@js-ak/excel-toolbox 1.6.0 → 1.8.0

package/build/cjs/lib/template/template-memory.js

@@ -76,6 +76,7 @@ class TemplateMemory {
     constructor(files) {
         this.files = files;
     }
+    /** Private methods */
     /**
      * Ensures that this Template instance has not been destroyed.
      * @private
@@ -140,7 +141,7 @@ class TemplateMemory {
      * @throws {Error} If the file key is not found.
      * @experimental This API is experimental and might change in future versions.
      */
-    #extractXmlFromSheet(fileKey) {
+    async #extractXmlFromSheet(fileKey) {
         if (!this.files[fileKey]) {
             throw new Error(`${fileKey} not found`);
         }
@@ -158,7 +159,7 @@ class TemplateMemory {
      * @throws {Error} If the file key is not found
      * @experimental This API is experimental and might change in future versions.
      */
-    #extractRowsFromSheet(fileKey) {
+    async #extractRowsFromSheet(fileKey) {
         if (!this.files[fileKey]) {
             throw new Error(`${fileKey} not found`);
         }
@@ -172,15 +173,15 @@ class TemplateMemory {
      * @throws {Error} If the sheet with the given name does not exist.
      * @experimental This API is experimental and might change in future versions.
      */
-    #getSheetPathByName(sheetName) {
+    async #getSheetPathByName(sheetName) {
         // Find the sheet
-        const workbookXml = this.#extractXmlFromSheet(this.#excelKeys.workbook);
+        const workbookXml = await this.#extractXmlFromSheet(this.#excelKeys.workbook);
         const sheetMatch = workbookXml.match(Utils.sheetMatch(sheetName));
         if (!sheetMatch || !sheetMatch[1]) {
             throw new Error(`Sheet "${sheetName}" not found`);
         }
         const rId = sheetMatch[1];
-        const relsXml = this.#extractXmlFromSheet(this.#excelKeys.workbookRels);
+        const relsXml = await this.#extractXmlFromSheet(this.#excelKeys.workbookRels);
         const relMatch = relsXml.match(Utils.relationshipMatch(rId));
         if (!relMatch || !relMatch[1]) {
             throw new Error(`Relationship "${rId}" not found`);
@@ -233,11 +234,11 @@ class TemplateMemory {
         let sharedStringsContent = "";
         let sheetContent = "";
         if (this.files[sharedStringsPath]) {
-            sharedStringsContent = this.#extractXmlFromSheet(sharedStringsPath);
+            sharedStringsContent = await this.#extractXmlFromSheet(sharedStringsPath);
         }
-        const sheetPath = this.#getSheetPathByName(sheetName);
+        const sheetPath = await this.#getSheetPathByName(sheetName);
         if (this.files[sheetPath]) {
-            sheetContent = this.#extractXmlFromSheet(sheetPath);
+            sheetContent = await this.#extractXmlFromSheet(sheetPath);
             const TABLE_REGEX = /\$\{table:([a-zA-Z0-9_]+)\.([a-zA-Z0-9_]+)\}/g;
             const hasTablePlaceholders = TABLE_REGEX.test(sharedStringsContent) || TABLE_REGEX.test(sheetContent);
             if (hasTablePlaceholders) {
@@ -272,11 +273,11 @@ class TemplateMemory {
      * @throws {Error} If no sheets are found to merge.
      * @experimental This API is experimental and might change in future versions.
      */
-    #mergeSheets(data) {
+    async #mergeSheets(data) {
         const { additions, baseSheetIndex = 1, baseSheetName, gap = 0, } = data;
         let fileKey = "";
         if (baseSheetName) {
-            fileKey = this.#getSheetPathByName(baseSheetName);
+            fileKey = await this.#getSheetPathByName(baseSheetName);
         }
         if (baseSheetIndex && !fileKey) {
             if (baseSheetIndex < 1) {
@@ -287,16 +288,16 @@ class TemplateMemory {
         if (!fileKey) {
             throw new Error("Base sheet not found");
         }
-        const { lastRowNumber, mergeCells: baseMergeCells, rows: baseRows, xml, } = this.#extractRowsFromSheet(fileKey);
+        const { lastRowNumber, mergeCells: baseMergeCells, rows: baseRows, xml, } = await this.#extractRowsFromSheet(fileKey);
         const allRows = [...baseRows];
         const allMergeCells = [...baseMergeCells];
         let currentRowOffset = lastRowNumber + gap;
         const sheetPaths = [];
         if (additions.sheetIndexes) {
-            sheetPaths.push(...(additions.sheetIndexes).map(e => this.#getSheetPathById(e)));
+            sheetPaths.push(...(await Promise.all(additions.sheetIndexes.map(e => this.#getSheetPathById(e)))));
         }
         if (additions.sheetNames) {
-            sheetPaths.push(...(additions.sheetNames).map(e => this.#getSheetPathByName(e)));
+            sheetPaths.push(...(await Promise.all(additions.sheetNames.map(e => this.#getSheetPathByName(e)))));
         }
         if (sheetPaths.length === 0) {
             throw new Error("No sheets found to merge");
@@ -305,7 +306,7 @@ class TemplateMemory {
             if (!this.files[sheetPath]) {
                 throw new Error(`Sheet "${sheetPath}" not found`);
             }
-            const { mergeCells, rows } = Xml.extractRowsFromSheet(this.files[sheetPath]);
+            const { mergeCells, rows } = await Xml.extractRowsFromSheet(this.files[sheetPath]);
             const shiftedRows = Xml.shiftRowIndices(rows, currentRowOffset);
             const shiftedMergeCells = mergeCells.map(cell => {
                 const [start, end] = cell.ref.split(":");
@@ -335,28 +336,45 @@ class TemplateMemory {
      * @throws {Error} If the sheet does not exist.
      * @experimental This API is experimental and might change in future versions.
      */
-    #removeSheets(data) {
+    async #removeSheets(data) {
         const { sheetIndexes = [], sheetNames = [] } = data;
-        for (const sheetIndex of sheetIndexes) {
+        // first get index of sheets to remove
+        const sheetIndexesToRemove = new Set(sheetIndexes);
+        for (const sheetName of sheetNames) {
+            const sheetPath = await this.#getSheetPathByName(sheetName);
+            const sheetIndexMatch = sheetPath.match(/sheet(\d+)\.xml$/);
+            if (!sheetIndexMatch || !sheetIndexMatch[1]) {
+                throw new Error(`Sheet "${sheetName}" not found`);
+            }
+            const sheetIndex = parseInt(sheetIndexMatch[1], 10);
+            sheetIndexesToRemove.add(sheetIndex);
+        }
+        // Remove sheets by index
+        for (const sheetIndex of sheetIndexesToRemove.values()) {
             const sheetPath = `xl/worksheets/sheet${sheetIndex}.xml`;
             if (!this.files[sheetPath]) {
                 continue;
             }
+            // remove sheet file
             delete this.files[sheetPath];
-            if (this.files["xl/workbook.xml"]) {
-                this.files["xl/workbook.xml"] = Buffer.from(Utils.Common.removeSheetFromWorkbook(this.files["xl/workbook.xml"].toString(), sheetIndex));
+            // remove sheet from workbook
+            const workbook = this.files[this.#excelKeys.workbook];
+            if (workbook) {
+                this.files[this.#excelKeys.workbook] = Buffer.from(Utils.Common.removeSheetFromWorkbook(workbook.toString(), sheetIndex));
             }
-            if (this.files["xl/_rels/workbook.xml.rels"]) {
-                this.files["xl/_rels/workbook.xml.rels"] = Buffer.from(Utils.Common.removeSheetFromRels(this.files["xl/_rels/workbook.xml.rels"].toString(), sheetIndex));
+            // remove sheet from workbook relations
+            const workbookRels = this.files[this.#excelKeys.workbookRels];
+            if (workbookRels) {
+                this.files[this.#excelKeys.workbookRels] = Buffer.from(Utils.Common.removeSheetFromRels(workbookRels.toString(), sheetIndex));
             }
-            if (this.files["[Content_Types].xml"]) {
-                this.files["[Content_Types].xml"] = Buffer.from(Utils.Common.removeSheetFromContentTypes(this.files["[Content_Types].xml"].toString(), sheetIndex));
+            // remove sheet from content types
+            const contentTypes = this.files[this.#excelKeys.contentTypes];
+            if (contentTypes) {
+                this.files[this.#excelKeys.contentTypes] = Buffer.from(Utils.Common.removeSheetFromContentTypes(contentTypes.toString(), sheetIndex));
             }
         }
-        for (const sheetName of sheetNames) {
-            Utils.Common.removeSheetByName(this.files, sheetName);
-        }
     }
+    /** Public methods */
     /**
      * Copies a sheet from the template to a new name.
      *
@@ -377,7 +395,7 @@ class TemplateMemory {
             }
             // Read workbook.xml and find the source sheet
             const workbookXmlPath = this.#excelKeys.workbook;
-            const workbookXml = this.#extractXmlFromSheet(this.#excelKeys.workbook);
+            const workbookXml = await this.#extractXmlFromSheet(this.#excelKeys.workbook);
             // Find the source sheet
             const sheetMatch = workbookXml.match(Utils.sheetMatch(sourceName));
             if (!sheetMatch || !sheetMatch[1]) {
@@ -391,7 +409,7 @@ class TemplateMemory {
             // Find the source sheet path by rId
             const rId = sheetMatch[1];
             const relsXmlPath = this.#excelKeys.workbookRels;
-            const relsXml = this.#extractXmlFromSheet(this.#excelKeys.workbookRels);
+            const relsXml = await this.#extractXmlFromSheet(this.#excelKeys.workbookRels);
             const relMatch = relsXml.match(Utils.relationshipMatch(rId));
             if (!relMatch || !relMatch[1]) {
                 throw new Error(`Relationship "${rId}" not found`);
@@ -433,7 +451,7 @@ class TemplateMemory {
             // Read [Content_Types].xml
             // Update [Content_Types].xml
             const contentTypesPath = "[Content_Types].xml";
-            const contentTypesXml = this.#extractXmlFromSheet(contentTypesPath);
+            const contentTypesXml = await this.#extractXmlFromSheet(contentTypesPath);
             const overrideTag = `<Override PartName="/xl/worksheets/${newSheetFilename}" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml"/>`;
             const updatedContentTypesXml = contentTypesXml.replace("</Types>", overrideTag + "</Types>");
             await this.#set(contentTypesPath, Buffer.from(updatedContentTypesXml));
@@ -454,12 +472,12 @@ class TemplateMemory {
      * @param replacements - An object where keys represent placeholder paths and values are the replacements.
      * @returns A promise that resolves when the substitution is complete.
      */
-    substitute(sheetName, replacements) {
+    async substitute(sheetName, replacements) {
         this.#ensureNotProcessing();
         this.#ensureNotDestroyed();
         this.#isProcessing = true;
         try {
-            return this.#substitute(sheetName, replacements);
+            await this.#substitute(sheetName, replacements);
         }
         finally {
             this.#isProcessing = false;
@@ -490,8 +508,8 @@ class TemplateMemory {
             Utils.checkStartRow(startRowNumber);
             Utils.checkRows(preparedRows);
             // Find the sheet
-            const sheetPath = this.#getSheetPathByName(sheetName);
-            const sheetXml = this.#extractXmlFromSheet(sheetPath);
+            const sheetPath = await this.#getSheetPathByName(sheetName);
+            const sheetXml = await this.#extractXmlFromSheet(sheetPath);
             let nextRow = 0;
             if (!startRowNumber) {
                 // Find the last row
@@ -525,7 +543,7 @@ class TemplateMemory {
             else {
                 updatedXml = sheetXml.replace(/<worksheet[^>]*>/, (match) => `${match}<sheetData>${rowsXml}</sheetData>`);
             }
-            await this.#set(sheetPath, Buffer.from(updatedXml));
+            await this.#set(sheetPath, Buffer.from(Utils.updateDimension(updatedXml)));
         }
         finally {
             this.#isProcessing = false;
@@ -554,10 +572,30 @@ class TemplateMemory {
             if (!sheetName)
                 throw new Error("Sheet name is required");
             // Read XML workbook to find sheet name and path
-            const sheetPath = this.#getSheetPathByName(sheetName);
-            const sheetXml = this.#extractXmlFromSheet(sheetPath);
+            const sheetPath = await this.#getSheetPathByName(sheetName);
+            const sheetXml = await this.#extractXmlFromSheet(sheetPath);
             const output = new memory_write_stream_js_1.MemoryWriteStream();
             let inserted = false;
+            const initialDimension = sheetXml.match(/<dimension\s+ref="[^"]*"/)?.[0] || "";
+            const dimension = {
+                maxColumn: "A",
+                maxRow: 1,
+                minColumn: "A",
+                minRow: 1,
+            };
+            if (initialDimension) {
+                const dimensionMatch = initialDimension.match(/<dimension\s+ref="([^"]*)"/);
+                if (dimensionMatch) {
+                    const dimensionRef = dimensionMatch[1];
+                    if (dimensionRef) {
+                        const [min, max] = dimensionRef.split(":");
+                        dimension.minColumn = min.slice(0, 1);
+                        dimension.minRow = parseInt(min.slice(1));
+                        dimension.maxColumn = max.slice(0, 1);
+                        dimension.maxRow = parseInt(max.slice(1));
+                    }
+                }
+            }
             // --- Case 1: <sheetData>...</sheetData> on one line ---
             const singleLineMatch = sheetXml.match(/(<sheetData[^>]*>)(.*)(<\/sheetData>)/);
             if (!inserted && singleLineMatch) {
@@ -578,7 +616,13 @@ class TemplateMemory {
                         output.write(innerRows);
                     }
                 }
-                const { rowNumber: actualRowNumber } = await Utils.writeRowsToStream(output, rows, maxRowNumber);
+                const { dimension: newDimension, rowNumber: actualRowNumber } = await Utils.writeRowsToStream(output, rows, maxRowNumber);
+                if (Utils.compareColumns(newDimension.maxColumn, dimension.maxColumn) > 0) {
+                    dimension.maxColumn = newDimension.maxColumn;
+                }
+                if (newDimension.maxRow > dimension.maxRow) {
+                    dimension.maxRow = newDimension.maxRow;
+                }
                 if (innerRows) {
                     const filtered = Utils.getRowsAbove(innerRowsMap, actualRowNumber);
                     if (filtered)
@@ -595,7 +639,13 @@ class TemplateMemory {
                 const matchIndex = match.index;
                 output.write(sheetXml.slice(0, matchIndex));
                 output.write("<sheetData>");
-                await Utils.writeRowsToStream(output, rows, maxRowNumber);
+                const { dimension: newDimension } = await Utils.writeRowsToStream(output, rows, maxRowNumber);
+                if (Utils.compareColumns(newDimension.maxColumn, dimension.maxColumn) > 0) {
+                    dimension.maxColumn = newDimension.maxColumn;
+                }
+                if (newDimension.maxRow > dimension.maxRow) {
+                    dimension.maxRow = newDimension.maxRow;
+                }
                 output.write("</sheetData>");
                 output.write(sheetXml.slice(matchIndex + match[0].length));
                 inserted = true;
@@ -626,7 +676,13 @@ class TemplateMemory {
                         output.write(innerRows);
                     }
                 }
-                const { rowNumber: actualRowNumber } = await Utils.writeRowsToStream(output, rows, Utils.getMaxRowNumber(innerRows));
+                const { dimension: newDimension, rowNumber: actualRowNumber } = await Utils.writeRowsToStream(output, rows, Utils.getMaxRowNumber(innerRows));
+                if (Utils.compareColumns(newDimension.maxColumn, dimension.maxColumn) > 0) {
+                    dimension.maxColumn = newDimension.maxColumn;
+                }
+                if (newDimension.maxRow > dimension.maxRow) {
+                    dimension.maxRow = newDimension.maxRow;
+                }
                 if (innerRows) {
                     const filtered = Utils.getRowsAbove(innerRowsMap, actualRowNumber);
                     if (filtered)
@@ -638,8 +694,18 @@ class TemplateMemory {
             }
             if (!inserted)
                 throw new Error("Failed to locate <sheetData> for insertion");
+            let result = output.toBuffer();
+            // update dimension
+            {
+                const target = initialDimension;
+                const refRange = `${dimension.minColumn}${dimension.minRow}:${dimension.maxColumn}${dimension.maxRow}`;
+                const replacement = `<dimension ref="${refRange}"`;
+                if (target) {
+                    result = Buffer.from(result.toString().replace(target, replacement));
+                }
+            }
             // Save the buffer to the sheet
-            this.files[sheetPath] = output.toBuffer();
+            this.files[sheetPath] = result;
         }
         finally {
             this.#isProcessing = false;
@@ -702,12 +768,12 @@ class TemplateMemory {
      * @param {number} [data.gap=0] - The number of empty rows to insert between each added section.
      * @returns {void}
      */
-    mergeSheets(data) {
+    async mergeSheets(data) {
         this.#ensureNotProcessing();
         this.#ensureNotDestroyed();
         this.#isProcessing = true;
         try {
-            this.#mergeSheets(data);
+            await this.#mergeSheets(data);
         }
         finally {
             this.#isProcessing = false;
@@ -721,17 +787,18 @@ class TemplateMemory {
      * @param {string[]} [data.sheetNames] - The names of the sheets to remove.
      * @returns {void}
      */
-    removeSheets(data) {
+    async removeSheets(data) {
         this.#ensureNotProcessing();
         this.#ensureNotDestroyed();
         this.#isProcessing = true;
         try {
-            this.#removeSheets(data);
+            await this.#removeSheets(data);
         }
         finally {
             this.#isProcessing = false;
         }
     }
+    /** Static methods */
     /**
      * Creates a Template instance from an Excel file source.
      *

package/build/cjs/lib/template/utils/compare-columns.js

@@ -0,0 +1,16 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.compareColumns = compareColumns;
+/**
+ * Compares two column strings and returns a number indicating their relative order.
+ *
+ * @param a - The first column string to compare.
+ * @param b - The second column string to compare.
+ * @returns 0 if the columns are equal, -1 if the first column is less than the second, or 1 if the first column is greater than the second.
+ */
+function compareColumns(a, b) {
+    if (a === b) {
+        return 0;
+    }
+    return a.length === b.length ? (a < b ? -1 : 1) : (a.length < b.length ? -1 : 1);
+}

package/build/cjs/lib/template/utils/index.js

@@ -43,6 +43,7 @@ __exportStar(require("./check-row.js"), exports);
 __exportStar(require("./check-rows.js"), exports);
 __exportStar(require("./check-start-row.js"), exports);
 __exportStar(require("./column-index-to-letter.js"), exports);
+__exportStar(require("./compare-columns.js"), exports);
 __exportStar(require("./escape-xml.js"), exports);
 __exportStar(require("./extract-xml-declaration.js"), exports);
 __exportStar(require("./get-by-path.js"), exports);

package/build/cjs/lib/xml/extract-rows-from-sheet-sync.js

@@ -0,0 +1,67 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.extractRowsFromSheetSync = extractRowsFromSheetSync;
+const extract_xml_from_sheet_sync_js_1 = require("./extract-xml-from-sheet-sync.js");
+/**
+ * Parses a worksheet (either as Buffer or string) to extract row data,
+ * last row number, and merge cell information from Excel XML format.
+ *
+ * This function is particularly useful for processing Excel files in
+ * Open XML Spreadsheet format (.xlsx).
+ *
+ * @param {Buffer|string} sheet - The worksheet content to parse, either as:
+ *                               - Buffer (binary Excel sheet)
+ *                               - string (raw XML content)
+ * @returns {{
+ *   rows: string[],
+ *   lastRowNumber: number,
+ *   mergeCells: {ref: string}[]
+ * }} An object containing:
+ *   - rows: Array of raw XML strings for each <row> element
+ *   - lastRowNumber: Highest row number found in the sheet (1-based)
+ *   - mergeCells: Array of merged cell ranges (e.g., [{ref: "A1:B2"}])
+ * @throws {Error} If the sheetData section is not found in the XML
+ */
+function extractRowsFromSheetSync(sheet) {
+    // Convert Buffer input to XML string if needed
+    const xml = typeof sheet === "string"
+        ? sheet
+        : (0, extract_xml_from_sheet_sync_js_1.extractXmlFromSheetSync)(sheet);
+    // Extract the sheetData section containing all rows
+    const sheetDataMatch = xml.match(/<sheetData[^>]*>([\s\S]*?)<\/sheetData>/);
+    if (!sheetDataMatch) {
+        throw new Error("sheetData not found in worksheet XML");
+    }
+    const sheetDataContent = sheetDataMatch[1] || "";
+    // Extract all <row> elements using regex
+    const rowMatches = [...sheetDataContent.matchAll(/<row\b[^>]*\/>|<row\b[^>]*>[\s\S]*?<\/row>/g)];
+    const rows = rowMatches.map(match => match[0]);
+    // Calculate the highest row number present in the sheet
+    const lastRowNumber = rowMatches
+        .map(match => {
+        // Extract row number from r="..." attribute (1-based)
+        const rowNumMatch = match[0].match(/r="(\d+)"/);
+        return rowNumMatch?.[1] ? parseInt(rowNumMatch[1], 10) : null;
+    })
+        .filter((row) => row !== null) // Type guard to filter out nulls
+        .reduce((max, current) => Math.max(max, current), 0); // Find maximum row number
+    // Extract all merged cell ranges from the worksheet
+    const mergeCells = [];
+    const mergeCellsMatch = xml.match(/<mergeCells[^>]*>([\s\S]*?)<\/mergeCells>/);
+    if (mergeCellsMatch) {
+        // Find all mergeCell entries with ref attributes
+        const mergeCellMatches = mergeCellsMatch[1]?.match(/<mergeCell[^>]+ref="([^"]+)"[^>]*>/g) || [];
+        mergeCellMatches.forEach(match => {
+            const refMatch = match.match(/ref="([^"]+)"/);
+            if (refMatch?.[1]) {
+                mergeCells.push({ ref: refMatch[1] }); // Store the cell range (e.g., "A1:B2")
+            }
+        });
+    }
+    return {
+        lastRowNumber,
+        mergeCells,
+        rows,
+        xml,
+    };
+}

package/build/cjs/lib/xml/extract-rows-from-sheet.js

@@ -22,9 +22,11 @@ const extract_xml_from_sheet_js_1 = require("./extract-xml-from-sheet.js");
  *   - mergeCells: Array of merged cell ranges (e.g., [{ref: "A1:B2"}])
  * @throws {Error} If the sheetData section is not found in the XML
  */
-function extractRowsFromSheet(sheet) {
+async function extractRowsFromSheet(sheet) {
     // Convert Buffer input to XML string if needed
-    const xml = typeof sheet === "string" ? sheet : (0, extract_xml_from_sheet_js_1.extractXmlFromSheet)(sheet);
+    const xml = typeof sheet === "string"
+        ? sheet
+        : await (0, extract_xml_from_sheet_js_1.extractXmlFromSheet)(sheet);
     // Extract the sheetData section containing all rows
     const sheetDataMatch = xml.match(/<sheetData[^>]*>([\s\S]*?)<\/sheetData>/);
     if (!sheetDataMatch) {

package/build/cjs/lib/xml/extract-xml-from-sheet-sync.js

@@ -0,0 +1,43 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.extractXmlFromSheetSync = extractXmlFromSheetSync;
+const node_zlib_1 = require("node:zlib");
+/**
+ * Extracts and parses XML content from an Excel worksheet file (e.g., xl/worksheets/sheet1.xml).
+ * Handles both compressed (raw deflate) and uncompressed (plain XML) formats.
+ *
+ * This function is designed to work with Excel Open XML (.xlsx) worksheet files,
+ * which may be stored in either compressed or uncompressed format within the ZIP container.
+ *
+ * @param {Buffer} buffer - The file content to process, which may be:
+ *                         - Raw XML text
+ *                         - Deflate-compressed XML data (without zlib headers)
+ * @returns {string} - The extracted XML content as a UTF-8 string
+ * @throws {Error} - If the buffer is empty or cannot be processed
+ */
+function extractXmlFromSheetSync(buffer) {
+    if (!buffer || buffer.length === 0) {
+        throw new Error("Empty buffer provided");
+    }
+    let xml;
+    // Check if the buffer starts with an XML declaration (<?xml)
+    const head = buffer.subarray(0, 1024).toString("utf8").replace(/[\x00-\x08\x0B\x0C\x0E-\x1F]/g, "").trim();
+    const isXml = /^<\?xml[\s\S]+<\w+[\s>]/.test(head);
+    if (isXml) {
+        // Case 1: Already uncompressed XML - convert directly to string
+        xml = buffer.toString("utf8");
+    }
+    else {
+        // Case 2: Attempt to decompress as raw deflate data
+        try {
+            xml = (0, node_zlib_1.inflateRawSync)(buffer).toString("utf8");
+        }
+        catch (err) {
+            throw new Error("Failed to decompress sheet XML: " + (err instanceof Error ? err.message : String(err)));
+        }
+    }
+    // Sanitize XML by removing control characters (except tab, newline, carriage return)
+    // This handles potential corruption from binary data or encoding issues
+    xml = xml.replace(/[\x00-\x08\x0B\x0C\x0E-\x1F]/g, "");
+    return xml;
+}

package/build/cjs/lib/xml/extract-xml-from-sheet.js

@@ -1,7 +1,12 @@
 "use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.extractXmlFromSheet = extractXmlFromSheet;
-const pako_1 = require("pako");
+const node_util_1 = __importDefault(require("node:util"));
+const node_zlib_1 = __importDefault(require("node:zlib"));
+const inflateRaw = node_util_1.default.promisify(node_zlib_1.default.inflateRaw);
 /**
  * Extracts and parses XML content from an Excel worksheet file (e.g., xl/worksheets/sheet1.xml).
  * Handles both compressed (raw deflate) and uncompressed (plain XML) formats.
@@ -12,35 +17,30 @@ const pako_1 = require("pako");
  * @param {Buffer} buffer - The file content to process, which may be:
  *                         - Raw XML text
  *                         - Deflate-compressed XML data (without zlib headers)
- * @returns {string} - The extracted XML content as a UTF-8 string
+ * @returns {Promise<string>} - The extracted XML content as a UTF-8 string
  * @throws {Error} - If the buffer is empty or cannot be processed
  */
-function extractXmlFromSheet(buffer) {
+async function extractXmlFromSheet(buffer) {
     if (!buffer || buffer.length === 0) {
         throw new Error("Empty buffer provided");
     }
     let xml;
     // Check if the buffer starts with an XML declaration (<?xml)
-    const startsWithXml = buffer.subarray(0, 5).toString("utf8").trim().startsWith("<?xml");
-    if (startsWithXml) {
+    const head = buffer.subarray(0, 1024).toString("utf8").replace(/[\x00-\x08\x0B\x0C\x0E-\x1F]/g, "").trim();
+    const isXml = /^<\?xml[\s\S]+<\w+[\s>]/.test(head);
+    if (isXml) {
         // Case 1: Already uncompressed XML - convert directly to string
         xml = buffer.toString("utf8");
     }
     else {
         // Case 2: Attempt to decompress as raw deflate data
-        const inflated = (0, pako_1.inflateRaw)(buffer, { to: "string" });
-        // Validate the decompressed content contains worksheet data
-        if (inflated && inflated.includes("<sheetData")) {
-            xml = inflated;
+        try {
+            xml = (await inflateRaw(buffer)).toString("utf8");
         }
-        else {
-            throw new Error("Decompressed data does not contain sheetData");
+        catch (err) {
+            throw new Error("Failed to decompress sheet XML: " + (err instanceof Error ? err.message : String(err)));
         }
     }
-    // Fallback: If no XML obtained yet, try direct UTF-8 conversion
-    if (!xml) {
-        xml = buffer.toString("utf8");
-    }
     // Sanitize XML by removing control characters (except tab, newline, carriage return)
     // This handles potential corruption from binary data or encoding issues
     xml = xml.replace(/[\x00-\x08\x0B\x0C\x0E-\x1F]/g, "");

package/build/cjs/lib/xml/index.js

@@ -15,7 +15,8 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
 };
 Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./build-merged-sheet.js"), exports);
+__exportStar(require("./extract-rows-from-sheet-sync.js"), exports);
 __exportStar(require("./extract-rows-from-sheet.js"), exports);
+__exportStar(require("./extract-xml-from-sheet-sync.js"), exports);
 __exportStar(require("./extract-xml-from-sheet.js"), exports);
-__exportStar(require("./extract-xml-from-system-content.js"), exports);
 __exportStar(require("./shift-row-indices.js"), exports);

package/build/esm/lib/merge-sheets-to-base-file-process-sync.js

@@ -0,0 +1,69 @@
+import * as Utils from "./utils/index.js";
+import * as Xml from "./xml/index.js";
+/**
+ * Merges rows from other Excel files into a base Excel file.
+ *
+ * This function is a process-friendly version of mergeSheetsToBaseFile.
+ * It takes a single object with the following properties:
+ * - additions: An array of objects with two properties:
+ *   - files: A dictionary of file paths to their corresponding XML content
+ *   - sheetIndexes: The 1-based indexes of the sheet to extract rows from
+ * - baseFiles: A dictionary of file paths to their corresponding XML content
+ * - baseSheetIndex: The 1-based index of the sheet in the base file to add rows to
+ * - gap: The number of empty rows to insert between each added section
+ * - sheetNamesToRemove: The names of sheets to remove from the output file
+ * - sheetsToRemove: The 1-based indices of sheets to remove from the output file
+ *
+ * The function returns a dictionary of file paths to their corresponding XML content.
+ */
+export function mergeSheetsToBaseFileProcessSync(data) {
+    const { additions, baseFiles, baseSheetIndex, gap, sheetNamesToRemove, sheetsToRemove, } = data;
+    const basePath = `xl/worksheets/sheet${baseSheetIndex}.xml`;
+    if (!baseFiles[basePath]) {
+        throw new Error(`Base file does not contain ${basePath}`);
+    }
+    const { lastRowNumber, mergeCells: baseMergeCells, rows: baseRows, xml, } = Xml.extractRowsFromSheetSync(baseFiles[basePath]);
+    const allRows = [...baseRows];
+    const allMergeCells = [...baseMergeCells];
+    let currentRowOffset = lastRowNumber + gap;
+    for (const { files, sheetIndexes } of additions) {
+        for (const sheetIndex of sheetIndexes) {
+            const sheetPath = `xl/worksheets/sheet${sheetIndex}.xml`;
+            if (!files[sheetPath]) {
+                throw new Error(`File does not contain ${sheetPath}`);
+            }
+            const { mergeCells, rows } = Xml.extractRowsFromSheetSync(files[sheetPath]);
+            const shiftedRows = Xml.shiftRowIndices(rows, currentRowOffset);
+            const shiftedMergeCells = mergeCells.map(cell => {
+                const [start, end] = cell.ref.split(":");
+                if (!start || !end) {
+                    return cell;
+                }
+                const shiftedStart = Utils.shiftCellRef(start, currentRowOffset);
+                const shiftedEnd = Utils.shiftCellRef(end, currentRowOffset);
+                return { ...cell, ref: `${shiftedStart}:${shiftedEnd}` };
+            });
+            allRows.push(...shiftedRows);
+            allMergeCells.push(...shiftedMergeCells);
+            currentRowOffset += Utils.getMaxRowNumber(rows) + gap;
+        }
+    }
+    const mergedXml = Xml.buildMergedSheet(xml, allRows, allMergeCells);
+    baseFiles[basePath] = mergedXml;
+    for (const sheetIndex of sheetsToRemove) {
+        const sheetPath = `xl/worksheets/sheet${sheetIndex}.xml`;
+        delete baseFiles[sheetPath];
+        if (baseFiles["xl/workbook.xml"]) {
+            baseFiles["xl/workbook.xml"] = Buffer.from(Utils.removeSheetFromWorkbook(baseFiles["xl/workbook.xml"].toString(), sheetIndex));
+        }
+        if (baseFiles["xl/_rels/workbook.xml.rels"]) {
+            baseFiles["xl/_rels/workbook.xml.rels"] = Buffer.from(Utils.removeSheetFromRels(baseFiles["xl/_rels/workbook.xml.rels"].toString(), sheetIndex));
+        }
+        if (baseFiles["[Content_Types].xml"]) {
+            baseFiles["[Content_Types].xml"] = Buffer.from(Utils.removeSheetFromContentTypes(baseFiles["[Content_Types].xml"].toString(), sheetIndex));
+        }
+    }
+    for (const sheetName of sheetNamesToRemove) {
+        Utils.removeSheetByName(baseFiles, sheetName);
+    }
+}