@lix-js/sdk 0.6.0-preview.3 → 0.6.0-preview.5
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 +1 -1
- package/SKILL.md +105 -65
- package/dist/engine-wasm/index.js +4 -4
- package/dist/engine-wasm/wasm/lix_engine.d.ts +30 -6
- package/dist/engine-wasm/wasm/lix_engine.js +187 -117
- package/dist/engine-wasm/wasm/lix_engine.wasm +0 -0
- package/dist/engine-wasm/wasm/lix_engine.wasm.d.ts +14 -8
- package/dist/generated/builtin-schemas.d.ts +69 -69
- package/dist/generated/builtin-schemas.js +94 -94
- package/dist/open-lix.d.ts +42 -28
- package/dist/open-lix.js +49 -10
- package/dist/sqlite/index.js +86 -30
- package/dist-engine-src/README.md +3 -3
- package/dist-engine-src/src/backend/capabilities.rs +67 -0
- package/dist-engine-src/src/backend/conformance/baseline.rs +1127 -0
- package/dist-engine-src/src/backend/conformance/factory.rs +93 -0
- package/dist-engine-src/src/backend/conformance/failure_tests.rs +608 -0
- package/dist-engine-src/src/backend/conformance/fixtures.rs +26 -0
- package/dist-engine-src/src/backend/conformance/mod.rs +75 -0
- package/dist-engine-src/src/backend/conformance/model.rs +28 -0
- package/dist-engine-src/src/backend/conformance/model_based.rs +257 -0
- package/dist-engine-src/src/backend/conformance/persistence.rs +204 -0
- package/dist-engine-src/src/backend/conformance/projection.rs +21 -0
- package/dist-engine-src/src/backend/conformance/pushdown.rs +24 -0
- package/dist-engine-src/src/backend/conformance/runner.rs +90 -0
- package/dist-engine-src/src/backend/conformance/scan.rs +24 -0
- package/dist-engine-src/src/backend/conformance/write.rs +16 -0
- package/dist-engine-src/src/backend/error.rs +94 -0
- package/dist-engine-src/src/backend/in_memory.rs +670 -0
- package/dist-engine-src/src/backend/mod.rs +36 -9
- package/dist-engine-src/src/backend/predicate.rs +80 -0
- package/dist-engine-src/src/backend/traits.rs +260 -0
- package/dist-engine-src/src/backend/types.rs +224 -81
- package/dist-engine-src/src/binary_cas/context.rs +8 -8
- package/dist-engine-src/src/binary_cas/kv.rs +234 -259
- package/dist-engine-src/src/{version → branch}/context.rs +12 -12
- package/dist-engine-src/src/branch/lifecycle.rs +221 -0
- package/dist-engine-src/src/branch/mod.rs +13 -0
- package/dist-engine-src/src/branch/refs.rs +321 -0
- package/dist-engine-src/src/branch/stage_rows.rs +67 -0
- package/dist-engine-src/src/branch/types.rs +21 -0
- package/dist-engine-src/src/catalog/context.rs +18 -18
- package/dist-engine-src/src/catalog/snapshot.rs +8 -8
- package/dist-engine-src/src/changelog/bench_support.rs +785 -0
- package/dist-engine-src/src/changelog/change.rs +1 -0
- package/dist-engine-src/src/changelog/codec.rs +497 -0
- package/dist-engine-src/src/changelog/commit.rs +1 -0
- package/dist-engine-src/src/changelog/context.rs +1614 -0
- package/dist-engine-src/src/changelog/mod.rs +29 -0
- package/dist-engine-src/src/changelog/store.rs +163 -0
- package/dist-engine-src/src/changelog/test_support.rs +54 -0
- package/dist-engine-src/src/changelog/types.rs +213 -0
- package/dist-engine-src/src/commit_graph/context.rs +317 -274
- package/dist-engine-src/src/commit_graph/mod.rs +2 -4
- package/dist-engine-src/src/commit_graph/types.rs +22 -42
- package/dist-engine-src/src/commit_graph/walker.rs +133 -103
- package/dist-engine-src/src/common/error.rs +52 -18
- package/dist-engine-src/src/common/identity.rs +2 -2
- package/dist-engine-src/src/common/mod.rs +1 -1
- package/dist-engine-src/src/domain.rs +42 -46
- package/dist-engine-src/src/engine.rs +74 -96
- package/dist-engine-src/src/{entity_identity.rs → entity_pk.rs} +89 -92
- package/dist-engine-src/src/functions/context.rs +56 -52
- package/dist-engine-src/src/functions/state.rs +51 -52
- package/dist-engine-src/src/init.rs +288 -154
- package/dist-engine-src/src/json_store/context.rs +15 -266
- package/dist-engine-src/src/json_store/mod.rs +26 -0
- package/dist-engine-src/src/json_store/store.rs +103 -718
- package/dist-engine-src/src/json_store/types.rs +4 -9
- package/dist-engine-src/src/lib.rs +49 -19
- package/dist-engine-src/src/live_state/context.rs +654 -790
- package/dist-engine-src/src/live_state/mod.rs +9 -3
- package/dist-engine-src/src/live_state/overlay.rs +4 -4
- package/dist-engine-src/src/live_state/types.rs +30 -21
- package/dist-engine-src/src/live_state/visibility.rs +514 -71
- package/dist-engine-src/src/plugin/install.rs +48 -48
- package/dist-engine-src/src/plugin/manifest.rs +7 -7
- package/dist-engine-src/src/plugin/materializer.rs +0 -275
- package/dist-engine-src/src/plugin/plugin_manifest.json +4 -3
- package/dist-engine-src/src/schema/builtin/lix_binary_blob_ref.json +2 -2
- package/dist-engine-src/src/schema/builtin/lix_branch_descriptor.json +34 -0
- package/dist-engine-src/src/schema/builtin/lix_branch_ref.json +48 -0
- package/dist-engine-src/src/schema/builtin/lix_change.json +3 -3
- package/dist-engine-src/src/schema/builtin/lix_commit.json +1 -1
- package/dist-engine-src/src/schema/builtin/lix_label_assignment.json +6 -6
- package/dist-engine-src/src/schema/builtin/mod.rs +18 -20
- package/dist-engine-src/src/schema/compatibility.rs +11 -11
- package/dist-engine-src/src/schema/definition.json +2 -2
- package/dist-engine-src/src/schema/definition.rs +5 -5
- package/dist-engine-src/src/schema/key.rs +3 -3
- package/dist-engine-src/src/schema/mod.rs +1 -1
- package/dist-engine-src/src/schema/tests.rs +18 -18
- package/dist-engine-src/src/session/context.rs +819 -124
- package/dist-engine-src/src/session/create_branch.rs +94 -0
- package/dist-engine-src/src/session/execute.rs +260 -57
- package/dist-engine-src/src/session/merge/analysis.rs +9 -3
- package/dist-engine-src/src/session/merge/{version.rs → branch.rs} +119 -129
- package/dist-engine-src/src/session/merge/conflicts.rs +2 -2
- package/dist-engine-src/src/session/merge/mod.rs +5 -6
- package/dist-engine-src/src/session/merge/stats.rs +7 -11
- package/dist-engine-src/src/session/mod.rs +19 -16
- package/dist-engine-src/src/session/switch_branch.rs +113 -0
- package/dist-engine-src/src/session/transaction.rs +557 -0
- package/dist-engine-src/src/sql2/bind/classify.rs +102 -0
- package/dist-engine-src/src/sql2/bind/error.rs +5 -0
- package/dist-engine-src/src/sql2/bind/expr.rs +29 -0
- package/dist-engine-src/src/sql2/bind/mod.rs +12 -0
- package/dist-engine-src/src/sql2/{udfs/public_call.rs → bind/public_udf.rs} +98 -3
- package/dist-engine-src/src/sql2/bind/read.rs +65 -0
- package/dist-engine-src/src/sql2/bind/statement.rs +2236 -0
- package/dist-engine-src/src/sql2/bind/table.rs +273 -0
- package/dist-engine-src/src/sql2/bind/write.rs +86 -0
- package/dist-engine-src/src/sql2/branch_scope.rs +436 -0
- package/dist-engine-src/src/sql2/catalog/capability.rs +20 -0
- package/dist-engine-src/src/sql2/catalog/entity_surface.rs +296 -0
- package/dist-engine-src/src/sql2/catalog/mod.rs +15 -0
- package/dist-engine-src/src/sql2/catalog/registry.rs +556 -0
- package/dist-engine-src/src/sql2/catalog/schema.rs +88 -0
- package/dist-engine-src/src/sql2/catalog/surface.rs +41 -0
- package/dist-engine-src/src/sql2/change_materialization.rs +122 -0
- package/dist-engine-src/src/sql2/context.rs +36 -30
- package/dist-engine-src/src/sql2/error.rs +4 -5
- package/dist-engine-src/src/sql2/exec/bound_public_write.rs +1593 -0
- package/dist-engine-src/src/sql2/exec/datafusion.rs +5266 -0
- package/dist-engine-src/src/sql2/exec/fast_write.rs +82 -0
- package/dist-engine-src/src/sql2/exec/mod.rs +24 -0
- package/dist-engine-src/src/sql2/exec/write.rs +661 -0
- package/dist-engine-src/src/sql2/filesystem_planner.rs +72 -77
- package/dist-engine-src/src/sql2/filesystem_visibility.rs +21 -21
- package/dist-engine-src/src/sql2/history_projection.rs +8 -8
- package/dist-engine-src/src/sql2/history_route.rs +35 -31
- package/dist-engine-src/src/sql2/mod.rs +30 -24
- package/dist-engine-src/src/sql2/optimize/datafusion.rs +1 -0
- package/dist-engine-src/src/sql2/optimize/mod.rs +2 -0
- package/dist-engine-src/src/sql2/optimize/simple_write.rs +116 -0
- package/dist-engine-src/src/sql2/parse/mod.rs +69 -0
- package/dist-engine-src/src/sql2/parse/normalize.rs +1 -0
- package/dist-engine-src/src/sql2/plan/branch_scope.rs +24 -0
- package/dist-engine-src/src/sql2/plan/mod.rs +5 -0
- package/dist-engine-src/src/sql2/plan/predicate.rs +22 -0
- package/dist-engine-src/src/sql2/plan/write.rs +147 -0
- package/dist-engine-src/src/sql2/predicate_typecheck.rs +258 -0
- package/dist-engine-src/src/sql2/{version_provider.rs → providers/branch.rs} +218 -214
- package/dist-engine-src/src/sql2/{change_provider.rs → providers/change.rs} +156 -42
- package/dist-engine-src/src/sql2/{directory_provider.rs → providers/directory.rs} +291 -322
- package/dist-engine-src/src/sql2/{directory_history_provider.rs → providers/directory_history.rs} +56 -42
- package/dist-engine-src/src/sql2/providers/entity.rs +1484 -0
- package/dist-engine-src/src/sql2/{entity_history_provider.rs → providers/entity_history.rs} +43 -31
- package/dist-engine-src/src/sql2/{file_provider.rs → providers/file.rs} +323 -316
- package/dist-engine-src/src/sql2/{file_history_provider.rs → providers/file_history.rs} +60 -46
- package/dist-engine-src/src/sql2/{history_provider.rs → providers/history.rs} +46 -32
- package/dist-engine-src/src/sql2/{lix_state_provider.rs → providers/lix_state.rs} +359 -329
- package/dist-engine-src/src/sql2/providers/mod.rs +508 -0
- package/dist-engine-src/src/sql2/read_only.rs +2 -2
- package/dist-engine-src/src/sql2/session.rs +47 -96
- package/dist-engine-src/src/sql2/storage/constraints.rs +1 -0
- package/dist-engine-src/src/sql2/storage/mod.rs +1 -0
- package/dist-engine-src/src/sql2/test_support/differential.rs +712 -0
- package/dist-engine-src/src/sql2/test_support/generators.rs +354 -0
- package/dist-engine-src/src/sql2/test_support/mod.rs +2 -0
- package/dist-engine-src/src/sql2/udfs/{lix_active_version_commit_id.rs → lix_active_branch_commit_id.rs} +7 -7
- package/dist-engine-src/src/sql2/udfs/mod.rs +3 -6
- package/dist-engine-src/src/sql2/write_normalization.rs +45 -22
- package/dist-engine-src/src/storage/conformance.rs +399 -0
- package/dist-engine-src/src/storage/context.rs +552 -288
- package/dist-engine-src/src/storage/mod.rs +48 -10
- package/dist-engine-src/src/storage/point.rs +440 -0
- package/dist-engine-src/src/storage/read_scope.rs +43 -64
- package/dist-engine-src/src/storage/reader.rs +867 -0
- package/dist-engine-src/src/storage/scan.rs +784 -0
- package/dist-engine-src/src/storage/spaces.rs +236 -0
- package/dist-engine-src/src/storage/stats.rs +80 -0
- package/dist-engine-src/src/storage/write_set.rs +962 -0
- package/dist-engine-src/src/storage_bench.rs +136 -4828
- package/dist-engine-src/src/test_support.rs +360 -138
- package/dist-engine-src/src/tracked_state/bench_support.rs +394 -0
- package/dist-engine-src/src/tracked_state/codec.rs +155 -1057
- package/dist-engine-src/src/tracked_state/commit_root_rebuild.rs +358 -0
- package/dist-engine-src/src/tracked_state/context.rs +1927 -993
- package/dist-engine-src/src/tracked_state/diff.rs +1715 -261
- package/dist-engine-src/src/tracked_state/merge.rs +74 -88
- package/dist-engine-src/src/tracked_state/mod.rs +19 -16
- package/dist-engine-src/src/tracked_state/{materialization.rs → row_materialization.rs} +50 -178
- package/dist-engine-src/src/tracked_state/storage.rs +243 -191
- package/dist-engine-src/src/tracked_state/tree.rs +247 -371
- package/dist-engine-src/src/tracked_state/types.rs +49 -42
- package/dist-engine-src/src/transaction/bench_support.rs +407 -0
- package/dist-engine-src/src/transaction/commit.rs +821 -713
- package/dist-engine-src/src/transaction/context.rs +705 -600
- package/dist-engine-src/src/transaction/mod.rs +13 -2
- package/dist-engine-src/src/transaction/normalization.rs +63 -76
- package/dist-engine-src/src/transaction/prep.rs +13 -13
- package/dist-engine-src/src/transaction/schema_resolver.rs +19 -5
- package/dist-engine-src/src/transaction/staging.rs +228 -434
- package/dist-engine-src/src/transaction/types.rs +41 -98
- package/dist-engine-src/src/transaction/validation.rs +382 -446
- package/dist-engine-src/src/untracked_state/codec.rs +337 -29
- package/dist-engine-src/src/untracked_state/context.rs +7 -7
- package/dist-engine-src/src/untracked_state/materialization.rs +2 -2
- package/dist-engine-src/src/untracked_state/mod.rs +1 -1
- package/dist-engine-src/src/untracked_state/storage.rs +659 -157
- package/dist-engine-src/src/untracked_state/types.rs +21 -21
- package/package.json +71 -68
- package/dist-engine-src/src/backend/kv.rs +0 -358
- package/dist-engine-src/src/backend/testing.rs +0 -658
- package/dist-engine-src/src/commit_store/codec.rs +0 -887
- package/dist-engine-src/src/commit_store/context.rs +0 -944
- package/dist-engine-src/src/commit_store/materialization.rs +0 -84
- package/dist-engine-src/src/commit_store/mod.rs +0 -16
- package/dist-engine-src/src/commit_store/storage.rs +0 -600
- package/dist-engine-src/src/commit_store/types.rs +0 -215
- package/dist-engine-src/src/schema/builtin/lix_version_descriptor.json +0 -34
- package/dist-engine-src/src/schema/builtin/lix_version_ref.json +0 -48
- package/dist-engine-src/src/session/create_version.rs +0 -88
- package/dist-engine-src/src/session/merge/apply.rs +0 -23
- package/dist-engine-src/src/session/optimization9_sql2_bench.rs +0 -100
- package/dist-engine-src/src/session/switch_version.rs +0 -109
- package/dist-engine-src/src/sql2/classify.rs +0 -182
- package/dist-engine-src/src/sql2/entity_provider.rs +0 -3211
- package/dist-engine-src/src/sql2/execute.rs +0 -3440
- package/dist-engine-src/src/sql2/public_bind/assignment.rs +0 -46
- package/dist-engine-src/src/sql2/public_bind/capability.rs +0 -41
- package/dist-engine-src/src/sql2/public_bind/dml.rs +0 -166
- package/dist-engine-src/src/sql2/public_bind/mod.rs +0 -25
- package/dist-engine-src/src/sql2/public_bind/table.rs +0 -168
- package/dist-engine-src/src/sql2/version_scope.rs +0 -394
- package/dist-engine-src/src/storage/types.rs +0 -501
- package/dist-engine-src/src/tracked_state/by_file_index.rs +0 -98
- package/dist-engine-src/src/tracked_state/materializer.rs +0 -488
- package/dist-engine-src/src/transaction/live_state_overlay.rs +0 -35
- package/dist-engine-src/src/version/lifecycle.rs +0 -221
- package/dist-engine-src/src/version/mod.rs +0 -13
- package/dist-engine-src/src/version/refs.rs +0 -330
- package/dist-engine-src/src/version/stage_rows.rs +0 -67
- package/dist-engine-src/src/version/types.rs +0 -21
|
@@ -1,4 +1,8 @@
|
|
|
1
|
+
use std::collections::{BTreeMap, BTreeSet};
|
|
2
|
+
|
|
1
3
|
use datafusion::arrow::datatypes::{Field, Schema};
|
|
4
|
+
use datafusion::common::metadata::FieldMetadata;
|
|
5
|
+
use datafusion::common::tree_node::{Transformed, TreeNode};
|
|
2
6
|
use datafusion::common::{DFSchema, DataFusionError, ScalarValue};
|
|
3
7
|
use datafusion::logical_expr::expr::{Between, InList};
|
|
4
8
|
use datafusion::logical_expr::{BinaryExpr, Expr, Like, Operator};
|
|
@@ -19,6 +23,17 @@ pub(crate) fn validate_json_predicate_filters(
|
|
|
19
23
|
Ok(())
|
|
20
24
|
}
|
|
21
25
|
|
|
26
|
+
pub(crate) fn canonicalize_json_identity_text_filters(
|
|
27
|
+
schema: &Schema,
|
|
28
|
+
filters: &[Expr],
|
|
29
|
+
) -> Result<Vec<Expr>, DataFusionError> {
|
|
30
|
+
filters
|
|
31
|
+
.iter()
|
|
32
|
+
.cloned()
|
|
33
|
+
.map(|filter| canonicalize_json_identity_text_filter(schema, filter))
|
|
34
|
+
.collect()
|
|
35
|
+
}
|
|
36
|
+
|
|
22
37
|
pub(crate) fn validate_json_predicate_expr_with_dfschema(
|
|
23
38
|
schema: &DFSchema,
|
|
24
39
|
expr: &Expr,
|
|
@@ -31,6 +46,140 @@ pub(crate) fn validate_json_predicate_expr_with_dfschema(
|
|
|
31
46
|
})
|
|
32
47
|
}
|
|
33
48
|
|
|
49
|
+
pub(crate) fn json_predicate_placeholder_indexes_with_dfschema(
|
|
50
|
+
schema: &DFSchema,
|
|
51
|
+
expr: &Expr,
|
|
52
|
+
) -> BTreeSet<usize> {
|
|
53
|
+
let mut indexes = BTreeSet::new();
|
|
54
|
+
collect_json_predicate_placeholder_indexes(expr, &mut indexes, &|column| {
|
|
55
|
+
schema
|
|
56
|
+
.field_with_name(column.relation.as_ref(), &column.name)
|
|
57
|
+
.ok()
|
|
58
|
+
.map(|field| field.as_ref())
|
|
59
|
+
});
|
|
60
|
+
indexes
|
|
61
|
+
}
|
|
62
|
+
|
|
63
|
+
fn canonicalize_json_identity_text_filter(
|
|
64
|
+
schema: &Schema,
|
|
65
|
+
expr: Expr,
|
|
66
|
+
) -> Result<Expr, DataFusionError> {
|
|
67
|
+
expr.transform(|expr| canonicalize_json_identity_text_expr(schema, expr))
|
|
68
|
+
.map(|transformed| transformed.data)
|
|
69
|
+
}
|
|
70
|
+
|
|
71
|
+
fn canonicalize_json_identity_text_expr(
|
|
72
|
+
schema: &Schema,
|
|
73
|
+
expr: Expr,
|
|
74
|
+
) -> Result<Transformed<Expr>, DataFusionError> {
|
|
75
|
+
match expr {
|
|
76
|
+
Expr::BinaryExpr(binary) if is_comparison_operator(binary.op) => {
|
|
77
|
+
canonicalize_json_identity_text_binary(schema, binary)
|
|
78
|
+
}
|
|
79
|
+
Expr::InList(in_list) => canonicalize_json_identity_text_in_list(schema, in_list),
|
|
80
|
+
_ => Ok(Transformed::no(expr)),
|
|
81
|
+
}
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
fn canonicalize_json_identity_text_binary(
|
|
85
|
+
schema: &Schema,
|
|
86
|
+
binary: BinaryExpr,
|
|
87
|
+
) -> Result<Transformed<Expr>, DataFusionError> {
|
|
88
|
+
let BinaryExpr { left, op, right } = binary;
|
|
89
|
+
let left_identity_json = is_identity_json_expr_for_arrow_schema(schema, &left);
|
|
90
|
+
let right_identity_json = is_identity_json_expr_for_arrow_schema(schema, &right);
|
|
91
|
+
let left = if right_identity_json {
|
|
92
|
+
Box::new(canonicalize_json_text_literal(*left)?)
|
|
93
|
+
} else {
|
|
94
|
+
left
|
|
95
|
+
};
|
|
96
|
+
let right = if left_identity_json {
|
|
97
|
+
Box::new(canonicalize_json_text_literal(*right)?)
|
|
98
|
+
} else {
|
|
99
|
+
right
|
|
100
|
+
};
|
|
101
|
+
Ok(Transformed::yes(Expr::BinaryExpr(BinaryExpr::new(
|
|
102
|
+
left, op, right,
|
|
103
|
+
))))
|
|
104
|
+
}
|
|
105
|
+
|
|
106
|
+
fn canonicalize_json_identity_text_in_list(
|
|
107
|
+
schema: &Schema,
|
|
108
|
+
in_list: InList,
|
|
109
|
+
) -> Result<Transformed<Expr>, DataFusionError> {
|
|
110
|
+
let expr_identity_json = is_identity_json_expr_for_arrow_schema(schema, &in_list.expr);
|
|
111
|
+
let list_has_identity_json = in_list
|
|
112
|
+
.list
|
|
113
|
+
.iter()
|
|
114
|
+
.any(|item| is_identity_json_expr_for_arrow_schema(schema, item));
|
|
115
|
+
|
|
116
|
+
let expr = if list_has_identity_json {
|
|
117
|
+
Box::new(canonicalize_json_text_literal(*in_list.expr)?)
|
|
118
|
+
} else {
|
|
119
|
+
in_list.expr
|
|
120
|
+
};
|
|
121
|
+
let list = if expr_identity_json {
|
|
122
|
+
in_list
|
|
123
|
+
.list
|
|
124
|
+
.into_iter()
|
|
125
|
+
.map(canonicalize_json_text_literal)
|
|
126
|
+
.collect::<Result<Vec<_>, _>>()?
|
|
127
|
+
} else {
|
|
128
|
+
in_list.list
|
|
129
|
+
};
|
|
130
|
+
|
|
131
|
+
Ok(Transformed::yes(Expr::InList(InList::new(
|
|
132
|
+
expr,
|
|
133
|
+
list,
|
|
134
|
+
in_list.negated,
|
|
135
|
+
))))
|
|
136
|
+
}
|
|
137
|
+
|
|
138
|
+
fn canonicalize_json_text_literal(expr: Expr) -> Result<Expr, DataFusionError> {
|
|
139
|
+
let Expr::Literal(literal, metadata) = expr else {
|
|
140
|
+
return Ok(expr);
|
|
141
|
+
};
|
|
142
|
+
let canonical = match &literal {
|
|
143
|
+
ScalarValue::Utf8(Some(value))
|
|
144
|
+
| ScalarValue::Utf8View(Some(value))
|
|
145
|
+
| ScalarValue::LargeUtf8(Some(value)) => Some(canonical_json_text(value)?),
|
|
146
|
+
_ => None,
|
|
147
|
+
};
|
|
148
|
+
Ok(match canonical {
|
|
149
|
+
Some(value) => Expr::Literal(ScalarValue::Utf8(Some(value)), Some(json_field_metadata())),
|
|
150
|
+
None => Expr::Literal(literal, metadata),
|
|
151
|
+
})
|
|
152
|
+
}
|
|
153
|
+
|
|
154
|
+
fn canonical_json_text(raw: &str) -> Result<String, DataFusionError> {
|
|
155
|
+
serde_json::from_str::<serde_json::Value>(raw)
|
|
156
|
+
.map(|value| value.to_string())
|
|
157
|
+
.map_err(|error| {
|
|
158
|
+
lix_error_to_datafusion_error(LixError::new(
|
|
159
|
+
LixError::CODE_TYPE_MISMATCH,
|
|
160
|
+
format!("JSON comparison value is not valid JSON: {error}"),
|
|
161
|
+
))
|
|
162
|
+
})
|
|
163
|
+
}
|
|
164
|
+
|
|
165
|
+
fn json_field_metadata() -> FieldMetadata {
|
|
166
|
+
FieldMetadata::new(BTreeMap::from([(
|
|
167
|
+
LIX_VALUE_TYPE_METADATA_KEY.to_string(),
|
|
168
|
+
LIX_VALUE_TYPE_JSON.to_string(),
|
|
169
|
+
)]))
|
|
170
|
+
}
|
|
171
|
+
|
|
172
|
+
fn is_identity_json_expr_for_arrow_schema(schema: &Schema, expr: &Expr) -> bool {
|
|
173
|
+
is_identity_json_expr(expr)
|
|
174
|
+
&& is_json_expr(expr, &|column| {
|
|
175
|
+
schema
|
|
176
|
+
.fields()
|
|
177
|
+
.iter()
|
|
178
|
+
.find(|field| field.name() == &column.name)
|
|
179
|
+
.map(|field| field.as_ref())
|
|
180
|
+
})
|
|
181
|
+
}
|
|
182
|
+
|
|
34
183
|
fn validate_json_predicate_expr_with_arrow_schema(
|
|
35
184
|
schema: &Schema,
|
|
36
185
|
expr: &Expr,
|
|
@@ -101,6 +250,105 @@ fn validate_expr<'a>(
|
|
|
101
250
|
}
|
|
102
251
|
}
|
|
103
252
|
|
|
253
|
+
fn collect_json_predicate_placeholder_indexes<'a>(
|
|
254
|
+
expr: &'a Expr,
|
|
255
|
+
indexes: &mut BTreeSet<usize>,
|
|
256
|
+
lookup_field: &impl Fn(&datafusion::common::Column) -> Option<&'a Field>,
|
|
257
|
+
) {
|
|
258
|
+
match expr {
|
|
259
|
+
Expr::BinaryExpr(binary) if is_comparison_operator(binary.op) => {
|
|
260
|
+
collect_json_predicate_placeholder_indexes(&binary.left, indexes, lookup_field);
|
|
261
|
+
collect_json_predicate_placeholder_indexes(&binary.right, indexes, lookup_field);
|
|
262
|
+
if is_json_expr(&binary.left, lookup_field) {
|
|
263
|
+
collect_placeholder_indexes(&binary.right, indexes);
|
|
264
|
+
}
|
|
265
|
+
if is_json_expr(&binary.right, lookup_field) {
|
|
266
|
+
collect_placeholder_indexes(&binary.left, indexes);
|
|
267
|
+
}
|
|
268
|
+
}
|
|
269
|
+
Expr::BinaryExpr(binary) => {
|
|
270
|
+
collect_json_predicate_placeholder_indexes(&binary.left, indexes, lookup_field);
|
|
271
|
+
collect_json_predicate_placeholder_indexes(&binary.right, indexes, lookup_field);
|
|
272
|
+
}
|
|
273
|
+
Expr::InList(in_list) => {
|
|
274
|
+
collect_json_predicate_placeholder_indexes(&in_list.expr, indexes, lookup_field);
|
|
275
|
+
for item in &in_list.list {
|
|
276
|
+
collect_json_predicate_placeholder_indexes(item, indexes, lookup_field);
|
|
277
|
+
}
|
|
278
|
+
if is_json_expr(&in_list.expr, lookup_field) {
|
|
279
|
+
for item in &in_list.list {
|
|
280
|
+
collect_placeholder_indexes(item, indexes);
|
|
281
|
+
}
|
|
282
|
+
}
|
|
283
|
+
for item in &in_list.list {
|
|
284
|
+
if is_json_expr(item, lookup_field) {
|
|
285
|
+
collect_placeholder_indexes(&in_list.expr, indexes);
|
|
286
|
+
}
|
|
287
|
+
}
|
|
288
|
+
}
|
|
289
|
+
Expr::Between(between) => {
|
|
290
|
+
collect_json_predicate_placeholder_indexes(&between.expr, indexes, lookup_field);
|
|
291
|
+
collect_json_predicate_placeholder_indexes(&between.low, indexes, lookup_field);
|
|
292
|
+
collect_json_predicate_placeholder_indexes(&between.high, indexes, lookup_field);
|
|
293
|
+
if is_json_expr(&between.expr, lookup_field) {
|
|
294
|
+
collect_placeholder_indexes(&between.low, indexes);
|
|
295
|
+
collect_placeholder_indexes(&between.high, indexes);
|
|
296
|
+
}
|
|
297
|
+
}
|
|
298
|
+
Expr::Alias(alias) => {
|
|
299
|
+
collect_json_predicate_placeholder_indexes(&alias.expr, indexes, lookup_field)
|
|
300
|
+
}
|
|
301
|
+
Expr::Not(inner)
|
|
302
|
+
| Expr::IsNotNull(inner)
|
|
303
|
+
| Expr::IsNull(inner)
|
|
304
|
+
| Expr::IsTrue(inner)
|
|
305
|
+
| Expr::IsFalse(inner)
|
|
306
|
+
| Expr::IsUnknown(inner)
|
|
307
|
+
| Expr::IsNotTrue(inner)
|
|
308
|
+
| Expr::IsNotFalse(inner)
|
|
309
|
+
| Expr::IsNotUnknown(inner)
|
|
310
|
+
| Expr::Negative(inner) => {
|
|
311
|
+
collect_json_predicate_placeholder_indexes(inner, indexes, lookup_field)
|
|
312
|
+
}
|
|
313
|
+
Expr::Cast(cast) => {
|
|
314
|
+
collect_json_predicate_placeholder_indexes(&cast.expr, indexes, lookup_field)
|
|
315
|
+
}
|
|
316
|
+
Expr::TryCast(cast) => {
|
|
317
|
+
collect_json_predicate_placeholder_indexes(&cast.expr, indexes, lookup_field)
|
|
318
|
+
}
|
|
319
|
+
Expr::ScalarFunction(function) => {
|
|
320
|
+
for arg in &function.args {
|
|
321
|
+
collect_json_predicate_placeholder_indexes(arg, indexes, lookup_field);
|
|
322
|
+
}
|
|
323
|
+
}
|
|
324
|
+
Expr::Case(case) => {
|
|
325
|
+
if let Some(expr) = &case.expr {
|
|
326
|
+
collect_json_predicate_placeholder_indexes(expr, indexes, lookup_field);
|
|
327
|
+
}
|
|
328
|
+
for (when, then) in &case.when_then_expr {
|
|
329
|
+
collect_json_predicate_placeholder_indexes(when, indexes, lookup_field);
|
|
330
|
+
collect_json_predicate_placeholder_indexes(then, indexes, lookup_field);
|
|
331
|
+
}
|
|
332
|
+
if let Some(expr) = &case.else_expr {
|
|
333
|
+
collect_json_predicate_placeholder_indexes(expr, indexes, lookup_field);
|
|
334
|
+
}
|
|
335
|
+
}
|
|
336
|
+
_ => {}
|
|
337
|
+
}
|
|
338
|
+
}
|
|
339
|
+
|
|
340
|
+
fn collect_placeholder_indexes(expr: &Expr, indexes: &mut BTreeSet<usize>) {
|
|
341
|
+
if let Expr::Placeholder(placeholder) = expr {
|
|
342
|
+
if let Some(index) = placeholder
|
|
343
|
+
.id
|
|
344
|
+
.strip_prefix('$')
|
|
345
|
+
.and_then(|value| value.parse::<usize>().ok())
|
|
346
|
+
{
|
|
347
|
+
indexes.insert(index);
|
|
348
|
+
}
|
|
349
|
+
}
|
|
350
|
+
}
|
|
351
|
+
|
|
104
352
|
fn validate_binary_expr<'a>(
|
|
105
353
|
binary: &'a BinaryExpr,
|
|
106
354
|
lookup_field: &impl Fn(&datafusion::common::Column) -> Option<&'a Field>,
|
|
@@ -219,6 +467,16 @@ fn is_json_expr<'a>(
|
|
|
219
467
|
}
|
|
220
468
|
}
|
|
221
469
|
|
|
470
|
+
fn is_identity_json_expr(expr: &Expr) -> bool {
|
|
471
|
+
match expr {
|
|
472
|
+
Expr::Column(column) => matches!(column.name.as_str(), "entity_pk" | "lixcol_entity_pk"),
|
|
473
|
+
Expr::Alias(alias) => is_identity_json_expr(&alias.expr),
|
|
474
|
+
Expr::Cast(cast) => is_identity_json_expr(&cast.expr),
|
|
475
|
+
Expr::TryCast(cast) => is_identity_json_expr(&cast.expr),
|
|
476
|
+
_ => false,
|
|
477
|
+
}
|
|
478
|
+
}
|
|
479
|
+
|
|
222
480
|
fn is_null_literal(expr: &Expr) -> bool {
|
|
223
481
|
matches!(expr, Expr::Literal(value, _) if matches!(value, ScalarValue::Null))
|
|
224
482
|
}
|