public void WriteUnicodeStringAndCharsWithVaryingSegmentSizes(char singleChar, int segmentSize) { const string testString = "aいbろ"; const int iterations = 10; var testBufferWriter = new TestMemoryBufferWriter(segmentSize); var sb = new StringBuilder(); using (var textWriter = new Utf8BufferTextWriter()) { textWriter.SetWriter(testBufferWriter); for (int i = 0; i < iterations; i++) { textWriter.Write(singleChar); textWriter.Write(testString); textWriter.Write(singleChar); sb.Append(singleChar); sb.Append(testString); sb.Append(singleChar); } } var expected = sb.ToString(); var data = testBufferWriter.ToArray(); var result = Encoding.UTF8.GetString(data); Assert.Equal(expected, result); }
private void WriteMultiByteCharactersToSmallBuffers() { // Test string breakdown (char => UTF-8 hex values): // a => 61 // い => E3-81-84 // b => 62 // ろ => E3-82-8D // c => 63 // d => 64 // は => E3-81-AF // に => E3-81-AB // e => 65 // ほ => E3-81-BB // f => 66 // へ => E3-81-B8 // ど => E3-81-A9 // g => 67 // h => 68 // i => 69 // \uD800\uDC00 => F0-90-80-80 (this is a surrogate pair that is represented as a single 4-byte UTF-8 encoding) const string testString = "aいbろcdはにeほfへどghi\uD800\uDC00"; // By mixing single byte and multi-byte characters, we know that there will // be spaces in the active segment that cannot fit the current character. This // means we'll be testing the GetMemory(minimumSize) logic. var bufferWriter = new TestMemoryBufferWriter(segmentSize: 5); var writer = new Utf8BufferTextWriter(); writer.SetWriter(bufferWriter); writer.Write(testString); writer.Flush(); // Verify the output var allSegments = bufferWriter.GetSegments().Select(s => s.ToArray()).ToArray(); Assert.Collection(allSegments, seg => Assert.Equal(new byte[] { 0x61, 0xE3, 0x81, 0x84, 0x62 }, seg), // "aいb" seg => Assert.Equal(new byte[] { 0xE3, 0x82, 0x8D, 0x63, 0x64 }, seg), // "ろcd" seg => Assert.Equal(new byte[] { 0xE3, 0x81, 0xAF }, seg), // "は" seg => Assert.Equal(new byte[] { 0xE3, 0x81, 0xAB, 0x65 }, seg), // "にe" seg => Assert.Equal(new byte[] { 0xE3, 0x81, 0xBB, 0x66 }, seg), // "ほf" seg => Assert.Equal(new byte[] { 0xE3, 0x81, 0xB8 }, seg), // "へ" seg => Assert.Equal(new byte[] { 0xE3, 0x81, 0xA9, 0x67, 0x68 }, seg), // "どgh" seg => Assert.Equal(new byte[] { 0x69, 0xF0, 0x90, 0x80, 0x80 }, seg)); // "i\uD800\uDC00" Assert.Equal(testString, Encoding.UTF8.GetString(bufferWriter.ToArray())); }
public void GetAndReturnCachedBufferTextWriter() { var bufferWriter1 = new TestMemoryBufferWriter(); var textWriter1 = Utf8BufferTextWriter.Get(bufferWriter1); textWriter1.Write("Hello"); textWriter1.Flush(); Utf8BufferTextWriter.Return(textWriter1); Assert.Equal("Hello", Encoding.UTF8.GetString(bufferWriter1.ToArray())); var bufferWriter2 = new TestMemoryBufferWriter(); var textWriter2 = Utf8BufferTextWriter.Get(bufferWriter2); textWriter2.Write("World"); textWriter2.Flush(); Utf8BufferTextWriter.Return(textWriter2); Assert.Equal("World", Encoding.UTF8.GetString(bufferWriter2.ToArray())); Assert.Same(textWriter1, textWriter2); }