X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=recctrl%2Frecgrs.c;h=5514b2b2b69691695876300155bd57b32baf7d33;hb=ff8552d3012ab841cc90d5f80e5ad1373e194fde;hp=5546f2d4b62f515717be627879116d80a3e1daab;hpb=e1dd69ab7c08046ca9e02ea55536492763bd9f2e;p=idzebra-moved-to-github.git diff --git a/recctrl/recgrs.c b/recctrl/recgrs.c index 5546f2d..5514b2b 100644 --- a/recctrl/recgrs.c +++ b/recctrl/recgrs.c @@ -1,9 +1,24 @@ -/* - * Copyright (C) 1994-2002, Index Data - * All rights reserved. - * - * $Id: recgrs.c,v 1.57 2002-08-01 09:37:44 adam Exp $ - */ +/* $Id: recgrs.c,v 1.63 2002-08-28 19:52:29 adam Exp $ + Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002 + Index Data Aps + +This file is part of the Zebra server. + +Zebra 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. + +Zebra 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 Zebra; see the file LICENSE.zebra. If not, write to the +Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA +02111-1307, USA. +*/ #include #include @@ -84,7 +99,7 @@ static void *grs_init(RecType recType) grs_add_handler (h, recTypeGrs_tcl); #endif grs_add_handler (h, recTypeGrs_marc); -#if YAZ_HAVE_EXPAT +#if HAVE_EXPAT_H grs_add_handler (h, recTypeGrs_xml); #endif return h; @@ -175,29 +190,13 @@ static void index_xpath (data1_node *n, struct recExtractCtrl *p, else { data1_xattr *xp; - (*p->tokenAdd)(wrd); - -#if 0 - for (xp = n->u.tag.attributes; xp; xp = xp->next) + (*p->tokenAdd)(wrd); /* index element pag (AKA tag path) */ + if (use == 1) { - if (use == 1) - { /* attribute (no value) */ - wrd->reg_type = '0'; - wrd->attrUse = 3; - wrd->string = xp->name; - wrd->length = strlen(xp->name); - - wrd->seqno--; - (*p->tokenAdd)(wrd); - } - } -#else - for (xp = n->u.tag.attributes; xp; xp = xp->next) - { - char comb[512]; - - if (use == 1) - { /* attribute start */ + for (xp = n->u.tag.attributes; xp; xp = xp->next) + { + char comb[512]; + /* attribute (no value) */ wrd->reg_type = '0'; wrd->attrUse = 3; wrd->string = xp->name; @@ -205,46 +204,53 @@ static void index_xpath (data1_node *n, struct recExtractCtrl *p, wrd->seqno--; (*p->tokenAdd)(wrd); - } - - if (use == 1 && xp->value && - strlen(xp->name) + strlen(xp->value) < sizeof(comb)-2) + + if (xp->value && + strlen(xp->name) + strlen(xp->value) < sizeof(comb)-2) + { + /* attribute value exact */ + strcpy (comb, xp->name); + strcat (comb, "="); + strcat (comb, xp->value); + + wrd->attrUse = 3; + wrd->reg_type = '0'; + wrd->string = comb; + wrd->length = strlen(comb); + wrd->seqno--; + + (*p->tokenAdd)(wrd); + } + } + for (xp = n->u.tag.attributes; xp; xp = xp->next) { - /* attribute value exact */ - strcpy (comb, xp->name); - strcat (comb, "="); - strcat (comb, xp->value); + char attr_tag_path_full[1024]; + int int_len = flen; - wrd->attrUse = 3; + sprintf (attr_tag_path_full, "@%s/%.*s", + xp->name, int_len, tag_path_full); + wrd->reg_type = '0'; - wrd->string = comb; - wrd->length = strlen(comb); - wrd->seqno--; - + wrd->attrUse = 1; + wrd->string = attr_tag_path_full; + wrd->length = strlen(attr_tag_path_full); (*p->tokenAdd)(wrd); - - /* attribute value phrase */ - + wrd->attrUse = 1015; wrd->reg_type = 'w'; wrd->string = xp->value; wrd->length = strlen(xp->value); - + (*p->tokenAdd)(wrd); - } - if (use == 2) - { - wrd->reg_type = '0'; - wrd->attrUse = 4; - wrd->string = xp->name; - wrd->length = strlen(xp->name); + wrd->reg_type = '0'; + wrd->attrUse = 2; + wrd->string = attr_tag_path_full; + wrd->length = strlen(attr_tag_path_full); (*p->tokenAdd)(wrd); } } -#endif } - break; } } @@ -371,8 +377,12 @@ static int dumpkeys(data1_node *n, struct recExtractCtrl *p, int level, { index_termlist (n, n, p, level, wrd); /* index start tag */ + assert (n->root->u.root.absyn); + if (!n->root->u.root.absyn) index_xpath (n, p, level, wrd, 1); + else if (n->root->u.root.absyn->enable_xpath_indexing) + index_xpath (n, p, level, wrd, 1); } if (n->child) @@ -388,8 +398,8 @@ static int dumpkeys(data1_node *n, struct recExtractCtrl *p, int level, { printf("%*s", level * 4, ""); printf("Data: "); - if (n->u.data.len > 32) - printf("'%.24s ... %.6s'\n", n->u.data.data, + if (n->u.data.len > 256) + printf("'%.240s ... %.6s'\n", n->u.data.data, n->u.data.data + n->u.data.len-6); else if (n->u.data.len > 0) printf("'%.*s'\n", n->u.data.len, n->u.data.data); @@ -401,7 +411,8 @@ static int dumpkeys(data1_node *n, struct recExtractCtrl *p, int level, index_termlist (par, n, p, level, wrd); if (!n->root->u.root.absyn) index_xpath (n, p, level, wrd, 1016); - + else if (n->root->u.root.absyn->enable_xpath_indexing) + index_xpath (n, p, level, wrd, 1016); } if (n->which == DATA1N_tag) @@ -409,9 +420,10 @@ static int dumpkeys(data1_node *n, struct recExtractCtrl *p, int level, /* index end tag */ if (!n->root->u.root.absyn) index_xpath (n, p, level, wrd, 2); + else if (n->root->u.root.absyn->enable_xpath_indexing) + index_xpath (n, p, level, wrd, 2); } - if (p->flagShowRecords && n->which == DATA1N_root) { printf("%*s-------------\n\n", level * 4, ""); @@ -459,7 +471,7 @@ static int grs_extract_sub(struct grs_handlers *h, struct recExtractCtrl *p, gri.dh = p->dh; if (read_grs_type (h, &gri, p->subType, &n)) - return RECCTRL_EXTRACT_ERROR; + return RECCTRL_EXTRACT_ERROR_NO_SUCH_FILTER; if (!n) return RECCTRL_EXTRACT_EOF; oe.proto = PROTO_Z3950; @@ -486,7 +498,7 @@ static int grs_extract_sub(struct grs_handlers *h, struct recExtractCtrl *p, if (dumpkeys(n, p, 0, &wrd) < 0) { data1_free_tree(p->dh, n); - return RECCTRL_EXTRACT_ERROR; + return RECCTRL_EXTRACT_ERROR_GENERIC; } data1_free_tree(p->dh, n); return RECCTRL_EXTRACT_OK; @@ -642,7 +654,7 @@ static int grs_retrieve(void *clientData, struct recRetrieveCtrl *p) /* ensure our data1 tree is UTF-8 */ data1_iconv (p->dh, mem, node, "UTF-8", data1_get_encoding(p->dh, node)); -#if 0 +#if 1 data1_pr_tree (p->dh, node, stdout); #endif top = data1_get_root_tag (p->dh, node);