1 /* PSPP - computes sample statistics.
2 Copyright (C) 1997-9, 2000, 2006 Free Software Foundation, Inc.
3 Written by Ben Pfaff <blp@gnu.org>.
5 This program is free software; you can redistribute it and/or
6 modify it under the terms of the GNU General Public License as
7 published by the Free Software Foundation; either version 2 of the
8 License, or (at your option) any later version.
10 This program is distributed in the hope that it will be useful, but
11 WITHOUT ANY WARRANTY; without even the implied warranty of
12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 General Public License for more details.
15 You should have received a copy of the GNU General Public License
16 along with this program; if not, write to the Free Software
17 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
25 #include <data/dictionary.h>
26 #include <data/file-handle-def.h>
27 #include <data/format.h>
28 #include <data/missing-values.h>
29 #include <data/procedure.h>
30 #include <data/sys-file-reader.h>
31 #include <data/value-labels.h>
32 #include <data/variable.h>
33 #include <data/vector.h>
34 #include <language/command.h>
35 #include <language/data-io/file-handle.h>
36 #include <language/lexer/lexer.h>
37 #include <language/lexer/variable-parser.h>
38 #include <libpspp/alloc.h>
39 #include <libpspp/array.h>
40 #include <libpspp/hash.h>
41 #include <libpspp/magic.h>
42 #include <libpspp/message.h>
43 #include <libpspp/message.h>
44 #include <libpspp/misc.h>
45 #include <output/manager.h>
46 #include <output/output.h>
47 #include <output/table.h>
52 #define _(msgid) gettext (msgid)
54 /* Constants for DISPLAY utility. */
66 static int describe_variable (struct variable *v, struct tab_table *t, int r, int as);
68 /* Sets the widths of all the columns and heights of all the rows in
69 table T for driver D. */
71 sysfile_info_dim (struct tab_table *t, struct outp_driver *d)
73 static const int max[] = {20, 5, 35, 3, 0};
77 for (p = max; *p; p++)
78 t->w[p - max] = MIN (tab_natural_width (t, d, p - max),
79 *p * d->prop_em_width);
80 for (i = 0; i < t->nr; i++)
81 t->h[i] = tab_natural_height (t, d, i);
84 /* SYSFILE INFO utility. */
86 cmd_sysfile_info (struct lexer *lexer, struct dataset *ds UNUSED)
88 struct file_handle *h;
91 struct sfm_reader *reader;
92 struct sfm_read_info info;
96 lex_match_id (lexer, "FILE");
97 lex_match (lexer, '=');
99 h = fh_parse (lexer, FH_REF_FILE);
103 reader = sfm_open_reader (h, &d, &info);
106 sfm_close_reader (reader);
108 t = tab_create (2, 10, 0);
109 tab_vline (t, TAL_GAP, 1, 0, 8);
110 tab_text (t, 0, 0, TAB_LEFT, _("File:"));
111 tab_text (t, 1, 0, TAB_LEFT, fh_get_file_name (h));
112 tab_text (t, 0, 1, TAB_LEFT, _("Label:"));
114 const char *label = dict_get_label (d);
116 label = _("No label.");
117 tab_text (t, 1, 1, TAB_LEFT, label);
119 tab_text (t, 0, 2, TAB_LEFT, _("Created:"));
120 tab_text (t, 1, 2, TAB_LEFT | TAT_PRINTF, "%s %s by %s",
121 info.creation_date, info.creation_time, info.product);
122 tab_text (t, 0, 3, TAB_LEFT, _("Integer Format:"));
123 tab_text (t, 1, 3, TAB_LEFT,
124 info.integer_format == INTEGER_MSB_FIRST ? _("Big Endian.")
125 : info.integer_format == INTEGER_LSB_FIRST ? _("Little Endian.")
127 tab_text (t, 0, 4, TAB_LEFT, _("Real Format:"));
128 tab_text (t, 1, 4, TAB_LEFT,
129 info.float_format == FLOAT_IEEE_DOUBLE_LE ? _("IEEE 754 LE.")
130 : info.float_format == FLOAT_IEEE_DOUBLE_BE ? _("IEEE 754 BE.")
131 : info.float_format == FLOAT_VAX_D ? _("VAX D.")
132 : info.float_format == FLOAT_VAX_G ? _("VAX G.")
133 : info.float_format == FLOAT_Z_LONG ? _("IBM 390 Hex Long.")
135 tab_text (t, 0, 5, TAB_LEFT, _("Variables:"));
136 tab_text (t, 1, 5, TAB_LEFT | TAT_PRINTF, "%d",
137 dict_get_var_cnt (d));
138 tab_text (t, 0, 6, TAB_LEFT, _("Cases:"));
139 tab_text (t, 1, 6, TAB_LEFT | TAT_PRINTF,
140 info.case_cnt == -1 ? _("Unknown") : "%d", info.case_cnt);
141 tab_text (t, 0, 7, TAB_LEFT, _("Type:"));
142 tab_text (t, 1, 7, TAB_LEFT, _("System File."));
143 tab_text (t, 0, 8, TAB_LEFT, _("Weight:"));
145 struct variable *weight_var = dict_get_weight (d);
146 tab_text (t, 1, 8, TAB_LEFT,
148 ? var_get_name (weight_var) : _("Not weighted.")));
150 tab_text (t, 0, 9, TAB_LEFT, _("Mode:"));
151 tab_text (t, 1, 9, TAB_LEFT | TAT_PRINTF,
152 _("Compression %s."), info.compressed ? _("on") : _("off"));
153 tab_dim (t, tab_natural_dimensions);
156 nr = 1 + 2 * dict_get_var_cnt (d);
158 t = tab_create (4, nr, 1);
159 tab_dim (t, sysfile_info_dim);
160 tab_headers (t, 0, 0, 1, 0);
161 tab_text (t, 0, 0, TAB_LEFT | TAT_TITLE, _("Variable"));
162 tab_joint_text (t, 1, 0, 2, 0, TAB_LEFT | TAT_TITLE, _("Description"));
163 tab_text (t, 3, 0, TAB_LEFT | TAT_TITLE, _("Position"));
164 tab_hline (t, TAL_2, 0, 3, 1);
165 for (r = 1, i = 0; i < dict_get_var_cnt (d); i++)
167 struct variable *v = dict_get_var (d, i);
168 const int nvl = val_labs_count (var_get_value_labels (v));
170 if (r + 10 + nvl > nr)
172 nr = MAX (nr * dict_get_var_cnt (d) / (i + 1), nr);
174 tab_realloc (t, 4, nr);
177 r = describe_variable (v, t, r, AS_DICTIONARY);
180 tab_box (t, TAL_1, TAL_1, -1, -1, 0, 0, 3, r);
181 tab_vline (t, TAL_1, 1, 0, r);
182 tab_vline (t, TAL_1, 3, 0, r);
184 tab_resize (t, -1, r);
185 tab_flags (t, SOMF_NO_TITLE);
190 return lex_end_of_command (lexer);
193 /* DISPLAY utility. */
195 static void display_macros (void);
196 static void display_documents (const struct dictionary *dict);
197 static void display_variables (struct variable **, size_t, int);
198 static void display_vectors (const struct dictionary *dict, int sorted);
201 cmd_display (struct lexer *lexer, struct dataset *ds)
203 /* Whether to sort the list of variables alphabetically. */
206 /* Variables to display. */
208 struct variable **vl;
210 if (lex_match_id (lexer, "MACROS"))
212 else if (lex_match_id (lexer, "DOCUMENTS"))
213 display_documents (dataset_dict (ds));
214 else if (lex_match_id (lexer, "FILE"))
217 if (!lex_force_match_id (lexer, "LABEL"))
219 if (dict_get_label (dataset_dict (ds)) == NULL)
220 tab_output_text (TAB_LEFT,
221 _("The active file does not have a file label."));
224 tab_output_text (TAB_LEFT | TAT_TITLE, _("File label:"));
225 tab_output_text (TAB_LEFT | TAB_FIX, dict_get_label (dataset_dict (ds)));
230 static const char *sbc[] =
231 {"NAMES", "INDEX", "VARIABLES", "LABELS",
232 "DICTIONARY", "SCRATCH", "VECTORS", NULL};
236 sorted = lex_match_id (lexer, "SORTED");
238 for (cp = sbc; *cp; cp++)
239 if (lex_token (lexer) == T_ID
240 && lex_id_match (ss_cstr (*cp), ss_cstr (lex_tokid (lexer))))
252 display_vectors (dataset_dict(ds), sorted);
256 lex_match (lexer, '/');
257 lex_match_id (lexer, "VARIABLES");
258 lex_match (lexer, '=');
260 if (lex_token (lexer) != '.')
262 if (!parse_variables (lexer, dataset_dict (ds), &vl, &n, PV_NONE))
270 dict_get_vars (dataset_dict (ds), &vl, &n, 0);
272 if (as == AS_SCRATCH)
275 for (i = 0, m = n; i < n; i++)
276 if (dict_class_from_id (var_get_name (vl[i])) != DC_SCRATCH)
287 msg (SW, _("No variables to display."));
292 sort (vl, n, sizeof *vl, compare_var_ptrs_by_name, NULL);
294 display_variables (vl, n, as);
299 return lex_end_of_command (lexer);
303 display_macros (void)
306 tab_output_text (TAB_LEFT, _("Macros not supported."));
310 display_documents (const struct dictionary *dict)
312 const char *documents = dict_get_documents (dict);
315 if (documents == NULL)
316 tab_output_text (TAB_LEFT, _("The active file dictionary does not "
317 "contain any documents."));
320 size_t n_lines = strlen (documents) / 80;
324 tab_output_text (TAB_LEFT | TAT_TITLE,
325 _("Documents in the active file:"));
328 for (i = 0; i < n_lines; i++)
332 memcpy (buf, &documents[i * 80], 80);
333 while ((isspace ((unsigned char) buf[len]) || buf[len] == 0)
337 tab_output_text (TAB_LEFT | TAB_FIX | TAT_NOWRAP, buf);
344 /* Sets the widths of all the columns and heights of all the rows in
345 table T for driver D. */
347 variables_dim (struct tab_table *t, struct outp_driver *d)
352 t->w[0] = tab_natural_width (t, d, 0);
353 if (_as == AS_DICTIONARY || _as == AS_VARIABLES || _as == AS_LABELS)
355 t->w[1] = MAX (tab_natural_width (t, d, 1), d->prop_em_width * 5);
356 t->w[2] = MAX (tab_natural_width (t, d, 2), d->prop_em_width * 35);
361 t->w[pc] = tab_natural_width (t, d, pc);
363 for (i = 0; i < t->nr; i++)
364 t->h[i] = tab_natural_height (t, d, i);
368 display_variables (struct variable **vl, size_t n, int as)
370 struct variable **vp = vl; /* Variable pointer. */
372 int nc; /* Number of columns. */
373 int nr; /* Number of rows. */
374 int pc; /* `Position column' */
375 int r; /* Current row. */
392 t = tab_create (nc, n + 5, 1);
393 tab_headers (t, 0, 0, 1, 0);
395 tab_hline (t, TAL_2, 0, nc - 1, 1);
396 tab_text (t, 0, 0, TAB_LEFT | TAT_TITLE, _("Variable"));
397 pc = (as == AS_INDEX ? 1 : 3);
399 tab_text (t, pc, 0, TAB_LEFT | TAT_TITLE, _("Position"));
400 if (as == AS_DICTIONARY || as == AS_VARIABLES)
401 tab_joint_text (t, 1, 0, 2, 0, TAB_LEFT | TAT_TITLE, _("Description"));
402 else if (as == AS_LABELS)
403 tab_joint_text (t, 1, 0, 2, 0, TAB_LEFT | TAT_TITLE, _("Label"));
404 tab_dim (t, variables_dim);
406 for (i = r = 1; i <= n; i++)
414 if (as == AS_DICTIONARY || as == AS_VARIABLES)
416 int nvl = val_labs_count (var_get_value_labels (v));
418 if (r + 10 + nvl > nr)
420 nr = MAX (nr * n / (i + 1), nr);
422 tab_realloc (t, nc, nr);
425 r = describe_variable (v, t, r, as);
427 tab_text (t, 0, r, TAB_LEFT, var_get_name (v));
430 const char *label = var_get_label (v);
431 tab_joint_text (t, 1, r, 2, r, TAB_LEFT,
432 label != NULL ? "(no label)" : label);
436 tab_text (t, pc, r, TAT_PRINTF, "%d",
437 (int) var_get_dict_index (v) + 1);
438 tab_hline (t, TAL_1, 0, nc - 1, r);
443 tab_hline (t, as == AS_NAMES ? TAL_1 : TAL_2, 0, nc - 1, 1);
446 tab_box (t, TAL_1, TAL_1, -1, -1, 0, 0, nc - 1, r - 1);
447 tab_vline (t, TAL_1, 1, 0, r - 1);
450 tab_flags (t, SOMF_NO_TITLE);
451 if (as == AS_DICTIONARY || as == AS_VARIABLES || as == AS_LABELS)
452 tab_vline (t, TAL_1, 3, 0, r - 1);
453 tab_resize (t, -1, r);
454 tab_columns (t, TAB_COL_DOWN, 1);
458 /* Puts a description of variable V into table T starting at row R.
459 The variable will be described in the format AS. Returns the next
460 row available for use in the table. */
462 describe_variable (struct variable *v, struct tab_table *t, int r, int as)
464 const struct fmt_spec *print = var_get_print_format (v);
465 const struct fmt_spec *write = var_get_write_format (v);
467 /* Put the name, var label, and position into the first row. */
468 tab_text (t, 0, r, TAB_LEFT, var_get_name (v));
469 tab_text (t, 3, r, TAT_PRINTF, "%d", (int) var_get_dict_index (v) + 1);
471 if (as == AS_DICTIONARY && var_has_label (v))
473 tab_joint_text (t, 1, r, 2, r, TAB_LEFT, var_get_label (v));
477 /* Print/write format, or print and write formats. */
478 if (fmt_equal (print, write))
480 char str[FMT_STRING_LEN_MAX + 1];
481 tab_joint_text (t, 1, r, 2, r, TAB_LEFT | TAT_PRINTF, _("Format: %s"),
482 fmt_to_string (print, str));
487 char str[FMT_STRING_LEN_MAX + 1];
488 tab_joint_text (t, 1, r, 2, r, TAB_LEFT | TAT_PRINTF,
489 _("Print Format: %s"), fmt_to_string (print, str));
491 tab_joint_text (t, 1, r, 2, r, TAB_LEFT | TAT_PRINTF,
492 _("Write Format: %s"), fmt_to_string (write, str));
496 /* Missing values if any. */
497 if (var_has_missing_values (v))
501 struct missing_values mv;
504 cp = stpcpy (buf, _("Missing Values: "));
506 mv_copy (&mv, var_get_missing_values (v));
507 if (mv_has_range (&mv))
510 mv_pop_range (&mv, &x, &y);
512 cp += sprintf (cp, "LOWEST THRU %g", y);
513 else if (y == HIGHEST)
514 cp += sprintf (cp, "%g THRU HIGHEST", x);
516 cp += sprintf (cp, "%g THRU %g", x, y);
519 while (mv_has_value (&mv))
522 mv_pop_value (&mv, &value);
524 cp += sprintf (cp, "; ");
525 if (var_is_numeric (v))
526 cp += sprintf (cp, "%g", value.f);
530 memcpy (cp, value.s, var_get_width (v));
531 cp += var_get_width (v);
537 tab_joint_text (t, 1, r, 2, r, TAB_LEFT, buf);
542 if (as == AS_DICTIONARY && var_has_value_labels (v))
544 const struct val_labs *val_labs = var_get_value_labels (v);
545 struct val_labs_iterator *i;
550 tab_text (t, 1, r, TAB_LEFT, _("Value"));
551 tab_text (t, 2, r, TAB_LEFT, _("Label"));
555 tab_hline (t, TAL_1, 1, 2, r);
556 for (vl = val_labs_first_sorted (val_labs, &i); vl != NULL;
557 vl = val_labs_next (val_labs, &i))
561 if (var_is_alpha (v))
563 memcpy (buf, vl->value.s, var_get_width (v));
564 buf[var_get_width (v)] = 0;
567 sprintf (buf, "%g", vl->value.f);
569 tab_text (t, 1, r, TAB_NONE, buf);
570 tab_text (t, 2, r, TAB_LEFT, vl->label);
574 tab_vline (t, TAL_1, 2, orig_r, r - 1);
577 /* Draw a line below the last row of information on this variable. */
578 tab_hline (t, TAL_1, 0, 3, r);
583 /* Display a list of vectors. If SORTED is nonzero then they are
584 sorted alphabetically. */
586 display_vectors (const struct dictionary *dict, int sorted)
588 const struct vector **vl;
593 nvec = dict_get_vector_cnt (dict);
596 msg (SW, _("No vectors defined."));
600 vl = xnmalloc (nvec, sizeof *vl);
601 for (i = 0; i < nvec; i++)
602 vl[i] = dict_get_vector (dict, i);
604 qsort (vl, nvec, sizeof *vl, compare_vector_ptrs_by_name);
606 t = tab_create (1, nvec + 1, 0);
607 tab_headers (t, 0, 0, 1, 0);
608 tab_columns (t, TAB_COL_DOWN, 1);
609 tab_dim (t, tab_natural_dimensions);
610 tab_hline (t, TAL_1, 0, 0, 1);
611 tab_text (t, 0, 0, TAT_TITLE | TAB_LEFT, _("Vector"));
612 tab_flags (t, SOMF_NO_TITLE);
613 for (i = 0; i < nvec; i++)
614 tab_text (t, 0, i + 1, TAB_LEFT, vector_get_name (vl[i]));