/* PSPP - a program for statistical analysis.
- Copyright (C) 2007 Free Software Foundation, Inc.
+ Copyright (C) 2007, 2008, 2009, 2010, 2011, 2012, 2013 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 <stdlib.h>
-#include <data/gnumeric-reader.h>
-
-#include <data/dictionary.h>
-#include <data/format.h>
-#include <data/procedure.h>
-#include <language/command.h>
-#include <language/data-io/data-parser.h>
-#include <language/data-io/data-reader.h>
-#include <language/data-io/file-handle.h>
-#include <language/data-io/placement-parser.h>
-#include <language/lexer/format-parser.h>
-#include <language/lexer/lexer.h>
-#include <libpspp/message.h>
+#include <string.h>
+
+#include "data/dataset.h"
+#include "data/dictionary.h"
+#include "data/format.h"
+#include "data/gnumeric-reader.h"
+#include "data/ods-reader.h"
+#include "data/spreadsheet-reader.h"
+#include "data/psql-reader.h"
+#include "data/settings.h"
+#include "language/command.h"
+#include "language/data-io/data-parser.h"
+#include "language/data-io/data-reader.h"
+#include "language/data-io/file-handle.h"
+#include "language/data-io/placement-parser.h"
+#include "language/lexer/format-parser.h"
+#include "language/lexer/lexer.h"
+#include "libpspp/cast.h"
+#include "libpspp/i18n.h"
+#include "libpspp/message.h"
+
+#include "gl/xalloc.h"
#include "gettext.h"
#define _(msgid) gettext (msgid)
#define N_(msgid) (msgid)
-static int parse_get_gnm (struct lexer *lexer, struct dataset *);
+static struct spreadsheet_read_info *parse_spreadsheet (struct lexer *lexer);
+static void destroy_spreadsheet_read_info (struct spreadsheet_read_info *);
+
static int parse_get_txt (struct lexer *lexer, struct dataset *);
+static int parse_get_psql (struct lexer *lexer, struct dataset *);
int
cmd_get_data (struct lexer *lexer, struct dataset *ds)
{
- lex_force_match (lexer, '/');
+ char *tok = NULL;
+ lex_force_match (lexer, T_SLASH);
if (!lex_force_match_id (lexer, "TYPE"))
return CMD_FAILURE;
- lex_force_match (lexer, '=');
+ lex_force_match (lexer, T_EQUALS);
- if (lex_match_id (lexer, "GNM"))
- return parse_get_gnm (lexer, ds);
- else if (lex_match_id (lexer, "TXT"))
- return parse_get_txt (lexer, ds);
+ tok = strdup (lex_tokcstr (lexer));
+ if (lex_match_id (lexer, "TXT"))
+ {
+ free (tok);
+ return parse_get_txt (lexer, ds);
+ }
+ else if (lex_match_id (lexer, "PSQL"))
+ {
+ free (tok);
+ return parse_get_psql (lexer, ds);
+ }
+ else if (lex_match_id (lexer, "GNM") ||
+ lex_match_id (lexer, "ODS"))
+ {
+ struct casereader *reader = NULL;
+ struct dictionary *dict = NULL;
+ struct spreadsheet_read_info *sri = parse_spreadsheet (lexer);
+ if (NULL == sri)
+ goto error;
+
+ if ( 0 == strncasecmp (tok, "GNM", 3))
+ reader = gnumeric_open_reader (sri, &dict);
+ else if (0 == strncasecmp (tok, "ODS", 3))
+ reader = ods_open_reader (sri, &dict);
+
+ if (reader)
+ {
+ dataset_set_dict (ds, dict);
+ dataset_set_source (ds, reader);
+ destroy_spreadsheet_read_info (sri);
+ free (tok);
+ return CMD_SUCCESS;
+ }
+ destroy_spreadsheet_read_info (sri);
+ }
+ else
+ msg (SE, _("Unsupported TYPE %s."), tok);
- msg (SE, _("Unsupported TYPE %s"), lex_tokid (lexer));
+ error:
+ free (tok);
return CMD_FAILURE;
}
-
static int
-parse_get_gnm (struct lexer *lexer, struct dataset *ds)
+parse_get_psql (struct lexer *lexer, struct dataset *ds)
+{
+ struct psql_read_info psql;
+ psql.allow_clear = false;
+ psql.conninfo = NULL;
+ psql.str_width = -1;
+ psql.bsize = -1;
+ ds_init_empty (&psql.sql);
+
+ lex_force_match (lexer, T_SLASH);
+
+ if (!lex_force_match_id (lexer, "CONNECT"))
+ goto error;
+
+ lex_force_match (lexer, T_EQUALS);
+
+ if (!lex_force_string (lexer))
+ goto error;
+
+ psql.conninfo = ss_xstrdup (lex_tokss (lexer));
+
+ lex_get (lexer);
+
+ while (lex_match (lexer, T_SLASH) )
+ {
+ if ( lex_match_id (lexer, "ASSUMEDSTRWIDTH"))
+ {
+ lex_match (lexer, T_EQUALS);
+ psql.str_width = lex_integer (lexer);
+ lex_get (lexer);
+ }
+ else if ( lex_match_id (lexer, "BSIZE"))
+ {
+ lex_match (lexer, T_EQUALS);
+ psql.bsize = lex_integer (lexer);
+ lex_get (lexer);
+ }
+ else if ( lex_match_id (lexer, "UNENCRYPTED"))
+ {
+ psql.allow_clear = true;
+ }
+ else if (lex_match_id (lexer, "SQL"))
+ {
+ lex_match (lexer, T_EQUALS);
+ if ( ! lex_force_string (lexer) )
+ goto error;
+
+ ds_put_substring (&psql.sql, lex_tokss (lexer));
+ lex_get (lexer);
+ }
+ }
+ {
+ struct dictionary *dict = NULL;
+ struct casereader *reader = psql_open_reader (&psql, &dict);
+
+ if ( reader )
+ {
+ dataset_set_dict (ds, dict);
+ dataset_set_source (ds, reader);
+ }
+ }
+
+ ds_destroy (&psql.sql);
+ free (psql.conninfo);
+
+ return CMD_SUCCESS;
+
+ error:
+
+ ds_destroy (&psql.sql);
+ free (psql.conninfo);
+
+ return CMD_FAILURE;
+}
+
+static struct spreadsheet_read_info *
+parse_spreadsheet (struct lexer *lexer)
{
- struct gnumeric_read_info gri = {NULL, NULL, NULL, 1, true, -1};
+ struct spreadsheet_read_info *sri = xzalloc (sizeof *sri);
+ sri->sheet_index = 1;
+ sri->read_names = true;
+ sri->asw = -1;
- lex_force_match (lexer, '/');
+ lex_force_match (lexer, T_SLASH);
if (!lex_force_match_id (lexer, "FILE"))
goto error;
- lex_force_match (lexer, '=');
+ lex_force_match (lexer, T_EQUALS);
if (!lex_force_string (lexer))
goto error;
- gri.file_name = strdup (ds_cstr (lex_tokstr (lexer)));
+ sri->file_name = utf8_to_filename (lex_tokcstr (lexer));
lex_get (lexer);
- while (lex_match (lexer, '/') )
+ while (lex_match (lexer, T_SLASH) )
{
if ( lex_match_id (lexer, "ASSUMEDSTRWIDTH"))
{
- lex_match (lexer, '=');
- gri.asw = lex_integer (lexer);
+ lex_match (lexer, T_EQUALS);
+ sri->asw = lex_integer (lexer);
+ lex_get (lexer);
}
else if (lex_match_id (lexer, "SHEET"))
{
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (lex_match_id (lexer, "NAME"))
{
if ( ! lex_force_string (lexer) )
goto error;
- gri.sheet_name = strdup (ds_cstr (lex_tokstr (lexer)));
- gri.sheet_index = -1;
+ sri->sheet_name = ss_xstrdup (lex_tokss (lexer));
+ sri->sheet_index = -1;
+
+ lex_get (lexer);
}
else if (lex_match_id (lexer, "INDEX"))
{
- gri.sheet_index = lex_integer (lexer);
+ sri->sheet_index = lex_integer (lexer);
+ if (sri->sheet_index <= 0)
+ {
+ msg (SE, _("The sheet index must be greater than or equal to 1"));
+ goto error;
+ }
+ lex_get (lexer);
}
else
- goto error;
+ {
+ msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."),
+ "/SHEET", "NAME", "INDEX");
+ goto error;
+ }
}
else if (lex_match_id (lexer, "CELLRANGE"))
{
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (lex_match_id (lexer, "FULL"))
{
- gri.cell_range = NULL;
- lex_put_back (lexer, T_ID);
+ sri->cell_range = NULL;
}
else if (lex_match_id (lexer, "RANGE"))
{
if ( ! lex_force_string (lexer) )
goto error;
- gri.cell_range = strdup (ds_cstr (lex_tokstr (lexer)));
+ sri->cell_range = ss_xstrdup (lex_tokss (lexer));
+ lex_get (lexer);
}
else
- goto error;
+ {
+ msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."),
+ "/CELLRANGE", "FULL", "RANGE");
+ goto error;
+ }
}
else if (lex_match_id (lexer, "READNAMES"))
{
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if ( lex_match_id (lexer, "ON"))
{
- gri.read_names = true;
+ sri->read_names = true;
}
else if (lex_match_id (lexer, "OFF"))
{
- gri.read_names = false;
+ sri->read_names = false;
}
else
- goto error;
- lex_put_back (lexer, T_ID);
+ {
+ msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."),
+ "/READNAMES", "ON", "OFF");
+ goto error;
+ }
}
else
{
- printf ("Unknown data file type \"\%s\"\n", lex_tokid (lexer));
+ lex_error (lexer, NULL);
goto error;
}
- lex_get (lexer);
}
- {
- struct dictionary *dict = NULL;
- struct casereader *reader = gnumeric_open_reader (&gri, &dict);
-
- if ( reader )
- proc_set_active_file (ds, reader, dict);
- }
-
- free (gri.file_name);
- free (gri.sheet_name);
- free (gri.cell_range);
- return CMD_SUCCESS;
+ return sri;
error:
-
- free (gri.file_name);
- free (gri.sheet_name);
- free (gri.cell_range);
- return CMD_FAILURE;
+ destroy_spreadsheet_read_info (sri);
+ return NULL;
}
+
static bool
set_type (struct data_parser *parser, const char *subcommand,
enum data_parser_type type, bool *has_type)
parse_get_txt (struct lexer *lexer, struct dataset *ds)
{
struct data_parser *parser = NULL;
- struct dictionary *dict = NULL;
+ struct dictionary *dict = dict_create (get_default_encoding ());
struct file_handle *fh = NULL;
struct dfm_reader *reader = NULL;
+ char *encoding = NULL;
+ char *name = NULL;
int record;
enum data_parser_type type;
bool has_type;
- lex_force_match (lexer, '/');
+ lex_force_match (lexer, T_SLASH);
if (!lex_force_match_id (lexer, "FILE"))
goto error;
- lex_force_match (lexer, '=');
- fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE);
+ lex_force_match (lexer, T_EQUALS);
+ fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE, NULL);
if (fh == NULL)
goto error;
- parser = data_parser_create ();
+ parser = data_parser_create (dict);
has_type = false;
data_parser_set_type (parser, DP_DELIMITED);
data_parser_set_span (parser, false);
for (;;)
{
- if (!lex_force_match (lexer, '/'))
+ if (!lex_force_match (lexer, T_SLASH))
goto error;
- if (lex_match_id (lexer, "ARRANGEMENT"))
+ if (lex_match_id (lexer, "ENCODING"))
+ {
+ lex_match (lexer, T_EQUALS);
+ if (!lex_force_string (lexer))
+ goto error;
+
+ free (encoding);
+ encoding = ss_xstrdup (lex_tokss (lexer));
+
+ lex_get (lexer);
+ }
+ else if (lex_match_id (lexer, "ARRANGEMENT"))
{
bool ok;
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (lex_match_id (lexer, "FIXED"))
ok = set_type (parser, "ARRANGEMENT=FIXED", DP_FIXED, &has_type);
else if (lex_match_id (lexer, "DELIMITED"))
DP_DELIMITED, &has_type);
else
{
- lex_error (lexer, _("expecting FIXED or DELIMITED"));
+ lex_error_expecting (lexer, "FIXED", "DELIMITED", NULL_SENTINEL);
goto error;
}
if (!ok)
}
else if (lex_match_id (lexer, "FIRSTCASE"))
{
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (!lex_force_int (lexer))
goto error;
if (lex_integer (lexer) < 1)
{
if (!set_type (parser, "DELCASE", DP_DELIMITED, &has_type))
goto error;
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (lex_match_id (lexer, "LINE"))
data_parser_set_span (parser, false);
else if (lex_match_id (lexer, "VARIABLES"))
}
else
{
- lex_error (lexer, _("expecting LINE or VARIABLES"));
+ lex_error_expecting (lexer, "LINE", "VARIABLES", NULL_SENTINEL);
goto error;
}
}
{
if (!set_type (parser, "FIXCASE", DP_FIXED, &has_type))
goto error;
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (!lex_force_int (lexer))
goto error;
if (lex_integer (lexer) < 1)
}
else if (lex_match_id (lexer, "IMPORTCASES"))
{
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (lex_match (lexer, T_ALL))
{
data_parser_set_case_limit (parser, -1);
if (!set_type (parser, "DELIMITERS", DP_DELIMITED, &has_type))
goto error;
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (!lex_force_string (lexer))
goto error;
- s = ds_ss (lex_tokstr (lexer));
+ /* XXX should support multibyte UTF-8 characters */
+ s = lex_tokss (lexer);
if (ss_match_string (&s, ss_cstr ("\\t")))
ds_put_cstr (&hard_seps, "\t");
if (ss_match_string (&s, ss_cstr ("\\\\")))
ds_put_cstr (&hard_seps, "\\");
- while ((c = ss_get_char (&s)) != EOF)
+ while ((c = ss_get_byte (&s)) != EOF)
if (c == ' ')
soft_seps = " ";
else
- ds_put_char (&hard_seps, c);
+ ds_put_byte (&hard_seps, c);
data_parser_set_soft_delimiters (parser, ss_cstr (soft_seps));
data_parser_set_hard_delimiters (parser, ds_ss (&hard_seps));
ds_destroy (&hard_seps);
lex_get (lexer);
}
- else if (lex_match_id (lexer, "QUALIFIER"))
+ else if (lex_match_id (lexer, "QUALIFIERS"))
{
- if (!set_type (parser, "QUALIFIER", DP_DELIMITED, &has_type))
+ if (!set_type (parser, "QUALIFIERS", DP_DELIMITED, &has_type))
goto error;
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
if (!lex_force_string (lexer))
goto error;
- data_parser_set_quotes (parser, ds_ss (lex_tokstr (lexer)));
+ /* XXX should support multibyte UTF-8 characters */
+ if (settings_get_syntax () == COMPATIBLE
+ && ss_length (lex_tokss (lexer)) != 1)
+ {
+ msg (SE, _("In compatible syntax mode, the QUALIFIER string "
+ "must contain exactly one character."));
+ goto error;
+ }
+
+ data_parser_set_quotes (parser, lex_tokss (lexer));
lex_get (lexer);
}
+ else if (settings_get_syntax () == ENHANCED
+ && lex_match_id (lexer, "ESCAPE"))
+ data_parser_set_quote_escape (parser, true);
else if (lex_match_id (lexer, "VARIABLES"))
break;
else
{
- lex_error (lexer, _("expecting VARIABLES"));
+ lex_error_expecting (lexer, "VARIABLES", NULL_SENTINEL);
goto error;
}
}
- lex_match (lexer, '=');
+ lex_match (lexer, T_EQUALS);
- dict = dict_create ();
record = 1;
type = data_parser_get_type (parser);
do
{
- char name[VAR_NAME_LEN + 1];
struct fmt_spec input, output;
- int fc, lc;
struct variable *v;
+ int fc, lc;
- while (type == DP_FIXED && lex_match (lexer, '/'))
+ while (type == DP_FIXED && lex_match (lexer, T_SLASH))
{
if (!lex_force_int (lexer))
goto error;
lex_get (lexer);
}
- if (!lex_force_id (lexer))
+ if (!lex_force_id (lexer)
+ || !dict_id_is_valid (dict, lex_tokcstr (lexer), true))
goto error;
- strcpy (name, lex_tokid (lexer));
+ name = xstrdup (lex_tokcstr (lexer));
lex_get (lexer);
if (type == DP_DELIMITED)
if (!parse_format_specifier (lexer, &input)
|| !fmt_check_input (&input))
goto error;
+
+ output = fmt_for_output_from_input (&input);
}
else
{
+ char fmt_type_name[FMT_TYPE_LEN_MAX + 1];
+ enum fmt_type fmt_type;
+ int w, d;
+
if (!parse_column_range (lexer, 0, &fc, &lc, NULL))
goto error;
- if (!parse_format_specifier_name (lexer, &input.type))
+
+ /* Accept a format (e.g. F8.2) or just a type name (e.g. DOLLAR). */
+ if (!parse_abstract_format_specifier (lexer, fmt_type_name, &w, &d))
goto error;
+ if (!fmt_from_name (fmt_type_name, &fmt_type))
+ {
+ msg (SE, _("Unknown format type `%s'."), fmt_type_name);
+ goto error;
+ }
+
+ /* Compose input format. */
+ input.type = fmt_type;
input.w = lc - fc + 1;
input.d = 0;
if (!fmt_check_input (&input))
goto error;
+
+ /* Compose output format. */
+ if (w != 0)
+ {
+ output.type = fmt_type;
+ output.w = w;
+ output.d = d;
+ if (!fmt_check_output (&output))
+ goto error;
+ }
+ else
+ output = fmt_for_output_from_input (&input);
}
- output = fmt_for_output_from_input (&input);
v = dict_create_var (dict, name, fmt_var_width (&input));
if (v == NULL)
else
data_parser_add_fixed_field (parser, &input, var_get_case_index (v),
name, record, fc);
+ free (name);
+ name = NULL;
}
- while (lex_token (lexer) != '.');
+ while (lex_token (lexer) != T_ENDCMD);
- reader = dfm_open_reader (fh, lexer);
+ reader = dfm_open_reader (fh, lexer, encoding);
if (reader == NULL)
goto error;
data_parser_make_active_file (parser, ds, reader, dict);
fh_unref (fh);
+ free (encoding);
return CMD_SUCCESS;
error:
data_parser_destroy (parser);
dict_destroy (dict);
fh_unref (fh);
+ free (name);
+ free (encoding);
return CMD_CASCADING_FAILURE;
}
+
+
+static void
+destroy_spreadsheet_read_info (struct spreadsheet_read_info *sri)
+{
+ if ( NULL == sri)
+ return;
+
+ free (sri->sheet_name);
+ free (sri->cell_range);
+ free (sri->file_name);
+ free (sri);
+}