zhztheplayer · ogregoire · Apr 1, 2017 · Apr 1, 2017 · Jan 24, 2018 · Apr 11, 2018
diff --git a/LICENSE b/LICENSE
@@ -1,4 +1,4 @@
-Copyright 2015-2016 yatt.top
+Copyright 2015-2018 yatt.top
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.

diff --git a/README.md b/README.md
@@ -43,12 +43,5 @@ Regex | Input | Time Cost (Java Native) | Time Cost (DFA Regex)
 - brackets
 
 ### Todo List:
-- capture groups `(<name>)`
-- some zero width tokens `\b`
-- look forward / look back `(?=)` `(?<)`
-- anchor points `^` `$`
-- ranged set `[0-9]`
-
-
-
-*Be free to file issues or promote unsupported features that you want to see to make this project better.*
+- [POSIX-Extended Regex](http://www.boost.org/doc/libs/1_44_0/libs/regex/doc/html/boost_regex/syntax/basic_extended.html) syntax support
+- Liner time searching
diff --git a/checkstyle.xml b/checkstyle.xml
@@ -0,0 +1,148 @@
+<?xml version="1.0"?>
+<!DOCTYPE module PUBLIC
+        "-//Puppy Crawl//DTD Check Configuration 1.3//EN"
+        "http://checkstyle.sourceforge.net/dtds/configuration_1_3.dtd">
+
+<!--
+    Checkstyle configuration that checks the Google coding conventions from Google Java Style
+    that can be found at https://google.github.io/styleguide/javaguide.html.
+    Checkstyle is very configurable. Be sure to read the documentation at
+    http://checkstyle.sf.net (or in your downloaded distribution).
+    To completely disable a check, just comment it out or delete it from the file.
+    Authors: Max Vetrenko, Ruslan Diachenko, Roman Ivanov.
+ -->
+
+<module name = "Checker">
+    <property name="charset" value="UTF-8"/>
+
+    <property name="fileExtensions" value="java, properties, xml"/>
+    <!-- Checks for whitespace                               -->
+    <!-- See http://checkstyle.sf.net/config_whitespace.html -->
+    <module name="FileTabCharacter">
+        <property name="eachLine" value="true"/>
+    </module>
+
+    <module name="TreeWalker">
+        <module name="OuterTypeFilename"/>
+        <module name="IllegalTokenText">
+            <property name="tokens" value="STRING_LITERAL, CHAR_LITERAL"/>
+            <property name="format" value="\\u00(09|0(a|A)|0(c|C)|0(d|D)|22|27|5(C|c))|\\(0(10|11|12|14|15|42|47)|134)"/>
+            <property name="message" value="Consider using special escape sequence instead of octal value or Unicode escaped value."/>
+        </module>
+        <module name="AvoidEscapedUnicodeCharacters">
+            <property name="allowEscapesForControlCharacters" value="true"/>
+            <property name="allowByTailComment" value="true"/>
+            <property name="allowNonPrintableEscapes" value="true"/>
+        </module>
+        <module name="OneTopLevelClass"/>
+        <module name="NoLineWrap"/>
+        <module name="EmptyBlock">
+            <property name="option" value="TEXT"/>
+            <property name="tokens" value="LITERAL_TRY, LITERAL_FINALLY, LITERAL_IF, LITERAL_ELSE, LITERAL_SWITCH"/>
+        </module>
+        <module name="NeedBraces"/>
+        <module name="LeftCurly"/>
+        <module name="RightCurly">
+            <property name="id" value="RightCurlySame"/>
+            <property name="tokens" value="LITERAL_TRY, LITERAL_CATCH, LITERAL_FINALLY, LITERAL_IF, LITERAL_ELSE, LITERAL_DO"/>
+        </module>
+        <module name="RightCurly">
+            <property name="id" value="RightCurlyAlone"/>
+            <property name="option" value="alone"/>
+            <property name="tokens" value="CLASS_DEF, METHOD_DEF, CTOR_DEF, LITERAL_FOR, LITERAL_WHILE, STATIC_INIT, INSTANCE_INIT"/>
+        </module>
+        <module name="WhitespaceAround">
+            <property name="allowEmptyConstructors" value="true"/>
+            <property name="allowEmptyMethods" value="true"/>
+            <property name="allowEmptyTypes" value="true"/>
+            <property name="allowEmptyLoops" value="true"/>
+            <message key="ws.notFollowed"
+                     value="WhitespaceAround: ''{0}'' is not followed by whitespace. Empty blocks may only be represented as '{}' when not part of a multi-block statement (4.1.3)"/>
+            <message key="ws.notPreceded"
+                     value="WhitespaceAround: ''{0}'' is not preceded with whitespace."/>
+        </module>
+        <module name="OneStatementPerLine"/>
+        <module name="MultipleVariableDeclarations"/>
+        <module name="ArrayTypeStyle"/>
+        <module name="MissingSwitchDefault"/>
+        <module name="FallThrough"/>
+        <module name="UpperEll"/>
+        <module name="ModifierOrder"/>
+        <module name="EmptyLineSeparator">
+            <property name="allowNoEmptyLineBetweenFields" value="true"/>
+        </module>
+        <module name="SeparatorWrap">
+            <property name="id" value="SeparatorWrapDot"/>
+            <property name="tokens" value="DOT"/>
+            <property name="option" value="nl"/>
+        </module>
+        <module name="SeparatorWrap">
+            <property name="id" value="SeparatorWrapComma"/>
+            <property name="tokens" value="COMMA"/>
+            <property name="option" value="EOL"/>
+        </module>
+        <module name="SeparatorWrap">
+            <!-- ELLIPSIS is EOL until https://github.com/google/styleguide/issues/258 -->
+            <property name="id" value="SeparatorWrapEllipsis"/>
+            <property name="tokens" value="ELLIPSIS"/>
+            <property name="option" value="EOL"/>
+        </module>
+        <module name="SeparatorWrap">
+            <!-- ARRAY_DECLARATOR is EOL until https://github.com/google/styleguide/issues/259 -->
+            <property name="id" value="SeparatorWrapArrayDeclarator"/>
+            <property name="tokens" value="ARRAY_DECLARATOR"/>
+            <property name="option" value="EOL"/>
+        </module>
+        <module name="SeparatorWrap">
+            <property name="id" value="SeparatorWrapMethodRef"/>
+            <property name="tokens" value="METHOD_REF"/>
+            <property name="option" value="nl"/>
+        </module>
+        <module name="NoFinalizer"/>
+        <module name="GenericWhitespace">
+            <message key="ws.followed"
+                     value="GenericWhitespace ''{0}'' is followed by whitespace."/>
+            <message key="ws.preceded"
+                     value="GenericWhitespace ''{0}'' is preceded with whitespace."/>
+            <message key="ws.illegalFollow"
+                     value="GenericWhitespace ''{0}'' should followed by whitespace."/>
+            <message key="ws.notPreceded"
+                     value="GenericWhitespace ''{0}'' is not preceded with whitespace."/>
+        </module>
+        <!--<module name="OverloadMethodsDeclarationOrder"/>-->
+        <module name="VariableDeclarationUsageDistance"/>
+        <module name="MethodParamPad"/>
+        <module name="ParenPad"/>
+        <!--<module name="OperatorWrap">-->
+            <!--<property name="option" value="NL"/>-->
+            <!--<property name="tokens" value="BAND, BOR, BSR, BXOR, DIV, EQUAL, GE, GT, LAND, LE, LITERAL_INSTANCEOF, LOR, LT, MINUS, MOD, NOT_EQUAL, PLUS, QUESTION, SL, SR, STAR, METHOD_REF "/>-->
+        <!--</module>-->
+        <module name="AnnotationLocation">
+            <property name="id" value="AnnotationLocationMostCases"/>
+            <property name="tokens" value="CLASS_DEF, INTERFACE_DEF, ENUM_DEF, METHOD_DEF, CTOR_DEF"/>
+        </module>
+        <module name="AnnotationLocation">
+            <property name="id" value="AnnotationLocationVariables"/>
+            <property name="tokens" value="VARIABLE_DEF"/>
+            <property name="allowSamelineMultipleAnnotations" value="true"/>
+        </module>
+        <module name="EmptyCatchBlock">
+            <property name="exceptionVariableName" value="expected"/>
+        </module>
+        <!--<module name="AvoidNestedBlocks"/>-->
+        <module name="EmptyCatchBlock" />
+        <module name="EmptyStatement" />
+        <module name="MissingOverride"/>
+        <module name="MultipleVariableDeclarations"/>
+        <module name="ParameterAssignment"/>
+        <module name="StringLiteralEquality"/>
+        <module name="RedundantImport"/>
+        <module name="UnusedImports"/>
+        <module name="WhitespaceAfter"/>
+        <module name="NeedBraces" />
+        <module name="UnnecessaryParentheses" />
+        <module name="LeftCurly"/>
+        <module name="RightCurly"/>
+        <module name="SuppressWarningsHolder" />
+    </module>
+</module>
diff --git a/pom.xml b/pom.xml
@@ -6,12 +6,12 @@
 
     <groupId>top.yatt.dfargx</groupId>
     <artifactId>dfargx</artifactId>
-    <version>0.2.1</version>
+    <version>0.2.2-SNAPSHOT</version>
     <packaging>jar</packaging>
 
     <name>DFA-Regex</name>
-    <url>https://github.com/zbdzzg/DFA-Regex</url>
-    <description>A pretty fast regex engine built in java using pure DFA.</description>
+    <url>https://github.com/zhztheplayer/DFA-Regex</url>
+    <description>A Java DFA regex engine implementation.</description>
     <inceptionYear>2015</inceptionYear>
 
     <distributionManagement>
@@ -36,23 +36,23 @@
     </licenses>
 
     <scm>
-        <connection>scm:git:git@github.com:zbdzzg/DFA-Regex.git</connection>
-        <developerConnection>scm:git:git@github.com:zbdzzg/DFA-Regex.git</developerConnection>
-        <url>https://github.com/zbdzzg/DFA-Regex</url>
+        <connection>scm:git:git@github.com:zhztheplayer/DFA-Regex.git</connection>
+        <developerConnection>scm:git:git@github.com:zhztheplayer/DFA-Regex.git</developerConnection>
+        <url>https://github.com/zhztheplayer/DFA-Regex</url>
         <tag>HEAD</tag>
     </scm>
 
     <developers>
         <developer>
-            <id>zbdzzg</id>
+            <id>zhz</id>
             <name>Zhang Hongze</name>
-            <email>zbdzzg@sina.cn</email>
+            <email>talktozhz@126.com</email>
         </developer>
     </developers>
 
     <issueManagement>
         <system>GitHub Issues</system>
-        <url>https://github.com/zbdzzg/DFA-Regex/issues</url>
+        <url>https://github.com/zhztheplayer/DFA-Regex/issues</url>
     </issueManagement>
     <profiles>
         <profile>
@@ -120,7 +120,37 @@
                     </execution>
                 </executions>
             </plugin>
-
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-checkstyle-plugin</artifactId>
+                <executions>
+                    <execution>
+                        <id>verify-style</id>
+                        <phase>process-classes</phase>
+                        <goals>
+                            <goal>check</goal>
+                        </goals>
+                    </execution>
+                </executions>
+                <configuration>
+                    <configLocation>checkstyle.xml</configLocation>
+                    <logViolationsToConsole>true</logViolationsToConsole>
+                    <includeTestSourceDirectory>true</includeTestSourceDirectory>
+                    <sourceDirectories>
+                        <sourceDirectory>
+                            ${project.build.sourceDirectory}
+                        </sourceDirectory>
+                    </sourceDirectories>
+                </configuration>
+                <dependencies>
+                    <!-- https://mvnrepository.com/artifact/com.puppycrawl.tools/checkstyle -->
+                    <dependency>
+                        <groupId>com.puppycrawl.tools</groupId>
+                        <artifactId>checkstyle</artifactId>
+                        <version>8.1</version>
+                    </dependency>
+                </dependencies>
+            </plugin>
         </plugins>
     </build>
 

diff --git a/src/main/java/top/yatt/dfargx/RegexComparator.java b/src/main/java/top/yatt/dfargx/RegexComparator.java
@@ -0,0 +1,26 @@
+package top.yatt.dfargx;
+
+import top.yatt.dfargx.automata.DFA;
+import top.yatt.dfargx.automata.NFA;
+import top.yatt.dfargx.tree.SyntaxTree;
+
+public class RegexComparator {
+
+    /**
+     * Checks if the matching space of <code>regexp1</code> contains the matching space of <code>regexp1</code>.
+     */
+    public static final boolean contains(String regexp1, String regexp2) {
+        SyntaxTree syntaxTree = new SyntaxTree(regexp1);
+        NFA nfa = new NFA(syntaxTree.getRoot());
+        DFA dfa = new DFA(nfa.getStateList());
+
+        // by definition if the matching space of A is equal than the matching space of A|B then B is contained in A
+        // similarly, if DFA(A) is identical to DFA(A|B) then B is contained in A.
+        SyntaxTree syntaxTree2 = new SyntaxTree(regexp1 + "|" + regexp2);
+        NFA nfa2 = new NFA(syntaxTree2.getRoot());
+        DFA dfa2 = new DFA(nfa2.getStateList());
+
+        return dfa.equals(dfa2);
+
+    }
+}
diff --git a/src/main/java/top/yatt/dfargx/automata/DFA.java b/src/main/java/top/yatt/dfargx/automata/DFA.java
@@ -10,9 +10,12 @@
 public class DFA {
 
     private int[][] transitionTable;
-    private int is; // init state
-    private int rs; // rejected state
-    private boolean[] fs; // final states
+    // init state
+    private int is;
+    // rejected state
+    private int rs;
+    // final states
+    private boolean[] fs;
 
     public DFA(List<NFAState> nfaStateList) {
         transitionTable = null;
@@ -37,6 +40,52 @@ public boolean[] getFinalStates() {
         return fs;
     }
 
+    @Override
+    public boolean equals(Object o) {
+        if (!(o instanceof DFA)) {
+            return false;
+        }
+        DFA other = (DFA) o;
+
+        int [][] checked = new int[transitionTable.length][other.transitionTable.length];
+        return dfaEquivalenceCheck(other, is, other.is, checked);
+    }
+
+    private boolean dfaEquivalenceCheck(DFA other, int initialState, int otherInitialState, int [][] checked) {
+        // transitions for this DFA for state initialState
+        int [] initialTransitions = transitionTable[initialState];
+        // transitions for the other DFA for state otherInitialState
+        int [] otherInitialTransitions = other.transitionTable[otherInitialState];
+
+        // For every possible transition from initialState (and otherInitialState)
+        for (int i = 0; i < initialTransitions.length; i++) {
+
+            // if the target state is already computed in previous iterations, skip
+            if (checked[initialTransitions[i]][otherInitialTransitions[i]] == 1) {
+                continue;
+            }
+            // mark the transition as computed
+            checked[initialTransitions[i]][otherInitialTransitions[i]] = 1;
+
+            if (fs[initialTransitions[i]] != other.fs[otherInitialTransitions[i]]) {
+                // one transition goes to a final state and the other does not, this DFA is not equivalent
+                return false;
+            } else if ((initialTransitions[i] == rs && otherInitialTransitions[i] != other.rs)
+                    || (initialTransitions[i] != rs && otherInitialTransitions[i] == other.rs)) {
+                // one transition goes to rejected state and the other does not, this DFA is not equivalent
+                return false;
+            } else if (fs[initialTransitions[i]] == false && other.fs[otherInitialTransitions[i]] == false) {
+                // both transitions go to intermediate states, needs further computing using current states as initial
+                if (!dfaEquivalenceCheck(other, initialTransitions[i], otherInitialTransitions[i], checked)) {
+                    // the transition is not equivalent further down, this DFA is not equivalent
+                    return false;
+                }
+            }
+        }
+        // All transitions check were equivalent, this DFA is equivalent
+        return true;
+    }
+
     private void convert(List<NFAState> nfaStateList) {
         NFAState initState = nfaStateList.get(0);
         NFAState finalState = nfaStateList.get(1);
@@ -143,7 +192,7 @@ private void minimize(Map<Set<NFAState>, Map<Character, Set<NFAState>>> oriDFATr
         // rename all states
         for (Set<NFAState> nfaState : oriDFATransitionMap.keySet()) {
             if (initStateAfterRenaming == -1 && nfaState.equals(initClosure)) {
-                initStateAfterRenaming = renamingStateID; // record init state id
+                initStateAfterRenaming = renamingStateID; // preserve init state id
             }
             stateRenamingMap.put(nfaState, renamingStateID++);
         }
@@ -161,15 +210,20 @@ private void minimize(Map<Set<NFAState>, Map<Character, Set<NFAState>>> oriDFATr
             renamedDFATransitionTable.put(renamingStateID, state);
             if (entry.getKey().contains(finalNFAState)) {
                 finalFlags.put(renamingStateID, true);
-            } else finalFlags.put(renamingStateID, false);
+            } else {
+                finalFlags.put(renamingStateID, false);
+            }
         }
 
-        // split states to final states and non-final states
+        // group states to final states and non-final states
         Map<Integer, Integer> groupFlags = new HashMap<>();
         for (int i = 0; i < finalFlags.size(); i++) {
             boolean b = finalFlags.get(i);
-            if (b) groupFlags.put(i, 0);
-            else groupFlags.put(i, 1);
+            if (b) {
+                groupFlags.put(i, 0);
+            } else {
+                groupFlags.put(i, 1);
+            }
         }
 
         int groupTotal = 2;
@@ -230,7 +284,7 @@ private void minimize(Map<Set<NFAState>, Map<Character, Set<NFAState>>> oriDFATr
             fs[i] = finalGroupFlags.contains(i);
         }
 
-        // construct the final transition table
+        // construct the output transition table
         transitionTable = new int[groupTotal][];
 
         for (int groupID = 0; groupID < groupTotal; groupID++) {