Add practice exercise: run-length-encoding

config.json

@@ -418,6 +418,14 @@
         "prerequisites": [],
         "difficulty": 8
       },
+      {
+        "slug": "run-length-encoding",
+        "name": "Run-Length Encoding",
+        "uuid": "065feae7-f6fc-46b9-a226-d3d9df9d192b",  
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 8
+      },
       {
         "slug": "scrabble-score",
         "name": "Scrabble Score",

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": [
+    "jimmytty"
+  ],
+  "files": {
+    "solution": [
+      "run-length-encoding.sql"
+    ],
+    "test": [
+      "run-length-encoding_test.sql"
+    ],
+    "example": [
+      ".meta/example.sql"
+    ]
+  },
+  "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.sql

@@ -0,0 +1,88 @@
+UPDATE "run-length-encoding"
+   SET result = ''
+ WHERE string = ''
+;
+
+UPDATE "run-length-encoding"
+   SET result = (
+     WITH RECURSIVE rcte (input, chr, next_chr, idx, grp) AS (
+       VALUES (string, NULL, NULL, 0, 1)
+       UNION ALL
+       SELECT SUBSTR(input, 2),
+              SUBSTR(input, 1, 1),
+              SUBSTR(input, 2, 1),
+              idx + 1,
+              IIF(chr <> next_chr, grp + 1, grp)
+         FROM rcte
+        WHERE input <> ''
+     )
+     SELECT GROUP_CONCAT(PRINTF('%s%s', IIF(cnt = 1, '', cnt), chr), '')
+       FROM (
+         SELECT COUNT(*) cnt, chr
+           FROM rcte
+          WHERE chr NOT NULL
+          GROUP BY chr, grp
+          ORDER BY idx
+       )
+   )
+ WHERE property = 'encode'
+   AND string <> ''
+;
+
+UPDATE "run-length-encoding"
+   SET result = (
+     WITH RECURSIVE rcte (input, num, chr) AS (
+       VALUES (REPLACE(string, ' ', CHAR(7)), NULL, NULL)
+       UNION ALL
+       SELECT SUBSTR(LTRIM(input, CAST(input AS INT)), 2),
+              CAST(input AS INT),
+              SUBSTR(LTRIM(input, CAST(input AS INT)), 1, 1)
+         FROM rcte
+        WHERE input <> ''
+     )
+     SELECT REPLACE(GROUP_CONCAT(PRINTF('%.*c', num, chr), ''), CHAR(7), ' ')
+       FROM rcte
+      WHERE chr NOT NULL
+   )
+ WHERE property = 'decode'
+   AND string <> ''
+;
+
+UPDATE "run-length-encoding"
+   SET result = (
+     WITH RECURSIVE rcte (input, num, chr) AS (
+       VALUES (REPLACE(
+         (
+           WITH RECURSIVE rcte (input, chr, next_chr, idx, grp) AS (
+             VALUES (string, NULL, NULL, 0, 1)
+             UNION ALL
+             SELECT SUBSTR(input, 2),
+                    SUBSTR(input, 1, 1),
+                    SUBSTR(input, 2, 1),
+                    idx + 1,
+                    IIF(chr <> next_chr, grp + 1, grp)
+               FROM rcte
+              WHERE input <> ''
+           )
+           SELECT GROUP_CONCAT(PRINTF('%s%s', IIF(cnt = 1, '', cnt), chr), '')
+             FROM (
+               SELECT COUNT(*) cnt, chr
+                 FROM rcte
+                WHERE chr NOT NULL
+                GROUP BY chr, grp
+                ORDER BY idx
+             )
+         ), ' ', CHAR(7)), NULL, NULL)
+         UNION ALL
+         SELECT SUBSTR(LTRIM(input, CAST(input AS INT)), 2),
+                CAST(input AS INT),
+                SUBSTR(LTRIM(input, CAST(input AS INT)), 1, 1)
+           FROM rcte
+          WHERE input <> ''
+     )
+     SELECT REPLACE(GROUP_CONCAT(PRINTF('%.*c', num, chr), ''), CHAR(7), ' ')
+       FROM rcte
+      WHERE chr NOT NULL
+   )
+ WHERE property = 'consistency'
+;

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/create_fixture.sql

@@ -0,0 +1,11 @@
+DROP TABLE IF EXISTS "run-length-encoding";
+CREATE TABLE "run-length-encoding" (
+    property TEXT NOT NULL,
+    string   TEXT NOT NULL,
+    result   TEXT
+);
+
+.mode csv
+.import ./data.csv "run-length-encoding"
+
+UPDATE "run-length-encoding" SET result = NULL;

exercises/practice/run-length-encoding/create_test_table.sql

@@ -0,0 +1,33 @@
+DROP TABLE IF EXISTS tests;
+CREATE TABLE IF NOT EXISTS tests (
+    -- uuid and description are taken from the test.toml file
+    uuid TEXT PRIMARY KEY,
+    description TEXT NOT NULL,
+    -- The following section is needed by the online test-runner
+    status TEXT DEFAULT 'fail',
+    message TEXT,
+    output TEXT,
+    test_code TEXT,
+    task_id INTEGER DEFAULT NULL,
+    -- Here are columns for the actual tests
+    property TEXT NOT NULL,
+    string TEXT NOT NULL,
+    expected TEXT NOT NULL
+);
+
+INSERT INTO tests (uuid, description, property, string, expected)
+VALUES
+        ('ad53b61b-6ffc-422f-81a6-61f7df92a231', 'empty string', 'encode', '', ''),
+        ('52012823-b7e6-4277-893c-5b96d42f82de', 'single characters only are encoded without count', 'encode', 'XYZ', 'XYZ'),
+        ('b7868492-7e3a-415f-8da3-d88f51f80409', 'string with no single characters', 'encode', 'AABBBCCCC', '2A3B4C'),
+        ('859b822b-6e9f-44d6-9c46-6091ee6ae358', 'single characters mixed with repeated characters', 'encode', 'WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB', '12WB12W3B24WB'),
+        ('1b34de62-e152-47be-bc88-469746df63b3', 'multiple whitespace mixed in string', 'encode', '  hsqq qww  ', '2 hs2q q2w2 '),
+        ('abf176e2-3fbd-40ad-bb2f-2dd6d4df721a', 'lowercase characters', 'encode', 'aabbbcccc', '2a3b4c'),
+        ('7ec5c390-f03c-4acf-ac29-5f65861cdeb5', 'empty string', 'decode', '', ''),
+        ('ad23f455-1ac2-4b0e-87d0-b85b10696098', 'single characters only', 'decode', 'XYZ', 'XYZ'),
+        ('21e37583-5a20-4a0e-826c-3dee2c375f54', 'string with no single characters', 'decode', '2A3B4C', 'AABBBCCCC'),
+        ('1389ad09-c3a8-4813-9324-99363fba429c', 'single characters with repeated characters', 'decode', '12WB12W3B24WB', 'WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB'),
+        ('3f8e3c51-6aca-4670-b86c-a213bf4706b0', 'multiple whitespace mixed in string', 'decode', '2 hs2q q2w2 ', '  hsqq qww  '),
+        ('29f721de-9aad-435f-ba37-7662df4fb551', 'lowercase string', 'decode', '2a3b4c', 'aabbbcccc'),
+        ('2a762efd-8695-4e04-b0d6-9736899fbc16', 'encode followed by decode gives original string', 'consistency', 'zzz ZZ  zZ', 'zzz ZZ  zZ');
+

exercises/practice/run-length-encoding/data.csv

@@ -0,0 +1,13 @@
+"encode","",
+"encode","XYZ",
+"encode","AABBBCCCC",
+"encode","WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB",
+"encode","  hsqq qww  ",
+"encode","aabbbcccc",
+"decode","",
+"decode","XYZ",
+"decode","2A3B4C",
+"decode","12WB12W3B24WB",
+"decode","2 hs2q q2w2 ",
+"decode","2a3b4c",
+"consistency","zzz ZZ  zZ",

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

@@ -0,0 +1,8 @@
+-- Schema:
+-- CREATE TABLE "run-length-encoding" (
+--     property TEXT NOT NULL,
+--     string   TEXT NOT NULL,
+--     result   TEXT
+-- );
+--
+-- Task: update the run-length-encoding table and set the result based on the property and string.

exercises/practice/run-length-encoding/run-length-encoding_test.sql

@@ -0,0 +1,43 @@
+-- Create database:
+.read ./create_fixture.sql
+
+-- Read user student solution and save any output as markdown in user_output.md:
+.mode markdown
+.output user_output.md
+.read ./run-length-encoding.sql
+.output
+
+-- Create a clean testing environment:
+.read ./create_test_table.sql
+
+-- Comparison of user input and the tests updates the status for each test:
+UPDATE tests
+   SET status = 'pass'
+  FROM (SELECT property, string, result FROM "run-length-encoding") AS actual
+ WHERE (actual.property, actual.string, actual.result)  =
+       ( tests.property,  tests.string,  tests.expected);
+
+-- Update message for failed tests to give helpful information:
+UPDATE tests
+   SET message = (
+     'Result for "'
+     || PRINTF('property=%s, string=%s', tests.property, tests.string)
+     || '"'
+     || ' is <' || COALESCE(actual.result, 'NULL')
+     || '> but should be <' || tests.expected || '>'
+   )
+  FROM (SELECT property, string, result FROM "run-length-encoding") AS actual
+ WHERE (actual.property, actual.string) =
+       ( tests.property,  tests.string)
+   AND tests.status = 'fail';
+
+-- Save results to ./output.json (needed by the online test-runner)
+.mode json
+.once './output.json'
+SELECT description, status, message, output, test_code, task_id
+FROM tests;
+
+-- Display test results in readable form for the student:
+.mode table
+SELECT description, status, message
+FROM tests;