@chkit/plugin-backfill 0.1.0-beta.20 → 0.1.0-beta.21
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.
- package/README.md +130 -0
- package/dist/async-backfill.d.ts +4 -4
- package/dist/async-backfill.d.ts.map +1 -1
- package/dist/async-backfill.js +2 -2
- package/dist/async-backfill.js.map +1 -1
- package/dist/chunking/analyze.d.ts +5 -35
- package/dist/chunking/analyze.d.ts.map +1 -1
- package/dist/chunking/analyze.js +3 -71
- package/dist/chunking/analyze.js.map +1 -1
- package/dist/chunking/boundary-codec.d.ts +10 -0
- package/dist/chunking/boundary-codec.d.ts.map +1 -0
- package/dist/chunking/boundary-codec.js +79 -0
- package/dist/chunking/boundary-codec.js.map +1 -0
- package/dist/chunking/e2e/constants.d.ts +2 -0
- package/dist/chunking/e2e/constants.d.ts.map +1 -0
- package/dist/chunking/e2e/constants.js +2 -0
- package/dist/chunking/e2e/constants.js.map +1 -0
- package/dist/chunking/e2e/seed-datasets.script.d.ts +20 -0
- package/dist/chunking/e2e/seed-datasets.script.d.ts.map +1 -0
- package/dist/chunking/e2e/seed-datasets.script.js +134 -0
- package/dist/chunking/e2e/seed-datasets.script.js.map +1 -0
- package/dist/chunking/introspect.d.ts +6 -0
- package/dist/chunking/introspect.d.ts.map +1 -1
- package/dist/chunking/introspect.js +113 -22
- package/dist/chunking/introspect.js.map +1 -1
- package/dist/chunking/partition-slices.d.ts +14 -0
- package/dist/chunking/partition-slices.d.ts.map +1 -0
- package/dist/chunking/partition-slices.js +111 -0
- package/dist/chunking/partition-slices.js.map +1 -0
- package/dist/chunking/planner.d.ts +3 -0
- package/dist/chunking/planner.d.ts.map +1 -0
- package/dist/chunking/planner.js +343 -0
- package/dist/chunking/planner.js.map +1 -0
- package/dist/chunking/services/distribution-source.d.ts +11 -0
- package/dist/chunking/services/distribution-source.d.ts.map +1 -0
- package/dist/chunking/services/distribution-source.js +60 -0
- package/dist/chunking/services/distribution-source.js.map +1 -0
- package/dist/chunking/services/metadata-source.d.ts +4 -0
- package/dist/chunking/services/metadata-source.d.ts.map +1 -0
- package/dist/chunking/services/metadata-source.js +138 -0
- package/dist/chunking/services/metadata-source.js.map +1 -0
- package/dist/chunking/services/row-probe.d.ts +14 -0
- package/dist/chunking/services/row-probe.d.ts.map +1 -0
- package/dist/chunking/services/row-probe.js +62 -0
- package/dist/chunking/services/row-probe.js.map +1 -0
- package/dist/chunking/sql.d.ts +13 -5
- package/dist/chunking/sql.d.ts.map +1 -1
- package/dist/chunking/sql.js +190 -107
- package/dist/chunking/sql.js.map +1 -1
- package/dist/chunking/strategies/equal-width-split.d.ts +4 -0
- package/dist/chunking/strategies/equal-width-split.d.ts.map +1 -0
- package/dist/chunking/strategies/equal-width-split.js +46 -0
- package/dist/chunking/strategies/equal-width-split.js.map +1 -0
- package/dist/chunking/strategies/group-by-key-split.d.ts +3 -0
- package/dist/chunking/strategies/group-by-key-split.d.ts.map +1 -0
- package/dist/chunking/strategies/group-by-key-split.js +54 -0
- package/dist/chunking/strategies/group-by-key-split.js.map +1 -0
- package/dist/chunking/strategies/metadata-single-chunk.d.ts +3 -0
- package/dist/chunking/strategies/metadata-single-chunk.d.ts.map +1 -0
- package/dist/chunking/strategies/metadata-single-chunk.js +5 -0
- package/dist/chunking/strategies/metadata-single-chunk.js.map +1 -0
- package/dist/chunking/strategies/quantile-range-split.d.ts +5 -0
- package/dist/chunking/strategies/quantile-range-split.d.ts.map +1 -0
- package/dist/chunking/strategies/quantile-range-split.js +132 -0
- package/dist/chunking/strategies/quantile-range-split.js.map +1 -0
- package/dist/chunking/strategies/refinement.d.ts +4 -0
- package/dist/chunking/strategies/refinement.d.ts.map +1 -0
- package/dist/chunking/strategies/refinement.js +61 -0
- package/dist/chunking/strategies/refinement.js.map +1 -0
- package/dist/chunking/strategies/string-prefix-split.d.ts +4 -0
- package/dist/chunking/strategies/string-prefix-split.d.ts.map +1 -0
- package/dist/chunking/strategies/string-prefix-split.js +73 -0
- package/dist/chunking/strategies/string-prefix-split.js.map +1 -0
- package/dist/chunking/strategies/temporal-bucket-split.d.ts +4 -0
- package/dist/chunking/strategies/temporal-bucket-split.d.ts.map +1 -0
- package/dist/chunking/strategies/temporal-bucket-split.js +67 -0
- package/dist/chunking/strategies/temporal-bucket-split.js.map +1 -0
- package/dist/chunking/strategy-policy.d.ts +3 -0
- package/dist/chunking/strategy-policy.d.ts.map +1 -0
- package/dist/chunking/strategy-policy.js +4 -0
- package/dist/chunking/strategy-policy.js.map +1 -0
- package/dist/chunking/types.d.ts +128 -18
- package/dist/chunking/types.d.ts.map +1 -1
- package/dist/chunking/utils/binary-string.d.ts +8 -0
- package/dist/chunking/utils/binary-string.d.ts.map +1 -0
- package/dist/chunking/utils/binary-string.js +52 -0
- package/dist/chunking/utils/binary-string.js.map +1 -0
- package/dist/chunking/utils/ids.d.ts +4 -0
- package/dist/chunking/utils/ids.d.ts.map +1 -0
- package/dist/chunking/utils/ids.js +11 -0
- package/dist/chunking/utils/ids.js.map +1 -0
- package/dist/chunking/utils/ranges.d.ts +5 -0
- package/dist/chunking/utils/ranges.d.ts.map +1 -0
- package/dist/chunking/utils/ranges.js +19 -0
- package/dist/chunking/utils/ranges.js.map +1 -0
- package/dist/index.d.ts +0 -5
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +0 -2
- package/dist/index.js.map +1 -1
- package/dist/logging.d.ts +12 -0
- package/dist/logging.d.ts.map +1 -0
- package/dist/logging.js +61 -0
- package/dist/logging.js.map +1 -0
- package/dist/payload.d.ts.map +1 -1
- package/dist/payload.js +4 -6
- package/dist/payload.js.map +1 -1
- package/dist/planner.d.ts +2 -1
- package/dist/planner.d.ts.map +1 -1
- package/dist/planner.js +31 -52
- package/dist/planner.js.map +1 -1
- package/dist/plugin.d.ts.map +1 -1
- package/dist/plugin.js +27 -11
- package/dist/plugin.js.map +1 -1
- package/dist/queries.js +3 -3
- package/dist/queries.js.map +1 -1
- package/dist/sdk.d.ts +12 -0
- package/dist/sdk.d.ts.map +1 -0
- package/dist/sdk.js +9 -0
- package/dist/sdk.js.map +1 -0
- package/dist/state.d.ts.map +1 -1
- package/dist/state.js +16 -5
- package/dist/state.js.map +1 -1
- package/dist/types.d.ts +10 -22
- package/dist/types.d.ts.map +1 -1
- package/package.json +11 -3
package/dist/chunking/types.d.ts
CHANGED
|
@@ -1,29 +1,139 @@
|
|
|
1
|
-
export
|
|
1
|
+
export type RowProbeStrategy = 'explain-estimate' | 'count';
|
|
2
|
+
export type SortKeyCategory = 'numeric' | 'datetime' | 'string';
|
|
3
|
+
export type SortKeyBoundaryEncoding = 'literal' | 'hex-latin1';
|
|
4
|
+
export type EstimateConfidence = 'high' | 'low' | 'exact';
|
|
5
|
+
export type EstimateReason = 'partition-metadata' | 'quantile-estimate' | 'string-prefix-distribution' | 'group-by-key-distribution' | 'temporal-distribution' | 'equal-width-distribution' | 'exact-count';
|
|
6
|
+
export interface SortKey {
|
|
7
|
+
name: string;
|
|
8
|
+
type: string;
|
|
9
|
+
category: SortKeyCategory;
|
|
10
|
+
boundaryEncoding: SortKeyBoundaryEncoding;
|
|
11
|
+
}
|
|
12
|
+
export interface ChunkRange {
|
|
13
|
+
dimensionIndex: number;
|
|
14
|
+
from?: string;
|
|
15
|
+
to?: string;
|
|
16
|
+
}
|
|
17
|
+
export interface ChunkDerivationStep {
|
|
18
|
+
strategyId: string;
|
|
19
|
+
dimensionIndex?: number;
|
|
20
|
+
reason: string;
|
|
21
|
+
}
|
|
22
|
+
export interface ChunkEstimate {
|
|
23
|
+
rows: number;
|
|
24
|
+
bytesCompressed: number;
|
|
25
|
+
bytesUncompressed: number;
|
|
26
|
+
confidence: EstimateConfidence;
|
|
27
|
+
reason: EstimateReason;
|
|
28
|
+
}
|
|
29
|
+
export interface FocusedValue {
|
|
30
|
+
dimensionIndex: number;
|
|
31
|
+
value: string;
|
|
32
|
+
}
|
|
33
|
+
export interface ChunkAnalysis {
|
|
34
|
+
focusedValue?: FocusedValue;
|
|
35
|
+
lineage: ChunkDerivationStep[];
|
|
36
|
+
}
|
|
37
|
+
export interface Chunk {
|
|
38
|
+
id: string;
|
|
39
|
+
partitionId: string;
|
|
40
|
+
ranges: ChunkRange[];
|
|
41
|
+
estimate: ChunkEstimate;
|
|
42
|
+
analysis: ChunkAnalysis;
|
|
43
|
+
}
|
|
44
|
+
export interface PartitionDiagnostics {
|
|
45
|
+
estimatedRowSum: number;
|
|
46
|
+
exactPartitionRows: number;
|
|
47
|
+
estimateToExactRatio: number;
|
|
48
|
+
suspiciousEstimate: boolean;
|
|
49
|
+
lowConfidenceChunkCount: number;
|
|
50
|
+
usedDistributionFallback: boolean;
|
|
51
|
+
usedLowConfidenceChunkRefinement: boolean;
|
|
52
|
+
usedExactCountFallback: boolean;
|
|
53
|
+
}
|
|
54
|
+
export interface Partition {
|
|
2
55
|
partitionId: string;
|
|
3
56
|
rows: number;
|
|
4
|
-
|
|
57
|
+
bytesCompressed: number;
|
|
58
|
+
bytesUncompressed: number;
|
|
5
59
|
minTime: string;
|
|
6
60
|
maxTime: string;
|
|
61
|
+
diagnostics?: PartitionDiagnostics;
|
|
7
62
|
}
|
|
8
|
-
export interface
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
63
|
+
export interface TableProfile {
|
|
64
|
+
database: string;
|
|
65
|
+
table: string;
|
|
66
|
+
sortKeys: SortKey[];
|
|
67
|
+
}
|
|
68
|
+
export interface ChunkPlanStats {
|
|
69
|
+
totalPartitions: number;
|
|
70
|
+
oversizedPartitions: number;
|
|
71
|
+
focusedChunks: number;
|
|
72
|
+
totalChunks: number;
|
|
73
|
+
avgChunkBytes: number;
|
|
74
|
+
maxChunkBytes: number;
|
|
75
|
+
minChunkBytes: number;
|
|
12
76
|
}
|
|
13
|
-
export interface
|
|
77
|
+
export interface ChunkPlan {
|
|
78
|
+
planId: string;
|
|
79
|
+
generatedAt: string;
|
|
80
|
+
rowProbeStrategy: RowProbeStrategy;
|
|
81
|
+
targetChunkBytes: number;
|
|
82
|
+
table: TableProfile;
|
|
83
|
+
partitions: Partition[];
|
|
84
|
+
chunks: Chunk[];
|
|
85
|
+
totalRows: number;
|
|
86
|
+
totalBytesCompressed: number;
|
|
87
|
+
totalBytesUncompressed: number;
|
|
88
|
+
stats: ChunkPlanStats;
|
|
89
|
+
}
|
|
90
|
+
export type PlannerQuery = <T>(sql: string, settings?: Record<string, string | number | boolean | undefined>) => Promise<T[]>;
|
|
91
|
+
export interface PlannerContext {
|
|
92
|
+
database: string;
|
|
93
|
+
table: string;
|
|
94
|
+
from?: string;
|
|
95
|
+
to?: string;
|
|
96
|
+
targetChunkBytes: number;
|
|
97
|
+
query: PlannerQuery;
|
|
98
|
+
querySettings?: Record<string, string | number | boolean | undefined>;
|
|
99
|
+
rowProbeStrategy: RowProbeStrategy;
|
|
100
|
+
}
|
|
101
|
+
export interface EstimateFilter {
|
|
14
102
|
partitionId: string;
|
|
15
|
-
|
|
16
|
-
|
|
17
|
-
|
|
103
|
+
ranges: ChunkRange[];
|
|
104
|
+
exactDimensionIndex?: number;
|
|
105
|
+
exactValue?: string;
|
|
18
106
|
}
|
|
19
|
-
export interface
|
|
20
|
-
|
|
107
|
+
export interface StringPrefixBucket {
|
|
108
|
+
value: string;
|
|
109
|
+
rowCount: number;
|
|
110
|
+
isExactValue: boolean;
|
|
111
|
+
}
|
|
112
|
+
export interface TemporalBucket {
|
|
113
|
+
start: string;
|
|
114
|
+
rowCount: number;
|
|
115
|
+
}
|
|
116
|
+
export interface PartitionSlice {
|
|
21
117
|
partitionId: string;
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
118
|
+
ranges: ChunkRange[];
|
|
119
|
+
estimate: ChunkEstimate;
|
|
120
|
+
analysis: ChunkAnalysis;
|
|
121
|
+
}
|
|
122
|
+
export interface PartitionBuildResult {
|
|
123
|
+
slices: PartitionSlice[];
|
|
124
|
+
diagnostics: PartitionDiagnostics;
|
|
125
|
+
}
|
|
126
|
+
export interface PlanChunkOptions {
|
|
127
|
+
requireIdempotencyToken: boolean;
|
|
128
|
+
}
|
|
129
|
+
export interface GenerateChunkPlanInput {
|
|
130
|
+
database: string;
|
|
131
|
+
table: string;
|
|
132
|
+
from?: string;
|
|
133
|
+
to?: string;
|
|
134
|
+
targetChunkBytes: number;
|
|
135
|
+
query: PlannerQuery;
|
|
136
|
+
querySettings?: Record<string, string | number | boolean | undefined>;
|
|
137
|
+
rowProbeStrategy?: RowProbeStrategy;
|
|
28
138
|
}
|
|
29
139
|
//# sourceMappingURL=types.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../../src/chunking/types.ts"],"names":[],"mappings":"AAAA,MAAM,
|
|
1
|
+
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../../src/chunking/types.ts"],"names":[],"mappings":"AAAA,MAAM,MAAM,gBAAgB,GAAG,kBAAkB,GAAG,OAAO,CAAA;AAE3D,MAAM,MAAM,eAAe,GAAG,SAAS,GAAG,UAAU,GAAG,QAAQ,CAAA;AAE/D,MAAM,MAAM,uBAAuB,GAAG,SAAS,GAAG,YAAY,CAAA;AAE9D,MAAM,MAAM,kBAAkB,GAAG,MAAM,GAAG,KAAK,GAAG,OAAO,CAAA;AAEzD,MAAM,MAAM,cAAc,GACtB,oBAAoB,GACpB,mBAAmB,GACnB,4BAA4B,GAC5B,2BAA2B,GAC3B,uBAAuB,GACvB,0BAA0B,GAC1B,aAAa,CAAA;AAEjB,MAAM,WAAW,OAAO;IACtB,IAAI,EAAE,MAAM,CAAA;IACZ,IAAI,EAAE,MAAM,CAAA;IACZ,QAAQ,EAAE,eAAe,CAAA;IACzB,gBAAgB,EAAE,uBAAuB,CAAA;CAC1C;AAED,MAAM,WAAW,UAAU;IACzB,cAAc,EAAE,MAAM,CAAA;IACtB,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,EAAE,CAAC,EAAE,MAAM,CAAA;CACZ;AAED,MAAM,WAAW,mBAAmB;IAClC,UAAU,EAAE,MAAM,CAAA;IAClB,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB,MAAM,EAAE,MAAM,CAAA;CACf;AAED,MAAM,WAAW,aAAa;IAC5B,IAAI,EAAE,MAAM,CAAA;IACZ,eAAe,EAAE,MAAM,CAAA;IACvB,iBAAiB,EAAE,MAAM,CAAA;IACzB,UAAU,EAAE,kBAAkB,CAAA;IAC9B,MAAM,EAAE,cAAc,CAAA;CACvB;AAED,MAAM,WAAW,YAAY;IAC3B,cAAc,EAAE,MAAM,CAAA;IACtB,KAAK,EAAE,MAAM,CAAA;CACd;AAED,MAAM,WAAW,aAAa;IAC5B,YAAY,CAAC,EAAE,YAAY,CAAA;IAC3B,OAAO,EAAE,mBAAmB,EAAE,CAAA;CAC/B;AAED,MAAM,WAAW,KAAK;IACpB,EAAE,EAAE,MAAM,CAAA;IACV,WAAW,EAAE,MAAM,CAAA;IACnB,MAAM,EAAE,UAAU,EAAE,CAAA;IACpB,QAAQ,EAAE,aAAa,CAAA;IACvB,QAAQ,EAAE,aAAa,CAAA;CACxB;AAED,MAAM,WAAW,oBAAoB;IACnC,eAAe,EAAE,MAAM,CAAA;IACvB,kBAAkB,EAAE,MAAM,CAAA;IAC1B,oBAAoB,EAAE,MAAM,CAAA;IAC5B,kBAAkB,EAAE,OAAO,CAAA;IAC3B,uBAAuB,EAAE,MAAM,CAAA;IAC/B,wBAAwB,EAAE,OAAO,CAAA;IACjC,gCAAgC,EAAE,OAAO,CAAA;IACzC,sBAAsB,EAAE,OAAO,CAAA;CAChC;AAED,MAAM,WAAW,SAAS;IACxB,WAAW,EAAE,MAAM,CAAA;IACnB,IAAI,EAAE,MAAM,CAAA;IACZ,eAAe,EAAE,MAAM,CAAA;IACvB,iBAAiB,EAAE,MAAM,CAAA;IACzB,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;IACf,WAAW,CAAC,EAAE,oBAAoB,CAAA;CACnC;AAED,MAAM,WAAW,YAAY;IAC3B,QAAQ,EAAE,MAAM,CAAA;IAChB,KAAK,EAAE,MAAM,CAAA;IACb,QAAQ,EAAE,OAAO,EAAE,CAAA;CACpB;AAED,MAAM,WAAW,cAAc;IAC7B,eAAe,EAAE,MAAM,CAAA;IACvB,mBAAmB,EAAE,MAAM,CAAA;IAC3B,aAAa,EAAE,MAAM,CAAA;IACrB,WAAW,EAAE,MAAM,CAAA;IACnB,aAAa,EAAE,MAAM,CAAA;IACrB,aAAa,EAAE,MAAM,CAAA;IACrB,aAAa,EAAE,MAAM,CAAA;CACtB;AAED,MAAM,WAAW,SAAS;IACxB,MAAM,EAAE,MAAM,CAAA;IACd,WAAW,EAAE,MAAM,CAAA;IACnB,gBAAgB,EAAE,gBAAgB,CAAA;IAClC,gBAAgB,EAAE,MAAM,CAAA;IACxB,KAAK,EAAE,YAAY,CAAA;IACnB,UAAU,EAAE,SAAS,EAAE,CAAA;IACvB,MAAM,EAAE,KAAK,EAAE,CAAA;IACf,SAAS,EAAE,MAAM,CAAA;IACjB,oBAAoB,EAAE,MAAM,CAAA;IAC5B,sBAAsB,EAAE,MAAM,CAAA;IAC9B,KAAK,EAAE,cAAc,CAAA;CACtB;AAED,MAAM,MAAM,YAAY,GAAG,CAAC,CAAC,EAAE,GAAG,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,SAAS,CAAC,KAAK,OAAO,CAAC,CAAC,EAAE,CAAC,CAAA;AAE7H,MAAM,WAAW,cAAc;IAC7B,QAAQ,EAAE,MAAM,CAAA;IAChB,KAAK,EAAE,MAAM,CAAA;IACb,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,EAAE,CAAC,EAAE,MAAM,CAAA;IACX,gBAAgB,EAAE,MAAM,CAAA;IACxB,KAAK,EAAE,YAAY,CAAA;IACnB,aAAa,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,SAAS,CAAC,CAAA;IACrE,gBAAgB,EAAE,gBAAgB,CAAA;CACnC;AAED,MAAM,WAAW,cAAc;IAC7B,WAAW,EAAE,MAAM,CAAA;IACnB,MAAM,EAAE,UAAU,EAAE,CAAA;IACpB,mBAAmB,CAAC,EAAE,MAAM,CAAA;IAC5B,UAAU,CAAC,EAAE,MAAM,CAAA;CACpB;AAED,MAAM,WAAW,kBAAkB;IACjC,KAAK,EAAE,MAAM,CAAA;IACb,QAAQ,EAAE,MAAM,CAAA;IAChB,YAAY,EAAE,OAAO,CAAA;CACtB;AAED,MAAM,WAAW,cAAc;IAC7B,KAAK,EAAE,MAAM,CAAA;IACb,QAAQ,EAAE,MAAM,CAAA;CACjB;AAED,MAAM,WAAW,cAAc;IAC7B,WAAW,EAAE,MAAM,CAAA;IACnB,MAAM,EAAE,UAAU,EAAE,CAAA;IACpB,QAAQ,EAAE,aAAa,CAAA;IACvB,QAAQ,EAAE,aAAa,CAAA;CACxB;AAED,MAAM,WAAW,oBAAoB;IACnC,MAAM,EAAE,cAAc,EAAE,CAAA;IACxB,WAAW,EAAE,oBAAoB,CAAA;CAClC;AAED,MAAM,WAAW,gBAAgB;IAC/B,uBAAuB,EAAE,OAAO,CAAA;CACjC;AAED,MAAM,WAAW,sBAAsB;IACrC,QAAQ,EAAE,MAAM,CAAA;IAChB,KAAK,EAAE,MAAM,CAAA;IACb,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,EAAE,CAAC,EAAE,MAAM,CAAA;IACX,gBAAgB,EAAE,MAAM,CAAA;IACxB,KAAK,EAAE,YAAY,CAAA;IACnB,aAAa,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,SAAS,CAAC,CAAA;IACrE,gBAAgB,CAAC,EAAE,gBAAgB,CAAA;CACpC"}
|
|
@@ -0,0 +1,8 @@
|
|
|
1
|
+
export declare function compareBinaryStrings(left: string, right: string): number;
|
|
2
|
+
export declare function minBinaryString(left: string, right: string): string;
|
|
3
|
+
export declare function maxBinaryString(left: string, right: string): string;
|
|
4
|
+
export declare function nextPrefixValue(prefix: string): string | undefined;
|
|
5
|
+
export declare function buildObservedStringUpperBound(maxValue: string): string;
|
|
6
|
+
export declare function strToBigInt(value: string, padTo: number): bigint;
|
|
7
|
+
export declare function bigIntToStr(value: bigint, length: number, minLength?: number): string;
|
|
8
|
+
//# sourceMappingURL=binary-string.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"binary-string.d.ts","sourceRoot":"","sources":["../../../src/chunking/utils/binary-string.ts"],"names":[],"mappings":"AAAA,wBAAgB,oBAAoB,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,CAExE;AAED,wBAAgB,eAAe,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,CAEnE;AAED,wBAAgB,eAAe,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,CAEnE;AAED,wBAAgB,eAAe,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAclE;AAED,wBAAgB,6BAA6B,CAAC,QAAQ,EAAE,MAAM,GAAG,MAAM,CAEtE;AAED,wBAAgB,WAAW,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,CAUhE;AAED,wBAAgB,WAAW,CAAC,KAAK,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,SAAI,GAAG,MAAM,CAiBhF"}
|
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
export function compareBinaryStrings(left, right) {
|
|
2
|
+
return Buffer.from(left, 'latin1').compare(Buffer.from(right, 'latin1'));
|
|
3
|
+
}
|
|
4
|
+
export function minBinaryString(left, right) {
|
|
5
|
+
return compareBinaryStrings(left, right) <= 0 ? left : right;
|
|
6
|
+
}
|
|
7
|
+
export function maxBinaryString(left, right) {
|
|
8
|
+
return compareBinaryStrings(left, right) >= 0 ? left : right;
|
|
9
|
+
}
|
|
10
|
+
export function nextPrefixValue(prefix) {
|
|
11
|
+
if (prefix.length === 0)
|
|
12
|
+
return undefined;
|
|
13
|
+
const buffer = Buffer.from(prefix, 'latin1');
|
|
14
|
+
for (let index = buffer.length - 1; index >= 0; index--) {
|
|
15
|
+
const byte = buffer[index];
|
|
16
|
+
if (byte === undefined || byte === 0xff)
|
|
17
|
+
continue;
|
|
18
|
+
const next = Buffer.from(buffer.subarray(0, index + 1));
|
|
19
|
+
next[index] = byte + 1;
|
|
20
|
+
return next.toString('latin1');
|
|
21
|
+
}
|
|
22
|
+
return undefined;
|
|
23
|
+
}
|
|
24
|
+
export function buildObservedStringUpperBound(maxValue) {
|
|
25
|
+
return `${maxValue}\0`;
|
|
26
|
+
}
|
|
27
|
+
export function strToBigInt(value, padTo) {
|
|
28
|
+
const buffer = Buffer.from(value, 'latin1');
|
|
29
|
+
let result = 0n;
|
|
30
|
+
for (let index = 0; index < padTo; index++) {
|
|
31
|
+
const byte = index < buffer.length ? (buffer[index] ?? 0) : 0;
|
|
32
|
+
result = (result << 8n) | BigInt(byte);
|
|
33
|
+
}
|
|
34
|
+
return result;
|
|
35
|
+
}
|
|
36
|
+
export function bigIntToStr(value, length, minLength = 0) {
|
|
37
|
+
const buffer = Buffer.alloc(length);
|
|
38
|
+
let remaining = value;
|
|
39
|
+
for (let index = length - 1; index >= 0; index--) {
|
|
40
|
+
buffer[index] = Number(remaining & 0xffn);
|
|
41
|
+
remaining >>= 8n;
|
|
42
|
+
}
|
|
43
|
+
// Strip trailing null bytes so boundaries match real string values
|
|
44
|
+
// in ClickHouse comparisons (where "abc" < "abc\0"), but preserve
|
|
45
|
+
// at least minLength bytes to avoid losing meaningful trailing nulls
|
|
46
|
+
// (e.g. from buildObservedStringUpperBound which appends "\0").
|
|
47
|
+
let end = length;
|
|
48
|
+
while (end > minLength && buffer[end - 1] === 0)
|
|
49
|
+
end--;
|
|
50
|
+
return buffer.subarray(0, end).toString('latin1');
|
|
51
|
+
}
|
|
52
|
+
//# sourceMappingURL=binary-string.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"binary-string.js","sourceRoot":"","sources":["../../../src/chunking/utils/binary-string.ts"],"names":[],"mappings":"AAAA,MAAM,UAAU,oBAAoB,CAAC,IAAY,EAAE,KAAa;IAC9D,OAAO,MAAM,CAAC,IAAI,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC,CAAA;AAC1E,CAAC;AAED,MAAM,UAAU,eAAe,CAAC,IAAY,EAAE,KAAa;IACzD,OAAO,oBAAoB,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,KAAK,CAAA;AAC9D,CAAC;AAED,MAAM,UAAU,eAAe,CAAC,IAAY,EAAE,KAAa;IACzD,OAAO,oBAAoB,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,KAAK,CAAA;AAC9D,CAAC;AAED,MAAM,UAAU,eAAe,CAAC,MAAc;IAC5C,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,SAAS,CAAA;IAEzC,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,EAAE,QAAQ,CAAC,CAAA;IAC5C,KAAK,IAAI,KAAK,GAAG,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,KAAK,IAAI,CAAC,EAAE,KAAK,EAAE,EAAE,CAAC;QACxD,MAAM,IAAI,GAAG,MAAM,CAAC,KAAK,CAAC,CAAA;QAC1B,IAAI,IAAI,KAAK,SAAS,IAAI,IAAI,KAAK,IAAI;YAAE,SAAQ;QAEjD,MAAM,IAAI,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,KAAK,GAAG,CAAC,CAAC,CAAC,CAAA;QACvD,IAAI,CAAC,KAAK,CAAC,GAAG,IAAI,GAAG,CAAC,CAAA;QACtB,OAAO,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAA;IAChC,CAAC;IAED,OAAO,SAAS,CAAA;AAClB,CAAC;AAED,MAAM,UAAU,6BAA6B,CAAC,QAAgB;IAC5D,OAAO,GAAG,QAAQ,IAAI,CAAA;AACxB,CAAC;AAED,MAAM,UAAU,WAAW,CAAC,KAAa,EAAE,KAAa;IACtD,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAA;IAC3C,IAAI,MAAM,GAAG,EAAE,CAAA;IAEf,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,EAAE,KAAK,EAAE,EAAE,CAAC;QAC3C,MAAM,IAAI,GAAG,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;QAC7D,MAAM,GAAG,CAAC,MAAM,IAAI,EAAE,CAAC,GAAG,MAAM,CAAC,IAAI,CAAC,CAAA;IACxC,CAAC;IAED,OAAO,MAAM,CAAA;AACf,CAAC;AAED,MAAM,UAAU,WAAW,CAAC,KAAa,EAAE,MAAc,EAAE,SAAS,GAAG,CAAC;IACtE,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAA;IACnC,IAAI,SAAS,GAAG,KAAK,CAAA;IAErB,KAAK,IAAI,KAAK,GAAG,MAAM,GAAG,CAAC,EAAE,KAAK,IAAI,CAAC,EAAE,KAAK,EAAE,EAAE,CAAC;QACjD,MAAM,CAAC,KAAK,CAAC,GAAG,MAAM,CAAC,SAAS,GAAG,KAAK,CAAC,CAAA;QACzC,SAAS,KAAK,EAAE,CAAA;IAClB,CAAC;IAED,mEAAmE;IACnE,kEAAkE;IAClE,qEAAqE;IACrE,gEAAgE;IAChE,IAAI,GAAG,GAAG,MAAM,CAAA;IAChB,OAAO,GAAG,GAAG,SAAS,IAAI,MAAM,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,CAAC;QAAE,GAAG,EAAE,CAAA;IAEtD,OAAO,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAA;AACnD,CAAC"}
|
|
@@ -0,0 +1,4 @@
|
|
|
1
|
+
export declare function generatePlanId(): string;
|
|
2
|
+
export declare function generateChunkId(planId: string, partitionId: string, index: number): string;
|
|
3
|
+
export declare function generateIdempotencyToken(planId: string, chunkId: string): string;
|
|
4
|
+
//# sourceMappingURL=ids.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"ids.d.ts","sourceRoot":"","sources":["../../../src/chunking/utils/ids.ts"],"names":[],"mappings":"AAEA,wBAAgB,cAAc,IAAI,MAAM,CAEvC;AAED,wBAAgB,eAAe,CAC7B,MAAM,EAAE,MAAM,EACd,WAAW,EAAE,MAAM,EACnB,KAAK,EAAE,MAAM,GACZ,MAAM,CAER;AAED,wBAAgB,wBAAwB,CAAC,MAAM,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM,CAEhF"}
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
import { hashId, randomPlanId } from '../../state.js';
|
|
2
|
+
export function generatePlanId() {
|
|
3
|
+
return randomPlanId();
|
|
4
|
+
}
|
|
5
|
+
export function generateChunkId(planId, partitionId, index) {
|
|
6
|
+
return hashId(`chunk:${planId}:${partitionId}:${index}`).slice(0, 16);
|
|
7
|
+
}
|
|
8
|
+
export function generateIdempotencyToken(planId, chunkId) {
|
|
9
|
+
return hashId(`token:${planId}:${chunkId}`);
|
|
10
|
+
}
|
|
11
|
+
//# sourceMappingURL=ids.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"ids.js","sourceRoot":"","sources":["../../../src/chunking/utils/ids.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,YAAY,EAAE,MAAM,gBAAgB,CAAA;AAErD,MAAM,UAAU,cAAc;IAC5B,OAAO,YAAY,EAAE,CAAA;AACvB,CAAC;AAED,MAAM,UAAU,eAAe,CAC7B,MAAc,EACd,WAAmB,EACnB,KAAa;IAEb,OAAO,MAAM,CAAC,SAAS,MAAM,IAAI,WAAW,IAAI,KAAK,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;AACvE,CAAC;AAED,MAAM,UAAU,wBAAwB,CAAC,MAAc,EAAE,OAAe;IACtE,OAAO,MAAM,CAAC,SAAS,MAAM,IAAI,OAAO,EAAE,CAAC,CAAA;AAC7C,CAAC"}
|
|
@@ -0,0 +1,5 @@
|
|
|
1
|
+
import type { ChunkRange, PartitionSlice } from '../types.js';
|
|
2
|
+
export declare function getChunkRange(slice: Pick<PartitionSlice, 'ranges'>, dimensionIndex: number): ChunkRange;
|
|
3
|
+
export declare function replaceChunkRange(slice: Pick<PartitionSlice, 'ranges'>, dimensionIndex: number, from: string | undefined, to: string | undefined): ChunkRange[];
|
|
4
|
+
export declare function isExactChunkRange(range: Pick<ChunkRange, 'from' | 'to'>): boolean;
|
|
5
|
+
//# sourceMappingURL=ranges.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"ranges.d.ts","sourceRoot":"","sources":["../../../src/chunking/utils/ranges.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE7D,wBAAgB,aAAa,CAC3B,KAAK,EAAE,IAAI,CAAC,cAAc,EAAE,QAAQ,CAAC,EACrC,cAAc,EAAE,MAAM,GACrB,UAAU,CAQZ;AAED,wBAAgB,iBAAiB,CAC/B,KAAK,EAAE,IAAI,CAAC,cAAc,EAAE,QAAQ,CAAC,EACrC,cAAc,EAAE,MAAM,EACtB,IAAI,EAAE,MAAM,GAAG,SAAS,EACxB,EAAE,EAAE,MAAM,GAAG,SAAS,GACrB,UAAU,EAAE,CAKd;AAED,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,IAAI,CAAC,UAAU,EAAE,MAAM,GAAG,IAAI,CAAC,GAAG,OAAO,CAGjF"}
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
export function getChunkRange(slice, dimensionIndex) {
|
|
2
|
+
return (slice.ranges.find((range) => range.dimensionIndex === dimensionIndex) ?? {
|
|
3
|
+
dimensionIndex,
|
|
4
|
+
from: undefined,
|
|
5
|
+
to: undefined,
|
|
6
|
+
});
|
|
7
|
+
}
|
|
8
|
+
export function replaceChunkRange(slice, dimensionIndex, from, to) {
|
|
9
|
+
return slice.ranges
|
|
10
|
+
.filter((range) => range.dimensionIndex !== dimensionIndex)
|
|
11
|
+
.concat([{ dimensionIndex, from, to }])
|
|
12
|
+
.sort((left, right) => left.dimensionIndex - right.dimensionIndex);
|
|
13
|
+
}
|
|
14
|
+
export function isExactChunkRange(range) {
|
|
15
|
+
if (range.from === undefined || range.to === undefined)
|
|
16
|
+
return false;
|
|
17
|
+
return range.to === `${range.from}\0`;
|
|
18
|
+
}
|
|
19
|
+
//# sourceMappingURL=ranges.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"ranges.js","sourceRoot":"","sources":["../../../src/chunking/utils/ranges.ts"],"names":[],"mappings":"AAEA,MAAM,UAAU,aAAa,CAC3B,KAAqC,EACrC,cAAsB;IAEtB,OAAO,CACL,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,cAAc,KAAK,cAAc,CAAC,IAAI;QACvE,cAAc;QACd,IAAI,EAAE,SAAS;QACf,EAAE,EAAE,SAAS;KACd,CACF,CAAA;AACH,CAAC;AAED,MAAM,UAAU,iBAAiB,CAC/B,KAAqC,EACrC,cAAsB,EACtB,IAAwB,EACxB,EAAsB;IAEtB,OAAO,KAAK,CAAC,MAAM;SAChB,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,cAAc,KAAK,cAAc,CAAC;SAC1D,MAAM,CAAC,CAAC,EAAE,cAAc,EAAE,IAAI,EAAE,EAAE,EAAE,CAAC,CAAC;SACtC,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,cAAc,GAAG,KAAK,CAAC,cAAc,CAAC,CAAA;AACtE,CAAC;AAED,MAAM,UAAU,iBAAiB,CAAC,KAAsC;IACtE,IAAI,KAAK,CAAC,IAAI,KAAK,SAAS,IAAI,KAAK,CAAC,EAAE,KAAK,SAAS;QAAE,OAAO,KAAK,CAAA;IACpE,OAAO,KAAK,CAAC,EAAE,KAAK,GAAG,KAAK,CAAC,IAAI,IAAI,CAAA;AACvC,CAAC"}
|
package/dist/index.d.ts
CHANGED
|
@@ -1,11 +1,6 @@
|
|
|
1
1
|
import './table-config.js';
|
|
2
2
|
export { backfill, createBackfillPlugin } from './plugin.js';
|
|
3
|
-
export { executeBackfill, syncProgress } from './async-backfill.js';
|
|
4
|
-
export { analyzeAndChunk } from './chunking/analyze.js';
|
|
5
|
-
export type { BackfillOptions, BackfillChunkState, BackfillProgress, BackfillResult, } from './async-backfill.js';
|
|
6
3
|
export type { BackfillPlugin, BackfillPluginOptions, BackfillPluginRegistration } from './types.js';
|
|
7
4
|
export type { PluginConfig } from './options.js';
|
|
8
5
|
export type { BackfillTableConfig } from './table-config.js';
|
|
9
|
-
export type { AnalyzeAndChunkInput, AnalyzeAndChunkResult } from './chunking/analyze.js';
|
|
10
|
-
export type { PlannedChunk, PartitionInfo, SortKeyInfo } from './chunking/types.js';
|
|
11
6
|
//# sourceMappingURL=index.d.ts.map
|
package/dist/index.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,mBAAmB,CAAA;AAE1B,OAAO,EAAE,QAAQ,EAAE,oBAAoB,EAAE,MAAM,aAAa,CAAA;AAC5D,
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,mBAAmB,CAAA;AAE1B,OAAO,EAAE,QAAQ,EAAE,oBAAoB,EAAE,MAAM,aAAa,CAAA;AAC5D,YAAY,EAAE,cAAc,EAAE,qBAAqB,EAAE,0BAA0B,EAAE,MAAM,YAAY,CAAA;AACnG,YAAY,EAAE,YAAY,EAAE,MAAM,cAAc,CAAA;AAChD,YAAY,EAAE,mBAAmB,EAAE,MAAM,mBAAmB,CAAA"}
|
package/dist/index.js
CHANGED
package/dist/index.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,mBAAmB,CAAA;AAE1B,OAAO,EAAE,QAAQ,EAAE,oBAAoB,EAAE,MAAM,aAAa,CAAA
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,mBAAmB,CAAA;AAE1B,OAAO,EAAE,QAAQ,EAAE,oBAAoB,EAAE,MAAM,aAAa,CAAA"}
|
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
import { type Logger } from '@logtape/logtape';
|
|
2
|
+
export declare const CHKIT_LOGGER_CATEGORY: readonly ["chkit"];
|
|
3
|
+
export declare const CHKIT_BACKFILL_LOGGER_CATEGORY: readonly ["chkit", "backfill"];
|
|
4
|
+
export declare const SLOW_CLICKHOUSE_QUERY_MS = 5000;
|
|
5
|
+
export declare const SLOW_CLICKHOUSE_QUERY_REPEAT_INITIAL_MS = 5000;
|
|
6
|
+
export declare const SLOW_CLICKHOUSE_QUERY_REPEAT_MAX_MS = 30000;
|
|
7
|
+
export declare function getBackfillLogger(...segments: string[]): Logger;
|
|
8
|
+
export declare function formatBytes(bytes: number): string;
|
|
9
|
+
export declare function summarizeSql(sql: string, maxLength?: number): string;
|
|
10
|
+
export declare function describeSqlOperation(sql: string): string;
|
|
11
|
+
export declare function describeSqlContext(sql: string): string | undefined;
|
|
12
|
+
//# sourceMappingURL=logging.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"logging.d.ts","sourceRoot":"","sources":["../src/logging.ts"],"names":[],"mappings":"AAAA,OAAO,EAAa,KAAK,MAAM,EAAE,MAAM,kBAAkB,CAAA;AAEzD,eAAO,MAAM,qBAAqB,oBAAqB,CAAA;AACvD,eAAO,MAAM,8BAA8B,gCAAkD,CAAA;AAC7F,eAAO,MAAM,wBAAwB,OAAO,CAAA;AAC5C,eAAO,MAAM,uCAAuC,OAAO,CAAA;AAC3D,eAAO,MAAM,mCAAmC,QAAQ,CAAA;AAExD,wBAAgB,iBAAiB,CAAC,GAAG,QAAQ,EAAE,MAAM,EAAE,GAAG,MAAM,CAE/D;AAED,wBAAgB,WAAW,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAMjD;AAED,wBAAgB,YAAY,CAAC,GAAG,EAAE,MAAM,EAAE,SAAS,SAAM,GAAG,MAAM,CAIjE;AAED,wBAAgB,oBAAoB,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,CAqBxD;AAED,wBAAgB,kBAAkB,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAMlE"}
|
package/dist/logging.js
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
import { getLogger } from '@logtape/logtape';
|
|
2
|
+
export const CHKIT_LOGGER_CATEGORY = ['chkit'];
|
|
3
|
+
export const CHKIT_BACKFILL_LOGGER_CATEGORY = [...CHKIT_LOGGER_CATEGORY, 'backfill'];
|
|
4
|
+
export const SLOW_CLICKHOUSE_QUERY_MS = 5000;
|
|
5
|
+
export const SLOW_CLICKHOUSE_QUERY_REPEAT_INITIAL_MS = 5000;
|
|
6
|
+
export const SLOW_CLICKHOUSE_QUERY_REPEAT_MAX_MS = 30000;
|
|
7
|
+
export function getBackfillLogger(...segments) {
|
|
8
|
+
return getLogger([...CHKIT_BACKFILL_LOGGER_CATEGORY, ...segments]);
|
|
9
|
+
}
|
|
10
|
+
export function formatBytes(bytes) {
|
|
11
|
+
if (bytes >= 1024 ** 4)
|
|
12
|
+
return `${(bytes / 1024 ** 4).toFixed(1)} TiB`;
|
|
13
|
+
if (bytes >= 1024 ** 3)
|
|
14
|
+
return `${(bytes / 1024 ** 3).toFixed(1)} GiB`;
|
|
15
|
+
if (bytes >= 1024 ** 2)
|
|
16
|
+
return `${(bytes / 1024 ** 2).toFixed(1)} MiB`;
|
|
17
|
+
if (bytes >= 1024)
|
|
18
|
+
return `${(bytes / 1024).toFixed(1)} KiB`;
|
|
19
|
+
return `${bytes} B`;
|
|
20
|
+
}
|
|
21
|
+
export function summarizeSql(sql, maxLength = 240) {
|
|
22
|
+
const normalized = normalizeSql(sql);
|
|
23
|
+
if (normalized.length <= maxLength)
|
|
24
|
+
return normalized;
|
|
25
|
+
return `${normalized.slice(0, maxLength - 3)}...`;
|
|
26
|
+
}
|
|
27
|
+
export function describeSqlOperation(sql) {
|
|
28
|
+
const normalized = normalizeSql(sql);
|
|
29
|
+
const prefixDistribution = normalized.match(/^SELECT substring\((\w+), 1, \d+\) AS prefix, count\(\) AS cnt /);
|
|
30
|
+
if (prefixDistribution?.[1])
|
|
31
|
+
return `prefix distribution on ${prefixDistribution[1]}`;
|
|
32
|
+
const temporalDistribution = normalized.match(/^SELECT formatDateTime\(toStartOf(Day|Hour)\((\w+)\)/);
|
|
33
|
+
if (temporalDistribution?.[1] && temporalDistribution[2]) {
|
|
34
|
+
return `${temporalDistribution[1].toLowerCase()} distribution on ${temporalDistribution[2]}`;
|
|
35
|
+
}
|
|
36
|
+
const minMaxProbe = normalized.match(/^SELECT toString\(min\((\w+)\)\) AS minVal, toString\(max\(\1\)\) AS maxVal /);
|
|
37
|
+
if (minMaxProbe?.[1])
|
|
38
|
+
return `range probe on ${minMaxProbe[1]}`;
|
|
39
|
+
if (normalized.startsWith('SELECT count() AS cnt FROM '))
|
|
40
|
+
return 'row count probe';
|
|
41
|
+
if (normalized.startsWith('SELECT sorting_key FROM system.tables'))
|
|
42
|
+
return 'sort key introspection';
|
|
43
|
+
if (normalized.startsWith('SELECT name, type FROM system.columns'))
|
|
44
|
+
return 'column introspection';
|
|
45
|
+
if (normalized.startsWith('SELECT partition_id,'))
|
|
46
|
+
return 'partition introspection';
|
|
47
|
+
if (normalized.startsWith('SELECT 1 FROM '))
|
|
48
|
+
return 'table existence probe';
|
|
49
|
+
return summarizeSql(normalized, 100);
|
|
50
|
+
}
|
|
51
|
+
export function describeSqlContext(sql) {
|
|
52
|
+
const normalized = normalizeSql(sql);
|
|
53
|
+
const partitionId = normalized.match(/_partition_id = '([^']+)'/)?.[1];
|
|
54
|
+
if (partitionId)
|
|
55
|
+
return `partition ${partitionId}`;
|
|
56
|
+
return undefined;
|
|
57
|
+
}
|
|
58
|
+
function normalizeSql(sql) {
|
|
59
|
+
return sql.replace(/\s+/g, ' ').trim();
|
|
60
|
+
}
|
|
61
|
+
//# sourceMappingURL=logging.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"logging.js","sourceRoot":"","sources":["../src/logging.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAe,MAAM,kBAAkB,CAAA;AAEzD,MAAM,CAAC,MAAM,qBAAqB,GAAG,CAAC,OAAO,CAAU,CAAA;AACvD,MAAM,CAAC,MAAM,8BAA8B,GAAG,CAAC,GAAG,qBAAqB,EAAE,UAAU,CAAU,CAAA;AAC7F,MAAM,CAAC,MAAM,wBAAwB,GAAG,IAAI,CAAA;AAC5C,MAAM,CAAC,MAAM,uCAAuC,GAAG,IAAI,CAAA;AAC3D,MAAM,CAAC,MAAM,mCAAmC,GAAG,KAAK,CAAA;AAExD,MAAM,UAAU,iBAAiB,CAAC,GAAG,QAAkB;IACrD,OAAO,SAAS,CAAC,CAAC,GAAG,8BAA8B,EAAE,GAAG,QAAQ,CAAC,CAAC,CAAA;AACpE,CAAC;AAED,MAAM,UAAU,WAAW,CAAC,KAAa;IACvC,IAAI,KAAK,IAAI,IAAI,IAAI,CAAC;QAAE,OAAO,GAAG,CAAC,KAAK,GAAG,IAAI,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAA;IACtE,IAAI,KAAK,IAAI,IAAI,IAAI,CAAC;QAAE,OAAO,GAAG,CAAC,KAAK,GAAG,IAAI,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAA;IACtE,IAAI,KAAK,IAAI,IAAI,IAAI,CAAC;QAAE,OAAO,GAAG,CAAC,KAAK,GAAG,IAAI,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAA;IACtE,IAAI,KAAK,IAAI,IAAI;QAAE,OAAO,GAAG,CAAC,KAAK,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAA;IAC5D,OAAO,GAAG,KAAK,IAAI,CAAA;AACrB,CAAC;AAED,MAAM,UAAU,YAAY,CAAC,GAAW,EAAE,SAAS,GAAG,GAAG;IACvD,MAAM,UAAU,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;IACpC,IAAI,UAAU,CAAC,MAAM,IAAI,SAAS;QAAE,OAAO,UAAU,CAAA;IACrD,OAAO,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,EAAE,SAAS,GAAG,CAAC,CAAC,KAAK,CAAA;AACnD,CAAC;AAED,MAAM,UAAU,oBAAoB,CAAC,GAAW;IAC9C,MAAM,UAAU,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;IAEpC,MAAM,kBAAkB,GAAG,UAAU,CAAC,KAAK,CAAC,iEAAiE,CAAC,CAAA;IAC9G,IAAI,kBAAkB,EAAE,CAAC,CAAC,CAAC;QAAE,OAAO,0BAA0B,kBAAkB,CAAC,CAAC,CAAC,EAAE,CAAA;IAErF,MAAM,oBAAoB,GAAG,UAAU,CAAC,KAAK,CAAC,sDAAsD,CAAC,CAAA;IACrG,IAAI,oBAAoB,EAAE,CAAC,CAAC,CAAC,IAAI,oBAAoB,CAAC,CAAC,CAAC,EAAE,CAAC;QACzD,OAAO,GAAG,oBAAoB,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,oBAAoB,oBAAoB,CAAC,CAAC,CAAC,EAAE,CAAA;IAC9F,CAAC;IAED,MAAM,WAAW,GAAG,UAAU,CAAC,KAAK,CAAC,8EAA8E,CAAC,CAAA;IACpH,IAAI,WAAW,EAAE,CAAC,CAAC,CAAC;QAAE,OAAO,kBAAkB,WAAW,CAAC,CAAC,CAAC,EAAE,CAAA;IAE/D,IAAI,UAAU,CAAC,UAAU,CAAC,6BAA6B,CAAC;QAAE,OAAO,iBAAiB,CAAA;IAClF,IAAI,UAAU,CAAC,UAAU,CAAC,uCAAuC,CAAC;QAAE,OAAO,wBAAwB,CAAA;IACnG,IAAI,UAAU,CAAC,UAAU,CAAC,uCAAuC,CAAC;QAAE,OAAO,sBAAsB,CAAA;IACjG,IAAI,UAAU,CAAC,UAAU,CAAC,sBAAsB,CAAC;QAAE,OAAO,yBAAyB,CAAA;IACnF,IAAI,UAAU,CAAC,UAAU,CAAC,gBAAgB,CAAC;QAAE,OAAO,uBAAuB,CAAA;IAE3E,OAAO,YAAY,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;AACtC,CAAC;AAED,MAAM,UAAU,kBAAkB,CAAC,GAAW;IAC5C,MAAM,UAAU,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;IACpC,MAAM,WAAW,GAAG,UAAU,CAAC,KAAK,CAAC,2BAA2B,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAEtE,IAAI,WAAW;QAAE,OAAO,aAAa,WAAW,EAAE,CAAA;IAClD,OAAO,SAAS,CAAA;AAClB,CAAC;AAED,SAAS,YAAY,CAAC,GAAW;IAC/B,OAAO,GAAG,CAAC,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;AACxC,CAAC"}
|
package/dist/payload.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"payload.d.ts","sourceRoot":"","sources":["../src/payload.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,oBAAoB,EACpB,kBAAkB,EAClB,qBAAqB,EACrB,uBAAuB,EACxB,MAAM,YAAY,CAAA;AAEnB,wBAAgB,WAAW,CAAC,MAAM,EAAE,uBAAuB,GAAG;IAC5D,EAAE,EAAE,IAAI,CAAA;IACR,OAAO,EAAE,MAAM,CAAA;IACf,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,CAAA;IACZ,EAAE,EAAE,MAAM,CAAA;IACV,UAAU,EAAE,MAAM,CAAA;IAClB,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB,UAAU,CAAC,EAAE,MAAM,CAAA;CACpB,
|
|
1
|
+
{"version":3,"file":"payload.d.ts","sourceRoot":"","sources":["../src/payload.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,oBAAoB,EACpB,kBAAkB,EAClB,qBAAqB,EACrB,uBAAuB,EACxB,MAAM,YAAY,CAAA;AAEnB,wBAAgB,WAAW,CAAC,MAAM,EAAE,uBAAuB,GAAG;IAC5D,EAAE,EAAE,IAAI,CAAA;IACR,OAAO,EAAE,MAAM,CAAA;IACf,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,CAAA;IACZ,EAAE,EAAE,MAAM,CAAA;IACV,UAAU,EAAE,MAAM,CAAA;IAClB,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB,UAAU,CAAC,EAAE,MAAM,CAAA;CACpB,CAgBA;AAED,wBAAgB,aAAa,CAAC,OAAO,EAAE,qBAAqB,GAAG;IAC7D,EAAE,EAAE,OAAO,CAAA;IACX,OAAO,EAAE,QAAQ,CAAA;IACjB,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,kBAAkB,CAAA;IAC1B,WAAW,EAAE,qBAAqB,CAAC,QAAQ,CAAC,CAAA;IAC5C,WAAW,EAAE,MAAM,CAAA;IACnB,OAAO,EAAE,MAAM,CAAA;IACf,SAAS,EAAE,MAAM,CAAA;IACjB,SAAS,CAAC,EAAE,MAAM,CAAA;CACnB,CAYA;AAED,wBAAgB,aAAa,CAAC,OAAO,EAAE,qBAAqB,GAAG;IAC7D,EAAE,EAAE,OAAO,CAAA;IACX,OAAO,EAAE,QAAQ,CAAA;IACjB,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,kBAAkB,CAAA;IAC1B,WAAW,EAAE,qBAAqB,CAAC,QAAQ,CAAC,CAAA;IAC5C,OAAO,EAAE,MAAM,CAAA;CAChB,CASA;AAED,wBAAgB,aAAa,CAAC,MAAM,EAAE,oBAAoB,GAAG;IAC3D,EAAE,EAAE,OAAO,CAAA;IACX,OAAO,EAAE,QAAQ,CAAA;IACjB,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,kBAAkB,CAAA;IAC1B,UAAU,EAAE,MAAM,EAAE,CAAA;IACpB,eAAe,EAAE,MAAM,EAAE,CAAA;IACzB,cAAc,EAAE,MAAM,EAAE,CAAA;CACzB,CAUA"}
|
package/dist/payload.js
CHANGED
|
@@ -6,15 +6,13 @@ export function planPayload(output) {
|
|
|
6
6
|
target: output.plan.target,
|
|
7
7
|
from: output.plan.from,
|
|
8
8
|
to: output.plan.to,
|
|
9
|
-
chunkCount: output.plan.chunks.length,
|
|
9
|
+
chunkCount: output.plan.chunkPlan.chunks.length,
|
|
10
10
|
maxChunkBytes: output.plan.options.maxChunkBytes,
|
|
11
11
|
sortKeyColumn: output.plan.options.sortKeyColumn,
|
|
12
12
|
planPath: output.planPath,
|
|
13
|
-
strategy: output.plan.
|
|
14
|
-
partitionCount: output.plan.partitions
|
|
15
|
-
totalBytes: output.plan.
|
|
16
|
-
? output.plan.partitions.reduce((sum, p) => sum + p.bytesOnDisk, 0)
|
|
17
|
-
: undefined,
|
|
13
|
+
strategy: output.plan.execution.mode,
|
|
14
|
+
partitionCount: output.plan.chunkPlan.partitions.length,
|
|
15
|
+
totalBytes: output.plan.chunkPlan.totalBytesCompressed,
|
|
18
16
|
};
|
|
19
17
|
}
|
|
20
18
|
export function statusPayload(summary) {
|
package/dist/payload.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"payload.js","sourceRoot":"","sources":["../src/payload.ts"],"names":[],"mappings":"AAOA,MAAM,UAAU,WAAW,CAAC,MAA+B;IAezD,OAAO;QACL,EAAE,EAAE,IAAI;QACR,OAAO,EAAE,MAAM;QACf,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,MAAM;QAC1B,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,MAAM;QAC1B,IAAI,EAAE,MAAM,CAAC,IAAI,CAAC,IAAI;QACtB,EAAE,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;QAClB,UAAU,EAAE,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM;
|
|
1
|
+
{"version":3,"file":"payload.js","sourceRoot":"","sources":["../src/payload.ts"],"names":[],"mappings":"AAOA,MAAM,UAAU,WAAW,CAAC,MAA+B;IAezD,OAAO;QACL,EAAE,EAAE,IAAI;QACR,OAAO,EAAE,MAAM;QACf,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,MAAM;QAC1B,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,MAAM;QAC1B,IAAI,EAAE,MAAM,CAAC,IAAI,CAAC,IAAI;QACtB,EAAE,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;QAClB,UAAU,EAAE,MAAM,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,MAAM;QAC/C,aAAa,EAAE,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,aAAa;QAChD,aAAa,EAAE,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,aAAa;QAChD,QAAQ,EAAE,MAAM,CAAC,QAAQ;QACzB,QAAQ,EAAE,MAAM,CAAC,IAAI,CAAC,SAAS,CAAC,IAAI;QACpC,cAAc,EAAE,MAAM,CAAC,IAAI,CAAC,SAAS,CAAC,UAAU,CAAC,MAAM;QACvD,UAAU,EAAE,MAAM,CAAC,IAAI,CAAC,SAAS,CAAC,oBAAoB;KACvD,CAAA;AACH,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,OAA8B;IAW1D,OAAO;QACL,EAAE,EAAE,OAAO,CAAC,MAAM,KAAK,QAAQ;QAC/B,OAAO,EAAE,QAAQ;QACjB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,WAAW,EAAE,OAAO,CAAC,MAAM;QAC3B,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,OAAO,EAAE,OAAO,CAAC,OAAO;QACxB,SAAS,EAAE,OAAO,CAAC,SAAS;QAC5B,SAAS,EAAE,OAAO,CAAC,SAAS;KAC7B,CAAA;AACH,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,OAA8B;IAQ1D,OAAO;QACL,EAAE,EAAE,OAAO,CAAC,MAAM,KAAK,WAAW;QAClC,OAAO,EAAE,QAAQ;QACjB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,WAAW,EAAE,OAAO,CAAC,MAAM;QAC3B,OAAO,EAAE,OAAO,CAAC,OAAO;KACzB,CAAA;AACH,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,MAA4B;IASxD,OAAO;QACL,EAAE,EAAE,MAAM,CAAC,UAAU,CAAC,MAAM,KAAK,CAAC;QAClC,OAAO,EAAE,QAAQ;QACjB,MAAM,EAAE,MAAM,CAAC,MAAM;QACrB,MAAM,EAAE,MAAM,CAAC,MAAM;QACrB,UAAU,EAAE,MAAM,CAAC,UAAU;QAC7B,eAAe,EAAE,MAAM,CAAC,eAAe;QACvC,cAAc,EAAE,MAAM,CAAC,cAAc;KACtC,CAAA;AACH,CAAC"}
|
package/dist/planner.d.ts
CHANGED
|
@@ -9,6 +9,7 @@ export declare function buildBackfillPlan(input: {
|
|
|
9
9
|
url: string;
|
|
10
10
|
database: string;
|
|
11
11
|
};
|
|
12
|
-
clickhouseQuery: <T>(sql: string) => Promise<T[]>;
|
|
12
|
+
clickhouseQuery: <T>(sql: string, settings?: Record<string, string | number | boolean | undefined>) => Promise<T[]>;
|
|
13
|
+
querySettings?: Record<string, string | number | boolean | undefined>;
|
|
13
14
|
}): Promise<BuildBackfillPlanOutput>;
|
|
14
15
|
//# sourceMappingURL=planner.d.ts.map
|
package/dist/planner.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"planner.d.ts","sourceRoot":"","sources":["../src/planner.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"planner.d.ts","sourceRoot":"","sources":["../src/planner.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,iBAAiB,EAAE,MAAM,aAAa,CAAA;AAOpD,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,cAAc,CAAA;AAQ/C,OAAO,KAAK,EAAE,uBAAuB,EAAE,MAAM,YAAY,CAAA;AAEzD,wBAAsB,iBAAiB,CAAC,KAAK,EAAE;IAC7C,IAAI,EAAE,WAAW,CAAA;IACjB,UAAU,EAAE,MAAM,CAAA;IAClB,MAAM,EAAE,IAAI,CAAC,iBAAiB,EAAE,SAAS,GAAG,QAAQ,CAAC,CAAA;IACrD,UAAU,CAAC,EAAE;QAAE,GAAG,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAA;KAAE,CAAA;IAC9C,eAAe,EAAE,CAAC,CAAC,EAAE,GAAG,EAAE,MAAM,EAAE,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,SAAS,CAAC,KAAK,OAAO,CAAC,CAAC,EAAE,CAAC,CAAA;IACnH,aAAa,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,SAAS,CAAC,CAAA;CACtE,GAAG,OAAO,CAAC,uBAAuB,CAAC,CAqGnC"}
|
package/dist/planner.js
CHANGED
|
@@ -1,36 +1,34 @@
|
|
|
1
1
|
import { dirname } from 'node:path';
|
|
2
2
|
import { loadSchemaDefinitions } from '@chkit/core/schema-loader';
|
|
3
|
-
import {
|
|
4
|
-
import {
|
|
3
|
+
import { encodeChunkPlanForPersistence } from './chunking/boundary-codec.js';
|
|
4
|
+
import { generateChunkPlan } from './chunking/planner.js';
|
|
5
5
|
import { findMvForTarget } from './detect.js';
|
|
6
6
|
import { BackfillConfigError } from './errors.js';
|
|
7
|
-
import { backfillPaths, computeBackfillStateDir, computeEnvironmentFingerprint, writeJson, } from './state.js';
|
|
7
|
+
import { backfillPaths, computeBackfillStateDir, computeEnvironmentFingerprint, nowIso, writeJson, } from './state.js';
|
|
8
8
|
export async function buildBackfillPlan(input) {
|
|
9
9
|
const { opts } = input;
|
|
10
10
|
const [database, table] = opts.target.split('.');
|
|
11
11
|
if (!database || !table) {
|
|
12
12
|
throw new BackfillConfigError('Invalid target format. Expected <database.table>.');
|
|
13
13
|
}
|
|
14
|
-
const
|
|
15
|
-
// 1. Analyze table and build planned chunks
|
|
16
|
-
const { planId, partitions, sortKey, chunks: plannedChunks } = await analyzeAndChunk({
|
|
14
|
+
const chunkPlan = await generateChunkPlan({
|
|
17
15
|
database,
|
|
18
16
|
table,
|
|
19
17
|
from: opts.from,
|
|
20
18
|
to: opts.to,
|
|
21
|
-
|
|
22
|
-
requireIdempotencyToken: opts.requireIdempotencyToken,
|
|
19
|
+
targetChunkBytes: opts.maxChunkBytes,
|
|
23
20
|
query: input.clickhouseQuery,
|
|
21
|
+
querySettings: input.querySettings,
|
|
24
22
|
});
|
|
25
|
-
|
|
23
|
+
const firstPartition = chunkPlan.partitions[0];
|
|
24
|
+
if (!firstPartition) {
|
|
26
25
|
throw new BackfillConfigError(`No partitions found for ${opts.target}${opts.from || opts.to ? ' within the specified time range' : ''}. The table may be empty.`);
|
|
27
26
|
}
|
|
28
|
-
const
|
|
29
|
-
const derivedFrom = opts.from ?? partitions.reduce((min,
|
|
30
|
-
const derivedTo = opts.to ?? partitions.reduce((max,
|
|
27
|
+
const env = computeEnvironmentFingerprint(input.clickhouse);
|
|
28
|
+
const derivedFrom = opts.from ?? chunkPlan.partitions.reduce((min, partition) => (partition.minTime < min ? partition.minTime : min), firstPartition.minTime);
|
|
29
|
+
const derivedTo = opts.to ?? chunkPlan.partitions.reduce((max, partition) => (partition.maxTime > max ? partition.maxTime : max), firstPartition.maxTime);
|
|
31
30
|
const stateDir = computeBackfillStateDir(input.config, input.configPath, opts.stateDir);
|
|
32
|
-
const paths = backfillPaths(stateDir, planId);
|
|
33
|
-
// 2. Detect MV for replay strategy
|
|
31
|
+
const paths = backfillPaths(stateDir, chunkPlan.planId);
|
|
34
32
|
let mvAsQuery;
|
|
35
33
|
let targetColumns;
|
|
36
34
|
try {
|
|
@@ -40,58 +38,36 @@ export async function buildBackfillPlan(input) {
|
|
|
40
38
|
const mv = findMvForTarget(definitions, database, table);
|
|
41
39
|
if (mv) {
|
|
42
40
|
mvAsQuery = mv.as;
|
|
43
|
-
const tableDef = definitions.find((
|
|
44
|
-
if (tableDef
|
|
45
|
-
targetColumns = tableDef.columns.map((
|
|
41
|
+
const tableDef = definitions.find((definition) => definition.kind === 'table' && definition.database === database && definition.name === table);
|
|
42
|
+
if (tableDef?.kind === 'table') {
|
|
43
|
+
targetColumns = tableDef.columns.map((column) => column.name);
|
|
46
44
|
}
|
|
47
45
|
}
|
|
48
46
|
}
|
|
49
47
|
catch {
|
|
50
|
-
// Schema load failed
|
|
48
|
+
// Schema load failed, fall back to direct copy.
|
|
51
49
|
}
|
|
52
|
-
// 3. Stamp SQL on each planned chunk to produce BackfillChunk[]
|
|
53
|
-
const chunks = plannedChunks.map(planned => {
|
|
54
|
-
const sqlTemplate = buildChunkSql({
|
|
55
|
-
planId,
|
|
56
|
-
chunk: planned,
|
|
57
|
-
target: opts.target,
|
|
58
|
-
sortKey,
|
|
59
|
-
mvAsQuery,
|
|
60
|
-
targetColumns,
|
|
61
|
-
});
|
|
62
|
-
return {
|
|
63
|
-
id: planned.id,
|
|
64
|
-
from: planned.from,
|
|
65
|
-
to: planned.to,
|
|
66
|
-
status: 'pending',
|
|
67
|
-
attempts: 0,
|
|
68
|
-
idempotencyToken: planned.idempotencyToken,
|
|
69
|
-
sqlTemplate,
|
|
70
|
-
partitionId: planned.partitionId,
|
|
71
|
-
estimatedBytes: planned.estimatedBytes,
|
|
72
|
-
...(planned.sortKeyFrom !== undefined ? { sortKeyFrom: planned.sortKeyFrom } : {}),
|
|
73
|
-
...(planned.sortKeyTo !== undefined ? { sortKeyTo: planned.sortKeyTo } : {}),
|
|
74
|
-
};
|
|
75
|
-
});
|
|
76
|
-
const strategy = mvAsQuery ? 'mv_replay' : 'partition';
|
|
77
50
|
const plan = {
|
|
78
|
-
planId,
|
|
51
|
+
planId: chunkPlan.planId,
|
|
79
52
|
target: opts.target,
|
|
80
|
-
createdAt:
|
|
81
|
-
status: 'planned',
|
|
82
|
-
strategy: strategy,
|
|
53
|
+
createdAt: nowIso(),
|
|
83
54
|
...(env ? { environment: env } : {}),
|
|
84
55
|
from: derivedFrom,
|
|
85
56
|
to: derivedTo,
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
57
|
+
chunkPlan,
|
|
58
|
+
execution: {
|
|
59
|
+
mode: mvAsQuery ? 'mv_replay' : 'copy',
|
|
60
|
+
sourceTarget: opts.target,
|
|
61
|
+
...(mvAsQuery ? { mvAsQuery } : {}),
|
|
62
|
+
...(targetColumns ? { targetColumns } : {}),
|
|
63
|
+
requireIdempotencyToken: opts.requireIdempotencyToken,
|
|
64
|
+
},
|
|
89
65
|
options: {
|
|
90
66
|
maxChunkBytes: opts.maxChunkBytes,
|
|
91
67
|
maxParallelChunks: opts.maxParallelChunks,
|
|
92
68
|
maxRetriesPerChunk: opts.maxRetriesPerChunk,
|
|
93
69
|
requireIdempotencyToken: opts.requireIdempotencyToken,
|
|
94
|
-
sortKeyColumn:
|
|
70
|
+
sortKeyColumn: chunkPlan.table.sortKeys[0]?.name,
|
|
95
71
|
},
|
|
96
72
|
policy: {
|
|
97
73
|
requireDryRunBeforeRun: opts.requireDryRunBeforeRun,
|
|
@@ -104,7 +80,10 @@ export async function buildBackfillPlan(input) {
|
|
|
104
80
|
minChunkMinutes: opts.minChunkMinutes,
|
|
105
81
|
},
|
|
106
82
|
};
|
|
107
|
-
await writeJson(paths.planPath,
|
|
83
|
+
await writeJson(paths.planPath, {
|
|
84
|
+
...plan,
|
|
85
|
+
chunkPlan: encodeChunkPlanForPersistence(plan.chunkPlan),
|
|
86
|
+
});
|
|
108
87
|
return {
|
|
109
88
|
plan,
|
|
110
89
|
planPath: paths.planPath,
|