run-length-encoding (#50)

Author: glennj

config.json

@@ -382,6 +382,14 @@
         "practices": [],
         "prerequisites": [],
         "difficulty": 4
+      },
+      {
+        "slug": "run-length-encoding",
+        "name": "Run-Length Encoding",
+        "uuid": "909d5671-60a1-498f-80ce-82d6e0b88465",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 4
       }
     ]
   },

exercises/practice/run-length-encoding/.busted

@@ -0,0 +1,5 @@
+return {
+  default = {
+    ROOT = { '.' }
+  }
+}

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": [
+    "glennj"
+  ],
+  "files": {
+    "solution": [
+      "run_length_encoding.moon"
+    ],
+    "test": [
+      "run_length_encoding_spec.moon"
+    ],
+    "example": [
+      ".meta/example.moon"
+    ]
+  },
+  "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.moon

@@ -0,0 +1,29 @@
+{
+  encode: (plaintext) ->
+    encoded, prev, n = '', '', 0
+
+    add_run = -> encoded ..= "#{if n <= 1 then '' else n}#{prev}"
+
+    for char in plaintext\gmatch '.'
+      if char != prev
+        add_run!
+        n = 1
+        prev = char
+      else
+        n += 1
+    add_run!
+    encoded
+
+
+  decode: (ciphertext) ->
+    decoded, length = '', ''
+    for char in ciphertext\gmatch '.'
+      if char\find '%d'
+        length ..= char
+      else
+        n = tonumber(length) or 1
+        decoded ..= string.rep char, n
+        length = ''
+    decoded
+}
+

exercises/practice/run-length-encoding/.meta/spec_generator.moon

@@ -0,0 +1,18 @@
+{
+  module_imports: {'encode', 'decode'},
+
+  generate_test: (case, level) ->
+    local lines
+    if case.property == 'consistency'
+      lines = {
+        "encoded = encode #{quote case.input.string}",
+        "decoded = decode encoded",
+        "assert.are.equal #{quote case.expected}, decoded"
+      }
+    else
+      lines = {
+        "result = #{case.property} #{quote case.input.string}",
+        "assert.are.equal #{quote case.expected}, result"
+      }
+    table.concat [indent line, level for line in *lines], '\n'
+}

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.moon

@@ -0,0 +1,7 @@
+{
+  encode: (plaintext) ->
+    error 'Implement the encode function'
+
+  decode: (ciphertext) ->
+    error 'Implement the decode function'
+}

exercises/practice/run-length-encoding/run_length_encoding_spec.moon

@@ -0,0 +1,58 @@
+import encode, decode from require 'run_length_encoding'
+
+describe 'run-length-encoding', ->
+  describe 'run-length encode a string', ->
+    it 'empty string', ->
+      result = encode ''
+      assert.are.equal '', result
+
+    pending 'single characters only are encoded without count', ->
+      result = encode 'XYZ'
+      assert.are.equal 'XYZ', result
+
+    pending 'string with no single characters', ->
+      result = encode 'AABBBCCCC'
+      assert.are.equal '2A3B4C', result
+
+    pending 'single characters mixed with repeated characters', ->
+      result = encode 'WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB'
+      assert.are.equal '12WB12W3B24WB', result
+
+    pending 'multiple whitespace mixed in string', ->
+      result = encode '  hsqq qww  '
+      assert.are.equal '2 hs2q q2w2 ', result
+
+    pending 'lowercase characters', ->
+      result = encode 'aabbbcccc'
+      assert.are.equal '2a3b4c', result
+
+  describe 'run-length decode a string', ->
+    pending 'empty string', ->
+      result = decode ''
+      assert.are.equal '', result
+
+    pending 'single characters only', ->
+      result = decode 'XYZ'
+      assert.are.equal 'XYZ', result
+
+    pending 'string with no single characters', ->
+      result = decode '2A3B4C'
+      assert.are.equal 'AABBBCCCC', result
+
+    pending 'single characters with repeated characters', ->
+      result = decode '12WB12W3B24WB'
+      assert.are.equal 'WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB', result
+
+    pending 'multiple whitespace mixed in string', ->
+      result = decode '2 hs2q q2w2 '
+      assert.are.equal '  hsqq qww  ', result
+
+    pending 'lowercase string', ->
+      result = decode '2a3b4c'
+      assert.are.equal 'aabbbcccc', result
+
+  describe 'encode and then decode', ->
+    pending 'encode followed by decode gives original string', ->
+      encoded = encode 'zzz ZZ  zZ'
+      decoded = decode encoded
+      assert.are.equal 'zzz ZZ  zZ', decoded