web-csv-toolbox 0.14.0-next-386eebeaafe5857e28c876345c14c9fe5f1a3774 → 0.14.0-next-978b88933762ecc27270ce746b80a3fa7ed8c4f7

package/README.md

@@ -407,7 +407,7 @@ catering to users who need more detailed and fine-tuned functionality.
 - **`function parseBlob(blob[, options])`**: [📑](https://kamiazya.github.io/web-csv-toolbox/functions/parseBlob-1.html)
   - Parse CSV data from `Blob` or `File` objects.
 - **`function parseFile(file[, options])`**: [📑](https://kamiazya.github.io/web-csv-toolbox/functions/parseFile-1.html)
-  - Alias for `parseBlob`, semantically clearer for `File` objects.
+  - Parse `File` objects with automatic filename tracking in error messages.
 - **`function parseStream(stream[, options])`**: [📑](https://kamiazya.github.io/web-csv-toolbox/functions/parseStream-1.html)
   - Stream-based parsing for larger or continuous data.
 - **`function parseStringStream(stream[, options])`**: [📑](https://kamiazya.github.io/web-csv-toolbox/functions/parseStringStream-1.html)
@@ -440,28 +440,21 @@ new CSVRecordAssemblerTransformer(options?, writableStrategy?, readableStrategy?
 **Default queuing strategies (starting points, not benchmarked):**
 ```typescript
 // CSVLexerTransformer defaults
-writableStrategy: {
-  highWaterMark: 65536,           // 64KB of characters
-  size: (chunk) => chunk.length,  // Count by string length
-  checkInterval: 100              // Check backpressure every 100 tokens
-}
-readableStrategy: {
-  highWaterMark: 1024,              // 1024 tokens
-  size: (tokens) => tokens.length,  // Count by number of tokens
-  checkInterval: 100                // Check backpressure every 100 tokens
-}
+new CSVLexerTransformer(
+  { backpressureCheckInterval: 100 },  // Check every 100 tokens
+  {
+    highWaterMark: 65536,              // 64KB of characters
+    size: (chunk) => chunk.length,     // Count by string length
+  },
+  new CountQueuingStrategy({ highWaterMark: 1024 })  // 1024 tokens
+)
 
 // CSVRecordAssemblerTransformer defaults
-writableStrategy: {
-  highWaterMark: 1024,              // 1024 tokens
-  size: (tokens) => tokens.length,  // Count by number of tokens
-  checkInterval: 10                 // Check backpressure every 10 records
-}
-readableStrategy: {
-  highWaterMark: 256,     // 256 records
-  size: () => 1,          // Each record counts as 1
-  checkInterval: 10       // Check backpressure every 10 records
-}
+new CSVRecordAssemblerTransformer(
+  { backpressureCheckInterval: 10 },  // Check every 10 records
+  new CountQueuingStrategy({ highWaterMark: 1024 }),  // 1024 tokens
+  new CountQueuingStrategy({ highWaterMark: 256 })    // 256 records
+)
 ```
 
 **Key Features:**
@@ -477,8 +470,8 @@ readableStrategy: {
 - Prevents blocking the main thread
 - Critical for browser UI responsiveness
 
-🔧 **Tunable Check Interval:**
-- `checkInterval`: How often to check for backpressure
+🔧 **Tunable Backpressure Check Interval:**
+- `backpressureCheckInterval` (in options): How often to check for backpressure (count-based)
 - Lower values (5-25): More responsive, slight overhead
 - Higher values (100-500): Less overhead, slower response
 - Customize based on downstream consumer speed
@@ -486,9 +479,9 @@ readableStrategy: {
 > ⚠️ **Important**: These defaults are theoretical starting points based on data flow characteristics, **not empirical benchmarks**. Optimal values vary by runtime (browser/Node.js/Deno), file size, memory constraints, and CPU performance. **Profile your specific use case** to find the best values.
 
 **When to customize:**
-- 🚀 **High-throughput servers**: Higher `highWaterMark` (128KB+, 2048+ tokens), higher `checkInterval` (200-500)
-- 📱 **Memory-constrained environments**: Lower `highWaterMark` (16KB, 256 tokens), lower `checkInterval` (10-25)
-- 🐌 **Slow consumers** (DB writes, API calls): Lower `highWaterMark`, lower `checkInterval` for responsive backpressure
+- 🚀 **High-throughput servers**: Higher `highWaterMark` (128KB+, 2048+ tokens), higher `backpressureCheckInterval` (200-500)
+- 📱 **Memory-constrained environments**: Lower `highWaterMark` (16KB, 256 tokens), lower `backpressureCheckInterval` (10-25)
+- 🐌 **Slow consumers** (DB writes, API calls): Lower `highWaterMark`, lower `backpressureCheckInterval` for responsive backpressure
 - 🏃 **Fast processing**: Higher values to reduce overhead
 
 **Example - High-throughput server:**
@@ -499,30 +492,17 @@ const response = await fetch('large-dataset.csv');
 await response.body
   .pipeThrough(new TextDecoderStream())
   .pipeThrough(new CSVLexerTransformer(
-    {},
+    { backpressureCheckInterval: 200 },  // Less frequent checks
     {
-      highWaterMark: 131072,          // 128KB
+      highWaterMark: 131072,             // 128KB
       size: (chunk) => chunk.length,
-      checkInterval: 200              // Less frequent checks
     },
-    {
-      highWaterMark: 2048,            // 2048 tokens
-      size: (tokens) => tokens.length,
-      checkInterval: 100
-    }
+    new CountQueuingStrategy({ highWaterMark: 2048 })  // 2048 tokens
   ))
   .pipeThrough(new CSVRecordAssemblerTransformer(
-    {},
-    {
-      highWaterMark: 2048,            // 2048 tokens
-      size: (tokens) => tokens.length,
-      checkInterval: 20
-    },
-    {
-      highWaterMark: 512,             // 512 records
-      size: () => 1,
-      checkInterval: 10
-    }
+    { backpressureCheckInterval: 20 },  // Less frequent checks
+    new CountQueuingStrategy({ highWaterMark: 2048 }),  // 2048 tokens
+    new CountQueuingStrategy({ highWaterMark: 512 })    // 512 records
   ))
   .pipeTo(yourRecordProcessor);
 ```
@@ -532,9 +512,9 @@ await response.body
 await csvStream
   .pipeThrough(new CSVLexerTransformer())  // Use defaults
   .pipeThrough(new CSVRecordAssemblerTransformer(
-    {},
-    { highWaterMark: 512, size: (t) => t.length, checkInterval: 5 },
-    { highWaterMark: 64, size: () => 1, checkInterval: 2 }  // Very responsive
+    { backpressureCheckInterval: 2 },  // Very responsive
+    new CountQueuingStrategy({ highWaterMark: 512 }),
+    new CountQueuingStrategy({ highWaterMark: 64 })
   ))
   .pipeTo(new WritableStream({
     async write(record) {

package/dist/CSVLexer.js

@@ -20,6 +20,7 @@ class CSVLexer {
   };
   #rowNumber = 1;
   #signal;
+  #source;
   /**
    * Constructs a new CSVLexer instance.
    * @param options - The common options for the lexer.
@@ -29,21 +30,21 @@ class CSVLexer {
       delimiter = DEFAULT_DELIMITER,
       quotation = DEFAULT_QUOTATION,
       maxBufferSize = DEFAULT_MAX_BUFFER_SIZE,
-      signal
+      signal,
+      source
     } = options;
     assertCommonOptions({ delimiter, quotation, maxBufferSize });
     this.#delimiter = delimiter;
     this.#quotation = quotation;
     this.#fieldDelimiterLength = delimiter.length;
     this.#maxBufferSize = maxBufferSize;
+    this.#source = source;
+    this.#signal = signal;
     const d = escapeRegExp(delimiter);
     const q = escapeRegExp(quotation);
     this.#matcher = new RegExp(
       `^(?:(?!${q})(?!${d})(?![\\r\\n]))([\\S\\s\\uFEFF\\xA0]+?)(?=${q}|${d}|\\r|\\n|$)`
     );
-    if (signal) {
-      this.#signal = signal;
-    }
   }
   /**
    * Lexes the given chunk of CSV data.
@@ -208,7 +209,9 @@ class CSVLexer {
       } while (cur !== void 0);
       if (this.#flush) {
         throw new ParseError("Unexpected EOF while parsing quoted field.", {
-          position: { ...this.#cursor }
+          position: { ...this.#cursor },
+          rowNumber: this.#rowNumber,
+          source: this.#source
         });
       }
       return null;

package/dist/CSVLexer.js.map

@@ -1 +1 @@
-{"version":3,"file":"CSVLexer.js","sources":["../src/CSVLexer.ts"],"sourcesContent":["import { assertCommonOptions } from \"./assertCommonOptions.ts\";\nimport { Field, FieldDelimiter, RecordDelimiter } from \"./common/constants.ts\";\nimport { ParseError } from \"./common/errors.ts\";\nimport type {\n  AbortSignalOptions,\n  CommonOptions,\n  Position,\n  RecordDelimiterToken,\n  Token,\n} from \"./common/types.ts\";\nimport { CRLF, DEFAULT_DELIMITER, DEFAULT_QUOTATION, LF } from \"./constants.ts\";\nimport { escapeRegExp } from \"./utils/escapeRegExp.ts\";\n\n/**\n * Default maximum buffer size in characters (UTF-16 code units).\n * Approximately 10MB for ASCII text, but may vary for non-ASCII characters.\n */\nexport const DEFAULT_MAX_BUFFER_SIZE = 10 * 1024 * 1024;\n\n/**\n * Options for the CSVLexer.lex method.\n */\nexport interface CSVLexerLexOptions {\n  /**\n   * If true, indicates that more chunks are expected.\n   * If false or omitted, flushes remaining data.\n   */\n  stream?: boolean;\n}\n\n/**\n * CSV Lexer.\n *\n * CSVLexer tokenizes CSV data into fields and records.\n */\nexport class CSVLexer<\n  Delimiter extends string = DEFAULT_DELIMITER,\n  Quotation extends string = DEFAULT_QUOTATION,\n> {\n  #delimiter: string;\n  #quotation: string;\n  #buffer = \"\";\n  #flush = false;\n  #matcher: RegExp;\n  #fieldDelimiterLength: number;\n  #maxBufferSize: number;\n\n  #cursor: Position = {\n    line: 1,\n    column: 1,\n    offset: 0,\n  };\n  #rowNumber = 1;\n\n  #signal?: AbortSignal;\n\n  /**\n   * Constructs a new CSVLexer instance.\n   * @param options - The common options for the lexer.\n   */\n  constructor(\n    options: CommonOptions<Delimiter, Quotation> & AbortSignalOptions = {},\n  ) {\n    const {\n      delimiter = DEFAULT_DELIMITER,\n      quotation = DEFAULT_QUOTATION,\n      maxBufferSize = DEFAULT_MAX_BUFFER_SIZE,\n      signal,\n    } = options;\n    assertCommonOptions({ delimiter, quotation, maxBufferSize });\n    this.#delimiter = delimiter;\n    this.#quotation = quotation;\n    this.#fieldDelimiterLength = delimiter.length;\n    this.#maxBufferSize = maxBufferSize;\n    const d = escapeRegExp(delimiter);\n    const q = escapeRegExp(quotation);\n    this.#matcher = new RegExp(\n      `^(?:(?!${q})(?!${d})(?![\\\\r\\\\n]))([\\\\S\\\\s\\\\uFEFF\\\\xA0]+?)(?=${q}|${d}|\\\\r|\\\\n|$)`,\n    );\n    if (signal) {\n      this.#signal = signal;\n    }\n  }\n\n  /**\n   * Lexes the given chunk of CSV data.\n   * @param chunk - The chunk of CSV data to be lexed. Omit to flush remaining data.\n   * @param options - Lexer options.\n   * @returns An iterable iterator of tokens.\n   */\n  public lex(\n    chunk?: string,\n    options?: CSVLexerLexOptions,\n  ): IterableIterator<Token> {\n    const stream = options?.stream ?? false;\n\n    if (!stream) {\n      this.#flush = true;\n    }\n    if (chunk !== undefined && chunk.length !== 0) {\n      this.#buffer += chunk;\n      this.#checkBufferSize();\n    }\n\n    return this.#tokens();\n  }\n\n  /**\n   * Generates tokens from the buffered CSV data.\n   * @yields Tokens from the buffered CSV data.\n   */\n  *#tokens(): Generator<Token> {\n    if (this.#flush) {\n      // Trim the last CRLF or LF\n      if (this.#buffer.endsWith(CRLF)) {\n        this.#buffer = this.#buffer.slice(0, -2 /* -CRLF.length */);\n      } else if (this.#buffer.endsWith(LF)) {\n        this.#buffer = this.#buffer.slice(0, -1 /* -LF.length */);\n      }\n    }\n    let token: Token | null;\n    while ((token = this.#nextToken())) {\n      yield token;\n    }\n  }\n\n  /**\n   * Checks if the buffer size exceeds the maximum allowed size.\n   * @throws {RangeError} If the buffer size exceeds the maximum.\n   */\n  #checkBufferSize(): void {\n    if (this.#buffer.length > this.#maxBufferSize) {\n      throw new RangeError(\n        `Buffer size (${this.#buffer.length} characters) exceeded maximum allowed size of ${this.#maxBufferSize} characters`,\n      );\n    }\n  }\n\n  /**\n   * Retrieves the next token from the buffered CSV data.\n   * @returns The next token or null if there are no more tokens.\n   */\n  #nextToken(): Token | null {\n    this.#signal?.throwIfAborted();\n    if (this.#buffer.length === 0) {\n      return null;\n    }\n    // Buffer is Record Delimiter, defer to the next iteration.\n    if (\n      this.#flush === false &&\n      (this.#buffer === CRLF || this.#buffer === LF)\n    ) {\n      return null;\n    }\n\n    // Check for CRLF\n    if (this.#buffer.startsWith(CRLF)) {\n      this.#buffer = this.#buffer.slice(2);\n      const start: Position = { ...this.#cursor };\n      this.#cursor.line++;\n      this.#cursor.column = 1;\n      this.#cursor.offset += 2; // CRLF.length\n      const token: RecordDelimiterToken = {\n        type: RecordDelimiter,\n        value: CRLF,\n        location: {\n          start,\n          end: { ...this.#cursor },\n          rowNumber: this.#rowNumber++,\n        },\n      };\n      return token;\n    }\n\n    // Check for LF\n    if (this.#buffer.startsWith(LF)) {\n      this.#buffer = this.#buffer.slice(1);\n      const start: Position = { ...this.#cursor };\n      this.#cursor.line++;\n      this.#cursor.column = 1;\n      this.#cursor.offset += 1; // LF.length\n      const token: RecordDelimiterToken = {\n        type: RecordDelimiter,\n        value: LF,\n        location: {\n          start,\n          end: { ...this.#cursor },\n          rowNumber: this.#rowNumber++,\n        },\n      };\n      return token;\n    }\n\n    // Check for Delimiter\n    if (this.#buffer.startsWith(this.#delimiter)) {\n      this.#buffer = this.#buffer.slice(1);\n      const start: Position = { ...this.#cursor };\n      this.#cursor.column += this.#fieldDelimiterLength;\n      this.#cursor.offset += this.#fieldDelimiterLength;\n      return {\n        type: FieldDelimiter,\n        value: this.#delimiter,\n        location: {\n          start,\n          end: { ...this.#cursor },\n          rowNumber: this.#rowNumber,\n        },\n      };\n    }\n\n    // Check for Quoted String\n    if (this.#buffer.startsWith(this.#quotation)) {\n      /**\n       * Extract Quoted field.\n       *\n       * The following code is equivalent to the following:\n       *\n       * If the next character is a quote:\n       * - If the character after that is a quote, then append a quote to the value and skip two characters.\n       * - Otherwise, return the quoted string.\n       * Otherwise, append the character to the value and skip one character.\n       *\n       * ```plaintext\n       * | `i`        | `i + 1`    | `i + 2`  |\n       * |------------|------------|----------|\n       * | cur        | next       |          | => Variable names\n       * | #quotation | #quotation |          | => Escaped quote\n       * | #quotation | (EOF)      |          | => Closing quote\n       * | #quotation | undefined  |          | => End of buffer\n       * | undefined  |            |          | => End of buffer\n       * ```\n       */\n      let value = \"\";\n      let offset = 1; // Skip the opening quote\n      let column = 2; // Skip the opening quote\n      let line = 0;\n\n      // Define variables\n      let cur: string = this.#buffer[offset];\n      let next: string | undefined = this.#buffer[offset + 1];\n      do {\n        // If the current character is a quote, check the next characters for closing quotes.\n        if (cur === this.#quotation) {\n          // If the cur character is a quote and the next character is a quote,\n          // then append a quote to the value and skip two characters.\n          if (next === this.#quotation) {\n            // Append a quote to the value and skip two characters.\n            value += this.#quotation;\n            offset += 2;\n            cur = this.#buffer[offset];\n            next = this.#buffer[offset + 1];\n\n            // Update the diff\n            column += 2;\n            continue;\n          }\n\n          // If the cur character is a quote and the next character is undefined,\n          // then return null.\n          if (next === undefined && this.#flush === false) {\n            return null;\n          }\n\n          // Otherwise, return the quoted string.\n          // Update the buffer and return the token\n          offset++;\n          this.#buffer = this.#buffer.slice(offset);\n          const start: Position = { ...this.#cursor };\n          this.#cursor.column += column;\n          this.#cursor.offset += offset;\n          this.#cursor.line += line;\n          return {\n            type: Field,\n            value,\n            location: {\n              start,\n              end: { ...this.#cursor },\n              rowNumber: this.#rowNumber,\n            },\n          };\n        }\n\n        // Append the character to the value.\n        value += cur;\n\n        // Prepare for the next iteration\n        if (cur === LF) {\n          // If the current character is a LF,\n          // then increment the line number and reset the column number.\n          line++;\n          column = 1;\n        } else {\n          // Otherwise, increment the column number and offset.\n          column++;\n        }\n\n        offset++;\n        cur = next;\n        next = this.#buffer[offset + 1];\n      } while (cur !== undefined);\n\n      if (this.#flush) {\n        throw new ParseError(\"Unexpected EOF while parsing quoted field.\", {\n          position: { ...this.#cursor },\n        });\n      }\n      return null;\n    }\n\n    // Check for Unquoted String\n    const match = this.#matcher.exec(this.#buffer);\n    if (match) {\n      // If we're flushing and the match doesn't consume the entire buffer,\n      // then return null\n      if (this.#flush === false && match[0].length === this.#buffer.length) {\n        return null;\n      }\n      const value = match[1];\n      this.#buffer = this.#buffer.slice(value.length);\n      const start: Position = { ...this.#cursor };\n      this.#cursor.column += value.length;\n      this.#cursor.offset += value.length;\n      return {\n        type: Field,\n        value,\n        location: {\n          start,\n          end: { ...this.#cursor },\n          rowNumber: this.#rowNumber,\n        },\n      };\n    }\n\n    // Otherwise, return null\n    return null;\n  }\n}\n"],"names":[],"mappings":";;;;;;AAiBO,MAAM,uBAAA,GAA0B,KAAK,IAAA,GAAO;AAkB5C,MAAM,QAAA,CAGX;AAAA,EACA,UAAA;AAAA,EACA,UAAA;AAAA,EACA,OAAA,GAAU,EAAA;AAAA,EACV,MAAA,GAAS,KAAA;AAAA,EACT,QAAA;AAAA,EACA,qBAAA;AAAA,EACA,cAAA;AAAA,EAEA,OAAA,GAAoB;AAAA,IAClB,IAAA,EAAM,CAAA;AAAA,IACN,MAAA,EAAQ,CAAA;AAAA,IACR,MAAA,EAAQ;AAAA,GACV;AAAA,EACA,UAAA,GAAa,CAAA;AAAA,EAEb,OAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,WAAA,CACE,OAAA,GAAoE,EAAC,EACrE;AACA,IAAA,MAAM;AAAA,MACJ,SAAA,GAAY,iBAAA;AAAA,MACZ,SAAA,GAAY,iBAAA;AAAA,MACZ,aAAA,GAAgB,uBAAA;AAAA,MAChB;AAAA,KACF,GAAI,OAAA;AACJ,IAAA,mBAAA,CAAoB,EAAE,SAAA,EAAW,SAAA,EAAW,aAAA,EAAe,CAAA;AAC3D,IAAA,IAAA,CAAK,UAAA,GAAa,SAAA;AAClB,IAAA,IAAA,CAAK,UAAA,GAAa,SAAA;AAClB,IAAA,IAAA,CAAK,wBAAwB,SAAA,CAAU,MAAA;AACvC,IAAA,IAAA,CAAK,cAAA,GAAiB,aAAA;AACtB,IAAA,MAAM,CAAA,GAAI,aAAa,SAAS,CAAA;AAChC,IAAA,MAAM,CAAA,GAAI,aAAa,SAAS,CAAA;AAChC,IAAA,IAAA,CAAK,WAAW,IAAI,MAAA;AAAA,MAClB,UAAU,CAAC,CAAA,IAAA,EAAO,CAAC,CAAA,yCAAA,EAA4C,CAAC,IAAI,CAAC,CAAA,WAAA;AAAA,KACvE;AACA,IAAA,IAAI,MAAA,EAAQ;AACV,MAAA,IAAA,CAAK,OAAA,GAAU,MAAA;AAAA,IACjB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQO,GAAA,CACL,OACA,OAAA,EACyB;AACzB,IAAA,MAAM,MAAA,GAAS,SAAS,MAAA,IAAU,KAAA;AAElC,IAAA,IAAI,CAAC,MAAA,EAAQ;AACX,MAAA,IAAA,CAAK,MAAA,GAAS,IAAA;AAAA,IAChB;AACA,IAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,CAAM,MAAA,KAAW,CAAA,EAAG;AAC7C,MAAA,IAAA,CAAK,OAAA,IAAW,KAAA;AAChB,MAAA,IAAA,CAAK,gBAAA,EAAiB;AAAA,IACxB;AAEA,IAAA,OAAO,KAAK,OAAA,EAAQ;AAAA,EACtB;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,CAAC,OAAA,GAA4B;AAC3B,IAAA,IAAI,KAAK,MAAA,EAAQ;AAEf,MAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,QAAA,CAAS,IAAI,CAAA,EAAG;AAC/B,QAAA,IAAA,CAAK,OAAA,GAAU,KAAK,OAAA,CAAQ,KAAA;AAAA,UAAM,CAAA;AAAA,UAAG;AAAA;AAAA,SAAqB;AAAA,MAC5D,CAAA,MAAA,IAAW,IAAA,CAAK,OAAA,CAAQ,QAAA,CAAS,EAAE,CAAA,EAAG;AACpC,QAAA,IAAA,CAAK,OAAA,GAAU,KAAK,OAAA,CAAQ,KAAA;AAAA,UAAM,CAAA;AAAA,UAAG;AAAA;AAAA,SAAmB;AAAA,MAC1D;AAAA,IACF;AACA,IAAA,IAAI,KAAA;AACJ,IAAA,OAAQ,KAAA,GAAQ,IAAA,CAAK,UAAA,EAAW,EAAI;AAClC,MAAA,MAAM,KAAA;AAAA,IACR;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,gBAAA,GAAyB;AACvB,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,MAAA,GAAS,IAAA,CAAK,cAAA,EAAgB;AAC7C,MAAA,MAAM,IAAI,UAAA;AAAA,QACR,gBAAgB,IAAA,CAAK,OAAA,CAAQ,MAAM,CAAA,8CAAA,EAAiD,KAAK,cAAc,CAAA,WAAA;AAAA,OACzG;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,UAAA,GAA2B;AACzB,IAAA,IAAA,CAAK,SAAS,cAAA,EAAe;AAC7B,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,MAAA,KAAW,CAAA,EAAG;AAC7B,MAAA,OAAO,IAAA;AAAA,IACT;AAEA,IAAA,IACE,IAAA,CAAK,WAAW,KAAA,KACf,IAAA,CAAK,YAAY,IAAA,IAAQ,IAAA,CAAK,YAAY,EAAA,CAAA,EAC3C;AACA,MAAA,OAAO,IAAA;AAAA,IACT;AAGA,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,UAAA,CAAW,IAAI,CAAA,EAAG;AACjC,MAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,CAAC,CAAA;AACnC,MAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,MAAA,IAAA,CAAK,OAAA,CAAQ,IAAA,EAAA;AACb,MAAA,IAAA,CAAK,QAAQ,MAAA,GAAS,CAAA;AACtB,MAAA,IAAA,CAAK,QAAQ,MAAA,IAAU,CAAA;AACvB,MAAA,MAAM,KAAA,GAA8B;AAAA,QAClC,IAAA,EAAM,eAAA;AAAA,QACN,KAAA,EAAO,IAAA;AAAA,QACP,QAAA,EAAU;AAAA,UACR,KAAA;AAAA,UACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UACvB,WAAW,IAAA,CAAK,UAAA;AAAA;AAClB,OACF;AACA,MAAA,OAAO,KAAA;AAAA,IACT;AAGA,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,UAAA,CAAW,EAAE,CAAA,EAAG;AAC/B,MAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,CAAC,CAAA;AACnC,MAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,MAAA,IAAA,CAAK,OAAA,CAAQ,IAAA,EAAA;AACb,MAAA,IAAA,CAAK,QAAQ,MAAA,GAAS,CAAA;AACtB,MAAA,IAAA,CAAK,QAAQ,MAAA,IAAU,CAAA;AACvB,MAAA,MAAM,KAAA,GAA8B;AAAA,QAClC,IAAA,EAAM,eAAA;AAAA,QACN,KAAA,EAAO,EAAA;AAAA,QACP,QAAA,EAAU;AAAA,UACR,KAAA;AAAA,UACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UACvB,WAAW,IAAA,CAAK,UAAA;AAAA;AAClB,OACF;AACA,MAAA,OAAO,KAAA;AAAA,IACT;AAGA,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,UAAA,CAAW,IAAA,CAAK,UAAU,CAAA,EAAG;AAC5C,MAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,CAAC,CAAA;AACnC,MAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,MAAA,IAAA,CAAK,OAAA,CAAQ,UAAU,IAAA,CAAK,qBAAA;AAC5B,MAAA,IAAA,CAAK,OAAA,CAAQ,UAAU,IAAA,CAAK,qBAAA;AAC5B,MAAA,OAAO;AAAA,QACL,IAAA,EAAM,cAAA;AAAA,QACN,OAAO,IAAA,CAAK,UAAA;AAAA,QACZ,QAAA,EAAU;AAAA,UACR,KAAA;AAAA,UACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UACvB,WAAW,IAAA,CAAK;AAAA;AAClB,OACF;AAAA,IACF;AAGA,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,UAAA,CAAW,IAAA,CAAK,UAAU,CAAA,EAAG;AAqB5C,MAAA,IAAI,KAAA,GAAQ,EAAA;AACZ,MAAA,IAAI,MAAA,GAAS,CAAA;AACb,MAAA,IAAI,MAAA,GAAS,CAAA;AACb,MAAA,IAAI,IAAA,GAAO,CAAA;AAGX,MAAA,IAAI,GAAA,GAAc,IAAA,CAAK,OAAA,CAAQ,MAAM,CAAA;AACrC,MAAA,IAAI,IAAA,GAA2B,IAAA,CAAK,OAAA,CAAQ,MAAA,GAAS,CAAC,CAAA;AACtD,MAAA,GAAG;AAED,QAAA,IAAI,GAAA,KAAQ,KAAK,UAAA,EAAY;AAG3B,UAAA,IAAI,IAAA,KAAS,KAAK,UAAA,EAAY;AAE5B,YAAA,KAAA,IAAS,IAAA,CAAK,UAAA;AACd,YAAA,MAAA,IAAU,CAAA;AACV,YAAA,GAAA,GAAM,IAAA,CAAK,QAAQ,MAAM,CAAA;AACzB,YAAA,IAAA,GAAO,IAAA,CAAK,OAAA,CAAQ,MAAA,GAAS,CAAC,CAAA;AAG9B,YAAA,MAAA,IAAU,CAAA;AACV,YAAA;AAAA,UACF;AAIA,UAAA,IAAI,IAAA,KAAS,MAAA,IAAa,IAAA,CAAK,MAAA,KAAW,KAAA,EAAO;AAC/C,YAAA,OAAO,IAAA;AAAA,UACT;AAIA,UAAA,MAAA,EAAA;AACA,UAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,MAAM,CAAA;AACxC,UAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,UAAA,IAAA,CAAK,QAAQ,MAAA,IAAU,MAAA;AACvB,UAAA,IAAA,CAAK,QAAQ,MAAA,IAAU,MAAA;AACvB,UAAA,IAAA,CAAK,QAAQ,IAAA,IAAQ,IAAA;AACrB,UAAA,OAAO;AAAA,YACL,IAAA,EAAM,KAAA;AAAA,YACN,KAAA;AAAA,YACA,QAAA,EAAU;AAAA,cACR,KAAA;AAAA,cACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,cACvB,WAAW,IAAA,CAAK;AAAA;AAClB,WACF;AAAA,QACF;AAGA,QAAA,KAAA,IAAS,GAAA;AAGT,QAAA,IAAI,QAAQ,EAAA,EAAI;AAGd,UAAA,IAAA,EAAA;AACA,UAAA,MAAA,GAAS,CAAA;AAAA,QACX,CAAA,MAAO;AAEL,UAAA,MAAA,EAAA;AAAA,QACF;AAEA,QAAA,MAAA,EAAA;AACA,QAAA,GAAA,GAAM,IAAA;AACN,QAAA,IAAA,GAAO,IAAA,CAAK,OAAA,CAAQ,MAAA,GAAS,CAAC,CAAA;AAAA,MAChC,SAAS,GAAA,KAAQ,MAAA;AAEjB,MAAA,IAAI,KAAK,MAAA,EAAQ;AACf,QAAA,MAAM,IAAI,WAAW,4CAAA,EAA8C;AAAA,UACjE,QAAA,EAAU,EAAE,GAAG,IAAA,CAAK,OAAA;AAAQ,SAC7B,CAAA;AAAA,MACH;AACA,MAAA,OAAO,IAAA;AAAA,IACT;AAGA,IAAA,MAAM,KAAA,GAAQ,IAAA,CAAK,QAAA,CAAS,IAAA,CAAK,KAAK,OAAO,CAAA;AAC7C,IAAA,IAAI,KAAA,EAAO;AAGT,MAAA,IAAI,IAAA,CAAK,WAAW,KAAA,IAAS,KAAA,CAAM,CAAC,CAAA,CAAE,MAAA,KAAW,IAAA,CAAK,OAAA,CAAQ,MAAA,EAAQ;AACpE,QAAA,OAAO,IAAA;AAAA,MACT;AACA,MAAA,MAAM,KAAA,GAAQ,MAAM,CAAC,CAAA;AACrB,MAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,MAAM,MAAM,CAAA;AAC9C,MAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,MAAA,IAAA,CAAK,OAAA,CAAQ,UAAU,KAAA,CAAM,MAAA;AAC7B,MAAA,IAAA,CAAK,OAAA,CAAQ,UAAU,KAAA,CAAM,MAAA;AAC7B,MAAA,OAAO;AAAA,QACL,IAAA,EAAM,KAAA;AAAA,QACN,KAAA;AAAA,QACA,QAAA,EAAU;AAAA,UACR,KAAA;AAAA,UACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UACvB,WAAW,IAAA,CAAK;AAAA;AAClB,OACF;AAAA,IACF;AAGA,IAAA,OAAO,IAAA;AAAA,EACT;AACF;;;;"}
+{"version":3,"file":"CSVLexer.js","sources":["../src/CSVLexer.ts"],"sourcesContent":["import { assertCommonOptions } from \"./assertCommonOptions.ts\";\nimport { Field, FieldDelimiter, RecordDelimiter } from \"./common/constants.ts\";\nimport { ParseError } from \"./common/errors.ts\";\nimport type {\n  AbortSignalOptions,\n  CommonOptions,\n  Position,\n  RecordDelimiterToken,\n  Token,\n} from \"./common/types.ts\";\nimport { CRLF, DEFAULT_DELIMITER, DEFAULT_QUOTATION, LF } from \"./constants.ts\";\nimport { escapeRegExp } from \"./utils/escapeRegExp.ts\";\n\n/**\n * Default maximum buffer size in characters (UTF-16 code units).\n * Approximately 10MB for ASCII text, but may vary for non-ASCII characters.\n */\nexport const DEFAULT_MAX_BUFFER_SIZE = 10 * 1024 * 1024;\n\n/**\n * Options for the CSVLexer.lex method.\n */\nexport interface CSVLexerLexOptions {\n  /**\n   * If true, indicates that more chunks are expected.\n   * If false or omitted, flushes remaining data.\n   */\n  stream?: boolean;\n}\n\n/**\n * CSV Lexer.\n *\n * CSVLexer tokenizes CSV data into fields and records.\n */\nexport class CSVLexer<\n  Delimiter extends string = DEFAULT_DELIMITER,\n  Quotation extends string = DEFAULT_QUOTATION,\n> {\n  #delimiter: string;\n  #quotation: string;\n  #buffer = \"\";\n  #flush = false;\n  #matcher: RegExp;\n  #fieldDelimiterLength: number;\n  #maxBufferSize: number;\n\n  #cursor: Position = {\n    line: 1,\n    column: 1,\n    offset: 0,\n  };\n  #rowNumber = 1;\n\n  #signal?: AbortSignal;\n  #source?: string;\n\n  /**\n   * Constructs a new CSVLexer instance.\n   * @param options - The common options for the lexer.\n   */\n  constructor(\n    options: CommonOptions<Delimiter, Quotation> & AbortSignalOptions = {},\n  ) {\n    const {\n      delimiter = DEFAULT_DELIMITER,\n      quotation = DEFAULT_QUOTATION,\n      maxBufferSize = DEFAULT_MAX_BUFFER_SIZE,\n      signal,\n      source,\n    } = options;\n    assertCommonOptions({ delimiter, quotation, maxBufferSize });\n    this.#delimiter = delimiter;\n    this.#quotation = quotation;\n    this.#fieldDelimiterLength = delimiter.length;\n    this.#maxBufferSize = maxBufferSize;\n    this.#source = source;\n    this.#signal = signal;\n    const d = escapeRegExp(delimiter);\n    const q = escapeRegExp(quotation);\n    this.#matcher = new RegExp(\n      `^(?:(?!${q})(?!${d})(?![\\\\r\\\\n]))([\\\\S\\\\s\\\\uFEFF\\\\xA0]+?)(?=${q}|${d}|\\\\r|\\\\n|$)`,\n    );\n  }\n\n  /**\n   * Lexes the given chunk of CSV data.\n   * @param chunk - The chunk of CSV data to be lexed. Omit to flush remaining data.\n   * @param options - Lexer options.\n   * @returns An iterable iterator of tokens.\n   */\n  public lex(\n    chunk?: string,\n    options?: CSVLexerLexOptions,\n  ): IterableIterator<Token> {\n    const stream = options?.stream ?? false;\n\n    if (!stream) {\n      this.#flush = true;\n    }\n    if (chunk !== undefined && chunk.length !== 0) {\n      this.#buffer += chunk;\n      this.#checkBufferSize();\n    }\n\n    return this.#tokens();\n  }\n\n  /**\n   * Generates tokens from the buffered CSV data.\n   * @yields Tokens from the buffered CSV data.\n   */\n  *#tokens(): Generator<Token> {\n    if (this.#flush) {\n      // Trim the last CRLF or LF\n      if (this.#buffer.endsWith(CRLF)) {\n        this.#buffer = this.#buffer.slice(0, -2 /* -CRLF.length */);\n      } else if (this.#buffer.endsWith(LF)) {\n        this.#buffer = this.#buffer.slice(0, -1 /* -LF.length */);\n      }\n    }\n    let token: Token | null;\n    while ((token = this.#nextToken())) {\n      yield token;\n    }\n  }\n\n  /**\n   * Checks if the buffer size exceeds the maximum allowed size.\n   * @throws {RangeError} If the buffer size exceeds the maximum.\n   */\n  #checkBufferSize(): void {\n    if (this.#buffer.length > this.#maxBufferSize) {\n      throw new RangeError(\n        `Buffer size (${this.#buffer.length} characters) exceeded maximum allowed size of ${this.#maxBufferSize} characters`,\n      );\n    }\n  }\n\n  /**\n   * Retrieves the next token from the buffered CSV data.\n   * @returns The next token or null if there are no more tokens.\n   */\n  #nextToken(): Token | null {\n    this.#signal?.throwIfAborted();\n    if (this.#buffer.length === 0) {\n      return null;\n    }\n    // Buffer is Record Delimiter, defer to the next iteration.\n    if (\n      this.#flush === false &&\n      (this.#buffer === CRLF || this.#buffer === LF)\n    ) {\n      return null;\n    }\n\n    // Check for CRLF\n    if (this.#buffer.startsWith(CRLF)) {\n      this.#buffer = this.#buffer.slice(2);\n      const start: Position = { ...this.#cursor };\n      this.#cursor.line++;\n      this.#cursor.column = 1;\n      this.#cursor.offset += 2; // CRLF.length\n      const token: RecordDelimiterToken = {\n        type: RecordDelimiter,\n        value: CRLF,\n        location: {\n          start,\n          end: { ...this.#cursor },\n          rowNumber: this.#rowNumber++,\n        },\n      };\n      return token;\n    }\n\n    // Check for LF\n    if (this.#buffer.startsWith(LF)) {\n      this.#buffer = this.#buffer.slice(1);\n      const start: Position = { ...this.#cursor };\n      this.#cursor.line++;\n      this.#cursor.column = 1;\n      this.#cursor.offset += 1; // LF.length\n      const token: RecordDelimiterToken = {\n        type: RecordDelimiter,\n        value: LF,\n        location: {\n          start,\n          end: { ...this.#cursor },\n          rowNumber: this.#rowNumber++,\n        },\n      };\n      return token;\n    }\n\n    // Check for Delimiter\n    if (this.#buffer.startsWith(this.#delimiter)) {\n      this.#buffer = this.#buffer.slice(1);\n      const start: Position = { ...this.#cursor };\n      this.#cursor.column += this.#fieldDelimiterLength;\n      this.#cursor.offset += this.#fieldDelimiterLength;\n      return {\n        type: FieldDelimiter,\n        value: this.#delimiter,\n        location: {\n          start,\n          end: { ...this.#cursor },\n          rowNumber: this.#rowNumber,\n        },\n      };\n    }\n\n    // Check for Quoted String\n    if (this.#buffer.startsWith(this.#quotation)) {\n      /**\n       * Extract Quoted field.\n       *\n       * The following code is equivalent to the following:\n       *\n       * If the next character is a quote:\n       * - If the character after that is a quote, then append a quote to the value and skip two characters.\n       * - Otherwise, return the quoted string.\n       * Otherwise, append the character to the value and skip one character.\n       *\n       * ```plaintext\n       * | `i`        | `i + 1`    | `i + 2`  |\n       * |------------|------------|----------|\n       * | cur        | next       |          | => Variable names\n       * | #quotation | #quotation |          | => Escaped quote\n       * | #quotation | (EOF)      |          | => Closing quote\n       * | #quotation | undefined  |          | => End of buffer\n       * | undefined  |            |          | => End of buffer\n       * ```\n       */\n      let value = \"\";\n      let offset = 1; // Skip the opening quote\n      let column = 2; // Skip the opening quote\n      let line = 0;\n\n      // Define variables\n      let cur: string = this.#buffer[offset];\n      let next: string | undefined = this.#buffer[offset + 1];\n      do {\n        // If the current character is a quote, check the next characters for closing quotes.\n        if (cur === this.#quotation) {\n          // If the cur character is a quote and the next character is a quote,\n          // then append a quote to the value and skip two characters.\n          if (next === this.#quotation) {\n            // Append a quote to the value and skip two characters.\n            value += this.#quotation;\n            offset += 2;\n            cur = this.#buffer[offset];\n            next = this.#buffer[offset + 1];\n\n            // Update the diff\n            column += 2;\n            continue;\n          }\n\n          // If the cur character is a quote and the next character is undefined,\n          // then return null.\n          if (next === undefined && this.#flush === false) {\n            return null;\n          }\n\n          // Otherwise, return the quoted string.\n          // Update the buffer and return the token\n          offset++;\n          this.#buffer = this.#buffer.slice(offset);\n          const start: Position = { ...this.#cursor };\n          this.#cursor.column += column;\n          this.#cursor.offset += offset;\n          this.#cursor.line += line;\n          return {\n            type: Field,\n            value,\n            location: {\n              start,\n              end: { ...this.#cursor },\n              rowNumber: this.#rowNumber,\n            },\n          };\n        }\n\n        // Append the character to the value.\n        value += cur;\n\n        // Prepare for the next iteration\n        if (cur === LF) {\n          // If the current character is a LF,\n          // then increment the line number and reset the column number.\n          line++;\n          column = 1;\n        } else {\n          // Otherwise, increment the column number and offset.\n          column++;\n        }\n\n        offset++;\n        cur = next;\n        next = this.#buffer[offset + 1];\n      } while (cur !== undefined);\n\n      if (this.#flush) {\n        throw new ParseError(\"Unexpected EOF while parsing quoted field.\", {\n          position: { ...this.#cursor },\n          rowNumber: this.#rowNumber,\n          source: this.#source,\n        });\n      }\n      return null;\n    }\n\n    // Check for Unquoted String\n    const match = this.#matcher.exec(this.#buffer);\n    if (match) {\n      // If we're flushing and the match doesn't consume the entire buffer,\n      // then return null\n      if (this.#flush === false && match[0].length === this.#buffer.length) {\n        return null;\n      }\n      const value = match[1];\n      this.#buffer = this.#buffer.slice(value.length);\n      const start: Position = { ...this.#cursor };\n      this.#cursor.column += value.length;\n      this.#cursor.offset += value.length;\n      return {\n        type: Field,\n        value,\n        location: {\n          start,\n          end: { ...this.#cursor },\n          rowNumber: this.#rowNumber,\n        },\n      };\n    }\n\n    // Otherwise, return null\n    return null;\n  }\n}\n"],"names":[],"mappings":";;;;;;AAiBO,MAAM,uBAAA,GAA0B,KAAK,IAAA,GAAO;AAkB5C,MAAM,QAAA,CAGX;AAAA,EACA,UAAA;AAAA,EACA,UAAA;AAAA,EACA,OAAA,GAAU,EAAA;AAAA,EACV,MAAA,GAAS,KAAA;AAAA,EACT,QAAA;AAAA,EACA,qBAAA;AAAA,EACA,cAAA;AAAA,EAEA,OAAA,GAAoB;AAAA,IAClB,IAAA,EAAM,CAAA;AAAA,IACN,MAAA,EAAQ,CAAA;AAAA,IACR,MAAA,EAAQ;AAAA,GACV;AAAA,EACA,UAAA,GAAa,CAAA;AAAA,EAEb,OAAA;AAAA,EACA,OAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,WAAA,CACE,OAAA,GAAoE,EAAC,EACrE;AACA,IAAA,MAAM;AAAA,MACJ,SAAA,GAAY,iBAAA;AAAA,MACZ,SAAA,GAAY,iBAAA;AAAA,MACZ,aAAA,GAAgB,uBAAA;AAAA,MAChB,MAAA;AAAA,MACA;AAAA,KACF,GAAI,OAAA;AACJ,IAAA,mBAAA,CAAoB,EAAE,SAAA,EAAW,SAAA,EAAW,aAAA,EAAe,CAAA;AAC3D,IAAA,IAAA,CAAK,UAAA,GAAa,SAAA;AAClB,IAAA,IAAA,CAAK,UAAA,GAAa,SAAA;AAClB,IAAA,IAAA,CAAK,wBAAwB,SAAA,CAAU,MAAA;AACvC,IAAA,IAAA,CAAK,cAAA,GAAiB,aAAA;AACtB,IAAA,IAAA,CAAK,OAAA,GAAU,MAAA;AACf,IAAA,IAAA,CAAK,OAAA,GAAU,MAAA;AACf,IAAA,MAAM,CAAA,GAAI,aAAa,SAAS,CAAA;AAChC,IAAA,MAAM,CAAA,GAAI,aAAa,SAAS,CAAA;AAChC,IAAA,IAAA,CAAK,WAAW,IAAI,MAAA;AAAA,MAClB,UAAU,CAAC,CAAA,IAAA,EAAO,CAAC,CAAA,yCAAA,EAA4C,CAAC,IAAI,CAAC,CAAA,WAAA;AAAA,KACvE;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQO,GAAA,CACL,OACA,OAAA,EACyB;AACzB,IAAA,MAAM,MAAA,GAAS,SAAS,MAAA,IAAU,KAAA;AAElC,IAAA,IAAI,CAAC,MAAA,EAAQ;AACX,MAAA,IAAA,CAAK,MAAA,GAAS,IAAA;AAAA,IAChB;AACA,IAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,CAAM,MAAA,KAAW,CAAA,EAAG;AAC7C,MAAA,IAAA,CAAK,OAAA,IAAW,KAAA;AAChB,MAAA,IAAA,CAAK,gBAAA,EAAiB;AAAA,IACxB;AAEA,IAAA,OAAO,KAAK,OAAA,EAAQ;AAAA,EACtB;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,CAAC,OAAA,GAA4B;AAC3B,IAAA,IAAI,KAAK,MAAA,EAAQ;AAEf,MAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,QAAA,CAAS,IAAI,CAAA,EAAG;AAC/B,QAAA,IAAA,CAAK,OAAA,GAAU,KAAK,OAAA,CAAQ,KAAA;AAAA,UAAM,CAAA;AAAA,UAAG;AAAA;AAAA,SAAqB;AAAA,MAC5D,CAAA,MAAA,IAAW,IAAA,CAAK,OAAA,CAAQ,QAAA,CAAS,EAAE,CAAA,EAAG;AACpC,QAAA,IAAA,CAAK,OAAA,GAAU,KAAK,OAAA,CAAQ,KAAA;AAAA,UAAM,CAAA;AAAA,UAAG;AAAA;AAAA,SAAmB;AAAA,MAC1D;AAAA,IACF;AACA,IAAA,IAAI,KAAA;AACJ,IAAA,OAAQ,KAAA,GAAQ,IAAA,CAAK,UAAA,EAAW,EAAI;AAClC,MAAA,MAAM,KAAA;AAAA,IACR;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,gBAAA,GAAyB;AACvB,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,MAAA,GAAS,IAAA,CAAK,cAAA,EAAgB;AAC7C,MAAA,MAAM,IAAI,UAAA;AAAA,QACR,gBAAgB,IAAA,CAAK,OAAA,CAAQ,MAAM,CAAA,8CAAA,EAAiD,KAAK,cAAc,CAAA,WAAA;AAAA,OACzG;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,UAAA,GAA2B;AACzB,IAAA,IAAA,CAAK,SAAS,cAAA,EAAe;AAC7B,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,MAAA,KAAW,CAAA,EAAG;AAC7B,MAAA,OAAO,IAAA;AAAA,IACT;AAEA,IAAA,IACE,IAAA,CAAK,WAAW,KAAA,KACf,IAAA,CAAK,YAAY,IAAA,IAAQ,IAAA,CAAK,YAAY,EAAA,CAAA,EAC3C;AACA,MAAA,OAAO,IAAA;AAAA,IACT;AAGA,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,UAAA,CAAW,IAAI,CAAA,EAAG;AACjC,MAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,CAAC,CAAA;AACnC,MAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,MAAA,IAAA,CAAK,OAAA,CAAQ,IAAA,EAAA;AACb,MAAA,IAAA,CAAK,QAAQ,MAAA,GAAS,CAAA;AACtB,MAAA,IAAA,CAAK,QAAQ,MAAA,IAAU,CAAA;AACvB,MAAA,MAAM,KAAA,GAA8B;AAAA,QAClC,IAAA,EAAM,eAAA;AAAA,QACN,KAAA,EAAO,IAAA;AAAA,QACP,QAAA,EAAU;AAAA,UACR,KAAA;AAAA,UACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UACvB,WAAW,IAAA,CAAK,UAAA;AAAA;AAClB,OACF;AACA,MAAA,OAAO,KAAA;AAAA,IACT;AAGA,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,UAAA,CAAW,EAAE,CAAA,EAAG;AAC/B,MAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,CAAC,CAAA;AACnC,MAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,MAAA,IAAA,CAAK,OAAA,CAAQ,IAAA,EAAA;AACb,MAAA,IAAA,CAAK,QAAQ,MAAA,GAAS,CAAA;AACtB,MAAA,IAAA,CAAK,QAAQ,MAAA,IAAU,CAAA;AACvB,MAAA,MAAM,KAAA,GAA8B;AAAA,QAClC,IAAA,EAAM,eAAA;AAAA,QACN,KAAA,EAAO,EAAA;AAAA,QACP,QAAA,EAAU;AAAA,UACR,KAAA;AAAA,UACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UACvB,WAAW,IAAA,CAAK,UAAA;AAAA;AAClB,OACF;AACA,MAAA,OAAO,KAAA;AAAA,IACT;AAGA,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,UAAA,CAAW,IAAA,CAAK,UAAU,CAAA,EAAG;AAC5C,MAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,CAAC,CAAA;AACnC,MAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,MAAA,IAAA,CAAK,OAAA,CAAQ,UAAU,IAAA,CAAK,qBAAA;AAC5B,MAAA,IAAA,CAAK,OAAA,CAAQ,UAAU,IAAA,CAAK,qBAAA;AAC5B,MAAA,OAAO;AAAA,QACL,IAAA,EAAM,cAAA;AAAA,QACN,OAAO,IAAA,CAAK,UAAA;AAAA,QACZ,QAAA,EAAU;AAAA,UACR,KAAA;AAAA,UACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UACvB,WAAW,IAAA,CAAK;AAAA;AAClB,OACF;AAAA,IACF;AAGA,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,UAAA,CAAW,IAAA,CAAK,UAAU,CAAA,EAAG;AAqB5C,MAAA,IAAI,KAAA,GAAQ,EAAA;AACZ,MAAA,IAAI,MAAA,GAAS,CAAA;AACb,MAAA,IAAI,MAAA,GAAS,CAAA;AACb,MAAA,IAAI,IAAA,GAAO,CAAA;AAGX,MAAA,IAAI,GAAA,GAAc,IAAA,CAAK,OAAA,CAAQ,MAAM,CAAA;AACrC,MAAA,IAAI,IAAA,GAA2B,IAAA,CAAK,OAAA,CAAQ,MAAA,GAAS,CAAC,CAAA;AACtD,MAAA,GAAG;AAED,QAAA,IAAI,GAAA,KAAQ,KAAK,UAAA,EAAY;AAG3B,UAAA,IAAI,IAAA,KAAS,KAAK,UAAA,EAAY;AAE5B,YAAA,KAAA,IAAS,IAAA,CAAK,UAAA;AACd,YAAA,MAAA,IAAU,CAAA;AACV,YAAA,GAAA,GAAM,IAAA,CAAK,QAAQ,MAAM,CAAA;AACzB,YAAA,IAAA,GAAO,IAAA,CAAK,OAAA,CAAQ,MAAA,GAAS,CAAC,CAAA;AAG9B,YAAA,MAAA,IAAU,CAAA;AACV,YAAA;AAAA,UACF;AAIA,UAAA,IAAI,IAAA,KAAS,MAAA,IAAa,IAAA,CAAK,MAAA,KAAW,KAAA,EAAO;AAC/C,YAAA,OAAO,IAAA;AAAA,UACT;AAIA,UAAA,MAAA,EAAA;AACA,UAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,MAAM,CAAA;AACxC,UAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,UAAA,IAAA,CAAK,QAAQ,MAAA,IAAU,MAAA;AACvB,UAAA,IAAA,CAAK,QAAQ,MAAA,IAAU,MAAA;AACvB,UAAA,IAAA,CAAK,QAAQ,IAAA,IAAQ,IAAA;AACrB,UAAA,OAAO;AAAA,YACL,IAAA,EAAM,KAAA;AAAA,YACN,KAAA;AAAA,YACA,QAAA,EAAU;AAAA,cACR,KAAA;AAAA,cACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,cACvB,WAAW,IAAA,CAAK;AAAA;AAClB,WACF;AAAA,QACF;AAGA,QAAA,KAAA,IAAS,GAAA;AAGT,QAAA,IAAI,QAAQ,EAAA,EAAI;AAGd,UAAA,IAAA,EAAA;AACA,UAAA,MAAA,GAAS,CAAA;AAAA,QACX,CAAA,MAAO;AAEL,UAAA,MAAA,EAAA;AAAA,QACF;AAEA,QAAA,MAAA,EAAA;AACA,QAAA,GAAA,GAAM,IAAA;AACN,QAAA,IAAA,GAAO,IAAA,CAAK,OAAA,CAAQ,MAAA,GAAS,CAAC,CAAA;AAAA,MAChC,SAAS,GAAA,KAAQ,MAAA;AAEjB,MAAA,IAAI,KAAK,MAAA,EAAQ;AACf,QAAA,MAAM,IAAI,WAAW,4CAAA,EAA8C;AAAA,UACjE,QAAA,EAAU,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UAC5B,WAAW,IAAA,CAAK,UAAA;AAAA,UAChB,QAAQ,IAAA,CAAK;AAAA,SACd,CAAA;AAAA,MACH;AACA,MAAA,OAAO,IAAA;AAAA,IACT;AAGA,IAAA,MAAM,KAAA,GAAQ,IAAA,CAAK,QAAA,CAAS,IAAA,CAAK,KAAK,OAAO,CAAA;AAC7C,IAAA,IAAI,KAAA,EAAO;AAGT,MAAA,IAAI,IAAA,CAAK,WAAW,KAAA,IAAS,KAAA,CAAM,CAAC,CAAA,CAAE,MAAA,KAAW,IAAA,CAAK,OAAA,CAAQ,MAAA,EAAQ;AACpE,QAAA,OAAO,IAAA;AAAA,MACT;AACA,MAAA,MAAM,KAAA,GAAQ,MAAM,CAAC,CAAA;AACrB,MAAA,IAAA,CAAK,OAAA,GAAU,IAAA,CAAK,OAAA,CAAQ,KAAA,CAAM,MAAM,MAAM,CAAA;AAC9C,MAAA,MAAM,KAAA,GAAkB,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAC1C,MAAA,IAAA,CAAK,OAAA,CAAQ,UAAU,KAAA,CAAM,MAAA;AAC7B,MAAA,IAAA,CAAK,OAAA,CAAQ,UAAU,KAAA,CAAM,MAAA;AAC7B,MAAA,OAAO;AAAA,QACL,IAAA,EAAM,KAAA;AAAA,QACN,KAAA;AAAA,QACA,QAAA,EAAU;AAAA,UACR,KAAA;AAAA,UACA,GAAA,EAAK,EAAE,GAAG,IAAA,CAAK,OAAA,EAAQ;AAAA,UACvB,WAAW,IAAA,CAAK;AAAA;AAClB,OACF;AAAA,IACF;AAGA,IAAA,OAAO,IAAA;AAAA,EACT;AACF;;;;"}

package/dist/CSVLexerTransformer.d.ts

@@ -1,14 +1,14 @@
 import { CSVLexer } from './CSVLexer.ts';
-import { CSVLexerTransformerOptions, ExtendedQueuingStrategy, Token } from './common/types.ts';
+import { CSVLexerTransformerOptions, Token } from './common/types.ts';
 import { DEFAULT_DELIMITER, DEFAULT_QUOTATION } from './constants.ts';
 /**
  * A transform stream that converts a stream of strings into a stream of tokens.
  *
  * @category Low-level API
  *
- * @param options - CSV-specific options (delimiter, quotation, etc.)
- * @param writableStrategy - Strategy for the writable side (default: `{ highWaterMark: 65536, size: chunk => chunk.length, checkInterval: 100 }`)
- * @param readableStrategy - Strategy for the readable side (default: `{ highWaterMark: 1024, size: () => 1, checkInterval: 100 }`)
+ * @param options - CSV-specific options (delimiter, quotation, checkInterval, etc.)
+ * @param writableStrategy - Strategy for the writable side (default: `{ highWaterMark: 65536, size: chunk => chunk.length }`)
+ * @param readableStrategy - Strategy for the readable side (default: `{ highWaterMark: 1024, size: () => 1 }`)
  *
  * @remarks
  * Follows the Web Streams API pattern where queuing strategies are passed as
@@ -52,17 +52,15 @@ import { DEFAULT_DELIMITER, DEFAULT_QUOTATION } from './constants.ts';
  * @example Custom queuing strategies with backpressure tuning
  * ```ts
  * const transformer = new CSVLexerTransformer(
- *   { delimiter: ',' },
+ *   {
+ *     delimiter: ',',
+ *     backpressureCheckInterval: 50  // Check backpressure every 50 tokens
+ *   },
  *   {
  *     highWaterMark: 131072,         // 128KB of characters
  *     size: (chunk) => chunk.length, // Count by character length
- *     checkInterval: 200             // Check backpressure every 200 tokens
  *   },
- *   {
- *     highWaterMark: 2048,           // 2048 tokens
- *     size: () => 1,                 // Each token counts as 1
- *     checkInterval: 50              // Check backpressure every 50 tokens
- *   }
+ *   new CountQueuingStrategy({ highWaterMark: 2048 })  // 2048 tokens
  * );
  *
  * await fetch('large-file.csv')
@@ -80,5 +78,5 @@ export declare class CSVLexerTransformer<Delimiter extends string = DEFAULT_DELI
      * @internal
      */
     protected yieldToEventLoop(): Promise<void>;
-    constructor(options?: CSVLexerTransformerOptions<Delimiter, Quotation>, writableStrategy?: ExtendedQueuingStrategy<string>, readableStrategy?: ExtendedQueuingStrategy<Token>);
+    constructor(options?: CSVLexerTransformerOptions<Delimiter, Quotation>, writableStrategy?: QueuingStrategy<string>, readableStrategy?: QueuingStrategy<Token>);
 }

package/dist/CSVLexerTransformer.js

@@ -1,5 +1,15 @@
 import { CSVLexer } from './CSVLexer.js';
 
+const DEFAULT_WRITABLE_STRATEGY = {
+  highWaterMark: 65536,
+  // 64KB worth of characters
+  size: (chunk) => chunk.length
+  // Count by string length
+};
+const DEFAULT_READABLE_STRATEGY = new CountQueuingStrategy({
+  highWaterMark: 1024
+  // 1024 tokens
+});
 class CSVLexerTransformer extends TransformStream {
   lexer;
   /**
@@ -10,23 +20,9 @@ class CSVLexerTransformer extends TransformStream {
   async yieldToEventLoop() {
     await new Promise((resolve) => setTimeout(resolve, 0));
   }
-  constructor(options = {}, writableStrategy = {
-    highWaterMark: 65536,
-    // 64KB worth of characters
-    size: (chunk) => chunk.length,
-    // Count by string length (character count)
-    checkInterval: 100
-    // Check backpressure every 100 tokens
-  }, readableStrategy = {
-    highWaterMark: 1024,
-    // 1024 tokens
-    size: () => 1,
-    // Each token counts as 1
-    checkInterval: 100
-    // Check backpressure every 100 tokens
-  }) {
+  constructor(options = {}, writableStrategy = DEFAULT_WRITABLE_STRATEGY, readableStrategy = DEFAULT_READABLE_STRATEGY) {
     const lexer = new CSVLexer(options);
-    const checkInterval = writableStrategy.checkInterval ?? readableStrategy.checkInterval ?? 100;
+    const checkInterval = options.backpressureCheckInterval ?? 100;
     super(
       {
         transform: async (chunk, controller) => {

package/dist/CSVLexerTransformer.js.map

@@ -1 +1 @@
-{"version":3,"file":"CSVLexerTransformer.js","sources":["../src/CSVLexerTransformer.ts"],"sourcesContent":["import { CSVLexer } from \"./CSVLexer.ts\";\nimport type {\n  CSVLexerTransformerOptions,\n  ExtendedQueuingStrategy,\n  Token,\n} from \"./common/types.ts\";\nimport type { DEFAULT_DELIMITER, DEFAULT_QUOTATION } from \"./constants.ts\";\n\n/**\n * A transform stream that converts a stream of strings into a stream of tokens.\n *\n * @category Low-level API\n *\n * @param options - CSV-specific options (delimiter, quotation, etc.)\n * @param writableStrategy - Strategy for the writable side (default: `{ highWaterMark: 65536, size: chunk => chunk.length, checkInterval: 100 }`)\n * @param readableStrategy - Strategy for the readable side (default: `{ highWaterMark: 1024, size: () => 1, checkInterval: 100 }`)\n *\n * @remarks\n * Follows the Web Streams API pattern where queuing strategies are passed as\n * constructor arguments, similar to the standard `TransformStream`.\n *\n * **Default Queuing Strategy:**\n * - Writable side: Counts by string length (characters). Default highWaterMark is 65536 characters (≈64KB).\n * - Readable side: Counts each token as 1. Default highWaterMark is 1024 tokens.\n *\n * **Backpressure Handling:**\n * The transformer monitors `controller.desiredSize` and yields to the event loop when backpressure\n * is detected (desiredSize ≤ 0). This prevents blocking the main thread during heavy processing\n * and allows the downstream consumer to catch up.\n *\n * These defaults are starting points based on data flow characteristics, not empirical benchmarks.\n * Optimal values depend on your runtime environment, data size, and performance requirements.\n *\n * @example Basic usage\n * ```ts\n * new ReadableStream({\n *   start(controller) {\n *     controller.enqueue(\"name,age\\r\\n\");\n *     controller.enqueue(\"Alice,20\\r\\n\");\n *     controller.close();\n *   }\n * })\n *   .pipeThrough(new CSVLexerTransformer())\n *   .pipeTo(new WritableStream({ write(token) {\n *     console.log(token);\n *   }}));\n * // { type: Field, value: \"name\", location: {...} }\n * // { type: FieldDelimiter, value: \",\", location: {...} }\n * // { type: Field, value: \"age\", location: {...} }\n * // { type: RecordDelimiter, value: \"\\r\\n\", location: {...} }\n * // { type: Field, value: \"Alice\", location: {...} }\n * // { type: FieldDelimiter, value: \",\", location: {...} }\n * // { type: Field, value: \"20\" }\n * // { type: RecordDelimiter, value: \"\\r\\n\", location: {...} }\n * ```\n *\n * @example Custom queuing strategies with backpressure tuning\n * ```ts\n * const transformer = new CSVLexerTransformer(\n *   { delimiter: ',' },\n *   {\n *     highWaterMark: 131072,         // 128KB of characters\n *     size: (chunk) => chunk.length, // Count by character length\n *     checkInterval: 200             // Check backpressure every 200 tokens\n *   },\n *   {\n *     highWaterMark: 2048,           // 2048 tokens\n *     size: () => 1,                 // Each token counts as 1\n *     checkInterval: 50              // Check backpressure every 50 tokens\n *   }\n * );\n *\n * await fetch('large-file.csv')\n *   .then(res => res.body)\n *   .pipeThrough(new TextDecoderStream())\n *   .pipeThrough(transformer)\n *   .pipeTo(yourProcessor);\n * ```\n */\nexport class CSVLexerTransformer<\n  Delimiter extends string = DEFAULT_DELIMITER,\n  Quotation extends string = DEFAULT_QUOTATION,\n> extends TransformStream<string, Token> {\n  public readonly lexer: CSVLexer<Delimiter, Quotation>;\n\n  /**\n   * Yields to the event loop to allow backpressure handling.\n   * Can be overridden for testing purposes.\n   * @internal\n   */\n  protected async yieldToEventLoop(): Promise<void> {\n    await new Promise((resolve) => setTimeout(resolve, 0));\n  }\n\n  constructor(\n    options: CSVLexerTransformerOptions<Delimiter, Quotation> = {},\n    writableStrategy: ExtendedQueuingStrategy<string> = {\n      highWaterMark: 65536, // 64KB worth of characters\n      size: (chunk) => chunk.length, // Count by string length (character count)\n      checkInterval: 100, // Check backpressure every 100 tokens\n    },\n    readableStrategy: ExtendedQueuingStrategy<Token> = {\n      highWaterMark: 1024, // 1024 tokens\n      size: () => 1, // Each token counts as 1\n      checkInterval: 100, // Check backpressure every 100 tokens\n    },\n  ) {\n    const lexer = new CSVLexer(options);\n    const checkInterval =\n      writableStrategy.checkInterval ?? readableStrategy.checkInterval ?? 100;\n\n    super(\n      {\n        transform: async (chunk, controller) => {\n          if (chunk.length !== 0) {\n            try {\n              let tokenCount = 0;\n              for (const token of lexer.lex(chunk, { stream: true })) {\n                controller.enqueue(token);\n                tokenCount++;\n\n                // Check backpressure periodically based on checkInterval\n                if (\n                  tokenCount % checkInterval === 0 &&\n                  controller.desiredSize !== null &&\n                  controller.desiredSize <= 0\n                ) {\n                  // Yield to event loop when backpressure is detected\n                  await this.yieldToEventLoop();\n                }\n              }\n            } catch (error) {\n              controller.error(error);\n            }\n          }\n        },\n        flush: async (controller) => {\n          try {\n            let tokenCount = 0;\n            for (const token of lexer.lex()) {\n              controller.enqueue(token);\n              tokenCount++;\n\n              // Check backpressure periodically based on checkInterval\n              if (\n                tokenCount % checkInterval === 0 &&\n                controller.desiredSize !== null &&\n                controller.desiredSize <= 0\n              ) {\n                await this.yieldToEventLoop();\n              }\n            }\n          } catch (error) {\n            controller.error(error);\n          }\n        },\n      },\n      writableStrategy,\n      readableStrategy,\n    );\n    this.lexer = lexer;\n  }\n}\n"],"names":[],"mappings":";;AA+EO,MAAM,4BAGH,eAAA,CAA+B;AAAA,EACvB,KAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOhB,MAAgB,gBAAA,GAAkC;AAChD,IAAA,MAAM,IAAI,OAAA,CAAQ,CAAC,YAAY,UAAA,CAAW,OAAA,EAAS,CAAC,CAAC,CAAA;AAAA,EACvD;AAAA,EAEA,WAAA,CACE,OAAA,GAA4D,EAAC,EAC7D,gBAAA,GAAoD;AAAA,IAClD,aAAA,EAAe,KAAA;AAAA;AAAA,IACf,IAAA,EAAM,CAAC,KAAA,KAAU,KAAA,CAAM,MAAA;AAAA;AAAA,IACvB,aAAA,EAAe;AAAA;AAAA,KAEjB,gBAAA,GAAmD;AAAA,IACjD,aAAA,EAAe,IAAA;AAAA;AAAA,IACf,MAAM,MAAM,CAAA;AAAA;AAAA,IACZ,aAAA,EAAe;AAAA;AAAA,GACjB,EACA;AACA,IAAA,MAAM,KAAA,GAAQ,IAAI,QAAA,CAAS,OAAO,CAAA;AAClC,IAAA,MAAM,aAAA,GACJ,gBAAA,CAAiB,aAAA,IAAiB,gBAAA,CAAiB,aAAA,IAAiB,GAAA;AAEtE,IAAA,KAAA;AAAA,MACE;AAAA,QACE,SAAA,EAAW,OAAO,KAAA,EAAO,UAAA,KAAe;AACtC,UAAA,IAAI,KAAA,CAAM,WAAW,CAAA,EAAG;AACtB,YAAA,IAAI;AACF,cAAA,IAAI,UAAA,GAAa,CAAA;AACjB,cAAA,KAAA,MAAW,KAAA,IAAS,MAAM,GAAA,CAAI,KAAA,EAAO,EAAE,MAAA,EAAQ,IAAA,EAAM,CAAA,EAAG;AACtD,gBAAA,UAAA,CAAW,QAAQ,KAAK,CAAA;AACxB,gBAAA,UAAA,EAAA;AAGA,gBAAA,IACE,UAAA,GAAa,kBAAkB,CAAA,IAC/B,UAAA,CAAW,gBAAgB,IAAA,IAC3B,UAAA,CAAW,eAAe,CAAA,EAC1B;AAEA,kBAAA,MAAM,KAAK,gBAAA,EAAiB;AAAA,gBAC9B;AAAA,cACF;AAAA,YACF,SAAS,KAAA,EAAO;AACd,cAAA,UAAA,CAAW,MAAM,KAAK,CAAA;AAAA,YACxB;AAAA,UACF;AAAA,QACF,CAAA;AAAA,QACA,KAAA,EAAO,OAAO,UAAA,KAAe;AAC3B,UAAA,IAAI;AACF,YAAA,IAAI,UAAA,GAAa,CAAA;AACjB,YAAA,KAAA,MAAW,KAAA,IAAS,KAAA,CAAM,GAAA,EAAI,EAAG;AAC/B,cAAA,UAAA,CAAW,QAAQ,KAAK,CAAA;AACxB,cAAA,UAAA,EAAA;AAGA,cAAA,IACE,UAAA,GAAa,kBAAkB,CAAA,IAC/B,UAAA,CAAW,gBAAgB,IAAA,IAC3B,UAAA,CAAW,eAAe,CAAA,EAC1B;AACA,gBAAA,MAAM,KAAK,gBAAA,EAAiB;AAAA,cAC9B;AAAA,YACF;AAAA,UACF,SAAS,KAAA,EAAO;AACd,YAAA,UAAA,CAAW,MAAM,KAAK,CAAA;AAAA,UACxB;AAAA,QACF;AAAA,OACF;AAAA,MACA,gBAAA;AAAA,MACA;AAAA,KACF;AACA,IAAA,IAAA,CAAK,KAAA,GAAQ,KAAA;AAAA,EACf;AACF;;;;"}
+{"version":3,"file":"CSVLexerTransformer.js","sources":["../src/CSVLexerTransformer.ts"],"sourcesContent":["import { CSVLexer } from \"./CSVLexer.ts\";\nimport type { CSVLexerTransformerOptions, Token } from \"./common/types.ts\";\nimport type { DEFAULT_DELIMITER, DEFAULT_QUOTATION } from \"./constants.ts\";\n\n/**\n * Default queuing strategy for the writable side (string input).\n * Counts by character length for accurate memory tracking.\n * @internal\n */\nconst DEFAULT_WRITABLE_STRATEGY: QueuingStrategy<string> = {\n  highWaterMark: 65536, // 64KB worth of characters\n  size: (chunk) => chunk.length, // Count by string length\n};\n\n/**\n * Default queuing strategy for the readable side (token output).\n * @internal\n */\nconst DEFAULT_READABLE_STRATEGY = new CountQueuingStrategy({\n  highWaterMark: 1024, // 1024 tokens\n});\n\n/**\n * A transform stream that converts a stream of strings into a stream of tokens.\n *\n * @category Low-level API\n *\n * @param options - CSV-specific options (delimiter, quotation, checkInterval, etc.)\n * @param writableStrategy - Strategy for the writable side (default: `{ highWaterMark: 65536, size: chunk => chunk.length }`)\n * @param readableStrategy - Strategy for the readable side (default: `{ highWaterMark: 1024, size: () => 1 }`)\n *\n * @remarks\n * Follows the Web Streams API pattern where queuing strategies are passed as\n * constructor arguments, similar to the standard `TransformStream`.\n *\n * **Default Queuing Strategy:**\n * - Writable side: Counts by string length (characters). Default highWaterMark is 65536 characters (≈64KB).\n * - Readable side: Counts each token as 1. Default highWaterMark is 1024 tokens.\n *\n * **Backpressure Handling:**\n * The transformer monitors `controller.desiredSize` and yields to the event loop when backpressure\n * is detected (desiredSize ≤ 0). This prevents blocking the main thread during heavy processing\n * and allows the downstream consumer to catch up.\n *\n * These defaults are starting points based on data flow characteristics, not empirical benchmarks.\n * Optimal values depend on your runtime environment, data size, and performance requirements.\n *\n * @example Basic usage\n * ```ts\n * new ReadableStream({\n *   start(controller) {\n *     controller.enqueue(\"name,age\\r\\n\");\n *     controller.enqueue(\"Alice,20\\r\\n\");\n *     controller.close();\n *   }\n * })\n *   .pipeThrough(new CSVLexerTransformer())\n *   .pipeTo(new WritableStream({ write(token) {\n *     console.log(token);\n *   }}));\n * // { type: Field, value: \"name\", location: {...} }\n * // { type: FieldDelimiter, value: \",\", location: {...} }\n * // { type: Field, value: \"age\", location: {...} }\n * // { type: RecordDelimiter, value: \"\\r\\n\", location: {...} }\n * // { type: Field, value: \"Alice\", location: {...} }\n * // { type: FieldDelimiter, value: \",\", location: {...} }\n * // { type: Field, value: \"20\" }\n * // { type: RecordDelimiter, value: \"\\r\\n\", location: {...} }\n * ```\n *\n * @example Custom queuing strategies with backpressure tuning\n * ```ts\n * const transformer = new CSVLexerTransformer(\n *   {\n *     delimiter: ',',\n *     backpressureCheckInterval: 50  // Check backpressure every 50 tokens\n *   },\n *   {\n *     highWaterMark: 131072,         // 128KB of characters\n *     size: (chunk) => chunk.length, // Count by character length\n *   },\n *   new CountQueuingStrategy({ highWaterMark: 2048 })  // 2048 tokens\n * );\n *\n * await fetch('large-file.csv')\n *   .then(res => res.body)\n *   .pipeThrough(new TextDecoderStream())\n *   .pipeThrough(transformer)\n *   .pipeTo(yourProcessor);\n * ```\n */\nexport class CSVLexerTransformer<\n  Delimiter extends string = DEFAULT_DELIMITER,\n  Quotation extends string = DEFAULT_QUOTATION,\n> extends TransformStream<string, Token> {\n  public readonly lexer: CSVLexer<Delimiter, Quotation>;\n\n  /**\n   * Yields to the event loop to allow backpressure handling.\n   * Can be overridden for testing purposes.\n   * @internal\n   */\n  protected async yieldToEventLoop(): Promise<void> {\n    await new Promise((resolve) => setTimeout(resolve, 0));\n  }\n\n  constructor(\n    options: CSVLexerTransformerOptions<Delimiter, Quotation> = {},\n    writableStrategy: QueuingStrategy<string> = DEFAULT_WRITABLE_STRATEGY,\n    readableStrategy: QueuingStrategy<Token> = DEFAULT_READABLE_STRATEGY,\n  ) {\n    const lexer = new CSVLexer(options);\n    const checkInterval = options.backpressureCheckInterval ?? 100;\n\n    super(\n      {\n        transform: async (chunk, controller) => {\n          if (chunk.length !== 0) {\n            try {\n              let tokenCount = 0;\n              for (const token of lexer.lex(chunk, { stream: true })) {\n                controller.enqueue(token);\n                tokenCount++;\n\n                // Check backpressure periodically based on checkInterval\n                if (\n                  tokenCount % checkInterval === 0 &&\n                  controller.desiredSize !== null &&\n                  controller.desiredSize <= 0\n                ) {\n                  // Yield to event loop when backpressure is detected\n                  await this.yieldToEventLoop();\n                }\n              }\n            } catch (error) {\n              controller.error(error);\n            }\n          }\n        },\n        flush: async (controller) => {\n          try {\n            let tokenCount = 0;\n            for (const token of lexer.lex()) {\n              controller.enqueue(token);\n              tokenCount++;\n\n              // Check backpressure periodically based on checkInterval\n              if (\n                tokenCount % checkInterval === 0 &&\n                controller.desiredSize !== null &&\n                controller.desiredSize <= 0\n              ) {\n                await this.yieldToEventLoop();\n              }\n            }\n          } catch (error) {\n            controller.error(error);\n          }\n        },\n      },\n      writableStrategy,\n      readableStrategy,\n    );\n    this.lexer = lexer;\n  }\n}\n"],"names":[],"mappings":";;AASA,MAAM,yBAAA,GAAqD;AAAA,EACzD,aAAA,EAAe,KAAA;AAAA;AAAA,EACf,IAAA,EAAM,CAAC,KAAA,KAAU,KAAA,CAAM;AAAA;AACzB,CAAA;AAMA,MAAM,yBAAA,GAA4B,IAAI,oBAAA,CAAqB;AAAA,EACzD,aAAA,EAAe;AAAA;AACjB,CAAC,CAAA;AAuEM,MAAM,4BAGH,eAAA,CAA+B;AAAA,EACvB,KAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOhB,MAAgB,gBAAA,GAAkC;AAChD,IAAA,MAAM,IAAI,OAAA,CAAQ,CAAC,YAAY,UAAA,CAAW,OAAA,EAAS,CAAC,CAAC,CAAA;AAAA,EACvD;AAAA,EAEA,YACE,OAAA,GAA4D,IAC5D,gBAAA,GAA4C,yBAAA,EAC5C,mBAA2C,yBAAA,EAC3C;AACA,IAAA,MAAM,KAAA,GAAQ,IAAI,QAAA,CAAS,OAAO,CAAA;AAClC,IAAA,MAAM,aAAA,GAAgB,QAAQ,yBAAA,IAA6B,GAAA;AAE3D,IAAA,KAAA;AAAA,MACE;AAAA,QACE,SAAA,EAAW,OAAO,KAAA,EAAO,UAAA,KAAe;AACtC,UAAA,IAAI,KAAA,CAAM,WAAW,CAAA,EAAG;AACtB,YAAA,IAAI;AACF,cAAA,IAAI,UAAA,GAAa,CAAA;AACjB,cAAA,KAAA,MAAW,KAAA,IAAS,MAAM,GAAA,CAAI,KAAA,EAAO,EAAE,MAAA,EAAQ,IAAA,EAAM,CAAA,EAAG;AACtD,gBAAA,UAAA,CAAW,QAAQ,KAAK,CAAA;AACxB,gBAAA,UAAA,EAAA;AAGA,gBAAA,IACE,UAAA,GAAa,kBAAkB,CAAA,IAC/B,UAAA,CAAW,gBAAgB,IAAA,IAC3B,UAAA,CAAW,eAAe,CAAA,EAC1B;AAEA,kBAAA,MAAM,KAAK,gBAAA,EAAiB;AAAA,gBAC9B;AAAA,cACF;AAAA,YACF,SAAS,KAAA,EAAO;AACd,cAAA,UAAA,CAAW,MAAM,KAAK,CAAA;AAAA,YACxB;AAAA,UACF;AAAA,QACF,CAAA;AAAA,QACA,KAAA,EAAO,OAAO,UAAA,KAAe;AAC3B,UAAA,IAAI;AACF,YAAA,IAAI,UAAA,GAAa,CAAA;AACjB,YAAA,KAAA,MAAW,KAAA,IAAS,KAAA,CAAM,GAAA,EAAI,EAAG;AAC/B,cAAA,UAAA,CAAW,QAAQ,KAAK,CAAA;AACxB,cAAA,UAAA,EAAA;AAGA,cAAA,IACE,UAAA,GAAa,kBAAkB,CAAA,IAC/B,UAAA,CAAW,gBAAgB,IAAA,IAC3B,UAAA,CAAW,eAAe,CAAA,EAC1B;AACA,gBAAA,MAAM,KAAK,gBAAA,EAAiB;AAAA,cAC9B;AAAA,YACF;AAAA,UACF,SAAS,KAAA,EAAO;AACd,YAAA,UAAA,CAAW,MAAM,KAAK,CAAA;AAAA,UACxB;AAAA,QACF;AAAA,OACF;AAAA,MACA,gBAAA;AAAA,MACA;AAAA,KACF;AACA,IAAA,IAAA,CAAK,KAAA,GAAQ,KAAA;AAAA,EACf;AACF;;;;"}

package/dist/CSVRecordAssembler.js

@@ -10,6 +10,8 @@ class CSVRecordAssembler {
   #signal;
   #maxFieldCount;
   #skipEmptyLines;
+  #currentRowNumber;
+  #source;
   constructor(options = {}) {
     const mfc = options.maxFieldCount ?? DEFAULT_MAX_FIELD_COUNT;
     if (!(Number.isFinite(mfc) || mfc === Number.POSITIVE_INFINITY) || Number.isFinite(mfc) && (mfc < 1 || !Number.isInteger(mfc))) {
@@ -19,6 +21,7 @@ class CSVRecordAssembler {
     }
     this.#maxFieldCount = mfc;
     this.#skipEmptyLines = options.skipEmptyLines ?? false;
+    this.#source = options.source;
     if (options.header !== void 0 && Array.isArray(options.header)) {
       this.#setHeader(options.header);
     }
@@ -58,6 +61,9 @@ class CSVRecordAssembler {
    */
   *#processToken(token) {
     this.#signal?.throwIfAborted();
+    if (token.location) {
+      this.#currentRowNumber = token.location.rowNumber;
+    }
     switch (token.type) {
       case FieldDelimiter:
         this.#fieldIndex++;
@@ -119,22 +125,26 @@ class CSVRecordAssembler {
   #checkFieldCount() {
     if (this.#fieldIndex + 1 > this.#maxFieldCount) {
       throw new RangeError(
-        `Field count (${this.#fieldIndex + 1}) exceeded maximum allowed count of ${this.#maxFieldCount}`
+        `Field count (${this.#fieldIndex + 1}) exceeded maximum allowed count of ${this.#maxFieldCount}${this.#currentRowNumber ? ` at row ${this.#currentRowNumber}` : ""}${this.#source ? ` in ${JSON.stringify(this.#source)}` : ""}`
       );
     }
   }
   #setHeader(header) {
     if (header.length > this.#maxFieldCount) {
       throw new RangeError(
-        `Header field count (${header.length}) exceeded maximum allowed count of ${this.#maxFieldCount}`
+        `Header field count (${header.length}) exceeded maximum allowed count of ${this.#maxFieldCount}${this.#source ? ` in ${JSON.stringify(this.#source)}` : ""}`
       );
     }
     this.#header = header;
     if (this.#header.length === 0) {
-      throw new ParseError("The header must not be empty.");
+      throw new ParseError("The header must not be empty.", {
+        source: this.#source
+      });
     }
     if (new Set(this.#header).size !== this.#header.length) {
-      throw new ParseError("The header must not contain duplicate fields.");
+      throw new ParseError("The header must not contain duplicate fields.", {
+        source: this.#source
+      });
     }
   }
 }

package/dist/CSVRecordAssembler.js.map

@@ -1 +1 @@
-{"version":3,"file":"CSVRecordAssembler.js","sources":["../src/CSVRecordAssembler.ts"],"sourcesContent":["import { FieldDelimiter, RecordDelimiter } from \"./common/constants.ts\";\nimport { ParseError } from \"./common/errors.ts\";\nimport type {\n  CSVRecord,\n  CSVRecordAssemblerOptions,\n  Token,\n} from \"./common/types.ts\";\n\n/**\n * Default maximum field count per record (100,000 fields).\n */\nconst DEFAULT_MAX_FIELD_COUNT = 100_000;\n\n/**\n * Options for the CSVRecordAssembler.assemble method.\n */\nexport interface CSVRecordAssemblerAssembleOptions {\n  /**\n   * If true, indicates that more tokens are expected.\n   * If false or omitted, flushes remaining data.\n   */\n  stream?: boolean;\n}\n\n/**\n * CSV Record Assembler.\n *\n * CSVRecordAssembler assembles tokens into CSV records.\n */\nexport class CSVRecordAssembler<Header extends ReadonlyArray<string>> {\n  #fieldIndex = 0;\n  #row: string[] = [];\n  #header: Header | undefined;\n  #dirty = false;\n  #signal?: AbortSignal;\n  #maxFieldCount: number;\n  #skipEmptyLines: boolean;\n\n  constructor(options: CSVRecordAssemblerOptions<Header> = {}) {\n    const mfc = options.maxFieldCount ?? DEFAULT_MAX_FIELD_COUNT;\n    // Validate maxFieldCount\n    if (\n      !(Number.isFinite(mfc) || mfc === Number.POSITIVE_INFINITY) ||\n      (Number.isFinite(mfc) && (mfc < 1 || !Number.isInteger(mfc)))\n    ) {\n      throw new RangeError(\n        \"maxFieldCount must be a positive integer or Number.POSITIVE_INFINITY\",\n      );\n    }\n    this.#maxFieldCount = mfc;\n    this.#skipEmptyLines = options.skipEmptyLines ?? false;\n    if (options.header !== undefined && Array.isArray(options.header)) {\n      this.#setHeader(options.header);\n    }\n    if (options.signal) {\n      this.#signal = options.signal;\n    }\n  }\n\n  /**\n   * Assembles tokens into CSV records.\n   * @param input - A single token or an iterable of tokens. Omit to flush remaining data.\n   * @param options - Assembler options.\n   * @returns An iterable iterator of CSV records.\n   */\n  public *assemble(\n    input?: Token | Iterable<Token>,\n    options?: CSVRecordAssemblerAssembleOptions,\n  ): IterableIterator<CSVRecord<Header>> {\n    const stream = options?.stream ?? false;\n\n    if (input !== undefined) {\n      // Check if input is iterable (has Symbol.iterator)\n      if (this.#isIterable(input)) {\n        for (const token of input) {\n          yield* this.#processToken(token);\n        }\n      } else {\n        // Single token\n        yield* this.#processToken(input);\n      }\n    }\n\n    if (!stream) {\n      yield* this.#flush();\n    }\n  }\n\n  /**\n   * Checks if a value is iterable.\n   */\n  #isIterable(value: any): value is Iterable<Token> {\n    return value != null && typeof value[Symbol.iterator] === \"function\";\n  }\n\n  /**\n   * Processes a single token and yields a record if one is completed.\n   */\n  *#processToken(token: Token): IterableIterator<CSVRecord<Header>> {\n    this.#signal?.throwIfAborted();\n\n    switch (token.type) {\n      case FieldDelimiter:\n        this.#fieldIndex++;\n        this.#checkFieldCount();\n        this.#dirty = true;\n        break;\n      case RecordDelimiter:\n        if (this.#header === undefined) {\n          this.#setHeader(this.#row as unknown as Header);\n        } else {\n          if (this.#dirty) {\n            // SAFETY: Object.fromEntries() is safe from prototype pollution.\n            // See CSVRecordAssembler.prototype-safety.test.ts for details.\n            yield Object.fromEntries(\n              this.#header\n                .map((header, index) => [header, index] as const)\n                .filter(([header]) => header)\n                .map(([header, index]) => [header, this.#row.at(index)]),\n            ) as unknown as CSVRecord<Header>;\n          } else {\n            if (!this.#skipEmptyLines) {\n              // SAFETY: Object.fromEntries() is safe from prototype pollution.\n              // See CSVRecordAssembler.prototype-safety.test.ts for details.\n              yield Object.fromEntries(\n                this.#header\n                  .filter((header) => header)\n                  .map((header) => [header, \"\"]),\n              ) as CSVRecord<Header>;\n            }\n          }\n        }\n        // Reset the row fields buffer.\n        this.#fieldIndex = 0;\n        this.#row = new Array(this.#header?.length).fill(\"\");\n        this.#dirty = false;\n        break;\n      default:\n        this.#dirty = true;\n        this.#row[this.#fieldIndex] = token.value;\n        break;\n    }\n  }\n\n  /**\n   * Flushes any remaining buffered data as a final record.\n   *\n   * @remarks\n   * Prototype Pollution Safety:\n   * This method uses Object.fromEntries() to create record objects from CSV data.\n   * Object.fromEntries() is safe from prototype pollution because it creates\n   * own properties (not prototype properties) even when keys like \"__proto__\",\n   * \"constructor\", or \"prototype\" are used.\n   *\n   * For example, Object.fromEntries([[\"__proto__\", \"value\"]]) creates an object\n   * with an own property \"__proto__\" set to \"value\", which does NOT pollute\n   * Object.prototype and does NOT affect other objects.\n   *\n   * This safety is verified by regression tests in:\n   * CSVRecordAssembler.prototype-safety.test.ts\n   */\n  *#flush(): IterableIterator<CSVRecord<Header>> {\n    if (this.#header !== undefined) {\n      if (this.#dirty) {\n        // SAFETY: Object.fromEntries() creates own properties, preventing prototype pollution\n        // even when CSV headers contain dangerous property names like __proto__, constructor, etc.\n        // See CSVRecordAssembler.prototype-safety.test.ts for verification tests.\n        yield Object.fromEntries(\n          this.#header\n            .map((header, index) => [header, index] as const)\n            .filter(([header]) => header)\n            .map(([header, index]) => [header, this.#row.at(index)]),\n        ) as unknown as CSVRecord<Header>;\n      }\n    }\n  }\n\n  #checkFieldCount(): void {\n    if (this.#fieldIndex + 1 > this.#maxFieldCount) {\n      throw new RangeError(\n        `Field count (${this.#fieldIndex + 1}) exceeded maximum allowed count of ${this.#maxFieldCount}`,\n      );\n    }\n  }\n\n  #setHeader(header: Header) {\n    if (header.length > this.#maxFieldCount) {\n      throw new RangeError(\n        `Header field count (${header.length}) exceeded maximum allowed count of ${this.#maxFieldCount}`,\n      );\n    }\n    this.#header = header;\n    if (this.#header.length === 0) {\n      throw new ParseError(\"The header must not be empty.\");\n    }\n    if (new Set(this.#header).size !== this.#header.length) {\n      throw new ParseError(\"The header must not contain duplicate fields.\");\n    }\n  }\n}\n"],"names":[],"mappings":";;;AAWA,MAAM,uBAAA,GAA0B,GAAA;AAkBzB,MAAM,kBAAA,CAAyD;AAAA,EACpE,WAAA,GAAc,CAAA;AAAA,EACd,OAAiB,EAAC;AAAA,EAClB,OAAA;AAAA,EACA,MAAA,GAAS,KAAA;AAAA,EACT,OAAA;AAAA,EACA,cAAA;AAAA,EACA,eAAA;AAAA,EAEA,WAAA,CAAY,OAAA,GAA6C,EAAC,EAAG;AAC3D,IAAA,MAAM,GAAA,GAAM,QAAQ,aAAA,IAAiB,uBAAA;AAErC,IAAA,IACE,EAAE,MAAA,CAAO,QAAA,CAAS,GAAG,CAAA,IAAK,GAAA,KAAQ,OAAO,iBAAA,CAAA,IACxC,MAAA,CAAO,QAAA,CAAS,GAAG,MAAM,GAAA,GAAM,CAAA,IAAK,CAAC,MAAA,CAAO,SAAA,CAAU,GAAG,CAAA,CAAA,EAC1D;AACA,MAAA,MAAM,IAAI,UAAA;AAAA,QACR;AAAA,OACF;AAAA,IACF;AACA,IAAA,IAAA,CAAK,cAAA,GAAiB,GAAA;AACtB,IAAA,IAAA,CAAK,eAAA,GAAkB,QAAQ,cAAA,IAAkB,KAAA;AACjD,IAAA,IAAI,QAAQ,MAAA,KAAW,MAAA,IAAa,MAAM,OAAA,CAAQ,OAAA,CAAQ,MAAM,CAAA,EAAG;AACjE,MAAA,IAAA,CAAK,UAAA,CAAW,QAAQ,MAAM,CAAA;AAAA,IAChC;AACA,IAAA,IAAI,QAAQ,MAAA,EAAQ;AAClB,MAAA,IAAA,CAAK,UAAU,OAAA,CAAQ,MAAA;AAAA,IACzB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,CAAQ,QAAA,CACN,KAAA,EACA,OAAA,EACqC;AACrC,IAAA,MAAM,MAAA,GAAS,SAAS,MAAA,IAAU,KAAA;AAElC,IAAA,IAAI,UAAU,MAAA,EAAW;AAEvB,MAAA,IAAI,IAAA,CAAK,WAAA,CAAY,KAAK,CAAA,EAAG;AAC3B,QAAA,KAAA,MAAW,SAAS,KAAA,EAAO;AACzB,UAAA,OAAO,IAAA,CAAK,cAAc,KAAK,CAAA;AAAA,QACjC;AAAA,MACF,CAAA,MAAO;AAEL,QAAA,OAAO,IAAA,CAAK,cAAc,KAAK,CAAA;AAAA,MACjC;AAAA,IACF;AAEA,IAAA,IAAI,CAAC,MAAA,EAAQ;AACX,MAAA,OAAO,KAAK,MAAA,EAAO;AAAA,IACrB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,YAAY,KAAA,EAAsC;AAChD,IAAA,OAAO,SAAS,IAAA,IAAQ,OAAO,KAAA,CAAM,MAAA,CAAO,QAAQ,CAAA,KAAM,UAAA;AAAA,EAC5D;AAAA;AAAA;AAAA;AAAA,EAKA,CAAC,cAAc,KAAA,EAAmD;AAChE,IAAA,IAAA,CAAK,SAAS,cAAA,EAAe;AAE7B,IAAA,QAAQ,MAAM,IAAA;AAAM,MAClB,KAAK,cAAA;AACH,QAAA,IAAA,CAAK,WAAA,EAAA;AACL,QAAA,IAAA,CAAK,gBAAA,EAAiB;AACtB,QAAA,IAAA,CAAK,MAAA,GAAS,IAAA;AACd,QAAA;AAAA,MACF,KAAK,eAAA;AACH,QAAA,IAAI,IAAA,CAAK,YAAY,MAAA,EAAW;AAC9B,UAAA,IAAA,CAAK,UAAA,CAAW,KAAK,IAAyB,CAAA;AAAA,QAChD,CAAA,MAAO;AACL,UAAA,IAAI,KAAK,MAAA,EAAQ;AAGf,YAAA,MAAM,MAAA,CAAO,WAAA;AAAA,cACX,IAAA,CAAK,OAAA,CACF,GAAA,CAAI,CAAC,MAAA,EAAQ,KAAA,KAAU,CAAC,MAAA,EAAQ,KAAK,CAAU,CAAA,CAC/C,MAAA,CAAO,CAAC,CAAC,MAAM,CAAA,KAAM,MAAM,CAAA,CAC3B,GAAA,CAAI,CAAC,CAAC,QAAQ,KAAK,CAAA,KAAM,CAAC,MAAA,EAAQ,IAAA,CAAK,IAAA,CAAK,EAAA,CAAG,KAAK,CAAC,CAAC;AAAA,aAC3D;AAAA,UACF,CAAA,MAAO;AACL,YAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AAGzB,cAAA,MAAM,MAAA,CAAO,WAAA;AAAA,gBACX,IAAA,CAAK,OAAA,CACF,MAAA,CAAO,CAAC,MAAA,KAAW,MAAM,CAAA,CACzB,GAAA,CAAI,CAAC,MAAA,KAAW,CAAC,MAAA,EAAQ,EAAE,CAAC;AAAA,eACjC;AAAA,YACF;AAAA,UACF;AAAA,QACF;AAEA,QAAA,IAAA,CAAK,WAAA,GAAc,CAAA;AACnB,QAAA,IAAA,CAAK,IAAA,GAAO,IAAI,KAAA,CAAM,IAAA,CAAK,SAAS,MAAM,CAAA,CAAE,KAAK,EAAE,CAAA;AACnD,QAAA,IAAA,CAAK,MAAA,GAAS,KAAA;AACd,QAAA;AAAA,MACF;AACE,QAAA,IAAA,CAAK,MAAA,GAAS,IAAA;AACd,QAAA,IAAA,CAAK,IAAA,CAAK,IAAA,CAAK,WAAW,CAAA,GAAI,KAAA,CAAM,KAAA;AACpC,QAAA;AAAA;AACJ,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAmBA,CAAC,MAAA,GAA8C;AAC7C,IAAA,IAAI,IAAA,CAAK,YAAY,MAAA,EAAW;AAC9B,MAAA,IAAI,KAAK,MAAA,EAAQ;AAIf,QAAA,MAAM,MAAA,CAAO,WAAA;AAAA,UACX,IAAA,CAAK,OAAA,CACF,GAAA,CAAI,CAAC,MAAA,EAAQ,KAAA,KAAU,CAAC,MAAA,EAAQ,KAAK,CAAU,CAAA,CAC/C,MAAA,CAAO,CAAC,CAAC,MAAM,CAAA,KAAM,MAAM,CAAA,CAC3B,GAAA,CAAI,CAAC,CAAC,QAAQ,KAAK,CAAA,KAAM,CAAC,MAAA,EAAQ,IAAA,CAAK,IAAA,CAAK,EAAA,CAAG,KAAK,CAAC,CAAC;AAAA,SAC3D;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAAA,EAEA,gBAAA,GAAyB;AACvB,IAAA,IAAI,IAAA,CAAK,WAAA,GAAc,CAAA,GAAI,IAAA,CAAK,cAAA,EAAgB;AAC9C,MAAA,MAAM,IAAI,UAAA;AAAA,QACR,gBAAgB,IAAA,CAAK,WAAA,GAAc,CAAC,CAAA,oCAAA,EAAuC,KAAK,cAAc,CAAA;AAAA,OAChG;AAAA,IACF;AAAA,EACF;AAAA,EAEA,WAAW,MAAA,EAAgB;AACzB,IAAA,IAAI,MAAA,CAAO,MAAA,GAAS,IAAA,CAAK,cAAA,EAAgB;AACvC,MAAA,MAAM,IAAI,UAAA;AAAA,QACR,CAAA,oBAAA,EAAuB,MAAA,CAAO,MAAM,CAAA,oCAAA,EAAuC,KAAK,cAAc,CAAA;AAAA,OAChG;AAAA,IACF;AACA,IAAA,IAAA,CAAK,OAAA,GAAU,MAAA;AACf,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,MAAA,KAAW,CAAA,EAAG;AAC7B,MAAA,MAAM,IAAI,WAAW,+BAA+B,CAAA;AAAA,IACtD;AACA,IAAA,IAAI,IAAI,IAAI,IAAA,CAAK,OAAO,EAAE,IAAA,KAAS,IAAA,CAAK,QAAQ,MAAA,EAAQ;AACtD,MAAA,MAAM,IAAI,WAAW,+CAA+C,CAAA;AAAA,IACtE;AAAA,EACF;AACF;;;;"}
+{"version":3,"file":"CSVRecordAssembler.js","sources":["../src/CSVRecordAssembler.ts"],"sourcesContent":["import { FieldDelimiter, RecordDelimiter } from \"./common/constants.ts\";\nimport { ParseError } from \"./common/errors.ts\";\nimport type {\n  CSVRecord,\n  CSVRecordAssemblerOptions,\n  Token,\n} from \"./common/types.ts\";\n\n/**\n * Default maximum field count per record (100,000 fields).\n */\nconst DEFAULT_MAX_FIELD_COUNT = 100_000;\n\n/**\n * Options for the CSVRecordAssembler.assemble method.\n */\nexport interface CSVRecordAssemblerAssembleOptions {\n  /**\n   * If true, indicates that more tokens are expected.\n   * If false or omitted, flushes remaining data.\n   */\n  stream?: boolean;\n}\n\n/**\n * CSV Record Assembler.\n *\n * CSVRecordAssembler assembles tokens into CSV records.\n */\nexport class CSVRecordAssembler<Header extends ReadonlyArray<string>> {\n  #fieldIndex = 0;\n  #row: string[] = [];\n  #header: Header | undefined;\n  #dirty = false;\n  #signal?: AbortSignal;\n  #maxFieldCount: number;\n  #skipEmptyLines: boolean;\n  #currentRowNumber?: number;\n  #source?: string;\n\n  constructor(options: CSVRecordAssemblerOptions<Header> = {}) {\n    const mfc = options.maxFieldCount ?? DEFAULT_MAX_FIELD_COUNT;\n    // Validate maxFieldCount\n    if (\n      !(Number.isFinite(mfc) || mfc === Number.POSITIVE_INFINITY) ||\n      (Number.isFinite(mfc) && (mfc < 1 || !Number.isInteger(mfc)))\n    ) {\n      throw new RangeError(\n        \"maxFieldCount must be a positive integer or Number.POSITIVE_INFINITY\",\n      );\n    }\n    this.#maxFieldCount = mfc;\n    this.#skipEmptyLines = options.skipEmptyLines ?? false;\n    this.#source = options.source;\n    if (options.header !== undefined && Array.isArray(options.header)) {\n      this.#setHeader(options.header);\n    }\n    if (options.signal) {\n      this.#signal = options.signal;\n    }\n  }\n\n  /**\n   * Assembles tokens into CSV records.\n   * @param input - A single token or an iterable of tokens. Omit to flush remaining data.\n   * @param options - Assembler options.\n   * @returns An iterable iterator of CSV records.\n   */\n  public *assemble(\n    input?: Token | Iterable<Token>,\n    options?: CSVRecordAssemblerAssembleOptions,\n  ): IterableIterator<CSVRecord<Header>> {\n    const stream = options?.stream ?? false;\n\n    if (input !== undefined) {\n      // Check if input is iterable (has Symbol.iterator)\n      if (this.#isIterable(input)) {\n        for (const token of input) {\n          yield* this.#processToken(token);\n        }\n      } else {\n        // Single token\n        yield* this.#processToken(input);\n      }\n    }\n\n    if (!stream) {\n      yield* this.#flush();\n    }\n  }\n\n  /**\n   * Checks if a value is iterable.\n   */\n  #isIterable(value: any): value is Iterable<Token> {\n    return value != null && typeof value[Symbol.iterator] === \"function\";\n  }\n\n  /**\n   * Processes a single token and yields a record if one is completed.\n   */\n  *#processToken(token: Token): IterableIterator<CSVRecord<Header>> {\n    this.#signal?.throwIfAborted();\n\n    // Track the current record number for error reporting\n    if (token.location) {\n      this.#currentRowNumber = token.location.rowNumber;\n    }\n\n    switch (token.type) {\n      case FieldDelimiter:\n        this.#fieldIndex++;\n        this.#checkFieldCount();\n        this.#dirty = true;\n        break;\n      case RecordDelimiter:\n        if (this.#header === undefined) {\n          this.#setHeader(this.#row as unknown as Header);\n        } else {\n          if (this.#dirty) {\n            // SAFETY: Object.fromEntries() is safe from prototype pollution.\n            // See CSVRecordAssembler.prototype-safety.test.ts for details.\n            yield Object.fromEntries(\n              this.#header\n                .map((header, index) => [header, index] as const)\n                .filter(([header]) => header)\n                .map(([header, index]) => [header, this.#row.at(index)]),\n            ) as unknown as CSVRecord<Header>;\n          } else {\n            if (!this.#skipEmptyLines) {\n              // SAFETY: Object.fromEntries() is safe from prototype pollution.\n              // See CSVRecordAssembler.prototype-safety.test.ts for details.\n              yield Object.fromEntries(\n                this.#header\n                  .filter((header) => header)\n                  .map((header) => [header, \"\"]),\n              ) as CSVRecord<Header>;\n            }\n          }\n        }\n        // Reset the row fields buffer.\n        this.#fieldIndex = 0;\n        this.#row = new Array(this.#header?.length).fill(\"\");\n        this.#dirty = false;\n        break;\n      default:\n        this.#dirty = true;\n        this.#row[this.#fieldIndex] = token.value;\n        break;\n    }\n  }\n\n  /**\n   * Flushes any remaining buffered data as a final record.\n   *\n   * @remarks\n   * Prototype Pollution Safety:\n   * This method uses Object.fromEntries() to create record objects from CSV data.\n   * Object.fromEntries() is safe from prototype pollution because it creates\n   * own properties (not prototype properties) even when keys like \"__proto__\",\n   * \"constructor\", or \"prototype\" are used.\n   *\n   * For example, Object.fromEntries([[\"__proto__\", \"value\"]]) creates an object\n   * with an own property \"__proto__\" set to \"value\", which does NOT pollute\n   * Object.prototype and does NOT affect other objects.\n   *\n   * This safety is verified by regression tests in:\n   * CSVRecordAssembler.prototype-safety.test.ts\n   */\n  *#flush(): IterableIterator<CSVRecord<Header>> {\n    if (this.#header !== undefined) {\n      if (this.#dirty) {\n        // SAFETY: Object.fromEntries() creates own properties, preventing prototype pollution\n        // even when CSV headers contain dangerous property names like __proto__, constructor, etc.\n        // See CSVRecordAssembler.prototype-safety.test.ts for verification tests.\n        yield Object.fromEntries(\n          this.#header\n            .map((header, index) => [header, index] as const)\n            .filter(([header]) => header)\n            .map(([header, index]) => [header, this.#row.at(index)]),\n        ) as unknown as CSVRecord<Header>;\n      }\n    }\n  }\n\n  #checkFieldCount(): void {\n    if (this.#fieldIndex + 1 > this.#maxFieldCount) {\n      throw new RangeError(\n        `Field count (${this.#fieldIndex + 1}) exceeded maximum allowed count of ${this.#maxFieldCount}${\n          this.#currentRowNumber ? ` at row ${this.#currentRowNumber}` : \"\"\n        }${this.#source ? ` in ${JSON.stringify(this.#source)}` : \"\"}`,\n      );\n    }\n  }\n\n  #setHeader(header: Header) {\n    if (header.length > this.#maxFieldCount) {\n      throw new RangeError(\n        `Header field count (${header.length}) exceeded maximum allowed count of ${this.#maxFieldCount}${\n          this.#source ? ` in ${JSON.stringify(this.#source)}` : \"\"\n        }`,\n      );\n    }\n    this.#header = header;\n    if (this.#header.length === 0) {\n      throw new ParseError(\"The header must not be empty.\", {\n        source: this.#source,\n      });\n    }\n    if (new Set(this.#header).size !== this.#header.length) {\n      throw new ParseError(\"The header must not contain duplicate fields.\", {\n        source: this.#source,\n      });\n    }\n  }\n}\n"],"names":[],"mappings":";;;AAWA,MAAM,uBAAA,GAA0B,GAAA;AAkBzB,MAAM,kBAAA,CAAyD;AAAA,EACpE,WAAA,GAAc,CAAA;AAAA,EACd,OAAiB,EAAC;AAAA,EAClB,OAAA;AAAA,EACA,MAAA,GAAS,KAAA;AAAA,EACT,OAAA;AAAA,EACA,cAAA;AAAA,EACA,eAAA;AAAA,EACA,iBAAA;AAAA,EACA,OAAA;AAAA,EAEA,WAAA,CAAY,OAAA,GAA6C,EAAC,EAAG;AAC3D,IAAA,MAAM,GAAA,GAAM,QAAQ,aAAA,IAAiB,uBAAA;AAErC,IAAA,IACE,EAAE,MAAA,CAAO,QAAA,CAAS,GAAG,CAAA,IAAK,GAAA,KAAQ,OAAO,iBAAA,CAAA,IACxC,MAAA,CAAO,QAAA,CAAS,GAAG,MAAM,GAAA,GAAM,CAAA,IAAK,CAAC,MAAA,CAAO,SAAA,CAAU,GAAG,CAAA,CAAA,EAC1D;AACA,MAAA,MAAM,IAAI,UAAA;AAAA,QACR;AAAA,OACF;AAAA,IACF;AACA,IAAA,IAAA,CAAK,cAAA,GAAiB,GAAA;AACtB,IAAA,IAAA,CAAK,eAAA,GAAkB,QAAQ,cAAA,IAAkB,KAAA;AACjD,IAAA,IAAA,CAAK,UAAU,OAAA,CAAQ,MAAA;AACvB,IAAA,IAAI,QAAQ,MAAA,KAAW,MAAA,IAAa,MAAM,OAAA,CAAQ,OAAA,CAAQ,MAAM,CAAA,EAAG;AACjE,MAAA,IAAA,CAAK,UAAA,CAAW,QAAQ,MAAM,CAAA;AAAA,IAChC;AACA,IAAA,IAAI,QAAQ,MAAA,EAAQ;AAClB,MAAA,IAAA,CAAK,UAAU,OAAA,CAAQ,MAAA;AAAA,IACzB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,CAAQ,QAAA,CACN,KAAA,EACA,OAAA,EACqC;AACrC,IAAA,MAAM,MAAA,GAAS,SAAS,MAAA,IAAU,KAAA;AAElC,IAAA,IAAI,UAAU,MAAA,EAAW;AAEvB,MAAA,IAAI,IAAA,CAAK,WAAA,CAAY,KAAK,CAAA,EAAG;AAC3B,QAAA,KAAA,MAAW,SAAS,KAAA,EAAO;AACzB,UAAA,OAAO,IAAA,CAAK,cAAc,KAAK,CAAA;AAAA,QACjC;AAAA,MACF,CAAA,MAAO;AAEL,QAAA,OAAO,IAAA,CAAK,cAAc,KAAK,CAAA;AAAA,MACjC;AAAA,IACF;AAEA,IAAA,IAAI,CAAC,MAAA,EAAQ;AACX,MAAA,OAAO,KAAK,MAAA,EAAO;AAAA,IACrB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,YAAY,KAAA,EAAsC;AAChD,IAAA,OAAO,SAAS,IAAA,IAAQ,OAAO,KAAA,CAAM,MAAA,CAAO,QAAQ,CAAA,KAAM,UAAA;AAAA,EAC5D;AAAA;AAAA;AAAA;AAAA,EAKA,CAAC,cAAc,KAAA,EAAmD;AAChE,IAAA,IAAA,CAAK,SAAS,cAAA,EAAe;AAG7B,IAAA,IAAI,MAAM,QAAA,EAAU;AAClB,MAAA,IAAA,CAAK,iBAAA,GAAoB,MAAM,QAAA,CAAS,SAAA;AAAA,IAC1C;AAEA,IAAA,QAAQ,MAAM,IAAA;AAAM,MAClB,KAAK,cAAA;AACH,QAAA,IAAA,CAAK,WAAA,EAAA;AACL,QAAA,IAAA,CAAK,gBAAA,EAAiB;AACtB,QAAA,IAAA,CAAK,MAAA,GAAS,IAAA;AACd,QAAA;AAAA,MACF,KAAK,eAAA;AACH,QAAA,IAAI,IAAA,CAAK,YAAY,MAAA,EAAW;AAC9B,UAAA,IAAA,CAAK,UAAA,CAAW,KAAK,IAAyB,CAAA;AAAA,QAChD,CAAA,MAAO;AACL,UAAA,IAAI,KAAK,MAAA,EAAQ;AAGf,YAAA,MAAM,MAAA,CAAO,WAAA;AAAA,cACX,IAAA,CAAK,OAAA,CACF,GAAA,CAAI,CAAC,MAAA,EAAQ,KAAA,KAAU,CAAC,MAAA,EAAQ,KAAK,CAAU,CAAA,CAC/C,MAAA,CAAO,CAAC,CAAC,MAAM,CAAA,KAAM,MAAM,CAAA,CAC3B,GAAA,CAAI,CAAC,CAAC,QAAQ,KAAK,CAAA,KAAM,CAAC,MAAA,EAAQ,IAAA,CAAK,IAAA,CAAK,EAAA,CAAG,KAAK,CAAC,CAAC;AAAA,aAC3D;AAAA,UACF,CAAA,MAAO;AACL,YAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AAGzB,cAAA,MAAM,MAAA,CAAO,WAAA;AAAA,gBACX,IAAA,CAAK,OAAA,CACF,MAAA,CAAO,CAAC,MAAA,KAAW,MAAM,CAAA,CACzB,GAAA,CAAI,CAAC,MAAA,KAAW,CAAC,MAAA,EAAQ,EAAE,CAAC;AAAA,eACjC;AAAA,YACF;AAAA,UACF;AAAA,QACF;AAEA,QAAA,IAAA,CAAK,WAAA,GAAc,CAAA;AACnB,QAAA,IAAA,CAAK,IAAA,GAAO,IAAI,KAAA,CAAM,IAAA,CAAK,SAAS,MAAM,CAAA,CAAE,KAAK,EAAE,CAAA;AACnD,QAAA,IAAA,CAAK,MAAA,GAAS,KAAA;AACd,QAAA;AAAA,MACF;AACE,QAAA,IAAA,CAAK,MAAA,GAAS,IAAA;AACd,QAAA,IAAA,CAAK,IAAA,CAAK,IAAA,CAAK,WAAW,CAAA,GAAI,KAAA,CAAM,KAAA;AACpC,QAAA;AAAA;AACJ,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAmBA,CAAC,MAAA,GAA8C;AAC7C,IAAA,IAAI,IAAA,CAAK,YAAY,MAAA,EAAW;AAC9B,MAAA,IAAI,KAAK,MAAA,EAAQ;AAIf,QAAA,MAAM,MAAA,CAAO,WAAA;AAAA,UACX,IAAA,CAAK,OAAA,CACF,GAAA,CAAI,CAAC,MAAA,EAAQ,KAAA,KAAU,CAAC,MAAA,EAAQ,KAAK,CAAU,CAAA,CAC/C,MAAA,CAAO,CAAC,CAAC,MAAM,CAAA,KAAM,MAAM,CAAA,CAC3B,GAAA,CAAI,CAAC,CAAC,QAAQ,KAAK,CAAA,KAAM,CAAC,MAAA,EAAQ,IAAA,CAAK,IAAA,CAAK,EAAA,CAAG,KAAK,CAAC,CAAC;AAAA,SAC3D;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAAA,EAEA,gBAAA,GAAyB;AACvB,IAAA,IAAI,IAAA,CAAK,WAAA,GAAc,CAAA,GAAI,IAAA,CAAK,cAAA,EAAgB;AAC9C,MAAA,MAAM,IAAI,UAAA;AAAA,QACR,CAAA,aAAA,EAAgB,IAAA,CAAK,WAAA,GAAc,CAAC,CAAA,oCAAA,EAAuC,KAAK,cAAc,CAAA,EAC5F,IAAA,CAAK,iBAAA,GAAoB,CAAA,QAAA,EAAW,IAAA,CAAK,iBAAiB,CAAA,CAAA,GAAK,EACjE,CAAA,EAAG,IAAA,CAAK,OAAA,GAAU,CAAA,IAAA,EAAO,IAAA,CAAK,SAAA,CAAU,IAAA,CAAK,OAAO,CAAC,CAAA,CAAA,GAAK,EAAE,CAAA;AAAA,OAC9D;AAAA,IACF;AAAA,EACF;AAAA,EAEA,WAAW,MAAA,EAAgB;AACzB,IAAA,IAAI,MAAA,CAAO,MAAA,GAAS,IAAA,CAAK,cAAA,EAAgB;AACvC,MAAA,MAAM,IAAI,UAAA;AAAA,QACR,uBAAuB,MAAA,CAAO,MAAM,CAAA,oCAAA,EAAuC,IAAA,CAAK,cAAc,CAAA,EAC5F,IAAA,CAAK,OAAA,GAAU,CAAA,IAAA,EAAO,KAAK,SAAA,CAAU,IAAA,CAAK,OAAO,CAAC,KAAK,EACzD,CAAA;AAAA,OACF;AAAA,IACF;AACA,IAAA,IAAA,CAAK,OAAA,GAAU,MAAA;AACf,IAAA,IAAI,IAAA,CAAK,OAAA,CAAQ,MAAA,KAAW,CAAA,EAAG;AAC7B,MAAA,MAAM,IAAI,WAAW,+BAAA,EAAiC;AAAA,QACpD,QAAQ,IAAA,CAAK;AAAA,OACd,CAAA;AAAA,IACH;AACA,IAAA,IAAI,IAAI,IAAI,IAAA,CAAK,OAAO,EAAE,IAAA,KAAS,IAAA,CAAK,QAAQ,MAAA,EAAQ;AACtD,MAAA,MAAM,IAAI,WAAW,+CAAA,EAAiD;AAAA,QACpE,QAAQ,IAAA,CAAK;AAAA,OACd,CAAA;AAAA,IACH;AAAA,EACF;AACF;;;;"}

package/dist/CSVRecordAssemblerTransformer.d.ts

@@ -1,12 +1,12 @@
 import { CSVRecordAssembler } from './CSVRecordAssembler.ts';
-import { CSVRecord, CSVRecordAssemblerOptions, ExtendedQueuingStrategy, Token } from './common/types.ts';
+import { CSVRecord, CSVRecordAssemblerOptions, Token } from './common/types.ts';
 /**
  * A transform stream that converts a stream of tokens into a stream of CSV records.
  *
  * @template Header The type of the header row.
- * @param options - CSV-specific options (header, maxFieldCount, etc.)
- * @param writableStrategy - Strategy for the writable side (default: `{ highWaterMark: 1024, size: () => 1, checkInterval: 10 }`)
- * @param readableStrategy - Strategy for the readable side (default: `{ highWaterMark: 256, size: () => 1, checkInterval: 10 }`)
+ * @param options - CSV-specific options (header, maxFieldCount, checkInterval, etc.)
+ * @param writableStrategy - Strategy for the writable side (default: `{ highWaterMark: 1024, size: () => 1 }`)
+ * @param readableStrategy - Strategy for the readable side (default: `{ highWaterMark: 256, size: () => 1 }`)
  *
  * @category Low-level API
  *
@@ -65,17 +65,11 @@ import { CSVRecord, CSVRecordAssemblerOptions, ExtendedQueuingStrategy, Token }
  * @example Custom queuing strategies with backpressure tuning
  * ```ts
  * const transformer = new CSVRecordAssemblerTransformer(
- *   {},
  *   {
- *     highWaterMark: 2048,  // 2048 tokens
- *     size: () => 1,        // Each token counts as 1
- *     checkInterval: 20     // Check backpressure every 20 records
+ *     backpressureCheckInterval: 20  // Check backpressure every 20 records
  *   },
- *   {
- *     highWaterMark: 512,   // 512 records
- *     size: () => 1,        // Each record counts as 1
- *     checkInterval: 5      // Check backpressure every 5 records
- *   }
+ *   new CountQueuingStrategy({ highWaterMark: 2048 }),  // 2048 tokens
+ *   new CountQueuingStrategy({ highWaterMark: 512 })    // 512 records
  * );
  *
  * await tokenStream
@@ -91,5 +85,5 @@ export declare class CSVRecordAssemblerTransformer<Header extends ReadonlyArray<
      * @internal
      */
     protected yieldToEventLoop(): Promise<void>;
-    constructor(options?: CSVRecordAssemblerOptions<Header>, writableStrategy?: ExtendedQueuingStrategy<Token>, readableStrategy?: ExtendedQueuingStrategy<CSVRecord<Header>>);
+    constructor(options?: CSVRecordAssemblerOptions<Header>, writableStrategy?: QueuingStrategy<Token>, readableStrategy?: QueuingStrategy<CSVRecord<Header>>);
 }

package/dist/CSVRecordAssemblerTransformer.js

@@ -1,5 +1,13 @@
 import { CSVRecordAssembler } from './CSVRecordAssembler.js';
 
+const DEFAULT_WRITABLE_STRATEGY = new CountQueuingStrategy({
+  highWaterMark: 1024
+  // 1024 tokens
+});
+const DEFAULT_READABLE_STRATEGY = new CountQueuingStrategy({
+  highWaterMark: 256
+  // 256 records
+});
 class CSVRecordAssemblerTransformer extends TransformStream {
   assembler;
   /**
@@ -10,23 +18,9 @@ class CSVRecordAssemblerTransformer extends TransformStream {
   async yieldToEventLoop() {
     await new Promise((resolve) => setTimeout(resolve, 0));
   }
-  constructor(options = {}, writableStrategy = {
-    highWaterMark: 1024,
-    // 1024 tokens
-    size: () => 1,
-    // Each token counts as 1
-    checkInterval: 10
-    // Check backpressure every 10 records
-  }, readableStrategy = {
-    highWaterMark: 256,
-    // 256 records
-    size: () => 1,
-    // Each record counts as 1
-    checkInterval: 10
-    // Check backpressure every 10 records
-  }) {
+  constructor(options = {}, writableStrategy = DEFAULT_WRITABLE_STRATEGY, readableStrategy = DEFAULT_READABLE_STRATEGY) {
     const assembler = new CSVRecordAssembler(options);
-    const checkInterval = writableStrategy.checkInterval ?? readableStrategy.checkInterval ?? 10;
+    const checkInterval = options.backpressureCheckInterval ?? 10;
     super(
       {
         transform: async (token, controller) => {