Implemented the ENCODING subcommand to DATA LIST.

Implemented the ENCODING subcommand which enables syntax
authors to tell pspp the encoding of a text file from which
data is to be read.

diff --git a/doc/data-io.texi b/doc/data-io.texi
index 0b9583b0200779d9b4c8eda507158f3fd2499adb..b7bfda9c98d0c5b020a35957cb897fcaf1734d35 100644 (file)
--- a/doc/data-io.texi
+++ b/doc/data-io.texi
@@ -178,7 +178,7 @@ situations.
 @display
 DATA LIST [FIXED]
         @{TABLE,NOTABLE@}
-        [FILE='file-name']
+        [FILE='file-name' [ENCODING='encoding']]
         [RECORDS=record_count]
         [END=end_var]
         [SKIP=record_count]
@@ -198,6 +198,8 @@ external file.  It may be used to specify a file name as a string or a
 file handle (@pxref{File Handles}).  If the FILE subcommand is not used,
 then input is assumed to be specified within the command file using
 @cmd{BEGIN DATA}@dots{}@cmd{END DATA} (@pxref{BEGIN DATA}).
+The ENCODING subcommand may only be used if the FILE subcommand is also used.
+It specifies the character encoding of the file.
 
 The optional RECORDS subcommand, which takes a single integer as an
 argument, is used to specify the number of lines per record.  If RECORDS
@@ -391,7 +393,7 @@ This example shows keywords abbreviated to their first 3 letters.
 DATA LIST FREE
         [(@{TAB,'c'@}, @dots{})]
         [@{NOTABLE,TABLE@}]
-        [FILE='file-name']
+        [FILE='file-name' [ENCODING='encoding']]
         [SKIP=record_cnt]
         /var_spec@dots{}
 
@@ -443,7 +445,7 @@ on field width apply, but they are honored on output.
 DATA LIST LIST
         [(@{TAB,'c'@}, @dots{})]
         [@{NOTABLE,TABLE@}]
-        [FILE='file-name']
+        [FILE='file-name' [ENCODING='encoding']]
         [SKIP=record_count]
         /var_spec@dots{}
 

diff --git a/src/language/data-io/data-list.c b/src/language/data-io/data-list.c
index d07eae5c554f7cb19b665175e2a45f9146e08102..3b091404f80f491edfe04418cf7c6b6830a16e72 100644 (file)
--- a/src/language/data-io/data-list.c
+++ b/src/language/data-io/data-list.c
@@ -75,8 +75,9 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
   struct dictionary *dict;
   struct data_parser *parser;
   struct dfm_reader *reader;
-  struct variable *end;
-  struct file_handle *fh;
+  struct variable *end = NULL;
+  struct file_handle *fh = NULL;
+  struct string encoding = DS_EMPTY_INITIALIZER;
 
   int table;
   enum data_parser_type type;
@@ -87,8 +88,6 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
   dict = in_input_program () ? dataset_dict (ds) : dict_create ();
   parser = data_parser_create ();
   reader = NULL;
-  end = NULL;
-  fh = NULL;
 
   table = -1;                /* Print table if nonzero, -1=undecided. */
   has_type = false;
@@ -103,6 +102,16 @@ cmd_data_list (struct lexer *lexer, struct dataset *ds)
          if (fh == NULL)
            goto error;
        }
+      else if (lex_match_id (lexer, "ENCODING"))
+       {
+         lex_match (lexer, '=');
+         if (!lex_force_string (lexer))
+           goto error;
+
+         ds_init_string (&encoding, lex_tokstr (lexer));
+
+         lex_get (lexer);
+       }
       else if (lex_match_id (lexer, "RECORDS"))
        {
          lex_match (lexer, '=');
@@ -228,6 +237,14 @@ 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 (fh == NULL)
     fh = fh_inline_file ();
   fh_set_default_handle (fh);