Modified: stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/SimpleCharStream.java URL: http://svn.apache.org/viewvc/stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/SimpleCharStream.java?rev=1465023&r1=1465022&r2=1465023&view=diff ============================================================================== --- stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/SimpleCharStream.java (original) +++ stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/SimpleCharStream.java Fri Apr 5 16:09:09 2013 @@ -1,415 +1,471 @@ -/* - * 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. - */ /* Generated By:JavaCC: Do not edit this line. SimpleCharStream.java Version 5.0 */ /* JavaCCOptions:STATIC=false,SUPPORT_CLASS_VISIBILITY_PUBLIC=true */ package org.apache.stanbol.rules.manager.parse; /** - * An implementation of interface CharStream, where the stream is assumed to contain only ASCII characters - * (without unicode processing). + * An implementation of interface CharStream, where the stream is assumed to + * contain only ASCII characters (without unicode processing). */ -public class SimpleCharStream { - /** Whether parser is static. */ - public static final boolean staticFlag = false; - int bufsize; - int available; - int tokenBegin; - /** Position in buffer. */ - public int bufpos = -1; - protected int bufline[]; - protected int bufcolumn[]; - - protected int column = 0; - protected int line = 1; - - protected boolean prevCharIsCR = false; - protected boolean prevCharIsLF = false; - - protected java.io.Reader inputStream; - - protected char[] buffer; - protected int maxNextCharInd = 0; - protected int inBuf = 0; - protected int tabSize = 8; - - protected void setTabSize(int i) { - tabSize = i; - } - - protected int getTabSize(int i) { - return tabSize; - } - - protected void ExpandBuff(boolean wrapAround) { - char[] newbuffer = new char[bufsize + 2048]; - int newbufline[] = new int[bufsize + 2048]; - int newbufcolumn[] = new int[bufsize + 2048]; - - try { - if (wrapAround) { - System.arraycopy(buffer, tokenBegin, newbuffer, 0, bufsize - tokenBegin); - System.arraycopy(buffer, 0, newbuffer, bufsize - tokenBegin, bufpos); - buffer = newbuffer; - - System.arraycopy(bufline, tokenBegin, newbufline, 0, bufsize - tokenBegin); - System.arraycopy(bufline, 0, newbufline, bufsize - tokenBegin, bufpos); - bufline = newbufline; - - System.arraycopy(bufcolumn, tokenBegin, newbufcolumn, 0, bufsize - tokenBegin); - System.arraycopy(bufcolumn, 0, newbufcolumn, bufsize - tokenBegin, bufpos); - bufcolumn = newbufcolumn; - - maxNextCharInd = (bufpos += (bufsize - tokenBegin)); - } else { - System.arraycopy(buffer, tokenBegin, newbuffer, 0, bufsize - tokenBegin); - buffer = newbuffer; - - System.arraycopy(bufline, tokenBegin, newbufline, 0, bufsize - tokenBegin); - bufline = newbufline; - - System.arraycopy(bufcolumn, tokenBegin, newbufcolumn, 0, bufsize - tokenBegin); - bufcolumn = newbufcolumn; - - maxNextCharInd = (bufpos -= tokenBegin); - } - } catch (Throwable t) { - throw new Error(t.getMessage()); - } - - bufsize += 2048; +public class SimpleCharStream +{ +/** Whether parser is static. */ + public static final boolean staticFlag = false; + int bufsize; + int available; + int tokenBegin; +/** Position in buffer. */ + public int bufpos = -1; + protected int bufline[]; + protected int bufcolumn[]; + + protected int column = 0; + protected int line = 1; + + protected boolean prevCharIsCR = false; + protected boolean prevCharIsLF = false; + + protected java.io.Reader inputStream; + + protected char[] buffer; + protected int maxNextCharInd = 0; + protected int inBuf = 0; + protected int tabSize = 8; + + protected void setTabSize(int i) { tabSize = i; } + protected int getTabSize(int i) { return tabSize; } + + + protected void ExpandBuff(boolean wrapAround) + { + char[] newbuffer = new char[bufsize + 2048]; + int newbufline[] = new int[bufsize + 2048]; + int newbufcolumn[] = new int[bufsize + 2048]; + + try + { + if (wrapAround) + { + System.arraycopy(buffer, tokenBegin, newbuffer, 0, bufsize - tokenBegin); + System.arraycopy(buffer, 0, newbuffer, bufsize - tokenBegin, bufpos); + buffer = newbuffer; + + System.arraycopy(bufline, tokenBegin, newbufline, 0, bufsize - tokenBegin); + System.arraycopy(bufline, 0, newbufline, bufsize - tokenBegin, bufpos); + bufline = newbufline; + + System.arraycopy(bufcolumn, tokenBegin, newbufcolumn, 0, bufsize - tokenBegin); + System.arraycopy(bufcolumn, 0, newbufcolumn, bufsize - tokenBegin, bufpos); + bufcolumn = newbufcolumn; + + maxNextCharInd = (bufpos += (bufsize - tokenBegin)); + } + else + { + System.arraycopy(buffer, tokenBegin, newbuffer, 0, bufsize - tokenBegin); + buffer = newbuffer; + + System.arraycopy(bufline, tokenBegin, newbufline, 0, bufsize - tokenBegin); + bufline = newbufline; + + System.arraycopy(bufcolumn, tokenBegin, newbufcolumn, 0, bufsize - tokenBegin); + bufcolumn = newbufcolumn; + + maxNextCharInd = (bufpos -= tokenBegin); + } + } + catch (Throwable t) + { + throw new Error(t.getMessage()); + } + + + bufsize += 2048; + available = bufsize; + tokenBegin = 0; + } + + protected void FillBuff() throws java.io.IOException + { + if (maxNextCharInd == available) + { + if (available == bufsize) + { + if (tokenBegin > 2048) + { + bufpos = maxNextCharInd = 0; + available = tokenBegin; + } + else if (tokenBegin < 0) + bufpos = maxNextCharInd = 0; + else + ExpandBuff(false); + } + else if (available > tokenBegin) available = bufsize; - tokenBegin = 0; - } - - protected void FillBuff() throws java.io.IOException { - if (maxNextCharInd == available) { - if (available == bufsize) { - if (tokenBegin > 2048) { - bufpos = maxNextCharInd = 0; - available = tokenBegin; - } else if (tokenBegin < 0) bufpos = maxNextCharInd = 0; - else ExpandBuff(false); - } else if (available > tokenBegin) available = bufsize; - else if ((tokenBegin - available) < 2048) ExpandBuff(true); - else available = tokenBegin; - } - - int i; - try { - if ((i = inputStream.read(buffer, maxNextCharInd, available - maxNextCharInd)) == -1) { - inputStream.close(); - throw new java.io.IOException(); - } else maxNextCharInd += i; - return; - } catch (java.io.IOException e) { - --bufpos; - backup(0); - if (tokenBegin == -1) tokenBegin = bufpos; - throw e; - } - } - - /** Start. */ - public char BeginToken() throws java.io.IOException { - tokenBegin = -1; - char c = readChar(); + else if ((tokenBegin - available) < 2048) + ExpandBuff(true); + else + available = tokenBegin; + } + + int i; + try { + if ((i = inputStream.read(buffer, maxNextCharInd, available - maxNextCharInd)) == -1) + { + inputStream.close(); + throw new java.io.IOException(); + } + else + maxNextCharInd += i; + return; + } + catch(java.io.IOException e) { + --bufpos; + backup(0); + if (tokenBegin == -1) tokenBegin = bufpos; - - return c; - } - - protected void UpdateLineColumn(char c) { - column++; - - if (prevCharIsLF) { - prevCharIsLF = false; - line += (column = 1); - } else if (prevCharIsCR) { - prevCharIsCR = false; - if (c == '\n') { - prevCharIsLF = true; - } else line += (column = 1); - } - - switch (c) { - case '\r': - prevCharIsCR = true; - break; - case '\n': - prevCharIsLF = true; - break; - case '\t': - column--; - column += (tabSize - (column % tabSize)); - break; - default: - break; - } - - bufline[bufpos] = line; - bufcolumn[bufpos] = column; - } - - /** Read a character. */ - public char readChar() throws java.io.IOException { - if (inBuf > 0) { - --inBuf; - - if (++bufpos == bufsize) bufpos = 0; - - return buffer[bufpos]; - } - - if (++bufpos >= maxNextCharInd) FillBuff(); - - char c = buffer[bufpos]; - - UpdateLineColumn(c); - return c; - } - - @Deprecated - /** - * @deprecated - * @see #getEndColumn - */ - public int getColumn() { - return bufcolumn[bufpos]; - } - - @Deprecated - /** - * @deprecated - * @see #getEndLine - */ - public int getLine() { - return bufline[bufpos]; - } - - /** Get token end column number. */ - public int getEndColumn() { - return bufcolumn[bufpos]; - } - - /** Get token end line number. */ - public int getEndLine() { - return bufline[bufpos]; - } - - /** Get token beginning column number. */ - public int getBeginColumn() { - return bufcolumn[tokenBegin]; - } - - /** Get token beginning line number. */ - public int getBeginLine() { - return bufline[tokenBegin]; - } - - /** Backup a number of characters. */ - public void backup(int amount) { - - inBuf += amount; - if ((bufpos -= amount) < 0) bufpos += bufsize; - } - - /** Constructor. */ - public SimpleCharStream(java.io.Reader dstream, int startline, int startcolumn, int buffersize) { - inputStream = dstream; - line = startline; - column = startcolumn - 1; - - available = bufsize = buffersize; - buffer = new char[buffersize]; - bufline = new int[buffersize]; - bufcolumn = new int[buffersize]; - } - - /** Constructor. */ - public SimpleCharStream(java.io.Reader dstream, int startline, int startcolumn) { - this(dstream, startline, startcolumn, 4096); - } - - /** Constructor. */ - public SimpleCharStream(java.io.Reader dstream) { - this(dstream, 1, 1, 4096); + throw e; } + } - /** Reinitialise. */ - public void ReInit(java.io.Reader dstream, int startline, int startcolumn, int buffersize) { - inputStream = dstream; - line = startline; - column = startcolumn - 1; - - if (buffer == null || buffersize != buffer.length) { - available = bufsize = buffersize; - buffer = new char[buffersize]; - bufline = new int[buffersize]; - bufcolumn = new int[buffersize]; - } - prevCharIsLF = prevCharIsCR = false; - tokenBegin = inBuf = maxNextCharInd = 0; - bufpos = -1; - } - - /** Reinitialise. */ - public void ReInit(java.io.Reader dstream, int startline, int startcolumn) { - ReInit(dstream, startline, startcolumn, 4096); - } - - /** Reinitialise. */ - public void ReInit(java.io.Reader dstream) { - ReInit(dstream, 1, 1, 4096); - } - - /** Constructor. */ - public SimpleCharStream(java.io.InputStream dstream, - String encoding, - int startline, - int startcolumn, - int buffersize) throws java.io.UnsupportedEncodingException { - this(encoding == null ? new java.io.InputStreamReader(dstream) : new java.io.InputStreamReader( - dstream, encoding), startline, startcolumn, buffersize); - } - - /** Constructor. */ - public SimpleCharStream(java.io.InputStream dstream, int startline, int startcolumn, int buffersize) { - this(new java.io.InputStreamReader(dstream), startline, startcolumn, buffersize); - } - - /** Constructor. */ - public SimpleCharStream(java.io.InputStream dstream, String encoding, int startline, int startcolumn) throws java.io.UnsupportedEncodingException { - this(dstream, encoding, startline, startcolumn, 4096); - } - - /** Constructor. */ - public SimpleCharStream(java.io.InputStream dstream, int startline, int startcolumn) { - this(dstream, startline, startcolumn, 4096); - } - - /** Constructor. */ - public SimpleCharStream(java.io.InputStream dstream, String encoding) throws java.io.UnsupportedEncodingException { - this(dstream, encoding, 1, 1, 4096); - } - - /** Constructor. */ - public SimpleCharStream(java.io.InputStream dstream) { - this(dstream, 1, 1, 4096); - } - - /** Reinitialise. */ - public void ReInit(java.io.InputStream dstream, - String encoding, - int startline, - int startcolumn, - int buffersize) throws java.io.UnsupportedEncodingException { - ReInit(encoding == null ? new java.io.InputStreamReader(dstream) : new java.io.InputStreamReader( - dstream, encoding), startline, startcolumn, buffersize); - } - - /** Reinitialise. */ - public void ReInit(java.io.InputStream dstream, int startline, int startcolumn, int buffersize) { - ReInit(new java.io.InputStreamReader(dstream), startline, startcolumn, buffersize); - } - - /** Reinitialise. */ - public void ReInit(java.io.InputStream dstream, String encoding) throws java.io.UnsupportedEncodingException { - ReInit(dstream, encoding, 1, 1, 4096); - } - - /** Reinitialise. */ - public void ReInit(java.io.InputStream dstream) { - ReInit(dstream, 1, 1, 4096); - } - - /** Reinitialise. */ - public void ReInit(java.io.InputStream dstream, String encoding, int startline, int startcolumn) throws java.io.UnsupportedEncodingException { - ReInit(dstream, encoding, startline, startcolumn, 4096); - } - - /** Reinitialise. */ - public void ReInit(java.io.InputStream dstream, int startline, int startcolumn) { - ReInit(dstream, startline, startcolumn, 4096); - } - - /** Get token literal value. */ - public String GetImage() { - if (bufpos >= tokenBegin) return new String(buffer, tokenBegin, bufpos - tokenBegin + 1); - else return new String(buffer, tokenBegin, bufsize - tokenBegin) + new String(buffer, 0, bufpos + 1); - } - - /** Get the suffix. */ - public char[] GetSuffix(int len) { - char[] ret = new char[len]; - - if ((bufpos + 1) >= len) System.arraycopy(buffer, bufpos - len + 1, ret, 0, len); - else { - System.arraycopy(buffer, bufsize - (len - bufpos - 1), ret, 0, len - bufpos - 1); - System.arraycopy(buffer, 0, ret, len - bufpos - 1, bufpos + 1); - } - - return ret; - } - - /** Reset buffer when finished. */ - public void Done() { - buffer = null; - bufline = null; - bufcolumn = null; - } - - /** - * Method to adjust line and column numbers for the start of a token. - */ - public void adjustBeginLineColumn(int newLine, int newCol) { - int start = tokenBegin; - int len; - - if (bufpos >= tokenBegin) { - len = bufpos - tokenBegin + inBuf + 1; - } else { - len = bufsize - tokenBegin + bufpos + 1 + inBuf; - } - - int i = 0, j = 0, k = 0; - int nextColDiff = 0, columnDiff = 0; - - while (i < len && bufline[j = start % bufsize] == bufline[k = ++start % bufsize]) { - bufline[j] = newLine; - nextColDiff = columnDiff + bufcolumn[k] - bufcolumn[j]; - bufcolumn[j] = newCol + columnDiff; - columnDiff = nextColDiff; - i++; - } - - if (i < len) { - bufline[j] = newLine++; - bufcolumn[j] = newCol + columnDiff; - - while (i++ < len) { - if (bufline[j = start % bufsize] != bufline[++start % bufsize]) bufline[j] = newLine++; - else bufline[j] = newLine; - } - } - - line = bufline[j]; - column = bufcolumn[j]; - } +/** Start. */ + public char BeginToken() throws java.io.IOException + { + tokenBegin = -1; + char c = readChar(); + tokenBegin = bufpos; + + return c; + } + + protected void UpdateLineColumn(char c) + { + column++; + + if (prevCharIsLF) + { + prevCharIsLF = false; + line += (column = 1); + } + else if (prevCharIsCR) + { + prevCharIsCR = false; + if (c == '\n') + { + prevCharIsLF = true; + } + else + line += (column = 1); + } + + switch (c) + { + case '\r' : + prevCharIsCR = true; + break; + case '\n' : + prevCharIsLF = true; + break; + case '\t' : + column--; + column += (tabSize - (column % tabSize)); + break; + default : + break; + } + + bufline[bufpos] = line; + bufcolumn[bufpos] = column; + } + +/** Read a character. */ + public char readChar() throws java.io.IOException + { + if (inBuf > 0) + { + --inBuf; + + if (++bufpos == bufsize) + bufpos = 0; + + return buffer[bufpos]; + } + + if (++bufpos >= maxNextCharInd) + FillBuff(); + + char c = buffer[bufpos]; + + UpdateLineColumn(c); + return c; + } + + @Deprecated + /** + * @deprecated + * @see #getEndColumn + */ + + public int getColumn() { + return bufcolumn[bufpos]; + } + + @Deprecated + /** + * @deprecated + * @see #getEndLine + */ + + public int getLine() { + return bufline[bufpos]; + } + + /** Get token end column number. */ + public int getEndColumn() { + return bufcolumn[bufpos]; + } + + /** Get token end line number. */ + public int getEndLine() { + return bufline[bufpos]; + } + + /** Get token beginning column number. */ + public int getBeginColumn() { + return bufcolumn[tokenBegin]; + } + + /** Get token beginning line number. */ + public int getBeginLine() { + return bufline[tokenBegin]; + } + +/** Backup a number of characters. */ + public void backup(int amount) { + + inBuf += amount; + if ((bufpos -= amount) < 0) + bufpos += bufsize; + } + + /** Constructor. */ + public SimpleCharStream(java.io.Reader dstream, int startline, + int startcolumn, int buffersize) + { + inputStream = dstream; + line = startline; + column = startcolumn - 1; + + available = bufsize = buffersize; + buffer = new char[buffersize]; + bufline = new int[buffersize]; + bufcolumn = new int[buffersize]; + } + + /** Constructor. */ + public SimpleCharStream(java.io.Reader dstream, int startline, + int startcolumn) + { + this(dstream, startline, startcolumn, 4096); + } + + /** Constructor. */ + public SimpleCharStream(java.io.Reader dstream) + { + this(dstream, 1, 1, 4096); + } + + /** Reinitialise. */ + public void ReInit(java.io.Reader dstream, int startline, + int startcolumn, int buffersize) + { + inputStream = dstream; + line = startline; + column = startcolumn - 1; + + if (buffer == null || buffersize != buffer.length) + { + available = bufsize = buffersize; + buffer = new char[buffersize]; + bufline = new int[buffersize]; + bufcolumn = new int[buffersize]; + } + prevCharIsLF = prevCharIsCR = false; + tokenBegin = inBuf = maxNextCharInd = 0; + bufpos = -1; + } + + /** Reinitialise. */ + public void ReInit(java.io.Reader dstream, int startline, + int startcolumn) + { + ReInit(dstream, startline, startcolumn, 4096); + } + + /** Reinitialise. */ + public void ReInit(java.io.Reader dstream) + { + ReInit(dstream, 1, 1, 4096); + } + /** Constructor. */ + public SimpleCharStream(java.io.InputStream dstream, String encoding, int startline, + int startcolumn, int buffersize) throws java.io.UnsupportedEncodingException + { + this(encoding == null ? new java.io.InputStreamReader(dstream) : new java.io.InputStreamReader(dstream, encoding), startline, startcolumn, buffersize); + } + + /** Constructor. */ + public SimpleCharStream(java.io.InputStream dstream, int startline, + int startcolumn, int buffersize) + { + this(new java.io.InputStreamReader(dstream), startline, startcolumn, buffersize); + } + + /** Constructor. */ + public SimpleCharStream(java.io.InputStream dstream, String encoding, int startline, + int startcolumn) throws java.io.UnsupportedEncodingException + { + this(dstream, encoding, startline, startcolumn, 4096); + } + + /** Constructor. */ + public SimpleCharStream(java.io.InputStream dstream, int startline, + int startcolumn) + { + this(dstream, startline, startcolumn, 4096); + } + + /** Constructor. */ + public SimpleCharStream(java.io.InputStream dstream, String encoding) throws java.io.UnsupportedEncodingException + { + this(dstream, encoding, 1, 1, 4096); + } + + /** Constructor. */ + public SimpleCharStream(java.io.InputStream dstream) + { + this(dstream, 1, 1, 4096); + } + + /** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, String encoding, int startline, + int startcolumn, int buffersize) throws java.io.UnsupportedEncodingException + { + ReInit(encoding == null ? new java.io.InputStreamReader(dstream) : new java.io.InputStreamReader(dstream, encoding), startline, startcolumn, buffersize); + } + + /** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, int startline, + int startcolumn, int buffersize) + { + ReInit(new java.io.InputStreamReader(dstream), startline, startcolumn, buffersize); + } + + /** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, String encoding) throws java.io.UnsupportedEncodingException + { + ReInit(dstream, encoding, 1, 1, 4096); + } + + /** Reinitialise. */ + public void ReInit(java.io.InputStream dstream) + { + ReInit(dstream, 1, 1, 4096); + } + /** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, String encoding, int startline, + int startcolumn) throws java.io.UnsupportedEncodingException + { + ReInit(dstream, encoding, startline, startcolumn, 4096); + } + /** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, int startline, + int startcolumn) + { + ReInit(dstream, startline, startcolumn, 4096); + } + /** Get token literal value. */ + public String GetImage() + { + if (bufpos >= tokenBegin) + return new String(buffer, tokenBegin, bufpos - tokenBegin + 1); + else + return new String(buffer, tokenBegin, bufsize - tokenBegin) + + new String(buffer, 0, bufpos + 1); + } + + /** Get the suffix. */ + public char[] GetSuffix(int len) + { + char[] ret = new char[len]; + + if ((bufpos + 1) >= len) + System.arraycopy(buffer, bufpos - len + 1, ret, 0, len); + else + { + System.arraycopy(buffer, bufsize - (len - bufpos - 1), ret, 0, + len - bufpos - 1); + System.arraycopy(buffer, 0, ret, len - bufpos - 1, bufpos + 1); + } + + return ret; + } + + /** Reset buffer when finished. */ + public void Done() + { + buffer = null; + bufline = null; + bufcolumn = null; + } + + /** + * Method to adjust line and column numbers for the start of a token. + */ + public void adjustBeginLineColumn(int newLine, int newCol) + { + int start = tokenBegin; + int len; + + if (bufpos >= tokenBegin) + { + len = bufpos - tokenBegin + inBuf + 1; + } + else + { + len = bufsize - tokenBegin + bufpos + 1 + inBuf; + } + + int i = 0, j = 0, k = 0; + int nextColDiff = 0, columnDiff = 0; + + while (i < len && bufline[j = start % bufsize] == bufline[k = ++start % bufsize]) + { + bufline[j] = newLine; + nextColDiff = columnDiff + bufcolumn[k] - bufcolumn[j]; + bufcolumn[j] = newCol + columnDiff; + columnDiff = nextColDiff; + i++; + } + + if (i < len) + { + bufline[j] = newLine++; + bufcolumn[j] = newCol + columnDiff; + + while (i++ < len) + { + if (bufline[j = start % bufsize] != bufline[++start % bufsize]) + bufline[j] = newLine++; + else + bufline[j] = newLine; + } + } + + line = bufline[j]; + column = bufcolumn[j]; + } } /* JavaCC - OriginalChecksum=296b46b529ae054e669055c0bbf65487 (do not edit this line) */
Modified: stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/Token.java URL: http://svn.apache.org/viewvc/stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/Token.java?rev=1465023&r1=1465022&r2=1465023&view=diff ============================================================================== --- stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/Token.java (original) +++ stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/Token.java Fri Apr 5 16:09:09 2013 @@ -1,19 +1,3 @@ -/* - * 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. - */ /* Generated By:JavaCC: Do not edit this line. Token.java Version 5.0 */ /* JavaCCOptions:TOKEN_EXTENDS=,KEEP_LINE_COL=null,SUPPORT_CLASS_VISIBILITY_PUBLIC=true */ package org.apache.stanbol.rules.manager.parse; @@ -24,109 +8,124 @@ package org.apache.stanbol.rules.manager public class Token implements java.io.Serializable { - /** - * The version identifier for this Serializable class. Increment only if the <i>serialized</i> form of the - * class changes. - */ - private static final long serialVersionUID = 1L; - - /** - * An integer that describes the kind of this token. This numbering system is determined by JavaCCParser, - * and a table of these numbers is stored in the file ...Constants.java. - */ - public int kind; - - /** The line number of the first character of this Token. */ - public int beginLine; - /** The column number of the first character of this Token. */ - public int beginColumn; - /** The line number of the last character of this Token. */ - public int endLine; - /** The column number of the last character of this Token. */ - public int endColumn; - - /** - * The string image of the token. - */ - public String image; - - /** - * A reference to the next regular (non-special) token from the input stream. If this is the last token - * from the input stream, or if the token manager has not read tokens beyond this one, this field is set - * to null. This is true only if this token is also a regular token. Otherwise, see below for a - * description of the contents of this field. - */ - public Token next; - - /** - * This field is used to access special tokens that occur prior to this token, but after the immediately - * preceding regular (non-special) token. If there are no such special tokens, this field is set to null. - * When there are more than one such special token, this field refers to the last of these special tokens, - * which in turn refers to the next previous special token through its specialToken field, and so on until - * the first special token (whose specialToken field is null). The next fields of special tokens refer to - * other special tokens that immediately follow it (without an intervening regular token). If there is no - * such token, this field is null. - */ - public Token specialToken; - - /** - * An optional attribute value of the Token. Tokens which are not used as syntactic sugar will often - * contain meaningful values that will be used later on by the compiler or interpreter. This attribute - * value is often different from the image. Any subclass of Token that actually wants to return a non-null - * value can override this method as appropriate. - */ - public Object getValue() { - return null; - } - - /** - * No-argument constructor - */ - public Token() {} - - /** - * Constructs a new token for the specified Image. - */ - public Token(int kind) { - this(kind, null); - } - - /** - * Constructs a new token for the specified Image and Kind. - */ - public Token(int kind, String image) { - this.kind = kind; - this.image = image; - } - - /** - * Returns the image. - */ - public String toString() { - return image; - } - - /** - * Returns a new Token object, by default. However, if you want, you can create and return subclass - * objects based on the value of ofKind. Simply add the cases to the switch for all those special cases. - * For example, if you have a subclass of Token called IDToken that you want to create if ofKind is ID, - * simply add something like : - * - * case MyParserConstants.ID : return new IDToken(ofKind, image); - * - * to the following switch statement. Then you can cast matchedToken variable to the appropriate type and - * use sit in your lexical actions. - */ - public static Token newToken(int ofKind, String image) { - switch (ofKind) { - default: - return new Token(ofKind, image); - } - } - - public static Token newToken(int ofKind) { - return newToken(ofKind, null); - } + /** + * The version identifier for this Serializable class. + * Increment only if the <i>serialized</i> form of the + * class changes. + */ + private static final long serialVersionUID = 1L; + + /** + * An integer that describes the kind of this token. This numbering + * system is determined by JavaCCParser, and a table of these numbers is + * stored in the file ...Constants.java. + */ + public int kind; + + /** The line number of the first character of this Token. */ + public int beginLine; + /** The column number of the first character of this Token. */ + public int beginColumn; + /** The line number of the last character of this Token. */ + public int endLine; + /** The column number of the last character of this Token. */ + public int endColumn; + + /** + * The string image of the token. + */ + public String image; + + /** + * A reference to the next regular (non-special) token from the input + * stream. If this is the last token from the input stream, or if the + * token manager has not read tokens beyond this one, this field is + * set to null. This is true only if this token is also a regular + * token. Otherwise, see below for a description of the contents of + * this field. + */ + public Token next; + + /** + * This field is used to access special tokens that occur prior to this + * token, but after the immediately preceding regular (non-special) token. + * If there are no such special tokens, this field is set to null. + * When there are more than one such special token, this field refers + * to the last of these special tokens, which in turn refers to the next + * previous special token through its specialToken field, and so on + * until the first special token (whose specialToken field is null). + * The next fields of special tokens refer to other special tokens that + * immediately follow it (without an intervening regular token). If there + * is no such token, this field is null. + */ + public Token specialToken; + + /** + * An optional attribute value of the Token. + * Tokens which are not used as syntactic sugar will often contain + * meaningful values that will be used later on by the compiler or + * interpreter. This attribute value is often different from the image. + * Any subclass of Token that actually wants to return a non-null value can + * override this method as appropriate. + */ + public Object getValue() { + return null; + } + + /** + * No-argument constructor + */ + public Token() {} + + /** + * Constructs a new token for the specified Image. + */ + public Token(int kind) + { + this(kind, null); + } + + /** + * Constructs a new token for the specified Image and Kind. + */ + public Token(int kind, String image) + { + this.kind = kind; + this.image = image; + } + + /** + * Returns the image. + */ + public String toString() + { + return image; + } + + /** + * Returns a new Token object, by default. However, if you want, you + * can create and return subclass objects based on the value of ofKind. + * Simply add the cases to the switch for all those special cases. + * For example, if you have a subclass of Token called IDToken that + * you want to create if ofKind is ID, simply add something like : + * + * case MyParserConstants.ID : return new IDToken(ofKind, image); + * + * to the following switch statement. Then you can cast matchedToken + * variable to the appropriate type and use sit in your lexical actions. + */ + public static Token newToken(int ofKind, String image) + { + switch(ofKind) + { + default : return new Token(ofKind, image); + } + } + + public static Token newToken(int ofKind) + { + return newToken(ofKind, null); + } } /* JavaCC - OriginalChecksum=9e470861229c55fdb5d0dd6632a8a0e0 (do not edit this line) */ Modified: stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/TokenMgrError.java URL: http://svn.apache.org/viewvc/stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/TokenMgrError.java?rev=1465023&r1=1465022&r2=1465023&view=diff ============================================================================== --- stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/TokenMgrError.java (original) +++ stanbol/trunk/rules/manager/src/main/java/org/apache/stanbol/rules/manager/parse/TokenMgrError.java Fri Apr 5 16:09:09 2013 @@ -1,165 +1,147 @@ -/* - * 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. - */ /* Generated By:JavaCC: Do not edit this line. TokenMgrError.java Version 5.0 */ /* JavaCCOptions: */ package org.apache.stanbol.rules.manager.parse; /** Token Manager Error. */ -public class TokenMgrError extends Error { +public class TokenMgrError extends Error +{ - /** - * The version identifier for this Serializable class. Increment only if the <i>serialized</i> form of the - * class changes. - */ - private static final long serialVersionUID = 1L; - - /* - * Ordinals for various reasons why an Error of this type can be thrown. - */ - - /** - * Lexical error occurred. - */ - static final int LEXICAL_ERROR = 0; - - /** - * An attempt was made to create a second instance of a static token manager. - */ - static final int STATIC_LEXER_ERROR = 1; - - /** - * Tried to change to an invalid lexical state. - */ - static final int INVALID_LEXICAL_STATE = 2; - - /** - * Detected (and bailed out of) an infinite loop in the token manager. - */ - static final int LOOP_DETECTED = 3; - - /** - * Indicates the reason why the exception is thrown. It will have one of the above 4 values. - */ - int errorCode; - - /** - * Replaces unprintable characters by their escaped (or unicode escaped) equivalents in the given string - */ - protected static final String addEscapes(String str) { - StringBuffer retval = new StringBuffer(); - char ch; - for (int i = 0; i < str.length(); i++) { - switch (str.charAt(i)) { - case 0: - continue; - case '\b': - retval.append("\\b"); - continue; - case '\t': - retval.append("\\t"); - continue; - case '\n': - retval.append("\\n"); - continue; - case '\f': - retval.append("\\f"); - continue; - case '\r': - retval.append("\\r"); - continue; - case '\"': - retval.append("\\\""); - continue; - case '\'': - retval.append("\\\'"); - continue; - case '\\': - retval.append("\\\\"); - continue; - default: - if ((ch = str.charAt(i)) < 0x20 || ch > 0x7e) { - String s = "0000" + Integer.toString(ch, 16); - retval.append("\\u" + s.substring(s.length() - 4, s.length())); - } else { - retval.append(ch); - } - continue; - } - } - return retval.toString(); + /** + * The version identifier for this Serializable class. + * Increment only if the <i>serialized</i> form of the + * class changes. + */ + private static final long serialVersionUID = 1L; + + /* + * Ordinals for various reasons why an Error of this type can be thrown. + */ + + /** + * Lexical error occurred. + */ + static final int LEXICAL_ERROR = 0; + + /** + * An attempt was made to create a second instance of a static token manager. + */ + static final int STATIC_LEXER_ERROR = 1; + + /** + * Tried to change to an invalid lexical state. + */ + static final int INVALID_LEXICAL_STATE = 2; + + /** + * Detected (and bailed out of) an infinite loop in the token manager. + */ + static final int LOOP_DETECTED = 3; + + /** + * Indicates the reason why the exception is thrown. It will have + * one of the above 4 values. + */ + int errorCode; + + /** + * Replaces unprintable characters by their escaped (or unicode escaped) + * equivalents in the given string + */ + protected static final String addEscapes(String str) { + StringBuffer retval = new StringBuffer(); + char ch; + for (int i = 0; i < str.length(); i++) { + switch (str.charAt(i)) + { + case 0 : + continue; + case '\b': + retval.append("\\b"); + continue; + case '\t': + retval.append("\\t"); + continue; + case '\n': + retval.append("\\n"); + continue; + case '\f': + retval.append("\\f"); + continue; + case '\r': + retval.append("\\r"); + continue; + case '\"': + retval.append("\\\""); + continue; + case '\'': + retval.append("\\\'"); + continue; + case '\\': + retval.append("\\\\"); + continue; + default: + if ((ch = str.charAt(i)) < 0x20 || ch > 0x7e) { + String s = "0000" + Integer.toString(ch, 16); + retval.append("\\u" + s.substring(s.length() - 4, s.length())); + } else { + retval.append(ch); + } + continue; + } } + return retval.toString(); + } - /** - * Returns a detailed message for the Error when it is thrown by the token manager to indicate a lexical - * error. Parameters : EOFSeen : indicates if EOF caused the lexical error curLexState : lexical state in - * which this error occurred errorLine : line number when the error occurred errorColumn : column number - * when the error occurred errorAfter : prefix that was seen before this error occurred curchar : the - * offending character Note: You can customize the lexical error message by modifying this method. - */ - protected static String LexicalError(boolean EOFSeen, - int lexState, - int errorLine, - int errorColumn, - String errorAfter, - char curChar) { - return ("Lexical error at line " - + errorLine - + ", column " - + errorColumn - + ". Encountered: " - + (EOFSeen ? "<EOF> " : ("\"" + addEscapes(String.valueOf(curChar)) + "\"") + " (" - + (int) curChar + "), ") + "after : \"" + addEscapes(errorAfter) + "\""); - } - - /** - * You can also modify the body of this method to customize your error messages. For example, cases like - * LOOP_DETECTED and INVALID_LEXICAL_STATE are not of end-users concern, so you can return something like - * : - * - * "Internal Error : Please file a bug report .... " - * - * from this method for such cases in the release version of your parser. - */ - public String getMessage() { - return super.getMessage(); - } - - /* - * Constructors of various flavors follow. - */ - - /** No arg constructor. */ - public TokenMgrError() {} - - /** Constructor with message and reason. */ - public TokenMgrError(String message, int reason) { - super(message); - errorCode = reason; - } - - /** Full Constructor. */ - public TokenMgrError(boolean EOFSeen, - int lexState, - int errorLine, - int errorColumn, - String errorAfter, - char curChar, - int reason) { - this(LexicalError(EOFSeen, lexState, errorLine, errorColumn, errorAfter, curChar), reason); - } + /** + * Returns a detailed message for the Error when it is thrown by the + * token manager to indicate a lexical error. + * Parameters : + * EOFSeen : indicates if EOF caused the lexical error + * curLexState : lexical state in which this error occurred + * errorLine : line number when the error occurred + * errorColumn : column number when the error occurred + * errorAfter : prefix that was seen before this error occurred + * curchar : the offending character + * Note: You can customize the lexical error message by modifying this method. + */ + protected static String LexicalError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar) { + return("Lexical error at line " + + errorLine + ", column " + + errorColumn + ". Encountered: " + + (EOFSeen ? "<EOF> " : ("\"" + addEscapes(String.valueOf(curChar)) + "\"") + " (" + (int)curChar + "), ") + + "after : \"" + addEscapes(errorAfter) + "\""); + } + + /** + * You can also modify the body of this method to customize your error messages. + * For example, cases like LOOP_DETECTED and INVALID_LEXICAL_STATE are not + * of end-users concern, so you can return something like : + * + * "Internal Error : Please file a bug report .... " + * + * from this method for such cases in the release version of your parser. + */ + public String getMessage() { + return super.getMessage(); + } + + /* + * Constructors of various flavors follow. + */ + + /** No arg constructor. */ + public TokenMgrError() { + } + + /** Constructor with message and reason. */ + public TokenMgrError(String message, int reason) { + super(message); + errorCode = reason; + } + + /** Full Constructor. */ + public TokenMgrError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar, int reason) { + this(LexicalError(EOFSeen, lexState, errorLine, errorColumn, errorAfter, curChar), reason); + } } /* JavaCC - OriginalChecksum=b290e2629e47f0260a40d57d321bc81b (do not edit this line) */ Modified: stanbol/trunk/rules/refactor/src/main/java/org/apache/stanbol/rules/refactor/impl/RefactorerImpl.java URL: http://svn.apache.org/viewvc/stanbol/trunk/rules/refactor/src/main/java/org/apache/stanbol/rules/refactor/impl/RefactorerImpl.java?rev=1465023&r1=1465022&r2=1465023&view=diff ============================================================================== --- stanbol/trunk/rules/refactor/src/main/java/org/apache/stanbol/rules/refactor/impl/RefactorerImpl.java (original) +++ stanbol/trunk/rules/refactor/src/main/java/org/apache/stanbol/rules/refactor/impl/RefactorerImpl.java Fri Apr 5 16:09:09 2013 @@ -16,8 +16,10 @@ */ package org.apache.stanbol.rules.refactor.impl; +import java.io.ByteArrayInputStream; import java.io.IOException; import java.util.Dictionary; +import java.util.Hashtable; import java.util.List; import org.apache.clerezza.rdf.core.Graph; @@ -27,32 +29,50 @@ import org.apache.clerezza.rdf.core.UriR import org.apache.clerezza.rdf.core.access.TcManager; import org.apache.clerezza.rdf.core.access.WeightedTcProvider; import org.apache.clerezza.rdf.core.impl.SimpleMGraph; +import org.apache.clerezza.rdf.core.serializedform.Serializer; +import org.apache.clerezza.rdf.core.sparql.QueryEngine; import org.apache.clerezza.rdf.core.sparql.query.ConstructQuery; +import org.apache.clerezza.rdf.jena.sparql.JenaSparqlEngine; +import org.apache.clerezza.rdf.simple.storage.SimpleTcProvider; import org.apache.felix.scr.annotations.Activate; import org.apache.felix.scr.annotations.Component; import org.apache.felix.scr.annotations.Deactivate; import org.apache.felix.scr.annotations.Reference; import org.apache.felix.scr.annotations.Service; +import org.apache.stanbol.commons.owl.transformation.JenaToClerezzaConverter; +import org.apache.stanbol.ontologymanager.ontonet.api.ONManager; +import org.apache.stanbol.rules.adapters.clerezza.ClerezzaAdapter; +import org.apache.stanbol.rules.adapters.impl.RuleAdaptersFactoryImpl; +import org.apache.stanbol.rules.adapters.impl.RuleAdaptersManagerImpl; import org.apache.stanbol.rules.base.api.NoSuchRecipeException; import org.apache.stanbol.rules.base.api.Recipe; import org.apache.stanbol.rules.base.api.RecipeConstructionException; import org.apache.stanbol.rules.base.api.RuleAdapter; import org.apache.stanbol.rules.base.api.RuleAdapterManager; +import org.apache.stanbol.rules.base.api.RuleAdaptersFactory; import org.apache.stanbol.rules.base.api.RuleAtomCallExeption; import org.apache.stanbol.rules.base.api.RuleStore; import org.apache.stanbol.rules.base.api.UnavailableRuleObjectException; import org.apache.stanbol.rules.base.api.UnsupportedTypeForExportException; +import org.apache.stanbol.rules.manager.ClerezzaRuleStore; +import org.apache.stanbol.rules.manager.KB; +import org.apache.stanbol.rules.manager.RecipeImpl; import org.apache.stanbol.rules.manager.arqextention.CreatePropertyURIStringFromLabel; import org.apache.stanbol.rules.manager.arqextention.CreateStandardLabel; import org.apache.stanbol.rules.manager.arqextention.CreateURI; +import org.apache.stanbol.rules.manager.parse.RuleParserImpl; import org.apache.stanbol.rules.refactor.api.Refactorer; import org.apache.stanbol.rules.refactor.api.RefactoringException; import org.osgi.service.component.ComponentContext; import org.slf4j.Logger; import org.slf4j.LoggerFactory; +import com.hp.hpl.jena.rdf.model.Model; +import com.hp.hpl.jena.rdf.model.ModelFactory; +import com.hp.hpl.jena.reasoner.Reasoner; import com.hp.hpl.jena.sparql.function.FunctionRegistry; import com.hp.hpl.jena.sparql.pfunction.PropertyFunctionRegistry; +import com.hp.hpl.jena.vocabulary.XSD; /** * The RefactorerImpl is the concrete implementation of the Refactorer interface defined in the rule APIs of @@ -86,9 +106,9 @@ public class RefactorerImpl implements R * <p> * DO NOT USE to manually create instances - the RefactorerImpl instances do need to be configured! YOU * NEED TO USE - * {@link #RefactorerImpl(WeightedTcProvider, TcManager, RuleStore, RuleAdapterManager, Dictionary)} or - * its overloads, to parse the configuration and then initialise the rule store if running outside a OSGI - * environment. + * {@link #RefactorerImpl(WeightedTcProvider, Serializer, TcManager, ONManager, SemionManager, RuleStore, Reasoner, Dictionary)} + * or its overloads, to parse the configuration and then initialise the rule store if running outside a + * OSGI environment. */ public RefactorerImpl() { @@ -271,7 +291,9 @@ public class RefactorerImpl implements R List<ConstructQuery> constructQueries = (List<ConstructQuery>) ruleAdapter.adaptTo(recipe, ConstructQuery.class); - log.info("RULE LIST SIZE : " + constructQueries.size()); + for(ConstructQuery constructQuery : constructQueries){ + System.out.println(constructQuery.toString()); + } MGraph unionMGraph = new SimpleMGraph(); for (ConstructQuery constructQuery : constructQueries) { @@ -288,5 +310,71 @@ public class RefactorerImpl implements R } } + + + public static void main(String[] args){ + String graph = "<http://revyu.com/things/eswc-2008-paper-exposing-large-sitemaps> <http://purl.org/stuff/rev#hasReview> <http://revyu.com/reviews/bbecea3192d3c3bc5473ca8d9ab38cb143314a8e> ." + + "<http://revyu.com/reviews/bbecea3192d3c3bc5473ca8d9ab38cb143314a8e> <http://purl.org/stuff/rev#reviewer> <http://revyu.com/people/ChrisBizer> . " + + "<http://people.apache.org/~alexdma> <http://xmlns.com/foaf/0.1/knows> <http://revyu.com/people/ChrisBizer> . " + + "<http://revyu.com/reviews/bbecea3192d3c3bc5473ca8d9ab38cb143314a8e> <http://purl.org/stuff/rev#rating> \"4\"^^<" + XSD.integer.getURI() + "> . "; + + ByteArrayInputStream inputStream = new ByteArrayInputStream(graph.getBytes()); + + Model model = ModelFactory.createDefaultModel(); + model.read(inputStream, null, "N3"); + MGraph deserializedGraph = JenaToClerezzaConverter.jenaModelToClerezzaMGraph(model); + + String recipeString = "foaf = <http://xmlns.com/foaf/0.1/> . " + + "revyu = <http://purl.org/stuff/rev#> . " + + "myvoc = <http://www.semanticweb.org/voc/my/> . " + + "trustedContent[ " + + "has(revyu:hasReview, ?ci, ?review) . " + + "has(revyu:reviewer, ?review, ?y) . has(foaf:knows, ?x, ?y) . " + + "values(revyu:rating, ?review, ?rating) . gt(str(?rating), 3) " + + "-> has(myvoc:trustsContent, ?x, ?ci) " + + "]"; + + KB kb = RuleParserImpl.parse("http://test.org/recipe";, recipeString); + + Recipe recipe = new RecipeImpl(new UriRef("recipe"), "A recipe", kb.getRuleList()); + + class SpecialTcManager extends TcManager { + public SpecialTcManager(QueryEngine qe, WeightedTcProvider wtcp) { + super(); + bindQueryEngine(qe); + bindWeightedTcProvider(wtcp); + } + } + + QueryEngine qe = new JenaSparqlEngine(); + WeightedTcProvider wtcp = new SimpleTcProvider(); + TcManager tcm = new SpecialTcManager(qe, wtcp); + + Dictionary<String,Object> configuration = new Hashtable<String,Object>(); + RuleStore store = new ClerezzaRuleStore(configuration, tcm); + + Dictionary<String,Object> configuration2 = new Hashtable<String,Object>(); + + RuleAdaptersFactory ruleAdaptersFactory = new RuleAdaptersFactoryImpl(); + + Dictionary<String,Object> configuration3 = new Hashtable<String,Object>(); + new ClerezzaAdapter(configuration3, store, ruleAdaptersFactory); + + RuleAdapterManager ruleAdapterManager = new RuleAdaptersManagerImpl(configuration2, + ruleAdaptersFactory); + + Dictionary<String,Object> configuration4 = new Hashtable<String,Object>(); + + RefactorerImpl refactorer = new RefactorerImpl(wtcp, tcm, store, ruleAdapterManager, configuration4); + try { + MGraph mGraph = new SimpleMGraph(); + mGraph.addAll(refactorer.graphRefactoring(deserializedGraph, recipe)); + JenaToClerezzaConverter.clerezzaMGraphToJenaModel(mGraph).write(System.out); + } catch (RefactoringException e) { + // TODO Auto-generated catch block + e.printStackTrace(); + } + + } }
