1 /* PSPP - a program for statistical analysis.
2 Copyright (C) 1997-9, 2000, 2010, 2011, 2013, 2014 Free Software Foundation, Inc.
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.
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.
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/>. */
24 #include "data/identifier.h"
25 #include "data/variable.h"
26 #include "language/lexer/segment.h"
27 #include "libpspp/cast.h"
28 #include "libpspp/compiler.h"
29 #include "libpspp/prompt.h"
33 /* Handling of errors. */
36 LEX_ERROR_TERMINAL, /* Discard input line and continue reading. */
37 LEX_ERROR_CONTINUE, /* Continue to next command, except for
38 cascading failures. */
39 LEX_ERROR_STOP /* Stop processing. */
42 /* Reads a single syntax file as a stream of bytes encoded in UTF-8.
47 const struct lex_reader_class *class;
48 enum segmenter_mode syntax;
49 enum lex_error_mode error;
51 char *file_name; /* NULL if not associated with a file. */
52 int line_number; /* 1-based initial line number, 0 if none. */
56 /* An implementation of a lex_reader. */
57 struct lex_reader_class
59 /* Reads up to N bytes of data from READER into N. Returns the positive
60 number of bytes read if successful, or zero at end of input or on
63 STYLE provides a hint to interactive readers as to what kind of syntax
64 is being read right now. */
65 size_t (*read) (struct lex_reader *reader, char *buf, size_t n,
66 enum prompt_style style);
68 /* Closes and destroys READER, releasing any allocated storage.
70 The caller will free the 'file_name' member of READER, so the
71 implementation should not do so. */
72 void (*destroy) (struct lex_reader *reader);
75 /* Helper functions for lex_reader. */
76 void lex_reader_init (struct lex_reader *, const struct lex_reader_class *);
77 void lex_reader_set_file_name (struct lex_reader *, const char *file_name);
79 /* Creating various kinds of lex_readers. */
80 struct lex_reader *lex_reader_for_file (const char *file_name,
82 enum segmenter_mode syntax,
83 enum lex_error_mode error);
84 struct lex_reader *lex_reader_for_string (const char *, const char *encoding);
85 struct lex_reader *lex_reader_for_format (const char *, const char *, ...)
87 struct lex_reader *lex_reader_for_substring_nocopy (struct substring, const char *encoding);
90 struct lexer *lex_create (void);
91 void lex_destroy (struct lexer *);
94 void lex_include (struct lexer *, struct lex_reader *);
95 void lex_append (struct lexer *, struct lex_reader *);
98 void lex_get (struct lexer *);
100 /* Token testing functions. */
101 bool lex_is_number (const struct lexer *);
102 double lex_number (const struct lexer *);
103 bool lex_is_integer (const struct lexer *);
104 long lex_integer (const struct lexer *);
105 bool lex_is_string (const struct lexer *);
107 /* Token testing functions with lookahead. */
108 bool lex_next_is_number (const struct lexer *, int n);
109 double lex_next_number (const struct lexer *, int n);
110 bool lex_next_is_integer (const struct lexer *, int n);
111 long lex_next_integer (const struct lexer *, int n);
112 bool lex_next_is_string (const struct lexer *, int n);
114 /* Token matching functions. */
115 bool lex_match (struct lexer *, enum token_type);
116 bool lex_match_id (struct lexer *, const char *);
117 bool lex_match_id_n (struct lexer *, const char *, size_t n);
118 bool lex_match_int (struct lexer *, int);
119 bool lex_match_phrase (struct lexer *, const char *s);
121 /* Forcible matching functions. */
122 bool lex_force_match (struct lexer *, enum token_type) WARN_UNUSED_RESULT;
123 bool lex_force_match_id (struct lexer *, const char *) WARN_UNUSED_RESULT;
124 bool lex_force_int (struct lexer *) WARN_UNUSED_RESULT;
125 bool lex_force_int_range (struct lexer *, const char *name,
126 long min, long max) WARN_UNUSED_RESULT;
127 bool lex_force_num (struct lexer *) WARN_UNUSED_RESULT;
128 bool lex_force_id (struct lexer *) WARN_UNUSED_RESULT;
129 bool lex_force_string (struct lexer *) WARN_UNUSED_RESULT;
130 bool lex_force_string_or_id (struct lexer *) WARN_UNUSED_RESULT;
132 /* Token accessors. */
133 enum token_type lex_token (const struct lexer *);
134 double lex_tokval (const struct lexer *);
135 const char *lex_tokcstr (const struct lexer *);
136 struct substring lex_tokss (const struct lexer *);
139 const struct token *lex_next (const struct lexer *, int n);
140 enum token_type lex_next_token (const struct lexer *, int n);
141 const char *lex_next_tokcstr (const struct lexer *, int n);
142 double lex_next_tokval (const struct lexer *, int n);
143 struct substring lex_next_tokss (const struct lexer *, int n);
145 /* Token representation. */
146 struct substring lex_next_representation (const struct lexer *,
149 /* Current position. */
150 int lex_get_first_line_number (const struct lexer *, int n);
151 int lex_get_last_line_number (const struct lexer *, int n);
152 int lex_get_first_column (const struct lexer *, int n);
153 int lex_get_last_column (const struct lexer *, int n);
154 const char *lex_get_file_name (const struct lexer *);
155 struct msg_location *lex_get_location (const struct lexer *, int n0, int n1);
156 struct msg_location *lex_get_lines (const struct lexer *, int n0, int n1);
157 const char *lex_get_encoding (const struct lexer *);
159 /* Issuing errors. */
160 void lex_error (struct lexer *, const char *, ...) PRINTF_FORMAT (2, 3);
161 void lex_next_error (struct lexer *, int n0, int n1, const char *, ...)
162 PRINTF_FORMAT (4, 5);
163 int lex_end_of_command (struct lexer *);
165 void lex_error_expecting (struct lexer *, ...) SENTINEL(0);
166 #define lex_error_expecting(...) \
167 lex_error_expecting(__VA_ARGS__, NULL_SENTINEL)
168 void lex_error_expecting_valist (struct lexer *, va_list);
169 void lex_error_expecting_array (struct lexer *, const char **, size_t n);
171 void lex_sbc_only_once (const char *);
172 void lex_sbc_missing (const char *);
174 void lex_spec_only_once (struct lexer *, const char *subcommand,
175 const char *specification);
176 void lex_spec_missing (struct lexer *, const char *subcommand,
177 const char *specification);
179 void lex_error_valist (struct lexer *, const char *, va_list)
180 PRINTF_FORMAT (2, 0);
181 void lex_next_error_valist (struct lexer *lexer, int n0, int n1,
182 const char *format, va_list)
183 PRINTF_FORMAT (4, 0);
185 /* Error handling. */
186 enum segmenter_mode lex_get_syntax_mode (const struct lexer *);
187 enum lex_error_mode lex_get_error_mode (const struct lexer *);
188 void lex_discard_rest_of_command (struct lexer *);
189 void lex_interactive_reset (struct lexer *);
190 void lex_discard_noninteractive (struct lexer *);