word-count

config.json

@@ -422,6 +422,14 @@
         "practices": [],
         "prerequisites": [],
         "difficulty": 4
+      },
+      {
+        "slug": "word-count",
+        "name": "Word Count",
+        "uuid": "4b927a16-b0f2-4b71-980f-4d4f36288814",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 4
       }
     ]
   },

exercises/practice/word-count/.busted

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

exercises/practice/word-count/.docs/instructions.md

@@ -0,0 +1,47 @@
+# Instructions
+
+Your task is to count how many times each word occurs in a subtitle of a drama.
+
+The subtitles from these dramas use only ASCII characters.
+
+The characters often speak in casual English, using contractions like _they're_ or _it's_.
+Though these contractions come from two words (e.g. _we are_), the contraction (_we're_) is considered a single word.
+
+Words can be separated by any form of punctuation (e.g. ":", "!", or "?") or whitespace (e.g. "\t", "\n", or " ").
+The only punctuation that does not separate words is the apostrophe in contractions.
+
+Numbers are considered words.
+If the subtitles say _It costs 100 dollars._ then _100_ will be its own word.
+
+Words are case insensitive.
+For example, the word _you_ occurs three times in the following sentence:
+
+> You come back, you hear me? DO YOU HEAR ME?
+
+The ordering of the word counts in the results doesn't matter.
+
+Here's an example that incorporates several of the elements discussed above:
+
+- simple words
+- contractions
+- numbers
+- case insensitive words
+- punctuation (including apostrophes) to separate words
+- different forms of whitespace to separate words
+
+`"That's the password: 'PASSWORD 123'!", cried the Special Agent.\nSo I fled.`
+
+The mapping for this subtitle would be:
+
+```text
+123: 1
+agent: 1
+cried: 1
+fled: 1
+i: 1
+password: 2
+so: 1
+special: 1
+that's: 1
+the: 2
+```

exercises/practice/word-count/.docs/introduction.md

@@ -0,0 +1,8 @@
+# Introduction
+
+You teach English as a foreign language to high school students.
+
+You've decided to base your entire curriculum on TV shows.
+You need to analyze which words are used, and how often they're repeated.
+
+This will let you choose the simplest shows to start with, and to gradually increase the difficulty as time passes.

exercises/practice/word-count/.meta/config.json

@@ -0,0 +1,18 @@
+{
+  "authors": [
+    "glennj"
+  ],
+  "files": {
+    "solution": [
+      "word_count.moon"
+    ],
+    "test": [
+      "word_count_spec.moon"
+    ],
+    "example": [
+      ".meta/example.moon"
+    ]
+  },
+  "blurb": "Given a phrase, count the occurrences of each word in that phrase.",
+  "source": "This is a classic toy problem, but we were reminded of it by seeing it in the Go Tour."
+}

exercises/practice/word-count/.meta/example.moon

@@ -0,0 +1,10 @@
+trim = (str) -> str\gsub("^'+", '')\gsub("'+$", '')
+
+{
+  count_words: (sentence) ->
+    result = {}
+    for word in sentence\lower!\gmatch("[%w+']+")
+      w = trim word
+      result[w] = (result[w] or 0) + 1
+    result
+}

exercises/practice/word-count/.meta/spec_generator.moon

@@ -0,0 +1,39 @@
+json = require 'dkjson'
+
+kv_table = (tbl, level) ->
+  lines = {'{'}
+  for k, v in pairs tbl
+    key = if k\match('^%a%w*$') then k else "#{quote k}"
+    table.insert lines, indent "#{key}: #{v},", level + 1
+  table.insert lines, indent '}', level
+  table.concat lines, '\n'
+
+
+{
+  module_imports: {'count_words'},
+
+  test_helpers: [[
+  -- ----------------------------------------------------------
+  same_kv = (state, arguments) ->
+    expected = arguments[1]
+    actual = arguments[2]
+    return false if #expected != #actual
+    for k, v in pairs expected
+      return false if actual[k] != v
+    true
+
+  say = require 'say'
+  say\set 'assertion.same_kv.positive', 'Expected\n%s\nto have the same keys and values as\n%s'
+  say\set 'assertion.same_kv.negative', 'Expected\n%s\nto not have the same keys and values as\n%s'
+  assert\register 'assertion', 'same_kv', same_kv, 'assertion.same_kv.positive', 'assertion.same_kv.negative'
+  -- ----------------------------------------------------------
+]]
+
+  generate_test: (case, level) ->
+    lines = {
+      "result = count_words #{json.encode case.input.sentence}",
+      "expected = #{kv_table case.expected, level}",
+      "assert.has.same_kv expected, result"
+    }
+    table.concat [indent line, level for line in *lines], '\n'
+}

exercises/practice/word-count/.meta/tests.toml

@@ -0,0 +1,57 @@
+# 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.
+
+[61559d5f-2cad-48fb-af53-d3973a9ee9ef]
+description = "count one word"
+
+[5abd53a3-1aed-43a4-a15a-29f88c09cbbd]
+description = "count one of each word"
+
+[2a3091e5-952e-4099-9fac-8f85d9655c0e]
+description = "multiple occurrences of a word"
+
+[e81877ae-d4da-4af4-931c-d923cd621ca6]
+description = "handles cramped lists"
+
+[7349f682-9707-47c0-a9af-be56e1e7ff30]
+description = "handles expanded lists"
+
+[a514a0f2-8589-4279-8892-887f76a14c82]
+description = "ignore punctuation"
+
+[d2e5cee6-d2ec-497b-bdc9-3ebe092ce55e]
+description = "include numbers"
+
+[dac6bc6a-21ae-4954-945d-d7f716392dbf]
+description = "normalize case"
+
+[4185a902-bdb0-4074-864c-f416e42a0f19]
+description = "with apostrophes"
+include = false
+
+[4ff6c7d7-fcfc-43ef-b8e7-34ff1837a2d3]
+description = "with apostrophes"
+reimplements = "4185a902-bdb0-4074-864c-f416e42a0f19"
+
+[be72af2b-8afe-4337-b151-b297202e4a7b]
+description = "with quotations"
+
+[8d6815fe-8a51-4a65-96f9-2fb3f6dc6ed6]
+description = "substrings from the beginning"
+
+[c5f4ef26-f3f7-4725-b314-855c04fb4c13]
+description = "multiple spaces not detected as a word"
+
+[50176e8a-fe8e-4f4c-b6b6-aa9cf8f20360]
+description = "alternating word separators not detected as a word"
+
+[6d00f1db-901c-4bec-9829-d20eb3044557]
+description = "quotation for word with apostrophe"

exercises/practice/word-count/word_count.moon

@@ -0,0 +1,4 @@
+{
+  count_words: (sentence) ->
+    error 'Implement me'
+}

exercises/practice/word-count/word_count_spec.moon

@@ -0,0 +1,155 @@
+import count_words from require 'word_count'
+
+describe 'word-count', ->
+  -- ----------------------------------------------------------
+  same_kv = (state, arguments) ->
+    expected = arguments[1]
+    actual = arguments[2]
+    return false if #expected != #actual
+    for k, v in pairs expected
+      return false if actual[k] != v
+    true
+
+  say = require 'say'
+  say\set 'assertion.same_kv.positive', 'Expected\n%s\nto have the same keys and values as\n%s'
+  say\set 'assertion.same_kv.negative', 'Expected\n%s\nto not have the same keys and values as\n%s'
+  assert\register 'assertion', 'same_kv', same_kv, 'assertion.same_kv.positive', 'assertion.same_kv.negative'
+  -- ----------------------------------------------------------
+
+  it 'count one word', ->
+    result = count_words "word"
+    expected = {
+      word: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'count one of each word', ->
+    result = count_words "one of each"
+    expected = {
+      each: 1,
+      one: 1,
+      of: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'multiple occurrences of a word', ->
+    result = count_words "one fish two fish red fish blue fish"
+    expected = {
+      fish: 4,
+      blue: 1,
+      one: 1,
+      two: 1,
+      red: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'handles cramped lists', ->
+    result = count_words "one,two,three"
+    expected = {
+      two: 1,
+      one: 1,
+      three: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'handles expanded lists', ->
+    result = count_words "one,\ntwo,\nthree"
+    expected = {
+      two: 1,
+      one: 1,
+      three: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'ignore punctuation', ->
+    result = count_words "car: carpet as java: javascript!!&@$%^&"
+    expected = {
+      car: 1,
+      as: 1,
+      java: 1,
+      javascript: 1,
+      carpet: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'include numbers', ->
+    result = count_words "testing, 1, 2 testing"
+    expected = {
+      testing: 2,
+      '2': 1,
+      '1': 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'normalize case', ->
+    result = count_words "go Go GO Stop stop"
+    expected = {
+      go: 3,
+      stop: 2,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'with apostrophes', ->
+    result = count_words "'First: don't laugh. Then: don't cry. You're getting it.'"
+    expected = {
+      then: 1,
+      laugh: 1,
+      "don't": 2,
+      it: 1,
+      first: 1,
+      getting: 1,
+      "you're": 1,
+      cry: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'with quotations', ->
+    result = count_words "Joe can't tell between 'large' and large."
+    expected = {
+      joe: 1,
+      tell: 1,
+      large: 2,
+      and: 1,
+      between: 1,
+      "can't": 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'substrings from the beginning', ->
+    result = count_words "Joe can't tell between app, apple and a."
+    expected = {
+      a: 1,
+      and: 1,
+      joe: 1,
+      apple: 1,
+      tell: 1,
+      app: 1,
+      between: 1,
+      "can't": 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'multiple spaces not detected as a word', ->
+    result = count_words " multiple   whitespaces"
+    expected = {
+      multiple: 1,
+      whitespaces: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'alternating word separators not detected as a word', ->
+    result = count_words ",\n,one,\n ,two \n 'three'"
+    expected = {
+      two: 1,
+      one: 1,
+      three: 1,
+    }
+    assert.has.same_kv expected, result
+
+  pending 'quotation for word with apostrophe', ->
+    result = count_words "can, can't, 'can't'"
+    expected = {
+      "can't": 2,
+      can: 1,
+    }
+    assert.has.same_kv expected, result