A heuristic measure for detecting undesired influence of lossy JP2 compression on OCR in the absence of ground truth

Script

//Create a random session id
sessionID = new Random().nextInt(10000000);

Script

List split = new ArrayList();
if (!string.equals("")) {
	String regexString = ",";
	if (regex != void) {
		regexString = regex;
	}
	String[] result = string.split(regexString);
	for (int i = 0; i < result.length; i++) {
		split.add(result[i]);
	}
}

Value

Script

String outputFile = "/tmp/"+sessionID+"/data";
BufferedWriter out = new BufferedWriter(new FileWriter(outputFile));
out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(outputFile), "utf-8")); 
int num = resultList.size();
List sublist = resultList.get(0);
int num = resultList.size();
List sublist = (List) resultList.get(0);
int slnum = sublist.size();
for (int i = 0; i < slnum; i++) {
    int linesum = 0;
    double fileSizeSum = 0;
    int totSizeReducedPerRate = 0;
    int totSizeOrigPerRate = 0;
    for (int j = 0; j < num; j++) {
        linesum += Integer.parseInt((String)((List)resultList.get(j)).get(i));
        String fsvalStr = (String)((List)fileSizeList.get(j)).get(i);
        fsvalStr = fsvalStr.replaceAll("\\s+", "");
        int fsval = Integer.parseInt(fsvalStr);
        totSizeReducedPerRate += fsval;
        String origFsvalStr = (String)((List)origFileSizeList.get(j)).get(i);
        origFsvalStr = origFsvalStr.replaceAll("\\s+", "");
        totSizeOrigPerRate += Integer.parseInt(origFsvalStr);
    }
    double bytesReduced = (double)totSizeOrigPerRate - (double)totSizeReducedPerRate;
    double percentReduced = (bytesReduced/(double)totSizeOrigPerRate)*100;
    double sqDiffSum = 0.0;
    /* mean value of levenshtein distance values for one image */
    double lineAvg = (double)linesum / (double)num;
    for (int j = 0; j < num; j++) {
        int currInt = Integer.parseInt((String)((List)resultList.get(j)).get(i));
        sqDiffSum += Math.pow((((double)currInt) - lineAvg),2);
    }
    /* standard deviation of levenshtein distance values for one image  */
    double lineStdDev = Math.sqrt((double)sqDiffSum / (double)num);
    out.write(Integer.toString(i)+" "+Double.toString(lineAvg)  + " " +Double.toString(lineStdDev) + " " +Double.toString(percentReduced) + "\n");
}
out.flush();
out.close();
File outFile = new File(outputFile);
num_processed_files = num;
if(outFile.exists()) {
	datafile = "file://"+outFile.getAbsolutePath();
} else {
	throw new FileNotFoundException();
}

Script

BufferedReader getReader (String fileUrl, String encoding) throws IOException {
		InputStreamReader reader;
		try {
			if (encoding == null) {
				reader = new FileReader(fileUrl);
			} else {
				reader = new InputStreamReader(new FileInputStream(fileUrl),encoding); 
			}
		}
		catch (FileNotFoundException e) {
			// try a real URL instead
			URL url = new URL(fileUrl);
			if (encoding == null) {
				reader = new InputStreamReader (url.openStream());
			} else {
				reader = new InputStreamReader (url.openStream(), encoding);
			}
		}
		return new BufferedReader(reader);
	}



StringBuffer sb = new StringBuffer(4000);

if (encoding == void) {
	encoding = null;
}

BufferedReader in = getReader(fileurl, encoding);
String str;
String lineEnding = System.getProperty("line.separator");

while ((str = in.readLine()) != null) {
	sb.append(str);
	sb.append(lineEnding);
}
in.close();
filecontents = sb.toString();
  

Script

if ((url == void) || (url == null)) {
	throw new RuntimeException("The url must be specified");
}

URL inputURL = null;
if (base != void) {
	inputURL = new URL(new URL(base), url);
} else {
	inputURL = new URL(url);
}

int bytesRead = 0;
int totalBytesRead = 0;
InputStream is = inputURL.openStream();
ByteArrayOutputStream os = new ByteArrayOutputStream();
byte[] buffer = new byte[2048];
while (true) {
	bytesRead = is.read(buffer);
	if (bytesRead == -1) {
		break;	
	}

	os.write(buffer, 0, bytesRead);
}

image = os.toByteArray();
is.close();
os.close();