-/* PSPP - computes sample statistics.
+/* PSPP - a program for statistical analysis.
Copyright (C) 1997-9, 2000, 2006 Free Software Foundation, Inc.
- This program 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 of the
- License, or (at your option) any later version.
+ This program 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 3 of the License, or
+ (at your option) any later version.
- This program 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.
+ This program 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 this program; if not, write to the Free Software
- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- 02110-1301, USA. */
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
#include "value.h"
#include <libpspp/assertion.h>
+#include <libpspp/legacy-encoding.h>
#include <libpspp/compiler.h>
#include <libpspp/integer-format.h>
-#include <libpspp/magic.h>
#include <libpspp/message.h>
#include <libpspp/misc.h>
#include <libpspp/str.h>
-
#include "c-ctype.h"
+#include "c-strtod.h"
#include "minmax.h"
-#include "size_max.h"
#include "xalloc.h"
#include "gettext.h"
/* Information about parsing one data field. */
struct data_in
{
+ enum legacy_encoding encoding;/* Encoding of source. */
struct substring input; /* Source. */
enum fmt_type format; /* Input format. */
int implied_decimals; /* Number of implied decimal places. */
static int hexit_value (int c);
\f
-/* Parses the characters in INPUT according to FORMAT. Stores
- the parsed representation in OUTPUT, which has the given WIDTH
- (0 for a numeric field, otherwise the string width).
+/* Parses the characters in INPUT, which are encoded in the given
+ ENCODING, according to FORMAT. Stores the parsed
+ representation in OUTPUT, which has the given WIDTH (0 for
+ a numeric field, otherwise the string width).
If no decimal point is included in a numeric format, then
IMPLIED_DECIMALS decimal places are implied. Specify 0 if no
column number of the first character in INPUT, used in error
messages. */
bool
-data_in (struct substring input,
+data_in (struct substring input, enum legacy_encoding encoding,
enum fmt_type format, int implied_decimals,
int first_column, union value *output, int width)
{
};
struct data_in i;
+ void *copy = NULL;
bool ok;
assert ((width != 0) == fmt_is_string (format));
- i.input = input;
+ if (encoding == LEGACY_NATIVE
+ || fmt_get_category (format) & (FMT_CAT_BINARY | FMT_CAT_STRING))
+ {
+ i.input = input;
+ i.encoding = encoding;
+ }
+ else
+ {
+ ss_alloc_uninit (&i.input, ss_length (input));
+ legacy_recode (encoding, ss_data (input), LEGACY_NATIVE,
+ ss_data (i.input), ss_length (input));
+ i.encoding = LEGACY_NATIVE;
+ copy = ss_data (i.input);
+ }
i.format = format;
i.implied_decimals = implied_decimals;
ok = true;
}
+ if (copy)
+ free (copy);
+
return ok;
}
return false;
}
- /* Let strtod() do the conversion. */
+ /* Let c_strtod() do the conversion. */
save_errno = errno;
errno = 0;
- i->output->f = strtod (ds_cstr (&tmp), &tail);
+ i->output->f = c_strtod (ds_cstr (&tmp), &tail);
if (*tail != '\0')
{
data_warning (i, _("Invalid numeric syntax."));
return false;
}
- /* Let strtod() do the conversion. */
+ /* Let c_strtod() do the conversion. */
save_errno = errno;
errno = 0;
- i->output->f = strtod (ds_cstr (&tmp), NULL);
+ i->output->f = c_strtod (ds_cstr (&tmp), NULL);
if (errno == ERANGE)
{
if (fabs (i->output->f) > 1)
static bool
parse_A (struct data_in *i)
{
- buf_copy_rpad (i->output->s, i->width,
- ss_data (i->input), ss_length (i->input));
+ /* This is equivalent to buf_copy_rpad, except that we posibly
+ do a character set recoding in the middle. */
+ char *dst = i->output->s;
+ size_t dst_size = i->width;
+ const char *src = ss_data (i->input);
+ size_t src_size = ss_length (i->input);
+
+ legacy_recode (i->encoding, src, LEGACY_NATIVE, dst, MIN (src_size, dst_size));
+ if (dst_size > src_size)
+ memset (&dst[src_size], ' ', dst_size - src_size);
+
return true;
}
return false;
}
+ if (i->encoding != LEGACY_NATIVE)
+ {
+ hi = legacy_to_native (i->encoding, hi);
+ lo = legacy_to_native (i->encoding, lo);
+ }
if (!c_isxdigit (hi) || !c_isxdigit (lo))
{
data_warning (i, _("Field must contain only hex digits."));
exact matches (except for case) are allowed.
Returns true if successful, false otherwise. */
static bool
-match_name (struct substring token, const char **names, long *output)
+match_name (struct substring token, const char *const *names, long *output)
{
int i;
}
else
{
- static const char *english_names[] =
+ static const char *const english_names[] =
{
"jan", "feb", "mar", "apr", "may", "jun",
"jul", "aug", "sep", "oct", "nov", "dec",
NULL,
};
- static const char *roman_names[] =
+ static const char *const roman_names[] =
{
"i", "ii", "iii", "iv", "v", "vi",
"vii", "viii", "ix", "x", "xi", "xii",
static bool
parse_weekday (struct data_in *i, long *weekday)
{
- static const char *weekday_names[] =
+ static const char *const weekday_names[] =
{
"su", "mo", "tu", "we", "th", "fr", "sa",
NULL,
projects / pspp-builds.git / blobdiff