@wafertools/testdata-parser 0.14.0 → 0.15.0

package/README.md

@@ -84,7 +84,7 @@ Every parse function takes raw file bytes (`Uint8Array`), or throws a `ParserErr
 | `atdf_test_names` | `(bytes: Uint8Array) => ScanResult` | Same first-pass scan for ATDF |
 | `stdf_file_meta` | `(bytes: Uint8Array) => FileMeta` | Lot metadata, wafer count, first/last timestamps and site count from an MIR/SDR/WIR/WRR-only scan — no PTR/FTR/PIR/PRR walk, so it stays cheap across a batch of files |
 | `atdf_file_meta` | `(bytes: Uint8Array) => FileMeta` | Same metadata-only scan for ATDF |
-| `parquet_distinct_count` | `(bytes: Uint8Array, columns: string[]) => number` | How many distinct combinations of those columns the file holds — a wafer count from `['lot','wafer']` without a full parse, read as a column projection. A column missing from the schema is an error, not a count of zero. Parquet only: CSV/JSON have no equivalent shortcut |
+| `parquet_distinct_count` | `(bytes: Uint8Array, columns: string[], blankIsAValue: boolean) => number` | How many distinct combinations of those columns the file holds — a wafer count from `['lot','wafer']` without a full parse, read as a column projection. `blankIsAValue` is stated by every caller: `false` skips rows blank in every named column (a wafer count: an empty row is not a wafer), `true` counts them as one more value (is this column constant? a column that is "25" in some rows and empty in the rest is not). A column missing from the schema is an error, not a count of zero. Parquet only: CSV/JSON have no equivalent shortcut |
 | `parse_stdf_filtered` | `(bytes: Uint8Array, selected: number[]) => Uint8Array` | Full parse, skipping per-site accumulation for test numbers not in `selected` |
 | `parse_atdf_filtered` | `(bytes: Uint8Array, selected: number[]) => Uint8Array` | Same filtered parse for ATDF |
 
@@ -336,7 +336,7 @@ There is no `csv_headers`/`json_headers` in the WASM API — a browser caller th
 ```ts
 interface ParquetHeadersResult {
   headers: string[];
-  sample: Record<string, string>[];
+  sample: Record<string, string>[];   // the first five rows, then the first row of up to twenty later row groups, evenly spaced
   rowCount: number;
   columnTypes: Record<string, 'number' | 'bool' | 'string'>;
 }
@@ -358,7 +358,7 @@ The crate also builds as a native Rust library (used directly by tsmap's Tauri c
 | `parse_json_sync(path: String, mapping: CsvMapping) -> ParseResult<ParsedStdf>` | `parse_json` |
 | `parquet_headers_inner(path: String) -> ParseResult<ParquetHeadersResult>` | `parse_parquet` |
 | `parse_parquet_inner(path: String, mapping: CsvMapping) -> ParseResult<ParsedStdf>` | `parse_parquet` |
-| `parquet_distinct_count_inner(path: String, columns: Vec<String>) -> ParseResult<usize>` | `parse_parquet` |
+| `parquet_distinct_count_inner(path: String, columns: Vec<String>, blank_is_a_value: bool) -> ParseResult<usize>` | `parse_parquet` |
 | `read_bytes(path: &str) -> ParseResult<Vec<u8>>` | `read_file` |
 | `read_text(path: &str) -> ParseResult<String>` | `read_file` |
 
@@ -383,7 +383,7 @@ alone. Same codes as the WASM layer above; it is the same error, serialised ther
 | `parse_json_from_bytes(&[u8], mapping: CsvMapping) -> ParseResult<ParsedStdf>` | `parse_json` |
 | `parquet_headers_from_bytes(&[u8]) -> ParseResult<ParquetHeadersResult>` | `parse_parquet` |
 | `parse_parquet_from_bytes(&[u8], mapping: CsvMapping) -> ParseResult<ParsedStdf>` | `parse_parquet` |
-| `parquet_distinct_count_from_bytes(&[u8], &[String]) -> ParseResult<usize>` | `parse_parquet` |
+| `parquet_distinct_count_from_bytes(&[u8], &[String], bool) -> ParseResult<usize>` | `parse_parquet` |
 | `decompress_if_gzip(Vec<u8>) -> ParseResult<Vec<u8>>` | `read_file` |
 
 `CsvHeadersResult` and `JsonHeadersResult` are the same shape — the header row plus enough of the file to preview a mapping:
@@ -391,7 +391,7 @@ alone. Same codes as the WASM layer above; it is the same error, serialised ther
 ```rust
 pub struct CsvHeadersResult {
     pub headers: Vec<String>,
-    pub sample: Vec<HashMap<String, String>>, // first few rows, for a preview UI
+    pub sample: Vec<HashMap<String, String>>, // the first five rows, then up to twenty spread through the file
     pub row_count: usize,
 }
 ```

package/llms.txt

@@ -31,7 +31,8 @@ resolve.
 - `parse_csv(bytes, mapping)` / `parse_json(bytes, mapping)` / `parse_parquet(bytes, mapping)` - full parse with an explicit `CsvMapping`. There is no header auto-detection.
 - `stdf_test_names(bytes)` / `atdf_test_names(bytes)` - fast scan: test definitions + die count, no per-die accumulation.
 - `parse_stdf_filtered(bytes, selected)` / `parse_atdf_filtered(bytes, selected)` - full parse that accumulates values only for the selected test numbers.
-- `parquet_headers(bytes)` - schema, sample rows and per-column types, for a mapping UI. There is deliberately no `csv_headers`/`json_headers` in the WASM API: read a text header row in plain JS.
+- `parquet_headers(bytes)` - schema, sample rows (the first five, then the first row of up to twenty later row groups) and per-column types, for a mapping UI.
+- `parquet_distinct_count(bytes, columns, blankIsAValue)` - distinct combinations of the named columns, read as a projection. `blankIsAValue: false` skips rows blank in every named column (a wafer count); `true` counts them as a value (is this column constant?). There is deliberately no `csv_headers`/`json_headers` in the WASM API: read a text header row in plain JS.
 - `stdf_file_meta(bytes)` / `atdf_file_meta(bytes)` - lot metadata, wafer count, first/last timestamps and site count, without a full parse.
 
 ## Traps

package/package.json

@@ -2,7 +2,7 @@
   "name": "@wafertools/testdata-parser",
   "type": "module",
   "description": "Rust/WASM parsers for semiconductor test data formats (STDF, ATDF, CSV, JSON, Parquet)",
-  "version": "0.14.0",
+  "version": "0.15.0",
   "license": "MIT",
   "repository": {
     "type": "git",

package/testdata_parser.d.ts

@@ -240,7 +240,7 @@ export function init(): void;
 /**
  * `columns` is a JS string array. See `parquet_distinct_count_from_bytes`.
  */
-export function parquet_distinct_count(bytes: Uint8Array, columns: string[]): number;
+export function parquet_distinct_count(bytes: Uint8Array, columns: string[], blank_is_a_value: boolean): number;
 
 export function parquet_headers(bytes: Uint8Array): ParquetHeadersResult;
 
@@ -269,7 +269,7 @@ export interface InitOutput {
     readonly atdf_file_meta: (a: number, b: number) => [number, number, number];
     readonly atdf_test_names: (a: number, b: number) => [number, number, number];
     readonly init: () => void;
-    readonly parquet_distinct_count: (a: number, b: number, c: any) => [number, number, number];
+    readonly parquet_distinct_count: (a: number, b: number, c: any, d: number) => [number, number, number];
     readonly parquet_headers: (a: number, b: number) => [number, number, number];
     readonly parse_atdf: (a: number, b: number) => [number, number, number, number];
     readonly parse_atdf_filtered: (a: number, b: number, c: any) => [number, number, number, number];

package/testdata_parser.js

@@ -36,12 +36,13 @@ export function init() {
  * `columns` is a JS string array. See `parquet_distinct_count_from_bytes`.
  * @param {Uint8Array} bytes
  * @param {string[]} columns
+ * @param {boolean} blank_is_a_value
  * @returns {number}
  */
-export function parquet_distinct_count(bytes, columns) {
+export function parquet_distinct_count(bytes, columns, blank_is_a_value) {
     const ptr0 = passArray8ToWasm0(bytes, wasm.__wbindgen_malloc);
     const len0 = WASM_VECTOR_LEN;
-    const ret = wasm.parquet_distinct_count(ptr0, len0, columns);
+    const ret = wasm.parquet_distinct_count(ptr0, len0, columns, blank_is_a_value);
     if (ret[2]) {
         throw takeFromExternrefTable0(ret[1]);
     }