[ Implementation ] Run-Length Encoding (#744)

💜²⁹

--
🤝 https://forum.exercism.org/t/new-exercise-contributions/4077

config.json

@@ -743,6 +743,14 @@
         "practices": [],
         "prerequisites": [],
         "difficulty": 1
+      },
+      {
+        "slug": "run-length-encoding",
+        "name": "Run-Length Encoding",
+        "uuid": "8997f6f2-a8c3-42b5-94fc-12d0d386a64e",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 1
       }
     ]
   },

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": [
+    "habere-et-dispertire"
+  ],
+  "files": {
+    "solution": [
+      "lib/RunLengthEncoding.rakumod"
+    ],
+    "test": [
+      "t/run-length-encoding.rakutest"
+    ],
+    "example": [
+      ".meta/solutions/lib/RunLengthEncoding.rakumod"
+    ]
+  },
+  "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/solutions/lib/RunLengthEncoding.rakumod

@@ -0,0 +1,26 @@
+unit module RunLengthEncoding;
+
+grammar RLE {
+  token TOP     { <pair>+            }
+  token pair    { <tally>? <element> }
+  token tally   { <digit>+           }
+  token element { <alpha> | ' '      }
+}
+class RLE::Decode {
+  method TOP     ($/) { make $<pair>.map( *.made ).join               }
+  method pair    ($/) { make $<element>.made x ( $<tally>.made // 1 ) }
+  method tally   ($/) { make $/.Int                                   }
+  method element ($/) { make $/.Str                                   }
+}
+sub rle-decode ($compressed) is export {
+  RLE.parse( $compressed, actions => RLE::Decode ).made
+}
+sub rle-encode ($raw) is export {
+  given $raw.comb( / ( [<digit>+]? ) [<alpha> | ' ']+ % <same> / )
+     .map( { .chars == 1 ?? $_ !! .chars ~ .comb.head } )
+     .join
+  -> $compressed {
+    fail unless $raw eq rle-decode($compressed);
+    return $compressed
+  }
+}

exercises/practice/run-length-encoding/.meta/solutions/t/run-length-encoding.rakutest

@@ -0,0 +1 @@
+../../../t/run-length-encoding.rakutest

exercises/practice/run-length-encoding/.meta/template-data.yaml

@@ -0,0 +1,64 @@
+properties:
+  encode:
+    test: |-
+      sprintf(q :to 'END', %case<input><string>.Str.raku, %case<expected>.Str.raku, %case<description>.raku);
+        cmp-ok(
+          rle-encode(%s),
+          "eq",
+          %s,
+          %s,
+        );
+        END
+  decode:
+    test: |-
+      sprintf(q :to 'END', %case<input><string>.Str.raku, %case<expected>.Str.raku, %case<description>.raku);
+        cmp-ok(
+          rle-decode(%s),
+          "eq",
+          %s,
+          %s,
+        );
+        END
+  consistency:
+    test: |-
+      sprintf(q :to 'END', %case<input><string>.Str.raku, %case<expected>.Str.raku, %case<description>.raku);
+        cmp-ok(
+          rle-decode(rle-encode(%s)),
+          "eq",
+          %s,
+          %s,
+        );
+        END
+
+unit: module
+example: |-
+  grammar RLE {
+    token TOP     { <pair>+            }
+    token pair    { <tally>? <element> }
+    token tally   { <digit>+           }
+    token element { <alpha> | ' '      }
+  }
+  class RLE::Decode {
+    method TOP     ($/) { make $<pair>.map( *.made ).join               }
+    method pair    ($/) { make $<element>.made x ( $<tally>.made // 1 ) }
+    method tally   ($/) { make $/.Int                                   }
+    method element ($/) { make $/.Str                                   }
+  }
+  sub rle-decode ($compressed) is export {
+    RLE.parse( $compressed, actions => RLE::Decode ).made
+  }
+  sub rle-encode ($raw) is export {
+    given $raw.comb( / ( [<digit>+]? ) [<alpha> | ' ']+ % <same> / )
+       .map( { .chars == 1 ?? $_ !! .chars ~ .comb.head } )
+       .join
+    -> $compressed {
+      fail unless $raw eq rle-decode($compressed);
+      return $compressed
+    }
+  }
+
+stub: |-
+  sub rle-encode ($raw) is export {
+  }
+  sub rle-decode ($compressed) is export {
+  }

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/lib/RunLengthEncoding.rakumod

@@ -0,0 +1,6 @@
+unit module RunLengthEncoding;
+
+sub rle-encode ($raw) is export {
+}
+sub rle-decode ($compressed) is export {
+}

exercises/practice/run-length-encoding/t/run-length-encoding.rakutest

@@ -0,0 +1,97 @@
+#!/usr/bin/env raku
+use Test;
+use lib $?FILE.IO.parent(2).add('lib');
+use RunLengthEncoding;
+
+cmp-ok( # begin: ad53b61b-6ffc-422f-81a6-61f7df92a231
+  rle-encode(""),
+  "eq",
+  "",
+  "run-length encode a string: empty string",
+); # end: ad53b61b-6ffc-422f-81a6-61f7df92a231
+
+cmp-ok( # begin: 52012823-b7e6-4277-893c-5b96d42f82de
+  rle-encode("XYZ"),
+  "eq",
+  "XYZ",
+  "run-length encode a string: single characters only are encoded without count",
+); # end: 52012823-b7e6-4277-893c-5b96d42f82de
+
+cmp-ok( # begin: b7868492-7e3a-415f-8da3-d88f51f80409
+  rle-encode("AABBBCCCC"),
+  "eq",
+  "2A3B4C",
+  "run-length encode a string: string with no single characters",
+); # end: b7868492-7e3a-415f-8da3-d88f51f80409
+
+cmp-ok( # begin: 859b822b-6e9f-44d6-9c46-6091ee6ae358
+  rle-encode("WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB"),
+  "eq",
+  "12WB12W3B24WB",
+  "run-length encode a string: single characters mixed with repeated characters",
+); # end: 859b822b-6e9f-44d6-9c46-6091ee6ae358
+
+cmp-ok( # begin: 1b34de62-e152-47be-bc88-469746df63b3
+  rle-encode("  hsqq qww  "),
+  "eq",
+  "2 hs2q q2w2 ",
+  "run-length encode a string: multiple whitespace mixed in string",
+); # end: 1b34de62-e152-47be-bc88-469746df63b3
+
+cmp-ok( # begin: abf176e2-3fbd-40ad-bb2f-2dd6d4df721a
+  rle-encode("aabbbcccc"),
+  "eq",
+  "2a3b4c",
+  "run-length encode a string: lowercase characters",
+); # end: abf176e2-3fbd-40ad-bb2f-2dd6d4df721a
+
+cmp-ok( # begin: 7ec5c390-f03c-4acf-ac29-5f65861cdeb5
+  rle-decode(""),
+  "eq",
+  "",
+  "run-length decode a string: empty string",
+); # end: 7ec5c390-f03c-4acf-ac29-5f65861cdeb5
+
+cmp-ok( # begin: ad23f455-1ac2-4b0e-87d0-b85b10696098
+  rle-decode("XYZ"),
+  "eq",
+  "XYZ",
+  "run-length decode a string: single characters only",
+); # end: ad23f455-1ac2-4b0e-87d0-b85b10696098
+
+cmp-ok( # begin: 21e37583-5a20-4a0e-826c-3dee2c375f54
+  rle-decode("2A3B4C"),
+  "eq",
+  "AABBBCCCC",
+  "run-length decode a string: string with no single characters",
+); # end: 21e37583-5a20-4a0e-826c-3dee2c375f54
+
+cmp-ok( # begin: 1389ad09-c3a8-4813-9324-99363fba429c
+  rle-decode("12WB12W3B24WB"),
+  "eq",
+  "WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB",
+  "run-length decode a string: single characters with repeated characters",
+); # end: 1389ad09-c3a8-4813-9324-99363fba429c
+
+cmp-ok( # begin: 3f8e3c51-6aca-4670-b86c-a213bf4706b0
+  rle-decode("2 hs2q q2w2 "),
+  "eq",
+  "  hsqq qww  ",
+  "run-length decode a string: multiple whitespace mixed in string",
+); # end: 3f8e3c51-6aca-4670-b86c-a213bf4706b0
+
+cmp-ok( # begin: 29f721de-9aad-435f-ba37-7662df4fb551
+  rle-decode("2a3b4c"),
+  "eq",
+  "aabbbcccc",
+  "run-length decode a string: lowercase string",
+); # end: 29f721de-9aad-435f-ba37-7662df4fb551
+
+cmp-ok( # begin: 2a762efd-8695-4e04-b0d6-9736899fbc16
+  rle-decode(rle-encode("zzz ZZ  zZ")),
+  "eq",
+  "zzz ZZ  zZ",
+  "encode and then decode: encode followed by decode gives original string",
+); # end: 2a762efd-8695-4e04-b0d6-9736899fbc16
+
+done-testing;