-/*
- * Copyright (C) 1994-1995, Index Data I/S
- * All rights reserved.
- * Sebastian Hammer, Adam Dickmeiss
- *
- * $Log: rectext.c,v $
- * Revision 1.2 1996-10-29 14:02:45 adam
- * Uses buffered read to speed up things.
- *
- * Revision 1.1 1996/10/11 10:57:28 adam
- * New module recctrl. Used to manage records (extract/retrieval).
- *
- * Revision 1.7 1996/01/17 14:57:55 adam
- * Prototype changed for reader functions in extract/retrieve. File
- * is identified by 'void *' instead of 'int.
- *
- * Revision 1.6 1995/10/10 13:59:24 adam
- * Function rset_open changed its wflag parameter to general flags.
- *
- * Revision 1.5 1995/10/02 16:24:39 adam
- * Use attribute actually used in search requests.
- *
- * Revision 1.4 1995/10/02 15:42:55 adam
- * Extract uses file descriptors instead of FILE pointers.
- *
- * Revision 1.3 1995/09/28 09:19:45 adam
- * xfree/xmalloc used everywhere.
- * Extract/retrieve method seems to work for text records.
- *
- * Revision 1.2 1995/09/15 14:45:21 adam
- * Retrieve control.
- * Work on truncation.
- *
- * Revision 1.1 1995/09/14 07:48:25 adam
- * Record control management.
- *
- */
+/* $Id: rectext.c,v 1.15 2002-08-02 19:26:56 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 <stdio.h>
#include <assert.h>
#include <ctype.h>
#include <zebrautl.h>
#include "rectext.h"
-static void text_init (void)
+static void *text_init (RecType recType)
+{
+ return 0;
+}
+
+static void text_destroy (void *clientData)
{
}
struct buf_info *buf_open (struct recExtractCtrl *p)
{
- struct buf_info *fi = xmalloc (sizeof(*fi));
+ struct buf_info *fi = (struct buf_info *) xmalloc (sizeof(*fi));
fi->p = p;
- fi->buf = xmalloc (4096);
+ fi->buf = (char *) xmalloc (4096);
fi->offset = 1;
fi->max = 1;
return fi;
int buf_read (struct buf_info *fi, char *dst)
{
- if (fi->max <= 0)
- return 0;
if (fi->offset >= fi->max)
{
+ if (fi->max <= 0)
+ return 0;
fi->max = (*fi->p->readf)(fi->p->fh, fi->buf, 4096);
fi->offset = 0;
if (fi->max <= 0)
xfree (fi);
}
-static int text_extract (struct recExtractCtrl *p)
+static int text_extract (void *clientData, struct recExtractCtrl *p)
{
- char w[256];
+ char w[512];
RecWord recWord;
- int r, seqno = 1;
+ int r;
struct buf_info *fi = buf_open (p);
- (*p->init)(&recWord);
- recWord.which = Word_String;
+ (*p->init)(p, &recWord);
+ recWord.reg_type = 'w';
do
{
int i = 0;
r = buf_read (fi, w);
- while (r > 0 && i < 255 && isalnum(w[i]))
+ while (r > 0 && i < 511 && w[i] != '\n' && w[i] != '\r')
{
i++;
r = buf_read (fi, w + i);
}
if (i)
{
- int j;
- for (j = 0; j<i; j++)
- w[j] = tolower(w[j]);
- w[i] = 0;
- recWord.seqno = seqno++;
- recWord.u.string = w;
- (*p->add)(&recWord);
+ recWord.string = w;
+ recWord.length = i;
+ (*p->tokenAdd)(&recWord);
}
} while (r > 0);
buf_close (fi);
- return 0;
+ return RECCTRL_EXTRACT_OK;
}
-static int text_retrieve (struct recRetrieveCtrl *p)
+static int text_retrieve (void *clientData, struct recRetrieveCtrl *p)
{
int r, text_ptr = 0;
static char *text_buf = NULL;
static int text_size = 0;
int start_flag = 1;
+ const char *elementSetName = NULL;
+ int no_lines = 0;
+
+ if (p->comp && p->comp->which == Z_RecordComp_simple &&
+ p->comp->u.simple->which == Z_ElementSetNames_generic)
+ elementSetName = p->comp->u.simple->u.generic;
+ /* don't make header for the R(aw) element set name */
+ if (elementSetName && !strcmp(elementSetName, "R"))
+ start_flag = 0;
while (1)
{
if (text_ptr + 4096 >= text_size)
char *nb;
text_size = 2*text_size + 8192;
- nb = xmalloc (text_size);
+ nb = (char *) xmalloc (text_size);
if (text_buf)
{
memcpy (nb, text_buf, text_ptr);
break;
text_ptr += r;
}
+ text_buf[text_ptr] = '\0';
+ if (elementSetName)
+ {
+ if (!strcmp (elementSetName, "B"))
+ no_lines = 4;
+ if (!strcmp (elementSetName, "M"))
+ no_lines = 20;
+ }
+ if (no_lines)
+ {
+ char *p = text_buf;
+ int i = 0;
+
+ while (++i <= no_lines && (p = strchr (p, '\n')))
+ p++;
+ if (p)
+ {
+ p[1] = '\0';
+ text_ptr = p-text_buf;
+ }
+ }
p->output_format = VAL_SUTRS;
p->rec_buf = text_buf;
p->rec_len = text_ptr;
static struct recType text_type = {
"text",
text_init,
+ text_destroy,
text_extract,
text_retrieve
};
projects / idzebra-moved-to-github.git / blobdiff