Hi,

A frequently seen issue with importing SPSS data files, is that R does
not import the 'long variable names'.
I built a patch on the R-project's foreign module, in order to import
the 'long variable names' from SPSS (record 7, subtype 13).
To complete the job, I had to expand the "struct variable" definition
to have 64 +1 charachters. I'm not aware of side effects.
The sfm-read.c code works fine.
I didn't test a variety of platforms, as I don't have an idea of what is
regarded as sufficient testing. Anyway, I don't expect major troubles there
(no byteswapping problems, no 32<->64 bit issues) as it's mainly character 
processing.
The patch is relative to the foreign directory. It was created
against the trunk of R-project yesterday.

We would appreciate that you import such patch into the main tree.

Kind regards,

Kurt Van Dijck (C programmer) & Ilse Laurijssen (R user)
Belgium

Index: src/sfm-read.c
===================================================================
--- src/sfm-read.c      (revision 5168)
+++ src/sfm-read.c      (working copy)
@@ -188,6 +188,8 @@
 static int read_variables (struct file_handle * h, struct variable *** 
var_by_index);
 static int read_machine_int32_info (struct file_handle * h, int size, int 
count, int *encoding);
 static int read_machine_flt64_info (struct file_handle * h, int size, int 
count);
+static int read_long_var_names (struct file_handle * h, struct dictionary *
+               , unsigned long size, unsigned int count);
 static int read_documents (struct file_handle * h);

 /* Displays the message X with corrupt_msg, then jumps to the lossage
@@ -418,11 +420,15 @@
                break;

              case 7: /* Multiple-response sets (later versions of SPSS). */
-             case 13:  /* long variable names. PSPP now has code for these
-                          that could be ported if someone is interested. */
                skip = 1;
                break;

+             case 13:  /* long variable names. PSPP now has code for these
+                          that could be ported if someone is interested. */
+               if (!read_long_var_names(h, ext->dict, data.size, data.count))
+                 goto lossage;
+               break;
+
              case 16: /* See 
http://www.nabble.com/problem-loading-SPSS-15.0-save-files-t2726500.html */
                skip = 1;
                break;
@@ -584,14 +590,72 @@
   return 0;
 }

+/* Read record type 7, subtype 13.
+ * long variable names
+ */
 static int
+read_long_var_names (struct file_handle * h, struct dictionary * dict
+               , unsigned long size, unsigned int count)
+{
+  char * data;
+  unsigned int j;
+  struct variable ** lp;
+  struct variable ** end;
+  char * p;
+  char * endp;
+  char * val;
+  if ((1 != size)||(0 == count)) {
+    warning("%s: strange record info seen, size=%u, count=%u"
+      ", ignoring long variable names"
+      , h->fn, size, count);
+    return 0;
+  }
+  size *= count;
+  data = Calloc (size +1, char);
+  bufread(h, data, size, 0);
+  /* parse */
+  end = &dict->var[dict->nvar];
+  p = data;
+  do {
+    if (0 != (endp = strchr(p, '\t')))
+      *endp = 0; /* put null terminator */
+    if (0 == (val = strchr(p, '='))) {
+      warning("%s: no long variable name for variable '%s'", h->fn, p);
+    } else {
+      *val = 0;
+      ++val;
+      /* now, p is key, val is long name */
+      for (lp = dict->var; lp < end; ++lp) {
+        if (!strcmp(lp[0]->name, p)) {
+          strncpy(lp[0]->name, val, sizeof(lp[0]->name));
+          break;
+        }
+      }
+      if (lp >= end) {
+        warning("%s: long variable name mapping '%s' to '%s'"
+        "for variable which does not exist"
+        , h->fn, p, val);
+      }
+    }
+    p = &endp[1]; /* put to next */
+  } while (endp);
+
+  free(data);
+  return 1;
+
+lossage:
+  free(data);
+  return 0;
+}
+
+static int
 read_header (struct file_handle * h, struct sfm_read_info * inf)
 {
   struct sfm_fhuser_ext *ext = h->ext;      /* File extension strcut. */
   struct sysfile_header hdr;           /* Disk buffer. */
   struct dictionary *dict;             /* File dictionary. */
   char prod_name[sizeof hdr.prod_name + 1];    /* Buffer for product name. */
-  int skip_amt = 0;                    /* Amount of product name to omit. */
+  int skip_amt = 0;                    /* Amount of product name to omit. */
   int i;

   /* Create the dictionary. */
@@ -1495,7 +1559,7 @@
 /* Reads one case from system file H into the value array PERM
    according to the instructions given in associated dictionary DICT,
    which must have the get.* elements appropriately set.  Returns
-   nonzero only if successful.  */
+   nonzero only if successful. */
 int
 sfm_read_case (struct file_handle * h, union value * perm, struct dictionary * 
dict)
 {
Index: src/var.h.in
===================================================================
--- src/var.h.in        (revision 5168)
+++ src/var.h.in        (working copy)
@@ -41,6 +41,10 @@
 #error MAX_SHORT_STRING must be less than 8.
 #endif

+/* VAR_NAME_LEN: the length of a variable.
+ * SPSS supports names of 64 long
+ */
+#define VAR_NAME_LEN 64
 /* Special values. */
 #define SYSMIS (-DBL_MAX)
 #define LOWEST second_lowest_double_val()
@@ -228,7 +232,7 @@
 /* MODIFY VARS private data. */
 struct modify_vars_proc
   {
-    char new_name[9];          /* Variable's new name. */
+    char new_name[VAR_NAME_LEN +1];            /* Variable's new name. */
     int drop_this_var;         /* 0=keep this var, 1=drop this var. */
     struct variable *next;     /* Next in linked list. */
   };
@@ -302,7 +306,7 @@
 struct variable
   {
     /* Required by parse_variables() to be in this order.  */
-    char name[9];              /* As a string. */
+    char name[VAR_NAME_LEN +1];        /* As a string. */
     int index;                 /* Index into its dictionary's var[]. */
     int type;                  /* NUMERIC or ALPHA. */
     int foo;                   /* Used for temporary storage. */
@@ -373,9 +377,9 @@

     int weight_index;          /* `value' index of $WEIGHT, or -1 if none.
                                   Call update_weighting() before using! */
-    char weight_var[9];                /* Name of WEIGHT variable. */
+    char weight_var[VAR_NAME_LEN];/* Name of WEIGHT variable. */

-    char filter_var[9];                /* Name of FILTER variable. */
+    char filter_var[VAR_NAME_LEN];/* Name of FILTER variable. */
     /* Do not make another field the last field! or see
        temporary.c:restore_dictionary() before doing so! */
   };

______________________________________________
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel

Reply via email to