'bool'. */
/* If the compiler already has both 'bool' and '_Bool', we can assume they
are the same types. */
# if !@HAVE__BOOL@
typedef bool _Bool;
# endif
# else
# if !defined __GNUC__
/* If @HAVE__BOOL@:
Some HP-UX cc and AIX IBM C compiler versions have compiler bugs when
the built-in _Bool type is used. See
http://gcc.gnu.org/ml/gcc-patches/2003-12/msg02303.html
http://lists.gnu.org/archive/html/bug-coreutils/2005-11/msg00161.html
http://lists.gnu.org/archive/html/bug-coreutils/2005-10/msg00086.html
Similar bugs are likely with other compilers as well; this file
wouldn't be used if <stdbool.h> was working.
So we override the _Bool type.
If !@HAVE__BOOL@:
Need to define _Bool ourselves. As 'signed char' or as an enum type?
Use of a typedef, with SunPRO C, leads to a stupid
"warning: _Bool is a keyword in ISO C99".
Use of an enum type, with IRIX cc, leads to a stupid
"warning(1185): enumerated type mixed with another type".
Even the existence of an enum type, without a typedef,
"Invalid enumerator. (badenum)" with HP-UX cc on Tru64.
The only benefit of the enum, debuggability, is not important
with these compilers. So use 'signed char' and no enum. */
# define _Bool signed char
# else
/* With this compiler, trust the _Bool type if the compiler has it. */
# if !@HAVE__BOOL@
/* For the sake of symbolic names in gdb, define true and false as
enum constants, not only as macros.
It is tempting to write
typedef enum { false = 0, true = 1 } _Bool;
so that gdb prints values of type 'bool' symbolically. But then
values of type '_Bool' might promote to 'int' or 'unsigned int'
(see ISO C 99 6.7.2.2.(4)); however, '_Bool' must promote to 'int'
(see ISO C 99 6.3.1.1.(2)). So add a negative value to the
enum; this ensures that '_Bool' promotes to 'int'. */
typedef enum { _Bool_must_promote_to_int = -1, false = 0, true = 1 } _Bool;
# endif
# endif
# endif
# define bool _Bool
#endif
/* The other macros must be usable in preprocessor directives. */
#ifdef __cplusplus
# define false false
# define true true
#else
# define false 0
# define true 1
#endif
#define __bool_true_false_are_defined 1
#endif /* _GL_STDBOOL_H */
+108
View File
@@ -0,0 +1,108 @@
/* A substitute for POSIX 2008 <stddef.h>, for platforms that have issues.
Copyright (C) 2009-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
/* Written by Eric Blake. */
/*
* POSIX 2008 <stddef.h> for platforms that have issues.
* <http://www.opengroup.org/susv3xbd/stddef.h.html>
*/
#if __GNUC__ >= 3
@PRAGMA_SYSTEM_HEADER@
#endif
@PRAGMA_COLUMNS@
#if defined __need_wchar_t || defined __need_size_t \
|| defined __need_ptrdiff_t || defined __need_NULL \
|| defined __need_wint_t
/* Special invocation convention inside gcc header files. In
particular, gcc provides a version of <stddef.h> that blindly
redefines NULL even when __need_wint_t was defined, even though
wint_t is not normally provided by <stddef.h>. Hence, we must
remember if special invocation has ever been used to obtain wint_t,
in which case we need to clean up NULL yet again. */
# if !(defined _@GUARD_PREFIX@_STDDEF_H && defined _GL_STDDEF_WINT_T)
# ifdef __need_wint_t
# define _GL_STDDEF_WINT_T
# endif
# @INCLUDE_NEXT@ @NEXT_STDDEF_H@
# endif
#else
/* Normal invocation convention. */
# ifndef _@GUARD_PREFIX@_STDDEF_H
/* The include_next requires a split double-inclusion guard. */
# @INCLUDE_NEXT@ @NEXT_STDDEF_H@
/* On NetBSD 5.0, the definition of NULL lacks proper parentheses. */
# if (@REPLACE_NULL@ \
&& (!defined _@GUARD_PREFIX@_STDDEF_H || defined _GL_STDDEF_WINT_T))
# undef NULL
# ifdef __cplusplus
/* ISO C++ says that the macro NULL must expand to an integer constant
expression, hence '((void *) 0)' is not allowed in C++. */
# if __GNUG__ >= 3
/* GNU C++ has a __null macro that behaves like an integer ('int' or
'long') but has the same size as a pointer. Use that, to avoid
warnings. */
# define NULL __null
# else
# define NULL 0L
# endif
# else
# define NULL ((void *) 0)
# endif
# endif
# ifndef _@GUARD_PREFIX@_STDDEF_H
# define _@GUARD_PREFIX@_STDDEF_H
/* Some platforms lack wchar_t. */
#if !@HAVE_WCHAR_T@
# define wchar_t int
#endif
/* Some platforms lack max_align_t. */
#if !@HAVE_MAX_ALIGN_T@
/* On the x86, the maximum storage alignment of double, long, etc. is 4,
but GCC's C11 ABI for x86 says that max_align_t has an alignment of 8,
and the C11 standard allows this. Work around this problem by
using __alignof__ (which returns 8 for double) rather than _Alignof
(which returns 4), and align each union member accordingly. */
# ifdef __GNUC__
# define _GL_STDDEF_ALIGNAS(type) \
__attribute__ ((__aligned__ (__alignof__ (type))))
# else
# define _GL_STDDEF_ALIGNAS(type) /* */
# endif
typedef union
{
char *__p _GL_STDDEF_ALIGNAS (char *);
double __d _GL_STDDEF_ALIGNAS (double);
long double __ld _GL_STDDEF_ALIGNAS (long double);
long int __i _GL_STDDEF_ALIGNAS (long int);
} max_align_t;
#endif
# endif /* _@GUARD_PREFIX@_STDDEF_H */
# endif /* _@GUARD_PREFIX@_STDDEF_H */
#endif /* __need_XXX */
+636
View File
@@ -0,0 +1,636 @@
/* Copyright (C) 2001-2002, 2004-2015 Free Software Foundation, Inc.
Written by Paul Eggert, Bruno Haible, Sam Steingold, Peter Burwood.
This file is part of gnulib.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
/*
* ISO C 99 <stdint.h> for platforms that lack it.
* <http://www.opengroup.org/susv3xbd/stdint.h.html>
*/
#ifndef _@GUARD_PREFIX@_STDINT_H
#if __GNUC__ >= 3
@PRAGMA_SYSTEM_HEADER@
#endif
@PRAGMA_COLUMNS@
/* When including a system file that in turn includes <inttypes.h>,
use the system <inttypes.h>, not our substitute. This avoids
problems with (for example) VMS, whose <sys/bitypes.h> includes
<inttypes.h>. */
#define _GL_JUST_INCLUDE_SYSTEM_INTTYPES_H
/* On Android (Bionic libc), <sys/types.h> includes this file before
having defined 'time_t'. Therefore in this case avoid including
other system header files; just include the system's <stdint.h>.
Ideally we should test __BIONIC__ here, but it is only defined after
<sys/cdefs.h> has been included; hence test __ANDROID__ instead. */
#if defined __ANDROID__ && defined _GL_INCLUDING_SYS_TYPES_H
# @INCLUDE_NEXT@ @NEXT_STDINT_H@
#else
/* Get those types that are already defined in other system include
files, so that we can "#define int8_t signed char" below without
worrying about a later system include file containing a "typedef
signed char int8_t;" that will get messed up by our macro. Our
macros should all be consistent with the system versions, except
for the "fast" types and macros, which we recommend against using
in public interfaces due to compiler differences. */
#if @HAVE_STDINT_H@
# if defined __sgi && ! defined __c99
/* Bypass IRIX's <stdint.h> if in C89 mode, since it merely annoys users
with "This header file is to be used only for c99 mode compilations"
diagnostics. */
# define __STDINT_H__
# endif
/* Some pre-C++11 <stdint.h> implementations need this. */
# ifdef __cplusplus
# ifndef __STDC_CONSTANT_MACROS
# define __STDC_CONSTANT_MACROS 1
# endif
# ifndef __STDC_LIMIT_MACROS
# define __STDC_LIMIT_MACROS 1
# endif
# endif
/* Other systems may have an incomplete or buggy <stdint.h>.
Include it before <inttypes.h>, since any "#include <stdint.h>"
in <inttypes.h> would reinclude us, skipping our contents because
_@GUARD_PREFIX@_STDINT_H is defined.
The include_next requires a split double-inclusion guard. */
# @INCLUDE_NEXT@ @NEXT_STDINT_H@
#endif
#if ! defined _@GUARD_PREFIX@_STDINT_H && ! defined _GL_JUST_INCLUDE_SYSTEM_STDINT_H
#define _@GUARD_PREFIX@_STDINT_H
/* <sys/types.h> defines some of the stdint.h types as well, on glibc,
IRIX 6.5, and OpenBSD 3.8 (via <machine/types.h>).
AIX 5.2 <sys/types.h> isn't needed and causes troubles.
Mac OS X 10.4.6 <sys/types.h> includes <stdint.h> (which is us), but
relies on the system <stdint.h> definitions, so include
<sys/types.h> after @NEXT_STDINT_H@. */
#if @HAVE_SYS_TYPES_H@ && ! defined _AIX
# include <sys/types.h>
#endif
/* Get SCHAR_MIN, SCHAR_MAX, UCHAR_MAX, INT_MIN, INT_MAX,
LONG_MIN, LONG_MAX, ULONG_MAX. */
#include <limits.h>
#if @HAVE_INTTYPES_H@
/* In OpenBSD 3.8, <inttypes.h> includes <machine/types.h>, which defines
int{8,16,32,64}_t, uint{8,16,32,64}_t and __BIT_TYPES_DEFINED__.
<inttypes.h> also defines intptr_t and uintptr_t. */
# include <inttypes.h>
#elif @HAVE_SYS_INTTYPES_H@
/* Solaris 7 <sys/inttypes.h> has the types except the *_fast*_t types, and
the macros except for *_FAST*_*, INTPTR_MIN, PTRDIFF_MIN, PTRDIFF_MAX. */
# include <sys/inttypes.h>
#endif
#if @HAVE_SYS_BITYPES_H@ && ! defined __BIT_TYPES_DEFINED__
/* Linux libc4 >= 4.6.7 and libc5 have a <sys/bitypes.h> that defines
int{8,16,32,64}_t and __BIT_TYPES_DEFINED__. In libc5 >= 5.2.2 it is
included by <sys/types.h>. */
# include <sys/bitypes.h>
#endif
#undef _GL_JUST_INCLUDE_SYSTEM_INTTYPES_H
/* Minimum and maximum values for an integer type under the usual assumption.
Return an unspecified value if BITS == 0, adding a check to pacify
picky compilers. */
#define _STDINT_MIN(signed, bits, zero) \
((signed) ? (- ((zero) + 1) << ((bits) ? (bits) - 1 : 0)) : (zero))
#define _STDINT_MAX(signed, bits, zero) \
((signed) \
? ~ _STDINT_MIN (signed, bits, zero) \
: /* The expression for the unsigned case. The subtraction of (signed) \
is a nop in the unsigned case and avoids "signed integer overflow" \
warnings in the signed case. */ \
((((zero) + 1) << ((bits) ? (bits) - 1 - (signed) : 0)) - 1) * 2 + 1)
#if !GNULIB_defined_stdint_types
/* 7.18.1.1. Exact-width integer types */
/* Here we assume a standard architecture where the hardware integer
types have 8, 16, 32, optionally 64 bits. */
#undef int8_t
#undef uint8_t
typedef signed char gl_int8_t;
typedef unsigned char gl_uint8_t;
#define int8_t gl_int8_t
#define uint8_t gl_uint8_t
#undef int16_t
#undef uint16_t
typedef short int gl_int16_t;
typedef unsigned short int gl_uint16_t;
#define int16_t gl_int16_t
#define uint16_t gl_uint16_t
#undef int32_t
#undef uint32_t
typedef int gl_int32_t;
typedef unsigned int gl_uint32_t;
#define int32_t gl_int32_t
#define uint32_t gl_uint32_t
/* If the system defines INT64_MAX, assume int64_t works. That way,
if the underlying platform defines int64_t to be a 64-bit long long
int, the code below won't mistakenly define it to be a 64-bit long
int, which would mess up C++ name mangling. We must use #ifdef
rather than #if, to avoid an error with HP-UX 10.20 cc. */
#ifdef INT64_MAX
# define GL_INT64_T
#else
/* Do not undefine int64_t if gnulib is not being used with 64-bit
types, since otherwise it breaks platforms like Tandem/NSK. */
# if LONG_MAX >> 31 >> 31 == 1
# undef int64_t
typedef long int gl_int64_t;
# define int64_t gl_int64_t
# define GL_INT64_T
# elif defined _MSC_VER
# undef int64_t
typedef __int64 gl_int64_t;
# define int64_t gl_int64_t
# define GL_INT64_T
# elif @HAVE_LONG_LONG_INT@
# undef int64_t
typedef long long int gl_int64_t;
# define int64_t gl_int64_t
# define GL_INT64_T
# endif
#endif
#ifdef UINT64_MAX
# define GL_UINT64_T
#else
# if ULONG_MAX >> 31 >> 31 >> 1 == 1
# undef uint64_t
typedef unsigned long int gl_uint64_t;
# define uint64_t gl_uint64_t
# define GL_UINT64_T
# elif defined _MSC_VER
# undef uint64_t
typedef unsigned __int64 gl_uint64_t;
# define uint64_t gl_uint64_t
# define GL_UINT64_T
# elif @HAVE_UNSIGNED_LONG_LONG_INT@
# undef uint64_t
typedef unsigned long long int gl_uint64_t;
# define uint64_t gl_uint64_t
# define GL_UINT64_T
# endif
#endif
/* Avoid collision with Solaris 2.5.1 <pthread.h> etc. */
#define _UINT8_T
#define _UINT32_T
#define _UINT64_T
/* 7.18.1.2. Minimum-width integer types */
/* Here we assume a standard architecture where the hardware integer
types have 8, 16, 32, optionally 64 bits. Therefore the leastN_t types
are the same as the corresponding N_t types. */
#undef int_least8_t
#undef uint_least8_t
#undef int_least16_t
#undef uint_least16_t
#undef int_least32_t
#undef uint_least32_t
#undef int_least64_t
#undef uint_least64_t
#define int_least8_t int8_t
#define uint_least8_t uint8_t
#define int_least16_t int16_t
#define uint_least16_t uint16_t
#define int_least32_t int32_t
#define uint_least32_t uint32_t
#ifdef GL_INT64_T
# define int_least64_t int64_t
#endif
#ifdef GL_UINT64_T
# define uint_least64_t uint64_t
#endif
/* 7.18.1.3. Fastest minimum-width integer types */
/* Note: Other <stdint.h> substitutes may define these types differently.
It is not recommended to use these types in public header files. */
/* Here we assume a standard architecture where the hardware integer
types have 8, 16, 32, optionally 64 bits. Therefore the fastN_t types
are taken from the same list of types. The following code normally
uses types consistent with glibc, as that lessens the chance of
incompatibility with older GNU hosts. */
#undef int_fast8_t
#undef uint_fast8_t
#undef int_fast16_t
#undef uint_fast16_t
#undef int_fast32_t
#undef uint_fast32_t
#undef int_fast64_t
#undef uint_fast64_t
typedef signed char gl_int_fast8_t;
typedef unsigned char gl_uint_fast8_t;
#ifdef __sun
/* Define types compatible with SunOS 5.10, so that code compiled under
earlier SunOS versions works with code compiled under SunOS 5.10. */
typedef int gl_int_fast32_t;
typedef unsigned int gl_uint_fast32_t;
#else
typedef long int gl_int_fast32_t;
typedef unsigned long int gl_uint_fast32_t;
#endif
typedef gl_int_fast32_t gl_int_fast16_t;
typedef gl_uint_fast32_t gl_uint_fast16_t;
#define int_fast8_t gl_int_fast8_t
#define uint_fast8_t gl_uint_fast8_t
#define int_fast16_t gl_int_fast16_t
#define uint_fast16_t gl_uint_fast16_t
#define int_fast32_t gl_int_fast32_t
#define uint_fast32_t gl_uint_fast32_t
#ifdef GL_INT64_T
# define int_fast64_t int64_t
#endif
#ifdef GL_UINT64_T
# define uint_fast64_t uint64_t
#endif
/* 7.18.1.4. Integer types capable of holding object pointers */
#undef intptr_t
#undef uintptr_t
typedef long int gl_intptr_t;
typedef unsigned long int gl_uintptr_t;
#define intptr_t gl_intptr_t
#define uintptr_t gl_uintptr_t
/* 7.18.1.5. Greatest-width integer types */
/* Note: These types are compiler dependent. It may be unwise to use them in
public header files. */
/* If the system defines INTMAX_MAX, assume that intmax_t works, and
similarly for UINTMAX_MAX and uintmax_t. This avoids problems with
assuming one type where another is used by the system. */
#ifndef INTMAX_MAX
# undef INTMAX_C
# undef intmax_t
# if @HAVE_LONG_LONG_INT@ && LONG_MAX >> 30 == 1
typedef long long int gl_intmax_t;
# define intmax_t gl_intmax_t
# elif defined GL_INT64_T
# define intmax_t int64_t
# else
typedef long int gl_intmax_t;
# define intmax_t gl_intmax_t
# endif
#endif
#ifndef UINTMAX_MAX
# undef UINTMAX_C
# undef uintmax_t
# if @HAVE_UNSIGNED_LONG_LONG_INT@ && ULONG_MAX >> 31 == 1
typedef unsigned long long int gl_uintmax_t;
# define uintmax_t gl_uintmax_t
# elif defined GL_UINT64_T
# define uintmax_t uint64_t
# else
typedef unsigned long int gl_uintmax_t;
# define uintmax_t gl_uintmax_t
# endif
#endif
/* Verify that intmax_t and uintmax_t have the same size. Too much code
breaks if this is not the case. If this check fails, the reason is likely
to be found in the autoconf macros. */
typedef int _verify_intmax_size[sizeof (intmax_t) == sizeof (uintmax_t)
? 1 : -1];
#define GNULIB_defined_stdint_types 1
#endif /* !GNULIB_defined_stdint_types */
/* 7.18.2. Limits of specified-width integer types */
/* 7.18.2.1. Limits of exact-width integer types */
/* Here we assume a standard architecture where the hardware integer
types have 8, 16, 32, optionally 64 bits. */
#undef INT8_MIN
#undef INT8_MAX
#undef UINT8_MAX
#define INT8_MIN (~ INT8_MAX)
#define INT8_MAX 127
#define UINT8_MAX 255
#undef INT16_MIN
#undef INT16_MAX
#undef UINT16_MAX
#define INT16_MIN (~ INT16_MAX)
#define INT16_MAX 32767
#define UINT16_MAX 65535
#undef INT32_MIN
#undef INT32_MAX
#undef UINT32_MAX
#define INT32_MIN (~ INT32_MAX)
#define INT32_MAX 2147483647
#define UINT32_MAX 4294967295U
#if defined GL_INT64_T && ! defined INT64_MAX
/* Prefer (- INTMAX_C (1) << 63) over (~ INT64_MAX) because SunPRO C 5.0
evaluates the latter incorrectly in preprocessor expressions. */
# define INT64_MIN (- INTMAX_C (1) << 63)
# define INT64_MAX INTMAX_C (9223372036854775807)
#endif
#if defined GL_UINT64_T && ! defined UINT64_MAX
# define UINT64_MAX UINTMAX_C (18446744073709551615)
#endif
/* 7.18.2.2. Limits of minimum-width integer types */
/* Here we assume a standard architecture where the hardware integer
types have 8, 16, 32, optionally 64 bits. Therefore the leastN_t types
are the same as the corresponding N_t types. */
#undef INT_LEAST8_MIN
#undef INT_LEAST8_MAX
#undef UINT_LEAST8_MAX
#define INT_LEAST8_MIN INT8_MIN
#define INT_LEAST8_MAX INT8_MAX
#define UINT_LEAST8_MAX UINT8_MAX
#undef INT_LEAST16_MIN
#undef INT_LEAST16_MAX
#undef UINT_LEAST16_MAX
#define INT_LEAST16_MIN INT16_MIN
#define INT_LEAST16_MAX INT16_MAX
#define UINT_LEAST16_MAX UINT16_MAX
#undef INT_LEAST32_MIN
#undef INT_LEAST32_MAX
#undef UINT_LEAST32_MAX
#define INT_LEAST32_MIN INT32_MIN
#define INT_LEAST32_MAX INT32_MAX
#define UINT_LEAST32_MAX UINT32_MAX
#undef INT_LEAST64_MIN
#undef INT_LEAST64_MAX
#ifdef GL_INT64_T
# define INT_LEAST64_MIN INT64_MIN
# define INT_LEAST64_MAX INT64_MAX
#endif
#undef UINT_LEAST64_MAX
#ifdef GL_UINT64_T
# define UINT_LEAST64_MAX UINT64_MAX
#endif
/* 7.18.2.3. Limits of fastest minimum-width integer types */
/* Here we assume a standard architecture where the hardware integer
types have 8, 16, 32, optionally 64 bits. Therefore the fastN_t types
are taken from the same list of types. */
#undef INT_FAST8_MIN
#undef INT_FAST8_MAX
#undef UINT_FAST8_MAX
#define INT_FAST8_MIN SCHAR_MIN
#define INT_FAST8_MAX SCHAR_MAX
#define UINT_FAST8_MAX UCHAR_MAX
#undef INT_FAST16_MIN
#undef INT_FAST16_MAX
#undef UINT_FAST16_MAX
#define INT_FAST16_MIN INT_FAST32_MIN
#define INT_FAST16_MAX INT_FAST32_MAX
#define UINT_FAST16_MAX UINT_FAST32_MAX
#undef INT_FAST32_MIN
#undef INT_FAST32_MAX
#undef UINT_FAST32_MAX
#ifdef __sun
# define INT_FAST32_MIN INT_MIN
# define INT_FAST32_MAX INT_MAX
# define UINT_FAST32_MAX UINT_MAX
#else
# define INT_FAST32_MIN LONG_MIN
# define INT_FAST32_MAX LONG_MAX
# define UINT_FAST32_MAX ULONG_MAX
#endif
#undef INT_FAST64_MIN
#undef INT_FAST64_MAX
#ifdef GL_INT64_T
# define INT_FAST64_MIN INT64_MIN
# define INT_FAST64_MAX INT64_MAX
#endif
#undef UINT_FAST64_MAX
#ifdef GL_UINT64_T
# define UINT_FAST64_MAX UINT64_MAX
#endif
/* 7.18.2.4. Limits of integer types capable of holding object pointers */
#undef INTPTR_MIN
#undef INTPTR_MAX
#undef UINTPTR_MAX
#define INTPTR_MIN LONG_MIN
#define INTPTR_MAX LONG_MAX
#define UINTPTR_MAX ULONG_MAX
/* 7.18.2.5. Limits of greatest-width integer types */
#ifndef INTMAX_MAX
# undef INTMAX_MIN
# ifdef INT64_MAX
# define INTMAX_MIN INT64_MIN
# define INTMAX_MAX INT64_MAX
# else
# define INTMAX_MIN INT32_MIN
# define INTMAX_MAX INT32_MAX
# endif
#endif
#ifndef UINTMAX_MAX
# ifdef UINT64_MAX
# define UINTMAX_MAX UINT64_MAX
# else
# define UINTMAX_MAX UINT32_MAX
# endif
#endif
/* 7.18.3. Limits of other integer types */
/* ptrdiff_t limits */
#undef PTRDIFF_MIN
#undef PTRDIFF_MAX
#if @APPLE_UNIVERSAL_BUILD@
# ifdef _LP64
# define PTRDIFF_MIN _STDINT_MIN (1, 64, 0l)
# define PTRDIFF_MAX _STDINT_MAX (1, 64, 0l)
# else
# define PTRDIFF_MIN _STDINT_MIN (1, 32, 0)
# define PTRDIFF_MAX _STDINT_MAX (1, 32, 0)
# endif
#else
# define PTRDIFF_MIN \
_STDINT_MIN (1, @BITSIZEOF_PTRDIFF_T@, 0@PTRDIFF_T_SUFFIX@)
# define PTRDIFF_MAX \
_STDINT_MAX (1, @BITSIZEOF_PTRDIFF_T@, 0@PTRDIFF_T_SUFFIX@)
#endif
/* sig_atomic_t limits */
#undef SIG_ATOMIC_MIN
#undef SIG_ATOMIC_MAX
#define SIG_ATOMIC_MIN \
_STDINT_MIN (@HAVE_SIGNED_SIG_ATOMIC_T@, @BITSIZEOF_SIG_ATOMIC_T@, \
0@SIG_ATOMIC_T_SUFFIX@)
#define SIG_ATOMIC_MAX \
_STDINT_MAX (@HAVE_SIGNED_SIG_ATOMIC_T@, @BITSIZEOF_SIG_ATOMIC_T@, \
0@SIG_ATOMIC_T_SUFFIX@)
/* size_t limit */
#undef SIZE_MAX
#if @APPLE_UNIVERSAL_BUILD@
# ifdef _LP64
# define SIZE_MAX _STDINT_MAX (0, 64, 0ul)
# else
# define SIZE_MAX _STDINT_MAX (0, 32, 0ul)
# endif
#else
# define SIZE_MAX _STDINT_MAX (0, @BITSIZEOF_SIZE_T@, 0@SIZE_T_SUFFIX@)
#endif
/* wchar_t limits */
/* Get WCHAR_MIN, WCHAR_MAX.
This include is not on the top, above, because on OSF/1 4.0 we have a
sequence of nested includes
<wchar.h> -> <stdio.h> -> <getopt.h> -> <stdlib.h>, and the latter includes
<stdint.h> and assumes its types are already defined. */
#if @HAVE_WCHAR_H@ && ! (defined WCHAR_MIN && defined WCHAR_MAX)
/* BSD/OS 4.0.1 has a bug: <stddef.h>, <stdio.h> and <time.h> must be
included before <wchar.h>. */
# include <stddef.h>
# include <stdio.h>
# include <time.h>
# define _GL_JUST_INCLUDE_SYSTEM_WCHAR_H
/* We don't need WCHAR_* in libidn, so to avoid problems with
missing wchar.h, don't include wchar.h here. */
# undef _GL_JUST_INCLUDE_SYSTEM_WCHAR_H
#endif
#undef WCHAR_MIN
#undef WCHAR_MAX
#define WCHAR_MIN \
_STDINT_MIN (@HAVE_SIGNED_WCHAR_T@, @BITSIZEOF_WCHAR_T@, 0@WCHAR_T_SUFFIX@)
#define WCHAR_MAX \
_STDINT_MAX (@HAVE_SIGNED_WCHAR_T@, @BITSIZEOF_WCHAR_T@, 0@WCHAR_T_SUFFIX@)
/* wint_t limits */
#undef WINT_MIN
#undef WINT_MAX
#define WINT_MIN \
_STDINT_MIN (@HAVE_SIGNED_WINT_T@, @BITSIZEOF_WINT_T@, 0@WINT_T_SUFFIX@)
#define WINT_MAX \
_STDINT_MAX (@HAVE_SIGNED_WINT_T@, @BITSIZEOF_WINT_T@, 0@WINT_T_SUFFIX@)
/* 7.18.4. Macros for integer constants */
/* 7.18.4.1. Macros for minimum-width integer constants */
/* According to ISO C 99 Technical Corrigendum 1 */
/* Here we assume a standard architecture where the hardware integer
types have 8, 16, 32, optionally 64 bits, and int is 32 bits. */
#undef INT8_C
#undef UINT8_C
#define INT8_C(x) x
#define UINT8_C(x) x
#undef INT16_C
#undef UINT16_C
#define INT16_C(x) x
#define UINT16_C(x) x
#undef INT32_C
#undef UINT32_C
#define INT32_C(x) x
#define UINT32_C(x) x ## U
#undef INT64_C
#undef UINT64_C
#if LONG_MAX >> 31 >> 31 == 1
# define INT64_C(x) x##L
#elif defined _MSC_VER
# define INT64_C(x) x##i64
#elif @HAVE_LONG_LONG_INT@
# define INT64_C(x) x##LL
#endif
#if ULONG_MAX >> 31 >> 31 >> 1 == 1
# define UINT64_C(x) x##UL
#elif defined _MSC_VER
# define UINT64_C(x) x##ui64
#elif @HAVE_UNSIGNED_LONG_LONG_INT@
# define UINT64_C(x) x##ULL
#endif
/* 7.18.4.2. Macros for greatest-width integer constants */
#ifndef INTMAX_C
# if @HAVE_LONG_LONG_INT@ && LONG_MAX >> 30 == 1
# define INTMAX_C(x) x##LL
# elif defined GL_INT64_T
# define INTMAX_C(x) INT64_C(x)
# else
# define INTMAX_C(x) x##L
# endif
#endif
#ifndef UINTMAX_C
# if @HAVE_UNSIGNED_LONG_LONG_INT@ && ULONG_MAX >> 31 == 1
# define UINTMAX_C(x) x##ULL
# elif defined GL_UINT64_T
# define UINTMAX_C(x) UINT64_C(x)
# else
# define UINTMAX_C(x) x##UL
# endif
#endif
#endif /* _@GUARD_PREFIX@_STDINT_H */
#endif /* !(defined __ANDROID__ && ...) */
#endif /* !defined _@GUARD_PREFIX@_STDINT_H && !defined _GL_JUST_INCLUDE_SYSTEM_STDINT_H */
+463
View File
@@ -0,0 +1,463 @@
/* Charset conversion.
Copyright (C) 2001-2007, 2010-2015 Free Software Foundation, Inc.
Written by Bruno Haible and Simon Josefsson.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "striconv.h"
#include <errno.h>
#include <stdlib.h>
#include <string.h>
#if HAVE_ICONV
# include <iconv.h>
/* Get MB_LEN_MAX, CHAR_BIT. */
# include <limits.h>
#endif
#include "c-strcase.h"
#ifndef SIZE_MAX
# define SIZE_MAX ((size_t) -1)
#endif
#if HAVE_ICONV
int
mem_cd_iconv (const char *src, size_t srclen, iconv_t cd,
char **resultp, size_t *lengthp)
{
# define tmpbufsize 4096
size_t length;
char *result;
/* Avoid glibc-2.1 bug and Solaris 2.7-2.9 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
/* Set to the initial state. */
iconv (cd, NULL, NULL, NULL, NULL);
# endif
/* Determine the length we need. */
{
size_t count = 0;
/* The alignment is needed when converting e.g. to glibc's WCHAR_T or
libiconv's UCS-4-INTERNAL encoding. */
union { unsigned int align; char buf[tmpbufsize]; } tmp;
# define tmpbuf tmp.buf
const char *inptr = src;
size_t insize = srclen;
while (insize > 0)
{
char *outptr = tmpbuf;
size_t outsize = tmpbufsize;
size_t res = iconv (cd,
(ICONV_CONST char **) &inptr, &insize,
&outptr, &outsize);
if (res == (size_t)(-1))
{
if (errno == E2BIG)
;
else if (errno == EINVAL)
break;
else
return -1;
}
# if !defined _LIBICONV_VERSION && !(defined __GLIBC__ && !defined __UCLIBC__)
/* Irix iconv() inserts a NUL byte if it cannot convert.
NetBSD iconv() inserts a question mark if it cannot convert.
Only GNU libiconv and GNU libc are known to prefer to fail rather
than doing a lossy conversion. */
else if (res > 0)
{
errno = EILSEQ;
return -1;
}
# endif
count += outptr - tmpbuf;
}
/* Avoid glibc-2.1 bug and Solaris 2.7 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
{
char *outptr = tmpbuf;
size_t outsize = tmpbufsize;
size_t res = iconv (cd, NULL, NULL, &outptr, &outsize);
if (res == (size_t)(-1))
return -1;
count += outptr - tmpbuf;
}
# endif
length = count;
# undef tmpbuf
}
if (length == 0)
{
*lengthp = 0;
return 0;
}
if (*resultp != NULL && *lengthp >= length)
result = *resultp;
else
{
result = (char *) malloc (length);
if (result == NULL)
{
errno = ENOMEM;
return -1;
}
}
/* Avoid glibc-2.1 bug and Solaris 2.7-2.9 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
/* Return to the initial state. */
iconv (cd, NULL, NULL, NULL, NULL);
# endif
/* Do the conversion for real. */
{
const char *inptr = src;
size_t insize = srclen;
char *outptr = result;
size_t outsize = length;
while (insize > 0)
{
size_t res = iconv (cd,
(ICONV_CONST char **) &inptr, &insize,
&outptr, &outsize);
if (res == (size_t)(-1))
{
if (errno == EINVAL)
break;
else
goto fail;
}
# if !defined _LIBICONV_VERSION && !(defined __GLIBC__ && !defined __UCLIBC__)
/* Irix iconv() inserts a NUL byte if it cannot convert.
NetBSD iconv() inserts a question mark if it cannot convert.
Only GNU libiconv and GNU libc are known to prefer to fail rather
than doing a lossy conversion. */
else if (res > 0)
{
errno = EILSEQ;
goto fail;
}
# endif
}
/* Avoid glibc-2.1 bug and Solaris 2.7 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
{
size_t res = iconv (cd, NULL, NULL, &outptr, &outsize);
if (res == (size_t)(-1))
goto fail;
}
# endif
if (outsize != 0)
abort ();
}
*resultp = result;
*lengthp = length;
return 0;
fail:
{
if (result != *resultp)
{
int saved_errno = errno;
free (result);
errno = saved_errno;
}
return -1;
}
# undef tmpbufsize
}
char *
str_cd_iconv (const char *src, iconv_t cd)
{
/* For most encodings, a trailing NUL byte in the input will be converted
to a trailing NUL byte in the output. But not for UTF-7. So that this
function is usable for UTF-7, we have to exclude the NUL byte from the
conversion and add it by hand afterwards. */
# if !defined _LIBICONV_VERSION && !(defined __GLIBC__ && !defined __UCLIBC__)
/* Irix iconv() inserts a NUL byte if it cannot convert.
NetBSD iconv() inserts a question mark if it cannot convert.
Only GNU libiconv and GNU libc are known to prefer to fail rather
than doing a lossy conversion. For other iconv() implementations,
we have to look at the number of irreversible conversions returned;
but this information is lost when iconv() returns for an E2BIG reason.
Therefore we cannot use the second, faster algorithm. */
char *result = NULL;
size_t length = 0;
int retval = mem_cd_iconv (src, strlen (src), cd, &result, &length);
char *final_result;
if (retval < 0)
{
if (result != NULL)
abort ();
return NULL;
}
/* Add the terminating NUL byte. */
final_result =
(result != NULL ? realloc (result, length + 1) : malloc (length + 1));
if (final_result == NULL)
{
free (result);
errno = ENOMEM;
return NULL;
}
final_result[length] = '\0';
return final_result;
# else
/* This algorithm is likely faster than the one above. But it may produce
iconv() returns for an E2BIG reason, when the output size guess is too
small. Therefore it can only be used when we don't need the number of
irreversible conversions performed. */
char *result;
size_t result_size;
size_t length;
const char *inptr = src;
size_t inbytes_remaining = strlen (src);
/* Make a guess for the worst-case output size, in order to avoid a
realloc. It's OK if the guess is wrong as long as it is not zero and
doesn't lead to an integer overflow. */
result_size = inbytes_remaining;
{
size_t approx_sqrt_SIZE_MAX = SIZE_MAX >> (sizeof (size_t) * CHAR_BIT / 2);
if (result_size <= approx_sqrt_SIZE_MAX / MB_LEN_MAX)
result_size *= MB_LEN_MAX;
}
result_size += 1; /* for the terminating NUL */
result = (char *) malloc (result_size);
if (result == NULL)
{
errno = ENOMEM;
return NULL;
}
/* Avoid glibc-2.1 bug and Solaris 2.7-2.9 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
/* Set to the initial state. */
iconv (cd, NULL, NULL, NULL, NULL);
# endif
/* Do the conversion. */
{
char *outptr = result;
size_t outbytes_remaining = result_size - 1;
for (;;)
{
/* Here inptr + inbytes_remaining = src + strlen (src),
outptr + outbytes_remaining = result + result_size - 1. */
size_t res = iconv (cd,
(ICONV_CONST char **) &inptr, &inbytes_remaining,
&outptr, &outbytes_remaining);
if (res == (size_t)(-1))
{
if (errno == EINVAL)
break;
else if (errno == E2BIG)
{
size_t used = outptr - result;
size_t newsize = result_size * 2;
char *newresult;
if (!(newsize > result_size))
{
errno = ENOMEM;
goto failed;
}
newresult = (char *) realloc (result, newsize);
if (newresult == NULL)
{
errno = ENOMEM;
goto failed;
}
result = newresult;
result_size = newsize;
outptr = result + used;
outbytes_remaining = result_size - 1 - used;
}
else
goto failed;
}
else
break;
}
/* Avoid glibc-2.1 bug and Solaris 2.7 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
for (;;)
{
/* Here outptr + outbytes_remaining = result + result_size - 1. */
size_t res = iconv (cd, NULL, NULL, &outptr, &outbytes_remaining);
if (res == (size_t)(-1))
{
if (errno == E2BIG)
{
size_t used = outptr - result;
size_t newsize = result_size * 2;
char *newresult;
if (!(newsize > result_size))
{
errno = ENOMEM;
goto failed;
}
newresult = (char *) realloc (result, newsize);
if (newresult == NULL)
{
errno = ENOMEM;
goto failed;
}
result = newresult;
result_size = newsize;
outptr = result + used;
outbytes_remaining = result_size - 1 - used;
}
else
goto failed;
}
else
break;
}
# endif
/* Add the terminating NUL byte. */
*outptr++ = '\0';
length = outptr - result;
}
/* Give away unused memory. */
if (length < result_size)
{
char *smaller_result = (char *) realloc (result, length);
if (smaller_result != NULL)
result = smaller_result;
}
return result;
failed:
{
int saved_errno = errno;
free (result);
errno = saved_errno;
return NULL;
}
# endif
}
#endif
char *
str_iconv (const char *src, const char *from_codeset, const char *to_codeset)
{
if (*src == '\0' || c_strcasecmp (from_codeset, to_codeset) == 0)
{
char *result = strdup (src);
if (result == NULL)
errno = ENOMEM;
return result;
}
else
{
#if HAVE_ICONV
iconv_t cd;
char *result;
/* Avoid glibc-2.1 bug with EUC-KR. */
# if ((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
&& !defined _LIBICONV_VERSION
if (c_strcasecmp (from_codeset, "EUC-KR") == 0
|| c_strcasecmp (to_codeset, "EUC-KR") == 0)
{
errno = EINVAL;
return NULL;
}
# endif
cd = iconv_open (to_codeset, from_codeset);
if (cd == (iconv_t) -1)
return NULL;
result = str_cd_iconv (src, cd);
if (result == NULL)
{
/* Close cd, but preserve the errno from str_cd_iconv. */
int saved_errno = errno;
iconv_close (cd);
errno = saved_errno;
}
else
{
if (iconv_close (cd) < 0)
{
/* Return NULL, but free the allocated memory, and while doing
that, preserve the errno from iconv_close. */
int saved_errno = errno;
free (result);
errno = saved_errno;
return NULL;
}
}
return result;
#else
/* This is a different error code than if iconv_open existed but didn't
support from_codeset and to_codeset, so that the caller can emit
an error message such as
"iconv() is not supported. Installing GNU libiconv and
then reinstalling this package would fix this." */
errno = ENOSYS;
return NULL;
#endif
}
}
+75
View File
@@ -0,0 +1,75 @@
/* Charset conversion.
Copyright (C) 2001-2004, 2006-2007, 2009-2015 Free Software Foundation, Inc.
Written by Bruno Haible and Simon Josefsson.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#ifndef _STRICONV_H
#define _STRICONV_H
#include <stddef.h>
#if HAVE_ICONV
#include <iconv.h>
#endif
#ifdef __cplusplus
extern "C" {
#endif
#if HAVE_ICONV
/* Convert an entire string from one encoding to another, using iconv.
The original string is at [SRC,...,SRC+SRCLEN-1].
The conversion descriptor is passed as CD.
*RESULTP and *LENGTH should initially be a scratch buffer and its size,
or *RESULTP can initially be NULL.
May erase the contents of the memory at *RESULTP.
Return value: 0 if successful, otherwise -1 and errno set.
If successful: The resulting string is stored in *RESULTP and its length
in *LENGTHP. *RESULTP is set to a freshly allocated memory block, or is
unchanged if no dynamic memory allocation was necessary. */
extern int mem_cd_iconv (const char *src, size_t srclen, iconv_t cd,
char **resultp, size_t *lengthp);
/* Convert an entire string from one encoding to another, using iconv.
The original string is the NUL-terminated string starting at SRC.
The conversion descriptor is passed as CD. Both the "from" and the "to"
encoding must use a single NUL byte at the end of the string (i.e. not
UCS-2, UCS-4, UTF-16, UTF-32).
Allocate a malloced memory block for the result.
Return value: the freshly allocated resulting NUL-terminated string if
successful, otherwise NULL and errno set. */
extern char * str_cd_iconv (const char *src, iconv_t cd);
#endif
/* Convert an entire string from one encoding to another, using iconv.
The original string is the NUL-terminated string starting at SRC.
Both the "from" and the "to" encoding must use a single NUL byte at the
end of the string (i.e. not UCS-2, UCS-4, UTF-16, UTF-32).
Allocate a malloced memory block for the result.
Return value: the freshly allocated resulting NUL-terminated string if
successful, otherwise NULL and errno set. */
extern char * str_iconv (const char *src,
const char *from_codeset, const char *to_codeset);
#ifdef __cplusplus
}
#endif
#endif /* _STRICONV_H */
+2
View File
@@ -0,0 +1,2 @@
int strverscmp (const char *s1, const char *s2);
#include_next <string.h>
File diff suppressed because it is too large. Load diff
+131
View File
@@ -0,0 +1,131 @@
/* Compare strings while treating digits characters numerically.
Copyright (C) 1997, 2000, 2002, 2004, 2006, 2009-2015 Free Software
Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Jean-François Bignolles <bignolle@ecoledoc.ibp.fr>, 1997.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License along
with this program; if not, see <http://www.gnu.org/licenses/>. */
#if !_LIBC
# include <config.h>
#endif
#include <string.h>
#include <ctype.h>
/* states: S_N: normal, S_I: comparing integral part, S_F: comparing
fractional parts, S_Z: idem but with leading Zeroes only */
#define S_N 0x0
#define S_I 0x4
#define S_F 0x8
#define S_Z 0xC
/* result_type: CMP: return diff; LEN: compare using len_diff/diff */
#define CMP 2
#define LEN 3
/* ISDIGIT differs from isdigit, as follows:
- Its arg may be any int or unsigned int; it need not be an unsigned char
or EOF.
- It's typically faster.
POSIX says that only '0' through '9' are digits. Prefer ISDIGIT to
isdigit unless it's important to use the locale's definition
of "digit" even when the host does not conform to POSIX. */
#define ISDIGIT(c) ((unsigned int) (c) - '0' <= 9)
#undef __strverscmp
#undef strverscmp
#ifndef weak_alias
# define __strverscmp strverscmp
#endif
/* Compare S1 and S2 as strings holding indices/version numbers,
returning less than, equal to or greater than zero if S1 is less than,
equal to or greater than S2 (for more info, see the texinfo doc).
*/
int
__strverscmp (const char *s1, const char *s2)
{
const unsigned char *p1 = (const unsigned char *) s1;
const unsigned char *p2 = (const unsigned char *) s2;
unsigned char c1, c2;
int state;
int diff;
/* Symbol(s) 0 [1-9] others (padding)
Transition (10) 0 (01) d (00) x (11) - */
static const unsigned int next_state[] =
{
/* state x d 0 - */
/* S_N */ S_N, S_I, S_Z, S_N,
/* S_I */ S_N, S_I, S_I, S_I,
/* S_F */ S_N, S_F, S_F, S_F,
/* S_Z */ S_N, S_F, S_Z, S_Z
};
static const int result_type[] =
{
/* state x/x x/d x/0 x/- d/x d/d d/0 d/-
0/x 0/d 0/0 0/- -/x -/d -/0 -/- */
/* S_N */ CMP, CMP, CMP, CMP, CMP, LEN, CMP, CMP,
CMP, CMP, CMP, CMP, CMP, CMP, CMP, CMP,
/* S_I */ CMP, -1, -1, CMP, 1, LEN, LEN, CMP,
1, LEN, LEN, CMP, CMP, CMP, CMP, CMP,
/* S_F */ CMP, CMP, CMP, CMP, CMP, LEN, CMP, CMP,
CMP, CMP, CMP, CMP, CMP, CMP, CMP, CMP,
/* S_Z */ CMP, 1, 1, CMP, -1, CMP, CMP, CMP,
-1, CMP, CMP, CMP
};
if (p1 == p2)
return 0;
c1 = *p1++;
c2 = *p2++;
/* Hint: '0' is a digit too. */
state = S_N | ((c1 == '0') + (ISDIGIT (c1) != 0));
while ((diff = c1 - c2) == 0 && c1 != '\0')
{
state = next_state[state];
c1 = *p1++;
c2 = *p2++;
state |= (c1 == '0') + (ISDIGIT (c1) != 0);
}
state = result_type[state << 2 | ((c2 == '0') + (ISDIGIT (c2) != 0))];
switch (state)
{
case CMP:
return diff;
case LEN:
while (ISDIGIT (*p1++))
if (!ISDIGIT (*p2++))
return 1;
return ISDIGIT (*p2) ? -1 : diff;
default:
return state;
}
}
#ifdef weak_alias
weak_alias (__strverscmp, strverscmp)
#endif
+53
View File
@@ -0,0 +1,53 @@
/* Provide a more complete sys/types.h.
Copyright (C) 2011-2015 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>. */
#if __GNUC__ >= 3
@PRAGMA_SYSTEM_HEADER@
#endif
@PRAGMA_COLUMNS@
#ifndef _@GUARD_PREFIX@_SYS_TYPES_H
/* The include_next requires a split double-inclusion guard. */
# define _GL_INCLUDING_SYS_TYPES_H
#@INCLUDE_NEXT@ @NEXT_SYS_TYPES_H@
# undef _GL_INCLUDING_SYS_TYPES_H
#ifndef _@GUARD_PREFIX@_SYS_TYPES_H
#define _@GUARD_PREFIX@_SYS_TYPES_H
/* Override off_t if Large File Support is requested on native Windows. */
#if @WINDOWS_64_BIT_OFF_T@
/* Same as int64_t in <stdint.h>. */
# if defined _MSC_VER
# define off_t __int64
# else
# define off_t long long int
# endif
/* Indicator, for gnulib internal purposes. */
# define _GL_WINDOWS_64_BIT_OFF_T 1
#endif
/* MSVC 9 defines size_t in <stddef.h>, not in <sys/types.h>. */
/* But avoid namespace pollution on glibc systems. */
#if ((defined _WIN32 || defined __WIN32__) && ! defined __CYGWIN__) \
&& ! defined __GLIBC__
# include <stddef.h>
#endif
#endif /* _@GUARD_PREFIX@_SYS_TYPES_H */
#endif /* _@GUARD_PREFIX@_SYS_TYPES_H */
+750
View File
@@ -0,0 +1,750 @@
/* Elementary Unicode string functions.
Copyright (C) 2001-2002, 2005-2015 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation; either version 2.1 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#ifndef _UNISTR_H
#define _UNISTR_H
#include "unitypes.h"
/* Get common macros for C. */
#include "unused-parameter.h"
/* Get bool. */
#include <stdbool.h>
/* Get size_t. */
#include <stddef.h>
#ifdef __cplusplus
extern "C" {
#endif
/* Conventions:
All functions prefixed with u8_ operate on UTF-8 encoded strings.
Their unit is an uint8_t (1 byte).
All functions prefixed with u16_ operate on UTF-16 encoded strings.
Their unit is an uint16_t (a 2-byte word).
All functions prefixed with u32_ operate on UCS-4 encoded strings.
Their unit is an uint32_t (a 4-byte word).
All argument pairs (s, n) denote a Unicode string s[0..n-1] with exactly
n units.
All arguments starting with "str" and the arguments of functions starting
with u8_str/u16_str/u32_str denote a NUL terminated string, i.e. a string
which terminates at the first NUL unit. This termination unit is
considered part of the string for all memory allocation purposes, but
is not considered part of the string for all other logical purposes.
Functions returning a string result take a (resultbuf, lengthp) argument
pair. If resultbuf is not NULL and the result fits into *lengthp units,
it is put in resultbuf, and resultbuf is returned. Otherwise, a freshly
allocated string is returned. In both cases, *lengthp is set to the
length (number of units) of the returned string. In case of error,
NULL is returned and errno is set. */
/* Elementary string checks. */
/* Check whether an UTF-8 string is well-formed.
Return NULL if valid, or a pointer to the first invalid unit otherwise. */
extern const uint8_t *
u8_check (const uint8_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Check whether an UTF-16 string is well-formed.
Return NULL if valid, or a pointer to the first invalid unit otherwise. */
extern const uint16_t *
u16_check (const uint16_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Check whether an UCS-4 string is well-formed.
Return NULL if valid, or a pointer to the first invalid unit otherwise. */
extern const uint32_t *
u32_check (const uint32_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Elementary string conversions. */
/* Convert an UTF-8 string to an UTF-16 string. */
extern uint16_t *
u8_to_u16 (const uint8_t *s, size_t n, uint16_t *resultbuf,
size_t *lengthp);
/* Convert an UTF-8 string to an UCS-4 string. */
extern uint32_t *
u8_to_u32 (const uint8_t *s, size_t n, uint32_t *resultbuf,
size_t *lengthp);
/* Convert an UTF-16 string to an UTF-8 string. */
extern uint8_t *
u16_to_u8 (const uint16_t *s, size_t n, uint8_t *resultbuf,
size_t *lengthp);
/* Convert an UTF-16 string to an UCS-4 string. */
extern uint32_t *
u16_to_u32 (const uint16_t *s, size_t n, uint32_t *resultbuf,
size_t *lengthp);
/* Convert an UCS-4 string to an UTF-8 string. */
extern uint8_t *
u32_to_u8 (const uint32_t *s, size_t n, uint8_t *resultbuf,
size_t *lengthp);
/* Convert an UCS-4 string to an UTF-16 string. */
extern uint16_t *
u32_to_u16 (const uint32_t *s, size_t n, uint16_t *resultbuf,
size_t *lengthp);
/* Elementary string functions. */
/* Return the length (number of units) of the first character in S, which is
no longer than N. Return 0 if it is the NUL character. Return -1 upon
failure. */
/* Similar to mblen(), except that s must not be NULL. */
extern int
u8_mblen (const uint8_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u16_mblen (const uint16_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u32_mblen (const uint32_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Return the length (number of units) of the first character in S, putting
its 'ucs4_t' representation in *PUC. Upon failure, *PUC is set to 0xfffd,
and an appropriate number of units is returned.
The number of available units, N, must be > 0. */
/* Similar to mbtowc(), except that puc and s must not be NULL, n must be > 0,
and the NUL character is not treated specially. */
/* The variants with _safe suffix are safe, even if the library is compiled
without --enable-safety. */
#if GNULIB_UNISTR_U8_MBTOUC_UNSAFE || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u8_mbtouc_unsafe (ucs4_t *puc, const uint8_t *s, size_t n);
# else
extern int
u8_mbtouc_unsafe_aux (ucs4_t *puc, const uint8_t *s, size_t n);
static inline int
u8_mbtouc_unsafe (ucs4_t *puc, const uint8_t *s, size_t n)
{
uint8_t c = *s;
if (c < 0x80)
{
*puc = c;
return 1;
}
else
return u8_mbtouc_unsafe_aux (puc, s, n);
}
# endif
#endif
#if GNULIB_UNISTR_U16_MBTOUC_UNSAFE || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u16_mbtouc_unsafe (ucs4_t *puc, const uint16_t *s, size_t n);
# else
extern int
u16_mbtouc_unsafe_aux (ucs4_t *puc, const uint16_t *s, size_t n);
static inline int
u16_mbtouc_unsafe (ucs4_t *puc, const uint16_t *s, size_t n)
{
uint16_t c = *s;
if (c < 0xd800 || c >= 0xe000)
{
*puc = c;
return 1;
}
else
return u16_mbtouc_unsafe_aux (puc, s, n);
}
# endif
#endif
#if GNULIB_UNISTR_U32_MBTOUC_UNSAFE || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u32_mbtouc_unsafe (ucs4_t *puc, const uint32_t *s, size_t n);
# else
static inline int
u32_mbtouc_unsafe (ucs4_t *puc,
const uint32_t *s, size_t n _GL_UNUSED_PARAMETER)
{
uint32_t c = *s;
# if CONFIG_UNICODE_SAFETY
if (c < 0xd800 || (c >= 0xe000 && c < 0x110000))
# endif
*puc = c;
# if CONFIG_UNICODE_SAFETY
else
/* invalid multibyte character */
*puc = 0xfffd;
# endif
return 1;
}
# endif
#endif
#if GNULIB_UNISTR_U8_MBTOUC || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u8_mbtouc (ucs4_t *puc, const uint8_t *s, size_t n);
# else
extern int
u8_mbtouc_aux (ucs4_t *puc, const uint8_t *s, size_t n);
static inline int
u8_mbtouc (ucs4_t *puc, const uint8_t *s, size_t n)
{
uint8_t c = *s;
if (c < 0x80)
{
*puc = c;
return 1;
}
else
return u8_mbtouc_aux (puc, s, n);
}
# endif
#endif
#if GNULIB_UNISTR_U16_MBTOUC || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u16_mbtouc (ucs4_t *puc, const uint16_t *s, size_t n);
# else
extern int
u16_mbtouc_aux (ucs4_t *puc, const uint16_t *s, size_t n);
static inline int
u16_mbtouc (ucs4_t *puc, const uint16_t *s, size_t n)
{
uint16_t c = *s;
if (c < 0xd800 || c >= 0xe000)
{
*puc = c;
return 1;
}
else
return u16_mbtouc_aux (puc, s, n);
}
# endif
#endif
#if GNULIB_UNISTR_U32_MBTOUC || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u32_mbtouc (ucs4_t *puc, const uint32_t *s, size_t n);
# else
static inline int
u32_mbtouc (ucs4_t *puc, const uint32_t *s, size_t n _GL_UNUSED_PARAMETER)
{
uint32_t c = *s;
if (c < 0xd800 || (c >= 0xe000 && c < 0x110000))
*puc = c;
else
/* invalid multibyte character */
*puc = 0xfffd;
return 1;
}
# endif
#endif
/* Return the length (number of units) of the first character in S, putting
its 'ucs4_t' representation in *PUC. Upon failure, *PUC is set to 0xfffd,
and -1 is returned for an invalid sequence of units, -2 is returned for an
incomplete sequence of units.
The number of available units, N, must be > 0. */
/* Similar to u*_mbtouc(), except that the return value gives more details
about the failure, similar to mbrtowc(). */
#if GNULIB_UNISTR_U8_MBTOUCR || HAVE_LIBUNISTRING
extern int
u8_mbtoucr (ucs4_t *puc, const uint8_t *s, size_t n);
#endif
#if GNULIB_UNISTR_U16_MBTOUCR || HAVE_LIBUNISTRING
extern int
u16_mbtoucr (ucs4_t *puc, const uint16_t *s, size_t n);
#endif
#if GNULIB_UNISTR_U32_MBTOUCR || HAVE_LIBUNISTRING
extern int
u32_mbtoucr (ucs4_t *puc, const uint32_t *s, size_t n);
#endif
/* Put the multibyte character represented by UC in S, returning its
length. Return -1 upon failure, -2 if the number of available units, N,
is too small. The latter case cannot occur if N >= 6/2/1, respectively. */
/* Similar to wctomb(), except that s must not be NULL, and the argument n
must be specified. */
#if GNULIB_UNISTR_U8_UCTOMB || HAVE_LIBUNISTRING
/* Auxiliary function, also used by u8_chr, u8_strchr, u8_strrchr. */
extern int
u8_uctomb_aux (uint8_t *s, ucs4_t uc, int n);
# if !HAVE_INLINE
extern int
u8_uctomb (uint8_t *s, ucs4_t uc, int n);
# else
static inline int
u8_uctomb (uint8_t *s, ucs4_t uc, int n)
{
if (uc < 0x80 && n > 0)
{
s[0] = uc;
return 1;
}
else
return u8_uctomb_aux (s, uc, n);
}
# endif
#endif
#if GNULIB_UNISTR_U16_UCTOMB || HAVE_LIBUNISTRING
/* Auxiliary function, also used by u16_chr, u16_strchr, u16_strrchr. */
extern int
u16_uctomb_aux (uint16_t *s, ucs4_t uc, int n);
# if !HAVE_INLINE
extern int
u16_uctomb (uint16_t *s, ucs4_t uc, int n);
# else
static inline int
u16_uctomb (uint16_t *s, ucs4_t uc, int n)
{
if (uc < 0xd800 && n > 0)
{
s[0] = uc;
return 1;
}
else
return u16_uctomb_aux (s, uc, n);
}
# endif
#endif
#if GNULIB_UNISTR_U32_UCTOMB || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u32_uctomb (uint32_t *s, ucs4_t uc, int n);
# else
static inline int
u32_uctomb (uint32_t *s, ucs4_t uc, int n)
{
if (uc < 0xd800 || (uc >= 0xe000 && uc < 0x110000))
{
if (n > 0)
{
*s = uc;
return 1;
}
else
return -2;
}
else
return -1;
}
# endif
#endif
/* Copy N units from SRC to DEST. */
/* Similar to memcpy(). */
extern uint8_t *
u8_cpy (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_cpy (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_cpy (uint32_t *dest, const uint32_t *src, size_t n);
/* Copy N units from SRC to DEST, guaranteeing correct behavior for
overlapping memory areas. */
/* Similar to memmove(). */
extern uint8_t *
u8_move (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_move (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_move (uint32_t *dest, const uint32_t *src, size_t n);
/* Set the first N characters of S to UC. UC should be a character that
occupies only 1 unit. */
/* Similar to memset(). */
extern uint8_t *
u8_set (uint8_t *s, ucs4_t uc, size_t n);
extern uint16_t *
u16_set (uint16_t *s, ucs4_t uc, size_t n);
extern uint32_t *
u32_set (uint32_t *s, ucs4_t uc, size_t n);
/* Compare S1 and S2, each of length N. */
/* Similar to memcmp(). */
extern int
u8_cmp (const uint8_t *s1, const uint8_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u16_cmp (const uint16_t *s1, const uint16_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u32_cmp (const uint32_t *s1, const uint32_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
/* Compare S1 and S2. */
/* Similar to the gnulib function memcmp2(). */
extern int
u8_cmp2 (const uint8_t *s1, size_t n1, const uint8_t *s2, size_t n2)
_UC_ATTRIBUTE_PURE;
extern int
u16_cmp2 (const uint16_t *s1, size_t n1, const uint16_t *s2, size_t n2)
_UC_ATTRIBUTE_PURE;
extern int
u32_cmp2 (const uint32_t *s1, size_t n1, const uint32_t *s2, size_t n2)
_UC_ATTRIBUTE_PURE;
/* Search the string at S for UC. */
/* Similar to memchr(). */
extern uint8_t *
u8_chr (const uint8_t *s, size_t n, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_chr (const uint16_t *s, size_t n, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_chr (const uint32_t *s, size_t n, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
/* Count the number of Unicode characters in the N units from S. */
/* Similar to mbsnlen(). */
extern size_t
u8_mbsnlen (const uint8_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_mbsnlen (const uint16_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_mbsnlen (const uint32_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Elementary string functions with memory allocation. */
/* Make a freshly allocated copy of S, of length N. */
extern uint8_t *
u8_cpy_alloc (const uint8_t *s, size_t n);
extern uint16_t *
u16_cpy_alloc (const uint16_t *s, size_t n);
extern uint32_t *
u32_cpy_alloc (const uint32_t *s, size_t n);
/* Elementary string functions on NUL terminated strings. */
/* Return the length (number of units) of the first character in S.
Return 0 if it is the NUL character. Return -1 upon failure. */
extern int
u8_strmblen (const uint8_t *s)
_UC_ATTRIBUTE_PURE;
extern int
u16_strmblen (const uint16_t *s)
_UC_ATTRIBUTE_PURE;
extern int
u32_strmblen (const uint32_t *s)
_UC_ATTRIBUTE_PURE;
/* Return the length (number of units) of the first character in S, putting
its 'ucs4_t' representation in *PUC. Return 0 if it is the NUL
character. Return -1 upon failure. */
extern int
u8_strmbtouc (ucs4_t *puc, const uint8_t *s);
extern int
u16_strmbtouc (ucs4_t *puc, const uint16_t *s);
extern int
u32_strmbtouc (ucs4_t *puc, const uint32_t *s);
/* Forward iteration step. Advances the pointer past the next character,
or returns NULL if the end of the string has been reached. Puts the
character's 'ucs4_t' representation in *PUC. */
extern const uint8_t *
u8_next (ucs4_t *puc, const uint8_t *s);
extern const uint16_t *
u16_next (ucs4_t *puc, const uint16_t *s);
extern const uint32_t *
u32_next (ucs4_t *puc, const uint32_t *s);
/* Backward iteration step. Advances the pointer to point to the previous
character, or returns NULL if the beginning of the string had been reached.
Puts the character's 'ucs4_t' representation in *PUC. */
extern const uint8_t *
u8_prev (ucs4_t *puc, const uint8_t *s, const uint8_t *start);
extern const uint16_t *
u16_prev (ucs4_t *puc, const uint16_t *s, const uint16_t *start);
extern const uint32_t *
u32_prev (ucs4_t *puc, const uint32_t *s, const uint32_t *start);
/* Return the number of units in S. */
/* Similar to strlen(), wcslen(). */
extern size_t
u8_strlen (const uint8_t *s)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_strlen (const uint16_t *s)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_strlen (const uint32_t *s)
_UC_ATTRIBUTE_PURE;
/* Return the number of units in S, but at most MAXLEN. */
/* Similar to strnlen(), wcsnlen(). */
extern size_t
u8_strnlen (const uint8_t *s, size_t maxlen)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_strnlen (const uint16_t *s, size_t maxlen)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_strnlen (const uint32_t *s, size_t maxlen)
_UC_ATTRIBUTE_PURE;
/* Copy SRC to DEST. */
/* Similar to strcpy(), wcscpy(). */
extern uint8_t *
u8_strcpy (uint8_t *dest, const uint8_t *src);
extern uint16_t *
u16_strcpy (uint16_t *dest, const uint16_t *src);
extern uint32_t *
u32_strcpy (uint32_t *dest, const uint32_t *src);
/* Copy SRC to DEST, returning the address of the terminating NUL in DEST. */
/* Similar to stpcpy(). */
extern uint8_t *
u8_stpcpy (uint8_t *dest, const uint8_t *src);
extern uint16_t *
u16_stpcpy (uint16_t *dest, const uint16_t *src);
extern uint32_t *
u32_stpcpy (uint32_t *dest, const uint32_t *src);
/* Copy no more than N units of SRC to DEST. */
/* Similar to strncpy(), wcsncpy(). */
extern uint8_t *
u8_strncpy (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_strncpy (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_strncpy (uint32_t *dest, const uint32_t *src, size_t n);
/* Copy no more than N units of SRC to DEST. Return a pointer past the last
non-NUL unit written into DEST. */
/* Similar to stpncpy(). */
extern uint8_t *
u8_stpncpy (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_stpncpy (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_stpncpy (uint32_t *dest, const uint32_t *src, size_t n);
/* Append SRC onto DEST. */
/* Similar to strcat(), wcscat(). */
extern uint8_t *
u8_strcat (uint8_t *dest, const uint8_t *src);
extern uint16_t *
u16_strcat (uint16_t *dest, const uint16_t *src);
extern uint32_t *
u32_strcat (uint32_t *dest, const uint32_t *src);
/* Append no more than N units of SRC onto DEST. */
/* Similar to strncat(), wcsncat(). */
extern uint8_t *
u8_strncat (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_strncat (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_strncat (uint32_t *dest, const uint32_t *src, size_t n);
/* Compare S1 and S2. */
/* Similar to strcmp(), wcscmp(). */
#ifdef __sun
/* Avoid a collision with the u8_strcmp() function in Solaris 11 libc. */
extern int
u8_strcmp_gnu (const uint8_t *s1, const uint8_t *s2)
_UC_ATTRIBUTE_PURE;
# define u8_strcmp u8_strcmp_gnu
#else
extern int
u8_strcmp (const uint8_t *s1, const uint8_t *s2)
_UC_ATTRIBUTE_PURE;
#endif
extern int
u16_strcmp (const uint16_t *s1, const uint16_t *s2)
_UC_ATTRIBUTE_PURE;
extern int
u32_strcmp (const uint32_t *s1, const uint32_t *s2)
_UC_ATTRIBUTE_PURE;
/* Compare S1 and S2 using the collation rules of the current locale.
Return -1 if S1 < S2, 0 if S1 = S2, 1 if S1 > S2.
Upon failure, set errno and return any value. */
/* Similar to strcoll(), wcscoll(). */
extern int
u8_strcoll (const uint8_t *s1, const uint8_t *s2);
extern int
u16_strcoll (const uint16_t *s1, const uint16_t *s2);
extern int
u32_strcoll (const uint32_t *s1, const uint32_t *s2);
/* Compare no more than N units of S1 and S2. */
/* Similar to strncmp(), wcsncmp(). */
extern int
u8_strncmp (const uint8_t *s1, const uint8_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u16_strncmp (const uint16_t *s1, const uint16_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u32_strncmp (const uint32_t *s1, const uint32_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
/* Duplicate S, returning an identical malloc'd string. */
/* Similar to strdup(), wcsdup(). */
extern uint8_t *
u8_strdup (const uint8_t *s);
extern uint16_t *
u16_strdup (const uint16_t *s);
extern uint32_t *
u32_strdup (const uint32_t *s);
/* Find the first occurrence of UC in STR. */
/* Similar to strchr(), wcschr(). */
extern uint8_t *
u8_strchr (const uint8_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_strchr (const uint16_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_strchr (const uint32_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
/* Find the last occurrence of UC in STR. */
/* Similar to strrchr(), wcsrchr(). */
extern uint8_t *
u8_strrchr (const uint8_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_strrchr (const uint16_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_strrchr (const uint32_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
/* Return the length of the initial segment of STR which consists entirely
of Unicode characters not in REJECT. */
/* Similar to strcspn(), wcscspn(). */
extern size_t
u8_strcspn (const uint8_t *str, const uint8_t *reject)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_strcspn (const uint16_t *str, const uint16_t *reject)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_strcspn (const uint32_t *str, const uint32_t *reject)
_UC_ATTRIBUTE_PURE;
/* Return the length of the initial segment of STR which consists entirely
of Unicode characters in ACCEPT. */
/* Similar to strspn(), wcsspn(). */
extern size_t
u8_strspn (const uint8_t *str, const uint8_t *accept)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_strspn (const uint16_t *str, const uint16_t *accept)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_strspn (const uint32_t *str, const uint32_t *accept)
_UC_ATTRIBUTE_PURE;
/* Find the first occurrence in STR of any character in ACCEPT. */
/* Similar to strpbrk(), wcspbrk(). */
extern uint8_t *
u8_strpbrk (const uint8_t *str, const uint8_t *accept)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_strpbrk (const uint16_t *str, const uint16_t *accept)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_strpbrk (const uint32_t *str, const uint32_t *accept)
_UC_ATTRIBUTE_PURE;
/* Find the first occurrence of NEEDLE in HAYSTACK. */
/* Similar to strstr(), wcsstr(). */
extern uint8_t *
u8_strstr (const uint8_t *haystack, const uint8_t *needle)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_strstr (const uint16_t *haystack, const uint16_t *needle)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_strstr (const uint32_t *haystack, const uint32_t *needle)
_UC_ATTRIBUTE_PURE;
/* Test whether STR starts with PREFIX. */
extern bool
u8_startswith (const uint8_t *str, const uint8_t *prefix)
_UC_ATTRIBUTE_PURE;
extern bool
u16_startswith (const uint16_t *str, const uint16_t *prefix)
_UC_ATTRIBUTE_PURE;
extern bool
u32_startswith (const uint32_t *str, const uint32_t *prefix)
_UC_ATTRIBUTE_PURE;
/* Test whether STR ends with SUFFIX. */
extern bool
u8_endswith (const uint8_t *str, const uint8_t *suffix)
_UC_ATTRIBUTE_PURE;
extern bool
u16_endswith (const uint16_t *str, const uint16_t *suffix)
_UC_ATTRIBUTE_PURE;
extern bool
u32_endswith (const uint32_t *str, const uint32_t *suffix)
_UC_ATTRIBUTE_PURE;
/* Divide STR into tokens separated by characters in DELIM.
This interface is actually more similar to wcstok than to strtok. */
/* Similar to strtok_r(), wcstok(). */
extern uint8_t *
u8_strtok (uint8_t *str, const uint8_t *delim, uint8_t **ptr);
extern uint16_t *
u16_strtok (uint16_t *str, const uint16_t *delim, uint16_t **ptr);
extern uint32_t *
u32_strtok (uint32_t *str, const uint32_t *delim, uint32_t **ptr);
#ifdef __cplusplus
}
#endif
#endif /* _UNISTR_H */
+750
View File
@@ -0,0 +1,750 @@
/* Elementary Unicode string functions.
Copyright (C) 2001-2002, 2005-2015 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation; either version 2.1 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#ifndef _UNISTR_H
#define _UNISTR_H
#include "unitypes.h"
/* Get common macros for C. */
#include "unused-parameter.h"
/* Get bool. */
#include <stdbool.h>
/* Get size_t. */
#include <stddef.h>
#ifdef __cplusplus
extern "C" {
#endif
/* Conventions:
All functions prefixed with u8_ operate on UTF-8 encoded strings.
Their unit is an uint8_t (1 byte).
All functions prefixed with u16_ operate on UTF-16 encoded strings.
Their unit is an uint16_t (a 2-byte word).
All functions prefixed with u32_ operate on UCS-4 encoded strings.
Their unit is an uint32_t (a 4-byte word).
All argument pairs (s, n) denote a Unicode string s[0..n-1] with exactly
n units.
All arguments starting with "str" and the arguments of functions starting
with u8_str/u16_str/u32_str denote a NUL terminated string, i.e. a string
which terminates at the first NUL unit. This termination unit is
considered part of the string for all memory allocation purposes, but
is not considered part of the string for all other logical purposes.
Functions returning a string result take a (resultbuf, lengthp) argument
pair. If resultbuf is not NULL and the result fits into *lengthp units,
it is put in resultbuf, and resultbuf is returned. Otherwise, a freshly
allocated string is returned. In both cases, *lengthp is set to the
length (number of units) of the returned string. In case of error,
NULL is returned and errno is set. */
/* Elementary string checks. */
/* Check whether an UTF-8 string is well-formed.
Return NULL if valid, or a pointer to the first invalid unit otherwise. */
extern const uint8_t *
u8_check (const uint8_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Check whether an UTF-16 string is well-formed.
Return NULL if valid, or a pointer to the first invalid unit otherwise. */
extern const uint16_t *
u16_check (const uint16_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Check whether an UCS-4 string is well-formed.
Return NULL if valid, or a pointer to the first invalid unit otherwise. */
extern const uint32_t *
u32_check (const uint32_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Elementary string conversions. */
/* Convert an UTF-8 string to an UTF-16 string. */
extern uint16_t *
u8_to_u16 (const uint8_t *s, size_t n, uint16_t *resultbuf,
size_t *lengthp);
/* Convert an UTF-8 string to an UCS-4 string. */
extern uint32_t *
u8_to_u32 (const uint8_t *s, size_t n, uint32_t *resultbuf,
size_t *lengthp);
/* Convert an UTF-16 string to an UTF-8 string. */
extern uint8_t *
u16_to_u8 (const uint16_t *s, size_t n, uint8_t *resultbuf,
size_t *lengthp);
/* Convert an UTF-16 string to an UCS-4 string. */
extern uint32_t *
u16_to_u32 (const uint16_t *s, size_t n, uint32_t *resultbuf,
size_t *lengthp);
/* Convert an UCS-4 string to an UTF-8 string. */
extern uint8_t *
u32_to_u8 (const uint32_t *s, size_t n, uint8_t *resultbuf,
size_t *lengthp);
/* Convert an UCS-4 string to an UTF-16 string. */
extern uint16_t *
u32_to_u16 (const uint32_t *s, size_t n, uint16_t *resultbuf,
size_t *lengthp);
/* Elementary string functions. */
/* Return the length (number of units) of the first character in S, which is
no longer than N. Return 0 if it is the NUL character. Return -1 upon
failure. */
/* Similar to mblen(), except that s must not be NULL. */
extern int
u8_mblen (const uint8_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u16_mblen (const uint16_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u32_mblen (const uint32_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Return the length (number of units) of the first character in S, putting
its 'ucs4_t' representation in *PUC. Upon failure, *PUC is set to 0xfffd,
and an appropriate number of units is returned.
The number of available units, N, must be > 0. */
/* Similar to mbtowc(), except that puc and s must not be NULL, n must be > 0,
and the NUL character is not treated specially. */
/* The variants with _safe suffix are safe, even if the library is compiled
without --enable-safety. */
#if GNULIB_UNISTR_U8_MBTOUC_UNSAFE || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u8_mbtouc_unsafe (ucs4_t *puc, const uint8_t *s, size_t n);
# else
extern int
u8_mbtouc_unsafe_aux (ucs4_t *puc, const uint8_t *s, size_t n);
static inline int
u8_mbtouc_unsafe (ucs4_t *puc, const uint8_t *s, size_t n)
{
uint8_t c = *s;
if (c < 0x80)
{
*puc = c;
return 1;
}
else
return u8_mbtouc_unsafe_aux (puc, s, n);
}
# endif
#endif
#if GNULIB_UNISTR_U16_MBTOUC_UNSAFE || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u16_mbtouc_unsafe (ucs4_t *puc, const uint16_t *s, size_t n);
# else
extern int
u16_mbtouc_unsafe_aux (ucs4_t *puc, const uint16_t *s, size_t n);
static inline int
u16_mbtouc_unsafe (ucs4_t *puc, const uint16_t *s, size_t n)
{
uint16_t c = *s;
if (c < 0xd800 || c >= 0xe000)
{
*puc = c;
return 1;
}
else
return u16_mbtouc_unsafe_aux (puc, s, n);
}
# endif
#endif
#if GNULIB_UNISTR_U32_MBTOUC_UNSAFE || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u32_mbtouc_unsafe (ucs4_t *puc, const uint32_t *s, size_t n);
# else
static inline int
u32_mbtouc_unsafe (ucs4_t *puc,
const uint32_t *s, size_t n _GL_UNUSED_PARAMETER)
{
uint32_t c = *s;
# if CONFIG_UNICODE_SAFETY
if (c < 0xd800 || (c >= 0xe000 && c < 0x110000))
# endif
*puc = c;
# if CONFIG_UNICODE_SAFETY
else
/* invalid multibyte character */
*puc = 0xfffd;
# endif
return 1;
}
# endif
#endif
#if GNULIB_UNISTR_U8_MBTOUC || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u8_mbtouc (ucs4_t *puc, const uint8_t *s, size_t n);
# else
extern int
u8_mbtouc_aux (ucs4_t *puc, const uint8_t *s, size_t n);
static inline int
u8_mbtouc (ucs4_t *puc, const uint8_t *s, size_t n)
{
uint8_t c = *s;
if (c < 0x80)
{
*puc = c;
return 1;
}
else
return u8_mbtouc_aux (puc, s, n);
}
# endif
#endif
#if GNULIB_UNISTR_U16_MBTOUC || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u16_mbtouc (ucs4_t *puc, const uint16_t *s, size_t n);
# else
extern int
u16_mbtouc_aux (ucs4_t *puc, const uint16_t *s, size_t n);
static inline int
u16_mbtouc (ucs4_t *puc, const uint16_t *s, size_t n)
{
uint16_t c = *s;
if (c < 0xd800 || c >= 0xe000)
{
*puc = c;
return 1;
}
else
return u16_mbtouc_aux (puc, s, n);
}
# endif
#endif
#if GNULIB_UNISTR_U32_MBTOUC || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u32_mbtouc (ucs4_t *puc, const uint32_t *s, size_t n);
# else
static inline int
u32_mbtouc (ucs4_t *puc, const uint32_t *s, size_t n _GL_UNUSED_PARAMETER)
{
uint32_t c = *s;
if (c < 0xd800 || (c >= 0xe000 && c < 0x110000))
*puc = c;
else
/* invalid multibyte character */
*puc = 0xfffd;
return 1;
}
# endif
#endif
/* Return the length (number of units) of the first character in S, putting
its 'ucs4_t' representation in *PUC. Upon failure, *PUC is set to 0xfffd,
and -1 is returned for an invalid sequence of units, -2 is returned for an
incomplete sequence of units.
The number of available units, N, must be > 0. */
/* Similar to u*_mbtouc(), except that the return value gives more details
about the failure, similar to mbrtowc(). */
#if GNULIB_UNISTR_U8_MBTOUCR || HAVE_LIBUNISTRING
extern int
u8_mbtoucr (ucs4_t *puc, const uint8_t *s, size_t n);
#endif
#if GNULIB_UNISTR_U16_MBTOUCR || HAVE_LIBUNISTRING
extern int
u16_mbtoucr (ucs4_t *puc, const uint16_t *s, size_t n);
#endif
#if GNULIB_UNISTR_U32_MBTOUCR || HAVE_LIBUNISTRING
extern int
u32_mbtoucr (ucs4_t *puc, const uint32_t *s, size_t n);
#endif
/* Put the multibyte character represented by UC in S, returning its
length. Return -1 upon failure, -2 if the number of available units, N,
is too small. The latter case cannot occur if N >= 6/2/1, respectively. */
/* Similar to wctomb(), except that s must not be NULL, and the argument n
must be specified. */
#if GNULIB_UNISTR_U8_UCTOMB || HAVE_LIBUNISTRING
/* Auxiliary function, also used by u8_chr, u8_strchr, u8_strrchr. */
extern int
u8_uctomb_aux (uint8_t *s, ucs4_t uc, int n);
# if !HAVE_INLINE
extern int
u8_uctomb (uint8_t *s, ucs4_t uc, int n);
# else
static inline int
u8_uctomb (uint8_t *s, ucs4_t uc, int n)
{
if (uc < 0x80 && n > 0)
{
s[0] = uc;
return 1;
}
else
return u8_uctomb_aux (s, uc, n);
}
# endif
#endif
#if GNULIB_UNISTR_U16_UCTOMB || HAVE_LIBUNISTRING
/* Auxiliary function, also used by u16_chr, u16_strchr, u16_strrchr. */
extern int
u16_uctomb_aux (uint16_t *s, ucs4_t uc, int n);
# if !HAVE_INLINE
extern int
u16_uctomb (uint16_t *s, ucs4_t uc, int n);
# else
static inline int
u16_uctomb (uint16_t *s, ucs4_t uc, int n)
{
if (uc < 0xd800 && n > 0)
{
s[0] = uc;
return 1;
}
else
return u16_uctomb_aux (s, uc, n);
}
# endif
#endif
#if GNULIB_UNISTR_U32_UCTOMB || HAVE_LIBUNISTRING
# if !HAVE_INLINE
extern int
u32_uctomb (uint32_t *s, ucs4_t uc, int n);
# else
static inline int
u32_uctomb (uint32_t *s, ucs4_t uc, int n)
{
if (uc < 0xd800 || (uc >= 0xe000 && uc < 0x110000))
{
if (n > 0)
{
*s = uc;
return 1;
}
else
return -2;
}
else
return -1;
}
# endif
#endif
/* Copy N units from SRC to DEST. */
/* Similar to memcpy(). */
extern uint8_t *
u8_cpy (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_cpy (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_cpy (uint32_t *dest, const uint32_t *src, size_t n);
/* Copy N units from SRC to DEST, guaranteeing correct behavior for
overlapping memory areas. */
/* Similar to memmove(). */
extern uint8_t *
u8_move (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_move (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_move (uint32_t *dest, const uint32_t *src, size_t n);
/* Set the first N characters of S to UC. UC should be a character that
occupies only 1 unit. */
/* Similar to memset(). */
extern uint8_t *
u8_set (uint8_t *s, ucs4_t uc, size_t n);
extern uint16_t *
u16_set (uint16_t *s, ucs4_t uc, size_t n);
extern uint32_t *
u32_set (uint32_t *s, ucs4_t uc, size_t n);
/* Compare S1 and S2, each of length N. */
/* Similar to memcmp(). */
extern int
u8_cmp (const uint8_t *s1, const uint8_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u16_cmp (const uint16_t *s1, const uint16_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u32_cmp (const uint32_t *s1, const uint32_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
/* Compare S1 and S2. */
/* Similar to the gnulib function memcmp2(). */
extern int
u8_cmp2 (const uint8_t *s1, size_t n1, const uint8_t *s2, size_t n2)
_UC_ATTRIBUTE_PURE;
extern int
u16_cmp2 (const uint16_t *s1, size_t n1, const uint16_t *s2, size_t n2)
_UC_ATTRIBUTE_PURE;
extern int
u32_cmp2 (const uint32_t *s1, size_t n1, const uint32_t *s2, size_t n2)
_UC_ATTRIBUTE_PURE;
/* Search the string at S for UC. */
/* Similar to memchr(). */
extern uint8_t *
u8_chr (const uint8_t *s, size_t n, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_chr (const uint16_t *s, size_t n, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_chr (const uint32_t *s, size_t n, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
/* Count the number of Unicode characters in the N units from S. */
/* Similar to mbsnlen(). */
extern size_t
u8_mbsnlen (const uint8_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_mbsnlen (const uint16_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_mbsnlen (const uint32_t *s, size_t n)
_UC_ATTRIBUTE_PURE;
/* Elementary string functions with memory allocation. */
/* Make a freshly allocated copy of S, of length N. */
extern uint8_t *
u8_cpy_alloc (const uint8_t *s, size_t n);
extern uint16_t *
u16_cpy_alloc (const uint16_t *s, size_t n);
extern uint32_t *
u32_cpy_alloc (const uint32_t *s, size_t n);
/* Elementary string functions on NUL terminated strings. */
/* Return the length (number of units) of the first character in S.
Return 0 if it is the NUL character. Return -1 upon failure. */
extern int
u8_strmblen (const uint8_t *s)
_UC_ATTRIBUTE_PURE;
extern int
u16_strmblen (const uint16_t *s)
_UC_ATTRIBUTE_PURE;
extern int
u32_strmblen (const uint32_t *s)
_UC_ATTRIBUTE_PURE;
/* Return the length (number of units) of the first character in S, putting
its 'ucs4_t' representation in *PUC. Return 0 if it is the NUL
character. Return -1 upon failure. */
extern int
u8_strmbtouc (ucs4_t *puc, const uint8_t *s);
extern int
u16_strmbtouc (ucs4_t *puc, const uint16_t *s);
extern int
u32_strmbtouc (ucs4_t *puc, const uint32_t *s);
/* Forward iteration step. Advances the pointer past the next character,
or returns NULL if the end of the string has been reached. Puts the
character's 'ucs4_t' representation in *PUC. */
extern const uint8_t *
u8_next (ucs4_t *puc, const uint8_t *s);
extern const uint16_t *
u16_next (ucs4_t *puc, const uint16_t *s);
extern const uint32_t *
u32_next (ucs4_t *puc, const uint32_t *s);
/* Backward iteration step. Advances the pointer to point to the previous
character, or returns NULL if the beginning of the string had been reached.
Puts the character's 'ucs4_t' representation in *PUC. */
extern const uint8_t *
u8_prev (ucs4_t *puc, const uint8_t *s, const uint8_t *start);
extern const uint16_t *
u16_prev (ucs4_t *puc, const uint16_t *s, const uint16_t *start);
extern const uint32_t *
u32_prev (ucs4_t *puc, const uint32_t *s, const uint32_t *start);
/* Return the number of units in S. */
/* Similar to strlen(), wcslen(). */
extern size_t
u8_strlen (const uint8_t *s)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_strlen (const uint16_t *s)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_strlen (const uint32_t *s)
_UC_ATTRIBUTE_PURE;
/* Return the number of units in S, but at most MAXLEN. */
/* Similar to strnlen(), wcsnlen(). */
extern size_t
u8_strnlen (const uint8_t *s, size_t maxlen)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_strnlen (const uint16_t *s, size_t maxlen)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_strnlen (const uint32_t *s, size_t maxlen)
_UC_ATTRIBUTE_PURE;
/* Copy SRC to DEST. */
/* Similar to strcpy(), wcscpy(). */
extern uint8_t *
u8_strcpy (uint8_t *dest, const uint8_t *src);
extern uint16_t *
u16_strcpy (uint16_t *dest, const uint16_t *src);
extern uint32_t *
u32_strcpy (uint32_t *dest, const uint32_t *src);
/* Copy SRC to DEST, returning the address of the terminating NUL in DEST. */
/* Similar to stpcpy(). */
extern uint8_t *
u8_stpcpy (uint8_t *dest, const uint8_t *src);
extern uint16_t *
u16_stpcpy (uint16_t *dest, const uint16_t *src);
extern uint32_t *
u32_stpcpy (uint32_t *dest, const uint32_t *src);
/* Copy no more than N units of SRC to DEST. */
/* Similar to strncpy(), wcsncpy(). */
extern uint8_t *
u8_strncpy (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_strncpy (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_strncpy (uint32_t *dest, const uint32_t *src, size_t n);
/* Copy no more than N units of SRC to DEST. Return a pointer past the last
non-NUL unit written into DEST. */
/* Similar to stpncpy(). */
extern uint8_t *
u8_stpncpy (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_stpncpy (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_stpncpy (uint32_t *dest, const uint32_t *src, size_t n);
/* Append SRC onto DEST. */
/* Similar to strcat(), wcscat(). */
extern uint8_t *
u8_strcat (uint8_t *dest, const uint8_t *src);
extern uint16_t *
u16_strcat (uint16_t *dest, const uint16_t *src);
extern uint32_t *
u32_strcat (uint32_t *dest, const uint32_t *src);
/* Append no more than N units of SRC onto DEST. */
/* Similar to strncat(), wcsncat(). */
extern uint8_t *
u8_strncat (uint8_t *dest, const uint8_t *src, size_t n);
extern uint16_t *
u16_strncat (uint16_t *dest, const uint16_t *src, size_t n);
extern uint32_t *
u32_strncat (uint32_t *dest, const uint32_t *src, size_t n);
/* Compare S1 and S2. */
/* Similar to strcmp(), wcscmp(). */
#ifdef __sun
/* Avoid a collision with the u8_strcmp() function in Solaris 11 libc. */
extern int
u8_strcmp_gnu (const uint8_t *s1, const uint8_t *s2)
_UC_ATTRIBUTE_PURE;
# define u8_strcmp u8_strcmp_gnu
#else
extern int
u8_strcmp (const uint8_t *s1, const uint8_t *s2)
_UC_ATTRIBUTE_PURE;
#endif
extern int
u16_strcmp (const uint16_t *s1, const uint16_t *s2)
_UC_ATTRIBUTE_PURE;
extern int
u32_strcmp (const uint32_t *s1, const uint32_t *s2)
_UC_ATTRIBUTE_PURE;
/* Compare S1 and S2 using the collation rules of the current locale.
Return -1 if S1 < S2, 0 if S1 = S2, 1 if S1 > S2.
Upon failure, set errno and return any value. */
/* Similar to strcoll(), wcscoll(). */
extern int
u8_strcoll (const uint8_t *s1, const uint8_t *s2);
extern int
u16_strcoll (const uint16_t *s1, const uint16_t *s2);
extern int
u32_strcoll (const uint32_t *s1, const uint32_t *s2);
/* Compare no more than N units of S1 and S2. */
/* Similar to strncmp(), wcsncmp(). */
extern int
u8_strncmp (const uint8_t *s1, const uint8_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u16_strncmp (const uint16_t *s1, const uint16_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
extern int
u32_strncmp (const uint32_t *s1, const uint32_t *s2, size_t n)
_UC_ATTRIBUTE_PURE;
/* Duplicate S, returning an identical malloc'd string. */
/* Similar to strdup(), wcsdup(). */
extern uint8_t *
u8_strdup (const uint8_t *s);
extern uint16_t *
u16_strdup (const uint16_t *s);
extern uint32_t *
u32_strdup (const uint32_t *s);
/* Find the first occurrence of UC in STR. */
/* Similar to strchr(), wcschr(). */
extern uint8_t *
u8_strchr (const uint8_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_strchr (const uint16_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_strchr (const uint32_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
/* Find the last occurrence of UC in STR. */
/* Similar to strrchr(), wcsrchr(). */
extern uint8_t *
u8_strrchr (const uint8_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_strrchr (const uint16_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_strrchr (const uint32_t *str, ucs4_t uc)
_UC_ATTRIBUTE_PURE;
/* Return the length of the initial segment of STR which consists entirely
of Unicode characters not in REJECT. */
/* Similar to strcspn(), wcscspn(). */
extern size_t
u8_strcspn (const uint8_t *str, const uint8_t *reject)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_strcspn (const uint16_t *str, const uint16_t *reject)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_strcspn (const uint32_t *str, const uint32_t *reject)
_UC_ATTRIBUTE_PURE;
/* Return the length of the initial segment of STR which consists entirely
of Unicode characters in ACCEPT. */
/* Similar to strspn(), wcsspn(). */
extern size_t
u8_strspn (const uint8_t *str, const uint8_t *accept)
_UC_ATTRIBUTE_PURE;
extern size_t
u16_strspn (const uint16_t *str, const uint16_t *accept)
_UC_ATTRIBUTE_PURE;
extern size_t
u32_strspn (const uint32_t *str, const uint32_t *accept)
_UC_ATTRIBUTE_PURE;
/* Find the first occurrence in STR of any character in ACCEPT. */
/* Similar to strpbrk(), wcspbrk(). */
extern uint8_t *
u8_strpbrk (const uint8_t *str, const uint8_t *accept)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_strpbrk (const uint16_t *str, const uint16_t *accept)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_strpbrk (const uint32_t *str, const uint32_t *accept)
_UC_ATTRIBUTE_PURE;
/* Find the first occurrence of NEEDLE in HAYSTACK. */
/* Similar to strstr(), wcsstr(). */
extern uint8_t *
u8_strstr (const uint8_t *haystack, const uint8_t *needle)
_UC_ATTRIBUTE_PURE;
extern uint16_t *
u16_strstr (const uint16_t *haystack, const uint16_t *needle)
_UC_ATTRIBUTE_PURE;
extern uint32_t *
u32_strstr (const uint32_t *haystack, const uint32_t *needle)
_UC_ATTRIBUTE_PURE;
/* Test whether STR starts with PREFIX. */
extern bool
u8_startswith (const uint8_t *str, const uint8_t *prefix)
_UC_ATTRIBUTE_PURE;
extern bool
u16_startswith (const uint16_t *str, const uint16_t *prefix)
_UC_ATTRIBUTE_PURE;
extern bool
u32_startswith (const uint32_t *str, const uint32_t *prefix)
_UC_ATTRIBUTE_PURE;
/* Test whether STR ends with SUFFIX. */
extern bool
u8_endswith (const uint8_t *str, const uint8_t *suffix)
_UC_ATTRIBUTE_PURE;
extern bool
u16_endswith (const uint16_t *str, const uint16_t *suffix)
_UC_ATTRIBUTE_PURE;
extern bool
u32_endswith (const uint32_t *str, const uint32_t *suffix)
_UC_ATTRIBUTE_PURE;
/* Divide STR into tokens separated by characters in DELIM.
This interface is actually more similar to wcstok than to strtok. */
/* Similar to strtok_r(), wcstok(). */
extern uint8_t *
u8_strtok (uint8_t *str, const uint8_t *delim, uint8_t **ptr);
extern uint16_t *
u16_strtok (uint16_t *str, const uint16_t *delim, uint16_t **ptr);
extern uint32_t *
u32_strtok (uint32_t *str, const uint32_t *delim, uint32_t **ptr);
#ifdef __cplusplus
}
#endif
#endif /* _UNISTR_H */
+105
View File
@@ -0,0 +1,105 @@
/* Check UTF-8 string.
Copyright (C) 2002, 2006-2007, 2009-2015 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2002.
This program is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation; either version 2.1 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "unistr.h"
const uint8_t *
u8_check (const uint8_t *s, size_t n)
{
const uint8_t *s_end = s + n;
while (s < s_end)
{
/* Keep in sync with unistr.h and u8-mbtouc-aux.c. */
uint8_t c = *s;
if (c < 0x80)
{
s++;
continue;
}
if (c >= 0xc2)
{
if (c < 0xe0)
{
if (s + 2 <= s_end
&& (s[1] ^ 0x80) < 0x40)
{
s += 2;
continue;
}
}
else if (c < 0xf0)
{
if (s + 3 <= s_end
&& (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
&& (c >= 0xe1 || s[1] >= 0xa0)
&& (c != 0xed || s[1] < 0xa0))
{
s += 3;
continue;
}
}
else if (c < 0xf8)
{
if (s + 4 <= s_end
&& (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
&& (s[3] ^ 0x80) < 0x40
&& (c >= 0xf1 || s[1] >= 0x90)
#if 1
&& (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
#endif
)
{
s += 4;
continue;
}
}
#if 0
else if (c < 0xfc)
{
if (s + 5 <= s_end
&& (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
&& (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
&& (c >= 0xf9 || s[1] >= 0x88))
{
s += 5;
continue;
}
}
else if (c < 0xfe)
{
if (s + 6 <= s_end
&& (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
&& (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
&& (s[5] ^ 0x80) < 0x40
&& (c >= 0xfd || s[1] >= 0x84))
{
s += 6;
continue;
}
}
#endif
}
/* invalid or incomplete multibyte character */
return s;
}
return NULL;
}
+285
View File
@@ -0,0 +1,285 @@
/* Look at first character in UTF-8 string, returning an error code.
Copyright (C) 1999-2002, 2006-2007, 2009-2015 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2001.
This program is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation; either version 2.1 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "unistr.h"
int
u8_mbtoucr (ucs4_t *puc, const uint8_t *s, size_t n)
{
uint8_t c = *s;
if (c < 0x80)
{
*puc = c;
return 1;
}
else if (c >= 0xc2)
{
if (c < 0xe0)
{
if (n >= 2)
{
if ((s[1] ^ 0x80) < 0x40)
{
*puc = ((unsigned int) (c & 0x1f) << 6)
| (unsigned int) (s[1] ^ 0x80);
return 2;
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
else if (c < 0xf0)
{
if (n >= 2)
{
if ((s[1] ^ 0x80) < 0x40
&& (c >= 0xe1 || s[1] >= 0xa0)
&& (c != 0xed || s[1] < 0xa0))
{
if (n >= 3)
{
if ((s[2] ^ 0x80) < 0x40)
{
*puc = ((unsigned int) (c & 0x0f) << 12)
| ((unsigned int) (s[1] ^ 0x80) << 6)
| (unsigned int) (s[2] ^ 0x80);
return 3;
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
else if (c < 0xf8)
{
if (n >= 2)
{
if ((s[1] ^ 0x80) < 0x40
&& (c >= 0xf1 || s[1] >= 0x90)
#if 1
&& (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
#endif
)
{
if (n >= 3)
{
if ((s[2] ^ 0x80) < 0x40)
{
if (n >= 4)
{
if ((s[3] ^ 0x80) < 0x40)
{
*puc = ((unsigned int) (c & 0x07) << 18)
| ((unsigned int) (s[1] ^ 0x80) << 12)
| ((unsigned int) (s[2] ^ 0x80) << 6)
| (unsigned int) (s[3] ^ 0x80);
return 4;
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
#if 0
else if (c < 0xfc)
{
if (n >= 2)
{
if ((s[1] ^ 0x80) < 0x40
&& (c >= 0xf9 || s[1] >= 0x88))
{
if (n >= 3)
{
if ((s[2] ^ 0x80) < 0x40)
{
if (n >= 4)
{
if ((s[3] ^ 0x80) < 0x40)
{
if (n >= 5)
{
if ((s[4] ^ 0x80) < 0x40)
{
*puc = ((unsigned int) (c & 0x03) << 24)
| ((unsigned int) (s[1] ^ 0x80) << 18)
| ((unsigned int) (s[2] ^ 0x80) << 12)
| ((unsigned int) (s[3] ^ 0x80) << 6)
| (unsigned int) (s[4] ^ 0x80);
return 5;
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
else if (c < 0xfe)
{
if (n >= 2)
{
if ((s[1] ^ 0x80) < 0x40
&& (c >= 0xfd || s[1] >= 0x84))
{
if (n >= 3)
{
if ((s[2] ^ 0x80) < 0x40)
{
if (n >= 4)
{
if ((s[3] ^ 0x80) < 0x40)
{
if (n >= 5)
{
if ((s[4] ^ 0x80) < 0x40)
{
if (n >= 6)
{
if ((s[5] ^ 0x80) < 0x40)
{
*puc = ((unsigned int) (c & 0x01) << 30)
| ((unsigned int) (s[1] ^ 0x80) << 24)
| ((unsigned int) (s[2] ^ 0x80) << 18)
| ((unsigned int) (s[3] ^ 0x80) << 12)
| ((unsigned int) (s[4] ^ 0x80) << 6)
| (unsigned int) (s[5] ^ 0x80);
return 6;
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
/* invalid multibyte character */
}
else
{
/* incomplete multibyte character */
*puc = 0xfffd;
return -2;
}
}
#endif
}
/* invalid multibyte character */
*puc = 0xfffd;
return -1;
}
+69
View File
@@ -0,0 +1,69 @@
/* Conversion UCS-4 to UTF-8.
Copyright (C) 2002, 2006-2007, 2009-2015 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2002.
This program is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation; either version 2.1 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "unistr.h"
int
u8_uctomb_aux (uint8_t *s, ucs4_t uc, int n)
{
int count;
if (uc < 0x80)
/* The case n >= 1 is already handled by the caller. */
return -2;
else if (uc < 0x800)
count = 2;
else if (uc < 0x10000)
{
if (uc < 0xd800 || uc >= 0xe000)
count = 3;
else
return -1;
}
#if 0
else if (uc < 0x200000)
count = 4;
else if (uc < 0x4000000)
count = 5;
else if (uc <= 0x7fffffff)
count = 6;
#else
else if (uc < 0x110000)
count = 4;
#endif
else
return -1;
if (n < count)
return -2;
switch (count) /* note: code falls through cases! */
{
#if 0
case 6: s[5] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x4000000;
case 5: s[4] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x200000;
#endif
case 4: s[3] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x10000;
case 3: s[2] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x800;
case 2: s[1] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0xc0;
/*case 1:*/ s[0] = uc;
}
return count;
}
+88
View File
@@ -0,0 +1,88 @@
/* Store a character in UTF-8 string.
Copyright (C) 2002, 2005-2006, 2009-2015 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2002.
This program is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation; either version 2.1 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
#if defined IN_LIBUNISTRING
/* Tell unistr.h to declare u8_uctomb as 'extern', not 'static inline'. */
# include "unistring-notinline.h"
#endif
/* Specification. */
#include "unistr.h"
#if !HAVE_INLINE
int
u8_uctomb (uint8_t *s, ucs4_t uc, int n)
{
if (uc < 0x80)
{
if (n > 0)
{
s[0] = uc;
return 1;
}
/* else return -2, below. */
}
else
{
int count;
if (uc < 0x800)
count = 2;
else if (uc < 0x10000)
{
if (uc < 0xd800 || uc >= 0xe000)
count = 3;
else
return -1;
}
#if 0
else if (uc < 0x200000)
count = 4;
else if (uc < 0x4000000)
count = 5;
else if (uc <= 0x7fffffff)
count = 6;
#else
else if (uc < 0x110000)
count = 4;
#endif
else
return -1;
if (n >= count)
{
switch (count) /* note: code falls through cases! */
{
#if 0
case 6: s[5] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x4000000;
case 5: s[4] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x200000;
#endif
case 4: s[3] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x10000;
case 3: s[2] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x800;
case 2: s[1] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0xc0;
/*case 1:*/ s[0] = uc;
}
return count;
}
}
return -2;
}
#endif
+46
View File
@@ -0,0 +1,46 @@
/* Elementary types and macros for the GNU UniString library.
Copyright (C) 2002, 2005-2006, 2009-2015 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation; either version 2.1 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#ifndef _UNITYPES_H
#define _UNITYPES_H
/* Get uint8_t, uint16_t, uint32_t. */
#include <stdint.h>
/* Type representing a Unicode character. */
typedef uint32_t ucs4_t;
/* Attribute of a function whose result depends only on the arguments
(not pointers!) and which has no side effects. */
#ifndef _UC_ATTRIBUTE_CONST
# if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 95)
# define _UC_ATTRIBUTE_CONST __attribute__ ((__const__))
# else
# define _UC_ATTRIBUTE_CONST
# endif
#endif
/* Attribute of a function whose result depends only on the arguments
(possibly pointers) and global memory, and which has no side effects. */
#ifndef _UC_ATTRIBUTE_PURE
# if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96)
# define _UC_ATTRIBUTE_PURE __attribute__ ((__pure__))
# else
# define _UC_ATTRIBUTE_PURE
# endif
#endif
#endif /* _UNITYPES_H */
+46
View File
@@ -0,0 +1,46 @@
/* Elementary types and macros for the GNU UniString library.
Copyright (C) 2002, 2005-2006, 2009-2015 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation; either version 2.1 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#ifndef _UNITYPES_H
#define _UNITYPES_H
/* Get uint8_t, uint16_t, uint32_t. */
#include <stdint.h>
/* Type representing a Unicode character. */
typedef uint32_t ucs4_t;
/* Attribute of a function whose result depends only on the arguments
(not pointers!) and which has no side effects. */
#ifndef _UC_ATTRIBUTE_CONST
# if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 95)
# define _UC_ATTRIBUTE_CONST __attribute__ ((__const__))
# else
# define _UC_ATTRIBUTE_CONST
# endif
#endif
/* Attribute of a function whose result depends only on the arguments
(possibly pointers) and global memory, and which has no side effects. */
#ifndef _UC_ATTRIBUTE_PURE
# if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96)
# define _UC_ATTRIBUTE_PURE __attribute__ ((__pure__))
# else
# define _UC_ATTRIBUTE_PURE
# endif
#endif
#endif /* _UNITYPES_H */