AK: Implement `slugify` function for URL slug generation

The slugify function is used to convert input into URL-friendly slugs.
It processes each character in the input, keeping ascii alpha characters
after lowercase and replacing non-alphanum characters with the glue
character or a space if multiple spaces are encountered consecutively.
The resulting string is trimmed of leading and trailing whitespace, and
any internal whitespace is replaced with the glue character.

It is currently used in LibMarkdown headings generation code.

AK/CMakeLists.txt

@@ -24,6 +24,7 @@ set(AK_SOURCES
     OptionParser.cpp
     Random.cpp
     SipHash.cpp
+    Slugify.cpp
     StackInfo.cpp
     Stream.cpp
     String.cpp

AK/Slugify.cpp

@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2023, Gurkirat Singh <tbhaxor@gmail.com>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#include <AK/CharacterTypes.h>
+#include <AK/Slugify.h>
+#include <AK/StringView.h>
+
+namespace AK {
+ErrorOr<String> slugify(String const& input, char const glue)
+{
+    StringBuilder sb;
+    bool just_processed_space = false;
+
+    for (auto const& code_point : input.code_points()) {
+        if (is_ascii_alphanumeric(code_point)) {
+            sb.append_code_point(to_ascii_lowercase(code_point));
+            just_processed_space = false;
+        } else if ((code_point == static_cast<u32>(glue) || is_ascii_space(code_point)) && !just_processed_space) {
+            sb.append_code_point(glue);
+            just_processed_space = true;
+        }
+    }
+
+    auto output = TRY(sb.to_string());
+    if (output.ends_with(static_cast<u32>(glue))) {
+        return output.trim(StringView { &glue, 1 }, TrimMode::Right);
+    }
+    return output;
+}
+}

AK/Slugify.h

@@ -0,0 +1,17 @@
+/*
+ * Copyright (c) 2023, Gurkirat Singh <tbhaxor@gmail.com>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#pragma once
+
+#include <AK/String.h>
+
+namespace AK {
+ErrorOr<String> slugify(String const& input, char glue = '-');
+}
+
+#if USING_AK_GLOBALLY
+using AK::slugify;
+#endif

Tests/AK/CMakeLists.txt

@@ -65,6 +65,7 @@ set(AK_TEST_SOURCES
     TestRefPtr.cpp
     TestSIMD.cpp
     TestSinglyLinkedList.cpp
+    TestSlugify.cpp
     TestSourceGenerator.cpp
     TestSourceLocation.cpp
     TestSpan.cpp

Tests/AK/TestSlugify.cpp

@@ -0,0 +1,43 @@
+/*
+ * Copyright (c) 2023, Gurkirat Singh <tbhaxor@gmail.com>
+ *
+ * SPDX-License-Identifier: BSD-2-Clause
+ */
+
+#include <AK/Slugify.h>
+#include <LibTest/TestCase.h>
+
+TEST_CASE(ignore_unicode_characters)
+{
+    EXPECT_EQ(MUST(slugify("Hello World!🎉"_string)), "hello-world"_string);
+}
+
+TEST_CASE(all_whitespace_empty_string)
+{
+    EXPECT_EQ(MUST(slugify("  "_string)), ""_string);
+}
+
+TEST_CASE(squeeze_multiple_whitespace)
+{
+    EXPECT_EQ(MUST(slugify("Hello   World"_string)), "hello-world"_string);
+}
+
+TEST_CASE(trim_trailing_whitelist)
+{
+    EXPECT_EQ(MUST(slugify("Hello   World    "_string)), "hello-world"_string);
+}
+
+TEST_CASE(lowercase_all_result)
+{
+    EXPECT_EQ(MUST(slugify("HelloWorld"_string)), "helloworld"_string);
+}
+
+TEST_CASE(slug_glue_change)
+{
+    EXPECT_EQ(MUST(slugify("Hello World"_string, '|')), "hello|world"_string);
+}
+
+TEST_CASE(multiple_glue_squeeze)
+{
+    EXPECT_EQ(MUST(slugify("Hello_ World"_string, '_')), "hello_world"_string);
+}