-/* $Id: normalize7bit.c,v 1.1 2007-04-26 21:33:32 marc Exp $
+/* $Id: normalize7bit.c,v 1.5 2007-10-31 05:29:08 quinn Exp $
Copyright (c) 2006-2007, Index Data.
-This file is part of Pazpar2.
+ This file is part of Pazpar2.
-Pazpar2 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.
+ Pazpar2 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.
-Pazpar2 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.
+ Pazpar2 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 Pazpar2; see the file LICENSE. If not, write to the
-Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA
-02111-1307, USA.
- */
+ You should have received a copy of the GNU General Public License
+ along with Pazpar2; see the file LICENSE. If not, write to the
+ Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA
+ 02111-1307, USA.
+*/
/** \file normalize7bit.c
\brief char and string normalization for 7bit ascii only
#include "normalize7bit.h"
-char * normalize7bit_generic(char* str, char* rm_chars)
+/** \brief removes leading whitespace.. Removes suffix cahrs in rm_chars */
+char * normalize7bit_generic(char * str, const char * rm_chars)
{
char *p, *pe;
- for (p = str; *p && isspace(*p); p++)
- ;
- for (pe = p + strlen(p) - 1;
- pe > p && strchr(rm_chars, *pe); pe--)
- *pe = '\0';
- return p;
+ for (p = str; *p && isspace(*p); p++)
+ ;
+ for (pe = p + strlen(p) - 1;
+ pe > p && strchr(rm_chars, *pe); pe--)
+ *pe = '\0';
+ return p;
}
*(pout--) = '\0';
}
while (pout > buf && *pout == ' ');
-
+
return buf;
}
// Extract what appears to be years from buf, storing highest and
// lowest values.
-int extract_years(const char *buf, int *first, int *last)
+// longdate==1, look for YYYYMMDD, longdate=0 look only for YYYY
+int extract7bit_dates(const char *buf, int *first, int *last, int longdate)
{
*first = -1;
*last = -1;
len = 0;
for (e = buf; *e && isdigit(*e); e++)
len++;
- if (len == 4)
+ if ((len == 4 && !longdate) || (longdate && len >= 4 && len <= 8))
{
int value = atoi(buf);
+ if (longdate && len == 4)
+ value *= 10000; // should really suffix 0101?
if (*first < 0 || value < *first)
*first = value;
if (*last < 0 || value > *last)