diff options
author | Paul Eggert <eggert@cs.ucla.edu> | 2005-09-22 06:22:44 +0000 |
---|---|---|
committer | Paul Eggert <eggert@cs.ucla.edu> | 2005-09-22 06:22:44 +0000 |
commit | 3833e2bc3402fadfa2a1d256210a2cd35ba3f062 (patch) | |
tree | c385b4af4cfb7e81e98d5598b1756a5ca3c0ada5 | |
parent | 0ed6bb9a65c09df997d62e83a07c9426f5aa4838 (diff) | |
download | coreutils-3833e2bc3402fadfa2a1d256210a2cd35ba3f062.tar.xz |
New file, from gnulib.
-rw-r--r-- | lib/canon-host.h | 30 | ||||
-rw-r--r-- | lib/gai_strerror.c | 78 | ||||
-rw-r--r-- | lib/getaddrinfo.c | 210 | ||||
-rw-r--r-- | lib/getaddrinfo.h | 95 | ||||
-rw-r--r-- | lib/getdelim.c | 119 | ||||
-rw-r--r-- | lib/getdelim.h | 28 | ||||
-rw-r--r-- | lib/mbchar.c | 38 | ||||
-rw-r--r-- | lib/mbchar.h | 352 | ||||
-rw-r--r-- | lib/mbuiter.h | 203 | ||||
-rw-r--r-- | lib/strcase.h | 48 | ||||
-rw-r--r-- | lib/strnlen.h | 32 | ||||
-rw-r--r-- | lib/strnlen1.c | 39 | ||||
-rw-r--r-- | lib/strnlen1.h | 41 | ||||
-rw-r--r-- | lib/strstr.h | 37 | ||||
-rw-r--r-- | m4/getaddrinfo.m4 | 19 | ||||
-rw-r--r-- | m4/getdelim.m4 | 30 | ||||
-rw-r--r-- | m4/mbchar.m4 | 14 | ||||
-rw-r--r-- | m4/mbiter.m4 | 14 | ||||
-rw-r--r-- | m4/sockpfaf.m4 | 39 |
19 files changed, 1466 insertions, 0 deletions
diff --git a/lib/canon-host.h b/lib/canon-host.h new file mode 100644 index 000000000..c1f6cb178 --- /dev/null +++ b/lib/canon-host.h @@ -0,0 +1,30 @@ +/* Host name canonicalization + + Copyright (C) 2005 Free Software Foundation, Inc. + + Written by Derek Price <derek@ximbiot.com> + + This program is free software; you can redistribute it and/or + modify it under the terms of the GNU General Public License as + published by the Free Software Foundation; either version 2, or (at + your option) any later version. + + This program is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + +#ifndef CANON_HOST_H +# define CANON_HOST_H 1 + +char *canon_host (char const *host); +char *canon_host_r (char const *host, int *cherror); + +const char *ch_strerror (void); +# define ch_strerror_r(cherror) gai_strerror (cherror); + +#endif /* !CANON_HOST_H */ diff --git a/lib/gai_strerror.c b/lib/gai_strerror.c new file mode 100644 index 000000000..f2898706e --- /dev/null +++ b/lib/gai_strerror.c @@ -0,0 +1,78 @@ +/* Copyright (C) 1997, 2001, 2002, 2004, 2005 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Philip Blundell <pjb27@cam.ac.uk>, 1997. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + +#ifdef HAVE_CONFIG_H +# include <config.h> +#endif + +#ifndef _LIBC +# include "getaddrinfo.h" +#endif + +#include <stdio.h> +#include <netdb.h> + +#ifdef _LIBC +# include <libintl.h> +#else +# include "gettext.h" +# define _(String) gettext (String) +# define N_(String) String +#endif + +static struct + { + int code; + const char *msg; + } +values[] = + { + { EAI_ADDRFAMILY, N_("Address family for hostname not supported") }, + { EAI_AGAIN, N_("Temporary failure in name resolution") }, + { EAI_BADFLAGS, N_("Bad value for ai_flags") }, + { EAI_FAIL, N_("Non-recoverable failure in name resolution") }, + { EAI_FAMILY, N_("ai_family not supported") }, + { EAI_MEMORY, N_("Memory allocation failure") }, + { EAI_NODATA, N_("No address associated with hostname") }, + { EAI_NONAME, N_("Name or service not known") }, + { EAI_SERVICE, N_("Servname not supported for ai_socktype") }, + { EAI_SOCKTYPE, N_("ai_socktype not supported") }, + { EAI_SYSTEM, N_("System error") }, +#ifdef __USE_GNU + { EAI_INPROGRESS, N_("Processing request in progress") }, + { EAI_CANCELED, N_("Request canceled") }, + { EAI_NOTCANCELED, N_("Request not canceled") }, + { EAI_ALLDONE, N_("All requests done") }, + { EAI_INTR, N_("Interrupted by a signal") }, + { EAI_IDN_ENCODE, N_("Parameter string not correctly encoded") } +#endif + }; + +const char * +gai_strerror (int code) +{ + size_t i; + for (i = 0; i < sizeof (values) / sizeof (values[0]); ++i) + if (values[i].code == code) + return _(values[i].msg); + + return _("Unknown error"); +} +#ifdef _LIBC +libc_hidden_def (gai_strerror) +#endif diff --git a/lib/getaddrinfo.c b/lib/getaddrinfo.c new file mode 100644 index 000000000..594b76494 --- /dev/null +++ b/lib/getaddrinfo.c @@ -0,0 +1,210 @@ +/* Get address information (partial implementation). + Copyright (C) 1997, 2001, 2002, 2004, 2005 Free Software Foundation, Inc. + Contributed by Simon Josefsson <simon@josefsson.org>. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + +#ifdef HAVE_CONFIG_H +# include <config.h> +#endif + +#include "getaddrinfo.h" + +/* Get calloc. */ +#include <stdlib.h> + +/* Get memcpy. */ +#include <string.h> + +#include <stdbool.h> + +#include "gettext.h" +#define _(String) gettext (String) +#define N_(String) String + +#include "strdup.h" + +static inline bool +validate_family (int family) +{ + /* FIXME: Support more families. */ +#if HAVE_IPV4 + if (family == PF_INET) + return true; +#endif +#if HAVE_IPV6 + if (family == PF_INET6) + return true; +#endif + if (family == PF_UNSPEC) + return true; + return false; +} + +/* Translate name of a service location and/or a service name to set of + socket addresses. */ +int +getaddrinfo (const char *restrict nodename, + const char *restrict servname, + const struct addrinfo *restrict hints, + struct addrinfo **restrict res) +{ + struct addrinfo *tmp; + struct servent *se; + struct hostent *he; + size_t sinlen; + + if (hints && (hints->ai_flags & ~AI_CANONNAME)) + /* FIXME: Support more flags. */ + return EAI_BADFLAGS; + + if (hints && !validate_family (hints->ai_family)) + return EAI_FAMILY; + + if (hints && + hints->ai_socktype != SOCK_STREAM && hints->ai_socktype != SOCK_DGRAM) + /* FIXME: Support other socktype. */ + return EAI_SOCKTYPE; /* FIXME: Better return code? */ + + if (!nodename) + /* FIXME: Support server bind mode. */ + return EAI_NONAME; + + if (servname) + { + const char *proto = + (hints && hints->ai_socktype == SOCK_DGRAM) ? "udp" : "tcp"; + + /* FIXME: Use getservbyname_r if available. */ + se = getservbyname (servname, proto); + + if (!se) + return EAI_SERVICE; + } + + /* FIXME: Use gethostbyname_r if available. */ + he = gethostbyname (nodename); + if (!he || he->h_addr_list[0] == NULL) + return EAI_NONAME; + + switch (he->h_addrtype) + { +#if HAVE_IPV6 + case PF_INET6: + sinlen = sizeof (struct sockaddr_in6); + break; +#endif + +#if HAVE_IPV4 + case PF_INET: + sinlen = sizeof (struct sockaddr_in); + break; +#endif + + default: + return EAI_NODATA; + } + + tmp = calloc (1, sizeof (*tmp) + sinlen); + if (!tmp) + return EAI_MEMORY; + + switch (he->h_addrtype) + { +#if HAVE_IPV6 + case PF_INET6: + { + struct sockaddr_in6 *sinp = (char *) tmp + sizeof (*tmp); + + if (se) + sinp->sin6_port = se->s_port; + + if (he->h_length != sizeof (sinp->sin6_addr)) + return EAI_SYSTEM; /* FIXME: Better return code? Set errno? */ + + memcpy (&sinp->sin6_addr, he->h_addr_list[0], he->h_length); + + tmp->ai_addr = (struct sockaddr *) sinp; + tmp->ai_addrlen = sinlen; + } + break; +#endif + +#if HAVE_IPV4 + case PF_INET: + { + struct sockaddr_in *sinp = (char *) tmp + sizeof (*tmp); + + if (se) + sinp->sin_port = se->s_port; + + if (he->h_length != sizeof (sinp->sin_addr)) + return EAI_SYSTEM; /* FIXME: Better return code? Set errno? */ + + memcpy (&sinp->sin_addr, he->h_addr_list[0], he->h_length); + + tmp->ai_addr = (struct sockaddr *) sinp; + tmp->ai_addrlen = sinlen; + } + break; +#endif + + default: + free (tmp); + return EAI_NODATA; + } + + if (hints && hints->ai_flags & AI_CANONNAME) + { + const char *cn; + if (he->h_name) + cn = he->h_name; + else + cn = nodename; + + tmp->ai_canonname = strdup (cn); + if (!tmp->ai_canonname) + { + free (tmp); + return EAI_MEMORY; + } + } + + tmp->ai_protocol = (hints) ? hints->ai_protocol : 0; + tmp->ai_socktype = (hints) ? hints->ai_socktype : 0; + tmp->ai_addr->sa_family = he->h_addrtype; + + /* FIXME: If more than one address, create linked list of addrinfo's. */ + + *res = tmp; + + return 0; +} + +/* Free `addrinfo' structure AI including associated storage. */ +void +freeaddrinfo (struct addrinfo *ai) +{ + while (ai) + { + struct addrinfo *cur; + + cur = ai; + ai = ai->ai_next; + + if (cur->ai_canonname) free (cur->ai_canonname); + free (cur); + } +} diff --git a/lib/getaddrinfo.h b/lib/getaddrinfo.h new file mode 100644 index 000000000..5d14562c2 --- /dev/null +++ b/lib/getaddrinfo.h @@ -0,0 +1,95 @@ +/* Get address information. + Copyright (C) 1996-2002, 2003, 2004, 2005 Free Software Foundation, Inc. + Contributed by Simon Josefsson <simon@josefsson.org>. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + +#ifndef GETADDRINFO_H +# define GETADDRINFO_H + +/* Get getaddrinfo declarations, if available. Also get 'socklen_t', + and 'struct sockaddr' via sys/types.h which are used below. */ +# include <sys/types.h> +# include <sys/socket.h> +# include <netdb.h> + +# if !HAVE_GETADDRINFO + +/* Structure to contain information about address of a service provider. */ +struct addrinfo +{ + int ai_flags; /* Input flags. */ + int ai_family; /* Protocol family for socket. */ + int ai_socktype; /* Socket type. */ + int ai_protocol; /* Protocol for socket. */ + socklen_t ai_addrlen; /* Length of socket address. */ + struct sockaddr *ai_addr; /* Socket address for socket. */ + char *ai_canonname; /* Canonical name for service location. */ + struct addrinfo *ai_next; /* Pointer to next in list. */ +}; + +/* Possible values for `ai_flags' field in `addrinfo' structure. */ +# define AI_PASSIVE 0x0001 /* Socket address is intended for `bind'. */ +# define AI_CANONNAME 0x0002 /* Request for canonical name. */ +# define AI_NUMERICHOST 0x0004 /* Don't use name resolution. */ +# define AI_V4MAPPED 0x0008 /* IPv4 mapped addresses are acceptable. */ +# define AI_ALL 0x0010 /* Return IPv4 mapped and IPv6 addresses. */ +# define AI_ADDRCONFIG 0x0020 /* Use configuration of this host to choose + returned address type.. */ + +/* Error values for `getaddrinfo' function. */ +# define EAI_BADFLAGS -1 /* Invalid value for `ai_flags' field. */ +# define EAI_NONAME -2 /* NAME or SERVICE is unknown. */ +# define EAI_AGAIN -3 /* Temporary failure in name resolution. */ +# define EAI_FAIL -4 /* Non-recoverable failure in name res. */ +# define EAI_NODATA -5 /* No address associated with NAME. */ +# define EAI_FAMILY -6 /* `ai_family' not supported. */ +# define EAI_SOCKTYPE -7 /* `ai_socktype' not supported. */ +# define EAI_SERVICE -8 /* SERVICE not supported for `ai_socktype'. */ +# define EAI_ADDRFAMILY -9 /* Address family for NAME not supported. */ +# define EAI_MEMORY -10 /* Memory allocation failure. */ +# define EAI_SYSTEM -11 /* System error returned in `errno'. */ +# define EAI_OVERFLOW -12 /* Argument buffer overflow. */ +# ifdef __USE_GNU +# define EAI_INPROGRESS -100 /* Processing request in progress. */ +# define EAI_CANCELED -101 /* Request canceled. */ +# define EAI_NOTCANCELED -102 /* Request not canceled. */ +# define EAI_ALLDONE -103 /* All requests done. */ +# define EAI_INTR -104 /* Interrupted by a signal. */ +# define EAI_IDN_ENCODE -105 /* IDN encoding failed. */ +# endif + +/* Translate name of a service location and/or a service name to set of + socket addresses. + For more details, see the POSIX:2001 specification + <http://www.opengroup.org/susv3xsh/getaddrinfo.html>. */ +extern int getaddrinfo (const char *restrict nodename, + const char *restrict servname, + const struct addrinfo *restrict hints, + struct addrinfo **restrict res); + +/* Free `addrinfo' structure AI including associated storage. + For more details, see the POSIX:2001 specification + <http://www.opengroup.org/susv3xsh/getaddrinfo.html>. */ +extern void freeaddrinfo (struct addrinfo *ai); + +/* Convert error return from getaddrinfo() to a string. + For more details, see the POSIX:2001 specification + <http://www.opengroup.org/susv3xsh/gai_strerror.html>. */ +extern const char *gai_strerror (int ecode); + +# endif /* !HAVE_GETADDRINFO */ + +#endif /* GETADDRINFO_H */ diff --git a/lib/getdelim.c b/lib/getdelim.c new file mode 100644 index 000000000..8498b7556 --- /dev/null +++ b/lib/getdelim.c @@ -0,0 +1,119 @@ +/* getdelim.c --- Implementation of replacement getdelim function. + Copyright (C) 1994, 1996, 1997, 1998, 2001, 2003, 2005 Free + Software Foundation, Inc. + + This program is free software; you can redistribute it and/or + modify it under the terms of the GNU General Public License as + published by the Free Software Foundation; either version 2, or (at + your option) any later version. + + This program is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + 02110-1301, USA. */ + +/* Ported from glibc by Simon Josefsson. */ + +#ifdef HAVE_CONFIG_H +# include <config.h> +#endif + +#include <stdlib.h> +#include <errno.h> + +#include "getdelim.h" + +#if !HAVE_FLOCKFILE +# undef flockfile +# define flockfile(x) ((void) 0) +#endif +#if !HAVE_FUNLOCKFILE +# undef funlockfile +# define funlockfile(x) ((void) 0) +#endif + +/* Read up to (and including) a DELIMITER from FP into *LINEPTR (and + NUL-terminate it). *LINEPTR is a pointer returned from malloc (or + NULL), pointing to *N characters of space. It is realloc'ed as + necessary. Returns the number of characters read (not including + the null terminator), or -1 on error or EOF. */ + +ssize_t +getdelim (char **lineptr, size_t *n, int delimiter, FILE *fp) +{ + int result = 0; + ssize_t cur_len = 0; + ssize_t len; + + if (lineptr == NULL || n == NULL || fp == NULL) + { + errno = EINVAL; + return -1; + } + + flockfile (fp); + + if (*lineptr == NULL || *n == 0) + { + *n = 120; + *lineptr = (char *) malloc (*n); + if (*lineptr == NULL) + { + result = -1; + goto unlock_return; + } + } + + for (;;) + { + char *t; + int i; + + i = getc (fp); + if (i == EOF) + { + result = -1; + break; + } + + /* Make enough space for len+1 (for final NUL) bytes. */ + if (cur_len + 1 >= *n) + { + size_t needed = 2 * (cur_len + 1) + 1; /* Be generous. */ + char *new_lineptr; + + if (needed < cur_len) + { + result = -1; + goto unlock_return; + } + + new_lineptr = (char *) realloc (*lineptr, needed); + if (new_lineptr == NULL) + { + result = -1; + goto unlock_return; + } + + *lineptr = new_lineptr; + *n = needed; + } + + (*lineptr)[cur_len] = i; + cur_len++; + + if (i == delimiter) + break; + } + (*lineptr)[cur_len] = '\0'; + result = cur_len ? cur_len : result; + + unlock_return: + funlockfile (fp); + return result; +} diff --git a/lib/getdelim.h b/lib/getdelim.h new file mode 100644 index 000000000..8bc61307e --- /dev/null +++ b/lib/getdelim.h @@ -0,0 +1,28 @@ +/* getdelim.h --- Prototype for replacement getdelim function. + Copyright (C) 2005 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or + modify it under the terms of the GNU General Public License as + published by the Free Software Foundation; either version 2, or (at + your option) any later version. + + This program is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + 02110-1301, USA. */ + +/* Written by Simon Josefsson. */ + +/* Get size_t, FILE, ssize_t. And getdelim, if available. */ +# include <stddef.h> +# include <stdio.h> +# include <sys/types.h> + +#if !HAVE_DECL_GETDELIM +ssize_t getdelim (char **lineptr, size_t *n, int delimiter, FILE *stream); +#endif /* !HAVE_GETDELIM */ diff --git a/lib/mbchar.c b/lib/mbchar.c new file mode 100644 index 000000000..6facc1492 --- /dev/null +++ b/lib/mbchar.c @@ -0,0 +1,38 @@ +/* Copyright (C) 2001 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ + + +#ifdef HAVE_CONFIG_H +# include <config.h> +#endif + +#include <limits.h> + +#include "mbchar.h" + +#if IS_BASIC_ASCII + +/* Bit table of characters in the ISO C "basic character set". */ +unsigned int is_basic_table [UCHAR_MAX / 32 + 1] = +{ + 0x00001a00, /* '\t' '\v' '\f' */ + 0xffffffef, /* ' '...'#' '%'...'?' */ + 0xfffffffe, /* 'A'...'Z' '[' '\\' ']' '^' '_' */ + 0x7ffffffe /* 'a'...'z' '{' '|' '}' '~' */ + /* The remaining bits are 0. */ +}; + +#endif /* IS_BASIC_ASCII */ diff --git a/lib/mbchar.h b/lib/mbchar.h new file mode 100644 index 000000000..4472aa020 --- /dev/null +++ b/lib/mbchar.h @@ -0,0 +1,352 @@ +/* Multibyte character data type. + Copyright (C) 2001, 2005 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ + +/* Written by Bruno Haible <bruno@clisp.org>. */ + +/* A multibyte character is a short subsequence of a char* string, + representing a single wide character. + + We use multibyte characters instead of wide characters because of + the following goals: + 1) correct multibyte handling, i.e. operate according to the LC_CTYPE + locale, + 2) ease of maintenance, i.e. the maintainer needs not know all details + of the ISO C 99 standard, + 3) don't fail grossly if the input is not in the encoding set by the + locale, because often different encodings are in use in the same + countries (ISO-8859-1/UTF-8, EUC-JP/Shift_JIS, ...), + 4) fast in the case of ASCII characters, + 5) portability, i.e. don't make unportable assumptions about wchar_t. + + Multibyte characters are only accessed through the mb* macros. + + mb_ptr (mbc) + return a pointer to the beginning of the multibyte sequence. + + mb_len (mbc) + returns the number of bytes occupied by the multibyte sequence. + Always > 0. + + mb_iseq (mbc, sc) + returns true if mbc is the standard ASCII character sc. + + mb_isnul (mbc) + returns true if mbc is the nul character. + + mb_cmp (mbc1, mbc2) + returns a positive, zero, or negative value depending on whether mbc1 + sorts after, same or before mbc2. + + mb_casecmp (mbc1, mbc2) + returns a positive, zero, or negative value depending on whether mbc1 + sorts after, same or before mbc2, modulo upper/lowercase conversion. + + mb_equal (mbc1, mbc2) + returns true if mbc1 and mbc2 are equal. + + mb_caseequal (mbc1, mbc2) + returns true if mbc1 and mbc2 are equal modulo upper/lowercase conversion. + + mb_isalnum (mbc) + returns true if mbc is alphanumeric. + + mb_isalpha (mbc) + returns true if mbc is alphabetic. + + mb_isascii(mbc) + returns true if mbc is plain ASCII. + + mb_isblank (mbc) + returns true if mbc is a blank. + + mb_iscntrl (mbc) + returns true if mbc is a control character. + + mb_isdigit (mbc) + returns true if mbc is a decimal digit. + + mb_isgraph (mbc) + returns true if mbc is a graphic character. + + mb_islower (mbc) + returns true if mbc is lowercase. + + mb_isprint (mbc) + returns true if mbc is a printable character. + + mb_ispunct (mbc) + returns true if mbc is a punctuation character. + + mb_isspace (mbc) + returns true if mbc is a space character. + + mb_isupper (mbc) + returns true if mbc is uppercase. + + mb_isxdigit (mbc) + returns true if mbc is a hexadecimal digit. + + mb_width (mbc) + returns the number of columns on the output device occupied by mbc. + Always >= 0. + + mb_putc (mbc, stream) + outputs mbc on stream, a byte oriented FILE stream opened for output. + + mb_setascii (&mbc, sc) + assigns the standard ASCII character sc to mbc. + + mb_copy (&destmbc, &srcmbc) + copies srcmbc to destmbc. + + Here are the function prototypes of the macros. + + extern const char * mb_ptr (const mbchar_t mbc); + extern size_t mb_len (const mbchar_t mbc); + extern bool mb_iseq (const mbchar_t mbc, char sc); + extern bool mb_isnul (const mbchar_t mbc); + extern int mb_cmp (const mbchar_t mbc1, const mbchar_t mbc2); + extern int mb_casecmp (const mbchar_t mbc1, const mbchar_t mbc2); + extern bool mb_equal (const mbchar_t mbc1, const mbchar_t mbc2); + extern bool mb_caseequal (const mbchar_t mbc1, const mbchar_t mbc2); + extern bool mb_isalnum (const mbchar_t mbc); + extern bool mb_isalpha (const mbchar_t mbc); + extern bool mb_isascii (const mbchar_t mbc); + extern bool mb_isblank (const mbchar_t mbc); + extern bool mb_iscntrl (const mbchar_t mbc); + extern bool mb_isdigit (const mbchar_t mbc); + extern bool mb_isgraph (const mbchar_t mbc); + extern bool mb_islower (const mbchar_t mbc); + extern bool mb_isprint (const mbchar_t mbc); + extern bool mb_ispunct (const mbchar_t mbc); + extern bool mb_isspace (const mbchar_t mbc); + extern bool mb_isupper (const mbchar_t mbc); + extern bool mb_isxdigit (const mbchar_t mbc); + extern int mb_width (const mbchar_t mbc); + extern void mb_putc (const mbchar_t mbc, FILE *stream); + extern void mb_setascii (mbchar_t *new, char sc); + extern void mb_copy (mbchar_t *new, const mbchar_t *old); + */ + +#ifndef _MBCHAR_H +#define _MBCHAR_H 1 + +#include <stdbool.h> +#include <string.h> + +/* Tru64 with Desktop Toolkit C has a bug: <stdio.h> must be included before + <wchar.h>. + BSD/OS 4.1 has a bug: <stdio.h> and <time.h> must be included before + <wchar.h>. */ +#include <stdio.h> +#include <time.h> +#include <wchar.h> + +#include <wctype.h> + +#define MBCHAR_BUF_SIZE 24 + +struct mbchar +{ + const char *ptr; /* pointer to current character */ + size_t bytes; /* number of bytes of current character, > 0 */ + bool wc_valid; /* true if wc is a valid wide character */ + wchar_t wc; /* if wc_valid: the current character */ + char buf[MBCHAR_BUF_SIZE]; /* room for the bytes, used for file input only */ +}; + +/* EOF (not a real character) is represented with bytes = 0 and + wc_valid = false. */ + +typedef struct mbchar mbchar_t; + +/* Access the current character. */ +#define mb_ptr(mbc) ((mbc).ptr) +#define mb_len(mbc) ((mbc).bytes) + +/* Comparison of characters. */ +#define mb_iseq(mbc, sc) ((mbc).wc_valid && (mbc).wc == (sc)) +#define mb_isnul(mbc) ((mbc).wc_valid && (mbc).wc == 0) +#define mb_cmp(mbc1, mbc2) \ + ((mbc1).wc_valid \ + ? ((mbc2).wc_valid \ + ? (int) (mbc1).wc - (int) (mbc2).wc \ + : -1) \ + : ((mbc2).wc_valid \ + ? 1 \ + : (mbc1).bytes == (mbc2).bytes \ + ? memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) \ + : (mbc1).bytes < (mbc2).bytes \ + ? (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) > 0 ? 1 : -1) \ + : (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc2).bytes) >= 0 ? 1 : -1))) +#define mb_casecmp(mbc1, mbc2) \ + ((mbc1).wc_valid \ + ? ((mbc2).wc_valid \ + ? (int) towlower ((mbc1).wc) - (int) towlower ((mbc2).wc) \ + : -1) \ + : ((mbc2).wc_valid \ + ? 1 \ + : (mbc1).bytes == (mbc2).bytes \ + ? memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) \ + : (mbc1).bytes < (mbc2).bytes \ + ? (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) > 0 ? 1 : -1) \ + : (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc2).bytes) >= 0 ? 1 : -1))) +#define mb_equal(mbc1, mbc2) \ + ((mbc1).wc_valid && (mbc2).wc_valid \ + ? (mbc1).wc == (mbc2).wc \ + : (mbc1).bytes == (mbc2).bytes \ + && memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) == 0) +#define mb_caseequal(mbc1, mbc2) \ + ((mbc1).wc_valid && (mbc2).wc_valid \ + ? towlower ((mbc1).wc) == towlower ((mbc2).wc) \ + : (mbc1).bytes == (mbc2).bytes \ + && memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) == 0) + +/* <ctype.h>, <wctype.h> classification. */ +#define mb_isascii(mbc) \ + ((mbc).wc_valid && (mbc).wc >= 0 && (mbc).wc <= 127) +#define mb_isalnum(mbc) ((mbc).wc_valid && iswalnum ((mbc).wc)) +#define mb_isalpha(mbc) ((mbc).wc_valid && iswalpha ((mbc).wc)) +#define mb_isblank(mbc) ((mbc).wc_valid && iswblank ((mbc).wc)) +#define mb_iscntrl(mbc) ((mbc).wc_valid && iswcntrl ((mbc).wc)) +#define mb_isdigit(mbc) ((mbc).wc_valid && iswdigit ((mbc).wc)) +#define mb_isgraph(mbc) ((mbc).wc_valid && iswgraph ((mbc).wc)) +#define mb_islower(mbc) ((mbc).wc_valid && iswlower ((mbc).wc)) +#define mb_isprint(mbc) ((mbc).wc_valid && iswprint ((mbc).wc)) +#define mb_ispunct(mbc) ((mbc).wc_valid && iswpunct ((mbc).wc)) +#define mb_isspace(mbc) ((mbc).wc_valid && iswspace ((mbc).wc)) +#define mb_isupper(mbc) ((mbc).wc_valid && iswupper ((mbc).wc)) +#define mb_isxdigit(mbc) ((mbc).wc_valid && iswxdigit ((mbc).wc)) + +/* Extra <wchar.h> function. */ + +/* Unprintable characters appear as a small box of width 1. */ +#define MB_UNPRINTABLE_WIDTH 1 + +static inline int +mb_width_aux (wint_t wc) +{ + int w = wcwidth (wc); + /* For unprintable characters, arbitrarily return 0 for control characters + and MB_UNPRINTABLE_WIDTH otherwise. */ + return (w >= 0 ? w : iswcntrl (wc) ? 0 : MB_UNPRINTABLE_WIDTH); +} + +#define mb_width(mbc) \ + ((mbc).wc_valid ? mb_width_aux ((mbc).wc) : MB_UNPRINTABLE_WIDTH) + +/* Output. */ +#define mb_putc(mbc, stream) fwrite ((mbc).ptr, 1, (mbc).bytes, (stream)) + +/* Assignment. */ +#define mb_setascii(mbc, sc) \ + ((mbc)->ptr = (mbc)->buf, (mbc)->bytes = 1, (mbc)->wc_valid = 1, \ + (mbc)->wc = (mbc)->buf[0] = (sc)) + +/* Copying a character. */ +static inline void +mb_copy (mbchar_t *new, const mbchar_t *old) +{ + if (old->ptr == &old->buf[0]) + { + memcpy (&new->buf[0], &old->buf[0], old->bytes); + new->ptr = &new->buf[0]; + } + else + new->ptr = old->ptr; + new->bytes = old->bytes; + if ((new->wc_valid = old->wc_valid)) + new->wc = old->wc; +} + + +/* is_basic(c) tests whether the single-byte character c is in the + ISO C "basic character set". + This is a convenience function, and is in this file only to share code + between mbiter_multi.h and mbfile_multi.h. */ +#if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \ + && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \ + && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \ + && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \ + && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \ + && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \ + && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \ + && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \ + && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \ + && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \ + && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \ + && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \ + && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \ + && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \ + && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \ + && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \ + && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \ + && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \ + && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \ + && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \ + && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \ + && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \ + && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126) +/* The character set is ISO-646, not EBCDIC. */ +# define IS_BASIC_ASCII 1 + +extern unsigned int is_basic_table[]; + +static inline bool +is_basic (char c) +{ + return (is_basic_table [(unsigned char) c >> 5] >> ((unsigned char) c & 31)) + & 1; +} + +#else + +static inline bool +is_basic (char c) +{ + switch (c) + { + case '\t': case '\v': case '\f': + 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 '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 '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 + +#endif /* _MBCHAR_H */ diff --git a/lib/mbuiter.h b/lib/mbuiter.h new file mode 100644 index 000000000..9da3a6c79 --- /dev/null +++ b/lib/mbuiter.h @@ -0,0 +1,203 @@ +/* Iterating through multibyte strings: macros for multi-byte encodings. + Copyright (C) 2001, 2005 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ + +/* Written by Bruno Haible <bruno@clisp.org>. */ + +/* The macros in this file implement forward iteration through a + multi-byte string, without knowing its length a-priori. + + With these macros, an iteration loop that looks like + + char *iter; + for (iter = buf; *iter != '\0'; iter++) + { + do_something (*iter); + } + + becomes + + mbui_iterator_t iter; + for (mbui_init (iter, buf); mbui_avail (iter); mbui_advance (iter)) + { + do_something (mbui_cur_ptr (iter), mb_len (mbui_cur (iter))); + } + + The benefit of these macros over plain use of mbrtowc is: + - Handling of invalid multibyte sequences is possible without + making the code more complicated, while still preserving the + invalid multibyte sequences. + + Compared to mbiter.h, the macros here don't need to know the string's + length a-priori. The downside is that at each step, the look-ahead + that guards against overrunning the terminating '\0' is more expensive. + The mbui_* macros are therefore suitable when there is a high probability + that only the first few multibyte characters need to be inspected. + Whereas the mbi_* macros are better if usually the iteration runs + through the entire string. + + mbui_iterator_t + is a type usable for variable declarations. + + mbui_init (iter, startptr) + initializes the iterator, starting at startptr. + + mbui_avail (iter) + returns true if there are more multibyte chracters available before + the end of string is reached. In this case, mbui_cur (iter) is + initialized to the next multibyte chracter. + + mbui_advance (iter) + advances the iterator by one multibyte character. + + mbui_cur (iter) + returns the current multibyte character, of type mbchar_t. All the + macros defined in mbchar.h can be used on it. + + mbui_cur_ptr (iter) + return a pointer to the beginning of the current multibyte character. + + mbui_reloc (iter, ptrdiff) + relocates iterator when the string is moved by ptrdiff bytes. + + Here are the function prototypes of the macros. + + extern void mbui_init (mbui_iterator_t iter, const char *startptr); + extern bool mbui_avail (mbui_iterator_t iter); + extern void mbui_advance (mbui_iterator_t iter); + extern mbchar_t mbui_cur (mbui_iterator_t iter); + extern const char * mbui_cur_ptr (mbui_iterator_t iter); + extern void mbui_reloc (mbui_iterator_t iter, ptrdiff_t ptrdiff); + */ + +#ifndef _MBUITER_H +#define _MBUITER_H 1 + +#include <assert.h> +#include <stdbool.h> +#include <stdlib.h> + +/* Tru64 with Desktop Toolkit C has a bug: <stdio.h> must be included before + <wchar.h>. + BSD/OS 4.1 has a bug: <stdio.h> and <time.h> must be included before + <wchar.h>. */ +#include <stdio.h> +#include <time.h> +#include <wchar.h> + +#include "mbchar.h" +#include "strnlen1.h" + +struct mbuiter_multi +{ + bool in_shift; /* true if next byte may not be interpreted as ASCII */ + mbstate_t state; /* if in_shift: current shift state */ + bool next_done; /* true if mbui_avail has already filled the following */ + struct mbchar cur; /* the current character: + const char *cur.ptr pointer to current character + The following are only valid after mbui_avail. + size_t cur.bytes number of bytes of current character + bool cur.wc_valid true if wc is a valid wide character + wchar_t cur.wc if wc_valid: the current character + */ +}; + +static inline void +mbuiter_multi_next (struct mbuiter_multi *iter) +{ + if (iter->next_done) + return; + if (iter->in_shift) + goto with_shift; + /* Handle most ASCII characters quickly, without calling mbrtowc(). */ + if (is_basic (*iter->cur.ptr)) + { + /* These characters are part of the basic character set. ISO C 99 + guarantees that their wide character code is identical to their + char code. */ + iter->cur.bytes = 1; + iter->cur.wc = *iter->cur.ptr; + iter->cur.wc_valid = true; + } + else + { + assert (mbsinit (&iter->state)); + iter->in_shift = true; + with_shift: + iter->cur.bytes = mbrtowc (&iter->cur.wc, iter->cur.ptr, + strnlen1 (iter->cur.ptr, MB_CUR_MAX), + &iter->state); + if (iter->cur.bytes == (size_t) -1) + { + /* An invalid multibyte sequence was encountered. */ + iter->cur.bytes = 1; + iter->cur.wc_valid = false; + /* Whether to set iter->in_shift = false and reset iter->state + or not is not very important; the string is bogus anyway. */ + } + else if (iter->cur.bytes == (size_t) -2) + { + /* An incomplete multibyte character at the end. */ + iter->cur.bytes = strlen (iter->cur.ptr); + iter->cur.wc_valid = false; + /* Whether to set iter->in_shift = false and reset iter->state + or not is not important; the string end is reached anyway. */ + } + else + { + if (iter->cur.bytes == 0) + { + /* A null wide character was encountered. */ + iter->cur.bytes = 1; + assert (*iter->cur.ptr == '\0'); + assert (iter->cur.wc == 0); + } + iter->cur.wc_valid = true; + + /* When in the initial state, we can go back treating ASCII + characters more quickly. */ + if (mbsinit (&iter->state)) + iter->in_shift = false; + } + } + iter->next_done = true; +} + +static inline void +mbuiter_multi_reloc (struct mbuiter_multi *iter, ptrdiff_t ptrdiff) +{ + iter->cur.ptr += ptrdiff; +} + +/* Iteration macros. */ +typedef struct mbuiter_multi mbui_iterator_t; +#define mbui_init(iter, startptr) \ + ((iter).cur.ptr = (startptr), \ + (iter).in_shift = false, memset (&(iter).state, '\0', sizeof (mbstate_t)), \ + (iter).next_done = false) +#define mbui_avail(iter) \ + (mbuiter_multi_next (&(iter)), !mb_isnul ((iter).cur)) +#define mbui_advance(iter) \ + ((iter).cur.ptr += (iter).cur.bytes, (iter).next_done = false) + +/* Access to the current character. */ +#define mbui_cur(iter) (iter).cur +#define mbui_cur_ptr(iter) (iter).cur.ptr + +/* Relocation. */ +#define mbui_reloc(iter, ptrdiff) mbuiter_multi_reloc (&iter, ptrdiff) + +#endif /* _MBUITER_H */ diff --git a/lib/strcase.h b/lib/strcase.h new file mode 100644 index 000000000..e42079805 --- /dev/null +++ b/lib/strcase.h @@ -0,0 +1,48 @@ +/* Case-insensitive string comparison functions. + Copyright (C) 1995-1996, 2001, 2003, 2005 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + +#ifndef _STRCASE_H +#define _STRCASE_H + +#include <stddef.h> + + +#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. + Note: This function may, in multibyte locales, return 0 for strings of + different lengths! */ +extern int strcasecmp (const char *s1, const char *s2); + +/* 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. + Note: This function can not work correctly in multibyte locales. */ +extern int strncasecmp (const char *s1, const char *s2, size_t n); + + +#ifdef __cplusplus +} +#endif + + +#endif /* _STRCASE_H */ diff --git a/lib/strnlen.h b/lib/strnlen.h new file mode 100644 index 000000000..ba74dba7b --- /dev/null +++ b/lib/strnlen.h @@ -0,0 +1,32 @@ +/* Find the length of STRING, but scan at most MAXLEN characters. + Copyright (C) 2005 Free Software Foundation, Inc. + Written by Simon Josefsson. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + +#ifndef STRNLEN_H +#define STRNLEN_H + +/* Get strnlen declaration, if available. */ +#include <string.h> + +#if defined HAVE_DECL_STRNLEN && !HAVE_DECL_STRNLEN +/* Find the length (number of bytes) of STRING, but scan at most + MAXLEN bytes. If no '\0' terminator is found in that many bytes, + return MAXLEN. */ +extern size_t strnlen(const char *string, size_t maxlen); +#endif + +#endif /* STRNLEN_H */ diff --git a/lib/strnlen1.c b/lib/strnlen1.c new file mode 100644 index 000000000..f3338e7cf --- /dev/null +++ b/lib/strnlen1.c @@ -0,0 +1,39 @@ +/* Find the length of STRING + 1, but scan at most MAXLEN bytes. + Copyright (C) 2005 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify it + under the terms of the GNU Library General Public License as published + by the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, + USA. */ + +#ifdef HAVE_CONFIG_H +# include <config.h> +#endif + +/* Specification. */ +#include "strnlen1.h" + +#include <string.h> + +/* Find the length of STRING + 1, but scan at most MAXLEN bytes. + If no '\0' terminator is found in that many characters, return MAXLEN. */ +/* This is the same as strnlen (string, maxlen - 1) + 1. */ +size_t +strnlen1 (const char *string, size_t maxlen) +{ + const char *end = memchr (string, '\0', maxlen); + if (end != NULL) + return end - string + 1; + else + return maxlen; +} diff --git a/lib/strnlen1.h b/lib/strnlen1.h new file mode 100644 index 000000000..4f913ffe8 --- /dev/null +++ b/lib/strnlen1.h @@ -0,0 +1,41 @@ +/* Find the length of STRING + 1, but scan at most MAXLEN bytes. + Copyright (C) 2005 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify it + under the terms of the GNU Library General Public License as published + by the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, + USA. */ + +#ifndef _STRNLEN1_H +#define _STRNLEN1_H + +#include <stddef.h> + + +#ifdef __cplusplus +extern "C" { +#endif + + +/* Find the length of STRING + 1, but scan at most MAXLEN bytes. + If no '\0' terminator is found in that many characters, return MAXLEN. */ +/* This is the same as strnlen (string, maxlen - 1) + 1. */ +extern size_t strnlen1 (const char *string, size_t maxlen); + + +#ifdef __cplusplus +} +#endif + + +#endif /* _STRNLEN1_H */ diff --git a/lib/strstr.h b/lib/strstr.h new file mode 100644 index 000000000..a28b1401e --- /dev/null +++ b/lib/strstr.h @@ -0,0 +1,37 @@ +/* Searching in a string. + Copyright (C) 2001-2003, 2005 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software Foundation, + Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + + +/* Include string.h: on glibc systems, it contains a macro definition of + strstr() that would collide with our definition if included afterwards. */ +#include <string.h> + +#ifdef __cplusplus +extern "C" { +#endif + +/* No known system has a strstr() function that works correctly in + multibyte locales. Therefore we use our version always. */ +#undef strstr +#define strstr rpl_strstr + +/* Find the first occurrence of NEEDLE in HAYSTACK. */ +extern char *strstr (const char *haystack, const char *needle); + +#ifdef __cplusplus +} +#endif diff --git a/m4/getaddrinfo.m4 b/m4/getaddrinfo.m4 new file mode 100644 index 000000000..4bc9f6719 --- /dev/null +++ b/m4/getaddrinfo.m4 @@ -0,0 +1,19 @@ +# getaddrinfo.m4 serial 3 +dnl Copyright (C) 2004 Free Software Foundation, Inc. +dnl This file is free software; the Free Software Foundation +dnl gives unlimited permission to copy and/or distribute it, +dnl with or without modifications, as long as this notice is preserved. + +AC_DEFUN([gl_GETADDRINFO], +[ + AC_SEARCH_LIBS(getaddrinfo, nsl socket) + AC_REPLACE_FUNCS(getaddrinfo gai_strerror) + gl_PREREQ_GETADDRINFO +]) + +# Prerequisites of lib/getaddrinfo.h and lib/getaddrinfo.c. +AC_DEFUN([gl_PREREQ_GETADDRINFO], [ + AC_REQUIRE([gl_C_RESTRICT]) + AC_REQUIRE([gl_SOCKET_FAMILIES]) + AC_REQUIRE([AC_C_INLINE]) +]) diff --git a/m4/getdelim.m4 b/m4/getdelim.m4 new file mode 100644 index 000000000..340bb7126 --- /dev/null +++ b/m4/getdelim.m4 @@ -0,0 +1,30 @@ +# getdelim.m4 serial 1 + +dnl Copyright (C) 2005 Free Software dnl Foundation, Inc. +dnl +dnl This file is free software; the Free Software Foundation +dnl gives unlimited permission to copy and/or distribute it, +dnl with or without modifications, as long as this notice is preserved. + +AC_PREREQ(2.52) + +AC_DEFUN([gl_FUNC_GETDELIM], +[ + AC_LIBSOURCES([getdelim.c, getdelim.h]) + + dnl Persuade glibc <stdio.h> to declare getdelim(). + AC_REQUIRE([AC_GNU_SOURCE]) + + AC_REPLACE_FUNCS(getdelim) + AC_CHECK_DECLS_ONCE(getdelim) + + if test $ac_cv_func_getdelim = no; then + gl_PREREQ_GETDELIM + fi +]) + +# Prerequisites of lib/getdelim.c. +AC_DEFUN([gl_PREREQ_GETDELIM], +[ + AC_CHECK_FUNCS([flockfile funlockfile]) +]) diff --git a/m4/mbchar.m4 b/m4/mbchar.m4 new file mode 100644 index 000000000..dd613cbc6 --- /dev/null +++ b/m4/mbchar.m4 @@ -0,0 +1,14 @@ +# mbchar.m4 serial 1 +dnl Copyright (C) 2005 Free Software Foundation, Inc. +dnl This file is free software; the Free Software Foundation +dnl gives unlimited permission to copy and/or distribute it, +dnl with or without modifications, as long as this notice is preserved. + +dnl autoconf tests required for use of mbchar.m4 +dnl From Bruno Haible. + +AC_DEFUN([gl_MBCHAR], +[ + AC_REQUIRE([AC_GNU_SOURCE]) + : +]) diff --git a/m4/mbiter.m4 b/m4/mbiter.m4 new file mode 100644 index 000000000..3eb92bcca --- /dev/null +++ b/m4/mbiter.m4 @@ -0,0 +1,14 @@ +# mbiter.m4 serial 1 +dnl Copyright (C) 2005 Free Software Foundation, Inc. +dnl This file is free software; the Free Software Foundation +dnl gives unlimited permission to copy and/or distribute it, +dnl with or without modifications, as long as this notice is preserved. + +dnl autoconf tests required for use of mbiter.h +dnl From Bruno Haible. + +AC_DEFUN([gl_MBITER], +[ + AC_REQUIRE([AC_TYPE_MBSTATE_T]) + : +]) diff --git a/m4/sockpfaf.m4 b/m4/sockpfaf.m4 new file mode 100644 index 000000000..b224faec5 --- /dev/null +++ b/m4/sockpfaf.m4 @@ -0,0 +1,39 @@ +# sockpfaf.m4 serial 2 +dnl Copyright (C) 2004 Free Software Foundation, Inc. +dnl This file is free software; the Free Software Foundation +dnl gives unlimited permission to copy and/or distribute it, +dnl with or without modifications, as long as this notice is preserved. + +dnl Test for some common socket protocol families (PF_INET, PF_INET6, ...) +dnl and some common address families (AF_INET, AF_INET6, ...). +dnl This test assumes that a system supports an address family if and only if +dnl it supports the corresponding protocol family. + +dnl From Bruno Haible. + +AC_DEFUN([gl_SOCKET_FAMILIES], +[ + AC_MSG_CHECKING(for IPv4 sockets) + AC_CACHE_VAL(gl_cv_socket_ipv4, + [AC_TRY_COMPILE([#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h>], +[int x = AF_INET; struct in_addr y; struct sockaddr_in z;], + gl_cv_socket_ipv4=yes, gl_cv_socket_ipv4=no)]) + AC_MSG_RESULT($gl_cv_socket_ipv4) + if test $gl_cv_socket_ipv4 = yes; then + AC_DEFINE(HAVE_IPV4, 1, [Define to 1 if <sys/socket.h> defines AF_INET.]) + fi + + AC_MSG_CHECKING(for IPv6 sockets) + AC_CACHE_VAL(gl_cv_socket_ipv6, + [AC_TRY_COMPILE([#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h>], +[int x = AF_INET6; struct in6_addr y; struct sockaddr_in6 z;], + gl_cv_socket_ipv6=yes, gl_cv_socket_ipv6=no)]) + AC_MSG_RESULT($gl_cv_socket_ipv6) + if test $gl_cv_socket_ipv6 = yes; then + AC_DEFINE(HAVE_IPV6, 1, [Define to 1 if <sys/socket.h> defines AF_INET6.]) + fi +]) |