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/message.h"
30 #include "libpspp/prompt.h"
31 #include "libpspp/str.h"
37 void lex_source_ref (const struct lex_source *);
38 void lex_source_unref (struct lex_source *);
39 struct substring lex_source_get_line (const struct lex_source *, int line);
41 /* Handling of errors. */
44 LEX_ERROR_TERMINAL, /* Discard input line and continue reading. */
45 LEX_ERROR_CONTINUE, /* Continue to next command, except for
46 cascading failures. */
47 LEX_ERROR_STOP /* Stop processing. */
50 /* Reads a single syntax file as a stream of bytes encoded in UTF-8.
55 const struct lex_reader_class *class;
56 enum segmenter_mode syntax;
57 enum lex_error_mode error;
59 char *file_name; /* NULL if not associated with a file. */
60 int line_number; /* 1-based initial line number, 0 if none. */
64 /* An implementation of a lex_reader. */
65 struct lex_reader_class
67 /* Reads up to N bytes of data from READER into N. Returns the positive
68 number of bytes read if successful, or zero at end of input or on
71 STYLE provides a hint to interactive readers as to what kind of syntax
72 is being read right now. */
73 size_t (*read) (struct lex_reader *reader, char *buf, size_t n,
74 enum prompt_style style);
76 /* Closes and destroys READER, releasing any allocated storage.
78 The caller will free the 'file_name' member of READER, so the
79 implementation should not do so. */
80 void (*destroy) (struct lex_reader *reader);
83 /* Helper functions for lex_reader. */
84 void lex_reader_init (struct lex_reader *, const struct lex_reader_class *);
85 void lex_reader_set_file_name (struct lex_reader *, const char *file_name);
87 /* Creating various kinds of lex_readers. */
88 struct lex_reader *lex_reader_for_file (const char *file_name,
90 enum segmenter_mode syntax,
91 enum lex_error_mode error);
92 struct lex_reader *lex_reader_for_string (const char *, const char *encoding);
93 struct lex_reader *lex_reader_for_format (const char *, const char *, ...)
95 struct lex_reader *lex_reader_for_substring_nocopy (struct substring, const char *encoding);
98 struct lexer *lex_create (void);
99 void lex_destroy (struct lexer *);
102 void lex_define_macro (struct lexer *, struct macro *);
105 void lex_include (struct lexer *, struct lex_reader *);
106 void lex_append (struct lexer *, struct lex_reader *);
109 void lex_get (struct lexer *);
110 void lex_get_n (struct lexer *, size_t n);
112 /* Token testing functions. */
113 bool lex_is_number (const struct lexer *);
114 double lex_number (const struct lexer *);
115 bool lex_is_integer (const struct lexer *);
116 long lex_integer (const struct lexer *);
117 bool lex_is_string (const struct lexer *);
119 /* Token testing functions with lookahead. */
120 bool lex_next_is_number (const struct lexer *, int n);
121 double lex_next_number (const struct lexer *, int n);
122 bool lex_next_is_integer (const struct lexer *, int n);
123 long lex_next_integer (const struct lexer *, int n);
124 bool lex_next_is_string (const struct lexer *, int n);
126 /* Token matching functions. */
127 bool lex_match (struct lexer *, enum token_type);
128 bool lex_match_id (struct lexer *, const char *);
129 bool lex_match_id_n (struct lexer *, const char *, size_t n);
130 bool lex_match_int (struct lexer *, int);
131 bool lex_at_phrase (struct lexer *, const char *s);
132 bool lex_match_phrase (struct lexer *, const char *s);
134 /* Forcible matching functions. */
135 bool lex_force_match (struct lexer *, enum token_type) WARN_UNUSED_RESULT;
136 bool lex_force_match_id (struct lexer *, const char *) WARN_UNUSED_RESULT;
137 bool lex_force_int (struct lexer *) WARN_UNUSED_RESULT;
138 bool lex_force_int_range (struct lexer *, const char *name,
139 long min, long max) WARN_UNUSED_RESULT;
140 bool lex_force_num (struct lexer *) WARN_UNUSED_RESULT;
141 bool lex_force_id (struct lexer *) WARN_UNUSED_RESULT;
142 bool lex_force_string (struct lexer *) WARN_UNUSED_RESULT;
143 bool lex_force_string_or_id (struct lexer *) WARN_UNUSED_RESULT;
145 /* Token accessors. */
146 enum token_type lex_token (const struct lexer *);
147 double lex_tokval (const struct lexer *);
148 const char *lex_tokcstr (const struct lexer *);
149 struct substring lex_tokss (const struct lexer *);
152 const struct token *lex_next (const struct lexer *, int n);
153 enum token_type lex_next_token (const struct lexer *, int n);
154 const char *lex_next_tokcstr (const struct lexer *, int n);
155 double lex_next_tokval (const struct lexer *, int n);
156 struct substring lex_next_tokss (const struct lexer *, int n);
158 int lex_ofs (const struct lexer *);
159 const struct token *lex_ofs_token (const struct lexer *, int ofs);
160 struct msg_location *lex_ofs_location (const struct lexer *, int ofs0, int ofs1);
161 struct msg_point lex_ofs_start_point (const struct lexer *, int ofs);
162 struct msg_point lex_ofs_end_point (const struct lexer *, int ofs);
164 /* Token representation. */
165 char *lex_next_representation (const struct lexer *, int n0, int n1);
166 bool lex_next_is_from_macro (const struct lexer *, int n);
168 /* Current position. */
169 int lex_get_first_line_number (const struct lexer *, int n);
170 int lex_get_last_line_number (const struct lexer *, int n);
171 int lex_get_first_column (const struct lexer *, int n);
172 int lex_get_last_column (const struct lexer *, int n);
173 const char *lex_get_file_name (const struct lexer *);
174 struct msg_location *lex_get_location (const struct lexer *, int n0, int n1);
175 struct msg_location *lex_get_lines (const struct lexer *, int n0, int n1);
176 void lex_extend_location (const struct lexer *, int n, struct msg_location **);
177 const char *lex_get_encoding (const struct lexer *);
179 /* Issuing errors. */
180 void lex_error (struct lexer *, const char *, ...) PRINTF_FORMAT (2, 3);
181 void lex_next_error (struct lexer *, int n0, int n1, const char *, ...)
182 PRINTF_FORMAT (4, 5);
183 int lex_end_of_command (struct lexer *);
185 void lex_error_expecting (struct lexer *, ...) SENTINEL(0);
186 #define lex_error_expecting(...) \
187 lex_error_expecting(__VA_ARGS__, NULL_SENTINEL)
188 void lex_error_expecting_valist (struct lexer *, va_list);
189 void lex_error_expecting_array (struct lexer *, const char **, size_t n);
191 void lex_sbc_only_once (const char *);
192 void lex_sbc_missing (const char *);
194 void lex_spec_only_once (struct lexer *, const char *subcommand,
195 const char *specification);
196 void lex_spec_missing (struct lexer *, const char *subcommand,
197 const char *specification);
199 void lex_error_valist (struct lexer *, const char *, va_list)
200 PRINTF_FORMAT (2, 0);
201 void lex_next_error_valist (struct lexer *lexer, int n0, int n1,
202 const char *format, va_list)
203 PRINTF_FORMAT (4, 0);
205 /* Error handling. */
206 enum segmenter_mode lex_get_syntax_mode (const struct lexer *);
207 enum lex_error_mode lex_get_error_mode (const struct lexer *);
208 void lex_discard_rest_of_command (struct lexer *);
209 void lex_interactive_reset (struct lexer *);
210 void lex_discard_noninteractive (struct lexer *);