X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=utilities%2Fpspp-dump-sav.c;h=f207d8ecbf0f3362f2daf5e4f7d9245714555c86;hb=65481c834dca537af5851fa2b7efe209f09af613;hp=307add8db3b56b339afe79f3d0e7d732c6c21236;hpb=41f83a8f1c88489e4fc458fb7661430ff91d8a61;p=pspp

diff --git a/utilities/pspp-dump-sav.c b/utilities/pspp-dump-sav.c
index 307add8db3..f207d8ecbf 100644
--- a/utilities/pspp-dump-sav.c
+++ b/utilities/pspp-dump-sav.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 2007, 2008, 2009, 2010, 2011, 2012, 2013 Free Software Foundation, Inc.
+   Copyright (C) 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014 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
@@ -18,6 +18,7 @@
 
 #include <ctype.h>
 #include <errno.h>
+#include <float.h>
 #include <getopt.h>
 #include <inttypes.h>
 #include <limits.h>
@@ -39,6 +40,13 @@
 
 #define ID_MAX_LEN 64
 
+enum compression
+  {
+    COMP_NONE,
+    COMP_SIMPLE,
+    COMP_ZLIB
+  };
+
 struct sfm_reader
   {
     const char *file_name;
@@ -52,7 +60,7 @@ struct sfm_reader
     enum integer_format integer_format;
     enum float_format float_format;
 
-    bool compressed;
+    enum compression compression;
     double bias;
   };
 
@@ -83,9 +91,12 @@ static void read_character_encoding (struct sfm_reader *r,
 				       size_t size, size_t count);
 static void read_long_string_value_labels (struct sfm_reader *r,
                                            size_t size, size_t count);
+static void read_long_string_missing_values (struct sfm_reader *r,
+                                             size_t size, size_t count);
 static void read_unknown_extension (struct sfm_reader *,
                                     size_t size, size_t count);
-static void read_compressed_data (struct sfm_reader *, int max_cases);
+static void read_simple_compressed_data (struct sfm_reader *, int max_cases);
+static void read_zlib_compressed_data (struct sfm_reader *);
 
 static struct text_record *open_text_record (
   struct sfm_reader *, size_t size);
@@ -178,11 +189,11 @@ main (int argc, char *argv[])
       r.n_var_widths = 0;
       r.allocated_var_widths = 0;
       r.var_widths = 0;
-      r.compressed = false;
+      r.compression = COMP_NONE;
 
       if (argc - optind > 1)
         printf ("Reading \"%s\":\n", r.file_name);
-      
+
       read_header (&r);
       while ((rec_type = read_int (&r)) != 999)
         {
@@ -216,12 +227,17 @@ main (int argc, char *argv[])
               (long long int) ftello (r.file),
               (long long int) ftello (r.file) + 4);
 
-      if (r.compressed && max_cases > 0)
-        read_compressed_data (&r, max_cases);
+      if (r.compression == COMP_SIMPLE)
+        {
+          if (max_cases > 0)
+            read_simple_compressed_data (&r, max_cases);
+        }
+      else if (r.compression == COMP_ZLIB)
+        read_zlib_compressed_data (&r);
 
       fclose (r.file);
     }
-  
+
   return 0;
 }
 
@@ -239,11 +255,16 @@ read_header (struct sfm_reader *r)
   char creation_date[10];
   char creation_time[9];
   char file_label[65];
+  bool zmagic;
 
   read_string (r, rec_type, sizeof rec_type);
   read_string (r, eye_catcher, sizeof eye_catcher);
 
-  if (strcmp ("$FL2", rec_type) != 0)
+  if (!strcmp ("$FL2", rec_type))
+    zmagic = false;
+  else if (!strcmp ("$FL3", rec_type))
+    zmagic = true;
+  else
     sys_error (r, "This is not an SPSS system file.");
 
   /* Identify integer format. */
@@ -263,7 +284,24 @@ read_header (struct sfm_reader *r)
   weight_index = read_int (r);
   ncases = read_int (r);
 
-  r->compressed = compressed != 0;
+  if (!zmagic)
+    {
+      if (compressed == 0)
+        r->compression = COMP_NONE;
+      else if (compressed == 1)
+        r->compression = COMP_SIMPLE;
+      else if (compressed != 0)
+        sys_error (r, "SAV file header has invalid compression value "
+                   "%"PRId32".", compressed);
+    }
+  else
+    {
+      if (compressed == 2)
+        r->compression = COMP_ZLIB;
+      else
+        sys_error (r, "ZSAV file header has invalid compression value "
+                   "%"PRId32".", compressed);
+    }
 
   /* Identify floating-point format and obtain compression bias. */
   read_bytes (r, raw_bias, sizeof raw_bias);
@@ -287,10 +325,15 @@ read_header (struct sfm_reader *r)
   printf ("File header record:\n");
   printf ("\t%17s: %s\n", "Product name", eye_catcher);
   printf ("\t%17s: %"PRId32"\n", "Layout code", layout_code);
-  printf ("\t%17s: %"PRId32"\n", "Compressed", compressed);
+  printf ("\t%17s: %"PRId32" (%s)\n", "Compressed",
+          compressed,
+          r->compression == COMP_NONE ? "no compression"
+          : r->compression == COMP_SIMPLE ? "simple compression"
+          : r->compression == COMP_ZLIB ? "ZLIB compression"
+          : "<error>");
   printf ("\t%17s: %"PRId32"\n", "Weight index", weight_index);
   printf ("\t%17s: %"PRId32"\n", "Number of cases", ncases);
-  printf ("\t%17s: %g\n", "Compression bias", r->bias);
+  printf ("\t%17s: %.*g\n", "Compression bias", DBL_DIG + 1, r->bias);
   printf ("\t%17s: %s\n", "Creation date", creation_date);
   printf ("\t%17s: %s\n", "Creation time", creation_time);
   printf ("\t%17s: \"%s\"\n", "File label", file_label);
@@ -401,18 +444,16 @@ read_variable_record (struct sfm_reader *r)
   if (has_variable_label == 1)
     {
       long long int offset = ftello (r->file);
-      size_t len, read_len;
-      char label[255 + 1];
+      size_t len;
+      char *label;
 
       len = read_int (r);
 
       /* Read up to 255 bytes of label. */
-      read_len = MIN (sizeof label - 1, len);
-      read_string (r, label, read_len + 1);
+      label = xmalloc (len + 1);
+      read_string (r, label, len + 1);
       printf("\t%08llx Variable label: \"%s\"\n", offset, label);
-
-      /* Skip unread label bytes. */
-      skip_bytes (r, len - read_len);
+      free (label);
 
       /* Skip label padding up to multiple of 4 bytes. */
       skip_bytes (r, ROUND_UP (len, 4) - len);
@@ -434,11 +475,11 @@ read_variable_record (struct sfm_reader *r)
             {
               double low = read_float (r);
               double high = read_float (r);
-              printf (" %g...%g", low, high);
+              printf (" %.*g...%.*g", DBL_DIG + 1, low, DBL_DIG + 1, high);
               missing_value_code = -missing_value_code - 2;
             }
           for (i = 0; i < missing_value_code; i++)
-            printf (" %g", read_float (r));
+            printf (" %.*g", DBL_DIG + 1, read_float (r));
         }
       else if (width > 0)
         {
@@ -467,7 +508,7 @@ print_untyped_value (struct sfm_reader *r, char raw_value[8])
     if (!isprint (raw_value[n_printable]))
       break;
 
-  printf ("%g/\"%.*s\"", value, n_printable, raw_value);
+  printf ("%.*g/\"%.*s\"", DBL_DIG + 1, value, n_printable, raw_value);
 }
 
 /* Reads value labels from sysfile R and inserts them into the
@@ -563,12 +604,6 @@ read_extension_record (struct sfm_reader *r)
       read_machine_float_info (r, size, count);
       return;
 
-    case 5:
-      /* Variable sets information.  We don't use these yet.
-         They only apply to GUIs; see VARSETS on the APPLY
-         DICTIONARY command in SPSS documentation. */
-      break;
-
     case 6:
       /* DATE variable information.  We don't use it yet, but we
          should. */
@@ -615,6 +650,10 @@ read_extension_record (struct sfm_reader *r)
       read_long_string_value_labels (r, size, count);
       return;
 
+    case 22:
+      read_long_string_missing_values (r, size, count);
+      return;
+
     default:
       sys_warn (r, "Unrecognized record type 7, subtype %d.", subtype);
       read_unknown_extension (r, size, count);
@@ -672,20 +711,20 @@ read_machine_float_info (struct sfm_reader *r, size_t size, size_t count)
     sys_error (r, "Bad size (%zu) or count (%zu) on extension 4.",
                size, count);
 
-  printf ("\tsysmis: %g (%a)\n", sysmis, sysmis);
+  printf ("\tsysmis: %.*g (%a)\n", DBL_DIG + 1, sysmis, sysmis);
   if (sysmis != SYSMIS)
-    sys_warn (r, "File specifies unexpected value %g (%a) as %s.",
-              sysmis, sysmis, "SYSMIS");
+    sys_warn (r, "File specifies unexpected value %.*g (%a) as %s.",
+              DBL_DIG + 1, sysmis, sysmis, "SYSMIS");
 
-  printf ("\thighest: %g (%a)\n", highest, highest);
+  printf ("\thighest: %.*g (%a)\n", DBL_DIG + 1, highest, highest);
   if (highest != HIGHEST)
-    sys_warn (r, "File specifies unexpected value %g (%a) as %s.",
-              highest, highest, "HIGHEST");
+    sys_warn (r, "File specifies unexpected value %.*g (%a) as %s.",
+              DBL_DIG + 1, highest, highest, "HIGHEST");
 
-  printf ("\tlowest: %g (%a)\n", lowest, lowest);
+  printf ("\tlowest: %.*g (%a)\n", DBL_DIG + 1, lowest, lowest);
   if (lowest != LOWEST && lowest != SYSMIS)
-    sys_warn (r, "File specifies unexpected value %g (%a) as %s.",
-              lowest, lowest, "LOWEST");
+    sys_warn (r, "File specifies unexpected value %.*g (%a) as %s.",
+              DBL_DIG + 1, lowest, lowest, "LOWEST");
 }
 
 static void
@@ -721,6 +760,9 @@ read_mrsets (struct sfm_reader *r, size_t size, size_t count)
       const char *label;
       const char *variables;
 
+      while (text_match (text, '\n'))
+        continue;
+
       name = text_tokenize (text, '=');
       if (name == NULL)
         break;
@@ -782,12 +824,6 @@ read_mrsets (struct sfm_reader *r, size_t size, size_t count)
         break;
 
       variables = text_tokenize (text, '\n');
-      if (variables == NULL)
-        {
-          sys_warn (r, "missing variable names following label "
-                    "at offset %zu in mrsets record", text_pos (text));
-          break;
-        }
 
       printf ("\t\"%s\": multiple %s set",
               name, type == MRSET_MC ? "category" : "dichotomy");
@@ -799,7 +835,10 @@ read_mrsets (struct sfm_reader *r, size_t size, size_t count)
         printf (", label \"%s\"", label);
       if (label_from_var_label)
         printf (", label from variable label");
-      printf(", variables \"%s\"\n", variables);
+      if (variables != NULL)
+        printf(", variables \"%s\"\n", variables);
+      else
+        printf(", no variables\n");
     }
   close_text_record (text);
 }
@@ -896,17 +935,17 @@ read_attributes (struct sfm_reader *r, struct text_record *text,
   const char *key;
   int index;
 
-  for (;;) 
+  for (;;)
     {
       key = text_tokenize (text, '(');
       if (key == NULL)
         return true;
-  
+
       for (index = 1; ; index++)
         {
           /* Parse the value. */
           const char *value = text_tokenize (text, '\n');
-          if (value == NULL) 
+          if (value == NULL)
             {
               sys_warn (r, "%s: Error parsing attribute value %s[%d]",
                         variable, key, index);
@@ -926,7 +965,7 @@ read_attributes (struct sfm_reader *r, struct text_record *text,
         }
 
       if (text_match (text, '/'))
-        return true; 
+        return true;
     }
 }
 
@@ -956,10 +995,10 @@ read_ncases64 (struct sfm_reader *r, size_t size, size_t count)
 }
 
 static void
-read_datafile_attributes (struct sfm_reader *r, size_t size, size_t count) 
+read_datafile_attributes (struct sfm_reader *r, size_t size, size_t count)
 {
   struct text_record *text;
-  
+
   printf ("%08llx: datafile attributes\n", (long long int) ftello (r->file));
   text = open_text_record (r, size * count);
   read_attributes (r, text, "datafile");
@@ -1036,6 +1075,56 @@ read_long_string_value_labels (struct sfm_reader *r, size_t size, size_t count)
     }
 }
 
+static void
+read_long_string_missing_values (struct sfm_reader *r,
+                                 size_t size, size_t count)
+{
+  long long int start = ftello (r->file);
+
+  printf ("%08llx: long string missing values\n", start);
+  while (ftello (r->file) - start < size * count)
+    {
+      long long posn = ftello (r->file);
+      char var_name[ID_MAX_LEN + 1];
+      uint8_t n_missing_values;
+      int var_name_len;
+      int i;
+
+      /* Read variable name. */
+      var_name_len = read_int (r);
+      if (var_name_len > ID_MAX_LEN)
+        sys_error (r, "Variable name length in long string value label "
+                   "record (%d) exceeds %d-byte limit.",
+                   var_name_len, ID_MAX_LEN);
+      read_string (r, var_name, var_name_len + 1);
+
+      /* Read number of values. */
+      read_bytes (r, &n_missing_values, 1);
+
+      printf ("\t%08llx: %s, %d missing values:",
+              posn, var_name, n_missing_values);
+
+      /* Read values. */
+      for (i = 0; i < n_missing_values; i++)
+	{
+          char *value;
+          int value_length;
+
+          posn = ftello (r->file);
+
+          /* Read value. */
+          value_length = read_int (r);
+          value = xmalloc (value_length + 1);
+          read_string (r, value, value_length + 1);
+
+          printf (" \"%s\"", value);
+
+          free (value);
+	}
+      printf ("\n");
+    }
+}
+
 static void
 hex_dump (size_t offset, const void *buffer_, size_t buffer_size)
 {
@@ -1098,23 +1187,23 @@ read_unknown_extension (struct sfm_reader *r, size_t size, size_t count)
 }
 
 static void
-read_variable_attributes (struct sfm_reader *r, size_t size, size_t count) 
+read_variable_attributes (struct sfm_reader *r, size_t size, size_t count)
 {
   struct text_record *text;
-  
+
   printf ("%08llx: variable attributes\n", (long long int) ftello (r->file));
   text = open_text_record (r, size * count);
-  for (;;) 
+  for (;;)
     {
       const char *variable = text_tokenize (text, ':');
       if (variable == NULL || !read_attributes (r, text, variable))
-        break; 
+        break;
     }
   close_text_record (text);
 }
 
 static void
-read_compressed_data (struct sfm_reader *r, int max_cases)
+read_simple_compressed_data (struct sfm_reader *r, int max_cases)
 {
   enum { N_OPCODES = 8 };
   uint8_t opcodes[N_OPCODES];
@@ -1158,7 +1247,7 @@ read_compressed_data (struct sfm_reader *r, int max_cases)
           switch (opcode)
             {
             default:
-              printf ("%g", opcode - r->bias);
+              printf ("%.*g", DBL_DIG + 1, opcode - r->bias);
               if (width != 0)
                 printf (", but this is a string variable (width=%d)", width);
               printf ("\n");
@@ -1202,6 +1291,87 @@ read_compressed_data (struct sfm_reader *r, int max_cases)
         }
     }
 }
+
+static void
+read_zlib_compressed_data (struct sfm_reader *r)
+{
+  long long int ofs;
+  long long int this_ofs, next_ofs, next_len;
+  long long int bias, zero;
+  long long int expected_uncmp_ofs, expected_cmp_ofs;
+  unsigned int block_size, n_blocks;
+  unsigned int i;
+
+  read_int (r);
+  ofs = ftello (r->file);
+  printf ("\n%08llx: ZLIB compressed data header:\n", ofs);
+
+  this_ofs = read_int64 (r);
+  next_ofs = read_int64 (r);
+  next_len = read_int64 (r);
+
+  printf ("\tzheader_ofs: 0x%llx\n", this_ofs);
+  if (this_ofs != ofs)
+    printf ("\t\t(Expected 0x%llx.)\n", ofs);
+  printf ("\tztrailer_ofs: 0x%llx\n", next_ofs);
+  printf ("\tztrailer_len: %lld\n", next_len);
+  if (next_len < 24 || next_len % 24)
+    printf ("\t\t(Trailer length is not a positive multiple of 24.)\n");
+
+  printf ("\n%08llx: 0x%llx bytes of ZLIB compressed data\n",
+          ofs + 8 * 3, next_ofs - (ofs + 8 * 3));
+
+  skip_bytes (r, next_ofs - (ofs + 8 * 3));
+
+  printf ("\n%08llx: ZLIB trailer fixed header:\n", next_ofs);
+  bias = read_int64 (r);
+  zero = read_int64 (r);
+  block_size = read_int (r);
+  n_blocks = read_int (r);
+  printf ("\tbias: %lld\n", bias);
+  printf ("\tzero: 0x%llx\n", zero);
+  if (zero != 0)
+    printf ("\t\t(Expected 0.)\n");
+  printf ("\tblock_size: 0x%x\n", block_size);
+  if (block_size != 0x3ff000)
+    printf ("\t\t(Expected 0x3ff000.)\n");
+  printf ("\tn_blocks: %u\n", n_blocks);
+  if (n_blocks != next_len / 24 - 1)
+    printf ("\t\t(Expected %llu.)\n", next_len / 24 - 1);
+
+  expected_uncmp_ofs = ofs;
+  expected_cmp_ofs = ofs + 24;
+  for (i = 0; i < n_blocks; i++)
+    {
+      long long int blockinfo_ofs = ftello (r->file);
+      unsigned long long int uncompressed_ofs = read_int64 (r);
+      unsigned long long int compressed_ofs = read_int64 (r);
+      unsigned int uncompressed_size = read_int (r);
+      unsigned int compressed_size = read_int (r);
+
+      printf ("\n%08llx: ZLIB block descriptor %d\n", blockinfo_ofs, i + 1);
+
+      printf ("\tuncompressed_ofs: 0x%llx\n", uncompressed_ofs);
+      if (uncompressed_ofs != expected_uncmp_ofs)
+        printf ("\t\t(Expected 0x%llx.)\n", ofs);
+
+      printf ("\tcompressed_ofs: 0x%llx\n", compressed_ofs);
+      if (compressed_ofs != expected_cmp_ofs)
+        printf ("\t\t(Expected 0x%llx.)\n", ofs + 24);
+
+      printf ("\tuncompressed_size: 0x%x\n", uncompressed_size);
+      if (i < n_blocks - 1 && uncompressed_size != block_size)
+        printf ("\t\t(Expected 0x%x.)\n", block_size);
+
+      printf ("\tcompressed_size: 0x%x\n", compressed_size);
+      if (i == n_blocks - 1 && compressed_ofs + compressed_size != next_ofs)
+        printf ("\t\t(This was expected to be 0x%llx.)\n",
+                next_ofs - compressed_size);
+
+      expected_uncmp_ofs += uncompressed_size;
+      expected_cmp_ofs += compressed_size;
+    }
+}
 
 /* Helpers for reading records that consist of structured text
    strings. */
@@ -1256,9 +1426,9 @@ text_tokenize (struct text_record *text, int delimiter)
 }
 
 static bool
-text_match (struct text_record *text, int c) 
+text_match (struct text_record *text, int c)
 {
-  if (text->pos < text->size && text->buffer[text->pos] == c) 
+  if (text->pos < text->size && text->buffer[text->pos] == c)
     {
       text->pos++;
       return true;