src/language/data-io/data-parser.h

   1 /* PSPP - a program for statistical analysis.
   2    Copyright (C) 2007, 2011, 2016 Free Software Foundation, Inc.
   3
   4    This program is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU General Public License as published by
   6    the Free Software Foundation, either version 3 of the License, or
   7    (at your option) any later version.
   8
   9    This program is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU General Public License for more details.
  13
  14    You should have received a copy of the GNU General Public License
  15    along with this program.  If not, see <http://www.gnu.org/licenses/>. */
  16
  17 #ifndef LANGUAGE_DATA_IO_DATA_PARSER_H
  18 #define LANGUAGE_DATA_IO_DATA_PARSER_H
  19
  20 /* Abstraction of a DATA LIST or GET DATA TYPE=TXT data parser. */
  21
  22 #include <stdbool.h>
  23 #include "data/case.h"
  24 #include "libpspp/str.h"
  25
  26 struct dataset;
  27 struct dfm_reader;
  28 struct dictionary;
  29 struct file_handle;
  30 struct fmt_spec;
  31 struct substring;
  32
  33 /* Type of data read by a data parser. */
  34 enum data_parser_type
  35   {
  36     DP_FIXED,                   /* Fields in fixed column positions. */
  37     DP_DELIMITED                /* Fields delimited by e.g. commas. */
  38   };
  39
  40 /* Creating and configuring any parser. */
  41 struct data_parser *data_parser_create (void);
  42 void data_parser_destroy (struct data_parser *);
  43
  44 enum data_parser_type data_parser_get_type (const struct data_parser *);
  45 void data_parser_set_type (struct data_parser *, enum data_parser_type);
  46
  47 void data_parser_set_skip (struct data_parser *, int initial_records_to_skip);
  48
  49 /* For configuring delimited parsers only. */
  50 bool data_parser_get_span (const struct data_parser *);
  51 void data_parser_set_span (struct data_parser *, bool may_cases_span_records);
  52
  53 void data_parser_set_empty_line_has_field (struct data_parser *,
  54                                            bool empty_line_has_field);
  55 void data_parser_set_warn_missing_fields (struct data_parser *parser,
  56                                           bool warn_missing_fields);
  57
  58 void data_parser_set_quotes (struct data_parser *, struct substring);
  59 void data_parser_set_quote_escape (struct data_parser *, bool escape);
  60 void data_parser_set_soft_delimiters (struct data_parser *, struct substring);
  61 void data_parser_set_hard_delimiters (struct data_parser *, struct substring);
  62
  63 /* For configuring fixed parsers only. */
  64 int data_parser_get_records (const struct data_parser *);
  65 void data_parser_set_records (struct data_parser *, int records_per_case);
  66
  67 /* Field setup and parsing. */
  68 void data_parser_add_delimited_field (struct data_parser *,
  69                                       const struct fmt_spec *, int fv,
  70                                       const char *name);
  71 void data_parser_add_fixed_field (struct data_parser *,
  72                                   const struct fmt_spec *, int fv,
  73                                   const char *name,
  74                                   int record, int first_column);
  75 bool data_parser_any_fields (const struct data_parser *);
  76 bool data_parser_parse (struct data_parser *, struct dfm_reader *,
  77                         struct dictionary *, struct ccase *);
  78
  79
  80 /* Uses for a configured parser. */
  81 void data_parser_output_description (struct data_parser *,
  82                                      const struct file_handle *);
  83 struct casereader;
  84 void data_parser_make_active_file (struct data_parser *, struct dataset *,
  85                                    struct dfm_reader *, struct dictionary *,
  86                                    struct casereader* (*func)(struct casereader *,
  87                                                               const struct dictionary *,
  88                                                               void *),
  89                                    void *ud);
  90
  91
  92 #endif /* language/data-io/data-parser.h */