prism 1.9.0 → 2.0.0.rc2

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 (244) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +88 -0
  3. data/CODE_OF_CONDUCT.md +1 -1
  4. data/LICENSE.md +1 -1
  5. data/Makefile +41 -12
  6. data/README.md +35 -97
  7. data/config.yml +174 -161
  8. data/docs/build_system.md +2 -2
  9. data/docs/configuration.md +5 -4
  10. data/docs/encoding.md +2 -2
  11. data/docs/fuzzing.md +4 -11
  12. data/docs/javascript.md +19 -4
  13. data/docs/mapping.md +1 -1
  14. data/docs/releasing.md +77 -5
  15. data/docs/relocation.md +2 -4
  16. data/docs/serialization.md +22 -24
  17. data/docs/testing.md +46 -29
  18. data/ext/prism/api_node.c +1461 -1401
  19. data/ext/prism/extconf.rb +3 -4
  20. data/ext/prism/extension.c +796 -422
  21. data/ext/prism/extension.h +3 -3
  22. data/include/prism/arena.h +37 -0
  23. data/include/prism/ast.h +2727 -610
  24. data/include/prism/buffer.h +52 -0
  25. data/include/prism/comments.h +55 -0
  26. data/include/prism/compiler/accel.h +26 -0
  27. data/include/prism/compiler/align.h +36 -0
  28. data/include/prism/compiler/assume.h +25 -0
  29. data/include/prism/compiler/bswap.h +46 -0
  30. data/include/prism/compiler/endianness.h +34 -0
  31. data/include/prism/compiler/exported.h +24 -0
  32. data/include/prism/compiler/fallthrough.h +22 -0
  33. data/include/prism/compiler/filesystem.h +32 -0
  34. data/include/prism/compiler/flex_array.h +19 -0
  35. data/include/prism/compiler/force_inline.h +21 -0
  36. data/include/prism/compiler/format.h +25 -0
  37. data/include/prism/compiler/inline.h +17 -0
  38. data/include/prism/compiler/nodiscard.h +22 -0
  39. data/include/prism/compiler/nonnull.h +18 -0
  40. data/include/prism/compiler/unused.h +18 -0
  41. data/include/prism/constant_pool.h +81 -0
  42. data/include/prism/diagnostic.h +38 -403
  43. data/include/prism/errors_format.h +53 -0
  44. data/include/prism/excludes.h +29 -0
  45. data/include/prism/integer.h +41 -0
  46. data/include/prism/internal/allocator.h +68 -0
  47. data/include/prism/internal/allocator_debug.h +88 -0
  48. data/include/prism/internal/arena.h +108 -0
  49. data/include/prism/internal/bit.h +42 -0
  50. data/include/prism/internal/buffer.h +94 -0
  51. data/include/prism/internal/char.h +145 -0
  52. data/include/prism/internal/comments.h +53 -0
  53. data/include/prism/internal/constant_pool.h +152 -0
  54. data/include/prism/internal/diagnostic.h +389 -0
  55. data/include/prism/{encoding.h → internal/encoding.h} +27 -68
  56. data/include/prism/internal/integer.h +68 -0
  57. data/include/prism/internal/isinf.h +16 -0
  58. data/include/prism/internal/line_offset_list.h +34 -0
  59. data/include/prism/{util/pm_list.h → internal/list.h} +11 -52
  60. data/include/prism/internal/magic_comments.h +23 -0
  61. data/include/prism/internal/memchr.h +15 -0
  62. data/include/prism/internal/node.h +38 -0
  63. data/include/prism/internal/options.h +232 -0
  64. data/include/prism/internal/parser.h +1004 -0
  65. data/include/prism/internal/regexp.h +26 -0
  66. data/include/prism/internal/serialize.h +39 -0
  67. data/include/prism/internal/source.h +72 -0
  68. data/include/prism/{static_literals.h → internal/static_literals.h} +26 -47
  69. data/include/prism/internal/stringy.h +35 -0
  70. data/include/prism/{util/pm_strncasecmp.h → internal/strncasecmp.h} +3 -17
  71. data/include/prism/{util/pm_strpbrk.h → internal/strpbrk.h} +7 -20
  72. data/include/prism/internal/tokens.h +11 -0
  73. data/include/prism/internal/xxh3.h +16 -0
  74. data/include/prism/json.h +32 -0
  75. data/include/prism/line_offset_list.h +61 -0
  76. data/include/prism/magic_comments.h +35 -0
  77. data/include/prism/node.h +18 -53
  78. data/include/prism/options.h +146 -280
  79. data/include/prism/parser.h +356 -867
  80. data/include/prism/prettyprint.h +6 -9
  81. data/include/prism/serialize.h +115 -0
  82. data/include/prism/source.h +155 -0
  83. data/include/prism/stream.h +28 -0
  84. data/include/prism/string_query.h +74 -0
  85. data/include/prism/stringy.h +72 -0
  86. data/include/prism/version.h +12 -3
  87. data/include/prism.h +43 -320
  88. data/lib/prism/compiler.rb +319 -305
  89. data/lib/prism/desugar_compiler.rb +105 -34
  90. data/lib/prism/dispatcher.rb +646 -473
  91. data/lib/prism/dot_visitor.rb +592 -511
  92. data/lib/prism/dsl.rb +391 -25
  93. data/lib/prism/ffi.rb +258 -90
  94. data/lib/prism/inspect_visitor.rb +357 -325
  95. data/lib/prism/lex_compat.rb +254 -212
  96. data/lib/prism/mutation_compiler.rb +313 -305
  97. data/lib/prism/node.rb +20966 -6992
  98. data/lib/prism/node_ext.rb +180 -187
  99. data/lib/prism/node_find.rb +215 -0
  100. data/lib/prism/parse_result/errors.rb +7 -1
  101. data/lib/prism/parse_result/newlines.rb +276 -8
  102. data/lib/prism/parse_result.rb +468 -139
  103. data/lib/prism/pattern.rb +65 -20
  104. data/lib/prism/reflection.rb +23 -12
  105. data/lib/prism/relocation.rb +149 -87
  106. data/lib/prism/serialize.rb +3460 -539
  107. data/lib/prism/string_query.rb +24 -1
  108. data/lib/prism/translation/parser/builder.rb +10 -2
  109. data/lib/prism/translation/parser/compiler.rb +44 -52
  110. data/lib/prism/translation/parser/lexer.rb +41 -92
  111. data/lib/prism/translation/parser.rb +1 -1
  112. data/lib/prism/translation/parser_current.rb +1 -1
  113. data/lib/prism/translation/ripper/lexer.rb +8 -10
  114. data/lib/prism/translation/ripper/sexp.rb +2 -10
  115. data/lib/prism/translation/ripper/shim.rb +2 -0
  116. data/lib/prism/translation/ripper.rb +967 -209
  117. data/lib/prism/translation/ruby_parser.rb +73 -316
  118. data/lib/prism/translation.rb +2 -0
  119. data/lib/prism/visitor.rb +632 -5
  120. data/lib/prism.rb +79 -9
  121. data/prism.gemspec +128 -62
  122. data/rbi/generated/prism/compiler.rbi +489 -0
  123. data/rbi/generated/prism/desugar_compiler.rbi +306 -0
  124. data/rbi/generated/prism/dispatcher.rbi +1138 -0
  125. data/rbi/generated/prism/dot_visitor.rbi +618 -0
  126. data/rbi/generated/prism/dsl.rbi +751 -0
  127. data/rbi/generated/prism/inspect_visitor.rbi +503 -0
  128. data/rbi/generated/prism/lex_compat.rbi +162 -0
  129. data/rbi/generated/prism/mutation_compiler.rbi +464 -0
  130. data/rbi/generated/prism/node.rbi +14407 -0
  131. data/rbi/generated/prism/node_ext.rbi +259 -0
  132. data/rbi/generated/prism/node_find.rbi +79 -0
  133. data/rbi/generated/prism/parse_result/errors.rbi +21 -0
  134. data/rbi/generated/prism/parse_result/newlines.rbi +208 -0
  135. data/rbi/generated/prism/parse_result.rbi +776 -0
  136. data/rbi/generated/prism/pattern.rbi +134 -0
  137. data/rbi/generated/prism/reflection.rbi +89 -0
  138. data/rbi/generated/prism/relocation.rbi +329 -0
  139. data/rbi/generated/prism/serialize.rbi +184 -0
  140. data/rbi/generated/prism/string_query.rbi +43 -0
  141. data/rbi/generated/prism/translation.rbi +7 -0
  142. data/rbi/generated/prism/visitor.rbi +650 -0
  143. data/rbi/generated/prism.rbi +86 -0
  144. data/rbi/prism/translation/parser_versions.rbi +5 -0
  145. data/rbi/rubyvm/node_find.rbi +14 -0
  146. data/sig/generated/prism/compiler.rbs +492 -0
  147. data/sig/generated/prism/desugar_compiler.rbs +305 -0
  148. data/sig/generated/prism/dispatcher.rbs +1292 -0
  149. data/sig/generated/prism/dot_visitor.rbs +635 -0
  150. data/sig/generated/prism/dsl.rbs +928 -0
  151. data/sig/generated/prism/inspect_visitor.rbs +509 -0
  152. data/sig/generated/prism/lex_compat.rbs +166 -0
  153. data/sig/{prism → generated/prism}/mutation_compiler.rbs +309 -4
  154. data/sig/generated/prism/node.rbs +20896 -0
  155. data/sig/generated/prism/node_ext.rbs +290 -0
  156. data/sig/generated/prism/node_find.rbs +90 -0
  157. data/sig/generated/prism/parse_result/errors.rbs +22 -0
  158. data/sig/generated/prism/parse_result/newlines.rbs +223 -0
  159. data/sig/generated/prism/parse_result.rbs +871 -0
  160. data/sig/generated/prism/pattern.rbs +156 -0
  161. data/sig/generated/prism/reflection.rbs +101 -0
  162. data/sig/generated/prism/relocation.rbs +428 -0
  163. data/sig/generated/prism/serialize.rbs +198 -0
  164. data/sig/generated/prism/string_query.rbs +43 -0
  165. data/sig/generated/prism/translation.rbs +8 -0
  166. data/sig/generated/prism/visitor.rbs +1111 -0
  167. data/sig/generated/prism.rbs +84 -0
  168. data/sig/manifest.yaml +2 -0
  169. data/src/arena.c +117 -0
  170. data/src/{util/pm_buffer.c → buffer.c} +53 -21
  171. data/src/{util/pm_char.c → char.c} +28 -57
  172. data/src/comments.c +454 -0
  173. data/src/constant_pool.c +406 -0
  174. data/src/diagnostic.c +97 -65
  175. data/src/encoding.c +8 -3
  176. data/src/errors_format.c +519 -0
  177. data/src/{util/pm_integer.c → integer.c} +33 -22
  178. data/src/json.c +5733 -0
  179. data/src/line_offset_list.c +100 -0
  180. data/src/list.c +24 -0
  181. data/src/{util/pm_memchr.c → memchr.c} +8 -6
  182. data/src/node.c +3504 -7674
  183. data/src/options.c +162 -49
  184. data/src/parser.c +367 -0
  185. data/src/prettyprint.c +421 -354
  186. data/src/prism.c +8402 -7161
  187. data/src/regexp.c +961 -45
  188. data/src/serialize.c +460 -424
  189. data/src/source.c +518 -0
  190. data/src/static_literals.c +111 -43
  191. data/src/string_query.c +180 -0
  192. data/src/stringy.c +91 -0
  193. data/src/{util/pm_strncasecmp.c → strncasecmp.c} +5 -4
  194. data/src/strpbrk.c +447 -0
  195. data/src/{token_type.c → tokens.c} +39 -18
  196. data/src/xxh3.c +292 -0
  197. metadata +128 -63
  198. data/ext/prism/api_pack.c +0 -276
  199. data/include/prism/defines.h +0 -260
  200. data/include/prism/pack.h +0 -163
  201. data/include/prism/regexp.h +0 -43
  202. data/include/prism/util/pm_buffer.h +0 -236
  203. data/include/prism/util/pm_char.h +0 -204
  204. data/include/prism/util/pm_constant_pool.h +0 -218
  205. data/include/prism/util/pm_integer.h +0 -130
  206. data/include/prism/util/pm_memchr.h +0 -29
  207. data/include/prism/util/pm_newline_list.h +0 -113
  208. data/include/prism/util/pm_string.h +0 -200
  209. data/lib/prism/pack.rb +0 -230
  210. data/lib/prism/parse_result/comments.rb +0 -188
  211. data/rbi/prism/compiler.rbi +0 -12
  212. data/rbi/prism/dsl.rbi +0 -524
  213. data/rbi/prism/inspect_visitor.rbi +0 -12
  214. data/rbi/prism/node.rbi +0 -8750
  215. data/rbi/prism/node_ext.rbi +0 -107
  216. data/rbi/prism/parse_result.rbi +0 -404
  217. data/rbi/prism/reflection.rbi +0 -58
  218. data/rbi/prism/string_query.rbi +0 -12
  219. data/rbi/prism/visitor.rbi +0 -473
  220. data/rbi/prism.rbi +0 -63
  221. data/sig/prism/compiler.rbs +0 -9
  222. data/sig/prism/dispatcher.rbs +0 -19
  223. data/sig/prism/dot_visitor.rbs +0 -6
  224. data/sig/prism/dsl.rbs +0 -351
  225. data/sig/prism/inspect_visitor.rbs +0 -22
  226. data/sig/prism/lex_compat.rbs +0 -10
  227. data/sig/prism/node.rbs +0 -4042
  228. data/sig/prism/node_ext.rbs +0 -149
  229. data/sig/prism/pack.rbs +0 -43
  230. data/sig/prism/parse_result/comments.rbs +0 -38
  231. data/sig/prism/parse_result.rbs +0 -197
  232. data/sig/prism/pattern.rbs +0 -13
  233. data/sig/prism/reflection.rbs +0 -50
  234. data/sig/prism/relocation.rbs +0 -185
  235. data/sig/prism/serialize.rbs +0 -8
  236. data/sig/prism/string_query.rbs +0 -11
  237. data/sig/prism/visitor.rbs +0 -169
  238. data/sig/prism.rbs +0 -272
  239. data/src/pack.c +0 -509
  240. data/src/util/pm_constant_pool.c +0 -342
  241. data/src/util/pm_list.c +0 -49
  242. data/src/util/pm_newline_list.c +0 -125
  243. data/src/util/pm_string.c +0 -381
  244. data/src/util/pm_strpbrk.c +0 -206
data/src/pack.c DELETED
@@ -1,509 +0,0 @@
1
- #include "prism/pack.h"
2
-
3
- // We optionally support parsing String#pack templates. For systems that don't
4
- // want or need this functionality, it can be turned off with the
5
- // PRISM_EXCLUDE_PACK define.
6
- #ifdef PRISM_EXCLUDE_PACK
7
-
8
- void pm_pack_parse(void) {}
9
-
10
- #else
11
-
12
- #include <stdbool.h>
13
- #include <errno.h>
14
-
15
- static uintmax_t
16
- strtoumaxc(const char **format) {
17
- uintmax_t value = 0;
18
- while (**format >= '0' && **format <= '9') {
19
- if (value > UINTMAX_MAX / 10) {
20
- errno = ERANGE;
21
- }
22
- value = value * 10 + ((uintmax_t) (**format - '0'));
23
- (*format)++;
24
- }
25
- return value;
26
- }
27
-
28
- PRISM_EXPORTED_FUNCTION pm_pack_result
29
- pm_pack_parse(
30
- pm_pack_variant variant,
31
- const char **format,
32
- const char *format_end,
33
- pm_pack_type *type,
34
- pm_pack_signed *signed_type,
35
- pm_pack_endian *endian,
36
- pm_pack_size *size,
37
- pm_pack_length_type *length_type,
38
- uint64_t *length,
39
- pm_pack_encoding *encoding
40
- ) {
41
- if (*encoding == PM_PACK_ENCODING_START) {
42
- *encoding = PM_PACK_ENCODING_US_ASCII;
43
- }
44
-
45
- if (*format == format_end) {
46
- *type = PM_PACK_END;
47
- *signed_type = PM_PACK_SIGNED_NA;
48
- *endian = PM_PACK_ENDIAN_NA;
49
- *size = PM_PACK_SIZE_NA;
50
- *length_type = PM_PACK_LENGTH_NA;
51
- return PM_PACK_OK;
52
- }
53
-
54
- *length_type = PM_PACK_LENGTH_FIXED;
55
- *length = 1;
56
- bool length_changed_allowed = true;
57
-
58
- char directive = **format;
59
- (*format)++;
60
- switch (directive) {
61
- case ' ':
62
- case '\t':
63
- case '\n':
64
- case '\v':
65
- case '\f':
66
- case '\r':
67
- *type = PM_PACK_SPACE;
68
- *signed_type = PM_PACK_SIGNED_NA;
69
- *endian = PM_PACK_ENDIAN_NA;
70
- *size = PM_PACK_SIZE_NA;
71
- *length_type = PM_PACK_LENGTH_NA;
72
- *length = 0;
73
- return PM_PACK_OK;
74
- case '#':
75
- while ((*format < format_end) && (**format != '\n')) {
76
- (*format)++;
77
- }
78
- *type = PM_PACK_COMMENT;
79
- *signed_type = PM_PACK_SIGNED_NA;
80
- *endian = PM_PACK_ENDIAN_NA;
81
- *size = PM_PACK_SIZE_NA;
82
- *length_type = PM_PACK_LENGTH_NA;
83
- *length = 0;
84
- return PM_PACK_OK;
85
- case 'C':
86
- *type = PM_PACK_INTEGER;
87
- *signed_type = PM_PACK_UNSIGNED;
88
- *endian = PM_PACK_AGNOSTIC_ENDIAN;
89
- *size = PM_PACK_SIZE_8;
90
- break;
91
- case 'S':
92
- *type = PM_PACK_INTEGER;
93
- *signed_type = PM_PACK_UNSIGNED;
94
- *endian = PM_PACK_NATIVE_ENDIAN;
95
- *size = PM_PACK_SIZE_16;
96
- break;
97
- case 'L':
98
- *type = PM_PACK_INTEGER;
99
- *signed_type = PM_PACK_UNSIGNED;
100
- *endian = PM_PACK_NATIVE_ENDIAN;
101
- *size = PM_PACK_SIZE_32;
102
- break;
103
- case 'Q':
104
- *type = PM_PACK_INTEGER;
105
- *signed_type = PM_PACK_UNSIGNED;
106
- *endian = PM_PACK_NATIVE_ENDIAN;
107
- *size = PM_PACK_SIZE_64;
108
- break;
109
- case 'J':
110
- *type = PM_PACK_INTEGER;
111
- *signed_type = PM_PACK_UNSIGNED;
112
- *endian = PM_PACK_NATIVE_ENDIAN;
113
- *size = PM_PACK_SIZE_P;
114
- break;
115
- case 'c':
116
- *type = PM_PACK_INTEGER;
117
- *signed_type = PM_PACK_SIGNED;
118
- *endian = PM_PACK_AGNOSTIC_ENDIAN;
119
- *size = PM_PACK_SIZE_8;
120
- break;
121
- case 's':
122
- *type = PM_PACK_INTEGER;
123
- *signed_type = PM_PACK_SIGNED;
124
- *endian = PM_PACK_NATIVE_ENDIAN;
125
- *size = PM_PACK_SIZE_16;
126
- break;
127
- case 'l':
128
- *type = PM_PACK_INTEGER;
129
- *signed_type = PM_PACK_SIGNED;
130
- *endian = PM_PACK_NATIVE_ENDIAN;
131
- *size = PM_PACK_SIZE_32;
132
- break;
133
- case 'q':
134
- *type = PM_PACK_INTEGER;
135
- *signed_type = PM_PACK_SIGNED;
136
- *endian = PM_PACK_NATIVE_ENDIAN;
137
- *size = PM_PACK_SIZE_64;
138
- break;
139
- case 'j':
140
- *type = PM_PACK_INTEGER;
141
- *signed_type = PM_PACK_SIGNED;
142
- *endian = PM_PACK_NATIVE_ENDIAN;
143
- *size = PM_PACK_SIZE_P;
144
- break;
145
- case 'I':
146
- *type = PM_PACK_INTEGER;
147
- *signed_type = PM_PACK_UNSIGNED;
148
- *endian = PM_PACK_NATIVE_ENDIAN;
149
- *size = PM_PACK_SIZE_INT;
150
- break;
151
- case 'i':
152
- *type = PM_PACK_INTEGER;
153
- *signed_type = PM_PACK_SIGNED;
154
- *endian = PM_PACK_NATIVE_ENDIAN;
155
- *size = PM_PACK_SIZE_INT;
156
- break;
157
- case 'n':
158
- *type = PM_PACK_INTEGER;
159
- *signed_type = PM_PACK_UNSIGNED;
160
- *endian = PM_PACK_BIG_ENDIAN;
161
- *size = PM_PACK_SIZE_16;
162
- length_changed_allowed = false;
163
- break;
164
- case 'N':
165
- *type = PM_PACK_INTEGER;
166
- *signed_type = PM_PACK_UNSIGNED;
167
- *endian = PM_PACK_BIG_ENDIAN;
168
- *size = PM_PACK_SIZE_32;
169
- length_changed_allowed = false;
170
- break;
171
- case 'v':
172
- *type = PM_PACK_INTEGER;
173
- *signed_type = PM_PACK_UNSIGNED;
174
- *endian = PM_PACK_LITTLE_ENDIAN;
175
- *size = PM_PACK_SIZE_16;
176
- length_changed_allowed = false;
177
- break;
178
- case 'V':
179
- *type = PM_PACK_INTEGER;
180
- *signed_type = PM_PACK_UNSIGNED;
181
- *endian = PM_PACK_LITTLE_ENDIAN;
182
- *size = PM_PACK_SIZE_32;
183
- length_changed_allowed = false;
184
- break;
185
- case 'U':
186
- *type = PM_PACK_UTF8;
187
- *signed_type = PM_PACK_SIGNED_NA;
188
- *endian = PM_PACK_ENDIAN_NA;
189
- *size = PM_PACK_SIZE_NA;
190
- break;
191
- case 'w':
192
- *type = PM_PACK_BER;
193
- *signed_type = PM_PACK_SIGNED_NA;
194
- *endian = PM_PACK_ENDIAN_NA;
195
- *size = PM_PACK_SIZE_NA;
196
- break;
197
- case 'D':
198
- case 'd':
199
- *type = PM_PACK_FLOAT;
200
- *signed_type = PM_PACK_SIGNED_NA;
201
- *endian = PM_PACK_NATIVE_ENDIAN;
202
- *size = PM_PACK_SIZE_64;
203
- break;
204
- case 'F':
205
- case 'f':
206
- *type = PM_PACK_FLOAT;
207
- *signed_type = PM_PACK_SIGNED_NA;
208
- *endian = PM_PACK_NATIVE_ENDIAN;
209
- *size = PM_PACK_SIZE_32;
210
- break;
211
- case 'E':
212
- *type = PM_PACK_FLOAT;
213
- *signed_type = PM_PACK_SIGNED_NA;
214
- *endian = PM_PACK_LITTLE_ENDIAN;
215
- *size = PM_PACK_SIZE_64;
216
- break;
217
- case 'e':
218
- *type = PM_PACK_FLOAT;
219
- *signed_type = PM_PACK_SIGNED_NA;
220
- *endian = PM_PACK_LITTLE_ENDIAN;
221
- *size = PM_PACK_SIZE_32;
222
- break;
223
- case 'G':
224
- *type = PM_PACK_FLOAT;
225
- *signed_type = PM_PACK_SIGNED_NA;
226
- *endian = PM_PACK_BIG_ENDIAN;
227
- *size = PM_PACK_SIZE_64;
228
- break;
229
- case 'g':
230
- *type = PM_PACK_FLOAT;
231
- *signed_type = PM_PACK_SIGNED_NA;
232
- *endian = PM_PACK_BIG_ENDIAN;
233
- *size = PM_PACK_SIZE_32;
234
- break;
235
- case 'A':
236
- *type = PM_PACK_STRING_SPACE_PADDED;
237
- *signed_type = PM_PACK_SIGNED_NA;
238
- *endian = PM_PACK_ENDIAN_NA;
239
- *size = PM_PACK_SIZE_NA;
240
- break;
241
- case 'a':
242
- *type = PM_PACK_STRING_NULL_PADDED;
243
- *signed_type = PM_PACK_SIGNED_NA;
244
- *endian = PM_PACK_ENDIAN_NA;
245
- *size = PM_PACK_SIZE_NA;
246
- break;
247
- case 'Z':
248
- *type = PM_PACK_STRING_NULL_TERMINATED;
249
- *signed_type = PM_PACK_SIGNED_NA;
250
- *endian = PM_PACK_ENDIAN_NA;
251
- *size = PM_PACK_SIZE_NA;
252
- break;
253
- case 'B':
254
- *type = PM_PACK_STRING_MSB;
255
- *signed_type = PM_PACK_SIGNED_NA;
256
- *endian = PM_PACK_ENDIAN_NA;
257
- *size = PM_PACK_SIZE_NA;
258
- break;
259
- case 'b':
260
- *type = PM_PACK_STRING_LSB;
261
- *signed_type = PM_PACK_SIGNED_NA;
262
- *endian = PM_PACK_ENDIAN_NA;
263
- *size = PM_PACK_SIZE_NA;
264
- break;
265
- case 'H':
266
- *type = PM_PACK_STRING_HEX_HIGH;
267
- *signed_type = PM_PACK_SIGNED_NA;
268
- *endian = PM_PACK_ENDIAN_NA;
269
- *size = PM_PACK_SIZE_NA;
270
- break;
271
- case 'h':
272
- *type = PM_PACK_STRING_HEX_LOW;
273
- *signed_type = PM_PACK_SIGNED_NA;
274
- *endian = PM_PACK_ENDIAN_NA;
275
- *size = PM_PACK_SIZE_NA;
276
- break;
277
- case 'u':
278
- *type = PM_PACK_STRING_UU;
279
- *signed_type = PM_PACK_SIGNED_NA;
280
- *endian = PM_PACK_ENDIAN_NA;
281
- *size = PM_PACK_SIZE_NA;
282
- break;
283
- case 'M':
284
- *type = PM_PACK_STRING_MIME;
285
- *signed_type = PM_PACK_SIGNED_NA;
286
- *endian = PM_PACK_ENDIAN_NA;
287
- *size = PM_PACK_SIZE_NA;
288
- break;
289
- case 'm':
290
- *type = PM_PACK_STRING_BASE64;
291
- *signed_type = PM_PACK_SIGNED_NA;
292
- *endian = PM_PACK_ENDIAN_NA;
293
- *size = PM_PACK_SIZE_NA;
294
- break;
295
- case 'P':
296
- *type = PM_PACK_STRING_FIXED;
297
- *signed_type = PM_PACK_SIGNED_NA;
298
- *endian = PM_PACK_ENDIAN_NA;
299
- *size = PM_PACK_SIZE_NA;
300
- break;
301
- case 'p':
302
- *type = PM_PACK_STRING_POINTER;
303
- *signed_type = PM_PACK_SIGNED_NA;
304
- *endian = PM_PACK_ENDIAN_NA;
305
- *size = PM_PACK_SIZE_NA;
306
- break;
307
- case '@':
308
- *type = PM_PACK_MOVE;
309
- *signed_type = PM_PACK_SIGNED_NA;
310
- *endian = PM_PACK_ENDIAN_NA;
311
- *size = PM_PACK_SIZE_NA;
312
- break;
313
- case 'X':
314
- *type = PM_PACK_BACK;
315
- *signed_type = PM_PACK_SIGNED_NA;
316
- *endian = PM_PACK_ENDIAN_NA;
317
- *size = PM_PACK_SIZE_NA;
318
- break;
319
- case 'x':
320
- *type = PM_PACK_NULL;
321
- *signed_type = PM_PACK_SIGNED_NA;
322
- *endian = PM_PACK_ENDIAN_NA;
323
- *size = PM_PACK_SIZE_NA;
324
- break;
325
- case '%':
326
- return PM_PACK_ERROR_UNSUPPORTED_DIRECTIVE;
327
- default:
328
- return PM_PACK_ERROR_UNKNOWN_DIRECTIVE;
329
- }
330
-
331
- bool explicit_endian = false;
332
-
333
- while (*format < format_end) {
334
- switch (**format) {
335
- case '_':
336
- case '!':
337
- (*format)++;
338
- if (*type != PM_PACK_INTEGER || !length_changed_allowed) {
339
- return PM_PACK_ERROR_BANG_NOT_ALLOWED;
340
- }
341
- switch (*size) {
342
- case PM_PACK_SIZE_SHORT:
343
- case PM_PACK_SIZE_INT:
344
- case PM_PACK_SIZE_LONG:
345
- case PM_PACK_SIZE_LONG_LONG:
346
- break;
347
- case PM_PACK_SIZE_16:
348
- *size = PM_PACK_SIZE_SHORT;
349
- break;
350
- case PM_PACK_SIZE_32:
351
- *size = PM_PACK_SIZE_LONG;
352
- break;
353
- case PM_PACK_SIZE_64:
354
- *size = PM_PACK_SIZE_LONG_LONG;
355
- break;
356
- case PM_PACK_SIZE_P:
357
- break;
358
- default:
359
- return PM_PACK_ERROR_BANG_NOT_ALLOWED;
360
- }
361
- break;
362
- case '<':
363
- (*format)++;
364
- if (explicit_endian) {
365
- return PM_PACK_ERROR_DOUBLE_ENDIAN;
366
- }
367
- *endian = PM_PACK_LITTLE_ENDIAN;
368
- explicit_endian = true;
369
- break;
370
- case '>':
371
- (*format)++;
372
- if (explicit_endian) {
373
- return PM_PACK_ERROR_DOUBLE_ENDIAN;
374
- }
375
- *endian = PM_PACK_BIG_ENDIAN;
376
- explicit_endian = true;
377
- break;
378
- default:
379
- goto exit_modifier_loop;
380
- }
381
- }
382
-
383
- exit_modifier_loop:
384
-
385
- if (variant == PM_PACK_VARIANT_UNPACK && *type == PM_PACK_MOVE) {
386
- *length = 0;
387
- }
388
-
389
- if (*format < format_end) {
390
- if (**format == '*') {
391
- switch (*type) {
392
- case PM_PACK_NULL:
393
- case PM_PACK_BACK:
394
- switch (variant) {
395
- case PM_PACK_VARIANT_PACK:
396
- *length_type = PM_PACK_LENGTH_FIXED;
397
- break;
398
- case PM_PACK_VARIANT_UNPACK:
399
- *length_type = PM_PACK_LENGTH_MAX;
400
- break;
401
- }
402
- *length = 0;
403
- break;
404
-
405
- case PM_PACK_MOVE:
406
- switch (variant) {
407
- case PM_PACK_VARIANT_PACK:
408
- *length_type = PM_PACK_LENGTH_FIXED;
409
- break;
410
- case PM_PACK_VARIANT_UNPACK:
411
- *length_type = PM_PACK_LENGTH_RELATIVE;
412
- break;
413
- }
414
- *length = 0;
415
- break;
416
-
417
- case PM_PACK_STRING_UU:
418
- *length_type = PM_PACK_LENGTH_FIXED;
419
- *length = 0;
420
- break;
421
-
422
- case PM_PACK_STRING_FIXED:
423
- switch (variant) {
424
- case PM_PACK_VARIANT_PACK:
425
- *length_type = PM_PACK_LENGTH_FIXED;
426
- *length = 1;
427
- break;
428
- case PM_PACK_VARIANT_UNPACK:
429
- *length_type = PM_PACK_LENGTH_MAX;
430
- *length = 0;
431
- break;
432
- }
433
- break;
434
-
435
- case PM_PACK_STRING_MIME:
436
- case PM_PACK_STRING_BASE64:
437
- *length_type = PM_PACK_LENGTH_FIXED;
438
- *length = 1;
439
- break;
440
-
441
- default:
442
- *length_type = PM_PACK_LENGTH_MAX;
443
- *length = 0;
444
- break;
445
- }
446
-
447
- (*format)++;
448
- } else if (**format >= '0' && **format <= '9') {
449
- errno = 0;
450
- *length_type = PM_PACK_LENGTH_FIXED;
451
- #if UINTMAX_MAX < UINT64_MAX
452
- #error "prism's design assumes uintmax_t is at least as large as uint64_t"
453
- #endif
454
- uintmax_t length_max = strtoumaxc(format);
455
- if (errno || length_max > UINT64_MAX) {
456
- return PM_PACK_ERROR_LENGTH_TOO_BIG;
457
- }
458
- *length = (uint64_t) length_max;
459
- }
460
- }
461
-
462
- switch (*type) {
463
- case PM_PACK_UTF8:
464
- /* if encoding is US-ASCII, upgrade to UTF-8 */
465
- if (*encoding == PM_PACK_ENCODING_US_ASCII) {
466
- *encoding = PM_PACK_ENCODING_UTF_8;
467
- }
468
- break;
469
- case PM_PACK_STRING_MIME:
470
- case PM_PACK_STRING_BASE64:
471
- case PM_PACK_STRING_UU:
472
- /* keep US-ASCII (do nothing) */
473
- break;
474
- default:
475
- /* fall back to BINARY */
476
- *encoding = PM_PACK_ENCODING_ASCII_8BIT;
477
- break;
478
- }
479
-
480
- return PM_PACK_OK;
481
- }
482
-
483
- PRISM_EXPORTED_FUNCTION size_t
484
- pm_size_to_native(pm_pack_size size) {
485
- switch (size) {
486
- case PM_PACK_SIZE_SHORT:
487
- return sizeof(short);
488
- case PM_PACK_SIZE_INT:
489
- return sizeof(int);
490
- case PM_PACK_SIZE_LONG:
491
- return sizeof(long);
492
- case PM_PACK_SIZE_LONG_LONG:
493
- return sizeof(long long);
494
- case PM_PACK_SIZE_8:
495
- return 1;
496
- case PM_PACK_SIZE_16:
497
- return 2;
498
- case PM_PACK_SIZE_32:
499
- return 4;
500
- case PM_PACK_SIZE_64:
501
- return 8;
502
- case PM_PACK_SIZE_P:
503
- return sizeof(void *);
504
- default:
505
- return 0;
506
- }
507
- }
508
-
509
- #endif