pdfreader - npm Package Compare versions

Comparing version 0.1.5 to 0.2.0

package.json

 {
   "name": "pdfreader",
-  "version": "0.1.5",
+  "version": "0.2.0",
   "description": "Utility for simplifying the development of scripted / rule-based parsing of PDF files, including tabular data (tables, with automatic column detection).",
@@ -5,0 +5,0 @@ "main": "index.js",

README.md

@@ -38,4 +38,80 @@ # pdfreader
 
-Other example of use: [parsing a CV/résumé](https://github.com/adrienjoly/npm-pdfreader-example)
+## Example: parsing lines of text from a PDF file
 
+![example cv resume parse convert pdf to text](https://github.com/adrienjoly/npm-pdfreader-example/raw/master/parseRows.png)
+
+Here is the code required to convert this PDF file into text:
+
+```js
+var pdfreader = require('pdfreader');
+
+var rows = {}; // indexed by y-position
+
+function printRows() {
+  Object.keys(rows) // => array of y-positions (type: float)
+    .sort((y1, y2) => parseFloat(y1) - parseFloat(y2)) // sort float positions
+    .forEach((y) => console.log((rows[y] || []).join('')));
+}
+
+new pdfreader.PdfReader().parseFileItems('CV_ErhanYasar.pdf', function(err, item){
+  if (!item || item.page) {
+    // end of file, or page
+    printRows();
+    console.log('PAGE:', item.page);
+    rows = {}; // clear rows for next page
+  }
+  else if (item.text) {
+    // accumulate text items into rows object, per line
+    (rows[item.y] = rows[item.y] || []).push(item.text);
+  }
+});
+```
+
+Fork this example from [parsing a CV/résumé](https://github.com/adrienjoly/npm-pdfreader-example).
+
+## Example: parsing a table from a PDF file
+
+![example cv resume parse convert pdf table to text](https://github.com/adrienjoly/npm-pdfreader-example/raw/master/parseTable.png)
+
+Here is the code required to convert this PDF file into a textual table:
+
+```js
+var pdfreader = require('pdfreader');
+
+const nbCols = 2;
+const cellPadding = 40; // each cell is padded to fit 40 characters
+const columnQuantitizer = (item) => parseFloat(item.x) >= 20;
+
+const padColumns = (array, nb) =>
+  Array.apply(null, {length: nb}).map((val, i) => array[i] || []);
+  // .. because map() skips undefined elements
+
+const mergeCells = (cells) => (cells || [])
+  .map((cell) => cell.text).join('') // merge cells
+  .substr(0, cellPadding).padEnd(cellPadding, ' '); // padding
+
+const renderMatrix = (matrix) => (matrix || [])
+  .map((row, y) => padColumns(row, nbCols)
+    .map(mergeCells)
+    .join(' | ')
+  ).join('\n');
+
+var table = new pdfreader.TableParser();
+
+new pdfreader.PdfReader().parseFileItems(filename, function(err, item){
+  if (!item || item.page) {
+    // end of file, or page
+    console.log(renderMatrix(table.getMatrix()));
+    console.log('PAGE:', item.page);
+    table = new pdfreader.TableParser(); // new/clear table for next page
+  } else if (item.text) {
+    // accumulate text items into rows object, per line
+    table.processItem(item, columnQuantitizer(item));
+  }
+});
+```
+
+Fork this example from [parsing a CV/résumé](https://github.com/adrienjoly/npm-pdfreader-example).
+
+
 ## Rule-based data extraction
@@ -42,0 +118,0 @@

No alert changes

Improved metrics

Total package byte prevSize

52692

increased by4.83%

Number of lines in readme file

135

increased by128.81%

No dependency changes