Spreadsheet readers: Seperate the mandatory from the optional arguments.

[pspp] / 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 4274f959d26048de21d79797d3eed879da6766fd..fa033f22e86c2de2b126d5d50a826f3bb4132c13 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, 2011 Free Software Foundation, Inc.
+   Copyright (C) 2007, 2008, 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
@@ -45,8 +45,10 @@
 #define _(msgid) gettext (msgid)
 #define N_(msgid) (msgid)
 
-static struct spreadsheet_read_info *parse_spreadsheet (struct lexer *lexer);
-static void destroy_spreadsheet_read_info (struct spreadsheet_read_info *);
+static bool parse_spreadsheet (struct lexer *lexer, struct spreadsheet_read_info *sri, 
+                              struct spreadsheet_read_options *opts);
+
+static void destroy_spreadsheet_read_info (struct spreadsheet_read_info *, struct spreadsheet_read_options *);
 
 static int parse_get_txt (struct lexer *lexer, struct dataset *);
 static int parse_get_psql (struct lexer *lexer, struct dataset *);
@@ -65,10 +67,12 @@ cmd_get_data (struct lexer *lexer, struct dataset *ds)
   tok = strdup (lex_tokcstr (lexer));
   if (lex_match_id (lexer, "TXT"))
     {
+      free (tok);
       return parse_get_txt (lexer, ds);
     }
   else if (lex_match_id (lexer, "PSQL"))
     {
+      free (tok);
       return parse_get_psql (lexer, ds);
     }
   else if (lex_match_id (lexer, "GNM") || 
@@ -76,24 +80,25 @@ cmd_get_data (struct lexer *lexer, struct dataset *ds)
     {
       struct casereader *reader = NULL;
       struct dictionary *dict = NULL;
-      struct spreadsheet_read_info *sri = parse_spreadsheet (lexer);
-      if (NULL == sri)
+      struct spreadsheet_read_info sri;
+      struct spreadsheet_read_options opts;
+      if (!parse_spreadsheet (lexer, &sri, &opts))
        goto error;
 
       if ( 0 == strncasecmp (tok, "GNM", 3))
-       reader = gnumeric_open_reader (sri, &dict);
+       reader = gnumeric_open_reader (&sri, &opts, &dict);
       else if (0 == strncasecmp (tok, "ODS", 3))
-       reader = ods_open_reader (sri, &dict);
+       reader = ods_open_reader (&sri, &opts, &dict);
 
       if (reader)
        {
          dataset_set_dict (ds, dict);
          dataset_set_source (ds, reader);
-         destroy_spreadsheet_read_info (sri);
+         destroy_spreadsheet_read_info (&sri, &opts);
          free (tok);
          return CMD_SUCCESS;
        }
-      destroy_spreadsheet_read_info (sri);
+      destroy_spreadsheet_read_info (&sri, &opts);
     }
   else
     msg (SE, _("Unsupported TYPE %s."), tok);
@@ -179,13 +184,16 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds)
   return CMD_FAILURE;
 }
 
-static struct spreadsheet_read_info *
-parse_spreadsheet (struct lexer *lexer)
+static bool
+parse_spreadsheet (struct lexer *lexer, struct spreadsheet_read_info *sri, 
+                  struct spreadsheet_read_options *opts)
 {
-  struct spreadsheet_read_info *sri = xzalloc (sizeof *sri);
-  sri->sheet_index = 1;
+  opts->sheet_index = 1;
+  opts->sheet_name = NULL;
+  opts->cell_range = NULL;
   sri->read_names = true;
   sri->asw = -1;
+  sri->file_name = NULL;
 
   lex_force_match (lexer, T_SLASH);
 
@@ -217,18 +225,27 @@ parse_spreadsheet (struct lexer *lexer)
              if ( ! lex_force_string (lexer) )
                goto error;
 
-             sri->sheet_name = ss_xstrdup (lex_tokss (lexer));
-             sri->sheet_index = -1;
+             opts->sheet_name = ss_xstrdup (lex_tokss (lexer));
+             opts->sheet_index = -1;
 
              lex_get (lexer);
            }
          else if (lex_match_id (lexer, "INDEX"))
            {
              sri->sheet_index = lex_integer (lexer);
+             if (sri->sheet_index <= 0)
+               {
+                 msg (SE, _("The sheet index must be greater than or equal to 1"));
+                 goto error;
+               }
              lex_get (lexer);
            }
          else
-           goto error;
+           {
+             msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."),
+                  "/SHEET", "NAME", "INDEX");
+             goto error;
+           }
        }
       else if (lex_match_id (lexer, "CELLRANGE"))
        {
@@ -236,18 +253,22 @@ parse_spreadsheet (struct lexer *lexer)
 
          if (lex_match_id (lexer, "FULL"))
            {
-             sri->cell_range = NULL;
+             opts->cell_range = NULL;
            }
          else if (lex_match_id (lexer, "RANGE"))
            {
              if ( ! lex_force_string (lexer) )
                goto error;
 
-             sri->cell_range = ss_xstrdup (lex_tokss (lexer));
+             opts->cell_range = ss_xstrdup (lex_tokss (lexer));
              lex_get (lexer);
            }
          else
-           goto error;
+           {
+             msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."),
+                  "/CELLRANGE", "FULL", "RANGE");
+             goto error;
+           }
        }
       else if (lex_match_id (lexer, "READNAMES"))
        {
@@ -262,7 +283,11 @@ parse_spreadsheet (struct lexer *lexer)
              sri->read_names = false;
            }
          else
-           goto error;
+           {
+             msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."),
+                  "/READNAMES", "ON", "OFF");
+             goto error;
+           }
        }
       else
        {
@@ -271,11 +296,11 @@ parse_spreadsheet (struct lexer *lexer)
        }
     }
 
-  return sri;
+  return true;
 
  error:
-  destroy_spreadsheet_read_info (sri);
-  return NULL;
+  destroy_spreadsheet_read_info (sri, opts);
+  return false;
 }
 
 
@@ -307,6 +332,7 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
   struct dictionary *dict = dict_create (get_default_encoding ());
   struct file_handle *fh = NULL;
   struct dfm_reader *reader = NULL;
+  char *encoding = NULL;
   char *name = NULL;
 
   int record;
@@ -334,7 +360,18 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
       if (!lex_force_match (lexer, T_SLASH))
         goto error;
 
-      if (lex_match_id (lexer, "ARRANGEMENT"))
+      if (lex_match_id (lexer, "ENCODING"))
+       {
+         lex_match (lexer, T_EQUALS);
+         if (!lex_force_string (lexer))
+           goto error;
+
+          free (encoding);
+          encoding = ss_xstrdup (lex_tokss (lexer));
+
+         lex_get (lexer);
+       }
+      else if (lex_match_id (lexer, "ARRANGEMENT"))
         {
           bool ok;
 
@@ -606,12 +643,13 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
     }
   while (lex_token (lexer) != T_ENDCMD);
 
-  reader = dfm_open_reader (fh, lexer);
+  reader = dfm_open_reader (fh, lexer, encoding);
   if (reader == NULL)
     goto error;
 
   data_parser_make_active_file (parser, ds, reader, dict);
   fh_unref (fh);
+  free (encoding);
   return CMD_SUCCESS;
 
  error:
@@ -619,18 +657,16 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds)
   dict_destroy (dict);
   fh_unref (fh);
   free (name);
+  free (encoding);
   return CMD_CASCADING_FAILURE;
 }
 
 
 static void 
-destroy_spreadsheet_read_info (struct spreadsheet_read_info *sri)
+destroy_spreadsheet_read_info (struct spreadsheet_read_info *sri,
+                              struct spreadsheet_read_options *opts)
 {
-  if ( NULL == sri)
-    return;
-
-  free (sri->sheet_name);
-  free (sri->cell_range);
+  free (opts->sheet_name);
+  free (opts->cell_range);
   free (sri->file_name);
-  free (sri);
 }