@forzalabs/remora 2.5.0 → 2.6.1

package/workers/ExecutorWorker.js

@@ -11809,7 +11809,7 @@ var CONSTANTS, Constants_default;
 var init_Constants = __esm({
   "../../packages/constants/src/Constants.ts"() {
     CONSTANTS = {
-      cliVersion: "2.5.0",
+      cliVersion: "2.6.1",
       backendVersion: 1,
       backendPort: 5088,
       workerVersion: 2,
@@ -11937,7 +11937,7 @@ var init_Constants = __esm({
         /**
          * Record layouts one FIXED output may write into a single file, which is also how many write
          * streams its block-ordering pass holds open. A copybook of this size is already unusual —
-         * the NASCO POD feed writes five transaction types — and the bound stops a generated config
+         * a POD-style transaction feed may write five transaction types — and the bound stops a generated config
          * from opening a descriptor per distinct value of the wrong field.
          */
         MAX_FIXED_LAYOUTS: 64,
@@ -33745,21 +33745,29 @@ var init_CSVParser = __esm({
 });
 
 // ../../packages/parsing/src/DatasetCodec.ts
-var NULL_FIELD, NEEDS_ESCAPE, DatasetCodecClass, DatasetCodec, DatasetCodec_default;
+var NULL_FIELD, EMPTY_FIELD, NEEDS_ESCAPE, QUOTE_CODE, QUOTE_TESTS, DatasetCodecClass, DatasetCodec, DatasetCodec_default;
 var init_DatasetCodec = __esm({
   "../../packages/parsing/src/DatasetCodec.ts"() {
     init_src();
     NULL_FIELD = "";
+    EMPTY_FIELD = '""';
     NEEDS_ESCAPE = /["\n\r]/;
+    QUOTE_CODE = 34;
+    QUOTE_TESTS = /* @__PURE__ */ new Map([[",", /^\s|\s$|[",\n\r]/]]);
     DatasetCodecClass = class {
       constructor() {
         /**
-         * One value as an internal positional field: quoted, with `"`, `\n` and `\r` escaped - or the
-         * unquoted null marker when there is no value.
+         * One value as an internal positional field. Bare where it can be, quoted where it must be -
+         * around the delimiter, a quote, a line break or an edge space - or the unquoted null marker
+         * when there is no value. The delimiter is a parameter rather than a comma because `redelimit`
+         * re-encodes a staged line with the export's own: a tab is safe bare in the staged file and is
+         * not once that file is re-emitted tab-delimited.
          */
-        this.encodeField = (value) => {
+        this.encodeField = (value, delimiter = ",") => {
           if (value === null || value === void 0) return NULL_FIELD;
           const text = typeof value === "string" ? value : String(value);
+          if (text === "") return EMPTY_FIELD;
+          if (!this._quoteTest(delimiter).test(text)) return text;
           if (!NEEDS_ESCAPE.test(text)) return `"${text}"`;
           return `"${text.replaceAll('"', '""').replaceAll("\r", "\\r").replaceAll("\n", "\\n")}"`;
         };
@@ -33771,7 +33779,7 @@ var init_DatasetCodec = __esm({
           for (let index = 0; index < values.length; index++) {
             if (index > 0)
               row += delimiter;
-            row += this.encodeField(values[index]);
+            row += this.encodeField(values[index], delimiter);
           }
           return row;
         };
@@ -33791,26 +33799,26 @@ var init_DatasetCodec = __esm({
           let index = 0;
           while (index < length) {
             const char = line.charCodeAt(index);
-            if (char === 34) {
+            if (char === QUOTE_CODE) {
               if (!inQuotes) {
                 inQuotes = true;
                 hasQuotes = true;
                 fieldStart = index + 1;
-              } else if (line.charCodeAt(index + 1) === 34) {
+              } else if (line.charCodeAt(index + 1) === QUOTE_CODE) {
                 index++;
               } else {
                 inQuotes = false;
                 fieldEnd = index;
               }
             } else if (char === delimiterCode && !inQuotes) {
-              fields.push(this._field(line, fieldStart, fieldEnd, hasQuotes));
+              fields.push(this._field(line, fieldStart, hasQuotes ? fieldEnd : index, hasQuotes));
               fieldStart = index + 1;
               fieldEnd = 0;
               hasQuotes = false;
             }
             index++;
           }
-          fields.push(this._field(line, fieldStart, fieldEnd, hasQuotes));
+          fields.push(this._field(line, fieldStart, hasQuotes ? fieldEnd : length, hasQuotes));
           return fields;
         };
         /**
@@ -33821,9 +33829,24 @@ var init_DatasetCodec = __esm({
           Affirm_default(delimiter, "Invalid delimiter");
           return this.encodeRow(this.decodeRow(line), delimiter);
         };
-        /** One field's text, or null for the unquoted marker. Only a quoted token carries a value. */
+        /**
+         * The quoting test for one delimiter, built on first use. The four characters escaped into the
+         * class are the ones a character class reads as syntax; anything else stands for itself there.
+         */
+        this._quoteTest = (delimiter) => {
+          let test = QUOTE_TESTS.get(delimiter);
+          if (!test) {
+            test = new RegExp(`^\\s|\\s$|["\\n\\r${delimiter.replace(/[\\\]^-]/g, "\\$&")}]`);
+            QUOTE_TESTS.set(delimiter, test);
+          }
+          return test;
+        };
+        /**
+         * One field's text, or null for the unquoted empty marker. A bare token carries its value as it
+         * stands - nothing bare can hold a quote, so there is nothing to unescape in it.
+         */
         this._field = (line, start, end, hasQuotes) => {
-          if (!hasQuotes) return null;
+          if (!hasQuotes) return start === end ? null : line.slice(start, end);
           const raw = line.slice(start, end);
           return raw.indexOf('"') === -1 ? raw : raw.replaceAll('""', '"');
         };
@@ -34275,7 +34298,7 @@ var init_FixedWidthWriter = __esm({
          * `lf` output needs nothing here and a `crlf` one needs the `\r` that turns that newline into a
          * CRLF — which is exactly what a CRLF file looks like to anything that splits on `\n`.
          *
-         * A real positional feed picks one terminator and holds it: the NASCO POD files are CRLF on
+         * A real positional feed picks one terminator and holds it: some are CRLF on
          * every line including the last, and `lf` is the default everywhere else.
          */
         this.lineSuffix = (output) => {
@@ -56687,7 +56710,7 @@ var init_OutputExecutor = __esm({
           for (let index = 0; index < visibleKeys.length; index++) {
             if (index > 0)
               row += delimiter;
-            row += DatasetCodec_default.encodeField(record[visibleKeys[index]]);
+            row += DatasetCodec_default.encodeField(record[visibleKeys[index]], delimiter);
           }
           return row;
         };
@@ -56872,9 +56895,10 @@ var init_OutputExecutor = __esm({
           return resultList[0];
         };
         /**
-         * The header line of a positional export: the visible field names, in column order, quoted and
-         * delimited exactly as the rows under them — so the header parses with the same reader the data
-         * does. Null for a JSON/API output, where a record already carries its own field names, for a
+         * The header line of a positional export: the visible field names, in column order, written
+         * through the SAME codec as the rows under them — so a name is quoted on the same rule a value
+         * is, and the header parses with the reader the data does. Null for a JSON/API output, where a
+         * record already carries its own field names, for a
          * FIXED one, where a name does not fit the column it describes and the receiver reads by
          * position anyway, and for an output that turns the header off.
          *
@@ -56883,7 +56907,7 @@ var init_OutputExecutor = __esm({
         this._composeHeader = (output, dsSchema) => {
           if (output.header === false) return null;
           if (output.format !== "CSV" && output.format !== "TXT") return null;
-          return CSVParser_default.stringifyRow(DatasetSchema_default.names(dsSchema), this._getDelimiter(output));
+          return DatasetCodec_default.encodeRow(DatasetSchema_default.names(dsSchema), this._getDelimiter(output));
         };
         /** The delimiter the exported file is written with. Only TXT configures it; CSV is a comma. */
         this._getDelimiter = (output) => {