pdf2json - npm Package Compare versions

Comparing version 0.4.4 to 0.4.5

lib/pdf.js

@@ -73,3 +73,3 @@ var nodeUtil = require("util"),
     // constructor
-    var cls = function (pdfPage, id, scale) {
+    var cls = function (pdfPage, id, scale, ptiParser) {
         nodeEvents.EventEmitter.call(this);
@@ -86,2 +86,3 @@ // private
         this.pdfPage = pdfPage;
+        this.ptiParser = ptiParser;
 
@@ -136,3 +137,2 @@ this.scale = scale || 1.0;
         var self = this;
-
         function pageViewDrawCallback(error) {
@@ -148,5 +148,11 @@ self.renderingState = RenderingStates.FINISHED;
             else {
-                nodeUtil._logN.call(self, 'page ' + (self.id + 1) + ' is rendered successfully.');
+                if (self.ptiParser) {
+                    var extraFields = self.ptiParser.getFields(parseInt(self.id) + 1);
+                    _.each(extraFields, _addField, self);
+                }
+
                 _.extend(self, ctx.canvas);
                 self.stats = self.pdfPage.stats;
+
+                nodeUtil._logN.call(self, 'page ' + (self.id + 1) + ' is rendered successfully.');
                 callback();
@@ -219,5 +225,6 @@ }
     cls.prototype.parsePDFData = function(arrayBuffer) {
-        var parameters = {password: '', data: arrayBuffer};
         this.pdfDocument = null;
         this.formImage = null;
+
+        var parameters = {password: '', data: arrayBuffer};
         var self = this;
@@ -239,2 +246,22 @@ PDFJS.getDocument(parameters).then(
 
+    cls.prototype.tryLoadFieldInfoXML = function(pdfFilePath) {
+        var fieldInfoXMLPath = pdfFilePath.replace(".pdf", "_fieldInfo.xml");
+        if (!fs.existsSync(fieldInfoXMLPath)) {
+            return;
+        }
+        nodeUtil._logN.call(this, "About to load fieldInfo XML : " + fieldInfoXMLPath);
+
+        var PTIXmlParser = require('./ptixmlinject');
+        this.ptiParser = new PTIXmlParser();
+        this.ptiParser.parseXml(fieldInfoXMLPath, _.bind(function(err) {
+            if (err) {
+                nodeUtil._logN.call(this, "fieldInfo XML Error: " + JSON.stringify(err));
+                this.ptiParser = null;
+            }
+            else {
+                nodeUtil._logN.call(this, "fieldInfo XML loaded.");
+            }
+        }, this));
+    };
+
     cls.prototype.load = function(pdfDocument, scale) {
@@ -251,7 +278,7 @@ this.pdfDocument = pdfDocument;
 
-        var self = this;
         var pagesPromise = PDFJS.Promise.all(pagePromises);
 
-        nodeUtil._logN.call(self, "PDF loaded. pagesCount = " + pagesCount);
+        nodeUtil._logN.call(this, "PDF loaded. pagesCount = " + pagesCount);
 
+        var self = this;
         pagesPromise.then(function(promisedPages) {
@@ -301,3 +328,4 @@ self.parsePage(promisedPages, 0, 1.5);
         var pdfPage = promisedPages[id];
-        var pageParser = new PDFPageParser(pdfPage, id, scale);
+        var pageParser = new PDFPageParser(pdfPage, id, scale, this.ptiParser);
+
         pageParser.parsePage(function() {
@@ -304,0 +332,0 @@ if (!self.pageWidth)  //get PDF width

lib/pdfline.js

@@ -43,3 +43,3 @@ var nodeUtil = require("util"),
         var yDelta = Math.abs(this.y2 - this.y1);
-        var minDelta = 3 * this.lineWidth;
+        var minDelta = this.lineWidth;
 
@@ -46,0 +46,0 @@ var oneLine = {x:0, y:0, w:this.lineWidth, l:0};

package.json

 {
   "name": "pdf2json",
-  "_id": "pdf2json@0.4.4",
-  "version": "0.4.4",
+  "_id": "pdf2json@0.4.5",
+  "version": "0.4.5",
   "description": "A PDF file parser that converts PDF binaries to text based JSON, powered by porting a fork of PDF.JS to Node.js",
@@ -6,0 +6,0 @@ "keywords": [

pdfparser.js

@@ -115,12 +115,12 @@ var nodeUtil = require("util"),
     cls.prototype.loadPDF = function (pdfFilePath) {
-        var self = this;
-        self.pdfFilePath = pdfFilePath;
-
         nodeUtil._logN.call(this, " is about to load PDF file " + pdfFilePath);
 
+        this.pdfFilePath = pdfFilePath;
+        this.PDFJS.tryLoadFieldInfoXML(pdfFilePath);
+
         if (processBinaryCache.call(this))
             return;
 
-//        fs.readFile(pdfFilePath, _.bind(processPDFContent, self));
-        fq.push({path: pdfFilePath}, _.bind(processPDFContent, self));
+//        fs.readFile(pdfFilePath, _.bind(processPDFContent, this));
+        fq.push({path: pdfFilePath}, _.bind(processPDFContent, this));
     };
@@ -127,0 +127,0 @@

readme.md

@@ -94,2 +94,4 @@ Introduction
 
+v0.4.5 added support when fields attributes information is defined in external xml file. pdf2json will always try load field attributes xml file based on file name convention (pdffilename.pdf's field XML file must be named pdffilename_fieldInfo.xml in the same directory). If found, fields info will be injected.
+
 Dictionary Reference
@@ -96,0 +98,0 @@ -----

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

3261175

increased by0.12%

Number of package files

124

increased by0.81%

Lines of code

35842

increased by0.27%

Number of lines in readme file

622

increased by0.32%

Worsened metrics

Number of low supply chain risk alerts

16

increased by6.67%

No dependency changes