Sync and re-implement hamming (#170)

exercises/practice/hamming/.docs/instructions.md

@@ -2,11 +2,17 @@
 
 Calculate the Hamming Distance between two DNA strands.
 
-Your body is made up of cells that contain DNA. Those cells regularly wear out and need replacing, which they achieve by dividing into daughter cells. In fact, the average human body experiences about 10 quadrillion cell divisions in a lifetime!
+Your body is made up of cells that contain DNA.
+Those cells regularly wear out and need replacing, which they achieve by dividing into daughter cells.
+In fact, the average human body experiences about 10 quadrillion cell divisions in a lifetime!
 
-When cells divide, their DNA replicates too. Sometimes during this process mistakes happen and single pieces of DNA get encoded with the incorrect information. If we compare two strands of DNA and count the differences between them we can see how many mistakes occurred. This is known as the "Hamming Distance".
+When cells divide, their DNA replicates too.
+Sometimes during this process mistakes happen and single pieces of DNA get encoded with the incorrect information.
+If we compare two strands of DNA and count the differences between them we can see how many mistakes occurred.
+This is known as the "Hamming Distance".
 
-We read DNA using the letters C,A,G and T. Two strands might look like this:
+We read DNA using the letters C,A,G and T.
+Two strands might look like this:
 
     GAGCCTACTAACGGGAT
     CATCGTAATGACGGCCT
@@ -16,9 +22,6 @@ They have 7 differences, and therefore the Hamming Distance is 7.
 
 The Hamming Distance is useful for lots of things in science, not just biology, so it's a nice phrase to be familiar with :)
 
-# Implementation notes
+## Implementation notes
 
-The Hamming distance is only defined for sequences of equal length, so
-an attempt to calculate it between sequences of different lengths should
-not work. The general handling of this situation (e.g., raising an
-exception vs returning a special value) may differ between languages.
+The Hamming distance is only defined for sequences of equal length, so an attempt to calculate it between sequences of different lengths should not work.

exercises/practice/hamming/.meta/config.json

@@ -3,6 +3,7 @@
     "stevejb71"
   ],
   "contributors": [
+    "keiravillekode",
     "NobbZ",
     "yurrriq"
   ],
@@ -19,5 +20,5 @@
   },
   "blurb": "Calculate the Hamming difference between two DNA strands.",
   "source": "The Calculating Point Mutations problem at Rosalind",
-  "source_url": "http://rosalind.info/problems/hamm/"
+  "source_url": "https://rosalind.info/problems/hamm/"
 }

exercises/practice/hamming/.meta/tests.toml

@@ -26,36 +26,46 @@ description = "long different strands"
 
 [919f8ef0-b767-4d1b-8516-6379d07fcb28]
 description = "disallow first strand longer"
+include = false
 
 [b9228bb1-465f-4141-b40f-1f99812de5a8]
 description = "disallow first strand longer"
 reimplements = "919f8ef0-b767-4d1b-8516-6379d07fcb28"
+include = false
 
 [8a2d4ed0-ead5-4fdd-924d-27c4cf56e60e]
 description = "disallow second strand longer"
+include = false
 
 [dab38838-26bb-4fff-acbe-3b0a9bfeba2d]
 description = "disallow second strand longer"
 reimplements = "8a2d4ed0-ead5-4fdd-924d-27c4cf56e60e"
+include = false
 
 [5dce058b-28d4-4ca7-aa64-adfe4e17784c]
 description = "disallow left empty strand"
+include = false
 
 [db92e77e-7c72-499d-8fe6-9354d2bfd504]
 description = "disallow left empty strand"
+include = false
 reimplements = "5dce058b-28d4-4ca7-aa64-adfe4e17784c"
 
 [b764d47c-83ff-4de2-ab10-6cfe4b15c0f3]
 description = "disallow empty first strand"
 reimplements = "db92e77e-7c72-499d-8fe6-9354d2bfd504"
+include = false
 
 [38826d4b-16fb-4639-ac3e-ba027dec8b5f]
 description = "disallow right empty strand"
+include = false
 
 [920cd6e3-18f4-4143-b6b8-74270bb8f8a3]
 description = "disallow right empty strand"
+include = false
 reimplements = "38826d4b-16fb-4639-ac3e-ba027dec8b5f"
 
 [9ab9262f-3521-4191-81f5-0ed184a5aa89]
 description = "disallow empty second strand"
 reimplements = "920cd6e3-18f4-4143-b6b8-74270bb8f8a3"
+include = false

exercises/practice/hamming/example/Hamming.idr

@@ -16,8 +16,4 @@ implementation Eq Nucleotide where
 export
 hamming_distance : Eq a => Vect n a -> Vect n a -> Nat
 hamming_distance s1 s2 = 
-  fst $ filter ((/=) 0) $ map (\(n1,n2) => if n1 == n2 then 0 else 1) $ zip s1 s2
-
-export
-version : String
-version = "1.0.0"
+  fst $ filter (\(n1,n2) => n1 /= n2) $ zip s1 s2

exercises/practice/hamming/src/Hamming.idr

@@ -12,7 +12,3 @@ implementation Eq Nucleotide where
 export
 hamming_distance : Eq a => Vect n a -> Vect n a -> Nat
 hamming_distance s1 s2 = ?hamming_distance_rhs
-
-export
-version : String
-version = "1.0.0"

exercises/practice/hamming/test/src/Main.idr

@@ -1,36 +1,23 @@
 module Main
 
-import Data.Vect
 import System
 import Tester
 import Tester.Runner
 
 import Hamming
-
-collect : {default 0 acc : Nat} -> (List (IO Bool)) -> IO Nat
-collect {acc} []               = pure acc
-collect {acc} (test :: tests) = do
-    bool <- test
-    case bool of
-        True  => collect {acc=acc}   tests
-        False => collect {acc=S acc} tests
+import Data.Vect
 
 tests : List Test
-tests = map (test "")
-        [ assertEq (hamming_distance [A] [A]) 0
-        , assertEq (hamming_distance [G,G,A,C,T,G,A] [G,G,A,C,T,G,A]) 0
-        , assertEq (hamming_distance [A] [G]) 1
-        , assertEq (hamming_distance [A,G] [C,T]) 2
-        , assertEq (hamming_distance [A,T] [C,T]) 1
-        , assertEq (hamming_distance [G,G,A,C,G] [G,G,T,C,G]) 1
-        , assertEq (hamming_distance [A,C,C,A,G,G,G] [A,C,T,A,T,G,G]) 2
-        , assertEq (hamming_distance [A,G,A] [A,G,G]) 1
-        , assertEq (hamming_distance [A,G,G] [A,G,A]) 1
-        , assertEq (hamming_distance [T,A,G] [G,A,T]) 2
-        , assertEq (hamming_distance [G,A,T,A,C,A] [G,C,A,T,A,A]) 4
-        , assertEq (hamming_distance [G,G,A,C,G,G,A,T,T,C,T,G] [A,G,G,A,C,G,G,A,T,T,C,T]) 9
---        , assertEq (hamming_distance empty empty) 0
-        ]
+tests =
+  [ test "empty strands"                   (assertEq (hamming_distance (the (Vect 0 Nucleotide) []) (the (Vect 0 Nucleotide) [])) 0)
+  , test "single letter identical strands" (assertEq (hamming_distance [A] [A]) 0)
+  , test "single letter different strands" (assertEq (hamming_distance [G] [T]) 1)
+  , test "long identical strands"          (assertEq (hamming_distance [G, G, A, C, T, G, A, A, A, T, C, T, G] [G, G, A, C, T, G, A, A, A, T, C, T, G]) 0)
+  , test "long different strands"          (assertEq (hamming_distance [G, G, A, C, G, G, A, T, T, C, T, G] [A, G, G, A, C, G, G, A, T, T, C, T]) 9)
+  , test "short identical strands"         (assertEq (hamming_distance [G, G, A, C, T, G, A] [G, G, A, C, T, G, A]) 0)
+  , test "short different strands"         (assertEq (hamming_distance [A, C, C, A, G, G, G] [A, C, T, A, T, G, G]) 2)
+  ]
+
 export
 main : IO ()
 main = do

generators/exercises/hamming.py

@@ -0,0 +1,38 @@
+
+EXTRA_CASES = [
+    {
+        "description": "short identical strands",
+        "input": {
+            "strand1": "GGACTGA",
+            "strand2": "GGACTGA"
+        },
+        "expected": 0
+    },
+    {
+        "description": "short different strands",
+        "input": {
+            "strand1": "ACCAGGG",
+            "strand2": "ACTATGG"
+        },
+        "expected": 2
+    }
+]
+
+def header():
+    return "import Data.Vect\n"
+
+def extra_cases():
+    return EXTRA_CASES
+
+def generate_test(case):
+    def to_vect(strand):
+        if strand == "":
+            return "(the (Vect 0 Nucleotide) [])"
+        return str(list(strand)).replace("'", "")
+
+    property = "hamming_distance"
+    expected = case["expected"]
+    strand1 = to_vect(case["input"]["strand1"])
+    strand2 = to_vect(case["input"]["strand2"])
+
+    return f'assertEq ({property} {strand1} {strand2}) {expected}'