Last active
December 17, 2018 20:21
-
-
Save milindjagre/a41d85d0130e9cf101fb9eaad92dd4e6 to your computer and use it in GitHub Desktop.
This method returns the HashMap of words and their respective counts.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Map<String, Integer> wordCountMap = new HashMap<String, Integer>(); | |
String[] inputFilePathArray = new String[4]; | |
inputFilePathArray[0] = "C:\\input1.txt"; | |
inputFilePathArray[1] = "C:\\input2.txt"; | |
inputFilePathArray[2] = "C:\\input3.txt"; | |
inputFilePathArray[3] = "C:\\input4.txt"; | |
for (String inputFilePath : inputFilePathArray) { | |
BufferedReader br = new BufferedReader( | |
new FileReader(inputFilePath)); | |
String line = null, mapKey = null; | |
String[] lineSplitter = null; | |
int i = 0; | |
while ((line = br.readLine()) != null) { | |
lineSplitter = line.split(" "); | |
for (i = 0; i < lineSplitter.length; i++) { | |
mapKey = lineSplitter[i].replaceAll("[\\.\\',\\?]", ""); | |
if (!(stopWordsList.contains(mapKey)) | |
&& mapKey.length() > 3) { | |
if (wordCountMap.containsKey(mapKey)) | |
wordCountMap.put(mapKey, | |
wordCountMap.get(mapKey) + 1); | |
else | |
wordCountMap.put(mapKey, 1); | |
} | |
} | |
} | |
br.close(); | |
} | |
LinkedHashMap<String, Integer> sortedWordCountMap = sortHashMapByValues(wordCountMap); | |
System.out.println("***TOP 10 MOST USED WORDS***"); | |
int count = 0; | |
for (Entry<String, Integer> entry : sortedWordCountMap.entrySet()) { | |
if (count < 10) | |
System.out.println(entry.getKey() + " - " + entry.getValue()); | |
count++; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment