qvdjs 2.0.0 → 2.0.2

package/dist/index.cjs

@@ -5,7 +5,7 @@ var path2 = require('path');
 var assert3 = require('assert');
 var crypto2 = require('crypto');
 var promises = require('timers/promises');
-var xml2 = require('xml2js');
+var xml = require('xml2js');
 var os = require('os');
 var v8 = require('v8');
 var util = require('util');
@@ -16,7 +16,7 @@ var fs2__default = /*#__PURE__*/_interopDefault(fs2);
 var path2__default = /*#__PURE__*/_interopDefault(path2);
 var assert3__default = /*#__PURE__*/_interopDefault(assert3);
 var crypto2__default = /*#__PURE__*/_interopDefault(crypto2);
-var xml2__default = /*#__PURE__*/_interopDefault(xml2);
+var xml__default = /*#__PURE__*/_interopDefault(xml);
 var os__default = /*#__PURE__*/_interopDefault(os);
 var v8__default = /*#__PURE__*/_interopDefault(v8);
 
@@ -1098,8 +1098,12 @@ function fieldGeometry(bitOffset, bitWidth) {
     byteCount: bitWidth === 0 ? 0 : shift + bitWidth + 7 >>> 3
   };
 }
-function decodeIndexColumn(buffer, recordSize, rowCount, bitOffset, bitWidth, bias, out) {
+function decodeIndexColumn(buffer, recordSize, rowCount, bitOffset, bitWidth, bias, out, bounds = null) {
+  const symbolCount = bounds === null ? Infinity : bounds.symbolCount;
   if (bitWidth === 0) {
+    if (bounds !== null && rowCount > 0 && bias >= symbolCount) {
+      refuse2(bounds, 0, bias, bias);
+    }
     out.fill(bias, 0, rowCount);
     return out;
   }
@@ -1113,10 +1117,25 @@ function decodeIndexColumn(buffer, recordSize, rowCount, bitOffset, bitWidth, bi
     if (byteCount > 2) acc += buffer[base + 2] * 65536;
     if (byteCount > 3) acc += buffer[base + 3] * 16777216;
     if (byteCount > 4) acc += buffer[base + 4] * 4294967296;
-    out[row] = Math.floor(acc / divisor) % modulus + bias;
+    const index = Math.floor(acc / divisor) % modulus + bias;
+    if ((index >= symbolCount || index < 0 && index !== bias) && bounds !== null) {
+      refuse2(bounds, row, index, bias);
+    }
+    out[row] = index;
   }
   return out;
 }
+function refuse2(bounds, row, index, bias) {
+  throw new exports.QvdCorruptedError("Symbol index out of range", {
+    field: bounds.field,
+    row: bounds.firstRow + row,
+    symbolIndex: index,
+    symbolCount: bounds.symbolCount,
+    bias,
+    file: bounds.file,
+    stage: "parseIndexTable"
+  });
+}
 function writeBitField(buffer, recordBase, geometry, value) {
   const { byteStart, shift, byteCount } = geometry;
   if (byteCount === 0) {
@@ -1133,10 +1152,12 @@ function writeBitField(buffer, recordBase, geometry, value) {
 var MAX_BIT_WIDTH, POW2;
 var init_bitUtils = __esm({
   "src/util/bitUtils.js"() {
+    init_QvdErrors();
     MAX_BIT_WIDTH = 31;
     POW2 = Array.from({ length: 41 }, (_, exponent) => 2 ** exponent);
     __name(fieldGeometry, "fieldGeometry");
     __name(decodeIndexColumn, "decodeIndexColumn");
+    __name(refuse2, "refuse");
     __name(writeBitField, "writeBitField");
   }
 });
@@ -1781,7 +1802,7 @@ var init_QvdFileWriter = __esm({
             });
           }
         }
-        const builder = new xml2__default.default.Builder({
+        const builder = new xml__default.default.Builder({
           renderOpts: {
             pretty: true,
             newline: "\r\n",
@@ -2343,6 +2364,13 @@ var init_memoryUtils = __esm({
 });
 
 // src/util/validationUtils.js
+function headerInteger(value) {
+  if (typeof value !== "string" || !/^\s*-?\d+\s*$/.test(value)) {
+    return NaN;
+  }
+  const number = Number(value);
+  return number === 0 ? 0 : number;
+}
 function validateHeaderStructure(headerObj, filePath, stage) {
   const tableHeader = headerObj?.["QvdTableHeader"];
   if (tableHeader === null || typeof tableHeader !== "object" || Array.isArray(tableHeader)) {
@@ -2352,7 +2380,7 @@ function validateHeaderStructure(headerObj, filePath, stage) {
       stage
     });
   }
-  const symbolTableLength = parseInt(tableHeader["Offset"], 10);
+  const symbolTableLength = headerInteger(tableHeader["Offset"]);
   if (isNaN(symbolTableLength) || !Number.isSafeInteger(symbolTableLength) || symbolTableLength < 0) {
     throw new exports.QvdCorruptedError("Invalid symbol table offset", {
       offset: tableHeader["Offset"],
@@ -2360,6 +2388,47 @@ function validateHeaderStructure(headerObj, filePath, stage) {
       stage
     });
   }
+  const fields = tableHeader["Fields"]?.["QvdFieldHeader"];
+  const fieldList = fields === void 0 || fields === null ? [] : Array.isArray(fields) ? fields : [fields];
+  if (fieldList.length === 0) {
+    throw new exports.QvdCorruptedError("The QVD file header declares no fields", {
+      file: filePath,
+      stage
+    });
+  }
+  const malformedIndex = fieldList.findIndex(
+    (field) => field === null || typeof field !== "object" || Array.isArray(field)
+  );
+  if (malformedIndex !== -1) {
+    throw new exports.QvdCorruptedError("The QVD file header declares a field with no properties", {
+      fieldIndex: malformedIndex,
+      fieldCount: fieldList.length,
+      file: filePath,
+      stage
+    });
+  }
+  const seen = /* @__PURE__ */ new Map();
+  fieldList.forEach((field, fieldIndex) => {
+    const name = field["FieldName"];
+    if (typeof name !== "string" || name === "") {
+      throw new exports.QvdCorruptedError("The QVD file header declares a field with no usable name", {
+        fieldIndex,
+        fieldName: name,
+        file: filePath,
+        stage
+      });
+    }
+    if (seen.has(name)) {
+      throw new exports.QvdCorruptedError("The QVD file header declares two fields with the same name", {
+        field: name,
+        fieldIndexes: [seen.get(name), fieldIndex],
+        file: filePath,
+        stage
+      });
+    }
+    seen.set(name, fieldIndex);
+  });
+  return fieldList;
 }
 function validateSymbolTableSizeEarly(symbolTableLength, filePath) {
   const heapLimit = getHeapLimit();
@@ -2405,8 +2474,8 @@ function validateSymbolTableSize(symbolTableLength, filePath, totalRows) {
   }
 }
 function validateFieldMetadata(field, symbolBufferLength, filePath) {
-  const symbolsOffset = parseInt(field["Offset"], 10);
-  const symbolsLength = parseInt(field["Length"], 10);
+  const symbolsOffset = headerInteger(field["Offset"]);
+  const symbolsLength = headerInteger(field["Length"]);
   if (isNaN(symbolsOffset) || !Number.isSafeInteger(symbolsOffset) || symbolsOffset < 0) {
     throw new exports.QvdCorruptedError("Invalid symbol offset", {
       field: field["FieldName"],
@@ -2434,6 +2503,63 @@ function validateFieldMetadata(field, symbolBufferLength, filePath) {
     });
   }
 }
+function firstOverlap(ranges) {
+  const claimed = ranges.filter((range) => range.length > 0).sort((a, b) => a.start - b.start);
+  let furthest = null;
+  for (const range of claimed) {
+    if (furthest !== null && range.start < furthest.start + furthest.length) {
+      return [furthest, range];
+    }
+    if (furthest === null || range.start + range.length > furthest.start + furthest.length) {
+      furthest = range;
+    }
+  }
+  return null;
+}
+function validateSymbolAreas(fields, filePath) {
+  const overlap = firstOverlap(
+    fields.map((field) => ({
+      field: field["FieldName"],
+      start: headerInteger(field["Offset"]),
+      length: headerInteger(field["Length"])
+    }))
+  );
+  if (overlap !== null) {
+    const [first, second] = overlap;
+    throw new exports.QvdCorruptedError("Symbol areas overlap", {
+      field: second.field,
+      offset: second.start,
+      length: second.length,
+      overlaps: first.field,
+      overlapsOffset: first.start,
+      overlapsLength: first.length,
+      file: filePath,
+      stage: "parseSymbolTable"
+    });
+  }
+}
+function validateBitFields(fields, filePath) {
+  const overlap = firstOverlap(
+    fields.map((field) => ({
+      field: field["FieldName"],
+      start: headerInteger(field["BitOffset"]),
+      length: headerInteger(field["BitWidth"])
+    }))
+  );
+  if (overlap !== null) {
+    const [first, second] = overlap;
+    throw new exports.QvdCorruptedError("Bit fields overlap", {
+      field: second.field,
+      bitOffset: second.start,
+      bitWidth: second.length,
+      overlaps: first.field,
+      overlapsBitOffset: first.start,
+      overlapsBitWidth: first.length,
+      file: filePath,
+      stage: "parseIndexTable"
+    });
+  }
+}
 function validateRecordCount(totalRows, filePath, stage = "parseIndexTable") {
   if (isNaN(totalRows) || !Number.isSafeInteger(totalRows) || totalRows < 0) {
     throw new exports.QvdCorruptedError("Invalid number of records", {
@@ -2443,14 +2569,17 @@ function validateRecordCount(totalRows, filePath, stage = "parseIndexTable") {
     });
   }
 }
-function validateIndexTableMetadata(recordSize, totalRows, indexTableLength, indexTableOffset, bufferLength, rowsToLoad, filePath, fileSize = null, windowFirstRow = 0, bufferFirstRow = 0) {
+function validateRecordSize(recordSize, filePath, stage = "parseIndexTable") {
   if (isNaN(recordSize) || !Number.isSafeInteger(recordSize) || recordSize < 0) {
     throw new exports.QvdCorruptedError("Invalid record byte size", {
       recordSize,
       file: filePath,
-      stage: "parseIndexTable"
+      stage
     });
   }
+}
+function validateIndexTableMetadata(recordSize, totalRows, indexTableLength, indexTableOffset, bufferLength, rowsToLoad, filePath, fileSize = null, windowFirstRow = 0, bufferFirstRow = 0) {
+  validateRecordSize(recordSize, filePath);
   validateRecordCount(totalRows, filePath);
   if (recordSize === 0 && totalRows > 0) {
     throw new exports.QvdCorruptedError("Record byte size cannot be zero when records exist", {
@@ -2534,8 +2663,8 @@ function validateIndexTableMetadata(recordSize, totalRows, indexTableLength, ind
   }
 }
 function validateFieldBitMetadata(field, recordSize, filePath) {
-  const bitOffset = parseInt(field["BitOffset"], 10);
-  const bitWidth = parseInt(field["BitWidth"], 10);
+  const bitOffset = headerInteger(field["BitOffset"]);
+  const bitWidth = headerInteger(field["BitWidth"]);
   if (isNaN(bitOffset) || !Number.isSafeInteger(bitOffset) || bitOffset < 0) {
     throw new exports.QvdCorruptedError("Invalid bit offset", {
       field: field["FieldName"],
@@ -2552,7 +2681,7 @@ function validateFieldBitMetadata(field, recordSize, filePath) {
       stage: "parseIndexTable"
     });
   }
-  const bias = parseInt(field["Bias"], 10);
+  const bias = headerInteger(field["Bias"]);
   if (isNaN(bias) || !Number.isSafeInteger(bias)) {
     throw new exports.QvdCorruptedError("Invalid bias", {
       field: field["FieldName"],
@@ -2570,6 +2699,23 @@ function validateFieldBitMetadata(field, recordSize, filePath) {
       stage: "parseIndexTable"
     });
   }
+  if (bias < -2147483648 || bias + 2 ** bitWidth - 1 > 2 ** 31 - 1) {
+    throw new exports.QvdCorruptedError("Bias out of range", {
+      field: field["FieldName"],
+      bias,
+      bitWidth,
+      file: filePath,
+      stage: "parseIndexTable"
+    });
+  }
+  if (bias !== 0 && bias !== -2) {
+    throw new exports.QvdCorruptedError("Bias is neither 0 nor -2", {
+      field: field["FieldName"],
+      bias,
+      file: filePath,
+      stage: "parseIndexTable"
+    });
+  }
   const recordSizeInBits = recordSize * 8;
   if (bitOffset + bitWidth > recordSizeInBits) {
     throw new exports.QvdCorruptedError("Bit field extends beyond record size", {
@@ -2587,11 +2733,16 @@ var init_validationUtils = __esm({
     init_QvdErrors();
     init_memoryUtils();
     init_bitUtils();
+    __name(headerInteger, "headerInteger");
     __name(validateHeaderStructure, "validateHeaderStructure");
     __name(validateSymbolTableSizeEarly, "validateSymbolTableSizeEarly");
     __name(validateSymbolTableSize, "validateSymbolTableSize");
     __name(validateFieldMetadata, "validateFieldMetadata");
+    __name(firstOverlap, "firstOverlap");
+    __name(validateSymbolAreas, "validateSymbolAreas");
+    __name(validateBitFields, "validateBitFields");
     __name(validateRecordCount, "validateRecordCount");
+    __name(validateRecordSize, "validateRecordSize");
     __name(validateIndexTableMetadata, "validateIndexTableMetadata");
     __name(validateFieldBitMetadata, "validateFieldBitMetadata");
   }
@@ -2697,7 +2848,10 @@ function parseFieldSymbols(symbolBuffer, start, end, keep, fieldName, filePath)
   }
   return { numbers, texts };
 }
-var MAX_TEXT_BYTES;
+function countFieldSymbols(symbolBuffer, start, end, fieldName, filePath) {
+  return parseFieldSymbols(symbolBuffer, start, end, DECODE_NOTHING, fieldName, filePath).numbers.length;
+}
+var MAX_TEXT_BYTES, DECODE_NOTHING;
 var init_symbolParser = __esm({
   "src/util/symbolParser.js"() {
     init_QvdErrors();
@@ -2705,6 +2859,8 @@ var init_symbolParser = __esm({
     __name(textEnd, "textEnd");
     __name(overflow, "overflow");
     __name(parseFieldSymbols, "parseFieldSymbols");
+    DECODE_NOTHING = /* @__PURE__ */ new Set();
+    __name(countFieldSymbols, "countFieldSymbols");
   }
 });
 
@@ -3218,7 +3374,32 @@ async function* chunksFrom(handle, chunkSize, failed) {
     position += bytesRead;
   }
 }
-var MAX_HEADER_SIZE, READ_CHUNK_SIZE, ANALYSIS_SLICE_ROWS; exports.QvdFileReader = void 0;
+async function parseHeaderXml(text, file, stage) {
+  let parsed;
+  try {
+    parsed = await xml__default.default.parseStringPromise(text, { explicitArray: false });
+  } catch (error) {
+    throw new exports.QvdParseError(
+      "The XML header could not be parsed.",
+      {
+        // The first line of the parser's message. The rest is the line and column it stopped at, which
+        // stay on `cause`.
+        reason: String(
+          /** @type {any} */
+          error?.message ?? error
+        ).split("\n")[0],
+        file,
+        stage
+      },
+      { cause: error }
+    );
+  }
+  if (!parsed) {
+    throw new exports.QvdParseError("The XML header could not be parsed.", { file, stage });
+  }
+  return parsed;
+}
+var MAX_HEADER_SIZE, READ_CHUNK_SIZE, ANALYSIS_SLICE_ROWS, COUNT_SYMBOLS_PAST; exports.QvdFileReader = void 0;
 var init_QvdFileReader = __esm({
   "src/QvdFileReader.js"() {
     init_QvdDataFrame();
@@ -3236,7 +3417,9 @@ var init_QvdFileReader = __esm({
     MAX_HEADER_SIZE = 16 * 1024 * 1024;
     READ_CHUNK_SIZE = 512 * 1024 * 1024;
     ANALYSIS_SLICE_ROWS = 65536;
+    COUNT_SYMBOLS_PAST = 65536;
     __name(chunksFrom, "chunksFrom");
+    __name(parseHeaderXml, "parseHeaderXml");
     exports.QvdFileReader = class {
       static {
         __name(this, "QvdFileReader");
@@ -3472,29 +3655,19 @@ var init_QvdFileReader = __esm({
         const headerBuffer = Buffer.concat(headerChunks);
         const headerEndIndex = headerDelimiterIndex + HEADER_DELIMITER.length;
         const headerXml = headerBuffer.subarray(0, headerEndIndex).toString();
-        const headerObj = await xml2__default.default.parseStringPromise(headerXml, { explicitArray: false });
-        if (!headerObj) {
-          throw new exports.QvdParseError("The XML header could not be parsed.", {
-            file: this._path,
-            stage: "readData"
-          });
-        }
-        validateHeaderStructure(headerObj, this._path, "readData");
+        const headerObj = await parseHeaderXml(headerXml, this._path, "readData");
+        const headerFields = validateHeaderStructure(headerObj, this._path, "readData");
         const symbolTableOffset = headerEndIndex;
-        const symbolTableLength = parseInt(headerObj["QvdTableHeader"]["Offset"], 10);
+        const symbolTableLength = headerInteger(headerObj["QvdTableHeader"]["Offset"]);
         const indexTableOffset = symbolTableOffset + symbolTableLength;
-        const recordSize = parseInt(headerObj["QvdTableHeader"]["RecordByteSize"], 10);
-        const totalRows = parseInt(headerObj["QvdTableHeader"]["NoOfRecords"], 10);
+        const recordSize = headerInteger(headerObj["QvdTableHeader"]["RecordByteSize"]);
+        const totalRows = headerInteger(headerObj["QvdTableHeader"]["NoOfRecords"]);
         if (headerOnly) {
           this._buffer = headerBuffer.subarray(0, headerEndIndex);
           this._emitProgress("read", 1, 1);
           return;
         }
-        let headerFields = headerObj["QvdTableHeader"]?.["Fields"]?.["QvdFieldHeader"];
-        if (headerFields && !Array.isArray(headerFields)) {
-          headerFields = [headerFields];
-        }
-        const columnCount = Array.isArray(headerFields) ? selectFields(headerFields, this._requestedFields, this._path).length : 0;
+        const columnCount = selectFields(headerFields, this._requestedFields, this._path).length;
         const headerNumbersUsable = [symbolTableLength, recordSize, totalRows].every(
           (value) => Number.isSafeInteger(value) && value >= 0
         );
@@ -3526,20 +3699,8 @@ var init_QvdFileReader = __esm({
         }
         const rowsToLoad = windowRows;
         validateSymbolTableSizeEarly(symbolTableLength, this._path);
-        for (const [name, value] of [
-          ["Offset", symbolTableLength],
-          ["RecordByteSize", recordSize],
-          ["NoOfRecords", totalRows]
-        ]) {
-          if (!Number.isSafeInteger(value) || Number(value) < 0) {
-            throw new exports.QvdCorruptedError(`Invalid header value: ${name}`, {
-              name,
-              value,
-              file: this._path,
-              stage: "readData"
-            });
-          }
-        }
+        validateRecordSize(recordSize, this._path, "readData");
+        validateRecordCount(totalRows, this._path, "readData");
         const skippedIndexBytes = resolved.offset * recordSize;
         const indexTableBytesToRead = rowsToLoad * recordSize;
         const totalBytesToRead = indexTableOffset + indexTableBytesToRead;
@@ -3637,36 +3798,12 @@ var init_QvdFileReader = __esm({
         }
         const headerEndIndex = headerDelimiterIndex + HEADER_DELIMITER.length;
         const headerBuffer = this._buffer.subarray(headerBeginIndex, headerEndIndex);
-        this._header = await xml2__default.default.parseStringPromise(headerBuffer.toString(), { explicitArray: false });
-        if (!this._header) {
-          throw new exports.QvdParseError("The XML header could not be parsed.", {
-            file: this._path,
-            stage: "parseHeader"
-          });
-        }
-        validateHeaderStructure(this._header, this._path, "parseHeader");
-        const fields = this._header["QvdTableHeader"]?.["Fields"]?.["QvdFieldHeader"];
-        const fieldList = fields === void 0 || fields === null ? [] : Array.isArray(fields) ? fields : [fields];
-        if (fieldList.length === 0) {
-          throw new exports.QvdCorruptedError("The QVD file header declares no fields", {
-            file: this._path,
-            stage: "parseHeader"
-          });
-        }
-        const malformedIndex = fieldList.findIndex(
-          (field) => field === null || typeof field !== "object" || Array.isArray(field)
-        );
-        if (malformedIndex !== -1) {
-          throw new exports.QvdCorruptedError("The QVD file header declares a field with no properties", {
-            fieldIndex: malformedIndex,
-            fieldCount: fieldList.length,
-            file: this._path,
-            stage: "parseHeader"
-          });
-        }
+        this._fieldBitMetadataValidated = false;
+        this._header = await parseHeaderXml(headerBuffer.toString(), this._path, "parseHeader");
+        const fieldList = validateHeaderStructure(this._header, this._path, "parseHeader");
         this._headerOffset = headerBeginIndex;
         this._symbolTableOffset = headerEndIndex;
-        this._indexTableOffset = this._symbolTableOffset + parseInt(this._header["QvdTableHeader"]["Offset"], 10);
+        this._indexTableOffset = this._symbolTableOffset + headerInteger(this._header["QvdTableHeader"]["Offset"]);
         this._allFields = fieldList;
         this._selectedFields = selectFields(this._allFields, this._requestedFields, this._path);
       }
@@ -3682,8 +3819,8 @@ var init_QvdFileReader = __esm({
        * @param {QvdRowWindow} window The rows of interest, as file row indices.
        * @param {string} stage Stage name for any error raised here.
        * @return {{fields: Array<any>, recordSize: number, totalRows: number, rowsToLoad: number,
-       *   indexBuffer: Buffer}} The record geometry. `indexBuffer` starts at the window's first
-       *   record, so the decoder always counts from zero.
+       *   indexBuffer: Buffer, firstRow: number}} The record geometry. `indexBuffer` starts at the
+       *   window's first record, file row `firstRow`, so the decoder always counts from zero.
        * @private
        */
       _planIndexTable(window, stage) {
@@ -3698,9 +3835,9 @@ var init_QvdFileReader = __esm({
         }
         const allFields = this._allFields;
         const fields = this._selectedFields;
-        const recordSize = parseInt(this._header["QvdTableHeader"]["RecordByteSize"], 10);
-        const totalRows = parseInt(this._header["QvdTableHeader"]["NoOfRecords"], 10);
-        const indexTableLength = parseInt(this._header["QvdTableHeader"]["Length"], 10);
+        const recordSize = headerInteger(this._header["QvdTableHeader"]["RecordByteSize"]);
+        const totalRows = headerInteger(this._header["QvdTableHeader"]["NoOfRecords"]);
+        const indexTableLength = headerInteger(this._header["QvdTableHeader"]["Length"]);
         const { offset: firstRow, limit: rowsToLoad } = resolveWindow(window, totalRows);
         validateIndexTableMetadata(
           recordSize,
@@ -3723,13 +3860,14 @@ var init_QvdFileReader = __esm({
           for (const field of allFields) {
             validateFieldBitMetadata(field, recordSize, this._path);
           }
+          validateBitFields(allFields, this._path);
           this._fieldBitMetadataValidated = true;
         }
         assert3__default.default(
           rowsToLoad === 0 || recordSize === 0 || Math.floor(indexBuffer.length / recordSize) >= rowsToLoad,
           `The index table holds ${Math.floor(indexBuffer.length / (recordSize || 1))} whole records but ${rowsToLoad} were validated as present.`
         );
-        return { fields, recordSize, totalRows, rowsToLoad, indexBuffer };
+        return { fields, recordSize, totalRows, rowsToLoad, indexBuffer, firstRow };
       }
       /**
        * Analyzes the index table to determine which symbols are actually needed.
@@ -3753,9 +3891,12 @@ var init_QvdFileReader = __esm({
           this._throwIfAborted();
           const needed = /* @__PURE__ */ new Set();
           symbolUsage[position] = needed;
-          const bitOffset = parseInt(field["BitOffset"], 10);
-          const bitWidth = parseInt(field["BitWidth"], 10);
-          const bias = parseInt(field["Bias"], 10);
+          const bitOffset = headerInteger(field["BitOffset"]);
+          const bitWidth = headerInteger(field["BitWidth"]);
+          const bias = headerInteger(field["Bias"]);
+          const length = headerInteger(field["Length"]);
+          let indexLimit = Number.isSafeInteger(length) && length >= 0 ? Math.ceil(length / 2) : Infinity;
+          let counted = false;
           for (let first = 0; first < rowsToLoad; first += sliceRows) {
             const count = Math.min(sliceRows, rowsToLoad - first);
             decodeIndexColumn(
@@ -3768,15 +3909,53 @@ var init_QvdFileReader = __esm({
               column
             );
             for (let row = 0; row < count; row++) {
-              if (column[row] >= 0) {
+              if (column[row] >= 0 && column[row] < indexLimit) {
                 needed.add(column[row]);
               }
             }
+            if (!counted && needed.size > COUNT_SYMBOLS_PAST) {
+              counted = true;
+              indexLimit = Math.min(indexLimit, this._countFieldSymbols(field));
+              for (const index of needed) {
+                if (index >= indexLimit) {
+                  needed.delete(index);
+                }
+              }
+            }
           }
           this._emitProgress("symbol-analysis", position + 1, fields.length);
         });
         return symbolUsage;
       }
+      /**
+       * How many symbols a field holds, for the symbol-usage pass, which runs before the symbols are parsed.
+       *
+       * The count is `countFieldSymbols`, the parse itself told to decode nothing, so it is the count
+       * `_parseSymbolTable` will produce and `_parseIndexTable` will check against. The field's area is
+       * validated first, as `_parseSymbolTable` would, so a damaged `Offset` or `Length` is reported the
+       * same way wherever it is met.
+       *
+       * @param {any} field The field's header.
+       * @return {number} Its symbols.
+       * @throws {QvdCorruptedError} If the area is not inside the symbol table, or a symbol runs past it.
+       * @private
+       */
+      _countFieldSymbols(field) {
+        assert3__default.default(
+          this._buffer && this._symbolTableOffset && this._indexTableOffset,
+          "The QVD file has not been read before its symbols were counted."
+        );
+        const symbolBuffer = this._buffer.subarray(this._symbolTableOffset, this._indexTableOffset);
+        validateFieldMetadata(field, symbolBuffer.length, this._path);
+        const offset = headerInteger(field["Offset"]);
+        return countFieldSymbols(
+          symbolBuffer,
+          offset,
+          offset + headerInteger(field["Length"]),
+          field["FieldName"],
+          this._path
+        );
+      }
       /**
        * Parses the symbol table of the QVD file. This method is part of the parsing process
        * and should not be called directly.
@@ -3807,7 +3986,7 @@ var init_QvdFileReader = __esm({
         const fields = this._selectedFields;
         const symbolBuffer = this._buffer.subarray(this._symbolTableOffset, this._indexTableOffset);
         const symbolTableSize = symbolBuffer.length;
-        const totalRows = parseInt(this._header["QvdTableHeader"]["NoOfRecords"], 10);
+        const totalRows = headerInteger(this._header["QvdTableHeader"]["NoOfRecords"]);
         validateSymbolTableSize(symbolTableSize, this._path, totalRows);
         if (this._headerMatchesFile) {
           validateMemoryAvailability(
@@ -3825,10 +4004,11 @@ var init_QvdFileReader = __esm({
         for (const field of allFields) {
           validateFieldMetadata(field, symbolBuffer.length, this._path);
         }
+        validateSymbolAreas(allFields, this._path);
         this._symbolTable = fields.map((field, position) => {
           this._throwIfAborted();
-          const symbolsOffset = parseInt(field["Offset"], 10);
-          const symbolsLength = parseInt(field["Length"], 10);
+          const symbolsOffset = headerInteger(field["Offset"]);
+          const symbolsLength = headerInteger(field["Length"]);
           const symbols = parseFieldSymbols(
             symbolBuffer,
             symbolsOffset,
@@ -3862,25 +4042,35 @@ var init_QvdFileReader = __esm({
        * `base += recordSize`, so decoding rows k to k+n is a question of where the buffer slice starts
        * and how many iterations run. Nothing about the decoder changed to support it.
        *
+       * Every index is checked as it is decoded. One that addresses neither a symbol of its field nor
+       * NULL throws a `QvdCorruptedError` naming the file row (#125). Here and not where rows or columns
+       * are built, because every read decodes through this method and a columnar read hands its codes
+       * straight to the caller. Rows outside the window are not decoded, so they are not checked.
+       *
        * @param {QvdRowWindow} window The rows to decode.
+       * @throws {QvdCorruptedError} If an index in the window addresses neither a symbol nor NULL.
        */
       async _parseIndexTable(window) {
-        const { fields, recordSize, rowsToLoad, indexBuffer } = this._planIndexTable(window, "parseIndexTable");
-        this._rowsDecoded = rowsToLoad;
-        this._indexColumns = fields.map((field, position) => {
+        const { fields, recordSize, rowsToLoad, indexBuffer, firstRow } = this._planIndexTable(window, "parseIndexTable");
+        assert3__default.default(this._symbolTable, "The QVD file symbol table has not been parsed.");
+        const symbolTable = this._symbolTable;
+        const columns = fields.map((field, position) => {
           this._throwIfAborted();
           const column = decodeIndexColumn(
             indexBuffer,
             recordSize,
             rowsToLoad,
-            parseInt(field["BitOffset"], 10),
-            parseInt(field["BitWidth"], 10),
-            parseInt(field["Bias"], 10),
-            new Int32Array(rowsToLoad)
+            headerInteger(field["BitOffset"]),
+            headerInteger(field["BitWidth"]),
+            headerInteger(field["Bias"]),
+            new Int32Array(rowsToLoad),
+            { symbolCount: symbolTable[position].numbers.length, field: field["FieldName"], file: this._path, firstRow }
           );
           this._emitProgress("index-table", position + 1, fields.length);
           return column;
         });
+        this._indexColumns = columns;
+        this._rowsDecoded = rowsToLoad;
       }
       /**
        * Reads the file's schema and header metadata, without touching the symbol or index tables.
@@ -3902,23 +4092,13 @@ var init_QvdFileReader = __esm({
         await this._parseHeader();
         this._emitProgress("header", 1, 1);
         this._throwIfAborted();
-        assert3__default.default(this._header, "The QVD file header has not been parsed.");
+        assert3__default.default(this._header && this._allFields, "The QVD file header has not been parsed.");
         const header = this._header["QvdTableHeader"];
-        let fields = header["Fields"]?.["QvdFieldHeader"] ?? [];
-        if (!Array.isArray(fields)) {
-          fields = [fields];
-        }
-        if (fields.length === 0) {
-          throw new exports.QvdCorruptedError("The QVD file header declares no fields", {
-            file: this._path,
-            stage: "readMetadata"
-          });
-        }
-        const columns = fields.map((field) => field["FieldName"]);
-        const rowCount = parseInt(header["NoOfRecords"], 10);
+        const columns = this._allFields.map((field) => field["FieldName"]);
+        const rowCount = headerInteger(header["NoOfRecords"]);
         validateRecordCount(rowCount, this._path, "readMetadata");
         const shape = new exports.QvdDataFrame([], columns, header, {
-          symbolTableBytes: parseInt(header["Offset"], 10),
+          symbolTableBytes: headerInteger(header["Offset"]),
           totalRows: rowCount,
           rowsLoaded: 0,
           symbolFiltering: false,
@@ -4009,7 +4189,8 @@ var init_QvdFileReader = __esm({
        * `chunkSize * 2`, and why the heap it needs is twice what one chunk suggests.
        *
        * A window covering no rows yields nothing at all, rather than one empty frame - so
-       * `for await` over an exhausted offset does nothing, which is what a paging loop wants.
+       * `for await` over an exhausted offset does nothing, which is what a paging loop wants. Its header
+       * is still checked, as every read of a file's rows checks it.
        *
        * @param {number|null|{offset?: number, limit?: number|null, maxRows?: number|null}} window
        *   The rows to cover, in the same spellings `load()` accepts.
@@ -4027,6 +4208,10 @@ var init_QvdFileReader = __esm({
         const liveRows = { rows: chunkSize * 2, perChunk: 2 };
         const rows = normaliseWindow(window, this._path);
         const prepared = await this._prepare(rows, liveRows);
+        if (prepared.rowsAvailable === 0) {
+          this._planIndexTable({ offset: prepared.offset, limit: 0 }, "parseIndexTable");
+          return;
+        }
         for (let done = 0; done < prepared.rowsAvailable; done += chunkSize) {
           this._throwIfAborted();
           const count = Math.min(chunkSize, prepared.rowsAvailable - done);
@@ -4078,8 +4263,8 @@ var init_QvdFileReader = __esm({
         this._emitProgress("header", 1, 1);
         this._throwIfAborted();
         assert3__default.default(this._header, "The QVD file header has not been parsed.");
-        const totalRows = parseInt(this._header["QvdTableHeader"]["NoOfRecords"], 10);
-        const symbolTableLength = parseInt(this._header["QvdTableHeader"]["Offset"], 10);
+        const totalRows = headerInteger(this._header["QvdTableHeader"]["NoOfRecords"]);
+        const symbolTableLength = headerInteger(this._header["QvdTableHeader"]["Offset"]);
         const resolved = resolveWindow(window, totalRows);
         const rowsAvailable = resolved.limit;
         let symbolsToKeep = null;