diff --git a/jdk/src/share/classes/java/util/regex/Matcher.java b/jdk/src/share/classes/java/util/regex/Matcher.java index ee7931688e2..61b75ebc73e 100644 --- a/jdk/src/share/classes/java/util/regex/Matcher.java +++ b/jdk/src/share/classes/java/util/regex/Matcher.java @@ -490,6 +490,45 @@ public final class Matcher implements MatchResult { return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString(); } + /** + * Returns the input subsequence captured by the given + * named-capturing group during the previous + * match operation. + * + *

If the match was successful but the group specified failed to match + * any part of the input sequence, then null is returned. Note + * that some groups, for example (a*), match the empty string. + * This method will return the empty string when such a group successfully + * matches the empty string in the input.

+ * + * @param name + * The name of a named-capturing group in this matcher's pattern + * + * @return The (possibly empty) subsequence captured by the named group + * during the previous match, or null if the group + * failed to match part of the input + * + * @throws IllegalStateException + * If no match has yet been attempted, + * or if the previous match operation failed + * + * @throws IllegalArgumentException + * If there is no capturing group in the pattern + * with the given name + */ + public String group(String name) { + if (name == null) + throw new NullPointerException("Null group name"); + if (first < 0) + throw new IllegalStateException("No match found"); + if (!parentPattern.namedGroups().containsKey(name)) + throw new IllegalArgumentException("No group with name <" + name + ">"); + int group = parentPattern.namedGroups().get(name); + if ((groups[group*2] == -1) || (groups[group*2+1] == -1)) + return null; + return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString(); + } + /** * Returns the number of capturing groups in this matcher's pattern. * @@ -649,9 +688,11 @@ public final class Matcher implements MatchResult { * *

The replacement string may contain references to subsequences * captured during the previous match: Each occurrence of - * $g will be replaced by the result of - * evaluating {@link #group(int) group}(g). - * The first number after the $ is always treated as part of + * $<name> or $g + * will be replaced by the result of evaluating the corresponding + * {@link #group(String) group(name)} or {@link #group(int) group(g)} + * respectively. For $g, + * the first number after the $ is always treated as part of * the group reference. Subsequent numbers are incorporated into g if * they would form a legal group reference. Only the numerals '0' * through '9' are considered as potential components of the group @@ -695,6 +736,10 @@ public final class Matcher implements MatchResult { * If no match has yet been attempted, * or if the previous match operation failed * + * @throws IllegalArgumentException + * If the replacement string refers to a named-capturing + * group that does not exist in the pattern + * * @throws IndexOutOfBoundsException * If the replacement string refers to a capturing group * that does not exist in the pattern @@ -719,29 +764,62 @@ public final class Matcher implements MatchResult { } else if (nextChar == '$') { // Skip past $ cursor++; - // The first number is always a group - int refNum = (int)replacement.charAt(cursor) - '0'; - if ((refNum < 0)||(refNum > 9)) - throw new IllegalArgumentException( - "Illegal group reference"); - cursor++; - - // Capture the largest legal group string - boolean done = false; - while (!done) { - if (cursor >= replacement.length()) { - break; + // A StringIndexOutOfBoundsException is thrown if + // this "$" is the last character in replacement + // string in current implementation, a IAE might be + // more appropriate. + nextChar = replacement.charAt(cursor); + int refNum = -1; + if (nextChar == '<') { + cursor++; + StringBuilder gsb = new StringBuilder(); + while (cursor < replacement.length()) { + nextChar = replacement.charAt(cursor); + if (ASCII.isLower(nextChar) || + ASCII.isUpper(nextChar) || + ASCII.isDigit(nextChar)) { + gsb.append(nextChar); + cursor++; + } else { + break; + } } - int nextDigit = replacement.charAt(cursor) - '0'; - if ((nextDigit < 0)||(nextDigit > 9)) { // not a number - break; - } - int newRefNum = (refNum * 10) + nextDigit; - if (groupCount() < newRefNum) { - done = true; - } else { - refNum = newRefNum; - cursor++; + if (gsb.length() == 0) + throw new IllegalArgumentException( + "named capturing group has 0 length name"); + if (nextChar != '>') + throw new IllegalArgumentException( + "named capturing group is missing trailing '>'"); + String gname = gsb.toString(); + if (!parentPattern.namedGroups().containsKey(gname)) + throw new IllegalArgumentException( + "No group with name <" + gname + ">"); + refNum = parentPattern.namedGroups().get(gname); + cursor++; + } else { + // The first number is always a group + refNum = (int)nextChar - '0'; + if ((refNum < 0)||(refNum > 9)) + throw new IllegalArgumentException( + "Illegal group reference"); + cursor++; + // Capture the largest legal group string + boolean done = false; + while (!done) { + if (cursor >= replacement.length()) { + break; + } + int nextDigit = replacement.charAt(cursor) - '0'; + if ((nextDigit < 0)||(nextDigit > 9)) { // not a number + break; + } + int newRefNum = (refNum * 10) + nextDigit; + if (groupCount() < newRefNum) { + done = true; + } else { + refNum = newRefNum; + cursor++; + } } } // Append group diff --git a/jdk/src/share/classes/java/util/regex/Pattern.java b/jdk/src/share/classes/java/util/regex/Pattern.java index 2458a855e08..919c1bf3c55 100644 --- a/jdk/src/share/classes/java/util/regex/Pattern.java +++ b/jdk/src/share/classes/java/util/regex/Pattern.java @@ -29,6 +29,7 @@ import java.security.AccessController; import java.security.PrivilegedAction; import java.text.CharacterIterator; import java.text.Normalizer; +import java.util.Map; import java.util.ArrayList; import java.util.HashMap; import java.util.Arrays; @@ -298,6 +299,10 @@ import java.util.Arrays; * Whatever the nth * capturing group matched * + * \k<name> + * Whatever the + * named-capturing group "name" matched + * *   * Quotation * @@ -310,8 +315,10 @@ import java.util.Arrays; * * *   - * Special constructs (non-capturing) + * Special constructs (named-capturing and non-capturing) * + * (?<name>X) + * X, as a named-capturing group * (?:X) * X, as a non-capturing group * (?idmsux-idmsux)  @@ -449,6 +456,8 @@ import java.util.Arrays; * *

Groups and capturing

* + * + *
Group number
*

Capturing groups are numbered by counting their opening parentheses from * left to right. In the expression ((A)(B(C))), for example, there * are four such groups:

@@ -471,6 +480,24 @@ import java.util.Arrays; * subsequence may be used later in the expression, via a back reference, and * may also be retrieved from the matcher once the match operation is complete. * + * + *
Group name
+ *

A capturing group can also be assigned a "name", a named-capturing group, + * and then be back-referenced later by the "name". Group names are composed of + * the following characters: + * + *

+ * + *

A named-capturing group is still numbered as described in + * Group number. + * *

The captured input associated with a group is always the subsequence * that the group most recently matched. If a group is evaluated a second time * because of quantification then its previously-captured value, if any, will @@ -479,9 +506,9 @@ import java.util.Arrays; * group two set to "b". All captured input is discarded at the * beginning of each match. * - *

Groups beginning with (? are pure, non-capturing groups - * that do not capture text and do not count towards the group total. - * + *

Groups beginning with (? are either pure, non-capturing groups + * that do not capture text and do not count towards the group total, or + * named-capturing group. * *

Unicode support

* @@ -794,6 +821,12 @@ public final class Pattern */ transient int[] buffer; + /** + * Map the "name" of the "named capturing group" to its group id + * node. + */ + transient volatile Map namedGroups; + /** * Temporary storage used while parsing group references. */ @@ -1467,6 +1500,7 @@ loop: for(int x=0, offset=0; x namedGroups() { + if (namedGroups == null) + namedGroups = new HashMap(2); + return namedGroups; + } + /** * Used to print out a subtree of the Pattern to help with debugging. */ @@ -2156,7 +2196,22 @@ loop: for(int x=0, offset=0; x does not exit"); + if (create) { + if (has(CASE_INSENSITIVE)) + root = new CIBackRef(namedGroups().get(name), has(UNICODE_CASE)); + else + root = new BackRef(namedGroups().get(name)); + } + return -1; case 'l': case 'm': break; @@ -2455,6 +2510,24 @@ loop: for(int x=0, offset=0; x" is consumed after parsing. + */ + private String groupname(int ch) { + StringBuilder sb = new StringBuilder(); + sb.append(Character.toChars(ch)); + while (ASCII.isLower(ch=read()) || ASCII.isUpper(ch) || + ASCII.isDigit(ch)) { + sb.append(Character.toChars(ch)); + } + if (sb.length() == 0) + throw error("named capturing group has 0 length name"); + if (ch != '>') + throw error("named capturing group is missing trailing '>'"); + return sb.toString(); + } + /** * Parses a group and returns the head node of a set of nodes that process * the group. Sometimes a double return system is used where the tail is @@ -2494,6 +2567,18 @@ loop: for(int x=0, offset=0; x is already defined"); + capturingGroup = true; + head = createGroup(false); + tail = root; + namedGroups().put(name, capturingGroupCount-1); + head.next = expr(tail); + break; + } int start = cursor; head = createGroup(true); tail = root; diff --git a/jdk/test/java/util/regex/BMPTestCases.txt b/jdk/test/java/util/regex/BMPTestCases.txt new file mode 100644 index 00000000000..c50f49628e3 --- /dev/null +++ b/jdk/test/java/util/regex/BMPTestCases.txt @@ -0,0 +1,951 @@ +// +// Copyright 1999-2009 Sun Microsystems, Inc. All Rights Reserved. +// DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +// +// This code is free software; you can redistribute it and/or modify it +// under the terms of the GNU General Public License version 2 only, as +// published by the Free Software Foundation. +// +// This code is distributed in the hope that it will be useful, but WITHOUT +// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +// version 2 for more details (a copy is included in the LICENSE file that +// accompanied this code). +// +// You should have received a copy of the GNU General Public License version +// 2 along with this work; if not, write to the Free Software Foundation, +// Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. +// +// Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, +// CA 95054 USA or visit www.sun.com if you need additional information or +// have any questions. +// +// +// This file contains test cases with BMP characters for regular expressions. +// A test case consists of three lines: +// The first line is a pattern used in the test +// The second line is the input to search for the pattern in +// The third line is a concatentation of the match, the number of groups, +// and the contents of the first four subexpressions. +// Empty lines and lines beginning with comment slashes are ignored. + +// Test unsetting of backed off groups +^(\u3042)?\u3042 +\u3042 +true \u3042 1 + +^(\u3042\u3042(\u3043\u3043)?)+$ +\u3042\u3042\u3043\u3043\u3042\u3042 +true \u3042\u3042\u3043\u3043\u3042\u3042 2 \u3042\u3042 \u3043\u3043 + +((\u3042|\u3043)?\u3043)+ +\u3043 +true \u3043 2 \u3043 + +(\u3042\u3042\u3042)?\u3042\u3042\u3042 +\u3042\u3042\u3042 +true \u3042\u3042\u3042 1 + +^(\u3042(\u3043)?)+$ +\u3042\u3043\u3042 +true \u3042\u3043\u3042 2 \u3042 \u3043 + +^(\u3042(\u3043(\u3044)?)?)?\u3042\u3043\u3044 +\u3042\u3043\u3044 +true \u3042\u3043\u3044 3 + +^(\u3042(\u3043(\u3044))).* +\u3042\u3043\u3044 +true \u3042\u3043\u3044 3 \u3042\u3043\u3044 \u3043\u3044 \u3044 + +// use of x modifier +\u3042\u3043\u3044(?x)\u3043la\u3049 +\u3042\u3043\u3044\u3043la\u3049 +true \u3042\u3043\u3044\u3043la\u3049 0 + +\u3042\u3043\u3044(?x) bla\u3049 +\u3042\u3043\u3044bla\u3049 +true \u3042\u3043\u3044bla\u3049 0 + +\u3042\u3043\u3044(?x) bla\u3049 ble\u3044\u3049 +\u3042\u3043\u3044bla\u3049ble\u3044\u3049 +true \u3042\u3043\u3044bla\u3049ble\u3044\u3049 0 + +\u3042\u3043\u3044(?x) bla\u3049 # ignore comment +\u3042\u3043\u3044bla\u3049 +true \u3042\u3043\u3044bla\u3049 0 + +// Simple alternation +\u3042|\u3043 +\u3042 +true \u3042 0 + +\u3042|\u3043 +\u305B +false 0 + +\u3042|\u3043 +\u3043 +true \u3043 0 + +\u3042|\u3043|\u3044\u3045 +\u3044\u3045 +true \u3044\u3045 0 + +\u3042|\u3042\u3045 +\u3042\u3045 +true \u3042 0 + +\u305B(\u3042|\u3042\u3044)\u3043 +\u305B\u3042\u3044\u3043 +true \u305B\u3042\u3044\u3043 1 \u3042\u3044 + +// Simple char class +[\u3042\u3043\u3044]+ +\u3042\u3043\u3042\u3043\u3042\u3043 +true \u3042\u3043\u3042\u3043\u3042\u3043 0 + +[\u3042\u3043\u3044]+ +\u3045\u3046\u3047\u3048 +false 0 + +[\u3042\u3043\u3044]+[\u3045\u3046\u3047]+[\u3048\u3049\u304A]+ +\u305B\u305B\u305B\u3042\u3042\u3045\u3045\u3048\u3048\u305B\u305B\u305B +true \u3042\u3042\u3045\u3045\u3048\u3048 0 + +// Range char class +[\u3042-\u3048]+ +\u305B\u305B\u305B\u3048\u3048\u3048 +true \u3048\u3048\u3048 0 + +[\u3042-\u3048]+ +mmm +false 0 + +[\u3042-]+ +\u305B\u3042-9\u305B +true \u3042- 0 + +[\u3042-\\u4444]+ +\u305B\u3042-9\u305B +true \u305B\u3042 0 + +// Negated char class +[^\u3042\u3043\u3044]+ +\u3042\u3043\u3042\u3043\u3042\u3043 +false 0 + +[^\u3042\u3043\u3044]+ +\u3042\u3042\u3042\u3043\u3043\u3043\u3044\u3044\u3044\u3045\u3046\u3047\u3048 +true \u3045\u3046\u3047\u3048 0 + +// Making sure a ^ not in first position matches literal ^ +[\u3042\u3043\u3044^\u3043] +\u3043 +true \u3043 0 + +[\u3042\u3043\u3044^\u3043] +^ +true ^ 0 + +// Class union and intersection +[\u3042\u3043\u3044[\u3045\u3046\u3047]] +\u3043 +true \u3043 0 + +[\u3042\u3043\u3044[\u3045\u3046\u3047]] +\u3046 +true \u3046 0 + +[\u3042-\u3045[0-9][\u304e-\u3051]] +\u3042 +true \u3042 0 + +[\u3042-\u3045[0-9][\u304e-\u3051]] +\u3050 +true \u3050 0 + +[\u3042-\u3045[0-9][\u304e-\u3051]] +4 +true 4 0 + +[\u3042-\u3045[0-9][\u304e-\u3051]] +\u3046 +false 0 + +[\u3042-\u3045[0-9][\u304e-\u3051]] +\u3056 +false 0 + +[[\u3042-\u3045][0-9][\u304e-\u3051]] +\u3043 +true \u3043 0 + +[[\u3042-\u3045][0-9][\u304e-\u3051]] +\u305B +false 0 + +[\u3042-\u3044[\u3045-\u3047[\u3048-\u304A]]] +\u3042 +true \u3042 0 + +[\u3042-\u3044[\u3045-\u3047[\u3048-\u304A]]] +\u3046 +true \u3046 0 + +[\u3042-\u3044[\u3045-\u3047[\u3048-\u304A]]] +\u3049 +true \u3049 0 + +[\u3042-\u3044[\u3045-\u3047[\u3048-\u304A]]] +m +false 0 + +[\u3042-\u3044[\u3045-\u3047[\u3048-\u304A]]m] +m +true m 0 + +[\u3042\u3043\u3044[\u3045\u3046\u3047]\u3048\u3049\u304A] +\u3042 +true \u3042 0 + +[\u3042\u3043\u3044[\u3045\u3046\u3047]\u3048\u3049\u304A] +\u3045 +true \u3045 0 + +[\u3042\u3043\u3044[\u3045\u3046\u3047]\u3048\u3049\u304A] +\u3049 +true \u3049 0 + +[\u3042\u3043\u3044[\u3045\u3046\u3047]\u3048\u3049\u304A] +w +false 0 + +[\u3042-\u3044&&[\u3045-\u3047]] +\u3042 +false 0 + +[\u3042-\u3044&&[\u3045-\u3047]] +\u3046 +false 0 + +[\u3042-\u3044&&[\u3045-\u3047]] +\u305B +false 0 + +[[\u3042-\u3044]&&[\u3045-\u3047]] +\u3042 +false 0 + +[[\u3042-\u3044]&&[\u3045-\u3047]] +\u3046 +false 0 + +[[\u3042-\u3044]&&[\u3045-\u3047]] +\u305B +false 0 + +[\u3042-\u3044&&\u3045-\u3047] +\u3042 +false 0 + +[\u3042-\u304e&&\u304e-\u305B] +\u304e +true \u304e 0 + +[\u3042-\u304e&&\u304e-\u305B&&\u3042-\u3044] +\u304e +false 0 + +[\u3042-\u304e&&\u304e-\u305B&&\u3042-\u305B] +\u304e +true \u304e 0 + +[[\u3042-\u304e]&&[\u304e-\u305B]] +\u3042 +false 0 + +[[\u3042-\u304e]&&[\u304e-\u305B]] +\u304e +true \u304e 0 + +[[\u3042-\u304e]&&[\u304e-\u305B]] +\u305B +false 0 + +[[\u3042-\u304e]&&[^\u3042-\u3044]] +\u3042 +false 0 + +[[\u3042-\u304e]&&[^\u3042-\u3044]] +\u3045 +true \u3045 0 + +[\u3042-\u304e&&[^\u3042-\u3044]] +\u3042 +false 0 + +[\u3042-\u304e&&[^\u3042-\u3044]] +\u3045 +true \u3045 0 + +[\u3042-\u3044\u3045-\u3047&&[\u3045-\u3047]] +\u3042 +false 0 + +[\u3042-\u3044\u3045-\u3047&&[\u3045-\u3047]] +\u3046 +true \u3046 0 + +[[\u3042-\u3044]&&\u3045-\u3047\u3042-\u3044] +\u3042 +true \u3042 0 + +[[\u3042-\u3044]&&[\u3045-\u3047][\u3042-\u3044]] +\u3042 +true \u3042 0 + +[[\u3042-\u3044][\u3045-\u3047]&&\u3042\u3043\u3044] +\u3042 +true \u3042 0 + +[[\u3042-\u3044][\u3045-\u3047]&&\u3042\u3043\u3044[\u3045\u3046\u3047]] +\u3046 +true \u3046 0 + +[[\u3042-\u3044]&&[\u3043-\u3045]&&[\u3044-\u3046]] +\u3042 +false 0 + +[[\u3042-\u3044]&&[\u3043-\u3045]&&[\u3044-\u3046]] +\u3044 +true \u3044 0 + +[[\u3042-\u3044]&&[\u3043-\u3045][\u3044-\u3046]&&[\u3056-\u305B]] +\u3044 +false 0 + +[\u3042\u3043\u3044[^\u3043\u3044\u3045]] +\u3042 +true \u3042 0 + +[\u3042\u3043\u3044[^\u3043\u3044\u3045]] +\u3045 +false 0 + +[\u3042-\u3044&&\u3042-\u3045&&\u3042-\u3046\u3048\u3049\u304A] +\u3043 +true \u3043 0 + +[\u3042-\u3044&&\u3042-\u3045&&\u3042-\u3046\u3048\u3049\u304A] +\u3048 +false 0 + +[[\u3042[\u3043]]&&[\u3043[\u3042]]] +\u3042 +true \u3042 0 + +[[\u3042]&&[\u3043][\u3044][\u3042]&&[^\u3045]] +\u3042 +true \u3042 0 + +[[\u3042]&&[b][c][\u3042]&&[^d]] +\u3042 +true \u3042 0 + +[[\u3042]&&[\u3043][\u3044][\u3042]&&[^\u3045]] +\u3045 +false 0 + +[[[\u3042-\u3045]&&[\u3044-\u3047]]] +\u3042 +false 0 + +[[[\u3042-\u3045]&&[\u3044-\u3047]]] +\u3044 +true \u3044 0 + +[[[\u3042-\u3045]&&[\u3044-\u3047]]&&[\u3044]] +\u3044 +true \u3044 0 + +[[[\u3042-\u3045]&&[\u3044-\u3047]]&&[\u3044]&&\u3044] +\u3044 +true \u3044 0 + +[[[\u3042-\u3045]&&[\u3044-\u3047]]&&[\u3044]&&\u3044&&\u3044] +\u3044 +true \u3044 0 + +[[[\u3042-\u3045]&&[\u3044-\u3047]]&&[\u3044]&&\u3044&&[\u3044\u3045\u3046]] +\u3044 +true \u3044 0 + +[\u305B[\u3042\u3043\u3044&&\u3043\u3044\u3045]] +\u3044 +true \u3044 0 + +[\u305B[\u3042\u3043\u3044&&\u3043\u3044\u3045]&&[\u3056-\u305B]] +\u305B +true \u305B 0 + +[\u3059[\u3042\u3043\u3044&&\u3043\u3044\u3045[\u305B]]&&[\u3056-\u305B]] +\u305B +false 0 + +[\u3059[[w\u305B]\u3042\u3043\u3044&&\u3043\u3044\u3045[\u305B]]&&[\u3056-\u305B]] +\u305B +true \u305B 0 + +[[\u3042\u3043\u3044]&&[\u3045\u3046\u3047]\u3042\u3043\u3044] +\u3042 +true \u3042 0 + +[[\u3042\u3043\u3044]&&[\u3045\u3046\u3047]\u3059\u305A\u305B[\u3042\u3043\u3044]] +\u3042 +true \u3042 0 + +\pL +\u3042 +true \u3042 0 + +\pL +7 +false 0 + +\p{L} +\u3042 +true \u3042 0 + +\p{IsL} +\u3042 +true \u3042 0 + +\p{InHiragana} +\u3042 +true \u3042 0 + +\p{InHiragana} +\u0370 +false 0 + +\pL\u3043\u3044 +\u3042\u3043\u3044 +true \u3042\u3043\u3044 0 + +\u3042[r\p{InGreek}]\u3044 +\u3042\u0370\u3044 +true \u3042\u0370\u3044 0 + +\u3042\p{InGreek} +\u3042\u0370 +true \u3042\u0370 0 + +\u3042\P{InGreek} +\u3042\u0370 +false 0 + +\u3042\P{InGreek} +\u3042\u3043 +true \u3042\u3043 0 + +\u3042{^InGreek} +- +error + +\u3042\p{^InGreek} +- +error + +\u3042\P{^InGreek} +- +error + +\u3042\p{InGreek} +\u3042\u0370 +true \u3042\u0370 0 + +\u3042[\p{InGreek}]\u3044 +\u3042\u0370\u3044 +true \u3042\u0370\u3044 0 + +\u3042[\P{InGreek}]\u3044 +\u3042\u0370\u3044 +false 0 + +\u3042[\P{InGreek}]\u3044 +\u3042\u3043\u3044 +true \u3042\u3043\u3044 0 + +\u3042[{^InGreek}]\u3044 +\u3042n\u3044 +true \u3042n\u3044 0 + +\u3042[{^InGreek}]\u3044 +\u3042\u305B\u3044 +false 0 + +\u3042[\p{^InGreek}]\u3044 +- +error + +\u3042[\P{^InGreek}]\u3044 +- +error + +\u3042[\p{InGreek}] +\u3042\u0370 +true \u3042\u0370 0 + +\u3042[r\p{InGreek}]\u3044 +\u3042r\u3044 +true \u3042r\u3044 0 + +\u3042[\p{InGreek}r]\u3044 +\u3042r\u3044 +true \u3042r\u3044 0 + +\u3042[r\p{InGreek}]\u3044 +\u3042r\u3044 +true \u3042r\u3044 0 + +\u3042[^\p{InGreek}]\u3044 +\u3042\u0370\u3044 +false 0 + +\u3042[^\P{InGreek}]\u3044 +\u3042\u0370\u3044 +true \u3042\u0370\u3044 0 + +\u3042[\p{InGreek}&&[^\u0370]]\u3044 +\u3042\u0370\u3044 +false 0 + +// Test the dot metacharacter +\u3042.\u3044.+ +\u3042#\u3044%& +true \u3042#\u3044%& 0 + +\u3042\u3043. +\u3042\u3043\n +false 0 + +(?s)\u3042\u3043. +\u3042\u3043\n +true \u3042\u3043\n 0 + +\u3042[\p{L}&&[\P{InGreek}]]\u3044 +\u3042\u6000\u3044 +true \u3042\u6000\u3044 0 + +\u3042[\p{L}&&[\P{InGreek}]]\u3044 +\u3042r\u3044 +true \u3042r\u3044 0 + +\u3042[\p{L}&&[\P{InGreek}]]\u3044 +\u3042\u0370\u3044 +false 0 + +\u3042\p{InGreek}\u3044 +\u3042\u0370\u3044 +true \u3042\u0370\u3044 0 + +\u3042\p{Sc} +\u3042$ +true \u3042$ 0 + +\W\w\W +rrrr#\u3048\u3048\u3048 +false 0 + +\u3042\u3043\u3044[\s\u3045\u3046\u3047]* +\u3042\u3043\u3044 \u3045\u3046\u3047 +true \u3042\u3043\u3044 \u3045\u3046\u3047 0 + +\u3042\u3043\u3044[\s\u305A-\u305B]* +\u3042\u3043\u3044 \u305A \u305B +true \u3042\u3043\u3044 \u305A \u305B 0 + +\u3042\u3043\u3044[\u3042-\u3045\s\u304e-\u3051]* +\u3042\u3043\u3044\u3042\u3042 \u304e\u304f \u3051 +true \u3042\u3043\u3044\u3042\u3042 \u304e\u304f \u3051 0 + +// Test the whitespace escape sequence +\u3042\u3043\s\u3044 +\u3042\u3043 \u3044 +true \u3042\u3043 \u3044 0 + +\s\s\s +\u3043l\u3042\u3049 \u3046rr +false 0 + +\S\S\s +\u3043l\u3042\u3049 \u3046rr +true \u3042\u3049 0 + +// Test the digit escape sequence +\u3042\u3043\d\u3044 +\u3042\u30439\u3044 +true \u3042\u30439\u3044 0 + +\d\d\d +\u3043l\u3042\u304945 +false 0 + +// Test the caret metacharacter +^\u3042\u3043\u3044 +\u3042\u3043\u3044\u3045\u3046\u3047 +true \u3042\u3043\u3044 0 + +^\u3042\u3043\u3044 +\u3043\u3044\u3045\u3042\u3043\u3044 +false 0 + +// Greedy ? metacharacter +\u3042?\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3043 0 + +\u3042?\u3043 +\u3043 +true \u3043 0 + +\u3042?\u3043 +\u3042\u3042\u3042\u3044\u3044\u3044 +false 0 + +.?\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3043 0 + +// Reluctant ? metacharacter +\u3042??\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3043 0 + +\u3042??\u3043 +\u3043 +true \u3043 0 + +\u3042??\u3043 +\u3042\u3042\u3042\u3044\u3044\u3044 +false 0 + +.??\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3043 0 + +// Possessive ? metacharacter +\u3042?+\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3043 0 + +\u3042?+\u3043 +\u3043 +true \u3043 0 + +\u3042?+\u3043 +\u3042\u3042\u3042\u3044\u3044\u3044 +false 0 + +.?+\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3043 0 + +// Greedy + metacharacter +\u3042+\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3042\u3042\u3042\u3043 0 + +\u3042+\u3043 +\u3043 +false 0 + +\u3042+\u3043 +\u3042\u3042\u3042\u3044\u3044\u3044 +false 0 + +.+\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3042\u3042\u3042\u3043 0 + +// Reluctant + metacharacter +\u3042+?\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3042\u3042\u3042\u3043 0 + +\u3042+?\u3043 +\u3043 +false 0 + +\u3042+?\u3043 +\u3042\u3042\u3042\u3044\u3044\u3044 +false 0 + +.+?\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3042\u3042\u3042\u3043 0 + +// Possessive + metacharacter +\u3042++\u3043 +\u3042\u3042\u3042\u3042\u3043 +true \u3042\u3042\u3042\u3042\u3043 0 + +\u3042++\u3043 +\u3043 +false 0 + +\u3042++\u3043 +\u3042\u3042\u3042\u3044\u3044\u3044 +false 0 + +.++\u3043 +\u3042\u3042\u3042\u3042\u3043 +false 0 + +// Greedy Repetition +\u3042{2,3} +\u3042 +false 0 + +\u3042{2,3} +\u3042\u3042 +true \u3042\u3042 0 + +\u3042{2,3} +\u3042\u3042\u3042 +true \u3042\u3042\u3042 0 + +\u3042{2,3} +\u3042\u3042\u3042\u3042 +true \u3042\u3042\u3042 0 + +\u3042{3,} +\u305B\u305B\u305B\u3042\u3042\u3042\u3042\u305B\u305B\u305B +true \u3042\u3042\u3042\u3042 0 + +\u3042{3,} +\u305B\u305B\u305B\u3042\u3042\u305B\u305B\u305B +false 0 + +// Reluctant Repetition +\u3042{2,3}? +\u3042 +false 0 + +\u3042{2,3}? +\u3042\u3042 +true \u3042\u3042 0 + +\u3042{2,3}? +\u3042\u3042\u3042 +true \u3042\u3042 0 + +\u3042{2,3}? +\u3042\u3042\u3042\u3042 +true \u3042\u3042 0 + +// Zero width Positive lookahead +\u3042\u3043\u3044(?=\u3045) +\u305B\u305B\u305B\u3042\u3043\u3044\u3045 +true \u3042\u3043\u3044 0 + +\u3042\u3043\u3044(?=\u3045) +\u305B\u305B\u305B\u3042\u3043\u3044\u3046\u3045 +false 0 + +// Zero width Negative lookahead +\u3042\u3043\u3044(?!\u3045) +\u305B\u305B\u3042\u3043\u3044\u3045 +false 0 + +\u3042\u3043\u3044(?!\u3045) +\u305B\u305B\u3042\u3043\u3044\u3046\u3045 +true \u3042\u3043\u3044 0 + +// Zero width Positive lookbehind +\u3042(?<=\u3042) +###\u3042\u3043\u3044 +true \u3042 0 + +\u3042(?<=\u3042) +###\u3043\u3044### +false 0 + +// Zero width Negative lookbehind +(?3 +// So that the BM optimization is part of test +\Q***\E\u3042\u3043\u3044 +***\u3042\u3043\u3044 +true ***\u3042\u3043\u3044 0 + +\u3043l\Q***\E\u3042\u3043\u3044 +\u3043l***\u3042\u3043\u3044 +true \u3043l***\u3042\u3043\u3044 0 + +\Q***\u3042\u3043\u3044 +***\u3042\u3043\u3044 +true ***\u3042\u3043\u3044 0 + +\u3043l\u3042\u3049\Q***\E\u3042\u3043\u3044 +\u3043l\u3042\u3049***\u3042\u3043\u3044 +true \u3043l\u3042\u3049***\u3042\u3043\u3044 0 + +\Q***\u3042\u3043\u3044 +***\u3042\u3043\u3044 +true ***\u3042\u3043\u3044 0 + +\Q*\u3042\u3043 +*\u3042\u3043 +true *\u3042\u3043 0 + +\u3043l\u3042\u3049\Q***\u3042\u3043\u3044 +\u3043l\u3042\u3049***\u3042\u3043\u3044 +true \u3043l\u3042\u3049***\u3042\u3043\u3044 0 + +\u3043l\u3042\Q***\u3042\u3043\u3044 +\u3043l\u3042***\u3042\u3043\u3044 +true \u3043l\u3042***\u3042\u3043\u3044 0 + +[\043]+ +\u3043l\u3042\u3049\u3043l\u3042\u3049#\u3043le\u3044\u3049 +true # 0 + +[\042-\044]+ +\u3043l\u3042\u3049\u3043l\u3042\u3049#\u3043le\u3044\u3049 +true # 0 + +[\u1234-\u1236] +\u3043l\u3042\u3049\u3043l\u3042\u3049\u1235\u3043le\u3044\u3049 +true \u1235 0 + +[^\043]* +\u3043l\u3042\u3049\u3043l\u3042\u3049#\u3043le\u3044\u3049 +true \u3043l\u3042\u3049\u3043l\u3042\u3049 0 diff --git a/jdk/test/java/util/regex/RegExTest.java b/jdk/test/java/util/regex/RegExTest.java new file mode 100644 index 00000000000..29d8b55c437 --- /dev/null +++ b/jdk/test/java/util/regex/RegExTest.java @@ -0,0 +1,3511 @@ +/* + * Copyright 1999-2009 Sun Microsystems, Inc. All Rights Reserved. + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This code is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 only, as + * published by the Free Software Foundation. Sun designates this + * particular file as subject to the "Classpath" exception as provided + * by Sun in the LICENSE file that accompanied this code. + * + * This code is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * version 2 for more details (a copy is included in the LICENSE file that + * accompanied this code). + * + * You should have received a copy of the GNU General Public License version + * 2 along with this work; if not, write to the Free Software Foundation, + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, + * CA 95054 USA or visit www.sun.com if you need additional information or + * have any questions. + */ + +/** + * @test + * @summary tests RegExp framework + * @author Mike McCloskey + * @bug 4481568 4482696 4495089 4504687 4527731 4599621 4631553 4619345 + * 4630911 4672616 4711773 4727935 4750573 4792284 4803197 4757029 4808962 + * 4872664 4803179 4892980 4900747 4945394 4938995 4979006 4994840 4997476 + * 5013885 5003322 4988891 5098443 5110268 6173522 4829857 5027748 6376940 + * 6358731 6178785 6284152 6231989 6497148 6486934 6233084 6504326 6635133 + * 6350801 6676425 + */ + +import java.util.regex.*; +import java.util.Random; +import java.io.*; +import java.util.*; +import java.nio.CharBuffer; + +/** + * This is a test class created to check the operation of + * the Pattern and Matcher classes. + */ +public class RegExTest { + + private static Random generator = new Random(); + private static boolean failure = false; + private static int failCount = 0; + + /** + * Main to interpret arguments and run several tests. + * + */ + public static void main(String[] args) throws Exception { + // Most of the tests are in a file + processFile("TestCases.txt"); + //processFile("PerlCases.txt"); + processFile("BMPTestCases.txt"); + processFile("SupplementaryTestCases.txt"); + + // These test many randomly generated char patterns + bm(); + slice(); + + // These are hard to put into the file + escapes(); + blankInput(); + + // Substitition tests on randomly generated sequences + globalSubstitute(); + stringbufferSubstitute(); + substitutionBasher(); + + // Canonical Equivalence + ceTest(); + + // Anchors + anchorTest(); + + // boolean match calls + matchesTest(); + lookingAtTest(); + + // Pattern API + patternMatchesTest(); + + // Misc + lookbehindTest(); + nullArgumentTest(); + backRefTest(); + groupCaptureTest(); + caretTest(); + charClassTest(); + emptyPatternTest(); + findIntTest(); + group0Test(); + longPatternTest(); + octalTest(); + ampersandTest(); + negationTest(); + splitTest(); + appendTest(); + caseFoldingTest(); + commentsTest(); + unixLinesTest(); + replaceFirstTest(); + gTest(); + zTest(); + serializeTest(); + reluctantRepetitionTest(); + multilineDollarTest(); + dollarAtEndTest(); + caretBetweenTerminatorsTest(); + // This RFE rejected in Tiger numOccurrencesTest(); + javaCharClassTest(); + nonCaptureRepetitionTest(); + notCapturedGroupCurlyMatchTest(); + escapedSegmentTest(); + literalPatternTest(); + literalReplacementTest(); + regionTest(); + toStringTest(); + negatedCharClassTest(); + findFromTest(); + boundsTest(); + unicodeWordBoundsTest(); + caretAtEndTest(); + wordSearchTest(); + hitEndTest(); + toMatchResultTest(); + surrogatesInClassTest(); + namedGroupCaptureTest(); + + if (failure) + throw new RuntimeException("Failure in the RE handling."); + else + System.err.println("OKAY: All tests passed."); + } + + // Utility functions + + private static String getRandomAlphaString(int length) { + StringBuffer buf = new StringBuffer(length); + for (int i=0; i 0) + failure = true; + failCount = 0; + } + + /** + * Converts ASCII alphabet characters [A-Za-z] in the given 's' to + * supplementary characters. This method does NOT fully take care + * of the regex syntax. + */ + private static String toSupplementaries(String s) { + int length = s.length(); + StringBuffer sb = new StringBuffer(length * 2); + + for (int i = 0; i < length; ) { + char c = s.charAt(i++); + if (c == '\\') { + sb.append(c); + if (i < length) { + c = s.charAt(i++); + sb.append(c); + if (c == 'u') { + // assume no syntax error + sb.append(s.charAt(i++)); + sb.append(s.charAt(i++)); + sb.append(s.charAt(i++)); + sb.append(s.charAt(i++)); + } + } + } else if ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z')) { + sb.append('\ud800').append((char)('\udc00'+c)); + } else { + sb.append(c); + } + } + return sb.toString(); + } + + // Regular expression tests + + // This is for bug 6178785 + // Test if an expected NPE gets thrown when passing in a null argument + private static boolean check(Runnable test) { + try { + test.run(); + failCount++; + return false; + } catch (NullPointerException npe) { + return true; + } + } + + private static void nullArgumentTest() { + check(new Runnable() { public void run() { Pattern.compile(null); }}); + check(new Runnable() { public void run() { Pattern.matches(null, null); }}); + check(new Runnable() { public void run() { Pattern.matches("xyz", null);}}); + check(new Runnable() { public void run() { Pattern.quote(null);}}); + check(new Runnable() { public void run() { Pattern.compile("xyz").split(null);}}); + check(new Runnable() { public void run() { Pattern.compile("xyz").matcher(null);}}); + + final Matcher m = Pattern.compile("xyz").matcher("xyz"); + m.matches(); + check(new Runnable() { public void run() { m.appendTail(null);}}); + check(new Runnable() { public void run() { m.replaceAll(null);}}); + check(new Runnable() { public void run() { m.replaceFirst(null);}}); + check(new Runnable() { public void run() { m.appendReplacement(null, null);}}); + check(new Runnable() { public void run() { m.reset(null);}}); + check(new Runnable() { public void run() { Matcher.quoteReplacement(null);}}); + //check(new Runnable() { public void run() { m.usePattern(null);}}); + + report("Null Argument"); + } + + // This is for bug6635133 + // Test if surrogate pair in Unicode escapes can be handled correctly. + private static void surrogatesInClassTest() throws Exception { + Pattern pattern = Pattern.compile("[\\ud834\\udd21-\\ud834\\udd24]"); + Matcher matcher = pattern.matcher("\ud834\udd22"); + if (!matcher.find()) + failCount++; + } + + // This is for bug 4988891 + // Test toMatchResult to see that it is a copy of the Matcher + // that is not affected by subsequent operations on the original + private static void toMatchResultTest() throws Exception { + Pattern pattern = Pattern.compile("squid"); + Matcher matcher = pattern.matcher( + "agiantsquidofdestinyasmallsquidoffate"); + matcher.find(); + int matcherStart1 = matcher.start(); + MatchResult mr = matcher.toMatchResult(); + if (mr == matcher) + failCount++; + int resultStart1 = mr.start(); + if (matcherStart1 != resultStart1) + failCount++; + matcher.find(); + int matcherStart2 = matcher.start(); + int resultStart2 = mr.start(); + if (matcherStart2 == resultStart2) + failCount++; + if (resultStart1 != resultStart2) + failCount++; + MatchResult mr2 = matcher.toMatchResult(); + if (mr == mr2) + failCount++; + if (mr2.start() != matcherStart2) + failCount++; + report("toMatchResult is a copy"); + } + + // This is for bug 5013885 + // Must test a slice to see if it reports hitEnd correctly + private static void hitEndTest() throws Exception { + // Basic test of Slice node + Pattern p = Pattern.compile("^squidattack"); + Matcher m = p.matcher("squack"); + m.find(); + if (m.hitEnd()) + failCount++; + m.reset("squid"); + m.find(); + if (!m.hitEnd()) + failCount++; + + // Test Slice, SliceA and SliceU nodes + for (int i=0; i<3; i++) { + int flags = 0; + if (i==1) flags = Pattern.CASE_INSENSITIVE; + if (i==2) flags = Pattern.UNICODE_CASE; + p = Pattern.compile("^abc", flags); + m = p.matcher("ad"); + m.find(); + if (m.hitEnd()) + failCount++; + m.reset("ab"); + m.find(); + if (!m.hitEnd()) + failCount++; + } + + // Test Boyer-Moore node + p = Pattern.compile("catattack"); + m = p.matcher("attack"); + m.find(); + if (!m.hitEnd()) + failCount++; + + p = Pattern.compile("catattack"); + m = p.matcher("attackattackattackcatatta"); + m.find(); + if (!m.hitEnd()) + failCount++; + + report("hitEnd from a Slice"); + } + + // This is for bug 4997476 + // It is weird code submitted by customer demonstrating a regression + private static void wordSearchTest() throws Exception { + String testString = new String("word1 word2 word3"); + Pattern p = Pattern.compile("\\b"); + Matcher m = p.matcher(testString); + int position = 0; + int start = 0; + while (m.find(position)) { + start = m.start(); + if (start == testString.length()) + break; + if (m.find(start+1)) { + position = m.start(); + } else { + position = testString.length(); + } + if (testString.substring(start, position).equals(" ")) + continue; + if (!testString.substring(start, position-1).startsWith("word")) + failCount++; + } + report("Customer word search"); + } + + // This is for bug 4994840 + private static void caretAtEndTest() throws Exception { + // Problem only occurs with multiline patterns + // containing a beginning-of-line caret "^" followed + // by an expression that also matches the empty string. + Pattern pattern = Pattern.compile("^x?", Pattern.MULTILINE); + Matcher matcher = pattern.matcher("\r"); + matcher.find(); + matcher.find(); + report("Caret at end"); + } + + // This test is for 4979006 + // Check to see if word boundary construct properly handles unicode + // non spacing marks + private static void unicodeWordBoundsTest() throws Exception { + String spaces = " "; + String wordChar = "a"; + String nsm = "\u030a"; + + assert (Character.getType('\u030a') == Character.NON_SPACING_MARK); + + Pattern pattern = Pattern.compile("\\b"); + Matcher matcher = pattern.matcher(""); + // S=other B=word character N=non spacing mark .=word boundary + // SS.BB.SS + String input = spaces + wordChar + wordChar + spaces; + twoFindIndexes(input, matcher, 2, 4); + // SS.BBN.SS + input = spaces + wordChar +wordChar + nsm + spaces; + twoFindIndexes(input, matcher, 2, 5); + // SS.BN.SS + input = spaces + wordChar + nsm + spaces; + twoFindIndexes(input, matcher, 2, 4); + // SS.BNN.SS + input = spaces + wordChar + nsm + nsm + spaces; + twoFindIndexes(input, matcher, 2, 5); + // SSN.BB.SS + input = spaces + nsm + wordChar + wordChar + spaces; + twoFindIndexes(input, matcher, 3, 5); + // SS.BNB.SS + input = spaces + wordChar + nsm + wordChar + spaces; + twoFindIndexes(input, matcher, 2, 5); + // SSNNSS + input = spaces + nsm + nsm + spaces; + matcher.reset(input); + if (matcher.find()) + failCount++; + // SSN.BBN.SS + input = spaces + nsm + wordChar + wordChar + nsm + spaces; + twoFindIndexes(input, matcher, 3, 6); + + report("Unicode word boundary"); + } + + private static void twoFindIndexes(String input, Matcher matcher, int a, + int b) throws Exception + { + matcher.reset(input); + matcher.find(); + if (matcher.start() != a) + failCount++; + matcher.find(); + if (matcher.start() != b) + failCount++; + } + + // This test is for 6284152 + static void check(String regex, String input, String[] expected) { + List result = new ArrayList(); + Pattern p = Pattern.compile(regex); + Matcher m = p.matcher(input); + while (m.find()) { + result.add(m.group()); + } + if (!Arrays.asList(expected).equals(result)) + failCount++; + } + + private static void lookbehindTest() throws Exception { + //Positive + check("(?<=%.{0,5})foo\\d", + "%foo1\n%bar foo2\n%bar foo3\n%blahblah foo4\nfoo5", + new String[]{"foo1", "foo2", "foo3"}); + + //boundary at end of the lookbehind sub-regex should work consistently + //with the boundary just after the lookbehind sub-regex + check("(?<=.*\\b)foo", "abcd foo", new String[]{"foo"}); + check("(?<=.*)\\bfoo", "abcd foo", new String[]{"foo"}); + check("(?]"); + Matcher matcher = pattern.matcher("\u203A"); + if (!matcher.matches()) + failCount++; + pattern = Pattern.compile("[^fr]"); + matcher = pattern.matcher("a"); + if (!matcher.find()) + failCount++; + matcher.reset("\u203A"); + if (!matcher.find()) + failCount++; + String s = "for"; + String result[] = s.split("[^fr]"); + if (!result[0].equals("f")) + failCount++; + if (!result[1].equals("r")) + failCount++; + s = "f\u203Ar"; + result = s.split("[^fr]"); + if (!result[0].equals("f")) + failCount++; + if (!result[1].equals("r")) + failCount++; + + // Test adding to bits, subtracting a node, then adding to bits again + pattern = Pattern.compile("[^f\u203Ar]"); + matcher = pattern.matcher("a"); + if (!matcher.find()) + failCount++; + matcher.reset("f"); + if (matcher.find()) + failCount++; + matcher.reset("\u203A"); + if (matcher.find()) + failCount++; + matcher.reset("r"); + if (matcher.find()) + failCount++; + matcher.reset("\u203B"); + if (!matcher.find()) + failCount++; + + // Test subtracting a node, adding to bits, subtracting again + pattern = Pattern.compile("[^\u203Ar\u203B]"); + matcher = pattern.matcher("a"); + if (!matcher.find()) + failCount++; + matcher.reset("\u203A"); + if (matcher.find()) + failCount++; + matcher.reset("r"); + if (matcher.find()) + failCount++; + matcher.reset("\u203B"); + if (matcher.find()) + failCount++; + matcher.reset("\u203C"); + if (!matcher.find()) + failCount++; + + report("Negated Character Class"); + } + + // This test is for 4628291 + private static void toStringTest() throws Exception { + Pattern pattern = Pattern.compile("b+"); + if (pattern.toString() != "b+") + failCount++; + Matcher matcher = pattern.matcher("aaabbbccc"); + String matcherString = matcher.toString(); // unspecified + matcher.find(); + matcherString = matcher.toString(); // unspecified + matcher.region(0,3); + matcherString = matcher.toString(); // unspecified + matcher.reset(); + matcherString = matcher.toString(); // unspecified + report("toString"); + } + + // This test is for 4808962 + private static void literalPatternTest() throws Exception { + int flags = Pattern.LITERAL; + + Pattern pattern = Pattern.compile("abc\\t$^", flags); + check(pattern, "abc\\t$^", true); + + pattern = Pattern.compile(Pattern.quote("abc\\t$^")); + check(pattern, "abc\\t$^", true); + + pattern = Pattern.compile("\\Qa^$bcabc\\E", flags); + check(pattern, "\\Qa^$bcabc\\E", true); + check(pattern, "a^$bcabc", false); + + pattern = Pattern.compile("\\\\Q\\\\E"); + check(pattern, "\\Q\\E", true); + + pattern = Pattern.compile("\\Qabc\\Eefg\\\\Q\\\\Ehij"); + check(pattern, "abcefg\\Q\\Ehij", true); + + pattern = Pattern.compile("\\\\\\Q\\\\E"); + check(pattern, "\\\\\\\\", true); + + pattern = Pattern.compile(Pattern.quote("\\Qa^$bcabc\\E")); + check(pattern, "\\Qa^$bcabc\\E", true); + check(pattern, "a^$bcabc", false); + + pattern = Pattern.compile(Pattern.quote("\\Qabc\\Edef")); + check(pattern, "\\Qabc\\Edef", true); + check(pattern, "abcdef", false); + + pattern = Pattern.compile(Pattern.quote("abc\\Edef")); + check(pattern, "abc\\Edef", true); + check(pattern, "abcdef", false); + + pattern = Pattern.compile(Pattern.quote("\\E")); + check(pattern, "\\E", true); + + pattern = Pattern.compile("((((abc.+?:)", flags); + check(pattern, "((((abc.+?:)", true); + + flags |= Pattern.MULTILINE; + + pattern = Pattern.compile("^cat$", flags); + check(pattern, "abc^cat$def", true); + check(pattern, "cat", false); + + flags |= Pattern.CASE_INSENSITIVE; + + pattern = Pattern.compile("abcdef", flags); + check(pattern, "ABCDEF", true); + check(pattern, "AbCdEf", true); + + flags |= Pattern.DOTALL; + + pattern = Pattern.compile("a...b", flags); + check(pattern, "A...b", true); + check(pattern, "Axxxb", false); + + flags |= Pattern.CANON_EQ; + + Pattern p = Pattern.compile("testa\u030a", flags); + check(pattern, "testa\u030a", false); + check(pattern, "test\u00e5", false); + + // Supplementary character test + flags = Pattern.LITERAL; + + pattern = Pattern.compile(toSupplementaries("abc\\t$^"), flags); + check(pattern, toSupplementaries("abc\\t$^"), true); + + pattern = Pattern.compile(Pattern.quote(toSupplementaries("abc\\t$^"))); + check(pattern, toSupplementaries("abc\\t$^"), true); + + pattern = Pattern.compile(toSupplementaries("\\Qa^$bcabc\\E"), flags); + check(pattern, toSupplementaries("\\Qa^$bcabc\\E"), true); + check(pattern, toSupplementaries("a^$bcabc"), false); + + pattern = Pattern.compile(Pattern.quote(toSupplementaries("\\Qa^$bcabc\\E"))); + check(pattern, toSupplementaries("\\Qa^$bcabc\\E"), true); + check(pattern, toSupplementaries("a^$bcabc"), false); + + pattern = Pattern.compile(Pattern.quote(toSupplementaries("\\Qabc\\Edef"))); + check(pattern, toSupplementaries("\\Qabc\\Edef"), true); + check(pattern, toSupplementaries("abcdef"), false); + + pattern = Pattern.compile(Pattern.quote(toSupplementaries("abc\\Edef"))); + check(pattern, toSupplementaries("abc\\Edef"), true); + check(pattern, toSupplementaries("abcdef"), false); + + pattern = Pattern.compile(toSupplementaries("((((abc.+?:)"), flags); + check(pattern, toSupplementaries("((((abc.+?:)"), true); + + flags |= Pattern.MULTILINE; + + pattern = Pattern.compile(toSupplementaries("^cat$"), flags); + check(pattern, toSupplementaries("abc^cat$def"), true); + check(pattern, toSupplementaries("cat"), false); + + flags |= Pattern.DOTALL; + + // note: this is case-sensitive. + pattern = Pattern.compile(toSupplementaries("a...b"), flags); + check(pattern, toSupplementaries("a...b"), true); + check(pattern, toSupplementaries("axxxb"), false); + + flags |= Pattern.CANON_EQ; + + String t = toSupplementaries("test"); + p = Pattern.compile(t + "a\u030a", flags); + check(pattern, t + "a\u030a", false); + check(pattern, t + "\u00e5", false); + + report("Literal pattern"); + } + + // This test is for 4803179 + // This test is also for 4808962, replacement parts + private static void literalReplacementTest() throws Exception { + int flags = Pattern.LITERAL; + + Pattern pattern = Pattern.compile("abc", flags); + Matcher matcher = pattern.matcher("zzzabczzz"); + String replaceTest = "$0"; + String result = matcher.replaceAll(replaceTest); + if (!result.equals("zzzabczzz")) + failCount++; + + matcher.reset(); + String literalReplacement = matcher.quoteReplacement(replaceTest); + result = matcher.replaceAll(literalReplacement); + if (!result.equals("zzz$0zzz")) + failCount++; + + matcher.reset(); + replaceTest = "\\t$\\$"; + literalReplacement = matcher.quoteReplacement(replaceTest); + result = matcher.replaceAll(literalReplacement); + if (!result.equals("zzz\\t$\\$zzz")) + failCount++; + + // Supplementary character test + pattern = Pattern.compile(toSupplementaries("abc"), flags); + matcher = pattern.matcher(toSupplementaries("zzzabczzz")); + replaceTest = "$0"; + result = matcher.replaceAll(replaceTest); + if (!result.equals(toSupplementaries("zzzabczzz"))) + failCount++; + + matcher.reset(); + literalReplacement = matcher.quoteReplacement(replaceTest); + result = matcher.replaceAll(literalReplacement); + if (!result.equals(toSupplementaries("zzz$0zzz"))) + failCount++; + + matcher.reset(); + replaceTest = "\\t$\\$"; + literalReplacement = matcher.quoteReplacement(replaceTest); + result = matcher.replaceAll(literalReplacement); + if (!result.equals(toSupplementaries("zzz\\t$\\$zzz"))) + failCount++; + + report("Literal replacement"); + } + + // This test is for 4757029 + private static void regionTest() throws Exception { + Pattern pattern = Pattern.compile("abc"); + Matcher matcher = pattern.matcher("abcdefabc"); + + matcher.region(0,9); + if (!matcher.find()) + failCount++; + if (!matcher.find()) + failCount++; + matcher.region(0,3); + if (!matcher.find()) + failCount++; + matcher.region(3,6); + if (matcher.find()) + failCount++; + matcher.region(0,2); + if (matcher.find()) + failCount++; + + expectRegionFail(matcher, 1, -1); + expectRegionFail(matcher, -1, -1); + expectRegionFail(matcher, -1, 1); + expectRegionFail(matcher, 5, 3); + expectRegionFail(matcher, 5, 12); + expectRegionFail(matcher, 12, 12); + + pattern = Pattern.compile("^abc$"); + matcher = pattern.matcher("zzzabczzz"); + matcher.region(0,9); + if (matcher.find()) + failCount++; + matcher.region(3,6); + if (!matcher.find()) + failCount++; + matcher.region(3,6); + matcher.useAnchoringBounds(false); + if (matcher.find()) + failCount++; + + // Supplementary character test + pattern = Pattern.compile(toSupplementaries("abc")); + matcher = pattern.matcher(toSupplementaries("abcdefabc")); + matcher.region(0,9*2); + if (!matcher.find()) + failCount++; + if (!matcher.find()) + failCount++; + matcher.region(0,3*2); + if (!matcher.find()) + failCount++; + matcher.region(1,3*2); + if (matcher.find()) + failCount++; + matcher.region(3*2,6*2); + if (matcher.find()) + failCount++; + matcher.region(0,2*2); + if (matcher.find()) + failCount++; + matcher.region(0,2*2+1); + if (matcher.find()) + failCount++; + + expectRegionFail(matcher, 1*2, -1); + expectRegionFail(matcher, -1, -1); + expectRegionFail(matcher, -1, 1*2); + expectRegionFail(matcher, 5*2, 3*2); + expectRegionFail(matcher, 5*2, 12*2); + expectRegionFail(matcher, 12*2, 12*2); + + pattern = Pattern.compile(toSupplementaries("^abc$")); + matcher = pattern.matcher(toSupplementaries("zzzabczzz")); + matcher.region(0,9*2); + if (matcher.find()) + failCount++; + matcher.region(3*2,6*2); + if (!matcher.find()) + failCount++; + matcher.region(3*2+1,6*2); + if (matcher.find()) + failCount++; + matcher.region(3*2,6*2-1); + if (matcher.find()) + failCount++; + matcher.region(3*2,6*2); + matcher.useAnchoringBounds(false); + if (matcher.find()) + failCount++; + report("Regions"); + } + + private static void expectRegionFail(Matcher matcher, int index1, + int index2) + { + try { + matcher.region(index1, index2); + failCount++; + } catch (IndexOutOfBoundsException ioobe) { + // Correct result + } catch (IllegalStateException ise) { + // Correct result + } + } + + // This test is for 4803197 + private static void escapedSegmentTest() throws Exception { + + Pattern pattern = Pattern.compile("\\Qdir1\\dir2\\E"); + check(pattern, "dir1\\dir2", true); + + pattern = Pattern.compile("\\Qdir1\\dir2\\\\E"); + check(pattern, "dir1\\dir2\\", true); + + pattern = Pattern.compile("(\\Qdir1\\dir2\\\\E)"); + check(pattern, "dir1\\dir2\\", true); + + // Supplementary character test + pattern = Pattern.compile(toSupplementaries("\\Qdir1\\dir2\\E")); + check(pattern, toSupplementaries("dir1\\dir2"), true); + + pattern = Pattern.compile(toSupplementaries("\\Qdir1\\dir2")+"\\\\E"); + check(pattern, toSupplementaries("dir1\\dir2\\"), true); + + pattern = Pattern.compile(toSupplementaries("(\\Qdir1\\dir2")+"\\\\E)"); + check(pattern, toSupplementaries("dir1\\dir2\\"), true); + + report("Escaped segment"); + } + + // This test is for 4792284 + private static void nonCaptureRepetitionTest() throws Exception { + String input = "abcdefgh;"; + + String[] patterns = new String[] { + "(?:\\w{4})+;", + "(?:\\w{8})*;", + "(?:\\w{2}){2,4};", + "(?:\\w{4}){2,};", // only matches the + ".*?(?:\\w{5})+;", // specified minimum + ".*?(?:\\w{9})*;", // number of reps - OK + "(?:\\w{4})+?;", // lazy repetition - OK + "(?:\\w{4})++;", // possessive repetition - OK + "(?:\\w{2,}?)+;", // non-deterministic - OK + "(\\w{4})+;", // capturing group - OK + }; + + for (int i = 0; i < patterns.length; i++) { + // Check find() + check(patterns[i], 0, input, input, true); + // Check matches() + Pattern p = Pattern.compile(patterns[i]); + Matcher m = p.matcher(input); + + if (m.matches()) { + if (!m.group(0).equals(input)) + failCount++; + } else { + failCount++; + } + } + + report("Non capturing repetition"); + } + + // This test is for 6358731 + private static void notCapturedGroupCurlyMatchTest() throws Exception { + Pattern pattern = Pattern.compile("(abc)+|(abcd)+"); + Matcher matcher = pattern.matcher("abcd"); + if (!matcher.matches() || + matcher.group(1) != null || + !matcher.group(2).equals("abcd")) { + failCount++; + } + report("Not captured GroupCurly"); + } + + // This test is for 4706545 + private static void javaCharClassTest() throws Exception { + for (int i=0; i<1000; i++) { + char c = (char)generator.nextInt(); + check("{javaLowerCase}", c, Character.isLowerCase(c)); + check("{javaUpperCase}", c, Character.isUpperCase(c)); + check("{javaUpperCase}+", c, Character.isUpperCase(c)); + check("{javaTitleCase}", c, Character.isTitleCase(c)); + check("{javaDigit}", c, Character.isDigit(c)); + check("{javaDefined}", c, Character.isDefined(c)); + check("{javaLetter}", c, Character.isLetter(c)); + check("{javaLetterOrDigit}", c, Character.isLetterOrDigit(c)); + check("{javaJavaIdentifierStart}", c, + Character.isJavaIdentifierStart(c)); + check("{javaJavaIdentifierPart}", c, + Character.isJavaIdentifierPart(c)); + check("{javaUnicodeIdentifierStart}", c, + Character.isUnicodeIdentifierStart(c)); + check("{javaUnicodeIdentifierPart}", c, + Character.isUnicodeIdentifierPart(c)); + check("{javaIdentifierIgnorable}", c, + Character.isIdentifierIgnorable(c)); + check("{javaSpaceChar}", c, Character.isSpaceChar(c)); + check("{javaWhitespace}", c, Character.isWhitespace(c)); + check("{javaISOControl}", c, Character.isISOControl(c)); + check("{javaMirrored}", c, Character.isMirrored(c)); + + } + + // Supplementary character test + for (int i=0; i<1000; i++) { + int c = generator.nextInt(Character.MAX_CODE_POINT + - Character.MIN_SUPPLEMENTARY_CODE_POINT) + + Character.MIN_SUPPLEMENTARY_CODE_POINT; + check("{javaLowerCase}", c, Character.isLowerCase(c)); + check("{javaUpperCase}", c, Character.isUpperCase(c)); + check("{javaUpperCase}+", c, Character.isUpperCase(c)); + check("{javaTitleCase}", c, Character.isTitleCase(c)); + check("{javaDigit}", c, Character.isDigit(c)); + check("{javaDefined}", c, Character.isDefined(c)); + check("{javaLetter}", c, Character.isLetter(c)); + check("{javaLetterOrDigit}", c, Character.isLetterOrDigit(c)); + check("{javaJavaIdentifierStart}", c, + Character.isJavaIdentifierStart(c)); + check("{javaJavaIdentifierPart}", c, + Character.isJavaIdentifierPart(c)); + check("{javaUnicodeIdentifierStart}", c, + Character.isUnicodeIdentifierStart(c)); + check("{javaUnicodeIdentifierPart}", c, + Character.isUnicodeIdentifierPart(c)); + check("{javaIdentifierIgnorable}", c, + Character.isIdentifierIgnorable(c)); + check("{javaSpaceChar}", c, Character.isSpaceChar(c)); + check("{javaWhitespace}", c, Character.isWhitespace(c)); + check("{javaISOControl}", c, Character.isISOControl(c)); + check("{javaMirrored}", c, Character.isMirrored(c)); + } + + report("Java character classes"); + } + + // This test is for 4523620 + /* + private static void numOccurrencesTest() throws Exception { + Pattern pattern = Pattern.compile("aaa"); + + if (pattern.numOccurrences("aaaaaa", false) != 2) + failCount++; + if (pattern.numOccurrences("aaaaaa", true) != 4) + failCount++; + + pattern = Pattern.compile("^"); + if (pattern.numOccurrences("aaaaaa", false) != 1) + failCount++; + if (pattern.numOccurrences("aaaaaa", true) != 1) + failCount++; + + report("Number of Occurrences"); + } + */ + + // This test is for 4776374 + private static void caretBetweenTerminatorsTest() throws Exception { + int flags1 = Pattern.DOTALL; + int flags2 = Pattern.DOTALL | Pattern.UNIX_LINES; + int flags3 = Pattern.DOTALL | Pattern.UNIX_LINES | Pattern.MULTILINE; + int flags4 = Pattern.DOTALL | Pattern.MULTILINE; + + check("^....", flags1, "test\ntest", "test", true); + check(".....^", flags1, "test\ntest", "test", false); + check(".....^", flags1, "test\n", "test", false); + check("....^", flags1, "test\r\n", "test", false); + + check("^....", flags2, "test\ntest", "test", true); + check("....^", flags2, "test\ntest", "test", false); + check(".....^", flags2, "test\n", "test", false); + check("....^", flags2, "test\r\n", "test", false); + + check("^....", flags3, "test\ntest", "test", true); + check(".....^", flags3, "test\ntest", "test\n", true); + check(".....^", flags3, "test\u0085test", "test\u0085", false); + check(".....^", flags3, "test\n", "test", false); + check(".....^", flags3, "test\r\n", "test", false); + check("......^", flags3, "test\r\ntest", "test\r\n", true); + + check("^....", flags4, "test\ntest", "test", true); + check(".....^", flags3, "test\ntest", "test\n", true); + check(".....^", flags4, "test\u0085test", "test\u0085", true); + check(".....^", flags4, "test\n", "test\n", false); + check(".....^", flags4, "test\r\n", "test\r", false); + + // Supplementary character test + String t = toSupplementaries("test"); + check("^....", flags1, t+"\n"+t, t, true); + check(".....^", flags1, t+"\n"+t, t, false); + check(".....^", flags1, t+"\n", t, false); + check("....^", flags1, t+"\r\n", t, false); + + check("^....", flags2, t+"\n"+t, t, true); + check("....^", flags2, t+"\n"+t, t, false); + check(".....^", flags2, t+"\n", t, false); + check("....^", flags2, t+"\r\n", t, false); + + check("^....", flags3, t+"\n"+t, t, true); + check(".....^", flags3, t+"\n"+t, t+"\n", true); + check(".....^", flags3, t+"\u0085"+t, t+"\u0085", false); + check(".....^", flags3, t+"\n", t, false); + check(".....^", flags3, t+"\r\n", t, false); + check("......^", flags3, t+"\r\n"+t, t+"\r\n", true); + + check("^....", flags4, t+"\n"+t, t, true); + check(".....^", flags3, t+"\n"+t, t+"\n", true); + check(".....^", flags4, t+"\u0085"+t, t+"\u0085", true); + check(".....^", flags4, t+"\n", t+"\n", false); + check(".....^", flags4, t+"\r\n", t+"\r", false); + + report("Caret between terminators"); + } + + // This test is for 4727935 + private static void dollarAtEndTest() throws Exception { + int flags1 = Pattern.DOTALL; + int flags2 = Pattern.DOTALL | Pattern.UNIX_LINES; + int flags3 = Pattern.DOTALL | Pattern.MULTILINE; + + check("....$", flags1, "test\n", "test", true); + check("....$", flags1, "test\r\n", "test", true); + check(".....$", flags1, "test\n", "test\n", true); + check(".....$", flags1, "test\u0085", "test\u0085", true); + check("....$", flags1, "test\u0085", "test", true); + + check("....$", flags2, "test\n", "test", true); + check(".....$", flags2, "test\n", "test\n", true); + check(".....$", flags2, "test\u0085", "test\u0085", true); + check("....$", flags2, "test\u0085", "est\u0085", true); + + check("....$.blah", flags3, "test\nblah", "test\nblah", true); + check(".....$.blah", flags3, "test\n\nblah", "test\n\nblah", true); + check("....$blah", flags3, "test\nblah", "!!!!", false); + check(".....$blah", flags3, "test\nblah", "!!!!", false); + + // Supplementary character test + String t = toSupplementaries("test"); + String b = toSupplementaries("blah"); + check("....$", flags1, t+"\n", t, true); + check("....$", flags1, t+"\r\n", t, true); + check(".....$", flags1, t+"\n", t+"\n", true); + check(".....$", flags1, t+"\u0085", t+"\u0085", true); + check("....$", flags1, t+"\u0085", t, true); + + check("....$", flags2, t+"\n", t, true); + check(".....$", flags2, t+"\n", t+"\n", true); + check(".....$", flags2, t+"\u0085", t+"\u0085", true); + check("....$", flags2, t+"\u0085", toSupplementaries("est\u0085"), true); + + check("....$."+b, flags3, t+"\n"+b, t+"\n"+b, true); + check(".....$."+b, flags3, t+"\n\n"+b, t+"\n\n"+b, true); + check("....$"+b, flags3, t+"\n"+b, "!!!!", false); + check(".....$"+b, flags3, t+"\n"+b, "!!!!", false); + + report("Dollar at End"); + } + + // This test is for 4711773 + private static void multilineDollarTest() throws Exception { + Pattern findCR = Pattern.compile("$", Pattern.MULTILINE); + Matcher matcher = findCR.matcher("first bit\nsecond bit"); + matcher.find(); + if (matcher.start(0) != 9) + failCount++; + matcher.find(); + if (matcher.start(0) != 20) + failCount++; + + // Supplementary character test + matcher = findCR.matcher(toSupplementaries("first bit\n second bit")); // double BMP chars + matcher.find(); + if (matcher.start(0) != 9*2) + failCount++; + matcher.find(); + if (matcher.start(0) != 20*2) + failCount++; + + report("Multiline Dollar"); + } + + private static void reluctantRepetitionTest() throws Exception { + Pattern p = Pattern.compile("1(\\s\\S+?){1,3}?[\\s,]2"); + check(p, "1 word word word 2", true); + check(p, "1 wor wo w 2", true); + check(p, "1 word word 2", true); + check(p, "1 word 2", true); + check(p, "1 wo w w 2", true); + check(p, "1 wo w 2", true); + check(p, "1 wor w 2", true); + + p = Pattern.compile("([a-z])+?c"); + Matcher m = p.matcher("ababcdefdec"); + check(m, "ababc"); + + // Supplementary character test + p = Pattern.compile(toSupplementaries("([a-z])+?c")); + m = p.matcher(toSupplementaries("ababcdefdec")); + check(m, toSupplementaries("ababc")); + + report("Reluctant Repetition"); + } + + private static void serializeTest() throws Exception { + String patternStr = "(b)"; + String matchStr = "b"; + Pattern pattern = Pattern.compile(patternStr); + ByteArrayOutputStream baos = new ByteArrayOutputStream(); + ObjectOutputStream oos = new ObjectOutputStream(baos); + oos.writeObject(pattern); + oos.close(); + ObjectInputStream ois = new ObjectInputStream( + new ByteArrayInputStream(baos.toByteArray())); + Pattern serializedPattern = (Pattern)ois.readObject(); + ois.close(); + Matcher matcher = serializedPattern.matcher(matchStr); + if (!matcher.matches()) + failCount++; + if (matcher.groupCount() != 1) + failCount++; + + report("Serialization"); + } + + private static void gTest() { + Pattern pattern = Pattern.compile("\\G\\w"); + Matcher matcher = pattern.matcher("abc#x#x"); + matcher.find(); + matcher.find(); + matcher.find(); + if (matcher.find()) + failCount++; + + pattern = Pattern.compile("\\GA*"); + matcher = pattern.matcher("1A2AA3"); + matcher.find(); + if (matcher.find()) + failCount++; + + pattern = Pattern.compile("\\GA*"); + matcher = pattern.matcher("1A2AA3"); + if (!matcher.find(1)) + failCount++; + matcher.find(); + if (matcher.find()) + failCount++; + + report("\\G"); + } + + private static void zTest() { + Pattern pattern = Pattern.compile("foo\\Z"); + // Positives + check(pattern, "foo\u0085", true); + check(pattern, "foo\u2028", true); + check(pattern, "foo\u2029", true); + check(pattern, "foo\n", true); + check(pattern, "foo\r", true); + check(pattern, "foo\r\n", true); + // Negatives + check(pattern, "fooo", false); + check(pattern, "foo\n\r", false); + + pattern = Pattern.compile("foo\\Z", Pattern.UNIX_LINES); + // Positives + check(pattern, "foo", true); + check(pattern, "foo\n", true); + // Negatives + check(pattern, "foo\r", false); + check(pattern, "foo\u0085", false); + check(pattern, "foo\u2028", false); + check(pattern, "foo\u2029", false); + + report("\\Z"); + } + + private static void replaceFirstTest() { + Pattern pattern = Pattern.compile("(ab)(c*)"); + Matcher matcher = pattern.matcher("abccczzzabcczzzabccc"); + if (!matcher.replaceFirst("test").equals("testzzzabcczzzabccc")) + failCount++; + + matcher.reset("zzzabccczzzabcczzzabccczzz"); + if (!matcher.replaceFirst("test").equals("zzztestzzzabcczzzabccczzz")) + failCount++; + + matcher.reset("zzzabccczzzabcczzzabccczzz"); + String result = matcher.replaceFirst("$1"); + if (!result.equals("zzzabzzzabcczzzabccczzz")) + failCount++; + + matcher.reset("zzzabccczzzabcczzzabccczzz"); + result = matcher.replaceFirst("$2"); + if (!result.equals("zzzccczzzabcczzzabccczzz")) + failCount++; + + pattern = Pattern.compile("a*"); + matcher = pattern.matcher("aaaaaaaaaa"); + if (!matcher.replaceFirst("test").equals("test")) + failCount++; + + pattern = Pattern.compile("a+"); + matcher = pattern.matcher("zzzaaaaaaaaaa"); + if (!matcher.replaceFirst("test").equals("zzztest")) + failCount++; + + // Supplementary character test + pattern = Pattern.compile(toSupplementaries("(ab)(c*)")); + matcher = pattern.matcher(toSupplementaries("abccczzzabcczzzabccc")); + if (!matcher.replaceFirst(toSupplementaries("test")) + .equals(toSupplementaries("testzzzabcczzzabccc"))) + failCount++; + + matcher.reset(toSupplementaries("zzzabccczzzabcczzzabccczzz")); + if (!matcher.replaceFirst(toSupplementaries("test")). + equals(toSupplementaries("zzztestzzzabcczzzabccczzz"))) + failCount++; + + matcher.reset(toSupplementaries("zzzabccczzzabcczzzabccczzz")); + result = matcher.replaceFirst("$1"); + if (!result.equals(toSupplementaries("zzzabzzzabcczzzabccczzz"))) + failCount++; + + matcher.reset(toSupplementaries("zzzabccczzzabcczzzabccczzz")); + result = matcher.replaceFirst("$2"); + if (!result.equals(toSupplementaries("zzzccczzzabcczzzabccczzz"))) + failCount++; + + pattern = Pattern.compile(toSupplementaries("a*")); + matcher = pattern.matcher(toSupplementaries("aaaaaaaaaa")); + if (!matcher.replaceFirst(toSupplementaries("test")).equals(toSupplementaries("test"))) + failCount++; + + pattern = Pattern.compile(toSupplementaries("a+")); + matcher = pattern.matcher(toSupplementaries("zzzaaaaaaaaaa")); + if (!matcher.replaceFirst(toSupplementaries("test")).equals(toSupplementaries("zzztest"))) + failCount++; + + report("Replace First"); + } + + private static void unixLinesTest() { + Pattern pattern = Pattern.compile(".*"); + Matcher matcher = pattern.matcher("aa\u2028blah"); + matcher.find(); + if (!matcher.group(0).equals("aa")) + failCount++; + + pattern = Pattern.compile(".*", Pattern.UNIX_LINES); + matcher = pattern.matcher("aa\u2028blah"); + matcher.find(); + if (!matcher.group(0).equals("aa\u2028blah")) + failCount++; + + pattern = Pattern.compile("[az]$", + Pattern.MULTILINE | Pattern.UNIX_LINES); + matcher = pattern.matcher("aa\u2028zz"); + check(matcher, "a\u2028", false); + + // Supplementary character test + pattern = Pattern.compile(".*"); + matcher = pattern.matcher(toSupplementaries("aa\u2028blah")); + matcher.find(); + if (!matcher.group(0).equals(toSupplementaries("aa"))) + failCount++; + + pattern = Pattern.compile(".*", Pattern.UNIX_LINES); + matcher = pattern.matcher(toSupplementaries("aa\u2028blah")); + matcher.find(); + if (!matcher.group(0).equals(toSupplementaries("aa\u2028blah"))) + failCount++; + + pattern = Pattern.compile(toSupplementaries("[az]$"), + Pattern.MULTILINE | Pattern.UNIX_LINES); + matcher = pattern.matcher(toSupplementaries("aa\u2028zz")); + check(matcher, toSupplementaries("a\u2028"), false); + + report("Unix Lines"); + } + + private static void commentsTest() { + int flags = Pattern.COMMENTS; + + Pattern pattern = Pattern.compile("aa \\# aa", flags); + Matcher matcher = pattern.matcher("aa#aa"); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile("aa # blah", flags); + matcher = pattern.matcher("aa"); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile("aa blah", flags); + matcher = pattern.matcher("aablah"); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile("aa # blah blech ", flags); + matcher = pattern.matcher("aa"); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile("aa # blah\n ", flags); + matcher = pattern.matcher("aa"); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile("aa # blah\nbc # blech", flags); + matcher = pattern.matcher("aabc"); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile("aa # blah\nbc# blech", flags); + matcher = pattern.matcher("aabc"); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile("aa # blah\nbc\\# blech", flags); + matcher = pattern.matcher("aabc#blech"); + if (!matcher.matches()) + failCount++; + + // Supplementary character test + pattern = Pattern.compile(toSupplementaries("aa \\# aa"), flags); + matcher = pattern.matcher(toSupplementaries("aa#aa")); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile(toSupplementaries("aa # blah"), flags); + matcher = pattern.matcher(toSupplementaries("aa")); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile(toSupplementaries("aa blah"), flags); + matcher = pattern.matcher(toSupplementaries("aablah")); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile(toSupplementaries("aa # blah blech "), flags); + matcher = pattern.matcher(toSupplementaries("aa")); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile(toSupplementaries("aa # blah\n "), flags); + matcher = pattern.matcher(toSupplementaries("aa")); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile(toSupplementaries("aa # blah\nbc # blech"), flags); + matcher = pattern.matcher(toSupplementaries("aabc")); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile(toSupplementaries("aa # blah\nbc# blech"), flags); + matcher = pattern.matcher(toSupplementaries("aabc")); + if (!matcher.matches()) + failCount++; + + pattern = Pattern.compile(toSupplementaries("aa # blah\nbc\\# blech"), flags); + matcher = pattern.matcher(toSupplementaries("aabc#blech")); + if (!matcher.matches()) + failCount++; + + report("Comments"); + } + + private static void caseFoldingTest() { // bug 4504687 + int flags = Pattern.CASE_INSENSITIVE | Pattern.UNICODE_CASE; + Pattern pattern = Pattern.compile("aa", flags); + Matcher matcher = pattern.matcher("ab"); + if (matcher.matches()) + failCount++; + + pattern = Pattern.compile("aA", flags); + matcher = pattern.matcher("ab"); + if (matcher.matches()) + failCount++; + + pattern = Pattern.compile("aa", flags); + matcher = pattern.matcher("aB"); + if (matcher.matches()) + failCount++; + matcher = pattern.matcher("Ab"); + if (matcher.matches()) + failCount++; + + // ASCII "a" + // Latin-1 Supplement "a" + grave + // Cyrillic "a" + String[] patterns = new String[] { + //single + "a", "\u00e0", "\u0430", + //slice + "ab", "\u00e0\u00e1", "\u0430\u0431", + //class single + "[a]", "[\u00e0]", "[\u0430]", + //class range + "[a-b]", "[\u00e0-\u00e5]", "[\u0430-\u0431]", + //back reference + "(a)\\1", "(\u00e0)\\1", "(\u0430)\\1" + }; + + String[] texts = new String[] { + "A", "\u00c0", "\u0410", + "AB", "\u00c0\u00c1", "\u0410\u0411", + "A", "\u00c0", "\u0410", + "B", "\u00c2", "\u0411", + "aA", "\u00e0\u00c0", "\u0430\u0410" + }; + + boolean[] expected = new boolean[] { + true, false, false, + true, false, false, + true, false, false, + true, false, false, + true, false, false + }; + + flags = Pattern.CASE_INSENSITIVE; + for (int i = 0; i < patterns.length; i++) { + pattern = Pattern.compile(patterns[i], flags); + matcher = pattern.matcher(texts[i]); + if (matcher.matches() != expected[i]) { + System.out.println("<1> Failed at " + i); + failCount++; + } + } + + flags = Pattern.CASE_INSENSITIVE | Pattern.UNICODE_CASE; + for (int i = 0; i < patterns.length; i++) { + pattern = Pattern.compile(patterns[i], flags); + matcher = pattern.matcher(texts[i]); + if (!matcher.matches()) { + System.out.println("<2> Failed at " + i); + failCount++; + } + } + // flag unicode_case alone should do nothing + flags = Pattern.UNICODE_CASE; + for (int i = 0; i < patterns.length; i++) { + pattern = Pattern.compile(patterns[i], flags); + matcher = pattern.matcher(texts[i]); + if (matcher.matches()) { + System.out.println("<3> Failed at " + i); + failCount++; + } + } + + // Special cases: i, I, u+0131 and u+0130 + flags = Pattern.UNICODE_CASE | Pattern.CASE_INSENSITIVE; + pattern = Pattern.compile("[h-j]+", flags); + if (!pattern.matcher("\u0131\u0130").matches()) + failCount++; + report("Case Folding"); + } + + private static void appendTest() { + Pattern pattern = Pattern.compile("(ab)(cd)"); + Matcher matcher = pattern.matcher("abcd"); + String result = matcher.replaceAll("$2$1"); + if (!result.equals("cdab")) + failCount++; + + String s1 = "Swap all: first = 123, second = 456"; + String s2 = "Swap one: first = 123, second = 456"; + String r = "$3$2$1"; + pattern = Pattern.compile("([a-z]+)( *= *)([0-9]+)"); + matcher = pattern.matcher(s1); + + result = matcher.replaceAll(r); + if (!result.equals("Swap all: 123 = first, 456 = second")) + failCount++; + + matcher = pattern.matcher(s2); + + if (matcher.find()) { + StringBuffer sb = new StringBuffer(); + matcher.appendReplacement(sb, r); + matcher.appendTail(sb); + result = sb.toString(); + if (!result.equals("Swap one: 123 = first, second = 456")) + failCount++; + } + + // Supplementary character test + pattern = Pattern.compile(toSupplementaries("(ab)(cd)")); + matcher = pattern.matcher(toSupplementaries("abcd")); + result = matcher.replaceAll("$2$1"); + if (!result.equals(toSupplementaries("cdab"))) + failCount++; + + s1 = toSupplementaries("Swap all: first = 123, second = 456"); + s2 = toSupplementaries("Swap one: first = 123, second = 456"); + r = toSupplementaries("$3$2$1"); + pattern = Pattern.compile(toSupplementaries("([a-z]+)( *= *)([0-9]+)")); + matcher = pattern.matcher(s1); + + result = matcher.replaceAll(r); + if (!result.equals(toSupplementaries("Swap all: 123 = first, 456 = second"))) + failCount++; + + matcher = pattern.matcher(s2); + + if (matcher.find()) { + StringBuffer sb = new StringBuffer(); + matcher.appendReplacement(sb, r); + matcher.appendTail(sb); + result = sb.toString(); + if (!result.equals(toSupplementaries("Swap one: 123 = first, second = 456"))) + failCount++; + } + report("Append"); + } + + private static void splitTest() { + Pattern pattern = Pattern.compile(":"); + String[] result = pattern.split("foo:and:boo", 2); + if (!result[0].equals("foo")) + failCount++; + if (!result[1].equals("and:boo")) + failCount++; + // Supplementary character test + Pattern patternX = Pattern.compile(toSupplementaries("X")); + result = patternX.split(toSupplementaries("fooXandXboo"), 2); + if (!result[0].equals(toSupplementaries("foo"))) + failCount++; + if (!result[1].equals(toSupplementaries("andXboo"))) + failCount++; + + CharBuffer cb = CharBuffer.allocate(100); + cb.put("foo:and:boo"); + cb.flip(); + result = pattern.split(cb); + if (!result[0].equals("foo")) + failCount++; + if (!result[1].equals("and")) + failCount++; + if (!result[2].equals("boo")) + failCount++; + + // Supplementary character test + CharBuffer cbs = CharBuffer.allocate(100); + cbs.put(toSupplementaries("fooXandXboo")); + cbs.flip(); + result = patternX.split(cbs); + if (!result[0].equals(toSupplementaries("foo"))) + failCount++; + if (!result[1].equals(toSupplementaries("and"))) + failCount++; + if (!result[2].equals(toSupplementaries("boo"))) + failCount++; + + String source = "0123456789"; + for (int limit=-2; limit<3; limit++) { + for (int x=0; x<10; x++) { + result = source.split(Integer.toString(x), limit); + int expectedLength = limit < 1 ? 2 : limit; + + if ((limit == 0) && (x == 9)) { + // expected dropping of "" + if (result.length != 1) + failCount++; + if (!result[0].equals("012345678")) { + failCount++; + } + } else { + if (result.length != expectedLength) { + failCount++; + } + if (!result[0].equals(source.substring(0,x))) { + if (limit != 1) { + failCount++; + } else { + if (!result[0].equals(source.substring(0,10))) { + failCount++; + } + } + } + if (expectedLength > 1) { // Check segment 2 + if (!result[1].equals(source.substring(x+1,10))) + failCount++; + } + } + } + } + // Check the case for no match found + for (int limit=-2; limit<3; limit++) { + result = source.split("e", limit); + if (result.length != 1) + failCount++; + if (!result[0].equals(source)) + failCount++; + } + // Check the case for limit == 0, source = ""; + source = ""; + result = source.split("e", 0); + if (result.length != 1) + failCount++; + if (!result[0].equals(source)) + failCount++; + + report("Split"); + } + + private static void negationTest() { + Pattern pattern = Pattern.compile("[\\[@^]+"); + Matcher matcher = pattern.matcher("@@@@[[[[^^^^"); + if (!matcher.find()) + failCount++; + if (!matcher.group(0).equals("@@@@[[[[^^^^")) + failCount++; + pattern = Pattern.compile("[@\\[^]+"); + matcher = pattern.matcher("@@@@[[[[^^^^"); + if (!matcher.find()) + failCount++; + if (!matcher.group(0).equals("@@@@[[[[^^^^")) + failCount++; + pattern = Pattern.compile("[@\\[^@]+"); + matcher = pattern.matcher("@@@@[[[[^^^^"); + if (!matcher.find()) + failCount++; + if (!matcher.group(0).equals("@@@@[[[[^^^^")) + failCount++; + + pattern = Pattern.compile("\\)"); + matcher = pattern.matcher("xxx)xxx"); + if (!matcher.find()) + failCount++; + + report("Negation"); + } + + private static void ampersandTest() { + Pattern pattern = Pattern.compile("[&@]+"); + check(pattern, "@@@@&&&&", true); + + pattern = Pattern.compile("[@&]+"); + check(pattern, "@@@@&&&&", true); + + pattern = Pattern.compile("[@\\&]+"); + check(pattern, "@@@@&&&&", true); + + report("Ampersand"); + } + + private static void octalTest() throws Exception { + Pattern pattern = Pattern.compile("\\u0007"); + Matcher matcher = pattern.matcher("\u0007"); + if (!matcher.matches()) + failCount++; + pattern = Pattern.compile("\\07"); + matcher = pattern.matcher("\u0007"); + if (!matcher.matches()) + failCount++; + pattern = Pattern.compile("\\007"); + matcher = pattern.matcher("\u0007"); + if (!matcher.matches()) + failCount++; + pattern = Pattern.compile("\\0007"); + matcher = pattern.matcher("\u0007"); + if (!matcher.matches()) + failCount++; + pattern = Pattern.compile("\\040"); + matcher = pattern.matcher("\u0020"); + if (!matcher.matches()) + failCount++; + pattern = Pattern.compile("\\0403"); + matcher = pattern.matcher("\u00203"); + if (!matcher.matches()) + failCount++; + pattern = Pattern.compile("\\0103"); + matcher = pattern.matcher("\u0043"); + if (!matcher.matches()) + failCount++; + + report("Octal"); + } + + private static void longPatternTest() throws Exception { + try { + Pattern pattern = Pattern.compile( + "a 32-character-long pattern xxxx"); + pattern = Pattern.compile("a 33-character-long pattern xxxxx"); + pattern = Pattern.compile("a thirty four character long regex"); + StringBuffer patternToBe = new StringBuffer(101); + for (int i=0; i<100; i++) + patternToBe.append((char)(97 + i%26)); + pattern = Pattern.compile(patternToBe.toString()); + } catch (PatternSyntaxException e) { + failCount++; + } + + // Supplementary character test + try { + Pattern pattern = Pattern.compile( + toSupplementaries("a 32-character-long pattern xxxx")); + pattern = Pattern.compile(toSupplementaries("a 33-character-long pattern xxxxx")); + pattern = Pattern.compile(toSupplementaries("a thirty four character long regex")); + StringBuffer patternToBe = new StringBuffer(101*2); + for (int i=0; i<100; i++) + patternToBe.append(Character.toChars(Character.MIN_SUPPLEMENTARY_CODE_POINT + + 97 + i%26)); + pattern = Pattern.compile(patternToBe.toString()); + } catch (PatternSyntaxException e) { + failCount++; + } + report("LongPattern"); + } + + private static void group0Test() throws Exception { + Pattern pattern = Pattern.compile("(tes)ting"); + Matcher matcher = pattern.matcher("testing"); + check(matcher, "testing"); + + matcher.reset("testing"); + if (matcher.lookingAt()) { + if (!matcher.group(0).equals("testing")) + failCount++; + } else { + failCount++; + } + + matcher.reset("testing"); + if (matcher.matches()) { + if (!matcher.group(0).equals("testing")) + failCount++; + } else { + failCount++; + } + + pattern = Pattern.compile("(tes)ting"); + matcher = pattern.matcher("testing"); + if (matcher.lookingAt()) { + if (!matcher.group(0).equals("testing")) + failCount++; + } else { + failCount++; + } + + pattern = Pattern.compile("^(tes)ting"); + matcher = pattern.matcher("testing"); + if (matcher.matches()) { + if (!matcher.group(0).equals("testing")) + failCount++; + } else { + failCount++; + } + + // Supplementary character test + pattern = Pattern.compile(toSupplementaries("(tes)ting")); + matcher = pattern.matcher(toSupplementaries("testing")); + check(matcher, toSupplementaries("testing")); + + matcher.reset(toSupplementaries("testing")); + if (matcher.lookingAt()) { + if (!matcher.group(0).equals(toSupplementaries("testing"))) + failCount++; + } else { + failCount++; + } + + matcher.reset(toSupplementaries("testing")); + if (matcher.matches()) { + if (!matcher.group(0).equals(toSupplementaries("testing"))) + failCount++; + } else { + failCount++; + } + + pattern = Pattern.compile(toSupplementaries("(tes)ting")); + matcher = pattern.matcher(toSupplementaries("testing")); + if (matcher.lookingAt()) { + if (!matcher.group(0).equals(toSupplementaries("testing"))) + failCount++; + } else { + failCount++; + } + + pattern = Pattern.compile(toSupplementaries("^(tes)ting")); + matcher = pattern.matcher(toSupplementaries("testing")); + if (matcher.matches()) { + if (!matcher.group(0).equals(toSupplementaries("testing"))) + failCount++; + } else { + failCount++; + } + + report("Group0"); + } + + private static void findIntTest() throws Exception { + Pattern p = Pattern.compile("blah"); + Matcher m = p.matcher("zzzzblahzzzzzblah"); + boolean result = m.find(2); + if (!result) + failCount++; + + p = Pattern.compile("$"); + m = p.matcher("1234567890"); + result = m.find(10); + if (!result) + failCount++; + try { + result = m.find(11); + failCount++; + } catch (IndexOutOfBoundsException e) { + // correct result + } + + // Supplementary character test + p = Pattern.compile(toSupplementaries("blah")); + m = p.matcher(toSupplementaries("zzzzblahzzzzzblah")); + result = m.find(2); + if (!result) + failCount++; + + report("FindInt"); + } + + private static void emptyPatternTest() throws Exception { + Pattern p = Pattern.compile(""); + Matcher m = p.matcher("foo"); + + // Should find empty pattern at beginning of input + boolean result = m.find(); + if (result != true) + failCount++; + if (m.start() != 0) + failCount++; + + // Should not match entire input if input is not empty + m.reset(); + result = m.matches(); + if (result == true) + failCount++; + + try { + m.start(0); + failCount++; + } catch (IllegalStateException e) { + // Correct result + } + + // Should match entire input if input is empty + m.reset(""); + result = m.matches(); + if (result != true) + failCount++; + + result = Pattern.matches("", ""); + if (result != true) + failCount++; + + result = Pattern.matches("", "foo"); + if (result == true) + failCount++; + report("EmptyPattern"); + } + + private static void charClassTest() throws Exception { + Pattern pattern = Pattern.compile("blah[ab]]blech"); + check(pattern, "blahb]blech", true); + + pattern = Pattern.compile("[abc[def]]"); + check(pattern, "b", true); + + // Supplementary character tests + pattern = Pattern.compile(toSupplementaries("blah[ab]]blech")); + check(pattern, toSupplementaries("blahb]blech"), true); + + pattern = Pattern.compile(toSupplementaries("[abc[def]]")); + check(pattern, toSupplementaries("b"), true); + + try { + // u00ff when UNICODE_CASE + pattern = Pattern.compile("[ab\u00ffcd]", + Pattern.CASE_INSENSITIVE| + Pattern.UNICODE_CASE); + check(pattern, "ab\u00ffcd", true); + check(pattern, "Ab\u0178Cd", true); + + // u00b5 when UNICODE_CASE + pattern = Pattern.compile("[ab\u00b5cd]", + Pattern.CASE_INSENSITIVE| + Pattern.UNICODE_CASE); + check(pattern, "ab\u00b5cd", true); + check(pattern, "Ab\u039cCd", true); + } catch (Exception e) { failCount++; } + + /* Special cases + (1)LatinSmallLetterLongS u+017f + (2)LatinSmallLetterDotlessI u+0131 + (3)LatineCapitalLetterIWithDotAbove u+0130 + (4)KelvinSign u+212a + (5)AngstromSign u+212b + */ + int flags = Pattern.UNICODE_CASE | Pattern.CASE_INSENSITIVE; + pattern = Pattern.compile("[sik\u00c5]+", flags); + if (!pattern.matcher("\u017f\u0130\u0131\u212a\u212b").matches()) + failCount++; + + report("CharClass"); + } + + private static void caretTest() throws Exception { + Pattern pattern = Pattern.compile("\\w*"); + Matcher matcher = pattern.matcher("a#bc#def##g"); + check(matcher, "a"); + check(matcher, ""); + check(matcher, "bc"); + check(matcher, ""); + check(matcher, "def"); + check(matcher, ""); + check(matcher, ""); + check(matcher, "g"); + check(matcher, ""); + if (matcher.find()) + failCount++; + + pattern = Pattern.compile("^\\w*"); + matcher = pattern.matcher("a#bc#def##g"); + check(matcher, "a"); + if (matcher.find()) + failCount++; + + pattern = Pattern.compile("\\w"); + matcher = pattern.matcher("abc##x"); + check(matcher, "a"); + check(matcher, "b"); + check(matcher, "c"); + check(matcher, "x"); + if (matcher.find()) + failCount++; + + pattern = Pattern.compile("^\\w"); + matcher = pattern.matcher("abc##x"); + check(matcher, "a"); + if (matcher.find()) + failCount++; + + pattern = Pattern.compile("\\A\\p{Alpha}{3}"); + matcher = pattern.matcher("abcdef-ghi\njklmno"); + check(matcher, "abc"); + if (matcher.find()) + failCount++; + + pattern = Pattern.compile("^\\p{Alpha}{3}", Pattern.MULTILINE); + matcher = pattern.matcher("abcdef-ghi\njklmno"); + check(matcher, "abc"); + check(matcher, "jkl"); + if (matcher.find()) + failCount++; + + pattern = Pattern.compile("^", Pattern.MULTILINE); + matcher = pattern.matcher("this is some text"); + String result = matcher.replaceAll("X"); + if (!result.equals("Xthis is some text")) + failCount++; + + pattern = Pattern.compile("^"); + matcher = pattern.matcher("this is some text"); + result = matcher.replaceAll("X"); + if (!result.equals("Xthis is some text")) + failCount++; + + pattern = Pattern.compile("^", Pattern.MULTILINE | Pattern.UNIX_LINES); + matcher = pattern.matcher("this is some text\n"); + result = matcher.replaceAll("X"); + if (!result.equals("Xthis is some text\n")) + failCount++; + + report("Caret"); + } + + private static void groupCaptureTest() throws Exception { + // Independent group + Pattern pattern = Pattern.compile("x+(?>y+)z+"); + Matcher matcher = pattern.matcher("xxxyyyzzz"); + matcher.find(); + try { + String blah = matcher.group(1); + failCount++; + } catch (IndexOutOfBoundsException ioobe) { + // Good result + } + // Pure group + pattern = Pattern.compile("x+(?:y+)z+"); + matcher = pattern.matcher("xxxyyyzzz"); + matcher.find(); + try { + String blah = matcher.group(1); + failCount++; + } catch (IndexOutOfBoundsException ioobe) { + // Good result + } + + // Supplementary character tests + // Independent group + pattern = Pattern.compile(toSupplementaries("x+(?>y+)z+")); + matcher = pattern.matcher(toSupplementaries("xxxyyyzzz")); + matcher.find(); + try { + String blah = matcher.group(1); + failCount++; + } catch (IndexOutOfBoundsException ioobe) { + // Good result + } + // Pure group + pattern = Pattern.compile(toSupplementaries("x+(?:y+)z+")); + matcher = pattern.matcher(toSupplementaries("xxxyyyzzz")); + matcher.find(); + try { + String blah = matcher.group(1); + failCount++; + } catch (IndexOutOfBoundsException ioobe) { + // Good result + } + + report("GroupCapture"); + } + + private static void backRefTest() throws Exception { + Pattern pattern = Pattern.compile("(a*)bc\\1"); + check(pattern, "zzzaabcazzz", true); + + pattern = Pattern.compile("(a*)bc\\1"); + check(pattern, "zzzaabcaazzz", true); + + pattern = Pattern.compile("(abc)(def)\\1"); + check(pattern, "abcdefabc", true); + + pattern = Pattern.compile("(abc)(def)\\3"); + check(pattern, "abcdefabc", false); + + try { + for (int i = 1; i < 10; i++) { + // Make sure backref 1-9 are always accepted + pattern = Pattern.compile("abcdef\\" + i); + // and fail to match if the target group does not exit + check(pattern, "abcdef", false); + } + } catch(PatternSyntaxException e) { + failCount++; + } + + pattern = Pattern.compile("(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)\\11"); + check(pattern, "abcdefghija", false); + check(pattern, "abcdefghija1", true); + + pattern = Pattern.compile("(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\\11"); + check(pattern, "abcdefghijkk", true); + + pattern = Pattern.compile("(a)bcdefghij\\11"); + check(pattern, "abcdefghija1", true); + + // Supplementary character tests + pattern = Pattern.compile(toSupplementaries("(a*)bc\\1")); + check(pattern, toSupplementaries("zzzaabcazzz"), true); + + pattern = Pattern.compile(toSupplementaries("(a*)bc\\1")); + check(pattern, toSupplementaries("zzzaabcaazzz"), true); + + pattern = Pattern.compile(toSupplementaries("(abc)(def)\\1")); + check(pattern, toSupplementaries("abcdefabc"), true); + + pattern = Pattern.compile(toSupplementaries("(abc)(def)\\3")); + check(pattern, toSupplementaries("abcdefabc"), false); + + pattern = Pattern.compile(toSupplementaries("(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)\\11")); + check(pattern, toSupplementaries("abcdefghija"), false); + check(pattern, toSupplementaries("abcdefghija1"), true); + + pattern = Pattern.compile(toSupplementaries("(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\\11")); + check(pattern, toSupplementaries("abcdefghijkk"), true); + + report("BackRef"); + } + + /** + * Unicode Technical Report #18, section 2.6 End of Line + * There is no empty line to be matched in the sequence \u000D\u000A + * but there is an empty line in the sequence \u000A\u000D. + */ + private static void anchorTest() throws Exception { + Pattern p = Pattern.compile("^.*$", Pattern.MULTILINE); + Matcher m = p.matcher("blah1\r\nblah2"); + m.find(); + m.find(); + if (!m.group().equals("blah2")) + failCount++; + + m.reset("blah1\n\rblah2"); + m.find(); + m.find(); + m.find(); + if (!m.group().equals("blah2")) + failCount++; + + // Test behavior of $ with \r\n at end of input + p = Pattern.compile(".+$"); + m = p.matcher("blah1\r\n"); + if (!m.find()) + failCount++; + if (!m.group().equals("blah1")) + failCount++; + if (m.find()) + failCount++; + + // Test behavior of $ with \r\n at end of input in multiline + p = Pattern.compile(".+$", Pattern.MULTILINE); + m = p.matcher("blah1\r\n"); + if (!m.find()) + failCount++; + if (m.find()) + failCount++; + + // Test for $ recognition of \u0085 for bug 4527731 + p = Pattern.compile(".+$", Pattern.MULTILINE); + m = p.matcher("blah1\u0085"); + if (!m.find()) + failCount++; + + // Supplementary character test + p = Pattern.compile("^.*$", Pattern.MULTILINE); + m = p.matcher(toSupplementaries("blah1\r\nblah2")); + m.find(); + m.find(); + if (!m.group().equals(toSupplementaries("blah2"))) + failCount++; + + m.reset(toSupplementaries("blah1\n\rblah2")); + m.find(); + m.find(); + m.find(); + if (!m.group().equals(toSupplementaries("blah2"))) + failCount++; + + // Test behavior of $ with \r\n at end of input + p = Pattern.compile(".+$"); + m = p.matcher(toSupplementaries("blah1\r\n")); + if (!m.find()) + failCount++; + if (!m.group().equals(toSupplementaries("blah1"))) + failCount++; + if (m.find()) + failCount++; + + // Test behavior of $ with \r\n at end of input in multiline + p = Pattern.compile(".+$", Pattern.MULTILINE); + m = p.matcher(toSupplementaries("blah1\r\n")); + if (!m.find()) + failCount++; + if (m.find()) + failCount++; + + // Test for $ recognition of \u0085 for bug 4527731 + p = Pattern.compile(".+$", Pattern.MULTILINE); + m = p.matcher(toSupplementaries("blah1\u0085")); + if (!m.find()) + failCount++; + + report("Anchors"); + } + + /** + * A basic sanity test of Matcher.lookingAt(). + */ + private static void lookingAtTest() throws Exception { + Pattern p = Pattern.compile("(ab)(c*)"); + Matcher m = p.matcher("abccczzzabcczzzabccc"); + + if (!m.lookingAt()) + failCount++; + + if (!m.group().equals(m.group(0))) + failCount++; + + m = p.matcher("zzzabccczzzabcczzzabccczzz"); + if (m.lookingAt()) + failCount++; + + // Supplementary character test + p = Pattern.compile(toSupplementaries("(ab)(c*)")); + m = p.matcher(toSupplementaries("abccczzzabcczzzabccc")); + + if (!m.lookingAt()) + failCount++; + + if (!m.group().equals(m.group(0))) + failCount++; + + m = p.matcher(toSupplementaries("zzzabccczzzabcczzzabccczzz")); + if (m.lookingAt()) + failCount++; + + report("Looking At"); + } + + /** + * A basic sanity test of Matcher.matches(). + */ + private static void matchesTest() throws Exception { + // matches() + Pattern p = Pattern.compile("ulb(c*)"); + Matcher m = p.matcher("ulbcccccc"); + if (!m.matches()) + failCount++; + + // find() but not matches() + m.reset("zzzulbcccccc"); + if (m.matches()) + failCount++; + + // lookingAt() but not matches() + m.reset("ulbccccccdef"); + if (m.matches()) + failCount++; + + // matches() + p = Pattern.compile("a|ad"); + m = p.matcher("ad"); + if (!m.matches()) + failCount++; + + // Supplementary character test + // matches() + p = Pattern.compile(toSupplementaries("ulb(c*)")); + m = p.matcher(toSupplementaries("ulbcccccc")); + if (!m.matches()) + failCount++; + + // find() but not matches() + m.reset(toSupplementaries("zzzulbcccccc")); + if (m.matches()) + failCount++; + + // lookingAt() but not matches() + m.reset(toSupplementaries("ulbccccccdef")); + if (m.matches()) + failCount++; + + // matches() + p = Pattern.compile(toSupplementaries("a|ad")); + m = p.matcher(toSupplementaries("ad")); + if (!m.matches()) + failCount++; + + report("Matches"); + } + + /** + * A basic sanity test of Pattern.matches(). + */ + private static void patternMatchesTest() throws Exception { + // matches() + if (!Pattern.matches(toSupplementaries("ulb(c*)"), + toSupplementaries("ulbcccccc"))) + failCount++; + + // find() but not matches() + if (Pattern.matches(toSupplementaries("ulb(c*)"), + toSupplementaries("zzzulbcccccc"))) + failCount++; + + // lookingAt() but not matches() + if (Pattern.matches(toSupplementaries("ulb(c*)"), + toSupplementaries("ulbccccccdef"))) + failCount++; + + // Supplementary character test + // matches() + if (!Pattern.matches(toSupplementaries("ulb(c*)"), + toSupplementaries("ulbcccccc"))) + failCount++; + + // find() but not matches() + if (Pattern.matches(toSupplementaries("ulb(c*)"), + toSupplementaries("zzzulbcccccc"))) + failCount++; + + // lookingAt() but not matches() + if (Pattern.matches(toSupplementaries("ulb(c*)"), + toSupplementaries("ulbccccccdef"))) + failCount++; + + report("Pattern Matches"); + } + + /** + * Canonical equivalence testing. Tests the ability of the engine + * to match sequences that are not explicitly specified in the + * pattern when they are considered equivalent by the Unicode Standard. + */ + private static void ceTest() throws Exception { + // Decomposed char outside char classes + Pattern p = Pattern.compile("testa\u030a", Pattern.CANON_EQ); + Matcher m = p.matcher("test\u00e5"); + if (!m.matches()) + failCount++; + + m.reset("testa\u030a"); + if (!m.matches()) + failCount++; + + // Composed char outside char classes + p = Pattern.compile("test\u00e5", Pattern.CANON_EQ); + m = p.matcher("test\u00e5"); + if (!m.matches()) + failCount++; + + m.reset("testa\u030a"); + if (!m.find()) + failCount++; + + // Decomposed char inside a char class + p = Pattern.compile("test[abca\u030a]", Pattern.CANON_EQ); + m = p.matcher("test\u00e5"); + if (!m.find()) + failCount++; + + m.reset("testa\u030a"); + if (!m.find()) + failCount++; + + // Composed char inside a char class + p = Pattern.compile("test[abc\u00e5def\u00e0]", Pattern.CANON_EQ); + m = p.matcher("test\u00e5"); + if (!m.find()) + failCount++; + + m.reset("testa\u0300"); + if (!m.find()) + failCount++; + + m.reset("testa\u030a"); + if (!m.find()) + failCount++; + + // Marks that cannot legally change order and be equivalent + p = Pattern.compile("testa\u0308\u0300", Pattern.CANON_EQ); + check(p, "testa\u0308\u0300", true); + check(p, "testa\u0300\u0308", false); + + // Marks that can legally change order and be equivalent + p = Pattern.compile("testa\u0308\u0323", Pattern.CANON_EQ); + check(p, "testa\u0308\u0323", true); + check(p, "testa\u0323\u0308", true); + + // Test all equivalences of the sequence a\u0308\u0323\u0300 + p = Pattern.compile("testa\u0308\u0323\u0300", Pattern.CANON_EQ); + check(p, "testa\u0308\u0323\u0300", true); + check(p, "testa\u0323\u0308\u0300", true); + check(p, "testa\u0308\u0300\u0323", true); + check(p, "test\u00e4\u0323\u0300", true); + check(p, "test\u00e4\u0300\u0323", true); + + /* + * The following canonical equivalence tests don't work. Bug id: 4916384. + * + // Decomposed hangul (jamos) + p = Pattern.compile("\u1100\u1161", Pattern.CANON_EQ); + m = p.matcher("\u1100\u1161"); + if (!m.matches()) + failCount++; + + m.reset("\uac00"); + if (!m.matches()) + failCount++; + + // Composed hangul + p = Pattern.compile("\uac00", Pattern.CANON_EQ); + m = p.matcher("\u1100\u1161"); + if (!m.matches()) + failCount++; + + m.reset("\uac00"); + if (!m.matches()) + failCount++; + + // Decomposed supplementary outside char classes + p = Pattern.compile("test\ud834\uddbc\ud834\udd6f", Pattern.CANON_EQ); + m = p.matcher("test\ud834\uddc0"); + if (!m.matches()) + failCount++; + + m.reset("test\ud834\uddbc\ud834\udd6f"); + if (!m.matches()) + failCount++; + + // Composed supplementary outside char classes + p = Pattern.compile("test\ud834\uddc0", Pattern.CANON_EQ); + m.reset("test\ud834\uddbc\ud834\udd6f"); + if (!m.matches()) + failCount++; + + m = p.matcher("test\ud834\uddc0"); + if (!m.matches()) + failCount++; + + */ + + report("Canonical Equivalence"); + } + + /** + * A basic sanity test of Matcher.replaceAll(). + */ + private static void globalSubstitute() throws Exception { + // Global substitution with a literal + Pattern p = Pattern.compile("(ab)(c*)"); + Matcher m = p.matcher("abccczzzabcczzzabccc"); + if (!m.replaceAll("test").equals("testzzztestzzztest")) + failCount++; + + m.reset("zzzabccczzzabcczzzabccczzz"); + if (!m.replaceAll("test").equals("zzztestzzztestzzztestzzz")) + failCount++; + + // Global substitution with groups + m.reset("zzzabccczzzabcczzzabccczzz"); + String result = m.replaceAll("$1"); + if (!result.equals("zzzabzzzabzzzabzzz")) + failCount++; + + // Supplementary character test + // Global substitution with a literal + p = Pattern.compile(toSupplementaries("(ab)(c*)")); + m = p.matcher(toSupplementaries("abccczzzabcczzzabccc")); + if (!m.replaceAll(toSupplementaries("test")). + equals(toSupplementaries("testzzztestzzztest"))) + failCount++; + + m.reset(toSupplementaries("zzzabccczzzabcczzzabccczzz")); + if (!m.replaceAll(toSupplementaries("test")). + equals(toSupplementaries("zzztestzzztestzzztestzzz"))) + failCount++; + + // Global substitution with groups + m.reset(toSupplementaries("zzzabccczzzabcczzzabccczzz")); + result = m.replaceAll("$1"); + if (!result.equals(toSupplementaries("zzzabzzzabzzzabzzz"))) + failCount++; + + report("Global Substitution"); + } + + /** + * Tests the usage of Matcher.appendReplacement() with literal + * and group substitutions. + */ + private static void stringbufferSubstitute() throws Exception { + // SB substitution with literal + String blah = "zzzblahzzz"; + Pattern p = Pattern.compile("blah"); + Matcher m = p.matcher(blah); + StringBuffer result = new StringBuffer(); + try { + m.appendReplacement(result, "blech"); + failCount++; + } catch (IllegalStateException e) { + } + m.find(); + m.appendReplacement(result, "blech"); + if (!result.toString().equals("zzzblech")) + failCount++; + + m.appendTail(result); + if (!result.toString().equals("zzzblechzzz")) + failCount++; + + // SB substitution with groups + blah = "zzzabcdzzz"; + p = Pattern.compile("(ab)(cd)*"); + m = p.matcher(blah); + result = new StringBuffer(); + try { + m.appendReplacement(result, "$1"); + failCount++; + } catch (IllegalStateException e) { + } + m.find(); + m.appendReplacement(result, "$1"); + if (!result.toString().equals("zzzab")) + failCount++; + + m.appendTail(result); + if (!result.toString().equals("zzzabzzz")) + failCount++; + + // SB substitution with 3 groups + blah = "zzzabcdcdefzzz"; + p = Pattern.compile("(ab)(cd)*(ef)"); + m = p.matcher(blah); + result = new StringBuffer(); + try { + m.appendReplacement(result, "$1w$2w$3"); + failCount++; + } catch (IllegalStateException e) { + } + m.find(); + m.appendReplacement(result, "$1w$2w$3"); + if (!result.toString().equals("zzzabwcdwef")) + failCount++; + + m.appendTail(result); + if (!result.toString().equals("zzzabwcdwefzzz")) + failCount++; + + // SB substitution with groups and three matches + // skipping middle match + blah = "zzzabcdzzzabcddzzzabcdzzz"; + p = Pattern.compile("(ab)(cd*)"); + m = p.matcher(blah); + result = new StringBuffer(); + try { + m.appendReplacement(result, "$1"); + failCount++; + } catch (IllegalStateException e) { + } + m.find(); + m.appendReplacement(result, "$1"); + if (!result.toString().equals("zzzab")) + failCount++; + + m.find(); + m.find(); + m.appendReplacement(result, "$2"); + if (!result.toString().equals("zzzabzzzabcddzzzcd")) + failCount++; + + m.appendTail(result); + if (!result.toString().equals("zzzabzzzabcddzzzcdzzz")) + failCount++; + + // Check to make sure escaped $ is ignored + blah = "zzzabcdcdefzzz"; + p = Pattern.compile("(ab)(cd)*(ef)"); + m = p.matcher(blah); + result = new StringBuffer(); + m.find(); + m.appendReplacement(result, "$1w\\$2w$3"); + if (!result.toString().equals("zzzabw$2wef")) + failCount++; + + m.appendTail(result); + if (!result.toString().equals("zzzabw$2wefzzz")) + failCount++; + + // Check to make sure a reference to nonexistent group causes error + blah = "zzzabcdcdefzzz"; + p = Pattern.compile("(ab)(cd)*(ef)"); + m = p.matcher(blah); + result = new StringBuffer(); + m.find(); + try { + m.appendReplacement(result, "$1w$5w$3"); + failCount++; + } catch (IndexOutOfBoundsException ioobe) { + // Correct result + } + + // Check double digit group references + blah = "zzz123456789101112zzz"; + p = Pattern.compile("(1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)"); + m = p.matcher(blah); + result = new StringBuffer(); + m.find(); + m.appendReplacement(result, "$1w$11w$3"); + if (!result.toString().equals("zzz1w11w3")) + failCount++; + + // Check to make sure it backs off $15 to $1 if only three groups + blah = "zzzabcdcdefzzz"; + p = Pattern.compile("(ab)(cd)*(ef)"); + m = p.matcher(blah); + result = new StringBuffer(); + m.find(); + m.appendReplacement(result, "$1w$15w$3"); + if (!result.toString().equals("zzzabwab5wef")) + failCount++; + + + // Supplementary character test + // SB substitution with literal + blah = toSupplementaries("zzzblahzzz"); + p = Pattern.compile(toSupplementaries("blah")); + m = p.matcher(blah); + result = new StringBuffer(); + try { + m.appendReplacement(result, toSupplementaries("blech")); + failCount++; + } catch (IllegalStateException e) { + } + m.find(); + m.appendReplacement(result, toSupplementaries("blech")); + if (!result.toString().equals(toSupplementaries("zzzblech"))) + failCount++; + + m.appendTail(result); + if (!result.toString().equals(toSupplementaries("zzzblechzzz"))) + failCount++; + + // SB substitution with groups + blah = toSupplementaries("zzzabcdzzz"); + p = Pattern.compile(toSupplementaries("(ab)(cd)*")); + m = p.matcher(blah); + result = new StringBuffer(); + try { + m.appendReplacement(result, "$1"); + failCount++; + } catch (IllegalStateException e) { + } + m.find(); + m.appendReplacement(result, "$1"); + if (!result.toString().equals(toSupplementaries("zzzab"))) + failCount++; + + m.appendTail(result); + if (!result.toString().equals(toSupplementaries("zzzabzzz"))) + failCount++; + + // SB substitution with 3 groups + blah = toSupplementaries("zzzabcdcdefzzz"); + p = Pattern.compile(toSupplementaries("(ab)(cd)*(ef)")); + m = p.matcher(blah); + result = new StringBuffer(); + try { + m.appendReplacement(result, toSupplementaries("$1w$2w$3")); + failCount++; + } catch (IllegalStateException e) { + } + m.find(); + m.appendReplacement(result, toSupplementaries("$1w$2w$3")); + if (!result.toString().equals(toSupplementaries("zzzabwcdwef"))) + failCount++; + + m.appendTail(result); + if (!result.toString().equals(toSupplementaries("zzzabwcdwefzzz"))) + failCount++; + + // SB substitution with groups and three matches + // skipping middle match + blah = toSupplementaries("zzzabcdzzzabcddzzzabcdzzz"); + p = Pattern.compile(toSupplementaries("(ab)(cd*)")); + m = p.matcher(blah); + result = new StringBuffer(); + try { + m.appendReplacement(result, "$1"); + failCount++; + } catch (IllegalStateException e) { + } + m.find(); + m.appendReplacement(result, "$1"); + if (!result.toString().equals(toSupplementaries("zzzab"))) + failCount++; + + m.find(); + m.find(); + m.appendReplacement(result, "$2"); + if (!result.toString().equals(toSupplementaries("zzzabzzzabcddzzzcd"))) + failCount++; + + m.appendTail(result); + if (!result.toString().equals(toSupplementaries("zzzabzzzabcddzzzcdzzz"))) + failCount++; + + // Check to make sure escaped $ is ignored + blah = toSupplementaries("zzzabcdcdefzzz"); + p = Pattern.compile(toSupplementaries("(ab)(cd)*(ef)")); + m = p.matcher(blah); + result = new StringBuffer(); + m.find(); + m.appendReplacement(result, toSupplementaries("$1w\\$2w$3")); + if (!result.toString().equals(toSupplementaries("zzzabw$2wef"))) + failCount++; + + m.appendTail(result); + if (!result.toString().equals(toSupplementaries("zzzabw$2wefzzz"))) + failCount++; + + // Check to make sure a reference to nonexistent group causes error + blah = toSupplementaries("zzzabcdcdefzzz"); + p = Pattern.compile(toSupplementaries("(ab)(cd)*(ef)")); + m = p.matcher(blah); + result = new StringBuffer(); + m.find(); + try { + m.appendReplacement(result, toSupplementaries("$1w$5w$3")); + failCount++; + } catch (IndexOutOfBoundsException ioobe) { + // Correct result + } + + // Check double digit group references + blah = toSupplementaries("zzz123456789101112zzz"); + p = Pattern.compile("(1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)"); + m = p.matcher(blah); + result = new StringBuffer(); + m.find(); + m.appendReplacement(result, toSupplementaries("$1w$11w$3")); + if (!result.toString().equals(toSupplementaries("zzz1w11w3"))) + failCount++; + + // Check to make sure it backs off $15 to $1 if only three groups + blah = toSupplementaries("zzzabcdcdefzzz"); + p = Pattern.compile(toSupplementaries("(ab)(cd)*(ef)")); + m = p.matcher(blah); + result = new StringBuffer(); + m.find(); + m.appendReplacement(result, toSupplementaries("$1w$15w$3")); + if (!result.toString().equals(toSupplementaries("zzzabwab5wef"))) + failCount++; + + // Check nothing has been appended into the output buffer if + // the replacement string triggers IllegalArgumentException. + p = Pattern.compile("(abc)"); + m = p.matcher("abcd"); + result = new StringBuffer(); + m.find(); + try { + m.appendReplacement(result, ("xyz$g")); + failCount++; + } catch (IllegalArgumentException iae) { + if (result.length() != 0) + failCount++; + } + + report("SB Substitution"); + } + + /* + * 5 groups of characters are created to make a substitution string. + * A base string will be created including random lead chars, the + * substitution string, and random trailing chars. + * A pattern containing the 5 groups is searched for and replaced with: + * random group + random string + random group. + * The results are checked for correctness. + */ + private static void substitutionBasher() { + for (int runs = 0; runs<1000; runs++) { + // Create a base string to work in + int leadingChars = generator.nextInt(10); + StringBuffer baseBuffer = new StringBuffer(100); + String leadingString = getRandomAlphaString(leadingChars); + baseBuffer.append(leadingString); + + // Create 5 groups of random number of random chars + // Create the string to substitute + // Create the pattern string to search for + StringBuffer bufferToSub = new StringBuffer(25); + StringBuffer bufferToPat = new StringBuffer(50); + String[] groups = new String[5]; + for(int i=0; i<5; i++) { + int aGroupSize = generator.nextInt(5)+1; + groups[i] = getRandomAlphaString(aGroupSize); + bufferToSub.append(groups[i]); + bufferToPat.append('('); + bufferToPat.append(groups[i]); + bufferToPat.append(')'); + } + String stringToSub = bufferToSub.toString(); + String pattern = bufferToPat.toString(); + + // Place sub string into working string at random index + baseBuffer.append(stringToSub); + + // Append random chars to end + int trailingChars = generator.nextInt(10); + String trailingString = getRandomAlphaString(trailingChars); + baseBuffer.append(trailingString); + String baseString = baseBuffer.toString(); + + // Create test pattern and matcher + Pattern p = Pattern.compile(pattern); + Matcher m = p.matcher(baseString); + + // Reject candidate if pattern happens to start early + m.find(); + if (m.start() < leadingChars) + continue; + + // Reject candidate if more than one match + if (m.find()) + continue; + + // Construct a replacement string with : + // random group + random string + random group + StringBuffer bufferToRep = new StringBuffer(); + int groupIndex1 = generator.nextInt(5); + bufferToRep.append("$" + (groupIndex1 + 1)); + String randomMidString = getRandomAlphaString(5); + bufferToRep.append(randomMidString); + int groupIndex2 = generator.nextInt(5); + bufferToRep.append("$" + (groupIndex2 + 1)); + String replacement = bufferToRep.toString(); + + // Do the replacement + String result = m.replaceAll(replacement); + + // Construct expected result + StringBuffer bufferToRes = new StringBuffer(); + bufferToRes.append(leadingString); + bufferToRes.append(groups[groupIndex1]); + bufferToRes.append(randomMidString); + bufferToRes.append(groups[groupIndex2]); + bufferToRes.append(trailingString); + String expectedResult = bufferToRes.toString(); + + // Check results + if (!result.equals(expectedResult)) + failCount++; + } + + report("Substitution Basher"); + } + + /** + * Checks the handling of some escape sequences that the Pattern + * class should process instead of the java compiler. These are + * not in the file because the escapes should be be processed + * by the Pattern class when the regex is compiled. + */ + private static void escapes() throws Exception { + Pattern p = Pattern.compile("\\043"); + Matcher m = p.matcher("#"); + if (!m.find()) + failCount++; + + p = Pattern.compile("\\x23"); + m = p.matcher("#"); + if (!m.find()) + failCount++; + + p = Pattern.compile("\\u0023"); + m = p.matcher("#"); + if (!m.find()) + failCount++; + + report("Escape sequences"); + } + + /** + * Checks the handling of blank input situations. These + * tests are incompatible with my test file format. + */ + private static void blankInput() throws Exception { + Pattern p = Pattern.compile("abc", Pattern.CASE_INSENSITIVE); + Matcher m = p.matcher(""); + if (m.find()) + failCount++; + + p = Pattern.compile("a*", Pattern.CASE_INSENSITIVE); + m = p.matcher(""); + if (!m.find()) + failCount++; + + p = Pattern.compile("abc"); + m = p.matcher(""); + if (m.find()) + failCount++; + + p = Pattern.compile("a*"); + m = p.matcher(""); + if (!m.find()) + failCount++; + + report("Blank input"); + } + + /** + * Tests the Boyer-Moore pattern matching of a character sequence + * on randomly generated patterns. + */ + private static void bm() throws Exception { + doBnM('a'); + report("Boyer Moore (ASCII)"); + + doBnM(Character.MIN_SUPPLEMENTARY_CODE_POINT - 10); + report("Boyer Moore (Supplementary)"); + } + + private static void doBnM(int baseCharacter) throws Exception { + int achar=0; + + for (int i=0; i<100; i++) { + // Create a short pattern to search for + int patternLength = generator.nextInt(7) + 4; + StringBuffer patternBuffer = new StringBuffer(patternLength); + for (int x=0; xy+)z+"), + "xxxyyyzzz", + "gname", + "yyy"); + + //backref + Pattern pattern = Pattern.compile("(a*)bc\\1"); + check(pattern, "zzzaabcazzz", true); // found "abca" + + check(Pattern.compile("(?a*)bc\\k"), + "zzzaabcaazzz", true); + + check(Pattern.compile("(?abc)(def)\\k"), + "abcdefabc", true); + + check(Pattern.compile("(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(?k)\\k"), + "abcdefghijkk", true); + + // Supplementary character tests + check(Pattern.compile("(?" + toSupplementaries("a*)bc") + "\\k"), + toSupplementaries("zzzaabcazzz"), true); + + check(Pattern.compile("(?" + toSupplementaries("a*)bc") + "\\k"), + toSupplementaries("zzzaabcaazzz"), true); + + check(Pattern.compile("(?" + toSupplementaries("abc)(def)") + "\\k"), + toSupplementaries("abcdefabc"), true); + + check(Pattern.compile(toSupplementaries("(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)") + + "(?" + + toSupplementaries("k)") + "\\k"), + toSupplementaries("abcdefghijkk"), true); + + check(Pattern.compile("x+(?y+)z+\\k"), + "xxxyyyzzzyyy", + "gname", + "yyy"); + + //replaceFirst/All + checkReplaceFirst("(?ab)(c*)", + "abccczzzabcczzzabccc", + "$", + "abzzzabcczzzabccc"); + + checkReplaceAll("(?ab)(c*)", + "abccczzzabcczzzabccc", + "$", + "abzzzabzzzab"); + + + checkReplaceFirst("(?ab)(c*)", + "zzzabccczzzabcczzzabccczzz", + "$", + "zzzabzzzabcczzzabccczzz"); + + checkReplaceAll("(?ab)(c*)", + "zzzabccczzzabcczzzabccczzz", + "$", + "zzzabzzzabzzzabzzz"); + + checkReplaceFirst("(?ab)(?c*)", + "zzzabccczzzabcczzzabccczzz", + "$", + "zzzccczzzabcczzzabccczzz"); + + checkReplaceAll("(?ab)(?c*)", + "zzzabccczzzabcczzzabccczzz", + "$", + "zzzccczzzcczzzccczzz"); + + //toSupplementaries("(ab)(c*)")); + checkReplaceFirst("(?" + toSupplementaries("ab") + + ")(?" + toSupplementaries("c") + "*)", + toSupplementaries("abccczzzabcczzzabccc"), + "$", + toSupplementaries("abzzzabcczzzabccc")); + + + checkReplaceAll("(?" + toSupplementaries("ab") + + ")(?" + toSupplementaries("c") + "*)", + toSupplementaries("abccczzzabcczzzabccc"), + "$", + toSupplementaries("abzzzabzzzab")); + + checkReplaceFirst("(?" + toSupplementaries("ab") + + ")(?" + toSupplementaries("c") + "*)", + toSupplementaries("abccczzzabcczzzabccc"), + "$", + toSupplementaries("ccczzzabcczzzabccc")); + + + checkReplaceAll("(?" + toSupplementaries("ab") + + ")(?" + toSupplementaries("c") + "*)", + toSupplementaries("abccczzzabcczzzabccc"), + "$", + toSupplementaries("ccczzzcczzzccc")); + + checkReplaceFirst("(?Dog)AndCat", + "zzzDogAndCatzzzDogAndCatzzz", + "$", + "zzzDogzzzDogAndCatzzz"); + + + checkReplaceAll("(?Dog)AndCat", + "zzzDogAndCatzzzDogAndCatzzz", + "$", + "zzzDogzzzDogzzz"); + + // backref in Matcher & String + if (!"abcdefghij".replaceFirst("cd(?ef)gh", "$").equals("abefij") || + !"abbbcbdbefgh".replaceAll("(?[a-e])b", "$").equals("abcdefgh")) + failCount++; + + // negative + checkExpectedFail("(?abc)(def)"); + checkExpectedFail("(?abc)(def)"); + checkExpectedFail("(?abc)(def)\\k"); + checkExpectedFail("(?abc)(?def)\\k"); + checkExpectedFail(Pattern.compile("(?abc)(def)").matcher("abcdef"), + "gnameX"); + checkExpectedFail(Pattern.compile("(?abc)(def)").matcher("abcdef"), + null); + report("NamedGroupCapture"); + } +} diff --git a/jdk/test/java/util/regex/SupplementaryTestCases.txt b/jdk/test/java/util/regex/SupplementaryTestCases.txt new file mode 100644 index 00000000000..2f05d4fed46 --- /dev/null +++ b/jdk/test/java/util/regex/SupplementaryTestCases.txt @@ -0,0 +1,1434 @@ +// +// Copyright 1999-2009 Sun Microsystems, Inc. All Rights Reserved. +// DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +// +// This code is free software; you can redistribute it and/or modify it +// under the terms of the GNU General Public License version 2 only, as +// published by the Free Software Foundation. +// +// This code is distributed in the hope that it will be useful, but WITHOUT +// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +// version 2 for more details (a copy is included in the LICENSE file that +// accompanied this code). +// +// You should have received a copy of the GNU General Public License version +// 2 along with this work; if not, write to the Free Software Foundation, +// Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. +// +// Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, +// CA 95054 USA or visit www.sun.com if you need additional information or +// have any questions. +// +// -------------------------------------------------------- +// This file contains test cases with supplementary characters for regular expressions. +// A test case consists of three lines: +// The first line is a pattern used in the test +// The second line is the input to search for the pattern in +// The third line is a concatentation of the match, the number of groups, +// and the contents of the first four subexpressions. +// Empty lines and lines beginning with comment slashes are ignored. + +// Test unsetting of backed off groups +^(\ud800\udc61)?\ud800\udc61 +\ud800\udc61 +true \ud800\udc61 1 + +^(\ud800\udc61\ud800)?\ud800\udc61\ud800 +\ud800\udc61\ud800 +true \ud800\udc61\ud800 1 + +^(\ud800\udc61\ud800\udc61(\ud800\udc62\ud800\udc62)?)+$ +\ud800\udc61\ud800\udc61\ud800\udc62\ud800\udc62\ud800\udc61\ud800\udc61 +true \ud800\udc61\ud800\udc61\ud800\udc62\ud800\udc62\ud800\udc61\ud800\udc61 2 \ud800\udc61\ud800\udc61 \ud800\udc62\ud800\udc62 + +^(\ud800\udc61\ud800\udc61\ud800(\ud800\udc62\ud800\udc62\ud800)?)+$ +\ud800\udc61\ud800\udc61\ud800\ud800\udc62\ud800\udc62\ud800\ud800\udc61\ud800\udc61\ud800 +true \ud800\udc61\ud800\udc61\ud800\ud800\udc62\ud800\udc62\ud800\ud800\udc61\ud800\udc61\ud800 2 \ud800\udc61\ud800\udc61\ud800 \ud800\udc62\ud800\udc62\ud800 + +((\ud800\udc61|\ud800\udc62)?\ud800\udc62)+ +\ud800\udc62 +true \ud800\udc62 2 \ud800\udc62 + +((\ud800|\ud800\udc62)?\ud800\udc62)+ +\ud800\udc62 +true \ud800\udc62 2 \ud800\udc62 + +(\ud800\udc61\ud800\udc61\ud800\udc61)?\ud800\udc61\ud800\udc61\ud800\udc61 +\ud800\udc61\ud800\udc61\ud800\udc61 +true \ud800\udc61\ud800\udc61\ud800\udc61 1 + +(\ud800\udc61\ud800\udc61\ud800\ud800\udc61)?\ud800\udc61\ud800\udc61\ud800\ud800\udc61 +\ud800\udc61\ud800\udc61\ud800\ud800\udc61 +true \ud800\udc61\ud800\udc61\ud800\ud800\udc61 1 + +^(\ud800\udc61\ud800(\ud800\udc62\ud800)?)+$ +\ud800\udc61\ud800\ud800\udc62\ud800\ud800\udc61\ud800 +true \ud800\udc61\ud800\ud800\udc62\ud800\ud800\udc61\ud800 2 \ud800\udc61\ud800 \ud800\udc62\ud800 + +^(\ud800\udc61(\ud800\udc62)?)+$ +\ud800\udc61\ud800\udc62\ud800\udc61 +true \ud800\udc61\ud800\udc62\ud800\udc61 2 \ud800\udc61 \ud800\udc62 + +^(\ud800\udc61\ud800(\ud800\udc62\ud800)?)+$ +\ud800\udc61\ud800\ud800\udc62\ud800\ud800\udc61\ud800 +true \ud800\udc61\ud800\ud800\udc62\ud800\ud800\udc61\ud800 2 \ud800\udc61\ud800 \ud800\udc62\ud800 + +^(\ud800\udc61(\ud800\udc62(\ud800\udc63)?)?)?\ud800\udc61\ud800\udc62\ud800\udc63 +\ud800\udc61\ud800\udc62\ud800\udc63 +true \ud800\udc61\ud800\udc62\ud800\udc63 3 + +^(\ud800\udc61\ud800(\ud800\udc62(\ud800\udc63)?)?)?\ud800\udc61\ud800\ud800\udc62\ud800\udc63 +\ud800\udc61\ud800\ud800\udc62\ud800\udc63 +true \ud800\udc61\ud800\ud800\udc62\ud800\udc63 3 + +^(\ud800\udc61(\ud800\udc02(\ud800\udc63))).* +\ud800\udc61\ud800\udc02\ud800\udc63 +true \ud800\udc61\ud800\udc02\ud800\udc63 3 \ud800\udc61\ud800\udc02\ud800\udc63 \ud800\udc02\ud800\udc63 \ud800\udc63 + +^(\ud800\udc61(\ud800(\ud800\udc63))).* +\ud800\udc61\ud800\ud800\udc63 +true \ud800\udc61\ud800\ud800\udc63 3 \ud800\udc61\ud800\ud800\udc63 \ud800\ud800\udc63 \ud800\udc63 + +// Patterns including no surrogates +(.)([^a])xyz +\ud801\ud800\udc00xyz +true \ud801\ud800\udc00xyz 2 \ud801 \ud800\udc00 + +[^a-z].. +\ud801\ud800\udc00xyz +true \ud801\ud800\udc00x 0 + +.$ +\ud801\ud800\udc00 +true \ud800\udc00 0 + +.$ +\ud801\udc01\ud800\udc00 +true \ud800\udc00 0 + +.$ +\ud801\udc01\ud800\udc00\udcff +true \udcff 0 + +[^x-\uffff][^y-\uffff] +\ud800\udc00pqr +true \ud800\udc00p 0 + +[^x-\uffff]+ +\ud800\udc00pqrx +true \ud800\udc00pqr 0 + +/// The following test cases fail due to use of Start rather than +/// StartS. Disabled for now. +///[a-\uffff] +///\ud800\udc00x +///true x 0 +/// +///[a-\uffff] +///\ud800\udc00 +///false 0 + +// use of x modifier +\ud800\udc61bc(?x)bl\ud800\udc61h +\ud800\udc61bcbl\ud800\udc61h +true \ud800\udc61bcbl\ud800\udc61h 0 + +\ud800\udc61bc(?x) bl\ud800\udc61h +\ud800\udc61bcbl\ud800\udc61h +true \ud800\udc61bcbl\ud800\udc61h 0 + +\ud800\udc61bc(?x) bl\ud800\udc61h blech +\ud800\udc61bcbl\ud800\udc61hblech +true \ud800\udc61bcbl\ud800\udc61hblech 0 + +\ud800\udc61bc(?x) bl\ud800\udc61h # ignore comment +\ud800\udc61bcbl\ud800\udc61h +true \ud800\udc61bcbl\ud800\udc61h 0 + +// Simple alternation +\ud800\udc61|\ud800\udc62 +\ud800\udc61 +true \ud800\udc61 0 + +\ud800\udc61|\ud800\udc62|\ud800 +\ud800\udc61 +true \ud800\udc61 0 + +\ud800\udc61|\ud800 +\ud800\udc62 +false 0 + +\ud800\udc62|\ud800 +\ud800 +true \ud800 0 + +\ud800\udc61|\ud802\udc02 +z +false 0 + +\ud800\udc61|\ud802\udc02 +\ud802\udc02 +true \ud802\udc02 0 + +\ud800\udc61|\ud802\udc02|\ud803\udc03\ud804\udc04 +\ud803\udc03\ud804\udc04 +true \ud803\udc03\ud804\udc04 0 + +\ud800\udc61|\ud800\udc61d +\ud800\udc61d +true \ud800\udc61 0 + +z(\ud800\udc61|\ud800\udc61c)\ud802\udc02 +z\ud800\udc61c\ud802\udc02 +true z\ud800\udc61c\ud802\udc02 1 \ud800\udc61c + +z(\ud800\udc61|\ud800\udc61c|\udc61c)\ud802\udc02 +z\udc61c\ud802\udc02 +true z\udc61c\ud802\udc02 1 \udc61c + +// Simple codepoint class +[\ud800\udc61\ud802\udc02c]+ +\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02 +true \ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02 0 + +[\ud800\udc61\ud802\udc02c]+ +\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02 +true \ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02 0 + +[\ud800\udc61\ud802\udc02c\ud800]+ +\ud800\udc61\ud802\udc02\ud800\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02 +true \ud800\udc61\ud802\udc02\ud800\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02 0 + +[\ud800\udc61bc]+ +d\ud800\udc62fg +false 0 + +[\ud800\udc61bc]+[\ud804\udc04ef]+[\ud807\udc07hi]+ +zzz\ud800\udc61\ud800\udc61\ud804\udc04\ud804\udc04\ud807\udc07\ud807\udc07zzz +true \ud800\udc61\ud800\udc61\ud804\udc04\ud804\udc04\ud807\udc07\ud807\udc07 0 + +// Range codepoint class +[\ud801\udc01-\ud807\udc07]+ +\ud8ff\udcff\ud8ff\udcff\ud8ff\udcff\ud807\udc07\ud807\udc07\ud807\udc07 +true \ud807\udc07\ud807\udc07\ud807\udc07 0 + +[\ud801\udc01-\ud807\udc07]+ +mmm +false 0 + +[\ud800\udc61-]+ +z\ud800\udc61-9z +true \ud800\udc61- 0 + +// Negated char class +[^\ud800\udc61\ud802\udc02c]+ +\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02\ud800\udc61\ud802\udc02 +false 0 + +[^\ud800\udc61\ud802\udc02\ud803\udc03]+ +\ud800\udc61\ud800\udc61\ud800\udc61\ud802\udc02\ud802\udc02\ud802\udc02\ud803\udc03\ud803\udc03\ud803\udc03\ud804\udc04efg +true \ud804\udc04efg 0 + +[^\ud800\udc61\ud802\udc02\ud803\udc03\ud800]+ +\ud800\udc61\ud800\udc61\ud800\udc61\ud802\udc02\ud802\udc02\ud802\udc02\ud803\udc03\ud803\udc03\ud803\udc03\ud804\udc04efg +true \ud804\udc04efg 0 + +// Making sure a ^ not in first position matches literal ^ +[\ud801\udc01\ud802\udc02\ud803\udc03^\ud802\udc02] +\ud802\udc02 +true \ud802\udc02 0 + +[\ud801\udc01\ud802\udc02\ud803\udc03^\ud802\udc02] +^ +true ^ 0 + +// Class union and intersection +[\ud801\udc01\ud802\udc02\ud803\udc03[\ud804\udc04\ud805\udc05\ud806\udc06]] +\ud802\udc02 +true \ud802\udc02 0 + +[\ud800\udc61\ud802\udc02\ud803\udc03[\ud804\udc04\ud805\udc05\ud806\udc06]] +\ud805\udc05 +true \ud805\udc05 0 + +[\ud801\udc01-\ud804\udc04[0-9][\ud80b\udc0b-\ud80d\udc0d]] +\ud801\udc01 +true \ud801\udc01 0 + +[\ud801\udc01-\ud804\udc04[0-9][\ud80b\udc0b-\ud80d\udc0d]] +\ud80c\udc0c +true \ud80c\udc0c 0 + +[\ud801\udc01-\ud804\udc04[0-9][\ud80b\udc0b-\ud80d\udc0d]] +4 +true 4 0 + +[\ud801\udc01-\ud804\udc04[0-9][\ud80b\udc0b-\ud80d\udc0d]] +\ud805\udc05 +false 0 + +[\ud801\udc01-\ud804\udc04[0-9][\ud80b\udc0b-\ud80d\udc0d]] +\ud816\udc16 +false 0 + +[[\ud801\udc01-\ud804\udc04][0-9][\ud80b\udc0b-\ud80d\udc0d]] +\ud802\udc02 +true \ud802\udc02 0 + +[[\ud801\udc01-\ud804\udc04][0-9][\ud80b\udc0b-\ud80d\udc0d]] +\ud81a\udc1a +false 0 + +[\ud801\udc01-\ud803\udc03[\ud804\udc04-\ud806\udc06[\ud807\udc07-\ud809\udc09]]] +\ud801\udc01 +true \ud801\udc01 0 + +[\ud801\udc01-\ud803\udc03[\ud804\udc04-\ud806\udc06[\ud807\udc07-\ud809\udc09]]] +\ud805\udc05 +true \ud805\udc05 0 + +[\ud801\udc01-\ud803\udc03[\ud804\udc04-\ud806\udc06[\ud807\udc07-\ud809\udc09]]] +\ud808\udc08 +true \ud808\udc08 0 + +[\ud801\udc01-\ud803\udc03[\ud804\udc04-\ud806\udc06[\ud807\udc07-\ud809\udc09]]] +\ud80d\udc0d +false 0 + +[\ud801\udc01-\ud803\udc03[\ud804\udc04-\ud806\udc06[\ud807\udc07-\ud809\udc09]]\ud80d\udc0d] +\ud80d\udc0d +true \ud80d\udc0d 0 + +[\ud801\udc01\ud802\udc02\ud803\udc03[\ud804\udc04\ud805\udc05\ud806\udc06]\ud807\udc07\ud808\udc08\ud809\udc09] +\ud801\udc01 +true \ud801\udc01 0 + +[\ud800\udc61\ud802\udc02\ud803\udc03[\ud804\udc04\ud805\udc05\ud806\udc06]\ud807\udc07\ud808\udc08\ud809\udc09] +\ud804\udc04 +true \ud804\udc04 0 + +[\ud800\udc61\ud802\udc02\ud803\udc03[\ud804\udc04\ud805\udc05\ud806\udc06]\ud807\udc07\ud808\udc08\ud809\udc09] +\ud808\udc08 +true \ud808\udc08 0 + +[\ud800\udc61\ud802\udc02\ud803\udc03[\ud804\udc04\ud805\udc05\ud806\udc06]\ud807\udc07\ud808\udc08\ud809\udc09] +\ud816\udc16 +false 0 + +[\ud801\udc01-\ud803\udc03&&[\ud804\udc04-\ud806\udc06]] +\ud801\udc01 +false 0 + +[\ud801\udc01-\ud803\udc03&&[\ud804\udc04-\ud806\udc06]] +\ud805\udc05 +false 0 + +[\ud801\udc01-\ud803\udc03&&[\ud804\udc04-\ud806\udc06]] +\ud81a\udc1a +false 0 + +[[\ud801\udc01-\ud803\udc03]&&[\ud804\udc04-\ud806\udc06]] +\ud801\udc01 +false 0 + +[[\ud801\udc01-\ud803\udc03]&&[\ud804\udc04-\ud806\udc06]] +\ud805\udc05 +false 0 + +[[\ud801\udc01-\ud803\udc03]&&[\ud804\udc04-\ud806\udc06]] +\ud81a\udc1a +false 0 + +[\ud801\udc01-\ud803\udc03&&\ud804\udc04-\ud806\udc06] +\ud801\udc01 +false 0 + +[\ud801\udc01-\ud80d\udc0d&&\ud80d\udc0d-\ud81a\udc1a] +\ud80d\udc0d +true \ud80d\udc0d 0 + +[\ud801\udc01-\ud80d\udc0d&&\ud80d\udc0d-\ud81a\udc1a&&\ud801\udc01-\ud803\udc03] +\ud80d\udc0d +false 0 + +[\ud801\udc01-\ud80d\udc0d&&\ud80d\udc0d-\ud81a\udc1a&&\ud801\udc01-\ud81a\udc1a] +\ud80d\udc0d +true \ud80d\udc0d 0 + +[[\ud801\udc01-\ud80d\udc0d]&&[\ud80d\udc0d-\ud81a\udc1a]] +\ud801\udc01 +false 0 + +[[\ud801\udc01-\ud80d\udc0d]&&[\ud80d\udc0d-\ud81a\udc1a]] +\ud80d\udc0d +true \ud80d\udc0d 0 + +[[\ud801\udc01-\ud80d\udc0d]&&[\ud80d\udc0d-\ud81a\udc1a]] +\ud81a\udc1a +false 0 + +[[\ud801\udc01-\ud80d\udc0d]&&[^\ud801\udc01-\ud803\udc03]] +\ud801\udc01 +false 0 + +[[\ud801\udc01-\ud80d\udc0d]&&[^\ud801\udc01-\ud803\udc03]] +\ud804\udc04 +true \ud804\udc04 0 + +[\ud801\udc01-\ud80d\udc0d&&[^\ud801\udc01-\ud803\udc03]] +\ud801\udc01 +false 0 + +[\ud801\udc01-\ud80d\udc0d&&[^\ud801\udc01-\ud803\udc03]] +\ud804\udc04 +true \ud804\udc04 0 + +[\ud801\udc01-\ud803\udc03\ud804\udc04-\ud806\udc06&&[\ud804\udc04-\ud806\udc06]] +\ud801\udc01 +false 0 + +[\ud801\udc01-\ud803\udc03\ud804\udc04-\ud806\udc06&&[\ud804\udc04-\ud806\udc06]] +\ud805\udc05 +true \ud805\udc05 0 + +[[\ud801\udc01-\ud803\udc03]&&\ud804\udc04-\ud806\udc06\ud801\udc01-\ud803\udc03] +\ud801\udc01 +true \ud801\udc01 0 + +[[\ud801\udc01-\ud803\udc03]&&[\ud804\udc04-\ud806\udc06][\ud801\udc01-\ud803\udc03]] +\ud801\udc01 +true \ud801\udc01 0 + +[[\ud801\udc01-\ud803\udc03][\ud804\udc04-\ud806\udc06]&&\ud801\udc01\ud802\udc02\ud803\udc03] +\ud801\udc01 +true \ud801\udc01 0 + +[[\ud801\udc01-\ud803\udc03][\ud804\udc04-\ud806\udc06]&&\ud801\udc01\ud802\udc02\ud803\udc03[\ud804\udc04\ud805\udc05\ud806\udc06]] +\ud805\udc05 +true \ud805\udc05 0 + +[[\ud801\udc01-\ud803\udc03]&&[\ud802\udc02-\ud804\udc04]&&[\ud803\udc03-\ud805\udc05]] +\ud801\udc01 +false 0 + +[[\ud801\udc01-\ud803\udc03]&&[\ud802\udc02-\ud804\udc04]&&[\ud803\udc03-\ud805\udc05]] +\ud803\udc03 +true \ud803\udc03 0 + +[[\ud801\udc01-\ud803\udc03]&&[\ud802\udc02-\ud804\udc04][\ud803\udc03-\ud805\udc05]&&[\ud815\udc15-\ud81a\udc1a]] +\ud803\udc03 +false 0 + +[\ud801\udc01\ud802\udc02\ud803\udc03[^\ud802\udc02\ud803\udc03\ud804\udc04]] +\ud801\udc01 +true \ud801\udc01 0 + +[\ud800\udc61\ud802\udc02\ud803\udc03[^\ud802\udc02\ud803\udc03\ud804\udc04]] +\ud804\udc04 +false 0 + +[\ud801\udc01-\ud803\udc03&&\ud801\udc01-\ud804\udc04&&\ud801\udc01-\ud805\udc05\ud807\udc07\ud808\udc08\ud809\udc09] +\ud802\udc02 +true \ud802\udc02 0 + +[\ud801\udc01-\ud803\udc03&&\ud801\udc01-\ud804\udc04&&\ud801\udc01-\ud805\udc05\ud807\udc07\ud808\udc08\ud809\udc09] +\ud807\udc07 +false 0 + +[[\ud801\udc01[\ud802\udc02]]&&[\ud802\udc02[\ud801\udc01]]] +\ud801\udc01 +true \ud801\udc01 0 + +// Unicode isn't supported in clazz() +[[\ud800\udc61]&&[b][c][\ud800\udc61]&&[^d]] +\ud800\udc61 +true \ud800\udc61 0 + +[[\ud800\udc61]&&[\ud802\udc02][\ud800][\ud800\udc61]&&[^\ud804\udc04]] +\ud800\udc61 +true \ud800\udc61 0 + +[[\ud800\udc61]&&[b][\ud800][\ud800\udc61]&&[^\ud804\udc04]] +\ud804\udc04 +false 0 + +[[\ud800\udc61]&&[b][c][\ud800\udc61]&&[^d]] +d +false 0 + +[[[\ud800\udc01-\ud800\udc04]&&[\ud800\udc03-\ud800\udc06]]] +\ud800\udc01 +false 0 + +[[[\ud800\udc01-\ud800\udc04]&&[\ud800\udc03-\ud800\udc06]]] +\ud800\udc03 +true \ud800\udc03 0 + +[[[\ud800\udc01-\ud800\udc04]&&[\ud800\udc03-\ud800\udc06]]&&[\ud800\udc03]] +\ud800\udc03 +true \ud800\udc03 0 + +[[[\ud800\udc01-\ud800\udc04]&&[\ud800\udc03-\ud800\udc06]]&&[\ud800\udc03]&&\ud800\udc03] +\ud800\udc03 +true \ud800\udc03 0 + +[[[\ud800\udc01-\ud800\udc04]&&[\ud800\udc03-\ud800\udc06]]&&[\ud800\udc03]&&\ud800\udc03&&\ud800\udc03] +\ud800\udc03 +true \ud800\udc03 0 + +[[[\ud800\udc01-\ud800\udc04]&&[\ud800\udc03-\ud800\udc06]]&&[\ud800\udc03]&&\ud800\udc03&&[\ud800\udc03\ud800\udc04\ud800\udc05]] +\ud800\udc03 +true \ud800\udc03 0 + +[z[\ud800\udc61b\ud800\udc03&&b\ud800\udc03\ud800\udc04]] +\ud800\udc03 +true \ud800\udc03 0 + +[z[\ud800\udc61b\ud800\udc03&&b\ud800\udc03\ud800\udc04]&&[u-z]] +z +true z 0 + +[x[\ud800\udc61b\ud800\udc03&&b\ud800\udc03\ud800\udc04[z]]&&[u-z]] +z +false 0 + +[x[[wz]\ud800\udc61b\ud800\udc03&&b\ud800\udc03\ud800\udc04[z]]&&[u-z]] +z +true z 0 + +[[\ud800\udc61b\ud800\udc03]&&[\ud800\udc04\ud800\udc05f]\ud800\udc61b\ud800\udc03] +\ud800\udc61 +true \ud800\udc61 0 + +[[\ud800\udc61b\ud800\udc03]&&[\ud800\udc04\ud800\udc05f]xyz[\ud800\udc61b\ud800\udc03]] +\ud800\udc61 +true \ud800\udc61 0 + +\pL +\ud800\udc00 +true \ud800\udc00 0 + +\p{IsASCII} +\ud800\udc00 +false 0 + +\pLbc +\ud800\udc00bc +true \ud800\udc00bc 0 + +\ud800\udc61[r\p{InGreek}]c +\ud800\udc61\u0370c +true \ud800\udc61\u0370c 0 + +\ud800\udc61\p{InGreek} +\ud800\udc61\u0370 +true \ud800\udc61\u0370 0 + +\ud800\udc61\P{InGreek} +\ud800\udc61\u0370 +false 0 + +\ud800\udc61\P{InGreek} +\ud800\udc61b +true \ud800\udc61b 0 + +\ud800\udc61{^InGreek} +- +error + +\ud800\udc61\p{^InGreek} +- +error + +\ud800\udc61\P{^InGreek} +- +error + +\ud800\udc61\p{InGreek} +\ud800\udc61\u0370 +true \ud800\udc61\u0370 0 + +\ud800\udc61[\p{InGreek}]c +\ud800\udc61\u0370c +true \ud800\udc61\u0370c 0 + +\ud800\udc61[\P{InGreek}]c +\ud800\udc61\u0370c +false 0 + +\ud800\udc61[\P{InGreek}]c +\ud800\udc61bc +true \ud800\udc61bc 0 + +\ud800\udc61[{^InGreek}]c +\ud800\udc61nc +true \ud800\udc61nc 0 + +\ud800\udc61[{^InGreek}]c +\ud800\udc61zc +false 0 + +\ud800\udc61[\p{^InGreek}]c +- +error + +\ud800\udc61[\P{^InGreek}]c +- +error + +\ud800\udc61[\p{InGreek}] +\ud800\udc61\u0370 +true \ud800\udc61\u0370 0 + +\ud800\udc61[r\p{InGreek}]c +\ud800\udc61rc +true \ud800\udc61rc 0 + +\ud800\udc61[\p{InGreek}r]c +\ud800\udc61rc +true \ud800\udc61rc 0 + +\ud800\udc61[r\p{InGreek}]c +\ud800\udc61rc +true \ud800\udc61rc 0 + +\ud800\udc61[^\p{InGreek}]c +\ud800\udc61\u0370c +false 0 + +\ud800\udc61[^\P{InGreek}]c +\ud800\udc61\u0370c +true \ud800\udc61\u0370c 0 + +\ud800\udc61[\p{InGreek}&&[^\u0370]]c +\ud800\udc61\u0370c +false 0 + +// Test the dot metacharacter +\ud800\udc61.c.+ +\ud800\udc61#c%& +true \ud800\udc61#c%& 0 + +\ud800\udc61b. +\ud800\udc61b\n +false 0 + +(?s)\ud800\udc61b. +\ud800\udc61b\n +true \ud800\udc61b\n 0 + +\ud800\udc61[\p{L}&&[\P{InGreek}]]c +\ud800\udc61\u6000c +true \ud800\udc61\u6000c 0 + +\ud800\udc61[\p{L}&&[\P{InGreek}]]c +\ud800\udc61rc +true \ud800\udc61rc 0 + +\ud800\udc61[\p{L}&&[\P{InGreek}]]c +\ud800\udc61\u0370c +false 0 + +\ud800\udc61\p{InGreek}c +\ud800\udc61\u0370c +true \ud800\udc61\u0370c 0 + +\ud800\udc61\p{Sc} +\ud800\udc61$ +true \ud800\udc61$ 0 + +// Test \p{L} +\p{L} +\ud800\udf1e +true \ud800\udf1e 0 + +^a\p{L}z$ +a\ud800\udf1ez +true a\ud800\udf1ez 0 + +// Test \P{InDeseret} + +\ud800\udf00\p{L}{2,3}\P{L}*supp->\ud900\udc00<-\P{InDeseret} +\ud800\udf00\ud800\udf1e\ud800\udf1esupp->\ud900\udc00<-\ud901\udf00 +true \ud800\udf00\ud800\udf1e\ud800\udf1esupp->\ud900\udc00<-\ud901\udf00 0 + +\ud800\udf00\p{L}{2,3}\P{L}*supp->\ud900\udc00<-\P{InDeseret} +\ud800\udf00\ud800\udf1e\ud800\udf1e\ud901\udf00supp->\ud900\udc00<-\ud901\udf00 +true \ud800\udf00\ud800\udf1e\ud800\udf1e\ud901\udf00supp->\ud900\udc00<-\ud901\udf00 0 + +// Test \p{InDeseret} +\ud800\udf00\p{L}{2,3}\P{L}*supp->\ud900\udc00<-\p{InDeseret} +\ud800\udf00\ud800\udf1e\ud800\udf1e\ud901\udf00supp->\ud900\udc00<-\ud801\udc00 +true \ud800\udf00\ud800\udf1e\ud800\udf1e\ud901\udf00supp->\ud900\udc00<-\ud801\udc00 0 + +// Test the word char escape sequence +\ud800\udc61b\wc +\ud800\udc61bcc +true \ud800\udc61bcc 0 + +\ud800\udc61bc[\w] +\ud800\udc61bcd +true \ud800\udc61bcd 0 + +\ud800\udc61bc[\sdef]* +\ud800\udc61bc def +true \ud800\udc61bc def 0 + +\ud800\udc61bc[\sy-z]* +\ud800\udc61bc y z +true \ud800\udc61bc y z 0 + +\ud800\udc01bc[\ud800\udc01-\ud800\udc04\sm-p]* +\ud800\udc01bc\ud800\udc01\ud800\udc01 mn p +true \ud800\udc01bc\ud800\udc01\ud800\udc01 mn p 0 + +// Test the whitespace escape sequence +\ud800\udc61b\s\ud800\udc03 +\ud800\udc61b \ud800\udc03 +true \ud800\udc61b \ud800\udc03 0 + +\s\s\s +bl\ud800\udc61h err +false 0 + +\S\S\s +bl\ud800\udc61h err +true \ud800\udc61h 0 + +// Test the digit escape sequence +\ud800\udc61b\d\ud800\udc03 +\ud800\udc61b9\ud800\udc03 +true \ud800\udc61b9\ud800\udc03 0 + +\d\d\d +bl\ud800\udc61h45 +false 0 + +// Test the caret metacharacter +^\ud800\udc61bc +\ud800\udc61bcdef +true \ud800\udc61bc 0 + +^\ud800\udc61bc +bcd\ud800\udc61bc +false 0 + +// Greedy ? metacharacter +\ud800\udc61?\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc02 0 + +\udc61?\ud800\udc02 +\ud800\udc61\udc61\udc61\ud800\udc02 +true \udc61\ud800\udc02 0 + +\ud800\udc61?\ud800\udc02 +\ud800\udc02 +true \ud800\udc02 0 + +\ud800?\ud800\udc02 +\ud800\udc02 +true \ud800\udc02 0 + +\ud800\udc61?\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc03\ud800\udc03\ud800\udc03 +false 0 + +.?\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc02 0 + +// Reluctant ? metacharacter +\ud800\udc61??\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc02 0 + +\ud800??\ud800\udc02 +\ud800\ud800\ud8001\ud800\ud800\udc02 +true \ud800\ud800\udc02 0 + +\ud800\udc61??\ud800\udc02 +\ud800\udc02 +true \ud800\udc02 0 + +\ud800??\ud800\udc02 +\ud800\udc02 +true \ud800\udc02 0 + +\ud800\udc61??\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61ccc +false 0 + +.??\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc02 0 + +// Possessive ? metacharacter +\ud800\udc61?+\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc02 0 + +\ud800\udc61?+\ud800\udc02 +\ud800\udc02 +true \ud800\udc02 0 + +\ud800\udc61?+\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61ccc +false 0 + +.?+\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc02 0 + +// Greedy + metacharacter +\ud800\udc61+\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 0 + +\udc61+\ud800\udc02 +\ud800\udc61\udc61\udc61\udc61\ud800\udc02 +true \udc61\udc61\udc61\ud800\udc02 0 + +\ud800\udc61+\ud800\udc02 +\ud800\udc02 +false 0 + +\ud800+\ud800\udc02 +\ud800\udc02 +false 0 + +\ud800\udc61+\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61ccc +false 0 + +.+\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 0 + +.+\ud800\udc02 +\ud800\udc61\udc61\udc61\udc61\ud800\udc02 +true \ud800\udc61\udc61\udc61\udc61\ud800\udc02 0 + +// Reluctant + metacharacter +\ud800\udc61+?\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 0 + +\udc61+?\ud800\udc02 +\udc61\udc61\udc61\udc61\ud800\udc02 +true \udc61\udc61\udc61\udc61\ud800\udc02 0 + +\ud800\udc61+?\ud800\udc02 +\ud800\udc02 +false 0 + +\ud800+?\ud800\udc02 +\ud800\udc02 +false 0 + +\ud800\udc61+?\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61ccc +false 0 + +.+?\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 0 + +// Possessive + metacharacter +\ud800\udc61++\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +true \ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 0 + +\ud800\udc61++\ud800\udc02 +\ud800\udc02 +false 0 + +\ud800\udc61++\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61ccc +false 0 + +.++\ud800\udc02 +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc02 +false 0 + +// Greedy Repetition +\ud800\udc61{2,3} +\ud800\udc61 +false 0 + +\ud800\udc61{2,3} +\ud800\udc61\ud800\udc61 +true \ud800\udc61\ud800\udc61 0 + +\ud800\udc61{2,3} +\ud800\udc61\ud800\udc61\ud800\udc61 +true \ud800\udc61\ud800\udc61\ud800\udc61 0 + +\ud800\udc61{2,3} +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61 +true \ud800\udc61\ud800\udc61\ud800\udc61 0 + +\ud800\udc61{3,} +zzz\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61zzz +true \ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61 0 + +\ud800\udc61{3,} +zzz\ud800\udc61\ud800\udc61zzz +false 0 + +// Reluctant Repetition +\ud800\udc61{2,3}? +\ud800\udc61 +false 0 + +\ud800\udc61{2,3}? +\ud800\udc61\ud800\udc61 +true \ud800\udc61\ud800\udc61 0 + +\ud800\udc61{2,3}? +\ud800\udc61\ud800\udc61\ud800\udc61 +true \ud800\udc61\ud800\udc61 0 + +\ud800\udc61{2,3}? +\ud800\udc61\ud800\udc61\ud800\udc61\ud800\udc61 +true \ud800\udc61\ud800\udc61 0 + +// Zero width Positive lookahead +\ud800\udc61\ud802\udc02\ud803\udc03(?=\ud804\udc04) +zzz\ud800\udc61\ud802\udc02\ud803\udc03\ud804\udc04 +true \ud800\udc61\ud802\udc02\ud803\udc03 0 + +\ud800\udc61\ud802\udc02\ud803\udc03(?=\ud804\udc04) +zzz\ud800\udc61\ud802\udc02\ud803\udc03e\ud804\udc04 +false 0 + +\ud800\udc61\ud802\udc02\ud803\udc03(?=\udcff\ud804\udc04) +zzz\ud800\udc61\ud802\udc02\ud803\udc03\udcff\ud804\udc04 +true \ud800\udc61\ud802\udc02\ud803\udc03 0 + +\ud800\udc61\ud802\udc02\ud803\udc03(?=\udcff\ud804\udc04) +zzz\ud800\udc61\ud802\udc02\ud803\udc03\ud8ff\udcff\ud804\udc04 +false 0 + +// Zero width Negative lookahead +\ud800\udc61\ud802\udc02\ud803\udc03(?!\ud804\udc04) +zz\ud800\udc61\ud802\udc02\ud803\udc03\ud804\udc04 +false 0 + +a\ud802\udc02\ud803\udc03(?!\ud804\udc04) +zza\ud802\udc02\ud803\udc03\udc04\ud804\udc04 +true a\ud802\udc02\ud803\udc03 0 + +\ud800\udc61\ud802\udc02\ud803\udc03(?!\ud804\udc04\ud8ff) +zz\ud800\udc61\ud802\udc02\ud803\udc03\ud804\udc04\ud8ffX +false 0 + +a\ud802\udc02\ud803\udc03(?!\ud804\udc04\ud8ff) +zza\ud802\udc02\ud803\udc03e\ud804\udc04\ud8ff\udcff +true a\ud802\udc02\ud803\udc03 0 + +// Zero width Positive lookbehind +(?<=\ud801\udc01\ud802\udc02)\ud803\udc03 +\ud801\udc01\ud802\udc02\ud803\udc03 +true \ud803\udc03 0 + +// Zero width Negative lookbehind +(?3 +// So that the BM optimization is part of test +\Q***\E\ud801\udc01\ud802\udc02\ud800\udc03 +***\ud801\udc01\ud802\udc02\ud800\udc03 +true ***\ud801\udc01\ud802\udc02\ud800\udc03 0 + +\ud802\udc02l\Q***\E\ud801\udc01\ud802\udc02\ud800\udc03 +\ud802\udc02l***\ud801\udc01\ud802\udc02\ud800\udc03 +true \ud802\udc02l***\ud801\udc01\ud802\udc02\ud800\udc03 0 + +\Q***\ud801\udc01\ud802\udc02\ud800\udc03 +***\ud801\udc01\ud802\udc02\ud800\udc03 +true ***\ud801\udc01\ud802\udc02\ud800\udc03 0 + +\ud802\udc02l\ud801\udc01h\Q***\E\ud801\udc01\ud802\udc02\ud800\udc03 +\ud802\udc02l\ud801\udc01h***\ud801\udc01\ud802\udc02\ud800\udc03 +true \ud802\udc02l\ud801\udc01h***\ud801\udc01\ud802\udc02\ud800\udc03 0 + +\Q***\ud801\udc01\ud802\udc02\ud800\udc03 +***\ud801\udc01\ud802\udc02\ud800\udc03 +true ***\ud801\udc01\ud802\udc02\ud800\udc03 0 + +\Q*\ud801\udc01\ud802\udc02 +*\ud801\udc01\ud802\udc02 +true *\ud801\udc01\ud802\udc02 0 + +\ud802\udc02l\ud801\udc01h\Q***\ud801\udc01\ud802\udc02\ud800\udc03 +\ud802\udc02l\ud801\udc01h***\ud801\udc01\ud802\udc02\ud800\udc03 +true \ud802\udc02l\ud801\udc01h***\ud801\udc01\ud802\udc02\ud800\udc03 0 + +\ud802\udc02l\ud801\udc01\Q***\ud801\udc01\ud802\udc02\ud800\udc03 +\ud802\udc02l\ud801\udc01***\ud801\udc01\ud802\udc02\ud800\udc03 +true \ud802\udc02l\ud801\udc01***\ud801\udc01\ud802\udc02\ud800\udc03 0 + +//Test cases below copied from i18n QE's RegexSupplementaryTests.txt +\uD800\uDFFF\uD801\uDFF1\uDB00\uDC00 +\uD800\uDFFF\uD801\uDFF1\uDB00\uDC00 +true \uD800\uDFFF\uD801\uDFF1\uDB00\uDC00 0 + +\uD800\uDFFF\uD801\uDFF1\uDB00\uDC00 +\u1000\uD801\uDFF1\uDB00\uDC00 +false 0 + +\uD800\uDFFF\uD801\uDFF1\uDB00\uDC00 +\uD800\uDFFF\uFFFF\uDB00\uDC00 +false 0 + +\uD800\uDFFF\uD801\uDFF1\uDB00\uDC00 +\uD800\uDFFF\uD801\uDFF1\uFFFF +false 0 + +\u1000.\uFFFF +\u1000\uD800\uDFFF\uFFFF +true \u1000\uD800\uDFFF\uFFFF 0 + +//======= +// Ranges +//======= +[a-\uD800\uDFFF] +\uDFFF +true \uDFFF 0 + +[a-\uD800\uDFFF] +\uD800 +true \uD800 0 + +[a-\uD800\uDFFF] +\uD800\uDFFF +true \uD800\uDFFF 0 + +[\uD800\uDC00-\uDBFF\uDFFF] +\uDBFF +false 0 + +[\uD800\uDC00-\uDBFF\uDFFF] +\uDC00 +false 0 + +[\uD800-\uDFFF] +\uD800\uDFFF +false 0 + +[\uD800-\uDFFF] +\uDFFF\uD800 +true \uDFFF 0 + +foo[^\uD800-\uDFFF] +foo\uD800\uDFFF +true foo\uD800\uDFFF 0 + +foo[^\uD800-\uDFFF] +foo\uDFFF\uD800 +false 0 + +//fo\uD800[\uDC00-\uDFFF] + +//================== +// Character Classes +//================== +// Simple class +[ab\uD800\uDFFFcd]at +\uD800at +false 0 + +[ab\uD800\uDFFFcd]at +\uD800\uDFFFat +true \uD800\uDFFFat 0 + +// Negation +[^\uD800\uDFFFcd]at +\uD800at +true \uD800at 0 + +[^\uD800\uDFFFcd]at +\uDFFFat +true \uDFFFat 0 + +// Inclusive range +[\u0000-\uD800\uDFFF-\uFFFF] +\uD800\uDFFF +true \uD800\uDFFF 0 + +// Unions +[\u0000-\uD800[\uDFFF-\uFFFF]] +\uD800\uDFFF +false 0 + + +// Intersection +[\u0000-\uFFFF&&[\uD800\uDFFF]] +\uD800\uDFFF +false 0 + +[\u0000-\uFFFF&&[\uD800\uDFFF]] +\uD800 +false 0 + +[\u0000-\uFFFF&&[\uDFFF\uD800]] +\uD800 +true \uD800 0 + +[\u0000-\uFFFF&&[\uDFFF\uD800\uDC00]] +\uDC00 +false 0 + +[\u0000-\uDFFF&&[\uD800-\uFFFF]] +\uD800\uDFFF +false 0 + +[\u0000-\uDFFF&&[\uD800-\uFFFF]] +\uDFFF\uD800 +true \uDFFF 0 + +// Subtraction +[\u0000-\uD800\uDFFF&&[^\uD800\uDC00]] +\uD800 +true \uD800 0 + +[\u0000-\uD800\uDFFF&&[^\uD800\uDC00]] +\uDC00 +true \uDC00 0 + +[\u0000-\uD800\uDFFF&&[^\uD800\uDC00]] +\uD800\uDFFF +true \uD800\uDFFF 0 + +[\u0000-\uD800\uDFFF&&[^\uD800\uDBFF\uDC00]] +\uD800 +false 0 + +[\u0000-\uD800\uDFFF&&[^\uDC00\uD800\uDBFF]] +\uD800\uDC00 +true \uD800\uDC00 0 + +// Quantifiers +a\uD800\uDFFF? +a\uD800 +true a 0 + +a\uD800\uDFFF? +a\uDFFF +true a 0 + +a\uD800\uDFFF? +a\uD800\uDFFF +true a\uD800\uDFFF 0 + +a\uDFFF\uD800? +a\uDFFF +true a\uDFFF 0 + +a\uDFFF\uD800? +a\uD800 +false 0 + +\uD800\uDFFF\uDC00? +\uD800 +false 0 + +\uD800\uDFFF\uDC00? +\uD800\uDFFF +true \uD800\uDFFF 0 + +a\uD800\uDFFF?? +a\uDFFF +true a 0 + +a\uD800\uDFFF* +a +true a 0 + +a\uD800\uDFFF* +a\uD800 +true a 0 + +\uD800\uDFFF* +\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF +true \uD800\uDFFF\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF 0 + +\uD800\uDFFF* +\uD800\uDFFF\uDFFF\uDFFF\uDFFF +true \uD800\uDFFF 0 + +\uD800*\uDFFF +\uD800\uDFFF +false 0 + +a\uD800\uDFFF* +a\uD800 +true a 0 + +\uDFFF\uD800* +\uDFFF +true \uDFFF 0 + +\uDFFF\uD800* +\uDFFF\uD800\uD800\uD800 +true \uDFFF\uD800\uD800\uD800 0 + +\uD800\uDFFF+ +\uD800\uDFFF\uDFFF\uDFFF +true \uD800\uDFFF 0 + +\uD800\uDFFF+ +\uD800 +false 0 + +\uD800\uDFFF+ +\uD800\uDFFF +true \uD800\uDFFF 0 + +\uD800\uDFFF+ +\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF +true \uD800\uDFFF\uD800\uDFFF\uD800\uDFFF 0 + +\uDFFF\uD800+ +\uDFFF\uD800\uDFFF\uD800 +false 0 + +\uD800+\uDFFF +\uD800\uDFFF +false 0 + +\uD800+\uDFFF +\uD800 +false 0 + +\uDFFF+\uD800 +\uD800 +false 0 + +\uDFFF+\uD800 +\uDFFF\uD800 +true \uDFFF\uD800 0 + +\uD800\uDFFF{3} +\uD800\uDFFF\uDFFF\uDFFF +false 0 + +\uD800\uDFFF{3} +\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF +true \uD800\uDFFF\uD800\uDFFF\uD800\uDFFF 0 + +\uDFFF\uD800{3} +\uDFFF\uD800\uDFFF\uD800\uDFFF\uD800 +false 0 + +\uDFFF\uD800{3} +\uDFFF\uD800\uD800\uD800 +true \uDFFF\uD800\uD800\uD800 0 + +\uD800\uDFFF{2,} +\uD800\uDFFF +false 0 + +\uD800\uDFFF{2,} +\uD800\uDFFF\uDFFF +false 0 + +\uD800\uDFFF{2,} +\uD800\uDFFF\uD800\uDFFF +true \uD800\uDFFF\uD800\uDFFF 0 + +\uDFFF\uD800{2,} +\uDFFF\uD800\uDFFF\uD800 +false 0 + +\uDFFF\uD800{2,} +\uDFFF\uD800\uD800\uD800 +true \uDFFF\uD800\uD800\uD800 0 + +\uD800\uDFFF{3,4} +\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF +true \uD800\uDFFF\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF 0 + +\uD800\uDFFF{3,4} +\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF\uD800 +true \uD800\uDFFF\uD800\uDFFF\uD800\uDFFF 0 + +\uD800\uDFFF{3,4} +\uD800\uDFFF\uD800\uD800\uDFFF\uD800\uDFFF +false 0 + +\uDFFF\uD800{3,5} +\uDFFF\uD800\uD800\uD800\uD800\uD800\uD800\uD800 +true \uDFFF\uD800\uD800\uD800\uD800\uD800 0 + +\uD800\uDFFF{3,5} +\uD800\uDFFF\uDFFF\uDFFF +false 0 + +\uD800\uDFFF{3,5} +\uD800\uDFFF\uD800\uD800\uDFFF\uD800\uDFFF\uD800\uDFFF +true \uD800\uDFFF\uD800\uDFFF\uD800\uDFFF 0 + +// Groupings +(\uD800(\uDFFF)) +\uD800\uDFFF +false 2 + +(\uD800(\uDC00)(\uDFFF)) +\uD800\uDC00\uDFFF +false 3 + +((\uD800)(\uDFFF)) +\uD800\uDFFF +false 3 + +(\uD800(\uDFFF)\uDFFF) +\uD800\uDFFF +false 2 + +(\uDFFF(\uD800)(\uDBFF)) +\uDFFF\uD800\uDBFF +true \uDFFF\uD800\uDBFF 3 \uDFFF\uD800\uDBFF \uD800 \uDBFF + +(\uDFFF(\uD800)(\uDC00)) +\uDFFF\uD800\uDC00 +false 3 + +(\uDFFF\uD800(\uDC00\uDBFF)) +\uDFFF\uD800\uDC00\uDBFF +false 2 + +(\uD800\uDFFF(\uDBFF)(\uDC00)) +\uD800\uDFFF\uDBFF\uDC00 +false 3 + +(\uD800\uDFFF(\uDBFF\uDC00)) +\uD800\uDFFF\uDBFF\uDC00 +true \uD800\uDFFF\uDBFF\uDC00 2 \uD800\uDFFF\uDBFF\uDC00 \uDBFF\uDC00 diff --git a/jdk/test/java/util/regex/TestCases.txt b/jdk/test/java/util/regex/TestCases.txt new file mode 100644 index 00000000000..fd41df33f76 --- /dev/null +++ b/jdk/test/java/util/regex/TestCases.txt @@ -0,0 +1,1092 @@ +// +// Copyright 1999-2009 Sun Microsystems, Inc. All Rights Reserved. +// DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +// +// This code is free software; you can redistribute it and/or modify it +// under the terms of the GNU General Public License version 2 only, as +// published by the Free Software Foundation. +// +// This code is distributed in the hope that it will be useful, but WITHOUT +// ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +// FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +// version 2 for more details (a copy is included in the LICENSE file that +// accompanied this code). +// +// You should have received a copy of the GNU General Public License version +// 2 along with this work; if not, write to the Free Software Foundation, +// Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. +// +// Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, +// CA 95054 USA or visit www.sun.com if you need additional information or +// have any questions. +// +// +// This file contains test cases for regular expressions. +// A test case consists of three lines: +// The first line is a pattern used in the test +// The second line is the input to search for the pattern in +// The third line is a concatentation of the match, the number of groups, +// and the contents of the first four subexpressions. +// Empty lines and lines beginning with comment slashes are ignored. +// +// Test unsetting of backed off groups +^(a)?a +a +true a 1 + +^(aa(bb)?)+$ +aabbaa +true aabbaa 2 aa bb + +((a|b)?b)+ +b +true b 2 b + +(aaa)?aaa +aaa +true aaa 1 + +^(a(b)?)+$ +aba +true aba 2 a b + +^(a(b(c)?)?)?abc +abc +true abc 3 + +^(a(b(c))).* +abc +true abc 3 abc bc c + +// use of x modifier +abc(?x)blah +abcblah +true abcblah 0 + +abc(?x) blah +abcblah +true abcblah 0 + +abc(?x) blah blech +abcblahblech +true abcblahblech 0 + +abc(?x) blah # ignore comment +abcblah +true abcblah 0 + +// Simple alternation +a|b +a +true a 0 + +a|b +z +false 0 + +a|b +b +true b 0 + +a|b|cd +cd +true cd 0 + +a|ad +ad +true a 0 + +z(a|ac)b +zacb +true zacb 1 ac + +// Simple char class +[abc]+ +ababab +true ababab 0 + +[abc]+ +defg +false 0 + +[abc]+[def]+[ghi]+ +zzzaaddggzzz +true aaddgg 0 + +// Range char class +[a-g]+ +zzzggg +true ggg 0 + +[a-g]+ +mmm +false 0 + +[a-]+ +za-9z +true a- 0 + +[a-\\u4444]+ +za-9z +true za 0 + +// Negated char class +[^abc]+ +ababab +false 0 + +[^abc]+ +aaabbbcccdefg +true defg 0 + +// Making sure a ^ not in first position matches literal ^ +[abc^b] +b +true b 0 + +[abc^b] +^ +true ^ 0 + +// Class union and intersection +[abc[def]] +b +true b 0 + +[abc[def]] +e +true e 0 + +[a-d[0-9][m-p]] +a +true a 0 + +[a-d[0-9][m-p]] +o +true o 0 + +[a-d[0-9][m-p]] +4 +true 4 0 + +[a-d[0-9][m-p]] +e +false 0 + +[a-d[0-9][m-p]] +u +false 0 + +[[a-d][0-9][m-p]] +b +true b 0 + +[[a-d][0-9][m-p]] +z +false 0 + +[a-c[d-f[g-i]]] +a +true a 0 + +[a-c[d-f[g-i]]] +e +true e 0 + +[a-c[d-f[g-i]]] +h +true h 0 + +[a-c[d-f[g-i]]] +m +false 0 + +[a-c[d-f[g-i]]m] +m +true m 0 + +[abc[def]ghi] +a +true a 0 + +[abc[def]ghi] +d +true d 0 + +[abc[def]ghi] +h +true h 0 + +[abc[def]ghi] +w +false 0 + +[a-c&&[d-f]] +a +false 0 + +[a-c&&[d-f]] +e +false 0 + +[a-c&&[d-f]] +z +false 0 + +[[a-c]&&[d-f]] +a +false 0 + +[[a-c]&&[d-f]] +e +false 0 + +[[a-c]&&[d-f]] +z +false 0 + +[a-c&&d-f] +a +false 0 + +[a-m&&m-z] +m +true m 0 + +[a-m&&m-z&&a-c] +m +false 0 + +[a-m&&m-z&&a-z] +m +true m 0 + +[[a-m]&&[m-z]] +a +false 0 + +[[a-m]&&[m-z]] +m +true m 0 + +[[a-m]&&[m-z]] +z +false 0 + +[[a-m]&&[^a-c]] +a +false 0 + +[[a-m]&&[^a-c]] +d +true d 0 + +[a-m&&[^a-c]] +a +false 0 + +[a-m&&[^a-c]] +d +true d 0 + +[a-cd-f&&[d-f]] +a +false 0 + +[a-cd-f&&[d-f]] +e +true e 0 + +[[a-c]&&d-fa-c] +a +true a 0 + +[[a-c]&&[d-f][a-c]] +a +true a 0 + +[[a-c][d-f]&&abc] +a +true a 0 + +[[a-c][d-f]&&abc[def]] +e +true e 0 + +[[a-c]&&[b-d]&&[c-e]] +a +false 0 + +[[a-c]&&[b-d]&&[c-e]] +c +true c 0 + +[[a-c]&&[b-d][c-e]&&[u-z]] +c +false 0 + +[abc[^bcd]] +a +true a 0 + +[abc[^bcd]] +d +false 0 + +[a-c&&a-d&&a-eghi] +b +true b 0 + +[a-c&&a-d&&a-eghi] +g +false 0 + +[[a[b]]&&[b[a]]] +a +true a 0 + +[[a]&&[b][c][a]&&[^d]] +a +true a 0 + +[[a]&&[b][c][a]&&[^d]] +d +false 0 + +[[[a-d]&&[c-f]]] +a +false 0 + +[[[a-d]&&[c-f]]] +c +true c 0 + +[[[a-d]&&[c-f]]&&[c]] +c +true c 0 + +[[[a-d]&&[c-f]]&&[c]&&c] +c +true c 0 + +[[[a-d]&&[c-f]]&&[c]&&c&&c] +c +true c 0 + +[[[a-d]&&[c-f]]&&[c]&&c&&[cde]] +c +true c 0 + +[z[abc&&bcd]] +c +true c 0 + +[z[abc&&bcd]&&[u-z]] +z +true z 0 + +[x[abc&&bcd[z]]&&[u-z]] +z +false 0 + +[x[[wz]abc&&bcd[z]]&&[u-z]] +z +true z 0 + +[[abc]&&[def]abc] +a +true a 0 + +[[abc]&&[def]xyz[abc]] +a +true a 0 + +\pL +a +true a 0 + +\pL +7 +false 0 + +\p{L} +a +true a 0 + +\p{LC} +a +true a 0 + +\p{LC} +A +true A 0 + +\p{IsL} +a +true a 0 + +\p{IsLC} +a +true a 0 + +\p{IsLC} +A +true A 0 + +\p{IsLC} +9 +false 0 + +\P{IsLC} +9 +true 9 0 + +// Guillemet left is initial quote punctuation +\p{Pi} +\u00ab +true \u00ab 0 + +\P{Pi} +\u00ac +true \u00ac 0 + +// Guillemet right is final quote punctuation +\p{IsPf} +\u00bb +true \u00bb 0 + +\p{P} +\u00bb +true \u00bb 0 + +\p{P}+ +\u00bb +true \u00bb 0 + +\P{IsPf} +\u00bc +true \u00bc 0 + +\P{IsP} +\u00bc +true \u00bc 0 + +\p{L1} +\u00bc +true \u00bc 0 + +\p{L1}+ +\u00bc +true \u00bc 0 + +\p{L1} +\u02bc +false 0 + +\p{ASCII} +a +true a 0 + +\p{IsASCII} +a +true a 0 + +\p{IsASCII} +\u0370 +false 0 + +\pLbc +abc +true abc 0 + +a[r\p{InGreek}]c +a\u0370c +true a\u0370c 0 + +a\p{InGreek} +a\u0370 +true a\u0370 0 + +a\P{InGreek} +a\u0370 +false 0 + +a\P{InGreek} +ab +true ab 0 + +a{^InGreek} +- +error + +a\p{^InGreek} +- +error + +a\P{^InGreek} +- +error + +a\p{InGreek} +a\u0370 +true a\u0370 0 + +a[\p{InGreek}]c +a\u0370c +true a\u0370c 0 + +a[\P{InGreek}]c +a\u0370c +false 0 + +a[\P{InGreek}]c +abc +true abc 0 + +a[{^InGreek}]c +anc +true anc 0 + +a[{^InGreek}]c +azc +false 0 + +a[\p{^InGreek}]c +- +error + +a[\P{^InGreek}]c +- +error + +a[\p{InGreek}] +a\u0370 +true a\u0370 0 + +a[r\p{InGreek}]c +arc +true arc 0 + +a[\p{InGreek}r]c +arc +true arc 0 + +a[r\p{InGreek}]c +arc +true arc 0 + +a[^\p{InGreek}]c +a\u0370c +false 0 + +a[^\P{InGreek}]c +a\u0370c +true a\u0370c 0 + +a[\p{InGreek}&&[^\u0370]]c +a\u0370c +false 0 + +// Test the dot metacharacter +a.c.+ +a#c%& +true a#c%& 0 + +ab. +ab\n +false 0 + +(?s)ab. +ab\n +true ab\n 0 + +a[\p{L}&&[\P{InGreek}]]c +a\u6000c +true a\u6000c 0 + +a[\p{L}&&[\P{InGreek}]]c +arc +true arc 0 + +a[\p{L}&&[\P{InGreek}]]c +a\u0370c +false 0 + +a\p{InGreek}c +a\u0370c +true a\u0370c 0 + +a\p{Sc} +a$ +true a$ 0 + +// Test the word char escape sequence +ab\wc +abcc +true abcc 0 + +\W\w\W +#r# +true #r# 0 + +\W\w\W +rrrr#ggg +false 0 + +abc[\w] +abcd +true abcd 0 + +abc[\sdef]* +abc def +true abc def 0 + +abc[\sy-z]* +abc y z +true abc y z 0 + +abc[a-d\sm-p]* +abcaa mn p +true abcaa mn p 0 + +// Test the whitespace escape sequence +ab\sc +ab c +true ab c 0 + +\s\s\s +blah err +false 0 + +\S\S\s +blah err +true ah 0 + +// Test the digit escape sequence +ab\dc +ab9c +true ab9c 0 + +\d\d\d +blah45 +false 0 + +// Test the caret metacharacter +^abc +abcdef +true abc 0 + +^abc +bcdabc +false 0 + +// Greedy ? metacharacter +a?b +aaaab +true ab 0 + +a?b +b +true b 0 + +a?b +aaaccc +false 0 + +.?b +aaaab +true ab 0 + +// Reluctant ? metacharacter +a??b +aaaab +true ab 0 + +a??b +b +true b 0 + +a??b +aaaccc +false 0 + +.??b +aaaab +true ab 0 + +// Possessive ? metacharacter +a?+b +aaaab +true ab 0 + +a?+b +b +true b 0 + +a?+b +aaaccc +false 0 + +.?+b +aaaab +true ab 0 + +// Greedy + metacharacter +a+b +aaaab +true aaaab 0 + +a+b +b +false 0 + +a+b +aaaccc +false 0 + +.+b +aaaab +true aaaab 0 + +// Reluctant + metacharacter +a+?b +aaaab +true aaaab 0 + +a+?b +b +false 0 + +a+?b +aaaccc +false 0 + +.+?b +aaaab +true aaaab 0 + +// Possessive + metacharacter +a++b +aaaab +true aaaab 0 + +a++b +b +false 0 + +a++b +aaaccc +false 0 + +.++b +aaaab +false 0 + +// Greedy Repetition +a{2,3} +a +false 0 + +a{2,3} +aa +true aa 0 + +a{2,3} +aaa +true aaa 0 + +a{2,3} +aaaa +true aaa 0 + +a{3,} +zzzaaaazzz +true aaaa 0 + +a{3,} +zzzaazzz +false 0 + +// Reluctant Repetition +a{2,3}? +a +false 0 + +a{2,3}? +aa +true aa 0 + +a{2,3}? +aaa +true aa 0 + +a{2,3}? +aaaa +true aa 0 + +// Zero width Positive lookahead +abc(?=d) +zzzabcd +true abc 0 + +abc(?=d) +zzzabced +false 0 + +// Zero width Negative lookahead +abc(?!d) +zzabcd +false 0 + +abc(?!d) +zzabced +true abc 0 + +// Zero width Positive lookbehind +\w(?<=a) +###abc### +true a 0 + +\w(?<=a) +###ert### +false 0 + +// Zero width Negative lookbehind +(?3 +// So that the BM optimization is part of test +\Q***\Eabc +***abc +true ***abc 0 + +bl\Q***\Eabc +bl***abc +true bl***abc 0 + +\Q***abc +***abc +true ***abc 0 + +blah\Q***\Eabc +blah***abc +true blah***abc 0 + +\Q***abc +***abc +true ***abc 0 + +\Q*ab +*ab +true *ab 0 + +blah\Q***abc +blah***abc +true blah***abc 0 + +bla\Q***abc +bla***abc +true bla***abc 0 + +// Escapes in char classes +[ab\Qdef\E] +d +true d 0 + +[ab\Q[\E] +[ +true [ 0 + +[\Q]\E] +] +true ] 0 + +[\Q\\E] +\ +true \ 0 + +[\Q(\E] +( +true ( 0 + +[\n-#] +! +true ! 0 + +[\n-#] +- +false 0 + +[\w-#] +! +false 0 + +[\w-#] +a +true a 0 + +[\w-#] +- +true - 0 + +[\w-#] +# +true # 0 + +[\043]+ +blahblah#blech +true # 0 + +[\042-\044]+ +blahblah#blech +true # 0 + +[\u1234-\u1236] +blahblah\u1235blech +true \u1235 0 + +[^\043]* +blahblah#blech +true blahblah 0 + +(|f)?+ +foo +true 1