1.1 --- a/src/com/sun/org/apache/regexp/internal/REDebugCompiler.java Sat Oct 24 16:18:47 2020 +0800
1.2 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000
1.3 @@ -1,225 +0,0 @@
1.4 -/*
1.5 - * reserved comment block
1.6 - * DO NOT REMOVE OR ALTER!
1.7 - */
1.8 -/*
1.9 - * Copyright 1999-2004 The Apache Software Foundation.
1.10 - *
1.11 - * Licensed under the Apache License, Version 2.0 (the "License");
1.12 - * you may not use this file except in compliance with the License.
1.13 - * You may obtain a copy of the License at
1.14 - *
1.15 - * http://www.apache.org/licenses/LICENSE-2.0
1.16 - *
1.17 - * Unless required by applicable law or agreed to in writing, software
1.18 - * distributed under the License is distributed on an "AS IS" BASIS,
1.19 - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
1.20 - * See the License for the specific language governing permissions and
1.21 - * limitations under the License.
1.22 - */
1.23 -
1.24 -package com.sun.org.apache.regexp.internal;
1.25 -
1.26 -import java.io.PrintWriter;
1.27 -import java.util.Hashtable;
1.28 -
1.29 -/**
1.30 - * A subclass of RECompiler which can dump a regular expression program
1.31 - * for debugging purposes.
1.32 - *
1.33 - * @author <a href="mailto:jonl@muppetlabs.com">Jonathan Locke</a>
1.34 - */
1.35 -public class REDebugCompiler extends RECompiler
1.36 -{
1.37 - /**
1.38 - * Mapping from opcodes to descriptive strings
1.39 - */
1.40 - static Hashtable hashOpcode = new Hashtable();
1.41 - static
1.42 - {
1.43 - hashOpcode.put(new Integer(RE.OP_RELUCTANTSTAR), "OP_RELUCTANTSTAR");
1.44 - hashOpcode.put(new Integer(RE.OP_RELUCTANTPLUS), "OP_RELUCTANTPLUS");
1.45 - hashOpcode.put(new Integer(RE.OP_RELUCTANTMAYBE), "OP_RELUCTANTMAYBE");
1.46 - hashOpcode.put(new Integer(RE.OP_END), "OP_END");
1.47 - hashOpcode.put(new Integer(RE.OP_BOL), "OP_BOL");
1.48 - hashOpcode.put(new Integer(RE.OP_EOL), "OP_EOL");
1.49 - hashOpcode.put(new Integer(RE.OP_ANY), "OP_ANY");
1.50 - hashOpcode.put(new Integer(RE.OP_ANYOF), "OP_ANYOF");
1.51 - hashOpcode.put(new Integer(RE.OP_BRANCH), "OP_BRANCH");
1.52 - hashOpcode.put(new Integer(RE.OP_ATOM), "OP_ATOM");
1.53 - hashOpcode.put(new Integer(RE.OP_STAR), "OP_STAR");
1.54 - hashOpcode.put(new Integer(RE.OP_PLUS), "OP_PLUS");
1.55 - hashOpcode.put(new Integer(RE.OP_MAYBE), "OP_MAYBE");
1.56 - hashOpcode.put(new Integer(RE.OP_NOTHING), "OP_NOTHING");
1.57 - hashOpcode.put(new Integer(RE.OP_GOTO), "OP_GOTO");
1.58 - hashOpcode.put(new Integer(RE.OP_ESCAPE), "OP_ESCAPE");
1.59 - hashOpcode.put(new Integer(RE.OP_OPEN), "OP_OPEN");
1.60 - hashOpcode.put(new Integer(RE.OP_CLOSE), "OP_CLOSE");
1.61 - hashOpcode.put(new Integer(RE.OP_BACKREF), "OP_BACKREF");
1.62 - hashOpcode.put(new Integer(RE.OP_POSIXCLASS), "OP_POSIXCLASS");
1.63 - hashOpcode.put(new Integer(RE.OP_OPEN_CLUSTER), "OP_OPEN_CLUSTER");
1.64 - hashOpcode.put(new Integer(RE.OP_CLOSE_CLUSTER), "OP_CLOSE_CLUSTER");
1.65 - }
1.66 -
1.67 - /**
1.68 - * Returns a descriptive string for an opcode.
1.69 - * @param opcode Opcode to convert to a string
1.70 - * @return Description of opcode
1.71 - */
1.72 - String opcodeToString(char opcode)
1.73 - {
1.74 - // Get string for opcode
1.75 - String ret =(String)hashOpcode.get(new Integer(opcode));
1.76 -
1.77 - // Just in case we have a corrupt program
1.78 - if (ret == null)
1.79 - {
1.80 - ret = "OP_????";
1.81 - }
1.82 - return ret;
1.83 - }
1.84 -
1.85 - /**
1.86 - * Return a string describing a (possibly unprintable) character.
1.87 - * @param c Character to convert to a printable representation
1.88 - * @return String representation of character
1.89 - */
1.90 - String charToString(char c)
1.91 - {
1.92 - // If it's unprintable, convert to '\###'
1.93 - if (c < ' ' || c > 127)
1.94 - {
1.95 - return "\\" + (int)c;
1.96 - }
1.97 -
1.98 - // Return the character as a string
1.99 - return String.valueOf(c);
1.100 - }
1.101 -
1.102 - /**
1.103 - * Returns a descriptive string for a node in a regular expression program.
1.104 - * @param node Node to describe
1.105 - * @return Description of node
1.106 - */
1.107 - String nodeToString(int node)
1.108 - {
1.109 - // Get opcode and opdata for node
1.110 - char opcode = instruction[node + RE.offsetOpcode];
1.111 - int opdata = (int)instruction[node + RE.offsetOpdata];
1.112 -
1.113 - // Return opcode as a string and opdata value
1.114 - return opcodeToString(opcode) + ", opdata = " + opdata;
1.115 - }
1.116 -
1.117 - /**
1.118 - * Inserts a node with a given opcode and opdata at insertAt. The node relative next
1.119 - * pointer is initialized to 0.
1.120 - * @param opcode Opcode for new node
1.121 - * @param opdata Opdata for new node (only the low 16 bits are currently used)
1.122 - * @param insertAt Index at which to insert the new node in the program * /
1.123 - void nodeInsert(char opcode, int opdata, int insertAt) {
1.124 - System.out.println( "====> " + opcode + " " + opdata + " " + insertAt );
1.125 - PrintWriter writer = new PrintWriter( System.out );
1.126 - dumpProgram( writer );
1.127 - super.nodeInsert( opcode, opdata, insertAt );
1.128 - System.out.println( "====< " );
1.129 - dumpProgram( writer );
1.130 - writer.flush();
1.131 - }/**/
1.132 -
1.133 -
1.134 - /**
1.135 - * Appends a node to the end of a node chain
1.136 - * @param node Start of node chain to traverse
1.137 - * @param pointTo Node to have the tail of the chain point to * /
1.138 - void setNextOfEnd(int node, int pointTo) {
1.139 - System.out.println( "====> " + node + " " + pointTo );
1.140 - PrintWriter writer = new PrintWriter( System.out );
1.141 - dumpProgram( writer );
1.142 - super.setNextOfEnd( node, pointTo );
1.143 - System.out.println( "====< " );
1.144 - dumpProgram( writer );
1.145 - writer.flush();
1.146 - }/**/
1.147 -
1.148 -
1.149 - /**
1.150 - * Dumps the current program to a PrintWriter
1.151 - * @param p PrintWriter for program dump output
1.152 - */
1.153 - public void dumpProgram(PrintWriter p)
1.154 - {
1.155 - // Loop through the whole program
1.156 - for (int i = 0; i < lenInstruction; )
1.157 - {
1.158 - // Get opcode, opdata and next fields of current program node
1.159 - char opcode = instruction[i + RE.offsetOpcode];
1.160 - char opdata = instruction[i + RE.offsetOpdata];
1.161 - short next = (short)instruction[i + RE.offsetNext];
1.162 -
1.163 - // Display the current program node
1.164 - p.print(i + ". " + nodeToString(i) + ", next = ");
1.165 -
1.166 - // If there's no next, say 'none', otherwise give absolute index of next node
1.167 - if (next == 0)
1.168 - {
1.169 - p.print("none");
1.170 - }
1.171 - else
1.172 - {
1.173 - p.print(i + next);
1.174 - }
1.175 -
1.176 - // Move past node
1.177 - i += RE.nodeSize;
1.178 -
1.179 - // If character class
1.180 - if (opcode == RE.OP_ANYOF)
1.181 - {
1.182 - // Opening bracket for start of char class
1.183 - p.print(", [");
1.184 -
1.185 - // Show each range in the char class
1.186 - int rangeCount = opdata;
1.187 - for (int r = 0; r < rangeCount; r++)
1.188 - {
1.189 - // Get first and last chars in range
1.190 - char charFirst = instruction[i++];
1.191 - char charLast = instruction[i++];
1.192 -
1.193 - // Print range as X-Y, unless range encompasses only one char
1.194 - if (charFirst == charLast)
1.195 - {
1.196 - p.print(charToString(charFirst));
1.197 - }
1.198 - else
1.199 - {
1.200 - p.print(charToString(charFirst) + "-" + charToString(charLast));
1.201 - }
1.202 - }
1.203 -
1.204 - // Annotate the end of the char class
1.205 - p.print("]");
1.206 - }
1.207 -
1.208 - // If atom
1.209 - if (opcode == RE.OP_ATOM)
1.210 - {
1.211 - // Open quote
1.212 - p.print(", \"");
1.213 -
1.214 - // Print each character in the atom
1.215 - for (int len = opdata; len-- != 0; )
1.216 - {
1.217 - p.print(charToString(instruction[i++]));
1.218 - }
1.219 -
1.220 - // Close quote
1.221 - p.print("\"");
1.222 - }
1.223 -
1.224 - // Print a newline
1.225 - p.println("");
1.226 - }
1.227 - }
1.228 -}
