@polycode-projects/the-mechanical-code-talker 2.3.0 → 2.3.1

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 (89) hide show
  1. package/corpus/LICENSES.json +19 -4
  2. package/corpus/README.md +48 -0
  3. package/corpus/generated/README.md +24 -9
  4. package/corpus/generated/ace-surface-variants.jsonl +4 -1
  5. package/corpus/generated/manifest.json +4 -4
  6. package/corpus/prose/manifest.json +512 -0
  7. package/corpus/prose/sqlite/LICENSE-NOTICE +53 -0
  8. package/corpus/prose/sqlite/arch.txt +213 -0
  9. package/corpus/prose/sqlite/atomiccommit.txt +1117 -0
  10. package/corpus/prose/sqlite/faq.txt +473 -0
  11. package/corpus/prose/sqlite/fileformat.txt +1589 -0
  12. package/corpus/prose/sqlite/lang_createtable.txt +1339 -0
  13. package/corpus/prose/sqlite/lang_insert.txt +580 -0
  14. package/corpus/prose/sqlite/lang_select.txt +3293 -0
  15. package/corpus/prose/sqlite/optoverview.txt +908 -0
  16. package/corpus/prose/sqlite/queryplanner.txt +447 -0
  17. package/corpus/prose/sqlite/transactional.txt +41 -0
  18. package/corpus/prose/sqlite/wal.txt +567 -0
  19. package/corpus/prose/sqlite/whentouse.txt +300 -0
  20. package/corpus/prose/wikipedia/Apple.txt +4 -0
  21. package/corpus/prose/wikipedia/Attempto_Controlled_English.txt +169 -0
  22. package/corpus/prose/wikipedia/Automated_planning_and_scheduling.txt +67 -0
  23. package/corpus/prose/wikipedia/Bee.txt +7 -0
  24. package/corpus/prose/wikipedia/Bird.txt +8 -0
  25. package/corpus/prose/wikipedia/Bone.txt +4 -0
  26. package/corpus/prose/wikipedia/Book.txt +7 -0
  27. package/corpus/prose/wikipedia/Bread.txt +6 -0
  28. package/corpus/prose/wikipedia/Butterfly.txt +6 -0
  29. package/corpus/prose/wikipedia/Car.txt +1 -0
  30. package/corpus/prose/wikipedia/Cat.txt +1 -0
  31. package/corpus/prose/wikipedia/Child.txt +3 -0
  32. package/corpus/prose/wikipedia/City.txt +2 -0
  33. package/corpus/prose/wikipedia/Clock.txt +2 -0
  34. package/corpus/prose/wikipedia/Cooking.txt +1 -0
  35. package/corpus/prose/wikipedia/Description_logic.txt +660 -0
  36. package/corpus/prose/wikipedia/Doctor.txt +6 -0
  37. package/corpus/prose/wikipedia/Dog.txt +4 -0
  38. package/corpus/prose/wikipedia/Eagle.txt +4 -0
  39. package/corpus/prose/wikipedia/Emotion.txt +9 -0
  40. package/corpus/prose/wikipedia/Eye.txt +5 -0
  41. package/corpus/prose/wikipedia/Family.txt +3 -0
  42. package/corpus/prose/wikipedia/Farm.txt +4 -0
  43. package/corpus/prose/wikipedia/Fear.txt +4 -0
  44. package/corpus/prose/wikipedia/First-order_logic.txt +1518 -0
  45. package/corpus/prose/wikipedia/Fish.txt +10 -0
  46. package/corpus/prose/wikipedia/Flower.txt +3 -0
  47. package/corpus/prose/wikipedia/Food.txt +10 -0
  48. package/corpus/prose/wikipedia/Grass.txt +9 -0
  49. package/corpus/prose/wikipedia/Hand.txt +2 -0
  50. package/corpus/prose/wikipedia/Happiness.txt +3 -0
  51. package/corpus/prose/wikipedia/Heart.txt +4 -0
  52. package/corpus/prose/wikipedia/Horse.txt +4 -0
  53. package/corpus/prose/wikipedia/House.txt +6 -0
  54. package/corpus/prose/wikipedia/Human.txt +4 -0
  55. package/corpus/prose/wikipedia/Insect.txt +6 -0
  56. package/corpus/prose/wikipedia/Interactive_fiction.txt +112 -0
  57. package/corpus/prose/wikipedia/Knowledge.txt +5 -0
  58. package/corpus/prose/wikipedia/Knowledge_representation_and_reasoning.txt +87 -0
  59. package/corpus/prose/wikipedia/LICENSE-NOTICE +94 -0
  60. package/corpus/prose/wikipedia/Language.txt +10 -0
  61. package/corpus/prose/wikipedia/Learning.txt +4 -0
  62. package/corpus/prose/wikipedia/Mammal.txt +3 -0
  63. package/corpus/prose/wikipedia/Memory.txt +5 -0
  64. package/corpus/prose/wikipedia/Milk.txt +1 -0
  65. package/corpus/prose/wikipedia/Mountain.txt +1 -0
  66. package/corpus/prose/wikipedia/Natural_language_processing.txt +211 -0
  67. package/corpus/prose/wikipedia/Ostrich.txt +2 -0
  68. package/corpus/prose/wikipedia/Owl.txt +2 -0
  69. package/corpus/prose/wikipedia/Penguin.txt +2 -0
  70. package/corpus/prose/wikipedia/Plant.txt +5 -0
  71. package/corpus/prose/wikipedia/Rain.txt +1 -0
  72. package/corpus/prose/wikipedia/Resource_Description_Framework.txt +184 -0
  73. package/corpus/prose/wikipedia/River.txt +1 -0
  74. package/corpus/prose/wikipedia/School.txt +8 -0
  75. package/corpus/prose/wikipedia/Sea.txt +1 -0
  76. package/corpus/prose/wikipedia/Semantic_Web.txt +114 -0
  77. package/corpus/prose/wikipedia/Semantic_reasoner.txt +29 -0
  78. package/corpus/prose/wikipedia/Snow.txt +5 -0
  79. package/corpus/prose/wikipedia/Sun.txt +5 -0
  80. package/corpus/prose/wikipedia/Teacher.txt +4 -0
  81. package/corpus/prose/wikipedia/Team.txt +3 -0
  82. package/corpus/prose/wikipedia/Text-based_game.txt +17 -0
  83. package/corpus/prose/wikipedia/Tool.txt +4 -0
  84. package/corpus/prose/wikipedia/Tree.txt +7 -0
  85. package/corpus/prose/wikipedia/Weather.txt +4 -0
  86. package/corpus/prose/wikipedia/Web_Ontology_Language.txt +133 -0
  87. package/corpus/prose/wikipedia/Wind.txt +8 -0
  88. package/corpus/prose/wikipedia/Writing.txt +5 -0
  89. package/package.json +2 -1
@@ -0,0 +1,512 @@
1
+ {
2
+ "version": 1,
3
+ "generated": "by scripts/fetch-prose-corpus.mjs",
4
+ "fetched": "2026-07-16",
5
+ "description": "Frozen external prose corpus for the rescue pass and the coverage harness. Every file records the URL it came from and a sha256 of the committed bytes, so a re-fetch is verifiable and a doc edit in this repo can never drift it.",
6
+ "sources": [
7
+ {
8
+ "family": "sqlite",
9
+ "upstream": "SQLite documentation (sqlite.org)",
10
+ "license": "public-domain",
11
+ "licenseUrl": "https://www.sqlite.org/copyright.html",
12
+ "notice": "corpus/prose/sqlite/LICENSE-NOTICE",
13
+ "extraction": "HTML fetched per page; script/style/pre/code elements dropped, tags stripped, entities decoded"
14
+ },
15
+ {
16
+ "family": "wikipedia",
17
+ "upstream": "Wikipedia — simple.wikipedia.org lead sections (everyday concepts) and en.wikipedia.org full articles (tmct's technical domain)",
18
+ "license": "CC-BY-SA-4.0",
19
+ "licenseUrl": "https://creativecommons.org/licenses/by-sa/4.0/deed.en",
20
+ "notice": "corpus/prose/wikipedia/LICENSE-NOTICE",
21
+ "extraction": "MediaWiki API action=query&prop=extracts&explaintext=1 (&exintro=1 for the simple-English set); section headings removed"
22
+ }
23
+ ],
24
+ "totals": {
25
+ "files": 80,
26
+ "bytes": 748490
27
+ },
28
+ "files": [
29
+ {
30
+ "file": "sqlite/arch.txt",
31
+ "url": "https://www.sqlite.org/arch.html",
32
+ "bytes": 8536,
33
+ "sha256": "2872a7e1a6217a95ffa9f7a9a7860a02c93e2b85422979bf90b8360ac0abfc09"
34
+ },
35
+ {
36
+ "file": "sqlite/atomiccommit.txt",
37
+ "url": "https://www.sqlite.org/atomiccommit.html",
38
+ "bytes": 61558,
39
+ "sha256": "a971f1f7bd1b87efc99ae0fa23aff184b2187d3ea5349a745027110bf854101b"
40
+ },
41
+ {
42
+ "file": "sqlite/faq.txt",
43
+ "url": "https://www.sqlite.org/faq.html",
44
+ "bytes": 26309,
45
+ "sha256": "e17bc359f41dfac7cae19c7e7a492956ef7f274042d6213ef81509bdd651a43b"
46
+ },
47
+ {
48
+ "file": "sqlite/fileformat.txt",
49
+ "url": "https://www.sqlite.org/fileformat.html",
50
+ "bytes": 81267,
51
+ "sha256": "34a71924d80d1498f5f7e309c8ea9e8d2196c19762439f02645d84a9065cdd1c"
52
+ },
53
+ {
54
+ "file": "sqlite/lang_createtable.txt",
55
+ "url": "https://www.sqlite.org/lang_createtable.html",
56
+ "bytes": 24831,
57
+ "sha256": "0382d25c2891621fac08857bd67ab38d72f9463183b603df722c0e918c40ce56"
58
+ },
59
+ {
60
+ "file": "sqlite/lang_insert.txt",
61
+ "url": "https://www.sqlite.org/lang_insert.html",
62
+ "bytes": 7361,
63
+ "sha256": "e8edf3d8839830ea4c11cf9113b31a5486c55e0ab890f7e4b6ecf1ee2a208686"
64
+ },
65
+ {
66
+ "file": "sqlite/lang_select.txt",
67
+ "url": "https://www.sqlite.org/lang_select.html",
68
+ "bytes": 52567,
69
+ "sha256": "e8a73be6e1304310105c27b48f78eaec47ae18efe6b176f56719a9bfa9bec9d2"
70
+ },
71
+ {
72
+ "file": "sqlite/optoverview.txt",
73
+ "url": "https://www.sqlite.org/optoverview.html",
74
+ "bytes": 50081,
75
+ "sha256": "fc24a8f3458aff3da2340ea5c2b8a5e107663df8473d4b24d6fa65aa96eea1d7"
76
+ },
77
+ {
78
+ "file": "sqlite/queryplanner.txt",
79
+ "url": "https://www.sqlite.org/queryplanner.html",
80
+ "bytes": 24352,
81
+ "sha256": "82bed42de559b164d24cf5fb4905aaf2d85f6e1f3ee128d370d075c0e44ef8d0"
82
+ },
83
+ {
84
+ "file": "sqlite/transactional.txt",
85
+ "url": "https://www.sqlite.org/transactional.html",
86
+ "bytes": 1122,
87
+ "sha256": "bf865b4e5d5fb9d54b6440ddbff0b5c4fff572610549e072d3a6f0cf782c70ea"
88
+ },
89
+ {
90
+ "file": "sqlite/wal.txt",
91
+ "url": "https://www.sqlite.org/wal.html",
92
+ "bytes": 31203,
93
+ "sha256": "85fc412c7cb91afe22f5d05876640c47f09590cc702596d1af655a89f1bc800a"
94
+ },
95
+ {
96
+ "file": "sqlite/whentouse.txt",
97
+ "url": "https://www.sqlite.org/whentouse.html",
98
+ "bytes": 15297,
99
+ "sha256": "f4c68cb9cc2547184f12218f985ac9416f2a4bda29fe53bb7ed212aaff13d638"
100
+ },
101
+ {
102
+ "file": "wikipedia/Apple.txt",
103
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Apple",
104
+ "bytes": 1308,
105
+ "sha256": "bc29bc048829caab5821cc474d71c9cf1c9b7e1fd7b792623bc12701ff6256ab"
106
+ },
107
+ {
108
+ "file": "wikipedia/Attempto_Controlled_English.txt",
109
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Attempto_Controlled_English",
110
+ "bytes": 13762,
111
+ "sha256": "9c71574bb4767366c9e2e4047f117cdc18762c58e6282d7742831947dfdf8347"
112
+ },
113
+ {
114
+ "file": "wikipedia/Automated_planning_and_scheduling.txt",
115
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Automated_planning_and_scheduling",
116
+ "bytes": 13090,
117
+ "sha256": "91236c6358c6d4eb825bce2c1b9f2bdffdddd558edbabb61537649e574487514"
118
+ },
119
+ {
120
+ "file": "wikipedia/Bee.txt",
121
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Bee",
122
+ "bytes": 873,
123
+ "sha256": "412bab0db00730cf62624a826b0939eb17822a1d3da4808a8b93bb394a55193a"
124
+ },
125
+ {
126
+ "file": "wikipedia/Bird.txt",
127
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Bird",
128
+ "bytes": 3714,
129
+ "sha256": "c4d67c3c0f19aa4d9a0109309a431f3778729d5f9c9f5c1f95c522a645e5e0aa"
130
+ },
131
+ {
132
+ "file": "wikipedia/Bone.txt",
133
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Bone",
134
+ "bytes": 722,
135
+ "sha256": "2ec0fb8f8414190da3e55a94430583ead8b5a1a7631ed5d10c0f79959da79300"
136
+ },
137
+ {
138
+ "file": "wikipedia/Book.txt",
139
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Book",
140
+ "bytes": 1886,
141
+ "sha256": "11be7225611e82eb0d4467a8b29ef66fea8fe78473838a82943842a9dfb10750"
142
+ },
143
+ {
144
+ "file": "wikipedia/Bread.txt",
145
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Bread",
146
+ "bytes": 1512,
147
+ "sha256": "48162d08c4b5f41238c3b7d2c3a5b88178739e6aecacf3995b1752c44714bc20"
148
+ },
149
+ {
150
+ "file": "wikipedia/Butterfly.txt",
151
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Butterfly",
152
+ "bytes": 2391,
153
+ "sha256": "4ca7b30a14458c71148182f59667599dc6bca7eee80de111e2309571ad47b016"
154
+ },
155
+ {
156
+ "file": "wikipedia/Car.txt",
157
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Car",
158
+ "bytes": 367,
159
+ "sha256": "35bd9e9433ba556c5f5a58ef0dd125e3fdbb7843ca83137d4b6bc896978046e1",
160
+ "redirectedFrom": "Car",
161
+ "servedTitle": "Automobile"
162
+ },
163
+ {
164
+ "file": "wikipedia/Cat.txt",
165
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Cat",
166
+ "bytes": 404,
167
+ "sha256": "2ee0ca6e537986a2784dbead7ed5087e90af7fa75412839de9955dead44acc9a"
168
+ },
169
+ {
170
+ "file": "wikipedia/Child.txt",
171
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Child",
172
+ "bytes": 1201,
173
+ "sha256": "6d84301f460e8649f889c767feec34119538e342caeef686d9b63c1afbe6bf68"
174
+ },
175
+ {
176
+ "file": "wikipedia/City.txt",
177
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=City",
178
+ "bytes": 634,
179
+ "sha256": "a1f196acaf64360de83e3f0f0a80f7028a28402b7ee7c9721f8db62ca319daf4"
180
+ },
181
+ {
182
+ "file": "wikipedia/Clock.txt",
183
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Clock",
184
+ "bytes": 288,
185
+ "sha256": "074f7bf0701bbbb17747e38b813f2f8724836d8082015ec4977363b12e46c748"
186
+ },
187
+ {
188
+ "file": "wikipedia/Cooking.txt",
189
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Cooking",
190
+ "bytes": 62,
191
+ "sha256": "af3f5587d51bb9aa0c82acd9b48941f3b9d669855ee03f137a6ba4f47a86b5ea"
192
+ },
193
+ {
194
+ "file": "wikipedia/Description_logic.txt",
195
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Description_logic",
196
+ "bytes": 24119,
197
+ "sha256": "239e0bed2151a44f30bbb47bdc39120e35258289ec7ee2430f20f5be9cfd60f3"
198
+ },
199
+ {
200
+ "file": "wikipedia/Doctor.txt",
201
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Doctor",
202
+ "bytes": 304,
203
+ "sha256": "8ffa5a1e39aa776e0bbf06e2a140d109ddce2d59b1a4b71b219ad488cbf404c1"
204
+ },
205
+ {
206
+ "file": "wikipedia/Dog.txt",
207
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Dog",
208
+ "bytes": 996,
209
+ "sha256": "ed1424d4b2d17d32869a5c55f0724f3c2c1f0cdfeafa18549c4f77a00d369d3b"
210
+ },
211
+ {
212
+ "file": "wikipedia/Eagle.txt",
213
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Eagle",
214
+ "bytes": 1002,
215
+ "sha256": "e28bac24101f29f63dec1a1261175e9964dedb347941b5f88c521bd53c5b24bd"
216
+ },
217
+ {
218
+ "file": "wikipedia/Emotion.txt",
219
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Emotion",
220
+ "bytes": 1228,
221
+ "sha256": "ab6e1d8105630ed09047bc955e9f9a61cdda251a5158fa2ed01f143907062d2b"
222
+ },
223
+ {
224
+ "file": "wikipedia/Eye.txt",
225
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Eye",
226
+ "bytes": 1110,
227
+ "sha256": "f6ef1c0ba5bf30e6b9e1d79af078005a54e764ce40e83d5c2829fec56f8c64e1"
228
+ },
229
+ {
230
+ "file": "wikipedia/Family.txt",
231
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Family",
232
+ "bytes": 813,
233
+ "sha256": "3397a5550c414e5a21da03612c266cf587dde1d3cb1c7d78e33152dbb6592dd8"
234
+ },
235
+ {
236
+ "file": "wikipedia/Farm.txt",
237
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Farm",
238
+ "bytes": 844,
239
+ "sha256": "a175bd39bd24b9325b4a5c89c284cb3d699e6f230588a98e9026d50c559dff15"
240
+ },
241
+ {
242
+ "file": "wikipedia/Fear.txt",
243
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Fear",
244
+ "bytes": 1206,
245
+ "sha256": "2d0cc99fa097df65e317d0c1cbb470de2ff1620a46732cf7361f0b9515c76054"
246
+ },
247
+ {
248
+ "file": "wikipedia/First-order_logic.txt",
249
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=First-order_logic",
250
+ "bytes": 73814,
251
+ "sha256": "65dfee749f852070ab9d2836c155a5ee057082d699b4ef7db2f9047c953370ca"
252
+ },
253
+ {
254
+ "file": "wikipedia/Fish.txt",
255
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Fish",
256
+ "bytes": 1884,
257
+ "sha256": "ceaabc22c27ce549629b5ac43ba83f0b9fc3c4492f754b9688a0f89510b9cade"
258
+ },
259
+ {
260
+ "file": "wikipedia/Flower.txt",
261
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Flower",
262
+ "bytes": 661,
263
+ "sha256": "a4b5b3e33d372ee4537a96398a66e550b24f1e75b99647ff1ed40099d7b821df"
264
+ },
265
+ {
266
+ "file": "wikipedia/Food.txt",
267
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Food",
268
+ "bytes": 1947,
269
+ "sha256": "b14aa97e5dd6389041952fe217e232d03c633a656afd2c357b68ebc5bb0b1650"
270
+ },
271
+ {
272
+ "file": "wikipedia/Grass.txt",
273
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Grass",
274
+ "bytes": 2283,
275
+ "sha256": "8ff8b90c515ac2d41dcabc905b9aeb0460c183b5b57cc4ce6e8be9e884b783fb"
276
+ },
277
+ {
278
+ "file": "wikipedia/Hand.txt",
279
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Hand",
280
+ "bytes": 600,
281
+ "sha256": "0f81f49ff825d5957ef3fa367f085fc2dc615eb18c2d903c4df801b0c3aa685a"
282
+ },
283
+ {
284
+ "file": "wikipedia/Happiness.txt",
285
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Happiness",
286
+ "bytes": 844,
287
+ "sha256": "c31915754521ffde90c3dbf2883aaac1d3a83c49ab173959294003d013e3d3e0"
288
+ },
289
+ {
290
+ "file": "wikipedia/Heart.txt",
291
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Heart",
292
+ "bytes": 1187,
293
+ "sha256": "10e9313b21e5d03cfea00cecd9315208d7a621652570753720fc1fc491adb2ce"
294
+ },
295
+ {
296
+ "file": "wikipedia/Horse.txt",
297
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Horse",
298
+ "bytes": 687,
299
+ "sha256": "95d6537c7b38bff13b8cd1e9af01c1d539622dffbf46e182df1d04336fc05e4f"
300
+ },
301
+ {
302
+ "file": "wikipedia/House.txt",
303
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=House",
304
+ "bytes": 1994,
305
+ "sha256": "7c3d1bc390c4015399399352afda8f639364baf72e816809b74d6777ee2bc990"
306
+ },
307
+ {
308
+ "file": "wikipedia/Human.txt",
309
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Human",
310
+ "bytes": 1040,
311
+ "sha256": "1c719d6cb12293574847d27207273ae0f3c1641e3c2c3fb4498018a53ee2340b"
312
+ },
313
+ {
314
+ "file": "wikipedia/Insect.txt",
315
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Insect",
316
+ "bytes": 1001,
317
+ "sha256": "33ab50936ee0cf37f0977ddffaf533fa8f60582d18bbecb45c2fdea58e6c01bd"
318
+ },
319
+ {
320
+ "file": "wikipedia/Interactive_fiction.txt",
321
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Interactive_fiction",
322
+ "bytes": 33373,
323
+ "sha256": "25b3f2eab888106018077abb27c5d0b8eefaecca5d79fa69f1d05572b0a00a4a"
324
+ },
325
+ {
326
+ "file": "wikipedia/Knowledge_representation_and_reasoning.txt",
327
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Knowledge_representation_and_reasoning",
328
+ "bytes": 27698,
329
+ "sha256": "b3a6a78e66cbbf56a195d7fe12046b4ddf7d23b568888ce3a725970e9eb1a814"
330
+ },
331
+ {
332
+ "file": "wikipedia/Knowledge.txt",
333
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Knowledge",
334
+ "bytes": 4789,
335
+ "sha256": "685db268f2799be93d5de3a49b1ba21cbda1f15ca5ffcec433dac2e99e4bb182"
336
+ },
337
+ {
338
+ "file": "wikipedia/Language.txt",
339
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Language",
340
+ "bytes": 1012,
341
+ "sha256": "d894e1c549ee3c4dcd0bc83c53ca8858e07a6bbe3e3d9ff75fa94b7922738cac"
342
+ },
343
+ {
344
+ "file": "wikipedia/Learning.txt",
345
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Learning",
346
+ "bytes": 3942,
347
+ "sha256": "9b7f789c003ca153e17764d6e3df3cb47eeeb80172814f5aa7cca0f977700070"
348
+ },
349
+ {
350
+ "file": "wikipedia/Mammal.txt",
351
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Mammal",
352
+ "bytes": 584,
353
+ "sha256": "66ed2f3923a036f29ea8381b2b502c93902fc27bdc2df4b2112d8c172663b3df"
354
+ },
355
+ {
356
+ "file": "wikipedia/Memory.txt",
357
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Memory",
358
+ "bytes": 670,
359
+ "sha256": "017fa412aeb1223e2c7f0d3366be5c100043b7ba425d536946096c7587710592"
360
+ },
361
+ {
362
+ "file": "wikipedia/Milk.txt",
363
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Milk",
364
+ "bytes": 352,
365
+ "sha256": "6c4a9a2071ff290c5becd16096a717a19560ccd32d11d80608085e3df33c5d48"
366
+ },
367
+ {
368
+ "file": "wikipedia/Mountain.txt",
369
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Mountain",
370
+ "bytes": 305,
371
+ "sha256": "98e3e6ad7aaa6637af036c88b3fe80dc9d80e6b6e751b6cbb5cd8c0077c85f1e"
372
+ },
373
+ {
374
+ "file": "wikipedia/Natural_language_processing.txt",
375
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Natural_language_processing",
376
+ "bytes": 29865,
377
+ "sha256": "8ca6bec392a03be9af25289398c568989d868e97975bb33174f6c726dd2e83f3"
378
+ },
379
+ {
380
+ "file": "wikipedia/Ostrich.txt",
381
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Ostrich",
382
+ "bytes": 357,
383
+ "sha256": "c2036a63901b29de4e9207748ae1303cdc204a18b616125ba354a697c672db76"
384
+ },
385
+ {
386
+ "file": "wikipedia/Owl.txt",
387
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Owl",
388
+ "bytes": 505,
389
+ "sha256": "ca034c1375034af8c491c9f2fb79f083d8e37bd87b0fbc4621f83f184d445336"
390
+ },
391
+ {
392
+ "file": "wikipedia/Penguin.txt",
393
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Penguin",
394
+ "bytes": 468,
395
+ "sha256": "a18651aca0cfce1ac3270314e7566b2b753e3b7b8105179b474f8034f0813f7d"
396
+ },
397
+ {
398
+ "file": "wikipedia/Plant.txt",
399
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Plant",
400
+ "bytes": 1516,
401
+ "sha256": "f27694ef9cde44ca981ff63e7d92fb789f09aca4f96ebf4761bb42288c8f38a3"
402
+ },
403
+ {
404
+ "file": "wikipedia/Rain.txt",
405
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Rain",
406
+ "bytes": 168,
407
+ "sha256": "ae8cd569146d9b9cbdfa2e9b605099354e5060acba3d4384fa5b465ecd37f4d9"
408
+ },
409
+ {
410
+ "file": "wikipedia/Resource_Description_Framework.txt",
411
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Resource_Description_Framework",
412
+ "bytes": 23121,
413
+ "sha256": "4227706ed6ccb2c0b5a14fd026d32f9c426e551bc9b0c86dca347de268866228"
414
+ },
415
+ {
416
+ "file": "wikipedia/River.txt",
417
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=River",
418
+ "bytes": 398,
419
+ "sha256": "0c977a35fa60b5edf73a275006125e1f8ee0574e48d045870106a0bfcf377aed"
420
+ },
421
+ {
422
+ "file": "wikipedia/School.txt",
423
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=School",
424
+ "bytes": 2461,
425
+ "sha256": "bca92eab55cd91b411248b506b307e737465d987f0e444fa8452e74ec2f0f43d"
426
+ },
427
+ {
428
+ "file": "wikipedia/Sea.txt",
429
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Sea",
430
+ "bytes": 142,
431
+ "sha256": "279b65366b340430712868dc89f765873ea60fd8d94e58436d0fe4d21880e07e"
432
+ },
433
+ {
434
+ "file": "wikipedia/Semantic_reasoner.txt",
435
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Semantic_reasoner",
436
+ "bytes": 3437,
437
+ "sha256": "b635dd213999d33d47c4c70862653a9ad3ee19ec86fb8ca40f268ceeb15f5593"
438
+ },
439
+ {
440
+ "file": "wikipedia/Semantic_Web.txt",
441
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Semantic_Web",
442
+ "bytes": 30115,
443
+ "sha256": "88d8a95afd21618e2832689ce55c952d2391ac6ea8e639f3d3cd1c74fe1a6d25"
444
+ },
445
+ {
446
+ "file": "wikipedia/Snow.txt",
447
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Snow",
448
+ "bytes": 1517,
449
+ "sha256": "d50eb34e66db433703b8c8a1e8b3eb2dc6501e6941886125504a9c2e307c2df4"
450
+ },
451
+ {
452
+ "file": "wikipedia/Sun.txt",
453
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Sun",
454
+ "bytes": 3406,
455
+ "sha256": "5ac56e9f51ee7aa2344893f61d334bc0b93697361af13e6783b3204ab2985766"
456
+ },
457
+ {
458
+ "file": "wikipedia/Teacher.txt",
459
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Teacher",
460
+ "bytes": 756,
461
+ "sha256": "64b636ba86ae5110a7f2da896cc955ec08fe0c7badf9b806945fd1e3ac9d2603"
462
+ },
463
+ {
464
+ "file": "wikipedia/Team.txt",
465
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Team",
466
+ "bytes": 585,
467
+ "sha256": "4a1d447c0196f9a77056afc59cc942a3242ac25d8d45417dbaf05c5cb4734c11"
468
+ },
469
+ {
470
+ "file": "wikipedia/Text-based_game.txt",
471
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Text-based_game",
472
+ "bytes": 7083,
473
+ "sha256": "2f12953c5686525a3e363242f707b1fd56a560dbf2504f8854276a1c65e277eb"
474
+ },
475
+ {
476
+ "file": "wikipedia/Tool.txt",
477
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Tool",
478
+ "bytes": 1051,
479
+ "sha256": "16dde2f466ae26be9366be8fb66feceed1581ecf3199d5d26785de09edfd2ea5"
480
+ },
481
+ {
482
+ "file": "wikipedia/Tree.txt",
483
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Tree",
484
+ "bytes": 1638,
485
+ "sha256": "abecf6d15c24f98a97d79484d0abc159ceb17f94eb131a6b242ad74920571949"
486
+ },
487
+ {
488
+ "file": "wikipedia/Weather.txt",
489
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Weather",
490
+ "bytes": 891,
491
+ "sha256": "6c8b82ff45e42bc88acf908ac8c94e9c29317ea2fb58334fe7b4d18fc7967697"
492
+ },
493
+ {
494
+ "file": "wikipedia/Web_Ontology_Language.txt",
495
+ "url": "https://en.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&titles=Web_Ontology_Language",
496
+ "bytes": 16388,
497
+ "sha256": "be524b8709e7b2019b817b28c74108dd6aea4aff4e6258907c73164fafe9593f"
498
+ },
499
+ {
500
+ "file": "wikipedia/Wind.txt",
501
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Wind",
502
+ "bytes": 2121,
503
+ "sha256": "62493e44dc74d5703837f70b130b9067054f11ca4faaa5209494aef5ddf6ce58"
504
+ },
505
+ {
506
+ "file": "wikipedia/Writing.txt",
507
+ "url": "https://simple.wikipedia.org/w/api.php?action=query&prop=extracts&explaintext=1&redirects=1&format=json&exintro=1&titles=Writing",
508
+ "bytes": 1514,
509
+ "sha256": "340262ce26cc490e272f02ca74be2d48c244fbb66569ee733ffaf08a8b8316ae"
510
+ }
511
+ ]
512
+ }
@@ -0,0 +1,53 @@
1
+ LICENSE NOTICE — corpus/prose/sqlite/
2
+ =====================================
3
+
4
+ The *.txt files in this directory are plain-text extractions of pages from the
5
+ SQLite documentation (https://www.sqlite.org/). They are in the PUBLIC DOMAIN,
6
+ not under this repository's MPL-2.0 and not under any copyleft terms.
7
+
8
+ Public-domain dedication
9
+ ------------------------
10
+
11
+ https://www.sqlite.org/copyright.html states:
12
+
13
+ "All of the code and documentation in SQLite has been dedicated to the public
14
+ domain by the authors. All code authors, and representatives of the companies
15
+ they work for, have signed affidavits dedicating their contributions to the
16
+ public domain and originals of those signed affidavits are stored in a
17
+ firesafe at the main offices of Hwaci."
18
+
19
+ There is therefore NO attribution obligation and NO share-alike obligation on
20
+ this text. This notice records the provenance because the project's practice is
21
+ to say where every committed byte came from, not because the licence demands it.
22
+
23
+ Source
24
+ ------
25
+
26
+ - Pages: https://www.sqlite.org/<page>.html — one committed .txt per page,
27
+ named for the page (arch.txt is arch.html, and so on).
28
+ - The exact URL, byte count and sha256 of every committed file are recorded in
29
+ corpus/prose/manifest.json, along with the fetch date.
30
+ - Retrieved 2026-07-17 by scripts/fetch-prose-corpus.mjs, which is also the
31
+ reproduction route: `npm run gen:prose-corpus`.
32
+
33
+ Extraction
34
+ ----------
35
+
36
+ The fetched HTML is reduced to plain text: <script>, <style>, <pre> and <code>
37
+ elements are dropped whole (a code block is the thing most likely to look like
38
+ a sentence without being one), block-level closing tags become newlines, the
39
+ remaining tags are stripped, HTML entities are decoded, and whitespace is
40
+ collapsed. No text is rewritten, reordered or paraphrased in this directory.
41
+
42
+ How this text is used
43
+ ---------------------
44
+
45
+ This corpus feeds the rescue pass in scripts/generate-template-variants.mjs,
46
+ which substitutes single words and commits the result to
47
+ corpus/generated/ace-surface-variants.jsonl — a published, MODIFIED derivative.
48
+ The public-domain dedication permits that without condition. (Sources that
49
+ allow redistribution but NOT derivatives — IETF RFCs, W3C specifications — were
50
+ rejected for exactly this reason; see scripts/fetch-prose-corpus.mjs's header.)
51
+
52
+ The extraction code (scripts/fetch-prose-corpus.mjs) is tmct code under this
53
+ repository's MPL-2.0; only the .txt data files are public domain.