word-extractor - npm Package Compare versions

Comparing version 0.3.0 to 1.0.0

CHANGELOG.md

@@ -1,6 +0,19 @@
-### 0.2.2 / 23rd January 2019
+# Change log
 
- * Fixed [the bad dependency on event-stream](https://github.com/dominictarr/event-stream/issues/116)
+### 1.0.0 / 16th May 2021
 
+ * Major refactoring of the OLE code to use promises internally
+ * Added support for Open Office XML-based (.docx) Word files. See #1
+ * Added support for reading direct from a Buffer. See #11
+ * Removed event-stream dependency. See #19
+ * Fixed an issue with not closing files properly. See #23
+ * Corrected handling of extracting files with files. See #31
+ * Corrected handling of extracting files with deleted text. See #32
+ * Fixed issues with extracting multiple rows of table data. See #33 
 
+This is a major release, and while there are no incompatible API changes, 
+it seemed best to bump the version so as not to pick up updates automatically.
+However, all old applications should not require any code changes to use
+this version.
+
 ### 0.3.0 / 18th February 2019
@@ -13,2 +26,7 @@
 
+### 0.2.2 / 23rd January 2019
+
+ * Fixed [the bad dependency on event-stream](https://github.com/dominictarr/event-stream/issues/116)
+
+
 ### 0.2.1 / 21st January 2019
@@ -15,0 +33,0 @@

lib/document.js

@@ -1,107 +0,108 @@
-const filters =        require('./filters');
+/**
+ * @module document
+ * 
+ * @description
+ * Implements the main document returned when a Word file has been extracted. This exposes
+ * methods that allow the body, annotations, headers, footnotes, and endnotes, to be 
+ * read and used.
+ * 
+ * @author
+ * Stuart Watt <[e-mail]>
+ */
 
-const getPieceIndex = (pieces, position) => {
-  for (let i = 0; i < pieces.length; i++) {
-    const piece = pieces[i];
-    if (position <= piece.endPosition) { 
-      return i; 
-    }
-  }
-};
+const { filter } = require('./filters');
 
-const filter = (text, shouldFilter) => {
+class Document {
   
-  if (!shouldFilter) { 
-    return text; 
+  constructor() {
+    this._body = "";
+    this._footnotes = "";
+    this._endnotes = "";
+    this._headers = "";
+    this._annotations = "";
   }
 
-  const replacer = function(match, ...rest) {
-    if (match.length === 1) {
-      const replaced = filters[match.charCodeAt(0)];
-      if (replaced === 0) {
-        return "";
-      } else {
-        return replaced;
-      }
-    } else if (rest.length === 2) {
-      return "";
-    } else if (rest.length === 3) {
-      return rest[0];
-    }
-  };
+  /**
+   * Accessor to read the main body part of a Word file
+   * @returns a string, containing the Word file body
+   */
+  getBody(filterUnicode) { 
+    const value = this._body;
+    return (filterUnicode == false) ? value : filter(value);
+  }
 
-  const matcher = /(?:[\x02\x05\x07\x08\x0a\x0d\u2018\u2019\u201c\u201d\u2002\u2003\u2012\u2013\u2014]|\x13(?:[^\x14]*\x14)?([^\x15]*)\x15)/g;
-  return text.replace(matcher, replacer);
-};
+  /**
+   * Accessor to read the footnotes part of a Word file
+   * @returns a string, containing the Word file footnotes
+   */
+  getFootnotes(filterUnicode) {
+    const value = this._footnotes;
+    return (filterUnicode == false) ? value : filter(value);
+  }
 
-class Document {
+  /**
+   * Accessor to read the endnotes part of a Word file
+   * @returns a string, containing the Word file endnotes
+   */
+  getEndnotes(filterUnicode) {
+    const value = this._endnotes;
+    return (filterUnicode == false) ? value : filter(value);
+  }
 
-  constructor() {
-    this.pieces = [];
-    this.bookmarks = {};
-    this.boundaries = {};
+  /**
+   * Accessor to read the headers part of a Word file
+   * @returns a string, containing the Word file headers
+   */
+  getHeaders(filterUnicode) {
+    const value = this._headers;
+    return (filterUnicode == false) ? value : filter(value);
   }
 
-  getTextRange(start, end) {
-    const { pieces } = this;
-    const startPiece = getPieceIndex(pieces, start);
-    const endPiece = getPieceIndex(pieces, end);
-    const result = [];
-    for (let i = startPiece, end1 = endPiece; i <= end1; i++) {
-      const piece = pieces[i];
-      const xstart = i === startPiece ? start - piece.position : 0;
-      const xend = i === endPiece ? end - piece.position : piece.endPosition;
-      result.push(piece.text.substring(xstart, xend));
-    }
-
-    return result.join("");
+  /**
+   * Accessor to read the annotations part of a Word file
+   * @returns a string, containing the Word file annotations
+   */
+  getAnnotations(filterUnicode) {
+    const value = this._annotations;
+    return (filterUnicode == false) ? value : filter(value);
   }
 
-  getBody(shouldFilter) {
-    if (shouldFilter == null) { 
-      shouldFilter = true; 
-    }
-    const start = 0;
-    const string = this.getTextRange(start, start + this.boundaries.ccpText);
-    return filter(string, shouldFilter);
+  /**
+   * Accessor to set the main body part of a Word file
+   * @param {*} body the body string 
+   */
+  setBody(body) {
+    this._body = body;
   }
 
-
-  getFootnotes(shouldFilter) {
-    if (shouldFilter == null) { 
-      shouldFilter = true; 
-    }
-    const start = this.boundaries.ccpText;
-    const string = this.getTextRange(start, start + this.boundaries.ccpFtn);
-    return filter(string, shouldFilter);
+  /**
+   * Accessor to set the footnotes part of a Word file
+   * @param {*} footnotes the footnotes string 
+   */
+  setFootnotes(footnotes) {
+    this._footnotes = footnotes;
   }
 
-
-  getHeaders(shouldFilter) {
-    if (shouldFilter == null) { 
-      shouldFilter = true; 
-    }
-    const start = this.boundaries.ccpText + this.boundaries.ccpFtn;
-    const string = this.getTextRange(start, start + this.boundaries.ccpHdd);
-    return filter(string, shouldFilter);
+  /**
+   * Accessor to set the endnotes part of a Word file
+   * @param {*} endnotes the endnotes string 
+   */
+  setEndnotes(endnotes) {
+    this._endnotes = endnotes;
   }
 
-
-  getAnnotations(shouldFilter) {
-    if (shouldFilter == null) { 
-      shouldFilter = true; 
-    }
-    const start = this.boundaries.ccpText + this.boundaries.ccpFtn + this.boundaries.ccpHdd;
-    const string = this.getTextRange(start, start + this.boundaries.ccpAtn);
-    return filter(string, shouldFilter);
+  /**
+   * Accessor to set the headers part of a Word file
+   * @param {*} headers the headers string 
+   */
+  setHeaders(headers) {
+    this._headers = headers;
   }
 
-
-  getEndnotes(shouldFilter) {
-    if (shouldFilter == null) { 
-      shouldFilter = true; 
-    }
-    const start = this.boundaries.ccpText + this.boundaries.ccpFtn + this.boundaries.ccpHdd + this.boundaries.ccpAtn;
-    const string = this.getTextRange(start, start + this.boundaries.ccpAtn + this.boundaries.ccpEdn);
-    return filter(string, shouldFilter);
+  /**
+   * Accessor to set the annotations part of a Word file
+   * @param {*} annotations the annotations string 
+   */
+  setAnnotations(annotations) {
+    this._annotations = annotations;
   }
@@ -108,0 +109,0 @@ }

lib/filters.js

@@ -1,19 +0,98 @@
-const filters = [];
-filters[0x0002] = 0;
-filters[0x0005] = 0;
-filters[0x0008] = 0;
-filters[0x2018] = "'";
-filters[0x2019] = "'";
-filters[0x201C] = "\"";
-filters[0x201D] = "\"";
-filters[0x0007] = "\t";
-filters[0x000D] = "\n";
-filters[0x2002] = " ";
-filters[0x2003] = " ";
-filters[0x2012] = "-";
-filters[0x2013] = "-";
-filters[0x2014] = "-";
-filters[0x000A] = "\n";
-filters[0x000D] = "\n";
+/**
+ * @module filters
+ * 
+ * @description
+ * Exports several functions that implement various methods for translating
+ * characters into Unicode, and cleaning up some of the remaining residues from
+ * Word's odd internal marker character usage.
+ */
 
-module.exports = filters;
+const replaceTable = [];
+replaceTable[0x0002] = '\x00';
+replaceTable[0x0005] = '\x00';
+replaceTable[0x0007] = "\t";
+replaceTable[0x0008] = '\x00';
+replaceTable[0x000A] = "\n";
+replaceTable[0x000B] = "\n";
+replaceTable[0x000C] = "\n";
+replaceTable[0x000D] = "\n";
+replaceTable[0x001E] = "\u2011";
+
+const binaryToUnicodeTable = [];
+binaryToUnicodeTable[0x0082] = "\u201a";
+binaryToUnicodeTable[0x0083] = "\u0192";
+binaryToUnicodeTable[0x0084] = "\u201e";
+binaryToUnicodeTable[0x0085] = "\u2026";
+binaryToUnicodeTable[0x0086] = "\u2020";
+binaryToUnicodeTable[0x0087] = "\u2021";
+binaryToUnicodeTable[0x0088] = "\u02C6";
+binaryToUnicodeTable[0x0089] = "\u2030";
+binaryToUnicodeTable[0x008a] = "\u0160";
+binaryToUnicodeTable[0x008b] = "\u2039";
+binaryToUnicodeTable[0x008c] = "\u0152";
+binaryToUnicodeTable[0x008e] = "\u017D";
+binaryToUnicodeTable[0x0091] = "\u2018";
+binaryToUnicodeTable[0x0092] = "\u2019";
+binaryToUnicodeTable[0x0093] = "\u201C";
+binaryToUnicodeTable[0x0094] = "\u201D";
+binaryToUnicodeTable[0x0095] = "\u2022";
+binaryToUnicodeTable[0x0096] = "\u2013";
+binaryToUnicodeTable[0x0097] = "\u2014";
+binaryToUnicodeTable[0x0098] = "\u02DC";
+binaryToUnicodeTable[0x0099] = "\u2122";
+binaryToUnicodeTable[0x009a] = "\u0161";
+binaryToUnicodeTable[0x009b] = "\u203A";
+binaryToUnicodeTable[0x009c] = "\u0153";
+binaryToUnicodeTable[0x009e] = "\u017E";
+binaryToUnicodeTable[0x009f] = "\u0178";
+
+const binaryToUnicode = (string) => {
+  return string.replace(/([\x80-\x9f])/g, (match) => binaryToUnicodeTable[match.charCodeAt(0)]);
+};
+
+/**
+ * The main function for cleaning OLE-based text. It runs a few standard replacements on characters
+ * that are reserved for special purposes, also removes fields, and finally strips out any weird 
+ * characters that are likely not to be useful for anyone.
+ * @param {*} string an input string
+ * @returns a cleaned up string
+ */
+const clean = (string) => {
+
+  // Fields can be nested, which makes this awkward. We use a strict non-nesting model
+  // and repeat until we find no substitutions. This is because a second match might
+  // start before an earlier one, due to our replacements.
+
+  string = string.replace(/([\x02\x05\x07\x08\x0a\x0b\x0c\x0d\x1f])/g, (match) => replaceTable[match.charCodeAt(0)]);
+
+  let called = true;
+  while (called) {
+    called = false;
+    string = string.replace(/(?:\x13[^\x13\x14\x15]*\x14?([^\x13\x14\x15]*)\x15)/g, (match, p1) => { called = true; return p1; });
+  }
+
+  return string
+    .replace(/[\x00-\x07]/g, '');
+};
+
+const filterTable = [];
+filterTable[0x2002] = " ";
+filterTable[0x2003] = " ";
+filterTable[0x2012] = "-";
+filterTable[0x2013] = "-";
+filterTable[0x2014] = "-";
+filterTable[0x2018] = "'";
+filterTable[0x2019] = "'";
+filterTable[0x201c] = "\"";
+filterTable[0x201d] = "\"";
+
+const filter = (string) => {
+  return string
+    .replace(/[\u2002\u2003\u2012\u2013\u2014\u2018\u2019\u201c\u201d]/g, (match) => filterTable[match.charCodeAt(0)]);
+};
+
+module.exports = {
+  clean: clean,
+  binaryToUnicode: binaryToUnicode,
+  filter: filter
+};

lib/word.js

@@ -1,237 +0,72 @@
-/*
- * decaffeinate suggestions:
- * DS102: Remove unnecessary code created because of implicit returns
- * DS205: Consider reworking code to avoid use of IIFEs
- * DS206: Consider reworking classes to avoid initClass
- * Full docs: https://github.com/decaffeinate/decaffeinate/blob/master/docs/suggestions.md
+/**
+ * @module word
+ * 
+ * @description
+ * The main module for the package. This exports an extractor class, which
+ * provides a single `extract` method that can be called with either a 
+ * string (filename) or a buffer.
  */
-const { Buffer } =     require('buffer');
 
-const oleDoc =         require('./ole-doc').OleCompoundDoc;
+const { Buffer } =          require('buffer');
 
-const filters =        require('./filters');         // eslint-disable-line no-unused-vars
-const translations =   require('./translations');    // eslint-disable-line no-unused-vars
+const WordOleExtractor =    require('./word-ole-extractor');
+const OpenOfficeExtractor = require('./open-office-extractor');
 
-const Document =       require('./document');
+const BufferReader =        require('./buffer-reader');
+const FileReader =          require('./file-reader');
 
-var WordExtractor = (function() {
-  let streamBuffer = undefined;
-  let extractDocument = undefined;
-  let documentStream = undefined;
-  let writeBookmarks = undefined;
-  let writePieces = undefined;
-  let extractWordDocument = undefined;
-  let getPiece = undefined;
-  let addText = undefined;
-  let addUnicodeText = undefined;
-  WordExtractor = class WordExtractor {
-    static initClass() {
-  
-  
-      //# Given an OLE stream, returns all the data in a buffer,
-      //# as a promise.
-      streamBuffer = stream =>
-        new Promise(function(resolve, reject) {
-          const chunks = [];
-          stream.on('data', chunk => chunks.push(chunk));
-          stream.on('error', error => reject(error));
-          return stream.on('end', () => resolve(Buffer.concat(chunks)));
-        })
-      ;
-  
-  
-      extractDocument = filename =>
-        new Promise(function(resolve, reject) {
-          const document = new oleDoc(filename);
-          document.on('err', error => {
-            return reject(error);
-          });
-          document.on('ready', () => {
-            return resolve(document);
-          });
-          return document.read();
-        })
-      ;
-  
-  
-      documentStream = (document, stream) => Promise.resolve(document.stream(stream));
-  
-  
-      writeBookmarks = function(buffer, tableBuffer, result) {
-        const fcSttbfBkmk = buffer.readUInt32LE(0x0142);
-        const lcbSttbfBkmk = buffer.readUInt32LE(0x0146);
-        const fcPlcfBkf = buffer.readUInt32LE(0x014a);
-        const lcbPlcfBkf = buffer.readUInt32LE(0x014e);
-        const fcPlcfBkl = buffer.readUInt32LE(0x0152);
-        const lcbPlcfBkl = buffer.readUInt32LE(0x0156);
-  
-        if (lcbSttbfBkmk === 0) { return; }
-  
-        const sttbfBkmk = tableBuffer.slice(fcSttbfBkmk, fcSttbfBkmk + lcbSttbfBkmk);
-        const plcfBkf = tableBuffer.slice(fcPlcfBkf, fcPlcfBkf + lcbPlcfBkf);
-        const plcfBkl = tableBuffer.slice(fcPlcfBkl, fcPlcfBkl + lcbPlcfBkl);
-  
-        const fcExtend = sttbfBkmk.readUInt16LE(0);
-        const cData = sttbfBkmk.readUInt16LE(2);       // eslint-disable-line no-unused-vars
-        const cbExtra = sttbfBkmk.readUInt16LE(4);     // eslint-disable-line no-unused-vars
-  
-        if (fcExtend !== 0xffff) {
-          throw new Error("Internal error: unexpected single-byte bookmark data");
-        }
-  
-        let offset = 6;
-        const index = 0;
-        const bookmarks = {};                          // eslint-disable-line no-unused-vars
-  
-        while (offset < lcbSttbfBkmk) {
-          let length = sttbfBkmk.readUInt16LE(offset);
-          length = length * 2;
-          const segment = sttbfBkmk.slice(offset + 2, offset + 2 + length);
-          const cpStart = plcfBkf.readUInt32LE(index * 4);
-          const cpEnd = plcfBkl.readUInt32LE(index * 4);
-          result.bookmarks[segment] = {start: cpStart, end: cpEnd};
-          offset = offset + length + 2;
-        }
-      };
-  
-  
-      writePieces = function(buffer, tableBuffer, result) {
-        let flag;
-        let pos = buffer.readUInt32LE(0x01a2);
-  
-        while (true) {                          // eslint-disable-line no-constant-condition
-          flag = tableBuffer.readUInt8(pos);
-          if (flag !== 1) { break; }
-  
-          pos = pos + 1;
-          const skip = tableBuffer.readUInt16LE(pos);
-          pos = pos + 2 + skip;
-        }
-  
-        flag = tableBuffer.readUInt8(pos);
-        pos = pos + 1;
-        if (flag !== 2) {
-          throw new Error("Internal error: ccorrupted Word file");
-        }
-  
-        const pieceTableSize = tableBuffer.readUInt32LE(pos);
-        pos = pos + 4;
-  
-        const pieces = (pieceTableSize - 4) / 12;
-        let start = 0;
-        let lastPosition = 0;
-  
-        for (let x = 0, end = pieces - 1; x <= end; x++) {
-          const offset = pos + ((pieces + 1) * 4) + (x * 8) + 2;
-          let filePos = tableBuffer.readUInt32LE(offset);
-          let unicode = false;
-          if ((filePos & 0x40000000) === 0) {
-            unicode = true;
-          } else {
-            filePos = filePos & ~(0x40000000);
-            filePos = Math.floor(filePos / 2);
-          }
-          const lStart = tableBuffer.readUInt32LE(pos + (x * 4));
-          const lEnd = tableBuffer.readUInt32LE(pos + ((x + 1) * 4));
-          const totLength = lEnd - lStart;
+/**
+ * The main class for the word extraction package. Typically, people will make
+ * an instance of this class, and call the {@link #extract} method to transform 
+ * a Word file into a {@link Document} instance, which provides the accessors
+ * needed to read its body, and so on.
+ */
+class WordExtractor {
 
-          const piece = {
-            start,
-            totLength,
-            filePos,
-            unicode
-          };
+  constructor() {}
 
-          getPiece(buffer, piece);
-          piece.length = piece.text.length;
-          piece.position = lastPosition;
-          piece.endPosition = lastPosition + piece.length;
-          result.pieces.push(piece);
+  /**
+   * Extracts the main contents of the file. If a Buffer is passed, that
+   * is used instead. Opens the file, and reads the first block, uses that
+   * to detect whether this is a .doc file or a .docx file, and then calls
+   * either {@link WordOleDocument#extract} or {@link OpenOfficeDocument#extract}
+   * accordingly.
+   * 
+   * @param {*} source either a string filename, or a Buffer containing the file content
+   * @returns a {@link Document} providing accessors onto the text
+   */
+  extract(source) {
+    let reader = null;
+    if (Buffer.isBuffer(source)) {
+      reader = new BufferReader(source);
+    } else if (typeof source === 'string') {
+      reader = new FileReader(source);
+    }
+    const buffer = Buffer.alloc(512);
+    return reader.open()
+      .then(() => reader.read(buffer, 0, 512, 0))
+      .then((buffer) => {
+        let extractor = null;
 
-          start = start + (unicode ? Math.floor(totLength / 2) : totLength);
-          lastPosition = lastPosition + piece.length;
-        }
-      };
-  
-      extractWordDocument = (document, buffer) =>
-        new Promise(function(resolve, reject) {
-          const magic = buffer.readUInt16LE(0);
-          if (magic !== 0xa5ec) {
-            return reject(new Error(`This does not seem to be a Word document: Invalid magic number: ${magic.toString(16)}`));
+        if (buffer.readUInt16BE(0) === 0xd0cf) {
+          extractor = WordOleExtractor;
+        } else if (buffer.readUInt16BE(0) === 0x504b) {
+          const next = buffer.readUInt16BE(2);
+          if ((next === 0x0304) || (next === 0x0506) || (next === 0x0708)) {
+            extractor = OpenOfficeExtractor;
           }
-  
-          const flags = buffer.readUInt16LE(0xA);
-  
-          const table = (flags & 0x0200) !== 0 ? "1Table" : "0Table";
-  
-          return documentStream(document, table)
-            .then(stream => streamBuffer(stream)).then(function(tableBuffer) {
-              const result = new Document();
-              result.boundaries.fcMin = buffer.readUInt32LE(0x0018);
-              result.boundaries.ccpText = buffer.readUInt32LE(0x004c);
-              result.boundaries.ccpFtn = buffer.readUInt32LE(0x0050);
-              result.boundaries.ccpHdd = buffer.readUInt32LE(0x0054);
-              result.boundaries.ccpAtn = buffer.readUInt32LE(0x005c);
-              result.boundaries.ccpEdn = buffer.readUInt32LE(0x0060);
-  
-              writeBookmarks(buffer, tableBuffer, result);
-              writePieces(buffer, tableBuffer, result);
-  
-              return resolve(result);}).catch(error => reject(error));
-        })
-      ;
-  
-  
-      getPiece = function(buffer, piece) {
-        const pstart = piece.start;
-        const ptotLength = piece.totLength;
-        const pfilePos = piece.filePos;
-        const punicode = piece.unicode;
-  
-        const pend = pstart + ptotLength;
-        const textStart = pfilePos;
-        const textEnd = textStart + (pend - pstart);
-  
-        if (punicode) {
-          return piece.text = addUnicodeText(buffer, textStart, textEnd);
-        } else {
-          return piece.text = addText(buffer, textStart, textEnd);
         }
-      };
-  
-  
-      addText = function(buffer, textStart, textEnd) {
-        const slice = buffer.slice(textStart, textEnd);
-        return slice.toString('binary');
-      };
-  
-      addUnicodeText = function(buffer, textStart, textEnd) {
-        const slice = buffer.slice(textStart, (2*textEnd) - textStart);
-        const string = slice.toString('ucs2');
-  
-        // See the conversion table for FcCompressed structures. Note that these
-        // should not affect positions, as these are characters now, not bytes
-        // for i in [0..string.length]
-        //   if
-  
-        return string;
-      };
-    }
 
-    constructor() {}
+        if (! extractor) {
+          throw new Error("Unable to read this type of file");
+        }
 
+        return (new extractor()).extract(reader);
+      })
+      .finally(() => reader.close());
+  }
 
-    extract(filename) {
-      return extractDocument(filename)
-        .then(document =>
-          documentStream(document, 'WordDocument')
-            .then(stream => streamBuffer(stream)).then(buffer => extractWordDocument(document, buffer))
-        );
-    }
-  };
-  WordExtractor.initClass();
-  return WordExtractor;
-})();
+}
 
 
 module.exports = WordExtractor;

package.json

 {
   "name": "word-extractor",
-  "version": "0.3.0",
+  "version": "1.0.0",
   "description": "Node.js package to read Word .doc files",
@@ -8,3 +8,5 @@ "main": "lib/word.js",
     "test": "jest",
-    "test-watch": "jest --watch"
+    "test-watch": "jest --watch",
+    "coverage": "jest --coverage",
+    "jsdoc": "jsdoc lib --configure jsdoc.json"
   },
@@ -25,9 +27,10 @@ "repository": {
   "devDependencies": {
-    "eslint": "^5.8.0",
-    "jest": "^24.1.0"
+    "eslint": "^7.25.0",
+    "jest": "^26.6.0",
+    "jest-specific-snapshot": "^4.0.0",
+    "jsdoc": "^3.6.6"
   },
   "dependencies": {
-    "async": "^1.5.2",
-    "event-stream": "^3.3.4",
-    "underscore": "^1.8.3"
+    "sax": "^1.2.4",
+    "yauzl": "^2.10.0"
   },
@@ -40,3 +43,3 @@ "jest": {
     "transformIgnorePatterns": [],
-    "testRegex": "(/__tests__/.*|(\\.|/)(test))\\.jsx?$",
+    "testRegex": "(/__tests__/.*?_test)\\.jsx?$",
     "collectCoverageFrom": [
@@ -43,0 +46,0 @@ "lib/**/*.js"

README.md

@@ -1,14 +0,24 @@
-### word-extractor
+## word-extractor
 
-Read data from a Word document using node.js
+Read data from a Word document (.doc or .docx) using Node.js
 
+### Why use this module?
 
-#### Why use this module?
+There are a fair number of npm components which can extract text from Word .doc
+files, but they all appear to require some external helper program, and involve
+either spawning a process or communicating with a persistent one. That raises
+the installation and deployment burden as well as the runtime one.
 
-There are a fair number of npm components which can extract text from Word .doc files, but they all appear to require some external helper program, and involve either spawning a process or communicating with a persistent one. That raises the installation and deployment burden as well as the runtime one.
+This module is intended to provide a much faster way of reading the text from a
+Word file, without leaving the Node.js environment.
 
-This module is intended to provide a much faster way of reading the text from a Word file, without leaving the node.js environment.
+This means you do not need to install Word, Office, or anything else, and the
+module will work on all platforms, without any native binary code requirements.
 
-#### How do I install this module?
+As of version 1.0, this module supports both traditional, OLE-based, Word files (usually .doc), 
+and modern, Open Office-style, ECMA-376 Word files (usually .docx). It can be 
+used both with files and with file contents in a Node.js Buffer.
 
+### How do I install this module?
+
 ```bash=
@@ -21,45 +31,58 @@ yarn add word-extractor
 
-#### How do I use this module?
+### How do I use this module?
 
-    var WordExtractor = require("word-extractor");
-    var extractor = new WordExtractor();
-    var extracted = extractor.extract("file.doc");
-    extracted.then(function(doc) {
-      console.log(doc.getBody());
-    });
+```
+const WordExtractor = require("word-extractor"); 
+const extractor = new WordExtractor();
+const extracted = extractor.extract("file.doc");
 
-The object returned from the `extract()` method is a promise that resolves to a document object, which then provides several views onto different parts of the document contents.
+extracted.then(function(doc) { console.log(doc.getBody()); });
+```
 
+The object returned from the `extract()` method is a promise that resolves to a
+document object, which then provides several views onto different parts of the
+document contents.
 
-#### Methods
+### Methods
 
-`WordExtractor#extract(file)`
+`WordExtractor#extract(<filename>  | <Buffer>)`
 
-Main method to open a Word file and retrieve the data. Returns a promise which resolves to a `Document`.
+Main method to open a Word file and retrieve the data. Returns a promise which
+resolves to a `Document`. If a Buffer is passed instead of a filename, then
+the buffer is used directly, instad of reading a disk from the file system.
 
 `Document#getBody()`
 
-Retrieves the content text from a Word document. This will handle UNICODE characters correctly, so if there are accented or non-Latin-1 characters present in the document, they'll show as is in the returned string.
+Retrieves the content text from a Word document. This will handle UNICODE
+characters correctly, so if there are accented or non-Latin-1 characters
+present in the document, they'll show as is in the returned string.
 
 `Document#getFootnotes()`
 
-Retrieves the footnote text from a Word document. This will handle UNICODE characters correctly, so if there are accented or non-Latin-1 characters present in the document, they'll show as is in the returned string.
+Retrieves the footnote text from a Word document. This will handle UNICODE
+characters correctly, so if there are accented or non-Latin-1 characters
+present in the document, they'll show as is in the returned string.
 
 `Document#getEndnotes()`
 
-Retrieves the endnote text from a Word document. This will handle UNICODE characters correctly, so if there are accented or non-Latin-1 characters present in the document, they'll show as is in the returned string.
+Retrieves the endnote text from a Word document. This will handle UNICODE
+characters correctly, so if there are accented or non-Latin-1 characters
+present in the document, they'll show as is in the returned string.
 
 `Document#getHeaders()`
 
-Retrieves the header and footer text from a Word document. This will handle UNICODE characters correctly, so if there are accented or non-Latin-1 characters present in the document, they'll show as is in the returned string.
+Retrieves the header and footer text from a Word document. This will handle
+UNICODE characters correctly, so if there are accented or non-Latin-1
+characters present in the document, they'll show as is in the returned string.
 
 `Document#getAnnotations()`
 
-Retrieves the comment bubble text from a Word document. This will handle UNICODE characters correctly, so if there are accented or non-Latin-1 characters present in the document, they'll show as is in the returned string.
+Retrieves the comment bubble text from a Word document. This will handle
+UNICODE characters correctly, so if there are accented or non-Latin-1
+characters present in the document, they'll show as is in the returned string.
 
+### License
 
-#### License
+Copyright (c) 2016-2021. Stuart Watt.
 
-Copyright (c) 2016-2019. Stuart Watt.
-
 Licensed under the MIT License.

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Native code

Supply chain risk

Contains native code (e.g., compiled binaries or shared libraries). Including native code can obscure malicious behavior.

Found 12 instances in 1 package

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Mixed license

License

(Experimental) Package contains multiple licenses.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

No v1

Quality

Package is not semver >=1. This means it is not stable and does not support ^ ranges.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

1984648

increased by5397.18%

Dependency count

2

decreased by-33.33%

Number of package files

95

increased by691.67%

Lines of code

3170

increased by291.36%

Number of low quality alerts

0

decreased by-100%

Number of lines in readme file

88

increased by35.38%

Number of low supply chain risk alerts

1

decreased by-50%

Worsened metrics

Dev dependency count

4

increased by100%

Number of low license alerts

1

increased byInfinity%

Number of medium supply chain risk alerts

13

increased byInfinity%

Dependency changes

• + Addedsax@^1.2.4

• + Addedyauzl@^2.10.0

• + Addedbuffer-crc32@0.2.13(transitive)

• + Addedfd-slicer@1.1.0(transitive)

• + Addedpend@1.2.0(transitive)

• + Addedsax@1.4.1(transitive)

• + Addedyauzl@2.10.0(transitive)

• - Removedasync@^1.5.2

• - Removedevent-stream@^3.3.4

• - Removedunderscore@^1.8.3

• - Removedasync@1.5.2(transitive)

• - Removedduplexer@0.1.2(transitive)

• - Removedevent-stream@3.3.5(transitive)

• - Removedfrom@0.1.7(transitive)

• - Removedmap-stream@0.0.7(transitive)

• - Removedpause-stream@0.0.11(transitive)

• - Removedsplit@1.0.1(transitive)

• - Removedstream-combiner@0.2.2(transitive)

• - Removedthrough@2.3.8(transitive)

• - Removedunderscore@1.13.7(transitive)