@Test
public void wordMatch() {
// The "/w" just support[a-zA-Z0-9],do not support any unicode
// characters.
Matcher matcher = RegExpUtils.getMatcher("[^\\w]*\\w+", "中国");
assertFalse(matcher.matches());
matcher = RegExpUtils.getMatcher("[^\\w]*\\w+", "中国abs中国abs");
List<int[]> l = RegExpUtils.getAllMatchBoundsAsList(matcher);
assertEquals(l.size(), 2);
assertEquals(0, ((l.get(0)))[0]);
assertEquals(5, ((l.get(0)))[1]);
assertEquals(5, ((l.get(1)))[0]);
assertEquals(10, ((l.get(1)))[1]);
Matcher matcher2 = RegExpUtils.getMatcher(".*\\w+", "中国abs中国abs");
/*
* The matcher will treat the left most as the highest priority.
*/
assertTrue(matcher2.find());
assertEquals(0, matcher2.start());
assertEquals(10, matcher2.end());
}
@Test
public void shouldSupportPOSIXExp() {
/*
* The java regexp does not support this feature.
*/
Matcher matcher = RegExpUtils.getMatcher("[:lower:]", getAllUnicode());
RegExpUtils.printFound(matcher, 200);
matcher = RegExpUtils.getMatcher("[:alpha:]", getAllUnicode());
RegExpUtils.printFound(matcher, 200);
}
/**
* If you wish one search to pick up where the last one left off you can use the "\G" pattern
* element. If the string hasn't been searched before, then "\G" matches the beginning of the
* String.
*
* <pre>
* Regex r = new Regex("\\Gfoo");
* String x = "foofoo foo";
* System.out.println(r.search(x));
* System.out.println(r.search(x));
* System.out.println(r.search(x));
* // Prints true, true, false.
* </pre>
*/
@Test
public void testG() {
Matcher matcher = RegExpUtils.getMatcher("\\G[a-z]", "abcDDde");
List<int[]> result = RegExpUtils.getAllMatchBoundsAsList(matcher);
assertEquals(result.size(), 3);
assertEquals(result.get(0)[0], 0);
assertEquals(result.get(0)[1], 1);
assertEquals(result.get(1)[0], 1);
assertEquals(result.get(1)[1], 2);
assertEquals(result.get(2)[0], 2);
assertEquals(result.get(2)[1], 3);
}
/**
* If supported, the partial application of a mode is achieved with a regex construct that looks
* like (?i) to turn on case-insensitive matching, or (?-i) to turn it off. Some flavors also
* support (?i:⋯) and (?-i:⋯), which turn on and off case-insensitive matching for the
* subexpression enclosed.
*/
@Test
public void testCaseSensitive() {
String fortest = "html";
String fortest2 = "HTML";
Matcher matcher =
RegExpUtils.getMatcher(
"(?i:html)", fortest, Pattern.CASE_INSENSITIVE | Pattern.UNICODE_CASE);
assertTrue(matcher.matches());
matcher.reset();
RegExpUtils.printFound(matcher, 200);
matcher.reset(fortest2);
assertTrue(matcher.matches());
matcher.reset();
RegExpUtils.printFound(matcher, 200);
}
@Test
public void shouldSupportTheUnicodeProperties() {
/*
* Regular-expression support for these qualities varies, but many
* Unicode-enabled programs support matching via at least some of them
* with \p{quality} (matches characters that have the quality) and
* \P{quality} (matches characters without it). A basic example is
* \p{L}, where 'L' is the quality meaning "letter" (as opposed to
* number, punctuation, accents, etc.). 'L' is an example of a general
* property (also called a category). We'll soon see other "qualities"
* that can be tested by \p{⋯} and \P{⋯}, but the most commonly
* supported are the general properties.
*/
Matcher matcher = RegExpUtils.getMatcher("\\p{IsL}", "中");
assertTrue(matcher.find());
}
@Test
public void testDigitalMatcher() {
Matcher matcher = RegExpUtils.getMatcher("[\\d]", "12345d");
assertEquals(5, RegExpUtils.countFound(matcher));
matcher = RegExpUtils.getMatcher("\\D", "12345d");
assertEquals(1, RegExpUtils.countFound(matcher));
matcher = RegExpUtils.getMatcher("\\D", "12345d");
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
}
@Test
public void testLineModes() {
/*
* Has enhanced line-anchor mode
*/
String forTest =
"to be a great man ,you must pay great effort\nAnd you will meet the most difficult things like the bitch\n";
/*
* ^ matches at start of string
*/
long found = RegExpUtils.countFound(RegExpUtils.getMatcher("^", forTest));
assertEquals(1L, found);
/*
* $ matches at end of string,and matches before string-ending newline.
*/
found = RegExpUtils.countFound(RegExpUtils.getMatcher("$", forTest));
assertEquals(2L, found);
found = RegExpUtils.countFound(RegExpUtils.getMatcher("$", forTest));
assertEquals(2L, found);
/*
* In enhanced line-anchor mode ... ^ matches at start of string
*
* ^ matches after any newline $ matches at end of string $ matches
* before any newline \A always matches like normal ^ \Z always matches
* like normal $ \z always matches only at end of string
*/
found = RegExpUtils.countFound(RegExpUtils.getMatcher("\\Z", forTest));
assertEquals(2L, found);
found = RegExpUtils.countFound(RegExpUtils.getMatcher("\\A", forTest));
assertEquals(1L, found);
found = RegExpUtils.countFound(RegExpUtils.getMatcher("\\z", forTest));
assertEquals(1L, found);
// multiline mode
found = RegExpUtils.countFound(RegExpUtils.getMatcher("$", forTest, Pattern.MULTILINE));
assertEquals(3L, found);
found = RegExpUtils.countFound(RegExpUtils.getMatcher("\\A", forTest, Pattern.MULTILINE));
assertEquals(1L, found);
/*
* Always like the normal '$'
*/
found = RegExpUtils.countFound(RegExpUtils.getMatcher("\\Z", forTest, Pattern.MULTILINE));
assertEquals(2L, found);
/*
* Always matches end of String.
*/
found = RegExpUtils.countFound(RegExpUtils.getMatcher("\\z", forTest, Pattern.MULTILINE));
assertEquals(1L, found);
}
@Test
public void shouldPrintLanguages() {
/*
* The simplified chinese character using the \p{InCJKUnifiedIdeographs}
* match!The traditional chinese using the
* \p{InCJKCompatibilityIdeographs} match!
*/
String[] languages =
new String[] {
"\\p{InAlphabeticPresentationForms}",
"\\p{InArabic}",
"\\p{InArabicPresentationFormsA}",
"\\p{InArabicPresentationFormsB}",
"\\p{InArabicSupplement}",
"\\p{InArmenian}",
"\\p{InArrows}",
"\\p{InBalinese}",
"\\p{InBasicLatin}",
"\\p{InBengali}",
"\\p{InBlockElements}",
"\\p{InBopomofo}",
"\\p{InBopomofoExtended}",
"\\p{InBoxDrawing}",
"\\p{InBraillePatterns}",
"\\p{InBuginese}",
"\\p{InBuhid}",
"\\p{InCham}",
"\\p{InCherokee}",
"\\p{InCJKCompatibility}",
"\\p{InCJKCompatibilityForms}",
"\\p{InCJKCompatibilityIdeographs}",
"\\p{InCJKRadicalsSupplement}",
"\\p{InCJKStrokes}",
"\\p{InCJKSymbolsandPunctuation}",
"\\p{InCJKUnifiedIdeographs}",
"\\p{InCJKUnifiedIdeographsExtensionA}",
"\\p{InCombiningDiacriticalMarks}",
"\\p{InCombiningDiacriticalMarksforSymbols}",
"\\p{InCombiningDiacriticalMarksSupplement}",
"\\p{InCombiningHalfMarks}",
"\\p{InControlPictures}",
"\\p{InCoptic}",
"\\p{InCurrencySymbols}",
"\\p{InCyrillic}",
"\\p{InCyrillicExtendedA}",
"\\p{InCyrillicExtendedB}",
"\\p{InCyrillicSupplement}",
"\\p{InDevanagari}",
"\\p{InDingbats}",
"\\p{InEnclosedAlphanumerics}",
"\\p{InEnclosedCJKLettersandMonths}",
"\\p{InEthiopic}",
"\\p{InEthiopicExtended}",
"\\p{InEthiopicSupplement}",
"\\p{InGeneralPunctuation}",
"\\p{InGeometricShapes}",
"\\p{InGeorgian}",
"\\p{InGeorgianSupplement}",
"\\p{InGlagolitic}",
"\\p{InGreekandCoptic}",
"\\p{InGreekExtended}",
"\\p{InGujarati}",
"\\p{InGurmukhi}",
"\\p{InHalfwidthandFullwidthForms}",
"\\p{InHangulCompatibilityJamo}",
"\\p{InHangulJamo}",
"\\p{InHangulSyllables}",
"\\p{InHanunoo}",
"\\p{InHebrew}",
"\\p{InHighPrivateUseSurrogates}",
"\\p{InHighSurrogates}",
"\\p{InHiragana}",
"\\p{InIdeographicDescriptionCharacters}",
"\\p{InIPAExtensions}",
"\\p{InKanbun}",
"\\p{InKangxiRadicals}",
"\\p{InKannada}",
"\\p{InKatakana}",
"\\p{InKatakanaPhoneticExtensions}",
"\\p{InKayahLi}",
"\\p{InKhmer}",
"\\p{InKhmerSymbols}",
"\\p{InLao}",
"\\p{InLatin1Supplement}",
"\\p{InLatinExtendedA}",
"\\p{InLatinExtendedAdditional}",
"\\p{InLatinExtendedB}",
"\\p{InLatinExtendedC}",
"\\p{InLatinExtendedD}",
"\\p{InLepcha}",
"\\p{InLetterlikeSymbols}",
"\\p{InLimbu}",
"\\p{InLowSurrogates}",
"\\p{InMalayalam}",
"\\p{InMathematicalOperators}",
"\\p{InMiscellaneousMathematicalSymbolsA}",
"\\p{InMiscellaneousMathematicalSymbolsB}",
"\\p{InMiscellaneousSymbols}",
"\\p{InMiscellaneousSymbolsandArrows}",
"\\p{InMiscellaneousTechnical}",
"\\p{InModifierToneLetters}",
"\\p{InMongolian}",
"\\p{InMyanmar}",
"\\p{InNewTaiLue}",
"\\p{InNKo}",
"\\p{InNumberForms}",
"\\p{InOgham}",
"\\p{InOlChiki}",
"\\p{InOpticalCharacterRecognition}",
"\\p{InOriya}",
"\\p{InPhagspa}",
"\\p{InPhoneticExtensions}",
"\\p{InPhoneticExtensionsSupplement}",
"\\p{InPrivateUseArea}",
"\\p{InRejang}",
"\\p{InRunic}",
"\\p{InSaurashtra}",
"\\p{InSinhala}",
"\\p{InSmallFormVariants}",
"\\p{InSpacingModifierLetters}",
"\\p{InSpecials}",
"\\p{InSundanese}",
"\\p{InSuperscriptsandSubscripts}",
"\\p{InSupplementalArrowsA}",
"\\p{InSupplementalArrowsB}",
"\\p{InSupplementalMathematicalOperators}",
"\\p{InSupplementalPunctuation}",
"\\p{InSylotiNagri}",
"\\p{InSyriac}",
"\\p{InTagalog}",
"\\p{InTagbanwa}",
"\\p{InTaiLe}",
"\\p{InTamil}",
"\\p{InTelugu}",
"\\p{InThaana}",
"\\p{InThai}",
"\\p{InTibetan}",
"\\p{InTifinagh}",
"\\p{InUnifiedCanadianAboriginalSyllabics}",
"\\p{InVai}",
"\\p{InVariationSelectors}",
"\\p{InVerticalForms}",
"\\p{InYijingHexagramSymbols}",
"\\p{InYiRadicals}",
"\\p{InYiSyllables}"
};
Matcher matcher = null;
for (String s : languages) {
try {
matcher = RegExpUtils.getMatcher(s, getAllUnicode());
RegExpUtils.printFound(matcher, 200);
} catch (Exception e) {
System.out.println("!!!not supported:" + s);
}
}
}
@Test
public void testMatchProperties() {
/*
* \p{Lowercase_Letter} Lowercase letters.
*/
Matcher matcher = RegExpUtils.getMatcher("\\p{Ll}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Uppercase_Letter} Uppercase letters.
*/
matcher = RegExpUtils.getMatcher("\\p{Lu}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Titlecase_Letter} Letters that appear at the start of a word
* (e.g., the character D is the title case of the lowercase d and of
* the uppercase D).
*/
matcher = RegExpUtils.getMatcher("\\p{Lt}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
try {
/*
* A composite shorthand matching all \p{Ll}, \p{Lu}, and \p{Lt}
* characters.
*/
matcher = RegExpUtils.getMatcher("\\p{L&}", getAllUnicode());
fail("The java not support this pattern");
} catch (Exception e) {
}
/*
* \p{Letter} Things considered letters.
*/
matcher = RegExpUtils.getMatcher("\\p{L}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Mark} Various characters that are not meant to appear by
* themselves, but with other base characters (accent marks, enclosing
* boxes, ...).
*/
matcher = RegExpUtils.getMatcher("\\p{M}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Separator} Characters that separate things, but have no visual
* representation (various kinds of spaces ...).
*/
matcher = RegExpUtils.getMatcher("\\p{Z}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Symbol} Various types of Dingbats and symbols.
*/
matcher = RegExpUtils.getMatcher("\\p{S}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Number} Any kind of numeric character.
*/
matcher = RegExpUtils.getMatcher("\\p{N}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Punctuation} Punctuation characters.
*/
matcher = RegExpUtils.getMatcher("\\p{P}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Other} Catch-all for everything else (rarely used for normal
* characters).
*/
matcher = RegExpUtils.getMatcher("\\p{C}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Modifier_Letter} A small set of letter-like special-use
* characters.
*/
matcher = RegExpUtils.getMatcher("\\p{Lm}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Other_Letter} Letters that have no case, and aren't modifiers,
* including letters from Hebrew, Arabic, Bengali, Tibetan, Japanese,
* ...
*/
matcher = RegExpUtils.getMatcher("\\p{Lo}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Non_Spacing_Mark} "Characters" that modify other characters, such
* as accents, umlauts, certain "vowel signs," and tone marks.
*/
matcher = RegExpUtils.getMatcher("\\p{Mn}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Spacing_Combining_Mark} Modification characters that take up space
* of their own (mostly "vowel signs" in languages that have them,
* including Bengali, Gujarati, Tamil, Telugu, Kannada, Malayalam,
* Sinhala, Myanmar, and Khmer).
*/
matcher = RegExpUtils.getMatcher("\\p{Mc}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Enclosing_Mark} A small set of marks that can enclose other
* characters, such as circles, squares, diamonds, and "keycaps."
*/
matcher = RegExpUtils.getMatcher("\\p{Me}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Space_Separator} Various kinds of spacing characters, such as a
* normal space, non-break space, and various spaces of specific widths.
*/
matcher = RegExpUtils.getMatcher("\\p{Zs}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Line_Separator} The LINE SEPARATOR character (U+2028).
*/
matcher = RegExpUtils.getMatcher("\\p{Zl}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Paragraph_Separator} The PARAGRAPH SEPARATOR character (U+2029).
*/
matcher = RegExpUtils.getMatcher("\\p{Zp}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Math_Symbol} +, ÷, a fraction slash, , ...
*/
matcher = RegExpUtils.getMatcher("\\p{Sm}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Currency_Symbol} $, ¢, ¥, €, ...
*/
matcher = RegExpUtils.getMatcher("\\p{Sc}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Modifier_Symbol} Mostly versions of the combining characters, but
* as full-fledged characters in their own right.
*/
matcher = RegExpUtils.getMatcher("\\p{Sk}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Other_Symbol} Various Dingbats, box-drawing symbols, Braille
* patterns, non-letter Chinese characters
*/
matcher = RegExpUtils.getMatcher("\\p{So}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Decimal_Digit_Number} Zero through nine, in various scripts (not
* including Chinese, Japanese, and Korean).
*/
matcher = RegExpUtils.getMatcher("\\p{Nd}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Letter_Number} Mostly Roman numerals.
*/
matcher = RegExpUtils.getMatcher("\\p{Nl}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Other_Number} Numbers as superscripts or symbols; characters
* representing numbers that aren't digits (Chinese, Japanese, and
* Korean not included).
*/
matcher = RegExpUtils.getMatcher("\\p{No}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Dash_Punctuation} Hyphens and dashes of all sorts.
*/
matcher = RegExpUtils.getMatcher("\\p{Pd}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Open_Punctuation} Characters like (, ︽, and 《, ...
*/
matcher = RegExpUtils.getMatcher("\\p{Ps}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Close_Punctuation} Characters like), 》, 》, ...
*/
matcher = RegExpUtils.getMatcher("\\p{Pe}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Initial_Punctuation} Characters like , ', <, ...
*/
matcher = RegExpUtils.getMatcher("\\p{Pi}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Final_Punctuation} Characters like , ', >, ...
*/
matcher = RegExpUtils.getMatcher("\\p{Pf}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Connector_Punctuation} A few punctuation characters with special
* linguistic meaning, such as an underscore.
*/
matcher = RegExpUtils.getMatcher("\\p{Pc}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Other_Punctuation} Catch-all for other punctuation: !, &, ., :, :,
* ...
*/
matcher = RegExpUtils.getMatcher("\\p{Po}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Control} The ASCII and Latin-1 control characters (TAB, LF, CR,
* ...)
*/
matcher = RegExpUtils.getMatcher("\\p{Cc}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Format} Non-visible characters intended to indicate some basic
* formatting(zero width joiner, activate Arabic form shaping, ...)
*/
matcher = RegExpUtils.getMatcher("\\p{Cf}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Private_Use} Code points allocated for private use (company logos,
* etc.).
*/
matcher = RegExpUtils.getMatcher("\\p{Co}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
/*
* \p{Unassigned} Code points that have no characters assigned.
*/
matcher = RegExpUtils.getMatcher("\\p{Cn}", getAllUnicode());
RegExpUtils.printFound(matcher, OUTPUT_STRING_WIDTH);
}
@Test
public void defaultMatchModeShouldBeMultiLine() {
Matcher matcher = RegExpUtils.getMatcher("$", "\n");
assertEquals(2L, RegExpUtils.countFound(matcher));
}
@Test
public void checkThaiCharacters() {
Matcher m = RegExpUtils.getMatcher("[\\p{InThai}]", getAllUnicode());
RegExpUtils.printFound(m, OUTPUT_STRING_WIDTH);
}
