diff --git a/config.json b/config.json index 1cef0981..49a84d16 100644 --- a/config.json +++ b/config.json @@ -768,6 +768,14 @@ "practices": [], "prerequisites": [], "difficulty": 3 + }, + { + "slug": "run-length-encoding", + "name": "Run-Length Encoding", + "uuid": "e39b5e8b-cd91-4adf-bb1e-015367ef4f8c", + "practices": [], + "prerequisites": [], + "difficulty": 4 } ] }, diff --git a/exercises/practice/run-length-encoding/.docs/instructions.md b/exercises/practice/run-length-encoding/.docs/instructions.md new file mode 100644 index 00000000..fc8ce056 --- /dev/null +++ b/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. diff --git a/exercises/practice/run-length-encoding/.meta/config.json b/exercises/practice/run-length-encoding/.meta/config.json new file mode 100644 index 00000000..4b798261 --- /dev/null +++ b/exercises/practice/run-length-encoding/.meta/config.json @@ -0,0 +1,19 @@ +{ + "authors": [ + "erikschierboom" + ], + "files": { + "solution": [ + "run-length-encoding.R" + ], + "test": [ + "test_run-length-encoding.R" + ], + "example": [ + ".meta/example.R" + ] + }, + "blurb": "Implement run-length encoding and decoding.", + "source": "Wikipedia", + "source_url": "https://en.wikipedia.org/wiki/Run-length_encoding" +} diff --git a/exercises/practice/run-length-encoding/.meta/example.R b/exercises/practice/run-length-encoding/.meta/example.R new file mode 100644 index 00000000..935260c0 --- /dev/null +++ b/exercises/practice/run-length-encoding/.meta/example.R @@ -0,0 +1,22 @@ +library(stringr) + +encode <- function(plaintext) { + runs <- str_match_all(plaintext, "(.)\\1*")[[1]] + apply(runs, 1, encode_run) |> paste0(collapse = "") +} + +encode_run <- function(run) { + num_chars <- nchar(run[1]) + prefix <- ifelse(num_chars == 1, "", num_chars |> as.character()) + paste(prefix, run[2], sep = "") +} + +decode <- function(ciphertext) { + runs <- str_match_all(ciphertext, "(\\d+)?(.)")[[1]] + apply(runs, 1, decode_run) |> paste0(collapse = "") +} + +decode_run <- function(run) { + count <- ifelse(is.na(run[2]), 1, run[2] |> as.numeric()) + str_dup(run[3], count) +} diff --git a/exercises/practice/run-length-encoding/.meta/tests.toml b/exercises/practice/run-length-encoding/.meta/tests.toml new file mode 100644 index 00000000..7bdb8086 --- /dev/null +++ b/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" diff --git a/exercises/practice/run-length-encoding/run-length-encoding.R b/exercises/practice/run-length-encoding/run-length-encoding.R new file mode 100644 index 00000000..42ec9373 --- /dev/null +++ b/exercises/practice/run-length-encoding/run-length-encoding.R @@ -0,0 +1,7 @@ +encode <- function(plaintext) { + +} + +decode <- function(ciphertext) { + +} diff --git a/exercises/practice/run-length-encoding/test_run-length-encoding.R b/exercises/practice/run-length-encoding/test_run-length-encoding.R new file mode 100644 index 00000000..36f8af86 --- /dev/null +++ b/exercises/practice/run-length-encoding/test_run-length-encoding.R @@ -0,0 +1,60 @@ +source("./run-length-encoding.R") +library(testthat) + +test_that("Encode empty string", { + expect_equal(encode(""), "") +}) + +test_that("Encode single characters only are encoded without count", { + expect_equal(encode("XYZ"), "XYZ") +}) + +test_that("Encode string with no single characters", { + expect_equal(encode("AABBBCCCC"), "2A3B4C") +}) + +test_that("Encode single characters mixed with repeated characters", { + expect_equal( + encode("WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB"), + "12WB12W3B24WB" + ) +}) + +test_that("Encode multiple whitespace mixed in string", { + expect_equal(encode(" hsqq qww "), "2 hs2q q2w2 ") +}) + +test_that("Encode lowercase characters", { + expect_equal(encode("aabbbcccc"), "2a3b4c") +}) + +test_that("Decode empty string", { + expect_equal(decode(""), "") +}) + +test_that("Decode single characters only", { + expect_equal(decode("XYZ"), "XYZ") +}) + +test_that("Decode string with no single characters", { + expect_equal(decode("2A3B4C"), "AABBBCCCC") +}) + +test_that("Decode single characters with repeated characters", { + expect_equal( + decode("12WB12W3B24WB"), + "WWWWWWWWWWWWBWWWWWWWWWWWWBBBWWWWWWWWWWWWWWWWWWWWWWWWB" + ) +}) + +test_that("Decode multiple whitespace mixed in string", { + expect_equal(decode("2 hs2q q2w2 "), " hsqq qww ") +}) + +test_that("Decode lowercase string", { + expect_equal(decode("2a3b4c"), "aabbbcccc") +}) + +test_that("Encode followed by decode gives original string", { + expect_equal("zzz ZZ zZ" |> encode() |> decode(), "zzz ZZ zZ") +})