summaryrefslogtreecommitdiffstats
path: root/regex
diff options
context:
space:
mode:
authorThe Android Open Source Project <initial-contribution@android.com>2009-03-03 19:28:47 -0800
committerThe Android Open Source Project <initial-contribution@android.com>2009-03-03 19:28:47 -0800
commitadc854b798c1cfe3bfd4c27d68d5cee38ca617da (patch)
tree6aed8b4923ca428942cbaa7e848d50237a3d31e0 /regex
parent1c0fed63c71ddb230f3b304aac12caffbedf2f21 (diff)
downloadlibcore-adc854b798c1cfe3bfd4c27d68d5cee38ca617da.zip
libcore-adc854b798c1cfe3bfd4c27d68d5cee38ca617da.tar.gz
libcore-adc854b798c1cfe3bfd4c27d68d5cee38ca617da.tar.bz2
auto import from //depot/cupcake/@135843
Diffstat (limited to 'regex')
-rw-r--r--regex/MODULE_LICENSE_APACHE20
-rw-r--r--regex/src/main/java/java/util/regex/MatchResult.java112
-rw-r--r--regex/src/main/java/java/util/regex/MatchResultImpl.java79
-rw-r--r--regex/src/main/java/java/util/regex/Matcher.java779
-rw-r--r--regex/src/main/java/java/util/regex/Pattern.java479
-rw-r--r--regex/src/main/java/java/util/regex/PatternSyntaxException.java146
-rw-r--r--regex/src/main/java/java/util/regex/package.html884
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/AllTests.java49
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/Matcher2Test.java327
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/MatcherTest.java1471
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/ModeTest.java150
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/Pattern2Test.java1611
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternErrorTest.java103
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternSyntaxExceptionTest.java122
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternTest.java2410
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/ReplaceTest.java125
-rw-r--r--regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/SplitTest.java201
-rw-r--r--regex/src/test/java/tests/regex/AllTests.java38
-rwxr-xr-xregex/src/test/resources/serialization/org/apache/harmony/regex/tests/java/util/regex/PatternSyntaxExceptionTest.golden.serbin0 -> 1711 bytes
-rwxr-xr-xregex/src/test/resources/serialization/org/apache/harmony/regex/tests/java/util/regex/PatternTest.golden.serbin0 -> 94 bytes
20 files changed, 9086 insertions, 0 deletions
diff --git a/regex/MODULE_LICENSE_APACHE2 b/regex/MODULE_LICENSE_APACHE2
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/regex/MODULE_LICENSE_APACHE2
diff --git a/regex/src/main/java/java/util/regex/MatchResult.java b/regex/src/main/java/java/util/regex/MatchResult.java
new file mode 100644
index 0000000..fa67ba6
--- /dev/null
+++ b/regex/src/main/java/java/util/regex/MatchResult.java
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2007 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package java.util.regex;
+
+/**
+ * Holds the results of a successful match of a {@link Pattern} against a
+ * given string. The result is divided into groups, with one group for each
+ * pair of parentheses in the regular expression and an additional group for
+ * the whole regular expression. The start, end, and contents of each group
+ * can be queried.
+ *
+ * @see Matcher
+ * @see Matcher#toMatchResult()
+ *
+ * @since Android 1.0
+ */
+public interface MatchResult {
+
+ /**
+ * Returns the index of the first character following the text that matched
+ * the whole regular expression.
+ *
+ * @return the character index.
+ *
+ * @since Android 1.0
+ */
+ int end();
+
+ /**
+ * Returns the index of the first character following the text that matched
+ * a given group.
+ *
+ * @param group
+ * the group, ranging from 0 to groupCount() - 1, with 0
+ * representing the whole pattern.
+ *
+ * @return the character index.
+ *
+ * @since Android 1.0
+ */
+ int end(int group);
+
+ /**
+ * Returns the text that matched the whole regular expression.
+ *
+ * @return the text.
+ *
+ * @since Android 1.0
+ */
+ String group();
+
+ /**
+ * Returns the text that matched a given group of the regular expression.
+ *
+ * @param group
+ * the group, ranging from 0 to groupCount() - 1, with 0
+ * representing the whole pattern.
+ *
+ * @return the text that matched the group.
+ *
+ * @since Android 1.0
+ */
+ String group(int group);
+
+ /**
+ * Returns the number of groups in the result, which is always equal to
+ * the number of groups in the original regular expression.
+ *
+ * @return the number of groups.
+ *
+ * @since Android 1.0
+ */
+ int groupCount();
+
+ /**
+ * Returns the index of the first character of the text that matched
+ * the whole regular expression.
+ *
+ * @return the character index.
+ *
+ * @since Android 1.0
+ */
+ int start();
+
+ /**
+ * Returns the index of the first character of the text that matched a given
+ * group.
+ *
+ * @param group
+ * the group, ranging from 0 to groupCount() - 1, with 0
+ * representing the whole pattern.
+ *
+ * @return the character index.
+ *
+ * @since Android 1.0
+ */
+ int start(int group);
+}
diff --git a/regex/src/main/java/java/util/regex/MatchResultImpl.java b/regex/src/main/java/java/util/regex/MatchResultImpl.java
new file mode 100644
index 0000000..795f2f6
--- /dev/null
+++ b/regex/src/main/java/java/util/regex/MatchResultImpl.java
@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) 2007 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package java.util.regex;
+
+/**
+ * Holds the results of a successful match of a regular expression against a
+ * given string. Only used internally, thus sparsely documented (though the
+ * defining public interface has full documentation).
+ *
+ * @see java.util.regex.MatchResult
+ */
+class MatchResultImpl implements MatchResult {
+
+ /**
+ * Holds the original input text.
+ */
+ private String text;
+
+ /**
+ * Holds the offsets of the groups in the input text. The first two
+ * elements specifiy start and end of the zero group, the next two specify
+ * group 1, and so on.
+ */
+ private int[] offsets;
+
+ MatchResultImpl(String text, int[] offsets) {
+ this.text = text;
+ this.offsets = offsets.clone();
+ }
+
+ public int end() {
+ return end(0);
+ }
+
+ public int end(int group) {
+ return offsets[2 * group + 1];
+ }
+
+ public String group() {
+ return text.substring(start(), end());
+ }
+
+ public String group(int group) {
+ int from = offsets[group * 2];
+ int to = offsets[(group * 2) + 1];
+ if (from == -1 || to == -1) {
+ return null;
+ } else {
+ return text.substring(from, to);
+ }
+ }
+
+ public int groupCount() {
+ return (offsets.length / 2) - 1;
+ }
+
+ public int start() {
+ return start(0);
+ }
+
+ public int start(int group) {
+ return offsets[2 * group];
+ }
+
+}
diff --git a/regex/src/main/java/java/util/regex/Matcher.java b/regex/src/main/java/java/util/regex/Matcher.java
new file mode 100644
index 0000000..e3e4874
--- /dev/null
+++ b/regex/src/main/java/java/util/regex/Matcher.java
@@ -0,0 +1,779 @@
+/*
+ * Copyright (C) 2007 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package java.util.regex;
+
+import com.ibm.icu4jni.regex.NativeRegEx;
+
+/**
+ * Provides a means of matching regular expressions against a given input,
+ * finding occurrences of regular expressions in a given input, or replacing
+ * parts of a given input. A {@code Matcher} instance has an associated {@link
+ * Pattern} instance and an input text. A typical use case is to
+ * iteratively find all occurrences of the {@code Pattern}, until the end of
+ * the input is reached, as the following example illustrates:
+ *
+ * <p/>
+ *
+ * <pre>
+ * Pattern p = Pattern.compile("[A-Za-z]+");
+ *
+ * Matcher m = p.matcher("Hello, Android!");
+ * while (m.find()) {
+ * System.out.println(m.group()); // prints "Hello" and "Android"
+ * }
+ * </pre>
+ *
+ * <p/>
+ *
+ * The {@code Matcher} has a state that results from the previous operations.
+ * For example, it knows whether the most recent attempt to find the
+ * {@code Pattern} was successful and at which position the next attempt would
+ * resume the search. Depending on the application's needs, it may become
+ * necessary to explicitly {@link #reset()} this state from time to time.
+ *
+ * @since Android 1.0
+ */
+public final class Matcher implements MatchResult {
+
+ /**
+ * Holds the pattern, that is, the compiled regular expression.
+ */
+ private Pattern pattern;
+
+ /**
+ * Holds the handle for the native version of the pattern.
+ */
+ private int nativePattern;
+
+ /**
+ * 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;
+
+ /**
+ * Reflects whether we just reset the matcher or whether we already
+ * started some find/replace operations.
+ */
+ private boolean searching;
+
+ /**
+ * Holds the position where the next find operation will take place.
+ */
+ private int findPos;
+
+ /**
+ * 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;
+
+ /**
+ * Creates a matcher for a given combination of pattern and input. Both
+ * elements can be changed later on.
+ *
+ * @param pattern
+ * the pattern to use.
+ * @param input
+ * the input to use.
+ */
+ Matcher(Pattern pattern, CharSequence input) {
+ usePattern(pattern);
+ reset(input);
+ }
+
+ /**
+ * 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();
+ }
+
+ if (start < 0 || end < 0 || start > input.length() ||
+ end > input.length() || start > end) {
+ throw new IllegalArgumentException();
+ }
+
+ // Maybe should have a reset() here, but it makes thing worse...
+ // NativeRegEx.reset(nativePattern, 0);
+
+ if (!input.equals(this.input)) {
+ this.input = input.toString();
+
+ NativeRegEx.setText(nativePattern, this.input);
+
+ regionStart = 0;
+ regionEnd = input.length();
+ }
+
+ if (start != regionStart || end != regionEnd) {
+ regionStart = start;
+ regionEnd = end;
+
+ NativeRegEx.setRegion(nativePattern, regionStart, regionEnd);
+ }
+
+ searching = false;
+ matchFound = false;
+ findPos = regionStart;
+ appendPos = 0;
+
+ return this;
+ }
+
+ /**
+ * Resets the {@code Matcher}. This results in the region being set to the
+ * whole input. Results of a previous find get lost. The next attempt to
+ * find an occurrence of the {@link Pattern} in the string will start at the
+ * beginning of the input.
+ *
+ * @return the {@code Matcher} itself.
+ *
+ * @since Android 1.0
+ */
+ public Matcher reset() {
+ return reset(input, 0, input.length());
+ }
+
+ /**
+ * Provides a new input and resets the {@code Matcher}. This results in the
+ * region being set to the whole input. Results of a previous find get lost.
+ * The next attempt to find an occurrence of the {@link Pattern} in the
+ * string will start at the beginning of the input.
+ *
+ * @param input
+ * the new input sequence.
+ *
+ * @return the {@code Matcher} itself.
+ *
+ * @since Android 1.0
+ */
+ public Matcher reset(CharSequence input) {
+ return reset(input, 0, input.length());
+ }
+
+ /**
+ * Sets a new pattern for the {@code Matcher}. Results of a previous find
+ * get lost. The next attempt to find an occurrence of the {@link Pattern}
+ * in the string will start at the beginning of the input.
+ *
+ * @param pattern
+ * the new {@code Pattern}.
+ *
+ * @return the {@code Matcher} itself.
+ *
+ * @since Android 1.0
+ */
+ public Matcher usePattern(Pattern pattern) {
+ if (pattern == null) {
+ throw new IllegalArgumentException();
+ }
+
+ this.pattern = pattern;
+
+ if (nativePattern != 0) {
+ NativeRegEx.close(nativePattern);
+ }
+ nativePattern = NativeRegEx.clone(pattern.mNativePattern);
+
+ if (input != null) {
+ NativeRegEx.setText(nativePattern, input);
+ NativeRegEx.setRegion(nativePattern, regionStart, regionEnd);
+ NativeRegEx.useAnchoringBounds(nativePattern, anchoringBounds);
+ NativeRegEx.useTransparentBounds(nativePattern, transparentBounds);
+ }
+
+ matchOffsets = new int[(this.pattern.mGroupCount + 1) * 2];
+ matchFound = false;
+ return this;
+ }
+
+ /**
+ * Returns the {@link Pattern} instance used inside this matcher.
+ *
+ * @return the {@code Pattern} instance.
+ *
+ * @since Android 1.0
+ */
+ public Pattern pattern() {
+ return pattern;
+ }
+
+ /**
+ * Returns the number of groups in the results, which is always equal to
+ * the number of groups in the original regular expression.
+ *
+ * @return the number of groups.
+ *
+ * @since Android 1.0
+ */
+ public int groupCount() {
+ return pattern.mGroupCount;
+ }
+
+ /**
+ * Resets this matcher and sets a region. Only characters inside the region
+ * are considered for a match.
+ *
+ * @param start
+ * the first character of the region.
+ * @param end
+ * the first character after the end of the region.
+ * @return the {@code Matcher} itself.
+ * @since Android 1.0
+ */
+ public Matcher region(int start, int end) {
+ return reset(input, start, end);
+ }
+
+ /**
+ * Returns this matcher's region start, that is, the first character that is
+ * considered for a match.
+ *
+ * @return the start of the region.
+ * @since Android 1.0
+ */
+ public int regionStart() {
+ return regionStart;
+ }
+
+ /**
+ * Returns this matcher's region end, that is, the first character that is
+ * not considered for a match.
+ *
+ * @return the end of the region.
+ * @since Android 1.0
+ */
+ public int regionEnd() {
+ return regionEnd;
+ }
+
+ /**
+ * Determines whether this matcher has anchoring bounds enabled or not. When
+ * anchoring bounds are enabled, the start and end of the input match the
+ * '^' and '$' meta-characters, otherwise not. Anchoring bounds are enabled
+ * by default.
+ *
+ * @param value
+ * the new value for anchoring bounds.
+ * @return the {@code Matcher} itself.
+ * @since Android 1.0
+ */
+ public Matcher useAnchoringBounds(boolean value) {
+ anchoringBounds = value;
+ NativeRegEx.useAnchoringBounds(nativePattern, value);
+ return this;
+ }
+
+ /**
+ * Indicates whether this matcher has anchoring bounds enabled. When
+ * anchoring bounds are enabled, the start and end of the input match the
+ * '^' and '$' meta-characters, otherwise not. Anchoring bounds are enabled
+ * by default.
+ *
+ * @return true if (and only if) the {@code Matcher} uses anchoring bounds.
+ * @since Android 1.0
+ */
+ public boolean hasAnchoringBounds() {
+ return anchoringBounds;
+ }
+
+ /**
+ * Determines whether this matcher has transparent bounds enabled or not.
+ * When transparent bounds are enabled, the parts of the input outside the
+ * region are subject to lookahead and lookbehind, otherwise they are not.
+ * Transparent bounds are disabled by default.
+ *
+ * @param value
+ * the new value for transparent bounds.
+ * @return the {@code Matcher} itself.
+ * @since Android 1.0
+ */
+ public Matcher useTransparentBounds(boolean value) {
+ transparentBounds = value;
+ NativeRegEx.useTransparentBounds(nativePattern, value);
+ return this;
+ }
+
+ /**
+ * Indicates whether this matcher has transparent bounds enabled. When
+ * transparent bounds are enabled, the parts of the input outside the region
+ * are subject to lookahead and lookbehind, otherwise they are not.
+ * Transparent bounds are disabled by default.
+ *
+ * @return true if (and only if) the {@code Matcher} uses anchoring bounds.
+ * @since Android 1.0
+ */
+ public boolean hasTransparentBounds() {
+ return 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.
+ *
+ * @since Android 1.0
+ */
+ private void ensureMatch() throws IllegalStateException {
+ if (!matchFound) {
+ throw new IllegalStateException("No successful match so far");
+ }
+ }
+
+ /**
+ * Returns the next occurrence of the {@link Pattern} in the input. If a
+ * previous match was successful, the method continues the search from the
+ * first character following that match in the input. Otherwise it searches
+ * either from the region start (if one has been set), or from position 0.
+ *
+ * @return true if (and only if) a match has been found.
+ * @since Android 1.0
+ */
+ public boolean find() {
+ if (!searching) {
+ searching = true;
+ matchFound = NativeRegEx.find(nativePattern, -1);
+ } else {
+ matchFound = NativeRegEx.findNext(nativePattern);
+ }
+
+ if (matchFound) {
+ NativeRegEx.startEnd(nativePattern, matchOffsets);
+ findPos = matchOffsets[1];
+ }
+
+ return matchFound;
+ }
+
+ /**
+ * Returns the next occurrence of the {@link Pattern} in the input. The
+ * method starts the search from the given character in the input.
+ *
+ * @param start
+ * The index in the input at which the find operation is to
+ * begin. If this is less than the start of the region, it is
+ * automatically adjusted to that value. If it is beyond the end
+ * of the region, the method will fail.
+ * @return true if (and only if) a match has been found.
+ * @since Android 1.0
+ */
+ public boolean find(int start) {
+ findPos = start;
+
+ if (findPos < regionStart) {
+ findPos = regionStart;
+ } else if (findPos >= regionEnd) {
+ matchFound = false;
+ return false;
+ }
+
+ matchFound = NativeRegEx.find(nativePattern, findPos);
+ if (matchFound) {
+ NativeRegEx.startEnd(nativePattern, matchOffsets);
+ findPos = matchOffsets[1];
+ }
+
+ return matchFound;
+ }
+
+ /**
+ * Tries to match the {@link Pattern} against the entire region (or the
+ * entire input, if no region has been set).
+ *
+ * @return true if (and only if) the {@code Pattern} matches the entire
+ * region.
+ *
+ * @since Android 1.0
+ */
+ public boolean matches() {
+ matchFound = NativeRegEx.matches(nativePattern, -1);
+ if (matchFound) {
+ NativeRegEx.startEnd(nativePattern, matchOffsets);
+ findPos = matchOffsets[1];
+ }
+
+ return matchFound;
+ }
+
+ /**
+ * Tries to match the {@link Pattern}, starting from the beginning of the
+ * region (or the beginning of the input, if no region has been set).
+ * Doesn't require the {@code Pattern} to match against the whole region.
+ *
+ * @return true if (and only if) the {@code Pattern} matches.
+ *
+ * @since Android 1.0
+ */
+ public boolean lookingAt() {
+ matchFound = NativeRegEx.lookingAt(nativePattern, -1);
+ if (matchFound) {
+ NativeRegEx.startEnd(nativePattern, matchOffsets);
+ findPos = matchOffsets[1];
+ }
+
+ return matchFound;
+ }
+
+ /**
+ * Returns the index of the first character of the text that matched the
+ * whole regular expression.
+ *
+ * @return the character index.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ public int start() throws IllegalStateException {
+ return start(0);
+ }
+
+ /**
+ * Returns the index of the first character of the text that matched a given
+ * group.
+ *
+ * @param group
+ * the group, ranging from 0 to groupCount() - 1, with 0
+ * representing the whole pattern.
+ * @return the character index.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ public int start(int group) throws IllegalStateException {
+ ensureMatch();
+ return matchOffsets[group * 2];
+ }
+
+ /**
+ * Returns the index of the first character following the text that matched
+ * the whole regular expression.
+ *
+ * @return the character index.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ public int end() {
+ return end(0);
+ }
+
+ /**
+ * Returns the index of the first character following the text that matched
+ * a given group.
+ *
+ * @param group
+ * the group, ranging from 0 to groupCount() - 1, with 0
+ * representing the whole pattern.
+ * @return the character index.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ public int end(int group) {
+ ensureMatch();
+ return matchOffsets[(group * 2) + 1];
+ }
+
+ /**
+ * Returns the text that matched the whole regular expression.
+ *
+ * @return the text.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ public String group() {
+ return group(0);
+ }
+
+ /**
+ * Returns the text that matched a given group of the regular expression.
+ *
+ * @param group
+ * the group, ranging from 0 to groupCount() - 1, with 0
+ * representing the whole pattern.
+ * @return the text that matched the group.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ 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);
+ }
+ }
+
+ /**
+ * Indicates whether the last match hit the end of the input.
+ *
+ * @return true if (and only if) the last match hit the end of the input.
+ * @since Android 1.0
+ */
+ public boolean hitEnd() {
+ return NativeRegEx.hitEnd(nativePattern);
+ }
+
+ /**
+ * Indicates whether more input might change a successful match into an
+ * unsuccessful one.
+ *
+ * @return true if (and only if) more input might change a successful match
+ * into an unsuccessful one.
+ * @since Android 1.0
+ */
+ public boolean requireEnd() {
+ return NativeRegEx.requireEnd(nativePattern);
+ }
+
+ /**
+ * Converts the current match into a separate {@link MatchResult} instance
+ * that is independent from this matcher. The new object is unaffected when
+ * the state of this matcher changes.
+ *
+ * @return the new {@code MatchResult}.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ public MatchResult toMatchResult() {
+ ensureMatch();
+ return new MatchResultImpl(input, matchOffsets);
+ }
+
+ /**
+ * Appends a literal part of the input plus a replacement for the current
+ * match to a given {@link StringBuffer}. The literal part is exactly the
+ * part of the input between the previous match and the current match. The
+ * method can be used in conjunction with {@link #find()} and
+ * {@link #appendTail(StringBuffer)} to walk through the input and replace
+ * all occurrences of the {@code Pattern} with something else.
+ *
+ * @param buffer
+ * the {@code StringBuffer} to append to.
+ * @param replacement
+ * the replacement text.
+ * @return the {@code Matcher} itself.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ public Matcher appendReplacement(StringBuffer buffer, String replacement)
+ throws IllegalStateException {
+
+ buffer.append(input.substring(appendPos, start()));
+ appendEvaluated(buffer, replacement);
+ appendPos = end();
+
+ return this;
+ }
+
+ /**
+ * Appends the (unmatched) remainder of the input to the given
+ * {@link StringBuffer}. The method can be used in conjunction with
+ * {@link #find()} and {@link #appendReplacement(StringBuffer, String)} to
+ * walk through the input and replace all matches of the {@code Pattern}
+ * with something else.
+ *
+ * @param buffer
+ * the {@code StringBuffer} to append to.
+ * @return the {@code StringBuffer}.
+ * @throws IllegalStateException
+ * if no successful match has been made.
+ * @since Android 1.0
+ */
+ public StringBuffer appendTail(StringBuffer buffer) {
+ if (appendPos < regionEnd) {
+ buffer.append(input.substring(appendPos, regionEnd));
+ }
+
+ return buffer;
+ }
+
+ /**
+ * 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;
+
+ for (int i = 0; i < s.length(); i++) {
+ char c = s.charAt(i);
+ if (c == '\\' && !escape) {
+ escape = true;
+ } else if (c == '$' && !escape) {
+ dollar = true;
+ } else if (c >= '0' && c <= '9' && dollar) {
+ buffer.append(group(c - '0'));
+ dollar = false;
+ } else {
+ buffer.append(c);
+ dollar = false;
+ escape = false;
+ }
+ }
+
+ // This seemingly stupid piece of code reproduces a JDK bug.
+ if (escape) {
+ throw new ArrayIndexOutOfBoundsException(s.length());
+ }
+ }
+
+ /**
+ * Replaces all occurrences of this matcher's pattern in the input with a
+ * given string.
+ *
+ * @param replacement
+ * the replacement text.
+ * @return the modified input string.
+ * @since Android 1.0
+ */
+ public String replaceAll(String replacement) {
+ StringBuffer buffer = new StringBuffer(input.length());
+
+ findPos = 0;
+ appendPos = 0;
+ matchFound = false;
+ searching = false;
+
+ while (find()) {
+ appendReplacement(buffer, replacement);
+ }
+
+ return appendTail(buffer).toString();
+ }
+
+ /**
+ * Replaces the first occurrence of this matcher's pattern in the input with
+ * a given string.
+ *
+ * @param replacement
+ * the replacement text.
+ * @return the modified input string.
+ * @since Android 1.0
+ */
+ public String replaceFirst(String replacement) {
+ StringBuffer buffer = new StringBuffer(input.length());
+
+ findPos = 0;
+ appendPos = 0;
+ matchFound = false;
+ searching = false;
+
+ if (find()) {
+ appendReplacement(buffer, replacement);
+ }
+
+ return appendTail(buffer).toString();
+ }
+
+ /**
+ * Returns a replacement string for the given one that has all backslashes
+ * and dollar signs escaped.
+ *
+ * @param s
+ * the input string.
+ * @return the input string, with all backslashes and dollar signs having
+ * been escaped.
+ * @since Android 1.0
+ */
+ public static String quoteReplacement(String s) {
+ StringBuffer buffer = new StringBuffer(s.length());
+
+ for (int i = 0; i < s.length(); i++) {
+ char c = s.charAt(i);
+ if (c == '\\' || c == '$') {
+ buffer.append('\\');
+ }
+ buffer.append(c);
+ }
+
+ return buffer.toString();
+ }
+
+ @Override
+ protected void finalize() throws Throwable {
+ try {
+ if (nativePattern != 0) {
+ NativeRegEx.close(nativePattern);
+ }
+ }
+ finally {
+ super.finalize();
+ }
+ }
+
+}
diff --git a/regex/src/main/java/java/util/regex/Pattern.java b/regex/src/main/java/java/util/regex/Pattern.java
new file mode 100644
index 0000000..c058db8
--- /dev/null
+++ b/regex/src/main/java/java/util/regex/Pattern.java
@@ -0,0 +1,479 @@
+/*
+ * Copyright (C) 2007 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package java.util.regex;
+
+import java.io.Serializable;
+import java.util.ArrayList;
+import com.ibm.icu4jni.regex.NativeRegEx;
+
+/**
+ * Represents a pattern used for matching, searching, or replacing strings.
+ * {@code Pattern}s are specified in terms of regular expressions and compiled
+ * using an instance of this class. They are then used in conjunction with a
+ * {@link Matcher} to perform the actual search.
+ * <p/>
+ * A typical use case looks like this:
+ * <p/>
+ * <pre>
+ * Pattern p = Pattern.compile("Hello, A[a-z]*!");
+ *
+ * Matcher m = p.matcher("Hello, Android!");
+ * boolean b1 = m.matches(); // true
+ *
+ * m.setInput("Hello, Robot!");
+ * boolean b2 = m.matches(); // false
+ * </pre>
+ * <p/>
+ * The above code could also be written in a more compact fashion, though this
+ * variant is less efficient, since {@code Pattern} and {@code Matcher} objects
+ * are created on the fly instead of being reused.
+ * fashion:
+ * <pre>
+ * boolean b1 = Pattern.matches("Hello, A[a-z]*!", "Hello, Android!"); // true
+ * boolean b2 = Pattern.matches("Hello, A[a-z]*!", "Hello, Robot!"); // false
+ * </pre>
+ * <p/>
+ * Please consult the <a href="package.html">package documentation</a> for an
+ * overview of the regular expression syntax used in this class as well as
+ * Android-specific implementation details.
+ *
+ * @see Matcher
+ * @since Android 1.0
+ */
+public final class Pattern implements Serializable {
+
+ private static final long serialVersionUID = 5073258162644648461L;
+
+ /**
+ * This constant specifies that a pattern matches Unix line endings ('\n')
+ * only against the '.', '^', and '$' meta characters.
+ *
+ * @since Android 1.0
+ */
+ public static final int UNIX_LINES = 0x01;
+
+ /**
+ * This constant specifies that a {@code Pattern} is matched
+ * case-insensitively. That is, the patterns "a+" and "A+" would both match
+ * the string "aAaAaA".
+ * <p>
+ * Note: For Android, the {@code CASE_INSENSITIVE} constant
+ * (currently) always includes the meaning of the {@link #UNICODE_CASE}
+ * constant. So if case insensitivity is enabled, this automatically extends
+ * to all Unicode characters. The {@code UNICODE_CASE} constant itself has
+ * no special consequences.
+ *
+ * @since Android 1.0
+ */
+ public static final int CASE_INSENSITIVE = 0x02;
+
+ /**
+ * This constant specifies that a {@code Pattern} may contain whitespace or
+ * comments. Otherwise comments and whitespace are taken as literal
+ * characters.
+ *
+ * @since Android 1.0
+ */
+ public static final int COMMENTS = 0x04;
+
+ /**
+ * This constant specifies that the meta characters '^' and '$' match only
+ * the beginning and end end of an input line, respectively. Normally, they
+ * match the beginning and the end of the complete input.
+ *
+ * @since Android 1.0
+ */
+ public static final int MULTILINE = 0x08;
+
+ /**
+ * This constant specifies that the whole {@code Pattern} is to be taken
+ * literally, that is, all meta characters lose their meanings.
+ *
+ * @since Android 1.0
+ */
+ public static final int LITERAL = 0x10;
+
+ /**
+ * This constant specifies that the '.' meta character matches arbitrary
+ * characters, including line endings, which is normally not the case.
+ *
+ * @since Android 1.0
+ */
+ public static final int DOTALL = 0x20;
+
+ /**
+ * This constant specifies that a {@code Pattern} is matched
+ * case-insensitively with regard to all Unicode characters. It is used in
+ * conjunction with the {@link #CASE_INSENSITIVE} constant to extend its
+ * meaning to all Unicode characters.
+ * <p>
+ * Note: For Android, the {@code CASE_INSENSITIVE} constant
+ * (currently) always includes the meaning of the {@code UNICODE_CASE}
+ * constant. So if case insensitivity is enabled, this automatically extends
+ * to all Unicode characters. The {@code UNICODE_CASE} constant then has no
+ * special consequences.
+ *
+ * @since Android 1.0
+ */
+ public static final int UNICODE_CASE = 0x40;
+
+ /**
+ * This constant specifies that a character in a {@code Pattern} and a
+ * character in the input string only match if they are canonically
+ * equivalent. It is (currently) not supported in Android.
+ *
+ * @since Android 1.0
+ */
+ public static final int CANON_EQ = 0x80;
+
+ /**
+ * Holds the regular expression.
+ */
+ private String pattern;
+
+ /**
+ * Holds the flags used when compiling this pattern.
+ */
+ private int flags;
+
+ /**
+ * Holds a handle (a pointer, actually) for the native ICU pattern.
+ */
+ transient int mNativePattern;
+
+ /**
+ * Holds the number of groups in the pattern.
+ */
+ transient int mGroupCount;
+
+ /**
+ * Compiles a regular expression, creating a new Pattern instance in the
+ * process. This is actually a convenience method that calls {@link
+ * #compile(String, int)} with a {@code flags} value of zero.
+ *
+ * @param pattern
+ * the regular expression.
+ *
+ * @return the new {@code Pattern} instance.
+ *
+ * @throws PatternSyntaxException
+ * if the regular expression is syntactically incorrect.
+ *
+ * @since Android 1.0
+ */
+ public static Pattern compile(String pattern) throws PatternSyntaxException {
+ return new Pattern(pattern, 0);
+ }
+
+ /**
+ * Compiles a regular expression, creating a new {@code Pattern} instance in
+ * the process. Allows to set some flags that modify the behavior of the
+ * {@code Pattern}.
+ *
+ * @param pattern
+ * the regular expression.
+ * @param flags
+ * the flags to set. Basically, any combination of the constants
+ * defined in this class is valid.
+ * <p>
+ * Note: Currently, the {@link #CASE_INSENSITIVE} and
+ * {@link #UNICODE_CASE} constants have slightly special behavior
+ * in Android, and the {@link #CANON_EQ} constant is not
+ * supported at all.
+ *
+ * @return the new {@code Pattern} instance.
+ *
+ * @throws PatternSyntaxException
+ * if the regular expression is syntactically incorrect.
+ *
+ * @see #CANON_EQ
+ * @see #CASE_INSENSITIVE
+ * @see #COMMENTS
+ * @see #DOTALL
+ * @see #LITERAL
+ * @see #MULTILINE
+ * @see #UNICODE_CASE
+ * @see #UNIX_LINES
+ *
+ * @since Android 1.0
+ */
+ public static Pattern compile(String pattern, int flags) throws PatternSyntaxException {
+ return new Pattern(pattern, flags);
+ }
+
+ /**
+ * Creates a new {@code Pattern} instance from a given regular expression
+ * and flags.
+ *
+ * @param pattern
+ * the regular expression.
+ * @param flags
+ * the flags to set. Any combination of the constants defined in
+ * this class is valid.
+ *
+ * @throws PatternSyntaxException
+ * if the regular expression is syntactically incorrect.
+ */
+ private Pattern(String pattern, int flags) throws PatternSyntaxException {
+ if ((flags & CANON_EQ) != 0) {
+ throw new UnsupportedOperationException("CANON_EQ flag not supported");
+ }
+
+ this.pattern = pattern;
+ this.flags = flags;
+
+ compileImpl(pattern, flags);
+ }
+
+ /**
+ * Compiles the given regular expression using the given flags. Used
+ * internally only.
+ *
+ * @param pattern
+ * the regular expression.
+ * @param flags
+ * the flags.
+ */
+ private void compileImpl(String pattern, int flags) throws PatternSyntaxException {
+ if (pattern == null) {
+ throw new NullPointerException();
+ }
+
+ if ((flags & LITERAL) != 0) {
+ pattern = quote(pattern);
+ }
+
+ // These are the flags natively supported by ICU.
+ // They even have the same value in native code.
+ flags = flags & (CASE_INSENSITIVE | COMMENTS | MULTILINE | DOTALL | UNIX_LINES);
+
+ mNativePattern = NativeRegEx.open(pattern, flags);
+ mGroupCount = NativeRegEx.groupCount(mNativePattern);
+ }
+
+ /**
+ * Returns the regular expression that was compiled into this
+ * {@code Pattern}.
+ *
+ * @return the regular expression.
+ *
+ * @since Android 1.0
+ */
+ public String pattern() {
+ return pattern;
+ }
+
+ /**
+ * Returns the flags that have been set for this {@code Pattern}.
+ *
+ * @return the flags that have been set. A combination of the constants
+ * defined in this class.
+ *
+ * @see #CANON_EQ
+ * @see #CASE_INSENSITIVE
+ * @see #COMMENTS
+ * @see #DOTALL
+ * @see #LITERAL
+ * @see #MULTILINE
+ * @see #UNICODE_CASE
+ * @see #UNIX_LINES
+ *
+ * @since Android 1.0
+ */
+ public int flags() {
+ return flags;
+ }
+
+ /**
+ * Returns a {@link Matcher} for the {@code Pattern} and a given input. The
+ * {@code Matcher} can be used to match the {@code Pattern} against the
+ * whole input, find occurrences of the {@code Pattern} in the input, or
+ * replace parts of the input.
+ *
+ * @param input
+ * the input to process.
+ *
+ * @return the resulting {@code Matcher}.
+ *
+ * @since Android 1.0
+ */
+ public Matcher matcher(CharSequence input) {
+ return new Matcher(this, input);
+ }
+
+ /**
+ * Tries to match a given regular expression against a given input. This is
+ * actually nothing but a convenience method that compiles the regular
+ * expression into a {@code Pattern}, builds a {@link Matcher} for it, and
+ * then does the match. If the same regular expression is used for multiple
+ * operations, it is recommended to compile it into a {@code Pattern}
+ * explicitly and request a reusable {@code Matcher}.
+ *
+ * @param regex
+ * the regular expression.
+ * @param input
+ * the input to process.
+ *
+ * @return true if and only if the {@code Pattern} matches the input.
+ *
+ * @see Pattern#compile(java.lang.String, int)
+ * @see Matcher#matches()
+ *
+ * @since Android 1.0
+ */
+ static public boolean matches(String regex, CharSequence input) {
+ return new Matcher(new Pattern(regex, 0), input).matches();
+ }
+
+ /**
+ * Splits a given input around occurrences of a regular expression. This is
+ * a convenience method that is equivalent to calling the method
+ * {@link #split(java.lang.CharSequence, int)} with a limit of 0.
+ *
+ * @param input
+ * the input sequence.
+ *
+ * @return the resulting array.
+ *
+ * @since Android 1.0
+ */
+ public String[] split(CharSequence input) {
+ return split(input, 0);
+ }
+
+ /**
+ * Splits the given input sequence around occurrences of the {@code Pattern}.
+ * The function first determines all occurrences of the {@code Pattern}
+ * inside the input sequence. It then builds an array of the
+ * &quot;remaining&quot; strings before, in-between, and after these
+ * occurrences. An additional parameter determines the maximal number of
+ * entries in the resulting array and the handling of trailing empty
+ * strings.
+ *
+ * @param inputSeq
+ * the input sequence.
+ * @param limit
+ * Determines the maximal number of entries in the resulting
+ * array.
+ * <ul>
+ * <li>For n &gt; 0, it is guaranteed that the resulting array
+ * contains at most n entries.
+ * <li>For n &lt; 0, the length of the resulting array is
+ * exactly the number of occurrences of the {@code Pattern} +1.
+ * All entries are included.
+ * <li>For n == 0, the length of the resulting array is at most
+ * the number of occurrences of the {@code Pattern} +1. Empty
+ * strings at the end of the array are not included.
+ * </ul>
+ *
+ * @return the resulting array.
+ *
+ * @since Android 1.0
+ */
+ public String[] split(CharSequence inputSeq, int limit) {
+ int maxLength = limit <= 0 ? Integer.MAX_VALUE : limit;
+
+ String input = inputSeq.toString();
+ ArrayList<String> list = new ArrayList<String>();
+
+ Matcher matcher = new Matcher(this, inputSeq);
+ int savedPos = 0;
+
+ // Add text preceding each occurrence, if enough space. Only do this for
+ // non-empty input sequences, because otherwise we'd add the "trailing
+ // empty string" twice.
+ if (inputSeq.length() != 0) {
+ while(matcher.find() && list.size() + 1 < maxLength) {
+ list.add(input.substring(savedPos, matcher.start()));
+ savedPos = matcher.end();
+ }
+ }
+
+ // Add trailing text if enough space.
+ if (list.size() < maxLength) {
+ if (savedPos < input.length()) {
+ list.add(input.substring(savedPos));
+ } else {
+ list.add("");
+ }
+ }
+
+ // Remove trailing spaces, if limit == 0 is requested.
+ if (limit == 0) {
+ int i = list.size() - 1;
+ // Don't remove 1st element, since array must not be empty.
+ while(i > 0 && "".equals(list.get(i))) {
+ list.remove(i);
+ i--;
+ }
+ }
+
+ return list.toArray(new String[list.size()]);
+ }
+
+ /**
+ * Quotes a given string using "\Q" and "\E", so that all other
+ * meta-characters lose their special meaning. If the string is used for a
+ * {@code Pattern} afterwards, it can only be matched literally.
+ *
+ * @param s
+ * the string to quote.
+ *
+ * @return the quoted string.
+ *
+ * @since Android 1.0
+ */
+ public static String quote(String s) {
+ StringBuffer sb = new StringBuffer().append("\\Q");
+ int apos = 0;
+ int k;
+ while ((k = s.indexOf("\\E", apos)) >= 0) {
+ sb.append(s.substring(apos, k + 2)).append("\\\\E\\Q");
+ apos = k + 2;
+ }
+
+ return sb.append(s.substring(apos)).append("\\E").toString();
+ }
+
+ @Override
+ public String toString() {
+ return pattern;
+ }
+
+ @Override
+ protected void finalize() throws Throwable {
+ try {
+ if (mNativePattern != 0) {
+ NativeRegEx.close(mNativePattern);
+ }
+ }
+ finally {
+ super.finalize();
+ }
+ }
+
+ /**
+ * Provides serialization support
+ */
+ private void readObject(java.io.ObjectInputStream s)
+ throws java.io.IOException, ClassNotFoundException {
+ s.defaultReadObject();
+
+ compileImpl(pattern, flags);
+ }
+
+}
diff --git a/regex/src/main/java/java/util/regex/PatternSyntaxException.java b/regex/src/main/java/java/util/regex/PatternSyntaxException.java
new file mode 100644
index 0000000..e4d5abd
--- /dev/null
+++ b/regex/src/main/java/java/util/regex/PatternSyntaxException.java
@@ -0,0 +1,146 @@
+/*
+ * Copyright (C) 2007 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package java.util.regex;
+
+import java.util.Arrays;
+
+/**
+ * Encapsulates a syntax error that occurred during the compilation of a
+ * {@link Pattern}. Might include a detailed description, the original regular
+ * expression, and the index at which the error occurred.
+ *
+ * @see Pattern#compile(String)
+ * @see Pattern#compile(java.lang.String,int)
+ *
+ * @since Android 1.0
+ */
+public class PatternSyntaxException extends IllegalArgumentException {
+
+ private static final long serialVersionUID = -3864639126226059218L;
+
+ /**
+ * Holds the syntactically incorrect regular expression, or null if the
+ * regular expression is not known.
+ */
+ private String pattern;
+
+ /**
+ * Holds the description of the syntax error, or null if the description is
+ * not known.
+ */
+ private String description;
+
+ /**
+ * Holds the index around which the error occured, or -1, in case it is
+ * unknown.
+ */
+ private int index = -1;
+
+ /**
+ * Creates a new PatternSyntaxException for a given message, pattern, and
+ * error index.
+ *
+ * @param description
+ * the description of the syntax error, or {@code null} if the
+ * description is not known.
+ * @param pattern
+ * the syntactically incorrect regular expression, or
+ * {@code null} if the regular expression is not known.
+ * @param index
+ * the character index around which the error occurred, or -1 if
+ * the index is not known.
+ * @since Android 1.0
+ */
+ public PatternSyntaxException(String description, String pattern, int index) {
+ this.pattern = pattern;
+ this.description = description;
+ this.index = index;
+ }
+
+ /**
+ * Returns the syntactically incorrect regular expression.
+ *
+ * @return the regular expression.
+ *
+ * @since Android 1.0
+ */
+ public String getPattern() {
+ return pattern;
+ }
+
+ /**
+ * Returns a detailed error message for the exception. The message is
+ * potentially multi-line, and it might include a detailed description, the
+ * original regular expression, and the index at which the error occured.
+ *
+ * @return the error message.
+ *
+ * @since Android 1.0
+ */
+ @Override
+ public String getMessage() {
+ StringBuilder builder = new StringBuilder("Syntax error");
+
+ if (description != null) {
+ builder.append(' ');
+ builder.append(description);
+ }
+
+ if (index >= 0) {
+ builder.append(" near index " + index + ":");
+ }
+
+ if (pattern != null) {
+ builder.append('\n');
+ builder.append(pattern);
+
+ if (index >= 0) {
+ char[] spaces = new char[index];
+ Arrays.fill(spaces, ' ');
+ builder.append('\n');
+ builder.append(spaces);
+ builder.append('^');
+ }
+ }
+
+ return builder.toString();
+ }
+
+ /**
+ * Returns the description of the syntax error, or {@code null} if the
+ * description is not known.
+ *
+ * @return the description.
+ * @since Android 1.0
+ */
+ public String getDescription() {
+ return description;
+ }
+
+ /**
+ * Returns the character index around which the error occurred, or -1 if the
+ * index is not known.
+ *
+ * @return the index.
+ *
+ * @since Android 1.0
+ */
+ public int getIndex() {
+ return index;
+ }
+
+}
diff --git a/regex/src/main/java/java/util/regex/package.html b/regex/src/main/java/java/util/regex/package.html
new file mode 100644
index 0000000..0508f3e
--- /dev/null
+++ b/regex/src/main/java/java/util/regex/package.html
@@ -0,0 +1,884 @@
+<html>
+ <head>
+ <!--
+ /*
+ * Copyright (C) 2007 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+ -->
+ </head>
+ <body>
+ Provides an implementation of regular expressions, which is useful for
+ matching, searching, and replacing strings based on patterns. The two
+ fundamental classes are {@link java.util.regex.Pattern} and
+ {@link java.util.regex.Matcher}. The former
+ takes a pattern described by means of a regular expression and compiles it
+ into a special internal representation. The latter matches the compiled
+ pattern against a given input.
+
+ <h2>Regular expressions</h2>
+
+ A regular expression consists of literal text, meta characters, character
+ sets, and operators. The latter three have a special meaning when
+ encountered during the processing of a pattern.
+
+ <ul>
+ <li>
+ <a href="#metachars">Meta characters</a> are a special means to describe
+ single characters in the input text. A common example for a meta
+ character is the dot '.', which, when used in a regular expression,
+ matches any character.
+ </li>
+ <li>
+ <a href="#charsets">Character sets</a> are a convenient means to
+ describe different characters that match a single character in the
+ input. Character sets are enclosed in angular brackets '[' and ']'
+ and use the dash '-' for forming ranges. A typical example is
+ "[0-9a-fA-F]", which describes the set of all hexadecimal digits.
+ </li>
+ <li>
+ <a href="#operators">Operators</a> modify or combine whole regular
+ expressions, with the result being a regular expression again. An
+ example for an operator is the asterisk '*', which, together with the
+ regular expression preceding it, matches zero or more repetitions of
+ that regular expression. The plus sign '+' is similar, but requires at
+ least one occurrence.
+ </li>
+ </ul>
+
+ Meta characters, the '[' and ']' that form a character set, and operators
+ normally lose their special meaning when preceded by a backslash '\'. To get
+ a backslash by itself, use a double backslash. Note that when using regular
+ expressions in Java source code, some care has to be taken to get the
+ backslashes right (due to yet another level of escaping being necessary for
+ Java).
+
+ <p>
+
+ The following table gives some basic examples of regular expressions and
+ input strings that match them:
+
+ <p>
+
+ <table>
+ <tr>
+ <th>
+ Regular expression
+ </th>
+ <th>
+ Matched string(s)
+ </th>
+ </tr>
+ <tr>
+ <td>
+ "Hello, World!"
+ </td>
+ <td>
+ "Hello, World!"
+ </td>
+ </tr>
+ <tr>
+ <td>
+ "Hello, World."
+ </td>
+ <td>
+ "Hello, World!", "Hello, World?"
+ </td>
+ </tr>
+ <tr>
+ <td>
+ "Hello, .*d!"
+ </td>
+ <td>
+ "Hello, World!", "Hello, Android!", "Hello, Dad!"
+ </td>
+ </tr>
+ <tr>
+ <td>
+ "[0-9]+ green bottles"
+ </td>
+ <td>
+ "0 green bottles", "25 green bottles", "1234 green bottles"
+ </td>
+ </tr>
+ </table>
+
+ <p>
+
+ The following section describe the various features in detail. The are also
+ some <a href="#impnotes">implementation notes</a> at the end.
+
+ <p>
+
+ <a name="metachars"></a>
+ <h2>Meta characters</h2>
+
+ The following two tables lists the meta characters understood in regular
+ expressions.
+
+ <p>
+
+ <!-- ICU-copied documentation begins here -->
+
+ <table>
+ <tr>
+ <th>
+ Meta character
+ </th>
+ <th>
+ Description
+ </th>
+ </tr>
+ <tr>
+ <td>
+ \a
+ </td>
+ <td>
+ Match a BELL, \u0007.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \A
+ </td>
+ <td>
+ Match at the beginning of the input. Differs from ^ in that
+ \A will not match after a new line within the input.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \b, outside of a <a href="#charsets">character set</a>
+ </td>
+ <td>
+ Match if the current position is a word boundary. Boundaries
+ occur at the transitions between word (\w) and non-word (\W)
+ characters, with combining marks ignored.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \b, within a <a href="#charsets">character set</a>
+ </td>
+ <td>
+ Match a BACKSPACE, \u0008.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \B
+ </td>
+ <td>
+ Match if the current position is not a word boundary.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \cX
+ </td>
+ <td>
+ Match a control-X character (replace X with actual character).
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \e
+ </td>
+ <td>
+ Match an ESCAPE, \u001B.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \E
+ </td>
+ <td>
+ Ends quoting started by \Q. Meta characters, character classes, and
+ operators become active again.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \f
+ </td>
+ <td>
+ Match a FORM FEED, \u000C.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \G
+ </td>
+ <td>
+ Match if the current position is at the end of the previous
+ match.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \n
+ </td>
+ <td>
+ Match a LINE FEED, \u000A.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \N{UNICODE CHARACTER NAME}
+ </td>
+ <td>
+ Match the named Unicode character.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \Q
+ </td>
+ <td>
+ Quotes all following characters until \E. The following text is
+ treated as literal.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \r
+ </td>
+ <td>
+ Match a CARRIAGE RETURN, \u000D.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \t
+ </td>
+ <td>
+ Match a HORIZONTAL TABULATION, \u0009.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \uhhhh
+ </td>
+ <td>
+ Match the character with the hex value hhhh.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \Uhhhhhhhh
+ </td>
+ <td>
+ Match the character with the hex value hhhhhhhh. Exactly
+ eight hex digits must be provided, even though the largest Unicode
+ code point is \U0010ffff.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \x{hhhh}
+ </td>
+ <td>
+ Match the character with the hex value hhhh. From one to six hex
+ digits may be supplied.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \xhh
+ </td>
+ <td>
+ Match the character with the hex value hh.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \Z
+ </td>
+ <td>
+ Match if the current position is at the end of input, but
+ before the final line terminator, if one exists.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \z
+ </td>
+ <td>
+ Match if the current position is at the end of input.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \0n, \0nn, \0nnn
+ </td>
+ <td>
+ Match the character with the octal value n, nn, or nnn. Maximum
+ value is 0377.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \n
+ </td>
+ <td>
+ Back Reference. Match whatever the nth capturing group
+ matched. n must be a number &gt; 1 and &lt; total number of capture
+ groups in the pattern. Note: Octal escapes, such as \012, are not
+ supported in ICU regular expressions
+ </td>
+ </tr>
+ <tr>
+ <td>
+ [character set]
+ </td>
+ <td>
+ Match any one character from the character set. See
+ <a href="#charsets">character sets</a> for a full description of what
+ may appear between the angular brackets.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ .
+ </td>
+ <td>
+ Match any character.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ ^
+ </td>
+ <td>
+ Match at the beginning of a line.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ $
+ </td>
+ <td>
+ Match at the end of a line.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \
+ </td>
+ <td>
+ Quotes the following character, so that is loses any special
+ meaning it might have.
+ </td>
+ </tr>
+ </table>
+
+ <!-- ICU-copied documentation begins here -->
+
+ <p>
+
+ <a name="charsets"></a>
+ <h2>Character sets</h2>
+
+ The following table lists the syntax elements allowed inside a character
+ set:
+
+ <p>
+
+ <table>
+ <tr>
+ <th>
+ Element
+ </th>
+ <th>
+ Description
+ </th>
+ </tr>
+ <tr>
+ <td>
+ [a]
+ </td>
+ <td>
+ The character set consisting of the letter 'a' only.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ [xyz]
+ </td>
+ <td>
+ The character set consisting of the letters 'x', 'y', and 'z',
+ described by explicit enumeration.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ [x-z]
+ </td>
+ <td>
+ The character set consisting of the letters 'x', 'y', and 'z',
+ described by means of a range.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ [^xyz]
+ </td>
+ <td>
+ The character set consisting of everything but the letters 'x', 'y',
+ and 'z'.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ [[a-f][0-9]]
+ </td>
+ <td>
+ The character set formed by building the union of the two character
+ sets [a-f] and [0-9].
+ </td>
+ </tr>
+ <tr>
+ <td>
+ [[a-z]&amp;&amp;[jkl]]
+ </td>
+ <td>
+ The character set formed by building the intersection of the two
+ character sets [a-z] and [jkl]. You can also use a single '&amp;', but
+ this regular expression might not be <a href="#impnotes">portable</a>.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ [[a-z]--[jkl]]
+ </td>
+ <td>
+ The character set formed by building the difference of the two
+ character sets [a-z] and [jkl]. You can also use a single '-'. This
+ operator is generally not <a href="#impnotes">portable</a>.
+ </td>
+ </tr>
+ </table>
+
+ <p>
+
+ A couple of frequently used character sets are predefined and named.
+ These can be referenced by their name, but behave otherwise similar to
+ explicit character sets. The following table lists them:
+
+ <p>
+
+ <table>
+ <tr>
+ <th>
+ Character set
+ </th>
+ <th>
+ Description
+ </th>
+ </tr>
+ <tr>
+ <td>
+ \d, \D
+ </td>
+ <td>
+ The set consisting of all digit characters (\d) or the opposite of
+ it (\D).
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \s, \S
+ </td>
+ <td>
+ The set consisting of all space characters (\s) or the opposite of
+ it (\S).
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \w, \W
+ </td>
+ <td>
+ The set consisting of all word characters (\w) or the opposite
+ of it (\W).
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \X
+ </td>
+ <td>
+ The set of all grapheme clusters.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \p{NAME}, \P{NAME}
+ </td>
+ <td>
+ The Posix set with the specified NAME (\p{}) or the opposite
+ of it (\P{}) - Legal values for NAME are 'Alnum', 'Alpha', 'ASCII',
+ 'Blank', 'Cntrl', 'Digit', 'Graph', 'Lower', 'Print', 'Punct',
+ 'Upper', 'XDigit' .
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \p{inBLOCK}, \P{inBLOCK}
+ </td>
+ <td>
+ The character set equivalent to the given Unicode BLOCK (\p{}) or
+ the opposite of it (\P{}). An example for a legal BLOCK name is
+ 'Hebrew', meaning, unsurprisingly, all Hebrew characters.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \p{CATEGORY}, \P{CATEGORY}
+ </td>
+ <td>
+ The character set equivalent to the Unicode CATEGORY (\p{}) or the
+ opposite of it (\P{}). An example for a legal CATEGORY name is 'Lu',
+ meaning all uppercase letters.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ \p{javaMETHOD}, \P{javaMETHOD}
+ </td>
+ <td>
+ The character set equivalent to the isMETHOD() operation of the
+ {@link java.lang.Character} class (\p{}) or the opposite of it (\P{}).
+ </td>
+ </tr>
+ </table>
+
+ <p>
+
+ <a name="operators"></a>
+ <h2>Operators</h2>
+
+ The following table lists the operators understood inside regular
+ expressions:
+
+ <p>
+
+ <!-- ICU-copied documentation begins here -->
+
+ <table>
+ <tr>
+ <th>
+ Operator
+ </th>
+ <th>
+ Description
+ </th>
+ </tr>
+ <tr>
+ <td>
+ |
+ </td>
+ <td>
+ Alternation. A|B matches either A or B.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ *
+ </td>
+ <td>
+ Match 0 or more times. Match as many times as possible.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ +
+ </td>
+ <td>
+ Match 1 or more times. Match as many times as possible.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ ?
+ </td>
+ <td>
+ Match zero or one times. Prefer one.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n}
+ </td>
+ <td>
+ Match exactly n times
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n,}
+ </td>
+ <td>
+ Match at least n times. Match as many times as possible.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n,m}
+ </td>
+ <td>
+ Match between n and m times. Match as many times as possible,
+ but not more than m.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ *?
+ </td>
+ <td>
+ Match 0 or more times. Match as few times as possible.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ +?
+ </td>
+ <td>
+ Match 1 or more times. Match as few times as possible.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ ??
+ </td>
+ <td>
+ Match zero or one times. Prefer zero.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n}?
+ </td>
+ <td>
+ Match exactly n times.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n,}?
+ </td>
+ <td>
+ Match at least n times, but no more than required for an
+ overall pattern match
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n,m}?
+ </td>
+ <td>
+ Match between n and m times. Match as few times as possible,
+ but not less than n.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ *+
+ </td>
+ <td>
+ Match 0 or more times. Match as many times as possible when
+ first encountered, do not retry with fewer even if overall match
+ fails (Possessive Match)
+ </td>
+ </tr>
+ <tr>
+ <td>
+ ++
+ </td>
+ <td>
+ Match 1 or more times. Possessive match.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ ?+
+ </td>
+ <td>
+ Match zero or one times. Possessive match.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n}+
+ </td>
+ <td>
+ Match exactly n times.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n,}+
+ </td>
+ <td>
+ Match at least n times. Possessive Match.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ {n,m}+
+ </td>
+ <td>
+ Match between n and m times. Possessive Match.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ ( ... )
+ </td>
+ <td>
+ Capturing parentheses. Range of input that matched the
+ parenthesized subexpression is available after the match.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?: ... )
+ </td>
+ <td>
+ Non-capturing parentheses. Groups the included pattern, but
+ does not provide capturing of matching text. Somewhat more efficient
+ than capturing parentheses.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?&gt; ... )
+ </td>
+ <td>
+ Atomic-match parentheses. First match of the parenthesized
+ subexpression is the only one tried; if it does not lead to an
+ overall pattern match, back up the search for a match to a position
+ before the "(?&gt;"
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?# ... )
+ </td>
+ <td>
+ Free-format comment (?# comment ).
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?= ... )
+ </td>
+ <td>
+ Look-ahead assertion. True if the parenthesized pattern
+ matches at the current input position, but does not advance the
+ input position.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?! ... )
+ </td>
+ <td>
+ Negative look-ahead assertion. True if the parenthesized
+ pattern does not match at the current input position. Does not
+ advance the input position.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?&lt;= ... )
+ </td>
+ <td>
+ Look-behind assertion. True if the parenthesized pattern
+ matches text preceding the current input position, with the last
+ character of the match being the input character just before the
+ current position. Does not alter the input position. The length of
+ possible strings matched by the look-behind pattern must not be
+ unbounded (no * or + operators.)
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?&lt;! ... )
+ </td>
+ <td>
+ Negative Look-behind assertion. True if the parenthesized
+ pattern does not match text preceding the current input position,
+ with the last character of the match being the input character just
+ before the current position. Does not alter the input position. The
+ length of possible strings matched by the look-behind pattern must
+ not be unbounded (no * or + operators.)
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?ismwx-ismwx: ... )
+ </td>
+ <td>
+ Flag settings. Evaluate the parenthesized expression with the
+ specified flags enabled or -disabled.
+ </td>
+ </tr>
+ <tr>
+ <td>
+ (?ismwx-ismwx)
+ </td>
+ <td>
+ Flag settings. Change the flag settings. Changes apply to the
+ portion of the pattern following the setting. For example, (?i)
+ changes to a case insensitive match.
+ </td>
+ </tr>
+ </table>
+
+ <!-- ICU-copied documentation ends here -->
+
+ <p>
+
+ <a name="impnotes"></a>
+ <h2>Implementation notes</h2>
+
+ The regular expression implementation used in Android is provided by
+ <a href="http://www.icu-project.org">ICU</a>. The notation for the regular
+ expressions is mostly a superset of those used in other Java language
+ implementations. This means that existing applications will normally work as
+ expected, but in rare cases some regular expression content that is meant to
+ be literal might be interpreted with a special meaning. The most notable
+ examples are the single '&amp;', which can also be used as the intersection
+ operator for <a href="#charsets">character sets</a>, and the intersection
+ operators '-' and '--'. Also, some of the flags are handled in a
+ slightly different way:
+
+ <ul>
+ <li>
+ The {@link java.util.regex.Pattern#CASE_INSENSITIVE} flag silently
+ assumes Unicode case-insensitivity. That is, the
+ {@link java.util.regex.Pattern#UNICODE_CASE} flag is effectively a
+ no-op.
+ </li>
+ <li>
+ The {@link java.util.regex.Pattern#CANON_EQ} flag is not supported at
+ all (throws an exception).
+ </li>
+ </ul>
+
+ @since Android 1.0
+
+ </body>
+</html>
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/AllTests.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/AllTests.java
new file mode 100644
index 0000000..b69c401
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/AllTests.java
@@ -0,0 +1,49 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import junit.framework.Test;
+import junit.framework.TestSuite;
+
+/**
+ * Provides a test suite for java.util.regex package.
+ */
+public class AllTests {
+
+ public static void main(String[] args) {
+ junit.textui.TestRunner.run(suite());
+ }
+
+ public static Test suite() {
+ TestSuite suite = tests.TestSuiteFactory.createTestSuite("Tests for java.util.regex");
+ //$JUnit-BEGIN$
+
+ suite.addTestSuite(Matcher2Test.class);
+ suite.addTestSuite(MatcherTest.class);
+ suite.addTestSuite(ModeTest.class);
+ suite.addTestSuite(Pattern2Test.class);
+ suite.addTestSuite(PatternErrorTest.class);
+ suite.addTestSuite(PatternSyntaxExceptionTest.class);
+ suite.addTestSuite(PatternTest.class);
+ suite.addTestSuite(ReplaceTest.class);
+ suite.addTestSuite(SplitTest.class);
+
+ //$JUnit-END$
+ return suite;
+ }
+}
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/Matcher2Test.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/Matcher2Test.java
new file mode 100644
index 0000000..ab0de63
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/Matcher2Test.java
@@ -0,0 +1,327 @@
+/* Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import dalvik.annotation.TestTargetClass;
+import dalvik.annotation.TestTargets;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestLevel;
+
+import junit.framework.TestCase;
+import java.util.regex.*;
+
+/**
+ * Tests Matcher methods
+ *
+ */
+@TestTargetClass(java.util.regex.Matcher.class)
+public class Matcher2Test extends TestCase {
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL,
+ notes = "Verifies the basic functionality of toString() method.",
+ method = "toString",
+ args = {}
+ )
+ public void test_toString() {
+ Pattern p = Pattern.compile("foo");
+ Matcher m = p.matcher("bar");
+ assertNotNull(m.toString());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies start, end, group, usePattern methods with wrong conditions, IllegalStateException should be thrown",
+ method = "start",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies start, end, group, usePattern methods with wrong conditions, IllegalStateException should be thrown",
+ method = "end",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies start, end, group, usePattern methods with wrong conditions, IllegalStateException should be thrown",
+ method = "group",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies start, end, group, usePattern methods with wrong conditions, IllegalStateException should be thrown",
+ method = "start",
+ args = {int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies start, end, group, usePattern methods with wrong conditions, IllegalStateException should be thrown",
+ method = "end",
+ args = {int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies start, end, group, usePattern methods with wrong conditions, IllegalStateException should be thrown",
+ method = "group",
+ args = {int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies start, end, group, usePattern methods with wrong conditions, IllegalStateException should be thrown",
+ method = "usePattern",
+ args = {java.util.regex.Pattern.class}
+ )
+ })
+ public void testErrorConditions() throws PatternSyntaxException {
+ // Test match cursors in absence of a match
+ Pattern p = Pattern.compile("foo");
+ Matcher m = p.matcher("bar");
+ assertFalse(m.matches());
+
+ try {
+ m.start();
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.end();
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.group();
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.start(1);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.end(1);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.group(1);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ // regression test for HARMONY-2418
+ try {
+ m.usePattern(null);
+ fail("IllegalArgumentException expected");
+ } catch (IllegalArgumentException e) {
+ // PASSED
+ }
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies end, start, group methods with wrong conditions, IndexOutOfBoundsException, IllegalStateException should be thrown",
+ method = "start",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies end, start, group methods with wrong conditions, IndexOutOfBoundsException, IllegalStateException should be thrown",
+ method = "end",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies end, start, group methods with wrong conditions, IndexOutOfBoundsException, IllegalStateException should be thrown",
+ method = "start",
+ args = {int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies end, start, group methods with wrong conditions, IndexOutOfBoundsException, IllegalStateException should be thrown",
+ method = "end",
+ args = {int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies end, start, group methods with wrong conditions, IndexOutOfBoundsException, IllegalStateException should be thrown",
+ method = "group",
+ args = {int.class}
+ )
+ })
+ public void testErrorConditions2() throws PatternSyntaxException {
+ // Test match cursors in absence of a match
+ Pattern p = Pattern.compile("(foo[0-9])(bar[a-z])");
+ Matcher m = p.matcher("foo1barzfoo2baryfoozbar5");
+
+ assertTrue(m.find());
+ assertEquals(0, m.start());
+ assertEquals(8, m.end());
+ assertEquals(0, m.start(1));
+ assertEquals(4, m.end(1));
+ assertEquals(4, m.start(2));
+ assertEquals(8, m.end(2));
+
+ try {
+ m.start(3);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.end(3);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.group(3);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.start(-1);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.end(-1);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.group(-1);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ assertTrue(m.find());
+ assertEquals(8, m.start());
+ assertEquals(16, m.end());
+ assertEquals(8, m.start(1));
+ assertEquals(12, m.end(1));
+ assertEquals(12, m.start(2));
+ assertEquals(16, m.end(2));
+
+ try {
+ m.start(3);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.end(3);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.group(3);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.start(-1);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.end(-1);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ try {
+ m.group(-1);
+ fail("IndexOutOfBoundsException expected");
+ } catch (IndexOutOfBoundsException e) {
+ }
+
+ assertFalse(m.find());
+
+ try {
+ m.start(3);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.end(3);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.group(3);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.start(-1);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.end(-1);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+
+ try {
+ m.group(-1);
+ fail("IllegalStateException expected");
+ } catch (IllegalStateException e) {
+ }
+ }
+
+ /*
+ * Regression test for HARMONY-997
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies that IndexOutOfBoundsException exception is thrown while calling of replaceAll method with incorrect string.",
+ method = "replaceAll",
+ args = {java.lang.String.class}
+ )
+ public void testReplacementBackSlash() {
+ String str = "replace me";
+ String replacedString = "me";
+ String substitutionString = "\\";
+ Pattern pat = Pattern.compile(replacedString);
+ Matcher mat = pat.matcher(str);
+ try {
+ String res = mat.replaceAll(substitutionString);
+ fail("IndexOutOfBoundsException should be thrown - " + res);
+ } catch (Exception e) {
+ }
+ }
+}
+
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/MatcherTest.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/MatcherTest.java
new file mode 100644
index 0000000..5e9137b
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/MatcherTest.java
@@ -0,0 +1,1471 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import junit.framework.TestCase;
+import dalvik.annotation.TestLevel;
+import dalvik.annotation.TestTargetClass;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestTargets;
+
+@TestTargetClass(
+ value = Matcher.class,
+ untestedMethods= {
+ @TestTargetNew(
+ level = TestLevel.NOT_FEASIBLE,
+ notes = "finalize is hard to test since the implementation only calls a native function",
+ method = "finalize",
+ args = {}
+ )
+ }
+
+)
+public class MatcherTest extends TestCase {
+ String[] testPatterns = {
+ "(a|b)*abb",
+ "(1*2*3*4*)*567",
+ "(a|b|c|d)*aab",
+ "(1|2|3|4|5|6|7|8|9|0)(1|2|3|4|5|6|7|8|9|0)*",
+ "(abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ)*",
+ "(a|b)*(a|b)*A(a|b)*lice.*",
+ "(a|b|c|d|e|f|g|h|i|j|k|l|m|n|o|p|q|r|s|t|u|v|w|x|y|z)(a|b|c|d|e|f|g|h|"
+ + "i|j|k|l|m|n|o|p|q|r|s|t|u|v|w|x|y|z)*(1|2|3|4|5|6|7|8|9|0)*|while|for|struct|if|do" };
+
+ String[] groupPatterns = { "(a|b)*aabb", "((a)|b)*aabb", "((a|b)*)a(abb)",
+ "(((a)|(b))*)aabb", "(((a)|(b))*)aa(b)b", "(((a)|(b))*)a(a(b)b)" };
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "",
+ method = "appendReplacement",
+ args = {java.lang.StringBuffer.class, java.lang.String.class}
+ )
+ public void testAppendReplacement() {
+ Pattern pat = Pattern.compile("XX");
+ Matcher m = pat.matcher("Today is XX-XX-XX ...");
+ StringBuffer sb = new StringBuffer();
+
+ for (int i = 0; m.find(); i++) {
+ m.appendReplacement(sb, new Integer(i * 10 + i).toString());
+ }
+ m.appendTail(sb);
+ assertEquals("Today is 0-11-22 ...", sb.toString());
+
+ pat = Pattern.compile("cat");
+ m = pat.matcher("one-cat-two-cats-in-the-yard");
+ sb = new StringBuffer();
+ Throwable t = null;
+ m.find();
+ try {
+ m.appendReplacement(null, "dog");
+ } catch (NullPointerException e) {
+ t = e;
+ }
+ assertNotNull(t);
+ t = null;
+ m.find();
+ try {
+ m.appendReplacement(sb, null);
+ } catch (NullPointerException e) {
+ t = e;
+ }
+ assertNotNull(t);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "",
+ method = "appendReplacement",
+ args = {java.lang.StringBuffer.class, java.lang.String.class}
+ )
+ public void testAppendReplacementRef() {
+ Pattern p = Pattern.compile("xx (rur|\\$)");
+ Matcher m = p.matcher("xx $ equals to xx rur.");
+ StringBuffer sb = new StringBuffer();
+ for (int i = 1; m.find(); i *= 30) {
+ String rep = new Integer(i).toString() + " $1";
+ m.appendReplacement(sb, rep);
+ }
+ m.appendTail(sb);
+ assertEquals("1 $ equals to 30 rur.", sb.toString());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "",
+ method = "replaceAll",
+ args = {java.lang.String.class}
+ )
+ public void testReplaceAll() {
+ String input = "aabfooaabfooabfoob";
+ String pattern = "a*b";
+ Pattern pat = Pattern.compile(pattern);
+ Matcher mat = pat.matcher(input);
+
+ assertEquals("-foo-foo-foo-", mat.replaceAll("-"));
+ }
+
+ /**
+ * @test java.util.regex.Matcher#reset(String)
+ * test reset(String) method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies the reset(CharSequence input) method.",
+ method = "reset",
+ args = {java.lang.CharSequence.class}
+ )
+ public void test_resetLjava_lang_String() {
+ String testPattern = "(abb)";
+ String testString1 = "babbabbcccabbabbabbabbabb";
+ String testString2 = "cddcddcddcddcddbbbb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString1);
+
+ while (mat.find());
+ assertEquals("Reset should return itself 1", mat, mat.reset(testString2));
+ assertFalse("After reset matcher should not find pattern in given input", mat.find());
+ assertEquals("Reset should return itself 2", mat, mat.reset(testString1));
+ assertTrue("After reset matcher should find pattern in given input", mat.find());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "",
+ method = "appendReplacement",
+ args = {java.lang.StringBuffer.class, java.lang.String.class}
+ )
+ public void testAppendSlashes() {
+ Pattern p = Pattern.compile("\\\\");
+ Matcher m = p.matcher("one\\cat\\two\\cats\\in\\the\\yard");
+ StringBuffer sb = new StringBuffer();
+ while (m.find()) {
+ m.appendReplacement(sb, "\\\\");
+ }
+ m.appendTail(sb);
+ assertEquals("one\\cat\\two\\cats\\in\\the\\yard", sb.toString());
+
+ }
+
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "appendTail",
+ args = {java.lang.StringBuffer.class}
+ )
+ public void testAppendTail() {
+ 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);
+ assertEquals("one-dog-two-dogs-in-the-yard", sb.toString());
+
+ p = Pattern.compile("cat|yard");
+ m = p.matcher("one-cat-two-cats-in-the-yard");
+ sb = new StringBuffer();
+ while (m.find()) {
+ m.appendReplacement(sb, "dog");
+ }
+ assertEquals("one-dog-two-dogs-in-the-dog", sb.toString());
+ m.appendTail(sb);
+ assertEquals("one-dog-two-dogs-in-the-dog", sb.toString());
+
+ p = Pattern.compile("cat");
+ m = p.matcher("one-cat-two-cats-in-the-yard");
+ sb = new StringBuffer();
+ while (m.find()) {
+ m.appendReplacement(sb, "dog");
+ }
+ Throwable t = null;
+ try {
+ m.appendTail(null);
+ } catch (NullPointerException e) {
+ t = e;
+ }
+ assertNotNull(t);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies replaceFirst(String replacement) method. ",
+ method = "replaceFirst",
+ args = {java.lang.String.class}
+ )
+ public void testReplaceFirst() {
+ String input = "zzzdogzzzdogzzz";
+ String pattern = "dog";
+ Pattern pat = Pattern.compile(pattern);
+ Matcher mat = pat.matcher(input);
+
+ assertEquals("zzzcatzzzdogzzz", mat.replaceFirst("cat"));
+ }
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies pattern() method.",
+ method = "pattern",
+ args = {}
+ )
+ public void testPattern() {
+ for (String element : testPatterns) {
+ Pattern test = Pattern.compile(element);
+ assertEquals(test, test.matcher("aaa").pattern());
+ }
+
+ for (String element : testPatterns) {
+ assertEquals(element, Pattern.compile(element).matcher("aaa")
+ .pattern().toString());
+ }
+ }
+
+ /**
+ * @test java.util.regex.Matcher#reset()
+ * test reset() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies the reset() method. ",
+ method = "reset",
+ args = {}
+ )
+ public void test_reset() {
+ String testPattern = "(abb)";
+ String testString = "babbabbcccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ while (mat.find());
+ assertEquals("Reset should return itself", mat, mat.reset());
+ assertTrue("After reset matcher should find pattern in given input", mat.find());
+ }
+
+ /*
+ * Class under test for String group(int)
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies group(int group) method.",
+ method = "group",
+ args = {int.class}
+ )
+ public void testGroupint() {
+ String positiveTestString = "ababababbaaabb";
+ String negativeTestString = "gjhfgdsjfhgcbv";
+
+ // test IndexOutOfBoundsException
+ // //
+ for (int i = 0; i < groupPatterns.length; i++) {
+ Pattern test = Pattern.compile(groupPatterns[i]);
+ Matcher mat = test.matcher(positiveTestString);
+ mat.matches();
+ try {
+ // groupPattern <index + 1> equals to number of groups
+ // of the specified pattern
+ // //
+ mat.group(i + 2);
+ fail("IndexOutBoundsException expected");
+ mat.group(i + 100);
+ fail("IndexOutBoundsException expected");
+ mat.group(-1);
+ fail("IndexOutBoundsException expected");
+ mat.group(-100);
+ fail("IndexOutBoundsException expected");
+ } catch (IndexOutOfBoundsException iobe) {
+ }
+ }
+
+ String[][] groupResults = { { "a" }, { "a", "a" },
+ { "ababababba", "a", "abb" }, { "ababababba", "a", "a", "b" },
+ { "ababababba", "a", "a", "b", "b" },
+ { "ababababba", "a", "a", "b", "abb", "b" }, };
+
+ for (int i = 0; i < groupPatterns.length; i++) {
+ Pattern test = Pattern.compile(groupPatterns[i]);
+ Matcher mat = test.matcher(positiveTestString);
+ mat.matches();
+ for (int j = 0; j < groupResults[i].length; j++) {
+ assertEquals("i: " + i + " j: " + j, groupResults[i][j], mat
+ .group(j + 1));
+ }
+
+ }
+
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies group() and group(int group) methods.",
+ method = "group",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies group() and group(int group) methods.",
+ method = "group",
+ args = {int.class}
+ )
+ })
+ public void testGroup() {
+ String positiveTestString = "ababababbaaabb";
+ String negativeTestString = "gjhfgdsjfhgcbv";
+ for (String element : groupPatterns) {
+ Pattern test = Pattern.compile(element);
+ Matcher mat = test.matcher(positiveTestString);
+ mat.matches();
+ // test result
+ assertEquals(positiveTestString, mat.group());
+
+ // test equal to group(0) result
+ assertEquals(mat.group(0), mat.group());
+ }
+
+ for (String element : groupPatterns) {
+ Pattern test = Pattern.compile(element);
+ Matcher mat = test.matcher(negativeTestString);
+ mat.matches();
+ try {
+ mat.group();
+ fail("IllegalStateException expected for <false> matches result");
+ } catch (IllegalStateException ise) {
+ }
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies group(int group) method.",
+ method = "group",
+ args = {int.class}
+ )
+ public void testGroupPossessive() {
+ Pattern pat = Pattern.compile("((a)|(b))++c");
+ Matcher mat = pat.matcher("aac");
+
+ mat.matches();
+ assertEquals("a", mat.group(1));
+ }
+
+ /**
+ * @test java.util.regex.Matcher#hasAnchoringBounds()
+ * test hasAnchoringBounds() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies that hasAnchoringBounds method returns correct value.",
+ method = "hasAnchoringBounds",
+ args = {}
+ )
+ public void test_hasAnchoringBounds() {
+ String testPattern = "abb";
+ String testString = "abb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ assertTrue("Matcher uses anchoring bound by default",
+ mat.hasAnchoringBounds());
+
+ Matcher mu = mat.useAnchoringBounds(true);
+ assertTrue("Incorrect value of anchoring bounds",
+ mu.hasAnchoringBounds());
+
+ mu = mat.useAnchoringBounds(false);
+ assertFalse("Incorrect value of anchoring bounds",
+ mu.hasAnchoringBounds());
+ }
+
+ /**
+ * @test java.util.regex.Matcher#hasTransparentBounds()
+ * test hasTransparentBounds() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies that hasTransparentBound method returns correct value.",
+ method = "hasTransparentBounds",
+ args = {}
+ )
+ public void test_hasTransparentBounds() {
+ String testPattern = "abb";
+ String testString = "ab\nb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ assertFalse("Matcher uses opaque bounds by default",
+ mat.hasTransparentBounds());
+
+ Matcher mu = mat.useTransparentBounds(true);
+ assertTrue("Incorrect value of anchoring bounds",
+ mu.hasTransparentBounds());
+
+ mu = mat.useTransparentBounds(false);
+ assertFalse("Incorrect value of anchoring bounds",
+ mu.hasTransparentBounds());
+ }
+
+ /**
+ * @test java.util.regex.Matcher#start(int)
+ * test start(int) method.
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the start(int group) method.",
+ method = "start",
+ args = {int.class}
+ )
+ public void test_startI() {
+ String testPattern = "(((abb)a)(bb))";
+ String testString = "cccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+ int start = 3;
+ int end = 6;
+ int i, j;
+
+ for (j = 0; j < 3; j++) {
+ while (mat.find(start + j - 2)) {
+ for (i = 0; i < 4; i++) {
+ assertEquals("Start is wrong for group " + i + " :" + mat.group(i), start, mat.start(i));
+ }
+ assertEquals("Start is wrong for group " + i + " :" + mat.group(i), start + 4, mat.start(i));
+
+ start = end;
+ end += 3;
+ }
+ }
+ }
+
+ /**
+ * @test java.util.regex.Matcher#end(int)
+ * test end(int) method.
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the basic functionality of end(int group) method.",
+ method = "end",
+ args = {int.class}
+ )
+ public void test_endI() {
+ String testPattern = "(((abb)a)(bb))";
+ String testString = "cccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+ int start = 3;
+ int end = 6;
+ int i, j;
+
+ for (j = 0; j < 3; j++) {
+ while (mat.find(start + j - 2)) {
+ for (i = 0; i < 4; i++) {
+ assertEquals("End is wrong for group " + i + " :" + mat.group(i), start + mat.group(i).length(), mat.end(i));
+ }
+ assertEquals("End is wrong for group " + i + " :" + mat.group(i), start + 4 + mat.group(i).length(), mat.end(i));
+
+ start = end;
+ end += 3;
+ }
+ }
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() method in miscellaneous cases.",
+ method = "matches",
+ args = {}
+ )
+ public void testMatchesMisc() {
+ String[][] posSeq = {
+ { "abb", "ababb", "abababbababb", "abababbababbabababbbbbabb" },
+ { "213567", "12324567", "1234567", "213213567",
+ "21312312312567", "444444567" },
+ { "abcdaab", "aab", "abaab", "cdaab", "acbdadcbaab" },
+ { "213234567", "3458", "0987654", "7689546432", "0398576",
+ "98432", "5" },
+ {
+ "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ",
+ "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
+ + "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ" },
+ { "ababbaAabababblice", "ababbaAliceababab", "ababbAabliceaaa",
+ "abbbAbbbliceaaa", "Alice" },
+ { "a123", "bnxnvgds156", "for", "while", "if", "struct" }
+
+ };
+
+ for (int i = 0; i < testPatterns.length; i++) {
+ Pattern pat = Pattern.compile(testPatterns[i]);
+ for (int j = 0; j < posSeq[i].length; j++) {
+ Matcher mat = pat.matcher(posSeq[i][j]);
+ assertTrue("Incorrect match: " + testPatterns[i] + " vs "
+ + posSeq[i][j], mat.matches());
+ }
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Stress test for matches() method.",
+ method = "matches",
+ args = {}
+ )
+ public void testMatchesQuantifiers() {
+ String[] testPatternsSingles = { "a{5}", "a{2,4}", "a{3,}" };
+ String[] testPatternsMultiple = { "((a)|(b)){1,2}abb",
+ "((a)|(b)){2,4}", "((a)|(b)){3,}" };
+
+ String[][] stringSingles = { { "aaaaa", "aaa" },
+ { "aa", "a", "aaa", "aaaaaa", "aaaa", "aaaaa" },
+ { "aaa", "a", "aaaa", "aa" }, };
+
+ String[][] stringMultiples = { { "ababb", "aba" },
+ { "ab", "b", "bab", "ababa", "abba", "abababbb" },
+ { "aba", "b", "abaa", "ba" }, };
+
+ for (int i = 0; i < testPatternsSingles.length; i++) {
+ Pattern pat = Pattern.compile(testPatternsSingles[i]);
+ for (int j = 0; j < stringSingles.length / 2; j++) {
+ assertTrue("Match expected, but failed: " + pat.pattern()
+ + " : " + stringSingles[i][j], pat.matcher(
+ stringSingles[i][j * 2]).matches());
+ assertFalse("Match failure expected, but match succeed: "
+ + pat.pattern() + " : " + stringSingles[i][j * 2 + 1],
+ pat.matcher(stringSingles[i][j * 2 + 1]).matches());
+ }
+ }
+
+ for (int i = 0; i < testPatternsMultiple.length; i++) {
+ Pattern pat = Pattern.compile(testPatternsMultiple[i]);
+ for (int j = 0; j < stringMultiples.length / 2; j++) {
+ assertTrue("Match expected, but failed: " + pat.pattern()
+ + " : " + stringMultiples[i][j], pat.matcher(
+ stringMultiples[i][j * 2]).matches());
+ assertFalse(
+ "Match failure expected, but match succeed: "
+ + pat.pattern() + " : "
+ + stringMultiples[i][j * 2 + 1], pat.matcher(
+ stringMultiples[i][j * 2 + 1]).matches());
+ }
+ }
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods for specific pattern.",
+ method = "matches",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods for specific pattern.",
+ method = "group",
+ args = {int.class}
+ )
+ })
+ public void testQuantVsGroup() {
+ String patternString = "(d{1,3})((a|c)*)(d{1,3})((a|c)*)(d{1,3})";
+ String testString = "dacaacaacaaddaaacaacaaddd";
+
+ Pattern pat = Pattern.compile(patternString);
+ Matcher mat = pat.matcher(testString);
+
+ mat.matches();
+ assertEquals("dacaacaacaaddaaacaacaaddd", mat.group());
+ assertEquals("d", mat.group(1));
+ assertEquals("acaacaacaa", mat.group(2));
+ assertEquals("dd", mat.group(4));
+ assertEquals("aaacaacaa", mat.group(5));
+ assertEquals("ddd", mat.group(7));
+ }
+
+ /**
+ * @test java.util.regex.Matcher#lookingAt()
+ * test lookingAt() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies that lookingAt() method returns correct value.",
+ method = "lookingAt",
+ args = {}
+ )
+ public void test_lookingAt() {
+ String testPattern = "(((abb)a)(bb))";
+ String testString1 = "babbabbcccabbabbabbabbabb";
+ String testString2 = "abbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat1 = pat.matcher(testString1);
+ Matcher mat2 = pat.matcher(testString2);
+
+ assertFalse("Should not find given pattern in 1 string", mat1.lookingAt());
+ mat1.region(1, 10);
+ assertTrue("Should find given pattern in region of string", mat1.lookingAt());
+ assertTrue("Should find given pattern in 2 string", mat2.lookingAt());
+ }
+
+ /*
+ * Class under test for boolean find()
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies that find() method returns correct value.",
+ method = "find",
+ args = {}
+ )
+ public void testFind() {
+ String testPattern = "(abb)";
+ String testString = "cccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+ int start = 3;
+ int end = 6;
+ while (mat.find()) {
+ assertEquals(start, mat.start(1));
+ assertEquals(end, mat.end(1));
+
+ start = end;
+ end += 3;
+ }
+
+ testPattern = "(\\d{1,3})";
+ testString = "aaaa123456789045";
+
+ Pattern pat2 = Pattern.compile(testPattern);
+ Matcher mat2 = pat2.matcher(testString);
+ start = 4;
+ int length = 3;
+ while (mat2.find()) {
+ assertEquals(testString.substring(start, start + length), mat2
+ .group(1));
+ start += length;
+ }
+ }
+
+ /**
+ * @test java.util.regex.Matcher#find(int)
+ * test find (int) method. Created via modifying method for find
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "find",
+ args = {int.class}
+ )
+ public void test_findI() {
+ String testPattern = "(abb)";
+ String testString = "cccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+ int start = 3;
+ int end = 6;
+ int j;
+
+ for (j = 0; j < 3; j++) {
+ while (mat.find(start + j - 2)) {
+ assertEquals(start, mat.start(1));
+ assertEquals(end, mat.end(1));
+
+ start = end;
+ end += 3;
+ }
+ start = 6;
+ end = 9;
+ }
+
+ testPattern = "(\\d{1,3})";
+ testString = "aaaa123456789045";
+
+ Pattern pat2 = Pattern.compile(testPattern);
+ Matcher mat2 = pat2.matcher(testString);
+ start = 4;
+ int length = 3;
+ for (j = 0; j < length; j++) {
+ for (int i = 4 + j; i < testString.length() - length; i += length) {
+ mat2.find(i);
+ assertEquals(testString.substring(i, i + length), mat2.group(1));
+ }
+ }
+
+ // Starting index out of region
+ Pattern pat3 = Pattern.compile("new");
+ Matcher mat3 = pat3.matcher("Brave new world");
+
+ assertTrue(mat3.find(-1));
+ assertTrue(mat3.find(6));
+ assertFalse(mat3.find(7));
+
+ mat3.region(7, 10);
+
+ assertFalse(mat3.find(3));
+ assertFalse(mat3.find(6));
+ assertFalse(mat3.find(7));
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() method for predefined.",
+ method = "replaceFirst",
+ args = {java.lang.String.class}
+ )
+ public void testSEOLsymbols() {
+ Pattern pat = Pattern.compile("^a\\(bb\\[$");
+ Matcher mat = pat.matcher("a(bb[");
+
+ assertTrue(mat.matches());
+ }
+
+ /**
+ * @test java.util.regex.Matcher#start()
+ * test start() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the start() method.",
+ method = "start",
+ args = {}
+ )
+ public void test_start() {
+ String testPattern = "(abb)";
+ String testString = "cccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+ int start = 3;
+ int end = 6;
+ int j;
+
+ for (j = 0; j < 3; j++) {
+ while (mat.find()) {
+ assertEquals("Start is wrong", start, mat.start());
+
+ start = end;
+ end += 3;
+ }
+ }
+ }
+
+ /**
+ * @test java.util.regex.Matcher#end()
+ * test end() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the basic functionality of end() method. ",
+ method = "end",
+ args = {}
+ )
+ public void test_end() {
+ String testPattern = "(abb)";
+ String testString = "cccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+ int start = 3;
+ int end = 6;
+ int j;
+
+ for (j = 0; j < 3; j++) {
+ while (mat.find()) {
+ assertEquals("Start is wrong", end, mat.end());
+
+ start = end;
+ end += 3;
+ }
+ }
+ }
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies groupCount() method.",
+ method = "groupCount",
+ args = {}
+ )
+ public void testGroupCount() {
+ for (int i = 0; i < groupPatterns.length; i++) {
+ Pattern test = Pattern.compile(groupPatterns[i]);
+ Matcher mat = test.matcher("ababababbaaabb");
+ mat.matches();
+ assertEquals(i + 1, mat.groupCount());
+ }
+ }
+
+
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "region",
+ args = {int.class, int.class}
+ )
+ public void testRegion() {
+ Pattern p = Pattern.compile("abba");
+ Matcher m = p.matcher("Gabba gabba hey");
+
+ m.region(0, 15);
+ assertTrue(m.find());
+ assertTrue(m.find());
+ assertFalse(m.find());
+
+ m.region(5, 15);
+ assertTrue(m.find());
+ assertFalse(m.find());
+
+ m.region(10, 15);
+ assertFalse(m.find());
+
+ Throwable t = null;
+
+ try {
+ m.region(-1, 15);
+ } catch (IllegalArgumentException e) {
+ t = e;
+ }
+ assertNotNull(t);
+
+ t = null;
+ try {
+ m.region(0, 16);
+ } catch (IllegalArgumentException e) {
+ t = e;
+ }
+ assertNotNull(t);
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods for specific pattern.",
+ method = "matches",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods for specific pattern.",
+ method = "group",
+ args = {int.class}
+ )
+ })
+ public void testRelactantQuantifiers() {
+ Pattern pat = Pattern.compile("(ab*)*b");
+ Matcher mat = pat.matcher("abbbb");
+
+ if (mat.matches()) {
+ assertEquals("abbb", mat.group(1));
+ } else {
+ fail("Match expected: (ab*)*b vs abbbb");
+ }
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies find() method.",
+ method = "find",
+ args = {}
+ )
+ public void testEnhancedFind() {
+ String input = "foob";
+ String pattern = "a*b";
+ Pattern pat = Pattern.compile(pattern);
+ Matcher mat = pat.matcher(input);
+
+ mat.find();
+ assertEquals("b", mat.group());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches method for input sequence specified by URL.",
+ method = "matches",
+ args = {}
+ )
+ public void testMatchesURI() {
+ Pattern pat = Pattern.
+ compile("^(//([^/?#]*))?([^?#]*)(\\?([^#]*))?(#(.*))?");
+ Matcher mat = pat
+ .matcher("file:/c:/workspace/api/build.win32/classes/META-INF/"
+ + "services/javax.xml.parsers.DocumentBuilderFactory");
+ assertTrue(mat.matches());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() method for composite pattern groups.",
+ method = "matches",
+ args = {}
+ )
+ public void testPosCompositeGroup() {
+ String[] posExamples = { "aabbcc", "aacc", "bbaabbcc" };
+ String[] negExamples = { "aabb", "bb", "bbaabb" };
+ Pattern posPat = Pattern.compile("(aa|bb){1,3}+cc");
+ Pattern negPat = Pattern.compile("(aa|bb){1,3}+bb");
+
+ Matcher mat;
+ for (String element : posExamples) {
+ mat = posPat.matcher(element);
+ assertTrue(mat.matches());
+ }
+
+ for (String element : negExamples) {
+ mat = negPat.matcher(element);
+ assertFalse(mat.matches());
+ }
+
+ assertTrue(Pattern.matches("(aa|bb){1,3}+bb", "aabbaabb"));
+
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() method for specific patterns.",
+ method = "matches",
+ args = {}
+ )
+ public void testPosAltGroup() {
+ String[] posExamples = { "aacc", "bbcc", "cc" };
+ String[] negExamples = { "bb", "aa" };
+ Pattern posPat = Pattern.compile("(aa|bb)?+cc");
+ Pattern negPat = Pattern.compile("(aa|bb)?+bb");
+
+ Matcher mat;
+ for (String element : posExamples) {
+ mat = posPat.matcher(element);
+ assertTrue(posPat.toString() + " vs: " + element, mat.matches());
+ }
+
+ for (String element : negExamples) {
+ mat = negPat.matcher(element);
+ assertFalse(mat.matches());
+ }
+
+ assertTrue(Pattern.matches("(aa|bb)?+bb", "aabb"));
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods for specific pattern.",
+ method = "matches",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods for specific pattern.",
+ method = "group",
+ args = {int.class}
+ )
+ })
+ public void testRelCompGroup() {
+
+ Matcher mat;
+ Pattern pat;
+ String res = "";
+ for (int i = 0; i < 4; i++) {
+ pat = Pattern.compile("((aa|bb){" + i + ",3}?).*cc");
+ mat = pat.matcher("aaaaaacc");
+ assertTrue(pat.toString() + " vs: " + "aaaaaacc", mat.matches());
+ assertEquals(res, mat.group(1));
+ res += "aa";
+ }
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods for specific pattern.",
+ method = "matches",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods for specific pattern.",
+ method = "group",
+ args = {int.class}
+ )
+ })
+ public void testRelAltGroup() {
+
+ Matcher mat;
+ Pattern pat;
+
+ pat = Pattern.compile("((aa|bb)??).*cc");
+ mat = pat.matcher("aacc");
+ assertTrue(pat.toString() + " vs: " + "aacc", mat.matches());
+ assertEquals("", mat.group(1));
+
+ pat = Pattern.compile("((aa|bb)??)cc");
+ mat = pat.matcher("aacc");
+ assertTrue(pat.toString() + " vs: " + "aacc", mat.matches());
+ assertEquals("aa", mat.group(1));
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() method for case insensitive pattern.",
+ method = "matches",
+ args = {}
+ )
+ public void testIgnoreCase() {
+ Pattern pat = Pattern.compile("(aa|bb)*", Pattern.CASE_INSENSITIVE);
+ Matcher mat = pat.matcher("aAbb");
+
+ assertTrue(mat.matches());
+
+ pat = Pattern.compile("(a|b|c|d|e)*", Pattern.CASE_INSENSITIVE);
+ mat = pat.matcher("aAebbAEaEdebbedEccEdebbedEaedaebEbdCCdbBDcdcdADa");
+ assertTrue(mat.matches());
+
+ pat = Pattern.compile("[a-e]*", Pattern.CASE_INSENSITIVE);
+ mat = pat.matcher("aAebbAEaEdebbedEccEdebbedEaedaebEbdCCdbBDcdcdADa");
+ assertTrue(mat.matches());
+
+ }
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "quoteReplacement",
+ args = {java.lang.String.class}
+ )
+ public void testQuoteReplacement() {
+ assertEquals("\\$dollar and slash\\\\", Matcher.quoteReplacement("$dollar and slash\\"));
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods.",
+ method = "matches",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() and group(int group) methods.",
+ method = "group",
+ args = {int.class}
+ )
+ })
+ public void testOverFlow() {
+ Pattern tp = Pattern.compile("(a*)*");
+ Matcher tm = tp.matcher("aaa");
+ assertTrue(tm.matches());
+ assertEquals("", tm.group(1));
+
+ assertTrue(Pattern.matches("(1+)\\1+", "11"));
+ assertTrue(Pattern.matches("(1+)(2*)\\2+", "11"));
+
+ Pattern pat = Pattern.compile("(1+)\\1*");
+ Matcher mat = pat.matcher("11");
+
+ assertTrue(mat.matches());
+ assertEquals("11", mat.group(1));
+
+ pat = Pattern.compile("((1+)|(2+))(\\2+)");
+ mat = pat.matcher("11");
+
+ assertTrue(mat.matches());
+ assertEquals("1", mat.group(2));
+ assertEquals("1", mat.group(1));
+ assertEquals("1", mat.group(4));
+ assertNull(mat.group(3));
+
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "",
+ method = "matches",
+ args = {}
+ )
+ public void testUnicode() {
+
+ assertTrue(Pattern.compile("\\x61a").matcher("aa").matches());
+// assertTrue(Pattern.matches("\\u0061a", "aa"));
+ assertTrue(Pattern.compile("\\0141a").matcher("aa").matches());
+ assertTrue(Pattern.compile("\\0777").matcher("?7").matches());
+
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "",
+ method = "matches",
+ args = {}
+ )
+ public void testUnicodeCategory() {
+ assertTrue(Pattern.compile("\\p{Ll}").matcher("k").matches()); // Unicode lower case
+ assertTrue(Pattern.compile("\\P{Ll}").matcher("K").matches()); // Unicode non-lower
+ // case
+ assertTrue(Pattern.compile("\\p{Lu}").matcher("K").matches()); // Unicode upper case
+ assertTrue(Pattern.compile("\\P{Lu}").matcher("k").matches()); // Unicode non-upper
+ // case
+ // combinations
+ assertTrue(Pattern.compile("[\\p{L}&&[^\\p{Lu}]]").matcher("k").matches());
+ assertTrue(Pattern.compile("[\\p{L}&&[^\\p{Ll}]]").matcher("K").matches());
+ assertFalse(Pattern.compile("[\\p{L}&&[^\\p{Lu}]]").matcher("K").matches());
+ assertFalse(Pattern.compile("[\\p{L}&&[^\\p{Ll}]]").matcher("k").matches());
+
+ // category/character combinations
+ assertFalse(Pattern.compile("[\\p{L}&&[^a-z]]").matcher("k").matches());
+ assertTrue(Pattern.compile("[\\p{L}&&[^a-z]]").matcher("K").matches());
+
+ assertTrue(Pattern.compile("[\\p{Lu}a-z]").matcher("k").matches());
+ assertTrue(Pattern.compile("[a-z\\p{Lu}]").matcher("k").matches());
+
+ assertFalse(Pattern.compile("[\\p{Lu}a-d]").matcher("k").matches());
+ assertTrue(Pattern.compile("[a-d\\p{Lu}]").matcher("K").matches());
+
+ // assertTrue(Pattern.matches("[\\p{L}&&[^\\p{Lu}&&[^K]]]", "K"));
+ assertFalse(Pattern.compile("[\\p{L}&&[^\\p{Lu}&&[^G]]]").matcher("K").matches());
+
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies that find() method works correctly with $ pattern.",
+ method = "find",
+ args = {}
+ )
+ public void testFindDollar() {
+ Matcher mat = Pattern.compile("a$").matcher("a\n");
+ assertTrue(mat.find());
+ assertEquals("a", mat.group());
+ }
+
+ /*
+ * Verify if the Matcher can match the input when region is changed
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches() method for the specified region.",
+ method = "matches",
+ args = {}
+ )
+ public void testMatchesRegionChanged() {
+ // Regression for HARMONY-610
+ String input = " word ";
+ Pattern pattern = Pattern.compile("\\w+");
+ Matcher matcher = pattern.matcher(input);
+ matcher.region(1, 5);
+ assertTrue(matcher.matches());
+ }
+
+ // BEGIN android-note
+ // Test took ages, now going in steps of 16 code points to speed things up.
+ // END android-note
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The stress test for matches(String regex) method from String class.",
+ clazz = String.class,
+ method = "matches",
+ args = {java.lang.String.class}
+ )
+ public void testAllCodePoints() {
+ // Regression for HARMONY-3145
+ int[] codePoint = new int[1];
+ Pattern p = Pattern.compile("(\\p{all})+");
+ boolean res = true;
+ int cnt = 0;
+ String s;
+ for (int i = 0; i < 0x110000; i = i + 0x10) {
+ codePoint[0] = i;
+ s = new String(codePoint, 0, 1);
+ if (!s.matches(p.toString())) {
+ cnt++;
+ res = false;
+ }
+ }
+ assertTrue(res);
+ assertEquals(0, cnt);
+
+ p = Pattern.compile("(\\P{all})+");
+ res = true;
+ cnt = 0;
+
+ for (int i = 0; i < 0x110000; i = i + 0x10) {
+ codePoint[0] = i;
+ s = new String(codePoint, 0, 1);
+ if (!s.matches(p.toString())) {
+ cnt++;
+ res = false;
+ }
+ }
+
+ assertFalse(res);
+ assertEquals(0x110000 / 0x10, cnt);
+ }
+
+ /*
+ * Verify if the Matcher behaves correct when region is changed
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies find() method for specified region in positive case.",
+ method = "find",
+ args = {}
+ )
+ public void testFindRegionChanged() {
+ // Regression for HARMONY-625
+ Pattern pattern = Pattern.compile("(?s).*");
+ Matcher matcher = pattern.matcher("abcde");
+ matcher.find();
+ assertEquals("abcde", matcher.group());
+
+ matcher = pattern.matcher("abcde");
+ matcher.region(0, 2);
+ matcher.find();
+ assertEquals("ab", matcher.group());
+
+ }
+
+ /*
+ * Verify if the Matcher behaves correct with pattern "c" when region is
+ * changed
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies find() method for specified region in negative case.",
+ method = "find",
+ args = {}
+ )
+ public void testFindRegionChanged2() {
+ // Regression for HARMONY-713
+ Pattern pattern = Pattern.compile("c");
+
+ String inputStr = "aabb.c";
+ Matcher matcher = pattern.matcher(inputStr);
+ matcher.region(0, 3);
+
+ assertFalse(matcher.find());
+ }
+
+ /**
+ * @test java.util.regex.Matcher#regionStart()
+ * test regionStart() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies the regionStart() method.",
+ method = "regionStart",
+ args = {}
+ )
+ public void test_regionStart() {
+ String testPattern = "(abb)";
+ String testString = "cccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ assertEquals("Region sould start from 0 position", 0, mat.regionStart());
+ mat.region(1, 10);
+ assertEquals("Region sould start from 1 position after setting new region", 1, mat.regionStart());
+ mat.reset();
+ assertEquals("Region sould start from 0 position after reset", 0, mat.regionStart());
+ }
+
+ /**
+ * @test java.util.regex.Matcher#regionEnd()
+ * test regionEnd() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies the regionEnd() method.",
+ method = "regionEnd",
+ args = {}
+ )
+ public void test_regionEnd() {
+ String testPattern = "(abb)";
+ String testString = "cccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ assertEquals("Region end value should be equal to string length", testString.length(), mat.regionEnd());
+ mat.region(1, 10);
+ assertEquals("Region end value should be equal to 10 after setting new region", 10, mat.regionEnd());
+ mat.reset();
+ assertEquals("Region end value should be equal to string length after reset", testString.length(), mat.regionEnd());
+ }
+
+ /**
+ * @test java.util.regex.Matcher#toMatchResult()
+ * test toMatchResult() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies the toMatchResult method.",
+ method = "toMatchResult",
+ args = {}
+ )
+ public void test_toMatchResult() {
+ String testPattern = "(((abb)a)(bb))";
+ String testString = "babbabbcccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ mat.region(1, 7);
+ assertTrue("matcher should find pattern in given region", mat.matches());
+ assertEquals("matched section should start from 1 position", 1, mat.toMatchResult().start());
+ assertEquals("matched section for 2 group should start from 1 position", 1, mat.toMatchResult().start(2));
+ assertEquals("matched section for whole pattern should end on 7 position", 7, mat.toMatchResult().end());
+ assertEquals("matched section for 3 group should end at 4 position", 4, mat.toMatchResult().end(3));
+ assertEquals("group not matched", "abbabb", mat.toMatchResult().group());
+ assertEquals("3 group not matched", "abb", mat.toMatchResult().group(3));
+ assertEquals("Total number of groups does not matched with given pattern", 4, mat.toMatchResult().groupCount());
+ }
+
+ /**
+ * @test java.util.regex.Matcher#usePattern(Pattern newPattern)
+ * test usePattern(Pattern newPattern) method.
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the usePattern(Pattern newPattern) method.",
+ method = "usePattern",
+ args = {java.util.regex.Pattern.class}
+ )
+ public void test_usePatternLjava_util_regex_Pattern() {
+ String testPattern1 = "(((abb)a)(bb))";
+ String testPattern2 = "(abbabb)";
+ String testPattern3 = "(babb)";
+ String testString = "babbabbcccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern1);
+ Matcher mat = pat.matcher(testString);
+
+ mat.region(1, 7);
+ assertTrue("matcher should find pattern in given region in case of groupe in pattern", mat.matches());
+ assertEquals("", mat, mat.usePattern(Pattern.compile(testPattern2)));
+ assertTrue("matcher should find pattern in given region", mat.matches());
+ assertEquals("", mat, mat.usePattern(Pattern.compile(testPattern3)));
+ assertFalse("matcher should not find pattern in given region", mat.matches());
+ }
+
+ /**
+ * @test java.util.regex.Matcher#useAchoringBounds()
+ * test useAchoringBounds() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "useAnchoringBounds",
+ args = {boolean.class}
+ )
+ public void test_anchoringBounds() {
+ String testPattern = "^ro$";
+ String testString = "android";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ mat.region(2, 5);
+ mat.useAnchoringBounds(false);
+ assertFalse("Shouldn't find pattern with non-anchoring bounds", mat.find(0));
+
+ mat.region(2, 5);
+ mat.useAnchoringBounds(true);
+ assertFalse("Should find pattern with anchoring bounds", mat.find(0));
+ }
+
+ /**
+ * @test java.util.regex.Matcher#useTransparentBounds()
+ * test useTransparentBounds() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies the useTransparentBounds(boolean b) method.",
+ method = "useTransparentBounds",
+ args = {boolean.class}
+ )
+ public void test_transparentBounds() {
+ String testPattern = "and(?=roid)";
+ String testString = "android";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ mat.region(0, 3);
+ mat.useTransparentBounds(false);
+ assertFalse("Shouldn't find pattern with opaque bounds", mat.matches());
+
+ mat.useTransparentBounds(true);
+ assertTrue("Should find pattern transparent bounds", mat.matches()); // ***
+
+ testPattern = "and(?!roid)";
+ testString = "android";
+ pat = Pattern.compile(testPattern);
+ mat = pat.matcher(testString);
+
+ mat.region(0, 3);
+ mat.useTransparentBounds(false);
+ assertTrue("Should find pattern with opaque bounds", mat.matches());
+
+ mat.useTransparentBounds(true);
+ assertFalse("Shouldn't find pattern transparent bounds", mat.matches()); // ***
+ }
+
+ /**
+ * @test java.util.regex.Matcher#hitEnd()
+ * test hitEnd() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies that hitEnd() method returns correct value. ",
+ method = "hitEnd",
+ args = {}
+ )
+ public void test_hitEnd() {
+ String testPattern = "abb";
+ String testString = "babbabbcccabbabbabbabbabb";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ while (mat.find()) {
+ assertFalse("hitEnd should return false during parsing input", mat.hitEnd());
+ }
+ assertTrue("hitEnd should return true after finding last match", mat.hitEnd()); // ***
+ }
+
+ /**
+ * @test java.util.regex.Matcher#requireEnd()
+ * test requireEnd() method.
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies the requireEnd() method.",
+ method = "requireEnd",
+ args = {}
+ )
+ public void test_requireEnd() {
+ String testPattern = "bba";
+ String testString = "abbbbba";
+ Pattern pat = Pattern.compile(testPattern);
+ Matcher mat = pat.matcher(testString);
+
+ assertTrue(mat.find());
+ assertFalse(mat.requireEnd());
+
+ testPattern = "bba$";
+ testString = "abbbbba";
+ pat = Pattern.compile(testPattern);
+ mat = pat.matcher(testString);
+
+ assertTrue(mat.find());
+ assertTrue(mat.requireEnd());
+ }
+
+ /*
+ * Regression test for HARMONY-674
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Special regression test for matches() method.",
+ method = "matches",
+ args = {}
+ )
+ public void testPatternMatcher() throws Exception {
+ Pattern pattern = Pattern.compile("(?:\\d+)(?:pt)");
+ assertTrue(pattern.matcher("14pt").matches());
+ }
+
+ public static void main(String[] args) {
+ junit.textui.TestRunner.run(MatcherTest.class);
+ }
+
+}
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/ModeTest.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/ModeTest.java
new file mode 100644
index 0000000..bad03f7
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/ModeTest.java
@@ -0,0 +1,150 @@
+/* Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import dalvik.annotation.TestTargetClass;
+import dalvik.annotation.TestTargets;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestLevel;
+
+import junit.framework.TestCase;
+import java.util.regex.Pattern;
+import java.util.regex.Matcher;
+import java.util.regex.PatternSyntaxException;
+
+/**
+ * Tests Pattern compilation modes and modes triggered in pattern strings
+ *
+ */
+@TestTargetClass(Pattern.class)
+public class ModeTest extends TestCase {
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies compile(String regex) and compile(String regex, int flags) methods with Pattern.CASE_INSENSITIVE mode.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies compile(String regex) and compile(String regex, int flags) methods with Pattern.CASE_INSENSITIVE mode.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ )
+ })
+ public void testCase() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+
+ p = Pattern.compile("([a-z]+)[0-9]+");
+ m = p.matcher("cAT123#dog345");
+ assertTrue(m.find());
+ assertEquals("dog", m.group(1));
+ assertFalse(m.find());
+
+
+ p = Pattern.compile("([a-z]+)[0-9]+", Pattern.CASE_INSENSITIVE);
+ m = p.matcher("cAt123#doG345");
+ assertTrue(m.find());
+ assertEquals("cAt", m.group(1));
+ assertTrue(m.find());
+ assertEquals("doG", m.group(1));
+ assertFalse(m.find());
+
+
+ p = Pattern.compile("(?i)([a-z]+)[0-9]+");
+ m = p.matcher("cAt123#doG345");
+ assertTrue(m.find());
+ assertEquals("cAt", m.group(1));
+ assertTrue(m.find());
+ assertEquals("doG", m.group(1));
+ assertFalse(m.find());
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies compile(String regex) and compile(String regex, int flags) methods with Pattern.MULTILINE mode.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies compile(String regex) and compile(String regex, int flags) methods with Pattern.MULTILINE mode.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ )
+ })
+ public void testMultiline() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+
+ p = Pattern.compile("^foo");
+ m = p.matcher("foobar");
+ assertTrue(m.find());
+ assertTrue(m.start() == 0 && m.end() == 3);
+ assertFalse(m.find());
+
+ m = p.matcher("barfoo");
+ assertFalse(m.find());
+
+
+ p = Pattern.compile("foo$");
+ m = p.matcher("foobar");
+ assertFalse(m.find());
+
+ m = p.matcher("barfoo");
+ assertTrue(m.find());
+ assertTrue(m.start() == 3 && m.end() == 6);
+ assertFalse(m.find());
+
+
+ p = Pattern.compile("^foo([0-9]*)", Pattern.MULTILINE);
+ m = p.matcher("foo1bar\nfoo2foo3\nbarfoo4");
+ assertTrue(m.find());
+ assertEquals("1", m.group(1));
+ assertTrue(m.find());
+ assertEquals("2", m.group(1));
+ assertFalse(m.find());
+
+
+ p = Pattern.compile("foo([0-9]*)$", Pattern.MULTILINE);
+ m = p.matcher("foo1bar\nfoo2foo3\nbarfoo4");
+ assertTrue(m.find());
+ assertEquals("3", m.group(1));
+ assertTrue(m.find());
+ assertEquals("4", m.group(1));
+ assertFalse(m.find());
+
+
+ p = Pattern.compile("(?m)^foo([0-9]*)");
+ m = p.matcher("foo1bar\nfoo2foo3\nbarfoo4");
+ assertTrue(m.find());
+ assertEquals("1", m.group(1));
+ assertTrue(m.find());
+ assertEquals("2", m.group(1));
+ assertFalse(m.find());
+
+ p = Pattern.compile("(?m)foo([0-9]*)$");
+ m = p.matcher("foo1bar\nfoo2foo3\nbarfoo4");
+ assertTrue(m.find());
+ assertEquals("3", m.group(1));
+ assertTrue(m.find());
+ assertEquals("4", m.group(1));
+ assertFalse(m.find());
+ }
+}
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/Pattern2Test.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/Pattern2Test.java
new file mode 100644
index 0000000..10d2534
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/Pattern2Test.java
@@ -0,0 +1,1611 @@
+/* Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import dalvik.annotation.BrokenTest;
+import dalvik.annotation.TestTargetClass;
+import dalvik.annotation.TestTargets;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestLevel;
+
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+import java.util.regex.PatternSyntaxException;
+
+import junit.framework.TestCase;
+@TestTargetClass(Pattern.class)
+/**
+ * Tests simple Pattern compilation and Matcher methods
+ *
+ */
+public class Pattern2Test extends TestCase {
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matches(String regex, CharSequence input) method.",
+ method = "matches",
+ args = {java.lang.String.class, java.lang.CharSequence.class}
+ )
+ public void testSimpleMatch() throws PatternSyntaxException {
+ Pattern p = Pattern.compile("foo.*");
+
+ Matcher m1 = p.matcher("foo123");
+ assertTrue(m1.matches());
+ assertTrue(m1.find(0));
+ assertTrue(m1.lookingAt());
+
+ Matcher m2 = p.matcher("fox");
+ assertFalse(m2.matches());
+ assertFalse(m2.find(0));
+ assertFalse(m2.lookingAt());
+
+ assertTrue(Pattern.matches("foo.*", "foo123"));
+ assertFalse(Pattern.matches("foo.*", "fox"));
+
+ assertFalse(Pattern.matches("bar", "foobar"));
+
+ assertTrue(Pattern.matches("", ""));
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testCursors() {
+ Pattern p;
+ Matcher m;
+
+ try {
+ p = Pattern.compile("foo");
+
+ m = p.matcher("foobar");
+ assertTrue(m.find());
+ assertEquals(0, m.start());
+ assertEquals(3, m.end());
+ assertFalse(m.find());
+
+ // Note: also testing reset here
+ m.reset();
+ assertTrue(m.find());
+ assertEquals(0, m.start());
+ assertEquals(3, m.end());
+ assertFalse(m.find());
+
+ m.reset("barfoobar");
+ assertTrue(m.find());
+ assertEquals(3, m.start());
+ assertEquals(6, m.end());
+ assertFalse(m.find());
+
+ m.reset("barfoo");
+ assertTrue(m.find());
+ assertEquals(3, m.start());
+ assertEquals(6, m.end());
+ assertFalse(m.find());
+
+ m.reset("foobarfoobarfoo");
+ assertTrue(m.find());
+ assertEquals(0, m.start());
+ assertEquals(3, m.end());
+ assertTrue(m.find());
+ assertEquals(6, m.start());
+ assertEquals(9, m.end());
+ assertTrue(m.find());
+ assertEquals(12, m.start());
+ assertEquals(15, m.end());
+ assertFalse(m.find());
+ assertTrue(m.find(0));
+ assertEquals(0, m.start());
+ assertEquals(3, m.end());
+ assertTrue(m.find(4));
+ assertEquals(6, m.start());
+ assertEquals(9, m.end());
+ } catch (PatternSyntaxException e) {
+ System.out.println(e.getMessage());
+ fail();
+ }
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testGroups() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+
+ p = Pattern.compile("(p[0-9]*)#?(q[0-9]*)");
+
+ m = p.matcher("p1#q3p2q42p5p71p63#q888");
+ assertTrue(m.find());
+ assertEquals(0, m.start());
+ assertEquals(5, m.end());
+ assertEquals(2, m.groupCount());
+ assertEquals(0, m.start(0));
+ assertEquals(5, m.end(0));
+ assertEquals(0, m.start(1));
+ assertEquals(2, m.end(1));
+ assertEquals(3, m.start(2));
+ assertEquals(5, m.end(2));
+ assertEquals("p1#q3", m.group());
+ assertEquals("p1#q3", m.group(0));
+ assertEquals("p1", m.group(1));
+ assertEquals("q3", m.group(2));
+
+ assertTrue(m.find());
+ assertEquals(5, m.start());
+ assertEquals(10, m.end());
+ assertEquals(2, m.groupCount());
+ assertEquals(10, m.end(0));
+ assertEquals(5, m.start(1));
+ assertEquals(7, m.end(1));
+ assertEquals(7, m.start(2));
+ assertEquals(10, m.end(2));
+ assertEquals("p2q42", m.group());
+ assertEquals("p2q42", m.group(0));
+ assertEquals("p2", m.group(1));
+ assertEquals("q42", m.group(2));
+
+ assertTrue(m.find());
+ assertEquals(15, m.start());
+ assertEquals(23, m.end());
+ assertEquals(2, m.groupCount());
+ assertEquals(15, m.start(0));
+ assertEquals(23, m.end(0));
+ assertEquals(15, m.start(1));
+ assertEquals(18, m.end(1));
+ assertEquals(19, m.start(2));
+ assertEquals(23, m.end(2));
+ assertEquals("p63#q888", m.group());
+ assertEquals("p63#q888", m.group(0));
+ assertEquals("p63", m.group(1));
+ assertEquals("q888", m.group(2));
+ assertFalse(m.find());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testReplace() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+
+ // Note: examples from book,
+ // Hitchens, Ron, 2002, "Java NIO", O'Reilly, page 171
+ p = Pattern.compile("a*b");
+
+ m = p.matcher("aabfooaabfooabfoob");
+ assertTrue(m.replaceAll("-").equals("-foo-foo-foo-"));
+ assertTrue(m.replaceFirst("-").equals("-fooaabfooabfoob"));
+
+ /*
+ * p = Pattern.compile ("\\p{Blank}");
+ *
+ * m = p.matcher ("fee fie foe fum"); assertTrue
+ * (m.replaceFirst("-").equals ("fee-fie foe fum")); assertTrue
+ * (m.replaceAll("-").equals ("fee-fie-foe-fum"));
+ */
+
+ p = Pattern.compile("([bB])yte");
+
+ m = p.matcher("Byte for byte");
+ assertTrue(m.replaceFirst("$1ite").equals("Bite for byte"));
+ assertTrue(m.replaceAll("$1ite").equals("Bite for bite"));
+
+ p = Pattern.compile("\\d\\d\\d\\d([- ])");
+
+ m = p.matcher("card #1234-5678-1234");
+ assertTrue(m.replaceFirst("xxxx$1").equals("card #xxxx-5678-1234"));
+ assertTrue(m.replaceAll("xxxx$1").equals("card #xxxx-xxxx-1234"));
+
+ p = Pattern.compile("(up|left)( *)(right|down)");
+
+ m = p.matcher("left right, up down");
+ assertTrue(m.replaceFirst("$3$2$1").equals("right left, up down"));
+ assertTrue(m.replaceAll("$3$2$1").equals("right left, down up"));
+
+ p = Pattern.compile("([CcPp][hl]e[ea]se)");
+
+ m = p.matcher("I want cheese. Please.");
+ assertTrue(m.replaceFirst("<b> $1 </b>").equals(
+ "I want <b> cheese </b>. Please."));
+ assertTrue(m.replaceAll("<b> $1 </b>").equals(
+ "I want <b> cheese </b>. <b> Please </b>."));
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testEscapes() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+
+ // Test \\ sequence
+ p = Pattern.compile("([a-z]+)\\\\([a-z]+);");
+ m = p.matcher("fred\\ginger;abbott\\costello;jekell\\hyde;");
+ assertTrue(m.find());
+ assertEquals("fred", m.group(1));
+ assertEquals("ginger", m.group(2));
+ assertTrue(m.find());
+ assertEquals("abbott", m.group(1));
+ assertEquals("costello", m.group(2));
+ assertTrue(m.find());
+ assertEquals("jekell", m.group(1));
+ assertEquals("hyde", m.group(2));
+ assertFalse(m.find());
+
+ // Test \n, \t, \r, \f, \e, \a sequences
+ p = Pattern.compile("([a-z]+)[\\n\\t\\r\\f\\e\\a]+([a-z]+)");
+ m = p.matcher("aa\nbb;cc\u0009\rdd;ee\u000C\u001Bff;gg\n\u0007hh");
+ assertTrue(m.find());
+ assertEquals("aa", m.group(1));
+ assertEquals("bb", m.group(2));
+ assertTrue(m.find());
+ assertEquals("cc", m.group(1));
+ assertEquals("dd", m.group(2));
+ assertTrue(m.find());
+ assertEquals("ee", m.group(1));
+ assertEquals("ff", m.group(2));
+ assertTrue(m.find());
+ assertEquals("gg", m.group(1));
+ assertEquals("hh", m.group(2));
+ assertFalse(m.find());
+
+ // Test \\u and \\x sequences
+/* p = Pattern.compile("([0-9]+)[\\u0020:\\x21];");
+ m = p.matcher("11:;22 ;33-;44!;");
+ assertTrue(m.find());
+ assertEquals("11", m.group(1));
+ assertTrue(m.find());
+ assertEquals("22", m.group(1));
+ assertTrue(m.find());
+ assertEquals("44", m.group(1));
+ assertFalse(m.find());
+*/
+ // Test invalid unicode sequences
+/* try {
+ p = Pattern.compile("\\u");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\u;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\u002");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\u002;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ // Test invalid hex sequences
+ try {
+ p = Pattern.compile("\\x");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\x;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\xa");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\xa;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+*/
+ // Test \0 (octal) sequences (1, 2 and 3 digit)
+ p = Pattern.compile("([0-9]+)[\\07\\040\\0160];");
+ m = p.matcher("11\u0007;22:;33 ;44p;");
+ assertTrue(m.find());
+ assertEquals("11", m.group(1));
+ assertTrue(m.find());
+ assertEquals("33", m.group(1));
+ assertTrue(m.find());
+ assertEquals("44", m.group(1));
+ assertFalse(m.find());
+
+ // Test invalid octal sequences
+ try {
+ p = Pattern.compile("\\08");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ //originally contributed test did not check the result
+ //TODO: check what RI does here
+// try {
+// p = Pattern.compile("\\0477");
+// fail("PatternSyntaxException expected");
+// } catch (PatternSyntaxException e) {
+// }
+
+ try {
+ p = Pattern.compile("\\0");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\0;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+
+ // Test \c (control character) sequence
+ p = Pattern.compile("([0-9]+)[\\cA\\cB\\cC\\cD];");
+ m = p.matcher("11\u0001;22:;33\u0002;44p;55\u0003;66\u0004;");
+ assertTrue(m.find());
+ assertEquals("11", m.group(1));
+ assertTrue(m.find());
+ assertEquals("33", m.group(1));
+ assertTrue(m.find());
+ assertEquals("55", m.group(1));
+ assertTrue(m.find());
+ assertEquals("66", m.group(1));
+ assertFalse(m.find());
+
+ // More thorough control escape test
+ // Ensure that each escape matches exactly the corresponding
+ // character
+ // code and no others (well, from 0-255 at least)
+ int i, j;
+ for (i = 0; i < 26; i++) {
+ p = Pattern.compile("\\c" + Character.toString((char) ('A' + i)));
+ int match_char = -1;
+ for (j = 0; j < 255; j++) {
+ m = p.matcher(Character.toString((char) j));
+ if (m.matches()) {
+ assertEquals(-1, match_char);
+ match_char = j;
+ }
+ }
+ assertTrue(match_char == i + 1);
+ }
+
+ // Test invalid control escapes
+// BEGIN android-removed
+// ICU doesn't complain about illegal control sequences
+// try {
+// p = Pattern.compile("\\c");
+// fail("PatternSyntaxException expected");
+// } catch (PatternSyntaxException e) {
+// }
+// END android-removed
+
+ //originally contributed test did not check the result
+ //TODO: check what RI does here
+// try {
+// p = Pattern.compile("\\c;");
+// fail("PatternSyntaxException expected");
+// } catch (PatternSyntaxException e) {
+// }
+//
+// try {
+// p = Pattern.compile("\\ca;");
+// fail("PatternSyntaxException expected");
+// } catch (PatternSyntaxException e) {
+// }
+//
+// try {
+// p = Pattern.compile("\\c4;");
+// fail("PatternSyntaxException expected");
+// } catch (PatternSyntaxException e) {
+// }
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies patterns with different ranges of characters.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies patterns with different ranges of characters.",
+ method = "matcher",
+ args = {CharSequence.class}
+ )
+ })
+ public void testCharacterClasses() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+
+ // Test one character range
+ p = Pattern.compile("[p].*[l]");
+ m = p.matcher("paul");
+ assertTrue(m.matches());
+ m = p.matcher("pool");
+ assertTrue(m.matches());
+ m = p.matcher("pong");
+ assertFalse(m.matches());
+ m = p.matcher("pl");
+ assertTrue(m.matches());
+
+ // Test two character range
+ p = Pattern.compile("[pm].*[lp]");
+ m = p.matcher("prop");
+ assertTrue(m.matches());
+ m = p.matcher("mall");
+ assertTrue(m.matches());
+ m = p.matcher("pong");
+ assertFalse(m.matches());
+ m = p.matcher("pill");
+ assertTrue(m.matches());
+
+ // Test range including [ and ]
+ p = Pattern.compile("[<\\[].*[\\]>]");
+ m = p.matcher("<foo>");
+ assertTrue(m.matches());
+ m = p.matcher("[bar]");
+ assertTrue(m.matches());
+ m = p.matcher("{foobar]");
+ assertFalse(m.matches());
+ m = p.matcher("<pill]");
+ assertTrue(m.matches());
+
+ // Test range using ^
+ p = Pattern.compile("[^bc][a-z]+[tr]");
+ m = p.matcher("pat");
+ assertTrue(m.matches());
+ m = p.matcher("liar");
+ assertTrue(m.matches());
+ m = p.matcher("car");
+ assertFalse(m.matches());
+ m = p.matcher("gnat");
+ assertTrue(m.matches());
+
+ // Test character range using -
+ p = Pattern.compile("[a-z]_+[a-zA-Z]-+[0-9p-z]");
+ m = p.matcher("d__F-8");
+ assertTrue(m.matches());
+ m = p.matcher("c_a-q");
+ assertTrue(m.matches());
+ m = p.matcher("a__R-a");
+ assertFalse(m.matches());
+ m = p.matcher("r_____d-----5");
+ assertTrue(m.matches());
+
+ // Test range using unicode characters and unicode and hex escapes
+ p = Pattern.compile("[\\u1234-\\u2345]_+[a-z]-+[\u0001-\\x11]");
+ m = p.matcher("\u2000_q-\u0007");
+ assertTrue(m.matches());
+ m = p.matcher("\u1234_z-\u0001");
+ assertTrue(m.matches());
+ m = p.matcher("r_p-q");
+ assertFalse(m.matches());
+ m = p.matcher("\u2345_____d-----\n");
+ assertTrue(m.matches());
+
+// BEGIN android-removed
+// The "---" collides with ICU's "--" operator and is likely to be a user error
+// anyway, so we simply comment this one out.
+// // Test ranges including the "-" character
+// p = Pattern.compile("[\\*-/]_+[---]!+[--AP]");
+// m = p.matcher("-_-!!A");
+// assertTrue(m.matches());
+// m = p.matcher("\u002b_-!!!-");
+// assertTrue(m.matches());
+// m = p.matcher("!_-!@");
+// assertFalse(m.matches());
+// m = p.matcher(",______-!!!!!!!P");
+// assertTrue(m.matches());
+// END android-removed
+
+ // Test nested ranges
+ p = Pattern.compile("[pm[t]][a-z]+[[r]lp]");
+ m = p.matcher("prop");
+ assertTrue(m.matches());
+ m = p.matcher("tsar");
+ assertTrue(m.matches());
+ m = p.matcher("pong");
+ assertFalse(m.matches());
+ m = p.matcher("moor");
+ assertTrue(m.matches());
+
+ // Test character class intersection with &&
+ // TODO: figure out what x&&y or any class with a null intersection
+ // set (like [[a-c]&&[d-f]]) might mean. It doesn't mean "match
+ // nothing" and doesn't mean "match anything" so I'm stumped.
+ p = Pattern.compile("[[a-p]&&[g-z]]+-+[[a-z]&&q]-+[x&&[a-z]]-+");
+ m = p.matcher("h--q--x--");
+ assertTrue(m.matches());
+ m = p.matcher("hog--q-x-");
+ assertTrue(m.matches());
+ m = p.matcher("ape--q-x-");
+ assertFalse(m.matches());
+ m = p.matcher("mop--q-x----");
+ assertTrue(m.matches());
+
+ // Test error cases with &&
+// BEGIN android-removed
+// This is more of a bug, and ICU doesn't have this behavior.
+// p = Pattern.compile("[&&[xyz]]");
+// m = p.matcher("&");
+// // System.out.println(m.matches());
+// m = p.matcher("x");
+// // System.out.println(m.matches());
+// m = p.matcher("y");
+// // System.out.println(m.matches());
+// END android-removed
+ p = Pattern.compile("[[xyz]&[axy]]");
+ m = p.matcher("x");
+ // System.out.println(m.matches());
+ m = p.matcher("z");
+ // System.out.println(m.matches());
+ m = p.matcher("&");
+ // System.out.println(m.matches());
+ p = Pattern.compile("[abc[123]&&[345]def]");
+ m = p.matcher("a");
+ // System.out.println(m.matches());
+
+// BEGIN android-removed
+// This is more of a bug, and ICU doesn't have this behavior.
+// p = Pattern.compile("[[xyz]&&]");
+// END android-removed
+ p = Pattern.compile("[[abc]&]");
+
+ try {
+ p = Pattern.compile("[[abc]&&");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ p = Pattern.compile("[[abc]\\&&[xyz]]");
+
+ p = Pattern.compile("[[abc]&\\&[xyz]]");
+
+ // Test 3-way intersection
+ p = Pattern.compile("[[a-p]&&[g-z]&&[d-k]]");
+ m = p.matcher("g");
+ assertTrue(m.matches());
+ m = p.matcher("m");
+ assertFalse(m.matches());
+
+ // Test nested intersection
+ p = Pattern.compile("[[[a-p]&&[g-z]]&&[d-k]]");
+ m = p.matcher("g");
+ assertTrue(m.matches());
+ m = p.matcher("m");
+ assertFalse(m.matches());
+
+ // Test character class subtraction with && and ^
+ p = Pattern.compile("[[a-z]&&[^aeiou]][aeiou][[^xyz]&&[a-z]]");
+ m = p.matcher("pop");
+ assertTrue(m.matches());
+ m = p.matcher("tag");
+ assertTrue(m.matches());
+ m = p.matcher("eat");
+ assertFalse(m.matches());
+ m = p.matcher("tax");
+ assertFalse(m.matches());
+ m = p.matcher("zip");
+ assertTrue(m.matches());
+
+ // Test . (DOT), with and without DOTALL
+ // Note: DOT not allowed in character classes
+ p = Pattern.compile(".+/x.z");
+ m = p.matcher("!$/xyz");
+ assertTrue(m.matches());
+ m = p.matcher("%\n\r/x\nz");
+ assertFalse(m.matches());
+ p = Pattern.compile(".+/x.z", Pattern.DOTALL);
+ m = p.matcher("%\n\r/x\nz");
+ assertTrue(m.matches());
+
+ // Test \d (digit)
+ p = Pattern.compile("\\d+[a-z][\\dx]");
+ m = p.matcher("42a6");
+ assertTrue(m.matches());
+ m = p.matcher("21zx");
+ assertTrue(m.matches());
+ m = p.matcher("ab6");
+ assertFalse(m.matches());
+ m = p.matcher("56912f9");
+ assertTrue(m.matches());
+
+ // Test \D (not a digit)
+ p = Pattern.compile("\\D+[a-z]-[\\D3]");
+ m = p.matcher("za-p");
+ assertTrue(m.matches());
+ m = p.matcher("%!e-3");
+ assertTrue(m.matches());
+ m = p.matcher("9a-x");
+ assertFalse(m.matches());
+ m = p.matcher("\u1234pp\ny-3");
+ assertTrue(m.matches());
+
+ // Test \s (whitespace)
+ p = Pattern.compile("<[a-zA-Z]+\\s+[0-9]+[\\sx][^\\s]>");
+ m = p.matcher("<cat \t1\fx>");
+ assertTrue(m.matches());
+ m = p.matcher("<cat \t1\f >");
+ assertFalse(m.matches());
+ m = p
+ .matcher("xyz <foo\n\r22 5> <pp \t\n\f\r \u000b41x\u1234><pp \nx7\rc> zzz");
+ assertTrue(m.find());
+ assertTrue(m.find());
+ assertFalse(m.find());
+
+ // Test \S (not whitespace)
+ p = Pattern.compile("<[a-z] \\S[0-9][\\S\n]+[^\\S]221>");
+ m = p.matcher("<f $0**\n** 221>");
+ assertTrue(m.matches());
+ m = p.matcher("<x 441\t221>");
+ assertTrue(m.matches());
+ m = p.matcher("<z \t9\ng 221>");
+ assertFalse(m.matches());
+ m = p.matcher("<z 60\ngg\u1234\f221>");
+ assertTrue(m.matches());
+ p = Pattern.compile("<[a-z] \\S[0-9][\\S\n]+[^\\S]221[\\S&&[^abc]]>");
+ m = p.matcher("<f $0**\n** 221x>");
+ assertTrue(m.matches());
+ m = p.matcher("<x 441\t221z>");
+ assertTrue(m.matches());
+ m = p.matcher("<x 441\t221 >");
+ assertFalse(m.matches());
+ m = p.matcher("<x 441\t221c>");
+ assertFalse(m.matches());
+ m = p.matcher("<z \t9\ng 221x>");
+ assertFalse(m.matches());
+ m = p.matcher("<z 60\ngg\u1234\f221\u0001>");
+ assertTrue(m.matches());
+
+ // Test \w (ascii word)
+ p = Pattern.compile("<\\w+\\s[0-9]+;[^\\w]\\w+/[\\w$]+;");
+ m = p.matcher("<f1 99;!foo5/a$7;");
+ assertTrue(m.matches());
+ m = p.matcher("<f$ 99;!foo5/a$7;");
+ assertFalse(m.matches());
+ m = p
+ .matcher("<abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_0123456789 99;!foo5/a$7;");
+ assertTrue(m.matches());
+
+ // Test \W (not an ascii word)
+ p = Pattern.compile("<\\W\\w+\\s[0-9]+;[\\W_][^\\W]+\\s[0-9]+;");
+ m = p.matcher("<$foo3\n99;_bar\t0;");
+ assertTrue(m.matches());
+ m = p.matcher("<hh 99;_g 0;");
+ assertFalse(m.matches());
+ m = p.matcher("<*xx\t00;^zz\f11;");
+ assertTrue(m.matches());
+
+ // Test x|y pattern
+ // TODO
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for patterns with POSIX characters.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for patterns with POSIX characters.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testPOSIXGroups() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+
+ // Test POSIX groups using \p and \P (in the group and not in the group)
+ // Groups are Lower, Upper, ASCII, Alpha, Digit, XDigit, Alnum, Punct,
+ // Graph, Print, Blank, Space, Cntrl
+ // Test \p{Lower}
+ /*
+ * FIXME: Requires complex range processing
+ * p = Pattern.compile("<\\p{Lower}\\d\\P{Lower}:[\\p{Lower}Z]\\s[^\\P{Lower}]>");
+ * m = p.matcher("<a4P:g x>"); assertTrue(m.matches()); m =
+ * p.matcher("<p4%:Z\tq>"); assertTrue(m.matches()); m =
+ * p.matcher("<A6#:e e>"); assertFalse(m.matches());
+ */
+ p = Pattern.compile("\\p{Lower}+");
+ m = p.matcher("abcdefghijklmnopqrstuvwxyz");
+ assertTrue(m.matches());
+
+ // Invalid uses of \p{Lower}
+ try {
+ p = Pattern.compile("\\p");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\p;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\p{");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\p{;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\p{Lower");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\p{Lower;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ // Test \p{Upper}
+ /*
+ * FIXME: Requires complex range processing
+ * p = Pattern.compile("<\\p{Upper}\\d\\P{Upper}:[\\p{Upper}z]\\s[^\\P{Upper}]>");
+ * m = p.matcher("<A4p:G X>"); assertTrue(m.matches()); m =
+ * p.matcher("<P4%:z\tQ>"); assertTrue(m.matches()); m =
+ * p.matcher("<a6#:E E>"); assertFalse(m.matches());
+ */
+ p = Pattern.compile("\\p{Upper}+");
+ m = p.matcher("ABCDEFGHIJKLMNOPQRSTUVWXYZ");
+ assertTrue(m.matches());
+
+ // Invalid uses of \p{Upper}
+ try {
+ p = Pattern.compile("\\p{Upper");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\p{Upper;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ // Test \p{ASCII}
+ /*
+ * FIXME: Requires complex range processing p = Pattern.compile("<\\p{ASCII}\\d\\P{ASCII}:[\\p{ASCII}\u1234]\\s[^\\P{ASCII}]>");
+ * m = p.matcher("<A4\u0080:G X>"); assertTrue(m.matches()); m =
+ * p.matcher("<P4\u00ff:\u1234\t\n>"); assertTrue(m.matches()); m =
+ * p.matcher("<\u00846#:E E>"); assertFalse(m.matches())
+ */
+ int i;
+ p = Pattern.compile("\\p{ASCII}");
+ for (i = 0; i < 0x80; i++) {
+ m = p.matcher(Character.toString((char) i));
+ assertTrue(m.matches());
+ }
+ for (; i < 0xff; i++) {
+ m = p.matcher(Character.toString((char) i));
+ assertFalse(m.matches());
+ }
+
+ // Invalid uses of \p{ASCII}
+ try {
+ p = Pattern.compile("\\p{ASCII");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ try {
+ p = Pattern.compile("\\p{ASCII;");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException e) {
+ }
+
+ // Test \p{Alpha}
+ // TODO
+
+ // Test \p{Digit}
+ // TODO
+
+ // Test \p{XDigit}
+ // TODO
+
+ // Test \p{Alnum}
+ // TODO
+
+ // Test \p{Punct}
+ // TODO
+
+ // Test \p{Graph}
+ // TODO
+
+ // Test \p{Print}
+ // TODO
+
+ // Test \p{Blank}
+ // TODO
+
+ // Test \p{Space}
+ // TODO
+
+ // Test \p{Cntrl}
+ // TODO
+ }
+ @TestTargetNew(
+ level = TestLevel.ADDITIONAL,
+ notes = "TODO empty test",
+ method = "!",
+ args = {}
+ )
+ @BrokenTest("empty test")
+ public void testUnicodeCategories() throws PatternSyntaxException {
+ // Test Unicode categories using \p and \P
+ // One letter codes: L, M, N, P, S, Z, C
+ // Two letter codes: Lu, Nd, Sc, Sm, ...
+ // See java.lang.Character and Unicode standard for complete list
+ // TODO
+ // Test \p{L}
+ // TODO
+
+ // Test \p{N}
+ // TODO
+
+ // ... etc
+
+ // Test two letter codes:
+ // From unicode.org:
+ // Lu
+ // Ll
+ // Lt
+ // Lm
+ // Lo
+ // Mn
+ // Mc
+ // Me
+ // Nd
+ // Nl
+ // No
+ // Pc
+ // Pd
+ // Ps
+ // Pe
+ // Pi
+ // Pf
+ // Po
+ // Sm
+ // Sc
+ // Sk
+ // So
+ // Zs
+ // Zl
+ // Zp
+ // Cc
+ // Cf
+ // Cs
+ // Co
+ // Cn
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies matcher(CharSequence input) method for input specified by Unicode blocks.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ public void testUnicodeBlocks() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+ int i, j;
+
+ // Test Unicode blocks using \p and \P
+ // FIXME:
+ // Note that LatinExtended-B and ArabicPresentations-B are unrecognized
+ // by the reference JDK.
+ for (i = 0; i < UBlocks.length; i++) {
+ /*
+ * p = Pattern.compile("\\p{"+UBlocks[i].name+"}");
+ *
+ * if (UBlocks[i].low > 0) { m =
+ * p.matcher(Character.toString((char)(UBlocks[i].low-1)));
+ * assertFalse(m.matches()); } for (j=UBlocks[i].low; j <=
+ * UBlocks[i].high; j++) { m =
+ * p.matcher(Character.toString((char)j));
+ * assertTrue(m.matches()); } if (UBlocks[i].high < 0xFFFF) { m =
+ * p.matcher(Character.toString((char)(UBlocks[i].high+1)));
+ * assertFalse(m.matches()); }
+ *
+ * p = Pattern.compile("\\P{"+UBlocks[i].name+"}");
+ *
+ * if (UBlocks[i].low > 0) { m =
+ * p.matcher(Character.toString((char)(UBlocks[i].low-1)));
+ * assertTrue(m.matches()); } for (j=UBlocks[i].low; j <
+ * UBlocks[i].high; j++) { m =
+ * p.matcher(Character.toString((char)j));
+ * assertFalse(m.matches()); } if (UBlocks[i].high < 0xFFFF) { m =
+ * p.matcher(Character.toString((char)(UBlocks[i].high+1)));
+ * assertTrue(m.matches()); }
+ */
+
+ p = Pattern.compile("\\p{In" + UBlocks[i].name + "}");
+// BEGIN android-changed
+// Added the name of the block under test to the assertion to get more output.
+
+ if (UBlocks[i].low > 0) {
+ m = p.matcher(Character.toString((char) (UBlocks[i].low - 1)));
+ assertFalse(UBlocks[i].name, m.matches());
+ }
+ for (j = UBlocks[i].low; j <= UBlocks[i].high; j++) {
+ m = p.matcher(Character.toString((char) j));
+ assertTrue(UBlocks[i].name, m.matches());
+ }
+ if (UBlocks[i].high < 0xFFFF) {
+ m = p.matcher(Character.toString((char) (UBlocks[i].high + 1)));
+ assertFalse(UBlocks[i].name, m.matches());
+ }
+
+ p = Pattern.compile("\\P{In" + UBlocks[i].name + "}");
+
+ if (UBlocks[i].low > 0) {
+ m = p.matcher(Character.toString((char) (UBlocks[i].low - 1)));
+ assertTrue(UBlocks[i].name, m.matches());
+ }
+ for (j = UBlocks[i].low; j < UBlocks[i].high; j++) {
+ m = p.matcher(Character.toString((char) j));
+ assertFalse(UBlocks[i].name, m.matches());
+ }
+ if (UBlocks[i].high < 0xFFFF) {
+ m = p.matcher(Character.toString((char) (UBlocks[i].high + 1)));
+ assertTrue(UBlocks[i].name, m.matches());
+ }
+
+// END android-changed
+ }
+ }
+ @TestTargetNew(
+ level = TestLevel.ADDITIONAL,
+ notes = "TODO empty test",
+ method = "!",
+ args = {}
+ )
+ @BrokenTest("empty test")
+ public void testCapturingGroups() throws PatternSyntaxException {
+ // Test simple capturing groups
+ // TODO
+
+ // Test grouping without capture (?:...)
+ // TODO
+
+ // Test combination of grouping and capture
+ // TODO
+
+ // Test \<num> sequence with capturing and non-capturing groups
+ // TODO
+
+ // Test \<num> with <num> out of range
+ // TODO
+ }
+ @TestTargetNew(
+ level = TestLevel.ADDITIONAL,
+ notes = "TODO empty test",
+ method = "!",
+ args = {}
+ )
+ @BrokenTest("empty test")
+ public void testRepeats() {
+ // Test ?
+ // TODO
+
+ // Test *
+ // TODO
+
+ // Test +
+ // TODO
+
+ // Test {<num>}, including 0, 1 and more
+ // TODO
+
+ // Test {<num>,}, including 0, 1 and more
+ // TODO
+
+ // Test {<n1>,<n2>}, with n1 < n2, n1 = n2 and n1 > n2 (illegal?)
+ // TODO
+ }
+ @TestTargetNew(
+ level = TestLevel.ADDITIONAL,
+ notes = "TODO empty test",
+ method = "!",
+ args = {}
+ )
+ @BrokenTest("empty test")
+ public void testAnchors() throws PatternSyntaxException {
+ // Test ^, default and MULTILINE
+ // TODO
+
+ // Test $, default and MULTILINE
+ // TODO
+
+ // Test \b (word boundary)
+ // TODO
+
+ // Test \B (not a word boundary)
+ // TODO
+
+ // Test \A (beginning of string)
+ // TODO
+
+ // Test \Z (end of string)
+ // TODO
+
+ // Test \z (end of string)
+ // TODO
+
+ // Test \G
+ // TODO
+
+ // Test positive lookahead using (?=...)
+ // TODO
+
+ // Test negative lookahead using (?!...)
+ // TODO
+
+ // Test positive lookbehind using (?<=...)
+ // TODO
+
+ // Test negative lookbehind using (?<!...)
+ // TODO
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method and matcher for created pattern.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testMisc() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+
+ // Test (?>...)
+ // TODO
+
+ // Test (?onflags-offflags)
+ // Valid flags are i,m,d,s,u,x
+ // TODO
+
+ // Test (?onflags-offflags:...)
+ // TODO
+
+ // Test \Q, \E
+ p = Pattern.compile("[a-z]+;\\Q[a-z]+;\\Q(foo.*);\\E[0-9]+");
+ m = p.matcher("abc;[a-z]+;\\Q(foo.*);411");
+ assertTrue(m.matches());
+ m = p.matcher("abc;def;foo42;555");
+ assertFalse(m.matches());
+ m = p.matcher("abc;\\Qdef;\\Qfoo99;\\E123");
+ assertFalse(m.matches());
+
+ p = Pattern.compile("[a-z]+;(foo[0-9]-\\Q(...)\\E);[0-9]+");
+ m = p.matcher("abc;foo5-(...);123");
+ assertTrue(m.matches());
+ assertEquals("foo5-(...)", m.group(1));
+ m = p.matcher("abc;foo9-(xxx);789");
+ assertFalse(m.matches());
+
+ p = Pattern.compile("[a-z]+;(bar[0-9]-[a-z\\Q$-\\E]+);[0-9]+");
+ m = p.matcher("abc;bar0-def$-;123");
+ assertTrue(m.matches());
+
+ // FIXME:
+ // This should work the same as the pattern above but fails with the
+ // the reference JDK
+ p = Pattern.compile("[a-z]+;(bar[0-9]-[a-z\\Q-$\\E]+);[0-9]+");
+ m = p.matcher("abc;bar0-def$-;123");
+ // assertTrue(m.matches());
+
+ // FIXME:
+ // This should work too .. it looks as if just about anything that
+ // has more
+ // than one character between \Q and \E is broken in the the reference JDK
+ p = Pattern.compile("[a-z]+;(bar[0-9]-[a-z\\Q[0-9]\\E]+);[0-9]+");
+ m = p.matcher("abc;bar0-def[99]-]0x[;123");
+ // assertTrue(m.matches());
+
+ // This is the same as above but with explicit escapes .. and this
+ // does work
+ // on the the reference JDK
+ p = Pattern.compile("[a-z]+;(bar[0-9]-[a-z\\[0\\-9\\]]+);[0-9]+");
+ m = p.matcher("abc;bar0-def[99]-]0x[;123");
+ assertTrue(m.matches());
+
+ // Test #<comment text>
+ // TODO
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testCompile1() throws PatternSyntaxException {
+ Pattern pattern = Pattern
+ .compile("[0-9A-Za-z][0-9A-Za-z\\x2e\\x3a\\x2d\\x5f]*");
+ String name = "iso-8859-1";
+ assertTrue(pattern.matcher(name).matches());
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex, int flag) method.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ )
+ public void testCompile2() throws PatternSyntaxException {
+ String findString = "\\Qimport\\E";
+
+ Pattern pattern = Pattern.compile(findString, 0);
+ Matcher matcher = pattern.matcher(new String(
+ "import a.A;\n\n import b.B;\nclass C {}"));
+
+ assertTrue(matcher.find(0));
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) and compile(String regex, int flag) method for specific patterns.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) and compile(String regex, int flag) method for specific patterns.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ )
+ })
+ public void testCompile3() throws PatternSyntaxException {
+ Pattern p;
+ Matcher m;
+ p = Pattern.compile("a$");
+ m = p.matcher("a\n");
+ assertTrue(m.find());
+ assertEquals("a", m.group());
+ assertFalse(m.find());
+
+ p = Pattern.compile("(a$)");
+ m = p.matcher("a\n");
+ assertTrue(m.find());
+ assertEquals("a", m.group());
+ assertEquals("a", m.group(1));
+ assertFalse(m.find());
+
+ p = Pattern.compile("^.*$", Pattern.MULTILINE);
+
+ m = p.matcher("a\n");
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertEquals("a", m.group());
+ assertFalse(m.find());
+
+ m = p.matcher("a\nb\n");
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertEquals("a", m.group());
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertEquals("b", m.group());
+ assertFalse(m.find());
+
+ m = p.matcher("a\nb");
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertEquals("a", m.group());
+ assertTrue(m.find());
+ assertEquals("b", m.group());
+ assertFalse(m.find());
+
+ m = p.matcher("\naa\r\nbb\rcc\n\n");
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertTrue(m.group().equals(""));
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertEquals("aa", m.group());
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertEquals("bb", m.group());
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertEquals("cc", m.group());
+ assertTrue(m.find());
+ // System.out.println("["+m.group()+"]");
+ assertTrue(m.group().equals(""));
+ assertFalse(m.find());
+
+ m = p.matcher("a");
+ assertTrue(m.find());
+ assertEquals("a", m.group());
+ assertFalse(m.find());
+
+// BEGIN android-removed
+// Makes no sense to duplicate this weird behavior
+// m = p.matcher("");
+// // FIXME: This matches the reference behaviour but is
+// // inconsistent with matching "a" - ie. the end of the
+// // target string should match against $ always but this
+// // appears to work with the null string only when not in
+// // multiline mode (see below)
+// assertFalse(m.find());
+// END android-removed
+
+ p = Pattern.compile("^.*$");
+ m = p.matcher("");
+ assertTrue(m.find());
+ assertTrue(m.group().equals(""));
+ assertFalse(m.find());
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex, int flag) method for specific string.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ )
+ public void testCompile4() throws PatternSyntaxException {
+ String findString = "\\Qpublic\\E";
+ StringBuffer text = new StringBuffer(" public class Class {\n"
+ + " public class Class {");
+
+ Pattern pattern = Pattern.compile(findString, 0);
+ Matcher matcher = pattern.matcher(text);
+
+ boolean found = matcher.find();
+ assertTrue(found);
+ assertEquals(4, matcher.start());
+ if (found) {
+ // modify text
+ text.delete(0, text.length());
+ text.append("Text have been changed.");
+ matcher.reset(text);
+ }
+
+ found = matcher.find();
+ assertFalse(found);
+ }
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) methodfor specific string.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testCompile5() throws PatternSyntaxException {
+ Pattern p = Pattern.compile("^[0-9]");
+ String s[] = p.split("12", -1);
+ assertEquals("", s[0]);
+ assertEquals("2", s[1]);
+ assertEquals(2, s.length);
+ }
+
+ // public void testCompile6() {
+ // String regex = "[\\p{L}[\\p{Mn}[\\p{Pc}[\\p{Nd}[\\p{Nl}[\\p{Sc}]]]]]]+";
+ // String regex = "[\\p{L}\\p{Mn}\\p{Pc}\\p{Nd}\\p{Nl}\\p{Sc}]+";
+ // try {
+ // Pattern pattern = Pattern.compile(regex, Pattern.MULTILINE);
+ // assertTrue(true);
+ // } catch (PatternSyntaxException e) {
+ // System.out.println(e.getMessage());
+ // assertTrue(false);
+ // }
+ // }
+
+ private static class UBInfo {
+ public UBInfo(int low, int high, String name) {
+ this.name = name;
+ this.low = low;
+ this.high = high;
+ }
+
+ public String name;
+
+ public int low, high;
+ }
+
+ // A table representing the unicode categories
+ //private static UBInfo[] UCategories = {
+ // Lu
+ // Ll
+ // Lt
+ // Lm
+ // Lo
+ // Mn
+ // Mc
+ // Me
+ // Nd
+ // Nl
+ // No
+ // Pc
+ // Pd
+ // Ps
+ // Pe
+ // Pi
+ // Pf
+ // Po
+ // Sm
+ // Sc
+ // Sk
+ // So
+ // Zs
+ // Zl
+ // Zp
+ // Cc
+ // Cf
+ // Cs
+ // Co
+ // Cn
+ //};
+
+ // A table representing the unicode character blocks
+ private static UBInfo[] UBlocks = {
+ /* 0000; 007F; Basic Latin */
+ new UBInfo(0x0000, 0x007F, "BasicLatin"), // Character.UnicodeBlock.BASIC_LATIN
+ /* 0080; 00FF; Latin-1 Supplement */
+ new UBInfo(0x0080, 0x00FF, "Latin-1Supplement"), // Character.UnicodeBlock.LATIN_1_SUPPLEMENT
+ /* 0100; 017F; Latin Extended-A */
+ new UBInfo(0x0100, 0x017F, "LatinExtended-A"), // Character.UnicodeBlock.LATIN_EXTENDED_A
+ /* 0180; 024F; Latin Extended-B */
+ // new UBInfo (0x0180,0x024F,"InLatinExtended-B"), //
+ // Character.UnicodeBlock.LATIN_EXTENDED_B
+ /* 0250; 02AF; IPA Extensions */
+ new UBInfo(0x0250, 0x02AF, "IPAExtensions"), // Character.UnicodeBlock.IPA_EXTENSIONS
+ /* 02B0; 02FF; Spacing Modifier Letters */
+ new UBInfo(0x02B0, 0x02FF, "SpacingModifierLetters"), // Character.UnicodeBlock.SPACING_MODIFIER_LETTERS
+ /* 0300; 036F; Combining Diacritical Marks */
+ new UBInfo(0x0300, 0x036F, "CombiningDiacriticalMarks"), // Character.UnicodeBlock.COMBINING_DIACRITICAL_MARKS
+ /* 0370; 03FF; Greek */
+ new UBInfo(0x0370, 0x03FF, "Greek"), // Character.UnicodeBlock.GREEK
+ /* 0400; 04FF; Cyrillic */
+ new UBInfo(0x0400, 0x04FF, "Cyrillic"), // Character.UnicodeBlock.CYRILLIC
+ /* 0530; 058F; Armenian */
+ new UBInfo(0x0530, 0x058F, "Armenian"), // Character.UnicodeBlock.ARMENIAN
+ /* 0590; 05FF; Hebrew */
+ new UBInfo(0x0590, 0x05FF, "Hebrew"), // Character.UnicodeBlock.HEBREW
+ /* 0600; 06FF; Arabic */
+ new UBInfo(0x0600, 0x06FF, "Arabic"), // Character.UnicodeBlock.ARABIC
+ /* 0700; 074F; Syriac */
+ new UBInfo(0x0700, 0x074F, "Syriac"), // Character.UnicodeBlock.SYRIAC
+ /* 0780; 07BF; Thaana */
+ new UBInfo(0x0780, 0x07BF, "Thaana"), // Character.UnicodeBlock.THAANA
+ /* 0900; 097F; Devanagari */
+ new UBInfo(0x0900, 0x097F, "Devanagari"), // Character.UnicodeBlock.DEVANAGARI
+ /* 0980; 09FF; Bengali */
+ new UBInfo(0x0980, 0x09FF, "Bengali"), // Character.UnicodeBlock.BENGALI
+ /* 0A00; 0A7F; Gurmukhi */
+ new UBInfo(0x0A00, 0x0A7F, "Gurmukhi"), // Character.UnicodeBlock.GURMUKHI
+ /* 0A80; 0AFF; Gujarati */
+ new UBInfo(0x0A80, 0x0AFF, "Gujarati"), // Character.UnicodeBlock.GUJARATI
+ /* 0B00; 0B7F; Oriya */
+ new UBInfo(0x0B00, 0x0B7F, "Oriya"), // Character.UnicodeBlock.ORIYA
+ /* 0B80; 0BFF; Tamil */
+ new UBInfo(0x0B80, 0x0BFF, "Tamil"), // Character.UnicodeBlock.TAMIL
+ /* 0C00; 0C7F; Telugu */
+ new UBInfo(0x0C00, 0x0C7F, "Telugu"), // Character.UnicodeBlock.TELUGU
+ /* 0C80; 0CFF; Kannada */
+ new UBInfo(0x0C80, 0x0CFF, "Kannada"), // Character.UnicodeBlock.KANNADA
+ /* 0D00; 0D7F; Malayalam */
+ new UBInfo(0x0D00, 0x0D7F, "Malayalam"), // Character.UnicodeBlock.MALAYALAM
+ /* 0D80; 0DFF; Sinhala */
+ new UBInfo(0x0D80, 0x0DFF, "Sinhala"), // Character.UnicodeBlock.SINHALA
+ /* 0E00; 0E7F; Thai */
+ new UBInfo(0x0E00, 0x0E7F, "Thai"), // Character.UnicodeBlock.THAI
+ /* 0E80; 0EFF; Lao */
+ new UBInfo(0x0E80, 0x0EFF, "Lao"), // Character.UnicodeBlock.LAO
+ /* 0F00; 0FFF; Tibetan */
+ new UBInfo(0x0F00, 0x0FFF, "Tibetan"), // Character.UnicodeBlock.TIBETAN
+ /* 1000; 109F; Myanmar */
+ new UBInfo(0x1000, 0x109F, "Myanmar"), // Character.UnicodeBlock.MYANMAR
+ /* 10A0; 10FF; Georgian */
+ new UBInfo(0x10A0, 0x10FF, "Georgian"), // Character.UnicodeBlock.GEORGIAN
+ /* 1100; 11FF; Hangul Jamo */
+ new UBInfo(0x1100, 0x11FF, "HangulJamo"), // Character.UnicodeBlock.HANGUL_JAMO
+ /* 1200; 137F; Ethiopic */
+ new UBInfo(0x1200, 0x137F, "Ethiopic"), // Character.UnicodeBlock.ETHIOPIC
+ /* 13A0; 13FF; Cherokee */
+ new UBInfo(0x13A0, 0x13FF, "Cherokee"), // Character.UnicodeBlock.CHEROKEE
+ /* 1400; 167F; Unified Canadian Aboriginal Syllabics */
+ new UBInfo(0x1400, 0x167F, "UnifiedCanadianAboriginalSyllabics"), // Character.UnicodeBlock.UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS
+ /* 1680; 169F; Ogham */
+ new UBInfo(0x1680, 0x169F, "Ogham"), // Character.UnicodeBlock.OGHAM
+ /* 16A0; 16FF; Runic */
+ new UBInfo(0x16A0, 0x16FF, "Runic"), // Character.UnicodeBlock.RUNIC
+ /* 1780; 17FF; Khmer */
+ new UBInfo(0x1780, 0x17FF, "Khmer"), // Character.UnicodeBlock.KHMER
+ /* 1800; 18AF; Mongolian */
+ new UBInfo(0x1800, 0x18AF, "Mongolian"), // Character.UnicodeBlock.MONGOLIAN
+ /* 1E00; 1EFF; Latin Extended Additional */
+ new UBInfo(0x1E00, 0x1EFF, "LatinExtendedAdditional"), // Character.UnicodeBlock.LATIN_EXTENDED_ADDITIONAL
+ /* 1F00; 1FFF; Greek Extended */
+ new UBInfo(0x1F00, 0x1FFF, "GreekExtended"), // Character.UnicodeBlock.GREEK_EXTENDED
+ /* 2000; 206F; General Punctuation */
+ new UBInfo(0x2000, 0x206F, "GeneralPunctuation"), // Character.UnicodeBlock.GENERAL_PUNCTUATION
+ /* 2070; 209F; Superscripts and Subscripts */
+ new UBInfo(0x2070, 0x209F, "SuperscriptsandSubscripts"), // Character.UnicodeBlock.SUPERSCRIPTS_AND_SUBSCRIPTS
+ /* 20A0; 20CF; Currency Symbols */
+ new UBInfo(0x20A0, 0x20CF, "CurrencySymbols"), // Character.UnicodeBlock.CURRENCY_SYMBOLS
+ /* 20D0; 20FF; Combining Marks for Symbols */
+ new UBInfo(0x20D0, 0x20FF, "CombiningMarksforSymbols"), // Character.UnicodeBlock.COMBINING_MARKS_FOR_SYMBOLS
+ /* 2100; 214F; Letterlike Symbols */
+ new UBInfo(0x2100, 0x214F, "LetterlikeSymbols"), // Character.UnicodeBlock.LETTERLIKE_SYMBOLS
+ /* 2150; 218F; Number Forms */
+ new UBInfo(0x2150, 0x218F, "NumberForms"), // Character.UnicodeBlock.NUMBER_FORMS
+ /* 2190; 21FF; Arrows */
+ new UBInfo(0x2190, 0x21FF, "Arrows"), // Character.UnicodeBlock.ARROWS
+ /* 2200; 22FF; Mathematical Operators */
+ new UBInfo(0x2200, 0x22FF, "MathematicalOperators"), // Character.UnicodeBlock.MATHEMATICAL_OPERATORS
+ /* 2300; 23FF; Miscellaneous Technical */
+ new UBInfo(0x2300, 0x23FF, "MiscellaneousTechnical"), // Character.UnicodeBlock.MISCELLANEOUS_TECHNICAL
+ /* 2400; 243F; Control Pictures */
+ new UBInfo(0x2400, 0x243F, "ControlPictures"), // Character.UnicodeBlock.CONTROL_PICTURES
+ /* 2440; 245F; Optical Character Recognition */
+ new UBInfo(0x2440, 0x245F, "OpticalCharacterRecognition"), // Character.UnicodeBlock.OPTICAL_CHARACTER_RECOGNITION
+ /* 2460; 24FF; Enclosed Alphanumerics */
+ new UBInfo(0x2460, 0x24FF, "EnclosedAlphanumerics"), // Character.UnicodeBlock.ENCLOSED_ALPHANUMERICS
+ /* 2500; 257F; Box Drawing */
+ new UBInfo(0x2500, 0x257F, "BoxDrawing"), // Character.UnicodeBlock.BOX_DRAWING
+ /* 2580; 259F; Block Elements */
+ new UBInfo(0x2580, 0x259F, "BlockElements"), // Character.UnicodeBlock.BLOCK_ELEMENTS
+ /* 25A0; 25FF; Geometric Shapes */
+ new UBInfo(0x25A0, 0x25FF, "GeometricShapes"), // Character.UnicodeBlock.GEOMETRIC_SHAPES
+ /* 2600; 26FF; Miscellaneous Symbols */
+ new UBInfo(0x2600, 0x26FF, "MiscellaneousSymbols"), // Character.UnicodeBlock.MISCELLANEOUS_SYMBOLS
+ /* 2700; 27BF; Dingbats */
+ new UBInfo(0x2700, 0x27BF, "Dingbats"), // Character.UnicodeBlock.DINGBATS
+ /* 2800; 28FF; Braille Patterns */
+ new UBInfo(0x2800, 0x28FF, "BraillePatterns"), // Character.UnicodeBlock.BRAILLE_PATTERNS
+ /* 2E80; 2EFF; CJK Radicals Supplement */
+ new UBInfo(0x2E80, 0x2EFF, "CJKRadicalsSupplement"), // Character.UnicodeBlock.CJK_RADICALS_SUPPLEMENT
+ /* 2F00; 2FDF; Kangxi Radicals */
+ new UBInfo(0x2F00, 0x2FDF, "KangxiRadicals"), // Character.UnicodeBlock.KANGXI_RADICALS
+ /* 2FF0; 2FFF; Ideographic Description Characters */
+ new UBInfo(0x2FF0, 0x2FFF, "IdeographicDescriptionCharacters"), // Character.UnicodeBlock.IDEOGRAPHIC_DESCRIPTION_CHARACTERS
+ /* 3000; 303F; CJK Symbols and Punctuation */
+ new UBInfo(0x3000, 0x303F, "CJKSymbolsandPunctuation"), // Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
+ /* 3040; 309F; Hiragana */
+ new UBInfo(0x3040, 0x309F, "Hiragana"), // Character.UnicodeBlock.HIRAGANA
+ /* 30A0; 30FF; Katakana */
+ new UBInfo(0x30A0, 0x30FF, "Katakana"), // Character.UnicodeBlock.KATAKANA
+ /* 3100; 312F; Bopomofo */
+ new UBInfo(0x3100, 0x312F, "Bopomofo"), // Character.UnicodeBlock.BOPOMOFO
+ /* 3130; 318F; Hangul Compatibility Jamo */
+ new UBInfo(0x3130, 0x318F, "HangulCompatibilityJamo"), // Character.UnicodeBlock.HANGUL_COMPATIBILITY_JAMO
+ /* 3190; 319F; Kanbun */
+ new UBInfo(0x3190, 0x319F, "Kanbun"), // Character.UnicodeBlock.KANBUN
+ /* 31A0; 31BF; Bopomofo Extended */
+ new UBInfo(0x31A0, 0x31BF, "BopomofoExtended"), // Character.UnicodeBlock.BOPOMOFO_EXTENDED
+ /* 3200; 32FF; Enclosed CJK Letters and Months */
+ new UBInfo(0x3200, 0x32FF, "EnclosedCJKLettersandMonths"), // Character.UnicodeBlock.ENCLOSED_CJK_LETTERS_AND_MONTHS
+ /* 3300; 33FF; CJK Compatibility */
+ new UBInfo(0x3300, 0x33FF, "CJKCompatibility"), // Character.UnicodeBlock.CJK_COMPATIBILITY
+ /* 3400; 4DB5; CJK Unified Ideographs Extension A */
+// BEGIN android-changed
+// Modified this to reflect current Unicode tables (or maybe it was a typo)
+ new UBInfo(0x3400, 0x4DBF, "CJKUnifiedIdeographsExtensionA"), // Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A
+// END android-changed
+ /* 4E00; 9FFF; CJK Unified Ideographs */
+ new UBInfo(0x4E00, 0x9FFF, "CJKUnifiedIdeographs"), // Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
+ /* A000; A48F; Yi Syllables */
+ new UBInfo(0xA000, 0xA48F, "YiSyllables"), // Character.UnicodeBlock.YI_SYLLABLES
+ /* A490; A4CF; Yi Radicals */
+ new UBInfo(0xA490, 0xA4CF, "YiRadicals"), // Character.UnicodeBlock.YI_RADICALS
+ /* AC00; D7A3; Hangul Syllables */
+// BEGIN android-changed
+// Modified this to reflect current Unicode tables (or maybe it was a typo)
+ new UBInfo(0xAC00, 0xD7AF, "HangulSyllables"), // Character.UnicodeBlock.HANGUL_SYLLABLES
+// END android-changed
+ /* D800; DB7F; High Surrogates */
+ /* DB80; DBFF; High Private Use Surrogates */
+ /* DC00; DFFF; Low Surrogates */
+ /* E000; F8FF; Private Use */
+ /* F900; FAFF; CJK Compatibility Ideographs */
+ new UBInfo(0xF900, 0xFAFF, "CJKCompatibilityIdeographs"), // Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
+ /* FB00; FB4F; Alphabetic Presentation Forms */
+ new UBInfo(0xFB00, 0xFB4F, "AlphabeticPresentationForms"), // Character.UnicodeBlock.ALPHABETIC_PRESENTATION_FORMS
+ /* FB50; FDFF; Arabic Presentation Forms-A */
+ new UBInfo(0xFB50, 0xFDFF, "ArabicPresentationForms-A"), // Character.UnicodeBlock.ARABIC_PRESENTATION_FORMS_A
+ /* FE20; FE2F; Combining Half Marks */
+ new UBInfo(0xFE20, 0xFE2F, "CombiningHalfMarks"), // Character.UnicodeBlock.COMBINING_HALF_MARKS
+ /* FE30; FE4F; CJK Compatibility Forms */
+ new UBInfo(0xFE30, 0xFE4F, "CJKCompatibilityForms"), // Character.UnicodeBlock.CJK_COMPATIBILITY_FORMS
+ /* FE50; FE6F; Small Form Variants */
+ new UBInfo(0xFE50, 0xFE6F, "SmallFormVariants"), // Character.UnicodeBlock.SMALL_FORM_VARIANTS
+ /* FE70; FEFE; Arabic Presentation Forms-B */
+ // new UBInfo (0xFE70,0xFEFE,"InArabicPresentationForms-B"), //
+ // Character.UnicodeBlock.ARABIC_PRESENTATION_FORMS_B
+ /* FEFF; FEFF; Specials */
+// BEGIN android-changed
+// Modified this to reflect current Unicode tables (or maybe it was a typo)
+// FEFF is actually still Arabic Presentation Forms B
+// new UBInfo(0xFEFF, 0xFEFF, "Specials"), // Character.UnicodeBlock.SPECIALS
+// END android-changed
+ /* FF00; FFEF; Halfwidth and Fullwidth Forms */
+ new UBInfo(0xFF00, 0xFFEF, "HalfwidthandFullwidthForms"), // Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS
+ /* FFF0; FFFD; Specials */
+ // BEGIN android-changed
+// Modified this to reflect current Unicode tables (or maybe it was a typo)
+ new UBInfo(0xFFF0, 0xFFFF, "Specials") // Character.UnicodeBlock.SPECIALS
+// END android-changed
+ };
+} \ No newline at end of file
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternErrorTest.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternErrorTest.java
new file mode 100644
index 0000000..a9b782b
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternErrorTest.java
@@ -0,0 +1,103 @@
+/* Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import dalvik.annotation.TestTargetClass;
+import dalvik.annotation.TestTargets;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestLevel;
+
+import java.util.regex.Pattern;
+import junit.framework.TestCase;
+
+@TestTargetClass(Pattern.class)
+/**
+ * Test boundary and error conditions in java.util.regex.Pattern
+ *
+ */
+public class PatternErrorTest extends TestCase {
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) and compile(String regex, int flag) method with invalid parameters. Doesn't verify IllegalArgumentException, PatternSyntaxException.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies compile(String regex) and compile(String regex, int flag) method with invalid parameters. Doesn't verify IllegalArgumentException, PatternSyntaxException.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ )
+ })
+ public void testCompileErrors() throws Exception {
+ // null regex string - should get NullPointerException
+ try {
+ Pattern.compile(null);
+ fail("NullPointerException expected");
+ } catch (NullPointerException e) {
+ }
+
+
+ // empty regex string - no exception should be thrown
+ Pattern.compile("");
+
+ // note: invalid regex syntax checked in PatternSyntaxExceptionTest
+
+ // flags = 0 should raise no exception
+ int flags = 0;
+ Pattern.compile("foo", flags);
+
+ // check that all valid flags accepted without exception
+ flags |= Pattern.UNIX_LINES;
+ flags |= Pattern.CASE_INSENSITIVE;
+ flags |= Pattern.MULTILINE;
+ // BEGIN android-changed
+ // We don't support that flag.
+ // flags |= Pattern.CANON_EQ;
+ // END android-changed
+ flags |= Pattern.COMMENTS;
+ flags |= Pattern.DOTALL;
+ flags |= Pattern.UNICODE_CASE;
+ Pattern.compile("foo", flags);
+
+ // add invalid flags - should get IllegalArgumentException
+ /*
+ * TODO: Inconsistency between the reference JDK behaviour and spec - exception is
+ * not thrown
+ */
+ /*
+ * Valid test is:
+ * flags |= 0xFFFFFFFF;
+ * try {
+ * Pattern.compile("foo",flags);
+ * } catch (IllegalArgumentException e) {
+ * // This is the expected exception
+ * } catch (Exception e) {
+ * fail();
+ * }
+ */
+
+ /* Workaround test is: */
+ // BEGIN android-changed
+ // We don't support that flag.
+ flags |= ~Pattern.CANON_EQ;
+ // END android-changed
+ // No exception expected to match incorrect the reference behaviour
+ Pattern.compile("foo", flags);
+ }
+}
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternSyntaxExceptionTest.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternSyntaxExceptionTest.java
new file mode 100644
index 0000000..9f3f389
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternSyntaxExceptionTest.java
@@ -0,0 +1,122 @@
+/*
+ * Copyright (C) 2008 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import java.util.regex.PatternSyntaxException;
+
+import junit.framework.TestCase;
+import dalvik.annotation.TestTargets;
+import dalvik.annotation.TestLevel;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestTargetClass;
+
+@TestTargetClass(PatternSyntaxException.class)
+public class PatternSyntaxExceptionTest extends TestCase {
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "PatternSyntaxException",
+ args = {java.lang.String.class, java.lang.String.class, int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "getDescription",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "getPattern",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "getIndex",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "getMessage",
+ args = {}
+ )
+ })
+ public void testPatternSyntaxException() {
+ // Normal case
+ PatternSyntaxException e = new PatternSyntaxException("Foo", "Bar", 0);
+ assertEquals("Foo", e.getDescription());
+ assertEquals("Bar", e.getPattern());
+ assertEquals(0, e.getIndex());
+
+ String s = e.getMessage();
+ assertTrue(s.contains("Foo"));
+ assertTrue(s.contains("Bar"));
+ assertTrue(s.contains("0"));
+
+ // No description specified
+ e = new PatternSyntaxException(null, "Bar", 0);
+ assertEquals(null, e.getDescription());
+ assertEquals("Bar", e.getPattern());
+ assertEquals(0, e.getIndex());
+
+ s = e.getMessage();
+ assertFalse(s.contains("Foo"));
+ assertTrue(s.contains("Bar"));
+ assertTrue(s.contains("0"));
+
+ // No pattern specified
+ e = new PatternSyntaxException("Foo", null, 0);
+ assertEquals("Foo", e.getDescription());
+ assertEquals(null, e.getPattern());
+ assertEquals(0, e.getIndex());
+
+ s = e.getMessage();
+ assertTrue(s.contains("Foo"));
+ assertFalse(s.contains("Bar"));
+ assertTrue(s.contains("0"));
+
+ // Neither description nor pattern specified
+ e = new PatternSyntaxException(null, null, 0);
+ assertEquals(null, e.getDescription());
+ assertEquals(null, e.getPattern());
+ assertEquals(0, e.getIndex());
+
+ s = e.getMessage();
+ assertFalse(s.contains("Foo"));
+ assertFalse(s.contains("Bar"));
+ assertTrue(s.contains("0"));
+
+ // No index specified
+ e = new PatternSyntaxException("Foo", "Bar", -1);
+ assertEquals(-1, e.getIndex());
+
+ s = e.getMessage();
+ assertFalse(s.contains("^"));
+
+ // No pattern, but index specified
+ e = new PatternSyntaxException("Foo", null, 0);
+ assertEquals(0, e.getIndex());
+
+ s = e.getMessage();
+ assertFalse(s.contains("^"));
+ }
+
+}
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternTest.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternTest.java
new file mode 100644
index 0000000..f70f9f1
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/PatternTest.java
@@ -0,0 +1,2410 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import dalvik.annotation.BrokenTest;
+import dalvik.annotation.TestTargetClass;
+import dalvik.annotation.TestTargets;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestLevel;
+
+import java.io.Serializable;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+import java.util.regex.PatternSyntaxException;
+
+import junit.framework.TestCase;
+
+import org.apache.harmony.testframework.serialization.SerializationTest;
+import org.apache.harmony.testframework.serialization.SerializationTest.SerializableAssert;
+
+@TestTargetClass(
+ value = Pattern.class,
+ untestedMethods= {
+ @TestTargetNew(
+ level = TestLevel.NOT_FEASIBLE,
+ notes = "finalize is hard to test since the implementation only calls a native function",
+ method = "finalize",
+ args = {}
+ )
+ }
+)
+public class PatternTest extends TestCase {
+ String[] testPatterns = {
+ "(a|b)*abb",
+ "(1*2*3*4*)*567",
+ "(a|b|c|d)*aab",
+ "(1|2|3|4|5|6|7|8|9|0)(1|2|3|4|5|6|7|8|9|0)*",
+ "(abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ)*",
+ "(a|b)*(a|b)*A(a|b)*lice.*",
+ "(a|b|c|d|e|f|g|h|i|j|k|l|m|n|o|p|q|r|s|t|u|v|w|x|y|z)(a|b|c|d|e|f|g|h|"
+ + "i|j|k|l|m|n|o|p|q|r|s|t|u|v|w|x|y|z)*(1|2|3|4|5|6|7|8|9|0)*|while|for|struct|if|do",
+// BEGIN android-changed
+// We don't have canonical equivalence.
+// "x(?c)y", "x(?cc)y"
+// "x(?:c)y"
+// END android-changed
+
+ };
+
+ String[] testPatternsAlt = {
+ /*
+ * According to JavaDoc 2 and 3 oct digit sequences like \\o70\\o347
+ * should be OK, but test is failed for them
+ */
+ "[ab]\\b\\\\o5\\xF9\\u1E7B\\t\\n\\f\\r\\a\\e[yz]",
+ "^\\p{Lower}*\\p{Upper}*\\p{ASCII}?\\p{Alpha}?\\p{Digit}*\\p{Alnum}\\p{Punct}\\p{Graph}\\p{Print}\\p{Blank}\\p{Cntrl}\\p{XDigit}\\p{Space}",
+ "$\\p{javaLowerCase}\\p{javaUpperCase}\\p{javaWhitespace}\\p{javaMirrored}",
+ "\\p{InGreek}\\p{Lu}\\p{Sc}\\P{InGreek}[\\p{L}&&[^\\p{Lu}]]" };
+
+ String[] wrongTestPatterns = { "\\o9A", "\\p{Lawer}", "\\xG0" };
+
+ final static int[] flagsSet = { Pattern.CASE_INSENSITIVE,
+ Pattern.MULTILINE, Pattern.DOTALL, Pattern.UNICODE_CASE
+ /* , Pattern.CANON_EQ */ };
+
+ /*
+ * Based on RI implenetation documents. Need to check this set regarding
+ * actual implementation.
+ */
+ final static int[] wrongFlagsSet = { 256, 512, 1024 };
+
+ final static int DEFAULT_FLAGS = 0;
+
+ @TestTargetNew(
+ level = TestLevel.ADDITIONAL,
+ notes = "TODO empty test",
+ method = "!",
+ args = {}
+ )
+ @BrokenTest("empty test")
+ public void testMatcher() {
+ }
+
+ /*
+ * Class under test for String[] split(CharSequence, int)
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of splitsplit(java.lang.String, int) method.",
+ method = "split",
+ args = {CharSequence.class, int.class}
+ )
+ public void testSplitCharSequenceint() {
+ // splitting CharSequence which ends with pattern
+ // bug6193
+ assertEquals(",,".split(",", 3).length, 3);
+ assertEquals(",,".split(",", 4).length, 3);
+ // bug6193
+ // bug5391
+ assertEquals(Pattern.compile("o").split("boo:and:foo", 5).length, 5);
+ assertEquals(Pattern.compile("b").split("ab", -1).length, 2);
+ // bug5391
+ String s[];
+ Pattern pat = Pattern.compile("x");
+ s = pat.split("zxx:zzz:zxx", 10);
+ assertEquals(s.length, 5);
+ s = pat.split("zxx:zzz:zxx", 3);
+ assertEquals(s.length, 3);
+ s = pat.split("zxx:zzz:zxx", -1);
+ assertEquals(s.length, 5);
+ s = pat.split("zxx:zzz:zxx", 0);
+ assertEquals(s.length, 3);
+ // other splitting
+ // negative limit
+ pat = Pattern.compile("b");
+ s = pat.split("abccbadfebb", -1);
+ assertEquals(s.length, 5);
+ s = pat.split("", -1);
+ assertEquals(s.length, 1);
+ pat = Pattern.compile("");
+ s = pat.split("", -1);
+ assertEquals(s.length, 1);
+ s = pat.split("abccbadfe", -1);
+ assertEquals(s.length, 11);
+ // zero limit
+ pat = Pattern.compile("b");
+ s = pat.split("abccbadfebb", 0);
+ assertEquals(s.length, 3);
+ s = pat.split("", 0);
+ assertEquals(s.length, 1);
+ pat = Pattern.compile("");
+ s = pat.split("", 0);
+ assertEquals(s.length, 1);
+ s = pat.split("abccbadfe", 0);
+ assertEquals(s.length, 10);
+ // positive limit
+ pat = Pattern.compile("b");
+ s = pat.split("abccbadfebb", 12);
+ assertEquals(s.length, 5);
+ s = pat.split("", 6);
+ assertEquals(s.length, 1);
+ pat = Pattern.compile("");
+ s = pat.split("", 11);
+ assertEquals(s.length, 1);
+ s = pat.split("abccbadfe", 15);
+ assertEquals(s.length, 11);
+
+ pat = Pattern.compile("b");
+ s = pat.split("abccbadfebb", 5);
+ assertEquals(s.length, 5);
+ s = pat.split("", 1);
+ assertEquals(s.length, 1);
+ pat = Pattern.compile("");
+ s = pat.split("", 1);
+ assertEquals(s.length, 1);
+ s = pat.split("abccbadfe", 11);
+ assertEquals(s.length, 11);
+
+ pat = Pattern.compile("b");
+ s = pat.split("abccbadfebb", 3);
+ assertEquals(s.length, 3);
+ pat = Pattern.compile("");
+ s = pat.split("abccbadfe", 5);
+ assertEquals(s.length, 5);
+ }
+
+ /*
+ * Class under test for String[] split(CharSequence)
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of splitsplit(java.lang.String) method.",
+ method = "split",
+ args = {CharSequence.class}
+ )
+ public void testSplitCharSequence() {
+ String s[];
+ Pattern pat = Pattern.compile("b");
+ s = pat.split("abccbadfebb");
+ assertEquals(s.length, 3);
+ s = pat.split("");
+ assertEquals(s.length, 1);
+ pat = Pattern.compile("");
+ s = pat.split("");
+ assertEquals(s.length, 1);
+ s = pat.split("abccbadfe");
+ assertEquals(s.length, 10);
+ // bug6544
+ String s1 = "";
+ String[] arr = s1.split(":");
+ assertEquals(arr.length, 1);
+ // bug6544
+ }
+
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "Verifies the functionality of pattern() method.",
+ method = "pattern",
+ args = {}
+ )
+ public void testPattern() {
+ /* Positive assertion test. */
+ for (String aPattern : testPatterns) {
+ Pattern p = Pattern.compile(aPattern);
+ try {
+ assertTrue(p.pattern().equals(aPattern));
+ } catch (Exception e) {
+ fail("Unexpected exception: " + e);
+ }
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testCompile() {
+ /* Positive assertion test. */
+ for (String aPattern : testPatterns) {
+ try {
+ Pattern p = Pattern.compile(aPattern);
+ } catch (Exception e) {
+ fail("Unexpected exception: " + e);
+ }
+ }
+
+ /* Positive assertion test with alternative templates. */
+ for (String aPattern : testPatternsAlt) {
+ try {
+ Pattern p = Pattern.compile(aPattern);
+ } catch (Exception e) {
+ fail("Unexpected exception: " + e);
+ }
+ }
+
+ /* Negative assertion test. */
+ for (String aPattern : wrongTestPatterns) {
+ try {
+ Pattern p = Pattern.compile(aPattern);
+ fail("PatternSyntaxException is expected");
+ } catch (PatternSyntaxException pse) {
+ /* OKAY */
+ } catch (Exception e) {
+ fail("Unexpected exception: " + e);
+ }
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method for different flags.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testFlags() {
+ String baseString;
+ String testString;
+ Pattern pat;
+ Matcher mat;
+
+ baseString = "((?i)|b)a";
+ testString = "A";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ baseString = "(?i)a|b";
+ testString = "A";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?i)a|b";
+ testString = "B";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "c|(?i)a|b";
+ testString = "B";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?i)a|(?s)b";
+ testString = "B";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?i)a|(?-i)b";
+ testString = "B";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ baseString = "(?i)a|(?-i)c|b";
+ testString = "B";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ baseString = "(?i)a|(?-i)c|(?i)b";
+ testString = "B";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?i)a|(?-i)b";
+ testString = "A";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "((?i))a";
+ testString = "A";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ baseString = "|(?i)|a";
+ testString = "A";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?i)((?s)a.)";
+ testString = "A\n";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?i)((?-i)a)";
+ testString = "A";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ baseString = "(?i)(?s:a.)";
+ testString = "A\n";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?i)fgh(?s:aa)";
+ testString = "fghAA";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?i)((?-i))a";
+ testString = "A";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "abc(?i)d";
+ testString = "ABCD";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ testString = "abcD";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "a(?i)a(?-i)a(?i)a(?-i)a";
+ testString = "aAaAa";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "aAAAa";
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+ }
+
+// BEGIN android-removed
+// The flags() method should only return those flags that were explicitly
+// passed during the compilation. The JDK also accepts the ones implicitly
+// contained in the pattern, but ICU doesn't do this.
+//
+// public void testFlagsMethod() {
+// String baseString;
+// Pattern pat;
+//
+// /*
+// * These tests are for compatibility with RI only. Logically we have to
+// * return only flags specified during the compilation. For example
+// * pat.flags() == 0 when we compile Pattern pat =
+// * Pattern.compile("(?i)abc(?-i)"); but the whole expression is compiled
+// * in a case insensitive manner. So there is little sense to do calls to
+// * flags() now.
+// */
+// baseString = "(?-i)";
+// pat = Pattern.compile(baseString);
+//
+// baseString = "(?idmsux)abc(?-i)vg(?-dmu)";
+// pat = Pattern.compile(baseString);
+// assertEquals(pat.flags(), Pattern.DOTALL | Pattern.COMMENTS);
+//
+// baseString = "(?idmsux)abc|(?-i)vg|(?-dmu)";
+// pat = Pattern.compile(baseString);
+// assertEquals(pat.flags(), Pattern.DOTALL | Pattern.COMMENTS);
+//
+// baseString = "(?is)a((?x)b.)";
+// pat = Pattern.compile(baseString);
+// assertEquals(pat.flags(), Pattern.DOTALL | Pattern.CASE_INSENSITIVE);
+//
+// baseString = "(?i)a((?-i))";
+// pat = Pattern.compile(baseString);
+// assertEquals(pat.flags(), Pattern.CASE_INSENSITIVE);
+//
+// baseString = "((?i)a)";
+// pat = Pattern.compile(baseString);
+// assertEquals(pat.flags(), 0);
+//
+// pat = Pattern.compile("(?is)abc");
+// assertEquals(pat.flags(), Pattern.CASE_INSENSITIVE | Pattern.DOTALL);
+// }
+//END android-removed
+
+ /*
+ * Check default flags when they are not specified in pattern. Based on RI
+ * since could not find that info
+ */
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of flags() method for default flags.",
+ method = "flags",
+ args = {}
+ )
+ public void testFlagsCompileDefault() {
+ for (String pat : testPatternsAlt) {
+ try {
+ Pattern p = Pattern.compile(pat);
+ assertEquals(p.flags(), DEFAULT_FLAGS);
+ } catch (Exception e) {
+ fail("Unexpected exception: " + e);
+ }
+ }
+ }
+
+ /*
+ * Check that flags specified during compile are set properly This is a
+ * simple implementation that does not use flags combinations. Need to
+ * improve.
+ */
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String, int) & flags() methods. Checks that compilation was corect.",
+ method = "flags",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String, int) & flags() methods. Checks that compilation was corect.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ )
+ })
+ public void testFlagsCompileValid() {
+ for (String pat : testPatternsAlt) {
+ for (int flags : flagsSet) {
+ try {
+ Pattern p = Pattern.compile(pat, flags);
+ assertEquals(p.flags(), flags);
+ } catch (Exception e) {
+ fail("Unexpected exception: " + e);
+ }
+ }
+ }
+ }
+
+ /*
+ * Class under test for Pattern compile(String, int)
+ */
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.Checks that correct exceptions were thrown.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testCompileStringint() {
+ /*
+ * these tests are needed to verify that appropriate exceptions are
+ * thrown
+ */
+ String pattern = "b)a";
+ try {
+ Pattern.compile(pattern);
+ fail("Expected a PatternSyntaxException when compiling pattern: "
+ + pattern);
+ } catch (PatternSyntaxException e) {
+ // pass
+ }
+ pattern = "bcde)a";
+ try {
+ Pattern.compile(pattern);
+ fail("Expected a PatternSyntaxException when compiling pattern: "
+ + pattern);
+ } catch (PatternSyntaxException e) {
+ // pass
+ }
+ pattern = "bbg())a";
+ try {
+ Pattern pat = Pattern.compile(pattern);
+ fail("Expected a PatternSyntaxException when compiling pattern: "
+ + pattern);
+ } catch (PatternSyntaxException e) {
+ // pass
+ }
+
+ pattern = "cdb(?i))a";
+ try {
+ Pattern pat = Pattern.compile(pattern);
+ fail("Expected a PatternSyntaxException when compiling pattern: "
+ + pattern);
+ } catch (PatternSyntaxException e) {
+ // pass
+ }
+
+ /*
+ * This pattern should compile - HARMONY-2127
+ */
+// pattern = "x(?c)y";
+// Pattern.compile(pattern);
+
+ /*
+ * this pattern doesn't match any string, but should be compiled anyway
+ */
+ pattern = "(b\\1)a";
+ Pattern.compile(pattern);
+ }
+
+ /*
+ * Class under test for Pattern compile(String)
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.Checks that correct exceptions were thrown.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testQuantCompileNeg() {
+ String[] patterns = { "5{,2}", "{5asd", "{hgdhg", "{5,hjkh", "{,5hdsh",
+ "{5,3shdfkjh}" };
+ for (String element : patterns) {
+ try {
+ Pattern.compile(element);
+ fail("PatternSyntaxException was expected, but compilation succeeds");
+ } catch (PatternSyntaxException pse) {
+ continue;
+ }
+ }
+ // Regression for HARMONY-1365
+// BEGIN android-changed
+// Original regex contained some illegal stuff. Changed it slightly,
+// while maintaining the wicked character of this "mother of all
+// regexes".
+// String pattern = "(?![^\\<C\\f\\0146\\0270\\}&&[|\\02-\\x3E\\}|X-\\|]]{7,}+)[|\\\\\\x98\\<\\?\\u4FCFr\\,\\0025\\}\\004|\\0025-\\052\061]|(?<![|\\01-\\u829E])|(?<!\\p{Alpha})|^|(?-s:[^\\x15\\\\\\x24F\\a\\,\\a\\u97D8[\\x38\\a[\\0224-\\0306[^\\0020-\\u6A57]]]]??)(?uxix:[^|\\{\\[\\0367\\t\\e\\x8C\\{\\[\\074c\\]V[|b\\fu\\r\\0175\\<\\07f\\066s[^D-\\x5D]]])(?xx:^{5,}+)(?uuu)(?=^\\D)|(?!\\G)(?>\\G*?)(?![^|\\]\\070\\ne\\{\\t\\[\\053\\?\\\\\\x51\\a\\075\\0023-\\[&&[|\\022-\\xEA\\00-\\u41C2&&[^|a-\\xCC&&[^\\037\\uECB3\\u3D9A\\x31\\|\\<b\\0206\\uF2EC\\01m\\,\\ak\\a\\03&&\\p{Punct}]]]])(?-dxs:[|\\06-\\07|\\e-\\x63&&[|Tp\\u18A3\\00\\|\\xE4\\05\\061\\015\\0116C|\\r\\{\\}\\006\\xEA\\0367\\xC4\\01\\0042\\0267\\xBB\\01T\\}\\0100\\?[|\\[-\\u459B|\\x23\\x91\\rF\\0376[|\\?-\\x94\\0113-\\\\\\s]]]]{6}?)(?<=[^\\t-\\x42H\\04\\f\\03\\0172\\?i\\u97B6\\e\\f\\uDAC2])(?=\\B*+)(?>[^\\016\\r\\{\\,\\uA29D\\034\\02[\\02-\\[|\\t\\056\\uF599\\x62\\e\\<\\032\\uF0AC\\0026\\0205Q\\|\\\\\\06\\0164[|\\057-\\u7A98&&[\\061-g|\\|\\0276\\n\\042\\011\\e\\xE8\\x64B\\04\\u6D0EDW^\\p{Lower}]]]]?)(?<=[^\\n\\\\\\t\\u8E13\\,\\0114\\u656E\\xA5\\]&&[\\03-\\026|\\uF39D\\01\\{i\\u3BC2\\u14FE]])(?<=[^|\\uAE62\\054H\\|\\}&&^\\p{Space}])(?sxx)(?<=[\\f\\006\\a\\r\\xB4]*+)|(?x-xd:^{5}+)()";
+ String pattern = "(?![^\\<C\\f\\0146\\0270\\}&&[|\\02-\\x3E\\}|X-\\|]]{7,}+)[|\\\\\\x98\\<\\?\\u4FCFr\\,\\0025\\}\\004|\\0025-\\052\061]|(?<![|\\01-\\u829E])|(?<!\\p{Alpha})|^|(?-s:[^\\x15\\\\\\x24F\\a\\,\\a\\u97D8[\\x38\\a[\\0224-\\0306[^\\0020-\\u6A57]]]]??)(?uxix:[^|\\{\\[\\0367\\t\\e\\x8C\\{\\[\\074c\\]V[|b\\fu\\r\\0175\\<\\07f\\066s[^D-\\x5D]]])(?xx:^{5,}+)(?uuu)(?=^\\D)|(?!\\G)(?>\\.*?)(?![^|\\]\\070\\ne\\{\\t\\[\\053\\?\\\\\\x51\\a\\075\\0023-\\[&&[|\\022-\\xEA\\00-\\u41C2&&[^|a-\\xCC&&[^\\037\\uECB3\\u3D9A\\x31\\|\\<b\\0206\\uF2EC\\01m\\,\\ak\\a\\03&&\\p{Punct}]]]])(?-dxs:[|\\06-\\07|\\e-\\x63&&[|Tp\\u18A3\\00\\|\\xE4\\05\\061\\015\\0116C|\\r\\{\\}\\006\\xEA\\0367\\xC4\\01\\0042\\0267\\xBB\\01T\\}\\0100\\?[|\\[-\\u459B|\\x23\\x91\\rF\\0376[|\\?-\\x94\\0113-\\\\\\s]]]]{6}?)(?<=[^\\t-\\x42H\\04\\f\\03\\0172\\?i\\u97B6\\e\\f\\uDAC2])(?=\\.*+)(?>[^\\016\\r\\{\\,\\uA29D\\034\\02[\\02-\\[|\\t\\056\\uF599\\x62\\e\\<\\032\\uF0AC\\0026\\0205Q\\|\\\\\\06\\0164[|\\057-\\u7A98&&[\\061-g|\\|\\0276\\n\\042\\011\\e\\xE8\\x64B\\04\\u6D0EDW^\\p{Lower}]]]]?)(?<=[^\\n\\\\\\t\\u8E13\\,\\0114\\u656E\\xA5\\]&&[\\03-\\026|\\uF39D\\01\\{i\\u3BC2\\u14FE]])(?<=[^|\\uAE62\\054H\\|\\}&&^\\p{Space}])(?sxx)(?<=[\\f\\006\\a\\r\\xB4]{1,5})|(?x-xd:^{5}+)()";
+// END android-changed
+ assertNotNull(Pattern.compile(pattern));
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testQuantCompilePos() {
+ String[] patterns = {/* "(abc){1,3}", */"abc{2,}", "abc{5}" };
+ for (String element : patterns) {
+ Pattern.compile(element);
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile() method. Also tested methods from matcher: matches(), start(int), group(int)",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testQuantComposition() {
+ String pattern = "(a{1,3})aab";
+ java.util.regex.Pattern pat = java.util.regex.Pattern.compile(pattern);
+ java.util.regex.Matcher mat = pat.matcher("aaab");
+ mat.matches();
+ mat.start(1);
+ mat.group(1);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "",
+ method = "matches",
+ args = {java.lang.String.class, java.lang.CharSequence.class}
+ )
+ public void testMatches() {
+ String[][] posSeq = {
+ { "abb", "ababb", "abababbababb", "abababbababbabababbbbbabb" },
+ { "213567", "12324567", "1234567", "213213567",
+ "21312312312567", "444444567" },
+ { "abcdaab", "aab", "abaab", "cdaab", "acbdadcbaab" },
+ { "213234567", "3458", "0987654", "7689546432", "0398576",
+ "98432", "5" },
+ {
+ "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ",
+ "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
+ + "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ" },
+ { "ababbaAabababblice", "ababbaAliceababab", "ababbAabliceaaa",
+ "abbbAbbbliceaaa", "Alice" },
+ { "a123", "bnxnvgds156", "for", "while", "if", "struct" },
+ { "xy" }, { "xy" }, { "xcy" }
+
+ };
+
+ for (int i = 0; i < testPatterns.length; i++) {
+ for (int j = 0; j < posSeq[i].length; j++) {
+ assertTrue("Incorrect match: " + testPatterns[i] + " vs "
+ + posSeq[i][j], Pattern.matches(testPatterns[i],
+ posSeq[i][j]));
+ }
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies exception",
+ method = "matches",
+ args = {java.lang.String.class, java.lang.CharSequence.class}
+ )
+ public void testMatchesException() {
+ /* Negative assertion test. */
+ for (String aPattern : wrongTestPatterns) {
+ try {
+ Pattern.matches(aPattern, "Foo");
+ fail("PatternSyntaxException is expected");
+ } catch (PatternSyntaxException pse) {
+ /* OKAY */
+ } catch (Exception e) {
+ fail("Unexpected exception: " + e);
+ }
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies the functionality of matches(java.lang.String,java.lang.CharSequence) method.",
+ method = "matches",
+ args = {java.lang.String.class, java.lang.CharSequence.class}
+ )
+ public void testTimeZoneIssue() {
+ Pattern p = Pattern.compile("GMT(\\+|\\-)(\\d+)(:(\\d+))?");
+ Matcher m = p.matcher("GMT-9:45");
+ assertTrue(m.matches());
+ assertEquals("-", m.group(1));
+ assertEquals("9", m.group(2));
+ assertEquals(":45", m.group(3));
+ assertEquals("45", m.group(4));
+ }
+
+// BEGIN android-changed
+// Removed one pattern that is buggy on the JDK. We don't want to duplicate that.
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of matches(java.lang.String,java.lang.CharSequence) method.",
+ method = "matches",
+ args = {java.lang.String.class, java.lang.CharSequence.class}
+ )
+ public void testCompileRanges() {
+ String[] correctTestPatterns = { "[^]*abb]*", /* "[^a-d[^m-p]]*abb", */
+ "[a-d\\d]*abb", "[abc]*abb", "[a-e&&[de]]*abb", "[^abc]*abb",
+ "[a-e&&[^de]]*abb", "[a-z&&[^m-p]]*abb", "[a-d[m-p]]*abb",
+ "[a-zA-Z]*abb", "[+*?]*abb", "[^+*?]*abb" };
+
+ String[] inputSecuence = { "kkkk", /* "admpabb", */ "abcabcd124654abb",
+ "abcabccbacababb", "dededededededeedabb", "gfdhfghgdfghabb",
+ "accabacbcbaabb", "acbvfgtyabb", "adbcacdbmopabcoabb",
+ "jhfkjhaSDFGHJkdfhHNJMjkhfabb", "+*??+*abb", "sdfghjkabb" };
+
+ Pattern pat;
+
+ for (int i = 0; i < correctTestPatterns.length; i++) {
+ assertTrue("pattern: " + correctTestPatterns[i] + " input: "
+ + inputSecuence[i], Pattern.matches(correctTestPatterns[i],
+ inputSecuence[i]));
+
+ }
+
+ String[] wrongInputSecuence = { "]", /* "admpkk", */ "abcabcd124k654abb",
+ "abwcabccbacababb", "abababdeababdeabb", "abcabcacbacbabb",
+ "acdcbecbaabb", "acbotyabb", "adbcaecdbmopabcoabb",
+ "jhfkjhaSDFGHJk;dfhHNJMjkhfabb", "+*?a?+*abb", "sdf+ghjkabb" };
+
+ for (int i = 0; i < correctTestPatterns.length; i++) {
+ assertFalse("pattern: " + correctTestPatterns[i] + " input: "
+ + wrongInputSecuence[i], Pattern.matches(
+ correctTestPatterns[i], wrongInputSecuence[i]));
+
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of matches(java.lang.String,java.lang.CharSequence) method for ranged patterns.",
+ method = "matches",
+ args = {java.lang.String.class, java.lang.CharSequence.class}
+ )
+ public void testRangesSpecialCases() {
+ String neg_patterns[] = { "[a-&&[b-c]]", "[a-\\w]", "[b-a]", "[]" };
+
+ for (String element : neg_patterns) {
+ try {
+ Pattern.compile(element);
+ fail("PatternSyntaxException was expected: " + element);
+ } catch (PatternSyntaxException pse) {
+ }
+ }
+
+ String pos_patterns[] = { "[-]+", "----", "[a-]+", "a-a-a-a-aa--",
+ "[\\w-a]+", "123-2312--aaa-213", "[a-]]+", "-]]]]]]]]]]]]]]]" };
+
+ for (int i = 0; i < pos_patterns.length; i++) {
+ String pat = pos_patterns[i++];
+ String inp = pos_patterns[i];
+ assertTrue("pattern: " + pat + " input: " + inp, Pattern.matches(
+ pat, inp));
+ }
+ }
+ // END android-changed
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies the functionality of matches(java.lang.String,java.lang.CharSequence) method.",
+ method = "matches",
+ args = {java.lang.String.class, java.lang.CharSequence.class}
+ )
+public void testZeroSymbols() {
+ assertTrue(Pattern.matches("[\0]*abb", "\0\0\0\0\0\0abb"));
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of matcher(java.lang.String) method.",
+ method = "matcher",
+ args = {CharSequence.class}
+ )
+ public void testEscapes() {
+ Pattern pat = Pattern.compile("\\Q{]()*?");
+ Matcher mat = pat.matcher("{]()*?");
+
+ assertTrue(mat.matches());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testBug181() {
+ Pattern.compile("[\\t-\\r]");
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testOrphanQuantifiers() {
+ try {
+ Pattern.compile("+++++");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException pse) {
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testOrphanQuantifiers2() {
+ try {
+ Pattern pat = Pattern.compile("\\d+*");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException pse) {
+ }
+ }
+
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ })
+ public void testBug197() {
+ Object[] vals = { ":", new Integer(2),
+ new String[] { "boo", "and:foo" }, ":", new Integer(5),
+ new String[] { "boo", "and", "foo" }, ":", new Integer(-2),
+ new String[] { "boo", "and", "foo" }, ":", new Integer(3),
+ new String[] { "boo", "and", "foo" }, ":", new Integer(1),
+ new String[] { "boo:and:foo" }, "o", new Integer(5),
+ new String[] { "b", "", ":and:f", "", "" }, "o",
+ new Integer(4), new String[] { "b", "", ":and:f", "o" }, "o",
+ new Integer(-2), new String[] { "b", "", ":and:f", "", "" },
+ "o", new Integer(0), new String[] { "b", "", ":and:f" } };
+
+ for (int i = 0; i < vals.length / 3;) {
+ String[] res = Pattern.compile(vals[i++].toString()).split(
+ "boo:and:foo", ((Integer) vals[i++]).intValue());
+ String[] expectedRes = (String[]) vals[i++];
+
+ assertEquals(expectedRes.length, res.length);
+
+ for (int j = 0; j < expectedRes.length; j++) {
+ assertEquals(expectedRes[j], res[j]);
+ }
+ }
+ }
+
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testURIPatterns() {
+ String URI_REGEXP_STR = "^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\\?([^#]*))?(#(.*))?";
+ String SCHEME_REGEXP_STR = "^[a-zA-Z]{1}[\\w+-.]+$";
+ String REL_URI_REGEXP_STR = "^(//([^/?#]*))?([^?#]*)(\\?([^#]*))?(#(.*))?";
+ String IPV6_REGEXP_STR = "^[0-9a-fA-F\\:\\.]+(\\%\\w+)?$";
+ String IPV6_REGEXP_STR2 = "^\\[[0-9a-fA-F\\:\\.]+(\\%\\w+)?\\]$";
+ String IPV4_REGEXP_STR = "^[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}$";
+ String HOSTNAME_REGEXP_STR = "\\w+[\\w\\-\\.]*";
+
+ Pattern URI_REGEXP = Pattern.compile(URI_REGEXP_STR);
+ Pattern REL_URI_REGEXP = Pattern.compile(REL_URI_REGEXP_STR);
+ Pattern SCHEME_REGEXP = Pattern.compile(SCHEME_REGEXP_STR);
+ Pattern IPV4_REGEXP = Pattern.compile(IPV4_REGEXP_STR);
+ Pattern IPV6_REGEXP = Pattern.compile(IPV6_REGEXP_STR);
+ Pattern IPV6_REGEXP2 = Pattern.compile(IPV6_REGEXP_STR2);
+ Pattern HOSTNAME_REGEXP = Pattern.compile(HOSTNAME_REGEXP_STR);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testFindBoundaryCases1() {
+ Pattern pat = Pattern.compile(".*\n");
+ Matcher mat = pat.matcher("a\n");
+
+ mat.find();
+ assertEquals("a\n", mat.group());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testFindBoundaryCases2() {
+ Pattern pat = Pattern.compile(".*A");
+ Matcher mat = pat.matcher("aAa");
+
+ mat.find();
+ assertEquals("aA", mat.group());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testFindBoundaryCases3() {
+ Pattern pat = Pattern.compile(".*A");
+ Matcher mat = pat.matcher("a\naA\n");
+
+ mat.find();
+ assertEquals("aA", mat.group());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testFindBoundaryCases4() {
+ Pattern pat = Pattern.compile("A.*");
+ Matcher mat = pat.matcher("A\n");
+
+ mat.find();
+ assertEquals("A", mat.group());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testFindBoundaryCases5() {
+ Pattern pat = Pattern.compile(".*A.*");
+ Matcher mat = pat.matcher("\nA\naaa\nA\naaAaa\naaaA\n");
+ // Matcher mat = pat.matcher("\nA\n");
+ String[] res = { "A", "A", "aaAaa", "aaaA" };
+ int k = 0;
+ for (; mat.find(); k++) {
+ assertEquals(res[k], mat.group());
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testFindBoundaryCases6() {
+ String[] res = { "", "a", "", "" };
+ Pattern pat = Pattern.compile(".*");
+ Matcher mat = pat.matcher("\na\n");
+ int k = 0;
+
+ for (; mat.find(); k++) {
+ assertEquals(res[k], mat.group());
+ }
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testBackReferences() {
+ Pattern pat = Pattern.compile("(\\((\\w*):(.*):(\\2)\\))");
+ Matcher mat = pat
+ .matcher("(start1: word :start1)(start2: word :start2)");
+ int k = 1;
+ for (; mat.find(); k++) {
+ assertEquals("start" + k, mat.group(2));
+ assertEquals(" word ", mat.group(3));
+ assertEquals("start" + k, mat.group(4));
+ }
+
+ assertEquals(3, k);
+ pat = Pattern.compile(".*(.)\\1");
+ mat = pat.matcher("saa");
+ assertTrue(mat.matches());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testNewLine() {
+ Pattern pat = Pattern.compile("(^$)*\n", Pattern.MULTILINE);
+ Matcher mat = pat.matcher("\r\n\n");
+ int counter = 0;
+ while (mat.find()) {
+ counter++;
+ }
+ assertEquals(2, counter);
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testFindGreedy() {
+ Pattern pat = Pattern.compile(".*aaa", Pattern.DOTALL);
+ Matcher mat = pat.matcher("aaaa\naaa\naaaaaa");
+ mat.matches();
+ assertEquals(15, mat.end());
+ }
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies serialization/deserialization.",
+ method = "!SerializationSelf",
+ args = {}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies serialization/deserialization.",
+ method = "!SerializationGolden",
+ args = {}
+ )
+ })
+ public void testSerialization() throws Exception {
+ Pattern pat = Pattern.compile("a*bc");
+ SerializableAssert comparator = new SerializableAssert() {
+ public void assertDeserialized(Serializable initial,
+ Serializable deserialized) {
+ assertEquals(((Pattern) initial).toString(),
+ ((Pattern) deserialized).toString());
+ }
+ };
+ SerializationTest.verifyGolden(this, pat, comparator);
+ SerializationTest.verifySelf(pat, comparator);
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testSOLQuant() {
+ Pattern pat = Pattern.compile("$*", Pattern.MULTILINE);
+ Matcher mat = pat.matcher("\n\n");
+ int counter = 0;
+ while (mat.find()) {
+ counter++;
+ }
+
+ assertEquals(3, counter);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testIllegalEscape() {
+ try {
+ Pattern.compile("\\y");
+ fail("PatternSyntaxException expected");
+ } catch (PatternSyntaxException pse) {
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testEmptyFamily() {
+ Pattern.compile("\\p{Lower}");
+ String a = "*";
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testNonCaptConstr() {
+ // Flags
+ Pattern pat = Pattern.compile("(?i)b*(?-i)a*");
+ assertTrue(pat.matcher("bBbBaaaa").matches());
+ assertFalse(pat.matcher("bBbBAaAa").matches());
+
+ // Non-capturing groups
+ pat = Pattern.compile("(?i:b*)a*");
+ assertTrue(pat.matcher("bBbBaaaa").matches());
+ assertFalse(pat.matcher("bBbBAaAa").matches());
+
+ pat = Pattern
+ // 1 2 3 4 5 6 7 8 9 10 11
+ .compile("(?:-|(-?\\d+\\d\\d\\d))?(?:-|-(\\d\\d))?(?:-|-(\\d\\d))?(T)?(?:(\\d\\d):(\\d\\d):(\\d\\d)(\\.\\d+)?)?(?:(?:((?:\\+|\\-)\\d\\d):(\\d\\d))|(Z))?");
+ Matcher mat = pat.matcher("-1234-21-31T41:51:61.789+71:81");
+ assertTrue(mat.matches());
+ assertEquals("-1234", mat.group(1));
+ assertEquals("21", mat.group(2));
+ assertEquals("31", mat.group(3));
+ assertEquals("T", mat.group(4));
+ assertEquals("41", mat.group(5));
+ assertEquals("51", mat.group(6));
+ assertEquals("61", mat.group(7));
+ assertEquals(".789", mat.group(8));
+ assertEquals("+71", mat.group(9));
+ assertEquals("81", mat.group(10));
+
+ // positive lookahead
+ pat = Pattern.compile(".*\\.(?=log$).*$");
+ assertTrue(pat.matcher("a.b.c.log").matches());
+ assertFalse(pat.matcher("a.b.c.log.").matches());
+
+ // negative lookahead
+ pat = Pattern.compile(".*\\.(?!log$).*$");
+ assertFalse(pat.matcher("abc.log").matches());
+ assertTrue(pat.matcher("abc.logg").matches());
+
+ // positive lookbehind
+ pat = Pattern.compile(".*(?<=abc)\\.log$");
+ assertFalse(pat.matcher("cde.log").matches());
+ assertTrue(pat.matcher("abc.log").matches());
+
+ // negative lookbehind
+ pat = Pattern.compile(".*(?<!abc)\\.log$");
+ assertTrue(pat.matcher("cde.log").matches());
+ assertFalse(pat.matcher("abc.log").matches());
+
+ // atomic group
+ pat = Pattern.compile("(?>a*)abb");
+ assertFalse(pat.matcher("aaabb").matches());
+ pat = Pattern.compile("(?>a*)bb");
+ assertTrue(pat.matcher("aaabb").matches());
+
+ pat = Pattern.compile("(?>a|aa)aabb");
+ assertTrue(pat.matcher("aaabb").matches());
+ pat = Pattern.compile("(?>aa|a)aabb");
+ assertFalse(pat.matcher("aaabb").matches());
+
+// BEGIN android-removed
+// Questionable constructs that ICU doesn't support.
+// // quantifiers over look ahead
+// pat = Pattern.compile(".*(?<=abc)*\\.log$");
+// assertTrue(pat.matcher("cde.log").matches());
+// pat = Pattern.compile(".*(?<=abc)+\\.log$");
+// assertFalse(pat.matcher("cde.log").matches());
+// END android-removed
+
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testCorrectReplacementBackreferencedJointSet() {
+ Pattern pat = Pattern.compile("ab(a)*\\1");
+ pat = Pattern.compile("abc(cd)fg");
+ pat = Pattern.compile("aba*cd");
+ pat = Pattern.compile("ab(a)*+cd");
+ pat = Pattern.compile("ab(a)*?cd");
+ pat = Pattern.compile("ab(a)+cd");
+ pat = Pattern.compile(".*(.)\\1");
+ pat = Pattern.compile("ab((a)|c|d)e");
+ pat = Pattern.compile("abc((a(b))cd)");
+ pat = Pattern.compile("ab(a)++cd");
+ pat = Pattern.compile("ab(a)?(c)d");
+ pat = Pattern.compile("ab(a)?+cd");
+ pat = Pattern.compile("ab(a)??cd");
+ pat = Pattern.compile("ab(a)??cd");
+ pat = Pattern.compile("ab(a){1,3}?(c)d");
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testCompilePatternWithTerminatorMark() {
+ Pattern pat = Pattern.compile("a\u0000\u0000cd");
+ Matcher mat = pat.matcher("a\u0000\u0000cd");
+ assertTrue(mat.matches());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testAlternations() {
+ String baseString = "|a|bc";
+ Pattern pat = Pattern.compile(baseString);
+ Matcher mat = pat.matcher("");
+
+ assertTrue(mat.matches());
+
+ baseString = "a||bc";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("");
+ assertTrue(mat.matches());
+
+ baseString = "a|bc|";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("");
+ assertTrue(mat.matches());
+
+ baseString = "a|b|";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("");
+ assertTrue(mat.matches());
+
+ baseString = "a(|b|cd)e";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("ae");
+ assertTrue(mat.matches());
+
+ baseString = "a(b||cd)e";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("ae");
+ assertTrue(mat.matches());
+
+ baseString = "a(b|cd|)e";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("ae");
+ assertTrue(mat.matches());
+
+ baseString = "a(b|c|)e";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("ae");
+ assertTrue(mat.matches());
+
+ baseString = "a(|)e";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("ae");
+ assertTrue(mat.matches());
+
+ baseString = "|";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("");
+ assertTrue(mat.matches());
+
+ baseString = "a(?:|)e";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("ae");
+ assertTrue(mat.matches());
+
+ baseString = "a||||bc";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("");
+ assertTrue(mat.matches());
+
+ baseString = "(?i-is)|a";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher("a");
+ assertTrue(mat.matches());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testMatchWithGroups() {
+ String baseString = "jwkerhjwehrkwjehrkwjhrwkjehrjwkehrjkwhrkwehrkwhrkwrhwkhrwkjehr";
+ String pattern = ".*(..).*\\1.*";
+ assertTrue(Pattern.compile(pattern).matcher(baseString).matches());
+
+ baseString = "saa";
+ pattern = ".*(.)\\1";
+ assertTrue(Pattern.compile(pattern).matcher(baseString).matches());
+ assertTrue(Pattern.compile(pattern).matcher(baseString).find());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies split method for empty string.",
+ method = "split",
+ args = {java.lang.CharSequence.class}
+ )
+ public void testSplitEmptyCharSequence() {
+ String s1 = "";
+ String[] arr = s1.split(":");
+ assertEquals(arr.length, 1);
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies the functionality of compile(java.lang.String) & split(java.lang.CharSequence, int) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies the functionality of compile(java.lang.String) & split(java.lang.CharSequence, int) methods.",
+ method = "split",
+ args = {java.lang.CharSequence.class, int.class}
+ )
+ })
+ public void testSplitEndsWithPattern() {
+ assertEquals(",,".split(",", 3).length, 3);
+ assertEquals(",,".split(",", 4).length, 3);
+
+ assertEquals(Pattern.compile("o").split("boo:and:foo", 5).length, 5);
+ assertEquals(Pattern.compile("b").split("ab", -1).length, 2);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies the functionality of matches(java.lang.String), java.lang.CharSequence) method for case insensitive flags.",
+ method = "matches",
+ args = {java.lang.String.class, java.lang.CharSequence.class}
+ )
+ public void testCaseInsensitiveFlag() {
+ assertTrue(Pattern.matches("(?i-:AbC)", "ABC"));
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testEmptyGroups() {
+ Pattern pat = Pattern.compile("ab(?>)cda");
+ Matcher mat = pat.matcher("abcda");
+ assertTrue(mat.matches());
+
+ pat = Pattern.compile("ab()");
+ mat = pat.matcher("ab");
+ assertTrue(mat.matches());
+
+ pat = Pattern.compile("abc(?:)(..)");
+ mat = pat.matcher("abcgf");
+ assertTrue(mat.matches());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & compile(java.lang.String, int) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & compile(java.lang.String, int) methods.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ )
+ })
+ public void testCompileNonCaptGroup() {
+ boolean isCompiled = false;
+
+ try {
+// BEGIN android-change
+// We don't have canonical equivalence.
+ Pattern pat = Pattern.compile("(?:)");
+ pat = Pattern.compile("(?:)", Pattern.DOTALL);
+ pat = Pattern.compile("(?:)", Pattern.CASE_INSENSITIVE);
+ pat = Pattern.compile("(?:)", Pattern.COMMENTS | Pattern.UNIX_LINES);
+// END android-change
+ isCompiled = true;
+ } catch (PatternSyntaxException e) {
+ System.out.println(e);
+ }
+ assertTrue(isCompiled);
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testEmbeddedFlags() {
+ String baseString = "(?i)((?s)a)";
+ String testString = "A";
+ Pattern pat = Pattern.compile(baseString);
+ Matcher mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?x)(?i)(?s)(?d)a";
+ testString = "A";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "(?x)(?i)(?s)(?d)a.";
+ testString = "a\n";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "abc(?x:(?i)(?s)(?d)a.)";
+ testString = "abcA\n";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ baseString = "abc((?x)d)(?i)(?s)a";
+ testString = "abcdA";
+ pat = Pattern.compile(baseString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testAltWithFlags() {
+ boolean isCompiled = false;
+
+ try {
+ Pattern pat = Pattern.compile("|(?i-xi)|()");
+ isCompiled = true;
+ } catch (PatternSyntaxException e) {
+ System.out.println(e);
+ }
+ assertTrue(isCompiled);
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+public void testRestoreFlagsAfterGroup() {
+ String baseString = "abc((?x)d) a";
+ String testString = "abcd a";
+ Pattern pat = Pattern.compile(baseString);
+ Matcher mat = pat.matcher(testString);
+
+ assertTrue(mat.matches());
+ }
+
+ /*
+ * Verify if the Pattern support the following character classes:
+ * \p{javaLowerCase} \p{javaUpperCase} \p{javaWhitespace} \p{javaMirrored}
+ */
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) method.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ public void testCompileCharacterClass() {
+ // Regression for HARMONY-606, 696
+ Pattern pattern = Pattern.compile("\\p{javaLowerCase}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaUpperCase}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaWhitespace}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaMirrored}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaDefined}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaDigit}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaIdentifierIgnorable}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaISOControl}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaJavaIdentifierPart}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaJavaIdentifierStart}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaLetter}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaLetterOrDigit}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaSpaceChar}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaTitleCase}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaUnicodeIdentifierPart}");
+ assertNotNull(pattern);
+
+ pattern = Pattern.compile("\\p{javaUnicodeIdentifierStart}");
+ assertNotNull(pattern);
+ }
+
+ /**
+ * s original test was fixed to pass on RI
+ */
+
+// BEGIN android-removed
+// We don't have canonical equivalence.
+// public void testCanonEqFlag() {
+//
+// /*
+// * for decompositions see
+// * http://www.unicode.org/Public/4.0-Update/UnicodeData-4.0.0.txt
+// * http://www.unicode.org/reports/tr15/#Decomposition
+// */
+// String baseString;
+// String testString;
+// Pattern pat;
+// Matcher mat;
+//
+// baseString = "ab(a*)\\1";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+//
+// baseString = "a(abcdf)d";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+//
+// baseString = "aabcdfd";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+//
+// // \u01E0 -> \u0226\u0304 ->\u0041\u0307\u0304
+// // \u00CC -> \u0049\u0300
+//
+// /*
+// * baseString = "\u01E0\u00CCcdb(ac)"; testString =
+// * "\u0226\u0304\u0049\u0300cdbac"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// */
+// baseString = "\u01E0cdb(a\u00CCc)";
+// testString = "\u0041\u0307\u0304cdba\u0049\u0300c";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+//
+// baseString = "a\u00CC";
+// testString = "a\u0049\u0300";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+//
+// /*
+// * baseString = "\u0226\u0304cdb(ac\u0049\u0300)"; testString =
+// * "\u01E0cdbac\u00CC"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// *
+// * baseString = "cdb(?:\u0041\u0307\u0304\u00CC)"; testString =
+// * "cdb\u0226\u0304\u0049\u0300"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// *
+// * baseString = "\u01E0[a-c]\u0049\u0300cdb(ac)"; testString =
+// * "\u01E0b\u00CCcdbac"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// *
+// * baseString = "\u01E0|\u00CCcdb(ac)"; testString =
+// * "\u0041\u0307\u0304"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// *
+// * baseString = "\u00CC?cdb(ac)*(\u01E0)*[a-c]"; testString =
+// * "cdb\u0041\u0307\u0304b"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// */
+// baseString = "a\u0300";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher("a\u00E0a");
+// assertTrue(mat.find());
+//
+// /*
+// * baseString = "\u7B20\uF9F8abc"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher("\uF9F8\uF9F8abc");
+// * assertTrue(mat.matches());
+// *
+// * //\u01F9 -> \u006E\u0300 //\u00C3 -> \u0041\u0303
+// *
+// * baseString = "cdb(?:\u00C3\u006E\u0300)"; testString =
+// * "cdb\u0041\u0303\u01F9"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// *
+// * //\u014C -> \u004F\u0304 //\u0163 -> \u0074\u0327
+// *
+// * baseString = "cdb(?:\u0163\u004F\u0304)"; testString =
+// * "cdb\u0074\u0327\u014C"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// */
+// // \u00E1->a\u0301
+// // canonical ordering takes place \u0301\u0327 -> \u0327\u0301
+// baseString = "c\u0327\u0301";
+// testString = "c\u0301\u0327";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+//
+// /*
+// * Hangul decompositions
+// */
+// // \uD4DB->\u1111\u1171\u11B6
+// // \uD21E->\u1110\u116D\u11B5
+// // \uD264->\u1110\u1170
+// // not Hangul:\u0453->\u0433\u0301
+// baseString = "a\uD4DB\u1111\u1171\u11B6\uD264";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+//
+// baseString = "\u0453c\uD4DB";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+//
+// baseString = "a\u1110\u116D\u11B5b\uD21Ebc";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+//
+// /*
+// * baseString = "\uD4DB\uD21E\u1110\u1170cdb(ac)"; testString =
+// * "\u1111\u1171\u11B6\u1110\u116D\u11B5\uD264cdbac"; pat =
+// * Pattern.compile(baseString, Pattern.CANON_EQ); mat =
+// * pat.matcher(testString); assertTrue(mat.matches());
+// */
+// baseString = "\uD4DB\uD264cdb(a\uD21Ec)";
+// testString = "\u1111\u1171\u11B6\u1110\u1170cdba\u1110\u116D\u11B5c";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+//
+// baseString = "a\uD4DB";
+// testString = "a\u1111\u1171\u11B6";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+//
+// baseString = "a\uD21E";
+// testString = "a\u1110\u116D\u11B5";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+//
+// /*
+// * baseString = "\u1111\u1171\u11B6cdb(ac\u1110\u116D\u11B5)";
+// * testString = "\uD4DBcdbac\uD21E"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// *
+// * baseString = "cdb(?:\u1111\u1171\u11B6\uD21E)"; testString =
+// * "cdb\uD4DB\u1110\u116D\u11B5"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// *
+// * baseString = "\uD4DB[a-c]\u1110\u116D\u11B5cdb(ac)"; testString =
+// * "\uD4DBb\uD21Ecdbac"; pat = Pattern.compile(baseString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// */
+// baseString = "\uD4DB|\u00CCcdb(ac)";
+// testString = "\u1111\u1171\u11B6";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+//
+// baseString = "\uD4DB|\u00CCcdb(ac)";
+// testString = "\u1111\u1171";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertFalse(mat.matches());
+//
+// baseString = "\u00CC?cdb(ac)*(\uD4DB)*[a-c]";
+// testString = "cdb\u1111\u1171\u11B6b";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+//
+// baseString = "\uD4DB";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher("a\u1111\u1171\u11B6a");
+// assertTrue(mat.find());
+//
+// baseString = "\u1111";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher("bcda\uD4DBr");
+// assertFalse(mat.find());
+// }
+//
+// /**
+// * s original test was fixed to pass on RI
+// */
+//
+// public void testIndexesCanonicalEq() {
+// String baseString;
+// String testString;
+// Pattern pat;
+// Matcher mat;
+//
+// baseString = "\uD4DB";
+// pat = Pattern.compile(baseString, Pattern.CANON_EQ);
+// mat = pat.matcher("bcda\u1111\u1171\u11B6awr");
+// assertTrue(mat.find());
+// assertEquals(mat.start(), 4);
+// assertEquals(mat.end(), 7);
+//
+// /*
+// * baseString = "\uD4DB\u1111\u1171\u11B6"; pat =
+// * Pattern.compile(baseString, Pattern.CANON_EQ); mat =
+// * pat.matcher("bcda\u1111\u1171\u11B6\uD4DBawr");
+// * assertTrue(mat.find()); assertEquals(mat.start(), 4);
+// * assertEquals(mat.end(), 8);
+// *
+// * baseString = "\uD4DB\uD21E\u1110\u1170"; testString =
+// * "abcabc\u1111\u1171\u11B6\u1110\u116D\u11B5\uD264cdbac"; pat =
+// * Pattern.compile(baseString, Pattern.CANON_EQ); mat =
+// * pat.matcher(testString); assertTrue(mat.find());
+// * assertEquals(mat.start(), 6); assertEquals(mat.end(), 13);
+// */}
+//
+// /**
+// * s original test was fixed to pass on RI
+// */
+//
+// public void testCanonEqFlagWithSupplementaryCharacters() {
+//
+// /*
+// * \u1D1BF->\u1D1BB\u1D16F->\u1D1B9\u1D165\u1D16F in UTF32
+// * \uD834\uDDBF->\uD834\uDDBB\uD834\uDD6F
+// * ->\uD834\uDDB9\uD834\uDD65\uD834\uDD6F in UTF16
+// */
+// String patString = "abc\uD834\uDDBFef";
+// String testString = "abc\uD834\uDDB9\uD834\uDD65\uD834\uDD6Fef";
+// Pattern pat = Pattern.compile(patString, Pattern.CANON_EQ);
+// Matcher mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+// /*
+// * testString = "abc\uD834\uDDBB\uD834\uDD6Fef"; mat =
+// * pat.matcher(testString); assertTrue(mat.matches());
+// *
+// * patString = "abc\uD834\uDDBB\uD834\uDD6Fef"; testString =
+// * "abc\uD834\uDDBFef"; pat = Pattern.compile(patString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// */
+// testString = "abc\uD834\uDDB9\uD834\uDD65\uD834\uDD6Fef";
+// mat = pat.matcher(testString);
+// assertTrue(mat.matches());
+// /*
+// * patString = "abc\uD834\uDDB9\uD834\uDD65\uD834\uDD6Fef"; testString =
+// * "abc\uD834\uDDBFef"; pat = Pattern.compile(patString,
+// * Pattern.CANON_EQ); mat = pat.matcher(testString);
+// * assertTrue(mat.matches());
+// *
+// * testString = "abc\uD834\uDDBB\uD834\uDD6Fef"; mat =
+// * pat.matcher(testString); assertTrue(mat.matches());
+// */
+// /*
+// * testSupplementary characters with no decomposition
+// */
+// /*
+// * patString = "a\uD9A0\uDE8Ebc\uD834\uDDBB\uD834\uDD6Fe\uDE8Ef";
+// * testString = "a\uD9A0\uDE8Ebc\uD834\uDDBFe\uDE8Ef"; pat =
+// * Pattern.compile(patString, Pattern.CANON_EQ); mat =
+// * pat.matcher(testString); assertTrue(mat.matches());
+// */}
+// END android-removed
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testRangesWithSurrogatesSupplementary() {
+ String patString = "[abc\uD8D2]";
+ String testString = "\uD8D2";
+ Pattern pat = Pattern.compile(patString);
+ Matcher mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "a";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "ef\uD8D2\uDD71gh";
+ mat = pat.matcher(testString);
+ assertFalse(mat.find());
+
+ testString = "ef\uD8D2gh";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ patString = "[abc\uD8D3&&[c\uD8D3]]";
+ testString = "c";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "a";
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ testString = "ef\uD8D3\uDD71gh";
+ mat = pat.matcher(testString);
+ assertFalse(mat.find());
+
+ testString = "ef\uD8D3gh";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ patString = "[abc\uD8D3\uDBEE\uDF0C&&[c\uD8D3\uDBEE\uDF0C]]";
+ testString = "c";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "\uDBEE\uDF0C";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "ef\uD8D3\uDD71gh";
+ mat = pat.matcher(testString);
+ assertFalse(mat.find());
+
+ testString = "ef\uD8D3gh";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ patString = "[abc\uDBFC]\uDDC2cd";
+ testString = "\uDBFC\uDDC2cd";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ testString = "a\uDDC2cd";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testSequencesWithSurrogatesSupplementary() {
+ String patString = "abcd\uD8D3";
+ String testString = "abcd\uD8D3\uDFFC";
+ Pattern pat = Pattern.compile(patString);
+ Matcher mat = pat.matcher(testString);
+// BEGIN android-changed
+// This one really doesn't make sense, as the above is a corrupt surrogate.
+// Even if it's matched by the JDK, it's more of a bug than of a behavior one
+// might want to duplicate.
+// assertFalse(mat.find());
+// END android-changed
+ testString = "abcd\uD8D3abc";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ patString = "ab\uDBEFcd";
+ testString = "ab\uDBEFcd";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ patString = "\uDFFCabcd";
+ testString = "\uD8D3\uDFFCabcd";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.find());
+
+ testString = "abc\uDFFCabcdecd";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ patString = "\uD8D3\uDFFCabcd";
+ testString = "abc\uD8D3\uD8D3\uDFFCabcd";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+ }
+
+ /**
+ * s original test was fixed to pass on RI
+ */
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testPredefinedClassesWithSurrogatesSupplementary() {
+ String patString = "[123\\D]";
+ String testString = "a";
+ Pattern pat = Pattern.compile(patString);
+ Matcher mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ testString = "5";
+ mat = pat.matcher(testString);
+ assertFalse(mat.find());
+
+ testString = "3";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ // low surrogate
+ testString = "\uDFC4";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ // high surrogate
+ testString = "\uDADA";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ testString = "\uDADA\uDFC4";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ patString = "[123[^\\p{javaDigit}]]";
+ testString = "a";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ testString = "5";
+ mat = pat.matcher(testString);
+ assertFalse(mat.find());
+
+ testString = "3";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ // low surrogate
+ testString = "\uDFC4";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ // high surrogate
+ testString = "\uDADA";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ testString = "\uDADA\uDFC4";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ // surrogate characters
+ patString = "\\p{Cs}";
+ testString = "\uD916\uDE27";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+
+ /*
+ * see http://www.unicode.org/reports/tr18/#Supplementary_Characters we
+ * have to treat text as code points not code units. \\p{Cs} matches any
+ * surrogate character but here testString is a one code point
+ * consisting of two code units (two surrogate characters) so we find
+ * nothing
+ */
+ // assertFalse(mat.find());
+ // swap low and high surrogates
+ testString = "\uDE27\uD916";
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ patString = "[\uD916\uDE271\uD91623&&[^\\p{Cs}]]";
+ testString = "1";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ testString = "\uD916";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.find());
+
+ testString = "\uD916\uDE27";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.find());
+
+ // \uD9A0\uDE8E=\u7828E
+ // \u78281=\uD9A0\uDE81
+ patString = "[a-\uD9A0\uDE8E]";
+ testString = "\uD9A0\uDE81";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & compile(java.lang.String, int) matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & compile(java.lang.String, int) matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & compile(java.lang.String, int) matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testDotConstructionWithSurrogatesSupplementary() {
+ String patString = ".";
+ String testString = "\uD9A0\uDE81";
+ Pattern pat = Pattern.compile(patString);
+ Matcher mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "\uDE81";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "\uD9A0";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "\n";
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ patString = ".*\uDE81";
+ testString = "\uD9A0\uDE81\uD9A0\uDE81\uD9A0\uDE81";
+ pat = Pattern.compile(patString);
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ testString = "\uD9A0\uDE81\uD9A0\uDE81\uDE81";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ patString = ".*";
+ testString = "\uD9A0\uDE81\n\uD9A0\uDE81\uD9A0\n\uDE81";
+ pat = Pattern.compile(patString, Pattern.DOTALL);
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+ }
+
+ /**
+ * s java.util.regex.Pattern.quote(String)
+ */
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "quote",
+ args = {java.lang.String.class}
+ )
+ public void test_quoteLjava_lang_String() {
+ for (String aPattern : testPatterns) {
+ Pattern p = Pattern.compile(aPattern);
+ try {
+ assertEquals("quote was wrong for plain text", "\\Qtest\\E", p
+ .quote("test"));
+ assertEquals("quote was wrong for text with quote sign",
+ "\\Q\\Qtest\\E", p.quote("\\Qtest"));
+ assertEquals("quote was wrong for quotted text",
+ "\\Q\\Qtest\\E\\\\E\\Q\\E", p.quote("\\Qtest\\E"));
+ } catch (Exception e) {
+ fail("Unexpected exception: " + e);
+ }
+ }
+ }
+
+ /**
+ * s java.util.regex.Pattern.matcher(String, CharSequence)
+ * coped from test for matches method
+ */
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void test_matcherLjava_lang_StringLjava_lang_CharSequence() {
+ String[][] posSeq = {
+ { "abb", "ababb", "abababbababb", "abababbababbabababbbbbabb" },
+ { "213567", "12324567", "1234567", "213213567",
+ "21312312312567", "444444567" },
+ { "abcdaab", "aab", "abaab", "cdaab", "acbdadcbaab" },
+ { "213234567", "3458", "0987654", "7689546432", "0398576",
+ "98432", "5" },
+ {
+ "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ",
+ "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
+ + "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ" },
+ { "ababbaAabababblice", "ababbaAliceababab", "ababbAabliceaaa",
+ "abbbAbbbliceaaa", "Alice" },
+ { "a123", "bnxnvgds156", "for", "while", "if", "struct" },
+ { "xy" }, { "xy" }, { "xcy" }
+
+ };
+
+ for (int i = 0; i < testPatterns.length; i++) {
+ for (int j = 0; j < posSeq[i].length; j++) {
+ assertTrue("Incorrect match: " + testPatterns[i] + " vs "
+ + posSeq[i][j], Pattern.compile(testPatterns[i])
+ .matcher(posSeq[i][j]).matches());
+ }
+ }
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testQuantifiersWithSurrogatesSupplementary() {
+ String patString = "\uD9A0\uDE81*abc";
+ String testString = "\uD9A0\uDE81\uD9A0\uDE81abc";
+ Pattern pat = Pattern.compile(patString);
+ Matcher mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "abc";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testAlternationsWithSurrogatesSupplementary() {
+ String patString = "\uDE81|\uD9A0\uDE81|\uD9A0";
+ String testString = "\uD9A0";
+ Pattern pat = Pattern.compile(patString);
+ Matcher mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "\uDE81";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "\uD9A0\uDE81";
+ mat = pat.matcher(testString);
+ assertTrue(mat.matches());
+
+ testString = "\uDE81\uD9A0";
+ mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class, int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of compile(java.lang.String) & compile(java.lang.String, int) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testGroupsWithSurrogatesSupplementary() {
+
+ //this pattern matches nothing
+ String patString = "(\uD9A0)\uDE81";
+ String testString = "\uD9A0\uDE81";
+ Pattern pat = Pattern.compile(patString);
+ Matcher mat = pat.matcher(testString);
+ assertFalse(mat.matches());
+
+ patString = "(\uD9A0)";
+ testString = "\uD9A0\uDE81";
+ pat = Pattern.compile(patString, Pattern.DOTALL);
+ mat = pat.matcher(testString);
+ assertFalse(mat.find());
+ }
+
+ /*
+ * Regression test for HARMONY-688
+ */
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test verifies the functionality of compile(java.lang.String) & matcher(java.lang.CharSequence) methods.",
+ method = "matcher",
+ args = {java.lang.CharSequence.class}
+ )
+ })
+ public void testUnicodeCategoryWithSurrogatesSupplementary() {
+ Pattern p = Pattern.compile("\\p{javaLowerCase}");
+ Matcher matcher = p.matcher("\uD801\uDC28");
+ assertTrue(matcher.find());
+ }
+
+ public static void main(String[] args) {
+ junit.textui.TestRunner.run(PatternTest.class);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "The test doesn't verify Matcher and should be moved to PatterTest.",
+ method = "split",
+ args = {java.lang.CharSequence.class, int.class}
+ )
+ public void testSplitEmpty() {
+
+ Pattern pat = Pattern.compile("");
+ String[] s = pat.split("", -1);
+
+ assertEquals(1, s.length);
+ assertEquals("", s[0]);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.COMPLETE,
+ notes = "",
+ method = "toString",
+ args = {}
+ )
+ public void testToString() {
+ for (int i = 0; i < testPatterns.length; i++) {
+ Pattern p = Pattern.compile(testPatterns[i]);
+ assertEquals(testPatterns[i], p.toString());
+ }
+ }
+
+}
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/ReplaceTest.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/ReplaceTest.java
new file mode 100644
index 0000000..82390e7
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/ReplaceTest.java
@@ -0,0 +1,125 @@
+/* Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import dalvik.annotation.TestTargetClass;
+import dalvik.annotation.TestTargets;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestLevel;
+
+import junit.framework.TestCase;
+import java.util.regex.Pattern;
+import java.util.regex.Matcher;
+import java.util.regex.PatternSyntaxException;
+
+@TestTargetClass(Matcher.class)
+public class ReplaceTest extends TestCase {
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the basic functionality of replaceFirst(java.lang.String) & replaceAll(java.lang.String) methods.",
+ method = "replaceFirst",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the basic functionality of replaceFirst(java.lang.String) & replaceAll(java.lang.String) methods.",
+ method = "replaceAll",
+ args = {java.lang.String.class}
+ )
+ })
+ public void testSimpleReplace() throws PatternSyntaxException {
+ String target, pattern, repl;
+
+ target = "foobarfobarfoofo1barfort";
+ pattern = "fo[^o]";
+ repl = "xxx";
+
+ Pattern p = Pattern.compile(pattern);
+ Matcher m = p.matcher(target);
+
+ assertEquals("foobarxxxarfoofo1barfort", m.replaceFirst(repl));
+ assertEquals("foobarxxxarfooxxxbarxxxt", m.replaceAll(repl));
+ }
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of replaceFirst(java.lang.String) & replaceAll(java.lang.String) methods.",
+ method = "replaceFirst",
+ args = {java.lang.String.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of replaceFirst(java.lang.String) & replaceAll(java.lang.String) methods.",
+ method = "replaceAll",
+ args = {java.lang.String.class}
+ )
+ })
+ public void testCaptureReplace() {
+ String target, pattern, repl, s;
+ Pattern p = null;
+ Matcher m;
+
+ target = "[31]foo;bar[42];[99]xyz";
+ pattern = "\\[([0-9]+)\\]([a-z]+)";
+ repl = "$2[$1]";
+
+ p = Pattern.compile(pattern);
+ m = p.matcher(target);
+ s = m.replaceFirst(repl);
+ assertEquals("foo[31];bar[42];[99]xyz", s);
+ s = m.replaceAll(repl);
+ assertEquals("foo[31];bar[42];xyz[99]", s);
+
+ target = "[31]foo(42)bar{63}zoo;[12]abc(34)def{56}ghi;{99}xyz[88]xyz(77)xyz;";
+ pattern = "\\[([0-9]+)\\]([a-z]+)\\(([0-9]+)\\)([a-z]+)\\{([0-9]+)\\}([a-z]+)";
+ repl = "[$5]$6($3)$4{$1}$2";
+ p = Pattern.compile(pattern);
+ m = p.matcher(target);
+ s = m.replaceFirst(repl);
+ // System.out.println(s);
+ assertEquals("[63]zoo(42)bar{31}foo;[12]abc(34)def{56}ghi;{99}xyz[88]xyz(77)xyz;", s
+ );
+ s = m.replaceAll(repl);
+ // System.out.println(s);
+ assertEquals("[63]zoo(42)bar{31}foo;[56]ghi(34)def{12}abc;{99}xyz[88]xyz(77)xyz;", s
+ );
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of replaceAll(java.lang.String) method with backslash chars.",
+ method = "replaceAll",
+ args = {java.lang.String.class}
+ )
+ public void testEscapeReplace() {
+ String target, pattern, repl, s;
+
+ target = "foo'bar''foo";
+ pattern = "'";
+ repl = "\\'";
+ s = target.replaceAll(pattern, repl);
+ assertEquals("foo'bar''foo", s);
+ repl = "\\\\'";
+ s = target.replaceAll(pattern, repl);
+ assertEquals("foo\\'bar\\'\\'foo", s);
+ repl = "\\$3";
+ s = target.replaceAll(pattern, repl);
+ assertEquals("foo$3bar$3$3foo", s);
+ }
+}
diff --git a/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/SplitTest.java b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/SplitTest.java
new file mode 100644
index 0000000..ea615c0
--- /dev/null
+++ b/regex/src/test/java/org/apache/harmony/regex/tests/java/util/regex/SplitTest.java
@@ -0,0 +1,201 @@
+package org.apache.harmony.regex.tests.java.util.regex;
+
+import dalvik.annotation.TestTargetClass;
+import dalvik.annotation.TestTargets;
+import dalvik.annotation.TestTargetNew;
+import dalvik.annotation.TestLevel;
+
+import junit.framework.TestCase;
+import java.util.regex.*;
+
+@TestTargetClass(java.util.regex.Pattern.class)
+/**
+ * TODO Type description
+ *
+ */
+public class SplitTest extends TestCase {
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the basic functionality of split(java.lang.CharSequence) & compile(java.lang.String)methods.",
+ method = "split",
+ args = {java.lang.CharSequence.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the basic functionality of split(java.lang.CharSequence) & compile(java.lang.String)methods.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ })
+ public void testSimple() {
+ Pattern p = Pattern.compile("/");
+ String[] results = p.split("have/you/done/it/right");
+ String[] expected = new String[] { "have", "you", "done", "it", "right" };
+ assertEquals(expected.length, results.length);
+ for (int i = 0; i < expected.length; i++) {
+ assertEquals(results[i], expected[i]);
+ }
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of split(java.lang.CharSequence). Test uses not empty pattern.",
+ method = "split",
+ args = {java.lang.CharSequence.class, int.class}
+ )
+ public void testSplit1() throws PatternSyntaxException {
+ Pattern p = Pattern.compile(" ");
+
+ String input = "poodle zoo";
+ String tokens[];
+
+ tokens = p.split(input, 1);
+ assertEquals(1, tokens.length);
+ assertTrue(tokens[0].equals(input));
+ tokens = p.split(input, 2);
+ assertEquals(2, tokens.length);
+ assertEquals("poodle", tokens[0]);
+ assertEquals("zoo", tokens[1]);
+ tokens = p.split(input, 5);
+ assertEquals(2, tokens.length);
+ assertEquals("poodle", tokens[0]);
+ assertEquals("zoo", tokens[1]);
+ tokens = p.split(input, -2);
+ assertEquals(2, tokens.length);
+ assertEquals("poodle", tokens[0]);
+ assertEquals("zoo", tokens[1]);
+ tokens = p.split(input, 0);
+ assertEquals(2, tokens.length);
+ assertEquals("poodle", tokens[0]);
+ assertEquals("zoo", tokens[1]);
+ tokens = p.split(input);
+ assertEquals(2, tokens.length);
+ assertEquals("poodle", tokens[0]);
+ assertEquals("zoo", tokens[1]);
+
+ p = Pattern.compile("d");
+
+ tokens = p.split(input, 1);
+ assertEquals(1, tokens.length);
+ assertTrue(tokens[0].equals(input));
+ tokens = p.split(input, 2);
+ assertEquals(2, tokens.length);
+ assertEquals("poo", tokens[0]);
+ assertEquals("le zoo", tokens[1]);
+ tokens = p.split(input, 5);
+ assertEquals(2, tokens.length);
+ assertEquals("poo", tokens[0]);
+ assertEquals("le zoo", tokens[1]);
+ tokens = p.split(input, -2);
+ assertEquals(2, tokens.length);
+ assertEquals("poo", tokens[0]);
+ assertEquals("le zoo", tokens[1]);
+ tokens = p.split(input, 0);
+ assertEquals(2, tokens.length);
+ assertEquals("poo", tokens[0]);
+ assertEquals("le zoo", tokens[1]);
+ tokens = p.split(input);
+ assertEquals(2, tokens.length);
+ assertEquals("poo", tokens[0]);
+ assertEquals("le zoo", tokens[1]);
+
+ p = Pattern.compile("o");
+
+ tokens = p.split(input, 1);
+ assertEquals(1, tokens.length);
+ assertTrue(tokens[0].equals(input));
+ tokens = p.split(input, 2);
+ assertEquals(2, tokens.length);
+ assertEquals("p", tokens[0]);
+ assertEquals("odle zoo", tokens[1]);
+ tokens = p.split(input, 5);
+ assertEquals(5, tokens.length);
+ assertEquals("p", tokens[0]);
+ assertTrue(tokens[1].equals(""));
+ assertEquals("dle z", tokens[2]);
+ assertTrue(tokens[3].equals(""));
+ assertTrue(tokens[4].equals(""));
+ tokens = p.split(input, -2);
+ assertEquals(5, tokens.length);
+ assertEquals("p", tokens[0]);
+ assertTrue(tokens[1].equals(""));
+ assertEquals("dle z", tokens[2]);
+ assertTrue(tokens[3].equals(""));
+ assertTrue(tokens[4].equals(""));
+ tokens = p.split(input, 0);
+ assertEquals(3, tokens.length);
+ assertEquals("p", tokens[0]);
+ assertTrue(tokens[1].equals(""));
+ assertEquals("dle z", tokens[2]);
+ tokens = p.split(input);
+ assertEquals(3, tokens.length);
+ assertEquals("p", tokens[0]);
+ assertTrue(tokens[1].equals(""));
+ assertEquals("dle z", tokens[2]);
+ }
+
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of split(java.lang.CharSequence). Test uses empty pattern.",
+ method = "split",
+ args = {java.lang.CharSequence.class, int.class}
+ )
+ public void testSplit2() {
+ Pattern p = Pattern.compile("");
+ String s[];
+ s = p.split("a", -1);
+ assertEquals(3, s.length);
+ assertEquals("", s[0]);
+ assertEquals("a", s[1]);
+ assertEquals("", s[2]);
+
+ s = p.split("", -1);
+ assertEquals(1, s.length);
+ assertEquals("", s[0]);
+
+ s = p.split("abcd", -1);
+ assertEquals(6, s.length);
+ assertEquals("", s[0]);
+ assertEquals("a", s[1]);
+ assertEquals("b", s[2]);
+ assertEquals("c", s[3]);
+ assertEquals("d", s[4]);
+ assertEquals("", s[5]);
+
+ // Regression test for Android
+ assertEquals("GOOG,23,500".split("|").length, 12);
+ }
+
+
+ @TestTargets({
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of split(java.lang.CharSequence) & compile(java.lang.String, int) methods. Test uses empty pattern and supplementary chars.",
+ method = "split",
+ args = {java.lang.CharSequence.class, int.class}
+ ),
+ @TestTargetNew(
+ level = TestLevel.PARTIAL_COMPLETE,
+ notes = "Verifies the functionality of split(java.lang.CharSequence) & compile(java.lang.String, int) methods. Test uses empty pattern and supplementary chars.",
+ method = "compile",
+ args = {java.lang.String.class}
+ )
+ })
+ public void testSplitSupplementaryWithEmptyString() {
+
+ /*
+ * See http://www.unicode.org/reports/tr18/#Supplementary_Characters
+ * We have to treat text as code points not code units.
+ */
+ Pattern p = Pattern.compile("");
+ String s[];
+ s = p.split("a\ud869\uded6b", -1);
+ assertEquals(5, s.length);
+ assertEquals("", s[0]);
+ assertEquals("a", s[1]);
+ assertEquals("\ud869\uded6", s[2]);
+ assertEquals("b", s[3]);
+ assertEquals("", s[4]);
+ }
+}
diff --git a/regex/src/test/java/tests/regex/AllTests.java b/regex/src/test/java/tests/regex/AllTests.java
new file mode 100644
index 0000000..d590d08
--- /dev/null
+++ b/regex/src/test/java/tests/regex/AllTests.java
@@ -0,0 +1,38 @@
+/* Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package tests.regex;
+
+import junit.framework.Test;
+import junit.framework.TestSuite;
+
+/**
+ * Test suite that includes all tests for the regex project.
+ */
+public class AllTests {
+
+ public static void main(String[] args) {
+ junit.textui.TestRunner.run(AllTests.suite());
+ }
+
+ public static Test suite() {
+ TestSuite suite = tests.TestSuiteFactory.createTestSuite("All regex test suites");
+ // $JUnit-BEGIN$
+ suite.addTest(org.apache.harmony.regex.tests.java.util.regex.AllTests.suite());
+ // $JUnit-END$
+ return suite;
+ }
+}
diff --git a/regex/src/test/resources/serialization/org/apache/harmony/regex/tests/java/util/regex/PatternSyntaxExceptionTest.golden.ser b/regex/src/test/resources/serialization/org/apache/harmony/regex/tests/java/util/regex/PatternSyntaxExceptionTest.golden.ser
new file mode 100755
index 0000000..623d6ac
--- /dev/null
+++ b/regex/src/test/resources/serialization/org/apache/harmony/regex/tests/java/util/regex/PatternSyntaxExceptionTest.golden.ser
Binary files differ
diff --git a/regex/src/test/resources/serialization/org/apache/harmony/regex/tests/java/util/regex/PatternTest.golden.ser b/regex/src/test/resources/serialization/org/apache/harmony/regex/tests/java/util/regex/PatternTest.golden.ser
new file mode 100755
index 0000000..6150adf
--- /dev/null
+++ b/regex/src/test/resources/serialization/org/apache/harmony/regex/tests/java/util/regex/PatternTest.golden.ser
Binary files differ