initial commit

TermFrequency.java

@@ -0,0 +1,18 @@
+import java.nio.file.Files;
+import java.nio.file.Paths;
+import java.nio.charset.StandardCharsets;
+import java.io.IOException;
+import java.util.Arrays;
+import java.util.Map;
+import java.util.Map.*;
+import java.util.HashMap;
+import java.util.function.*;
+import java.util.stream.Collectors.*;
+import java.util.stream.*;
+import java.util.Iterator;
+import java.util.Comparator;
+import java.util.LinkedHashMap;
+public class TermFrequency {
+  public static void main(final String[] args) {
+}
+

input-small.txt

@@ -0,0 +1,2 @@
+White tigers live mostly in India
+Wild lions live mostly in Africa

stop_words.txt

@@ -0,0 +1 @@
+a,able,about,across,after,all,almost,also,am,among,an,and,any,are,as,at,be,because,been,but,by,can,cannot,could,dear,did,do,does,either,else,ever,every,for,from,get,got,had,has,have,he,her,hers,him,his,how,however,i,if,in,into,is,it,its,just,least,let,like,likely,may,me,might,most,must,my,neither,no,nor,not,of,off,often,on,only,or,other,our,own,rather,said,say,says,she,should,since,so,some,than,that,the,their,them,then,there,these,they,this,tis,to,too,twas,us,wants,was,we,were,what,when,where,which,while,who,whom,why,will,with,would,yet,you,your,

test.js

@@ -0,0 +1,117 @@
+var os = require('os');
+var shell = require('shelljs');
+var argv = require('yargs')
+  .option(
+    {'size': {
+               alias: 's',
+               describe: 'Size of the test',
+               choices: ['small', 'large'],
+               default: 'small'
+             },
+     'lang': {
+               alias: 'l',
+               describe: 'Language of program to test',
+               choices: ['java', 'javascript', 'other'],
+               default: 'java'
+             },
+     'main': {
+               alias: 'm',
+               describe: 'Main Java class or JavaScript file or command to run',
+               default: 'TermFrequency'
+             }
+  })
+  .argv
+
+if (argv.lang == 'java') {
+  console.log('==> Compiling Java classes');
+  shell.exec('javac *.java');
+}
+
+var commandName = {'java': 'java', 'javascript': 'node', 'other': ''};
+var inputFile = ['input-', argv.size, '.txt'].join('');
+var command = [commandName[argv.lang], argv.main, inputFile, '25'].join(' ');
+
+console.log('==> Running \"' + command + '\"');
+var stdout = shell.exec(command).stdout;
+
+var byFreqAndAlpha = function(a, b) {
+  if (b[1] - a[1] != 0) {
+    return b[1] - a[1];
+  } else {
+    if (a[0] < b[0]) {
+      return -1;
+    } else if (a[0] > b[0]) {
+      return 1;
+    } else {
+      return 0;
+    }
+  }
+};
+
+var sort = function(rawOutput, sortCriteria) {
+  return rawOutput
+    .trim()
+    .split(os.EOL)
+    .map(line => line.split('  -  '))
+    .sort(sortCriteria)
+    .map(x => x.join('  -  '));
+}
+
+var outputSortedByFreqAndAlpha = sort(stdout, byFreqAndAlpha);
+var outputSortedByFreq = sort(stdout, (a, b) => b[1] - a[1]);
+
+var expected =
+  {
+    'small': [
+             'live  -  2',
+             'mostly  -  2',
+             'africa  -  1',
+             'india  -  1',
+             'lions  -  1',
+             'tigers  -  1',
+             'white  -  1',
+             'wild  -  1'
+    ],
+    'large': [
+             'mr  -  786',
+             'elizabeth  -  635',
+             'very  -  488',
+             'darcy  -  418',
+             'such  -  395',
+             'mrs  -  343',
+             'much  -  329',
+             'more  -  327',
+             'bennet  -  323',
+             'bingley  -  306',
+             'jane  -  295',
+             'miss  -  283',
+             'one  -  275',
+             'know  -  239',
+             'before  -  229',
+             'herself  -  227',
+             'though  -  226',
+             'well  -  224',
+             'never  -  220',
+             'sister  -  218',
+             'soon  -  216',
+             'think  -  211',
+             'now  -  209',
+             'time  -  203',
+             'good  -  201'
+    ]
+  };
+
+console.log('==> Checking output');
+
+if (stdout.trim() != outputSortedByFreq.join(os.EOL)) {
+  console.error('Test failed. Hint: your output should be sorted by frequency in descending order.');
+  process.exit(1);
+
+} else if (expected[argv.size].join() === outputSortedByFreqAndAlpha.join()) {
+  console.log('ok');
+
+} else {
+  var msg = ['Test failed. Expected:', expected[argv.size].join(os.EOL), 'but found:', stdout.trim()].join(os.EOL);
+  console.error(msg);
+  process.exit(1);
+}