/* * Copyright (c) 1999, 2015, 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 java.util.ConcurrentModificationException; import java.util.Iterator; import java.util.NoSuchElementException; import java.util.Objects; import java.util.Spliterator; import java.util.Spliterators; import java.util.function.Consumer; import java.util.function.Function; import java.util.stream.Stream; import java.util.stream.StreamSupport; /** * An engine that performs match operations on a {@linkplain 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: * *
The {@link #matches matches} method attempts to match the entire * input sequence against the pattern.
The {@link #lookingAt lookingAt} method attempts to match the * input sequence, starting at the beginning, against the pattern.
The {@link #find find} method scans the input sequence looking for * the next subsequence that matches the pattern.
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 string builder. Alternatively, * 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. */ Pattern parentPattern; /** * The storage used by groups. They may contain invalid values if * a group was skipped during the matching. */ int[] groups; /** * The range within the sequence that is to be matched. Anchors * will match at these "hard" boundaries. Changing the region * changes these values. */ int from, to; /** * Lookbehind uses this value to ensure that the subexpression * match ends at the point where the lookbehind was encountered. */ int lookbehindTo; /** * The original string being matched. */ CharSequence text; /** * Matcher state used by the last node. NOANCHOR is used when a * match does not have to consume all of the input. ENDANCHOR is * the mode used for matching all the input. */ static final int ENDANCHOR = 1; static final int NOANCHOR = 0; int acceptMode = NOANCHOR; /** * The range of string that last matched the pattern. If the last * match failed then first is -1; last initially holds 0 then it * holds the index of the end of the last match (which is where the * next search starts). */ int first = -1, last = 0; /** * The end index of what matched in the last match operation. */ int oldLast = -1; /** * The index of the last position appended in a substitution. */ int lastAppendPosition = 0; /** * Storage used by nodes to tell what repetition they are on in * a pattern, and where groups begin. The nodes themselves are stateless, * so they rely on this field to hold state during a match. */ int[] locals; /** * Boolean indicating whether or not more input could change * the results of the last match. * * If hitEnd is true, and a match was found, then more input * might cause a different match to be found. * If hitEnd is true and a match was not found, then more * input could cause a match to be found. * If hitEnd is false and a match was found, then more input * will not change the match. * If hitEnd is false and a match was not found, then more * input will not cause a match to be found. */ boolean hitEnd; /** * Boolean indicating whether or not more input could change * a positive match into a negative one. * * If requireEnd is true, and a match was found, then more * input could cause the match to be lost. * If requireEnd is 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. */ boolean requireEnd; /** * If transparentBounds is true then the boundaries of this * matcher's region are transparent to lookahead, lookbehind, * and boundary matching constructs that try to see beyond them. */ boolean transparentBounds = false; /** * If anchoringBounds is true then the boundaries of this * matcher's region match anchors such as ^ and $. */ boolean anchoringBounds = true; /** * Number of times this matcher's state has been modified */ int modCount; /** * No default constructor. */ Matcher() { } /** * All matchers have the state used by Pattern during a match. */ Matcher(Pattern parent, CharSequence text) { this.parentPattern = parent; this.text = text; // Allocate state storage int parentGroupCount = Math.max(parent.capturingGroupCount, 10); groups = new int[parentGroupCount * 2]; locals = new int[parent.localCount]; // Put fields into initial states reset(); } /** * Returns the pattern that is interpreted by this matcher. * * @return The pattern for which this matcher was created */ public Pattern pattern() { return parentPattern; } /** * Returns the match state of this matcher as a {@link MatchResult}. * The result is unaffected by subsequent operations performed upon this * matcher. * * @return a {@code MatchResult} with the state of this matcher * @since 1.5 */ public MatchResult toMatchResult() { return toMatchResult(text.toString()); } private MatchResult toMatchResult(String text) { return new ImmutableMatchResult(this.first, this.last, groupCount(), this.groups.clone(), text); } private static class ImmutableMatchResult implements MatchResult { private final int first; private final int last; private final int[] groups; private final int groupCount; private final String text; ImmutableMatchResult(int first, int last, int groupCount, int groups[], String text) { this.first = first; this.last = last; this.groupCount = groupCount; this.groups = groups; this.text = text; } @Override public int start() { checkMatch(); return first; } @Override public int start(int group) { checkMatch(); if (group < 0 || group > groupCount) throw new IndexOutOfBoundsException("No group " + group); return groups[group * 2]; } @Override public int end() { checkMatch(); return last; } @Override public int end(int group) { checkMatch(); if (group < 0 || group > groupCount) throw new IndexOutOfBoundsException("No group " + group); return groups[group * 2 + 1]; } @Override public int groupCount() { return groupCount; } @Override public String group() { checkMatch(); return group(0); } @Override public String group(int group) { checkMatch(); if (group < 0 || group > groupCount) throw new IndexOutOfBoundsException("No group " + group); if ((groups[group*2] == -1) || (groups[group*2+1] == -1)) return null; return text.subSequence(groups[group * 2], groups[group * 2 + 1]).toString(); } private void checkMatch() { if (first < 0) throw new IllegalStateException("No match found"); } } /** * Changes the {@code Pattern} that this {@code 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 {@code null} * @since 1.5 */ public Matcher usePattern(Pattern newPattern) { if (newPattern == null) throw new IllegalArgumentException("Pattern cannot be null"); parentPattern = newPattern; // Reallocate state storage int parentGroupCount = Math.max(newPattern.capturingGroupCount, 10); groups = new int[parentGroupCount * 2]; locals = new int[newPattern.localCount]; for (int i = 0; i < groups.length; i++) groups[i] = -1; for (int i = 0; i < locals.length; i++) locals[i] = -1; modCount++; return this; } /** * 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() {
first = -1;
last = 0;
oldLast = -1;
for(int i=0; i Capturing groups are indexed from left
* to right, starting at one. Group zero denotes the entire pattern, so
* the expression m.{@code start(0)} is equivalent to
* m.{@code start()}. Capturing groups are indexed from left
* to right, starting at one. Group zero denotes the entire pattern, so
* the expression m.{@code end(0)} is equivalent to
* m.{@code end()}. For a matcher m with input sequence s,
* the expressions m.{@code group()} and
* s.{@code substring(}m.{@code start(),} m.{@code end())}
* are equivalent. Note that some patterns, for example {@code a*}, match the empty
* string. This method will return the empty string when the pattern
* successfully matches the empty string in the input. For a matcher m, input sequence s, and group index
* g, the expressions m.{@code group(}g{@code )} and
* s.{@code substring(}m.{@code start(}g{@code
* ),} m.{@code end(}g{@code ))}
* are equivalent. Capturing groups are indexed from left
* to right, starting at one. Group zero denotes the entire pattern, so
* the expression {@code m.group(0)} is equivalent to {@code m.group()}.
* If the match was successful but the group specified failed to match
* any part of the input sequence, then {@code null} is returned. Note
* that some groups, for example {@code (a*)}, match the empty string.
* This method will return the empty string when such a group successfully
* matches the empty string in the input. If the match was successful but the group specified failed to match
* any part of the input sequence, then {@code null} is returned. Note
* that some groups, for example {@code (a*)}, match the empty string.
* This method will return the empty string when such a group successfully
* matches the empty string in the input. 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. If the match succeeds then more information can be obtained via the
* {@code start}, {@code end}, and {@code group} methods. 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
* {@code start}, {@code end}, and {@code group} methods. If the match succeeds then more information can be obtained via the
* {@code start}, {@code end}, and {@code group} methods, and subsequent
* invocations of the {@link #find()} method will start at the first
* character not matched by this match. 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
* {@code start}, {@code end}, and {@code group} methods.
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()} {@code -} {@code 1}.
It appends the given replacement string to the string buffer. *
It sets the append position of this matcher to the index of * the last character matched, plus one, that is, to {@link #end()}. *
The replacement string may contain references to subsequences
* captured during the previous match: Each occurrence of
* ${
name}
or {@code $}g
* will be replaced by the result of evaluating the corresponding
* {@link #group(String) group(name)} or {@link #group(int) group(g)}
* respectively. For {@code $}g,
* the first number after the {@code $} 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 {@code "foo"}, for
* example, then passing the replacement string {@code "$2bar"} would
* cause {@code "foobar"} to be appended to the string buffer. A dollar
* sign ({@code $}) may be included as a literal in the replacement
* string by preceding it with a backslash ({@code \$}).
*
*
Note that backslashes ({@code \}) and dollar signs ({@code $}) 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 {@code one dog two dogs in the * yard} to the standard-output stream:
* ** * @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) { // If no match, return error if (first < 0) throw new IllegalStateException("No match available"); StringBuilder result = new StringBuilder(); appendExpandedReplacement(replacement, result); // Append the intervening text sb.append(text, lastAppendPosition, first); // Append the match substitution sb.append(result); lastAppendPosition = last; modCount++; return this; } /** * Implements a non-terminal append-and-replace step. * ** 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());
This method performs the following actions:
* *It reads characters from the input sequence, starting at the * append position, and appends them to the given string builder. It * stops after reading the last character preceding the previous match, * that is, the character at index {@link * #start()} {@code -} {@code 1}.
It appends the given replacement string to the string builder. *
It sets the append position of this matcher to the index of * the last character matched, plus one, that is, to {@link #end()}. *
The replacement string may contain references to subsequences * captured during the previous match: Each occurrence of * {@code $}g will be replaced by the result of * evaluating {@link #group(int) group}{@code (}g{@code )}. * The first number after the {@code $} 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 {@code "foo"}, for * example, then passing the replacement string {@code "$2bar"} would * cause {@code "foobar"} to be appended to the string builder. A dollar * sign ({@code $}) may be included as a literal in the replacement * string by preceding it with a backslash ({@code \$}). * *
Note that backslashes ({@code \}) and dollar signs ({@code $}) 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 {@code one dog two dogs in the * yard} to the standard-output stream:
* ** * @param sb * The target string builder * @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 * @since 9 */ public Matcher appendReplacement(StringBuilder sb, String replacement) { // If no match, return error if (first < 0) throw new IllegalStateException("No match available"); StringBuilder result = new StringBuilder(); appendExpandedReplacement(replacement, result); // Append the intervening text sb.append(text, lastAppendPosition, first); // Append the match substitution sb.append(result); lastAppendPosition = last; modCount++; return this; } /** * Processes replacement string to replace group references with * groups. */ private StringBuilder appendExpandedReplacement( String replacement, StringBuilder result) { int cursor = 0; while (cursor < replacement.length()) { char nextChar = replacement.charAt(cursor); if (nextChar == '\\') { cursor++; if (cursor == replacement.length()) throw new IllegalArgumentException( "character to be escaped is missing"); nextChar = replacement.charAt(cursor); result.append(nextChar); cursor++; } else if (nextChar == '$') { // Skip past $ cursor++; // Throw IAE if this "$" is the last character in replacement if (cursor == replacement.length()) throw new IllegalArgumentException( "Illegal group reference: group index is missing"); 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; } } 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 (ASCII.isDigit(gname.charAt(0))) throw new IllegalArgumentException( "capturing group name {" + gname + "} starts with digit character"); 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 = 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 if (start(refNum) != -1 && end(refNum) != -1) result.append(text, start(refNum), end(refNum)); } else { result.append(nextChar); cursor++; } } return result; } /** * Implements a terminal append-and-replace step. * ** Pattern p = Pattern.compile("cat"); * Matcher m = p.matcher("one cat two cats in the yard"); * StringBuilder sb = new StringBuilder(); * while (m.find()) { * m.appendReplacement(sb, "dog"); * } * m.appendTail(sb); * System.out.println(sb.toString());
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) { sb.append(text, lastAppendPosition, getTextLength()); return sb; } /** * 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 builder. 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 builder * * @return The target string builder * * @since 9 */ public StringBuilder appendTail(StringBuilder sb) { sb.append(text, lastAppendPosition, getTextLength()); 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 ({@code \}) and dollar signs ({@code $}) 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 {@code a*b}, the input * {@code "aabfooaabfooabfoob"}, and the replacement string * {@code "-"}, an invocation of this method on a matcher for that * expression would yield the string {@code "-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(); boolean result = find(); if (result) { StringBuilder sb = new StringBuilder(); do { appendReplacement(sb, replacement); result = find(); } while (result); appendTail(sb); return sb.toString(); } return text.toString(); } /** * Replaces every subsequence of the input sequence that matches the * pattern with the result of applying the given replacer function to the * match result of this matcher corresponding to that subsequence. * Exceptions thrown by the function are relayed to the caller. * *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 applying the replacer function that * returns a replacement string. Each replacement string may contain * references to captured subsequences as in the {@link #appendReplacement * appendReplacement} method. * *
Note that backslashes ({@code \}) and dollar signs ({@code $}) in * a 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 {@code dog}, the input * {@code "zzzdogzzzdogzzz"}, and the function * {@code mr -> mr.group().toUpperCase()}, an invocation of this method on * a matcher for that expression would yield the string * {@code "zzzDOGzzzDOGzzz"}. * *
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.
* *The replacer function should not modify this matcher's state during * replacement. This method will, on a best-effort basis, throw a * {@link java.util.ConcurrentModificationException} if such modification is * detected. * *
The state of each match result passed to the replacer function is
* guaranteed to be constant only for the duration of the replacer function
* call and only if the replacer function does not modify this matcher's
* state.
*
* @implNote
* This implementation applies the replacer function to this matcher, which
* is an instance of {@code MatchResult}.
*
* @param replacer
* The function to be applied to the match result of this matcher
* that returns a replacement string.
* @return The string constructed by replacing each matching subsequence
* with the result of applying the replacer function to that
* matched subsequence, substituting captured subsequences as
* needed.
* @throws NullPointerException if the replacer function is null
* @throws ConcurrentModificationException if it is detected, on a
* best-effort basis, that the replacer function modified this
* matcher's state
* @since 9
*/
public String replaceAll(Function Each match result is produced as if by {@link #toMatchResult()}.
*
* This method does not reset this matcher. Matching starts on
* initiation of the terminal stream operation either at the beginning of
* this matcher's region, or, if the matcher has not since been reset, at
* the first character not matched by a previous match.
*
* If the matcher is to be used for further matching operations after
* the terminal stream operation completes then it should be first reset.
*
* This matcher's state should not be modified during execution of the
* returned stream's pipeline. The returned stream's source
* {@code Spliterator} is fail-fast and will, on a best-effort
* basis, throw a {@link java.util.ConcurrentModificationException} if such
* modification is detected.
*
* @return a sequential stream of match results.
* @since 9
*/
public Stream 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 ({@code \}) and dollar signs ({@code $}) 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 {@code dog}, the input
* {@code "zzzdogzzzdogzzz"}, and the replacement string
* {@code "cat"}, an invocation of this method on a matcher for that
* expression would yield the string {@code "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. 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 applying the replacer function that
* returns a replacement string. The replacement string may contain
* references to captured subsequences as in the {@link #appendReplacement
* appendReplacement} method.
*
* Note that backslashes ({@code \}) and dollar signs ({@code $}) 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 {@code dog}, the input
* {@code "zzzdogzzzdogzzz"}, and the function
* {@code mr -> mr.group().toUpperCase()}, an invocation of this method on
* a matcher for that expression would yield the string
* {@code "zzzDOGzzzdogzzz"}.
*
* 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.
*
* The replacer function should not modify this matcher's state during
* replacement. This method will, on a best-effort basis, throw a
* {@link java.util.ConcurrentModificationException} if such modification is
* detected.
*
* The state of the match result passed to the replacer function is
* guaranteed to be constant only for the duration of the replacer function
* call and only if the replacer function does not modify this matcher's
* state.
*
* @implNote
* This implementation applies the replacer function to this matcher, which
* is an instance of {@code MatchResult}.
*
* @param replacer
* The function to be applied to the match result of this matcher
* that returns a replacement string.
* @return The string constructed by replacing the first matching
* subsequence with the result of applying the replacer function to
* the matched subsequence, substituting captured subsequences as
* needed.
* @throws NullPointerException if the replacer function is null
* @throws ConcurrentModificationException if it is detected, on a
* best-effort basis, that the replacer function modified this
* matcher's state
* @since 9
*/
public String replaceFirst(Function 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) {
if ((start < 0) || (start > getTextLength()))
throw new IndexOutOfBoundsException("start");
if ((end < 0) || (end > getTextLength()))
throw new IndexOutOfBoundsException("end");
if (start > end)
throw new IndexOutOfBoundsException("start > end");
reset();
from = start;
to = end;
return this;
}
/**
* 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 from;
}
/**
* 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 to;
}
/**
* Queries the transparency of region bounds for this matcher.
*
* This method returns {@code true} if this matcher uses
* transparent bounds, {@code 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 {@code true} iff this matcher is using transparent bounds,
* {@code 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 {@code true} will set this
* matcher to use transparent bounds. If the boolean
* argument is {@code 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 b 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 b) {
transparentBounds = b;
return this;
}
/**
* Queries the anchoring of region bounds for this matcher.
*
* This method returns {@code true} if this matcher uses
* anchoring bounds, {@code false} otherwise.
*
* See {@link #useAnchoringBounds useAnchoringBounds} for a
* description of anchoring bounds.
*
* By default, a matcher uses anchoring region boundaries.
*
* @return {@code true} iff this matcher is using anchoring bounds,
* {@code 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 {@code true} will set this
* matcher to use anchoring bounds. If the boolean
* argument is {@code 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 b 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 b) {
anchoringBounds = b;
return this;
}
/**
* Returns the string representation of this matcher. The
* string representation of a {@code 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")
.append("[pattern=").append(pattern())
.append(" region=")
.append(regionStart()).append(',').append(regionEnd())
.append(" lastmatch=");
if ((first >= 0) && (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() {
return hitEnd;
}
/**
* 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() {
return requireEnd;
}
/**
* Initiates a search to find a Pattern within the given bounds.
* The groups are filled with default values and the match of the root
* of the state machine is called. The state machine will hold the state
* of the match as it proceeds in this matcher.
*
* Matcher.from is not set here, because it is the "hard" boundary
* of the start of the search which anchors will set to. The from param
* is the "soft" boundary of the start of the search, meaning that the
* regex tries to match at that index but ^ won't match there. Subsequent
* calls to the search methods start at a new "soft" boundary which is
* the end of the previous match.
*/
boolean search(int from) {
this.hitEnd = false;
this.requireEnd = false;
from = from < 0 ? 0 : from;
this.first = from;
this.oldLast = oldLast < 0 ? from : oldLast;
for (int i = 0; i < groups.length; i++)
groups[i] = -1;
acceptMode = NOANCHOR;
boolean result = parentPattern.root.match(this, from, text);
if (!result)
this.first = -1;
this.oldLast = this.last;
this.modCount++;
return result;
}
/**
* Initiates a search for an anchored match to a Pattern within the given
* bounds. The groups are filled with default values and the match of the
* root of the state machine is called. The state machine will hold the
* state of the match as it proceeds in this matcher.
*/
boolean match(int from, int anchor) {
this.hitEnd = false;
this.requireEnd = false;
from = from < 0 ? 0 : from;
this.first = from;
this.oldLast = oldLast < 0 ? from : oldLast;
for (int i = 0; i < groups.length; i++)
groups[i] = -1;
acceptMode = anchor;
boolean result = parentPattern.matchRoot.match(this, from, text);
if (!result)
this.first = -1;
this.oldLast = this.last;
this.modCount++;
return result;
}
/**
* Returns the end index of the text.
*
* @return the index after the last character in the text
*/
int getTextLength() {
return text.length();
}
/**
* Generates a String from this Matcher's input in the specified range.
*
* @param beginIndex the beginning index, inclusive
* @param endIndex the ending index, exclusive
* @return A String generated from this Matcher's input
*/
CharSequence getSubSequence(int beginIndex, int endIndex) {
return text.subSequence(beginIndex, endIndex);
}
/**
* Returns this Matcher's input character at index i.
*
* @return A char from the specified index
*/
char charAt(int i) {
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);
}
}