1 /* PSPP - a program for statistical analysis.
2 Copyright (C) 2010, 2011, 2013, 2016 Free Software Foundation, Inc.
4 This program is free software: you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation, either version 3 of the License, or
7 (at your option) any later version.
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <http://www.gnu.org/licenses/>. */
21 #include "data/case-map.h"
22 #include "data/casereader.h"
23 #include "data/casewriter.h"
24 #include "data/csv-file-writer.h"
25 #include "data/dataset.h"
26 #include "data/dictionary.h"
27 #include "data/file-name.h"
28 #include "data/format.h"
29 #include "data/settings.h"
30 #include "language/command.h"
31 #include "language/data-io/file-handle.h"
32 #include "language/data-io/trim.h"
33 #include "language/lexer/lexer.h"
34 #include "libpspp/message.h"
38 #define _(msgid) gettext (msgid)
39 #define N_(msgid) (msgid)
42 cmd_save_translate (struct lexer *lexer, struct dataset *ds)
44 enum { CSV_FILE = 1, TAB_FILE } type;
46 struct dictionary *dict;
47 struct case_map_stage *stage;
49 struct casewriter *writer;
50 struct file_handle *handle;
52 struct csv_writer_options csv_opts;
56 bool retain_unselected;
57 bool recode_user_missing;
58 bool include_var_names;
59 bool use_value_labels;
60 bool use_print_formats;
69 dict = dict_clone (dataset_dict (ds));
70 dict_set_names_must_be_ids (dict, false);
77 retain_unselected = true;
78 recode_user_missing = false;
79 include_var_names = false;
80 use_value_labels = false;
81 use_print_formats = false;
82 decimal = settings_get_decimal_char (FMT_F);
86 stage = case_map_stage_create (dict);
87 dict_delete_scratch_vars (dict);
89 while (lex_token (lexer) != T_ENDCMD)
91 if (!lex_force_match (lexer, T_SLASH))
94 if (lex_match_id (lexer, "OUTFILE"))
98 lex_sbc_only_once ("OUTFILE");
102 lex_match (lexer, T_EQUALS);
104 handle = fh_parse (lexer, FH_REF_FILE, NULL);
108 else if (lex_match_id (lexer, "TYPE"))
112 lex_sbc_only_once ("TYPE");
116 lex_match (lexer, T_EQUALS);
117 if (lex_match_id (lexer, "CSV"))
119 else if (lex_match_id (lexer, "TAB"))
123 lex_error_expecting (lexer, "CSV", "TAB");
127 else if (lex_match_id (lexer, "REPLACE"))
129 else if (lex_match_id (lexer, "FIELDNAMES"))
130 include_var_names = true;
131 else if (lex_match_id (lexer, "MISSING"))
133 lex_match (lexer, T_EQUALS);
134 if (lex_match_id (lexer, "IGNORE"))
135 recode_user_missing = false;
136 else if (lex_match_id (lexer, "RECODE"))
137 recode_user_missing = true;
140 lex_error_expecting (lexer, "IGNORE", "RECODE");
144 else if (lex_match_id (lexer, "CELLS"))
146 lex_match (lexer, T_EQUALS);
147 if (lex_match_id (lexer, "VALUES"))
148 use_value_labels = false;
149 else if (lex_match_id (lexer, "LABELS"))
150 use_value_labels = true;
153 lex_error_expecting (lexer, "VALUES", "LABELS");
157 else if (lex_match_id (lexer, "TEXTOPTIONS"))
159 lex_match (lexer, T_EQUALS);
162 if (lex_match_id (lexer, "DELIMITER"))
164 lex_match (lexer, T_EQUALS);
165 if (!lex_force_string (lexer))
167 /* XXX should support multibyte UTF-8 delimiters */
168 if (ss_length (lex_tokss (lexer)) != 1)
170 msg (SE, _("The %s string must contain exactly one "
171 "character."), "DELIMITER");
174 delimiter = ss_first (lex_tokss (lexer));
177 else if (lex_match_id (lexer, "QUALIFIER"))
179 lex_match (lexer, T_EQUALS);
180 if (!lex_force_string (lexer))
182 /* XXX should support multibyte UTF-8 qualifiers */
183 if (ss_length (lex_tokss (lexer)) != 1)
185 msg (SE, _("The %s string must contain exactly one "
186 "character."), "QUALIFIER");
189 qualifier = ss_first (lex_tokss (lexer));
192 else if (lex_match_id (lexer, "DECIMAL"))
194 lex_match (lexer, T_EQUALS);
195 if (lex_match_id (lexer, "DOT"))
197 else if (lex_match_id (lexer, "COMMA"))
201 lex_error_expecting (lexer, "DOT", "COMMA");
205 else if (lex_match_id (lexer, "FORMAT"))
207 lex_match (lexer, T_EQUALS);
208 if (lex_match_id (lexer, "PLAIN"))
209 use_print_formats = false;
210 else if (lex_match_id (lexer, "VARIABLE"))
211 use_print_formats = true;
214 lex_error_expecting (lexer, "PLAIN", "VARIABLE");
222 else if (lex_match_id (lexer, "UNSELECTED"))
224 lex_match (lexer, T_EQUALS);
225 if (lex_match_id (lexer, "RETAIN"))
226 retain_unselected = true;
227 else if (lex_match_id (lexer, "DELETE"))
228 retain_unselected = false;
231 lex_error_expecting (lexer, "RETAIN", "DELETE");
235 else if (!parse_dict_trim (lexer, dict, true))
241 lex_sbc_missing ("TYPE");
244 else if (handle == NULL)
246 lex_sbc_missing ("OUTFILE");
249 else if (!replace && fn_exists (handle))
251 msg (SE, _("Output file `%s' exists but %s was not specified."),
252 fh_get_file_name (handle), "REPLACE");
256 dict_delete_scratch_vars (dict);
257 dict_compact_values (dict);
259 csv_opts.recode_user_missing = recode_user_missing;
260 csv_opts.include_var_names = include_var_names;
261 csv_opts.use_value_labels = use_value_labels;
262 csv_opts.use_print_formats = use_print_formats;
263 csv_opts.decimal = decimal;
264 csv_opts.delimiter = (delimiter ? delimiter
265 : type == TAB_FILE ? '\t'
266 : decimal == '.' ? ','
268 csv_opts.qualifier = qualifier;
270 writer = csv_writer_open (handle, dict, &csv_opts);
275 map = case_map_stage_get_case_map (stage);
276 case_map_stage_destroy (stage);
278 writer = case_map_create_output_translator (map, writer);
281 casereader_transfer (proc_open_filtering (ds, !retain_unselected), writer);
282 ok = casewriter_destroy (writer);
283 ok = proc_commit (ds) && ok;
285 return ok ? CMD_SUCCESS : CMD_CASCADING_FAILURE;
288 case_map_stage_destroy (stage);
291 case_map_destroy (map);