debase-ruby_core_source 3.3.0 → 3.3.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (29) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +4 -0
  3. data/Rakefile +2 -1
  4. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/ast.h +4612 -0
  5. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/defines.h +94 -0
  6. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/diagnostic.h +297 -0
  7. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/encoding.h +248 -0
  8. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/extension.h +18 -0
  9. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/node.h +57 -0
  10. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/options.h +204 -0
  11. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/pack.h +152 -0
  12. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/parser.h +716 -0
  13. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/prettyprint.h +26 -0
  14. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/prism.h +272 -0
  15. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/regexp.h +33 -0
  16. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_buffer.h +146 -0
  17. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_char.h +205 -0
  18. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_constant_pool.h +191 -0
  19. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_list.h +97 -0
  20. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_memchr.h +29 -0
  21. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_newline_list.h +104 -0
  22. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_state_stack.h +42 -0
  23. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_string.h +150 -0
  24. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_string_list.h +44 -0
  25. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_strncasecmp.h +32 -0
  26. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/util/pm_strpbrk.h +43 -0
  27. data/lib/debase/ruby_core_source/ruby-3.3.0-p0/prism/version.h +29 -0
  28. data/lib/debase/ruby_core_source/version.rb +1 -1
  29. metadata +30 -6
@@ -0,0 +1,94 @@
1
+ /**
2
+ * @file defines.h
3
+ *
4
+ * Macro definitions used throughout the prism library.
5
+ *
6
+ * This file should be included first by any *.h or *.c in prism for consistency
7
+ * and to ensure that the macros are defined before they are used.
8
+ */
9
+ #ifndef PRISM_DEFINES_H
10
+ #define PRISM_DEFINES_H
11
+
12
+ #include <ctype.h>
13
+ #include <stdarg.h>
14
+ #include <stddef.h>
15
+ #include <stdint.h>
16
+ #include <stdio.h>
17
+ #include <string.h>
18
+
19
+ /**
20
+ * By default, we compile with -fvisibility=hidden. When this is enabled, we
21
+ * need to mark certain functions as being publically-visible. This macro does
22
+ * that in a compiler-agnostic way.
23
+ */
24
+ #ifndef PRISM_EXPORTED_FUNCTION
25
+ # ifdef PRISM_EXPORT_SYMBOLS
26
+ # ifdef _WIN32
27
+ # define PRISM_EXPORTED_FUNCTION __declspec(dllexport) extern
28
+ # else
29
+ # define PRISM_EXPORTED_FUNCTION __attribute__((__visibility__("default"))) extern
30
+ # endif
31
+ # else
32
+ # define PRISM_EXPORTED_FUNCTION
33
+ # endif
34
+ #endif
35
+
36
+ /**
37
+ * Certain compilers support specifying that a function accepts variadic
38
+ * parameters that look like printf format strings to provide a better developer
39
+ * experience when someone is using the function. This macro does that in a
40
+ * compiler-agnostic way.
41
+ */
42
+ #if defined(__GNUC__)
43
+ # define PRISM_ATTRIBUTE_FORMAT(string_index, argument_index) __attribute__((format(printf, string_index, argument_index)))
44
+ #elif defined(__clang__)
45
+ # define PRISM_ATTRIBUTE_FORMAT(string_index, argument_index) __attribute__((__format__(__printf__, string_index, argument_index)))
46
+ #else
47
+ # define PRISM_ATTRIBUTE_FORMAT(string_index, argument_index)
48
+ #endif
49
+
50
+ /**
51
+ * GCC will warn if you specify a function or parameter that is unused at
52
+ * runtime. This macro allows you to mark a function or parameter as unused in a
53
+ * compiler-agnostic way.
54
+ */
55
+ #if defined(__GNUC__)
56
+ # define PRISM_ATTRIBUTE_UNUSED __attribute__((unused))
57
+ #else
58
+ # define PRISM_ATTRIBUTE_UNUSED
59
+ #endif
60
+
61
+ /**
62
+ * Old Visual Studio versions do not support the inline keyword, so we need to
63
+ * define it to be __inline.
64
+ */
65
+ #if defined(_MSC_VER) && !defined(inline)
66
+ # define inline __inline
67
+ #endif
68
+
69
+ /**
70
+ * Old Visual Studio versions before 2015 do not implement sprintf, but instead
71
+ * implement _snprintf. We standard that here.
72
+ */
73
+ #if !defined(snprintf) && defined(_MSC_VER) && (_MSC_VER < 1900)
74
+ # define snprintf _snprintf
75
+ #endif
76
+
77
+ /**
78
+ * A simple utility macro to concatenate two tokens together, necessary when one
79
+ * of the tokens is itself a macro.
80
+ */
81
+ #define PM_CONCATENATE(left, right) left ## right
82
+
83
+ /**
84
+ * We want to be able to use static assertions, but they weren't standardized
85
+ * until C11. As such, we polyfill it here by making a hacky typedef that will
86
+ * fail to compile due to a negative array size if the condition is false.
87
+ */
88
+ #if defined(_Static_assert)
89
+ # define PM_STATIC_ASSERT(line, condition, message) _Static_assert(condition, message)
90
+ #else
91
+ # define PM_STATIC_ASSERT(line, condition, message) typedef char PM_CONCATENATE(static_assert_, line)[(condition) ? 1 : -1]
92
+ #endif
93
+
94
+ #endif
@@ -0,0 +1,297 @@
1
+ /**
2
+ * @file diagnostic.h
3
+ *
4
+ * A list of diagnostics generated during parsing.
5
+ */
6
+ #ifndef PRISM_DIAGNOSTIC_H
7
+ #define PRISM_DIAGNOSTIC_H
8
+
9
+ #include "prism/ast.h"
10
+ #include "prism/defines.h"
11
+ #include "prism/util/pm_list.h"
12
+
13
+ #include <stdbool.h>
14
+ #include <stdlib.h>
15
+ #include <assert.h>
16
+
17
+ /**
18
+ * This struct represents a diagnostic generated during parsing.
19
+ *
20
+ * @extends pm_list_node_t
21
+ */
22
+ typedef struct {
23
+ /** The embedded base node. */
24
+ pm_list_node_t node;
25
+
26
+ /** The location of the diagnostic in the source. */
27
+ pm_location_t location;
28
+
29
+ /** The message associated with the diagnostic. */
30
+ const char *message;
31
+
32
+ /**
33
+ * Whether or not the memory related to the message of this diagnostic is
34
+ * owned by this diagnostic. If it is, it needs to be freed when the
35
+ * diagnostic is freed.
36
+ */
37
+ bool owned;
38
+ } pm_diagnostic_t;
39
+
40
+ /**
41
+ * The diagnostic IDs of all of the diagnostics, used to communicate the types
42
+ * of errors between the parser and the user.
43
+ */
44
+ typedef enum {
45
+ PM_ERR_ALIAS_ARGUMENT,
46
+ PM_ERR_AMPAMPEQ_MULTI_ASSIGN,
47
+ PM_ERR_ARGUMENT_AFTER_BLOCK,
48
+ PM_ERR_ARGUMENT_AFTER_FORWARDING_ELLIPSES,
49
+ PM_ERR_ARGUMENT_BARE_HASH,
50
+ PM_ERR_ARGUMENT_BLOCK_MULTI,
51
+ PM_ERR_ARGUMENT_FORMAL_CLASS,
52
+ PM_ERR_ARGUMENT_FORMAL_CONSTANT,
53
+ PM_ERR_ARGUMENT_FORMAL_GLOBAL,
54
+ PM_ERR_ARGUMENT_FORMAL_IVAR,
55
+ PM_ERR_ARGUMENT_FORWARDING_UNBOUND,
56
+ PM_ERR_ARGUMENT_NO_FORWARDING_AMP,
57
+ PM_ERR_ARGUMENT_NO_FORWARDING_ELLIPSES,
58
+ PM_ERR_ARGUMENT_NO_FORWARDING_STAR,
59
+ PM_ERR_ARGUMENT_SPLAT_AFTER_ASSOC_SPLAT,
60
+ PM_ERR_ARGUMENT_SPLAT_AFTER_SPLAT,
61
+ PM_ERR_ARGUMENT_TERM_PAREN,
62
+ PM_ERR_ARGUMENT_UNEXPECTED_BLOCK,
63
+ PM_ERR_ARRAY_ELEMENT,
64
+ PM_ERR_ARRAY_EXPRESSION,
65
+ PM_ERR_ARRAY_EXPRESSION_AFTER_STAR,
66
+ PM_ERR_ARRAY_SEPARATOR,
67
+ PM_ERR_ARRAY_TERM,
68
+ PM_ERR_BEGIN_LONELY_ELSE,
69
+ PM_ERR_BEGIN_TERM,
70
+ PM_ERR_BEGIN_UPCASE_BRACE,
71
+ PM_ERR_BEGIN_UPCASE_TERM,
72
+ PM_ERR_BEGIN_UPCASE_TOPLEVEL,
73
+ PM_ERR_BLOCK_PARAM_LOCAL_VARIABLE,
74
+ PM_ERR_BLOCK_PARAM_PIPE_TERM,
75
+ PM_ERR_BLOCK_TERM_BRACE,
76
+ PM_ERR_BLOCK_TERM_END,
77
+ PM_ERR_CANNOT_PARSE_EXPRESSION,
78
+ PM_ERR_CANNOT_PARSE_STRING_PART,
79
+ PM_ERR_CASE_EXPRESSION_AFTER_CASE,
80
+ PM_ERR_CASE_EXPRESSION_AFTER_WHEN,
81
+ PM_ERR_CASE_MATCH_MISSING_PREDICATE,
82
+ PM_ERR_CASE_MISSING_CONDITIONS,
83
+ PM_ERR_CASE_TERM,
84
+ PM_ERR_CLASS_IN_METHOD,
85
+ PM_ERR_CLASS_NAME,
86
+ PM_ERR_CLASS_SUPERCLASS,
87
+ PM_ERR_CLASS_TERM,
88
+ PM_ERR_CLASS_UNEXPECTED_END,
89
+ PM_ERR_CONDITIONAL_ELSIF_PREDICATE,
90
+ PM_ERR_CONDITIONAL_IF_PREDICATE,
91
+ PM_ERR_CONDITIONAL_PREDICATE_TERM,
92
+ PM_ERR_CONDITIONAL_TERM,
93
+ PM_ERR_CONDITIONAL_TERM_ELSE,
94
+ PM_ERR_CONDITIONAL_UNLESS_PREDICATE,
95
+ PM_ERR_CONDITIONAL_UNTIL_PREDICATE,
96
+ PM_ERR_CONDITIONAL_WHILE_PREDICATE,
97
+ PM_ERR_CONSTANT_PATH_COLON_COLON_CONSTANT,
98
+ PM_ERR_DEF_ENDLESS,
99
+ PM_ERR_DEF_ENDLESS_SETTER,
100
+ PM_ERR_DEF_NAME,
101
+ PM_ERR_DEF_NAME_AFTER_RECEIVER,
102
+ PM_ERR_DEF_PARAMS_TERM,
103
+ PM_ERR_DEF_PARAMS_TERM_PAREN,
104
+ PM_ERR_DEF_RECEIVER,
105
+ PM_ERR_DEF_RECEIVER_TERM,
106
+ PM_ERR_DEF_TERM,
107
+ PM_ERR_DEFINED_EXPRESSION,
108
+ PM_ERR_EMBDOC_TERM,
109
+ PM_ERR_EMBEXPR_END,
110
+ PM_ERR_EMBVAR_INVALID,
111
+ PM_ERR_END_UPCASE_BRACE,
112
+ PM_ERR_END_UPCASE_TERM,
113
+ PM_ERR_ESCAPE_INVALID_CONTROL,
114
+ PM_ERR_ESCAPE_INVALID_CONTROL_REPEAT,
115
+ PM_ERR_ESCAPE_INVALID_HEXADECIMAL,
116
+ PM_ERR_ESCAPE_INVALID_META,
117
+ PM_ERR_ESCAPE_INVALID_META_REPEAT,
118
+ PM_ERR_ESCAPE_INVALID_UNICODE,
119
+ PM_ERR_ESCAPE_INVALID_UNICODE_CM_FLAGS,
120
+ PM_ERR_ESCAPE_INVALID_UNICODE_LITERAL,
121
+ PM_ERR_ESCAPE_INVALID_UNICODE_LONG,
122
+ PM_ERR_ESCAPE_INVALID_UNICODE_TERM,
123
+ PM_ERR_EXPECT_ARGUMENT,
124
+ PM_ERR_EXPECT_EOL_AFTER_STATEMENT,
125
+ PM_ERR_EXPECT_EXPRESSION_AFTER_AMPAMPEQ,
126
+ PM_ERR_EXPECT_EXPRESSION_AFTER_PIPEPIPEEQ,
127
+ PM_ERR_EXPECT_EXPRESSION_AFTER_COMMA,
128
+ PM_ERR_EXPECT_EXPRESSION_AFTER_EQUAL,
129
+ PM_ERR_EXPECT_EXPRESSION_AFTER_LESS_LESS,
130
+ PM_ERR_EXPECT_EXPRESSION_AFTER_LPAREN,
131
+ PM_ERR_EXPECT_EXPRESSION_AFTER_QUESTION,
132
+ PM_ERR_EXPECT_EXPRESSION_AFTER_OPERATOR,
133
+ PM_ERR_EXPECT_EXPRESSION_AFTER_SPLAT,
134
+ PM_ERR_EXPECT_EXPRESSION_AFTER_SPLAT_HASH,
135
+ PM_ERR_EXPECT_EXPRESSION_AFTER_STAR,
136
+ PM_ERR_EXPECT_IDENT_REQ_PARAMETER,
137
+ PM_ERR_EXPECT_LPAREN_REQ_PARAMETER,
138
+ PM_ERR_EXPECT_RBRACKET,
139
+ PM_ERR_EXPECT_RPAREN,
140
+ PM_ERR_EXPECT_RPAREN_AFTER_MULTI,
141
+ PM_ERR_EXPECT_RPAREN_REQ_PARAMETER,
142
+ PM_ERR_EXPECT_STRING_CONTENT,
143
+ PM_ERR_EXPECT_WHEN_DELIMITER,
144
+ PM_ERR_EXPRESSION_BARE_HASH,
145
+ PM_ERR_FOR_COLLECTION,
146
+ PM_ERR_FOR_IN,
147
+ PM_ERR_FOR_INDEX,
148
+ PM_ERR_FOR_TERM,
149
+ PM_ERR_HASH_EXPRESSION_AFTER_LABEL,
150
+ PM_ERR_HASH_KEY,
151
+ PM_ERR_HASH_ROCKET,
152
+ PM_ERR_HASH_TERM,
153
+ PM_ERR_HASH_VALUE,
154
+ PM_ERR_HEREDOC_TERM,
155
+ PM_ERR_INCOMPLETE_QUESTION_MARK,
156
+ PM_ERR_INCOMPLETE_VARIABLE_CLASS,
157
+ PM_ERR_INCOMPLETE_VARIABLE_INSTANCE,
158
+ PM_ERR_INVALID_ENCODING_MAGIC_COMMENT,
159
+ PM_ERR_INVALID_FLOAT_EXPONENT,
160
+ PM_ERR_INVALID_NUMBER_BINARY,
161
+ PM_ERR_INVALID_NUMBER_DECIMAL,
162
+ PM_ERR_INVALID_NUMBER_HEXADECIMAL,
163
+ PM_ERR_INVALID_NUMBER_OCTAL,
164
+ PM_ERR_INVALID_NUMBER_UNDERSCORE,
165
+ PM_ERR_INVALID_PERCENT,
166
+ PM_ERR_INVALID_TOKEN,
167
+ PM_ERR_INVALID_VARIABLE_GLOBAL,
168
+ PM_ERR_LAMBDA_OPEN,
169
+ PM_ERR_LAMBDA_TERM_BRACE,
170
+ PM_ERR_LAMBDA_TERM_END,
171
+ PM_ERR_LIST_I_LOWER_ELEMENT,
172
+ PM_ERR_LIST_I_LOWER_TERM,
173
+ PM_ERR_LIST_I_UPPER_ELEMENT,
174
+ PM_ERR_LIST_I_UPPER_TERM,
175
+ PM_ERR_LIST_W_LOWER_ELEMENT,
176
+ PM_ERR_LIST_W_LOWER_TERM,
177
+ PM_ERR_LIST_W_UPPER_ELEMENT,
178
+ PM_ERR_LIST_W_UPPER_TERM,
179
+ PM_ERR_MALLOC_FAILED,
180
+ PM_ERR_MIXED_ENCODING,
181
+ PM_ERR_MODULE_IN_METHOD,
182
+ PM_ERR_MODULE_NAME,
183
+ PM_ERR_MODULE_TERM,
184
+ PM_ERR_MULTI_ASSIGN_MULTI_SPLATS,
185
+ PM_ERR_NOT_EXPRESSION,
186
+ PM_ERR_NUMBER_LITERAL_UNDERSCORE,
187
+ PM_ERR_NUMBERED_PARAMETER_NOT_ALLOWED,
188
+ PM_ERR_NUMBERED_PARAMETER_OUTER_SCOPE,
189
+ PM_ERR_OPERATOR_MULTI_ASSIGN,
190
+ PM_ERR_OPERATOR_WRITE_ARGUMENTS,
191
+ PM_ERR_OPERATOR_WRITE_BLOCK,
192
+ PM_ERR_PARAMETER_ASSOC_SPLAT_MULTI,
193
+ PM_ERR_PARAMETER_BLOCK_MULTI,
194
+ PM_ERR_PARAMETER_CIRCULAR,
195
+ PM_ERR_PARAMETER_METHOD_NAME,
196
+ PM_ERR_PARAMETER_NAME_REPEAT,
197
+ PM_ERR_PARAMETER_NO_DEFAULT,
198
+ PM_ERR_PARAMETER_NO_DEFAULT_KW,
199
+ PM_ERR_PARAMETER_NUMBERED_RESERVED,
200
+ PM_ERR_PARAMETER_ORDER,
201
+ PM_ERR_PARAMETER_SPLAT_MULTI,
202
+ PM_ERR_PARAMETER_STAR,
203
+ PM_ERR_PARAMETER_UNEXPECTED_FWD,
204
+ PM_ERR_PARAMETER_WILD_LOOSE_COMMA,
205
+ PM_ERR_PATTERN_EXPRESSION_AFTER_BRACKET,
206
+ PM_ERR_PATTERN_EXPRESSION_AFTER_HROCKET,
207
+ PM_ERR_PATTERN_EXPRESSION_AFTER_COMMA,
208
+ PM_ERR_PATTERN_EXPRESSION_AFTER_IN,
209
+ PM_ERR_PATTERN_EXPRESSION_AFTER_KEY,
210
+ PM_ERR_PATTERN_EXPRESSION_AFTER_PAREN,
211
+ PM_ERR_PATTERN_EXPRESSION_AFTER_PIN,
212
+ PM_ERR_PATTERN_EXPRESSION_AFTER_PIPE,
213
+ PM_ERR_PATTERN_EXPRESSION_AFTER_RANGE,
214
+ PM_ERR_PATTERN_EXPRESSION_AFTER_REST,
215
+ PM_ERR_PATTERN_HASH_KEY,
216
+ PM_ERR_PATTERN_HASH_KEY_LABEL,
217
+ PM_ERR_PATTERN_IDENT_AFTER_HROCKET,
218
+ PM_ERR_PATTERN_LABEL_AFTER_COMMA,
219
+ PM_ERR_PATTERN_REST,
220
+ PM_ERR_PATTERN_TERM_BRACE,
221
+ PM_ERR_PATTERN_TERM_BRACKET,
222
+ PM_ERR_PATTERN_TERM_PAREN,
223
+ PM_ERR_PIPEPIPEEQ_MULTI_ASSIGN,
224
+ PM_ERR_REGEXP_TERM,
225
+ PM_ERR_RESCUE_EXPRESSION,
226
+ PM_ERR_RESCUE_MODIFIER_VALUE,
227
+ PM_ERR_RESCUE_TERM,
228
+ PM_ERR_RESCUE_VARIABLE,
229
+ PM_ERR_RETURN_INVALID,
230
+ PM_ERR_STATEMENT_ALIAS,
231
+ PM_ERR_STATEMENT_POSTEXE_END,
232
+ PM_ERR_STATEMENT_PREEXE_BEGIN,
233
+ PM_ERR_STATEMENT_UNDEF,
234
+ PM_ERR_STRING_CONCATENATION,
235
+ PM_ERR_STRING_INTERPOLATED_TERM,
236
+ PM_ERR_STRING_LITERAL_TERM,
237
+ PM_ERR_SYMBOL_INVALID,
238
+ PM_ERR_SYMBOL_TERM_DYNAMIC,
239
+ PM_ERR_SYMBOL_TERM_INTERPOLATED,
240
+ PM_ERR_TERNARY_COLON,
241
+ PM_ERR_TERNARY_EXPRESSION_FALSE,
242
+ PM_ERR_TERNARY_EXPRESSION_TRUE,
243
+ PM_ERR_UNARY_RECEIVER_BANG,
244
+ PM_ERR_UNARY_RECEIVER_MINUS,
245
+ PM_ERR_UNARY_RECEIVER_PLUS,
246
+ PM_ERR_UNARY_RECEIVER_TILDE,
247
+ PM_ERR_UNDEF_ARGUMENT,
248
+ PM_ERR_UNTIL_TERM,
249
+ PM_ERR_VOID_EXPRESSION,
250
+ PM_ERR_WHILE_TERM,
251
+ PM_ERR_WRITE_TARGET_IN_METHOD,
252
+ PM_ERR_WRITE_TARGET_READONLY,
253
+ PM_ERR_WRITE_TARGET_UNEXPECTED,
254
+ PM_ERR_XSTRING_TERM,
255
+ PM_WARN_AMBIGUOUS_FIRST_ARGUMENT_MINUS,
256
+ PM_WARN_AMBIGUOUS_FIRST_ARGUMENT_PLUS,
257
+ PM_WARN_AMBIGUOUS_PREFIX_STAR,
258
+ PM_WARN_AMBIGUOUS_SLASH,
259
+ PM_WARN_END_IN_METHOD,
260
+
261
+ /* This must be the last member. */
262
+ PM_DIAGNOSTIC_ID_LEN,
263
+ } pm_diagnostic_id_t;
264
+
265
+ /**
266
+ * Append a diagnostic to the given list of diagnostics that is using shared
267
+ * memory for its message.
268
+ *
269
+ * @param list The list to append to.
270
+ * @param start The start of the diagnostic.
271
+ * @param end The end of the diagnostic.
272
+ * @param diag_id The diagnostic ID.
273
+ * @return Whether the diagnostic was successfully appended.
274
+ */
275
+ bool pm_diagnostic_list_append(pm_list_t *list, const uint8_t *start, const uint8_t *end, pm_diagnostic_id_t diag_id);
276
+
277
+ /**
278
+ * Append a diagnostic to the given list of diagnostics that is using a format
279
+ * string for its message.
280
+ *
281
+ * @param list The list to append to.
282
+ * @param start The start of the diagnostic.
283
+ * @param end The end of the diagnostic.
284
+ * @param diag_id The diagnostic ID.
285
+ * @param ... The arguments to the format string for the message.
286
+ * @return Whether the diagnostic was successfully appended.
287
+ */
288
+ bool pm_diagnostic_list_append_format(pm_list_t *list, const uint8_t *start, const uint8_t *end, pm_diagnostic_id_t diag_id, ...);
289
+
290
+ /**
291
+ * Deallocate the internal state of the given diagnostic list.
292
+ *
293
+ * @param list The list to deallocate.
294
+ */
295
+ void pm_diagnostic_list_free(pm_list_t *list);
296
+
297
+ #endif
@@ -0,0 +1,248 @@
1
+ /**
2
+ * @file encoding.h
3
+ *
4
+ * The encoding interface and implementations used by the parser.
5
+ */
6
+ #ifndef PRISM_ENCODING_H
7
+ #define PRISM_ENCODING_H
8
+
9
+ #include "prism/defines.h"
10
+ #include "prism/util/pm_strncasecmp.h"
11
+
12
+ #include <assert.h>
13
+ #include <stdbool.h>
14
+ #include <stddef.h>
15
+ #include <stdint.h>
16
+
17
+ /**
18
+ * This struct defines the functions necessary to implement the encoding
19
+ * interface so we can determine how many bytes the subsequent character takes.
20
+ * Each callback should return the number of bytes, or 0 if the next bytes are
21
+ * invalid for the encoding and type.
22
+ */
23
+ typedef struct {
24
+ /**
25
+ * Return the number of bytes that the next character takes if it is valid
26
+ * in the encoding. Does not read more than n bytes. It is assumed that n is
27
+ * at least 1.
28
+ */
29
+ size_t (*char_width)(const uint8_t *b, ptrdiff_t n);
30
+
31
+ /**
32
+ * Return the number of bytes that the next character takes if it is valid
33
+ * in the encoding and is alphabetical. Does not read more than n bytes. It
34
+ * is assumed that n is at least 1.
35
+ */
36
+ size_t (*alpha_char)(const uint8_t *b, ptrdiff_t n);
37
+
38
+ /**
39
+ * Return the number of bytes that the next character takes if it is valid
40
+ * in the encoding and is alphanumeric. Does not read more than n bytes. It
41
+ * is assumed that n is at least 1.
42
+ */
43
+ size_t (*alnum_char)(const uint8_t *b, ptrdiff_t n);
44
+
45
+ /**
46
+ * Return true if the next character is valid in the encoding and is an
47
+ * uppercase character. Does not read more than n bytes. It is assumed that
48
+ * n is at least 1.
49
+ */
50
+ bool (*isupper_char)(const uint8_t *b, ptrdiff_t n);
51
+
52
+ /**
53
+ * The name of the encoding. This should correspond to a value that can be
54
+ * passed to Encoding.find in Ruby.
55
+ */
56
+ const char *name;
57
+
58
+ /**
59
+ * Return true if the encoding is a multibyte encoding.
60
+ */
61
+ bool multibyte;
62
+ } pm_encoding_t;
63
+
64
+ /**
65
+ * All of the lookup tables use the first bit of each embedded byte to indicate
66
+ * whether the codepoint is alphabetical.
67
+ */
68
+ #define PRISM_ENCODING_ALPHABETIC_BIT 1 << 0
69
+
70
+ /**
71
+ * All of the lookup tables use the second bit of each embedded byte to indicate
72
+ * whether the codepoint is alphanumeric.
73
+ */
74
+ #define PRISM_ENCODING_ALPHANUMERIC_BIT 1 << 1
75
+
76
+ /**
77
+ * All of the lookup tables use the third bit of each embedded byte to indicate
78
+ * whether the codepoint is uppercase.
79
+ */
80
+ #define PRISM_ENCODING_UPPERCASE_BIT 1 << 2
81
+
82
+ /**
83
+ * Return the size of the next character in the UTF-8 encoding if it is an
84
+ * alphabetical character.
85
+ *
86
+ * @param b The bytes to read.
87
+ * @param n The number of bytes that can be read.
88
+ * @returns The number of bytes that the next character takes if it is valid in
89
+ * the encoding, or 0 if it is not.
90
+ */
91
+ size_t pm_encoding_utf_8_alpha_char(const uint8_t *b, ptrdiff_t n);
92
+
93
+ /**
94
+ * Return the size of the next character in the UTF-8 encoding if it is an
95
+ * alphanumeric character.
96
+ *
97
+ * @param b The bytes to read.
98
+ * @param n The number of bytes that can be read.
99
+ * @returns The number of bytes that the next character takes if it is valid in
100
+ * the encoding, or 0 if it is not.
101
+ */
102
+ size_t pm_encoding_utf_8_alnum_char(const uint8_t *b, ptrdiff_t n);
103
+
104
+ /**
105
+ * Return true if the next character in the UTF-8 encoding if it is an uppercase
106
+ * character.
107
+ *
108
+ * @param b The bytes to read.
109
+ * @param n The number of bytes that can be read.
110
+ * @returns True if the next character is valid in the encoding and is an
111
+ * uppercase character, or false if it is not.
112
+ */
113
+ bool pm_encoding_utf_8_isupper_char(const uint8_t *b, ptrdiff_t n);
114
+
115
+ /**
116
+ * This lookup table is referenced in both the UTF-8 encoding file and the
117
+ * parser directly in order to speed up the default encoding processing. It is
118
+ * used to indicate whether a character is alphabetical, alphanumeric, or
119
+ * uppercase in unicode mappings.
120
+ */
121
+ extern const uint8_t pm_encoding_unicode_table[256];
122
+
123
+ /**
124
+ * These are all of the encodings that prism supports.
125
+ */
126
+ typedef enum {
127
+ PM_ENCODING_UTF_8 = 0,
128
+ PM_ENCODING_ASCII_8BIT,
129
+ PM_ENCODING_BIG5,
130
+ PM_ENCODING_BIG5_HKSCS,
131
+ PM_ENCODING_BIG5_UAO,
132
+ PM_ENCODING_CESU_8,
133
+ PM_ENCODING_CP51932,
134
+ PM_ENCODING_CP850,
135
+ PM_ENCODING_CP852,
136
+ PM_ENCODING_CP855,
137
+ PM_ENCODING_CP949,
138
+ PM_ENCODING_CP950,
139
+ PM_ENCODING_CP951,
140
+ PM_ENCODING_EMACS_MULE,
141
+ PM_ENCODING_EUC_JP,
142
+ PM_ENCODING_EUC_JP_MS,
143
+ PM_ENCODING_EUC_JIS_2004,
144
+ PM_ENCODING_EUC_KR,
145
+ PM_ENCODING_EUC_TW,
146
+ PM_ENCODING_GB12345,
147
+ PM_ENCODING_GB18030,
148
+ PM_ENCODING_GB1988,
149
+ PM_ENCODING_GB2312,
150
+ PM_ENCODING_GBK,
151
+ PM_ENCODING_IBM437,
152
+ PM_ENCODING_IBM720,
153
+ PM_ENCODING_IBM737,
154
+ PM_ENCODING_IBM775,
155
+ PM_ENCODING_IBM852,
156
+ PM_ENCODING_IBM855,
157
+ PM_ENCODING_IBM857,
158
+ PM_ENCODING_IBM860,
159
+ PM_ENCODING_IBM861,
160
+ PM_ENCODING_IBM862,
161
+ PM_ENCODING_IBM863,
162
+ PM_ENCODING_IBM864,
163
+ PM_ENCODING_IBM865,
164
+ PM_ENCODING_IBM866,
165
+ PM_ENCODING_IBM869,
166
+ PM_ENCODING_ISO_8859_1,
167
+ PM_ENCODING_ISO_8859_2,
168
+ PM_ENCODING_ISO_8859_3,
169
+ PM_ENCODING_ISO_8859_4,
170
+ PM_ENCODING_ISO_8859_5,
171
+ PM_ENCODING_ISO_8859_6,
172
+ PM_ENCODING_ISO_8859_7,
173
+ PM_ENCODING_ISO_8859_8,
174
+ PM_ENCODING_ISO_8859_9,
175
+ PM_ENCODING_ISO_8859_10,
176
+ PM_ENCODING_ISO_8859_11,
177
+ PM_ENCODING_ISO_8859_13,
178
+ PM_ENCODING_ISO_8859_14,
179
+ PM_ENCODING_ISO_8859_15,
180
+ PM_ENCODING_ISO_8859_16,
181
+ PM_ENCODING_KOI8_R,
182
+ PM_ENCODING_KOI8_U,
183
+ PM_ENCODING_MAC_CENT_EURO,
184
+ PM_ENCODING_MAC_CROATIAN,
185
+ PM_ENCODING_MAC_CYRILLIC,
186
+ PM_ENCODING_MAC_GREEK,
187
+ PM_ENCODING_MAC_ICELAND,
188
+ PM_ENCODING_MAC_JAPANESE,
189
+ PM_ENCODING_MAC_ROMAN,
190
+ PM_ENCODING_MAC_ROMANIA,
191
+ PM_ENCODING_MAC_THAI,
192
+ PM_ENCODING_MAC_TURKISH,
193
+ PM_ENCODING_MAC_UKRAINE,
194
+ PM_ENCODING_SHIFT_JIS,
195
+ PM_ENCODING_SJIS_DOCOMO,
196
+ PM_ENCODING_SJIS_KDDI,
197
+ PM_ENCODING_SJIS_SOFTBANK,
198
+ PM_ENCODING_STATELESS_ISO_2022_JP,
199
+ PM_ENCODING_STATELESS_ISO_2022_JP_KDDI,
200
+ PM_ENCODING_TIS_620,
201
+ PM_ENCODING_US_ASCII,
202
+ PM_ENCODING_UTF8_MAC,
203
+ PM_ENCODING_UTF8_DOCOMO,
204
+ PM_ENCODING_UTF8_KDDI,
205
+ PM_ENCODING_UTF8_SOFTBANK,
206
+ PM_ENCODING_WINDOWS_1250,
207
+ PM_ENCODING_WINDOWS_1251,
208
+ PM_ENCODING_WINDOWS_1252,
209
+ PM_ENCODING_WINDOWS_1253,
210
+ PM_ENCODING_WINDOWS_1254,
211
+ PM_ENCODING_WINDOWS_1255,
212
+ PM_ENCODING_WINDOWS_1256,
213
+ PM_ENCODING_WINDOWS_1257,
214
+ PM_ENCODING_WINDOWS_1258,
215
+ PM_ENCODING_WINDOWS_31J,
216
+ PM_ENCODING_WINDOWS_874,
217
+ PM_ENCODING_MAXIMUM
218
+ } pm_encoding_type_t;
219
+
220
+ /**
221
+ * This is the table of all of the encodings that prism supports.
222
+ */
223
+ extern const pm_encoding_t pm_encodings[PM_ENCODING_MAXIMUM];
224
+
225
+ /**
226
+ * This is the default UTF-8 encoding. We need a reference to it to quickly
227
+ * create parsers.
228
+ */
229
+ #define PM_ENCODING_UTF_8_ENTRY (&pm_encodings[PM_ENCODING_UTF_8])
230
+
231
+ /**
232
+ * This is the US-ASCII encoding. We need a reference to it to be able to
233
+ * compare against it when a string is being created because it could possibly
234
+ * need to fall back to ASCII-8BIT.
235
+ */
236
+ #define PM_ENCODING_US_ASCII_ENTRY (&pm_encodings[PM_ENCODING_US_ASCII])
237
+
238
+ /**
239
+ * Parse the given name of an encoding and return a pointer to the corresponding
240
+ * encoding struct if one can be found, otherwise return NULL.
241
+ *
242
+ * @param start A pointer to the first byte of the name.
243
+ * @param end A pointer to the last byte of the name.
244
+ * @returns A pointer to the encoding struct if one is found, otherwise NULL.
245
+ */
246
+ const pm_encoding_t * pm_encoding_find(const uint8_t *start, const uint8_t *end);
247
+
248
+ #endif
@@ -0,0 +1,18 @@
1
+ #ifndef PRISM_EXT_NODE_H
2
+ #define PRISM_EXT_NODE_H
3
+
4
+ #define EXPECTED_PRISM_VERSION "0.19.0"
5
+
6
+ #include <ruby.h>
7
+ #include <ruby/encoding.h>
8
+ #include "prism.h"
9
+
10
+ VALUE pm_source_new(pm_parser_t *parser, rb_encoding *encoding);
11
+ VALUE pm_token_new(pm_parser_t *parser, pm_token_t *token, rb_encoding *encoding, VALUE source);
12
+ VALUE pm_ast_new(pm_parser_t *parser, pm_node_t *node, rb_encoding *encoding);
13
+
14
+ void Init_prism_api_node(void);
15
+ void Init_prism_pack(void);
16
+ PRISM_EXPORTED_FUNCTION void Init_prism(void);
17
+
18
+ #endif
@@ -0,0 +1,57 @@
1
+ /**
2
+ * @file node.h
3
+ *
4
+ * Functions related to nodes in the AST.
5
+ */
6
+ #ifndef PRISM_NODE_H
7
+ #define PRISM_NODE_H
8
+
9
+ #include "prism/defines.h"
10
+ #include "prism/parser.h"
11
+
12
+ /**
13
+ * Append a new node onto the end of the node list.
14
+ *
15
+ * @param list The list to append to.
16
+ * @param node The node to append.
17
+ */
18
+ void pm_node_list_append(pm_node_list_t *list, pm_node_t *node);
19
+
20
+ /**
21
+ * Deallocate a node and all of its children.
22
+ *
23
+ * @param parser The parser that owns the node.
24
+ * @param node The node to deallocate.
25
+ */
26
+ PRISM_EXPORTED_FUNCTION void pm_node_destroy(pm_parser_t *parser, struct pm_node *node);
27
+
28
+ /**
29
+ * This struct stores the information gathered by the pm_node_memsize function.
30
+ * It contains both the memory footprint and additionally metadata about the
31
+ * shape of the tree.
32
+ */
33
+ typedef struct {
34
+ /** The total memory footprint of the node and all of its children. */
35
+ size_t memsize;
36
+
37
+ /** The number of children the node has. */
38
+ size_t node_count;
39
+ } pm_memsize_t;
40
+
41
+ /**
42
+ * Calculates the memory footprint of a given node.
43
+ *
44
+ * @param node The node to calculate the memory footprint of.
45
+ * @param memsize The memory footprint of the node and all of its children.
46
+ */
47
+ PRISM_EXPORTED_FUNCTION void pm_node_memsize(pm_node_t *node, pm_memsize_t *memsize);
48
+
49
+ /**
50
+ * Returns a string representation of the given node type.
51
+ *
52
+ * @param node_type The node type to convert to a string.
53
+ * @return A string representation of the given node type.
54
+ */
55
+ PRISM_EXPORTED_FUNCTION const char * pm_node_type_to_str(pm_node_type_t node_type);
56
+
57
+ #endif