Skip to content

Commit 42cf265

Browse files
alberk8alberk8
authored
Addtional UTF-8 unit tests (#237)
***NO_CI***
1 parent 952bd6b commit 42cf265

File tree

1 file changed

+266
-54
lines changed

1 file changed

+266
-54
lines changed

‎Tests/NFUnitTestStringBuilder/EncodingTests.cs

Lines changed: 266 additions & 54 deletions
Original file line numberDiff line numberDiff line change
@@ -10,58 +10,270 @@
1010

1111
namespace NFUnitTestStringBuilder
1212
{
13-
[TestClass]
14-
public class EncodingTests
15-
{
16-
[TestMethod]
17-
public void Utf8EncodingTests_Test1()
18-
{
19-
string str = "this is a normal string that will be used to convert to bytes then back to a string";
20-
21-
byte[] data = new byte[128];
22-
int len = str.Length;
23-
int idx = 0;
24-
25-
Random rand = new Random();
26-
27-
int cBytes = 0;
28-
29-
while (len > 0)
30-
{
31-
int size = (len <= 2) ? len : rand.Next(len / 2) + 1;
32-
len -= size;
33-
34-
int cnt = Encoding.UTF8.GetBytes(str, idx, size, data, cBytes);
35-
36-
Assert.AreEqual(str.Substring(idx, size), new string(Encoding.UTF8.GetChars(data, cBytes, cnt)));
37-
38-
cBytes += cnt;
39-
idx += size;
40-
}
41-
Assert.AreEqual(cBytes, str.Length);
42-
string strAfter = new string(Encoding.UTF8.GetChars(data, 0, cBytes));
43-
Assert.AreEqual(str, strAfter);
44-
}
45-
46-
[TestMethod]
47-
public void Utf8EncodingTests_Test2()
48-
{
49-
string str = "this is a normal string that will be used to convert to bytes then back to a string";
50-
byte[] data = Encoding.UTF8.GetBytes(str);
51-
Assert.AreEqual(data.Length, str.Length);
52-
string strAfter = new string(Encoding.UTF8.GetChars(data));
53-
Assert.AreEqual(str, strAfter);
54-
}
55-
56-
[TestMethod]
57-
public void Utf8EncodingTests_Test3()
58-
{
59-
// This tests involves a string with a special character
60-
string str = "AB\u010DAB";
61-
byte[] data = new byte[4];
62-
int count = Encoding.UTF8.GetBytes(str, 1, 3, data, 0);
63-
Assert.AreEqual(4, count);
64-
Assert.AreEqual("B\u010DA", new string(Encoding.UTF8.GetChars(data)));
65-
}
66-
}
13+
[TestClass]
14+
public class EncodingTests
15+
{
16+
[TestMethod]
17+
public void Utf8EncodingTests_Test1()
18+
{
19+
string str = "this is a normal string that will be used to convert to bytes then back to a string";
20+
21+
byte[] data = new byte[128];
22+
int len = str.Length;
23+
int idx = 0;
24+
25+
Random rand = new Random();
26+
27+
int cBytes = 0;
28+
29+
while (len > 0)
30+
{
31+
int size = (len <= 2) ? len : rand.Next(len / 2) + 1;
32+
len -= size;
33+
34+
int cnt = Encoding.UTF8.GetBytes(str, idx, size, data, cBytes);
35+
36+
Assert.AreEqual(str.Substring(idx, size), new string(Encoding.UTF8.GetChars(data, cBytes, cnt)));
37+
38+
cBytes += cnt;
39+
idx += size;
40+
}
41+
Assert.AreEqual(cBytes, str.Length);
42+
string strAfter = new string(Encoding.UTF8.GetChars(data, 0, cBytes));
43+
Assert.AreEqual(str, strAfter);
44+
}
45+
46+
[TestMethod]
47+
public void Utf8EncodingTests_Test2()
48+
{
49+
string str = "this is a normal string that will be used to convert to bytes then back to a string";
50+
byte[] data = Encoding.UTF8.GetBytes(str);
51+
Assert.AreEqual(data.Length, str.Length);
52+
string strAfter = new string(Encoding.UTF8.GetChars(data));
53+
Assert.AreEqual(str, strAfter);
54+
}
55+
56+
[TestMethod]
57+
public void Utf8EncodingTests_Test3()
58+
{
59+
// This tests involves a string with a special character
60+
string str = "AB\u010DAB";
61+
byte[] data = new byte[4];
62+
int count = Encoding.UTF8.GetBytes(str, 1, 3, data, 0);
63+
Assert.AreEqual(4, count);
64+
Assert.AreEqual("B\u010DA", new string(Encoding.UTF8.GetChars(data)));
65+
66+
}
67+
68+
private void RoundtripUtf8(byte[] input, byte[] expected, int expectedStringLength)
69+
{
70+
string decoded = Encoding.UTF8.GetString(input,0, input.Length);
71+
byte[] reencoded = Encoding.UTF8.GetBytes(decoded);
72+
Assert.AreEqual(expectedStringLength, decoded.Length);
73+
CollectionAssert.AreEqual(expected, reencoded, $"Failed on input: {BitConverter.ToString(input)}");
74+
}
75+
76+
[TestMethod]
77+
public void Utf8EncodingTests_TestValid2ByteSequence()
78+
{
79+
byte[] input = new byte[] { 0xC2, 0xA9 }; // U+00A9 ©
80+
byte[] expected = new byte[] { 0xC2, 0xA9 };
81+
RoundtripUtf8(input, expected, 1);
82+
}
83+
84+
[TestMethod]
85+
public void Utf8EncodingTests_TestValid3ByteSequence()
86+
{
87+
byte[] input = new byte[] { 0xE2, 0x82, 0xAC }; // U+20AC €
88+
byte[] expected = new byte[] { 0xE2, 0x82, 0xAC };
89+
RoundtripUtf8(input, expected, 1);
90+
}
91+
92+
[TestMethod]
93+
public void Utf8EncodingTests_TestValid4ByteSequence()
94+
{
95+
byte[] input = new byte[] { 0xF0, 0x9F, 0x98, 0x80 }; // U+1F600 😀
96+
byte[] expected = new byte[] { 0xF0, 0x9F, 0x98, 0x80 };
97+
RoundtripUtf8(input, expected, 2);
98+
}
99+
100+
101+
[TestMethod]
102+
public void Utf8EncodingTests_TestOverlongEncoding1()
103+
{
104+
// Should produce � (U+FFFD) for each bad byte pair
105+
byte[] input = new byte[] { 0xC0, 0xAF }; // Overlong '/'
106+
byte[] expected = new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD };
107+
RoundtripUtf8(input, expected, 2);
108+
}
109+
110+
[TestMethod]
111+
public void Utf8EncodingTests_TestOverlongEncoding2()
112+
{
113+
byte[] input = new byte[] { 0xE0, 0x80, 0xAF }; // Overlong '/'
114+
byte[] expected = new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD };
115+
RoundtripUtf8(input, expected, 3);
116+
}
117+
118+
[TestMethod]
119+
public void Utf8EncodingTests_TestInvalid3ByteLastByteInvalid()
120+
{
121+
byte[] input = new byte[] { 0xE2, 0x82, 0xFE }; // UTF-8 3 bytes, 0xFE is the invalid character
122+
byte[] expected = new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD };
123+
RoundtripUtf8(input, expected, 2);
124+
}
125+
126+
[TestMethod]
127+
public void Utf8EncodingTests_TestInvalid3ByteMiddleByteInvalid()
128+
{
129+
byte[] input = new byte[] { 0xE2, 0xFE, 0xAC }; // UTF-8 3 bytes, 0xFE is the invalid character
130+
byte[] expected = new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD };
131+
RoundtripUtf8(input, expected, 3);
132+
}
133+
134+
[TestMethod]
135+
public void Utf8EncodingTests_TestInvalid4ByteLastByteInvalid()
136+
{
137+
byte[] input = new byte[] { 0xF0, 0x9F, 0x98, 0xFE }; // UTF-8 4 bytes, 0xFE is the invalid character
138+
byte[] expected = new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD };
139+
RoundtripUtf8(input, expected, 2);
140+
}
141+
142+
// 0xF0, 0x9F, 0x98, 0x80
143+
[TestMethod]
144+
public void Utf8EncodingTests_TestInvalid4ByteThirdByteInvalid()
145+
{
146+
byte[] input = new byte[] { 0xF0, 0x9F, 0xFE, 0x80 }; // UTF-8 4 bytes, 0xFE is the invalid character
147+
byte[] expected = new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD };
148+
RoundtripUtf8(input, expected, 3);
149+
}
150+
151+
[TestMethod]
152+
public void Utf8EncodingTests_TestInvalid4ByteSecondByteInvalid()
153+
{
154+
byte[] input = new byte[] { 0xF0, 0xFE, 0x98, 0x80 }; // UTF-8 4 bytes, 0xFE is the invalid character
155+
byte[] expected = new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD };
156+
RoundtripUtf8(input, expected, 4);
157+
}
158+
159+
[TestMethod]
160+
public void Utf8EncodingTests_TestIsolatedContinuationByte()
161+
{
162+
byte[] input = new byte[] { 0x80 }; // Invalid lone continuation byte
163+
string decoded = Encoding.UTF8.GetString(input, 0, input.Length);
164+
byte[] reencoded = Encoding.UTF8.GetBytes(decoded);
165+
CollectionAssert.AreEqual(new byte[] { 0xEF, 0xBF, 0xBD }, reencoded);
166+
}
167+
168+
[TestMethod]
169+
public void Utf8EncodingTests_TestIllegalCodePositionSurrogate()
170+
{
171+
byte[] input = new byte[] { 0xED, 0xA0, 0x80 }; // U+D800 high surrogate
172+
string decoded = Encoding.UTF8.GetString(input, 0, input.Length);
173+
byte[] reencoded = Encoding.UTF8.GetBytes(decoded);
174+
CollectionAssert.AreEqual(new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD }, reencoded);
175+
}
176+
177+
[TestMethod]
178+
public void Utf8EncodingTests_TestMaximumValidCodepoint()
179+
{
180+
byte[] input = new byte[] { 0xF4, 0x8F, 0xBF, 0xBF }; // U+10FFFF
181+
byte[] expected = new byte[] { 0xF4, 0x8F, 0xBF, 0xBF };
182+
string decoded = Encoding.UTF8.GetString(input, 0, input.Length);
183+
RoundtripUtf8(input, expected, 2);
184+
}
185+
186+
[TestMethod]
187+
public void Utf8EncodingTests_TestCodepointBeyondUPlus10FFFF()
188+
{
189+
byte[] input = new byte[] { 0xF4, 0x90, 0x80, 0x80 }; // > U+10FFFF
190+
string decoded = Encoding.UTF8.GetString(input, 0, input.Length);
191+
byte[] reencoded = Encoding.UTF8.GetBytes(decoded);
192+
// All 4 bytes become one or two � depending on how it was handled
193+
CollectionAssert.AreEqual(
194+
new byte[] { 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD }, reencoded);
195+
}
196+
197+
[TestMethod]
198+
public void Utf8EncodingTests_TestUnexpectedContinuationSequence()
199+
{
200+
byte[] input = new byte[] { 0xC2, 0x41 }; // Valid 0xC2 (start of 2-byte), but 0x41 (A) not valid continuation
201+
string decoded = Encoding.UTF8.GetString(input, 0, input.Length);
202+
byte[] reencoded = Encoding.UTF8.GetBytes(decoded);
203+
// Expect: �A
204+
CollectionAssert.AreEqual(new byte[] { 0xEF, 0xBF, 0xBD, 0x41 }, reencoded);
205+
}
206+
207+
[TestMethod]
208+
public void Utf8EncodingTests_TestASCII()
209+
{
210+
byte[] input = new byte[] { 0x47, 0x6F, 0x6F, 0x64 }; // "Good"
211+
byte[] expected = new byte[] { 0x47, 0x6F, 0x6F, 0x64 };
212+
RoundtripUtf8(input, expected, 4);
213+
}
214+
215+
[TestMethod]
216+
public void Utf8EncodingTests_TestASCIIWithInvalidByte()
217+
{
218+
byte[] input = new byte[] { 0x42, 0x41, 0x44, 0xEF, 0xFF }; // BAD��
219+
byte[] expected = new byte[] { 0x42, 0x41, 0x44, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD };
220+
RoundtripUtf8(input, expected, 5);
221+
}
222+
223+
[TestMethod]
224+
public void Utf8EncodingTests_TestASCIIWithInvalidByteInBetween()
225+
{
226+
byte[] input = new byte[] { 0x42, 0x41, 0x44, 0xEF, 0xFF, 0x42, 0x41, 0x44 }; // BAD��BAD
227+
byte[] expected = new byte[] { 0x42, 0x41, 0x44, 0xEF, 0xBF, 0xBD, 0xEF, 0xBF, 0xBD, 0x42, 0x41, 0x44 };
228+
RoundtripUtf8(input, expected, 8);
229+
}
230+
231+
[TestMethod]
232+
public void Utf8EncodingTests_TestASCIIWithNull()
233+
{
234+
// All characters will be dropped after the null character in nanoFramework
235+
byte[] input = new byte[] { 0x54, 0x65, 0x73, 0x74, 0x20, 0x6E, 0x75, 0x6C, 0x6C, 0x00,
236+
0x61, 0x66, 0x74, 0x65, 0x72, 0x20, 0x6E, 0x75, 0x6C, 0x6C }; // Test null\0after null
237+
byte[] expected = new byte[] { 0x54, 0x65, 0x73, 0x74, 0x20, 0x6E, 0x75, 0x6C, 0x6C };
238+
RoundtripUtf8(input, expected, 9);
239+
}
240+
241+
[TestMethod]
242+
public void Utf8EncodingTests_TestStringWithEmoji()
243+
{
244+
string strInput = "nanoFramework is fantastic 🚀";
245+
var input = Encoding.UTF8.GetBytes(strInput);
246+
byte[] expected = new byte[] { 0x6E, 0x61, 0x6E, 0x6F, 0x46, 0x72, 0x61, 0x6D, 0x65, 0x77, 0x6F, 0x72, 0x6B, 0x20, 0x69,
247+
0x73, 0x20, 0x66, 0x61, 0x6E, 0x74, 0x61, 0x73, 0x74, 0x69, 0x63, 0x20, 0xF0, 0x9F, 0x9A, 0x80 };
248+
RoundtripUtf8(input, expected, 29);
249+
}
250+
251+
[TestMethod]
252+
public void Utf8EncodingTests_TestFullASCIIRange()
253+
{
254+
// Full ASCII Range except the null character
255+
byte[] input = new byte[]
256+
{
257+
0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
258+
0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
259+
0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
260+
0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
261+
0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
262+
0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
263+
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
264+
0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
265+
0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
266+
0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
267+
0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
268+
0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
269+
0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
270+
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
271+
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
272+
0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F
273+
};
274+
string decoded = Encoding.UTF8.GetString(input, 0, input.Length);
275+
byte[] reencoded = Encoding.UTF8.GetBytes(decoded);
276+
RoundtripUtf8(reencoded, input, 127);
277+
}
278+
}
67279
}

0 commit comments

Comments
 (0)