Add run-length-encoding exercise (#49)

Author: keiravillekode

config.json

@@ -334,6 +334,14 @@
         "prerequisites": [],
         "difficulty": 5
       },
+      {
+        "slug": "run-length-encoding",
+        "name": "Run-Length Encoding",
+        "uuid": "9b14d6e1-bd0e-4450-817f-e6e2c3958a3d",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 5
+      },
       {
         "slug": "variable-length-quantity",
         "name": "Variable Length Quantity",

exercises/practice/run-length-encoding/.docs/instructions.md

@@ -0,0 +1,20 @@
+# Instructions
+
+Implement run-length encoding and decoding.
+
+Run-length encoding (RLE) is a simple form of data compression, where runs (consecutive data elements) are replaced by just one data value and count.
+
+For example we can represent the original 53 characters with only 13.
+
+```text
+"WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB"  ->  "12WB12W3B24WB"
+```
+
+RLE allows the original data to be perfectly reconstructed from the compressed data, which makes it a lossless data compression.
+
+```text
+"AABCCCDEEEE"  ->  "2AB3CD4E"  ->  "AABCCCDEEEE"
+```
+
+For simplicity, you can assume that the unencoded string will only contain the letters A through Z (either lower or upper case) and whitespace.
+This way data to be encoded will never contain any numbers and numbers inside data to be decoded always represent the count for the following character.

exercises/practice/run-length-encoding/.meta/config.json

@@ -0,0 +1,19 @@
+{
+  "authors": [
+    "keiravillekode"
+  ],
+  "files": {
+    "solution": [
+      "run_length_encoding.fut"
+    ],
+    "test": [
+      "test.fut"
+    ],
+    "example": [
+      ".meta/example.fut"
+    ]
+  },
+  "blurb": "Implement run-length encoding and decoding.",
+  "source": "Wikipedia",
+  "source_url": "https://en.wikipedia.org/wiki/Run-length_encoding"
+}

exercises/practice/run-length-encoding/.meta/example.fut

@@ -0,0 +1,35 @@
+def encode [n] (string: [n]u8): []u8 =
+  let (a, i, _) = loop (a, i, k) = (replicate n '\0', n, n) while k > 0 do
+    let c = string[k - 1]
+    let j = loop j = k - 1 while j > 0 && string[j - 1] == c do
+      j - 1
+
+    -- Run-length encode the run from `j` (inclusive) to `k` (exclusive) of the character c
+    let a2 = a with [i - 1] = c
+    let i2 = i - 1
+    in
+      if k - j == 1 then (a2, i2, j) else
+      let (a3, i3, _) = loop (a3, i3, number) = (a2, i2, k - j) while number > 0 do
+        (a3 with [i3 - 1] = '0' + u8.i64 (number % 10), i3 - 1, number / 10)
+      in (a3, i3, j)
+  in
+    a[i:]
+
+def decode_length (string: []u8): i64 =
+  let (i, _) = loop (i, number) = (0, 0) for c in string do
+    if c >= '0' && c <= '9' then (i, number * 10 + i64.u8 c - '0') else
+    if number == 0 then (i + 1, 0) else
+    (i + number, 0)
+  in
+    i
+
+def decode [n] (string: [n]u8): []u8 =
+  let (a, _, _) = loop (a, i, number) = (replicate (decode_length string) '\0', 0, 0) for c in string do
+    if c >= '0' && c <= '9' then (a, i, number * 10 + i64.u8 c - '0') else
+    if number == 0 then (a with [i] = c, i + 1, 0) else
+    let (a2, i2, number2) = loop (a2, i2, number2) = (a, i, number) while number2 > 0 do
+      (a2 with [i2] = c, i2 + 1, number2 - 1)
+    in
+      (a2, i2, number2)
+  in
+    a

exercises/practice/run-length-encoding/.meta/tests.toml

@@ -0,0 +1,49 @@
+# This is an auto-generated file.
+#
+# Regenerating this file via `configlet sync` will:
+# - Recreate every `description` key/value pair
+# - Recreate every `reimplements` key/value pair, where they exist in problem-specifications
+# - Remove any `include = true` key/value pair (an omitted `include` key implies inclusion)
+# - Preserve any other key/value pair
+#
+# As user-added comments (using the # character) will be removed when this file
+# is regenerated, comments can be added via a `comment` key.
+
+[ad53b61b-6ffc-422f-81a6-61f7df92a231]
+description = "run-length encode a string -> empty string"
+
+[52012823-b7e6-4277-893c-5b96d42f82de]
+description = "run-length encode a string -> single characters only are encoded without count"
+
+[b7868492-7e3a-415f-8da3-d88f51f80409]
+description = "run-length encode a string -> string with no single characters"
+
+[859b822b-6e9f-44d6-9c46-6091ee6ae358]
+description = "run-length encode a string -> single characters mixed with repeated characters"
+
+[1b34de62-e152-47be-bc88-469746df63b3]
+description = "run-length encode a string -> multiple whitespace mixed in string"
+
+[abf176e2-3fbd-40ad-bb2f-2dd6d4df721a]
+description = "run-length encode a string -> lowercase characters"
+
+[7ec5c390-f03c-4acf-ac29-5f65861cdeb5]
+description = "run-length decode a string -> empty string"
+
+[ad23f455-1ac2-4b0e-87d0-b85b10696098]
+description = "run-length decode a string -> single characters only"
+
+[21e37583-5a20-4a0e-826c-3dee2c375f54]
+description = "run-length decode a string -> string with no single characters"
+
+[1389ad09-c3a8-4813-9324-99363fba429c]
+description = "run-length decode a string -> single characters with repeated characters"
+
+[3f8e3c51-6aca-4670-b86c-a213bf4706b0]
+description = "run-length decode a string -> multiple whitespace mixed in string"
+
+[29f721de-9aad-435f-ba37-7662df4fb551]
+description = "run-length decode a string -> lowercase string"
+
+[2a762efd-8695-4e04-b0d6-9736899fbc16]
+description = "encode and then decode -> encode followed by decode gives original string"

exercises/practice/run-length-encoding/run_length_encoding.fut

@@ -0,0 +1,3 @@
+def encode (string: []u8): []u8 = ???
+
+def decode (string: []u8): []u8 = ???

exercises/practice/run-length-encoding/test.fut

@@ -0,0 +1,88 @@
+import "run_length_encoding"
+
+-- empty string
+-- ==
+-- entry: test_encode
+-- input { "" }
+-- output { "" }
+
+-- single characters only are encoded without count
+-- ==
+-- entry: test_encode
+-- input { "XYZ" }
+-- output { "XYZ" }
+
+-- string with no single characters
+-- ==
+-- entry: test_encode
+-- input { "AABBBCCCC" }
+-- output { "2A3B4C" }
+
+-- single characters mixed with repeated characters
+-- ==
+-- entry: test_encode
+-- input { "WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB" }
+-- output { "12WB12W3B24WB" }
+
+-- multiple whitespace mixed in string
+-- ==
+-- entry: test_encode
+-- input { "  hsqq qww  " }
+-- output { "2 hs2q q2w2 " }
+
+-- lowercase characters
+-- ==
+-- entry: test_encode
+-- input { "aabbbcccc" }
+-- output { "2a3b4c" }
+
+-- empty string
+-- ==
+-- entry: test_decode
+-- input { "" }
+-- output { "" }
+
+-- single characters only
+-- ==
+-- entry: test_decode
+-- input { "XYZ" }
+-- output { "XYZ" }
+
+-- string with no single characters
+-- ==
+-- entry: test_decode
+-- input { "2A3B4C" }
+-- output { "AABBBCCCC" }
+
+-- single characters with repeated characters
+-- ==
+-- entry: test_decode
+-- input { "12WB12W3B24WB" }
+-- output { "WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB" }
+
+-- multiple whitespace mixed in string
+-- ==
+-- entry: test_decode
+-- input { "2 hs2q q2w2 " }
+-- output { "  hsqq qww  " }
+
+-- lowercase string
+-- ==
+-- entry: test_decode
+-- input { "2a3b4c" }
+-- output { "aabbbcccc" }
+
+-- encode followed by decode gives original string
+-- ==
+-- entry: test_consistency
+-- input { "zzz ZZ  zZ" }
+-- output { "zzz ZZ  zZ" }
+
+entry test_encode (string: []u8): []u8 =
+  encode string
+
+entry test_decode (string: []u8): []u8 =
+  decode string
+
+entry test_consistency (string: []u8): []u8 =
+  decode (encode string)