read-excel-file 9.2.0 → 9.3.1

package/{commonjs/xlsx/parseCellCoordinates.js → modules/xlsx/parseCellAddress.js}

@@ -1,32 +1,31 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports["default"] = parseCellCoordinates;
 function _slicedToArray(arr, i) { return _arrayWithHoles(arr) || _iterableToArrayLimit(arr, i) || _unsupportedIterableToArray(arr, i) || _nonIterableRest(); }
 function _nonIterableRest() { throw new TypeError("Invalid attempt to destructure non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method."); }
 function _unsupportedIterableToArray(o, minLen) { if (!o) return; if (typeof o === "string") return _arrayLikeToArray(o, minLen); var n = Object.prototype.toString.call(o).slice(8, -1); if (n === "Object" && o.constructor) n = o.constructor.name; if (n === "Map" || n === "Set") return Array.from(o); if (n === "Arguments" || /^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n)) return _arrayLikeToArray(o, minLen); }
 function _arrayLikeToArray(arr, len) { if (len == null || len > arr.length) len = arr.length; for (var i = 0, arr2 = new Array(len); i < len; i++) arr2[i] = arr[i]; return arr2; }
 function _iterableToArrayLimit(r, l) { var t = null == r ? null : "undefined" != typeof Symbol && r[Symbol.iterator] || r["@@iterator"]; if (null != t) { var e, n, i, u, a = [], f = !0, o = !1; try { if (i = (t = t.call(r)).next, 0 === l) { if (Object(t) !== t) return; f = !1; } else for (; !(f = (e = i.call(t)).done) && (a.push(e.value), a.length !== l); f = !0); } catch (r) { o = !0, n = r; } finally { try { if (!f && null != t["return"] && (u = t["return"](), Object(u) !== u)) return; } finally { if (o) throw n; } } return a; } }
 function _arrayWithHoles(arr) { if (Array.isArray(arr)) return arr; }
-function parseCellCoordinates(coordinatesString) {
+/**
+ * Parses XLSX cell address into a row number and a column number.
+ * @param {string} coordinatesString
+ * @returns {number[]} Returns `[rowNumber, columnNumber]`
+ */
+export default function parseCellAddress(coordinatesString) {
   // Coordinate examples: "AA2091", "R988", "B1".
   var _coordinatesString$sp = coordinatesString.split(/(\d+)/),
     _coordinatesString$sp2 = _slicedToArray(_coordinatesString$sp, 2),
     column = _coordinatesString$sp2[0],
     row = _coordinatesString$sp2[1];
   return [
-  // Row.
+  // Row number (starting at `1`).
   Number(row),
-  // Column.
-  // It's not clear why would `column` ever be non-trimmed,
-  // but if it was added here then perhaps it could hypothetically happen, or smth.
+  // Column number (starting at `1`).
+  // It's not clear if the `column` part could ever be non-trimmed,
+  // but this `.trim()` call was already here when I copied this code from somewhere.
   getColumnNumberFromColumnLetters(column.trim())];
 }
 
 // Maps "A1"-like coordinates to `{ row, column }` numeric coordinates.
-var LETTERS = ["", "A", "B", "C", "D", "E", "F", "G", "H", "I", "J", "K", "L", "M", "N", "O", "P", "Q", "R", "S", "T", "U", "V", "W", "X", "Y", "Z"];
+var LETTERS = ['', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z'];
 
 // Converts a letter coordinate to a digit coordinate.
 // Examples: "A" -> 1, "B" -> 2, "Z" -> 26, "AA" -> 27, etc.
@@ -41,4 +40,4 @@ function getColumnNumberFromColumnLetters(columnLetters) {
   }
   return n;
 }
-//# sourceMappingURL=parseCellCoordinates.js.map
+//# sourceMappingURL=parseCellAddress.js.map

package/modules/xlsx/parseCellAddress.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"parseCellAddress.js","names":["parseCellAddress","coordinatesString","_coordinatesString$sp","split","_coordinatesString$sp2","_slicedToArray","column","row","Number","getColumnNumberFromColumnLetters","trim","LETTERS","columnLetters","n","i","length","indexOf"],"sources":["../../source/xlsx/parseCellAddress.js"],"sourcesContent":["/**\r\n * Parses XLSX cell address into a row number and a column number.\r\n * @param {string} coordinatesString\r\n * @returns {number[]} Returns `[rowNumber, columnNumber]`\r\n */\r\nexport default function parseCellAddress(coordinatesString) {\r\n  // Coordinate examples: \"AA2091\", \"R988\", \"B1\".\r\n  const [column, row] = coordinatesString.split(/(\\d+)/)\r\n  return [\r\n    // Row number (starting at `1`).\r\n    Number(row),\r\n    // Column number (starting at `1`).\r\n\t\t// It's not clear if the `column` part could ever be non-trimmed,\r\n\t\t// but this `.trim()` call was already here when I copied this code from somewhere.\r\n    getColumnNumberFromColumnLetters(column.trim())\r\n  ]\r\n}\r\n\r\n// Maps \"A1\"-like coordinates to `{ row, column }` numeric coordinates.\r\nconst LETTERS = ['', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z']\r\n\r\n// Converts a letter coordinate to a digit coordinate.\r\n// Examples: \"A\" -> 1, \"B\" -> 2, \"Z\" -> 26, \"AA\" -> 27, etc.\r\nfunction getColumnNumberFromColumnLetters(columnLetters) {\r\n  // `for ... of ...` would require Babel polyfill for iterating a string.\r\n  let n = 0\r\n  let i = 0\r\n  while (i < columnLetters.length) {\r\n    n *= 26\r\n    n += LETTERS.indexOf(columnLetters[i])\r\n    i++\r\n  }\r\n  return n\r\n}\r\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASA,gBAAgBA,CAACC,iBAAiB,EAAE;EAC1D;EACA,IAAAC,qBAAA,GAAsBD,iBAAiB,CAACE,KAAK,CAAC,OAAO,CAAC;IAAAC,sBAAA,GAAAC,cAAA,CAAAH,qBAAA;IAA/CI,MAAM,GAAAF,sBAAA;IAAEG,GAAG,GAAAH,sBAAA;EAClB,OAAO;EACL;EACAI,MAAM,CAACD,GAAG,CAAC;EACX;EACF;EACA;EACEE,gCAAgC,CAACH,MAAM,CAACI,IAAI,CAAC,CAAC,CAAC,CAChD;AACH;;AAEA;AACA,IAAMC,OAAO,GAAG,CAAC,EAAE,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;;AAEtJ;AACA;AACA,SAASF,gCAAgCA,CAACG,aAAa,EAAE;EACvD;EACA,IAAIC,CAAC,GAAG,CAAC;EACT,IAAIC,CAAC,GAAG,CAAC;EACT,OAAOA,CAAC,GAAGF,aAAa,CAACG,MAAM,EAAE;IAC/BF,CAAC,IAAI,EAAE;IACPA,CAAC,IAAIF,OAAO,CAACK,OAAO,CAACJ,aAAa,CAACE,CAAC,CAAC,CAAC;IACtCA,CAAC,EAAE;EACL;EACA,OAAOD,CAAC;AACV"}

package/modules/xlsx/parseCellValue.js

@@ -1,11 +1,11 @@
 import parseExcelDate from './parseExcelDate.js';
+import parseNumber from './parseNumber.js';
 import isDateFormatStyle from './isDateFormatStyle.js';
 
 // Parses a string `value` of a cell.
 export default function parseCellValue(value, type, _ref) {
-  var getInlineStringValue = _ref.getInlineStringValue,
-    getInlineStringXml = _ref.getInlineStringXml,
-    getStyleId = _ref.getStyleId,
+  var inlineString = _ref.inlineString,
+    styleId = _ref.styleId,
     styles = _ref.styles,
     sharedStrings = _ref.sharedStrings,
     epoch1904 = _ref.epoch1904,
@@ -35,9 +35,9 @@ export default function parseCellValue(value, type, _ref) {
     // Perhaps the specification doesn't force it to use one or another.
     // Example: `<sheetData><row r="1"><c r="A1" s="1" t="inlineStr"><is><t>Test 123</t></is></c></row></sheetData>`.
     case 'inlineStr':
-      value = getInlineStringValue();
+      value = inlineString;
       if (value === undefined) {
-        throw new Error("Unsupported \"inline string\" cell value structure: ".concat(getInlineStringXml()));
+        throw new Error('Couldn\'t read "inline string" cell value');
       }
       value = parseString(value, options);
       break;
@@ -112,10 +112,9 @@ export default function parseCellValue(value, type, _ref) {
       }
       // XLSX does have "d" type for dates, but it's not commonly used.
       // Instead, it prefers using "n" type for storing dates as timestamps.
-      var styleId = getStyleId();
       if (styleId && isDateFormatStyle(styleId, styles, options)) {
         // Parse the number from string.
-        value = parseNumberDefault(value);
+        value = parseNumber(value);
         // Parse the number as a date timestamp.
         value = parseExcelDate(value, {
           epoch1904: epoch1904
@@ -124,8 +123,7 @@ export default function parseCellValue(value, type, _ref) {
         // Parse the number from string.
         // Supports custom parsing function to work around javascript number encoding precision issues.
         // https://gitlab.com/catamphetamine/read-excel-file/-/issues/85
-        var parseNumber = options.parseNumber || parseNumberDefault;
-        value = parseNumber(value);
+        value = (options.parseNumber || parseNumber)(value);
       }
       break;
     default:
@@ -179,18 +177,4 @@ function parseString(value, options) {
   }
   return value;
 }
-
-// Parses a number from string.
-// Throws an error if the number couldn't be parsed.
-// When parsing floating-point number, is affected by
-// the javascript number encoding precision issues:
-// https://www.youtube.com/watch?v=2gIxbTn7GSc
-// https://www.avioconsulting.com/blog/overcoming-javascript-numeric-precision-issues
-function parseNumberDefault(stringifiedNumber) {
-  var parsedNumber = Number(stringifiedNumber);
-  if (isNaN(parsedNumber)) {
-    throw new Error("Invalid \"numeric\" cell value: ".concat(stringifiedNumber));
-  }
-  return parsedNumber;
-}
 //# sourceMappingURL=parseCellValue.js.map

package/modules/xlsx/parseCellValue.js.map

@@ -1 +1 @@
-{"version":3,"file":"parseCellValue.js","names":["parseExcelDate","isDateFormatStyle","parseCellValue","value","type","_ref","getInlineStringValue","getInlineStringXml","getStyleId","styles","sharedStrings","epoch1904","options","parseString","undefined","Error","concat","sharedStringIndex","Number","isNaN","length","decodeError","parsedDate","Date","valueOf","styleId","parseNumberDefault","parseNumber","TypeError","errorCode","trim","stringifiedNumber","parsedNumber"],"sources":["../../source/xlsx/parseCellValue.js"],"sourcesContent":["import parseExcelDate from './parseExcelDate.js'\r\nimport isDateFormatStyle from './isDateFormatStyle.js'\r\n\r\n// Parses a string `value` of a cell.\r\nexport default function parseCellValue(value, type, {\r\n  getInlineStringValue,\r\n  getInlineStringXml,\r\n  getStyleId,\r\n  styles,\r\n  sharedStrings,\r\n  epoch1904,\r\n  options\r\n}) {\r\n  if (!type) {\r\n    // Default cell type is \"n\" (numeric).\r\n    // http://www.datypic.com/sc/ooxml/t-ssml_CT_Cell.html\r\n    type = 'n'\r\n  }\r\n\r\n  // Available Excel cell types:\r\n  // https://github.com/SheetJS/sheetjs/blob/19620da30be2a7d7b9801938a0b9b1fd3c4c4b00/docbits/52_datatype.md\r\n  //\r\n  // Some other document (seems to be old):\r\n  // http://webapp.docx4java.org/OnlineDemo/ecma376/SpreadsheetML/ST_CellType.html\r\n  //\r\n  switch (type) {\r\n    // XLSX tends to store all strings as \"shared\" (indexed) ones\r\n    // using \"s\" cell type (for saving on strage space).\r\n    // \"str\" cell type is then generally only used for storing\r\n    // formula-pre-calculated cell values.\r\n    case 'str':\r\n      value = parseString(value, options)\r\n      break\r\n\r\n    // Sometimes, XLSX stores strings as \"inline\" strings rather than \"shared\" (indexed) ones.\r\n    // Perhaps the specification doesn't force it to use one or another.\r\n    // Example: `<sheetData><row r=\"1\"><c r=\"A1\" s=\"1\" t=\"inlineStr\"><is><t>Test 123</t></is></c></row></sheetData>`.\r\n    case 'inlineStr':\r\n      value = getInlineStringValue()\r\n      if (value === undefined) {\r\n        throw new Error(`Unsupported \"inline string\" cell value structure: ${getInlineStringXml()}`)\r\n      }\r\n      value = parseString(value, options)\r\n      break\r\n\r\n    // XLSX tends to store string values as \"shared\" (indexed) ones.\r\n    // \"Shared\" strings is a way for an Excel editor to reduce\r\n    // the file size by storing \"commonly used\" strings in a dictionary\r\n    // and then referring to such strings by their index in that dictionary.\r\n    // Example: `<sheetData><row r=\"1\"><c r=\"A1\" s=\"1\" t=\"s\"><v>0</v></c></row></sheetData>`.\r\n    case 's':\r\n      // If a cell has no value then there's no `<c/>` element for it.\r\n      // If a `<c/>` element exists then it's not empty.\r\n      // The `<v/>`alue is a key in the \"shared strings\" dictionary of the\r\n      // XLSX file, so look it up in the `sharedStrings` dictionary by the numeric key.\r\n      const sharedStringIndex = Number(value)\r\n      if (isNaN(sharedStringIndex)) {\r\n        throw new Error(`Invalid \"shared\" string index: ${value}`)\r\n      }\r\n      if (sharedStringIndex >= sharedStrings.length) {\r\n        throw new Error(`An out-of-bounds \"shared\" string index: ${value}`)\r\n      }\r\n      value = sharedStrings[sharedStringIndex]\r\n      value = parseString(value, options)\r\n      break\r\n\r\n    // Boolean (TRUE/FALSE) values are stored as either \"1\" or \"0\"\r\n    // in cells of type \"b\".\r\n    case 'b':\r\n      if (value === '1') {\r\n        value = true\r\n      } else if (value === '0') {\r\n        value = false\r\n      } else {\r\n        throw new Error(`Unsupported \"boolean\" cell value: ${value}`)\r\n      }\r\n      break\r\n\r\n    // XLSX specification seems to support cells of type \"z\":\r\n    // blank \"stub\" cells that should be ignored by data processing utilities.\r\n    case 'z':\r\n      value = undefined\r\n      break\r\n\r\n    // XLSX specification also defines cells of type \"e\" containing a numeric \"error\" code.\r\n    // It's not clear what that means though.\r\n    // They also wrote: \"and `w` property stores its common name\".\r\n    // It's unclear what they meant by that.\r\n    case 'e':\r\n      value = decodeError(value)\r\n      break\r\n\r\n    // XLSX supports date cells of type \"d\", though seems like it (almost?) never\r\n    // uses it for storing dates, preferring \"n\" numeric timestamp cells instead.\r\n    // The value of a \"d\" cell is supposedly a string in \"ISO 8601\" format.\r\n    // I haven't seen an XLSX file having such cells.\r\n    // Example: `<sheetData><row r=\"1\"><c r=\"A1\" s=\"1\" t=\"d\"><v>2021-06-10T00:47:45.700Z</v></c></row></sheetData>`.\r\n    case 'd':\r\n      if (value === undefined) {\r\n        break\r\n      }\r\n      const parsedDate = new Date(value)\r\n      if (isNaN(parsedDate.valueOf())) {\r\n        throw new Error(`Unsupported \"date\" cell value: ${value}`)\r\n      }\r\n      value = parsedDate\r\n      break\r\n\r\n    // Numeric cells have type \"n\".\r\n    case 'n':\r\n      if (value === undefined) {\r\n        break\r\n      }\r\n      // XLSX does have \"d\" type for dates, but it's not commonly used.\r\n      // Instead, it prefers using \"n\" type for storing dates as timestamps.\r\n      const styleId = getStyleId()\r\n      if (styleId && isDateFormatStyle(styleId, styles, options)) {\r\n        // Parse the number from string.\r\n        value = parseNumberDefault(value)\r\n        // Parse the number as a date timestamp.\r\n        value = parseExcelDate(value, { epoch1904 })\r\n      } else {\r\n        // Parse the number from string.\r\n        // Supports custom parsing function to work around javascript number encoding precision issues.\r\n        // https://gitlab.com/catamphetamine/read-excel-file/-/issues/85\r\n        const parseNumber = options.parseNumber || parseNumberDefault\r\n        value = parseNumber(value)\r\n      }\r\n      break\r\n\r\n    default:\r\n      throw new TypeError(`Cell type not supported: ${type}`)\r\n  }\r\n\r\n  // Convert empty values to `null`.\r\n  if (value === undefined) {\r\n    value = null\r\n  }\r\n\r\n  return value\r\n}\r\n\r\n// Decodes numeric error code to a string code.\r\n// https://github.com/SheetJS/sheetjs/blob/19620da30be2a7d7b9801938a0b9b1fd3c4c4b00/docbits/52_datatype.md\r\nfunction decodeError(errorCode) {\r\n  // While the error values are determined by the application,\r\n  // the following are some example error values that could be used:\r\n  switch (errorCode) {\r\n    case 0x00:\r\n      return '#NULL!'\r\n    case 0x07:\r\n      return '#DIV/0!'\r\n    case 0x0F:\r\n      return '#VALUE!'\r\n    case 0x17:\r\n      return '#REF!'\r\n    case 0x1D:\r\n      return '#NAME?'\r\n    case 0x24:\r\n      return '#NUM!'\r\n    case 0x2A:\r\n      return '#N/A'\r\n    case 0x2B:\r\n      return '#GETTING_DATA'\r\n    default:\r\n      // Such error code doesn't exist. I made it up.\r\n      return `#ERROR_${errorCode}`\r\n  }\r\n}\r\n\r\nfunction parseString(value, options) {\r\n  // In some weird cases, a developer might want to disable\r\n  // the automatic trimming of all strings.\r\n  // For example, leading spaces might express a tree-like hierarchy.\r\n  // https://github.com/catamphetamine/read-excel-file/pull/106#issuecomment-1136062917\r\n  if (options.trim !== false) {\r\n    value = value.trim()\r\n  }\r\n  if (value === '') {\r\n    value = undefined\r\n  }\r\n  return value\r\n}\r\n\r\n// Parses a number from string.\r\n// Throws an error if the number couldn't be parsed.\r\n// When parsing floating-point number, is affected by\r\n// the javascript number encoding precision issues:\r\n// https://www.youtube.com/watch?v=2gIxbTn7GSc\r\n// https://www.avioconsulting.com/blog/overcoming-javascript-numeric-precision-issues\r\nfunction parseNumberDefault(stringifiedNumber) {\r\n  const parsedNumber = Number(stringifiedNumber)\r\n  if (isNaN(parsedNumber)) {\r\n    throw new Error(`Invalid \"numeric\" cell value: ${stringifiedNumber}`)\r\n  }\r\n  return parsedNumber\r\n}"],"mappings":"AAAA,OAAOA,cAAc,MAAM,qBAAqB;AAChD,OAAOC,iBAAiB,MAAM,wBAAwB;;AAEtD;AACA,eAAe,SAASC,cAAcA,CAACC,KAAK,EAAEC,IAAI,EAAAC,IAAA,EAQ/C;EAAA,IAPDC,oBAAoB,GAAAD,IAAA,CAApBC,oBAAoB;IACpBC,kBAAkB,GAAAF,IAAA,CAAlBE,kBAAkB;IAClBC,UAAU,GAAAH,IAAA,CAAVG,UAAU;IACVC,MAAM,GAAAJ,IAAA,CAANI,MAAM;IACNC,aAAa,GAAAL,IAAA,CAAbK,aAAa;IACbC,SAAS,GAAAN,IAAA,CAATM,SAAS;IACTC,OAAO,GAAAP,IAAA,CAAPO,OAAO;EAEP,IAAI,CAACR,IAAI,EAAE;IACT;IACA;IACAA,IAAI,GAAG,GAAG;EACZ;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA,QAAQA,IAAI;IACV;IACA;IACA;IACA;IACA,KAAK,KAAK;MACRD,KAAK,GAAGU,WAAW,CAACV,KAAK,EAAES,OAAO,CAAC;MACnC;;IAEF;IACA;IACA;IACA,KAAK,WAAW;MACdT,KAAK,GAAGG,oBAAoB,CAAC,CAAC;MAC9B,IAAIH,KAAK,KAAKW,SAAS,EAAE;QACvB,MAAM,IAAIC,KAAK,wDAAAC,MAAA,CAAsDT,kBAAkB,CAAC,CAAC,CAAE,CAAC;MAC9F;MACAJ,KAAK,GAAGU,WAAW,CAACV,KAAK,EAAES,OAAO,CAAC;MACnC;;IAEF;IACA;IACA;IACA;IACA;IACA,KAAK,GAAG;MACN;MACA;MACA;MACA;MACA,IAAMK,iBAAiB,GAAGC,MAAM,CAACf,KAAK,CAAC;MACvC,IAAIgB,KAAK,CAACF,iBAAiB,CAAC,EAAE;QAC5B,MAAM,IAAIF,KAAK,qCAAAC,MAAA,CAAmCb,KAAK,CAAE,CAAC;MAC5D;MACA,IAAIc,iBAAiB,IAAIP,aAAa,CAACU,MAAM,EAAE;QAC7C,MAAM,IAAIL,KAAK,8CAAAC,MAAA,CAA4Cb,KAAK,CAAE,CAAC;MACrE;MACAA,KAAK,GAAGO,aAAa,CAACO,iBAAiB,CAAC;MACxCd,KAAK,GAAGU,WAAW,CAACV,KAAK,EAAES,OAAO,CAAC;MACnC;;IAEF;IACA;IACA,KAAK,GAAG;MACN,IAAIT,KAAK,KAAK,GAAG,EAAE;QACjBA,KAAK,GAAG,IAAI;MACd,CAAC,MAAM,IAAIA,KAAK,KAAK,GAAG,EAAE;QACxBA,KAAK,GAAG,KAAK;MACf,CAAC,MAAM;QACL,MAAM,IAAIY,KAAK,wCAAAC,MAAA,CAAsCb,KAAK,CAAE,CAAC;MAC/D;MACA;;IAEF;IACA;IACA,KAAK,GAAG;MACNA,KAAK,GAAGW,SAAS;MACjB;;IAEF;IACA;IACA;IACA;IACA,KAAK,GAAG;MACNX,KAAK,GAAGkB,WAAW,CAAClB,KAAK,CAAC;MAC1B;;IAEF;IACA;IACA;IACA;IACA;IACA,KAAK,GAAG;MACN,IAAIA,KAAK,KAAKW,SAAS,EAAE;QACvB;MACF;MACA,IAAMQ,UAAU,GAAG,IAAIC,IAAI,CAACpB,KAAK,CAAC;MAClC,IAAIgB,KAAK,CAACG,UAAU,CAACE,OAAO,CAAC,CAAC,CAAC,EAAE;QAC/B,MAAM,IAAIT,KAAK,qCAAAC,MAAA,CAAmCb,KAAK,CAAE,CAAC;MAC5D;MACAA,KAAK,GAAGmB,UAAU;MAClB;;IAEF;IACA,KAAK,GAAG;MACN,IAAInB,KAAK,KAAKW,SAAS,EAAE;QACvB;MACF;MACA;MACA;MACA,IAAMW,OAAO,GAAGjB,UAAU,CAAC,CAAC;MAC5B,IAAIiB,OAAO,IAAIxB,iBAAiB,CAACwB,OAAO,EAAEhB,MAAM,EAAEG,OAAO,CAAC,EAAE;QAC1D;QACAT,KAAK,GAAGuB,kBAAkB,CAACvB,KAAK,CAAC;QACjC;QACAA,KAAK,GAAGH,cAAc,CAACG,KAAK,EAAE;UAAEQ,SAAS,EAATA;QAAU,CAAC,CAAC;MAC9C,CAAC,MAAM;QACL;QACA;QACA;QACA,IAAMgB,WAAW,GAAGf,OAAO,CAACe,WAAW,IAAID,kBAAkB;QAC7DvB,KAAK,GAAGwB,WAAW,CAACxB,KAAK,CAAC;MAC5B;MACA;IAEF;MACE,MAAM,IAAIyB,SAAS,6BAAAZ,MAAA,CAA6BZ,IAAI,CAAE,CAAC;EAC3D;;EAEA;EACA,IAAID,KAAK,KAAKW,SAAS,EAAE;IACvBX,KAAK,GAAG,IAAI;EACd;EAEA,OAAOA,KAAK;AACd;;AAEA;AACA;AACA,SAASkB,WAAWA,CAACQ,SAAS,EAAE;EAC9B;EACA;EACA,QAAQA,SAAS;IACf,KAAK,IAAI;MACP,OAAO,QAAQ;IACjB,KAAK,IAAI;MACP,OAAO,SAAS;IAClB,KAAK,IAAI;MACP,OAAO,SAAS;IAClB,KAAK,IAAI;MACP,OAAO,OAAO;IAChB,KAAK,IAAI;MACP,OAAO,QAAQ;IACjB,KAAK,IAAI;MACP,OAAO,OAAO;IAChB,KAAK,IAAI;MACP,OAAO,MAAM;IACf,KAAK,IAAI;MACP,OAAO,eAAe;IACxB;MACE;MACA,iBAAAb,MAAA,CAAiBa,SAAS;EAC9B;AACF;AAEA,SAAShB,WAAWA,CAACV,KAAK,EAAES,OAAO,EAAE;EACnC;EACA;EACA;EACA;EACA,IAAIA,OAAO,CAACkB,IAAI,KAAK,KAAK,EAAE;IAC1B3B,KAAK,GAAGA,KAAK,CAAC2B,IAAI,CAAC,CAAC;EACtB;EACA,IAAI3B,KAAK,KAAK,EAAE,EAAE;IAChBA,KAAK,GAAGW,SAAS;EACnB;EACA,OAAOX,KAAK;AACd;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASuB,kBAAkBA,CAACK,iBAAiB,EAAE;EAC7C,IAAMC,YAAY,GAAGd,MAAM,CAACa,iBAAiB,CAAC;EAC9C,IAAIZ,KAAK,CAACa,YAAY,CAAC,EAAE;IACvB,MAAM,IAAIjB,KAAK,oCAAAC,MAAA,CAAkCe,iBAAiB,CAAE,CAAC;EACvE;EACA,OAAOC,YAAY;AACrB"}
+{"version":3,"file":"parseCellValue.js","names":["parseExcelDate","parseNumber","isDateFormatStyle","parseCellValue","value","type","_ref","inlineString","styleId","styles","sharedStrings","epoch1904","options","parseString","undefined","Error","sharedStringIndex","Number","isNaN","concat","length","decodeError","parsedDate","Date","valueOf","TypeError","errorCode","trim"],"sources":["../../source/xlsx/parseCellValue.js"],"sourcesContent":["import parseExcelDate from './parseExcelDate.js'\r\nimport parseNumber from './parseNumber.js'\r\nimport isDateFormatStyle from './isDateFormatStyle.js'\r\n\r\n// Parses a string `value` of a cell.\r\nexport default function parseCellValue(value, type, {\r\n  inlineString,\r\n  styleId,\r\n  styles,\r\n  sharedStrings,\r\n  epoch1904,\r\n  options\r\n}) {\r\n  if (!type) {\r\n    // Default cell type is \"n\" (numeric).\r\n    // http://www.datypic.com/sc/ooxml/t-ssml_CT_Cell.html\r\n    type = 'n'\r\n  }\r\n\r\n  // Available Excel cell types:\r\n  // https://github.com/SheetJS/sheetjs/blob/19620da30be2a7d7b9801938a0b9b1fd3c4c4b00/docbits/52_datatype.md\r\n  //\r\n  // Some other document (seems to be old):\r\n  // http://webapp.docx4java.org/OnlineDemo/ecma376/SpreadsheetML/ST_CellType.html\r\n  //\r\n  switch (type) {\r\n    // XLSX tends to store all strings as \"shared\" (indexed) ones\r\n    // using \"s\" cell type (for saving on strage space).\r\n    // \"str\" cell type is then generally only used for storing\r\n    // formula-pre-calculated cell values.\r\n    case 'str':\r\n      value = parseString(value, options)\r\n      break\r\n\r\n    // Sometimes, XLSX stores strings as \"inline\" strings rather than \"shared\" (indexed) ones.\r\n    // Perhaps the specification doesn't force it to use one or another.\r\n    // Example: `<sheetData><row r=\"1\"><c r=\"A1\" s=\"1\" t=\"inlineStr\"><is><t>Test 123</t></is></c></row></sheetData>`.\r\n    case 'inlineStr':\r\n      value = inlineString\r\n      if (value === undefined) {\r\n        throw new Error('Couldn\\'t read \"inline string\" cell value')\r\n      }\r\n      value = parseString(value, options)\r\n      break\r\n\r\n    // XLSX tends to store string values as \"shared\" (indexed) ones.\r\n    // \"Shared\" strings is a way for an Excel editor to reduce\r\n    // the file size by storing \"commonly used\" strings in a dictionary\r\n    // and then referring to such strings by their index in that dictionary.\r\n    // Example: `<sheetData><row r=\"1\"><c r=\"A1\" s=\"1\" t=\"s\"><v>0</v></c></row></sheetData>`.\r\n    case 's':\r\n      // If a cell has no value then there's no `<c/>` element for it.\r\n      // If a `<c/>` element exists then it's not empty.\r\n      // The `<v/>`alue is a key in the \"shared strings\" dictionary of the\r\n      // XLSX file, so look it up in the `sharedStrings` dictionary by the numeric key.\r\n      const sharedStringIndex = Number(value)\r\n      if (isNaN(sharedStringIndex)) {\r\n        throw new Error(`Invalid \"shared\" string index: ${value}`)\r\n      }\r\n      if (sharedStringIndex >= sharedStrings.length) {\r\n        throw new Error(`An out-of-bounds \"shared\" string index: ${value}`)\r\n      }\r\n      value = sharedStrings[sharedStringIndex]\r\n      value = parseString(value, options)\r\n      break\r\n\r\n    // Boolean (TRUE/FALSE) values are stored as either \"1\" or \"0\"\r\n    // in cells of type \"b\".\r\n    case 'b':\r\n      if (value === '1') {\r\n        value = true\r\n      } else if (value === '0') {\r\n        value = false\r\n      } else {\r\n        throw new Error(`Unsupported \"boolean\" cell value: ${value}`)\r\n      }\r\n      break\r\n\r\n    // XLSX specification seems to support cells of type \"z\":\r\n    // blank \"stub\" cells that should be ignored by data processing utilities.\r\n    case 'z':\r\n      value = undefined\r\n      break\r\n\r\n    // XLSX specification also defines cells of type \"e\" containing a numeric \"error\" code.\r\n    // It's not clear what that means though.\r\n    // They also wrote: \"and `w` property stores its common name\".\r\n    // It's unclear what they meant by that.\r\n    case 'e':\r\n      value = decodeError(value)\r\n      break\r\n\r\n    // XLSX supports date cells of type \"d\", though seems like it (almost?) never\r\n    // uses it for storing dates, preferring \"n\" numeric timestamp cells instead.\r\n    // The value of a \"d\" cell is supposedly a string in \"ISO 8601\" format.\r\n    // I haven't seen an XLSX file having such cells.\r\n    // Example: `<sheetData><row r=\"1\"><c r=\"A1\" s=\"1\" t=\"d\"><v>2021-06-10T00:47:45.700Z</v></c></row></sheetData>`.\r\n    case 'd':\r\n      if (value === undefined) {\r\n        break\r\n      }\r\n      const parsedDate = new Date(value)\r\n      if (isNaN(parsedDate.valueOf())) {\r\n        throw new Error(`Unsupported \"date\" cell value: ${value}`)\r\n      }\r\n      value = parsedDate\r\n      break\r\n\r\n    // Numeric cells have type \"n\".\r\n    case 'n':\r\n      if (value === undefined) {\r\n        break\r\n      }\r\n      // XLSX does have \"d\" type for dates, but it's not commonly used.\r\n      // Instead, it prefers using \"n\" type for storing dates as timestamps.\r\n      if (styleId && isDateFormatStyle(styleId, styles, options)) {\r\n        // Parse the number from string.\r\n        value = parseNumber(value)\r\n        // Parse the number as a date timestamp.\r\n        value = parseExcelDate(value, { epoch1904 })\r\n      } else {\r\n        // Parse the number from string.\r\n        // Supports custom parsing function to work around javascript number encoding precision issues.\r\n        // https://gitlab.com/catamphetamine/read-excel-file/-/issues/85\r\n        value = (options.parseNumber || parseNumber)(value)\r\n      }\r\n      break\r\n\r\n    default:\r\n      throw new TypeError(`Cell type not supported: ${type}`)\r\n  }\r\n\r\n  // Convert empty values to `null`.\r\n  if (value === undefined) {\r\n    value = null\r\n  }\r\n\r\n  return value\r\n}\r\n\r\n// Decodes numeric error code to a string code.\r\n// https://github.com/SheetJS/sheetjs/blob/19620da30be2a7d7b9801938a0b9b1fd3c4c4b00/docbits/52_datatype.md\r\nfunction decodeError(errorCode) {\r\n  // While the error values are determined by the application,\r\n  // the following are some example error values that could be used:\r\n  switch (errorCode) {\r\n    case 0x00:\r\n      return '#NULL!'\r\n    case 0x07:\r\n      return '#DIV/0!'\r\n    case 0x0F:\r\n      return '#VALUE!'\r\n    case 0x17:\r\n      return '#REF!'\r\n    case 0x1D:\r\n      return '#NAME?'\r\n    case 0x24:\r\n      return '#NUM!'\r\n    case 0x2A:\r\n      return '#N/A'\r\n    case 0x2B:\r\n      return '#GETTING_DATA'\r\n    default:\r\n      // Such error code doesn't exist. I made it up.\r\n      return `#ERROR_${errorCode}`\r\n  }\r\n}\r\n\r\nfunction parseString(value, options) {\r\n  // In some weird cases, a developer might want to disable\r\n  // the automatic trimming of all strings.\r\n  // For example, leading spaces might express a tree-like hierarchy.\r\n  // https://github.com/catamphetamine/read-excel-file/pull/106#issuecomment-1136062917\r\n  if (options.trim !== false) {\r\n    value = value.trim()\r\n  }\r\n  if (value === '') {\r\n    value = undefined\r\n  }\r\n  return value\r\n}"],"mappings":"AAAA,OAAOA,cAAc,MAAM,qBAAqB;AAChD,OAAOC,WAAW,MAAM,kBAAkB;AAC1C,OAAOC,iBAAiB,MAAM,wBAAwB;;AAEtD;AACA,eAAe,SAASC,cAAcA,CAACC,KAAK,EAAEC,IAAI,EAAAC,IAAA,EAO/C;EAAA,IANDC,YAAY,GAAAD,IAAA,CAAZC,YAAY;IACZC,OAAO,GAAAF,IAAA,CAAPE,OAAO;IACPC,MAAM,GAAAH,IAAA,CAANG,MAAM;IACNC,aAAa,GAAAJ,IAAA,CAAbI,aAAa;IACbC,SAAS,GAAAL,IAAA,CAATK,SAAS;IACTC,OAAO,GAAAN,IAAA,CAAPM,OAAO;EAEP,IAAI,CAACP,IAAI,EAAE;IACT;IACA;IACAA,IAAI,GAAG,GAAG;EACZ;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA,QAAQA,IAAI;IACV;IACA;IACA;IACA;IACA,KAAK,KAAK;MACRD,KAAK,GAAGS,WAAW,CAACT,KAAK,EAAEQ,OAAO,CAAC;MACnC;;IAEF;IACA;IACA;IACA,KAAK,WAAW;MACdR,KAAK,GAAGG,YAAY;MACpB,IAAIH,KAAK,KAAKU,SAAS,EAAE;QACvB,MAAM,IAAIC,KAAK,CAAC,2CAA2C,CAAC;MAC9D;MACAX,KAAK,GAAGS,WAAW,CAACT,KAAK,EAAEQ,OAAO,CAAC;MACnC;;IAEF;IACA;IACA;IACA;IACA;IACA,KAAK,GAAG;MACN;MACA;MACA;MACA;MACA,IAAMI,iBAAiB,GAAGC,MAAM,CAACb,KAAK,CAAC;MACvC,IAAIc,KAAK,CAACF,iBAAiB,CAAC,EAAE;QAC5B,MAAM,IAAID,KAAK,qCAAAI,MAAA,CAAmCf,KAAK,CAAE,CAAC;MAC5D;MACA,IAAIY,iBAAiB,IAAIN,aAAa,CAACU,MAAM,EAAE;QAC7C,MAAM,IAAIL,KAAK,8CAAAI,MAAA,CAA4Cf,KAAK,CAAE,CAAC;MACrE;MACAA,KAAK,GAAGM,aAAa,CAACM,iBAAiB,CAAC;MACxCZ,KAAK,GAAGS,WAAW,CAACT,KAAK,EAAEQ,OAAO,CAAC;MACnC;;IAEF;IACA;IACA,KAAK,GAAG;MACN,IAAIR,KAAK,KAAK,GAAG,EAAE;QACjBA,KAAK,GAAG,IAAI;MACd,CAAC,MAAM,IAAIA,KAAK,KAAK,GAAG,EAAE;QACxBA,KAAK,GAAG,KAAK;MACf,CAAC,MAAM;QACL,MAAM,IAAIW,KAAK,wCAAAI,MAAA,CAAsCf,KAAK,CAAE,CAAC;MAC/D;MACA;;IAEF;IACA;IACA,KAAK,GAAG;MACNA,KAAK,GAAGU,SAAS;MACjB;;IAEF;IACA;IACA;IACA;IACA,KAAK,GAAG;MACNV,KAAK,GAAGiB,WAAW,CAACjB,KAAK,CAAC;MAC1B;;IAEF;IACA;IACA;IACA;IACA;IACA,KAAK,GAAG;MACN,IAAIA,KAAK,KAAKU,SAAS,EAAE;QACvB;MACF;MACA,IAAMQ,UAAU,GAAG,IAAIC,IAAI,CAACnB,KAAK,CAAC;MAClC,IAAIc,KAAK,CAACI,UAAU,CAACE,OAAO,CAAC,CAAC,CAAC,EAAE;QAC/B,MAAM,IAAIT,KAAK,qCAAAI,MAAA,CAAmCf,KAAK,CAAE,CAAC;MAC5D;MACAA,KAAK,GAAGkB,UAAU;MAClB;;IAEF;IACA,KAAK,GAAG;MACN,IAAIlB,KAAK,KAAKU,SAAS,EAAE;QACvB;MACF;MACA;MACA;MACA,IAAIN,OAAO,IAAIN,iBAAiB,CAACM,OAAO,EAAEC,MAAM,EAAEG,OAAO,CAAC,EAAE;QAC1D;QACAR,KAAK,GAAGH,WAAW,CAACG,KAAK,CAAC;QAC1B;QACAA,KAAK,GAAGJ,cAAc,CAACI,KAAK,EAAE;UAAEO,SAAS,EAATA;QAAU,CAAC,CAAC;MAC9C,CAAC,MAAM;QACL;QACA;QACA;QACAP,KAAK,GAAG,CAACQ,OAAO,CAACX,WAAW,IAAIA,WAAW,EAAEG,KAAK,CAAC;MACrD;MACA;IAEF;MACE,MAAM,IAAIqB,SAAS,6BAAAN,MAAA,CAA6Bd,IAAI,CAAE,CAAC;EAC3D;;EAEA;EACA,IAAID,KAAK,KAAKU,SAAS,EAAE;IACvBV,KAAK,GAAG,IAAI;EACd;EAEA,OAAOA,KAAK;AACd;;AAEA;AACA;AACA,SAASiB,WAAWA,CAACK,SAAS,EAAE;EAC9B;EACA;EACA,QAAQA,SAAS;IACf,KAAK,IAAI;MACP,OAAO,QAAQ;IACjB,KAAK,IAAI;MACP,OAAO,SAAS;IAClB,KAAK,IAAI;MACP,OAAO,SAAS;IAClB,KAAK,IAAI;MACP,OAAO,OAAO;IAChB,KAAK,IAAI;MACP,OAAO,QAAQ;IACjB,KAAK,IAAI;MACP,OAAO,OAAO;IAChB,KAAK,IAAI;MACP,OAAO,MAAM;IACf,KAAK,IAAI;MACP,OAAO,eAAe;IACxB;MACE;MACA,iBAAAP,MAAA,CAAiBO,SAAS;EAC9B;AACF;AAEA,SAASb,WAAWA,CAACT,KAAK,EAAEQ,OAAO,EAAE;EACnC;EACA;EACA;EACA;EACA,IAAIA,OAAO,CAACe,IAAI,KAAK,KAAK,EAAE;IAC1BvB,KAAK,GAAGA,KAAK,CAACuB,IAAI,CAAC,CAAC;EACtB;EACA,IAAIvB,KAAK,KAAK,EAAE,EAAE;IAChBA,KAAK,GAAGU,SAAS;EACnB;EACA,OAAOV,KAAK;AACd"}

package/modules/xlsx/parseFilePaths.js

@@ -1,15 +1,13 @@
-import { getRelationships } from '../xml/xlsx.js';
-
 /**
  * Returns sheet file paths.
  * Seems that the correct place to look for the `sheetId` -> `filename` mapping
  * is `xl/_rels/workbook.xml.rels` file.
  * https://github.com/tidyverse/readxl/issues/104
  * @param  {string} content — `xl/_rels/workbook.xml.rels` file contents.
- * @param  {object} xml
- * @return {object}
+ * @param  {function} parseXmlStream — SAX XML parser.
+ * @return {object} — An object of shape `{ sheets: Record<string, string>, sharedStrings: string?, styles: string? }`
  */
-export default function parseFilePaths(content, xml) {
+export default function parseFilePaths(content, parseXmlStream) {
   // Example:
   // <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
   //   ...
@@ -18,39 +16,39 @@ export default function parseFilePaths(content, xml) {
   //     Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet"
   //     Target="worksheets/sheet1.xml"/>
   // </Relationships>
-  var document = xml.createDocument(content);
-  var filePaths = {
+  return parseXmlStream(content, {
+    createInitialState: createInitialStateInWorkbookRelationships,
+    onOpenTag: onOpenTagInWorkbookRelationships
+  }).then(function (state) {
+    return state;
+  });
+}
+function createInitialStateInWorkbookRelationships() {
+  return {
     sheets: {},
     sharedStrings: undefined,
     styles: undefined
   };
-  var addFilePathInfo = function addFilePathInfo(relationship) {
-    var filePath = relationship.getAttribute('Target');
-    var fileType = relationship.getAttribute('Type');
-    switch (fileType) {
-      case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles':
-        filePaths.styles = getFilePath(filePath);
-        break;
-      case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/sharedStrings':
-        filePaths.sharedStrings = getFilePath(filePath);
-        break;
-      case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet':
-        filePaths.sheets[relationship.getAttribute('Id')] = getFilePath(filePath);
-        break;
-    }
-  };
-  getRelationships(document).forEach(addFilePathInfo);
-
-  // Seems like "sharedStrings.xml" is not required to exist.
-  // For example, when the spreadsheet doesn't contain any strings.
-  // https://github.com/catamphetamine/read-excel-file/issues/85
-  // if (!filePaths.sharedStrings) {
-  //   throw new Error('"sharedStrings.xml" file not found in the *.xlsx file')
-  // }
-
-  return filePaths;
 }
-function getFilePath(path) {
+function onOpenTagInWorkbookRelationships(tagName, attributes, state) {
+  if (tagName === 'Relationship') {
+    addFilePathForRelation(state, attributes.Id, attributes.Type, attributes.Target);
+  }
+}
+function addFilePathForRelation(state, id, type, target) {
+  switch (type) {
+    case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles':
+      state.styles = getFilePathFromRelationTarget(target);
+      break;
+    case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/sharedStrings':
+      state.sharedStrings = getFilePathFromRelationTarget(target);
+      break;
+    case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet':
+      state.sheets[id] = getFilePathFromRelationTarget(target);
+      break;
+  }
+}
+function getFilePathFromRelationTarget(path) {
   // Normally, `path` is a relative path inside the ZIP archive,
   // like "worksheets/sheet1.xml", or "sharedStrings.xml", or "styles.xml".
   // There has been one weird case when file path was an absolute path,

package/modules/xlsx/parseFilePaths.js.map

@@ -1 +1 @@
-{"version":3,"file":"parseFilePaths.js","names":["getRelationships","parseFilePaths","content","xml","document","createDocument","filePaths","sheets","sharedStrings","undefined","styles","addFilePathInfo","relationship","filePath","getAttribute","fileType","getFilePath","forEach","path","slice","length"],"sources":["../../source/xlsx/parseFilePaths.js"],"sourcesContent":["import {\r\n  getRelationships\r\n} from '../xml/xlsx.js'\r\n\r\n/**\r\n * Returns sheet file paths.\r\n * Seems that the correct place to look for the `sheetId` -> `filename` mapping\r\n * is `xl/_rels/workbook.xml.rels` file.\r\n * https://github.com/tidyverse/readxl/issues/104\r\n * @param  {string} content — `xl/_rels/workbook.xml.rels` file contents.\r\n * @param  {object} xml\r\n * @return {object}\r\n */\r\nexport default function parseFilePaths(content, xml) {\r\n  // Example:\r\n  // <Relationships xmlns=\"http://schemas.openxmlformats.org/package/2006/relationships\">\r\n  //   ...\r\n  //   <Relationship\r\n  //     Id=\"rId3\"\r\n  //     Type=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet\"\r\n  //     Target=\"worksheets/sheet1.xml\"/>\r\n  // </Relationships>\r\n  const document = xml.createDocument(content)\r\n\r\n  const filePaths = {\r\n    sheets: {},\r\n    sharedStrings: undefined,\r\n    styles: undefined\r\n  }\r\n\r\n  const addFilePathInfo = (relationship) => {\r\n    const filePath = relationship.getAttribute('Target')\r\n    const fileType = relationship.getAttribute('Type')\r\n    switch (fileType) {\r\n      case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles':\r\n        filePaths.styles = getFilePath(filePath)\r\n        break\r\n      case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/sharedStrings':\r\n        filePaths.sharedStrings = getFilePath(filePath)\r\n        break\r\n      case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet':\r\n        filePaths.sheets[relationship.getAttribute('Id')] = getFilePath(filePath)\r\n        break\r\n    }\r\n  }\r\n\r\n  getRelationships(document).forEach(addFilePathInfo)\r\n\r\n  // Seems like \"sharedStrings.xml\" is not required to exist.\r\n  // For example, when the spreadsheet doesn't contain any strings.\r\n  // https://github.com/catamphetamine/read-excel-file/issues/85\r\n  // if (!filePaths.sharedStrings) {\r\n  //   throw new Error('\"sharedStrings.xml\" file not found in the *.xlsx file')\r\n  // }\r\n\r\n  return filePaths\r\n}\r\n\r\nfunction getFilePath(path) {\r\n  // Normally, `path` is a relative path inside the ZIP archive,\r\n  // like \"worksheets/sheet1.xml\", or \"sharedStrings.xml\", or \"styles.xml\".\r\n  // There has been one weird case when file path was an absolute path,\r\n  // like \"/xl/worksheets/sheet1.xml\" (specifically for sheets):\r\n  // https://github.com/catamphetamine/read-excel-file/pull/95\r\n  // Other libraries (like `xlsx`) and software (like Google Docs)\r\n  // seem to support such absolute file paths, so this library does too.\r\n  if (path[0] === '/') {\r\n    return path.slice('/'.length)\r\n  }\r\n  // // Seems like a path could also be a URL.\r\n  // // http://officeopenxml.com/anatomyofOOXML-xlsx.php\r\n  // if (/^[a-z]+\\:\\/\\//.test(path)) {\r\n  //   return path\r\n  // }\r\n  return 'xl/' + path\r\n}"],"mappings":"AAAA,SACEA,gBAAgB,QACX,gBAAgB;;AAEvB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,cAAcA,CAACC,OAAO,EAAEC,GAAG,EAAE;EACnD;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA,IAAMC,QAAQ,GAAGD,GAAG,CAACE,cAAc,CAACH,OAAO,CAAC;EAE5C,IAAMI,SAAS,GAAG;IAChBC,MAAM,EAAE,CAAC,CAAC;IACVC,aAAa,EAAEC,SAAS;IACxBC,MAAM,EAAED;EACV,CAAC;EAED,IAAME,eAAe,GAAG,SAAlBA,eAAeA,CAAIC,YAAY,EAAK;IACxC,IAAMC,QAAQ,GAAGD,YAAY,CAACE,YAAY,CAAC,QAAQ,CAAC;IACpD,IAAMC,QAAQ,GAAGH,YAAY,CAACE,YAAY,CAAC,MAAM,CAAC;IAClD,QAAQC,QAAQ;MACd,KAAK,4EAA4E;QAC/ET,SAAS,CAACI,MAAM,GAAGM,WAAW,CAACH,QAAQ,CAAC;QACxC;MACF,KAAK,mFAAmF;QACtFP,SAAS,CAACE,aAAa,GAAGQ,WAAW,CAACH,QAAQ,CAAC;QAC/C;MACF,KAAK,+EAA+E;QAClFP,SAAS,CAACC,MAAM,CAACK,YAAY,CAACE,YAAY,CAAC,IAAI,CAAC,CAAC,GAAGE,WAAW,CAACH,QAAQ,CAAC;QACzE;IACJ;EACF,CAAC;EAEDb,gBAAgB,CAACI,QAAQ,CAAC,CAACa,OAAO,CAACN,eAAe,CAAC;;EAEnD;EACA;EACA;EACA;EACA;EACA;;EAEA,OAAOL,SAAS;AAClB;AAEA,SAASU,WAAWA,CAACE,IAAI,EAAE;EACzB;EACA;EACA;EACA;EACA;EACA;EACA;EACA,IAAIA,IAAI,CAAC,CAAC,CAAC,KAAK,GAAG,EAAE;IACnB,OAAOA,IAAI,CAACC,KAAK,CAAC,GAAG,CAACC,MAAM,CAAC;EAC/B;EACA;EACA;EACA;EACA;EACA;EACA,OAAO,KAAK,GAAGF,IAAI;AACrB"}
+{"version":3,"file":"parseFilePaths.js","names":["parseFilePaths","content","parseXmlStream","createInitialState","createInitialStateInWorkbookRelationships","onOpenTag","onOpenTagInWorkbookRelationships","then","state","sheets","sharedStrings","undefined","styles","tagName","attributes","addFilePathForRelation","Id","Type","Target","id","type","target","getFilePathFromRelationTarget","path","slice","length"],"sources":["../../source/xlsx/parseFilePaths.js"],"sourcesContent":["/**\r\n * Returns sheet file paths.\r\n * Seems that the correct place to look for the `sheetId` -> `filename` mapping\r\n * is `xl/_rels/workbook.xml.rels` file.\r\n * https://github.com/tidyverse/readxl/issues/104\r\n * @param  {string} content — `xl/_rels/workbook.xml.rels` file contents.\r\n * @param  {function} parseXmlStream — SAX XML parser.\r\n * @return {object} — An object of shape `{ sheets: Record<string, string>, sharedStrings: string?, styles: string? }`\r\n */\r\nexport default function parseFilePaths(content, parseXmlStream) {\r\n  // Example:\r\n  // <Relationships xmlns=\"http://schemas.openxmlformats.org/package/2006/relationships\">\r\n  //   ...\r\n  //   <Relationship\r\n  //     Id=\"rId3\"\r\n  //     Type=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet\"\r\n  //     Target=\"worksheets/sheet1.xml\"/>\r\n  // </Relationships>\r\n  return parseXmlStream(content, {\r\n    createInitialState: createInitialStateInWorkbookRelationships,\r\n    onOpenTag: onOpenTagInWorkbookRelationships\r\n  }).then((state) => {\r\n    return state\r\n  })\r\n}\r\n\r\nfunction createInitialStateInWorkbookRelationships() {\r\n  return {\r\n    sheets: {},\r\n    sharedStrings: undefined,\r\n    styles: undefined\r\n  }\r\n}\r\n\r\nfunction onOpenTagInWorkbookRelationships(tagName, attributes, state) {\r\n  if (tagName === 'Relationship') {\r\n    addFilePathForRelation(state, attributes.Id, attributes.Type, attributes.Target)\r\n  }\r\n}\r\n\r\nfunction addFilePathForRelation(state, id, type, target) {\r\n  switch (type) {\r\n    case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles':\r\n      state.styles = getFilePathFromRelationTarget(target)\r\n      break\r\n    case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/sharedStrings':\r\n      state.sharedStrings = getFilePathFromRelationTarget(target)\r\n      break\r\n    case 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet':\r\n      state.sheets[id] = getFilePathFromRelationTarget(target)\r\n      break\r\n  }\r\n}\r\n\r\nfunction getFilePathFromRelationTarget(path) {\r\n  // Normally, `path` is a relative path inside the ZIP archive,\r\n  // like \"worksheets/sheet1.xml\", or \"sharedStrings.xml\", or \"styles.xml\".\r\n  // There has been one weird case when file path was an absolute path,\r\n  // like \"/xl/worksheets/sheet1.xml\" (specifically for sheets):\r\n  // https://github.com/catamphetamine/read-excel-file/pull/95\r\n  // Other libraries (like `xlsx`) and software (like Google Docs)\r\n  // seem to support such absolute file paths, so this library does too.\r\n  if (path[0] === '/') {\r\n    return path.slice('/'.length)\r\n  }\r\n  // // Seems like a path could also be a URL.\r\n  // // http://officeopenxml.com/anatomyofOOXML-xlsx.php\r\n  // if (/^[a-z]+\\:\\/\\//.test(path)) {\r\n  //   return path\r\n  // }\r\n  return 'xl/' + path\r\n}\r\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASA,cAAcA,CAACC,OAAO,EAAEC,cAAc,EAAE;EAC9D;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA,OAAOA,cAAc,CAACD,OAAO,EAAE;IAC7BE,kBAAkB,EAAEC,yCAAyC;IAC7DC,SAAS,EAAEC;EACb,CAAC,CAAC,CAACC,IAAI,CAAC,UAACC,KAAK,EAAK;IACjB,OAAOA,KAAK;EACd,CAAC,CAAC;AACJ;AAEA,SAASJ,yCAAyCA,CAAA,EAAG;EACnD,OAAO;IACLK,MAAM,EAAE,CAAC,CAAC;IACVC,aAAa,EAAEC,SAAS;IACxBC,MAAM,EAAED;EACV,CAAC;AACH;AAEA,SAASL,gCAAgCA,CAACO,OAAO,EAAEC,UAAU,EAAEN,KAAK,EAAE;EACpE,IAAIK,OAAO,KAAK,cAAc,EAAE;IAC9BE,sBAAsB,CAACP,KAAK,EAAEM,UAAU,CAACE,EAAE,EAAEF,UAAU,CAACG,IAAI,EAAEH,UAAU,CAACI,MAAM,CAAC;EAClF;AACF;AAEA,SAASH,sBAAsBA,CAACP,KAAK,EAAEW,EAAE,EAAEC,IAAI,EAAEC,MAAM,EAAE;EACvD,QAAQD,IAAI;IACV,KAAK,4EAA4E;MAC/EZ,KAAK,CAACI,MAAM,GAAGU,6BAA6B,CAACD,MAAM,CAAC;MACpD;IACF,KAAK,mFAAmF;MACtFb,KAAK,CAACE,aAAa,GAAGY,6BAA6B,CAACD,MAAM,CAAC;MAC3D;IACF,KAAK,+EAA+E;MAClFb,KAAK,CAACC,MAAM,CAACU,EAAE,CAAC,GAAGG,6BAA6B,CAACD,MAAM,CAAC;MACxD;EACJ;AACF;AAEA,SAASC,6BAA6BA,CAACC,IAAI,EAAE;EAC3C;EACA;EACA;EACA;EACA;EACA;EACA;EACA,IAAIA,IAAI,CAAC,CAAC,CAAC,KAAK,GAAG,EAAE;IACnB,OAAOA,IAAI,CAACC,KAAK,CAAC,GAAG,CAACC,MAAM,CAAC;EAC/B;EACA;EACA;EACA;EACA;EACA;EACA,OAAO,KAAK,GAAGF,IAAI;AACrB"}

package/modules/xlsx/parseNumber.js

@@ -0,0 +1,14 @@
+// Parses a number from string.
+// Throws an error if the number couldn't be parsed.
+// When parsing floating-point number, is affected by
+// the javascript number encoding precision issues:
+// https://www.youtube.com/watch?v=2gIxbTn7GSc
+// https://www.avioconsulting.com/blog/overcoming-javascript-numeric-precision-issues
+export default function parseNumber(stringifiedNumber) {
+  var parsedNumber = Number(stringifiedNumber);
+  if (isNaN(parsedNumber)) {
+    throw new Error("Couldn't parse number: ".concat(stringifiedNumber));
+  }
+  return parsedNumber;
+}
+//# sourceMappingURL=parseNumber.js.map

package/modules/xlsx/parseNumber.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"parseNumber.js","names":["parseNumber","stringifiedNumber","parsedNumber","Number","isNaN","Error","concat"],"sources":["../../source/xlsx/parseNumber.js"],"sourcesContent":["// Parses a number from string.\r\n// Throws an error if the number couldn't be parsed.\r\n// When parsing floating-point number, is affected by\r\n// the javascript number encoding precision issues:\r\n// https://www.youtube.com/watch?v=2gIxbTn7GSc\r\n// https://www.avioconsulting.com/blog/overcoming-javascript-numeric-precision-issues\r\nexport default function parseNumber(stringifiedNumber) {\r\n  const parsedNumber = Number(stringifiedNumber)\r\n  if (isNaN(parsedNumber)) {\r\n    throw new Error(`Couldn't parse number: ${stringifiedNumber}`)\r\n  }\r\n  return parsedNumber\r\n}"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASA,WAAWA,CAACC,iBAAiB,EAAE;EACrD,IAAMC,YAAY,GAAGC,MAAM,CAACF,iBAAiB,CAAC;EAC9C,IAAIG,KAAK,CAACF,YAAY,CAAC,EAAE;IACvB,MAAM,IAAIG,KAAK,2BAAAC,MAAA,CAA2BL,iBAAiB,CAAE,CAAC;EAChE;EACA,OAAOC,YAAY;AACrB"}

package/modules/xlsx/parseSharedString.js

@@ -0,0 +1,55 @@
+export function createInitialStateInSharedString() {
+  return {
+    t: false,
+    r: false,
+    rPh: false,
+    string: ''
+  };
+}
+
+// In an XLSX `sharedStrings.xml` file, a <si/> (string item) element can have
+// either a single child <t/> element (meaning that "rich formatting" is not used)
+// or multiple child <r/> elements (meaning that "rich formatting" is used).
+export function onOpenTagInSharedString(tagName, attributes, state) {
+  // The possible children of <si> are:
+  // * <t>: Represents a simple text string. For plain text, this is the only child.
+  // * <r>: Represents a rich text run. When a cell contains text where only some words are bolded, colored, or styled differently, multiple <r> elements are used to break the text into formatted segments.
+  // * <rPh> (Phonetic Run): Used primarily for East Asian languages to provide phonetic reading/pronunciation data (e.g., furigana in Japanese). It associates a phonetic pronunciation run right alongside the base string text tag <t>.
+  // * <phoneticPr>: Defines the phonetic properties used for East Asian languages, specifically mapping how strings should be read for sorting and pronunciation.
+  if (tagName === 't') {
+    state.t = true;
+  } else if (tagName === 'r') {
+    // The possible children of <r/> are:
+    // * <rPr> (Run Properties): The formatting properties for the text (font, size, color, bold, italic, etc.).
+    // * <t> (Text): The actual text payload.
+    // * <rPh> (Phonetic Run): Phonetic pronunciation guidance (used for East Asian languages like Japanese). It associates a phonetic pronunciation run right alongside the base string text tag <t>.
+    state.r = true;
+  } else if (tagName === 'rPh') {
+    // The possible children of <rPh/> are:
+    // * <t> (Text):  Contains the actual phonetic text or reading (usually in Katakana for Japanese) that corresponds to the associated character string.
+    state.rPh = true;
+  }
+}
+export function onCloseTagInSharedString(tagName, state) {
+  if (tagName === 't') {
+    state.t = false;
+  } else if (tagName === 'r') {
+    state.r = false;
+  } else if (tagName === 'rPh') {
+    state.rPh = false;
+  }
+}
+export function onTextInSharedString(text, state) {
+  if (state.rPh) {
+    // Ignore anything inside `<rPh/>` tags
+  } else if (state.t) {
+    if (state.r) {
+      // An `<r/>` element could contain multiple `<t/>` elements,
+      // the text content from all of which should be concatenated.
+      state.string += text;
+    } else {
+      state.string = text;
+    }
+  }
+}
+//# sourceMappingURL=parseSharedString.js.map

package/modules/xlsx/parseSharedString.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"parseSharedString.js","names":["createInitialStateInSharedString","t","r","rPh","string","onOpenTagInSharedString","tagName","attributes","state","onCloseTagInSharedString","onTextInSharedString","text"],"sources":["../../source/xlsx/parseSharedString.js"],"sourcesContent":["export function createInitialStateInSharedString() {\r\n\treturn {\r\n\t\tt: false,\r\n\t\tr: false,\r\n\t\trPh: false,\r\n\t\tstring: ''\r\n\t}\r\n}\r\n\r\n// In an XLSX `sharedStrings.xml` file, a <si/> (string item) element can have\r\n// either a single child <t/> element (meaning that \"rich formatting\" is not used)\r\n// or multiple child <r/> elements (meaning that \"rich formatting\" is used).\r\nexport function onOpenTagInSharedString(tagName, attributes, state) {\r\n\t// The possible children of <si> are:\r\n\t// * <t>: Represents a simple text string. For plain text, this is the only child.\r\n\t// * <r>: Represents a rich text run. When a cell contains text where only some words are bolded, colored, or styled differently, multiple <r> elements are used to break the text into formatted segments.\r\n\t// * <rPh> (Phonetic Run): Used primarily for East Asian languages to provide phonetic reading/pronunciation data (e.g., furigana in Japanese). It associates a phonetic pronunciation run right alongside the base string text tag <t>.\r\n\t// * <phoneticPr>: Defines the phonetic properties used for East Asian languages, specifically mapping how strings should be read for sorting and pronunciation.\r\n\tif (tagName === 't') {\r\n\t\tstate.t = true\r\n\t} else if (tagName === 'r') {\r\n\t\t// The possible children of <r/> are:\r\n\t\t// * <rPr> (Run Properties): The formatting properties for the text (font, size, color, bold, italic, etc.).\r\n\t\t// * <t> (Text): The actual text payload.\r\n\t\t// * <rPh> (Phonetic Run): Phonetic pronunciation guidance (used for East Asian languages like Japanese). It associates a phonetic pronunciation run right alongside the base string text tag <t>.\r\n\t\tstate.r = true\r\n\t} else if (tagName === 'rPh') {\r\n\t\t// The possible children of <rPh/> are:\r\n\t\t// * <t> (Text):  Contains the actual phonetic text or reading (usually in Katakana for Japanese) that corresponds to the associated character string.\r\n\t\tstate.rPh = true\r\n\t}\r\n}\r\n\r\nexport function onCloseTagInSharedString(tagName, state) {\r\n\tif (tagName === 't') {\r\n\t\tstate.t = false\r\n\t} else if (tagName === 'r') {\r\n\t\tstate.r = false\r\n\t} else if (tagName === 'rPh') {\r\n\t\tstate.rPh = false\r\n\t}\r\n}\r\n\r\nexport function onTextInSharedString(text, state) {\r\n\tif (state.rPh) {\r\n\t\t// Ignore anything inside `<rPh/>` tags\r\n\t} else if (state.t) {\r\n\t\tif (state.r) {\r\n\t\t\t// An `<r/>` element could contain multiple `<t/>` elements,\r\n\t\t\t// the text content from all of which should be concatenated.\r\n\t\t\tstate.string += text\r\n\t\t} else {\r\n\t\t\tstate.string = text\r\n\t\t}\r\n\t}\r\n}"],"mappings":"AAAA,OAAO,SAASA,gCAAgCA,CAAA,EAAG;EAClD,OAAO;IACNC,CAAC,EAAE,KAAK;IACRC,CAAC,EAAE,KAAK;IACRC,GAAG,EAAE,KAAK;IACVC,MAAM,EAAE;EACT,CAAC;AACF;;AAEA;AACA;AACA;AACA,OAAO,SAASC,uBAAuBA,CAACC,OAAO,EAAEC,UAAU,EAAEC,KAAK,EAAE;EACnE;EACA;EACA;EACA;EACA;EACA,IAAIF,OAAO,KAAK,GAAG,EAAE;IACpBE,KAAK,CAACP,CAAC,GAAG,IAAI;EACf,CAAC,MAAM,IAAIK,OAAO,KAAK,GAAG,EAAE;IAC3B;IACA;IACA;IACA;IACAE,KAAK,CAACN,CAAC,GAAG,IAAI;EACf,CAAC,MAAM,IAAII,OAAO,KAAK,KAAK,EAAE;IAC7B;IACA;IACAE,KAAK,CAACL,GAAG,GAAG,IAAI;EACjB;AACD;AAEA,OAAO,SAASM,wBAAwBA,CAACH,OAAO,EAAEE,KAAK,EAAE;EACxD,IAAIF,OAAO,KAAK,GAAG,EAAE;IACpBE,KAAK,CAACP,CAAC,GAAG,KAAK;EAChB,CAAC,MAAM,IAAIK,OAAO,KAAK,GAAG,EAAE;IAC3BE,KAAK,CAACN,CAAC,GAAG,KAAK;EAChB,CAAC,MAAM,IAAII,OAAO,KAAK,KAAK,EAAE;IAC7BE,KAAK,CAACL,GAAG,GAAG,KAAK;EAClB;AACD;AAEA,OAAO,SAASO,oBAAoBA,CAACC,IAAI,EAAEH,KAAK,EAAE;EACjD,IAAIA,KAAK,CAACL,GAAG,EAAE;IACd;EAAA,CACA,MAAM,IAAIK,KAAK,CAACP,CAAC,EAAE;IACnB,IAAIO,KAAK,CAACN,CAAC,EAAE;MACZ;MACA;MACAM,KAAK,CAACJ,MAAM,IAAIO,IAAI;IACrB,CAAC,MAAM;MACNH,KAAK,CAACJ,MAAM,GAAGO,IAAI;IACpB;EACD;AACD"}

package/modules/xlsx/parseSharedStrings.js

@@ -1,8 +1,49 @@
-import { getSharedStrings } from '../xml/xlsx.js';
-export default function parseSharedStrings(content, xml) {
-  if (!content) {
-    return [];
+import { onOpenTagInSharedString, onCloseTagInSharedString, onTextInSharedString, createInitialStateInSharedString } from './parseSharedString.js';
+
+/**
+ * Parses `sharedStrings.xml` file.
+ * @param {string} content
+ * @param {function} parseXmlStream — SAX XML parser.
+ * @returns {Promise<string[]>}
+ */
+export default function parseSharedStrings(content, parseXmlStream) {
+  return parseXmlStream(content, {
+    createInitialState: createInitialStateInSharedStrings,
+    onOpenTag: onOpenTagInSharedStrings,
+    onCloseTag: onCloseTagInSharedStrings,
+    onText: onTextInSharedStrings
+  }).then(function (state) {
+    return state.strings;
+  });
+}
+function createInitialStateInSharedStrings() {
+  return {
+    si: undefined,
+    strings: []
+  };
+}
+
+// In an XLSX `sharedStrings.xml` file, a <si/> (string item) element can have
+// either a single child <t/> element (meaning that "rich formatting" is not used)
+// or multiple child <r/> elements (meaning that "rich formatting" is used).
+function onOpenTagInSharedStrings(tagName, attributes, state) {
+  if (tagName === 'si') {
+    state.si = createInitialStateInSharedString();
+  } else if (state.si) {
+    onOpenTagInSharedString(tagName, attributes, state.si);
+  }
+}
+function onCloseTagInSharedStrings(tagName, state) {
+  if (tagName === 'si') {
+    state.strings.push(state.si.string);
+    state.si = undefined;
+  } else if (state.si) {
+    onCloseTagInSharedString(tagName, state.si);
+  }
+}
+function onTextInSharedStrings(text, state) {
+  if (state.si) {
+    onTextInSharedString(text, state.si);
   }
-  return getSharedStrings(xml.createDocument(content));
 }
 //# sourceMappingURL=parseSharedStrings.js.map

package/modules/xlsx/parseSharedStrings.js.map

@@ -1 +1 @@
-{"version":3,"file":"parseSharedStrings.js","names":["getSharedStrings","parseSharedStrings","content","xml","createDocument"],"sources":["../../source/xlsx/parseSharedStrings.js"],"sourcesContent":["import {\r\n  getSharedStrings\r\n} from '../xml/xlsx.js'\r\n\r\nexport default function parseSharedStrings(content, xml) {\r\n  if (!content) {\r\n    return []\r\n  }\r\n  return getSharedStrings(xml.createDocument(content))\r\n}"],"mappings":"AAAA,SACEA,gBAAgB,QACX,gBAAgB;AAEvB,eAAe,SAASC,kBAAkBA,CAACC,OAAO,EAAEC,GAAG,EAAE;EACvD,IAAI,CAACD,OAAO,EAAE;IACZ,OAAO,EAAE;EACX;EACA,OAAOF,gBAAgB,CAACG,GAAG,CAACC,cAAc,CAACF,OAAO,CAAC,CAAC;AACtD"}
+{"version":3,"file":"parseSharedStrings.js","names":["onOpenTagInSharedString","onCloseTagInSharedString","onTextInSharedString","createInitialStateInSharedString","parseSharedStrings","content","parseXmlStream","createInitialState","createInitialStateInSharedStrings","onOpenTag","onOpenTagInSharedStrings","onCloseTag","onCloseTagInSharedStrings","onText","onTextInSharedStrings","then","state","strings","si","undefined","tagName","attributes","push","string","text"],"sources":["../../source/xlsx/parseSharedStrings.js"],"sourcesContent":["import {\r\n  onOpenTagInSharedString,\r\n  onCloseTagInSharedString,\r\n  onTextInSharedString,\r\n  createInitialStateInSharedString\r\n} from './parseSharedString.js'\r\n\r\n/**\r\n * Parses `sharedStrings.xml` file.\r\n * @param {string} content\r\n * @param {function} parseXmlStream — SAX XML parser.\r\n * @returns {Promise<string[]>}\r\n */\r\nexport default function parseSharedStrings(content, parseXmlStream) {\r\n  return parseXmlStream(content, {\r\n    createInitialState: createInitialStateInSharedStrings,\r\n    onOpenTag: onOpenTagInSharedStrings,\r\n    onCloseTag: onCloseTagInSharedStrings,\r\n    onText: onTextInSharedStrings\r\n  }).then((state) => {\r\n    return state.strings\r\n  })\r\n}\r\n\r\nfunction createInitialStateInSharedStrings() {\r\n  return {\r\n    si: undefined,\r\n    strings: []\r\n  }\r\n}\r\n\r\n// In an XLSX `sharedStrings.xml` file, a <si/> (string item) element can have\r\n// either a single child <t/> element (meaning that \"rich formatting\" is not used)\r\n// or multiple child <r/> elements (meaning that \"rich formatting\" is used).\r\nfunction onOpenTagInSharedStrings(tagName, attributes, state) {\r\n  if (tagName === 'si') {\r\n    state.si = createInitialStateInSharedString()\r\n  } else if (state.si) {\r\n    onOpenTagInSharedString(tagName, attributes, state.si)\r\n  }\r\n}\r\n\r\nfunction onCloseTagInSharedStrings(tagName, state) {\r\n  if (tagName === 'si') {\r\n    state.strings.push(state.si.string)\r\n    state.si = undefined\r\n  } else if (state.si) {\r\n    onCloseTagInSharedString(tagName, state.si)\r\n  }\r\n}\r\n\r\nfunction onTextInSharedStrings(text, state) {\r\n  if (state.si) {\r\n    onTextInSharedString(text, state.si)\r\n  }\r\n}"],"mappings":"AAAA,SACEA,uBAAuB,EACvBC,wBAAwB,EACxBC,oBAAoB,EACpBC,gCAAgC,QAC3B,wBAAwB;;AAE/B;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,kBAAkBA,CAACC,OAAO,EAAEC,cAAc,EAAE;EAClE,OAAOA,cAAc,CAACD,OAAO,EAAE;IAC7BE,kBAAkB,EAAEC,iCAAiC;IACrDC,SAAS,EAAEC,wBAAwB;IACnCC,UAAU,EAAEC,yBAAyB;IACrCC,MAAM,EAAEC;EACV,CAAC,CAAC,CAACC,IAAI,CAAC,UAACC,KAAK,EAAK;IACjB,OAAOA,KAAK,CAACC,OAAO;EACtB,CAAC,CAAC;AACJ;AAEA,SAAST,iCAAiCA,CAAA,EAAG;EAC3C,OAAO;IACLU,EAAE,EAAEC,SAAS;IACbF,OAAO,EAAE;EACX,CAAC;AACH;;AAEA;AACA;AACA;AACA,SAASP,wBAAwBA,CAACU,OAAO,EAAEC,UAAU,EAAEL,KAAK,EAAE;EAC5D,IAAII,OAAO,KAAK,IAAI,EAAE;IACpBJ,KAAK,CAACE,EAAE,GAAGf,gCAAgC,CAAC,CAAC;EAC/C,CAAC,MAAM,IAAIa,KAAK,CAACE,EAAE,EAAE;IACnBlB,uBAAuB,CAACoB,OAAO,EAAEC,UAAU,EAAEL,KAAK,CAACE,EAAE,CAAC;EACxD;AACF;AAEA,SAASN,yBAAyBA,CAACQ,OAAO,EAAEJ,KAAK,EAAE;EACjD,IAAII,OAAO,KAAK,IAAI,EAAE;IACpBJ,KAAK,CAACC,OAAO,CAACK,IAAI,CAACN,KAAK,CAACE,EAAE,CAACK,MAAM,CAAC;IACnCP,KAAK,CAACE,EAAE,GAAGC,SAAS;EACtB,CAAC,MAAM,IAAIH,KAAK,CAACE,EAAE,EAAE;IACnBjB,wBAAwB,CAACmB,OAAO,EAAEJ,KAAK,CAACE,EAAE,CAAC;EAC7C;AACF;AAEA,SAASJ,qBAAqBA,CAACU,IAAI,EAAER,KAAK,EAAE;EAC1C,IAAIA,KAAK,CAACE,EAAE,EAAE;IACZhB,oBAAoB,CAACsB,IAAI,EAAER,KAAK,CAACE,EAAE,CAAC;EACtC;AACF"}

package/modules/xlsx/parseSheet.js

@@ -1,14 +1,96 @@
-import parseCells from './parseCells.js';
-import parseSheetDimensions from './parseSheetDimensions.js';
+function _slicedToArray(arr, i) { return _arrayWithHoles(arr) || _iterableToArrayLimit(arr, i) || _unsupportedIterableToArray(arr, i) || _nonIterableRest(); }
+function _nonIterableRest() { throw new TypeError("Invalid attempt to destructure non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method."); }
+function _unsupportedIterableToArray(o, minLen) { if (!o) return; if (typeof o === "string") return _arrayLikeToArray(o, minLen); var n = Object.prototype.toString.call(o).slice(8, -1); if (n === "Object" && o.constructor) n = o.constructor.name; if (n === "Map" || n === "Set") return Array.from(o); if (n === "Arguments" || /^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n)) return _arrayLikeToArray(o, minLen); }
+function _arrayLikeToArray(arr, len) { if (len == null || len > arr.length) len = arr.length; for (var i = 0, arr2 = new Array(len); i < len; i++) arr2[i] = arr[i]; return arr2; }
+function _iterableToArrayLimit(r, l) { var t = null == r ? null : "undefined" != typeof Symbol && r[Symbol.iterator] || r["@@iterator"]; if (null != t) { var e, n, i, u, a = [], f = !0, o = !1; try { if (i = (t = t.call(r)).next, 0 === l) { if (Object(t) !== t) return; f = !1; } else for (; !(f = (e = i.call(t)).done) && (a.push(e.value), a.length !== l); f = !0); } catch (r) { o = !0, n = r; } finally { try { if (!f && null != t["return"] && (u = t["return"](), Object(u) !== u)) return; } finally { if (o) throw n; } } return a; } }
+function _arrayWithHoles(arr) { if (Array.isArray(arr)) return arr; }
+import parseSheetData, { createInitialStateInSheetData, onOpenTagInSheetData, onCloseTagInSheetData, onTextInSheetData } from './parseSheetData.js';
+import parseCellAddress from './parseCellAddress.js';
 import reconstructSheetDimensionsFromSheetCells from './reconstructSheetDimensionsFromSheetCells.js';
 import convertSheetToData2dArray from './convertCellsToData2dArray.js';
-export default function parseSheet(content, xml, sharedStrings, styles, epoch1904, options) {
-  var sheetDocument = xml.createDocument(content);
-  var cells = parseCells(sheetDocument, sharedStrings, styles, epoch1904, options);
 
-  // `dimensions` defines the spreadsheet area enclosing all non-empty cells.
-  // https://docs.microsoft.com/en-us/dotnet/api/documentformat.openxml.spreadsheet.sheetdimension?view=openxml-2.8.1
-  var dimensions = parseSheetDimensions(sheetDocument) || reconstructSheetDimensionsFromSheetCells(cells);
-  return convertSheetToData2dArray(cells, dimensions);
+/**
+ * Parses a `sheet.xml` file.
+ * @param {string} content
+ * @param {function} parseXmlStream — SAX XML parser.
+ * @param {object} options
+ * @returns {Promise<SheetData>}
+ */
+export default function parseSheet(content, parseXmlStream, _ref) {
+  var sharedStrings = _ref.sharedStrings,
+    styles = _ref.styles,
+    epoch1904 = _ref.epoch1904,
+    options = _ref.options;
+  // When XML parser is finished, it returns a `state`
+  // where it has accumulated the cells it encountered during parsing.
+  // `getSheetData()` function reads the parser `state` and transforms it to `SheetData`.
+  var getSheetData = function getSheetData(state) {
+    var cells = parseSheetData(state.sheetData, sharedStrings, styles, epoch1904, options);
+    var dimensions = state.dimension ? parseSheetDimensionRef(state.dimension) : reconstructSheetDimensionsFromSheetCells(cells);
+    return convertSheetToData2dArray(cells, dimensions);
+  };
+  return parseXmlStream(content, {
+    createInitialState: createInitialStateInSheet,
+    onOpenTag: onOpenTagInSheet,
+    onCloseTag: onCloseTagInSheet,
+    onText: onTextInSheet
+  }).then(function (state) {
+    return getSheetData(state);
+  });
+}
+function createInitialStateInSheet() {
+  return {
+    dimension: undefined,
+    sheetData: undefined
+  };
+}
+function onOpenTagInSheet(tagName, attributes, state) {
+  if (tagName === 'dimension') {
+    state.dimension = attributes.ref;
+  } else if (tagName === 'sheetData') {
+    state.sheetData = createInitialStateInSheetData();
+  } else if (state.sheetData) {
+    onOpenTagInSheetData(tagName, attributes, state.sheetData);
+  }
+}
+function onCloseTagInSheet(tagName, state) {
+  if (state.sheetData) {
+    onCloseTagInSheetData(tagName, state.sheetData);
+  }
+}
+function onTextInSheet(text, state) {
+  if (state.sheetData) {
+    onTextInSheetData(text, state.sheetData);
+  }
+}
+
+/**
+ * Sheet "dimension" defines the spreadsheet area containing all non-empty cells.
+ * Any cells outside the "dimension" are considered empty and should be ignored.
+ * https://docs.microsoft.com/en-us/dotnet/api/documentformat.openxml.spreadsheet.sheetdimension?view=openxml-2.8.1
+ * @param {string} `ref` — The value of `<dimension ref/>` attribute.
+ * @returns {object[]} `undefined` or `[{ row, column }, { row, column }]` — "From row number and column number to row number and column number".
+ */
+function parseSheetDimensionRef(ref) {
+  var dimensions = ref.split(':').map(parseCellAddress).map(function (_ref2) {
+    var _ref3 = _slicedToArray(_ref2, 2),
+      row = _ref3[0],
+      column = _ref3[1];
+    return {
+      row: row,
+      column: column
+    };
+  });
+  // Sometimes there can be just a single cell as a spreadsheet's "dimensions".
+  // For example, the default "dimensions" in Apache POI library is "A1",
+  // meaning that only the first cell in the spreadsheet is used.
+  //
+  // A quote from Apache POI library:
+  // "Single cell ranges are formatted like single cell references (e.g. 'A1' instead of 'A1:A1')."
+  //
+  if (dimensions.length === 1) {
+    dimensions = [dimensions[0], dimensions[0]];
+  }
+  return dimensions;
 }
 //# sourceMappingURL=parseSheet.js.map

package/modules/xlsx/parseSheet.js.map

@@ -1 +1 @@
-{"version":3,"file":"parseSheet.js","names":["parseCells","parseSheetDimensions","reconstructSheetDimensionsFromSheetCells","convertSheetToData2dArray","parseSheet","content","xml","sharedStrings","styles","epoch1904","options","sheetDocument","createDocument","cells","dimensions"],"sources":["../../source/xlsx/parseSheet.js"],"sourcesContent":["import parseCells from './parseCells.js'\r\nimport parseSheetDimensions from './parseSheetDimensions.js'\r\nimport reconstructSheetDimensionsFromSheetCells from './reconstructSheetDimensionsFromSheetCells.js'\r\nimport convertSheetToData2dArray from './convertCellsToData2dArray.js'\r\n\r\nexport default function parseSheet(content, xml, sharedStrings, styles, epoch1904, options) {\r\n  const sheetDocument = xml.createDocument(content)\r\n\r\n  const cells = parseCells(sheetDocument, sharedStrings, styles, epoch1904, options)\r\n\r\n  // `dimensions` defines the spreadsheet area enclosing all non-empty cells.\r\n  // https://docs.microsoft.com/en-us/dotnet/api/documentformat.openxml.spreadsheet.sheetdimension?view=openxml-2.8.1\r\n  const dimensions = parseSheetDimensions(sheetDocument) || reconstructSheetDimensionsFromSheetCells(cells)\r\n\r\n  return convertSheetToData2dArray(cells, dimensions)\r\n}"],"mappings":"AAAA,OAAOA,UAAU,MAAM,iBAAiB;AACxC,OAAOC,oBAAoB,MAAM,2BAA2B;AAC5D,OAAOC,wCAAwC,MAAM,+CAA+C;AACpG,OAAOC,yBAAyB,MAAM,gCAAgC;AAEtE,eAAe,SAASC,UAAUA,CAACC,OAAO,EAAEC,GAAG,EAAEC,aAAa,EAAEC,MAAM,EAAEC,SAAS,EAAEC,OAAO,EAAE;EAC1F,IAAMC,aAAa,GAAGL,GAAG,CAACM,cAAc,CAACP,OAAO,CAAC;EAEjD,IAAMQ,KAAK,GAAGb,UAAU,CAACW,aAAa,EAAEJ,aAAa,EAAEC,MAAM,EAAEC,SAAS,EAAEC,OAAO,CAAC;;EAElF;EACA;EACA,IAAMI,UAAU,GAAGb,oBAAoB,CAACU,aAAa,CAAC,IAAIT,wCAAwC,CAACW,KAAK,CAAC;EAEzG,OAAOV,yBAAyB,CAACU,KAAK,EAAEC,UAAU,CAAC;AACrD"}
+{"version":3,"file":"parseSheet.js","names":["parseSheetData","createInitialStateInSheetData","onOpenTagInSheetData","onCloseTagInSheetData","onTextInSheetData","parseCellAddress","reconstructSheetDimensionsFromSheetCells","convertSheetToData2dArray","parseSheet","content","parseXmlStream","_ref","sharedStrings","styles","epoch1904","options","getSheetData","state","cells","sheetData","dimensions","dimension","parseSheetDimensionRef","createInitialState","createInitialStateInSheet","onOpenTag","onOpenTagInSheet","onCloseTag","onCloseTagInSheet","onText","onTextInSheet","then","undefined","tagName","attributes","ref","text","split","map","_ref2","_ref3","_slicedToArray","row","column","length"],"sources":["../../source/xlsx/parseSheet.js"],"sourcesContent":["import parseSheetData, {\r\n  createInitialStateInSheetData,\r\n  onOpenTagInSheetData,\r\n  onCloseTagInSheetData,\r\n  onTextInSheetData\r\n} from './parseSheetData.js'\r\n\r\nimport parseCellAddress from './parseCellAddress.js'\r\n\r\nimport reconstructSheetDimensionsFromSheetCells from './reconstructSheetDimensionsFromSheetCells.js'\r\nimport convertSheetToData2dArray from './convertCellsToData2dArray.js'\r\n\r\n/**\r\n * Parses a `sheet.xml` file.\r\n * @param {string} content\r\n * @param {function} parseXmlStream — SAX XML parser.\r\n * @param {object} options\r\n * @returns {Promise<SheetData>}\r\n */\r\nexport default function parseSheet(content, parseXmlStream, { sharedStrings, styles, epoch1904, options }) {\r\n  // When XML parser is finished, it returns a `state`\r\n  // where it has accumulated the cells it encountered during parsing.\r\n  // `getSheetData()` function reads the parser `state` and transforms it to `SheetData`.\r\n  const getSheetData = (state) => {\r\n    const cells = parseSheetData(state.sheetData, sharedStrings, styles, epoch1904, options)\r\n    const dimensions = state.dimension\r\n      ? parseSheetDimensionRef(state.dimension)\r\n      : reconstructSheetDimensionsFromSheetCells(cells)\r\n    return convertSheetToData2dArray(cells, dimensions)\r\n  }\r\n\r\n  return parseXmlStream(content, {\r\n    createInitialState: createInitialStateInSheet,\r\n    onOpenTag: onOpenTagInSheet,\r\n    onCloseTag: onCloseTagInSheet,\r\n    onText: onTextInSheet\r\n  }).then((state) => {\r\n    return getSheetData(state)\r\n  })\r\n}\r\n\r\nfunction createInitialStateInSheet() {\r\n  return {\r\n    dimension: undefined,\r\n    sheetData: undefined\r\n  }\r\n}\r\n\r\nfunction onOpenTagInSheet(tagName, attributes, state) {\r\n  if (tagName === 'dimension') {\r\n    state.dimension = attributes.ref\r\n  } else if (tagName === 'sheetData') {\r\n    state.sheetData = createInitialStateInSheetData()\r\n  } else if (state.sheetData) {\r\n    onOpenTagInSheetData(tagName, attributes, state.sheetData)\r\n  }\r\n}\r\n\r\nfunction onCloseTagInSheet(tagName, state) {\r\n  if (state.sheetData) {\r\n    onCloseTagInSheetData(tagName, state.sheetData)\r\n  }\r\n}\r\n\r\nfunction onTextInSheet(text, state) {\r\n  if (state.sheetData) {\r\n    onTextInSheetData(text, state.sheetData)\r\n  }\r\n}\r\n\r\n/**\r\n * Sheet \"dimension\" defines the spreadsheet area containing all non-empty cells.\r\n * Any cells outside the \"dimension\" are considered empty and should be ignored.\r\n * https://docs.microsoft.com/en-us/dotnet/api/documentformat.openxml.spreadsheet.sheetdimension?view=openxml-2.8.1\r\n * @param {string} `ref` — The value of `<dimension ref/>` attribute.\r\n * @returns {object[]} `undefined` or `[{ row, column }, { row, column }]` — \"From row number and column number to row number and column number\".\r\n */\r\nfunction parseSheetDimensionRef(ref) {\r\n  let dimensions = ref.split(':').map(parseCellAddress).map(\r\n    ([row, column]) => ({ row, column })\r\n  )\r\n  // Sometimes there can be just a single cell as a spreadsheet's \"dimensions\".\r\n  // For example, the default \"dimensions\" in Apache POI library is \"A1\",\r\n  // meaning that only the first cell in the spreadsheet is used.\r\n  //\r\n  // A quote from Apache POI library:\r\n  // \"Single cell ranges are formatted like single cell references (e.g. 'A1' instead of 'A1:A1').\"\r\n  //\r\n  if (dimensions.length === 1) {\r\n    dimensions = [dimensions[0], dimensions[0]]\r\n  }\r\n  return dimensions\r\n}"],"mappings":";;;;;;AAAA,OAAOA,cAAc,IACnBC,6BAA6B,EAC7BC,oBAAoB,EACpBC,qBAAqB,EACrBC,iBAAiB,QACZ,qBAAqB;AAE5B,OAAOC,gBAAgB,MAAM,uBAAuB;AAEpD,OAAOC,wCAAwC,MAAM,+CAA+C;AACpG,OAAOC,yBAAyB,MAAM,gCAAgC;;AAEtE;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,UAAUA,CAACC,OAAO,EAAEC,cAAc,EAAAC,IAAA,EAAiD;EAAA,IAA7CC,aAAa,GAAAD,IAAA,CAAbC,aAAa;IAAEC,MAAM,GAAAF,IAAA,CAANE,MAAM;IAAEC,SAAS,GAAAH,IAAA,CAATG,SAAS;IAAEC,OAAO,GAAAJ,IAAA,CAAPI,OAAO;EACrG;EACA;EACA;EACA,IAAMC,YAAY,GAAG,SAAfA,YAAYA,CAAIC,KAAK,EAAK;IAC9B,IAAMC,KAAK,GAAGlB,cAAc,CAACiB,KAAK,CAACE,SAAS,EAAEP,aAAa,EAAEC,MAAM,EAAEC,SAAS,EAAEC,OAAO,CAAC;IACxF,IAAMK,UAAU,GAAGH,KAAK,CAACI,SAAS,GAC9BC,sBAAsB,CAACL,KAAK,CAACI,SAAS,CAAC,GACvCf,wCAAwC,CAACY,KAAK,CAAC;IACnD,OAAOX,yBAAyB,CAACW,KAAK,EAAEE,UAAU,CAAC;EACrD,CAAC;EAED,OAAOV,cAAc,CAACD,OAAO,EAAE;IAC7Bc,kBAAkB,EAAEC,yBAAyB;IAC7CC,SAAS,EAAEC,gBAAgB;IAC3BC,UAAU,EAAEC,iBAAiB;IAC7BC,MAAM,EAAEC;EACV,CAAC,CAAC,CAACC,IAAI,CAAC,UAACd,KAAK,EAAK;IACjB,OAAOD,YAAY,CAACC,KAAK,CAAC;EAC5B,CAAC,CAAC;AACJ;AAEA,SAASO,yBAAyBA,CAAA,EAAG;EACnC,OAAO;IACLH,SAAS,EAAEW,SAAS;IACpBb,SAAS,EAAEa;EACb,CAAC;AACH;AAEA,SAASN,gBAAgBA,CAACO,OAAO,EAAEC,UAAU,EAAEjB,KAAK,EAAE;EACpD,IAAIgB,OAAO,KAAK,WAAW,EAAE;IAC3BhB,KAAK,CAACI,SAAS,GAAGa,UAAU,CAACC,GAAG;EAClC,CAAC,MAAM,IAAIF,OAAO,KAAK,WAAW,EAAE;IAClChB,KAAK,CAACE,SAAS,GAAGlB,6BAA6B,CAAC,CAAC;EACnD,CAAC,MAAM,IAAIgB,KAAK,CAACE,SAAS,EAAE;IAC1BjB,oBAAoB,CAAC+B,OAAO,EAAEC,UAAU,EAAEjB,KAAK,CAACE,SAAS,CAAC;EAC5D;AACF;AAEA,SAASS,iBAAiBA,CAACK,OAAO,EAAEhB,KAAK,EAAE;EACzC,IAAIA,KAAK,CAACE,SAAS,EAAE;IACnBhB,qBAAqB,CAAC8B,OAAO,EAAEhB,KAAK,CAACE,SAAS,CAAC;EACjD;AACF;AAEA,SAASW,aAAaA,CAACM,IAAI,EAAEnB,KAAK,EAAE;EAClC,IAAIA,KAAK,CAACE,SAAS,EAAE;IACnBf,iBAAiB,CAACgC,IAAI,EAAEnB,KAAK,CAACE,SAAS,CAAC;EAC1C;AACF;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,sBAAsBA,CAACa,GAAG,EAAE;EACnC,IAAIf,UAAU,GAAGe,GAAG,CAACE,KAAK,CAAC,GAAG,CAAC,CAACC,GAAG,CAACjC,gBAAgB,CAAC,CAACiC,GAAG,CACvD,UAAAC,KAAA;IAAA,IAAAC,KAAA,GAAAC,cAAA,CAAAF,KAAA;MAAEG,GAAG,GAAAF,KAAA;MAAEG,MAAM,GAAAH,KAAA;IAAA,OAAO;MAAEE,GAAG,EAAHA,GAAG;MAAEC,MAAM,EAANA;IAAO,CAAC;EAAA,CACrC,CAAC;EACD;EACA;EACA;EACA;EACA;EACA;EACA;EACA,IAAIvB,UAAU,CAACwB,MAAM,KAAK,CAAC,EAAE;IAC3BxB,UAAU,GAAG,CAACA,UAAU,CAAC,CAAC,CAAC,EAAEA,UAAU,CAAC,CAAC,CAAC,CAAC;EAC7C;EACA,OAAOA,UAAU;AACnB"}