User:Pedro Sá Couto/Prototyping 3rd

Tesseract, OCR, Book scan

<script type="text/javascript">

    //store all class 'ocr_line' in 'lines'
    var lines = document.querySelectorAll(".ocr_line");    

    //loop through each element in 'lines'
    for (var i = 0; i < lines.length; i++){ 

      var line = lines[i];
      console.log(line.title) 

      //split the content of 'title' every space and store the list in 'parts'
      var parts = line.title.split(" ");
      console.log(parts);

      // width and height starts from the side 
      var left = parseInt(parts[1], 10);
      var top = parseInt(parts[2], 10);
      var width = (parseInt(parts[3], 10) - left);
      var height = (parseInt(parts[4], 10) - top);

      // create a style element with the content selected from the list 'parts'
      line.style = "position: absolute; left: " + parts[1] + "px; top: " + parts[2] + "px; width: " + width + "px; height: " + height + "px; border: 5px solid lightblue";

      var words = line.querySelectorAll(".ocrx_word");

      for (var e = 0; e < words.length; e++){ 

        var span = words[e];
        console.log(span.title) 

        var parts = span.title.split(" ");
        console.log(parts);

        var wleft = parseInt(parts[1], 10);
        var wtop = parseInt(parts[2], 10);
        var wwidth = (parseInt(parts[3], 10) - wleft);
        var wheight = (parseInt(parts[4], 10) - wtop);

        span.style = "position: absolute; left: " + (wleft - left) + "px; top: " + (wtop - top) + "px; width: " + wwidth  + "px; height: " + wheight + "px; border: 2px solid purple";
      } 
    }

• 
• 
• 
•