--- old/src/share/classes/java/util/regex/Matcher.java 2013-04-30 13:16:55.000000000 -0700 +++ new/src/share/classes/java/util/regex/Matcher.java 2013-04-30 13:16:55.000000000 -0700 @@ -25,6 +25,7 @@ package java.util.regex; +import java.util.Objects; /** * An engine that performs match operations on a {@link java.lang.CharSequence @@ -370,12 +371,37 @@ public int start(int group) { if (first < 0) throw new IllegalStateException("No match available"); - if (group > groupCount()) + if (group < 0 || group > groupCount()) throw new IndexOutOfBoundsException("No group " + group); return groups[group * 2]; } /** + * Returns the start index of the subsequence captured by the given + * named-capturing group during the + * previous match operation. + * + * @param name + * The name of a named-capturing group in this matcher's pattern + * + * @return The index of the first character captured by the group, + * or {@code -1} if the match was successful but the group + * itself did not match anything + * + * @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 + * @since 1.8 + */ + public int start(String name) { + return groups[getMatchedGroupIndex(name) * 2]; + } + + /** * Returns the offset after the last character matched.

* * @return The offset after the last character matched @@ -417,12 +443,36 @@ public int end(int group) { if (first < 0) throw new IllegalStateException("No match available"); - if (group > groupCount()) + if (group < 0 || group > groupCount()) throw new IndexOutOfBoundsException("No group " + group); return groups[group * 2 + 1]; } /** + * Returns the offset after the last character of the subsequence + * captured by the given named-capturing + * group during the previous match operation. + * + * @param name + * The name of a named-capturing group in this matcher's pattern + * + * @return The offset after the last character captured by the group, + * or {@code -1} if the match was successful + * but the group itself did not match anything + * + * @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 int end(String name) { + return groups[getMatchedGroupIndex(name) * 2 + 1]; + } + + /** * Returns the input subsequence matched by the previous match. * *

For a matcher m with input sequence s, @@ -518,13 +568,7 @@ * @since 1.7 */ 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); + int group = getMatchedGroupIndex(name); if ((groups[group*2] == -1) || (groups[group*2+1] == -1)) return null; return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString(); @@ -1257,4 +1301,17 @@ return text.charAt(i); } + /** + * Returns the group index of the matched capturing group. + * + * @return the index of the named-capturing group + */ + int getMatchedGroupIndex(String name) { + Objects.requireNonNull(name, "Group name"); + if (first < 0) + throw new IllegalStateException("No match found"); + if (!parentPattern.namedGroups().containsKey(name)) + throw new IllegalArgumentException("No group with name <" + name + ">"); + return parentPattern.namedGroups().get(name); + } } --- old/test/java/util/regex/RegExTest.java 2013-04-30 13:16:57.000000000 -0700 +++ new/test/java/util/regex/RegExTest.java 2013-04-30 13:16:56.000000000 -0700 @@ -33,7 +33,7 @@ * 5013885 5003322 4988891 5098443 5110268 6173522 4829857 5027748 6376940 * 6358731 6178785 6284152 6231989 6497148 6486934 6233084 6504326 6635133 * 6350801 6676425 6878475 6919132 6931676 6948903 6990617 7014645 7039066 - * 7067045 7014640 7189363 8007395 + * 7067045 7014640 7189363 8007395 8013252 8013254 */ import java.util.regex.*; @@ -3390,7 +3390,9 @@ private static void check(Pattern p, String s, String g, String expected) { Matcher m = p.matcher(s); m.find(); - if (!m.group(g).equals(expected)) + if (!m.group(g).equals(expected) || + s.charAt(m.start(g)) != expected.charAt(0) || + s.charAt(m.end(g) - 1) != expected.charAt(expected.length() - 1)) failCount++; } @@ -3420,19 +3422,42 @@ failCount++; } - private static void checkExpectedFail(Matcher m, String g) { + private static void checkExpectedIAE(Matcher m, String g) { m.find(); try { m.group(g); - } catch (IllegalArgumentException iae) { + } catch (IllegalArgumentException x) { //iae.printStackTrace(); - return; - } catch (NullPointerException npe) { - return; + try { + m.start(g); + } catch (IllegalArgumentException xx) { + try { + m.start(g); + } catch (IllegalArgumentException xxx) { + return; + } + } } failCount++; } + private static void checkExpectedNPE(Matcher m) { + m.find(); + try { + m.group(null); + } catch (NullPointerException x) { + try { + m.start(null); + } catch (NullPointerException xx) { + try { + m.end(null); + } catch (NullPointerException xxx) { + return; + } + } + } + failCount++; + } private static void namedGroupCaptureTest() throws Exception { check(Pattern.compile("x+(?y+)z+"), @@ -3559,10 +3584,9 @@ checkExpectedFail("(?<6groupnamestartswithdigit>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); + checkExpectedIAE(Pattern.compile("(?abc)(def)").matcher("abcdef"), + "gnameX"); + checkExpectedNPE(Pattern.compile("(?abc)(def)").matcher("abcdef")); report("NamedGroupCapture"); } @@ -3759,6 +3783,7 @@ Matcher spaceP = Pattern.compile("\\p{IsWhiteSpace}").matcher(""); Matcher definedP = Pattern.compile("\\p{IsAssigned}").matcher(""); Matcher nonCCPP = Pattern.compile("\\p{IsNoncharacterCodePoint}").matcher(""); + Matcher joinCrtl = Pattern.compile("\\p{IsJoinControl}").matcher(""); // javaMethod Matcher lowerJ = Pattern.compile("\\p{javaLowerCase}").matcher(""); @@ -3829,7 +3854,8 @@ Character.isIdeographic(cp) != ideogP.reset(str).matches() || Character.isIdeographic(cp) != ideogJ.reset(str).matches() || (Character.UNASSIGNED == type) == definedP.reset(str).matches() || - POSIX_Unicode.isNoncharacterCodePoint(cp) != nonCCPP.reset(str).matches()) + POSIX_Unicode.isNoncharacterCodePoint(cp) != nonCCPP.reset(str).matches() || + POSIX_Unicode.isJoinControl(cp) != joinCrtl.reset(str).matches()) failCount++; }