X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fdata%2Fsys-file-writer.c;h=1a65e3c067efc5688d912c0184d3e73be1fa59ed;hb=50f245ab3b7e42ae79ea4076ad7a2bbb97841cc6;hp=292ec9c5d053ba7603b1db27d26178e4eeb6335d;hpb=14aac9fe7a7efbb6c9bded2ed5969a643cb76645;p=pspp-builds.git

diff --git a/src/data/sys-file-writer.c b/src/data/sys-file-writer.c
index 292ec9c5..1a65e3c0 100644
--- a/src/data/sys-file-writer.c
+++ b/src/data/sys-file-writer.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 1997-9, 2000, 2006, 2007, 2009 Free Software Foundation, Inc.
+   Copyright (C) 1997-9, 2000, 2006, 2007, 2009, 2010, 2011 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
@@ -16,8 +16,8 @@
 
 #include <config.h>
 
-#include "sys-file-writer.h"
-#include "sys-file-private.h"
+#include "data/sys-file-writer.h"
+#include "data/sys-file-private.h"
 
 #include <ctype.h>
 #include <errno.h>
@@ -26,31 +26,33 @@
 #include <sys/stat.h>
 #include <time.h>
 
-#include <libpspp/float-format.h>
-#include <libpspp/integer-format.h>
-#include <libpspp/message.h>
-#include <libpspp/misc.h>
-#include <libpspp/str.h>
-#include <libpspp/version.h>
-
-#include <data/attributes.h>
-#include <data/case.h>
-#include <data/casewriter-provider.h>
-#include <data/casewriter.h>
-#include <data/dictionary.h>
-#include <data/file-handle-def.h>
-#include <data/file-name.h>
-#include <data/format.h>
-#include <data/make-file.h>
-#include <data/missing-values.h>
-#include <data/settings.h>
-#include <data/short-names.h>
-#include <data/value-labels.h>
-#include <data/variable.h>
-
-#include "minmax.h"
-#include "unlocked-io.h"
-#include "xalloc.h"
+#include "data/attributes.h"
+#include "data/case.h"
+#include "data/casewriter-provider.h"
+#include "data/casewriter.h"
+#include "data/dictionary.h"
+#include "data/file-handle-def.h"
+#include "data/file-name.h"
+#include "data/format.h"
+#include "data/make-file.h"
+#include "data/missing-values.h"
+#include "data/mrset.h"
+#include "data/settings.h"
+#include "data/short-names.h"
+#include "data/value-labels.h"
+#include "data/variable.h"
+#include "libpspp/float-format.h"
+#include "libpspp/i18n.h"
+#include "libpspp/integer-format.h"
+#include "libpspp/message.h"
+#include "libpspp/misc.h"
+#include "libpspp/str.h"
+#include "libpspp/version.h"
+
+#include "gl/xmemdup0.h"
+#include "gl/minmax.h"
+#include "gl/unlocked-io.h"
+#include "gl/xalloc.h"
 
 #include "gettext.h"
 #define _(msgid) gettext (msgid)
@@ -95,8 +97,8 @@ static const struct casewriter_class sys_file_casewriter_class;
 
 static void write_header (struct sfm_writer *, const struct dictionary *);
 static void write_variable (struct sfm_writer *, const struct variable *);
-static void write_value_labels (struct sfm_writer *,
-                                struct variable *, int idx);
+static void write_value_labels (struct sfm_writer *, struct variable *,
+                                int idx);
 static void write_integer_info_record (struct sfm_writer *);
 static void write_float_info_record (struct sfm_writer *);
 
@@ -109,6 +111,11 @@ static void write_encoding_record (struct sfm_writer *w,
 static void write_vls_length_table (struct sfm_writer *w,
 			      const struct dictionary *dict);
 
+static void write_long_string_value_labels (struct sfm_writer *,
+                                            const struct dictionary *);
+
+static void write_mrsets (struct sfm_writer *, const struct dictionary *,
+                          bool pre_v14);
 
 static void write_variable_display_parameters (struct sfm_writer *w,
                                                const struct dictionary *dict);
@@ -137,8 +144,8 @@ static void put_cmp_opcode (struct sfm_writer *, uint8_t);
 static void put_cmp_number (struct sfm_writer *, double);
 static void put_cmp_string (struct sfm_writer *, const void *, size_t);
 
-bool write_error (const struct sfm_writer *);
-bool close_writer (struct sfm_writer *);
+static bool write_error (const struct sfm_writer *);
+static bool close_writer (struct sfm_writer *);
 
 /* Returns default options for writing a system file. */
 struct sfm_write_options
@@ -152,8 +159,7 @@ sfm_writer_default_options (void)
 }
 
 /* Opens the system file designated by file handle FH for writing
-   cases from dictionary D according to the given OPTS.  If
-   COMPRESS is nonzero, the system file will be compressed.
+   cases from dictionary D according to the given OPTS.
 
    No reference to D is retained, so it may be modified or
    destroyed at will after this function returns.  D is not
@@ -202,14 +208,14 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d,
     goto error;
 
   /* Create the file on disk. */
-  mode = S_IRUSR | S_IRGRP | S_IROTH;
+  mode = 0444;
   if (opts.create_writeable)
-    mode |= S_IWUSR | S_IWGRP | S_IWOTH;
+    mode |= 0222;
   w->rf = replace_file_start (fh_get_file_name (fh), "wb", mode,
                               &w->file, NULL);
   if (w->rf == NULL)
     {
-      msg (ME, _("Error opening \"%s\" for writing as a system file: %s."),
+      msg (ME, _("Error opening `%s' for writing as a system file: %s."),
            fh_get_file_name (fh), strerror (errno));
       goto error;
     }
@@ -238,6 +244,8 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d,
   write_integer_info_record (w);
   write_float_info_record (w);
 
+  write_mrsets (w, d, true);
+
   write_variable_display_parameters (w, d);
 
   if (opts.version >= 3)
@@ -245,10 +253,14 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d,
 
   write_vls_length_table (w, d);
 
+  write_long_string_value_labels (w, d);
+
   if (attrset_count (dict_get_attributes (d)))
     write_data_file_attributes (w, d);
   write_variable_attributes (w, d);
 
+  write_mrsets (w, d, false);
+
   write_encoding_record (w, d);
 
   /* Write end-of-headers record. */
@@ -256,13 +268,9 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d,
   write_int (w, 0);
 
   if (write_error (w))
-    {
-      close_writer (w);
-      return NULL;
-    }
+    goto error;
 
-  return casewriter_create (dict_get_next_value_idx (d),
-                            &sys_file_casewriter_class, w);
+  return casewriter_create (dict_get_proto (d), &sys_file_casewriter_class, w);
 
 error:
   close_writer (w);
@@ -422,7 +430,7 @@ write_variable (struct sfm_writer *w, const struct variable *v)
   int width = var_get_width (v);
   int segment_cnt = sfm_width_to_segments (width);
   int seg0_width = sfm_segment_alloc_width (width, 0);
-  const struct missing_values *mv = var_get_missing_values (v);
+  struct missing_values mv;
   int i;
 
   /* Record type. */
@@ -437,7 +445,13 @@ write_variable (struct sfm_writer *w, const struct variable *v)
   /* Number of missing values.  If there is a range, then the
      range counts as 2 missing values and causes the number to be
      negated. */
-  write_int (w, mv_has_range (mv) ? -2 - mv_n_values (mv) : mv_n_values (mv));
+  mv_copy (&mv, var_get_missing_values (v));
+  if (mv_get_width (&mv) > 8)
+    mv_resize (&mv, 8);
+  if (mv_has_range (&mv))
+    write_int (w, -2 - mv_n_values (&mv));
+  else
+    write_int (w, mv_n_values (&mv));
 
   /* Print and write formats. */
   write_format (w, *var_get_print_format (v), seg0_width);
@@ -451,26 +465,24 @@ write_variable (struct sfm_writer *w, const struct variable *v)
   /* Value label. */
   if (var_has_label (v))
     {
-      const char *label = var_get_label (v);
-      size_t padded_len = ROUND_UP (MIN (strlen (label), 255), 4);
-      write_int (w, padded_len);
+      char *label = recode_string (var_get_encoding (v), UTF8, var_get_label (v), -1);
+      size_t label_len = MIN (strlen (label), 255);
+      size_t padded_len = ROUND_UP (label_len, 4);
+      write_int (w, label_len);
       write_string (w, label, padded_len);
+      free (label);
     }
 
   /* Write the missing values, if any, range first. */
-  if (mv_has_range (mv))
+  if (mv_has_range (&mv))
     {
       double x, y;
-      mv_get_range (mv, &x, &y);
+      mv_get_range (&mv, &x, &y);
       write_float (w, x);
       write_float (w, y);
     }
-  for (i = 0; i < mv_n_values (mv); i++)
-    {
-      union value value;
-      mv_get_value (mv, &value, i);
-      write_value (w, &value, seg0_width);
-    }
+  for (i = 0; i < mv_n_values (&mv); i++)
+    write_value (w, mv_get_value (&mv, i), mv_get_width (&mv));
 
   write_variable_continuation_records (w, seg0_width);
 
@@ -490,34 +502,45 @@ write_variable (struct sfm_writer *w, const struct variable *v)
 
       write_variable_continuation_records (w, seg_width);
     }
+
+  mv_destroy (&mv);
 }
 
 /* Writes the value labels for variable V having system file
-   variable index IDX to system file W. */
+   variable index IDX to system file W.
+
+   Value labels for long string variables are written separately,
+   by write_long_string_value_labels. */
 static void
 write_value_labels (struct sfm_writer *w, struct variable *v, int idx)
 {
   const struct val_labs *val_labs;
-  struct val_labs_iterator *i;
-  struct val_lab *vl;
+  const struct val_lab **labels;
+  size_t n_labels;
+  size_t i;
 
   val_labs = var_get_value_labels (v);
-  if (val_labs == NULL)
+  n_labels = val_labs_count (val_labs);
+  if (n_labels == 0 || var_get_width (v) > 8)
     return;
 
   /* Value label record. */
   write_int (w, 3);             /* Record type. */
   write_int (w, val_labs_count (val_labs));
-  for (vl = val_labs_first_sorted (val_labs, &i); vl != NULL;
-       vl = val_labs_next (val_labs, &i))
+  labels = val_labs_sorted (val_labs);
+  for (i = 0; i < n_labels; i++)
     {
-      uint8_t len = MIN (strlen (vl->label), 255);
+      const struct val_lab *vl = labels[i];
+      char *label = recode_string (var_get_encoding (v), UTF8, val_lab_get_label (vl), -1);
+      uint8_t len = MIN (strlen (label), 255);
 
-      write_value (w, &vl->value, var_get_width (v));
+      write_value (w, val_lab_get_value (vl), var_get_width (v));
       write_bytes (w, &len, 1);
-      write_bytes (w, vl->label, len);
+      write_bytes (w, label, len);
       write_zeros (w, REM_RND_UP (len + 1, 8));
+      free (label);
     }
+  free (labels);
 
   /* Value label variable record. */
   write_int (w, 4);             /* Record type. */
@@ -549,10 +572,10 @@ put_attrset (struct string *string, const struct attrset *attrs)
       size_t j;
 
       ds_put_cstr (string, attribute_get_name (attr));
-      ds_put_char (string, '(');
+      ds_put_byte (string, '(');
       for (j = 0; j < n_values; j++) 
         ds_put_format (string, "'%s'\n", attribute_get_value (attr, j));
-      ds_put_char (string, ')');
+      ds_put_byte (string, ')');
     }
 }
 
@@ -592,7 +615,7 @@ write_variable_attributes (struct sfm_writer *w, const struct dictionary *d)
       if (attrset_count (attrs)) 
         {
           if (n_attrsets++)
-            ds_put_char (&s, '/');
+            ds_put_byte (&s, '/');
           ds_put_format (&s, "%s:", var_get_short_name (v, 0));
           put_attrset (&s, attrs);
         }
@@ -602,6 +625,64 @@ write_variable_attributes (struct sfm_writer *w, const struct dictionary *d)
   ds_destroy (&s);
 }
 
+/* Write multiple response sets.  If PRE_V14 is true, writes sets supported by
+   SPSS before release 14, otherwise writes sets supported only by later
+   versions. */
+static void
+write_mrsets (struct sfm_writer *w, const struct dictionary *dict,
+              bool pre_v14)
+{
+  struct string s = DS_EMPTY_INITIALIZER;
+  size_t n_mrsets;
+  size_t i;
+
+  n_mrsets = dict_get_n_mrsets (dict);
+  if (n_mrsets == 0)
+    return;
+
+  for (i = 0; i < n_mrsets; i++)
+    {
+      const struct mrset *mrset = dict_get_mrset (dict, i);
+      const char *label;
+      size_t j;
+
+      if ((mrset->type != MRSET_MD || mrset->cat_source != MRSET_COUNTEDVALUES)
+          != pre_v14)
+        continue;
+
+      ds_put_format (&s, "%s=", mrset->name);
+      if (mrset->type == MRSET_MD)
+        {
+          char *counted;
+
+          if (mrset->cat_source == MRSET_COUNTEDVALUES)
+            ds_put_format (&s, "E %d ", mrset->label_from_var_label ? 11 : 1);
+          else
+            ds_put_byte (&s, 'D');
+
+          if (mrset->width == 0)
+            counted = xasprintf ("%.0f", mrset->counted.f);
+          else
+            counted = xmemdup0 (value_str (&mrset->counted, mrset->width),
+                                mrset->width);
+          ds_put_format (&s, "%zu %s", strlen (counted), counted);
+          free (counted);
+        }
+      else
+        ds_put_byte (&s, 'C');
+      ds_put_byte (&s, ' ');
+
+      label = mrset->label && !mrset->label_from_var_label ? mrset->label : "";
+      ds_put_format (&s, "%zu %s", strlen (label), label);
+
+      for (j = 0; j < mrset->n_vars; j++)
+        ds_put_format (&s, " %s", var_get_short_name (mrset->vars[j], 0));
+      ds_put_byte (&s, '\n');
+    }
+  write_attribute_record (w, &s, pre_v14 ? 7 : 19);
+  ds_destroy (&s);
+}
+
 /* Write the alignment, width and scale values. */
 static void
 write_variable_display_parameters (struct sfm_writer *w,
@@ -666,6 +747,71 @@ write_vls_length_table (struct sfm_writer *w,
 }
 
 
+static void
+write_long_string_value_labels (struct sfm_writer *w,
+                                const struct dictionary *dict)
+{
+  size_t n_vars = dict_get_var_cnt (dict);
+  size_t size, i;
+  off_t start UNUSED;
+
+  /* Figure out the size in advance. */
+  size = 0;
+  for (i = 0; i < n_vars; i++)
+    {
+      struct variable *var = dict_get_var (dict, i);
+      const struct val_labs *val_labs = var_get_value_labels (var);
+      int width = var_get_width (var);
+      const struct val_lab *val_lab;
+
+      if (val_labs_count (val_labs) == 0 || width < 9)
+        continue;
+
+      size += 12 + strlen (var_get_name (var));
+      for (val_lab = val_labs_first (val_labs); val_lab != NULL;
+           val_lab = val_labs_next (val_labs, val_lab))
+        size += 8 + width + strlen (val_lab_get_label (val_lab));
+    }
+  if (size == 0)
+    return;
+
+  write_int (w, 7);             /* Record type. */
+  write_int (w, 21);            /* Record subtype */
+  write_int (w, 1);             /* Data item (byte) size. */
+  write_int (w, size);          /* Number of data items. */
+
+  start = ftello (w->file);
+  for (i = 0; i < n_vars; i++)
+    {
+      struct variable *var = dict_get_var (dict, i);
+      const struct val_labs *val_labs = var_get_value_labels (var);
+      const char *var_name = var_get_name (var);
+      int width = var_get_width (var);
+      const struct val_lab *val_lab;
+
+      if (val_labs_count (val_labs) == 0 || width < 9)
+        continue;
+
+      write_int (w, strlen (var_name));
+      write_bytes (w, var_name, strlen (var_name));
+      write_int (w, width);
+      write_int (w, val_labs_count (val_labs));
+      for (val_lab = val_labs_first (val_labs); val_lab != NULL;
+           val_lab = val_labs_next (val_labs, val_lab))
+        {
+          const char *label = val_lab_get_label (val_lab);
+          size_t label_length = strlen (label);
+
+          write_int (w, width);
+          write_bytes (w, value_str (val_lab_get_value (val_lab), width),
+                       width);
+          write_int (w, label_length);
+          write_bytes (w, label, label_length);
+        }
+    }
+  assert (ftello (w->file) == start + size);
+}
+
 static void
 write_encoding_record (struct sfm_writer *w,
 		       const struct dictionary *d)
@@ -694,11 +840,13 @@ write_longvar_table (struct sfm_writer *w, const struct dictionary *dict)
   for (i = 0; i < dict_get_var_cnt (dict); i++)
     {
       struct variable *v = dict_get_var (dict, i);
+      char *longname = recode_string (dict_get_encoding (dict), UTF8, var_get_name (v), -1);
 
       if (i)
-        ds_put_char (&map, '\t');
+        ds_put_byte (&map, '\t');
       ds_put_format (&map, "%s=%s",
-                     var_get_short_name (v, 0), var_get_name (v));
+                     var_get_short_name (v, 0), longname);
+      free (longname);
     }
 
   write_int (w, 7);             /* Record type. */
@@ -795,7 +943,7 @@ sys_file_casewriter_destroy (struct casewriter *writer, void *w_)
 }
 
 /* Returns true if an I/O error has occurred on WRITER, false otherwise. */
-bool
+static bool
 write_error (const struct sfm_writer *writer)
 {
   return ferror (writer->file);
@@ -803,7 +951,7 @@ write_error (const struct sfm_writer *writer)
 
 /* Closes a system file after we're done with it.
    Returns true if successful, false if an I/O error occurred. */
-bool
+static bool
 close_writer (struct sfm_writer *w)
 {
   bool ok;
@@ -824,7 +972,7 @@ close_writer (struct sfm_writer *w)
       /* Seek back to the beginning and update the number of cases.
          This is just a courtesy to later readers, so there's no need
          to check return values or report errors. */
-      if (ok && w->case_cnt <= INT32_MAX && !fseek (w->file, 80, SEEK_SET))
+      if (ok && w->case_cnt <= INT32_MAX && !fseeko (w->file, 80, SEEK_SET))
         {
           write_int (w, w->case_cnt);
           clearerr (w->file);
@@ -834,7 +982,7 @@ close_writer (struct sfm_writer *w)
         ok = false;
 
       if (!ok)
-        msg (ME, _("An I/O error occurred writing system file \"%s\"."),
+        msg (ME, _("An I/O error occurred writing system file `%s'."),
              fh_get_file_name (w->fh));
 
       if (ok ? !replace_file_commit (w->rf) : !replace_file_abort (w->rf))
@@ -868,12 +1016,12 @@ write_case_uncompressed (struct sfm_writer *w, const struct ccase *c)
     {
       struct sfm_var *v = &w->sfm_vars[i];
 
-      if (v->width == 0)
+      if (v->var_width == 0)
         write_float (w, case_num_idx (c, v->case_index));
       else
         {
           write_bytes (w, case_str_idx (c, v->case_index) + v->offset,
-                       v->width);
+                       v->segment_width);
           write_spaces (w, v->padding);
         }
     }
@@ -889,7 +1037,7 @@ write_case_compressed (struct sfm_writer *w, const struct ccase *c)
     {
       struct sfm_var *v = &w->sfm_vars[i];
 
-      if (v->width == 0)
+      if (v->var_width == 0)
         {
           double d = case_num_idx (c, v->case_index);
           if (d == SYSMIS)
@@ -913,7 +1061,7 @@ write_case_compressed (struct sfm_writer *w, const struct ccase *c)
              multiple of 8, by ensuring that the final partial
              oct (8 byte unit) is treated as padded with spaces
              on the right. */
-          for (width = v->width; width > 0; width -= 8, offset += 8)
+          for (width = v->segment_width; width > 0; width -= 8, offset += 8)
             {
               const void *data = case_str_idx (c, v->case_index) + offset;
               int chunk_size = MIN (width, 8);
@@ -1036,7 +1184,7 @@ write_value (struct sfm_writer *w, const union value *value, int width)
     write_float (w, value->f);
   else
     {
-      write_bytes (w, value->s, width);
+      write_bytes (w, value_str (value, width), width);
       write_zeros (w, 8 - width);
     }
 }