From 7672ac945a7b8e35b600a9d2a2421caf16a5a364 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Zolt=C3=A1n=20K=C3=A9ri?= <z@zolk3ri.name>
Date: Tue, 24 Dec 2024 15:28:34 +0100
Subject: [PATCH] encoding/base32: Add RFC 4648 test suite

Add test suite based on RFC 4648 test vectors and validation rules:
- Add section 10 test vectors for valid encoding/decoding
- Add test cases for invalid character handling (section 3.2)
- Add test cases for padding validation (section 4)
- Add test cases for length requirements (section 6)

The test vectors verify that:
- Empty string encodes/decodes correctly
- Standard cases like "foo" -> "MZXW6===" work
- Invalid characters are rejected
- Missing or malformed padding is detected
- Invalid lengths are caught
---
 core/encoding/base32/base32.odin | 104 +++++++++++++++++++++++++++++++
 1 file changed, 104 insertions(+)

diff --git a/core/encoding/base32/base32.odin b/core/encoding/base32/base32.odin
index 8e3499dce..54737c9ce 100644
--- a/core/encoding/base32/base32.odin
+++ b/core/encoding/base32/base32.odin
@@ -1,5 +1,8 @@
 package encoding_base32
 
+import "core:testing"
+import "core:bytes"
+
 // @note(zh): Encoding utility for Base32
 // A secondary param can be used to supply a custom alphabet to
 // @link(encode) and a matching decoding table to @link(decode).
@@ -186,3 +189,104 @@ decode :: proc(data: string, DEC_TBL := DEC_TABLE, allocator := context.allocato
 
 	return out, .None
 }
+
+@(test)
+test_base32_decode_valid :: proc(t: ^testing.T) {
+	// RFC 4648 Section 10 - Test vectors
+	cases := [?]struct {
+		input, expected: string,
+	}{
+		{"", ""},
+		{"MY======", "f"},
+		{"MZXQ====", "fo"},
+		{"MZXW6===", "foo"},
+		{"MZXW6YQ=", "foob"},
+		{"MZXW6YTB", "fooba"},
+		{"MZXW6YTBOI======", "foobar"},
+	}
+
+
+	for c in cases {
+		output, err := decode(c.input)
+		testing.expect_value(t, err, Error.None)
+		expected := transmute([]u8)c.expected
+
+		if output != nil {
+			testing.expect(t, bytes.equal(output, expected))
+		} else {
+			testing.expect(t, len(c.expected) == 0)
+		}
+	}
+}
+
+@(test)
+test_base32_encode :: proc(t: ^testing.T) {
+	// RFC 4648 Section 10 - Test vectors
+	cases := [?]struct {
+		input, expected: string,
+	}{
+		{"", ""},
+		{"f", "MY======"},
+		{"fo", "MZXQ===="},
+		{"foo", "MZXW6==="},
+		{"foob", "MZXW6YQ="},
+		{"fooba", "MZXW6YTB"},
+		{"foobar", "MZXW6YTBOI======"},
+	}
+
+	for c in cases {
+		output := encode(transmute([]byte)c.input)
+		testing.expect(t, output == c.expected)
+	}
+}
+
+@(test)
+test_base32_decode_invalid :: proc(t: ^testing.T) {
+	// Section 3.2 - Alphabet check
+	{
+		// Characters outside alphabet
+		input := "MZ1W6YTB" // '1' not in alphabet (A-Z, 2-7)
+		_, err := decode(input)
+		testing.expect_value(t, err, Error.Invalid_Character)
+	}
+	{
+		// Lowercase not allowed
+		input := "mzxq===="
+		_, err := decode(input)
+		testing.expect_value(t, err, Error.Invalid_Character)
+	}
+
+	// Section 4 - Padding requirements
+	{
+		// Padding must only be at end
+		input := "MZ=Q===="
+		_, err := decode(input)
+		testing.expect_value(t, err, Error.Malformed_Input)
+	}
+	{
+		// Missing padding
+		input := "MZXQ" // Should be MZXQ====
+		_, err := decode(input)
+		testing.expect_value(t, err, Error.Malformed_Input)
+	}
+	{
+		// Incorrect padding length
+		input := "MZXQ=" // Needs 4 padding chars
+		_, err := decode(input)
+		testing.expect_value(t, err, Error.Malformed_Input)
+	}
+	{
+		// Too much padding
+		input := "MY=========" // Extra padding chars
+		_, err := decode(input)
+		testing.expect_value(t, err, Error.Malformed_Input)
+	}
+
+	// Section 6 - Block size requirements
+	{
+		// Single character (invalid block)
+		input := "M"
+		_, err := decode(input)
+		testing.expect_value(t, err, Error.Invalid_Length)
+	}
+}