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
@@ -0,0 +1,100 @@
1
+ #include "prism/compiler/align.h"
2
+ #include "prism/internal/line_offset_list.h"
3
+ #include "prism/internal/arena.h"
4
+
5
+ #include <assert.h>
6
+ #include <string.h>
7
+
8
+ /**
9
+ * Initialize a new line offset list with the given capacity.
10
+ */
11
+ void
12
+ pm_line_offset_list_init(pm_arena_t *arena, pm_line_offset_list_t *list, size_t capacity) {
13
+ list->offsets = (uint32_t *) pm_arena_alloc(arena, capacity * sizeof(uint32_t), PRISM_ALIGNOF(uint32_t));
14
+
15
+ // The first line always has offset 0.
16
+ list->offsets[0] = 0;
17
+ list->size = 1;
18
+ list->capacity = capacity;
19
+ }
20
+
21
+ /**
22
+ * Clear out the newlines that have been appended to the list.
23
+ */
24
+ void
25
+ pm_line_offset_list_clear(pm_line_offset_list_t *list) {
26
+ list->size = 1;
27
+ }
28
+
29
+ /**
30
+ * Append a new offset to the newline list (slow path: resize and store).
31
+ */
32
+ void
33
+ pm_line_offset_list_append_slow(pm_arena_t *arena, pm_line_offset_list_t *list, uint32_t cursor) {
34
+ size_t new_capacity = (list->capacity * 3) / 2;
35
+ uint32_t *new_offsets = (uint32_t *) pm_arena_alloc(arena, new_capacity * sizeof(uint32_t), PRISM_ALIGNOF(uint32_t));
36
+
37
+ memcpy(new_offsets, list->offsets, list->size * sizeof(uint32_t));
38
+
39
+ list->offsets = new_offsets;
40
+ list->capacity = new_capacity;
41
+
42
+ assert(list->size == 0 || cursor > list->offsets[list->size - 1]);
43
+ list->offsets[list->size++] = cursor;
44
+ }
45
+
46
+ /**
47
+ * Returns the line of the given offset. If the offset is not in the list, the
48
+ * line of the closest offset less than the given offset is returned.
49
+ */
50
+ int32_t
51
+ pm_line_offset_list_line(const pm_line_offset_list_t *list, uint32_t cursor, int32_t start_line) {
52
+ size_t left = 0;
53
+ size_t right = list->size - 1;
54
+
55
+ while (left <= right) {
56
+ size_t mid = left + (right - left) / 2;
57
+
58
+ if (list->offsets[mid] == cursor) {
59
+ return ((int32_t) mid) + start_line;
60
+ }
61
+
62
+ if (list->offsets[mid] < cursor) {
63
+ left = mid + 1;
64
+ } else {
65
+ right = mid - 1;
66
+ }
67
+ }
68
+
69
+ return ((int32_t) left) + start_line - 1;
70
+ }
71
+
72
+ /**
73
+ * Returns the line and column of the given offset. If the offset is not in the
74
+ * list, the line and column of the closest offset less than the given offset
75
+ * are returned.
76
+ */
77
+ pm_line_column_t
78
+ pm_line_offset_list_line_column(const pm_line_offset_list_t *list, uint32_t cursor, int32_t start_line) {
79
+ size_t left = 0;
80
+ size_t right = list->size - 1;
81
+
82
+ while (left <= right) {
83
+ size_t mid = left + (right - left) / 2;
84
+
85
+ if (list->offsets[mid] == cursor) {
86
+ return ((pm_line_column_t) { ((int32_t) mid) + start_line, 0 });
87
+ }
88
+
89
+ if (list->offsets[mid] < cursor) {
90
+ left = mid + 1;
91
+ } else {
92
+ right = mid - 1;
93
+ }
94
+ }
95
+
96
+ return ((pm_line_column_t) {
97
+ .line = ((int32_t) left) + start_line - 1,
98
+ .column = cursor - list->offsets[left - 1]
99
+ });
100
+ }
data/src/list.c ADDED
@@ -0,0 +1,24 @@
1
+ #include "prism/internal/list.h"
2
+
3
+ /**
4
+ * Returns the size of the list.
5
+ */
6
+ size_t
7
+ pm_list_size(pm_list_t *list) {
8
+ return list->size;
9
+ }
10
+
11
+ /**
12
+ * Append a node to the given list.
13
+ */
14
+ void
15
+ pm_list_append(pm_list_t *list, pm_list_node_t *node) {
16
+ if (list->head == NULL) {
17
+ list->head = node;
18
+ } else {
19
+ list->tail->next = node;
20
+ }
21
+
22
+ list->tail = node;
23
+ list->size++;
24
+ }
@@ -1,15 +1,19 @@
1
- #include "prism/util/pm_memchr.h"
1
+ #include "prism/internal/memchr.h"
2
2
 
3
- #define PRISM_MEMCHR_TRAILING_BYTE_MINIMUM 0x40
3
+ #include <stdbool.h>
4
+ #include <stdint.h>
5
+ #include <string.h>
6
+
7
+ #define TRAILING_BYTE_MINIMUM 0x40
4
8
 
5
9
  /**
6
10
  * We need to roll our own memchr to handle cases where the encoding changes and
7
11
  * we need to search for a character in a buffer that could be the trailing byte
8
12
  * of a multibyte character.
9
13
  */
10
- void *
14
+ const void *
11
15
  pm_memchr(const void *memory, int character, size_t number, bool encoding_changed, const pm_encoding_t *encoding) {
12
- if (encoding_changed && encoding->multibyte && character >= PRISM_MEMCHR_TRAILING_BYTE_MINIMUM) {
16
+ if (encoding_changed && encoding->multibyte && character >= TRAILING_BYTE_MINIMUM) {
13
17
  const uint8_t *source = (const uint8_t *) memory;
14
18
  size_t index = 0;
15
19
 
@@ -31,5 +35,3 @@ pm_memchr(const void *memory, int character, size_t number, bool encoding_change
31
35
  return memchr(memory, character, number);
32
36
  }
33
37
  }
34
-
35
- #undef PRISM_MEMCHR_TRAILING_BYTE_MINIMUM