work on datasets

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

diff --git a/src/language/data-io/data-parser.c b/src/language/data-io/data-parser.c
index 55c62e08c0e0612868313e8647a1f42fb46f0785..f7657e2c8e7bf34b38c202ceaaceb4aa62199a3f 100644 (file)
--- a/src/language/data-io/data-parser.c
+++ b/src/language/data-io/data-parser.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 2007, 2009, 2010, 2011, 2012, 2013 Free Software Foundation, Inc.
+   Copyright (C) 2007, 2009, 2010, 2011, 2012, 2013, 2016 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
@@ -27,6 +27,7 @@
 #include "data/dictionary.h"
 #include "data/format.h"
 #include "data/file-handle-def.h"
+#include "data/session.h"
 #include "data/settings.h"
 #include "language/data-io/data-reader.h"
 #include "libpspp/message.h"
@@ -44,8 +45,6 @@ struct data_parser
     const struct dictionary *dict; /*Dictionary of destination */
     enum data_parser_type type; /* Type of data to parse. */
     int skip_records;           /* Records to skip before first real data. */
-    casenumber max_cases;       /* Max number of cases to read. */
-    int percent_cases;          /* Approximate percent of cases to read. */
 
     struct field *fields;       /* Fields to parse. */
     size_t field_cnt;           /* Number of fields. */
@@ -86,8 +85,6 @@ data_parser_create (const struct dictionary *dict)
 
   parser->type = DP_FIXED;
   parser->skip_records = 0;
-  parser->max_cases = -1;
-  parser->percent_cases = 100;
 
   parser->fields = NULL;
   parser->field_cnt = 0;
@@ -154,24 +151,6 @@ data_parser_set_skip (struct data_parser *parser, int initial_records_to_skip)
   parser->skip_records = initial_records_to_skip;
 }
 
-/* Sets the maximum number of cases parsed by PARSER to
-   MAX_CASES.  The default is -1, meaning no limit. */
-void
-data_parser_set_case_limit (struct data_parser *parser, casenumber max_cases)
-{
-  parser->max_cases = max_cases;
-}
-
-/* Sets the percentage of cases that PARSER should read from the
-   input file to PERCENT_CASES.  By default, all cases are
-   read. */
-void
-data_parser_set_case_percent (struct data_parser *parser, int percent_cases)
-{
-  assert (percent_cases >= 0 && percent_cases <= 100);
-  parser->percent_cases = percent_cases;
-}
-
 /* Returns true if PARSER is configured to allow cases to span
    multiple records. */
 bool
@@ -389,12 +368,6 @@ data_parser_parse (struct data_parser *parser, struct dfm_reader *reader,
     }
 
   /* Limit cases. */
-  if (parser->max_cases != -1 && parser->max_cases-- == 0)
-    return false;
-  if (parser->percent_cases < 100
-      && dfm_get_percent_read (reader) >= parser->percent_cases)
-    return false;
-
   if (parser->type == DP_DELIMITED)
     {
       if (parser->span)
@@ -578,7 +551,6 @@ static bool
 parse_delimited_span (const struct data_parser *parser,
                       struct dfm_reader *reader, struct ccase *c)
 {
-  const char *input_encoding = dfm_reader_get_encoding (reader);
   const char *output_encoding = dict_get_encoding (parser->dict);
   struct string tmp = DS_EMPTY_INITIALIZER;
   struct field *f;
@@ -605,6 +577,7 @@ parse_delimited_span (const struct data_parser *parser,
            }
        }
 
+      const char *input_encoding = dfm_reader_get_encoding (reader);
       error = data_in (s, input_encoding, f->format.type,
                        case_data_rw_idx (c, f->case_idx),
                        fmt_var_width (&f->format), output_encoding);
@@ -622,7 +595,6 @@ static bool
 parse_delimited_no_span (const struct data_parser *parser,
                          struct dfm_reader *reader, struct ccase *c)
 {
-  const char *input_encoding = dfm_reader_get_encoding (reader);
   const char *output_encoding = dict_get_encoding (parser->dict);
   struct string tmp = DS_EMPTY_INITIALIZER;
   struct substring s;
@@ -650,6 +622,7 @@ parse_delimited_no_span (const struct data_parser *parser,
           goto exit;
        }
 
+      const char *input_encoding = dfm_reader_get_encoding (reader);
       error = data_in (s, input_encoding, f->format.type,
                        case_data_rw_idx (c, f->case_idx),
                        fmt_var_width (&f->format), output_encoding);
@@ -761,13 +734,13 @@ struct data_parser_casereader
 
 static const struct casereader_class data_parser_casereader_class;
 
-/* Replaces DS's active dataset by an input program that reads data
-   from READER according to the rules in PARSER, using DICT as
-   the underlying dictionary.  Ownership of PARSER and READER is
-   transferred to the input program, and ownership of DICT is
-   transferred to the dataset. */
+/* Creates a new unnamed dataset in SESSION.  The new dataset has an input
+   program that reads data from READER according to the rules in PARSER, using
+   DICT as the underlying dictionary.  Transfers ownership of PARSER and READER
+   is to the input program, and ownership of DICT to the dataset. */
 void
-data_parser_make_active_file (struct data_parser *parser, struct dataset *ds,
+data_parser_make_active_file (struct data_parser *parser,
+                              struct session *session,
                               struct dfm_reader *reader,
                               struct dictionary *dict)
 {
@@ -781,8 +754,11 @@ data_parser_make_active_file (struct data_parser *parser, struct dataset *ds,
   casereader = casereader_create_sequential (NULL, r->proto,
                                              CASENUMBER_MAX,
                                              &data_parser_casereader_class, r);
+
+  struct dataset *ds = dataset_create (session, "");
   dataset_set_dict (ds, dict);
   dataset_set_source (ds, casereader);
+  session_set_active_dataset (session, ds);
 }
 
 static struct ccase *