Examples of org.auraframework.util.Utf8InputStreamReader

org.auraframework.util.Utf8InputStreamReader
A minimal InputStreamReader implementation that reads only what it needs from the wrapped InputStream and not a byte more. Java's built-in InputStreamReader can read ahead, but that doesn't play well with use cases that mix binary and text data in one stream, so this InputStreamReader variant was created.

Note that its original user, JsonStreamReader, reads only one character at a time, so that is how this implementation is optimized. This can be updated if other use cases come along. At the very least, this InputStreamReader does intelligently handle the first byte in a UTF-8 character by bulk-reading the remaining bytes based on the character length, which is encoded into the first byte in a UTF-8 character. Another optimization is having one-byte UTF-8 characters bypass the CharsetDecoder.

This Reader assumes that characters in the InputStream are all UTF-8. Byte order mark (BOM) characters encoded as UTF-8 are dropped, since their presence is nonsensical in UTF-8 (and we don't want to potentially contaminate any UTF-16 outputs). 5-byte and 6-byte UTF-8 byte sequences are dropped at this time. Bytes with values 0xfe or 0xff are dropped as neither are valid UTF-8 bytes.

Codepoints that are represented in UTF-16 as surrogate pairs are supported by this reader.


    public void testLatinCharsOnly() throws Exception {
        final ByteArrayOutputStream baos = new ByteArrayOutputStream(10);
        final String testChars = "abc123_+/`";
        baos.write(testChars.getBytes(Charsets.UTF_8));
        final Reader reader = new Utf8InputStreamReader(new ByteArrayInputStream(baos.toByteArray()));
        final char[] actual = new char[10];
        try {
            assertTrue(reader.ready());
            assertEquals(8, reader.read(actual, 0, 8));
            assertFalse(reader.ready());
            assertEquals(2, reader.read(actual, 8, 8));
            assertEquals(-1, reader.read(actual, 10, 8));
            assertEquals(-1, reader.read());
            assertEquals(-1, reader.read(actual));
            assertFalse(reader.ready());


            // Ensure that we match
            assertTrue(Arrays.equals(testChars.toCharArray(), actual));
        } finally {
            reader.close();
        }
    }

View Full Code Here

                        return 0;
                    }
                }
            };
        }
        final Reader reader = new Utf8InputStreamReader(in);
        final char[] actual = new char[testChars.length()];
        try {
            if (!oneByteAtATime) {
                assertTrue(reader.ready());
            }
            assertEquals(testChars.length(), reader.read(actual));
            assertEquals(-1, reader.read());
            assertEquals(-1, reader.read(actual, 10, 8));
            assertEquals(-1, reader.read(actual));
            assertFalse(reader.ready());


            // Ensure that we match
            assertTrue(Arrays.equals(testChars.toCharArray(), actual));
        } finally {
            reader.close();
        }
    }

View Full Code Here

        baos.write(0xbf);
        baos.write('h');
        baos.write(0xfe); // not valid UTF-8
        baos.write(0xff); // not valid UTF-8
        baos.write('i');
        final Reader reader = new Utf8InputStreamReader(new ByteArrayInputStream(baos.toByteArray()));
        try {
            assertTrue(reader.ready());
            assertEquals('h', reader.read());
            assertFalse(reader.ready());
            assertEquals('i', reader.read());
            assertEquals(-1, reader.read());
            assertFalse(reader.ready());
        } finally {
            reader.close();
        }
    }

View Full Code Here

        baos.write(0xF0);
        baos.write(0xA0);
        baos.write(0x02);
        baos.write(0x03);
        baos.write(0x04);
        final Reader reader = new Utf8InputStreamReader(new ByteArrayInputStream(baos.toByteArray()));
        try {
            assertEquals(0x04, reader.read());
            assertEquals(-1, reader.read());
        } finally {
            reader.close();
        }
    }

View Full Code Here

        baos.write(0xB2); // middle of a UTF-8 sequence
        baos.write(0xB2); // middle of a UTF-8 sequence
        baos.write(0xBF); // middle of a UTF-8 sequence
        baos.write(0xB2); // middle of a UTF-8 sequence
        baos.write('H'); // 1-byte UTF-8
        final Reader reader = new Utf8InputStreamReader(new ByteArrayInputStream(baos.toByteArray()));
        try {
            assertEquals('䷾', reader.read());
            assertEquals('H', reader.read());
            assertEquals(-1, reader.read());
        } finally {
            reader.close();
        }
    }

View Full Code Here


    public void testTooShortUTF8() throws Exception {
        final ByteArrayOutputStream baos = new ByteArrayOutputStream(3);
        baos.write(0xF0);
        baos.write(0xA0);
        final Reader reader = new Utf8InputStreamReader(new ByteArrayInputStream(baos.toByteArray()));
        try {
            assertEquals(-1, reader.read());
        } finally {
            reader.close();
        }
    }

View Full Code Here

        baos.write(0xBF);
        baos.write('H');
        baos.write(0xEF); // Little endian BOM in UTF-8
        baos.write(0xBF);
        baos.write(0xBE);
        final Reader reader = new Utf8InputStreamReader(new ByteArrayInputStream(baos.toByteArray()));
        try {
            assertEquals('H', reader.read());
            assertEquals(-1, reader.read());
        } finally {
            reader.close();
        }
    }

View Full Code Here

        baos.write(0xEE); // First char after the last low surrogate (okay to
                          // read)
        baos.write(0x80);
        baos.write(0x80);
        baos.write('H');
        final Reader reader = new Utf8InputStreamReader(new ByteArrayInputStream(baos.toByteArray()));
        try {
            assertEquals('퟿', reader.read());
            assertEquals('', reader.read());
            assertEquals('H', reader.read());
            assertEquals(-1, reader.read());
        } finally {
            reader.close();
        }
    }

View Full Code Here

        json.writeMapEnd();
        json.close();


        // Compare this against our expectations
        final DataInputStream in = new DataInputStream(new ByteArrayInputStream(baos.toByteArray()));
        final Reader reader = new Utf8InputStreamReader(in);
        final char[] chars = new char[88];
        assertNextStringFromReader(reader, "{\"header\":[", chars);
        for (int i = 0; i < columns.length; i++) {
            assertNextStringFromReader(reader, "\"" + columns[i] + "\"", chars);
            if (i < columns.length - 1) {
                assertEquals(',', (char) reader.read());
            }
        }
        assertNextStringFromReader(reader, "],\"rows\":[[\"", chars);
        assertNextStringFromReader(reader, testChars, chars);
        assertNextStringFromReader(reader, "\",\"", chars);
        assertNextStringFromReader(reader, id1, chars);
        assertNextStringFromReader(reader, "\",`", chars);
        assertEquals(37, in.readLong());
        for (int i = 0; i < 37; i++) {
            assertEquals(i, in.read());
        }
        assertNextStringFromReader(reader, "`],[\"", chars);
        assertNextStringFromReader(reader, uuid, chars);
        assertNextStringFromReader(reader, "\",\"", chars);
        assertNextStringFromReader(reader, id2, chars);
        assertNextStringFromReader(reader, "\",`", chars);
        assertEquals(7, in.readLong());
        for (int i = 0; i < 7; i++) {
            assertEquals(255 - i, in.read());
        }
        assertNextStringFromReader(reader, "`]]}", chars);
        assertEquals(-1, reader.read());
        assertEquals(-1, in.read());
    }

View Full Code Here

        json.writeBinaryStreamEnd();
        json.close();


        // Check what was written
        final DataInputStream in = new DataInputStream(new ByteArrayInputStream(baos.toByteArray()));
        final Reader reader = new Utf8InputStreamReader(in);
        try {
            assertEquals('`', reader.read());
            assertEquals(0, in.readLong());
            assertEquals('`', reader.read());
            assertEquals(-1, reader.read());
        } finally {
            reader.close();
        }
    }

View Full Code Here

0 1

TOP

Related Classes of org.auraframework.util.Utf8InputStreamReader

org.auraframework.util.io.Utf8InputStreamReaderTest

org.auraframework.util.json.JsonStreamReader

org.auraframework.util.json.JsonTest

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.