", sw.toString() );
}
/**
* Tests Supplementary characters.
*
* From http://www.w3.org/International/questions/qa-escapes
*
*
* Supplementary characters are those Unicode characters that have code points higher than the characters in
* the Basic Multilingual Plane (BMP). In UTF-16 a supplementary character is encoded using two 16-bit surrogate code points from the
* BMP. Because of this, some people think that supplementary characters need to be represented using two escapes, but this is incorrect
* - you must use the single, code point value for that character. For example, use 𣎴 rather than ��.
*
* @see Using character escapes in markup and CSS
* @see LANG-728
*/
@Test
public void testEscapeXmlSupplementaryCharacters() {
CharSequenceTranslator escapeXml =
StringEscapeUtils.ESCAPE_XML.with( NumericEntityEscaper.between(0x7f, Integer.MAX_VALUE) );
assertEquals("Supplementary character must be represented using a single escape", "𣎴",
escapeXml.translate("\uD84C\uDFB4"));
}
/**
* Reverse of the above.
*
* @see LANG-729
*/
@Test
public void testUnescapeXmlSupplementaryCharacters() {
assertEquals("Supplementary character must be represented using a single escape", "\uD84C\uDFB4",
StringEscapeUtils.unescapeXml("𣎴") );
}
// Tests issue #38569
// http://issues.apache.org/bugzilla/show_bug.cgi?id=38569
@Test
public void testStandaloneAmphersand() {
assertEquals("", StringEscapeUtils.unescapeHtml4("<P&O>"));
assertEquals("test & <", StringEscapeUtils.unescapeHtml4("test & <"));
assertEquals("", StringEscapeUtils.unescapeXml("<P&O>"));
assertEquals("test & <", StringEscapeUtils.unescapeXml("test & <"));
}
@Test
public void testLang313() {
assertEquals("& &", StringEscapeUtils.unescapeHtml4("& &"));
}
@Test
public void testEscapeCsvString() throws Exception {
assertEquals("foo.bar", StringEscapeUtils.escapeCsv("foo.bar"));
assertEquals("\"foo,bar\"", StringEscapeUtils.escapeCsv("foo,bar"));
assertEquals("\"foo\nbar\"", StringEscapeUtils.escapeCsv("foo\nbar"));
assertEquals("\"foo\rbar\"", StringEscapeUtils.escapeCsv("foo\rbar"));
assertEquals("\"foo\"\"bar\"", StringEscapeUtils.escapeCsv("foo\"bar"));
assertEquals("", StringEscapeUtils.escapeCsv(""));
assertEquals(null, StringEscapeUtils.escapeCsv(null));
}
@Test
public void testEscapeCsvWriter() throws Exception {
checkCsvEscapeWriter("foo.bar", "foo.bar");
checkCsvEscapeWriter("\"foo,bar\"", "foo,bar");
checkCsvEscapeWriter("\"foo\nbar\"", "foo\nbar");
checkCsvEscapeWriter("\"foo\rbar\"", "foo\rbar");
checkCsvEscapeWriter("\"foo\"\"bar\"", "foo\"bar");
checkCsvEscapeWriter("", null);
checkCsvEscapeWriter("", "");
}
private void checkCsvEscapeWriter(String expected, String value) {
try {
StringWriter writer = new StringWriter();
StringEscapeUtils.ESCAPE_CSV.translate(value, writer);
assertEquals(expected, writer.toString());
} catch (IOException e) {
fail("Threw: " + e);
}
}
@Test
public void testUnescapeCsvString() throws Exception {
assertEquals("foo.bar", StringEscapeUtils.unescapeCsv("foo.bar"));
assertEquals("foo,bar", StringEscapeUtils.unescapeCsv("\"foo,bar\""));
assertEquals("foo\nbar", StringEscapeUtils.unescapeCsv("\"foo\nbar\""));
assertEquals("foo\rbar", StringEscapeUtils.unescapeCsv("\"foo\rbar\""));
assertEquals("foo\"bar", StringEscapeUtils.unescapeCsv("\"foo\"\"bar\""));
assertEquals("", StringEscapeUtils.unescapeCsv(""));
assertEquals(null, StringEscapeUtils.unescapeCsv(null));
assertEquals("\"foo.bar\"", StringEscapeUtils.unescapeCsv("\"foo.bar\""));
}
@Test
public void testUnescapeCsvWriter() throws Exception {
checkCsvUnescapeWriter("foo.bar", "foo.bar");
checkCsvUnescapeWriter("foo,bar", "\"foo,bar\"");
checkCsvUnescapeWriter("foo\nbar", "\"foo\nbar\"");
checkCsvUnescapeWriter("foo\rbar", "\"foo\rbar\"");
checkCsvUnescapeWriter("foo\"bar", "\"foo\"\"bar\"");
checkCsvUnescapeWriter("", null);
checkCsvUnescapeWriter("", "");
checkCsvUnescapeWriter("\"foo.bar\"", "\"foo.bar\"");
}
private void checkCsvUnescapeWriter(String expected, String value) {
try {
StringWriter writer = new StringWriter();
StringEscapeUtils.UNESCAPE_CSV.translate(value, writer);
assertEquals(expected, writer.toString());
} catch (IOException e) {
fail("Threw: " + e);
}
}
/**
* Tests // https://issues.apache.org/jira/browse/LANG-480
*
* @throws java.io.UnsupportedEncodingException
*/
@Test
public void testEscapeHtmlHighUnicode() throws java.io.UnsupportedEncodingException {
// this is the utf8 representation of the character:
// COUNTING ROD UNIT DIGIT THREE
// in Unicode
// codepoint: U+1D362
byte[] data = new byte[] { (byte)0xF0, (byte)0x9D, (byte)0x8D, (byte)0xA2 };
String original = new String(data, "UTF8");
String escaped = StringEscapeUtils.escapeHtml4( original );
assertEquals( "High Unicode should not have been escaped", original, escaped);
String unescaped = StringEscapeUtils.unescapeHtml4( escaped );
assertEquals( "High Unicode should have been unchanged", original, unescaped);
// TODO: I think this should hold, needs further investigation
// String unescapedFromEntity = StringEscapeUtils.unescapeHtml4( "𝍢" );
// assertEquals( "High Unicode should have been unescaped", original, unescapedFromEntity);
}
/**
* Tests https://issues.apache.org/jira/browse/LANG-339
*/
@Test
public void testEscapeHiragana() {
// Some random Japanese Unicode characters
String original = "\u304B\u304C\u3068";
String escaped = StringEscapeUtils.escapeHtml4(original);
assertEquals( "Hiragana character Unicode behaviour should not be being escaped by escapeHtml4",
original, escaped);
String unescaped = StringEscapeUtils.unescapeHtml4( escaped );
assertEquals( "Hiragana character Unicode behaviour has changed - expected no unescaping", escaped, unescaped);
}
/**
* Tests https://issues.apache.org/jira/browse/LANG-708
*
* @throws IOException
* if an I/O error occurs
*/
@Test
public void testLang708() throws IOException {
String input = IOUtils.toString(new FileInputStream("src/test/resources/lang-708-input.txt"), "UTF-8");
String escaped = StringEscapeUtils.escapeEcmaScript(input);
// just the end:
assertTrue(escaped, escaped.endsWith("}]"));
// a little more:
assertTrue(escaped, escaped.endsWith("\"valueCode\\\":\\\"\\\"}]"));
}
/**
* Tests https://issues.apache.org/jira/browse/LANG-720
*/
@Test
public void testLang720() {
String input = new StringBuilder("\ud842\udfb7").append("A").toString();
String escaped = StringEscapeUtils.escapeXml(input);
assertEquals(input, escaped);
}
}