/* PSPP - a program for statistical analysis.
- Copyright (C) 2007, 2009 Free Software Foundation, Inc.
+ Copyright (C) 2007, 2009, 2010 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
#include <language/data-io/data-reader.h>
#include <libpspp/message.h>
#include <libpspp/str.h>
-#include <output/table.h>
+#include <output/tab.h>
#include "xalloc.h"
/* Data parser for textual data like that read by DATA LIST. */
struct data_parser
{
+ const struct dictionary *dict; /*Dictionary of destination */
enum data_parser_type type; /* Type of data to parse. */
int skip_records; /* Records to skip before first real data. */
casenumber max_cases; /* Max number of cases to read. */
/* Creates and returns a new data parser. */
struct data_parser *
-data_parser_create (void)
+data_parser_create (const struct dictionary *dict)
{
struct data_parser *parser = xmalloc (sizeof *parser);
parser->fields = NULL;
parser->field_cnt = 0;
parser->field_allocated = 0;
+ parser->dict = dict;
parser->span = true;
parser->empty_line_has_field = false;
}
*field = ds_ss (tmp);
}
- *last_column = dfm_column_start (reader);
+ *last_column = *first_column + (ss_length (line) - ss_length (p));
/* Skip trailing soft separator and a single hard separator
if present. */
{
/* Regular field. */
ss_get_chars (&p, ss_cspan (p, ds_ss (&parser->any_sep)), field);
- *last_column = dfm_column_start (reader);
- if (!ss_ltrim (&p, parser->soft_seps) || ss_is_empty (p))
+ *last_column = *first_column + ss_length (*field);
+
+ if (!ss_ltrim (&p, parser->soft_seps) || ss_is_empty (p)
+ || ss_find_char (parser->hard_seps, p.string[0]) != SIZE_MAX)
{
/* Advance past a trailing hard separator,
regardless of whether one actually existed. If
parse_fixed (const struct data_parser *parser, struct dfm_reader *reader,
struct ccase *c)
{
- enum legacy_encoding encoding = dfm_reader_get_legacy_encoding (reader);
+ const char *encoding = dfm_reader_get_legacy_encoding (reader);
struct field *f;
int row;
line = dfm_get_record (reader);
for (; f < &parser->fields[parser->field_cnt] && f->record == row; f++)
- data_in (ss_substr (line, f->first_column - 1,
- f->format.w),
- encoding, f->format.type, f->format.d,
- f->first_column, f->first_column + f->format.w,
- case_data_rw_idx (c, f->case_idx),
- fmt_var_width (&f->format));
+ {
+ struct substring s = ss_substr (line, f->first_column - 1,
+ f->format.w);
+ union value *value = case_data_rw_idx (c, f->case_idx);
+
+ data_in (s, encoding, f->format.type,
+ f->first_column, f->first_column + f->format.w,
+ parser->dict, value, fmt_var_width (&f->format));
+
+ data_in_imply_decimals (s, encoding, f->format.type, f->format.d,
+ value);
+ }
dfm_forward_record (reader);
}
parse_delimited_span (const struct data_parser *parser,
struct dfm_reader *reader, struct ccase *c)
{
- enum legacy_encoding encoding = dfm_reader_get_legacy_encoding (reader);
+ const char *encoding = dfm_reader_get_legacy_encoding (reader);
struct string tmp = DS_EMPTY_INITIALIZER;
struct field *f;
}
}
- data_in (s, encoding, f->format.type, 0,
- first_column, last_column,
+ data_in (s, encoding, f->format.type, first_column, last_column,
+ parser->dict,
case_data_rw_idx (c, f->case_idx),
fmt_var_width (&f->format));
}
parse_delimited_no_span (const struct data_parser *parser,
struct dfm_reader *reader, struct ccase *c)
{
- enum legacy_encoding encoding = dfm_reader_get_legacy_encoding (reader);
+ const char *encoding = dfm_reader_get_legacy_encoding (reader);
struct string tmp = DS_EMPTY_INITIALIZER;
struct substring s;
- struct field *f;
+ struct field *f, *end;
if (dfm_eof (reader))
return false;
- for (f = parser->fields; f < &parser->fields[parser->field_cnt]; f++)
+ end = &parser->fields[parser->field_cnt];
+ for (f = parser->fields; f < end; f++)
{
int first_column, last_column;
if (!cut_field (parser, reader, &first_column, &last_column, &tmp, &s))
{
- if (settings_get_undefined ())
+ if (f < end - 1 && settings_get_undefined ())
msg (SW, _("Missing value(s) for all variables from %s onward. "
"These will be filled with the system-missing value "
"or blanks, as appropriate."),
f->name);
- for (; f < &parser->fields[parser->field_cnt]; f++)
+ for (; f < end; f++)
value_set_missing (case_data_rw_idx (c, f->case_idx),
fmt_var_width (&f->format));
goto exit;
}
- data_in (s, encoding, f->format.type, 0,
- first_column, last_column,
+ data_in (s, encoding, f->format.type, first_column, last_column,
+ parser->dict,
case_data_rw_idx (c, f->case_idx),
fmt_var_width (&f->format));
}
size_t i;
t = tab_create (4, parser->field_cnt + 1);
- tab_columns (t, TAB_COL_DOWN);
tab_headers (t, 0, 0, 1, 0);
tab_text (t, 0, 0, TAB_CENTER | TAT_TITLE, _("Variable"));
tab_text (t, 1, 0, TAB_CENTER | TAT_TITLE, _("Record"));
tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("Format"));
tab_box (t, TAL_1, TAL_1, TAL_0, TAL_1, 0, 0, 3, parser->field_cnt);
tab_hline (t, TAL_2, 0, 3, 1);
- tab_dim (t, tab_natural_dimensions, NULL, NULL);
for (i = 0; i < parser->field_cnt; i++)
{
size_t i;
t = tab_create (2, parser->field_cnt + 1);
- tab_columns (t, TAB_COL_DOWN);
tab_headers (t, 0, 0, 1, 0);
tab_text (t, 0, 0, TAB_CENTER | TAT_TITLE, _("Variable"));
tab_text (t, 1, 0, TAB_CENTER | TAT_TITLE, _("Format"));
tab_box (t, TAL_1, TAL_1, TAL_0, TAL_1, 0, 0, 1, parser->field_cnt);
tab_hline (t, TAL_2, 0, 1, 1);
- tab_dim (t, tab_natural_dimensions, NULL, NULL);
for (i = 0; i < parser->field_cnt; i++)
{
projects / pspp / blobdiff