Skip to content

[pull] master from jhy:master #290

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pull merged 1 commit into from
Sep 11, 2026
Merged

[pull] master from jhy:master #290

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGES.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
* Standardized parser normalization of tag and attribute names so that HTML comparisons use ASCII-only case folding, and accepted control characters are preserved, aligning name handling to the HTML and XML specs. [#2594](https://github.com/jhy/jsoup/issues/2594)
* Named character references without a semicolon before `-` or `_` now decode correctly in attribute values, matching HTML and browser behavior (e.g., `&copy-` becomes `漏-`). [#2588](https://github.com/jhy/jsoup/issues/2588)
* Support downloads > 2GB via `Response.bodyStream()` when `maxBodySize(0)` is configured. [#2593](https://github.com/jhy/jsoup/issues/2593)
* Updated the adoption-agency algorithm to align to the HTML5 spec. Misnested formatting in tables now places recovered blocks correctly, along with related table and fragment parsing cases. For example, `<table><b><p>X</b>` now places the paragraph before the table rather than inside it. [#2601](https://github.com/jhy/jsoup/issues/2601)

## 1.23.2 (2026-Aug-26)

Expand Down
122 changes: 77 additions & 45 deletions src/main/java/org/jsoup/parser/HtmlTreeBuilder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@

import java.io.Reader;
import java.util.ArrayList;
import java.util.Collection;
import java.util.List;

import static org.jsoup.internal.StringUtil.inSorted;
Expand All @@ -41,7 +42,8 @@ public class HtmlTreeBuilder extends TreeBuilder {
private boolean baseUriSetFromDoc;
private @Nullable Element headElement; // the current head element
private @Nullable FormElement formElement; // the current form element
private @Nullable Element contextElement; // fragment parse root; shallow copy of context, may be null during fragment parsing
private @Nullable Element contextElement; // context copy and fragment output container; not on the stack
private @Nullable Element fragmentRoot; // internal stack root; contextElement receives fragment nodes
ArrayList<Element> formattingElements; // active (open) formatting elements
private ArrayList<HtmlTreeBuilderState> tmplInsertMode; // stack of Template Insertion modes
private @Nullable NoscriptState noscriptState; // active noscript island state
Expand Down Expand Up @@ -72,6 +74,7 @@ protected void initialiseParse(Reader input, String baseUri, Parser parser) {
headElement = null;
formElement = null;
contextElement = null;
fragmentRoot = null;
formattingElements = new ArrayList<>();
tmplInsertMode = new ArrayList<>();
noscriptState = null;
Expand Down Expand Up @@ -120,8 +123,9 @@ protected void initialiseParse(Reader input, String baseUri, Parser parser) {
break;
}
tokeniser.transition(contextState);
fragmentRoot = new Element(tagFor("html", "html", NamespaceHtml, settings), baseUri);
doc.appendChild(contextElement);
push(contextElement);
push(fragmentRoot);
resetInsertionMode();

// setup form element to nearest form on context (up ancestor chain). ensures form controls are associated
Expand All @@ -135,21 +139,12 @@ protected void initialiseParse(Reader input, String baseUri, Parser parser) {
formSearch = formSearch.parent();
}

if (htmlContext && contextName.equals("noscript")) enterNoscript(contextElement);
if (htmlContext && contextName.equals("noscript")) enterNoscript(fragmentRoot);
}
}

@Override List<Node> completeParseFragment() {
if (contextElement != null) {
// depending on context and the input html, content may have been added outside of the root el
// e.g. context=p, input=div, the div will have been pushed out.
List<Node> nodes = contextElement.siblingNodes();
if (!nodes.isEmpty())
contextElement.insertChildren(-1, nodes);
return contextElement.childNodes();
}
else
return doc.childNodes();
return (contextElement != null ? contextElement : doc).childNodes();
}

@Override
Expand Down Expand Up @@ -220,7 +215,7 @@ private boolean insertNoscriptStartTag(Token.StartTag start) {
private boolean closeNoscriptEndTag(Token.EndTag end) {
String name = end.normalName();
NoscriptState island = Validate.expectNotNull(noscriptState, "Bug: noscript end tag processed with no island state");
if (name.equals("noscript") && island.boundary != contextElement) {
if (name.equals("noscript") && island.boundary != fragmentRoot) {
endNoscript();
return true;
}
Expand All @@ -239,7 +234,7 @@ boolean useCurrentOrForeignInsert(Token token) {
// If the stack of open elements is empty
if (stack.isEmpty())
return true;
final Element el = currentElement();
final Element el = adjustedCurrentElement();
final String ns = el.tag().namespace();

// If the adjusted current node is an element in the HTML namespace
Expand Down Expand Up @@ -462,15 +457,18 @@ private void doInsertElement(Element el) {
if (parser.getErrors().canAddError() && el.hasAttr("xmlns") && !el.attr("xmlns").equals(el.tag().namespace()))
error("Invalid xmlns attribute [%s] on tag [%s]", el.attr("xmlns"), el.tagName());

Element target = currentElOrDoc();
if (isFosterInserts() && StringUtil.inSorted(target.normalName(), InTableFoster))
insertInFosterParent(el);
else
target.appendChild(el);

insertNode(el, currentElOrDoc());
push(el);
}

/** Inserts a node at the appropriate location for the target. */
void insertNode(Node node, Element target) {
if (isFosterInserts() && target.tag().namespace().equals(NamespaceHtml) && inSorted(target.normalName(), InTableFoster))
insertInFosterParent(node);
else
insertionTarget(target).appendChild(node);
}

/** Inserts a comment into the current element, or the document when there is none. */
void insertCommentNode(Token.Comment token) {
insertCommentNode(token, currentElOrDoc());
Expand All @@ -479,7 +477,7 @@ void insertCommentNode(Token.Comment token) {
/** Inserts a comment into the supplied target. */
void insertCommentNode(Token.Comment token, Element target) {
Comment node = new Comment(token.getData());
target.appendChild(node);
insertionTarget(target).appendChild(node);
onNodeInserted(node);
}

Expand All @@ -506,6 +504,7 @@ void insertCharacterNode(Token.Character characterToken, boolean replace) {
void insertCharacterToElement(Token.Character characterToken, Element el) {
final Node node;
final String data = characterToken.getData();
el = insertionTarget(el);

if (characterToken.isCData())
node = new CDataNode(data);
Expand All @@ -521,6 +520,36 @@ ArrayList<Element> getStack() {
return stack;
}

/** Gets the insertion target for fragment content. */
private Element insertionTarget(Element target) {
// the html root is only used by the tree builder; content belongs in the context copy
return target == fragmentRoot && contextElement != null ? contextElement : target;
}

/** Notifies listeners that a node was inserted. */
@Override void onNodeInserted(Node node) {
// listeners observe the fragment's context copy, not its parser-only html root
super.onNodeInserted(node == fragmentRoot && contextElement != null ? contextElement : node);
}

/** Notifies listeners that a node was closed. */
@Override void onNodeClosed(Node node) {
super.onNodeClosed(node == fragmentRoot && contextElement != null ? contextElement : node);
}

/** Tests whether an element is open. */
@Override boolean isOpen(Element element) {
// the context copy remains open for streaming while its parser root is open
return super.isOpen(element == contextElement && fragmentRoot != null ? fragmentRoot : element);
}

/** Copies the open elements. */
@Override void copyOpenElementsTo(Collection<? super Element> elements) {
// streaming tracks the context copy in place of the parser-only root
for (Element element : stack)
elements.add(insertionTarget(element));
}

boolean onStack(Element el) {
return stack.contains(el);
}
Expand All @@ -530,10 +559,15 @@ boolean onStack(String elName) {
return getFromStack(elName) != null;
}

/** Checks if there is an HTML element with the given name above the synthetic fragment context. */
boolean onStackAboveContext(String elName) {
Element el = getFromStack(elName);
return el != null && el != contextElement;
/** Gets the adjusted current element for foreign-content dispatch. */
private Element adjustedCurrentElement() {
// fragment parsing uses the context at the parser root
return fragmentParsing && stack.size() == 1 && contextElement != null ? contextElement : currentElement();
}

/** Gets the namespace used to process the current token. */
@Override String currentElNs() {
return adjustedCurrentElement().tag().namespace();
}

/** Gets the nearest (lowest) HTML element with the given name from the stack. */
Expand Down Expand Up @@ -1135,26 +1169,24 @@ void insertMarkerToFormattingElements() {
formattingElements.add(null);
}

void insertInFosterParent(Node in) {
Element fosterParent;
Element lastTable = getFromStack("table");
boolean isLastTableParent = false;
if (lastTable != null) {
if (lastTable.parent() != null) {
fosterParent = lastTable.parent();
isLastTableParent = true;
} else
fosterParent = aboveOnStack(lastTable);
} else { // no table == frag
fosterParent = stack.get(0);
}

if (isLastTableParent) {
Validate.notNull(lastTable); // last table cannot be null by this point.
lastTable.before(in);
/** Inserts a foster-parented node. */
private void insertInFosterParent(Node in) {
for (int pos = stack.size() - 1; pos >= 0; pos--) {
Element el = stack.get(pos);
if (el.elementIs("template", NamespaceHtml)) {
// template contents are stored directly on the element
el.appendChild(in);
return;
}
if (el.elementIs("table", NamespaceHtml)) {
if (el.parent() != null)
el.before(in);
else
insertionTarget(stack.get(pos - 1)).appendChild(in);
return;
}
}
else
fosterParent.appendChild(in);
insertionTarget(stack.get(0)).appendChild(in);
}

// Template Insertion Mode stack
Expand Down
22 changes: 11 additions & 11 deletions src/main/java/org/jsoup/parser/HtmlTreeBuilderState.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,7 @@ private boolean anythingElse(Token t, HtmlTreeBuilder tb) {
} else if (inSorted(name, Constants.InHeadEnd)) {
return anythingElse(t, tb);
} else if (name.equals("template")) {
if (!tb.onStackAboveContext(name)) {
if (!tb.onStack(name)) {
tb.error(this);
} else {
tb.generateImpliedEndTags(true);
Expand Down Expand Up @@ -930,9 +930,7 @@ private boolean inBodyEndTagAdoption(Token t, HtmlTreeBuilder tb) {
} // end inner loop # 13

// 14. Insert whatever lastNode ended up being in the previous step at the [appropriate place for inserting a node], but using commonAncestor as the _override target_.
// todo - impl https://html.spec.whatwg.org/multipage/parsing.html#appropriate-place-for-inserting-a-node fostering
// just use commonAncestor as target:
commonAncestor.appendChild(lastEl);
tb.insertNode(lastEl, commonAncestor);
// 15. [Create an element for the token] for which formattingElement was created, in the [HTML namespace], with furthestBlock as the intended parent.
Element adoptor = tb.recreateElement(formatEl);
// 16. Take all of the child nodes of furthestBlock and append them to the element created in the last step.
Expand Down Expand Up @@ -1073,9 +1071,11 @@ private boolean inBodyEndTagAdoption(Token t, HtmlTreeBuilder tb) {

boolean anythingElse(Token t, HtmlTreeBuilder tb) {
tb.error(this);
boolean fosterInserts = tb.isFosterInserts();
tb.setFosterInserts(true);
tb.process(t, InBody);
tb.setFosterInserts(false);
// synthetic end tags can reenter this handler; restore the outer token's foster flag
tb.setFosterInserts(fosterInserts);
return true;
}
},
Expand Down Expand Up @@ -1189,6 +1189,9 @@ boolean anythingElse(Token t, HtmlTreeBuilder tb) {
tb.transition(InTable);
}
break;
case "col":
tb.error(this);
return false;
case "template":
tb.process(t, InHead);
break;
Expand All @@ -1197,10 +1200,7 @@ boolean anythingElse(Token t, HtmlTreeBuilder tb) {
}
break;
case EOF:
if (tb.currentElementIs("html"))
return true; // stop parsing; frag case
else
return anythingElse(t, tb);
return tb.process(t, InBody);
default:
return anythingElse(t, tb);
}
Expand Down Expand Up @@ -1579,7 +1579,7 @@ else if (name.equals("col")) {
}
break;
case EOF:
if (!tb.onStackAboveContext("template")) { // stop parsing
if (!tb.onStack("template")) { // stop parsing
return true;
}
tb.error(this);
Expand Down Expand Up @@ -1775,7 +1775,7 @@ else if (name.equals("col")) {

// Any other start:
// (whatwg says to fix up tag name and attribute case per a table - we will preserve original case instead)
String namespace = tb.currentElement().tag().namespace();
String namespace = tb.currentElNs();
tb.insertForeignElementFor(start, namespace);
// (self-closing handled in insert)
// if self-closing svg script -- level and execution elided
Expand Down
2 changes: 1 addition & 1 deletion src/main/java/org/jsoup/parser/Tokeniser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -265,7 +265,7 @@ void createTempBuffer() {
/** Test if CDATA sections are allowed at the adjusted current node. */
boolean isCdataAllowed() {
return syntax == Document.OutputSettings.Syntax.xml
|| (treeBuilder.hasCurrentElement() && !Parser.NamespaceHtml.equals(treeBuilder.currentElement().tag().namespace()));
|| (treeBuilder.hasCurrentElement() && !Parser.NamespaceHtml.equals(treeBuilder.currentElNs()));
}

/** Test if the pending end tag matches the last emitted start tag. */
Expand Down
5 changes: 5 additions & 0 deletions src/main/java/org/jsoup/parser/TreeBuilder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,6 +223,11 @@ int defaultMaxDepth() {
return 512;
}

/** The namespace used to process the current token. */
String currentElNs() {
return currentElement().tag().namespace();
}

/**
Gets the current open element for tree-construction decisions.
The stack must not be empty; use {@link #hasCurrentElement()} when it may be.
Expand Down
Loading