Word Count

config.json

@@ -820,6 +820,14 @@
         "prerequisites": [],
         "difficulty": 4
       },
+      {
+        "slug": "word-count",
+        "name": "Word Count",
+        "uuid": "5fded933-439a-4faa-bfb6-18ec7b7c8469",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 4
+      },
       {
         "slug": "binary-search-tree",
         "name": "Binary Search Tree",

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 +1,21 @@
+{
+  "authors": [
+    "Ephraim-nonso"
+  ],
+  "files": {
+    "solution": [
+      "src/lib.cairo"
+    ],
+    "test": [
+      "tests/word_count.cairo"
+    ],
+    "example": [
+      ".meta/example.cairo"
+    ],
+    "invalidator": [
+      "Scarb.toml"
+    ]
+  },
+  "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.cairo

@@ -0,0 +1,104 @@
+#[derive(Debug, PartialEq, Clone, Drop)]
+pub struct WordResult {
+    pub word: ByteArray,
+    pub count: u64,
+}
+
+pub fn count_words(phrase: ByteArray) -> Span<WordResult> {
+    let mut results: Array<WordResult> = ArrayTrait::new();
+    let words = split_phrase_into_words(phrase);
+
+    let mut i = 0;
+    while i < words.len() {
+        let mut found = false;
+
+        let mut j = 0;
+        while j < results.len() {
+            if results[j].word == words[i] {
+                let updated_result = WordResult {
+                    word: results[j].word.clone(), count: *results[j].count + 1,
+                };
+
+                results = remove_index_from_array(results, j);
+                results.append(updated_result);
+                found = true;
+                break;
+            }
+            j += 1;
+        };
+
+        if !found {
+            let word_and_count = WordResult { word: words[i].clone(), count: 1 };
+            results.append(word_and_count);
+        }
+
+        i += 1;
+    };
+
+    results.span()
+}
+
+fn remove_index_from_array(arr: Array<WordResult>, index: u32) -> Array<WordResult> {
+    let mut new_arr: Array<WordResult> = ArrayTrait::new();
+
+    let mut i = 0;
+    while i < arr.len() {
+        if i != index {
+            new_arr.append(arr[i].clone());
+        }
+        i += 1;
+    };
+
+    new_arr
+}
+
+fn split_phrase_into_words(phrase: ByteArray) -> Array<ByteArray> {
+    let mut words: Array<ByteArray> = ArrayTrait::new();
+    let mut current_word = "";
+
+    let mut i = 0;
+    while i < phrase.len() {
+        let lower_case = to_lowercase(phrase[i]);
+
+        if is_alphanumeric_or_apostrophe(lower_case) {
+            if !is_apostrophe(lower_case)
+                || (i > 0 && i < phrase.len()
+                    - 1
+                        && is_alphanumeric_or_apostrophe(phrase[i - 1])
+                        && is_alphanumeric_or_apostrophe(phrase[i + 1])) {
+                current_word.append_byte(lower_case);
+            }
+        } else if current_word.len() > 0 {
+            words.append(current_word.clone());
+            current_word = "";
+        }
+
+        i += 1;
+    };
+
+    if current_word.len() > 0 {
+        words.append(current_word);
+    }
+
+    words
+}
+
+fn is_alphanumeric_or_apostrophe(ch: u8) -> bool {
+    is_alphanumeric(ch) || is_apostrophe(ch)
+}
+
+fn is_alphanumeric(ch: u8) -> bool {
+    ('0' <= ch && ch <= '9') || ('a' <= ch && ch <= 'z') || ('A' <= ch && ch <= 'Z')
+}
+
+fn is_apostrophe(ch: u8) -> bool {
+    ch == '\''
+}
+
+fn to_lowercase(ch: u8) -> u8 {
+    if 'A' <= ch && ch <= 'Z' {
+        ch + 32
+    } else {
+        ch
+    }
+}

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/Scarb.toml

@@ -0,0 +1,7 @@
+[package]
+name = "word_count"
+version = "0.1.0"
+edition = "2024_07"
+
+[dev-dependencies]
+cairo_test = "2.8.2"

exercises/practice/word-count/src/lib.cairo

@@ -0,0 +1,9 @@
+#[derive(Debug, PartialEq, Clone, Drop)]
+pub struct WordResult {
+    pub word: ByteArray,
+    pub count: u64,
+}
+
+pub fn count_words(phrase: ByteArray) -> Span<WordResult> {
+    panic!("implement `count_words`")
+}