X-Git-Url: http://git.indexdata.com/?p=yaz-moved-to-github.git;a=blobdiff_plain;f=src%2Fccltoken.c;h=538cd56e9e02df5618ee5461fb53b33e449c5ad3;hp=e9c1f347220ac21e9cc365f0dc18ba8c22739033;hb=4f3bcae93d51a26709c12b51261c3d95af610cb2;hpb=fdb80724c17104b31f80527cca19b433f6c2fc33 diff --git a/src/ccltoken.c b/src/ccltoken.c index e9c1f34..538cd56 100644 --- a/src/ccltoken.c +++ b/src/ccltoken.c @@ -1,96 +1,18 @@ -/* - * Copyright (c) 1995, the EUROPAGATE consortium (see below). - * - * The EUROPAGATE consortium members are: - * - * University College Dublin - * Danmarks Teknologiske Videnscenter - * An Chomhairle Leabharlanna - * Consejo Superior de Investigaciones Cientificas - * - * Permission to use, copy, modify, distribute, and sell this software and - * its documentation, in whole or in part, for any purpose, is hereby granted, - * provided that: - * - * 1. This copyright and permission notice appear in all copies of the - * software and its documentation. Notices of copyright or attribution - * which appear at the beginning of any file must remain unchanged. - * - * 2. The names of EUROPAGATE or the project partners may not be used to - * endorse or promote products derived from this software without specific - * prior written permission. - * - * 3. Users of this software (implementors and gateway operators) agree to - * inform the EUROPAGATE consortium of their use of the software. This - * information will be used to evaluate the EUROPAGATE project and the - * software, and to plan further developments. The consortium may use - * the information in later publications. - * - * 4. Users of this software agree to make their best efforts, when - * documenting their use of the software, to acknowledge the EUROPAGATE - * consortium, and the role played by the software in their work. - * - * THIS SOFTWARE IS PROVIDED "AS IS" AND WITHOUT WARRANTY OF ANY KIND, - * EXPRESS, IMPLIED, OR OTHERWISE, INCLUDING WITHOUT LIMITATION, ANY - * WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. - * IN NO EVENT SHALL THE EUROPAGATE CONSORTIUM OR ITS MEMBERS BE LIABLE - * FOR ANY SPECIAL, INCIDENTAL, INDIRECT OR CONSEQUENTIAL DAMAGES OF - * ANY KIND, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA - * OR PROFITS, WHETHER OR NOT ADVISED OF THE POSSIBILITY OF DAMAGE, AND - * ON ANY THEORY OF LIABILITY, ARISING OUT OF OR IN CONNECTION WITH THE - * USE OR PERFORMANCE OF THIS SOFTWARE. - * +/* This file is part of the YAZ toolkit. + * Copyright (C) 1995-2011 Index Data + * See the file LICENSE for details. */ /** * \file ccltoken.c * \brief Implements CCL lexical analyzer (scanner) */ -/* CCL - lexical analysis - * Europagate, 1995 - * - * $Id: ccltoken.c,v 1.12 2007-04-30 19:55:40 adam Exp $ - * - * Old Europagate Log: - * - * Revision 1.10 1995/07/11 12:28:31 adam - * New function: ccl_token_simple (split into simple tokens) and - * ccl_token_del (delete tokens). - * - * Revision 1.9 1995/05/16 09:39:28 adam - * LICENSE. - * - * Revision 1.8 1995/05/11 14:03:57 adam - * Changes in the reading of qualifier(s). New function: ccl_qual_fitem. - * New variable ccl_case_sensitive, which controls whether reserved - * words and field names are case sensitive or not. - * - * Revision 1.7 1995/04/19 12:11:24 adam - * Minor change. - * - * Revision 1.6 1995/04/17 09:31:48 adam - * Improved handling of qualifiers. Aliases or reserved words. - * - * Revision 1.5 1995/02/23 08:32:00 adam - * Changed header. - * - * Revision 1.3 1995/02/15 17:42:16 adam - * Minor changes of the api of this module. FILE* argument added - * to ccl_pr_tree. - * - * Revision 1.2 1995/02/14 19:55:13 adam - * Header files ccl.h/cclp.h are gone! They have been merged an - * moved to ../include/ccl.h. - * Node kind(s) in ccl_rpn_node have changed names. - * - * Revision 1.1 1995/02/13 12:35:21 adam - * First version of CCL. Qualifiers aren't handled yet. - * - */ +#if HAVE_CONFIG_H +#include +#endif #include #include -#include - +#include #include "cclp.h" /* @@ -159,6 +81,7 @@ struct ccl_token *ccl_parser_tokenize(CCL_parser cclp, const char *command) last->next->prev = last; last = last->next; } + last->left_trunc = last->right_trunc = 0; last->ws_prefix_buf = (const char *) cp0; last->ws_prefix_len = cp - cp0; last->next = NULL; @@ -181,7 +104,7 @@ struct ccl_token *ccl_parser_tokenize(CCL_parser cclp, const char *command) case '%': case '!': last->kind = CCL_TOK_PROX; - while (isdigit(*cp)) + while (yaz_isdigit(*cp)) { ++ last->len; cp++; @@ -201,53 +124,66 @@ struct ccl_token *ccl_parser_tokenize(CCL_parser cclp, const char *command) else last->kind = CCL_TOK_REL; break; - case '\"': - last->kind = CCL_TOK_TERM; - last->name = (const char *) cp; - last->len = 0; - while (*cp && *cp != '\"') + default: + --cp; + --last->len; + if (*cp == '?') { + last->left_trunc = 1; cp++; - ++ last->len; } - if (*cp == '\"') - cp++; - break; - default: - if (!strchr("(),%!><= \t\n\r", cp[-1])) + if (*cp == '"') { - while (*cp && !strchr("(),%!><= \t\n\r", *cp)) + cp++; + last->kind = CCL_TOK_TERM; + last->name = (const char *) cp; + while (*cp && *cp != '"') { cp++; ++ last->len; } + if (*cp) + cp++; + } + else + { + last->kind = CCL_TOK_TERM; + last->name = (const char *) cp; + while (*cp && !strchr("(),%!><=? \t\n\r", *cp)) + { + ++ last->len; + cp++; + } + aliases = ccl_qual_search_special(cclp->bibset, "and"); + if (!aliases) + aliases = cclp->ccl_token_and; + if (token_cmp(cclp, aliases, last)) + last->kind = CCL_TOK_AND; + + aliases = ccl_qual_search_special(cclp->bibset, "or"); + if (!aliases) + aliases = cclp->ccl_token_or; + if (token_cmp(cclp, aliases, last)) + last->kind = CCL_TOK_OR; + + aliases = ccl_qual_search_special(cclp->bibset, "not"); + if (!aliases) + aliases = cclp->ccl_token_not; + if (token_cmp(cclp, aliases, last)) + last->kind = CCL_TOK_NOT; + + aliases = ccl_qual_search_special(cclp->bibset, "set"); + if (!aliases) + aliases = cclp->ccl_token_set; + + if (token_cmp(cclp, aliases, last)) + last->kind = CCL_TOK_SET; + } + if (*cp == '?') + { + last->right_trunc = 1; + cp++; } - last->kind = CCL_TOK_TERM; - - aliases = ccl_qual_search_special(cclp->bibset, "and"); - if (!aliases) - aliases = cclp->ccl_token_and; - if (token_cmp(cclp, aliases, last)) - last->kind = CCL_TOK_AND; - - aliases = ccl_qual_search_special(cclp->bibset, "or"); - if (!aliases) - aliases = cclp->ccl_token_or; - if (token_cmp(cclp, aliases, last)) - last->kind = CCL_TOK_OR; - - aliases = ccl_qual_search_special(cclp->bibset, "not"); - if (!aliases) - aliases = cclp->ccl_token_not; - if (token_cmp(cclp, aliases, last)) - last->kind = CCL_TOK_NOT; - - aliases = ccl_qual_search_special(cclp->bibset, "set"); - if (!aliases) - aliases = cclp->ccl_token_set; - - if (token_cmp(cclp, aliases, last)) - last->kind = CCL_TOK_SET; } } return first; @@ -264,6 +200,7 @@ struct ccl_token *ccl_token_add(struct ccl_token *at) n->next->prev = n; n->kind = CCL_TOK_TERM; + n->left_trunc = n->right_trunc = 0; n->name = 0; n->len = 0; n->ws_prefix_buf = 0; @@ -288,7 +225,7 @@ void ccl_token_del(struct ccl_token *list) static const char **create_ar(const char *v1, const char *v2) { - const char **a = xmalloc(3 * sizeof(*a)); + const char **a = (const char **) xmalloc(3 * sizeof(*a)); a[0] = xstrdup(v1); if (v2) { @@ -307,7 +244,7 @@ static void destroy_ar(const char **a) int i; for (i = 0; a[i]; i++) xfree((char *) a[i]); - xfree(a); + xfree((char **)a); } } @@ -357,6 +294,7 @@ int ccl_parser_get_error(CCL_parser cclp, int *pos) /* * Local variables: * c-basic-offset: 4 + * c-file-style: "Stroustrup" * indent-tabs-mode: nil * End: * vim: shiftwidth=4 tabstop=8 expandtab