m_elemStack = new Stack<>();
-
- /** Element recorded with this namespace will be converted to Node without a namespace */
- private String defaultNamespaceURI = null;
-
- /**
- * DOMBuilder instance constructor... it will add the DOM nodes to the document fragment.
- *
- * @param doc Root document
- * @param node Current node
- */
- public DOMBuilder(Document doc, Node node) {
- m_doc = doc;
- m_currentNode = node;
- }
-
- /**
- * DOMBuilder instance constructor... it will add the DOM nodes to the document fragment.
- *
- * @param doc Root document
- * @param docFrag Document fragment
- */
- DOMBuilder(Document doc, DocumentFragment docFrag) {
- m_doc = doc;
- m_docFrag = docFrag;
- }
-
- /**
- * DOMBuilder instance constructor... it will add the DOM nodes to the document.
- *
- * @param doc Root document
- */
- DOMBuilder(Document doc) {
- m_doc = doc;
- }
-
- /**
- * Get the root node of the DOM being created. This is either a Document or a DocumentFragment.
- *
- * @return The root document or document fragment if not null
- */
- Node getRootNode() {
- return (null != m_docFrag) ? (Node) m_docFrag : (Node) m_doc;
- }
-
- /**
- * Get the node currently being processed.
- *
- * @return the current node being processed
- */
- Node getCurrentNode() {
- return m_currentNode;
- }
-
- /**
- * Return null since there is no Writer for this class.
- *
- * @return null
- */
- java.io.Writer getWriter() {
- return null;
- }
-
- /**
- * Append a node to the current container.
- *
- * @param newNode New node to append
- */
- protected void append(Node newNode) throws org.xml.sax.SAXException {
-
- Node currentNode = m_currentNode;
-
- if (null != currentNode) {
- currentNode.appendChild(newNode);
-
- // System.out.println(newNode.getNodeName());
- } else if (null != m_docFrag) {
- m_docFrag.appendChild(newNode);
- } else {
- boolean ok = true;
- short type = newNode.getNodeType();
-
- if (type == Node.TEXT_NODE) {
- String data = newNode.getNodeValue();
-
- if ((null != data) && (data.trim().length() > 0)) {
- throw new org.xml.sax.SAXException(
- "Warning: can't output text before document element! Ignoring...");
- }
-
- ok = false;
- } else if (type == Node.ELEMENT_NODE) {
- if (m_doc.getDocumentElement() != null) {
- throw new org.xml.sax.SAXException("Can't have more than one root on a DOM!");
- }
- }
-
- if (ok) {
- m_doc.appendChild(newNode);
- }
- }
- }
-
- /**
- * Receive an object for locating the origin of SAX document events.
- *
- * SAX parsers are strongly encouraged (though not absolutely required) to supply a locator:
- * if it does so, it must supply the locator to the application by invoking this method before
- * invoking any of the other methods in the ContentHandler interface.
- *
- *
The locator allows the application to determine the end position of any document-related
- * event, even if the parser is not reporting an error. Typically, the application will use this
- * information for reporting its own errors (such as character content that does not match an
- * application's business rules). The information returned by the locator is probably not
- * sufficient for use with a search engine.
- *
- *
Note that the locator will return correct information only during the invocation of the
- * events in this interface. The application should not attempt to use it at any other time.
- *
- * @param locator An object that can return the location of any SAX document event.
- * @see org.xml.sax.Locator
- */
- @Override
- public void setDocumentLocator(Locator locator) {
-
- // No action for the moment.
- }
-
- /**
- * Receive notification of the beginning of a document.
- *
- *
The SAX parser will invoke this method only once, before any other methods in this
- * interface or in DTDHandler (except for setDocumentLocator).
- */
- @Override
- public void startDocument() throws org.xml.sax.SAXException {
-
- // No action for the moment.
- }
-
- /**
- * Receive notification of the end of a document.
- *
- *
The SAX parser will invoke this method only once, and it will be the last method invoked
- * during the parse. The parser shall not invoke this method until it has either abandoned
- * parsing (because of an unrecoverable error) or reached the end of input.
- */
- @Override
- public void endDocument() throws org.xml.sax.SAXException {
-
- // No action for the moment.
- }
-
- /**
- * Receive notification of the beginning of an element.
- *
- *
The Parser will invoke this method at the beginning of every element in the XML document;
- * there will be a corresponding endElement() event for every startElement() event (even when
- * the element is empty). All of the element's content will be reported, in order, before the
- * corresponding endElement() event.
- *
- *
If the element name has a namespace prefix, the prefix will still be attached. Note that
- * the attribute list provided will contain only attributes with explicit values (specified or
- * defaulted): #IMPLIED attributes will be omitted.
- *
- * @param ns The namespace of the node
- * @param localName The local part of the qualified name
- * @param name The element name.
- * @param atts The attributes attached to the element, if any.
- * @see #endElement
- * @see org.xml.sax.Attributes
- */
- @Override
- public void startElement(String ns, String localName, String name, Attributes atts)
- throws org.xml.sax.SAXException {
-
- Element elem;
-
- if (upperCaseElementNames) {
- name = name.toUpperCase(Locale.ROOT);
- }
-
- // Note that the namespace-aware call must be used to correctly
- // construct a Level 2 DOM, even for non-namespaced nodes.
- if ((null == ns) || (ns.length() == 0) || ns.equals(defaultNamespaceURI)) {
- elem = m_doc.createElementNS(null, name);
- } else {
- elem = m_doc.createElementNS(ns, name);
- }
-
- append(elem);
-
- try {
- int nAtts = atts.getLength();
-
- if (0 != nAtts) {
- for (int i = 0; i < nAtts; i++) {
- // First handle a possible ID attribute
- if (atts.getType(i).equalsIgnoreCase("ID")) {
- setIDAttribute(atts.getValue(i), elem);
- }
-
- String attrNS = atts.getURI(i);
-
- if ("".equals(attrNS)) {
- attrNS = null; // DOM represents no-namespace as null
- }
-
- // System.out.println("attrNS: "+attrNS+", localName: "+atts.getQName(i)
- // +", qname: "+atts.getQName(i)+", value: "+atts.getValue(i));
- // Crimson won't let us set an xmlns: attribute on the DOM.
- String attrQName = atts.getQName(i);
-
- // In SAX, xmlns: attributes have an empty namespace, while
- // in DOM they should have the xmlns namespace
- if (attrQName.startsWith("xmlns:")) {
- attrNS = "http://www.w3.org/2000/xmlns/";
- }
-
- // ALWAYS use the DOM Level 2 call!
- elem.setAttributeNS(attrNS, attrQName, atts.getValue(i));
- }
- }
-
- // append(elem);
-
- m_elemStack.push(elem);
-
- m_currentNode = elem;
-
- // append(elem);
- } catch (java.lang.Exception de) {
- // de.printStackTrace();
- throw new org.xml.sax.SAXException(de);
- }
- }
-
- /**
- * Receive notification of the end of an element.
- *
- *
The SAX parser will invoke this method at the end of every element in the XML document;
- * there will be a corresponding startElement() event for every endElement() event (even when
- * the element is empty).
- *
- *
If the element name has a namespace prefix, the prefix will still be attached to the name.
- *
- * @param ns the namespace of the element
- * @param localName The local part of the qualified name of the element
- * @param name The element name
- */
- @Override
- public void endElement(String ns, String localName, String name)
- throws org.xml.sax.SAXException {
- m_elemStack.pop();
- m_currentNode = m_elemStack.isEmpty() ? null : (Node) m_elemStack.peek();
- }
-
- /**
- * Set an ID string to node association in the ID table.
- *
- * @param id The ID string.
- * @param elem The associated ID.
- */
- public void setIDAttribute(String id, Element elem) {
-
- // Do nothing. This method is meant to be overridden.
- }
-
- /**
- * Receive notification of character data.
- *
- *
The Parser will call this method to report each chunk of character data. SAX parsers may
- * return all contiguous character data in a single chunk, or they may split it into several
- * chunks; however, all of the characters in any single event must come from the same external
- * entity, so that the Locator provides useful information.
- *
- *
The application must not attempt to read from the array outside of the specified range.
- *
- *
Note that some parsers will report whitespace using the ignorableWhitespace() method
- * rather than this one (validating parsers must do so).
- *
- * @param ch The characters from the XML document.
- * @param start The start position in the array.
- * @param length The number of characters to read from the array.
- * @see #ignorableWhitespace
- * @see org.xml.sax.Locator
- */
- @Override
- public void characters(char[] ch, int start, int length) throws org.xml.sax.SAXException {
- if (isOutsideDocElem() && XMLCharacterRecognizer.isWhiteSpace(ch, start, length)) {
- return; // avoid DOM006 Hierarchy request error
- }
-
- if (m_inCData) {
- cdata(ch, start, length);
-
- return;
- }
-
- String s = new String(ch, start, length);
- Node childNode;
- childNode = m_currentNode != null ? m_currentNode.getLastChild() : null;
- if (childNode != null && childNode.getNodeType() == Node.TEXT_NODE) {
- ((Text) childNode).appendData(s);
- } else {
- Text text = m_doc.createTextNode(s);
- append(text);
- }
- }
-
- /**
- * If available, when the disable-output-escaping attribute is used, output raw text without
- * escaping. A PI will be inserted in front of the node with the name "lotusxsl-next-is-raw" and
- * a value of "formatter-to-dom".
- *
- * @param ch Array containing the characters
- * @param start Index to start of characters in the array
- * @param length Number of characters in the array
- */
- public void charactersRaw(char[] ch, int start, int length) throws org.xml.sax.SAXException {
- if (isOutsideDocElem() && XMLCharacterRecognizer.isWhiteSpace(ch, start, length)) {
- return; // avoid DOM006 Hierarchy request error
- }
-
- String s = new String(ch, start, length);
-
- append(m_doc.createProcessingInstruction("xslt-next-is-raw", "formatter-to-dom"));
- append(m_doc.createTextNode(s));
- }
-
- /**
- * Report the beginning of an entity.
- *
- *
The start and end of the document entity are not reported. The start and end of the
- * external DTD subset are reported using the pseudo-name "[dtd]". All other events must be
- * properly nested within start/end entity events.
- *
- * @param name The name of the entity. If it is a parameter entity, the name will begin with
- * '%'.
- * @see #endEntity
- * @see org.xml.sax.ext.DeclHandler#internalEntityDecl
- * @see org.xml.sax.ext.DeclHandler#externalEntityDecl
- */
- @Override
- public void startEntity(String name) throws org.xml.sax.SAXException {
-
- // Almost certainly the wrong behavior...
- // entityReference(name);
- }
-
- /**
- * Report the end of an entity.
- *
- * @param name The name of the entity that is ending.
- * @see #startEntity
- */
- @Override
- public void endEntity(String name) throws org.xml.sax.SAXException {}
-
- /**
- * Receive notivication of a entityReference.
- *
- * @param name name of the entity reference
- */
- public void entityReference(String name) throws org.xml.sax.SAXException {
- append(m_doc.createEntityReference(name));
- }
-
- /**
- * Receive notification of ignorable whitespace in element content.
- *
- *
Validating Parsers must use this method to report each chunk of ignorable whitespace (see
- * the W3C XML 1.0 recommendation, section 2.10): non-validating parsers may also use this
- * method if they are capable of parsing and using content models.
- *
- *
SAX parsers may return all contiguous whitespace in a single chunk, or they may split it
- * into several chunks; however, all of the characters in any single event must come from the
- * same external entity, so that the Locator provides useful information.
- *
- *
The application must not attempt to read from the array outside of the specified range.
- *
- * @param ch The characters from the XML document.
- * @param start The start position in the array.
- * @param length The number of characters to read from the array.
- * @see #characters
- */
- @Override
- public void ignorableWhitespace(char[] ch, int start, int length)
- throws org.xml.sax.SAXException {
- if (isOutsideDocElem()) {
- return; // avoid DOM006 Hierarchy request error
- }
-
- String s = new String(ch, start, length);
-
- append(m_doc.createTextNode(s));
- }
-
- /**
- * Tell if the current node is outside the document element.
- *
- * @return true if the current node is outside the document element.
- */
- private boolean isOutsideDocElem() {
- return (null == m_docFrag)
- && m_elemStack.size() == 0
- && (null == m_currentNode || m_currentNode.getNodeType() == Node.DOCUMENT_NODE);
- }
-
- /**
- * Receive notification of a processing instruction.
- *
- *
The Parser will invoke this method once for each processing instruction found: note that
- * processing instructions may occur before or after the main document element.
- *
- *
A SAX parser should never report an XML declaration (XML 1.0, section 2.8) or a text
- * declaration (XML 1.0, section 4.3.1) using this method.
- *
- * @param target The processing instruction target.
- * @param data The processing instruction data, or null if none was supplied.
- */
- @Override
- public void processingInstruction(String target, String data) throws org.xml.sax.SAXException {
- append(m_doc.createProcessingInstruction(target, data));
- }
-
- /**
- * Report an XML comment anywhere in the document.
- *
- *
This callback will be used for comments inside or outside the document element, including
- * comments in the external DTD subset (if read).
- *
- * @param ch An array holding the characters in the comment.
- * @param start The starting position in the array.
- * @param length The number of characters to use from the array.
- */
- @Override
- public void comment(char[] ch, int start, int length) throws org.xml.sax.SAXException {
- // tagsoup sometimes submits invalid values here
- if (ch == null || start < 0 || length >= (ch.length - start) || length < 0) {
- return;
- }
- append(m_doc.createComment(new String(ch, start, length)));
- }
-
- /** Flag indicating that we are processing a CData section */
- protected boolean m_inCData = false;
-
- /**
- * Report the start of a CDATA section.
- *
- * @see #endCDATA
- */
- @Override
- public void startCDATA() throws org.xml.sax.SAXException {
- m_inCData = true;
- append(m_doc.createCDATASection(""));
- }
-
- /**
- * Report the end of a CDATA section.
- *
- * @see #startCDATA
- */
- @Override
- public void endCDATA() throws org.xml.sax.SAXException {
- m_inCData = false;
- }
-
- /**
- * Receive notification of cdata.
- *
- *
The Parser will call this method to report each chunk of character data. SAX parsers may
- * return all contiguous character data in a single chunk, or they may split it into several
- * chunks; however, all of the characters in any single event must come from the same external
- * entity, so that the Locator provides useful information.
- *
- *
The application must not attempt to read from the array outside of the specified range.
- *
- *
Note that some parsers will report whitespace using the ignorableWhitespace() method
- * rather than this one (validating parsers must do so).
- *
- * @param ch The characters from the XML document.
- * @param start The start position in the array.
- * @param length The number of characters to read from the array.
- * @see #ignorableWhitespace
- * @see org.xml.sax.Locator
- */
- public void cdata(char[] ch, int start, int length) {
- if (isOutsideDocElem() && XMLCharacterRecognizer.isWhiteSpace(ch, start, length)) {
- return; // avoid DOM006 Hierarchy request error
- }
-
- String s = new String(ch, start, length);
-
- // XXX ab@apache.org: modified from the original, to accommodate TagSoup.
- Node n = m_currentNode.getLastChild();
- if (n instanceof CDATASection) {
- ((CDATASection) n).appendData(s);
- } else if (n instanceof Comment) {
- ((Comment) n).appendData(s);
- }
- }
-
- /**
- * Report the start of DTD declarations, if any.
- *
- *
Any declarations are assumed to be in the internal subset unless otherwise indicated.
- *
- * @param name The document type name.
- * @param publicId The declared public identifier for the external DTD subset, or null if none
- * was declared.
- * @param systemId The declared system identifier for the external DTD subset, or null if none
- * was declared.
- * @see #endDTD
- * @see #startEntity
- */
- @Override
- public void startDTD(String name, String publicId, String systemId)
- throws org.xml.sax.SAXException {
-
- // Do nothing for now.
- }
-
- /**
- * Report the end of DTD declarations.
- *
- * @see #startDTD
- */
- @Override
- public void endDTD() throws org.xml.sax.SAXException {
-
- // Do nothing for now.
- }
-
- /**
- * Begin the scope of a prefix-URI Namespace mapping.
- *
- *
The information from this event is not necessary for normal Namespace processing: the SAX
- * XML reader will automatically replace prefixes for element and attribute names when the
- * http://xml.org/sax/features/namespaces feature is true (the default).
- *
- *
There are cases, however, when applications need to use prefixes in character data or in
- * attribute values, where they cannot safely be expanded automatically; the
- * start/endPrefixMapping event supplies the information to the application to expand prefixes
- * in those contexts itself, if necessary.
- *
- *
Note that start/endPrefixMapping events are not guaranteed to be properly nested relative
- * to each-other: all startPrefixMapping events will occur before the corresponding startElement
- * event, and all endPrefixMapping events will occur after the corresponding endElement event,
- * but their order is not guaranteed.
- *
- * @param prefix The Namespace prefix being declared.
- * @param uri The Namespace URI the prefix is mapped to.
- * @see #endPrefixMapping
- * @see #startElement
- */
- @Override
- public void startPrefixMapping(String prefix, String uri) throws org.xml.sax.SAXException {
-
- /*
- * // Not sure if this is needed or wanted // Also, it fails in the
- * stree. if((null != m_currentNode) && (m_currentNode.getNodeType() ==
- * Node.ELEMENT_NODE)) { String qname; if(((null != prefix) &&
- * (prefix.length() == 0)) || (null == prefix)) qname = "xmlns"; else
- * qname = "xmlns:"+prefix;
- *
- * Element elem = (Element)m_currentNode; String val =
- * elem.getAttribute(qname); // Obsolete, should be DOM2...? if(val ==
- * null) { elem.setAttributeNS("http://www.w3.org/XML/1998/namespace",
- * qname, uri); } }
- */
- }
-
- /**
- * End the scope of a prefix-URI mapping.
- *
- *
See startPrefixMapping for details. This event will always occur after the corresponding
- * endElement event, but the order of endPrefixMapping events is not otherwise guaranteed.
- *
- * @param prefix The prefix that was being mapping.
- * @see #startPrefixMapping
- * @see #endElement
- */
- @Override
- public void endPrefixMapping(String prefix) throws org.xml.sax.SAXException {}
-
- /**
- * Receive notification of a skipped entity.
- *
- *
The Parser will invoke this method once for each entity skipped. Non-validating processors
- * may skip entities if they have not seen the declarations (because, for example, the entity
- * was declared in an external DTD subset). All processors may skip external entities, depending
- * on the values of the http://xml.org/sax/features/external-general-entities and the
- * http://xml.org/sax/features/external-parameter-entities properties.
- *
- * @param name The name of the skipped entity. If it is a parameter entity, the name will begin
- * with '%'.
- */
- @Override
- public void skippedEntity(String name) throws org.xml.sax.SAXException {}
-
- public boolean isUpperCaseElementNames() {
- return upperCaseElementNames;
- }
-
- public void setUpperCaseElementNames(boolean upperCaseElementNames) {
- this.upperCaseElementNames = upperCaseElementNames;
- }
-
- public String getDefaultNamespaceURI() {
- return defaultNamespaceURI;
- }
-
- public void setDefaultNamespaceURI(String defaultNamespaceURI) {
- this.defaultNamespaceURI = defaultNamespaceURI;
- }
-}
diff --git a/external/tika/src/main/java/org/apache/stormcrawler/tika/ParserBolt.java b/external/tika/src/main/java/org/apache/stormcrawler/tika/ParserBolt.java
index be57f7b36..cbf19714a 100644
--- a/external/tika/src/main/java/org/apache/stormcrawler/tika/ParserBolt.java
+++ b/external/tika/src/main/java/org/apache/stormcrawler/tika/ParserBolt.java
@@ -44,7 +44,6 @@
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParserFactory;
import org.apache.commons.lang3.StringUtils;
-import org.apache.html.dom.HTMLDocumentImpl;
import org.apache.http.HttpHeaders;
import org.apache.storm.task.OutputCollector;
import org.apache.storm.task.TopologyContext;
@@ -97,11 +96,9 @@
import org.apache.tika.sax.Link;
import org.apache.tika.sax.LinkContentHandler;
import org.apache.tika.sax.TeeContentHandler;
-import org.apache.tika.sax.XHTMLContentHandler;
import org.apache.tika.serialization.ComponentNameResolver;
import org.jetbrains.annotations.NotNull;
import org.slf4j.LoggerFactory;
-import org.w3c.dom.DocumentFragment;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
@@ -201,7 +198,6 @@ private static SAXParserFactory newHardenedSaxParserFactory() {
private ScopedCounter eventCounter;
- private boolean upperCaseElementNames = true;
private Class htmlMapperClass = IdentityHtmlMapper.class;
private boolean extractEmbedded = false;
@@ -253,8 +249,6 @@ public void prepare(
jsoupFilters = JSoupFilters.fromConf(conf);
- upperCaseElementNames = ConfUtils.getBoolean(conf, "parser.uppercase.element.names", true);
-
extractEmbedded = ConfUtils.getBoolean(conf, "parser.extract.embedded", false);
String htmlmapperClassName =
@@ -429,18 +423,6 @@ public void execute(Tuple tuple) {
LOG.error("Exception while specifying HTMLMapper {}", url, e);
}
- // build a DOM if required by the parseFilters
- DocumentFragment root = null;
- if (parseFilters.needsDOM()) {
- HTMLDocumentImpl doc = new HTMLDocumentImpl();
- doc.setErrorChecking(false);
- root = doc.createDocumentFragment();
- DOMBuilder domhandler = new DOMBuilder(doc, root);
- domhandler.setUpperCaseElementNames(upperCaseElementNames);
- domhandler.setDefaultNamespaceURI(XHTMLContentHandler.XHTML);
- handlers.add(domhandler);
- }
-
// build a JSoup document if there are JSoupFilters
JSoupBuilder jsoupBuilder = null;
if (!jsoupFilters.isEmpty()) {
@@ -527,7 +509,7 @@ public void execute(Tuple tuple) {
// apply the parse filters if any
try {
- parseFilters.filter(url, content, root, parse);
+ parseFilters.filter(url, content, parse);
} catch (RuntimeException e) {
handleException(url, e, metadata, tuple, "parse filters");
return;
diff --git a/external/tika/src/main/java/org/apache/stormcrawler/tika/XMLCharacterRecognizer.java b/external/tika/src/main/java/org/apache/stormcrawler/tika/XMLCharacterRecognizer.java
deleted file mode 100644
index da079010c..000000000
--- a/external/tika/src/main/java/org/apache/stormcrawler/tika/XMLCharacterRecognizer.java
+++ /dev/null
@@ -1,107 +0,0 @@
-/*
- * 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.
- */
-
-/*
- * XXX NUTCH COMMENT
- * XXX ab@apache.org: This class is copied verbatim from Xalan-J 2.6.0
- * XXX distribution, org.apache.xml.utils.DOMBuilder, in order to
- * avoid dependency on Xalan.
- */
-
-package org.apache.stormcrawler.tika;
-
-/**
- * Class used to verify whether the specified ch conforms to the XML 1.0 definition of
- * whitespace.
- */
-class XMLCharacterRecognizer {
-
- private XMLCharacterRecognizer() {}
-
- /**
- * Returns whether the specified ch conforms to the XML 1.0 definition of whitespace.
- * Refer to the definition of S
- * for details.
- *
- * @param ch Character to check as XML whitespace.
- * @return =true if ch is XML whitespace; otherwise =false.
- */
- static boolean isWhiteSpace(char ch) {
- return (ch == 0x20) || (ch == 0x09) || (ch == 0xD) || (ch == 0xA);
- }
-
- /**
- * Tell if the string is whitespace.
- *
- * @param ch Character array to check as XML whitespace.
- * @param start Start index of characters in the array
- * @param length Number of characters in the array
- * @return True if the characters in the array are XML whitespace; otherwise, false.
- */
- static boolean isWhiteSpace(char[] ch, int start, int length) {
-
- int end = start + length;
-
- for (int s = start; s < end; s++) {
- if (!isWhiteSpace(ch[s])) {
- return false;
- }
- }
-
- return true;
- }
-
- /**
- * Tell if the string is whitespace.
- *
- * @param buf StringBuffer to check as XML whitespace.
- * @return True if characters in buffer are XML whitespace, false otherwise
- */
- static boolean isWhiteSpace(StringBuffer buf) {
-
- int n = buf.length();
-
- for (int i = 0; i < n; i++) {
- if (!isWhiteSpace(buf.charAt(i))) {
- return false;
- }
- }
-
- return true;
- }
-
- /**
- * Tell if the string is whitespace.
- *
- * @param s String to check as XML whitespace.
- * @return True if characters in buffer are XML whitespace, false otherwise
- */
- static boolean isWhiteSpace(String s) {
-
- if (null != s) {
- int n = s.length();
-
- for (int i = 0; i < n; i++) {
- if (!isWhiteSpace(s.charAt(i))) {
- return false;
- }
- }
- }
-
- return true;
- }
-}