rowpipe 2.1.0 → 2.2.0

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 (207) hide show
  1. package/README.md +183 -5
  2. package/dist/analytics/profiler.d.ts +56 -0
  3. package/dist/analytics/profiler.d.ts.map +1 -0
  4. package/dist/analytics/profiler.js +277 -0
  5. package/dist/analytics/profiler.js.map +1 -0
  6. package/dist/analytics/schema-inference.d.ts.map +1 -1
  7. package/dist/analytics/schema-inference.js +14 -0
  8. package/dist/analytics/schema-inference.js.map +1 -1
  9. package/dist/cli/commands/clean.d.ts +15 -0
  10. package/dist/cli/commands/clean.d.ts.map +1 -0
  11. package/dist/cli/commands/clean.js +108 -0
  12. package/dist/cli/commands/clean.js.map +1 -0
  13. package/dist/cli/commands/convert.d.ts +6 -0
  14. package/dist/cli/commands/convert.d.ts.map +1 -1
  15. package/dist/cli/commands/convert.js +6 -6
  16. package/dist/cli/commands/convert.js.map +1 -1
  17. package/dist/cli/commands/db.d.ts +35 -0
  18. package/dist/cli/commands/db.d.ts.map +1 -0
  19. package/dist/cli/commands/db.js +173 -0
  20. package/dist/cli/commands/db.js.map +1 -0
  21. package/dist/cli/commands/explain.d.ts +8 -1
  22. package/dist/cli/commands/explain.d.ts.map +1 -1
  23. package/dist/cli/commands/explain.js +89 -2
  24. package/dist/cli/commands/explain.js.map +1 -1
  25. package/dist/cli/commands/join.d.ts +23 -0
  26. package/dist/cli/commands/join.d.ts.map +1 -0
  27. package/dist/cli/commands/join.js +97 -0
  28. package/dist/cli/commands/join.js.map +1 -0
  29. package/dist/cli/commands/pipeline.d.ts +20 -0
  30. package/dist/cli/commands/pipeline.d.ts.map +1 -1
  31. package/dist/cli/commands/pipeline.js +53 -12
  32. package/dist/cli/commands/pipeline.js.map +1 -1
  33. package/dist/cli/commands/profile.d.ts +22 -0
  34. package/dist/cli/commands/profile.d.ts.map +1 -0
  35. package/dist/cli/commands/profile.js +53 -0
  36. package/dist/cli/commands/profile.js.map +1 -0
  37. package/dist/cli/commands/view.d.ts +12 -0
  38. package/dist/cli/commands/view.d.ts.map +1 -0
  39. package/dist/cli/commands/view.js +52 -0
  40. package/dist/cli/commands/view.js.map +1 -0
  41. package/dist/cli/commands/window.d.ts +10 -0
  42. package/dist/cli/commands/window.d.ts.map +1 -0
  43. package/dist/cli/commands/window.js +87 -0
  44. package/dist/cli/commands/window.js.map +1 -0
  45. package/dist/cli/index.js +201 -5
  46. package/dist/cli/index.js.map +1 -1
  47. package/dist/core/batch.d.ts +1 -1
  48. package/dist/core/batch.d.ts.map +1 -1
  49. package/dist/core/batch.js.map +1 -1
  50. package/dist/core/pipeline.d.ts +2 -2
  51. package/dist/core/pipeline.d.ts.map +1 -1
  52. package/dist/core/pipeline.js +5 -2
  53. package/dist/core/pipeline.js.map +1 -1
  54. package/dist/core/types.d.ts +21 -1
  55. package/dist/core/types.d.ts.map +1 -1
  56. package/dist/db/adapters/index.d.ts +6 -0
  57. package/dist/db/adapters/index.d.ts.map +1 -0
  58. package/dist/db/adapters/index.js +21 -0
  59. package/dist/db/adapters/index.js.map +1 -0
  60. package/dist/db/adapters/mysql.d.ts +16 -0
  61. package/dist/db/adapters/mysql.d.ts.map +1 -0
  62. package/dist/db/adapters/mysql.js +230 -0
  63. package/dist/db/adapters/mysql.js.map +1 -0
  64. package/dist/db/adapters/postgres.d.ts +17 -0
  65. package/dist/db/adapters/postgres.d.ts.map +1 -0
  66. package/dist/db/adapters/postgres.js +239 -0
  67. package/dist/db/adapters/postgres.js.map +1 -0
  68. package/dist/db/adapters/sqlite.d.ts +18 -0
  69. package/dist/db/adapters/sqlite.d.ts.map +1 -0
  70. package/dist/db/adapters/sqlite.js +210 -0
  71. package/dist/db/adapters/sqlite.js.map +1 -0
  72. package/dist/db/index.d.ts +11 -0
  73. package/dist/db/index.d.ts.map +1 -0
  74. package/dist/db/index.js +11 -0
  75. package/dist/db/index.js.map +1 -0
  76. package/dist/db/mapping.d.ts +45 -0
  77. package/dist/db/mapping.d.ts.map +1 -0
  78. package/dist/db/mapping.js +222 -0
  79. package/dist/db/mapping.js.map +1 -0
  80. package/dist/db/pushdown.d.ts +25 -0
  81. package/dist/db/pushdown.d.ts.map +1 -0
  82. package/dist/db/pushdown.js +165 -0
  83. package/dist/db/pushdown.js.map +1 -0
  84. package/dist/db/sink.d.ts +15 -0
  85. package/dist/db/sink.d.ts.map +1 -0
  86. package/dist/db/sink.js +47 -0
  87. package/dist/db/sink.js.map +1 -0
  88. package/dist/db/source.d.ts +14 -0
  89. package/dist/db/source.d.ts.map +1 -0
  90. package/dist/db/source.js +69 -0
  91. package/dist/db/source.js.map +1 -0
  92. package/dist/db/types.d.ts +80 -0
  93. package/dist/db/types.d.ts.map +1 -0
  94. package/dist/db/types.js +2 -0
  95. package/dist/db/types.js.map +1 -0
  96. package/dist/db/url.d.ts +15 -0
  97. package/dist/db/url.d.ts.map +1 -0
  98. package/dist/db/url.js +145 -0
  99. package/dist/db/url.js.map +1 -0
  100. package/dist/diff/hash.d.ts.map +1 -1
  101. package/dist/diff/hash.js +4 -3
  102. package/dist/diff/hash.js.map +1 -1
  103. package/dist/diff/key.d.ts.map +1 -1
  104. package/dist/diff/key.js +8 -1
  105. package/dist/diff/key.js.map +1 -1
  106. package/dist/diff/reporter.d.ts.map +1 -1
  107. package/dist/diff/reporter.js +5 -3
  108. package/dist/diff/reporter.js.map +1 -1
  109. package/dist/diff/storage/disk-index.d.ts.map +1 -1
  110. package/dist/diff/storage/disk-index.js +2 -1
  111. package/dist/diff/storage/disk-index.js.map +1 -1
  112. package/dist/diff/storage/memory-index.d.ts.map +1 -1
  113. package/dist/diff/storage/memory-index.js +3 -2
  114. package/dist/diff/storage/memory-index.js.map +1 -1
  115. package/dist/index.d.ts +8 -1
  116. package/dist/index.d.ts.map +1 -1
  117. package/dist/index.js +9 -1
  118. package/dist/index.js.map +1 -1
  119. package/dist/planner/executor.d.ts.map +1 -1
  120. package/dist/planner/executor.js +7 -0
  121. package/dist/planner/executor.js.map +1 -1
  122. package/dist/planner/types.d.ts +4 -0
  123. package/dist/planner/types.d.ts.map +1 -1
  124. package/dist/readers/csv.d.ts.map +1 -1
  125. package/dist/readers/csv.js +1 -2
  126. package/dist/readers/csv.js.map +1 -1
  127. package/dist/readers/index.d.ts +5 -1
  128. package/dist/readers/index.d.ts.map +1 -1
  129. package/dist/readers/index.js +43 -0
  130. package/dist/readers/index.js.map +1 -1
  131. package/dist/readers/json.d.ts.map +1 -1
  132. package/dist/readers/json.js +1 -2
  133. package/dist/readers/json.js.map +1 -1
  134. package/dist/readers/jsonl.d.ts.map +1 -1
  135. package/dist/readers/jsonl.js +1 -2
  136. package/dist/readers/jsonl.js.map +1 -1
  137. package/dist/readers/multi-file.d.ts +29 -0
  138. package/dist/readers/multi-file.d.ts.map +1 -0
  139. package/dist/readers/multi-file.js +169 -0
  140. package/dist/readers/multi-file.js.map +1 -0
  141. package/dist/transforms/clean.d.ts +18 -0
  142. package/dist/transforms/clean.d.ts.map +1 -0
  143. package/dist/transforms/clean.js +118 -0
  144. package/dist/transforms/clean.js.map +1 -0
  145. package/dist/transforms/expression.d.ts.map +1 -1
  146. package/dist/transforms/expression.js +12 -0
  147. package/dist/transforms/expression.js.map +1 -1
  148. package/dist/transforms/jit-compiler.d.ts +50 -0
  149. package/dist/transforms/jit-compiler.d.ts.map +1 -0
  150. package/dist/transforms/jit-compiler.js +275 -0
  151. package/dist/transforms/jit-compiler.js.map +1 -0
  152. package/dist/transforms/join/index-storage.d.ts +33 -0
  153. package/dist/transforms/join/index-storage.d.ts.map +1 -0
  154. package/dist/transforms/join/index-storage.js +139 -0
  155. package/dist/transforms/join/index-storage.js.map +1 -0
  156. package/dist/transforms/join/index.d.ts +4 -0
  157. package/dist/transforms/join/index.d.ts.map +1 -0
  158. package/dist/transforms/join/index.js +4 -0
  159. package/dist/transforms/join/index.js.map +1 -0
  160. package/dist/transforms/join/join.d.ts +15 -0
  161. package/dist/transforms/join/join.d.ts.map +1 -0
  162. package/dist/transforms/join/join.js +216 -0
  163. package/dist/transforms/join/join.js.map +1 -0
  164. package/dist/transforms/join/types.d.ts +29 -0
  165. package/dist/transforms/join/types.d.ts.map +1 -0
  166. package/dist/transforms/join/types.js +2 -0
  167. package/dist/transforms/join/types.js.map +1 -0
  168. package/dist/transforms/window.d.ts +24 -0
  169. package/dist/transforms/window.d.ts.map +1 -0
  170. package/dist/transforms/window.js +317 -0
  171. package/dist/transforms/window.js.map +1 -0
  172. package/dist/ui/colors.d.ts +57 -0
  173. package/dist/ui/colors.d.ts.map +1 -0
  174. package/dist/ui/colors.js +94 -0
  175. package/dist/ui/colors.js.map +1 -0
  176. package/dist/ui/viewer.d.ts +67 -0
  177. package/dist/ui/viewer.d.ts.map +1 -0
  178. package/dist/ui/viewer.js +673 -0
  179. package/dist/ui/viewer.js.map +1 -0
  180. package/dist/utils/compression.d.ts +68 -19
  181. package/dist/utils/compression.d.ts.map +1 -1
  182. package/dist/utils/compression.js +222 -34
  183. package/dist/utils/compression.js.map +1 -1
  184. package/dist/utils/formatting.d.ts +5 -0
  185. package/dist/utils/formatting.d.ts.map +1 -1
  186. package/dist/utils/formatting.js +15 -0
  187. package/dist/utils/formatting.js.map +1 -1
  188. package/dist/writers/csv.d.ts.map +1 -1
  189. package/dist/writers/csv.js +13 -14
  190. package/dist/writers/csv.js.map +1 -1
  191. package/dist/writers/index.d.ts +1 -0
  192. package/dist/writers/index.d.ts.map +1 -1
  193. package/dist/writers/index.js +35 -0
  194. package/dist/writers/index.js.map +1 -1
  195. package/dist/writers/json.d.ts.map +1 -1
  196. package/dist/writers/json.js +6 -5
  197. package/dist/writers/json.js.map +1 -1
  198. package/dist/writers/jsonl.d.ts.map +1 -1
  199. package/dist/writers/jsonl.js +6 -5
  200. package/dist/writers/jsonl.js.map +1 -1
  201. package/dist/writers/markdown.d.ts.map +1 -1
  202. package/dist/writers/markdown.js +5 -4
  203. package/dist/writers/markdown.js.map +1 -1
  204. package/dist/writers/parquet.d.ts +1 -1
  205. package/dist/writers/parquet.d.ts.map +1 -1
  206. package/package.json +10 -2
  207. package/skills/rowpipe/SKILL.md +8 -4
@@ -0,0 +1,139 @@
1
+ import { DatabaseSync } from "node:sqlite";
2
+ import * as fs from "node:fs";
3
+ import * as os from "node:os";
4
+ import * as path from "node:path";
5
+ import { parseMemoryLimit } from "../../diff/storage/spillable-index.js";
6
+ import { safeJsonStringify } from "../../utils/formatting.js";
7
+ /**
8
+ * High-performance Spillable Join Index that stores build-side rows in memory,
9
+ * and transparently spills to disk when memory threshold is reached.
10
+ */
11
+ export class SpillableJoinIndex {
12
+ memoryMap = new Map();
13
+ matchedKeys = new Set();
14
+ estimatedBytes = 0;
15
+ memoryLimitBytes;
16
+ isSpilled = false;
17
+ tempDir;
18
+ dbPath;
19
+ db;
20
+ insertStmt;
21
+ selectStmt;
22
+ hasStmt;
23
+ totalCount = 0;
24
+ constructor(options) {
25
+ this.memoryLimitBytes = parseMemoryLimit(options?.memoryLimit, 256 * 1024 * 1024);
26
+ this.tempDir = options?.tempDir;
27
+ }
28
+ async spillToDisk() {
29
+ if (this.isSpilled)
30
+ return;
31
+ const tmpFolder = this.tempDir || os.tmpdir();
32
+ this.dbPath = path.join(tmpFolder, `rowpipe_join_${Date.now()}_${Math.random().toString(36).slice(2)}.db`);
33
+ this.db = new DatabaseSync(this.dbPath);
34
+ this.db.exec(`
35
+ PRAGMA synchronous = OFF;
36
+ PRAGMA journal_mode = OFF;
37
+ CREATE TABLE join_store (
38
+ k TEXT NOT NULL,
39
+ data TEXT NOT NULL
40
+ );
41
+ CREATE INDEX idx_join_k ON join_store (k);
42
+ `);
43
+ this.insertStmt = this.db.prepare("INSERT INTO join_store (k, data) VALUES (?, ?)");
44
+ this.selectStmt = this.db.prepare("SELECT data FROM join_store WHERE k = ?");
45
+ this.hasStmt = this.db.prepare("SELECT 1 FROM join_store WHERE k = ? LIMIT 1");
46
+ this.db.exec("BEGIN TRANSACTION;");
47
+ for (const [key, rows] of this.memoryMap.entries()) {
48
+ for (const r of rows) {
49
+ this.insertStmt.run(key, safeJsonStringify(r));
50
+ }
51
+ }
52
+ this.db.exec("COMMIT;");
53
+ this.memoryMap.clear();
54
+ this.isSpilled = true;
55
+ }
56
+ async set(key, row) {
57
+ this.totalCount++;
58
+ if (this.isSpilled && this.insertStmt) {
59
+ this.insertStmt.run(key, safeJsonStringify(row));
60
+ return;
61
+ }
62
+ let existing = this.memoryMap.get(key);
63
+ if (!existing) {
64
+ existing = [];
65
+ this.memoryMap.set(key, existing);
66
+ }
67
+ existing.push(row);
68
+ // Rough size estimate: key bytes + row keys/values
69
+ this.estimatedBytes += key.length * 2 + 128 + Object.keys(row).length * 32;
70
+ if (this.estimatedBytes >= this.memoryLimitBytes) {
71
+ await this.spillToDisk();
72
+ }
73
+ }
74
+ async get(key) {
75
+ if (this.isSpilled && this.selectStmt) {
76
+ const records = this.selectStmt.all(key);
77
+ if (records.length === 0)
78
+ return undefined;
79
+ return records.map((rec) => JSON.parse(rec.data));
80
+ }
81
+ return this.memoryMap.get(key);
82
+ }
83
+ async has(key) {
84
+ if (this.isSpilled && this.hasStmt) {
85
+ const res = this.hasStmt.get(key);
86
+ return res !== undefined;
87
+ }
88
+ return this.memoryMap.has(key);
89
+ }
90
+ markMatched(key) {
91
+ this.matchedKeys.add(key);
92
+ }
93
+ async *getUnmatched() {
94
+ if (this.isSpilled && this.db) {
95
+ const stmt = this.db.prepare("SELECT k, data FROM join_store");
96
+ for (const item of stmt.iterate()) {
97
+ if (!this.matchedKeys.has(item.k)) {
98
+ yield JSON.parse(item.data);
99
+ }
100
+ }
101
+ }
102
+ else {
103
+ for (const [k, rows] of this.memoryMap.entries()) {
104
+ if (!this.matchedKeys.has(k)) {
105
+ for (const row of rows) {
106
+ yield row;
107
+ }
108
+ }
109
+ }
110
+ }
111
+ }
112
+ count() {
113
+ return this.totalCount;
114
+ }
115
+ async close() {
116
+ this.memoryMap.clear();
117
+ this.matchedKeys.clear();
118
+ if (this.db) {
119
+ try {
120
+ this.db.close();
121
+ }
122
+ catch {
123
+ // Ignore
124
+ }
125
+ this.db = undefined;
126
+ }
127
+ if (this.dbPath) {
128
+ try {
129
+ if (fs.existsSync(this.dbPath)) {
130
+ fs.unlinkSync(this.dbPath);
131
+ }
132
+ }
133
+ catch {
134
+ // Ignore unlink error on exit
135
+ }
136
+ }
137
+ }
138
+ }
139
+ //# sourceMappingURL=index-storage.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index-storage.js","sourceRoot":"","sources":["../../../src/transforms/join/index-storage.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAC3C,OAAO,KAAK,EAAE,MAAM,SAAS,CAAC;AAC9B,OAAO,KAAK,EAAE,MAAM,SAAS,CAAC;AAC9B,OAAO,KAAK,IAAI,MAAM,WAAW,CAAC;AAElC,OAAO,EAAE,gBAAgB,EAAE,MAAM,uCAAuC,CAAC;AACzE,OAAO,EAAE,iBAAiB,EAAE,MAAM,2BAA2B,CAAC;AAG9D;;;GAGG;AACH,MAAM,OAAO,kBAAkB;IACrB,SAAS,GAAG,IAAI,GAAG,EAAiB,CAAC;IACrC,WAAW,GAAG,IAAI,GAAG,EAAU,CAAC;IAChC,cAAc,GAAG,CAAC,CAAC;IACnB,gBAAgB,CAAS;IACzB,SAAS,GAAG,KAAK,CAAC;IAElB,OAAO,CAAU;IACjB,MAAM,CAAU;IAChB,EAAE,CAAgB;IAClB,UAAU,CAAO;IACjB,UAAU,CAAO;IACjB,OAAO,CAAO;IACd,UAAU,GAAG,CAAC,CAAC;IAEvB,YAAY,OAA6D;QACvE,IAAI,CAAC,gBAAgB,GAAG,gBAAgB,CAAC,OAAO,EAAE,WAAW,EAAE,GAAG,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC;QAClF,IAAI,CAAC,OAAO,GAAG,OAAO,EAAE,OAAO,CAAC;IAClC,CAAC;IAEO,KAAK,CAAC,WAAW;QACvB,IAAI,IAAI,CAAC,SAAS;YAAE,OAAO;QAE3B,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,IAAI,EAAE,CAAC,MAAM,EAAE,CAAC;QAC9C,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,gBAAgB,IAAI,CAAC,GAAG,EAAE,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;QAC3G,IAAI,CAAC,EAAE,GAAG,IAAI,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QAExC,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC;;;;;;;;KAQZ,CAAC,CAAC;QAEH,IAAI,CAAC,UAAU,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC,gDAAgD,CAAC,CAAC;QACpF,IAAI,CAAC,UAAU,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC,yCAAyC,CAAC,CAAC;QAC7E,IAAI,CAAC,OAAO,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC,8CAA8C,CAAC,CAAC;QAE/E,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,oBAAoB,CAAC,CAAC;QACnC,KAAK,MAAM,CAAC,GAAG,EAAE,IAAI,CAAC,IAAI,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,EAAE,CAAC;YACnD,KAAK,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC;gBACrB,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,GAAG,EAAE,iBAAiB,CAAC,CAAC,CAAC,CAAC,CAAC;YACjD,CAAC;QACH,CAAC;QACD,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QAExB,IAAI,CAAC,SAAS,CAAC,KAAK,EAAE,CAAC;QACvB,IAAI,CAAC,SAAS,GAAG,IAAI,CAAC;IACxB,CAAC;IAED,KAAK,CAAC,GAAG,CAAC,GAAW,EAAE,GAAQ;QAC7B,IAAI,CAAC,UAAU,EAAE,CAAC;QAElB,IAAI,IAAI,CAAC,SAAS,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;YACtC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,GAAG,EAAE,iBAAiB,CAAC,GAAG,CAAC,CAAC,CAAC;YACjD,OAAO;QACT,CAAC;QAED,IAAI,QAAQ,GAAG,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;QACvC,IAAI,CAAC,QAAQ,EAAE,CAAC;YACd,QAAQ,GAAG,EAAE,CAAC;YACd,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,GAAG,EAAE,QAAQ,CAAC,CAAC;QACpC,CAAC;QACD,QAAQ,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;QAEnB,mDAAmD;QACnD,IAAI,CAAC,cAAc,IAAI,GAAG,CAAC,MAAM,GAAG,CAAC,GAAG,GAAG,GAAG,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,MAAM,GAAG,EAAE,CAAC;QAE3E,IAAI,IAAI,CAAC,cAAc,IAAI,IAAI,CAAC,gBAAgB,EAAE,CAAC;YACjD,MAAM,IAAI,CAAC,WAAW,EAAE,CAAC;QAC3B,CAAC;IACH,CAAC;IAED,KAAK,CAAC,GAAG,CAAC,GAAW;QACnB,IAAI,IAAI,CAAC,SAAS,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;YACtC,MAAM,OAAO,GAAG,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,GAAG,CAA4B,CAAC;YACpE,IAAI,OAAO,CAAC,MAAM,KAAK,CAAC;gBAAE,OAAO,SAAS,CAAC;YAC3C,OAAO,OAAO,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC;QACpD,CAAC;QACD,OAAO,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;IACjC,CAAC;IAED,KAAK,CAAC,GAAG,CAAC,GAAW;QACnB,IAAI,IAAI,CAAC,SAAS,IAAI,IAAI,CAAC,OAAO,EAAE,CAAC;YACnC,MAAM,GAAG,GAAG,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;YAClC,OAAO,GAAG,KAAK,SAAS,CAAC;QAC3B,CAAC;QACD,OAAO,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;IACjC,CAAC;IAED,WAAW,CAAC,GAAW;QACrB,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;IAC5B,CAAC;IAED,KAAK,CAAC,CAAC,YAAY;QACjB,IAAI,IAAI,CAAC,SAAS,IAAI,IAAI,CAAC,EAAE,EAAE,CAAC;YAC9B,MAAM,IAAI,GAAG,IAAI,CAAC,EAAE,CAAC,OAAO,CAAC,gCAAgC,CAAC,CAAC;YAC/D,KAAK,MAAM,IAAI,IAAI,IAAI,CAAC,OAAO,EAA2C,EAAE,CAAC;gBAC3E,IAAI,CAAC,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;oBAClC,MAAM,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;gBAC9B,CAAC;YACH,CAAC;QACH,CAAC;aAAM,CAAC;YACN,KAAK,MAAM,CAAC,CAAC,EAAE,IAAI,CAAC,IAAI,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,EAAE,CAAC;gBACjD,IAAI,CAAC,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC;oBAC7B,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;wBACvB,MAAM,GAAG,CAAC;oBACZ,CAAC;gBACH,CAAC;YACH,CAAC;QACH,CAAC;IACH,CAAC;IAED,KAAK;QACH,OAAO,IAAI,CAAC,UAAU,CAAC;IACzB,CAAC;IAED,KAAK,CAAC,KAAK;QACT,IAAI,CAAC,SAAS,CAAC,KAAK,EAAE,CAAC;QACvB,IAAI,CAAC,WAAW,CAAC,KAAK,EAAE,CAAC;QAEzB,IAAI,IAAI,CAAC,EAAE,EAAE,CAAC;YACZ,IAAI,CAAC;gBACH,IAAI,CAAC,EAAE,CAAC,KAAK,EAAE,CAAC;YAClB,CAAC;YAAC,MAAM,CAAC;gBACP,SAAS;YACX,CAAC;YACD,IAAI,CAAC,EAAE,GAAG,SAAS,CAAC;QACtB,CAAC;QAED,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;YAChB,IAAI,CAAC;gBACH,IAAI,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC;oBAC/B,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;gBAC7B,CAAC;YACH,CAAC;YAAC,MAAM,CAAC;gBACP,8BAA8B;YAChC,CAAC;QACH,CAAC;IACH,CAAC;CACF"}
@@ -0,0 +1,4 @@
1
+ export * from "./types.js";
2
+ export * from "./index-storage.js";
3
+ export * from "./join.js";
4
+ //# sourceMappingURL=index.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/transforms/join/index.ts"],"names":[],"mappings":"AAAA,cAAc,YAAY,CAAC;AAC3B,cAAc,oBAAoB,CAAC;AACnC,cAAc,WAAW,CAAC"}
@@ -0,0 +1,4 @@
1
+ export * from "./types.js";
2
+ export * from "./index-storage.js";
3
+ export * from "./join.js";
4
+ //# sourceMappingURL=index.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/transforms/join/index.ts"],"names":[],"mappings":"AAAA,cAAc,YAAY,CAAC;AAC3B,cAAc,oBAAoB,CAAC;AACnC,cAAc,WAAW,CAAC"}
@@ -0,0 +1,15 @@
1
+ import type { DataStream, TabularReader, TransformFunction } from "../../core/types.js";
2
+ import type { JoinKeyMapping, JoinOptions } from "./types.js";
3
+ /**
4
+ * Parses user join key options into structured left/right column mappings.
5
+ */
6
+ export declare function parseJoinKeys(options: JoinOptions): JoinKeyMapping;
7
+ /**
8
+ * Joins two tabular streams with bounded memory and spill-to-disk index support.
9
+ */
10
+ export declare function joinStreams(leftSource: DataStream | TabularReader, rightSource: DataStream | TabularReader, options?: JoinOptions): DataStream;
11
+ /**
12
+ * Returns a TransformFunction for pipeline chaining (e.g. pipeline.pipe(joinRows(rightReader, options))).
13
+ */
14
+ export declare function joinRows(rightSource: DataStream | TabularReader, options?: JoinOptions): TransformFunction;
15
+ //# sourceMappingURL=join.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"join.d.ts","sourceRoot":"","sources":["../../../src/transforms/join/join.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAa,UAAU,EAAO,aAAa,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAC;AAExG,OAAO,KAAK,EAAE,cAAc,EAAE,WAAW,EAAY,MAAM,YAAY,CAAC;AAExE;;GAEG;AACH,wBAAgB,aAAa,CAAC,OAAO,EAAE,WAAW,GAAG,cAAc,CAgClE;AA8ED;;GAEG;AACH,wBAAuB,WAAW,CAChC,UAAU,EAAE,UAAU,GAAG,aAAa,EACtC,WAAW,EAAE,UAAU,GAAG,aAAa,EACvC,OAAO,GAAE,WAAgB,GACxB,UAAU,CA2GZ;AAED;;GAEG;AACH,wBAAgB,QAAQ,CACtB,WAAW,EAAE,UAAU,GAAG,aAAa,EACvC,OAAO,GAAE,WAAgB,GACxB,iBAAiB,CAInB"}
@@ -0,0 +1,216 @@
1
+ import { encodeCompositeKey } from "../../diff/key.js";
2
+ import { InvalidArgumentError } from "../../core/errors.js";
3
+ import { SpillableJoinIndex } from "./index-storage.js";
4
+ /**
5
+ * Parses user join key options into structured left/right column mappings.
6
+ */
7
+ export function parseJoinKeys(options) {
8
+ if (options.leftKey && options.rightKey) {
9
+ const leftCols = Array.isArray(options.leftKey) ? options.leftKey : options.leftKey.split(",").map((s) => s.trim());
10
+ const rightCols = Array.isArray(options.rightKey) ? options.rightKey : options.rightKey.split(",").map((s) => s.trim());
11
+ if (leftCols.length !== rightCols.length) {
12
+ throw new InvalidArgumentError(`Mismatched join keys: left has ${leftCols.length} columns (${leftCols.join(",")}), right has ${rightCols.length} columns (${rightCols.join(",")})`);
13
+ }
14
+ return { left: leftCols, right: rightCols };
15
+ }
16
+ if (options.on) {
17
+ const specs = Array.isArray(options.on) ? options.on : options.on.split(",").map((s) => s.trim());
18
+ const leftCols = [];
19
+ const rightCols = [];
20
+ for (const spec of specs) {
21
+ if (spec.includes("=")) {
22
+ const parts = spec.split("=");
23
+ leftCols.push(parts[0].trim());
24
+ rightCols.push(parts[1].trim());
25
+ }
26
+ else {
27
+ leftCols.push(spec.trim());
28
+ rightCols.push(spec.trim());
29
+ }
30
+ }
31
+ return { left: leftCols, right: rightCols };
32
+ }
33
+ // Default fallback to 'id'
34
+ return { left: ["id"], right: ["id"] };
35
+ }
36
+ /**
37
+ * Generates an encoded lookup key for a row given key columns.
38
+ */
39
+ function getRowKey(row, keyCols) {
40
+ return encodeCompositeKey(row, keyCols).encoded;
41
+ }
42
+ /**
43
+ * Merges a left row and right row, handling colliding column names.
44
+ */
45
+ function mergeRows(leftRow, rightRow, joinKeys, options, sampleLeftCols, sampleRightCols) {
46
+ const result = {};
47
+ const prefixRight = options.prefixRight || "";
48
+ const suffixRight = options.suffixRight !== undefined ? options.suffixRight : (prefixRight ? "" : "_right");
49
+ const prefixLeft = options.prefixLeft || "";
50
+ const suffixLeft = options.suffixLeft || "";
51
+ if (leftRow) {
52
+ for (const [k, v] of Object.entries(leftRow)) {
53
+ const isKey = joinKeys.left.includes(k);
54
+ const outKey = isKey ? k : `${prefixLeft}${k}${suffixLeft}`;
55
+ result[outKey] = v;
56
+ }
57
+ }
58
+ else if (sampleLeftCols) {
59
+ for (const col of sampleLeftCols) {
60
+ const isKey = joinKeys.left.includes(col);
61
+ const outKey = isKey ? col : `${prefixLeft}${col}${suffixLeft}`;
62
+ result[outKey] = null;
63
+ }
64
+ }
65
+ if (rightRow) {
66
+ for (const [k, v] of Object.entries(rightRow)) {
67
+ const rightKeyIdx = joinKeys.right.indexOf(k);
68
+ if (rightKeyIdx >= 0) {
69
+ // This is a join key column
70
+ const leftKeyName = joinKeys.left[rightKeyIdx];
71
+ if (!leftRow) {
72
+ result[leftKeyName] = v;
73
+ }
74
+ continue;
75
+ }
76
+ // Check if collides with left row non-key column
77
+ let targetKey = k;
78
+ if (leftRow && k in leftRow) {
79
+ targetKey = `${prefixRight}${k}${suffixRight}`;
80
+ }
81
+ else if (prefixRight || (suffixRight && suffixRight !== "_right")) {
82
+ targetKey = `${prefixRight}${k}${suffixRight}`;
83
+ }
84
+ result[targetKey] = v;
85
+ }
86
+ }
87
+ else if (sampleRightCols) {
88
+ for (const col of sampleRightCols) {
89
+ const rightKeyIdx = joinKeys.right.indexOf(col);
90
+ if (rightKeyIdx >= 0)
91
+ continue;
92
+ let targetKey = col;
93
+ if (leftRow && col in leftRow) {
94
+ targetKey = `${prefixRight}${col}${suffixRight}`;
95
+ }
96
+ else if (prefixRight || (suffixRight && suffixRight !== "_right")) {
97
+ targetKey = `${prefixRight}${col}${suffixRight}`;
98
+ }
99
+ result[targetKey] = null;
100
+ }
101
+ }
102
+ return result;
103
+ }
104
+ /**
105
+ * Joins two tabular streams with bounded memory and spill-to-disk index support.
106
+ */
107
+ export async function* joinStreams(leftSource, rightSource, options = {}) {
108
+ const joinType = options.type || "inner";
109
+ const keys = parseJoinKeys(options);
110
+ const effectiveBatchSize = Math.max(1, options.batchSize || 1000);
111
+ const rightIndex = new SpillableJoinIndex({
112
+ memoryLimit: options.memoryLimit,
113
+ tempDir: options.tempDir,
114
+ });
115
+ const rightStream = "read" in rightSource ? rightSource.read({ batchSize: effectiveBatchSize }) : rightSource;
116
+ const leftStream = "read" in leftSource ? leftSource.read({ batchSize: effectiveBatchSize }) : leftSource;
117
+ let rightSampleCols = [];
118
+ let leftSampleCols = [];
119
+ try {
120
+ // 1. Build Phase: Ingest right dataset into SpillableJoinIndex
121
+ for await (const batch of rightStream) {
122
+ for (const row of batch.rows) {
123
+ if (rightSampleCols.length === 0) {
124
+ rightSampleCols = Object.keys(row);
125
+ }
126
+ const key = getRowKey(row, keys.right);
127
+ await rightIndex.set(key, row);
128
+ }
129
+ }
130
+ // 2. Probe Phase: Stream left dataset and match against rightIndex
131
+ let currentBatch = [];
132
+ let globalOffset = 0;
133
+ for await (const batch of leftStream) {
134
+ for (const leftRow of batch.rows) {
135
+ if (leftSampleCols.length === 0) {
136
+ leftSampleCols = Object.keys(leftRow);
137
+ }
138
+ const key = getRowKey(leftRow, keys.left);
139
+ if (joinType === "semi") {
140
+ const exists = await rightIndex.has(key);
141
+ if (exists) {
142
+ currentBatch.push(leftRow);
143
+ }
144
+ }
145
+ else if (joinType === "anti") {
146
+ const exists = await rightIndex.has(key);
147
+ if (!exists) {
148
+ currentBatch.push(leftRow);
149
+ }
150
+ }
151
+ else {
152
+ const matchedRightRows = await rightIndex.get(key);
153
+ if (matchedRightRows && matchedRightRows.length > 0) {
154
+ rightIndex.markMatched(key);
155
+ for (const rightRow of matchedRightRows) {
156
+ const merged = mergeRows(leftRow, rightRow, keys, options, leftSampleCols, rightSampleCols);
157
+ currentBatch.push(merged);
158
+ }
159
+ }
160
+ else if (joinType === "left" || joinType === "full") {
161
+ const merged = mergeRows(leftRow, null, keys, options, leftSampleCols, rightSampleCols);
162
+ currentBatch.push(merged);
163
+ }
164
+ }
165
+ if (currentBatch.length >= effectiveBatchSize) {
166
+ yield {
167
+ rows: currentBatch,
168
+ offset: globalOffset,
169
+ };
170
+ globalOffset += currentBatch.length;
171
+ currentBatch = [];
172
+ }
173
+ }
174
+ }
175
+ // 3. Post-Probe Phase: For right and full outer joins, emit unmatched right rows
176
+ if (joinType === "right" || joinType === "full") {
177
+ for await (const unmatchedRightRow of rightIndex.getUnmatched()) {
178
+ const merged = mergeRows(null, unmatchedRightRow, keys, options, leftSampleCols, rightSampleCols);
179
+ currentBatch.push(merged);
180
+ if (currentBatch.length >= effectiveBatchSize) {
181
+ yield {
182
+ rows: currentBatch,
183
+ offset: globalOffset,
184
+ };
185
+ globalOffset += currentBatch.length;
186
+ currentBatch = [];
187
+ }
188
+ }
189
+ }
190
+ if (currentBatch.length > 0) {
191
+ yield {
192
+ rows: currentBatch,
193
+ offset: globalOffset,
194
+ };
195
+ globalOffset += currentBatch.length;
196
+ }
197
+ }
198
+ finally {
199
+ await rightIndex.close();
200
+ if ("close" in rightSource && typeof rightSource.close === "function") {
201
+ await rightSource.close();
202
+ }
203
+ if ("close" in leftSource && typeof leftSource.close === "function") {
204
+ await leftSource.close();
205
+ }
206
+ }
207
+ }
208
+ /**
209
+ * Returns a TransformFunction for pipeline chaining (e.g. pipeline.pipe(joinRows(rightReader, options))).
210
+ */
211
+ export function joinRows(rightSource, options = {}) {
212
+ return (leftStream) => {
213
+ return joinStreams(leftStream, rightSource, options);
214
+ };
215
+ }
216
+ //# sourceMappingURL=join.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"join.js","sourceRoot":"","sources":["../../../src/transforms/join/join.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,kBAAkB,EAAE,MAAM,mBAAmB,CAAC;AACvD,OAAO,EAAE,oBAAoB,EAAE,MAAM,sBAAsB,CAAC;AAE5D,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAC;AAGxD;;GAEG;AACH,MAAM,UAAU,aAAa,CAAC,OAAoB;IAChD,IAAI,OAAO,CAAC,OAAO,IAAI,OAAO,CAAC,QAAQ,EAAE,CAAC;QACxC,MAAM,QAAQ,GAAG,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QACpH,MAAM,SAAS,GAAG,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QACxH,IAAI,QAAQ,CAAC,MAAM,KAAK,SAAS,CAAC,MAAM,EAAE,CAAC;YACzC,MAAM,IAAI,oBAAoB,CAC5B,kCAAkC,QAAQ,CAAC,MAAM,aAAa,QAAQ,CAAC,IAAI,CAAC,GAAG,CAAC,gBAAgB,SAAS,CAAC,MAAM,aAAa,SAAS,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,CACpJ,CAAC;QACJ,CAAC;QACD,OAAO,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC;IAC9C,CAAC;IAED,IAAI,OAAO,CAAC,EAAE,EAAE,CAAC;QACf,MAAM,KAAK,GAAG,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QAClG,MAAM,QAAQ,GAAa,EAAE,CAAC;QAC9B,MAAM,SAAS,GAAa,EAAE,CAAC;QAE/B,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACzB,IAAI,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;gBACvB,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;gBAC9B,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,IAAI,EAAE,CAAC,CAAC;gBAChC,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,IAAI,EAAE,CAAC,CAAC;YACnC,CAAC;iBAAM,CAAC;gBACN,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC;gBAC3B,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC;YAC9B,CAAC;QACH,CAAC;QACD,OAAO,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC;IAC9C,CAAC;IAED,2BAA2B;IAC3B,OAAO,EAAE,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC;AACzC,CAAC;AAED;;GAEG;AACH,SAAS,SAAS,CAAC,GAAQ,EAAE,OAAiB;IAC5C,OAAO,kBAAkB,CAAC,GAAG,EAAE,OAAO,CAAC,CAAC,OAAO,CAAC;AAClD,CAAC;AAED;;GAEG;AACH,SAAS,SAAS,CAChB,OAAmB,EACnB,QAAoB,EACpB,QAAwB,EACxB,OAAoB,EACpB,cAAyB,EACzB,eAA0B;IAE1B,MAAM,MAAM,GAAQ,EAAE,CAAC;IACvB,MAAM,WAAW,GAAG,OAAO,CAAC,WAAW,IAAI,EAAE,CAAC;IAC9C,MAAM,WAAW,GAAG,OAAO,CAAC,WAAW,KAAK,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC;IAC5G,MAAM,UAAU,GAAG,OAAO,CAAC,UAAU,IAAI,EAAE,CAAC;IAC5C,MAAM,UAAU,GAAG,OAAO,CAAC,UAAU,IAAI,EAAE,CAAC;IAE5C,IAAI,OAAO,EAAE,CAAC;QACZ,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;YAC7C,MAAM,KAAK,GAAG,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;YACxC,MAAM,MAAM,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,UAAU,GAAG,CAAC,GAAG,UAAU,EAAE,CAAC;YAC5D,MAAM,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC;QACrB,CAAC;IACH,CAAC;SAAM,IAAI,cAAc,EAAE,CAAC;QAC1B,KAAK,MAAM,GAAG,IAAI,cAAc,EAAE,CAAC;YACjC,MAAM,KAAK,GAAG,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC;YAC1C,MAAM,MAAM,GAAG,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG,UAAU,GAAG,GAAG,GAAG,UAAU,EAAE,CAAC;YAChE,MAAM,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC;QACxB,CAAC;IACH,CAAC;IAED,IAAI,QAAQ,EAAE,CAAC;QACb,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,CAAC;YAC9C,MAAM,WAAW,GAAG,QAAQ,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YAC9C,IAAI,WAAW,IAAI,CAAC,EAAE,CAAC;gBACrB,4BAA4B;gBAC5B,MAAM,WAAW,GAAG,QAAQ,CAAC,IAAI,CAAC,WAAW,CAAE,CAAC;gBAChD,IAAI,CAAC,OAAO,EAAE,CAAC;oBACb,MAAM,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;gBAC1B,CAAC;gBACD,SAAS;YACX,CAAC;YAED,iDAAiD;YACjD,IAAI,SAAS,GAAG,CAAC,CAAC;YAClB,IAAI,OAAO,IAAI,CAAC,IAAI,OAAO,EAAE,CAAC;gBAC5B,SAAS,GAAG,GAAG,WAAW,GAAG,CAAC,GAAG,WAAW,EAAE,CAAC;YACjD,CAAC;iBAAM,IAAI,WAAW,IAAI,CAAC,WAAW,IAAI,WAAW,KAAK,QAAQ,CAAC,EAAE,CAAC;gBACpE,SAAS,GAAG,GAAG,WAAW,GAAG,CAAC,GAAG,WAAW,EAAE,CAAC;YACjD,CAAC;YACD,MAAM,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC;QACxB,CAAC;IACH,CAAC;SAAM,IAAI,eAAe,EAAE,CAAC;QAC3B,KAAK,MAAM,GAAG,IAAI,eAAe,EAAE,CAAC;YAClC,MAAM,WAAW,GAAG,QAAQ,CAAC,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;YAChD,IAAI,WAAW,IAAI,CAAC;gBAAE,SAAS;YAC/B,IAAI,SAAS,GAAG,GAAG,CAAC;YACpB,IAAI,OAAO,IAAI,GAAG,IAAI,OAAO,EAAE,CAAC;gBAC9B,SAAS,GAAG,GAAG,WAAW,GAAG,GAAG,GAAG,WAAW,EAAE,CAAC;YACnD,CAAC;iBAAM,IAAI,WAAW,IAAI,CAAC,WAAW,IAAI,WAAW,KAAK,QAAQ,CAAC,EAAE,CAAC;gBACpE,SAAS,GAAG,GAAG,WAAW,GAAG,GAAG,GAAG,WAAW,EAAE,CAAC;YACnD,CAAC;YACD,MAAM,CAAC,SAAS,CAAC,GAAG,IAAI,CAAC;QAC3B,CAAC;IACH,CAAC;IAED,OAAO,MAAM,CAAC;AAChB,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,WAAW,CAChC,UAAsC,EACtC,WAAuC,EACvC,UAAuB,EAAE;IAEzB,MAAM,QAAQ,GAAa,OAAO,CAAC,IAAI,IAAI,OAAO,CAAC;IACnD,MAAM,IAAI,GAAG,aAAa,CAAC,OAAO,CAAC,CAAC;IACpC,MAAM,kBAAkB,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,OAAO,CAAC,SAAS,IAAI,IAAI,CAAC,CAAC;IAElE,MAAM,UAAU,GAAG,IAAI,kBAAkB,CAAC;QACxC,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,OAAO,EAAE,OAAO,CAAC,OAAO;KACzB,CAAC,CAAC;IAEH,MAAM,WAAW,GAAe,MAAM,IAAI,WAAW,CAAC,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,EAAE,SAAS,EAAE,kBAAkB,EAAE,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC;IAC1H,MAAM,UAAU,GAAe,MAAM,IAAI,UAAU,CAAC,CAAC,CAAC,UAAU,CAAC,IAAI,CAAC,EAAE,SAAS,EAAE,kBAAkB,EAAE,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC;IAEtH,IAAI,eAAe,GAAa,EAAE,CAAC;IACnC,IAAI,cAAc,GAAa,EAAE,CAAC;IAElC,IAAI,CAAC;QACH,+DAA+D;QAC/D,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,WAAW,EAAE,CAAC;YACtC,KAAK,MAAM,GAAG,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC;gBAC7B,IAAI,eAAe,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;oBACjC,eAAe,GAAG,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;gBACrC,CAAC;gBACD,MAAM,GAAG,GAAG,SAAS,CAAC,GAAG,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;gBACvC,MAAM,UAAU,CAAC,GAAG,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC;YACjC,CAAC;QACH,CAAC;QAED,mEAAmE;QACnE,IAAI,YAAY,GAAU,EAAE,CAAC;QAC7B,IAAI,YAAY,GAAG,CAAC,CAAC;QAErB,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,EAAE,CAAC;YACrC,KAAK,MAAM,OAAO,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC;gBACjC,IAAI,cAAc,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;oBAChC,cAAc,GAAG,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;gBACxC,CAAC;gBACD,MAAM,GAAG,GAAG,SAAS,CAAC,OAAO,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;gBAE1C,IAAI,QAAQ,KAAK,MAAM,EAAE,CAAC;oBACxB,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;oBACzC,IAAI,MAAM,EAAE,CAAC;wBACX,YAAY,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;oBAC7B,CAAC;gBACH,CAAC;qBAAM,IAAI,QAAQ,KAAK,MAAM,EAAE,CAAC;oBAC/B,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;oBACzC,IAAI,CAAC,MAAM,EAAE,CAAC;wBACZ,YAAY,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;oBAC7B,CAAC;gBACH,CAAC;qBAAM,CAAC;oBACN,MAAM,gBAAgB,GAAG,MAAM,UAAU,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;oBACnD,IAAI,gBAAgB,IAAI,gBAAgB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;wBACpD,UAAU,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;wBAC5B,KAAK,MAAM,QAAQ,IAAI,gBAAgB,EAAE,CAAC;4BACxC,MAAM,MAAM,GAAG,SAAS,CAAC,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,OAAO,EAAE,cAAc,EAAE,eAAe,CAAC,CAAC;4BAC5F,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;wBAC5B,CAAC;oBACH,CAAC;yBAAM,IAAI,QAAQ,KAAK,MAAM,IAAI,QAAQ,KAAK,MAAM,EAAE,CAAC;wBACtD,MAAM,MAAM,GAAG,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,IAAI,EAAE,OAAO,EAAE,cAAc,EAAE,eAAe,CAAC,CAAC;wBACxF,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;oBAC5B,CAAC;gBACH,CAAC;gBAED,IAAI,YAAY,CAAC,MAAM,IAAI,kBAAkB,EAAE,CAAC;oBAC9C,MAAM;wBACJ,IAAI,EAAE,YAAY;wBAClB,MAAM,EAAE,YAAY;qBACrB,CAAC;oBACF,YAAY,IAAI,YAAY,CAAC,MAAM,CAAC;oBACpC,YAAY,GAAG,EAAE,CAAC;gBACpB,CAAC;YACH,CAAC;QACH,CAAC;QAED,iFAAiF;QACjF,IAAI,QAAQ,KAAK,OAAO,IAAI,QAAQ,KAAK,MAAM,EAAE,CAAC;YAChD,IAAI,KAAK,EAAE,MAAM,iBAAiB,IAAI,UAAU,CAAC,YAAY,EAAE,EAAE,CAAC;gBAChE,MAAM,MAAM,GAAG,SAAS,CAAC,IAAI,EAAE,iBAAiB,EAAE,IAAI,EAAE,OAAO,EAAE,cAAc,EAAE,eAAe,CAAC,CAAC;gBAClG,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;gBAE1B,IAAI,YAAY,CAAC,MAAM,IAAI,kBAAkB,EAAE,CAAC;oBAC9C,MAAM;wBACJ,IAAI,EAAE,YAAY;wBAClB,MAAM,EAAE,YAAY;qBACrB,CAAC;oBACF,YAAY,IAAI,YAAY,CAAC,MAAM,CAAC;oBACpC,YAAY,GAAG,EAAE,CAAC;gBACpB,CAAC;YACH,CAAC;QACH,CAAC;QAED,IAAI,YAAY,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC5B,MAAM;gBACJ,IAAI,EAAE,YAAY;gBAClB,MAAM,EAAE,YAAY;aACrB,CAAC;YACF,YAAY,IAAI,YAAY,CAAC,MAAM,CAAC;QACtC,CAAC;IACH,CAAC;YAAS,CAAC;QACT,MAAM,UAAU,CAAC,KAAK,EAAE,CAAC;QACzB,IAAI,OAAO,IAAI,WAAW,IAAI,OAAO,WAAW,CAAC,KAAK,KAAK,UAAU,EAAE,CAAC;YACtE,MAAM,WAAW,CAAC,KAAK,EAAE,CAAC;QAC5B,CAAC;QACD,IAAI,OAAO,IAAI,UAAU,IAAI,OAAO,UAAU,CAAC,KAAK,KAAK,UAAU,EAAE,CAAC;YACpE,MAAM,UAAU,CAAC,KAAK,EAAE,CAAC;QAC3B,CAAC;IACH,CAAC;AACH,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,QAAQ,CACtB,WAAuC,EACvC,UAAuB,EAAE;IAEzB,OAAO,CAAC,UAAsB,EAAc,EAAE;QAC5C,OAAO,WAAW,CAAC,UAAU,EAAE,WAAW,EAAE,OAAO,CAAC,CAAC;IACvD,CAAC,CAAC;AACJ,CAAC"}
@@ -0,0 +1,29 @@
1
+ import type { Row } from "../../core/types.js";
2
+ export type JoinType = "inner" | "left" | "right" | "full" | "semi" | "anti";
3
+ export interface JoinKeyMapping {
4
+ left: string[];
5
+ right: string[];
6
+ }
7
+ export interface JoinOptions {
8
+ on?: string | string[];
9
+ leftKey?: string | string[];
10
+ rightKey?: string | string[];
11
+ type?: JoinType;
12
+ prefixLeft?: string;
13
+ suffixLeft?: string;
14
+ prefixRight?: string;
15
+ suffixRight?: string;
16
+ memoryLimit?: number | string;
17
+ tempDir?: string;
18
+ batchSize?: number;
19
+ }
20
+ export interface JoinIndex {
21
+ set(key: string, row: Row): Promise<void>;
22
+ get(key: string): Promise<Row[] | undefined>;
23
+ has(key: string): Promise<boolean>;
24
+ markMatched(key: string): void;
25
+ getUnmatched(): AsyncIterable<Row>;
26
+ count(): number;
27
+ close(): Promise<void>;
28
+ }
29
+ //# sourceMappingURL=types.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../../../src/transforms/join/types.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,GAAG,EAAE,MAAM,qBAAqB,CAAC;AAE/C,MAAM,MAAM,QAAQ,GAAG,OAAO,GAAG,MAAM,GAAG,OAAO,GAAG,MAAM,GAAG,MAAM,GAAG,MAAM,CAAC;AAE7E,MAAM,WAAW,cAAc;IAC7B,IAAI,EAAE,MAAM,EAAE,CAAC;IACf,KAAK,EAAE,MAAM,EAAE,CAAC;CACjB;AAED,MAAM,WAAW,WAAW;IAC1B,EAAE,CAAC,EAAE,MAAM,GAAG,MAAM,EAAE,CAAC;IACvB,OAAO,CAAC,EAAE,MAAM,GAAG,MAAM,EAAE,CAAC;IAC5B,QAAQ,CAAC,EAAE,MAAM,GAAG,MAAM,EAAE,CAAC;IAC7B,IAAI,CAAC,EAAE,QAAQ,CAAC;IAChB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,WAAW,CAAC,EAAE,MAAM,GAAG,MAAM,CAAC;IAC9B,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;CACpB;AAED,MAAM,WAAW,SAAS;IACxB,GAAG,CAAC,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,GAAG,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IAC1C,GAAG,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,GAAG,EAAE,GAAG,SAAS,CAAC,CAAC;IAC7C,GAAG,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC,CAAC;IACnC,WAAW,CAAC,GAAG,EAAE,MAAM,GAAG,IAAI,CAAC;IAC/B,YAAY,IAAI,aAAa,CAAC,GAAG,CAAC,CAAC;IACnC,KAAK,IAAI,MAAM,CAAC;IAChB,KAAK,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC;CACxB"}
@@ -0,0 +1,2 @@
1
+ export {};
2
+ //# sourceMappingURL=types.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"types.js","sourceRoot":"","sources":["../../../src/transforms/join/types.ts"],"names":[],"mappings":""}
@@ -0,0 +1,24 @@
1
+ import type { TransformFunction } from "../core/types.js";
2
+ export interface WindowFunctionSpec {
3
+ outputCol: string;
4
+ fn: "row_number" | "rank" | "dense_rank" | "lag" | "lead" | "running_sum" | "running_avg" | "running_count" | "running_min" | "running_max" | "moving_sum" | "moving_avg" | "moving_min" | "moving_max";
5
+ sourceCol?: string;
6
+ offset?: number;
7
+ defaultValue?: unknown;
8
+ windowSize?: number;
9
+ }
10
+ export interface WindowOptions {
11
+ specs: Record<string, string> | WindowFunctionSpec[] | string[];
12
+ by?: string | string[];
13
+ batchSize?: number;
14
+ }
15
+ /**
16
+ * Parses user window function specifications (e.g. "rn=row_number()", "lag(revenue, 1, 0)", "moving_avg(rev, 7)").
17
+ */
18
+ export declare function parseWindowSpecs(input: Record<string, string> | WindowFunctionSpec[] | string[]): WindowFunctionSpec[];
19
+ /**
20
+ * Streaming Window / Rolling Function Transform.
21
+ * Operates over sliding ring buffers and running accumulators with bounded O(W) / O(1) memory.
22
+ */
23
+ export declare function windowRows(options: WindowOptions): TransformFunction;
24
+ //# sourceMappingURL=window.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"window.d.ts","sourceRoot":"","sources":["../../src/transforms/window.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAA8B,iBAAiB,EAAE,MAAM,kBAAkB,CAAC;AAItF,MAAM,WAAW,kBAAkB;IACjC,SAAS,EAAE,MAAM,CAAC;IAClB,EAAE,EACE,YAAY,GACZ,MAAM,GACN,YAAY,GACZ,KAAK,GACL,MAAM,GACN,aAAa,GACb,aAAa,GACb,eAAe,GACf,aAAa,GACb,aAAa,GACb,YAAY,GACZ,YAAY,GACZ,YAAY,GACZ,YAAY,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,YAAY,CAAC,EAAE,OAAO,CAAC;IACvB,UAAU,CAAC,EAAE,MAAM,CAAC;CACrB;AAED,MAAM,WAAW,aAAa;IAC5B,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,kBAAkB,EAAE,GAAG,MAAM,EAAE,CAAC;IAChE,EAAE,CAAC,EAAE,MAAM,GAAG,MAAM,EAAE,CAAC;IACvB,SAAS,CAAC,EAAE,MAAM,CAAC;CACpB;AAED;;GAEG;AACH,wBAAgB,gBAAgB,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,kBAAkB,EAAE,GAAG,MAAM,EAAE,GAAG,kBAAkB,EAAE,CAyBtH;AAmFD;;;GAGG;AACH,wBAAgB,UAAU,CAAC,OAAO,EAAE,aAAa,GAAG,iBAAiB,CA2OpE"}