summaryrefslogtreecommitdiffstats
path: root/parser/html/nsParserUtils.cpp
diff options
context:
space:
mode:
authorMatt A. Tobin <mattatobin@localhost.localdomain>2018-02-02 04:16:08 -0500
committerMatt A. Tobin <mattatobin@localhost.localdomain>2018-02-02 04:16:08 -0500
commit5f8de423f190bbb79a62f804151bc24824fa32d8 (patch)
tree10027f336435511475e392454359edea8e25895d /parser/html/nsParserUtils.cpp
parent49ee0794b5d912db1f95dce6eb52d781dc210db5 (diff)
downloadUXP-5f8de423f190bbb79a62f804151bc24824fa32d8.tar
UXP-5f8de423f190bbb79a62f804151bc24824fa32d8.tar.gz
UXP-5f8de423f190bbb79a62f804151bc24824fa32d8.tar.lz
UXP-5f8de423f190bbb79a62f804151bc24824fa32d8.tar.xz
UXP-5f8de423f190bbb79a62f804151bc24824fa32d8.zip
Add m-esr52 at 52.6.0
Diffstat (limited to 'parser/html/nsParserUtils.cpp')
-rw-r--r--parser/html/nsParserUtils.cpp232
1 files changed, 232 insertions, 0 deletions
diff --git a/parser/html/nsParserUtils.cpp b/parser/html/nsParserUtils.cpp
new file mode 100644
index 000000000..9e0bb8c9e
--- /dev/null
+++ b/parser/html/nsParserUtils.cpp
@@ -0,0 +1,232 @@
+/* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
+/* This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+#include "nsString.h"
+#include "nsIComponentManager.h"
+#include "nsCOMPtr.h"
+#include "nsXPCOM.h"
+#include "nsISupportsPrimitives.h"
+#include "nsXPIDLString.h"
+#include "nsScriptLoader.h"
+#include "nsEscape.h"
+#include "nsIParser.h"
+#include "nsIDTD.h"
+#include "nsNetCID.h"
+#include "nsNetUtil.h"
+#include "nsParserCIID.h"
+#include "nsContentUtils.h"
+#include "nsIContentSink.h"
+#include "nsIDocumentEncoder.h"
+#include "nsIDOMDocumentFragment.h"
+#include "nsIFragmentContentSink.h"
+#include "nsIDOMDocument.h"
+#include "nsIDOMNodeList.h"
+#include "nsIDOMNode.h"
+#include "nsIDOMElement.h"
+#include "nsIDocument.h"
+#include "nsIContent.h"
+#include "nsAttrName.h"
+#include "nsHTMLParts.h"
+#include "nsContentCID.h"
+#include "nsIScriptableUnescapeHTML.h"
+#include "nsParserUtils.h"
+#include "nsAutoPtr.h"
+#include "nsTreeSanitizer.h"
+#include "nsHtml5Module.h"
+#include "mozilla/dom/DocumentFragment.h"
+#include "nsNullPrincipal.h"
+
+#define XHTML_DIV_TAG "div xmlns=\"http://www.w3.org/1999/xhtml\""
+
+using namespace mozilla::dom;
+
+NS_IMPL_ISUPPORTS(nsParserUtils,
+ nsIScriptableUnescapeHTML,
+ nsIParserUtils)
+
+NS_IMETHODIMP
+nsParserUtils::ConvertToPlainText(const nsAString& aFromStr,
+ uint32_t aFlags,
+ uint32_t aWrapCol,
+ nsAString& aToStr)
+{
+ return nsContentUtils::ConvertToPlainText(aFromStr,
+ aToStr,
+ aFlags,
+ aWrapCol);
+}
+
+NS_IMETHODIMP
+nsParserUtils::Unescape(const nsAString& aFromStr,
+ nsAString& aToStr)
+{
+ return nsContentUtils::ConvertToPlainText(aFromStr,
+ aToStr,
+ nsIDocumentEncoder::OutputSelectionOnly |
+ nsIDocumentEncoder::OutputAbsoluteLinks,
+ 0);
+}
+
+NS_IMETHODIMP
+nsParserUtils::Sanitize(const nsAString& aFromStr,
+ uint32_t aFlags,
+ nsAString& aToStr)
+{
+ nsCOMPtr<nsIURI> uri;
+ NS_NewURI(getter_AddRefs(uri), "about:blank");
+ nsCOMPtr<nsIPrincipal> principal = nsNullPrincipal::Create();
+ nsCOMPtr<nsIDOMDocument> domDocument;
+ nsresult rv = NS_NewDOMDocument(getter_AddRefs(domDocument),
+ EmptyString(),
+ EmptyString(),
+ nullptr,
+ uri,
+ uri,
+ principal,
+ true,
+ nullptr,
+ DocumentFlavorHTML);
+ NS_ENSURE_SUCCESS(rv, rv);
+
+ nsCOMPtr<nsIDocument> document = do_QueryInterface(domDocument);
+ rv = nsContentUtils::ParseDocumentHTML(aFromStr, document, false);
+ NS_ENSURE_SUCCESS(rv, rv);
+
+ nsTreeSanitizer sanitizer(aFlags);
+ sanitizer.Sanitize(document);
+
+ nsCOMPtr<nsIDocumentEncoder> encoder =
+ do_CreateInstance(NS_DOC_ENCODER_CONTRACTID_BASE "text/html");
+
+ encoder->NativeInit(document,
+ NS_LITERAL_STRING("text/html"),
+ nsIDocumentEncoder::OutputDontRewriteEncodingDeclaration |
+ nsIDocumentEncoder::OutputNoScriptContent |
+ nsIDocumentEncoder::OutputEncodeBasicEntities |
+ nsIDocumentEncoder::OutputLFLineBreak |
+ nsIDocumentEncoder::OutputRaw);
+
+ return encoder->EncodeToString(aToStr);
+}
+
+NS_IMETHODIMP
+nsParserUtils::ParseFragment(const nsAString& aFragment,
+ bool aIsXML,
+ nsIURI* aBaseURI,
+ nsIDOMElement* aContextElement,
+ nsIDOMDocumentFragment** aReturn)
+{
+ return nsParserUtils::ParseFragment(aFragment,
+ 0,
+ aIsXML,
+ aBaseURI,
+ aContextElement,
+ aReturn);
+}
+
+NS_IMETHODIMP
+nsParserUtils::ParseFragment(const nsAString& aFragment,
+ uint32_t aFlags,
+ bool aIsXML,
+ nsIURI* aBaseURI,
+ nsIDOMElement* aContextElement,
+ nsIDOMDocumentFragment** aReturn)
+{
+ NS_ENSURE_ARG(aContextElement);
+ *aReturn = nullptr;
+
+ nsCOMPtr<nsIDocument> document;
+ nsCOMPtr<nsIDOMDocument> domDocument;
+ nsCOMPtr<nsIDOMNode> contextNode;
+ contextNode = do_QueryInterface(aContextElement);
+ contextNode->GetOwnerDocument(getter_AddRefs(domDocument));
+ document = do_QueryInterface(domDocument);
+ NS_ENSURE_TRUE(document, NS_ERROR_NOT_AVAILABLE);
+
+ nsAutoScriptBlockerSuppressNodeRemoved autoBlocker;
+
+ // stop scripts
+ RefPtr<nsScriptLoader> loader;
+ bool scripts_enabled = false;
+ if (document) {
+ loader = document->ScriptLoader();
+ scripts_enabled = loader->GetEnabled();
+ }
+ if (scripts_enabled) {
+ loader->SetEnabled(false);
+ }
+
+ // Wrap things in a div or body for parsing, but it won't show up in
+ // the fragment.
+ nsresult rv = NS_OK;
+ AutoTArray<nsString, 2> tagStack;
+ nsAutoCString base, spec;
+ if (aIsXML) {
+ // XHTML
+ if (aBaseURI) {
+ base.AppendLiteral(XHTML_DIV_TAG);
+ base.AppendLiteral(" xml:base=\"");
+ rv = aBaseURI->GetSpec(spec);
+ NS_ENSURE_SUCCESS(rv, rv);
+ // nsEscapeHTML is good enough, because we only need to get
+ // quotes, ampersands, and angle brackets
+ char* escapedSpec = nsEscapeHTML(spec.get());
+ if (escapedSpec)
+ base += escapedSpec;
+ free(escapedSpec);
+ base.Append('"');
+ tagStack.AppendElement(NS_ConvertUTF8toUTF16(base));
+ } else {
+ tagStack.AppendElement(NS_LITERAL_STRING(XHTML_DIV_TAG));
+ }
+ }
+
+ nsCOMPtr<nsIContent> fragment;
+ if (aIsXML) {
+ rv = nsContentUtils::ParseFragmentXML(aFragment,
+ document,
+ tagStack,
+ true,
+ aReturn);
+ fragment = do_QueryInterface(*aReturn);
+ } else {
+ NS_ADDREF(*aReturn = new DocumentFragment(document->NodeInfoManager()));
+ fragment = do_QueryInterface(*aReturn);
+ rv = nsContentUtils::ParseFragmentHTML(aFragment,
+ fragment,
+ nsGkAtoms::body,
+ kNameSpaceID_XHTML,
+ false,
+ true);
+ // Now, set the base URI on all subtree roots.
+ if (aBaseURI) {
+ nsresult rv2 = aBaseURI->GetSpec(spec);
+ NS_ENSURE_SUCCESS(rv2, rv2);
+ nsAutoString spec16;
+ CopyUTF8toUTF16(spec, spec16);
+ nsIContent* node = fragment->GetFirstChild();
+ while (node) {
+ if (node->IsElement()) {
+ node->SetAttr(kNameSpaceID_XML,
+ nsGkAtoms::base,
+ nsGkAtoms::xml,
+ spec16,
+ false);
+ }
+ node = node->GetNextSibling();
+ }
+ }
+ }
+ if (fragment) {
+ nsTreeSanitizer sanitizer(aFlags);
+ sanitizer.Sanitize(fragment);
+ }
+
+ if (scripts_enabled) {
+ loader->SetEnabled(true);
+ }
+
+ return rv;
+}