tranfi 0.0.2 → 0.2.0
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.
- package/LICENSE +177 -21
- package/NOTICE +8 -0
- package/README.md +627 -0
- package/app/assets/index-6quYZ5Ap.css +5 -0
- package/app/assets/index-BIAIKnrp.js +160 -0
- package/app/assets/materialdesignicons-webfont-B7mPwVP_.ttf +0 -0
- package/app/assets/materialdesignicons-webfont-CSr8KVlo.eot +0 -0
- package/app/assets/materialdesignicons-webfont-Dp5v-WZN.woff2 +0 -0
- package/app/assets/materialdesignicons-webfont-PXm3-2wK.woff +0 -0
- package/app/index.html +13 -0
- package/binding.gyp +121 -0
- package/csrc/arena.c +93 -0
- package/csrc/batch.c +976 -0
- package/csrc/buffer.c +154 -0
- package/csrc/cJSON.c +3386 -0
- package/csrc/cJSON.h +316 -0
- package/csrc/codec_csv.c +1951 -0
- package/csrc/codec_jsonl.c +1086 -0
- package/csrc/codec_table.c +248 -0
- package/csrc/codec_text.c +447 -0
- package/csrc/compiler.c +130 -0
- package/csrc/config.h +21 -0
- package/csrc/date_utils.h +94 -0
- package/csrc/dsl.c +5417 -0
- package/csrc/dsl.h +22 -0
- package/csrc/expr.c +1553 -0
- package/csrc/expr.h +58 -0
- package/csrc/internal.h +539 -0
- package/csrc/ir.c +166 -0
- package/csrc/ir.h +208 -0
- package/csrc/ir_schema.c +75 -0
- package/csrc/ir_serialize.c +166 -0
- package/csrc/ir_sql.c +1822 -0
- package/csrc/ir_validate.c +576 -0
- package/csrc/json_path.c +210 -0
- package/csrc/main.c +1241 -0
- package/csrc/memory_estimate.c +477 -0
- package/csrc/op_acf.c +283 -0
- package/csrc/op_across.c +477 -0
- package/csrc/op_anomaly.c +255 -0
- package/csrc/op_assert.c +761 -0
- package/csrc/op_bin.c +248 -0
- package/csrc/op_cast.c +523 -0
- package/csrc/op_clip.c +99 -0
- package/csrc/op_date_trunc.c +355 -0
- package/csrc/op_datetime.c +394 -0
- package/csrc/op_derive.c +216 -0
- package/csrc/op_diff.c +250 -0
- package/csrc/op_ewma.c +222 -0
- package/csrc/op_explode.c +206 -0
- package/csrc/op_fill_down.c +235 -0
- package/csrc/op_fill_null.c +268 -0
- package/csrc/op_filter.c +181 -0
- package/csrc/op_frequency.c +721 -0
- package/csrc/op_grep.c +181 -0
- package/csrc/op_group_agg.c +1956 -0
- package/csrc/op_hash.c +159 -0
- package/csrc/op_head.c +84 -0
- package/csrc/op_interpolate.c +445 -0
- package/csrc/op_join.c +2902 -0
- package/csrc/op_json_extract.c +227 -0
- package/csrc/op_json_filter.c +384 -0
- package/csrc/op_json_flatten.c +293 -0
- package/csrc/op_json_schema.c +503 -0
- package/csrc/op_label_encode.c +419 -0
- package/csrc/op_lag.c +181 -0
- package/csrc/op_lead.c +242 -0
- package/csrc/op_normalize.c +510 -0
- package/csrc/op_onehot.c +457 -0
- package/csrc/op_pivot.c +1754 -0
- package/csrc/op_quarantine.c +189 -0
- package/csrc/op_registry.c +3044 -0
- package/csrc/op_rename.c +129 -0
- package/csrc/op_replace.c +354 -0
- package/csrc/op_rleid.c +297 -0
- package/csrc/op_rowid.c +559 -0
- package/csrc/op_sample.c +158 -0
- package/csrc/op_schema.c +1341 -0
- package/csrc/op_schema_infer.c +252 -0
- package/csrc/op_select.c +340 -0
- package/csrc/op_set.c +3449 -0
- package/csrc/op_skip.c +95 -0
- package/csrc/op_sort.c +819 -0
- package/csrc/op_source_name.c +120 -0
- package/csrc/op_split.c +151 -0
- package/csrc/op_split_data.c +119 -0
- package/csrc/op_stack.c +271 -0
- package/csrc/op_stats.c +875 -0
- package/csrc/op_step.c +333 -0
- package/csrc/op_tail.c +105 -0
- package/csrc/op_tee.c +338 -0
- package/csrc/op_top.c +357 -0
- package/csrc/op_trim.c +138 -0
- package/csrc/op_unique.c +1343 -0
- package/csrc/op_unpivot.c +193 -0
- package/csrc/op_validate.c +648 -0
- package/csrc/op_window.c +591 -0
- package/csrc/path_policy.c +85 -0
- package/csrc/pipeline.c +1088 -0
- package/csrc/recipes.c +104 -0
- package/csrc/recipes.h +27 -0
- package/csrc/report.c +506 -0
- package/csrc/report.h +22 -0
- package/csrc/selector.c +1097 -0
- package/csrc/size_utils.c +348 -0
- package/csrc/spill.c +317 -0
- package/csrc/spill.h +21 -0
- package/csrc/tranfi.h +291 -0
- package/csrc/transform.h +209 -0
- package/csrc/transform_api.c +2237 -0
- package/csrc/transform_categorical.c +923 -0
- package/csrc/transform_internal.h +472 -0
- package/csrc/transform_json.c +3812 -0
- package/csrc/transform_numeric.c +1966 -0
- package/csrc/transform_sha256.c +154 -0
- package/csrc/transform_wasm.h +162 -0
- package/csrc/transform_wasm_api.c +1373 -0
- package/csrc/wasm_api.c +218 -0
- package/napi_api.c +534 -0
- package/napi_transform.c +1648 -0
- package/napi_transform.h +8 -0
- package/package.json +64 -59
- package/scripts/install-native.js +76 -0
- package/scripts/prepack.js +64 -0
- package/scripts/sync-csrc.js +23 -0
- package/src/cli.js +190 -0
- package/src/engines/duckdb.js +142 -0
- package/src/index.js +925 -0
- package/src/memory_policy.js +411 -0
- package/src/native.js +18 -0
- package/src/pipeline.js +709 -0
- package/src/recipe_json.js +80 -0
- package/src/server.js +279 -0
- package/src/transform.js +403 -0
- package/src/transform_error.js +10 -0
- package/src/wasm.js +21 -0
- package/wasm/index.js +732 -0
- package/wasm/package.json +1 -0
- package/wasm/tranfi_core.js +0 -0
- package/wasm/transform.js +1156 -0
- package/wasm/worker.js +786 -0
- package/dist/bundle.js +0 -1
- package/index.html +0 -18
- package/src/app.css +0 -169
- package/src/app.js +0 -203
- package/src/app.vue +0 -250
- package/src/bulma-input.vue +0 -110
- package/src/common-inputs.js +0 -28
- package/src/main.js +0 -20
- package/src/transforms.js +0 -166
- package/webpack.config.js +0 -108
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
package/app/index.html
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
<!DOCTYPE html>
|
|
2
|
+
<html lang="en">
|
|
3
|
+
<head>
|
|
4
|
+
<meta charset="UTF-8">
|
|
5
|
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
6
|
+
<title>Tranfi</title>
|
|
7
|
+
<script type="module" crossorigin src="/assets/index-BIAIKnrp.js"></script>
|
|
8
|
+
<link rel="stylesheet" crossorigin href="/assets/index-6quYZ5Ap.css">
|
|
9
|
+
</head>
|
|
10
|
+
<body>
|
|
11
|
+
<div id="app"></div>
|
|
12
|
+
</body>
|
|
13
|
+
</html>
|
package/binding.gyp
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
1
|
+
{
|
|
2
|
+
"targets": [
|
|
3
|
+
{
|
|
4
|
+
"target_name": "tranfi_napi",
|
|
5
|
+
"sources": [
|
|
6
|
+
"napi_api.c",
|
|
7
|
+
"napi_transform.c",
|
|
8
|
+
"csrc/cJSON.c",
|
|
9
|
+
"csrc/transform_api.c",
|
|
10
|
+
"csrc/transform_categorical.c",
|
|
11
|
+
"csrc/transform_json.c",
|
|
12
|
+
"csrc/transform_numeric.c",
|
|
13
|
+
"csrc/transform_sha256.c",
|
|
14
|
+
"csrc/arena.c",
|
|
15
|
+
"csrc/buffer.c",
|
|
16
|
+
"csrc/size_utils.c",
|
|
17
|
+
"csrc/path_policy.c",
|
|
18
|
+
"csrc/spill.c",
|
|
19
|
+
"csrc/batch.c",
|
|
20
|
+
"csrc/pipeline.c",
|
|
21
|
+
"csrc/expr.c",
|
|
22
|
+
"csrc/selector.c",
|
|
23
|
+
"csrc/memory_estimate.c",
|
|
24
|
+
"csrc/json_path.c",
|
|
25
|
+
"csrc/codec_csv.c",
|
|
26
|
+
"csrc/codec_jsonl.c",
|
|
27
|
+
"csrc/codec_text.c",
|
|
28
|
+
"csrc/codec_table.c",
|
|
29
|
+
"csrc/op_filter.c",
|
|
30
|
+
"csrc/op_select.c",
|
|
31
|
+
"csrc/op_rename.c",
|
|
32
|
+
"csrc/op_head.c",
|
|
33
|
+
"csrc/op_skip.c",
|
|
34
|
+
"csrc/op_derive.c",
|
|
35
|
+
"csrc/op_source_name.c",
|
|
36
|
+
"csrc/op_across.c",
|
|
37
|
+
"csrc/op_stats.c",
|
|
38
|
+
"csrc/op_unique.c",
|
|
39
|
+
"csrc/op_sort.c",
|
|
40
|
+
"csrc/op_validate.c",
|
|
41
|
+
"csrc/op_quarantine.c",
|
|
42
|
+
"csrc/op_assert.c",
|
|
43
|
+
"csrc/op_schema.c",
|
|
44
|
+
"csrc/op_schema_infer.c",
|
|
45
|
+
"csrc/op_tee.c",
|
|
46
|
+
"csrc/op_trim.c",
|
|
47
|
+
"csrc/op_fill_null.c",
|
|
48
|
+
"csrc/op_cast.c",
|
|
49
|
+
"csrc/op_clip.c",
|
|
50
|
+
"csrc/op_replace.c",
|
|
51
|
+
"csrc/op_hash.c",
|
|
52
|
+
"csrc/op_bin.c",
|
|
53
|
+
"csrc/op_fill_down.c",
|
|
54
|
+
"csrc/op_step.c",
|
|
55
|
+
"csrc/op_window.c",
|
|
56
|
+
"csrc/op_explode.c",
|
|
57
|
+
"csrc/op_split.c",
|
|
58
|
+
"csrc/op_unpivot.c",
|
|
59
|
+
"csrc/op_tail.c",
|
|
60
|
+
"csrc/op_top.c",
|
|
61
|
+
"csrc/op_sample.c",
|
|
62
|
+
"csrc/op_group_agg.c",
|
|
63
|
+
"csrc/op_frequency.c",
|
|
64
|
+
"csrc/op_datetime.c",
|
|
65
|
+
"csrc/op_grep.c",
|
|
66
|
+
"csrc/op_json_extract.c",
|
|
67
|
+
"csrc/op_json_filter.c",
|
|
68
|
+
"csrc/op_json_schema.c",
|
|
69
|
+
"csrc/op_json_flatten.c",
|
|
70
|
+
"csrc/op_pivot.c",
|
|
71
|
+
"csrc/op_join.c",
|
|
72
|
+
"csrc/op_set.c",
|
|
73
|
+
"csrc/op_stack.c",
|
|
74
|
+
"csrc/op_lead.c",
|
|
75
|
+
"csrc/op_lag.c",
|
|
76
|
+
"csrc/op_rowid.c",
|
|
77
|
+
"csrc/op_rleid.c",
|
|
78
|
+
"csrc/op_date_trunc.c",
|
|
79
|
+
"csrc/op_onehot.c",
|
|
80
|
+
"csrc/op_label_encode.c",
|
|
81
|
+
"csrc/op_ewma.c",
|
|
82
|
+
"csrc/op_diff.c",
|
|
83
|
+
"csrc/op_anomaly.c",
|
|
84
|
+
"csrc/op_split_data.c",
|
|
85
|
+
"csrc/op_interpolate.c",
|
|
86
|
+
"csrc/op_normalize.c",
|
|
87
|
+
"csrc/op_acf.c",
|
|
88
|
+
"csrc/ir.c",
|
|
89
|
+
"csrc/ir_serialize.c",
|
|
90
|
+
"csrc/ir_sql.c",
|
|
91
|
+
"csrc/ir_validate.c",
|
|
92
|
+
"csrc/ir_schema.c",
|
|
93
|
+
"csrc/op_registry.c",
|
|
94
|
+
"csrc/compiler.c",
|
|
95
|
+
"csrc/dsl.c",
|
|
96
|
+
"csrc/recipes.c",
|
|
97
|
+
"csrc/report.c"
|
|
98
|
+
],
|
|
99
|
+
"include_dirs": [
|
|
100
|
+
"csrc"
|
|
101
|
+
],
|
|
102
|
+
"cflags": [
|
|
103
|
+
"-std=c11",
|
|
104
|
+
"-Wall",
|
|
105
|
+
"-DNAPI_VERSION=8",
|
|
106
|
+
"-D_POSIX_C_SOURCE=200809L",
|
|
107
|
+
"-D_XOPEN_SOURCE=700",
|
|
108
|
+
"-D_FORTIFY_SOURCE=3",
|
|
109
|
+
"-Werror=implicit-function-declaration",
|
|
110
|
+
"-Werror=incompatible-pointer-types",
|
|
111
|
+
"-Wformat",
|
|
112
|
+
"-Werror=format-security",
|
|
113
|
+
"-Werror=unused-result",
|
|
114
|
+
"-fno-common",
|
|
115
|
+
"-fstack-protector-strong",
|
|
116
|
+
"-fno-fast-math",
|
|
117
|
+
"-ffp-contract=off"
|
|
118
|
+
]
|
|
119
|
+
}
|
|
120
|
+
]
|
|
121
|
+
}
|
package/csrc/arena.c
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
1
|
+
/*
|
|
2
|
+
* arena.c — Simple arena (bump) allocator.
|
|
3
|
+
* Allocates from fixed-size blocks, grows by adding new blocks.
|
|
4
|
+
*/
|
|
5
|
+
|
|
6
|
+
#include "internal.h"
|
|
7
|
+
#include <stdlib.h>
|
|
8
|
+
#include <string.h>
|
|
9
|
+
|
|
10
|
+
#define DEFAULT_BLOCK_SIZE (64 * 1024) /* 64 KB */
|
|
11
|
+
|
|
12
|
+
static tf_arena_block *block_create(size_t cap) {
|
|
13
|
+
tf_arena_block *blk = malloc(sizeof(tf_arena_block));
|
|
14
|
+
if (!blk) return NULL;
|
|
15
|
+
blk->data = malloc(cap);
|
|
16
|
+
if (!blk->data) { free(blk); return NULL; }
|
|
17
|
+
blk->used = 0;
|
|
18
|
+
blk->cap = cap;
|
|
19
|
+
blk->next = NULL;
|
|
20
|
+
return blk;
|
|
21
|
+
}
|
|
22
|
+
|
|
23
|
+
static void block_free(tf_arena_block *blk) {
|
|
24
|
+
while (blk) {
|
|
25
|
+
tf_arena_block *next = blk->next;
|
|
26
|
+
free(blk->data);
|
|
27
|
+
free(blk);
|
|
28
|
+
blk = next;
|
|
29
|
+
}
|
|
30
|
+
}
|
|
31
|
+
|
|
32
|
+
tf_arena *tf_arena_create(size_t block_size) {
|
|
33
|
+
if (block_size == 0) block_size = DEFAULT_BLOCK_SIZE;
|
|
34
|
+
if (tf_size_align(block_size, 8, &block_size) != TF_OK) return NULL;
|
|
35
|
+
tf_arena *a = malloc(sizeof(tf_arena));
|
|
36
|
+
if (!a) return NULL;
|
|
37
|
+
a->block_size = block_size;
|
|
38
|
+
a->head = block_create(block_size);
|
|
39
|
+
if (!a->head) { free(a); return NULL; }
|
|
40
|
+
a->current = a->head;
|
|
41
|
+
return a;
|
|
42
|
+
}
|
|
43
|
+
|
|
44
|
+
void *tf_arena_alloc(tf_arena *a, size_t size) {
|
|
45
|
+
if (!a || size == 0) return NULL;
|
|
46
|
+
if (tf_size_align(size, 8, &size) != TF_OK) return NULL;
|
|
47
|
+
|
|
48
|
+
/* Try current block */
|
|
49
|
+
size_t used_after = 0;
|
|
50
|
+
if (tf_size_add(a->current->used, size, &used_after) == TF_OK && used_after <= a->current->cap) {
|
|
51
|
+
void *ptr = a->current->data + a->current->used;
|
|
52
|
+
a->current->used = used_after;
|
|
53
|
+
return ptr;
|
|
54
|
+
}
|
|
55
|
+
|
|
56
|
+
/* Need a new block — at least big enough for this allocation */
|
|
57
|
+
size_t new_cap = a->block_size;
|
|
58
|
+
if (new_cap < size) new_cap = size;
|
|
59
|
+
tf_arena_block *blk = block_create(new_cap);
|
|
60
|
+
if (!blk) return NULL;
|
|
61
|
+
|
|
62
|
+
a->current->next = blk;
|
|
63
|
+
a->current = blk;
|
|
64
|
+
void *ptr = blk->data;
|
|
65
|
+
blk->used = size;
|
|
66
|
+
return ptr;
|
|
67
|
+
}
|
|
68
|
+
|
|
69
|
+
char *tf_arena_strdup(tf_arena *a, const char *s) {
|
|
70
|
+
if (!s) return NULL;
|
|
71
|
+
size_t len = 0;
|
|
72
|
+
if (tf_size_add(strlen(s), 1, &len) != TF_OK) return NULL;
|
|
73
|
+
char *copy = tf_arena_alloc(a, len);
|
|
74
|
+
if (copy) memcpy(copy, s, len);
|
|
75
|
+
return copy;
|
|
76
|
+
}
|
|
77
|
+
|
|
78
|
+
void tf_arena_reset(tf_arena *a) {
|
|
79
|
+
if (!a) return;
|
|
80
|
+
/* Free all blocks except the first, reset the first */
|
|
81
|
+
if (a->head->next) {
|
|
82
|
+
block_free(a->head->next);
|
|
83
|
+
a->head->next = NULL;
|
|
84
|
+
}
|
|
85
|
+
a->head->used = 0;
|
|
86
|
+
a->current = a->head;
|
|
87
|
+
}
|
|
88
|
+
|
|
89
|
+
void tf_arena_free(tf_arena *a) {
|
|
90
|
+
if (!a) return;
|
|
91
|
+
block_free(a->head);
|
|
92
|
+
free(a);
|
|
93
|
+
}
|