X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fdata%2Fsys-file-reader.c;h=8d973e4dbc103d09860e4c14cc12a006fda0bfcd;hb=e624e2da6ea68d22e6d4fba4eaa96d37d07a6730;hp=705fb015639a00ac74efab8ccb39d3119148624c;hpb=8cc788667db16517f96ba15979da3e3b9638dd3b;p=pspp-builds.git

diff --git a/src/data/sys-file-reader.c b/src/data/sys-file-reader.c
index 705fb015..8d973e4d 100644
--- a/src/data/sys-file-reader.c
+++ b/src/data/sys-file-reader.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 1997-9, 2000, 2006, 2007 Free Software Foundation, Inc.
+   Copyright (C) 1997-9, 2000, 2006, 2007, 2009 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
@@ -86,6 +86,7 @@ struct sfm_reader
     double bias;		/* Compression bias, usually 100.0. */
     uint8_t opcodes[8];         /* Current block of opcodes. */
     size_t opcode_idx;          /* Next opcode to interpret, 8 if none left. */
+    bool corruption_warning;    /* Warned about possible corruption? */
   };
 
 static const struct casereader_class sys_file_casereader_class;
@@ -192,6 +193,7 @@ sfm_open_reader (struct file_handle *fh, struct dictionary **dict,
   r->oct_cnt = 0;
   r->has_long_var_names = false;
   r->opcode_idx = sizeof r->opcodes;
+  r->corruption_warning = false;
 
   /* TRANSLATORS: this fragment will be interpolated into
      messages in fh_lock() that identify types of files. */
@@ -425,10 +427,21 @@ 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 (%g) is not the usual "
-                     "value of 100, or system file uses unrecognized "
-                     "floating-point format."),
-                r->bias);
+      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
@@ -729,7 +742,11 @@ read_extension_record (struct sfm_reader *r, struct dictionary *dict,
       break;
 
     case 7:
-      /* Unknown purpose. */
+      /* Used by the MRSETS command. */
+      break;
+
+    case 8:
+      /* Used by the SPSS Data Entry software. */
       break;
 
     case 11:
@@ -766,7 +783,8 @@ read_extension_record (struct sfm_reader *r, struct dictionary *dict,
       break;
 
     default:
-      sys_warn (r, _("Unrecognized record type 7, subtype %d."), subtype);
+      sys_warn (r, _("Unrecognized record type 7, subtype %d.  Please send a copy of this file, and the syntax which created it to %s"),
+		subtype, PACKAGE_BUGREPORT);
       break;
     }
 
@@ -1358,7 +1376,14 @@ read_compressed_number (struct sfm_reader *r, double *d)
       break;
 
     case 254:
-      sys_error (r, _("Compressed data is corrupt."));
+      float_convert (r->float_format, "        ", FLOAT_NATIVE_DOUBLE, d);
+      if (!r->corruption_warning)
+        {
+          r->corruption_warning = true;
+          sys_warn (r, _("Possible compressed data corruption: "
+                         "compressed spaces appear in numeric field."));
+        }
+      break;
 
     case 255:
       *d = SYSMIS;
@@ -1379,7 +1404,8 @@ read_compressed_number (struct sfm_reader *r, double *d)
 static bool
 read_compressed_string (struct sfm_reader *r, char *dst)
 {
-  switch (read_opcode (r))
+  int opcode = read_opcode (r);
+  switch (opcode)
     {
     case -1:
     case 252:
@@ -1394,7 +1420,25 @@ read_compressed_string (struct sfm_reader *r, char *dst)
       break;
 
     default:
-      sys_error (r, _("Compressed data is corrupt."));
+      {
+        double value = opcode - r->bias;
+        float_convert (FLOAT_NATIVE_DOUBLE, &value, r->float_format, dst);
+        if (value == 0.0)
+          {
+            /* This has actually been seen "in the wild".  The submitter of the
+               file that showed that the contents decoded as spaces, but they
+               were at the end of the field so it's possible that the null
+               bytes just acted as null terminators. */
+          }
+        else if (!r->corruption_warning)
+          {
+            r->corruption_warning = true;
+            sys_warn (r, _("Possible compressed data corruption: "
+                           "string contains compressed integer (opcode %d)"),
+                      opcode);
+          }
+      }
+      break;
     }
 
   return true;