any-extractor 1.0.0

package/dist/index.d.mts

@@ -0,0 +1,25 @@
+type InputType = 'buffer' | 'file' | 'fileurl';
+type ExtractionPayload = {
+    type: InputType;
+    input: string | Buffer;
+};
+type AnyParserMethod = {
+    mimes: string[];
+    apply: (_: Buffer) => Promise<string>;
+};
+type ExtractedFile = {
+    path: string;
+    content: string;
+};
+
+declare class AnyExtractor {
+    private parserMap;
+    private parsers;
+    addParser: (method: AnyParserMethod) => this;
+    getRegisteredParsers: () => string[];
+    extractText: ({ input, type }: ExtractionPayload) => Promise<string>;
+}
+
+declare const getAnyExtractor: () => AnyExtractor;
+
+export { type AnyParserMethod, type ExtractedFile, type ExtractionPayload, type InputType, getAnyExtractor };

package/dist/index.d.ts

@@ -0,0 +1,25 @@
+type InputType = 'buffer' | 'file' | 'fileurl';
+type ExtractionPayload = {
+    type: InputType;
+    input: string | Buffer;
+};
+type AnyParserMethod = {
+    mimes: string[];
+    apply: (_: Buffer) => Promise<string>;
+};
+type ExtractedFile = {
+    path: string;
+    content: string;
+};
+
+declare class AnyExtractor {
+    private parserMap;
+    private parsers;
+    addParser: (method: AnyParserMethod) => this;
+    getRegisteredParsers: () => string[];
+    extractText: ({ input, type }: ExtractionPayload) => Promise<string>;
+}
+
+declare const getAnyExtractor: () => AnyExtractor;
+
+export { type AnyParserMethod, type ExtractedFile, type ExtractionPayload, type InputType, getAnyExtractor };

package/dist/index.js

@@ -0,0 +1,428 @@
+"use strict";
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
+  // If the importer is in node compatibility mode or this is not an ESM
+  // file that has been converted to a CommonJS file using a Babel-
+  // compatible transform (i.e. "__esModule" has not been set), then set
+  // "default" to the CommonJS "module.exports" for node compatibility.
+  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
+  mod
+));
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+
+// src/index.ts
+var index_exports = {};
+__export(index_exports, {
+  getAnyExtractor: () => getAnyExtractor
+});
+module.exports = __toCommonJS(index_exports);
+
+// src/util.ts
+var import_promises = require("fs/promises");
+var import_undici = require("undici");
+var import_yauzl = __toESM(require("yauzl"));
+
+// src/constant.ts
+var ERRORMSG = {
+  extensionUnsupported: (ext) => `Sorry, AnyExtractor currently support docx, pptx, xlsx, odt, odp, ods, pdf files only. Create a ticket in Issues on github to add support for ${ext} files. Stay tuned for further updates.`,
+  fileCorrupted: (filepath) => `Your file ${filepath} seems to be corrupted. If you are sure it is fine, please create a ticket in Issues on github with the file to reproduce error.`,
+  fileDoesNotExist: (filepath) => `File ${filepath} could not be found! Check if the file exists or verify if the relative path to the file is correct from your terminal's location.`,
+  locationNotFound: (location) => `Entered location ${location} is not reachable! Please make sure that the entered directory location exists. Check relative paths and reenter.`,
+  improperArguments: `Improper arguments`,
+  improperBuffers: `Error occured while reading the file buffers`,
+  invalidInput: `Invalid input type: Expected a Buffer or a valid file path`
+};
+
+// src/util.ts
+var import_concat_stream = __toESM(require("concat-stream"));
+var import_xmldom = require("@xmldom/xmldom");
+var readFile = async (filePath) => await (0, import_promises.readFile)(filePath);
+var readFileUrl = async (url) => {
+  const res = await (0, import_undici.fetch)(url);
+  if (!res.ok) throw new Error(`Failed to fetch: ${res.statusText}`);
+  return Buffer.from(await res.arrayBuffer());
+};
+var extractFiles = (zipInput, filterFn) => {
+  return new Promise((res, rej) => {
+    const processZipfile = (zipfile) => {
+      const extractedFiles = [];
+      zipfile.readEntry();
+      function processEntry(entry) {
+        if (filterFn(entry.fileName)) {
+          zipfile.openReadStream(entry, (err, readStream) => {
+            if (err)
+              return rej(err);
+            readStream.pipe((0, import_concat_stream.default)((data) => {
+              extractedFiles.push({
+                path: entry.fileName,
+                content: data.toString()
+              });
+              zipfile.readEntry();
+            }));
+          });
+        } else
+          zipfile.readEntry();
+      }
+      zipfile.on("entry", processEntry);
+      zipfile.on("end", () => res(extractedFiles));
+      zipfile.on("error", rej);
+    };
+    if (Buffer.isBuffer(zipInput)) {
+      import_yauzl.default.fromBuffer(zipInput, { lazyEntries: true }, (err, zipfile) => {
+        if (err) return rej(err);
+        processZipfile(zipfile);
+      });
+    } else if (typeof zipInput === "string") {
+      import_yauzl.default.open(zipInput, { lazyEntries: true }, (err, zipfile) => {
+        if (err) return rej(err);
+        processZipfile(zipfile);
+      });
+    } else
+      rej(ERRORMSG.invalidInput);
+  });
+};
+var parseString = (xml) => {
+  let parser = new import_xmldom.DOMParser();
+  return parser.parseFromString(xml, "text/xml");
+};
+
+// src/extractors/any-extractor.ts
+var import_file_type = require("file-type");
+var AnyExtractor = class {
+  constructor() {
+    this.parserMap = /* @__PURE__ */ new Map();
+    this.parsers = [];
+    this.addParser = (method) => {
+      this.parsers.push(method);
+      method.mimes.forEach((mime) => {
+        this.parserMap.set(mime, method);
+      });
+      return this;
+    };
+    this.getRegisteredParsers = () => {
+      return Array.from(this.parserMap.keys());
+    };
+    this.extractText = async ({ input, type }) => {
+      let preparedInput;
+      if (typeof input === "string") {
+        switch (type) {
+          case "file":
+            preparedInput = await readFile(input);
+            break;
+          case "fileurl":
+            preparedInput = await readFileUrl(input);
+            break;
+          default:
+            preparedInput = Buffer.from(input);
+        }
+      } else {
+        preparedInput = input;
+      }
+      const mimeDetails = await (0, import_file_type.fileTypeFromBuffer)(preparedInput);
+      if (!mimeDetails) return preparedInput.toString("utf-8");
+      const extractor = this.parserMap.get(mimeDetails.mime);
+      if (!extractor?.apply) {
+        const message = `AnyExtractor: No extraction method registered for MIME type '${mimeDetails.mime}'`;
+        throw new Error(message);
+      }
+      return extractor.apply(preparedInput);
+    };
+  }
+};
+
+// src/parser/excel-parser.ts
+var ExcelParser = class {
+  constructor() {
+    this.mimes = ["application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"];
+  }
+  async apply(file) {
+    const sheetsRegex = /xl\/worksheets\/sheet\d+.xml/g;
+    const drawingsRegex = /xl\/drawings\/drawing\d+.xml/g;
+    const chartsRegex = /xl\/charts\/chart\d+.xml/g;
+    const stringsFilePath = "xl/sharedStrings.xml";
+    try {
+      let isValidInlineStringCNode2 = function(cNode) {
+        if (cNode.tagName.toLowerCase() != "c") return false;
+        if (cNode.getAttribute("t") != "inlineStr") return false;
+        const childNodesNamedIs = cNode.getElementsByTagName("is");
+        if (childNodesNamedIs.length != 1) return false;
+        const childNodesNamedT = childNodesNamedIs[0].getElementsByTagName("t");
+        if (childNodesNamedT.length != 1) return false;
+        return childNodesNamedT[0].childNodes[0] && childNodesNamedT[0].childNodes[0].nodeValue != "";
+      }, hasValidVNodeInCNode2 = function(cNode) {
+        const vNodes = cNode.getElementsByTagName("v");
+        return vNodes[0] && vNodes[0].childNodes[0] && vNodes[0].childNodes[0].nodeValue != "";
+      };
+      var isValidInlineStringCNode = isValidInlineStringCNode2, hasValidVNodeInCNode = hasValidVNodeInCNode2;
+      const files = await extractFiles(
+        file,
+        (x) => [sheetsRegex, drawingsRegex, chartsRegex].some((fileRegex) => x.match(fileRegex)) || x == stringsFilePath
+      );
+      if (files.length == 0 || !files.map((file2) => file2.path).some((filename) => filename.match(sheetsRegex))) {
+        throw ERRORMSG.fileCorrupted("TODO: figure this out");
+      }
+      const xmlContentFilesObject = {
+        sheetFiles: files.filter((file2) => file2.path.match(sheetsRegex)).map((file2) => file2.content),
+        drawingFiles: files.filter((file2) => file2.path.match(drawingsRegex)).map((file2) => file2.content),
+        chartFiles: files.filter((file2) => file2.path.match(chartsRegex)).map((file2) => file2.content),
+        sharedStringsFile: files.filter((file2) => file2.path == stringsFilePath).map((file2) => file2.content)[0]
+      };
+      let responseText = [];
+      const sharedStringsXmlTNodesList = xmlContentFilesObject.sharedStringsFile != void 0 ? parseString(xmlContentFilesObject.sharedStringsFile).getElementsByTagName("t") : [];
+      const sharedStrings = Array.from(sharedStringsXmlTNodesList).map((tNode) => tNode.childNodes[0]?.nodeValue ?? "");
+      for (const sheetXmlContent of xmlContentFilesObject.sheetFiles) {
+        const sheetsXmlCNodesList = parseString(sheetXmlContent).getElementsByTagName("c");
+        responseText.push(
+          Array.from(sheetsXmlCNodesList).filter((cNode) => isValidInlineStringCNode2(cNode) || hasValidVNodeInCNode2(cNode)).map((cNode) => {
+            if (isValidInlineStringCNode2(cNode))
+              return cNode.getElementsByTagName("is")[0].getElementsByTagName("t")[0].childNodes[0].nodeValue;
+            if (hasValidVNodeInCNode2(cNode)) {
+              const isIndexInSharedStrings = cNode.getAttribute("t") == "s";
+              const value = parseInt(cNode.getElementsByTagName("v")[0].childNodes[0].nodeValue ?? "", 10);
+              if (isIndexInSharedStrings && value >= sharedStrings.length)
+                throw ERRORMSG.fileCorrupted("TODO: figure this out");
+              return isIndexInSharedStrings ? sharedStrings[value] : value;
+            }
+            return "";
+          }).join("\n")
+        );
+      }
+      for (const drawingXmlContent of xmlContentFilesObject.drawingFiles) {
+        const drawingsXmlParagraphNodesList = parseString(drawingXmlContent).getElementsByTagName("a:p");
+        responseText.push(
+          Array.from(drawingsXmlParagraphNodesList).filter((paragraphNode) => paragraphNode.getElementsByTagName("a:t").length != 0).map((paragraphNode) => {
+            const xmlTextNodeList = paragraphNode.getElementsByTagName("a:t");
+            return Array.from(xmlTextNodeList).filter((textNode) => textNode.childNodes[0] && textNode.childNodes[0].nodeValue).map((textNode) => textNode.childNodes[0].nodeValue).join("");
+          }).join("\n")
+        );
+      }
+      for (const chartXmlContent of xmlContentFilesObject.chartFiles) {
+        const chartsXmlCVNodesList = parseString(chartXmlContent).getElementsByTagName("c:v");
+        responseText.push(
+          Array.from(chartsXmlCVNodesList).filter((cVNode) => cVNode.childNodes[0] && cVNode.childNodes[0].nodeValue).map((cVNode) => cVNode.childNodes[0].nodeValue).join("\n")
+        );
+      }
+      return responseText.join("\n");
+    } catch (error) {
+      console.error("Error parsing Excel file:", error);
+      throw error;
+    }
+  }
+};
+
+// src/parser/openoffice-paser.ts
+var OpenOfficeParser = class {
+  constructor() {
+    this.mimes = [
+      "application/vnd.oasis.opendocument.text",
+      "application/vnd.oasis.opendocument.spreadsheet",
+      "application/vnd.oasis.opendocument.presentation",
+      "application/vnd.oasis.opendocument.graphics",
+      "application/vnd.oasis.opendocument.formula"
+    ];
+    this.apply = async (file) => {
+      const mainContentFilePath = "content.xml";
+      const objectContentFilesRegex = /Object \d+\/content.xml/g;
+      try {
+        let extractAllTextsFromNode2 = function(root) {
+          let xmlTextArray = [];
+          for (let i = 0; i < root.childNodes.length; i++) {
+            traversal2(root.childNodes[i], xmlTextArray, true);
+          }
+          return xmlTextArray.join("");
+        }, traversal2 = function(node, xmlTextArray, isFirstRecursion) {
+          if (!node.childNodes || node.childNodes.length == 0) {
+            if (node.parentNode && node.parentNode.tagName.indexOf("text") == 0 && node.nodeValue) {
+              if (isNotesNode2(node.parentNode)) {
+                notesText.push(node.nodeValue);
+                if (allowedTextTags.includes(node.parentNode.tagName) && !isFirstRecursion) {
+                  notesText.push("\n");
+                }
+              } else {
+                xmlTextArray.push(node.nodeValue);
+                if (allowedTextTags.includes(node.parentNode.tagName) && !isFirstRecursion) {
+                  xmlTextArray.push("\n");
+                }
+              }
+            }
+            return;
+          }
+          for (let i = 0; i < node.childNodes.length; i++) {
+            traversal2(node.childNodes[i], xmlTextArray, false);
+          }
+        }, isNotesNode2 = function(node) {
+          if (node.tagName == notesTag) {
+            return true;
+          }
+          if (node.parentNode) {
+            return isNotesNode2(node.parentNode);
+          }
+          return false;
+        }, isInvalidTextNode2 = function(node) {
+          if (allowedTextTags.includes(node.tagName)) {
+            return true;
+          }
+          if (node.parentNode) {
+            return isInvalidTextNode2(node.parentNode);
+          }
+          return false;
+        };
+        var extractAllTextsFromNode = extractAllTextsFromNode2, traversal = traversal2, isNotesNode = isNotesNode2, isInvalidTextNode = isInvalidTextNode2;
+        const files = await extractFiles(file, (x) => x == mainContentFilePath || !!x.match(objectContentFilesRegex));
+        if (!files.map((file2) => file2.path).includes(mainContentFilePath)) {
+          throw ERRORMSG.fileCorrupted("TODO: figure this out");
+        }
+        const xmlContentFilesObject = {
+          mainContentFile: files.filter((file2) => file2.path == mainContentFilePath).map((file2) => file2.content)[0],
+          objectContentFiles: files.filter((file2) => file2.path.match(objectContentFilesRegex)).map((file2) => file2.content)
+        };
+        let notesText = [];
+        let responseText = [];
+        const allowedTextTags = ["text:p", "text:h"];
+        const notesTag = "presentation:notes";
+        const xmlContentArray = [xmlContentFilesObject.mainContentFile, ...xmlContentFilesObject.objectContentFiles].map((xmlContent) => parseString(xmlContent));
+        xmlContentArray.forEach((xmlContent) => {
+          const xmlTextNodesList = [...Array.from(xmlContent.getElementsByTagName("*")).filter((node) => allowedTextTags.includes(node.tagName) && !isInvalidTextNode2(node.parentNode))];
+          responseText.push(
+            xmlTextNodesList.map((textNode) => extractAllTextsFromNode2(textNode)).filter((text) => text != "").join("\n")
+          );
+        });
+        responseText = [...responseText, ...notesText];
+        return responseText.join("\n");
+      } catch (error) {
+        console.error("Error parsing OpenOffice file:", error);
+        throw error;
+      }
+    };
+  }
+};
+
+// src/parser/pdf-parser.ts
+var import_pdf_parse = __toESM(require("pdf-parse"));
+var PDFParser = class {
+  constructor() {
+    this.mimes = ["application/pdf"];
+    this.apply = async (file) => {
+      try {
+        const data = await (0, import_pdf_parse.default)(file);
+        const textContent = data.text;
+        return textContent;
+      } catch (error) {
+        console.error("Error parsing PDF file:", error);
+        throw error;
+      }
+    };
+  }
+};
+
+// src/parser/powerpoint-parser.ts
+var PowerPointParser = class {
+  constructor() {
+    this.mimes = ["application/vnd.openxmlformats-officedocument.presentationml.presentation"];
+  }
+  async apply(file) {
+    const allFilesRegex = /ppt\/(notesSlides|slides)\/(notesSlide|slide)\d+.xml/g;
+    const slidesRegex = /ppt\/slides\/slide\d+.xml/g;
+    const slideNumberRegex = /lide(\d+)\.xml/;
+    try {
+      const files = await extractFiles(file, (x) => !!x.match(allFilesRegex));
+      files.sort((a, b) => {
+        const matchedANumber = parseInt(a.path.match(slideNumberRegex)?.at(1) ?? "", 10);
+        const matchedBNumber = parseInt(b.path.match(slideNumberRegex)?.at(1) ?? "", 10);
+        const aNumber = isNaN(matchedANumber) ? Infinity : matchedANumber;
+        const bNumber = isNaN(matchedBNumber) ? Infinity : matchedBNumber;
+        return aNumber - bNumber || Number(a.path.includes("notes")) - Number(b.path.includes("notes"));
+      });
+      if (files.length == 0 || !files.map((file2) => file2.path).some((filename) => filename.match(slidesRegex))) {
+        throw ERRORMSG.fileCorrupted("TODO: figure this out");
+      }
+      files.sort((a, b) => a.path.indexOf("notes") - b.path.indexOf("notes"));
+      const xmlContentArray = files.map((file2) => file2.content);
+      let responseText = [];
+      for (const xmlContent of xmlContentArray) {
+        const xmlParagraphNodesList = parseString(xmlContent).getElementsByTagName("a:p");
+        responseText.push(
+          Array.from(xmlParagraphNodesList).filter((paragraphNode) => paragraphNode.getElementsByTagName("a:t").length != 0).map((paragraphNode) => {
+            const xmlTextNodeList = paragraphNode.getElementsByTagName("a:t");
+            return Array.from(xmlTextNodeList).filter((textNode) => textNode.childNodes[0] && textNode.childNodes[0].nodeValue).map((textNode) => textNode.childNodes[0].nodeValue).join("");
+          }).join("\n")
+        );
+      }
+      const responseTextString = responseText.join("\n");
+      return responseTextString;
+    } catch (error) {
+      console.error("Error parsing PowerPoint file:", error);
+      throw error;
+    }
+  }
+};
+
+// src/parser/word-parser.ts
+var WordParser = class {
+  constructor() {
+    this.mimes = ["application/vnd.openxmlformats-officedocument.wordprocessingml.document"];
+  }
+  async apply(file) {
+    const mainContentFileRegex = /word\/document[\d+]?.xml/g;
+    const footnotesFileRegex = /word\/footnotes[\d+]?.xml/g;
+    const endnotesFileRegex = /word\/endnotes[\d+]?.xml/g;
+    try {
+      const files = await extractFiles(
+        file,
+        (x) => [mainContentFileRegex, footnotesFileRegex, endnotesFileRegex].some((fileRegex) => x.match(fileRegex))
+      );
+      if (!files.some((file2) => file2.path.match(mainContentFileRegex))) {
+        throw ERRORMSG.fileCorrupted("TODO: figure this out");
+      }
+      const xmlContentArray = files.filter((file2) => file2.path.match(mainContentFileRegex) || file2.path.match(footnotesFileRegex) || file2.path.match(endnotesFileRegex)).map((file2) => file2.content);
+      let responseText = [];
+      xmlContentArray.forEach((xmlContent) => {
+        const xmlParagraphNodesList = parseString(xmlContent).getElementsByTagName("w:p");
+        responseText.push(
+          Array.from(xmlParagraphNodesList).filter((paragraphNode) => paragraphNode.getElementsByTagName("w:t").length != 0).map((paragraphNode) => {
+            const xmlTextNodeList = paragraphNode.getElementsByTagName("w:t");
+            return Array.from(xmlTextNodeList).filter((textNode) => textNode.childNodes[0] && textNode.childNodes[0].nodeValue).map((textNode) => textNode.childNodes[0].nodeValue).join("");
+          }).join("\n")
+        );
+      });
+      const responseTextString = responseText.join("\n");
+      return responseTextString;
+    } catch (error) {
+      console.error("Error parsing Word file:", error);
+      throw error;
+    }
+  }
+};
+
+// src/index.ts
+var getAnyExtractor = () => {
+  const anyExtractor = new AnyExtractor();
+  anyExtractor.addParser(new ExcelParser());
+  anyExtractor.addParser(new OpenOfficeParser());
+  anyExtractor.addParser(new PDFParser());
+  anyExtractor.addParser(new PowerPointParser());
+  anyExtractor.addParser(new WordParser());
+  return anyExtractor;
+};
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  getAnyExtractor
+});
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/index.ts","../src/util.ts","../src/constant.ts","../src/extractors/any-extractor.ts","../src/parser/excel-parser.ts","../src/parser/openoffice-paser.ts","../src/parser/pdf-parser.ts","../src/parser/powerpoint-parser.ts","../src/parser/word-parser.ts"],"sourcesContent":["import { AnyExtractor } from \"./extractors/any-extractor\";\nimport { ExcelParser } from \"./parser/excel-parser\";\nimport { OpenOfficeParser } from \"./parser/openoffice-paser\";\nimport { PDFParser } from \"./parser/pdf-parser\";\nimport { PowerPointParser } from \"./parser/powerpoint-parser\";\nimport { WordParser } from \"./parser/word-parser\";\n\nexport const getAnyExtractor = (): AnyExtractor => {\n  const anyExtractor = new AnyExtractor();\n  \n  anyExtractor.addParser(new ExcelParser());\n  anyExtractor.addParser(new OpenOfficeParser());\n  anyExtractor.addParser(new PDFParser());\n  anyExtractor.addParser(new PowerPointParser());\n  anyExtractor.addParser(new WordParser());\n\n  return anyExtractor;\n}\n\nexport * from \"./types\";","import { readFile as read } from 'node:fs/promises';\nimport { fetch } from 'undici';\nimport yauzl from 'yauzl';\nimport { ERRORMSG } from './constant';\nimport { ExtractedFile } from './types';\nimport concat from 'concat-stream';\nimport { DOMParser } from '@xmldom/xmldom';\n\nexport const readFile = async (filePath: string): Promise<Buffer> =>\n  (await read(filePath)) as unknown as Buffer;\n\nexport const readFileUrl = async (url: string): Promise<Buffer> => {\n  const res = await fetch(url);\n  if (!res.ok) throw new Error(`Failed to fetch: ${res.statusText}`);\n  return Buffer.from(await res.arrayBuffer());\n}\n\nexport const extractFiles = (zipInput: Buffer | string, filterFn: (x: string) => boolean): Promise<ExtractedFile[]> => {\n  return new Promise((res, rej) => {\n    const processZipfile = (zipfile: yauzl.ZipFile) => {\n      const extractedFiles: ExtractedFile[] = [];\n      zipfile.readEntry();\n\n      function processEntry(entry: yauzl.Entry) {\n        if (filterFn(entry.fileName)) {\n          zipfile.openReadStream(entry, (err, readStream) => {\n            if (err)\n              return rej(err);\n\n            readStream.pipe(concat((data: Buffer) => {\n              extractedFiles.push({\n              path: entry.fileName,\n              content: data.toString()\n              });\n              zipfile.readEntry();\n            }));\n          });\n        }\n        else\n          zipfile.readEntry();\n      }\n\n      zipfile.on('entry', processEntry);\n      zipfile.on('end', () => res(extractedFiles));\n      zipfile.on('error', rej);\n    };\n\n    if (Buffer.isBuffer(zipInput)) {\n      yauzl.fromBuffer(zipInput, { lazyEntries: true }, (err, zipfile) => {\n        if (err) return rej(err);\n        processZipfile(zipfile);\n      });\n    }\n    else if (typeof zipInput === 'string') {\n      yauzl.open(zipInput, { lazyEntries: true }, (err, zipfile) => {\n        if (err) return rej(err);\n        processZipfile(zipfile);\n      });\n    }\n    else\n      rej(ERRORMSG.invalidInput);\n  });\n}\n\nexport const parseString = (xml: string) => {\n  let parser = new DOMParser();\n  return parser.parseFromString(xml, \"text/xml\");\n};","/** Header for error messages */\nexport const ERRORHEADER = \"[AnyExtractor]: \";\n\n/** Error messages */\nexport const ERRORMSG = {\n  extensionUnsupported: (ext: string) => `Sorry, AnyExtractor currently support docx, pptx, xlsx, odt, odp, ods, pdf files only. Create a ticket in Issues on github to add support for ${ext} files. Stay tuned for further updates.`,\n  fileCorrupted: (filepath: string) => `Your file ${filepath} seems to be corrupted. If you are sure it is fine, please create a ticket in Issues on github with the file to reproduce error.`,\n  fileDoesNotExist: (filepath: string) => `File ${filepath} could not be found! Check if the file exists or verify if the relative path to the file is correct from your terminal's location.`,\n  locationNotFound: (location: string) => `Entered location ${location} is not reachable! Please make sure that the entered directory location exists. Check relative paths and reenter.`,\n  improperArguments: `Improper arguments`,\n  improperBuffers: `Error occured while reading the file buffers`,\n  invalidInput: `Invalid input type: Expected a Buffer or a valid file path`\n}","import { AnyParserMethod, ExtractionPayload } from \"../types\"\nimport { readFileUrl, readFile } from \"../util\"\nimport { fileTypeFromBuffer as getFileType } from 'file-type'\n\nexport class AnyExtractor {\n\tprivate parserMap: Map<string, AnyParserMethod> = new Map();\n\tprivate parsers: AnyParserMethod[] = [];\n\n\tpublic addParser = (method: AnyParserMethod): this => {\n\t\tthis.parsers.push(method);\n\t\tmethod.mimes.forEach((mime) => {\n\t\t\tthis.parserMap.set(mime, method);\n\t\t});\n\t\treturn this;\n\t}\n\n\tpublic getRegisteredParsers = (): string[] => {\n\t\treturn Array.from(this.parserMap.keys());\n\t}\n\n\tpublic extractText = async ({ input, type }: ExtractionPayload): Promise<string> => {\n\t\tlet preparedInput: Buffer;\n\t\tif (typeof input === 'string') {\n\t\t\tswitch (type) {\n\t\t\t\tcase 'file':\n\t\t\t\t\tpreparedInput = await readFile(input);\n\t\t\t\t\tbreak;\n\t\t\t\tcase 'fileurl':\n\t\t\t\t\tpreparedInput = await readFileUrl(input);\n\t\t\t\t\tbreak;\n\t\t\t\tdefault:\n\t\t\t\t\tpreparedInput = Buffer.from(input);\n\t\t\t}\n\t\t} else {\n\t\t\tpreparedInput = input;\n\t\t}\n\n\t\tconst mimeDetails = await getFileType(preparedInput);\n\t\tif (!mimeDetails) return preparedInput.toString('utf-8');\n\n\t\tconst extractor = this.parserMap.get(mimeDetails.mime);\n\n\t\tif (!extractor?.apply) {\n\t\t\tconst message = `AnyExtractor: No extraction method registered for MIME type '${mimeDetails.mime}'`;\n\t\t\tthrow new Error(message);\n\t\t}\n\n\t\treturn extractor.apply(preparedInput)\n\t}\n}","import { Element, LiveNodeList } from \"@xmldom/xmldom\";\nimport { ERRORMSG } from \"../constant\";\nimport { AnyParserMethod } from \"../types\";\nimport { extractFiles, parseString } from \"../util\";\n\nexport class ExcelParser implements AnyParserMethod {\n  mimes = [\"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet\"];\n\n  async apply(file: Buffer): Promise<string> {\n    const sheetsRegex = /xl\\/worksheets\\/sheet\\d+.xml/g;\n    const drawingsRegex = /xl\\/drawings\\/drawing\\d+.xml/g;\n    const chartsRegex = /xl\\/charts\\/chart\\d+.xml/g;\n    const stringsFilePath = 'xl/sharedStrings.xml';\n\n    try {\n      const files = await extractFiles(file, x =>\n        [sheetsRegex, drawingsRegex, chartsRegex].some(fileRegex => x.match(fileRegex)) || x == stringsFilePath\n      );\n\n      if (files.length == 0 || !files.map(file => file.path).some(filename => filename.match(sheetsRegex))) {\n        throw ERRORMSG.fileCorrupted(\"TODO: figure this out\");\n      }\n\n      const xmlContentFilesObject = {\n        sheetFiles: files.filter(file => file.path.match(sheetsRegex)).map(file => file.content),\n        drawingFiles: files.filter(file => file.path.match(drawingsRegex)).map(file => file.content),\n        chartFiles: files.filter(file => file.path.match(chartsRegex)).map(file => file.content),\n        sharedStringsFile: files.filter(file => file.path == stringsFilePath).map(file => file.content)[0],\n      };\n\n      let responseText: string[] = [];\n\n      function isValidInlineStringCNode(cNode: Element): boolean {\n        if (cNode.tagName.toLowerCase() != 'c') return false;\n        if (cNode.getAttribute(\"t\") != 'inlineStr') return false;\n        const childNodesNamedIs: LiveNodeList<Element> = cNode.getElementsByTagName('is');\n        if (childNodesNamedIs.length != 1) return false;\n        const childNodesNamedT: LiveNodeList<Element> = childNodesNamedIs[0].getElementsByTagName('t');\n        if (childNodesNamedT.length != 1) return false;\n        return childNodesNamedT[0].childNodes[0] && childNodesNamedT[0].childNodes[0].nodeValue != '';\n      }\n\n      function hasValidVNodeInCNode(cNode: Element): boolean {\n        const vNodes = cNode.getElementsByTagName(\"v\");\n        return vNodes[0] && vNodes[0].childNodes[0] && vNodes[0].childNodes[0].nodeValue != '';\n      }\n\n      const sharedStringsXmlTNodesList = xmlContentFilesObject.sharedStringsFile != undefined\n        ? parseString(xmlContentFilesObject.sharedStringsFile).getElementsByTagName(\"t\")\n        : [];\n\n      const sharedStrings = Array.from(sharedStringsXmlTNodesList)\n        .map(tNode => tNode.childNodes[0]?.nodeValue ?? '');\n\n      for (const sheetXmlContent of xmlContentFilesObject.sheetFiles) {\n        const sheetsXmlCNodesList = parseString(sheetXmlContent).getElementsByTagName(\"c\");\n        responseText.push(\n          Array.from(sheetsXmlCNodesList)\n            .filter(cNode => isValidInlineStringCNode(cNode) || hasValidVNodeInCNode(cNode))\n            .map(cNode => {\n              if (isValidInlineStringCNode(cNode))\n                return cNode.getElementsByTagName('is')[0].getElementsByTagName('t')[0].childNodes[0].nodeValue;\n              if (hasValidVNodeInCNode(cNode)) {\n                const isIndexInSharedStrings = cNode.getAttribute(\"t\") == \"s\";\n                const value = parseInt(cNode.getElementsByTagName(\"v\")[0].childNodes[0].nodeValue ?? \"\", 10);\n                if (isIndexInSharedStrings && value >= sharedStrings.length)\n                  throw ERRORMSG.fileCorrupted(\"TODO: figure this out\");\n\n                return isIndexInSharedStrings\n                  ? sharedStrings[value]\n                  : value;\n              }\n              return '';\n            })\n            .join(\"\\n\")\n        );\n      }\n\n      for (const drawingXmlContent of xmlContentFilesObject.drawingFiles) {\n        const drawingsXmlParagraphNodesList = parseString(drawingXmlContent).getElementsByTagName(\"a:p\");\n        responseText.push(\n          Array.from(drawingsXmlParagraphNodesList)\n            .filter(paragraphNode => paragraphNode.getElementsByTagName(\"a:t\").length != 0)\n            .map(paragraphNode => {\n              const xmlTextNodeList = paragraphNode.getElementsByTagName(\"a:t\");\n              return Array.from(xmlTextNodeList)\n                .filter(textNode => textNode.childNodes[0] && textNode.childNodes[0].nodeValue)\n                .map(textNode => textNode.childNodes[0].nodeValue)\n                .join(\"\");\n            })\n            .join(\"\\n\")\n        );\n      }\n\n      for (const chartXmlContent of xmlContentFilesObject.chartFiles) {\n        const chartsXmlCVNodesList = parseString(chartXmlContent).getElementsByTagName(\"c:v\");\n        responseText.push(\n          Array.from(chartsXmlCVNodesList)\n            .filter(cVNode => cVNode.childNodes[0] && cVNode.childNodes[0].nodeValue)\n            .map(cVNode => cVNode.childNodes[0].nodeValue)\n            .join(\"\\n\")\n        );\n      }\n\n      return responseText.join(\"\\n\");\n    } catch (error) {\n      console.error(\"Error parsing Excel file:\", error);\n      throw error;\n    }\n  }\n}\n","import { ERRORMSG } from \"../constant\";\nimport { AnyParserMethod } from \"../types\";\nimport { extractFiles, parseString } from \"../util\";\nimport { Element, Node } from \"@xmldom/xmldom\";\n\nexport class OpenOfficeParser implements AnyParserMethod {\n  mimes = [\"application/vnd.oasis.opendocument.text\",\n    \"application/vnd.oasis.opendocument.spreadsheet\",\n    \"application/vnd.oasis.opendocument.presentation\",\n    \"application/vnd.oasis.opendocument.graphics\",\n    \"application/vnd.oasis.opendocument.formula\"];\n\n  apply = async (file: Buffer): Promise<string> => {\n    const mainContentFilePath = 'content.xml';\n    const objectContentFilesRegex = /Object \\d+\\/content.xml/g;\n\n    try {\n      const files = await extractFiles(file, x => x == mainContentFilePath || !!x.match(objectContentFilesRegex));\n\n      if (!files.map(file => file.path).includes(mainContentFilePath)) {\n        throw ERRORMSG.fileCorrupted(\"TODO: figure this out\");\n      }\n\n      const xmlContentFilesObject = {\n        mainContentFile: files.filter(file => file.path == mainContentFilePath).map(file => file.content)[0],\n        objectContentFiles: files.filter(file => file.path.match(objectContentFilesRegex)).map(file => file.content),\n      };\n\n      let notesText: string[] = [];\n      let responseText: string[] = [];\n\n      const allowedTextTags = [\"text:p\", \"text:h\"];\n      const notesTag = \"presentation:notes\";\n\n      function extractAllTextsFromNode(root: Element): string {\n        let xmlTextArray: string[] = [];\n        for (let i = 0; i < root.childNodes.length; i++) {\n          traversal(root.childNodes[i], xmlTextArray, true);\n        }\n        return xmlTextArray.join(\"\");\n      }\n\n      function traversal(node: Node, xmlTextArray: string[], isFirstRecursion: boolean): void {\n        if (!node.childNodes || node.childNodes.length == 0) {\n          if (node.parentNode && (node.parentNode as Element).tagName.indexOf('text') == 0 && node.nodeValue) {\n            if (isNotesNode(node.parentNode as Element)) {\n              notesText.push(node.nodeValue);\n              if (allowedTextTags.includes((node.parentNode as Element).tagName) && !isFirstRecursion) {\n                notesText.push(\"\\n\");\n              }\n            } else {\n              xmlTextArray.push(node.nodeValue);\n              if (allowedTextTags.includes((node.parentNode as Element).tagName) && !isFirstRecursion) {\n                xmlTextArray.push(\"\\n\");\n              }\n            }\n          }\n          return;\n        }\n\n        for (let i = 0; i < node.childNodes.length; i++) {\n          traversal(node.childNodes[i] as Element, xmlTextArray, false);\n        }\n      }\n\n      function isNotesNode(node: Element): boolean {\n        if (node.tagName == notesTag) {\n          return true;\n        }\n        if (node.parentNode) {\n          return isNotesNode(node.parentNode as Element);\n        }\n        return false;\n      }\n\n      function isInvalidTextNode(node: Element) {\n        if (allowedTextTags.includes(node.tagName)) {\n          return true;\n        }\n        if (node.parentNode) {\n          return isInvalidTextNode(node.parentNode as Element);\n        }\n        return false;\n      }\n\n      const xmlContentArray = [xmlContentFilesObject.mainContentFile, ...xmlContentFilesObject.objectContentFiles].map(xmlContent => parseString(xmlContent));\n      xmlContentArray.forEach(xmlContent => {\n        const xmlTextNodesList = [...Array.from(xmlContent\n          .getElementsByTagName(\"*\"))\n          .filter(node => allowedTextTags.includes(node.tagName)\n            && !isInvalidTextNode(node.parentNode as Element))];\n        responseText.push(\n          xmlTextNodesList\n            .map(textNode => extractAllTextsFromNode(textNode))\n            .filter(text => text != \"\")\n            .join(\"\\n\")\n        );\n      });\n\n      responseText = [...responseText, ...notesText];\n      return responseText.join(\"\\n\");\n\n    } catch (error) {\n      console.error(\"Error parsing OpenOffice file:\", error);\n      throw error;\n    }\n  }\n}","import pdf from 'pdf-parse';\nimport { AnyParserMethod } from \"../types\";\n\nexport class PDFParser implements AnyParserMethod {\n  mimes = [\"application/pdf\"];\n\n  apply = async (file: Buffer): Promise<string> => {\n    try {\n      const data = await pdf(file);\n      const textContent = data.text;\n      return textContent;\n    } catch (error) {\n      console.error(\"Error parsing PDF file:\", error);\n      throw error;\n    }\n  };\n}","import { ERRORMSG } from \"../constant\";\nimport { AnyParserMethod } from \"../types\";\nimport { extractFiles, parseString } from \"../util\";\n\nexport class PowerPointParser implements AnyParserMethod {\n  mimes = [\"application/vnd.openxmlformats-officedocument.presentationml.presentation\"];\n\n  async apply(file: Buffer): Promise<string> {\n    const allFilesRegex = /ppt\\/(notesSlides|slides)\\/(notesSlide|slide)\\d+.xml/g;\n    const slidesRegex = /ppt\\/slides\\/slide\\d+.xml/g;\n    const slideNumberRegex = /lide(\\d+)\\.xml/;\n\n    try {\n      const files = await extractFiles(file, x => !!x.match(allFilesRegex));\n\n      files.sort((a, b) => {\n        const matchedANumber = parseInt(a.path.match(slideNumberRegex)?.at(1) ?? \"\", 10);\n        const matchedBNumber = parseInt(b.path.match(slideNumberRegex)?.at(1) ?? \"\", 10);\n\n        const aNumber = isNaN(matchedANumber) ? Infinity : matchedANumber;\n        const bNumber = isNaN(matchedBNumber) ? Infinity : matchedBNumber;\n\n        return aNumber - bNumber || Number(a.path.includes('notes')) - Number(b.path.includes('notes'));\n      });\n\n      if (files.length == 0 || !files.map(file => file.path).some(filename => filename.match(slidesRegex))) {\n        throw ERRORMSG.fileCorrupted(\"TODO: figure this out\");\n      }\n\n      files.sort((a, b) => a.path.indexOf(\"notes\") - b.path.indexOf(\"notes\"));\n\n      const xmlContentArray = files.map(file => file.content);\n\n      let responseText: string[] = [];\n\n      for (const xmlContent of xmlContentArray) {\n        const xmlParagraphNodesList = parseString(xmlContent).getElementsByTagName(\"a:p\");\n        responseText.push(\n          Array.from(xmlParagraphNodesList)\n            .filter(paragraphNode => paragraphNode.getElementsByTagName(\"a:t\").length != 0)\n            .map(paragraphNode => {\n              const xmlTextNodeList = paragraphNode.getElementsByTagName(\"a:t\");\n              return Array.from(xmlTextNodeList)\n                .filter(textNode => textNode.childNodes[0] && textNode.childNodes[0].nodeValue)\n                .map(textNode => textNode.childNodes[0].nodeValue)\n                .join(\"\");\n            })\n            .join(\"\\n\")\n        );\n      }\n      const responseTextString = responseText.join(\"\\n\");\n      return responseTextString;\n    } catch (error) {\n      console.error(\"Error parsing PowerPoint file:\", error);\n      throw error;\n    }\n  }\n}","import { ERRORMSG } from \"../constant\";\nimport { AnyParserMethod } from \"../types\";\nimport { extractFiles, parseString } from \"../util\";\n\nexport class WordParser implements AnyParserMethod {\n  mimes = [\"application/vnd.openxmlformats-officedocument.wordprocessingml.document\"];\n\n  async apply(file: Buffer): Promise<string> {\n    const mainContentFileRegex = /word\\/document[\\d+]?.xml/g;\n    const footnotesFileRegex = /word\\/footnotes[\\d+]?.xml/g;\n    const endnotesFileRegex = /word\\/endnotes[\\d+]?.xml/g;\n\n    try {\n      const files = await extractFiles(file, x =>\n        [mainContentFileRegex, footnotesFileRegex, endnotesFileRegex].some(fileRegex => x.match(fileRegex))\n      );\n\n      if (!files.some(file => file.path.match(mainContentFileRegex))) {\n        throw ERRORMSG.fileCorrupted(\"TODO: figure this out\");\n      }\n\n      const xmlContentArray = files\n        .filter(file => file.path.match(mainContentFileRegex) || file.path.match(footnotesFileRegex) || file.path.match(endnotesFileRegex))\n        .map(file => file.content);\n\n      let responseText: string[] = [];\n\n      xmlContentArray.forEach(xmlContent => {\n        const xmlParagraphNodesList = parseString(xmlContent).getElementsByTagName(\"w:p\");\n        responseText.push(\n          Array.from(xmlParagraphNodesList)\n            .filter(paragraphNode => paragraphNode.getElementsByTagName(\"w:t\").length != 0)\n            .map(paragraphNode => {\n              const xmlTextNodeList = paragraphNode.getElementsByTagName(\"w:t\");\n              return Array.from(xmlTextNodeList)\n                .filter(textNode => textNode.childNodes[0] && textNode.childNodes[0].nodeValue)\n                .map(textNode => textNode.childNodes[0].nodeValue)\n                .join(\"\");\n            })\n            .join(\"\\n\")\n        );\n      });\n      const responseTextString = responseText.join(\"\\n\");\n      return responseTextString;\n    } catch (error) {\n      console.error(\"Error parsing Word file:\", error);\n      throw error;\n    }\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;;;ACAA,sBAAiC;AACjC,oBAAsB;AACtB,mBAAkB;;;ACEX,IAAM,WAAW;AAAA,EACtB,sBAAsB,CAAC,QAAgB,iJAAiJ,GAAG;AAAA,EAC3L,eAAe,CAAC,aAAqB,aAAa,QAAQ;AAAA,EAC1D,kBAAkB,CAAC,aAAqB,QAAQ,QAAQ;AAAA,EACxD,kBAAkB,CAAC,aAAqB,oBAAoB,QAAQ;AAAA,EACpE,mBAAmB;AAAA,EACnB,iBAAiB;AAAA,EACjB,cAAc;AAChB;;;ADPA,2BAAmB;AACnB,oBAA0B;AAEnB,IAAM,WAAW,OAAO,aAC5B,UAAM,gBAAAA,UAAK,QAAQ;AAEf,IAAM,cAAc,OAAO,QAAiC;AACjE,QAAM,MAAM,UAAM,qBAAM,GAAG;AAC3B,MAAI,CAAC,IAAI,GAAI,OAAM,IAAI,MAAM,oBAAoB,IAAI,UAAU,EAAE;AACjE,SAAO,OAAO,KAAK,MAAM,IAAI,YAAY,CAAC;AAC5C;AAEO,IAAM,eAAe,CAAC,UAA2B,aAA+D;AACrH,SAAO,IAAI,QAAQ,CAAC,KAAK,QAAQ;AAC/B,UAAM,iBAAiB,CAAC,YAA2B;AACjD,YAAM,iBAAkC,CAAC;AACzC,cAAQ,UAAU;AAElB,eAAS,aAAa,OAAoB;AACxC,YAAI,SAAS,MAAM,QAAQ,GAAG;AAC5B,kBAAQ,eAAe,OAAO,CAAC,KAAK,eAAe;AACjD,gBAAI;AACF,qBAAO,IAAI,GAAG;AAEhB,uBAAW,SAAK,qBAAAC,SAAO,CAAC,SAAiB;AACvC,6BAAe,KAAK;AAAA,gBACpB,MAAM,MAAM;AAAA,gBACZ,SAAS,KAAK,SAAS;AAAA,cACvB,CAAC;AACD,sBAAQ,UAAU;AAAA,YACpB,CAAC,CAAC;AAAA,UACJ,CAAC;AAAA,QACH;AAEE,kBAAQ,UAAU;AAAA,MACtB;AAEA,cAAQ,GAAG,SAAS,YAAY;AAChC,cAAQ,GAAG,OAAO,MAAM,IAAI,cAAc,CAAC;AAC3C,cAAQ,GAAG,SAAS,GAAG;AAAA,IACzB;AAEA,QAAI,OAAO,SAAS,QAAQ,GAAG;AAC7B,mBAAAC,QAAM,WAAW,UAAU,EAAE,aAAa,KAAK,GAAG,CAAC,KAAK,YAAY;AAClE,YAAI,IAAK,QAAO,IAAI,GAAG;AACvB,uBAAe,OAAO;AAAA,MACxB,CAAC;AAAA,IACH,WACS,OAAO,aAAa,UAAU;AACrC,mBAAAA,QAAM,KAAK,UAAU,EAAE,aAAa,KAAK,GAAG,CAAC,KAAK,YAAY;AAC5D,YAAI,IAAK,QAAO,IAAI,GAAG;AACvB,uBAAe,OAAO;AAAA,MACxB,CAAC;AAAA,IACH;AAEE,UAAI,SAAS,YAAY;AAAA,EAC7B,CAAC;AACH;AAEO,IAAM,cAAc,CAAC,QAAgB;AAC1C,MAAI,SAAS,IAAI,wBAAU;AAC3B,SAAO,OAAO,gBAAgB,KAAK,UAAU;AAC/C;;;AEjEA,uBAAkD;AAE3C,IAAM,eAAN,MAAmB;AAAA,EAAnB;AACN,SAAQ,YAA8C,oBAAI,IAAI;AAC9D,SAAQ,UAAiC,CAAC;AAE1C,SAAO,YAAY,CAAC,WAAsC;AACzD,WAAK,QAAQ,KAAK,MAAM;AACxB,aAAO,MAAM,QAAQ,CAAC,SAAS;AAC9B,aAAK,UAAU,IAAI,MAAM,MAAM;AAAA,MAChC,CAAC;AACD,aAAO;AAAA,IACR;AAEA,SAAO,uBAAuB,MAAgB;AAC7C,aAAO,MAAM,KAAK,KAAK,UAAU,KAAK,CAAC;AAAA,IACxC;AAEA,SAAO,cAAc,OAAO,EAAE,OAAO,KAAK,MAA0C;AACnF,UAAI;AACJ,UAAI,OAAO,UAAU,UAAU;AAC9B,gBAAQ,MAAM;AAAA,UACb,KAAK;AACJ,4BAAgB,MAAM,SAAS,KAAK;AACpC;AAAA,UACD,KAAK;AACJ,4BAAgB,MAAM,YAAY,KAAK;AACvC;AAAA,UACD;AACC,4BAAgB,OAAO,KAAK,KAAK;AAAA,QACnC;AAAA,MACD,OAAO;AACN,wBAAgB;AAAA,MACjB;AAEA,YAAM,cAAc,UAAM,iBAAAC,oBAAY,aAAa;AACnD,UAAI,CAAC,YAAa,QAAO,cAAc,SAAS,OAAO;AAEvD,YAAM,YAAY,KAAK,UAAU,IAAI,YAAY,IAAI;AAErD,UAAI,CAAC,WAAW,OAAO;AACtB,cAAM,UAAU,4DAA4D,YAAY,IAAI;AAC5F,cAAM,IAAI,MAAM,OAAO;AAAA,MACxB;AAEA,aAAO,UAAU,MAAM,aAAa;AAAA,IACrC;AAAA;AACD;;;AC5CO,IAAM,cAAN,MAAiD;AAAA,EAAjD;AACL,iBAAQ,CAAC,mEAAmE;AAAA;AAAA,EAE5E,MAAM,MAAM,MAA+B;AACzC,UAAM,cAAc;AACpB,UAAM,gBAAgB;AACtB,UAAM,cAAc;AACpB,UAAM,kBAAkB;AAExB,QAAI;AAkBF,UAASC,4BAAT,SAAkC,OAAyB;AACzD,YAAI,MAAM,QAAQ,YAAY,KAAK,IAAK,QAAO;AAC/C,YAAI,MAAM,aAAa,GAAG,KAAK,YAAa,QAAO;AACnD,cAAM,oBAA2C,MAAM,qBAAqB,IAAI;AAChF,YAAI,kBAAkB,UAAU,EAAG,QAAO;AAC1C,cAAM,mBAA0C,kBAAkB,CAAC,EAAE,qBAAqB,GAAG;AAC7F,YAAI,iBAAiB,UAAU,EAAG,QAAO;AACzC,eAAO,iBAAiB,CAAC,EAAE,WAAW,CAAC,KAAK,iBAAiB,CAAC,EAAE,WAAW,CAAC,EAAE,aAAa;AAAA,MAC7F,GAESC,wBAAT,SAA8B,OAAyB;AACrD,cAAM,SAAS,MAAM,qBAAqB,GAAG;AAC7C,eAAO,OAAO,CAAC,KAAK,OAAO,CAAC,EAAE,WAAW,CAAC,KAAK,OAAO,CAAC,EAAE,WAAW,CAAC,EAAE,aAAa;AAAA,MACtF;AAbS,qCAAAD,2BAUA,uBAAAC;AA3BT,YAAM,QAAQ,MAAM;AAAA,QAAa;AAAA,QAAM,OACrC,CAAC,aAAa,eAAe,WAAW,EAAE,KAAK,eAAa,EAAE,MAAM,SAAS,CAAC,KAAK,KAAK;AAAA,MAC1F;AAEA,UAAI,MAAM,UAAU,KAAK,CAAC,MAAM,IAAI,CAAAC,UAAQA,MAAK,IAAI,EAAE,KAAK,cAAY,SAAS,MAAM,WAAW,CAAC,GAAG;AACpG,cAAM,SAAS,cAAc,uBAAuB;AAAA,MACtD;AAEA,YAAM,wBAAwB;AAAA,QAC5B,YAAY,MAAM,OAAO,CAAAA,UAAQA,MAAK,KAAK,MAAM,WAAW,CAAC,EAAE,IAAI,CAAAA,UAAQA,MAAK,OAAO;AAAA,QACvF,cAAc,MAAM,OAAO,CAAAA,UAAQA,MAAK,KAAK,MAAM,aAAa,CAAC,EAAE,IAAI,CAAAA,UAAQA,MAAK,OAAO;AAAA,QAC3F,YAAY,MAAM,OAAO,CAAAA,UAAQA,MAAK,KAAK,MAAM,WAAW,CAAC,EAAE,IAAI,CAAAA,UAAQA,MAAK,OAAO;AAAA,QACvF,mBAAmB,MAAM,OAAO,CAAAA,UAAQA,MAAK,QAAQ,eAAe,EAAE,IAAI,CAAAA,UAAQA,MAAK,OAAO,EAAE,CAAC;AAAA,MACnG;AAEA,UAAI,eAAyB,CAAC;AAiB9B,YAAM,6BAA6B,sBAAsB,qBAAqB,SAC1E,YAAY,sBAAsB,iBAAiB,EAAE,qBAAqB,GAAG,IAC7E,CAAC;AAEL,YAAM,gBAAgB,MAAM,KAAK,0BAA0B,EACxD,IAAI,WAAS,MAAM,WAAW,CAAC,GAAG,aAAa,EAAE;AAEpD,iBAAW,mBAAmB,sBAAsB,YAAY;AAC9D,cAAM,sBAAsB,YAAY,eAAe,EAAE,qBAAqB,GAAG;AACjF,qBAAa;AAAA,UACX,MAAM,KAAK,mBAAmB,EAC3B,OAAO,WAASF,0BAAyB,KAAK,KAAKC,sBAAqB,KAAK,CAAC,EAC9E,IAAI,WAAS;AACZ,gBAAID,0BAAyB,KAAK;AAChC,qBAAO,MAAM,qBAAqB,IAAI,EAAE,CAAC,EAAE,qBAAqB,GAAG,EAAE,CAAC,EAAE,WAAW,CAAC,EAAE;AACxF,gBAAIC,sBAAqB,KAAK,GAAG;AAC/B,oBAAM,yBAAyB,MAAM,aAAa,GAAG,KAAK;AAC1D,oBAAM,QAAQ,SAAS,MAAM,qBAAqB,GAAG,EAAE,CAAC,EAAE,WAAW,CAAC,EAAE,aAAa,IAAI,EAAE;AAC3F,kBAAI,0BAA0B,SAAS,cAAc;AACnD,sBAAM,SAAS,cAAc,uBAAuB;AAEtD,qBAAO,yBACH,cAAc,KAAK,IACnB;AAAA,YACN;AACA,mBAAO;AAAA,UACT,CAAC,EACA,KAAK,IAAI;AAAA,QACd;AAAA,MACF;AAEA,iBAAW,qBAAqB,sBAAsB,cAAc;AAClE,cAAM,gCAAgC,YAAY,iBAAiB,EAAE,qBAAqB,KAAK;AAC/F,qBAAa;AAAA,UACX,MAAM,KAAK,6BAA6B,EACrC,OAAO,mBAAiB,cAAc,qBAAqB,KAAK,EAAE,UAAU,CAAC,EAC7E,IAAI,mBAAiB;AACpB,kBAAM,kBAAkB,cAAc,qBAAqB,KAAK;AAChE,mBAAO,MAAM,KAAK,eAAe,EAC9B,OAAO,cAAY,SAAS,WAAW,CAAC,KAAK,SAAS,WAAW,CAAC,EAAE,SAAS,EAC7E,IAAI,cAAY,SAAS,WAAW,CAAC,EAAE,SAAS,EAChD,KAAK,EAAE;AAAA,UACZ,CAAC,EACA,KAAK,IAAI;AAAA,QACd;AAAA,MACF;AAEA,iBAAW,mBAAmB,sBAAsB,YAAY;AAC9D,cAAM,uBAAuB,YAAY,eAAe,EAAE,qBAAqB,KAAK;AACpF,qBAAa;AAAA,UACX,MAAM,KAAK,oBAAoB,EAC5B,OAAO,YAAU,OAAO,WAAW,CAAC,KAAK,OAAO,WAAW,CAAC,EAAE,SAAS,EACvE,IAAI,YAAU,OAAO,WAAW,CAAC,EAAE,SAAS,EAC5C,KAAK,IAAI;AAAA,QACd;AAAA,MACF;AAEA,aAAO,aAAa,KAAK,IAAI;AAAA,IAC/B,SAAS,OAAO;AACd,cAAQ,MAAM,6BAA6B,KAAK;AAChD,YAAM;AAAA,IACR;AAAA,EACF;AACF;;;ACzGO,IAAM,mBAAN,MAAsD;AAAA,EAAtD;AACL,iBAAQ;AAAA,MAAC;AAAA,MACP;AAAA,MACA;AAAA,MACA;AAAA,MACA;AAAA,IAA4C;AAE9C,iBAAQ,OAAO,SAAkC;AAC/C,YAAM,sBAAsB;AAC5B,YAAM,0BAA0B;AAEhC,UAAI;AAkBF,YAASE,2BAAT,SAAiC,MAAuB;AACtD,cAAI,eAAyB,CAAC;AAC9B,mBAAS,IAAI,GAAG,IAAI,KAAK,WAAW,QAAQ,KAAK;AAC/C,YAAAC,WAAU,KAAK,WAAW,CAAC,GAAG,cAAc,IAAI;AAAA,UAClD;AACA,iBAAO,aAAa,KAAK,EAAE;AAAA,QAC7B,GAESA,aAAT,SAAmB,MAAY,cAAwB,kBAAiC;AACtF,cAAI,CAAC,KAAK,cAAc,KAAK,WAAW,UAAU,GAAG;AACnD,gBAAI,KAAK,cAAe,KAAK,WAAuB,QAAQ,QAAQ,MAAM,KAAK,KAAK,KAAK,WAAW;AAClG,kBAAIC,aAAY,KAAK,UAAqB,GAAG;AAC3C,0BAAU,KAAK,KAAK,SAAS;AAC7B,oBAAI,gBAAgB,SAAU,KAAK,WAAuB,OAAO,KAAK,CAAC,kBAAkB;AACvF,4BAAU,KAAK,IAAI;AAAA,gBACrB;AAAA,cACF,OAAO;AACL,6BAAa,KAAK,KAAK,SAAS;AAChC,oBAAI,gBAAgB,SAAU,KAAK,WAAuB,OAAO,KAAK,CAAC,kBAAkB;AACvF,+BAAa,KAAK,IAAI;AAAA,gBACxB;AAAA,cACF;AAAA,YACF;AACA;AAAA,UACF;AAEA,mBAAS,IAAI,GAAG,IAAI,KAAK,WAAW,QAAQ,KAAK;AAC/C,YAAAD,WAAU,KAAK,WAAW,CAAC,GAAc,cAAc,KAAK;AAAA,UAC9D;AAAA,QACF,GAESC,eAAT,SAAqB,MAAwB;AAC3C,cAAI,KAAK,WAAW,UAAU;AAC5B,mBAAO;AAAA,UACT;AACA,cAAI,KAAK,YAAY;AACnB,mBAAOA,aAAY,KAAK,UAAqB;AAAA,UAC/C;AACA,iBAAO;AAAA,QACT,GAESC,qBAAT,SAA2B,MAAe;AACxC,cAAI,gBAAgB,SAAS,KAAK,OAAO,GAAG;AAC1C,mBAAO;AAAA,UACT;AACA,cAAI,KAAK,YAAY;AACnB,mBAAOA,mBAAkB,KAAK,UAAqB;AAAA,UACrD;AACA,iBAAO;AAAA,QACT;AAjDS,sCAAAH,0BAQA,YAAAC,YAuBA,cAAAC,cAUA,oBAAAC;AA1DT,cAAM,QAAQ,MAAM,aAAa,MAAM,OAAK,KAAK,uBAAuB,CAAC,CAAC,EAAE,MAAM,uBAAuB,CAAC;AAE1G,YAAI,CAAC,MAAM,IAAI,CAAAC,UAAQA,MAAK,IAAI,EAAE,SAAS,mBAAmB,GAAG;AAC/D,gBAAM,SAAS,cAAc,uBAAuB;AAAA,QACtD;AAEA,cAAM,wBAAwB;AAAA,UAC5B,iBAAiB,MAAM,OAAO,CAAAA,UAAQA,MAAK,QAAQ,mBAAmB,EAAE,IAAI,CAAAA,UAAQA,MAAK,OAAO,EAAE,CAAC;AAAA,UACnG,oBAAoB,MAAM,OAAO,CAAAA,UAAQA,MAAK,KAAK,MAAM,uBAAuB,CAAC,EAAE,IAAI,CAAAA,UAAQA,MAAK,OAAO;AAAA,QAC7G;AAEA,YAAI,YAAsB,CAAC;AAC3B,YAAI,eAAyB,CAAC;AAE9B,cAAM,kBAAkB,CAAC,UAAU,QAAQ;AAC3C,cAAM,WAAW;AAqDjB,cAAM,kBAAkB,CAAC,sBAAsB,iBAAiB,GAAG,sBAAsB,kBAAkB,EAAE,IAAI,gBAAc,YAAY,UAAU,CAAC;AACtJ,wBAAgB,QAAQ,gBAAc;AACpC,gBAAM,mBAAmB,CAAC,GAAG,MAAM,KAAK,WACrC,qBAAqB,GAAG,CAAC,EACzB,OAAO,UAAQ,gBAAgB,SAAS,KAAK,OAAO,KAChD,CAACD,mBAAkB,KAAK,UAAqB,CAAC,CAAC;AACtD,uBAAa;AAAA,YACX,iBACG,IAAI,cAAYH,yBAAwB,QAAQ,CAAC,EACjD,OAAO,UAAQ,QAAQ,EAAE,EACzB,KAAK,IAAI;AAAA,UACd;AAAA,QACF,CAAC;AAED,uBAAe,CAAC,GAAG,cAAc,GAAG,SAAS;AAC7C,eAAO,aAAa,KAAK,IAAI;AAAA,MAE/B,SAAS,OAAO;AACd,gBAAQ,MAAM,kCAAkC,KAAK;AACrD,cAAM;AAAA,MACR;AAAA,IACF;AAAA;AACF;;;AC3GA,uBAAgB;AAGT,IAAM,YAAN,MAA+C;AAAA,EAA/C;AACL,iBAAQ,CAAC,iBAAiB;AAE1B,iBAAQ,OAAO,SAAkC;AAC/C,UAAI;AACF,cAAM,OAAO,UAAM,iBAAAK,SAAI,IAAI;AAC3B,cAAM,cAAc,KAAK;AACzB,eAAO;AAAA,MACT,SAAS,OAAO;AACd,gBAAQ,MAAM,2BAA2B,KAAK;AAC9C,cAAM;AAAA,MACR;AAAA,IACF;AAAA;AACF;;;ACZO,IAAM,mBAAN,MAAsD;AAAA,EAAtD;AACL,iBAAQ,CAAC,2EAA2E;AAAA;AAAA,EAEpF,MAAM,MAAM,MAA+B;AACzC,UAAM,gBAAgB;AACtB,UAAM,cAAc;AACpB,UAAM,mBAAmB;AAEzB,QAAI;AACF,YAAM,QAAQ,MAAM,aAAa,MAAM,OAAK,CAAC,CAAC,EAAE,MAAM,aAAa,CAAC;AAEpE,YAAM,KAAK,CAAC,GAAG,MAAM;AACnB,cAAM,iBAAiB,SAAS,EAAE,KAAK,MAAM,gBAAgB,GAAG,GAAG,CAAC,KAAK,IAAI,EAAE;AAC/E,cAAM,iBAAiB,SAAS,EAAE,KAAK,MAAM,gBAAgB,GAAG,GAAG,CAAC,KAAK,IAAI,EAAE;AAE/E,cAAM,UAAU,MAAM,cAAc,IAAI,WAAW;AACnD,cAAM,UAAU,MAAM,cAAc,IAAI,WAAW;AAEnD,eAAO,UAAU,WAAW,OAAO,EAAE,KAAK,SAAS,OAAO,CAAC,IAAI,OAAO,EAAE,KAAK,SAAS,OAAO,CAAC;AAAA,MAChG,CAAC;AAED,UAAI,MAAM,UAAU,KAAK,CAAC,MAAM,IAAI,CAAAC,UAAQA,MAAK,IAAI,EAAE,KAAK,cAAY,SAAS,MAAM,WAAW,CAAC,GAAG;AACpG,cAAM,SAAS,cAAc,uBAAuB;AAAA,MACtD;AAEA,YAAM,KAAK,CAAC,GAAG,MAAM,EAAE,KAAK,QAAQ,OAAO,IAAI,EAAE,KAAK,QAAQ,OAAO,CAAC;AAEtE,YAAM,kBAAkB,MAAM,IAAI,CAAAA,UAAQA,MAAK,OAAO;AAEtD,UAAI,eAAyB,CAAC;AAE9B,iBAAW,cAAc,iBAAiB;AACxC,cAAM,wBAAwB,YAAY,UAAU,EAAE,qBAAqB,KAAK;AAChF,qBAAa;AAAA,UACX,MAAM,KAAK,qBAAqB,EAC7B,OAAO,mBAAiB,cAAc,qBAAqB,KAAK,EAAE,UAAU,CAAC,EAC7E,IAAI,mBAAiB;AACpB,kBAAM,kBAAkB,cAAc,qBAAqB,KAAK;AAChE,mBAAO,MAAM,KAAK,eAAe,EAC9B,OAAO,cAAY,SAAS,WAAW,CAAC,KAAK,SAAS,WAAW,CAAC,EAAE,SAAS,EAC7E,IAAI,cAAY,SAAS,WAAW,CAAC,EAAE,SAAS,EAChD,KAAK,EAAE;AAAA,UACZ,CAAC,EACA,KAAK,IAAI;AAAA,QACd;AAAA,MACF;AACA,YAAM,qBAAqB,aAAa,KAAK,IAAI;AACjD,aAAO;AAAA,IACT,SAAS,OAAO;AACd,cAAQ,MAAM,kCAAkC,KAAK;AACrD,YAAM;AAAA,IACR;AAAA,EACF;AACF;;;ACrDO,IAAM,aAAN,MAAgD;AAAA,EAAhD;AACL,iBAAQ,CAAC,yEAAyE;AAAA;AAAA,EAElF,MAAM,MAAM,MAA+B;AACzC,UAAM,uBAAuB;AAC7B,UAAM,qBAAqB;AAC3B,UAAM,oBAAoB;AAE1B,QAAI;AACF,YAAM,QAAQ,MAAM;AAAA,QAAa;AAAA,QAAM,OACrC,CAAC,sBAAsB,oBAAoB,iBAAiB,EAAE,KAAK,eAAa,EAAE,MAAM,SAAS,CAAC;AAAA,MACpG;AAEA,UAAI,CAAC,MAAM,KAAK,CAAAC,UAAQA,MAAK,KAAK,MAAM,oBAAoB,CAAC,GAAG;AAC9D,cAAM,SAAS,cAAc,uBAAuB;AAAA,MACtD;AAEA,YAAM,kBAAkB,MACrB,OAAO,CAAAA,UAAQA,MAAK,KAAK,MAAM,oBAAoB,KAAKA,MAAK,KAAK,MAAM,kBAAkB,KAAKA,MAAK,KAAK,MAAM,iBAAiB,CAAC,EACjI,IAAI,CAAAA,UAAQA,MAAK,OAAO;AAE3B,UAAI,eAAyB,CAAC;AAE9B,sBAAgB,QAAQ,gBAAc;AACpC,cAAM,wBAAwB,YAAY,UAAU,EAAE,qBAAqB,KAAK;AAChF,qBAAa;AAAA,UACX,MAAM,KAAK,qBAAqB,EAC7B,OAAO,mBAAiB,cAAc,qBAAqB,KAAK,EAAE,UAAU,CAAC,EAC7E,IAAI,mBAAiB;AACpB,kBAAM,kBAAkB,cAAc,qBAAqB,KAAK;AAChE,mBAAO,MAAM,KAAK,eAAe,EAC9B,OAAO,cAAY,SAAS,WAAW,CAAC,KAAK,SAAS,WAAW,CAAC,EAAE,SAAS,EAC7E,IAAI,cAAY,SAAS,WAAW,CAAC,EAAE,SAAS,EAChD,KAAK,EAAE;AAAA,UACZ,CAAC,EACA,KAAK,IAAI;AAAA,QACd;AAAA,MACF,CAAC;AACD,YAAM,qBAAqB,aAAa,KAAK,IAAI;AACjD,aAAO;AAAA,IACT,SAAS,OAAO;AACd,cAAQ,MAAM,4BAA4B,KAAK;AAC/C,YAAM;AAAA,IACR;AAAA,EACF;AACF;;;AR1CO,IAAM,kBAAkB,MAAoB;AACjD,QAAM,eAAe,IAAI,aAAa;AAEtC,eAAa,UAAU,IAAI,YAAY,CAAC;AACxC,eAAa,UAAU,IAAI,iBAAiB,CAAC;AAC7C,eAAa,UAAU,IAAI,UAAU,CAAC;AACtC,eAAa,UAAU,IAAI,iBAAiB,CAAC;AAC7C,eAAa,UAAU,IAAI,WAAW,CAAC;AAEvC,SAAO;AACT;","names":["read","concat","yauzl","getFileType","isValidInlineStringCNode","hasValidVNodeInCNode","file","extractAllTextsFromNode","traversal","isNotesNode","isInvalidTextNode","file","pdf","file","file"]}