Rename procedure.[ch] to dataset.[ch].

[pspp-builds.git] / src / language / data-io / get-data.c

diff --git a/src/language/data-io/get-data.c b/src/language/data-io/get-data.c
index eeb3827a58924dfa13eedd6bf2d2c2df43ffd8b5..07000eb2041aa1a9870c38d8d7ea42826292d024 100644 (file)
--- a/src/language/data-io/get-data.c
+++ b/src/language/data-io/get-data.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
+   Copyright (C) 2007, 2008, 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
@@ -18,23 +18,23 @@
 
 #include <stdlib.h>
 
-#include <data/gnumeric-reader.h>
-#include <data/psql-reader.h>
-
-#include <data/dictionary.h>
-#include <data/format.h>
-#include <data/procedure.h>
-#include <data/settings.h>
-#include <language/command.h>
-#include <language/data-io/data-parser.h>
-#include <language/data-io/data-reader.h>
-#include <language/data-io/file-handle.h>
-#include <language/data-io/placement-parser.h>
-#include <language/lexer/format-parser.h>
-#include <language/lexer/lexer.h>
-#include <libpspp/message.h>
-
-#include "xalloc.h"
+#include "data/dataset.h"
+#include "data/dictionary.h"
+#include "data/format.h"
+#include "data/gnumeric-reader.h"
+#include "data/psql-reader.h"
+#include "data/settings.h"
+#include "language/command.h"
+#include "language/data-io/data-parser.h"
+#include "language/data-io/data-reader.h"
+#include "language/data-io/file-handle.h"
+#include "language/data-io/placement-parser.h"
+#include "language/lexer/format-parser.h"
+#include "language/lexer/lexer.h"
+#include "libpspp/i18n.h"
+#include "libpspp/message.h"
+
+#include "gl/xalloc.h"
 
 #include "gettext.h"
 #define _(msgid) gettext (msgid)
@@ -61,7 +61,7 @@ cmd_get_data (struct lexer *lexer, struct dataset *ds)
   else if (lex_match_id (lexer, "PSQL"))
     return parse_get_psql (lexer, ds);
 
-  msg (SE, _("Unsupported TYPE %s"), lex_tokid (lexer));
+  msg (SE, _("Unsupported TYPE %s."), lex_tokcstr (lexer));
   return CMD_FAILURE;
 }
 
@@ -85,7 +85,7 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds)
   if (!lex_force_string (lexer))
     goto error;
 
-  psql.conninfo = xstrdup (ds_cstr (lex_tokstr (lexer)));
+  psql.conninfo = ss_xstrdup (lex_tokss (lexer));
 
   lex_get (lexer);
 
@@ -113,7 +113,7 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds)
          if ( ! lex_force_string (lexer) )
            goto error;
 
-         ds_put_substring (&psql.sql,  lex_tokstr (lexer)->ss);
+         ds_put_substring (&psql.sql, lex_tokss (lexer));
          lex_get (lexer);
        }
      }
@@ -153,7 +153,7 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds)
   if (!lex_force_string (lexer))
     goto error;
 
-  gri.file_name = xstrdup (ds_cstr (lex_tokstr (lexer)));
+  gri.file_name = utf8_to_filename (lex_tokcstr (lexer));
 
   lex_get (lexer);
 
@@ -163,6 +163,7 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds)
        {
          lex_match (lexer, T_EQUALS);
          gri.asw = lex_integer (lexer);
+         lex_get (lexer);
        }
       else if (lex_match_id (lexer, "SHEET"))
        {
@@ -172,12 +173,15 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds)
              if ( ! lex_force_string (lexer) )
                goto error;
 
-             gri.sheet_name = xstrdup (ds_cstr (lex_tokstr (lexer)));
+             gri.sheet_name = ss_xstrdup (lex_tokss (lexer));
              gri.sheet_index = -1;
+
+             lex_get (lexer);
            }
          else if (lex_match_id (lexer, "INDEX"))
            {
              gri.sheet_index = lex_integer (lexer);
+             lex_get (lexer);
            }
          else
            goto error;
@@ -189,14 +193,14 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds)
          if (lex_match_id (lexer, "FULL"))
            {
              gri.cell_range = NULL;
-             lex_put_back (lexer, T_ID);
            }
          else if (lex_match_id (lexer, "RANGE"))
            {
              if ( ! lex_force_string (lexer) )
                goto error;
 
-             gri.cell_range = xstrdup (ds_cstr (lex_tokstr (lexer)));
+             gri.cell_range = ss_xstrdup (lex_tokss (lexer));
+             lex_get (lexer);
            }
          else
            goto error;
@@ -215,13 +219,12 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds)
            }
          else
            goto error;
-         lex_put_back (lexer, T_ID);
        }
       else
        {
+         lex_error (lexer, NULL);
          goto error;
        }
-      lex_get (lexer);
     }
 
   {
@@ -273,6 +276,7 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
   struct dictionary *dict = dict_create ();
   struct file_handle *fh = NULL;
   struct dfm_reader *reader = NULL;
+  char *name = NULL;
 
   int record;
   enum data_parser_type type;
@@ -415,7 +419,8 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
           if (!lex_force_string (lexer))
             goto error;
 
-          s = ds_ss (lex_tokstr (lexer));
+          /* XXX should support multibyte UTF-8 characters */
+          s = lex_tokss (lexer);
           if (ss_match_string (&s, ss_cstr ("\\t")))
             ds_put_cstr (&hard_seps, "\t");
           if (ss_match_string (&s, ss_cstr ("\\\\")))
@@ -440,15 +445,16 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
           if (!lex_force_string (lexer))
             goto error;
 
+          /* XXX should support multibyte UTF-8 characters */
           if (settings_get_syntax () == COMPATIBLE
-              && ds_length (lex_tokstr (lexer)) != 1)
+              && ss_length (lex_tokss (lexer)) != 1)
             {
               msg (SE, _("In compatible syntax mode, the QUALIFIER string "
                          "must contain exactly one character."));
               goto error;
             }
 
-          data_parser_set_quotes (parser, ds_ss (lex_tokstr (lexer)));
+          data_parser_set_quotes (parser, lex_tokss (lexer));
           lex_get (lexer);
         }
       else if (settings_get_syntax () == ENHANCED
@@ -464,15 +470,13 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
     }
   lex_match (lexer, T_EQUALS);
 
-
   record = 1;
   type = data_parser_get_type (parser);
   do
     {
-      char name[VAR_NAME_LEN + 1];
       struct fmt_spec input, output;
-      int fc, lc;
       struct variable *v;
+      int fc, lc;
 
       while (type == DP_FIXED && lex_match (lexer, T_SLASH))
         {
@@ -499,9 +503,10 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
           lex_get (lexer);
         }
 
-      if (!lex_force_id (lexer))
+      if (!lex_force_id (lexer)
+          || !dict_id_is_valid (dict, lex_tokcstr (lexer), true))
         goto error;
-      strcpy (name, lex_tokid (lexer));
+      name = xstrdup (lex_tokcstr (lexer));
       lex_get (lexer);
 
       if (type == DP_DELIMITED)
@@ -538,6 +543,8 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
       else
         data_parser_add_fixed_field (parser, &input, var_get_case_index (v),
                                      name, record, fc);
+      free (name);
+      name = NULL;
     }
   while (lex_token (lexer) != T_ENDCMD);
 
@@ -553,5 +560,6 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
   data_parser_destroy (parser);
   dict_destroy (dict);
   fh_unref (fh);
+  free (name);
   return CMD_CASCADING_FAILURE;
 }