--- a/core_testing2/docdiff.scala	Mon Nov 06 21:49:55 2023 +0000
+++ b/core_testing2/docdiff.scala	Fri Dec 08 00:54:36 2023 +0000
@@ -1,57 +1,41 @@
-// Preliminary Part about Code Similarity
-//========================================
+// Core Part 2 about Code Similarity
+//===================================
 
 
 object C2 { 
 
-//(1) Complete the clean function below. It should find
-//    all words in a string using the regular expression
-//    \w+  and the library function 
-//
-//         some_regex.findAllIn(some_string)
-//
-//    The words should be Returned as a list of strings.
+// ADD YOUR CODE BELOW
+//======================
+
+//(1)
+def clean(s: String) : List[String] = """(\w+)""".r.findAllIn(s).toList
+  
 
-def clean(s: String) : List[String] = 
-  ("""\w+""".r).findAllIn(s).toList
+
+//(2)
+def occurrences(xs: List[String]): Map[String, Int] = {
+    val ls = xs.distinct
+    val occLs = for (s <- ls) yield (s, xs.count(_.equals(s)))
+    occLs.toMap
+}
 
 
-//(2) The function occurrences calculates the number of times  
-//    strings occur in a list of strings. These occurrences should 
-//    be calculated as a Map from strings to integers.
-
-def occurrences(xs: List[String]): Map[String, Int] =
-  (for (x <- xs.distinct) yield (x, xs.count(_ == x))).toMap
-
-//(3) This functions calculates the dot-product of two documents
-//    (list of strings). For this it calculates the occurrence
-//    maps from (2) and then multiplies the corresponding occurrences. 
-//    If a string does not occur in a document, the product is zero.
-//    The function finally sums up all products. 
-
+//(3)
 def prod(lst1: List[String], lst2: List[String]) : Int = {
-    val words = (lst1 ::: lst2).distinct
-    val occs1 = occurrences(lst1)
-    val occs2 = occurrences(lst2)
-    words.map{ w => occs1.getOrElse(w, 0) * occs2.getOrElse(w, 0) }.sum
-}          
-
-//(4) Complete the functions overlap and similarity. The overlap of
-//    two documents is calculated by the formula given in the assignment
-//    description. The similarity of two strings is given by the overlap
-//    of the cleaned (see (1)) strings.  
-
-def overlap(lst1: List[String], lst2: List[String]) : Double = {
-    val m1 = prod(lst1, lst1)
-    val m2 = prod(lst2, lst2) 
-    prod(lst1, lst2).toDouble / (List(m1, m2).max)
+    val occM1 = occurrences(lst1)
+    val occM2 = occurrences(lst2)
+    (for (s <- occM1) yield s._2 * occM2.getOrElse(s._1,0)).sum
 }
 
-def similarity(s1: String, s2: String) : Double =
-  overlap(clean(s1), clean(s2))
+
+//(4)
+def overlap(lst1: List[String], lst2: List[String]) : Double = prod(lst1,lst2) / prod(lst1,lst1).max(prod(lst2,lst2))
+
+def similarity(s1: String, s2: String) : Double = overlap(clean(s1), clean(s2))
 
 
-/*
+
+/* Test cases
 
 
 val list1 = List("a", "b", "b", "c", "d") 
@@ -81,7 +65,7 @@
 heritage which ensures Australia's capacity to attract international
 ecotourists."""
 
-similarity(orig1, plag1)
+similarity(orig1, plag1) // 0.8679245283018868
 
 
 // Plagiarism examples from 
@@ -105,13 +89,14 @@
 recovery: a controversial tactic that is often implemented immediately
 following an oil spill."""
 
-overlap(clean(orig2), clean(plag2))
-similarity(orig2, plag2)
+overlap(clean(orig2), clean(plag2))  // 0.728
+similarity(orig2, plag2)             // 0.728
+
 
+ 
 // The punchline: everything above 0.6 looks suspicious and 
-// should be looked at by staff.
+// should be investigated by staff.
 
 */
 
-
 }