DATA LIST: Do not treat the comma as a field separator if DECIMAL=COMMA

[pspp] / src / language / data-io / data-list.c

diff --git a/src/language/data-io/data-list.c b/src/language/data-io/data-list.c
index 6d21c8439e7cb9e3a7e5c3ebc31744a4dd92c437..90d060eaab66721a8462fcb81baa351494177441 100644 (file)
--- a/src/language/data-io/data-list.c
+++ b/src/language/data-io/data-list.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 1997-9, 2000, 2006, 2007, 2009, 2010, 2011 Free Software Foundation, Inc.
+   Copyright (C) 1997-9, 2000, 2006, 2007, 2009, 2010, 2011, 2012, 2013 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
@@ -25,9 +25,9 @@
 #include "data/case.h"
 #include "data/casereader.h"
 #include "data/data-in.h"
+#include "data/dataset.h"
 #include "data/dictionary.h"
 #include "data/format.h"
-#include "data/procedure.h"
 #include "data/settings.h"
 #include "data/transformations.h"
 #include "data/variable.h"
@@ -42,6 +42,7 @@
 #include "language/lexer/variable-parser.h"
 #include "libpspp/assertion.h"
 #include "libpspp/compiler.h"
+#include "libpspp/i18n.h"
 #include "libpspp/message.h"
 #include "libpspp/misc.h"
 #include "libpspp/pool.h"
@@ -77,7 +78,7 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
   struct dfm_reader *reader;
   struct variable *end = NULL;
   struct file_handle *fh = NULL;
-  struct string encoding = DS_EMPTY_INITIALIZER;
+  char *encoding = NULL;
 
   int table;
   enum data_parser_type type;
@@ -85,7 +86,9 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
   struct pool *tmp_pool;
   bool ok;
 
-  dict = in_input_program () ? dataset_dict (ds) : dict_create ();
+  dict = (in_input_program ()
+          ? dataset_dict (ds)
+          : dict_create (get_default_encoding ()));
   parser = data_parser_create (dict);
   reader = NULL;
 
@@ -98,7 +101,7 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
        {
          lex_match (lexer, T_EQUALS);
           fh_unref (fh);
-         fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE);
+         fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE, NULL);
          if (fh == NULL)
            goto error;
        }
@@ -108,7 +111,8 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
          if (!lex_force_string (lexer))
            goto error;
 
-         ds_init_substring (&encoding, lex_tokss (lexer));
+          free (encoding);
+          encoding = ss_xstrdup (lex_tokss (lexer));
 
          lex_get (lexer);
        }
@@ -134,13 +138,12 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
        {
           if (!in_input_program ())
             {
-              msg (SE, _("The END subcommand may only be used within "
-                         "INPUT PROGRAM."));
+              msg (SE, _("The %s subcommand may only be used within %s."), "END", "INPUT PROGRAM");
               goto error;
             }
          if (end)
            {
-             msg (SE, _("The END subcommand may only be specified once."));
+             msg (SE, _("The %s subcommand may only be specified once."), "END");
              goto error;
            }
 
@@ -226,7 +229,9 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
                   data_parser_set_quotes (parser, ss_cstr ("'\""));
                   data_parser_set_soft_delimiters (parser,
                                                    ss_cstr (CC_SPACES));
-                  data_parser_set_hard_delimiters (parser, ss_cstr (","));
+                  const char decimal = settings_get_decimal_char (FMT_F);
+                  data_parser_set_hard_delimiters (parser,
+                                                   ss_buffer (",", (decimal == '.') ? 1 : 0));
                 }
             }
         }
@@ -238,13 +243,9 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
     }
   type = data_parser_get_type (parser);
 
-  if (! ds_is_empty (&encoding))
-    {
-      if ( NULL == fh)
-       msg (MW, _("Encoding should not be specified for inline data. It will be ignored."));
-      else
-       dict_set_encoding (dict, ds_cstr (&encoding));
-    }
+  if (encoding && NULL == fh)
+    msg (MW, _("Encoding should not be specified for inline data. It will be "
+               "ignored."));
 
   if (fh == NULL)
     fh = fh_inline_file ();
@@ -252,7 +253,7 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
 
   if (type != DP_FIXED && end != NULL)
     {
-      msg (SE, _("The END subcommand may be used only with DATA LIST FIXED."));
+      msg (SE, _("The %s subcommand may be used only with %s."), "END", "DATA LIST FIXED");
       goto error;
     }
 
@@ -279,7 +280,7 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
   if (table)
     data_parser_output_description (parser, fh);
 
-  reader = dfm_open_reader (fh, lexer);
+  reader = dfm_open_reader (fh, lexer, encoding);
   if (reader == NULL)
     goto error;
 
@@ -295,16 +296,16 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
     data_parser_make_active_file (parser, ds, reader, dict);
 
   fh_unref (fh);
-  ds_destroy (&encoding);
+  free (encoding);
 
-  return CMD_SUCCESS;
+  return CMD_DATA_LIST;
 
  error:
   data_parser_destroy (parser);
   if (!in_input_program ())
     dict_destroy (dict);
   fh_unref (fh);
-  ds_destroy (&encoding);
+  free (encoding);
   return CMD_CASCADING_FAILURE;
 }
 \f
@@ -333,7 +334,7 @@ parse_fixed (struct lexer *lexer, struct dictionary *dict,
       if (!parse_record_placement (lexer, &record, &column)
           || !parse_DATA_LIST_vars_pool (lexer, dict, tmp_pool,
                                         &names, &name_cnt, PV_NONE)
-          || !parse_var_placements (lexer, tmp_pool, name_cnt, true,
+          || !parse_var_placements (lexer, tmp_pool, name_cnt, FMT_FOR_INPUT,
                                     &formats, &format_cnt))
         return false;
 
@@ -429,9 +430,28 @@ parse_free (struct lexer *lexer, struct dictionary *dict,
 
       if (lex_match (lexer, T_LPAREN))
        {
-         if (!parse_format_specifier (lexer, &input)
-              || !fmt_check_input (&input)
-              || !lex_force_match (lexer, T_RPAREN))
+          char type[FMT_TYPE_LEN_MAX + 1];
+
+         if (!parse_abstract_format_specifier (lexer, type, &input.w,
+                                                &input.d))
+            return NULL;
+          if (!fmt_from_name (type, &input.type))
+            {
+              msg (SE, _("Unknown format type `%s'."), type);
+              return NULL;
+            }
+
+          /* If no width was included, use the minimum width for the type.
+             This isn't quite right, because DATETIME by itself seems to become
+             DATETIME20 (see bug #30690), whereas this will become
+             DATETIME17.  The correct behavior is not documented. */
+          if (input.w == 0)
+            {
+              input.w = fmt_min_input_width (input.type);
+              input.d = 0;
+            }
+
+          if (!fmt_check_input (&input) || !lex_force_match (lexer, T_RPAREN))
             return NULL;
 
           /* As a special case, N format is treated as F format