word-extractor - npm Package Compare versions

Comparing version 1.0.1 to 1.0.2

CHANGELOG.md

 # Change log
 
+### 1.0.2 / 28th May 2021
+
+ * Added a new method for reading textbox content. See #35
+ 
 ### 1.0.1 / 24th May 2021
@@ -4,0 +8,0 @@

lib/document.js

@@ -112,2 +112,26 @@ /**
   }
+
+  /**
+   * Accessor to read the textboxes from a Word file. The text box content is aggregated as a 
+   * single long string. When both the body and header content exists, they will be separated
+   * by a newline.
+   * @param {Object} options - options for body data
+   * @param {boolean} options.filterUnicode - if true (the default), converts common Unicode quotes
+   *   to standard ASCII characters 
+   * @param {boolean} options.includeHeadersAndFooters - if true (the default), includes text box
+   *   content in headers and footers
+   * @param {boolean} options.includeBody - if true (the default), includes text box
+   *   content in the document body
+   * @returns a string, containing the Word file text box content
+   */
+  getTextboxes(options) {
+    options = options || {};
+    const segments = [];
+    if (options.includeBody != false) 
+      segments.push(this._textboxes);
+    if (options.includeHeadersAndFooters != false)
+      segments.push(this._headerTextboxes);
+    const value = segments.join("\n");
+    return (options.filterUnicode == false) ? value : filter(value);
+  }
 }
@@ -114,0 +138,0 @@

lib/open-office-extractor.js

@@ -118,2 +118,11 @@
         });
+      })
+      .then((document) => {
+        if (document._textboxes && document._textboxes.length > 0) {
+          document._textboxes = document._textboxes + "\n";
+        }
+        if (document._headerTextboxes && document._headerTextboxes.length > 0) {
+          document._headerTextboxes = document._headerTextboxes + "\n";
+        }
+        return document;
       });
@@ -128,3 +137,2 @@
     parser.on("opentag", (node) => {
-
       if (node.name === 'Override') {
@@ -150,6 +158,8 @@ const actionFunction = this._streamTypes[node.attributes['ContentType']];
                  node.name === 'w:endnotes' || 
-                 node.name === 'w:comments' || 
-                 node.name === 'w:hdr' ||
+                 node.name === 'w:comments') {
+        this._context = ['content', 'body'];
+        this._pieces = [];
+      } else if (node.name === 'w:hdr' ||
                  node.name === 'w:ftr') {
-        this._context = ['content'];
+        this._context = ['content', 'header'];
         this._pieces = [];
@@ -175,2 +185,6 @@ } else if (node.name === 'w:endnote' || node.name === 'w:footnote') {
         this._context.unshift('drawing');
+      } else if (node.name === 'w:txbxContent') {
+        this._context.unshift(this._pieces);
+        this._context.unshift('textbox');
+        this._pieces = [];
       }
@@ -202,4 +216,5 @@
       } else if (node === 'w:p') {
-        if (this._context[0] === 'content' || this._context[0] === 'cell')
+        if (this._context[0] === 'content' || this._context[0] === 'cell' || this._context[0] === 'textbox') {
           this._pieces.push("\n");
+        }
       } else if (node === 'w:del' || node === 'w:instrText') {
@@ -217,2 +232,25 @@ this._context.shift();
         this._context.shift();
+      } else if (node === 'w:txbxContent') {
+        const textBox = this._pieces.join("");
+        const context = this._context.shift();
+        if (context !== 'textbox') {
+          throw new Error("Invalid textbox context");
+        }
+        this._pieces = this._context.shift();
+        
+        // If in drawing context, discard
+        if (this._context[0] === 'drawing')
+          return;
+
+        if (textBox.length == 0)
+          return;
+        
+        const inHeader = this._context.includes('header');
+        const documentField = (inHeader) ? '_headerTextboxes' : '_textboxes';
+        if (this._document[documentField]) {
+          this._document[documentField] = this._document[documentField] + "\n" + textBox;
+        } else {
+          this._document[documentField] = textBox;
+        }
+
       }
@@ -224,3 +262,3 @@ });
         return;
-      if (this._context[0] === 'content' || this._context[0] === 'cell') {
+      if (this._context[0] === 'content' || this._context[0] === 'cell' || this._context[0] === 'textbox') {
         this._pieces.push(string);
@@ -227,0 +265,0 @@ }

lib/word-ole-extractor.js

@@ -289,2 +289,12 @@ /**
 
+    if (this._boundaries.ccpTxbx) {
+      document._textboxes = clean(getTextRangeByCP(pieces, start, start + this._boundaries.ccpTxbx - 1));
+      start += this._boundaries.ccpTxbx;  
+    }
+
+    if (this._boundaries.ccpHdrTxbx) {
+      document._headerTextboxes = clean(getTextRangeByCP(pieces, start, start + this._boundaries.ccpHdrTxbx - 1));
+      start += this._boundaries.ccpHdrTxbx;  
+    }
+
     return document;
@@ -318,2 +328,4 @@ }
         this._boundaries.ccpEdn = buffer.readUInt32LE(0x0060);
+        this._boundaries.ccpTxbx = buffer.readUInt32LE(0x0064);
+        this._boundaries.ccpHdrTxbx = buffer.readUInt32LE(0x0068);
 
@@ -320,0 +332,0 @@ this.writeBookmarks(buffer, streamBuffer);

package.json

 {
   "name": "word-extractor",
-  "version": "1.0.1",
+  "version": "1.0.2",
   "description": "Node.js package to read Word .doc files",
@@ -5,0 +5,0 @@ "main": "lib/word.js",

README.md

@@ -73,3 +73,3 @@ ## word-extractor
 
-`Document#getHeaders()`
+`Document#getHeaders(options?)`
 
@@ -98,2 +98,15 @@ Retrieves the header and footer text from a Word document. This will handle
 
+`Document#getTextboxes(options?)`
+
+Retrieves the textbox contenttext 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.
+
+Note that by default, `getTextboxes()` returns one string, containing all 
+textbox content from both main document and the headers and footers. You 
+can control what gets included by using the options `includeHeadersAndFooters`
+(which defaults to true) and `includeBody` (also defaults to true). So, 
+as an example, if you only want the body text box content, use: 
+`doc.getTextboxes({includeHeadersAndFooters: false})`.
+
 ### License
@@ -100,0 +113,0 @@

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

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

Improved metrics

Total package byte prevSize

72214

increased by3.82%

Lines of code

1665

increased by4.26%

Number of lines in readme file

115

increased by12.75%

Worsened metrics

Number of package files

18

decreased by-10%

No dependency changes