com.greenpepper.shaded.org.jsoup.nodes.Element Maven / Gradle / Ivy
package com.greenpepper.shaded.org.jsoup.nodes;
import com.greenpepper.shaded.org.jsoup.helper.StringUtil;
import com.greenpepper.shaded.org.jsoup.helper.Validate;
import com.greenpepper.shaded.org.jsoup.parser.Parser;
import com.greenpepper.shaded.org.jsoup.parser.Tag;
import com.greenpepper.shaded.org.jsoup.select.*;
import java.util.*;
import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;
/**
* A HTML element consists of a tag name, attributes, and child nodes (including text nodes and
* other elements).
*
* From an Element, you can extract data, traverse the node graph, and manipulate the HTML.
*
* @author Jonathan Hedley, [email protected]
*/
public class Element extends Node {
private Tag tag;
private static final Pattern classSplit = Pattern.compile("\\s+");
/**
* Create a new, standalone Element. (Standalone in that is has no parent.)
*
* @param tag tag of this element
* @param baseUri the base URI
* @param attributes initial attributes
* @see #appendChild(Node)
* @see #appendElement(String)
*/
public Element(Tag tag, String baseUri, Attributes attributes) {
super(baseUri, attributes);
Validate.notNull(tag);
this.tag = tag;
}
/**
* Create a new Element from a tag and a base URI.
*
* @param tag element tag
* @param baseUri the base URI of this element. It is acceptable for the base URI to be an empty
* string, but not null.
* @see Tag#valueOf(String)
*/
public Element(Tag tag, String baseUri) {
this(tag, baseUri, new Attributes());
}
@Override
public String nodeName() {
return tag.getName();
}
/**
* Get the name of the tag for this element. E.g. {@code div}
*
* @return the tag name
*/
public String tagName() {
return tag.getName();
}
/**
* Change the tag of this element. For example, convert a {@code } to a {@code } with
* {@code el.tagName("div");}.
*
* @param tagName new tag name for this element
* @return this element, for chaining
*/
public Element tagName(String tagName) {
Validate.notEmpty(tagName, "Tag name must not be empty.");
tag = Tag.valueOf(tagName);
return this;
}
/**
* Get the Tag for this element.
*
* @return the tag object
*/
public Tag tag() {
return tag;
}
/**
* Test if this element is a block-level element. (E.g. {@code == true} or an inline element
* {@code == false}).
*
* @return true if block, false if not (and thus inline)
*/
public boolean isBlock() {
return tag.isBlock();
}
/**
* Get the {@code id} attribute of this element.
*
* @return The id attribute, if present, or an empty string if not.
*/
public String id() {
return attributes.get("id");
}
/**
* Set an attribute value on this element. If this element already has an attribute with the
* key, its value is updated; otherwise, a new attribute is added.
*
* @return this element
*/
public Element attr(String attributeKey, String attributeValue) {
super.attr(attributeKey, attributeValue);
return this;
}
/**
* Set a boolean attribute value on this element. Setting to true sets the attribute value to "" and
* marks the attribute as boolean so no value is written out. Setting to false removes the attribute
* with the same key if it exists.
*
* @param attributeKey the attribute key
* @param attributeValue the attribute value
*
* @return this element
*/
public Element attr(String attributeKey, boolean attributeValue) {
attributes.put(attributeKey, attributeValue);
return this;
}
/**
* Get this element's HTML5 custom data attributes. Each attribute in the element that has a key
* starting with "data-" is included the dataset.
*
* E.g., the element {@code
...} has the dataset
* {@code package=jsoup, language=java}.
*
* This map is a filtered view of the element's attribute map. Changes to one map (add, remove, update) are reflected
* in the other map.
*
* You can find elements that have data attributes using the {@code [^data-]} attribute key prefix selector.
* @return a map of {@code key=value} custom data attributes.
*/
public Map dataset() {
return attributes.dataset();
}
@Override
public final Element parent() {
return (Element) parentNode;
}
/**
* Get this element's parent and ancestors, up to the document root.
* @return this element's stack of parents, closest first.
*/
public Elements parents() {
Elements parents = new Elements();
accumulateParents(this, parents);
return parents;
}
private static void accumulateParents(Element el, Elements parents) {
Element parent = el.parent();
if (parent != null && !parent.tagName().equals("#root")) {
parents.add(parent);
accumulateParents(parent, parents);
}
}
/**
* Get a child element of this element, by its 0-based index number.
*
* Note that an element can have both mixed Nodes and Elements as children. This method inspects
* a filtered list of children that are elements, and the index is based on that filtered list.
*
*
* @param index the index number of the element to retrieve
* @return the child element, if it exists, otherwise throws an {@code IndexOutOfBoundsException}
* @see #childNode(int)
*/
public Element child(int index) {
return children().get(index);
}
/**
* Get this element's child elements.
*
* This is effectively a filter on {@link #childNodes()} to get Element nodes.
*
* @return child elements. If this element has no children, returns an
* empty list.
* @see #childNodes()
*/
public Elements children() {
// create on the fly rather than maintaining two lists. if gets slow, memoize, and mark dirty on change
List elements = new ArrayList(childNodes.size());
for (Node node : childNodes) {
if (node instanceof Element)
elements.add((Element) node);
}
return new Elements(elements);
}
/**
* Get this element's child text nodes. The list is unmodifiable but the text nodes may be manipulated.
*
* This is effectively a filter on {@link #childNodes()} to get Text nodes.
* @return child text nodes. If this element has no text nodes, returns an
* empty list.
*
* For example, with the input HTML: {@code One Two Three
Four
} with the {@code p} element selected:
*
* - {@code p.text()} = {@code "One Two Three Four"}
* - {@code p.ownText()} = {@code "One Three Four"}
* - {@code p.children()} = {@code Elements[,
]}
* - {@code p.childNodes()} = {@code List
["One ", , " Three ",
, " Four"]}
* - {@code p.textNodes()} = {@code List
["One ", " Three ", " Four"]}
*
*/
public List textNodes() {
List textNodes = new ArrayList();
for (Node node : childNodes) {
if (node instanceof TextNode)
textNodes.add((TextNode) node);
}
return Collections.unmodifiableList(textNodes);
}
/**
* Get this element's child data nodes. The list is unmodifiable but the data nodes may be manipulated.
*
* This is effectively a filter on {@link #childNodes()} to get Data nodes.
*
* @return child data nodes. If this element has no data nodes, returns an
* empty list.
* @see #data()
*/
public List dataNodes() {
List dataNodes = new ArrayList();
for (Node node : childNodes) {
if (node instanceof DataNode)
dataNodes.add((DataNode) node);
}
return Collections.unmodifiableList(dataNodes);
}
/**
* Find elements that match the {@link Selector} CSS query, with this element as the starting context. Matched elements
* may include this element, or any of its children.
*
* This method is generally more powerful to use than the DOM-type {@code getElementBy*} methods, because
* multiple filters can be combined, e.g.:
*
*
* - {@code el.select("a[href]")} - finds links ({@code a} tags with {@code href} attributes)
*
- {@code el.select("a[href*=example.com]")} - finds links pointing to example.com (loosely)
*
*
* See the query syntax documentation in {@link com.greenpepper.shaded.org.jsoup.select.Selector}.
*
*
* @param cssQuery a {@link Selector} CSS-like query
* @return elements that match the query (empty if none match)
* @see com.greenpepper.shaded.org.jsoup.select.Selector
* @throws Selector.SelectorParseException (unchecked) on an invalid CSS query.
*/
public Elements select(String cssQuery) {
return Selector.select(cssQuery, this);
}
/**
* Add a node child node to this element.
*
* @param child node to add.
* @return this element, so that you can add more child nodes or elements.
*/
public Element appendChild(Node child) {
Validate.notNull(child);
// was - Node#addChildren(child). short-circuits an array create and a loop.
reparentChild(child);
ensureChildNodes();
childNodes.add(child);
child.setSiblingIndex(childNodes.size() - 1);
return this;
}
/**
* Add a node to the start of this element's children.
*
* @param child node to add.
* @return this element, so that you can add more child nodes or elements.
*/
public Element prependChild(Node child) {
Validate.notNull(child);
addChildren(0, child);
return this;
}
/**
* Inserts the given child nodes into this element at the specified index. Current nodes will be shifted to the
* right. The inserted nodes will be moved from their current parent. To prevent moving, copy the nodes first.
*
* @param index 0-based index to insert children at. Specify {@code 0} to insert at the start, {@code -1} at the
* end
* @param children child nodes to insert
* @return this element, for chaining.
*/
public Element insertChildren(int index, Collection children) {
Validate.notNull(children, "Children collection to be inserted must not be null.");
int currentSize = childNodeSize();
if (index < 0) index += currentSize +1; // roll around
Validate.isTrue(index >= 0 && index <= currentSize, "Insert position out of bounds.");
ArrayList nodes = new ArrayList(children);
Node[] nodeArray = nodes.toArray(new Node[nodes.size()]);
addChildren(index, nodeArray);
return this;
}
/**
* Create a new element by tag name, and add it as the last child.
*
* @param tagName the name of the tag (e.g. {@code div}).
* @return the new element, to allow you to add content to it, e.g.:
* {@code parent.appendElement("h1").attr("id", "header").text("Welcome");}
*/
public Element appendElement(String tagName) {
Element child = new Element(Tag.valueOf(tagName), baseUri());
appendChild(child);
return child;
}
/**
* Create a new element by tag name, and add it as the first child.
*
* @param tagName the name of the tag (e.g. {@code div}).
* @return the new element, to allow you to add content to it, e.g.:
* {@code parent.prependElement("h1").attr("id", "header").text("Welcome");}
*/
public Element prependElement(String tagName) {
Element child = new Element(Tag.valueOf(tagName), baseUri());
prependChild(child);
return child;
}
/**
* Create and append a new TextNode to this element.
*
* @param text the unencoded text to add
* @return this element
*/
public Element appendText(String text) {
TextNode node = new TextNode(text, baseUri());
appendChild(node);
return this;
}
/**
* Create and prepend a new TextNode to this element.
*
* @param text the unencoded text to add
* @return this element
*/
public Element prependText(String text) {
TextNode node = new TextNode(text, baseUri());
prependChild(node);
return this;
}
/**
* Add inner HTML to this element. The supplied HTML will be parsed, and each node appended to the end of the children.
* @param html HTML to add inside this element, after the existing HTML
* @return this element
* @see #html(String)
*/
public Element append(String html) {
Validate.notNull(html);
List nodes = Parser.parseFragment(html, this, baseUri());
addChildren(nodes.toArray(new Node[nodes.size()]));
return this;
}
/**
* Add inner HTML into this element. The supplied HTML will be parsed, and each node prepended to the start of the element's children.
* @param html HTML to add inside this element, before the existing HTML
* @return this element
* @see #html(String)
*/
public Element prepend(String html) {
Validate.notNull(html);
List nodes = Parser.parseFragment(html, this, baseUri());
addChildren(0, nodes.toArray(new Node[nodes.size()]));
return this;
}
/**
* Insert the specified HTML into the DOM before this element (as a preceding sibling).
*
* @param html HTML to add before this element
* @return this element, for chaining
* @see #after(String)
*/
@Override
public Element before(String html) {
return (Element) super.before(html);
}
/**
* Insert the specified node into the DOM before this node (as a preceding sibling).
* @param node to add before this element
* @return this Element, for chaining
* @see #after(Node)
*/
@Override
public Element before(Node node) {
return (Element) super.before(node);
}
/**
* Insert the specified HTML into the DOM after this element (as a following sibling).
*
* @param html HTML to add after this element
* @return this element, for chaining
* @see #before(String)
*/
@Override
public Element after(String html) {
return (Element) super.after(html);
}
/**
* Insert the specified node into the DOM after this node (as a following sibling).
* @param node to add after this element
* @return this element, for chaining
* @see #before(Node)
*/
@Override
public Element after(Node node) {
return (Element) super.after(node);
}
/**
* Remove all of the element's child nodes. Any attributes are left as-is.
* @return this element
*/
public Element empty() {
childNodes.clear();
return this;
}
/**
* Wrap the supplied HTML around this element.
*
* @param html HTML to wrap around this element, e.g. {@code }. Can be arbitrarily deep.
* @return this element, for chaining.
*/
@Override
public Element wrap(String html) {
return (Element) super.wrap(html);
}
/**
* Get a CSS selector that will uniquely select this element.
*
* If the element has an ID, returns #id;
* otherwise returns the parent (if any) CSS selector, followed by {@literal '>'},
* followed by a unique selector for the element (tag.class.class:nth-child(n)).
*
*
* @return the CSS Path that can be used to retrieve the element in a selector.
*/
public String cssSelector() {
if (id().length() > 0)
return "#" + id();
StringBuilder selector = new StringBuilder(tagName());
String classes = StringUtil.join(classNames(), ".");
if (classes.length() > 0)
selector.append('.').append(classes);
if (parent() == null || parent() instanceof Document) // don't add Document to selector, as will always have a html node
return selector.toString();
selector.insert(0, " > ");
if (parent().select(selector.toString()).size() > 1)
selector.append(String.format(
":nth-child(%d)", elementSiblingIndex() + 1));
return parent().cssSelector() + selector.toString();
}
/**
* Get sibling elements. If the element has no sibling elements, returns an empty list. An element is not a sibling
* of itself, so will not be included in the returned list.
* @return sibling elements
*/
public Elements siblingElements() {
if (parentNode == null)
return new Elements(0);
List elements = parent().children();
Elements siblings = new Elements(elements.size() - 1);
for (Element el: elements)
if (el != this)
siblings.add(el);
return siblings;
}
/**
* Gets the next sibling element of this element. E.g., if a {@code div} contains two {@code p}s,
* the {@code nextElementSibling} of the first {@code p} is the second {@code p}.
*
* This is similar to {@link #nextSibling()}, but specifically finds only Elements
*
* @return the next element, or null if there is no next element
* @see #previousElementSibling()
*/
public Element nextElementSibling() {
if (parentNode == null) return null;
List siblings = parent().children();
Integer index = indexInList(this, siblings);
Validate.notNull(index);
if (siblings.size() > index+1)
return siblings.get(index+1);
else
return null;
}
/**
* Gets the previous element sibling of this element.
* @return the previous element, or null if there is no previous element
* @see #nextElementSibling()
*/
public Element previousElementSibling() {
if (parentNode == null) return null;
List siblings = parent().children();
Integer index = indexInList(this, siblings);
Validate.notNull(index);
if (index > 0)
return siblings.get(index-1);
else
return null;
}
/**
* Gets the first element sibling of this element.
* @return the first sibling that is an element (aka the parent's first element child)
*/
public Element firstElementSibling() {
// todo: should firstSibling() exclude this?
List siblings = parent().children();
return siblings.size() > 1 ? siblings.get(0) : null;
}
/**
* Get the list index of this element in its element sibling list. I.e. if this is the first element
* sibling, returns 0.
* @return position in element sibling list
*/
public Integer elementSiblingIndex() {
if (parent() == null) return 0;
return indexInList(this, parent().children());
}
/**
* Gets the last element sibling of this element
* @return the last sibling that is an element (aka the parent's last element child)
*/
public Element lastElementSibling() {
List siblings = parent().children();
return siblings.size() > 1 ? siblings.get(siblings.size() - 1) : null;
}
private static Integer indexInList(Element search, List elements) {
Validate.notNull(search);
Validate.notNull(elements);
for (int i = 0; i < elements.size(); i++) {
E element = elements.get(i);
if (element == search)
return i;
}
return null;
}
// DOM type methods
/**
* Finds elements, including and recursively under this element, with the specified tag name.
* @param tagName The tag name to search for (case insensitively).
* @return a matching unmodifiable list of elements. Will be empty if this element and none of its children match.
*/
public Elements getElementsByTag(String tagName) {
Validate.notEmpty(tagName);
tagName = tagName.toLowerCase().trim();
return Collector.collect(new Evaluator.Tag(tagName), this);
}
/**
* Find an element by ID, including or under this element.
*
* Note that this finds the first matching ID, starting with this element. If you search down from a different
* starting point, it is possible to find a different element by ID. For unique element by ID within a Document,
* use {@link Document#getElementById(String)}
* @param id The ID to search for.
* @return The first matching element by ID, starting with this element, or null if none found.
*/
public Element getElementById(String id) {
Validate.notEmpty(id);
Elements elements = Collector.collect(new Evaluator.Id(id), this);
if (elements.size() > 0)
return elements.get(0);
else
return null;
}
/**
* Find elements that have this class, including or under this element. Case insensitive.
*
* Elements can have multiple classes (e.g. {@code
}. This method
* checks each class, so you can find the above with {@code el.getElementsByClass("header");}.
*
* @param className the name of the class to search for.
* @return elements with the supplied class name, empty if none
* @see #hasClass(String)
* @see #classNames()
*/
public Elements getElementsByClass(String className) {
Validate.notEmpty(className);
return Collector.collect(new Evaluator.Class(className), this);
}
/**
* Find elements that have a named attribute set. Case insensitive.
*
* @param key name of the attribute, e.g. {@code href}
* @return elements that have this attribute, empty if none
*/
public Elements getElementsByAttribute(String key) {
Validate.notEmpty(key);
key = key.trim().toLowerCase();
return Collector.collect(new Evaluator.Attribute(key), this);
}
/**
* Find elements that have an attribute name starting with the supplied prefix. Use {@code data-} to find elements
* that have HTML5 datasets.
* @param keyPrefix name prefix of the attribute e.g. {@code data-}
* @return elements that have attribute names that start with with the prefix, empty if none.
*/
public Elements getElementsByAttributeStarting(String keyPrefix) {
Validate.notEmpty(keyPrefix);
keyPrefix = keyPrefix.trim().toLowerCase();
return Collector.collect(new Evaluator.AttributeStarting(keyPrefix), this);
}
/**
* Find elements that have an attribute with the specific value. Case insensitive.
*
* @param key name of the attribute
* @param value value of the attribute
* @return elements that have this attribute with this value, empty if none
*/
public Elements getElementsByAttributeValue(String key, String value) {
return Collector.collect(new Evaluator.AttributeWithValue(key, value), this);
}
/**
* Find elements that either do not have this attribute, or have it with a different value. Case insensitive.
*
* @param key name of the attribute
* @param value value of the attribute
* @return elements that do not have a matching attribute
*/
public Elements getElementsByAttributeValueNot(String key, String value) {
return Collector.collect(new Evaluator.AttributeWithValueNot(key, value), this);
}
/**
* Find elements that have attributes that start with the value prefix. Case insensitive.
*
* @param key name of the attribute
* @param valuePrefix start of attribute value
* @return elements that have attributes that start with the value prefix
*/
public Elements getElementsByAttributeValueStarting(String key, String valuePrefix) {
return Collector.collect(new Evaluator.AttributeWithValueStarting(key, valuePrefix), this);
}
/**
* Find elements that have attributes that end with the value suffix. Case insensitive.
*
* @param key name of the attribute
* @param valueSuffix end of the attribute value
* @return elements that have attributes that end with the value suffix
*/
public Elements getElementsByAttributeValueEnding(String key, String valueSuffix) {
return Collector.collect(new Evaluator.AttributeWithValueEnding(key, valueSuffix), this);
}
/**
* Find elements that have attributes whose value contains the match string. Case insensitive.
*
* @param key name of the attribute
* @param match substring of value to search for
* @return elements that have attributes containing this text
*/
public Elements getElementsByAttributeValueContaining(String key, String match) {
return Collector.collect(new Evaluator.AttributeWithValueContaining(key, match), this);
}
/**
* Find elements that have attributes whose values match the supplied regular expression.
* @param key name of the attribute
* @param pattern compiled regular expression to match against attribute values
* @return elements that have attributes matching this regular expression
*/
public Elements getElementsByAttributeValueMatching(String key, Pattern pattern) {
return Collector.collect(new Evaluator.AttributeWithValueMatching(key, pattern), this);
}
/**
* Find elements that have attributes whose values match the supplied regular expression.
* @param key name of the attribute
* @param regex regular expression to match against attribute values. You can use embedded flags (such as (?i) and (?m) to control regex options.
* @return elements that have attributes matching this regular expression
*/
public Elements getElementsByAttributeValueMatching(String key, String regex) {
Pattern pattern;
try {
pattern = Pattern.compile(regex);
} catch (PatternSyntaxException e) {
throw new IllegalArgumentException("Pattern syntax error: " + regex, e);
}
return getElementsByAttributeValueMatching(key, pattern);
}
/**
* Find elements whose sibling index is less than the supplied index.
* @param index 0-based index
* @return elements less than index
*/
public Elements getElementsByIndexLessThan(int index) {
return Collector.collect(new Evaluator.IndexLessThan(index), this);
}
/**
* Find elements whose sibling index is greater than the supplied index.
* @param index 0-based index
* @return elements greater than index
*/
public Elements getElementsByIndexGreaterThan(int index) {
return Collector.collect(new Evaluator.IndexGreaterThan(index), this);
}
/**
* Find elements whose sibling index is equal to the supplied index.
* @param index 0-based index
* @return elements equal to index
*/
public Elements getElementsByIndexEquals(int index) {
return Collector.collect(new Evaluator.IndexEquals(index), this);
}
/**
* Find elements that contain the specified string. The search is case insensitive. The text may appear directly
* in the element, or in any of its descendants.
* @param searchText to look for in the element's text
* @return elements that contain the string, case insensitive.
* @see Element#text()
*/
public Elements getElementsContainingText(String searchText) {
return Collector.collect(new Evaluator.ContainsText(searchText), this);
}
/**
* Find elements that directly contain the specified string. The search is case insensitive. The text must appear directly
* in the element, not in any of its descendants.
* @param searchText to look for in the element's own text
* @return elements that contain the string, case insensitive.
* @see Element#ownText()
*/
public Elements getElementsContainingOwnText(String searchText) {
return Collector.collect(new Evaluator.ContainsOwnText(searchText), this);
}
/**
* Find elements whose text matches the supplied regular expression.
* @param pattern regular expression to match text against
* @return elements matching the supplied regular expression.
* @see Element#text()
*/
public Elements getElementsMatchingText(Pattern pattern) {
return Collector.collect(new Evaluator.Matches(pattern), this);
}
/**
* Find elements whose text matches the supplied regular expression.
* @param regex regular expression to match text against. You can use embedded flags (such as (?i) and (?m) to control regex options.
* @return elements matching the supplied regular expression.
* @see Element#text()
*/
public Elements getElementsMatchingText(String regex) {
Pattern pattern;
try {
pattern = Pattern.compile(regex);
} catch (PatternSyntaxException e) {
throw new IllegalArgumentException("Pattern syntax error: " + regex, e);
}
return getElementsMatchingText(pattern);
}
/**
* Find elements whose own text matches the supplied regular expression.
* @param pattern regular expression to match text against
* @return elements matching the supplied regular expression.
* @see Element#ownText()
*/
public Elements getElementsMatchingOwnText(Pattern pattern) {
return Collector.collect(new Evaluator.MatchesOwn(pattern), this);
}
/**
* Find elements whose text matches the supplied regular expression.
* @param regex regular expression to match text against. You can use embedded flags (such as (?i) and (?m) to control regex options.
* @return elements matching the supplied regular expression.
* @see Element#ownText()
*/
public Elements getElementsMatchingOwnText(String regex) {
Pattern pattern;
try {
pattern = Pattern.compile(regex);
} catch (PatternSyntaxException e) {
throw new IllegalArgumentException("Pattern syntax error: " + regex, e);
}
return getElementsMatchingOwnText(pattern);
}
/**
* Find all elements under this element (including self, and children of children).
*
* @return all elements
*/
public Elements getAllElements() {
return Collector.collect(new Evaluator.AllElements(), this);
}
/**
* Gets the combined text of this element and all its children. Whitespace is normalized and trimmed.
*
* For example, given HTML {@code
Hello there now!
}, {@code p.text()} returns {@code "Hello there now!"}
*
* @return unencoded text, or empty string if none.
* @see #ownText()
* @see #textNodes()
*/
public String text() {
final StringBuilder accum = new StringBuilder();
new NodeTraversor(new NodeVisitor() {
public void head(Node node, int depth) {
if (node instanceof TextNode) {
TextNode textNode = (TextNode) node;
appendNormalisedText(accum, textNode);
} else if (node instanceof Element) {
Element element = (Element) node;
if (accum.length() > 0 &&
(element.isBlock() || element.tag.getName().equals("br")) &&
!TextNode.lastCharIsWhitespace(accum))
accum.append(" ");
}
}
public void tail(Node node, int depth) {
}
}).traverse(this);
return accum.toString().trim();
}
/**
* Gets the text owned by this element only; does not get the combined text of all children.
*
* For example, given HTML {@code
Hello there now!
}, {@code p.ownText()} returns {@code "Hello now!"},
* whereas {@code p.text()} returns {@code "Hello there now!"}.
* Note that the text within the {@code b} element is not returned, as it is not a direct child of the {@code p} element.
*
* @return unencoded text, or empty string if none.
* @see #text()
* @see #textNodes()
*/
public String ownText() {
StringBuilder sb = new StringBuilder();
ownText(sb);
return sb.toString().trim();
}
private void ownText(StringBuilder accum) {
for (Node child : childNodes) {
if (child instanceof TextNode) {
TextNode textNode = (TextNode) child;
appendNormalisedText(accum, textNode);
} else if (child instanceof Element) {
appendWhitespaceIfBr((Element) child, accum);
}
}
}
private static void appendNormalisedText(StringBuilder accum, TextNode textNode) {
String text = textNode.getWholeText();
if (preserveWhitespace(textNode.parentNode))
accum.append(text);
else
StringUtil.appendNormalisedWhitespace(accum, text, TextNode.lastCharIsWhitespace(accum));
}
private static void appendWhitespaceIfBr(Element element, StringBuilder accum) {
if (element.tag.getName().equals("br") && !TextNode.lastCharIsWhitespace(accum))
accum.append(" ");
}
static boolean preserveWhitespace(Node node) {
// looks only at this element and one level up, to prevent recursion & needless stack searches
if (node != null && node instanceof Element) {
Element element = (Element) node;
return element.tag.preserveWhitespace() ||
element.parent() != null && element.parent().tag.preserveWhitespace();
}
return false;
}
/**
* Set the text of this element. Any existing contents (text or elements) will be cleared
* @param text unencoded text
* @return this element
*/
public Element text(String text) {
Validate.notNull(text);
empty();
TextNode textNode = new TextNode(text, baseUri);
appendChild(textNode);
return this;
}
/**
Test if this element has any text content (that is not just whitespace).
@return true if element has non-blank text content.
*/
public boolean hasText() {
for (Node child: childNodes) {
if (child instanceof TextNode) {
TextNode textNode = (TextNode) child;
if (!textNode.isBlank())
return true;
} else if (child instanceof Element) {
Element el = (Element) child;
if (el.hasText())
return true;
}
}
return false;
}
/**
* Get the combined data of this element. Data is e.g. the inside of a {@code script} tag.
* @return the data, or empty string if none
*
* @see #dataNodes()
*/
public String data() {
StringBuilder sb = new StringBuilder();
for (Node childNode : childNodes) {
if (childNode instanceof DataNode) {
DataNode data = (DataNode) childNode;
sb.append(data.getWholeData());
} else if (childNode instanceof Element) {
Element element = (Element) childNode;
String elementData = element.data();
sb.append(elementData);
}
}
return sb.toString();
}
/**
* Gets the literal value of this element's "class" attribute, which may include multiple class names, space
* separated. (E.g. on <div class="header gray"> returns, "header gray")
* @return The literal class attribute, or empty string if no class attribute set.
*/
public String className() {
return attr("class").trim();
}
/**
* Get all of the element's class names. E.g. on element {@code },
* returns a set of two elements {@code "header", "gray"}. Note that modifications to this set are not pushed to
* the backing {@code class} attribute; use the {@link #classNames(java.util.Set)} method to persist them.
* @return set of classnames, empty if no class attribute
*/
public Set classNames() {
String[] names = classSplit.split(className());
Set classNames = new LinkedHashSet(Arrays.asList(names));
classNames.remove(""); // if classNames() was empty, would include an empty class
return classNames;
}
/**
Set the element's {@code class} attribute to the supplied class names.
@param classNames set of classes
@return this element, for chaining
*/
public Element classNames(Set classNames) {
Validate.notNull(classNames);
attributes.put("class", StringUtil.join(classNames, " "));
return this;
}
/**
* Tests if this element has a class. Case insensitive.
* @param className name of class to check for
* @return true if it does, false if not
*/
/*
Used by common .class selector, so perf tweaked to reduce object creation vs hitting classnames().
Wiki: 71, 13 (5.4x)
CNN: 227, 91 (2.5x)
Alterslash: 59, 4 (14.8x)
Jsoup: 14, 1 (14x)
*/
public boolean hasClass(String className) {
String classAttr = attributes.get("class");
if (classAttr.equals("") || classAttr.length() < className.length())
return false;
final String[] classes = classSplit.split(classAttr);
for (String name : classes) {
if (className.equalsIgnoreCase(name))
return true;
}
return false;
}
/**
Add a class name to this element's {@code class} attribute.
@param className class name to add
@return this element
*/
public Element addClass(String className) {
Validate.notNull(className);
Set classes = classNames();
classes.add(className);
classNames(classes);
return this;
}
/**
Remove a class name from this element's {@code class} attribute.
@param className class name to remove
@return this element
*/
public Element removeClass(String className) {
Validate.notNull(className);
Set classes = classNames();
classes.remove(className);
classNames(classes);
return this;
}
/**
Toggle a class name on this element's {@code class} attribute: if present, remove it; otherwise add it.
@param className class name to toggle
@return this element
*/
public Element toggleClass(String className) {
Validate.notNull(className);
Set classes = classNames();
if (classes.contains(className))
classes.remove(className);
else
classes.add(className);
classNames(classes);
return this;
}
/**
* Get the value of a form element (input, textarea, etc).
* @return the value of the form element, or empty string if not set.
*/
public String val() {
if (tagName().equals("textarea"))
return text();
else
return attr("value");
}
/**
* Set the value of a form element (input, textarea, etc).
* @param value value to set
* @return this element (for chaining)
*/
public Element val(String value) {
if (tagName().equals("textarea"))
text(value);
else
attr("value", value);
return this;
}
void outerHtmlHead(StringBuilder accum, int depth, Document.OutputSettings out) {
if (accum.length() > 0 && out.prettyPrint() && (tag.formatAsBlock() || (parent() != null && parent().tag().formatAsBlock()) || out.outline()) )
indent(accum, depth, out);
accum
.append("<")
.append(tagName());
attributes.html(accum, out);
// selfclosing includes unknown tags, isEmpty defines tags that are always empty
if (childNodes.isEmpty() && tag.isSelfClosing()) {
if (out.syntax() == Document.OutputSettings.Syntax.html && tag.isEmpty())
accum.append('>');
else
accum.append(" />"); // ![]()
in html, ![]()
in xml
}
else
accum.append(">");
}
void outerHtmlTail(StringBuilder accum, int depth, Document.OutputSettings out) {
if (!(childNodes.isEmpty() && tag.isSelfClosing())) {
if (out.prettyPrint() && (!childNodes.isEmpty() && (
tag.formatAsBlock() || (out.outline() && (childNodes.size()>1 || (childNodes.size()==1 && !(childNodes.get(0) instanceof TextNode))))
)))
indent(accum, depth, out);
accum.append("");
}
}
/**
* Retrieves the element's inner HTML. E.g. on a {@code } with one empty {@code }, would return
* {@code
}. (Whereas {@link #outerHtml()} would return {@code }.)
*
* @return String of HTML.
* @see #outerHtml()
*/
public String html() {
StringBuilder accum = new StringBuilder();
html(accum);
return getOutputSettings().prettyPrint() ? accum.toString().trim() : accum.toString();
}
private void html(StringBuilder accum) {
for (Node node : childNodes)
node.outerHtml(accum);
}
/**
* Set this element's inner HTML. Clears the existing HTML first.
* @param html HTML to parse and set into this element
* @return this element
* @see #append(String)
*/
public Element html(String html) {
empty();
append(html);
return this;
}
public String toString() {
return outerHtml();
}
@Override
public boolean equals(Object o) {
if (this == o) return true;
if (o == null || getClass() != o.getClass()) return false;
if (!super.equals(o)) return false;
Element element = (Element) o;
return tag.equals(element.tag);
}
@Override
public int hashCode() {
int result = super.hashCode();
result = 31 * result + (tag != null ? tag.hashCode() : 0);
return result;
}
@Override
public Element clone() {
return (Element) super.clone();
}
}
© 2015 - 2024 Weber Informatics LLC | Privacy Policy