Thread: [Htmlparser-cvs] htmlparser/src/org/htmlparser/parserHelper AttributeParser.java,1.36,1.37 Composite
Brought to you by:
derrickoswald
Menu
▾
▴
htmlparser-cvs
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper
In directory sc8-pr-cvs1:/tmp/cvs-serv31228/parserHelper
Modified Files:
AttributeParser.java CompositeTagScannerHelper.java
ParserHelper.java ScriptScannerHelper.java StringParser.java
TagParser.java
Log Message:
Change tabs to spaces in all source files.
Index: AttributeParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/AttributeParser.java,v
retrieving revision 1.36
retrieving revision 1.37
diff -C2 -d -r1.36 -r1.37
*** AttributeParser.java 24 Aug 2003 21:59:42 -0000 1.36
--- AttributeParser.java 3 Sep 2003 23:36:19 -0000 1.37
***************
*** 52,87 ****
! private Hashtable attributeTable;
! private String element;
! private String name;
! private String value;
! private String part;
! private String empty;
! private boolean equal;
! private StringTokenizer tokenizer;
! private boolean doubleQuote;
! private boolean singleQuote;
! private boolean ready;
! private String currentToken;
! private String tokenAccumulator;
! /**
! * Method to break the tag into pieces.
! * @param text All the text within the tag inside < and >.
* @return A Hastable with elements containing the
! * pieces of the tag. The tag-name has the value field set to
! * the constant Tag.TAGNAME. In addition the tag-name is
! * stored into the Hashtable with the name Tag.TAGNAME
! * where the value is the name of the tag.
! * Tag parameters without value
! * has the value "". Parameters with value are represented
! * in the Hastable by a name/value pair.
! * As html is case insensitive but Hastable is not are all
! * names converted into UPPERCASE to the Hastable
! * E.g extract the href values from A-tag's and print them
! * <pre>
! *
* Tag tag;
! * Hashtable h;
! * String tmp;
* try {
* NodeReader in = new NodeReader(new FileReader(path),2048);
--- 52,87 ----
! private Hashtable attributeTable;
! private String element;
! private String name;
! private String value;
! private String part;
! private String empty;
! private boolean equal;
! private StringTokenizer tokenizer;
! private boolean doubleQuote;
! private boolean singleQuote;
! private boolean ready;
! private String currentToken;
! private String tokenAccumulator;
! /**
! * Method to break the tag into pieces.
! * @param text All the text within the tag inside < and >.
* @return A Hastable with elements containing the
! * pieces of the tag. The tag-name has the value field set to
! * the constant Tag.TAGNAME. In addition the tag-name is
! * stored into the Hashtable with the name Tag.TAGNAME
! * where the value is the name of the tag.
! * Tag parameters without value
! * has the value "". Parameters with value are represented
! * in the Hastable by a name/value pair.
! * As html is case insensitive but Hastable is not are all
! * names converted into UPPERCASE to the Hastable
! * E.g extract the href values from A-tag's and print them
! * <pre>
! *
* Tag tag;
! * Hashtable h;
! * String tmp;
* try {
* NodeReader in = new NodeReader(new FileReader(path),2048);
***************
*** 102,118 ****
* ie.printStackTrace();
* }
! * </pre>
! *
! */
public Hashtable parseAttributes (String text) {
! attributeTable = new SpecialHashtable();
! part = null;
! empty = null;
name=null;
value=null;
element=null;
! equal = false;
delim=DELIMETERS;
! tokenizer = new StringTokenizer(text,delim,true);
while (true) {
part=getNextPartUsing(delim);
--- 102,118 ----
* ie.printStackTrace();
* }
! * </pre>
! *
! */
public Hashtable parseAttributes (String text) {
! attributeTable = new SpecialHashtable();
! part = null;
! empty = null;
name=null;
value=null;
element=null;
! equal = false;
delim=DELIMETERS;
! tokenizer = new StringTokenizer(text,delim,true);
while (true) {
part=getNextPartUsing(delim);
***************
*** 127,131 ****
}
else {
! processInvalidPart();
if (!tokenizer.hasMoreTokens ())
break;
--- 127,131 ----
}
else {
! processInvalidPart();
if (!tokenizer.hasMoreTokens ())
break;
***************
*** 160,201 ****
}
! private boolean isValid(String part) {
! return part != null && (0 < part.length ());
! }
! private void process(String part) {
! if (name == null) {
! if (!part.substring(0,1).equals(" ")) {
! name = part;
! equal=true;
! }
! }
! else {
! if (equal){
! if (part.equals("=")) {
! equal=false;
! delim=DELIMETERS_WITHOUT_EQUALS;
value=Tag.NOTHING;
! }
! else {
! putDataIntoTable(attributeTable,name,Tag.NULLVALUE,false);
! name=part;
! value=null;
! }
! }
! if (!equal && !part.equals("=")) {
! value=part;
! putDataIntoTable(attributeTable,name,value,false);
! name=null;
! value=null;
! }
! }
! }
private String getNextPartUsing(String delimiter) {
! tokenAccumulator = null;
! doubleQuote = false;
! singleQuote = false;
! ready = false;
while (ready == false && tokenizer.hasMoreTokens()) {
currentToken = tokenizer.nextToken(delimiter);
--- 160,201 ----
}
! private boolean isValid(String part) {
! return part != null && (0 < part.length ());
! }
! private void process(String part) {
! if (name == null) {
! if (!part.substring(0,1).equals(" ")) {
! name = part;
! equal=true;
! }
! }
! else {
! if (equal){
! if (part.equals("=")) {
! equal=false;
! delim=DELIMETERS_WITHOUT_EQUALS;
value=Tag.NOTHING;
! }
! else {
! putDataIntoTable(attributeTable,name,Tag.NULLVALUE,false);
! name=part;
! value=null;
! }
! }
! if (!equal && !part.equals("=")) {
! value=part;
! putDataIntoTable(attributeTable,name,value,false);
! name=null;
! value=null;
! }
! }
! }
private String getNextPartUsing(String delimiter) {
! tokenAccumulator = null;
! doubleQuote = false;
! singleQuote = false;
! ready = false;
while (ready == false && tokenizer.hasMoreTokens()) {
currentToken = tokenizer.nextToken(delimiter);
***************
*** 210,214 ****
tokenAccumulator="";
} else {
! tokenAccumulator = currentToken;
ready = isReadyWithNextPart(currentToken);
}
--- 210,214 ----
tokenAccumulator="";
} else {
! tokenAccumulator = currentToken;
ready = isReadyWithNextPart(currentToken);
}
***************
*** 217,256 ****
}
! private boolean isReadyWithNextPart(String currentToken) {
! boolean ready = false;
! if (isDelimeter(currentToken)) {
! if (currentToken.equals("=")){
! ready=true;
! }
! }
! else {
! ready=true;
! }
! return ready;
! }
! private boolean isDelimeter(String token) {
! return delim.indexOf(tokenAccumulator)>=0;
! }
!
! private boolean isCurrentTokenSingleQuote() {
! return currentToken.charAt(0)==SINGLE_QUOTE;
! }
! private boolean isCurrentTokenDoubleQuote() {
! return currentToken.charAt(0)==DOUBLE_QUOTE;
! }
! private void combineTokensInsideSingleOrDoubleQuotes() {
! if (doubleQuote && currentToken.charAt(0)==DOUBLE_QUOTE){
! doubleQuote= false;
! ready=true;
! } else if (singleQuote && currentToken.charAt(0)==SINGLE_QUOTE) {
! singleQuote=false;
! ready=true;
! }else {
! tokenAccumulator += currentToken;
! }
! }
--- 217,256 ----
}
! private boolean isReadyWithNextPart(String currentToken) {
! boolean ready = false;
! if (isDelimeter(currentToken)) {
! if (currentToken.equals("=")){
! ready=true;
! }
! }
! else {
! ready=true;
! }
! return ready;
! }
! private boolean isDelimeter(String token) {
! return delim.indexOf(tokenAccumulator)>=0;
! }
!
! private boolean isCurrentTokenSingleQuote() {
! return currentToken.charAt(0)==SINGLE_QUOTE;
! }
! private boolean isCurrentTokenDoubleQuote() {
! return currentToken.charAt(0)==DOUBLE_QUOTE;
! }
! private void combineTokensInsideSingleOrDoubleQuotes() {
! if (doubleQuote && currentToken.charAt(0)==DOUBLE_QUOTE){
! doubleQuote= false;
! ready=true;
! } else if (singleQuote && currentToken.charAt(0)==SINGLE_QUOTE) {
! singleQuote=false;
! ready=true;
! }else {
! tokenAccumulator += currentToken;
! }
! }
Index: CompositeTagScannerHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/CompositeTagScannerHelper.java,v
retrieving revision 1.43
retrieving revision 1.44
diff -C2 -d -r1.43 -r1.44
*** CompositeTagScannerHelper.java 24 Aug 2003 21:59:42 -0000 1.43
--- CompositeTagScannerHelper.java 3 Sep 2003 23:36:19 -0000 1.44
***************
*** 41,225 ****
public class CompositeTagScannerHelper {
! private CompositeTagScanner scanner;
! private Tag tag;
! private String url;
! private NodeReader reader;
! private String currLine;
! private Tag endTag;
! private NodeList nodeList;
! private boolean endTagFound;
! private int startingLineNumber;
! private int endingLineNumber;
! private boolean balance_quotes;
!
! public CompositeTagScannerHelper(
! CompositeTagScanner scanner,
! Tag tag,
! String url,
! NodeReader reader,
! String currLine,
boolean balance_quotes) {
!
! this.scanner = scanner;
! this.tag = tag;
! this.url = url;
! this.reader = reader;
! this.currLine = currLine;
! this.endTag = null;
! this.nodeList = new NodeList();
! this.endTagFound = false;
this.balance_quotes = balance_quotes;
! }
! public Tag scan() throws ParserException {
! this.startingLineNumber = reader.getLastLineNumber();
! if (shouldCreateEndTagAndExit()) {
! return createEndTagAndRepositionReader();
! }
! scanner.beforeScanningStarts();
! Node currentNode = tag;
!
! doEmptyXmlTagCheckOn(currentNode);
! if (!endTagFound) {
! do {
! currentNode = reader.readElement(balance_quotes);
! if (currentNode==null) continue;
! currLine = reader.getCurrentLine();
! if (currentNode instanceof Tag)
! doForceCorrectionCheckOn((Tag)currentNode);
!
! doEmptyXmlTagCheckOn(currentNode);
! if (!endTagFound)
! doChildAndEndTagCheckOn(currentNode);
! }
! while (currentNode!=null && !endTagFound);
! }
! if (endTag==null) {
! createCorrectionEndTagBefore(reader.getLastReadPosition()+1);
! }
!
! this.endingLineNumber = reader.getLastLineNumber();
! return createTag();
! }
! private boolean shouldCreateEndTagAndExit() {
! return scanner.shouldCreateEndTagAndExit();
! }
! private Tag createEndTagAndRepositionReader() {
! createCorrectionEndTagBefore(tag.elementBegin());
! reader.setPosInLine(tag.elementBegin());
! reader.setDontReadNextLine(true);
! return endTag;
! }
! private void createCorrectionEndTagBefore(int pos) {
! String endTagName = tag.getTagName();
! int endTagBegin = pos ;
! int endTagEnd = endTagBegin + endTagName.length() + 2;
! endTag = new EndTag(
! new TagData(
! endTagBegin,
! endTagEnd,
! endTagName,
! currLine
! )
! );
! }
!
! private void createCorrectionEndTagBefore(Tag possibleEndTagCauser) {
! String endTagName = tag.getTagName();
! int endTagBegin = possibleEndTagCauser.elementBegin();
! int endTagEnd = endTagBegin + endTagName.length() + 2;
! possibleEndTagCauser.setTagBegin(endTagEnd+1);
! reader.addNextParsedNode(possibleEndTagCauser);
! endTag = new EndTag(
! new TagData(
! endTagBegin,
! endTagEnd,
! endTagName,
! currLine
! )
! );
! }
! private Tag createTag() throws ParserException {
! CompositeTag newTag =
! (CompositeTag)
! scanner.createTag(
! new TagData(
! tag.elementBegin(),
! endTag.elementEnd(),
! startingLineNumber,
! endingLineNumber,
! tag.getText(),
! currLine,
! url,
! tag.isEmptyXmlTag()
! ),
! new CompositeTagData(
! tag,endTag,nodeList
! )
! );
! for (int i=0;i<newTag.getChildCount();i++) {
! Node child = newTag.childAt(i);
! child.setParent(newTag);
! }
! return newTag;
! }
! private void doChildAndEndTagCheckOn(Node currentNode) {
! if (currentNode instanceof EndTag) {
! EndTag possibleEndTag = (EndTag)currentNode;
! if (isExpectedEndTag(possibleEndTag)) {
! endTagFound = true;
! endTag = possibleEndTag;
! return;
! }
! }
! nodeList.add(currentNode);
! scanner.childNodeEncountered(currentNode);
! }
! private boolean isExpectedEndTag(EndTag possibleEndTag) {
! return possibleEndTag.getTagName().equals(tag.getTagName());
! }
! private void doEmptyXmlTagCheckOn(Node currentNode) {
! if (currentNode instanceof Tag) {
! Tag possibleEndTag = (Tag)currentNode;
! if (isXmlEndTag(tag)) {
! endTag = possibleEndTag;
! endTagFound = true;
! }
! }
! }
! private void doForceCorrectionCheckOn(Tag possibleEndTagCauser) {
! if (isEndTagMissing(possibleEndTagCauser)) {
! createCorrectionEndTagBefore(possibleEndTagCauser);
! endTagFound = true;
! }
! }
! private boolean isEndTagMissing(Tag possibleEndTag) {
! return
! scanner.isTagToBeEndedFor(possibleEndTag) ||
! isSelfChildTagRecievedIncorrectly(possibleEndTag);
! }
! private boolean isSelfChildTagRecievedIncorrectly(Tag possibleEndTag) {
! return (
! !(possibleEndTag instanceof EndTag) &&
! !scanner.isAllowSelfChildren() &&
! possibleEndTag.getTagName().equals(tag.getTagName())
! );
! }
!
! public boolean isXmlEndTag(Tag tag) {
! String tagText = tag.getText();
! int lastSlash = tagText.lastIndexOf("/");
! return (lastSlash == tagText.length()-1 || tag.isEmptyXmlTag()) && tag.getText().indexOf("://")==-1;
! }
}
--- 41,225 ----
public class CompositeTagScannerHelper {
! private CompositeTagScanner scanner;
! private Tag tag;
! private String url;
! private NodeReader reader;
! private String currLine;
! private Tag endTag;
! private NodeList nodeList;
! private boolean endTagFound;
! private int startingLineNumber;
! private int endingLineNumber;
! private boolean balance_quotes;
!
! public CompositeTagScannerHelper(
! CompositeTagScanner scanner,
! Tag tag,
! String url,
! NodeReader reader,
! String currLine,
boolean balance_quotes) {
!
! this.scanner = scanner;
! this.tag = tag;
! this.url = url;
! this.reader = reader;
! this.currLine = currLine;
! this.endTag = null;
! this.nodeList = new NodeList();
! this.endTagFound = false;
this.balance_quotes = balance_quotes;
! }
! public Tag scan() throws ParserException {
! this.startingLineNumber = reader.getLastLineNumber();
! if (shouldCreateEndTagAndExit()) {
! return createEndTagAndRepositionReader();
! }
! scanner.beforeScanningStarts();
! Node currentNode = tag;
!
! doEmptyXmlTagCheckOn(currentNode);
! if (!endTagFound) {
! do {
! currentNode = reader.readElement(balance_quotes);
! if (currentNode==null) continue;
! currLine = reader.getCurrentLine();
! if (currentNode instanceof Tag)
! doForceCorrectionCheckOn((Tag)currentNode);
!
! doEmptyXmlTagCheckOn(currentNode);
! if (!endTagFound)
! doChildAndEndTagCheckOn(currentNode);
! }
! while (currentNode!=null && !endTagFound);
! }
! if (endTag==null) {
! createCorrectionEndTagBefore(reader.getLastReadPosition()+1);
! }
!
! this.endingLineNumber = reader.getLastLineNumber();
! return createTag();
! }
! private boolean shouldCreateEndTagAndExit() {
! return scanner.shouldCreateEndTagAndExit();
! }
! private Tag createEndTagAndRepositionReader() {
! createCorrectionEndTagBefore(tag.elementBegin());
! reader.setPosInLine(tag.elementBegin());
! reader.setDontReadNextLine(true);
! return endTag;
! }
! private void createCorrectionEndTagBefore(int pos) {
! String endTagName = tag.getTagName();
! int endTagBegin = pos ;
! int endTagEnd = endTagBegin + endTagName.length() + 2;
! endTag = new EndTag(
! new TagData(
! endTagBegin,
! endTagEnd,
! endTagName,
! currLine
! )
! );
! }
!
! private void createCorrectionEndTagBefore(Tag possibleEndTagCauser) {
! String endTagName = tag.getTagName();
! int endTagBegin = possibleEndTagCauser.elementBegin();
! int endTagEnd = endTagBegin + endTagName.length() + 2;
! possibleEndTagCauser.setTagBegin(endTagEnd+1);
! reader.addNextParsedNode(possibleEndTagCauser);
! endTag = new EndTag(
! new TagData(
! endTagBegin,
! endTagEnd,
! endTagName,
! currLine
! )
! );
! }
! private Tag createTag() throws ParserException {
! CompositeTag newTag =
! (CompositeTag)
! scanner.createTag(
! new TagData(
! tag.elementBegin(),
! endTag.elementEnd(),
! startingLineNumber,
! endingLineNumber,
! tag.getText(),
! currLine,
! url,
! tag.isEmptyXmlTag()
! ),
! new CompositeTagData(
! tag,endTag,nodeList
! )
! );
! for (int i=0;i<newTag.getChildCount();i++) {
! Node child = newTag.childAt(i);
! child.setParent(newTag);
! }
! return newTag;
! }
! private void doChildAndEndTagCheckOn(Node currentNode) {
! if (currentNode instanceof EndTag) {
! EndTag possibleEndTag = (EndTag)currentNode;
! if (isExpectedEndTag(possibleEndTag)) {
! endTagFound = true;
! endTag = possibleEndTag;
! return;
! }
! }
! nodeList.add(currentNode);
! scanner.childNodeEncountered(currentNode);
! }
! private boolean isExpectedEndTag(EndTag possibleEndTag) {
! return possibleEndTag.getTagName().equals(tag.getTagName());
! }
! private void doEmptyXmlTagCheckOn(Node currentNode) {
! if (currentNode instanceof Tag) {
! Tag possibleEndTag = (Tag)currentNode;
! if (isXmlEndTag(tag)) {
! endTag = possibleEndTag;
! endTagFound = true;
! }
! }
! }
! private void doForceCorrectionCheckOn(Tag possibleEndTagCauser) {
! if (isEndTagMissing(possibleEndTagCauser)) {
! createCorrectionEndTagBefore(possibleEndTagCauser);
! endTagFound = true;
! }
! }
! private boolean isEndTagMissing(Tag possibleEndTag) {
! return
! scanner.isTagToBeEndedFor(possibleEndTag) ||
! isSelfChildTagRecievedIncorrectly(possibleEndTag);
! }
! private boolean isSelfChildTagRecievedIncorrectly(Tag possibleEndTag) {
! return (
! !(possibleEndTag instanceof EndTag) &&
! !scanner.isAllowSelfChildren() &&
! possibleEndTag.getTagName().equals(tag.getTagName())
! );
! }
!
! public boolean isXmlEndTag(Tag tag) {
! String tagText = tag.getText();
! int lastSlash = tagText.lastIndexOf("/");
! return (lastSlash == tagText.length()-1 || tag.isEmptyXmlTag()) && tag.getText().indexOf("://")==-1;
! }
}
Index: ParserHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/ParserHelper.java,v
retrieving revision 1.13
retrieving revision 1.14
diff -C2 -d -r1.13 -r1.14
*** ParserHelper.java 24 Aug 2003 21:59:42 -0000 1.13
--- ParserHelper.java 3 Sep 2003 23:36:19 -0000 1.14
***************
*** 42,106 ****
public class ParserHelper implements Serializable {
! public ParserHelper() {
! super();
! }
! /**
! * Opens a connection using the given url.
! * @param url The url to open.
! * @param feedback The ibject to use for messages or <code>null</code>.
! * @exception ParserException if an i/o exception occurs accessing the url.
! */
! public static URLConnection openConnection (URL url, ParserFeedback feedback)
! throws
! ParserException
! {
! URLConnection ret;
!
! try
! {
! ret = url.openConnection ();
! }
! catch (IOException ioe)
! {
! String msg = "HTMLParser.openConnection() : Error in opening a connection to " + url.toExternalForm ();
! ParserException ex = new ParserException (msg, ioe);
! if (null != feedback)
! feedback.error (msg, ex);
! throw ex;
! }
!
! return (ret);
! }
! /**
! * Opens a connection based on a given string.
! * The string is either a file, in which case <code>file://localhost</code>
! * is prepended to a canonical path derived from the string, or a url that
! * begins with one of the known protocol strings, i.e. <code>http://</code>.
* Embedded spaces are silently converted to %20 sequences.
! * @param string The name of a file or a url.
! * @param feedback The object to use for messages or <code>null</code> for no feedback.
! * @exception ParserException if the string is not a valid url or file.
! */
! public static URLConnection openConnection (String string, ParserFeedback feedback)
! throws
! ParserException
! {
! final String prefix = "file://localhost";
! String resource;
! URL url;
! StringBuffer buffer;
! URLConnection ret;
!
! try
! {
! url = new URL (LinkProcessor.fixSpaces (string));
! ret = ParserHelper.openConnection (url, feedback);
! }
! catch (MalformedURLException murle)
! { // try it as a file
! try
! {
File file = new File (string);
resource = file.getCanonicalPath ();
--- 42,106 ----
public class ParserHelper implements Serializable {
! public ParserHelper() {
! super();
! }
! /**
! * Opens a connection using the given url.
! * @param url The url to open.
! * @param feedback The ibject to use for messages or <code>null</code>.
! * @exception ParserException if an i/o exception occurs accessing the url.
! */
! public static URLConnection openConnection (URL url, ParserFeedback feedback)
! throws
! ParserException
! {
! URLConnection ret;
!
! try
! {
! ret = url.openConnection ();
! }
! catch (IOException ioe)
! {
! String msg = "HTMLParser.openConnection() : Error in opening a connection to " + url.toExternalForm ();
! ParserException ex = new ParserException (msg, ioe);
! if (null != feedback)
! feedback.error (msg, ex);
! throw ex;
! }
!
! return (ret);
! }
! /**
! * Opens a connection based on a given string.
! * The string is either a file, in which case <code>file://localhost</code>
! * is prepended to a canonical path derived from the string, or a url that
! * begins with one of the known protocol strings, i.e. <code>http://</code>.
* Embedded spaces are silently converted to %20 sequences.
! * @param string The name of a file or a url.
! * @param feedback The object to use for messages or <code>null</code> for no feedback.
! * @exception ParserException if the string is not a valid url or file.
! */
! public static URLConnection openConnection (String string, ParserFeedback feedback)
! throws
! ParserException
! {
! final String prefix = "file://localhost";
! String resource;
! URL url;
! StringBuffer buffer;
! URLConnection ret;
!
! try
! {
! url = new URL (LinkProcessor.fixSpaces (string));
! ret = ParserHelper.openConnection (url, feedback);
! }
! catch (MalformedURLException murle)
! { // try it as a file
! try
! {
File file = new File (string);
resource = file.getCanonicalPath ();
***************
*** 110,189 ****
buffer.append ("/");
buffer.append (resource);
! url = new URL (LinkProcessor.fixSpaces (buffer.toString ()));
! ret = ParserHelper.openConnection (url, feedback);
! if (null != feedback)
! feedback.info (url.toExternalForm ());
! }
! catch (MalformedURLException murle2)
! {
! String msg = "HTMLParser.openConnection() : Error in opening a connection to " + string;
! ParserException ex = new ParserException (msg, murle2);
! if (null != feedback)
! feedback.error (msg, ex);
! throw ex;
! }
! catch (IOException ioe)
{
! String msg = "HTMLParser.openConnection() : Error in opening a connection to " + string;
! ParserException ex = new ParserException (msg, ioe);
! if (null != feedback)
! feedback.error (msg, ex);
! throw ex;
}
! }
!
! return (ret);
! }
! /**
! * Lookup a character set name.
! * <em>Vacuous for JVM's without <code>java.nio.charset</code>.</em>
! * This uses reflection so the code will still run under prior JDK's but
! * in that case the default is always returned.
! * @param name The name to look up. One of the aliases for a character set.
! * @param _default The name to return if the lookup fails.
! */
! public static String findCharset (String name, String _default)
! {
! String ret;
! try
! {
! Class cls;
! java.lang.reflect.Method method;
! Object object;
! cls = Class.forName ("java.nio.charset.Charset");
! method = cls.getMethod ("forName", new Class[] { String.class });
! object = method.invoke (null, new Object[] { name });
! method = cls.getMethod ("name", new Class[] { });
! object = method.invoke (object, new Object[] { });
! ret = (String)object;
! }
! catch (ClassNotFoundException cnfe)
! {
! // for reflection exceptions, assume the name is correct
! ret = name;
! }
! catch (NoSuchMethodException nsme)
! {
! // for reflection exceptions, assume the name is correct
! ret = name;
! }
! catch (IllegalAccessException ia)
! {
! // for reflection exceptions, assume the name is correct
! ret = name;
! }
! catch (java.lang.reflect.InvocationTargetException ita)
! {
! // java.nio.charset.IllegalCharsetNameException
! // and java.nio.charset.UnsupportedCharsetException
! // return the default
! ret = _default;
! }
! return (ret);
! }
}
--- 110,189 ----
buffer.append ("/");
buffer.append (resource);
! url = new URL (LinkProcessor.fixSpaces (buffer.toString ()));
! ret = ParserHelper.openConnection (url, feedback);
! if (null != feedback)
! feedback.info (url.toExternalForm ());
! }
! catch (MalformedURLException murle2)
{
! String msg = "HTMLParser.openConnection() : Error in opening a connection to " + string;
! ParserException ex = new ParserException (msg, murle2);
! if (null != feedback)
! feedback.error (msg, ex);
! throw ex;
}
! catch (IOException ioe)
! {
! String msg = "HTMLParser.openConnection() : Error in opening a connection to " + string;
! ParserException ex = new ParserException (msg, ioe);
! if (null != feedback)
! feedback.error (msg, ex);
! throw ex;
! }
! }
!
! return (ret);
! }
! /**
! * Lookup a character set name.
! * <em>Vacuous for JVM's without <code>java.nio.charset</code>.</em>
! * This uses reflection so the code will still run under prior JDK's but
! * in that case the default is always returned.
! * @param name The name to look up. One of the aliases for a character set.
! * @param _default The name to return if the lookup fails.
! */
! public static String findCharset (String name, String _default)
! {
! String ret;
! try
! {
! Class cls;
! java.lang.reflect.Method method;
! Object object;
! cls = Class.forName ("java.nio.charset.Charset");
! method = cls.getMethod ("forName", new Class[] { String.class });
! object = method.invoke (null, new Object[] { name });
! method = cls.getMethod ("name", new Class[] { });
! object = method.invoke (object, new Object[] { });
! ret = (String)object;
! }
! catch (ClassNotFoundException cnfe)
! {
! // for reflection exceptions, assume the name is correct
! ret = name;
! }
! catch (NoSuchMethodException nsme)
! {
! // for reflection exceptions, assume the name is correct
! ret = name;
! }
! catch (IllegalAccessException ia)
! {
! // for reflection exceptions, assume the name is correct
! ret = name;
! }
! catch (java.lang.reflect.InvocationTargetException ita)
! {
! // java.nio.charset.IllegalCharsetNameException
! // and java.nio.charset.UnsupportedCharsetException
! // return the default
! ret = _default;
! }
! return (ret);
! }
}
Index: ScriptScannerHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/ScriptScannerHelper.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** ScriptScannerHelper.java 24 Aug 2003 21:59:42 -0000 1.8
--- ScriptScannerHelper.java 3 Sep 2003 23:36:19 -0000 1.9
***************
*** 38,214 ****
public class ScriptScannerHelper {
! private int endTagLoc;
! private Tag endTag;
! private Tag startTag;
! private int startingPos;
! private boolean sameLine;
! private boolean endTagFound;
! private NodeReader reader;
! private StringBuffer scriptContents;
! private ScriptScanner scriptScanner;
! private Tag tag;
! private String url;
! private String currLine;
!
! public ScriptScannerHelper(Tag tag, String url, NodeReader nodeReader, String currLine, ScriptScanner scriptScanner) {
! this.reader = nodeReader;
! this.scriptScanner = scriptScanner;
! this.tag = tag;
! this.url = url;
! this.currLine = currLine;
! }
! public Tag scan() throws ParserException {
! int startLine = reader.getLastLineNumber();
! startTag = tag;
! extractScriptTagFrom(currLine);
! if (isScriptEndTagNotFound()) {
! createScriptEndTag(tag, currLine);
! }
! return createScriptTagUsing(url, currLine, startLine);
! }
!
! private Tag createScriptTagUsing(String url, String currLine, int startLine) {
! return scriptScanner.createTag(
! new TagData(
! startTag.elementBegin(),
! endTag.elementEnd(),
! startLine,
! reader.getLastLineNumber(),
! startTag.getText(),
! currLine,
! url,
! false
! ), new CompositeTagData(
! startTag,endTag,createChildrenNodeList()
! )
! );
! }
! private NodeList createChildrenNodeList() {
! NodeList childrenNodeList = new NodeList();
! childrenNodeList.add(
! new StringNode(
! scriptContents,
! startTag.elementEnd(),
! endTag.elementBegin()-1
! )
! );
! return childrenNodeList;
! }
! private void createScriptEndTag(Tag tag, String currLine) {
! // If end tag doesn't exist, create one
! String endTagName = tag.getTagName();
! int endTagBegin = reader.getLastReadPosition()+1 ;
! int endTagEnd = endTagBegin + endTagName.length() + 2;
! endTag = new EndTag(
! new TagData(
! endTagBegin,
! endTagEnd,
! endTagName,
! currLine
! )
! );
! }
! private boolean isScriptEndTagNotFound() {
! return endTag == null;
! }
! private void extractScriptTagFrom(String currLine) throws ParserException {
! String line = null;
! scriptContents = new StringBuffer();
! endTagFound = false;
!
! endTag = null;
! line = currLine;
! sameLine = true;
! startingPos = startTag.elementEnd();
! do {
! doExtractionOfScriptContentsFrom(line);
! if (!endTagFound) {
! line = reader.getNextLine();
! startingPos = 0;
! }
! if (sameLine)
! sameLine = false;
! }
! while (line!=null && !endTagFound);
! }
! private void doExtractionOfScriptContentsFrom(String line) throws ParserException {
! endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(),startingPos);
! findStartingAndEndingLocations(line);
!
! if (endTagLoc!=-1) {
! extractEndTagFrom(line);
! } else {
! continueParsing(line);
! }
! }
! private void continueParsing(String line) {
! if (sameLine)
! scriptContents.append(
! line.substring(
! startTag.elementEnd()+1
! )
! );
! else {
! scriptContents.append(Parser.getLineSeparator());
! scriptContents.append(line);
! }
! }
! private void extractEndTagFrom(String line) throws ParserException {
! endTagFound = true;
! endTag = (EndTag)EndTag.find(line,endTagLoc);
! if (sameLine)
! scriptContents.append(
! getCodeBetweenStartAndEndTags(
! line,
! startTag,
! endTagLoc)
! );
! else {
! scriptContents.append(Parser.getLineSeparator());
! scriptContents.append(line.substring(0,endTagLoc));
! }
!
! reader.setPosInLine(endTag.elementEnd());
! }
! private void findStartingAndEndingLocations(String line) {
! while (endTagLoc>0 && isThisEndTagLocationFalseMatch(line, endTagLoc)) {
! startingPos = endTagLoc+scriptScanner.getEndTag().length();
! endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(), startingPos);
! }
! }
! public String getCodeBetweenStartAndEndTags(
! String line,
! Tag startTag,
! int endTagLoc) throws ParserException {
! try {
!
! return line.substring(
! startTag.elementEnd()+1,
! endTagLoc
! );
! }
! catch (Exception e) {
! StringBuffer msg = new StringBuffer("Error in getCodeBetweenStartAndEndTags():\n");
! msg.append("substring starts at: "+(startTag.elementEnd()+1)).append("\n");
! msg.append("substring ends at: "+(endTagLoc));
! throw new ParserException(msg.toString(),e);
! }
! }
! private boolean isThisEndTagLocationFalseMatch(String line, int endTagLoc) {
! if (endTagLoc+scriptScanner.getEndTag().length() > line.length()-1) return false;
! char charAfterSuspectedEndTag =
! line.charAt(endTagLoc+scriptScanner.getEndTag().length());
! return charAfterSuspectedEndTag=='"' || charAfterSuspectedEndTag=='\'';
! }
}
--- 38,214 ----
public class ScriptScannerHelper {
! private int endTagLoc;
! private Tag endTag;
! private Tag startTag;
! private int startingPos;
! private boolean sameLine;
! private boolean endTagFound;
! private NodeReader reader;
! private StringBuffer scriptContents;
! private ScriptScanner scriptScanner;
! private Tag tag;
! private String url;
! private String currLine;
!
! public ScriptScannerHelper(Tag tag, String url, NodeReader nodeReader, String currLine, ScriptScanner scriptScanner) {
! this.reader = nodeReader;
! this.scriptScanner = scriptScanner;
! this.tag = tag;
! this.url = url;
! this.currLine = currLine;
! }
! public Tag scan() throws ParserException {
! int startLine = reader.getLastLineNumber();
! startTag = tag;
! extractScriptTagFrom(currLine);
! if (isScriptEndTagNotFound()) {
! createScriptEndTag(tag, currLine);
! }
! return createScriptTagUsing(url, currLine, startLine);
! }
!
! private Tag createScriptTagUsing(String url, String currLine, int startLine) {
! return scriptScanner.createTag(
! new TagData(
! startTag.elementBegin(),
! endTag.elementEnd(),
! startLine,
! reader.getLastLineNumber(),
! startTag.getText(),
! currLine,
! url,
! false
! ), new CompositeTagData(
! startTag,endTag,createChildrenNodeList()
! )
! );
! }
! private NodeList createChildrenNodeList() {
! NodeList childrenNodeList = new NodeList();
! childrenNodeList.add(
! new StringNode(
! scriptContents,
! startTag.elementEnd(),
! endTag.elementBegin()-1
! )
! );
! return childrenNodeList;
! }
! private void createScriptEndTag(Tag tag, String currLine) {
! // If end tag doesn't exist, create one
! String endTagName = tag.getTagName();
! int endTagBegin = reader.getLastReadPosition()+1 ;
! int endTagEnd = endTagBegin + endTagName.length() + 2;
! endTag = new EndTag(
! new TagData(
! endTagBegin,
! endTagEnd,
! endTagName,
! currLine
! )
! );
! }
! private boolean isScriptEndTagNotFound() {
! return endTag == null;
! }
! private void extractScriptTagFrom(String currLine) throws ParserException {
! String line = null;
! scriptContents = new StringBuffer();
! endTagFound = false;
!
! endTag = null;
! line = currLine;
! sameLine = true;
! startingPos = startTag.elementEnd();
! do {
! doExtractionOfScriptContentsFrom(line);
! if (!endTagFound) {
! line = reader.getNextLine();
! startingPos = 0;
! }
! if (sameLine)
! sameLine = false;
! }
! while (line!=null && !endTagFound);
! }
! private void doExtractionOfScriptContentsFrom(String line) throws ParserException {
! endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(),startingPos);
! findStartingAndEndingLocations(line);
!
! if (endTagLoc!=-1) {
! extractEndTagFrom(line);
! } else {
! continueParsing(line);
! }
! }
! private void continueParsing(String line) {
! if (sameLine)
! scriptContents.append(
! line.substring(
! startTag.elementEnd()+1
! )
! );
! else {
! scriptContents.append(Parser.getLineSeparator());
! scriptContents.append(line);
! }
! }
! private void extractEndTagFrom(String line) throws ParserException {
! endTagFound = true;
! endTag = (EndTag)EndTag.find(line,endTagLoc);
! if (sameLine)
! scriptContents.append(
! getCodeBetweenStartAndEndTags(
! line,
! startTag,
! endTagLoc)
! );
! else {
! scriptContents.append(Parser.getLineSeparator());
! scriptContents.append(line.substring(0,endTagLoc));
! }
!
! reader.setPosInLine(endTag.elementEnd());
! }
! private void findStartingAndEndingLocations(String line) {
! while (endTagLoc>0 && isThisEndTagLocationFalseMatch(line, endTagLoc)) {
! startingPos = endTagLoc+scriptScanner.getEndTag().length();
! endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(), startingPos);
! }
! }
! public String getCodeBetweenStartAndEndTags(
! String line,
! Tag startTag,
! int endTagLoc) throws ParserException {
! try {
!
! return line.substring(
! startTag.elementEnd()+1,
! endTagLoc
! );
! }
! catch (Exception e) {
! StringBuffer msg = new StringBuffer("Error in getCodeBetweenStartAndEndTags():\n");
! msg.append("substring starts at: "+(startTag.elementEnd()+1)).append("\n");
! msg.append("substring ends at: "+(endTagLoc));
! throw new ParserException(msg.toString(),e);
! }
! }
! private boolean isThisEndTagLocationFalseMatch(String line, int endTagLoc) {
! if (endTagLoc+scriptScanner.getEndTag().length() > line.length()-1) return false;
! char charAfterSuspectedEndTag =
! line.charAt(endTagLoc+scriptScanner.getEndTag().length());
! return charAfterSuspectedEndTag=='"' || charAfterSuspectedEndTag=='\'';
! }
}
Index: StringParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/StringParser.java,v
retrieving revision 1.36
retrieving revision 1.37
diff -C2 -d -r1.36 -r1.37
*** StringParser.java 24 Aug 2003 21:59:42 -0000 1.36
--- StringParser.java 3 Sep 2003 23:36:19 -0000 1.37
***************
*** 34,41 ****
public class StringParser {
! private final static int BEFORE_PARSE_BEGINS_STATE=0;
! private final static int PARSE_HAS_BEGUN_STATE=1;
! private final static int PARSE_COMPLETED_STATE=2;
! private final static int PARSE_IGNORE_STATE=3;
/**
--- 34,41 ----
public class StringParser {
! private final static int BEFORE_PARSE_BEGINS_STATE=0;
! private final static int PARSE_HAS_BEGUN_STATE=1;
! private final static int PARSE_COMPLETED_STATE=2;
! private final static int PARSE_IGNORE_STATE=3;
/**
***************
*** 65,89 ****
}
! /**
! * Locate the StringNode within the input string, by parsing from the given position
! * @param reader HTML reader to be provided so as to allow reading of next line
! * @param input Input String
! * @param position Position to start parsing from
! * @param balance_quotes If <code>true</code> enter ignoring state on
* encountering quotes.
! */
! public Node find(NodeReader reader,String input,int position, boolean balance_quotes)
! {
! StringBuffer textBuffer = new StringBuffer();
! int state = BEFORE_PARSE_BEGINS_STATE;
! int textBegin=position;
! int textEnd=position;
! int inputLen = input.length();
! char ch;
char ignore_ender = '\"';
! for (int i=position;(i<inputLen && state!=PARSE_COMPLETED_STATE);i++)
! {
! ch = input.charAt(i);
! if (ch=='<' && state!=PARSE_IGNORE_STATE)
{
if (beginTag (input, i))
--- 65,89 ----
}
! /**
! * Locate the StringNode within the input string, by parsing from the given position
! * @param reader HTML reader to be provided so as to allow reading of next line
! * @param input Input String
! * @param position Position to start parsing from
! * @param balance_quotes If <code>true</code> enter ignoring state on
* encountering quotes.
! */
! public Node find(NodeReader reader,String input,int position, boolean balance_quotes)
! {
! StringBuffer textBuffer = new StringBuffer();
! int state = BEFORE_PARSE_BEGINS_STATE;
! int textBegin=position;
! int textEnd=position;
! int inputLen = input.length();
! char ch;
char ignore_ender = '\"';
! for (int i=position;(i<inputLen && state!=PARSE_COMPLETED_STATE);i++)
! {
! ch = input.charAt(i);
! if (ch=='<' && state!=PARSE_IGNORE_STATE)
{
if (beginTag (input, i))
***************
*** 92,142 ****
textEnd=i-1;
}
! }
! if (balance_quotes && (ch=='\'' || ch=='"'))
{
! if (state==PARSE_IGNORE_STATE)
{
if (ch == ignore_ender)
state=PARSE_HAS_BEGUN_STATE;
}
! else
{
ignore_ender = ch;
state = PARSE_IGNORE_STATE;
! }
! }
! if (state==BEFORE_PARSE_BEGINS_STATE)
! {
! state=PARSE_HAS_BEGUN_STATE;
! }
! if (state==PARSE_HAS_BEGUN_STATE || state==PARSE_IGNORE_STATE)
! {
! textBuffer.append(input.charAt(i));
! }
! // Patch by Cedric Rosa
! if (state==BEFORE_PARSE_BEGINS_STATE && i==inputLen-1)
! state=PARSE_HAS_BEGUN_STATE;
! if (state==PARSE_HAS_BEGUN_STATE && i==inputLen-1)
! {
! do {
! input = reader.getNextLine();
! if (input!=null && input.length()==0)
! textBuffer.append(Parser.getLineSeparator());
! }
! while (input!=null && input.length()==0);
!
! if (input==null) {
! textEnd=i;
! state =PARSE_COMPLETED_STATE;
!
! } else {
! textBuffer.append(Parser.getLineSeparator());
! inputLen = input.length();
! i=-1;
! }
! }
! }
! return reader.getParser().getStringNodeFactory().createStringNode(textBuffer, textBegin, textEnd);
! }
}
--- 92,142 ----
textEnd=i-1;
}
! }
! if (balance_quotes && (ch=='\'' || ch=='"'))
{
! if (state==PARSE_IGNORE_STATE)
{
if (ch == ignore_ender)
state=PARSE_HAS_BEGUN_STATE;
}
! else
{
ignore_ender = ch;
state = PARSE_IGNORE_STATE;
! }
! }
! if (state==BEFORE_PARSE_BEGINS_STATE)
! {
! state=PARSE_HAS_BEGUN_STATE;
! }
! if (state==PARSE_HAS_BEGUN_STATE || state==PARSE_IGNORE_STATE)
! {
! textBuffer.append(input.charAt(i));
! }
! // Patch by Cedric Rosa
! if (state==BEFORE_PARSE_BEGINS_STATE && i==inputLen-1)
! state=PARSE_HAS_BEGUN_STATE;
! if (state==PARSE_HAS_BEGUN_STATE && i==inputLen-1)
! {
! do {
! input = reader.getNextLine();
! if (input!=null && input.length()==0)
! textBuffer.append(Parser.getLineSeparator());
! }
! while (input!=null && input.length()==0);
!
! if (input==null) {
! textEnd=i;
! state =PARSE_COMPLETED_STATE;
!
! } else {
! textBuffer.append(Parser.getLineSeparator());
! inputLen = input.length();
! i=-1;
! }
! }
! }
! return reader.getParser().getStringNodeFactory().createStringNode(textBuffer, textBegin, textEnd);
! }
}
Index: TagParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/TagParser.java,v
retrieving revision 1.39
retrieving revision 1.40
diff -C2 -d -r1.39 -r1.40
*** TagParser.java 24 Aug 2003 21:59:42 -0000 1.39
--- TagParser.java 3 Sep 2003 23:36:19 -0000 1.40
***************
*** 38,244 ****
public class TagParser {
! public final static int TAG_BEFORE_PARSING_STATE=1;
! public final static int TAG_BEGIN_PARSING_STATE=1<<2;
! public final static int TAG_FINISHED_PARSING_STATE=1<<3;
! public final static int TAG_ILLEGAL_STATE=1<<4;
! public final static int TAG_IGNORE_DATA_STATE=1<<5;
! public final static int TAG_IGNORE_BEGIN_TAG_STATE=1<<6;
! public final static int TAG_IGNORE_CHAR_SINGLE_QUOTE=1<<7;
!
! public final static String ENCOUNTERED_QUERY_MESSAGE = "TagParser : Encountered > after a query. Accepting without correction and continuing parsing";
!
! private ParserFeedback feedback;
! public TagParser(ParserFeedback feedback) {
! this.feedback = feedback;
! }
! public Tag find(NodeReader reader,String input,int position) {
! int state = TAG_BEFORE_PARSING_STATE;
! int i=position;
! char ch;
! char[] ignorechar = new char[1]; // holds the character we're looking for when in TAG_IGNORE_DATA_STATE
! Tag tag = new Tag(new TagData(position, 0, reader.getLastLineNumber(), 0, "", input, "", false));
! Bool encounteredQuery = new Bool(false);
! while (i<tag.getTagLine().length() &&
! state!=TAG_FINISHED_PARSING_STATE &&
! state!=TAG_ILLEGAL_STATE
! )
! {
! ch = tag.getTagLine().charAt(i);
! state = automataInput(encounteredQuery, i, state, ch, tag, i, ignorechar);
! i = incrementCounter(i, reader, state, tag);
! }
! if (state==TAG_FINISHED_PARSING_STATE) {
! String tagLine = tag.getTagLine();
! if (i>1 && tagLine.charAt(i-2)=='/') {
! tag.setEmptyXmlTag(true);
! String tagContents = tag.getText();
! tag.setText(tagContents.substring(0,tagContents.length()-1));
! }
! return tag;
! } else
! return null;
! }
! private int automataInput(Bool encounteredQuery, int i, int state,char ch, Tag tag, int pos, char[] ignorechar) {
! state = checkIllegalState(i, state, ch, tag);
! state = checkFinishedState(encounteredQuery, i, state, ch, tag, pos);
! state = toggleIgnoringState(state, ch, ignorechar);
! if (state==TAG_BEFORE_PARSING_STATE && ch!='<') {
! state= TAG_ILLEGAL_STATE;
! }
! if (state==TAG_IGNORE_DATA_STATE && ch=='<') {
! // If the next tag char is is close tag, then
! // this is legal, we should continue
! if (!isWellFormedTag(tag,pos))
! state = TAG_IGNORE_BEGIN_TAG_STATE;
! }
! if (state==TAG_IGNORE_BEGIN_TAG_STATE && ch=='>') {
! state = TAG_IGNORE_DATA_STATE;
! }
! checkIfAppendable(encounteredQuery, state, ch, tag);
! state = checkBeginParsingState(i, state, ch, tag);
! return state;
! }
! private int checkBeginParsingState(int i, int state, char ch, Tag tag) {
! if (ch=='<' &&
! (state==TAG_BEFORE_PARSING_STATE ||
! state==TAG_ILLEGAL_STATE))
! {
! // Transition from State 0 to State 1 - Record data till > is encountered
! tag.setTagBegin(i);
! state = TAG_BEGIN_PARSING_STATE;
! }
! return state;
! }
! private boolean isWellFormedTag(Tag tag, int pos) {
! String inputLine = tag.getTagLine();
! int closeTagPos = inputLine.indexOf('>',pos+1);
! int openTagPos = inputLine.indexOf('<',pos+1);
! return openTagPos > closeTagPos || (openTagPos ==-1 && closeTagPos!=-1);
! }
!
! private int checkFinishedState(Bool encounteredQuery, int i, int state, char ch, Tag tag, int pos) {
! if (ch=='>')
! {
! if (state==TAG_BEGIN_PARSING_STATE)
! {
! state = TAG_FINISHED_PARSING_STATE;
! tag.setTagEnd(i);
! }
! else
! if (state==TAG_IGNORE_DATA_STATE) {
! if (encounteredQuery.getBoolean()) {
! encounteredQuery.setBoolean(false);
! feedback.info(ENCOUNTERED_QUERY_MESSAGE);
! return state;
! }
! // Now, either this is a valid > input, and should be ignored,
! // or it is a mistake in the html, in which case we need to correct it *sigh*
! if (isWellFormedTag(tag,pos)) return state;
!
! state = TAG_FINISHED_PARSING_STATE;
! tag.setTagEnd(i);
! // Do Correction
! // Correct the tag - assuming its grouped into name value pairs
! // Remove all inverted commas.
! correctTag(tag);
!
! StringBuffer msg = new StringBuffer();
! msg.append("HTMLTagParser : Encountered > inside inverted commas in line \n");
! msg.append(tag.getTagLine());
! msg.append(", location ");
! msg.append(i);
! msg.append("\n");
! for (int j=0;j<i;j++) msg.append(' ');
! msg.append('^');
! msg.append("\nAutomatically corrected.");
! feedback.warning(msg.toString());
! }
! } else
! if (ch=='<' &&
! state==TAG_BEGIN_PARSING_STATE &&
! tag.getText().charAt(0)!='%'
! ) {
! state = TAG_FINISHED_PARSING_STATE;
! tag.setTagEnd(i-1);i--;
! }
! return state;
! }
! private void checkIfAppendable(Bool encounteredQuery,int state, char ch, Tag tag) {
! if (state==TAG_IGNORE_DATA_STATE ||
! state==TAG_BEGIN_PARSING_STATE ||
! state==TAG_IGNORE_BEGIN_TAG_STATE) {
! if (ch=='?')
! encounteredQuery.setBoolean(true);
! tag.append(ch);
! }
! }
! private int checkIllegalState(int i, int state, char ch, Tag tag) {
! if (ch=='/' && i>0 && tag.getTagLine().charAt(i-1)=='<' &&
! state!=TAG_IGNORE_DATA_STATE &&
! state!=TAG_IGNORE_BEGIN_TAG_STATE)
! {
! state = TAG_ILLEGAL_STATE;
! }
! return state;
! }
!
! public void correctTag(Tag tag) {
! String tempText = tag.getText();
! StringBuffer absorbedText = new StringBuffer();
! char c;
! for (int j=0;j<tempText.length();j++) {
! c = tempText.charAt(j);
! if (c!='"')
! absorbedText.append(c);
! }
! // Go into the next stage.
! StringBuffer result = insertInvertedCommasCorrectly(absorbedText);
! tag.setText(result.toString());
! }
! public StringBuffer insertInvertedCommasCorrectly(StringBuffer absorbedText) {
! StringBuffer result = new StringBuffer();
! StringTokenizer tok = new StringTokenizer(absorbedText.toString(),"=",false);
! String token;
! token= (String)tok.nextToken();
! result.append(token+"=");
! for (;tok.hasMoreTokens();) {
! token= (String)tok.nextToken();
! token = pruneSpaces(token);
! result.append('"');
! int lastIndex = token.lastIndexOf(' ');
! if (lastIndex!=-1 && tok.hasMoreTokens()) {
! result.append(token.substring(0,lastIndex));
! result.append('"');
! result.append(token.substring(lastIndex,token.length()));
! } else result.append(token+'"');
! if (tok.hasMoreTokens()) result.append("=");
! }
! return result;
! }
! public static String pruneSpaces(String token) {
! int firstSpace;
! int lastSpace;
! firstSpace = token.indexOf(' ');
! while (firstSpace==0) {
! token = token.substring(1,token.length());
! firstSpace = token.indexOf(' ');
! }
! lastSpace = token.lastIndexOf(' ');
! while (lastSpace==token.length()-1) {
! token = token.substring(0,token.length()-1);
! lastSpace = token.lastIndexOf(' ');
! }
! return token;
! }
/**
--- 38,244 ----
public class TagParser {
! public final static int TAG_BEFORE_PARSING_STATE=1;
! public final static int TAG_BEGIN_PARSING_STATE=1<<2;
! public final static int TAG_FINISHED_PARSING_STATE=1<<3;
! public final static int TAG_ILLEGAL_STATE=1<<4;
! public final static int TAG_IGNORE_DATA_STATE=1<<5;
! public final static int TAG_IGNORE_BEGIN_TAG_STATE=1<<6;
! public final static int TAG_IGNORE_CHAR_SINGLE_QUOTE=1<<7;
!
! public final static String ENCOUNTERED_QUERY_MESSAGE = "TagParser : Encountered > after a query. Accepting without correction and continuing parsing";
!
! private ParserFeedback feedback;
! public TagParser(ParserFeedback feedback) {
! this.feedback = feedback;
! }
! public Tag find(NodeReader reader,String input,int position) {
! int state = TAG_BEFORE_PARSING_STATE;
! int i=position;
! char ch;
! char[] ignorechar = new char[1]; // holds the character we're looking for when in TAG_IGNORE_DATA_STATE
! Tag tag = new Tag(new TagData(position, 0, reader.getLastLineNumber(), 0, "", input, "", false));
! Bool encounteredQuery = new Bool(false);
! while (i<tag.getTagLine().length() &&
! state!=TAG_FINISHED_PARSING_STATE &&
! state!=TAG_ILLEGAL_STATE
! )
! {
! ch = tag.getTagLine().charAt(i);
! state = automataInput(encounteredQuery, i, state, ch, tag, i, ignorechar);
! i = incrementCounter(i, reader, state, tag);
! }
! if (state==TAG_FINISHED_PARSING_STATE) {
! String tagLine = tag.getTagLine();
! if (i>1 && tagLine.charAt(i-2)=='/') {
! tag.setEmptyXmlTag(true);
! String tagContents = tag.getText();
! tag.setText(tagContents.substring(0,tagContents.length()-1));
! }
! return tag;
! } else
! return null;
! }
! private int automataInput(Bool encounteredQuery, int i, int state,char ch, Tag tag, int pos, char[] ignorechar) {
! state = checkIllegalState(i, state, ch, tag);
! state = checkFinishedState(encounteredQuery, i, state, ch, tag, pos);
! state = toggleIgnoringState(state, ch, ignorechar);
! if (state==TAG_BEFORE_PARSING_STATE && ch!='<') {
! state= TAG_ILLEGAL_STATE;
! }
! if (state==TAG_IGNORE_DATA_STATE && ch=='<') {
! // If the next tag char is is close tag, then
! // this is legal, we should continue
! if (!isWellFormedTag(tag,pos))
! state = TAG_IGNORE_BEGIN_TAG_STATE;
! }
! if (state==TAG_IGNORE_BEGIN_TAG_STATE && ch=='>') {
! state = TAG_IGNORE_DATA_STATE;
! }
! checkIfAppendable(encounteredQuery, state, ch, tag);
! state = checkBeginParsingState(i, state, ch, tag);
! return state;
! }
! private int checkBeginParsingState(int i, int state, char ch, Tag tag) {
! if (ch=='<' &&
! (state==TAG_BEFORE_PARSING_STATE ||
! state==TAG_ILLEGAL_STATE))
! {
! // Transition from State 0 to State 1 - Record data till > i...
[truncated message content] |
×
Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.
Thanks for helping keep SourceForge clean.
X