X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fdata%2Fsys-file-reader.c;h=b0a41a83573b0e986fb35bfb3bce46379282662f;hb=b5c82cc9aabe7e641011130240ae1b2e84348e23;hp=141fd881a1ea2323d2a999089e6594265bd88015;hpb=ddb1eb19cb9b78b1163a85d73dd05e8798a8037d;p=pspp-builds.git

diff --git a/src/data/sys-file-reader.c b/src/data/sys-file-reader.c
index 141fd881..b0a41a83 100644
--- a/src/data/sys-file-reader.c
+++ b/src/data/sys-file-reader.c
@@ -202,8 +202,17 @@ recode_strings (struct dictionary *dict)
     {
       /* Convert the long variable name */
       struct variable *var = dict_get_var (dict, i);
-      char *utf8_name = recode_string (UTF8, enc, var_get_name (var), -1);
-      dict_rename_var (dict, var, utf8_name);
+      const char *native_name = var_get_name (var);
+      char *utf8_name = recode_string (UTF8, enc, native_name, -1);
+      if ( 0 != strcmp (utf8_name, native_name))
+	{
+	  if ( NULL == dict_lookup_var (dict, utf8_name))
+	    dict_rename_var (dict, var, utf8_name);
+	  else
+	    msg (MW,
+	     _("Recoded variable name duplicates an existing `%s' within system file."), utf8_name);
+    }
+
       free (utf8_name);
 
       /* Convert the variable label */
@@ -496,9 +505,21 @@ read_header (struct sfm_reader *r, struct dictionary *dict,
   read_bytes (r, raw_bias, sizeof raw_bias);
   if (float_identify (100.0, raw_bias, sizeof raw_bias, &r->float_format) == 0)
     {
-      sys_warn (r, _("Compression bias is not the usual "
-                     "value of 100, or system file uses unrecognized "
-                     "floating-point format."));
+      uint8_t zero_bias[8] = { 0, 0, 0, 0, 0, 0, 0, 0 };
+
+      if (memcmp (raw_bias, zero_bias, 8))
+        sys_warn (r, _("Compression bias is not the usual "
+                       "value of 100, or system file uses unrecognized "
+                       "floating-point format."));
+      else
+        {
+          /* Some software is known to write all-zeros to this
+             field.  Such software also writes floating-point
+             numbers in the format that we expect by default
+             (it seems that all software most likely does, in
+             reality), so don't warn in this case. */
+        }
+
       if (r->integer_format == INTEGER_MSB_FIRST)
         r->float_format = FLOAT_IEEE_DOUBLE_BE;
       else
@@ -568,7 +589,7 @@ read_variable_record (struct sfm_reader *r, struct dictionary *dict,
 
   /* Create variable. */
   if (width < 0 || width > 255)
-    sys_error (r, _("Bad variable width %d."), width);
+    sys_error (r, _("Bad width %d for variable %s."), width, name);
   var = dict_create_var (dict, name, width);
   if (var == NULL)
     sys_error (r,
@@ -632,7 +653,7 @@ read_variable_record (struct sfm_reader *r, struct dictionary *dict,
           value_set_missing (&value, mv_width);
           for (i = 0; i < missing_value_code; i++)
             {
-              char *s = value_str_rw (&value, mv_width);
+              uint8_t *s = value_str_rw (&value, mv_width);
               read_bytes (r, s, 8);
               mv_add_str (&mv, s);
             }
@@ -972,11 +993,16 @@ read_machine_float_info (struct sfm_reader *r, size_t size, size_t count)
                size, count);
 
   if (sysmis != SYSMIS)
-    sys_warn (r, _("File specifies unexpected value %g as SYSMIS."), sysmis);
+    sys_warn (r, _("File specifies unexpected value %g as %s."),
+              sysmis, "SYSMIS");
+
   if (highest != HIGHEST)
-    sys_warn (r, _("File specifies unexpected value %g as HIGHEST."), highest);
+    sys_warn (r, _("File specifies unexpected value %g as %s."),
+              highest, "HIGHEST");
+
   if (lowest != LOWEST)
-    sys_warn (r, _("File specifies unexpected value %g as LOWEST."), lowest);
+    sys_warn (r, _("File specifies unexpected value %g as %s."),
+              lowest, "LOWEST");
 }
 
 /* Read record type 7, subtype 11, which specifies how variables
@@ -1183,7 +1209,7 @@ read_value_labels (struct sfm_reader *r,
 
   struct label
     {
-      char raw_value[8];        /* Value as uninterpreted bytes. */
+      uint8_t raw_value[8];        /* Value as uninterpreted bytes. */
       union value value;        /* Value. */
       char *label;              /* Null-terminated label string. */
     };
@@ -1281,7 +1307,7 @@ read_value_labels (struct sfm_reader *r,
 
       value_init_pool (subpool, &label->value, max_width);
       if (var_is_alpha (var[0]))
-        buf_copy_rpad (value_str_rw (&label->value, max_width), max_width,
+        u8_buf_copy_rpad (value_str_rw (&label->value, max_width), max_width,
                        label->raw_value, sizeof label->raw_value, ' ');
       else
         label->value.f = float_get_double (r->float_format, label->raw_value);
@@ -1461,7 +1487,7 @@ read_long_string_value_labels (struct sfm_reader *r,
           /* Read value. */
           value_length = read_int (r);
           if (value_length == width)
-            read_string (r, value_str_rw (&value, width), width + 1);
+            read_bytes (r, value_str_rw (&value, width), width);
           else
             {
               sys_warn (r, _("Ignoring long string value %zu for variable %s, "
@@ -1518,11 +1544,11 @@ static void partial_record (struct sfm_reader *r)
 static void read_error (struct casereader *, const struct sfm_reader *);
 
 static bool read_case_number (struct sfm_reader *, double *);
-static bool read_case_string (struct sfm_reader *, char *, size_t);
+static bool read_case_string (struct sfm_reader *, uint8_t *, size_t);
 static int read_opcode (struct sfm_reader *);
 static bool read_compressed_number (struct sfm_reader *, double *);
-static bool read_compressed_string (struct sfm_reader *, char *);
-static bool read_whole_strings (struct sfm_reader *, char *, size_t);
+static bool read_compressed_string (struct sfm_reader *, uint8_t *);
+static bool read_whole_strings (struct sfm_reader *, uint8_t *, size_t);
 static bool skip_whole_strings (struct sfm_reader *, size_t);
 
 /* Reads and returns one case from READER's file.  Returns a null
@@ -1557,7 +1583,7 @@ sys_file_casereader_read (struct casereader *reader, void *r_)
         }
       else
         {
-          char *s = value_str_rw (v, sv->var_width);
+          uint8_t *s = value_str_rw (v, sv->var_width);
           if (!read_case_string (r, s + sv->offset, sv->segment_width))
             goto eof;
           if (!skip_whole_strings (r, ROUND_DOWN (sv->padding, 8)))
@@ -1619,7 +1645,7 @@ read_case_number (struct sfm_reader *r, double *d)
    Returns true if successful, false if end of file is
    reached immediately. */
 static bool
-read_case_string (struct sfm_reader *r, char *s, size_t length)
+read_case_string (struct sfm_reader *r, uint8_t *s, size_t length)
 {
   size_t whole = ROUND_DOWN (length, 8);
   size_t partial = length % 8;
@@ -1632,7 +1658,7 @@ read_case_string (struct sfm_reader *r, char *s, size_t length)
 
   if (partial)
     {
-      char bounce[8];
+      uint8_t bounce[8];
       if (!read_whole_strings (r, bounce, sizeof bounce))
         {
           if (whole)
@@ -1703,7 +1729,7 @@ read_compressed_number (struct sfm_reader *r, double *d)
    Returns true if successful, false if end of file is
    reached immediately. */
 static bool
-read_compressed_string (struct sfm_reader *r, char *dst)
+read_compressed_string (struct sfm_reader *r, uint8_t *dst)
 {
   switch (read_opcode (r))
     {
@@ -1732,7 +1758,7 @@ read_compressed_string (struct sfm_reader *r, char *dst)
    Returns true if successful, false if end of file is
    reached immediately. */
 static bool
-read_whole_strings (struct sfm_reader *r, char *s, size_t length)
+read_whole_strings (struct sfm_reader *r, uint8_t *s, size_t length)
 {
   assert (length % 8 == 0);
   if (!r->compressed)
@@ -1760,7 +1786,7 @@ read_whole_strings (struct sfm_reader *r, char *s, size_t length)
 static bool
 skip_whole_strings (struct sfm_reader *r, size_t length)
 {
-  char buffer[1024];
+  uint8_t buffer[1024];
   assert (length < sizeof buffer);
   return read_whole_strings (r, buffer, length);
 }