X-Git-Url: http://git.indexdata.com/?a=blobdiff_plain;f=data1%2Fd1_read.c;h=742e170c0c2bafb2946fe5f04157533c2d5b8b7c;hb=cc4289d73c2b872c09d221d5e1188d3cdd9da438;hp=6597220b96f2368caf27f03e3db6b3fe95682b1a;hpb=519fefb91135ad52134b9fc4e82b3874f5525a2b;p=idzebra-moved-to-github.git diff --git a/data1/d1_read.c b/data1/d1_read.c index 6597220..742e170 100644 --- a/data1/d1_read.c +++ b/data1/d1_read.c @@ -1,9 +1,28 @@ +/* $Id: d1_read.c,v 1.9 2004-08-04 08:35:22 adam Exp $ + Copyright (C) 1995,1996,1997,1998,1999,2000,2001,2002,2003,2004 + 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. +*/ + + /* - * Copyright (c) 1995-2002, Index Data. - * See the file LICENSE for details. - * Sebastian Hammer, Adam Dickmeiss - * - * $Id: d1_read.c,v 1.1 2002-10-22 12:53:33 adam Exp $ + * This module reads "loose" SGML and converts it to data1 tree */ #include @@ -109,13 +128,13 @@ data1_node *data1_append_node (data1_handle dh, NMEM m, int type, data1_node *r = (data1_node *)nmem_malloc(m, sizeof(*r)); r->next = r->child = r->last_child = 0; r->destroy = 0; - + + r->parent = parent; if (!parent) r->root = r; else { r->root = parent->root; - r->parent = parent; if (!parent->child) parent->child = parent->last_child = r; else @@ -194,6 +213,24 @@ void data1_set_root(data1_handle dh, data1_node *res, res->u.root.absyn = absyn; } +void data1_add_attrs(data1_handle dh, NMEM nmem, const char **attr, + data1_xattr **p) +{ + while (*p) + p = &(*p)->next; + + while (attr && *attr) + { + *p = (data1_xattr*) nmem_malloc (nmem, sizeof(**p)); + (*p)->name = nmem_strdup (nmem, *attr++); + (*p)->value = nmem_strdup (nmem, *attr++); + (*p)->what = DATA1I_text; + + p = &(*p)->next; + } + *p = 0; +} + data1_node *data1_mk_preprocess (data1_handle dh, NMEM nmem, const char *target, const char **attr, data1_node *at) @@ -206,22 +243,31 @@ data1_node *data1_mk_preprocess_n (data1_handle dh, NMEM nmem, const char *target, size_t len, const char **attr, data1_node *at) { - data1_xattr **p; data1_node *res = data1_mk_node2 (dh, nmem, DATA1N_preprocess, at); res->u.preprocess.target = data1_insert_string_n (dh, res, nmem, target, len); - p = &res->u.preprocess.attributes; - while (attr && *attr) - { - *p = (data1_xattr*) nmem_malloc (nmem, sizeof(**p)); - (*p)->name = nmem_strdup (nmem, *attr++); - (*p)->value = nmem_strdup (nmem, *attr++); - (*p)->what = DATA1I_text; + data1_add_attrs(dh, nmem, attr, &res->u.preprocess.attributes); + return res; +} - p = &(*p)->next; - } - *p = 0; +data1_node *data1_insert_preprocess (data1_handle dh, NMEM nmem, + const char *target, + const char **attr, data1_node *at) +{ + return data1_insert_preprocess_n (dh, nmem, target, strlen(target), + attr, at); +} + +data1_node *data1_insert_preprocess_n (data1_handle dh, NMEM nmem, + const char *target, size_t len, + const char **attr, data1_node *at) +{ + data1_node *res = data1_insert_node (dh, nmem, DATA1N_preprocess, at); + res->u.preprocess.target = data1_insert_string_n (dh, res, nmem, + target, len); + + data1_add_attrs(dh, nmem, attr, &res->u.preprocess.attributes); return res; } @@ -231,7 +277,6 @@ data1_node *data1_mk_tag_n (data1_handle dh, NMEM nmem, { data1_node *partag = get_parent_tag(dh, at); data1_node *res = data1_mk_node2 (dh, nmem, DATA1N_tag, at); - data1_xattr **p; data1_element *e = 0; res->u.tag.tag = data1_insert_string_n (dh, res, nmem, tag, len); @@ -249,40 +294,17 @@ data1_node *data1_mk_tag_n (data1_handle dh, NMEM nmem, e, res->u.tag.tag); } res->u.tag.element = e; - p = &res->u.tag.attributes; - while (attr && *attr) - { - *p = (data1_xattr*) nmem_malloc (nmem, sizeof(**p)); - (*p)->name = nmem_strdup (nmem, *attr++); - (*p)->value = nmem_strdup (nmem, *attr++); - (*p)->what = DATA1I_text; - p = &(*p)->next; - } - *p = 0; + data1_add_attrs(dh, nmem, attr, &res->u.tag.attributes); return res; } void data1_tag_add_attr (data1_handle dh, NMEM nmem, data1_node *res, const char **attr) { - data1_xattr **p; - if (res->which != DATA1N_tag) return; - p = &res->u.tag.attributes; - while (*p) - p = &(*p)->next; - - while (attr && *attr) - { - *p = (data1_xattr*) nmem_malloc (nmem, sizeof(**p)); - (*p)->name = nmem_strdup (nmem, *attr++); - (*p)->value = nmem_strdup (nmem, *attr++); - (*p)->what = DATA1I_text; - p = &(*p)->next; - } - *p = 0; + data1_add_attrs(dh, nmem, attr, &res->u.tag.attributes); } data1_node *data1_mk_tag (data1_handle dh, NMEM nmem, @@ -303,7 +325,7 @@ data1_node *data1_search_tag (data1_handle dh, data1_node *n, } for (; n; n = n->next) if (n->which == DATA1N_tag && n->u.tag.tag && - !yaz_matchstr (tag, n->u.tag.tag)) + !yaz_matchstr (n->u.tag.tag, tag)) { return n; } @@ -448,8 +470,8 @@ data1_node *data1_add_taggeddata (data1_handle dh, data1_node *root, return data1_add_insert_taggeddata (dh, at, tagname, m, 1, 0); } -data1_node *data1_mk_tag_data_int (data1_handle dh, data1_node *at, - const char *tag, int num, +data1_node *data1_mk_tag_data_zint (data1_handle dh, data1_node *at, + const char *tag, zint num, NMEM nmem) { data1_node *node_data; @@ -459,11 +481,18 @@ data1_node *data1_mk_tag_data_int (data1_handle dh, data1_node *at, return 0; node_data->u.data.what = DATA1I_num; node_data->u.data.data = node_data->lbuf; - sprintf (node_data->u.data.data, "%d", num); + sprintf (node_data->u.data.data, ZINT_FORMAT, num); node_data->u.data.len = strlen (node_data->u.data.data); return node_data; } +data1_node *data1_mk_tag_data_int (data1_handle dh, data1_node *at, + const char *tag, int num, + NMEM nmem) +{ + return data1_mk_tag_data_zint(dh, at, tag, num, nmem); +} + data1_node *data1_mk_tag_data_oid (data1_handle dh, data1_node *at, const char *tag, Odr_oid *oid, NMEM nmem) @@ -1078,7 +1107,7 @@ int data1_iconv (data1_handle dh, NMEM m, data1_node *n, const char *tocode, const char *fromcode) { - if (strcmp (tocode, fromcode)) + if (yaz_matchstr (tocode, fromcode)) { WRBUF wrbuf = wrbuf_alloc(); yaz_iconv_t t = yaz_iconv_open (tocode, fromcode); @@ -1090,3 +1119,33 @@ int data1_iconv (data1_handle dh, NMEM m, data1_node *n, } return 0; } + +void data1_concat_text(data1_handle dh, NMEM m, data1_node *n) +{ + for (; n; n = n->next) + { + if (n->which == DATA1N_data && n->next && + n->next->which == DATA1N_data) + { + int sz = 0; + int off = 0; + char *ndata; + data1_node *np; + for (np = n; np && np->which == DATA1N_data; np=np->next) + sz += np->u.data.len; + ndata = nmem_malloc(m, sz); + for (np = n; np && np->which == DATA1N_data; np=np->next) + { + memcpy(ndata+off, np->u.data.data, np->u.data.len); + off += np->u.data.len; + } + n->u.data.data = ndata; + n->u.data.len = sz; + n->next = np; + if (!np && n->parent) + n->parent->last_child = n; + + } + data1_concat_text(dh, m, n->child); + } +}