Sync exercise word-count with problem spec

new tests found a bug in the example solution with apostrophe handling

Author: senekor

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

@@ -6,8 +6,8 @@ pub fn word_count(input: &str) -> HashMap<String, u32> {
     let slice: &str = lower.as_ref();
     for word in slice
         .split(|c: char| !c.is_alphanumeric() && c != '\'')
-        .filter(|s| !s.is_empty())
         .map(|s| s.trim_matches('\''))
+        .filter(|s| !s.is_empty())
     {
         *map.entry(word.to_string()).or_insert(0) += 1;
     }

exercises/practice/word-count/.meta/test_template.tera

@@ -0,0 +1,27 @@
+use std::collections::HashMap;
+
+fn check_word_count(mut output: HashMap<String, u32>, pairs: &[(&str, u32)]) {
+    // The reason for the awkward code in here is to ensure that the failure
+    // message for assert_eq! is as informative as possible. A simpler
+    // solution would simply check the length of the map, and then
+    // check for the presence and value of each key in the given pairs vector.
+    for &(k, v) in pairs.iter() {
+        assert_eq!((k, output.remove(&k.to_string()).unwrap_or(0)), (k, v));
+    }
+    // may fail with a message that clearly shows all extra pairs in the map
+    assert_eq!(output.iter().collect::<Vec<(&String, &u32)>>(), vec![]);
+}
+{% for test in cases %}
+#[test]
+{% if loop.index != 1 -%}
+#[ignore]
+{% endif -%}
+fn {{ test.description | slugify | replace(from="-", to="_") }}() {
+    let input = {{ test.input.sentence | json_encode() }};
+    let output = {{ crate_name }}::{{ fn_names[0] }}(input);
+    let expected = &[{% for key, value in test.expected -%}
+        ({{ key | json_encode() }}, {{ value }}),
+    {%- endfor %}];
+    check_word_count(output, expected);
+}
+{% endfor -%}

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

@@ -1,12 +1,57 @@
-# This is an auto-generated file. Regular comments will be removed when this
-# file is regenerated. Regenerating will not touch any manually added keys,
-# so comments can be added in a "comment" key.
+# 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/src/lib.rs

@@ -1,6 +1,15 @@
 use std::collections::HashMap;
 
-/// Count occurrences of words.
-pub fn word_count(words: &str) -> HashMap<String, u32> {
-    todo!("Count of occurrences of words in {words:?}");
+pub fn word_count(input: &str) -> HashMap<String, u32> {
+    let mut map: HashMap<String, u32> = HashMap::new();
+    let lower = input.to_lowercase();
+    let slice: &str = lower.as_ref();
+    for word in slice
+        .split(|c: char| !c.is_alphanumeric() && c != '\'')
+        .map(|s| s.trim_matches('\''))
+        .filter(|s| !s.is_empty())
+    {
+        *map.entry(word.to_string()).or_insert(0) += 1;
+    }
+    map
 }

exercises/practice/word-count/tests/word-count.rs

@@ -1,116 +1,169 @@
 use std::collections::HashMap;
 
-fn check_word_count(s: &str, pairs: &[(&str, u32)]) {
+fn check_word_count(mut output: HashMap<String, u32>, pairs: &[(&str, u32)]) {
     // The reason for the awkward code in here is to ensure that the failure
     // message for assert_eq! is as informative as possible. A simpler
     // solution would simply check the length of the map, and then
     // check for the presence and value of each key in the given pairs vector.
-    let mut m: HashMap<String, u32> = word_count::word_count(s);
     for &(k, v) in pairs.iter() {
-        assert_eq!((k, m.remove(&k.to_string()).unwrap_or(0)), (k, v));
+        assert_eq!((k, output.remove(&k.to_string()).unwrap_or(0)), (k, v));
     }
     // may fail with a message that clearly shows all extra pairs in the map
-    assert_eq!(m.iter().collect::<Vec<(&String, &u32)>>(), vec![]);
+    assert_eq!(output.iter().collect::<Vec<(&String, &u32)>>(), vec![]);
 }
 
 #[test]
 fn count_one_word() {
-    check_word_count("word", &[("word", 1)]);
+    let input = "word";
+    let output = word_count::word_count(input);
+    let expected = &[("word", 1)];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
-fn count_one_of_each() {
-    check_word_count("one of each", &[("one", 1), ("of", 1), ("each", 1)]);
+fn count_one_of_each_word() {
+    let input = "one of each";
+    let output = word_count::word_count(input);
+    let expected = &[("one", 1), ("of", 1), ("each", 1)];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
-fn count_multiple_occurrences() {
-    check_word_count(
-        "one fish two fish red fish blue fish",
-        &[("one", 1), ("fish", 4), ("two", 1), ("red", 1), ("blue", 1)],
-    );
+fn multiple_occurrences_of_a_word() {
+    let input = "one fish two fish red fish blue fish";
+    let output = word_count::word_count(input);
+    let expected = &[("one", 1), ("fish", 4), ("two", 1), ("red", 1), ("blue", 1)];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
-fn cramped_lists() {
-    check_word_count("one,two,three", &[("one", 1), ("two", 1), ("three", 1)]);
+fn handles_cramped_lists() {
+    let input = "one,two,three";
+    let output = word_count::word_count(input);
+    let expected = &[("one", 1), ("two", 1), ("three", 1)];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
-fn expanded_lists() {
-    check_word_count("one\ntwo\nthree", &[("one", 1), ("two", 1), ("three", 1)]);
+fn handles_expanded_lists() {
+    let input = "one,\ntwo,\nthree";
+    let output = word_count::word_count(input);
+    let expected = &[("one", 1), ("two", 1), ("three", 1)];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
 fn ignore_punctuation() {
-    check_word_count(
-        "car : carpet as java : javascript!!&@$%^&",
-        &[
-            ("car", 1),
-            ("carpet", 1),
-            ("as", 1),
-            ("java", 1),
-            ("javascript", 1),
-        ],
-    );
+    let input = "car: carpet as java: javascript!!&@$%^&";
+    let output = word_count::word_count(input);
+    let expected = &[
+        ("car", 1),
+        ("carpet", 1),
+        ("as", 1),
+        ("java", 1),
+        ("javascript", 1),
+    ];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
 fn include_numbers() {
-    check_word_count(
-        "testing, 1, 2 testing",
-        &[("testing", 2), ("1", 1), ("2", 1)],
-    );
+    let input = "testing, 1, 2 testing";
+    let output = word_count::word_count(input);
+    let expected = &[("testing", 2), ("1", 1), ("2", 1)];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
 fn normalize_case() {
-    check_word_count("go Go GO Stop stop", &[("go", 3), ("stop", 2)]);
+    let input = "go Go GO Stop stop";
+    let output = word_count::word_count(input);
+    let expected = &[("go", 3), ("stop", 2)];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
 fn with_apostrophes() {
-    check_word_count(
-        "First: don't laugh. Then: don't cry.",
-        &[
-            ("first", 1),
-            ("don't", 2),
-            ("laugh", 1),
-            ("then", 1),
-            ("cry", 1),
-        ],
-    );
+    let input = "'First: don't laugh. Then: don't cry. You're getting it.'";
+    let output = word_count::word_count(input);
+    let expected = &[
+        ("first", 1),
+        ("don't", 2),
+        ("laugh", 1),
+        ("then", 1),
+        ("cry", 1),
+        ("you're", 1),
+        ("getting", 1),
+        ("it", 1),
+    ];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
 fn with_quotations() {
-    check_word_count(
-        "Joe can't tell between 'large' and large.",
-        &[
-            ("joe", 1),
-            ("can't", 1),
-            ("tell", 1),
-            ("between", 1),
-            ("large", 2),
-            ("and", 1),
-        ],
-    );
+    let input = "Joe can't tell between 'large' and large.";
+    let output = word_count::word_count(input);
+    let expected = &[
+        ("joe", 1),
+        ("can't", 1),
+        ("tell", 1),
+        ("between", 1),
+        ("large", 2),
+        ("and", 1),
+    ];
+    check_word_count(output, expected);
+}
+
+#[test]
+#[ignore]
+fn substrings_from_the_beginning() {
+    let input = "Joe can't tell between app, apple and a.";
+    let output = word_count::word_count(input);
+    let expected = &[
+        ("joe", 1),
+        ("can't", 1),
+        ("tell", 1),
+        ("between", 1),
+        ("app", 1),
+        ("apple", 1),
+        ("and", 1),
+        ("a", 1),
+    ];
+    check_word_count(output, expected);
 }
 
 #[test]
 #[ignore]
 fn multiple_spaces_not_detected_as_a_word() {
-    check_word_count(
-        " multiple   whitespaces",
-        &[("multiple", 1), ("whitespaces", 1)],
-    );
+    let input = " multiple   whitespaces";
+    let output = word_count::word_count(input);
+    let expected = &[("multiple", 1), ("whitespaces", 1)];
+    check_word_count(output, expected);
+}
+
+#[test]
+#[ignore]
+fn alternating_word_separators_not_detected_as_a_word() {
+    let input = ",\n,one,\n ,two \n 'three'";
+    let output = word_count::word_count(input);
+    let expected = &[("one", 1), ("two", 1), ("three", 1)];
+    check_word_count(output, expected);
+}
+
+#[test]
+#[ignore]
+fn quotation_for_word_with_apostrophe() {
+    let input = "can, can't, 'can't'";
+    let output = word_count::word_count(input);
+    let expected = &[("can", 1), ("can't", 2)];
+    check_word_count(output, expected);
 }