/* * Copyright (C) 2014 The Android Open Source Project * Copyright (c) 1999, 2013, Oracle and/or its affiliates. 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. Oracle designates this * particular file as subject to the "Classpath" exception as provided * by Oracle 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 Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA * or visit www.oracle.com if you need additional information or have any * questions. */ package java.util.regex; import libcore.util.NativeAllocationRegistry; /** * An engine that performs match operations on a {@link java.lang.CharSequence * character sequence} by interpreting a {@link Pattern}. * *

A matcher is created from a pattern by invoking the pattern's {@link * Pattern#matcher matcher} method. Once created, a matcher can be used to * perform three different kinds of match operations: * *

* *

Each of these methods returns a boolean indicating success or failure. * More information about a successful match can be obtained by querying the * state of the matcher. * *

A matcher finds matches in a subset of its input called the * region. By default, the region contains all of the matcher's input. * The region can be modified via the{@link #region region} method and queried * via the {@link #regionStart regionStart} and {@link #regionEnd regionEnd} * methods. The way that the region boundaries interact with some pattern * constructs can be changed. See {@link #useAnchoringBounds * useAnchoringBounds} and {@link #useTransparentBounds useTransparentBounds} * for more details. * *

This class also defines methods for replacing matched subsequences with * new strings whose contents can, if desired, be computed from the match * result. The {@link #appendReplacement appendReplacement} and {@link * #appendTail appendTail} methods can be used in tandem in order to collect * the result into an existing string buffer, or the more convenient {@link * #replaceAll replaceAll} method can be used to create a string in which every * matching subsequence in the input sequence is replaced. * *

The explicit state of a matcher includes the start and end indices of * the most recent successful match. It also includes the start and end * indices of the input subsequence captured by each capturing group in the pattern as well as a total * count of such subsequences. As a convenience, methods are also provided for * returning these captured subsequences in string form. * *

The explicit state of a matcher is initially undefined; attempting to * query any part of it before a successful match will cause an {@link * IllegalStateException} to be thrown. The explicit state of a matcher is * recomputed by every match operation. * *

The implicit state of a matcher includes the input character sequence as * well as the append position, which is initially zero and is updated * by the {@link #appendReplacement appendReplacement} method. * *

A matcher may be reset explicitly by invoking its {@link #reset()} * method or, if a new input sequence is desired, its {@link * #reset(java.lang.CharSequence) reset(CharSequence)} method. Resetting a * matcher discards its explicit state information and sets the append position * to zero. * *

Instances of this class are not safe for use by multiple concurrent * threads.

* * * @author Mike McCloskey * @author Mark Reinhold * @author JSR-51 Expert Group * @since 1.4 * @spec JSR-51 */ public final class Matcher implements MatchResult { /** * The Pattern object that created this Matcher. */ private Pattern pattern; /** * The address of the native peer. * Uses of this must be manually synchronized to avoid native crashes. */ private long address; /** * If non-null, a Runnable that can be used to explicitly deallocate address. */ private Runnable nativeFinalizer; private static final NativeAllocationRegistry registry = new NativeAllocationRegistry( Matcher.class.getClassLoader(), getNativeFinalizer(), nativeSize()); /** * Holds the input text. */ private String input; /** * Holds the start of the region, or 0 if the matching should start at the * beginning of the text. */ private int regionStart; /** * Holds the end of the region, or input.length() if the matching should * go until the end of the input. */ private int regionEnd; /** * Holds the position where the next append operation will take place. */ private int appendPos; /** * Reflects whether a match has been found during the most recent find * operation. */ private boolean matchFound; /** * Holds the offsets for the most recent match. */ private int[] matchOffsets; /** * Reflects whether the bounds of the region are anchoring. */ private boolean anchoringBounds = true; /** * Reflects whether the bounds of the region are transparent. */ private boolean transparentBounds; /** * All matchers have the state used by Pattern during a match. */ Matcher(Pattern parent, CharSequence text) { usePattern(parent); reset(text); } /** * Returns the pattern that is interpreted by this matcher. * * @return The pattern for which this matcher was created */ public Pattern pattern() { return pattern; } /** * Returns the match state of this matcher as a {@link MatchResult}. * The result is unaffected by subsequent operations performed upon this * matcher. * * @return a MatchResult with the state of this matcher * @since 1.5 */ public MatchResult toMatchResult() { ensureMatch(); return new OffsetBasedMatchResult(input, matchOffsets); } /** * Changes the Pattern that this Matcher uses to * find matches with. * *

This method causes this matcher to lose information * about the groups of the last match that occurred. The * matcher's position in the input is maintained and its * last append position is unaffected.

* * @param newPattern * The new pattern used by this matcher * @return This matcher * @throws IllegalArgumentException * If newPattern is null * @since 1.5 */ public Matcher usePattern(Pattern newPattern) { if (newPattern == null) { throw new IllegalArgumentException("newPattern == null"); } this.pattern = newPattern; synchronized (this) { if (nativeFinalizer != null) { nativeFinalizer.run(); address = 0; // In case openImpl throws. nativeFinalizer = null; } address = openImpl(pattern.address); nativeFinalizer = registry.registerNativeAllocation(this, address); } if (input != null) { resetForInput(); } matchOffsets = new int[(groupCount() + 1) * 2]; matchFound = false; return this; } /** * Returns the offset after the last character matched.

* * @return The offset after the last character matched * * @throws IllegalStateException * If no match has yet been attempted, * or if the previous match operation failed */ public int end() { return end(0); } /** * Returns the offset after the last character of the subsequence * captured by the given group during the previous match operation. * *

Capturing groups are indexed from left * to right, starting at one. Group zero denotes the entire pattern, so * the expression m.end(0) is equivalent to * m.end().

* * @param group * The index of a capturing group in this matcher's pattern * * @return The offset after the last character captured by the group, * or -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 IndexOutOfBoundsException * If there is no capturing group in the pattern * with the given index */ public int end(int group) { ensureMatch(); return matchOffsets[(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 * @since 1.8 */ public int end(String name) { ensureMatch(); return matchOffsets[getMatchedGroupIndex(pattern.address, name) * 2 + 1]; } /** * Returns the input subsequence matched by the previous match. * *

For a matcher m with input sequence s, * the expressions m.group() and * s.substring(m.start(), m.end()) * are equivalent.

* *

Note that some patterns, for example a*, match the empty * string. This method will return the empty string when the pattern * successfully matches the empty string in the input.

* * @return The (possibly empty) subsequence matched by the previous match, * in string form * * @throws IllegalStateException * If no match has yet been attempted, * or if the previous match operation failed */ public String group() { return group(0); } /** * Returns the input subsequence captured by the given group during the * previous match operation. * *

For a matcher m, input sequence s, and group index * g, the expressions m.group(g) and * s.substring(m.start(g), m.end(g)) * are equivalent.

* *

Capturing groups are indexed from left * to right, starting at one. Group zero denotes the entire pattern, so * the expression m.group(0) is equivalent to m.group(). *

* *

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 group * The index of a capturing group in this matcher's pattern * * @return The (possibly empty) subsequence captured by the 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 IndexOutOfBoundsException * If there is no capturing group in the pattern * with the given index */ public String group(int group) { ensureMatch(); int from = matchOffsets[group * 2]; int to = matchOffsets[(group * 2) + 1]; if (from == -1 || to == -1) { return null; } else { return input.substring(from, to); } } /** * 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 * @since 1.7 */ public String group(String name) { ensureMatch(); int group = getMatchedGroupIndex(pattern.address, name); int from = matchOffsets[group * 2]; int to = matchOffsets[(group * 2) + 1]; if (from == -1 || to == -1) { return null; } else { return input.substring(from, to); } } /** * Returns the number of capturing groups in this matcher's pattern. * *

Group zero denotes the entire pattern by convention. It is not * included in this count. * *

Any non-negative integer smaller than or equal to the value * returned by this method is guaranteed to be a valid group index for * this matcher.

* * @return The number of capturing groups in this matcher's pattern */ public int groupCount() { synchronized (this) { return groupCountImpl(address); } } /** * Attempts to match the entire region against the pattern. * *

If the match succeeds then more information can be obtained via the * start, end, and group methods.

* * @return true if, and only if, the entire region sequence * matches this matcher's pattern */ public boolean matches() { synchronized (this) { matchFound = matchesImpl(address, matchOffsets); } return matchFound; } /** * Attempts to find the next subsequence of the input sequence that matches * the pattern. * *

This method starts at the beginning of this matcher's region, or, if * a previous invocation of the method was successful and the matcher has * not since been reset, at the first character not matched by the previous * match. * *

If the match succeeds then more information can be obtained via the * start, end, and group methods.

* * @return true if, and only if, a subsequence of the input * sequence matches this matcher's pattern */ public boolean find() { synchronized (this) { matchFound = findNextImpl(address, matchOffsets); } return matchFound; } /** * Resets this matcher and then attempts to find the next subsequence of * the input sequence that matches the pattern, starting at the specified * index. * *

If the match succeeds then more information can be obtained via the * start, end, and group methods, and subsequent * invocations of the {@link #find()} method will start at the first * character not matched by this match.

* * @throws IndexOutOfBoundsException * If start is less than zero or if start is greater than the * length of the input sequence. * * @return true if, and only if, a subsequence of the input * sequence starting at the given index matches this matcher's * pattern */ public boolean find(int start) { if (start < 0 || start > input.length()) { throw new IndexOutOfBoundsException("start=" + start + "; length=" + input.length()); } synchronized (this) { matchFound = findImpl(address, start, matchOffsets); } return matchFound; } /** * Attempts to match the input sequence, starting at the beginning of the * region, against the pattern. * *

Like the {@link #matches matches} method, this method always starts * at the beginning of the region; unlike that method, it does not * require that the entire region be matched. * *

If the match succeeds then more information can be obtained via the * start, end, and group methods.

* * @return true if, and only if, a prefix of the input * sequence matches this matcher's pattern */ public boolean lookingAt() { synchronized (this) { matchFound = lookingAtImpl(address, matchOffsets); } return matchFound; } /** * Returns a literal replacement String for the specified * String. * * This method produces a String that will work * as a literal replacement s in the * appendReplacement method of the {@link Matcher} class. * The String produced will match the sequence of characters * in s treated as a literal sequence. Slashes ('\') and * dollar signs ('$') will be given no special meaning. * * @param s The string to be literalized * @return A literal string replacement * @since 1.5 */ public static String quoteReplacement(String s) { if ((s.indexOf('\\') == -1) && (s.indexOf('$') == -1)) return s; StringBuilder sb = new StringBuilder(); for (int i=0; i This method performs the following actions:

* *
    * *

  1. It reads characters from the input sequence, starting at the * append position, and appends them to the given string buffer. It * stops after reading the last character preceding the previous match, * that is, the character at index {@link * #start()} - 1.

    2. * *

  2. It appends the given replacement string to the string buffer. *

    3. * *

  3. It sets the append position of this matcher to the index of * the last character matched, plus one, that is, to {@link #end()}. *

    4. * *
* *

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 the corresponding * {@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 * reference. If the second group matched the string "foo", for * example, then passing the replacement string "$2bar" would * cause "foobar" to be appended to the string buffer. A dollar * sign ($) may be included as a literal in the replacement * string by preceding it with a backslash (\$). * *

Note that backslashes (\) and dollar signs ($) in * the replacement string may cause the results to be different than if it * were being treated as a literal replacement string. Dollar signs may be * treated as references to captured subsequences as described above, and * backslashes are used to escape literal characters in the replacement * string. * *

This method is intended to be used in a loop together with the * {@link #appendTail appendTail} and {@link #find find} methods. The * following code, for example, writes one dog two dogs in the * yard to the standard-output stream:

* * 
     * Pattern p = Pattern.compile("cat");
     * Matcher m = p.matcher("one cat two cats in the yard");
     * StringBuffer sb = new StringBuffer();
     * while (m.find()) {
     *     m.appendReplacement(sb, "dog");
     * }
     * m.appendTail(sb);
     * System.out.println(sb.toString());
* * @param sb * The target string buffer * * @param replacement * The replacement string * * @return This matcher * * @throws IllegalStateException * 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 */ public Matcher appendReplacement(StringBuffer sb, String replacement) { sb.append(input.substring(appendPos, start())); appendEvaluated(sb, replacement); appendPos = end(); return this; } /** * Internal helper method to append a given string to a given string buffer. * If the string contains any references to groups, these are replaced by * the corresponding group's contents. * * @param buffer the string buffer. * @param s the string to append. */ private void appendEvaluated(StringBuffer buffer, String s) { boolean escape = false; boolean dollar = false; boolean escapeNamedGroup = false; int escapeNamedGroupStart = -1; for (int i = 0; i < s.length(); i++) { char c = s.charAt(i); if (c == '\\' && !escape) { escape = true; } else if (c == '$' && !escape) { dollar = true; } else if (c >= '0' && c <= '9' && dollar) { buffer.append(group(c - '0')); dollar = false; } else if (c == '{' && dollar) { escapeNamedGroup = true; escapeNamedGroupStart = i; } else if (c == '}' && dollar && escapeNamedGroup) { String namedGroupName = s.substring(escapeNamedGroupStart + 1, i); buffer.append(group(namedGroupName)); dollar = false; escapeNamedGroup = false; } else if (c != '}' && dollar && escapeNamedGroup) { continue; } else { buffer.append(c); dollar = false; escape = false; escapeNamedGroup = false; } } if (escapeNamedGroup) { throw new IllegalArgumentException("Missing ending brace '}' from replacement string"); } if (escape) { throw new ArrayIndexOutOfBoundsException(s.length()); } } /** * Implements a terminal append-and-replace step. * *

This method reads characters from the input sequence, starting at * the append position, and appends them to the given string buffer. It is * intended to be invoked after one or more invocations of the {@link * #appendReplacement appendReplacement} method in order to copy the * remainder of the input sequence.

* * @param sb * The target string buffer * * @return The target string buffer */ public StringBuffer appendTail(StringBuffer sb) { if (appendPos < regionEnd) { sb.append(input.substring(appendPos, regionEnd)); } return sb; } /** * Replaces every subsequence of the input sequence that matches the * pattern with the given replacement string. * *

This method first resets this matcher. It then scans the input * sequence looking for matches of the pattern. Characters that are not * part of any match are appended directly to the result string; each match * is replaced in the result by the replacement string. The replacement * string may contain references to captured subsequences as in the {@link * #appendReplacement appendReplacement} method. * *

Note that backslashes (\) and dollar signs ($) in * the replacement string may cause the results to be different than if it * were being treated as a literal replacement string. Dollar signs may be * treated as references to captured subsequences as described above, and * backslashes are used to escape literal characters in the replacement * string. * *

Given the regular expression a*b, the input * "aabfooaabfooabfoob", and the replacement string * "-", an invocation of this method on a matcher for that * expression would yield the string "-foo-foo-foo-". * *

Invoking this method changes this matcher's state. If the matcher * is to be used in further matching operations then it should first be * reset.

* * @param replacement * The replacement string * * @return The string constructed by replacing each matching subsequence * by the replacement string, substituting captured subsequences * as needed */ public String replaceAll(String replacement) { reset(); StringBuffer buffer = new StringBuffer(input.length()); while (find()) { appendReplacement(buffer, replacement); } return appendTail(buffer).toString(); } /** * Replaces the first subsequence of the input sequence that matches the * pattern with the given replacement string. * *

This method first resets this matcher. It then scans the input * sequence looking for a match of the pattern. Characters that are not * part of the match are appended directly to the result string; the match * is replaced in the result by the replacement string. The replacement * string may contain references to captured subsequences as in the {@link * #appendReplacement appendReplacement} method. * *

Note that backslashes (\) and dollar signs ($) in * the replacement string may cause the results to be different than if it * were being treated as a literal replacement string. Dollar signs may be * treated as references to captured subsequences as described above, and * backslashes are used to escape literal characters in the replacement * string. * *

Given the regular expression dog, the input * "zzzdogzzzdogzzz", and the replacement string * "cat", an invocation of this method on a matcher for that * expression would yield the string "zzzcatzzzdogzzz".

* *

Invoking this method changes this matcher's state. If the matcher * is to be used in further matching operations then it should first be * reset.

* * @param replacement * The replacement string * @return The string constructed by replacing the first matching * subsequence by the replacement string, substituting captured * subsequences as needed */ public String replaceFirst(String replacement) { reset(); StringBuffer buffer = new StringBuffer(input.length()); if (find()) { appendReplacement(buffer, replacement); } return appendTail(buffer).toString(); } /** * Sets the limits of this matcher's region. The region is the part of the * input sequence that will be searched to find a match. Invoking this * method resets the matcher, and then sets the region to start at the * index specified by the start parameter and end at the * index specified by the end parameter. * *

Depending on the transparency and anchoring being used (see * {@link #useTransparentBounds useTransparentBounds} and * {@link #useAnchoringBounds useAnchoringBounds}), certain constructs such * as anchors may behave differently at or around the boundaries of the * region. * * @param start * The index to start searching at (inclusive) * @param end * The index to end searching at (exclusive) * @throws IndexOutOfBoundsException * If start or end is less than zero, if * start is greater than the length of the input sequence, if * end is greater than the length of the input sequence, or if * start is greater than end. * @return this matcher * @since 1.5 */ public Matcher region(int start, int end) { return reset(input, start, end); } /** * Reports the start index of this matcher's region. The * searches this matcher conducts are limited to finding matches * within {@link #regionStart regionStart} (inclusive) and * {@link #regionEnd regionEnd} (exclusive). * * @return The starting point of this matcher's region * @since 1.5 */ public int regionStart() { return regionStart; } /** * Reports the end index (exclusive) of this matcher's region. * The searches this matcher conducts are limited to finding matches * within {@link #regionStart regionStart} (inclusive) and * {@link #regionEnd regionEnd} (exclusive). * * @return the ending point of this matcher's region * @since 1.5 */ public int regionEnd() { return regionEnd; } /** * Queries the transparency of region bounds for this matcher. * *

This method returns true if this matcher uses * transparent bounds, false if it uses opaque * bounds. * *

See {@link #useTransparentBounds useTransparentBounds} for a * description of transparent and opaque bounds. * *

By default, a matcher uses opaque region boundaries. * * @return true iff this matcher is using transparent bounds, * false otherwise. * @see java.util.regex.Matcher#useTransparentBounds(boolean) * @since 1.5 */ public boolean hasTransparentBounds() { return transparentBounds; } /** * Sets the transparency of region bounds for this matcher. * *

Invoking this method with an argument of true will set this * matcher to use transparent bounds. If the boolean * argument is false, then opaque bounds will be used. * *

Using transparent bounds, the boundaries of this * matcher's region are transparent to lookahead, lookbehind, * and boundary matching constructs. Those constructs can see beyond the * boundaries of the region to see if a match is appropriate. * *

Using opaque bounds, the boundaries of this matcher's * region are opaque to lookahead, lookbehind, and boundary matching * constructs that may try to see beyond them. Those constructs cannot * look past the boundaries so they will fail to match anything outside * of the region. * *

By default, a matcher uses opaque bounds. * * @param value a boolean indicating whether to use opaque or transparent * regions * @return this matcher * @see java.util.regex.Matcher#hasTransparentBounds * @since 1.5 */ public Matcher useTransparentBounds(boolean value) { synchronized (this) { transparentBounds = value; useTransparentBoundsImpl(address, value); } return this; } /** * Queries the anchoring of region bounds for this matcher. * *

This method returns true if this matcher uses * anchoring bounds, false otherwise. * *

See {@link #useAnchoringBounds useAnchoringBounds} for a * description of anchoring bounds. * *

By default, a matcher uses anchoring region boundaries. * * @return true iff this matcher is using anchoring bounds, * false otherwise. * @see java.util.regex.Matcher#useAnchoringBounds(boolean) * @since 1.5 */ public boolean hasAnchoringBounds() { return anchoringBounds; } /** * Sets the anchoring of region bounds for this matcher. * *

Invoking this method with an argument of true will set this * matcher to use anchoring bounds. If the boolean * argument is false, then non-anchoring bounds will be * used. * *

Using anchoring bounds, the boundaries of this * matcher's region match anchors such as ^ and $. * *

Without anchoring bounds, the boundaries of this * matcher's region will not match anchors such as ^ and $. * *

By default, a matcher uses anchoring region boundaries. * * @param value a boolean indicating whether or not to use anchoring bounds. * @return this matcher * @see java.util.regex.Matcher#hasAnchoringBounds * @since 1.5 */ public Matcher useAnchoringBounds(boolean value) { synchronized (this) { anchoringBounds = value; useAnchoringBoundsImpl(address, value); } return this; } /** *

Returns the string representation of this matcher. The * string representation of a Matcher contains information * that may be useful for debugging. The exact format is unspecified. * * @return The string representation of this matcher * @since 1.5 */ public String toString() { StringBuilder sb = new StringBuilder(); sb.append("java.util.regex.Matcher"); sb.append("[pattern=" + pattern()); sb.append(" region="); sb.append(regionStart() + "," + regionEnd()); sb.append(" lastmatch="); if (matchFound && (group() != null)) { sb.append(group()); } sb.append("]"); return sb.toString(); } /** *

Returns true if the end of input was hit by the search engine in * the last match operation performed by this matcher. * *

When this method returns true, then it is possible that more input * would have changed the result of the last search. * * @return true iff the end of input was hit in the last match; false * otherwise * @since 1.5 */ public boolean hitEnd() { synchronized (this) { return hitEndImpl(address); } } /** *

Returns true if more input could change a positive match into a * negative one. * *

If this method returns true, and a match was found, then more * input could cause the match to be lost. If this method returns false * and a match was found, then more input might change the match but the * match won't be lost. If a match was not found, then requireEnd has no * meaning. * * @return true iff more input could change a positive match into a * negative one. * @since 1.5 */ public boolean requireEnd() { synchronized (this) { return requireEndImpl(address); } } /** * Resets this matcher. * *

Resetting a matcher discards all of its explicit state information * and sets its append position to zero. The matcher's region is set to the * default region, which is its entire character sequence. The anchoring * and transparency of this matcher's region boundaries are unaffected. * * @return This matcher */ public Matcher reset() { return reset(input, 0, input.length()); } /** * Resets this matcher with a new input sequence. * *

Resetting a matcher discards all of its explicit state information * and sets its append position to zero. The matcher's region is set to * the default region, which is its entire character sequence. The * anchoring and transparency of this matcher's region boundaries are * unaffected. * * @param input * The new input character sequence * * @return This matcher */ public Matcher reset(CharSequence input) { return reset(input, 0, input.length()); } /** * Resets the Matcher. A new input sequence and a new region can be * specified. Results of a previous find get lost. The next attempt to find * an occurrence of the Pattern in the string will start at the beginning of * the region. This is the internal version of reset() to which the several * public versions delegate. * * @param input * the input sequence. * @param start * the start of the region. * @param end * the end of the region. * * @return the matcher itself. */ private Matcher reset(CharSequence input, int start, int end) { if (input == null) { throw new IllegalArgumentException("input == null"); } if (start < 0 || end < 0 || start > input.length() || end > input.length() || start > end) { throw new IndexOutOfBoundsException(); } this.input = input.toString(); this.regionStart = start; this.regionEnd = end; resetForInput(); matchFound = false; appendPos = 0; return this; } private void resetForInput() { synchronized (this) { setInputImpl(address, input, regionStart, regionEnd); useAnchoringBoundsImpl(address, anchoringBounds); useTransparentBoundsImpl(address, transparentBounds); } } /** * Makes sure that a successful match has been made. Is invoked internally * from various places in the class. * * @throws IllegalStateException * if no successful match has been made. */ private void ensureMatch() { if (!matchFound) { throw new IllegalStateException("No successful match so far"); } } /** * Returns the start index of the previous match.

* * @return The index of the first character matched * * @throws IllegalStateException * If no match has yet been attempted, * or if the previous match operation failed */ public int start() { return start(0); } /** * Returns the start index of the subsequence captured by the given group * during the previous match operation. * *

Capturing groups are indexed from left * to right, starting at one. Group zero denotes the entire pattern, so * the expression m.start(0) is equivalent to * m.start().

* * @param group * The index of a capturing group in this matcher's pattern * * @return The index of the first character captured by the group, * or -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 IndexOutOfBoundsException * If there is no capturing group in the pattern * with the given index */ public int start(int group) throws IllegalStateException { ensureMatch(); return matchOffsets[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) { ensureMatch(); return matchOffsets[getMatchedGroupIndex(pattern.address, name) * 2]; } private static int getMatchedGroupIndex(long patternAddr, String name) { int result = getMatchedGroupIndex0(patternAddr, name); if (result < 0) { throw new IllegalArgumentException("No capturing group in the pattern " + "with the name " + name); } return result; } private static native int getMatchedGroupIndex0(long patternAddr, String name); private static native boolean findImpl(long addr, int startIndex, int[] offsets); private static native boolean findNextImpl(long addr, int[] offsets); private static native long getNativeFinalizer(); private static native int groupCountImpl(long addr); private static native boolean hitEndImpl(long addr); private static native boolean lookingAtImpl(long addr, int[] offsets); private static native boolean matchesImpl(long addr, int[] offsets); private static native int nativeSize(); private static native long openImpl(long patternAddr); private static native boolean requireEndImpl(long addr); private static native void setInputImpl(long addr, String s, int start, int end); private static native void useAnchoringBoundsImpl(long addr, boolean value); private static native void useTransparentBoundsImpl(long addr, boolean value); /** * A trivial match result implementation that's based on an array of integers * representing match offsets. The array is of the form * {@code { start1, end1, start2, end2 ....}) where each consecutive pair of elements represents * the start and end of a match respectively. */ static final class OffsetBasedMatchResult implements MatchResult { private final String input; private final int[] offsets; OffsetBasedMatchResult(String input, int[] offsets) { this.input = input; this.offsets = offsets.clone(); } @Override public int start() { return start(0); } @Override public int start(int group) { return offsets[2 * group]; } @Override public int end() { return end(0); } @Override public int end(int group) { return offsets[2 * group + 1]; } @Override public String group() { return group(0); } @Override public String group(int group) { final int start = start(group); final int end = end(group); if (start == -1 || end == -1) { return null; } return input.substring(start, end); } @Override public int groupCount() { return (offsets.length / 2) - 1; } } }