gecko-dev/parser/html/nsHtml5SpeculativeLoad.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

159 строки
6.0 KiB
C++
Исходник Обычный вид История

/* 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 "nsHtml5SpeculativeLoad.h"
#include "mozilla/Encoding.h"
#include "nsHtml5TreeOpExecutor.h"
using namespace mozilla;
nsHtml5SpeculativeLoad::nsHtml5SpeculativeLoad()
: mOpCode(eSpeculativeLoadUninitialized),
mIsAsync(false),
mIsDefer(false),
mIsLinkPreload(false),
Bug 1701828 - meta charset rewrite. r=smaug Implements https://github.com/whatwg/html/issues/6962 . Improves performance when <meta charset> occurs in head but after the first kilobyte and aligns behavior better with WebKit and Blink. The main change is to avoid reloads when meta appears within head but after the first kilobyte. Prior to this change, Gecko reloaded in that case (in compliance with the spec!) even though WebKit and Blink did not. Differences from WebKit and Blink: * WebKit and Blink honor <meta charset> in <noscript>. This implementation does not. * WebKit and Blink look for meta as if the tree builder was unaware of foreign content. This implementation is foreign content-aware. This makes a difference for CDATA sections that contain a > before the meta as well as style and script elements within foreign content. This could happen if the CDATA section that has mysteriously been introduced around a what looks like a meta tag also contains another prior tag-looking run of text. * This implementation processes rel=preload and speculative loads that are seen before <meta charset> has been seen. WebKit and Blink instead first look for the meta and rewind before starting speculative parsing. * Unlike WebKit, if there is neither an honored meta nor syntax resembling an XML declaration, detection from content takes place (as in Blink). * Unlike Blink, if there is neither an honored meta nor syntax resembling an XML declaration, the detection from content is not dependent of network buffer boundaries. * Unlike Blink, detection from content can trigger a reload at the end of the stream if the guess made at that point differs from the first guess. (See below for the definition of the input to the first guess.) Differences from the old spec and Gecko previously: * Meta inside script and RCDATA elements is no longer honored. * Late meta is now ignored and no longer triggers a reload. * Later meta counts as early enough meta: In addition to the previous meta within the first 1024 bytes, now a meta that started within the first 1024 bytes counts as early enough. Additionally, if by then there hasn't been a template start tag and head hasn't ended, meta occurring before the earlier of the end of the head or a template start tag counts as early enough. * Meta now counts as not-late even if the encoding label has numeric character reference escapes. * Syntax resembling an XML declaration longer than a kilobyte is honored if there is no honored meta. * If there is neither an honored meta nor syntax resembling an XML declaration, the initial chardetng scan is potentially longer than before: the first 1024 bytes, the token spanning the 1024-byte boundary if there is such a token, and, if by then head hasn't ended and there hasn't been a template start tag until the end of the template start tag or the end of the token that causes head to end, ever comes first. However, if the token implying the end of the head is a text token, bytes only to the end of the previous non-text token is considered. (This definition avoids depending on network buffer boundaries.) * XML View Source now uses the code for syntax resembling an XML declaration instead of expat for extracting the internal encoding label. Reftest are added as both WPT and Gecko reftests in order to test both http: and file: URL scenarios. The Gecko tests retain the WPT <link> tags in order to use the exact same bytes. An encoding declaration has been added to a number of old tests that didn't intend to test the new speculation behavior especially in the context of https://bugzilla.mozilla.org/show_bug.cgi?id=1727750 . Differential Revision: https://phabricator.services.mozilla.com/D125808
2021-12-08 14:34:20 +03:00
mIsError(false),
mEncoding(nullptr) {
MOZ_COUNT_CTOR(nsHtml5SpeculativeLoad);
new (&mCharsetOrSrcset) nsString;
}
nsHtml5SpeculativeLoad::~nsHtml5SpeculativeLoad() {
MOZ_COUNT_DTOR(nsHtml5SpeculativeLoad);
NS_ASSERTION(mOpCode != eSpeculativeLoadUninitialized,
"Uninitialized speculative load.");
Bug 1701828 - meta charset rewrite. r=smaug Implements https://github.com/whatwg/html/issues/6962 . Improves performance when <meta charset> occurs in head but after the first kilobyte and aligns behavior better with WebKit and Blink. The main change is to avoid reloads when meta appears within head but after the first kilobyte. Prior to this change, Gecko reloaded in that case (in compliance with the spec!) even though WebKit and Blink did not. Differences from WebKit and Blink: * WebKit and Blink honor <meta charset> in <noscript>. This implementation does not. * WebKit and Blink look for meta as if the tree builder was unaware of foreign content. This implementation is foreign content-aware. This makes a difference for CDATA sections that contain a > before the meta as well as style and script elements within foreign content. This could happen if the CDATA section that has mysteriously been introduced around a what looks like a meta tag also contains another prior tag-looking run of text. * This implementation processes rel=preload and speculative loads that are seen before <meta charset> has been seen. WebKit and Blink instead first look for the meta and rewind before starting speculative parsing. * Unlike WebKit, if there is neither an honored meta nor syntax resembling an XML declaration, detection from content takes place (as in Blink). * Unlike Blink, if there is neither an honored meta nor syntax resembling an XML declaration, the detection from content is not dependent of network buffer boundaries. * Unlike Blink, detection from content can trigger a reload at the end of the stream if the guess made at that point differs from the first guess. (See below for the definition of the input to the first guess.) Differences from the old spec and Gecko previously: * Meta inside script and RCDATA elements is no longer honored. * Late meta is now ignored and no longer triggers a reload. * Later meta counts as early enough meta: In addition to the previous meta within the first 1024 bytes, now a meta that started within the first 1024 bytes counts as early enough. Additionally, if by then there hasn't been a template start tag and head hasn't ended, meta occurring before the earlier of the end of the head or a template start tag counts as early enough. * Meta now counts as not-late even if the encoding label has numeric character reference escapes. * Syntax resembling an XML declaration longer than a kilobyte is honored if there is no honored meta. * If there is neither an honored meta nor syntax resembling an XML declaration, the initial chardetng scan is potentially longer than before: the first 1024 bytes, the token spanning the 1024-byte boundary if there is such a token, and, if by then head hasn't ended and there hasn't been a template start tag until the end of the template start tag or the end of the token that causes head to end, ever comes first. However, if the token implying the end of the head is a text token, bytes only to the end of the previous non-text token is considered. (This definition avoids depending on network buffer boundaries.) * XML View Source now uses the code for syntax resembling an XML declaration instead of expat for extracting the internal encoding label. Reftest are added as both WPT and Gecko reftests in order to test both http: and file: URL scenarios. The Gecko tests retain the WPT <link> tags in order to use the exact same bytes. An encoding declaration has been added to a number of old tests that didn't intend to test the new speculation behavior especially in the context of https://bugzilla.mozilla.org/show_bug.cgi?id=1727750 . Differential Revision: https://phabricator.services.mozilla.com/D125808
2021-12-08 14:34:20 +03:00
if (!(mOpCode == eSpeculativeLoadSetDocumentCharset ||
mOpCode == eSpeculativeLoadMaybeComplainAboutCharset)) {
mCharsetOrSrcset.~nsString();
}
}
void nsHtml5SpeculativeLoad::Perform(nsHtml5TreeOpExecutor* aExecutor) {
switch (mOpCode) {
case eSpeculativeLoadBase:
aExecutor->SetSpeculationBase(mUrlOrSizes);
break;
case eSpeculativeLoadCSP:
aExecutor->AddSpeculationCSP(
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity);
break;
case eSpeculativeLoadMetaReferrer:
aExecutor->UpdateReferrerInfoFromMeta(mReferrerPolicyOrIntegrity);
break;
case eSpeculativeLoadImage:
aExecutor->PreloadImage(
mUrlOrSizes, mCrossOrigin, mMedia, mCharsetOrSrcset,
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity,
mReferrerPolicyOrIntegrity, mIsLinkPreload, mInitTimestamp);
break;
case eSpeculativeLoadOpenPicture:
aExecutor->PreloadOpenPicture();
break;
case eSpeculativeLoadEndPicture:
aExecutor->PreloadEndPicture();
break;
case eSpeculativeLoadPictureSource:
aExecutor->PreloadPictureSource(
mCharsetOrSrcset, mUrlOrSizes,
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity,
mMedia);
break;
case eSpeculativeLoadScript:
aExecutor->PreloadScript(
mUrlOrSizes, mCharsetOrSrcset,
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity,
mCrossOrigin, mMedia, mReferrerPolicyOrIntegrity,
mScriptReferrerPolicy, false, mIsAsync, mIsDefer, false,
mIsLinkPreload);
break;
case eSpeculativeLoadScriptFromHead:
aExecutor->PreloadScript(
mUrlOrSizes, mCharsetOrSrcset,
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity,
mCrossOrigin, mMedia, mReferrerPolicyOrIntegrity,
mScriptReferrerPolicy, true, mIsAsync, mIsDefer, false,
mIsLinkPreload);
break;
case eSpeculativeLoadNoModuleScript:
aExecutor->PreloadScript(
mUrlOrSizes, mCharsetOrSrcset,
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity,
mCrossOrigin, mMedia, mReferrerPolicyOrIntegrity,
mScriptReferrerPolicy, false, mIsAsync, mIsDefer, true,
mIsLinkPreload);
break;
case eSpeculativeLoadNoModuleScriptFromHead:
aExecutor->PreloadScript(
mUrlOrSizes, mCharsetOrSrcset,
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity,
mCrossOrigin, mMedia, mReferrerPolicyOrIntegrity,
mScriptReferrerPolicy, true, mIsAsync, mIsDefer, true,
mIsLinkPreload);
break;
case eSpeculativeLoadStyle:
aExecutor->PreloadStyle(
mUrlOrSizes, mCharsetOrSrcset, mCrossOrigin, mMedia,
mReferrerPolicyOrIntegrity,
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity,
mIsLinkPreload);
break;
case eSpeculativeLoadManifest:
// TODO: remove this
break;
case eSpeculativeLoadSetDocumentCharset: {
Bug 1701828 - meta charset rewrite. r=smaug Implements https://github.com/whatwg/html/issues/6962 . Improves performance when <meta charset> occurs in head but after the first kilobyte and aligns behavior better with WebKit and Blink. The main change is to avoid reloads when meta appears within head but after the first kilobyte. Prior to this change, Gecko reloaded in that case (in compliance with the spec!) even though WebKit and Blink did not. Differences from WebKit and Blink: * WebKit and Blink honor <meta charset> in <noscript>. This implementation does not. * WebKit and Blink look for meta as if the tree builder was unaware of foreign content. This implementation is foreign content-aware. This makes a difference for CDATA sections that contain a > before the meta as well as style and script elements within foreign content. This could happen if the CDATA section that has mysteriously been introduced around a what looks like a meta tag also contains another prior tag-looking run of text. * This implementation processes rel=preload and speculative loads that are seen before <meta charset> has been seen. WebKit and Blink instead first look for the meta and rewind before starting speculative parsing. * Unlike WebKit, if there is neither an honored meta nor syntax resembling an XML declaration, detection from content takes place (as in Blink). * Unlike Blink, if there is neither an honored meta nor syntax resembling an XML declaration, the detection from content is not dependent of network buffer boundaries. * Unlike Blink, detection from content can trigger a reload at the end of the stream if the guess made at that point differs from the first guess. (See below for the definition of the input to the first guess.) Differences from the old spec and Gecko previously: * Meta inside script and RCDATA elements is no longer honored. * Late meta is now ignored and no longer triggers a reload. * Later meta counts as early enough meta: In addition to the previous meta within the first 1024 bytes, now a meta that started within the first 1024 bytes counts as early enough. Additionally, if by then there hasn't been a template start tag and head hasn't ended, meta occurring before the earlier of the end of the head or a template start tag counts as early enough. * Meta now counts as not-late even if the encoding label has numeric character reference escapes. * Syntax resembling an XML declaration longer than a kilobyte is honored if there is no honored meta. * If there is neither an honored meta nor syntax resembling an XML declaration, the initial chardetng scan is potentially longer than before: the first 1024 bytes, the token spanning the 1024-byte boundary if there is such a token, and, if by then head hasn't ended and there hasn't been a template start tag until the end of the template start tag or the end of the token that causes head to end, ever comes first. However, if the token implying the end of the head is a text token, bytes only to the end of the previous non-text token is considered. (This definition avoids depending on network buffer boundaries.) * XML View Source now uses the code for syntax resembling an XML declaration instead of expat for extracting the internal encoding label. Reftest are added as both WPT and Gecko reftests in order to test both http: and file: URL scenarios. The Gecko tests retain the WPT <link> tags in order to use the exact same bytes. An encoding declaration has been added to a number of old tests that didn't intend to test the new speculation behavior especially in the context of https://bugzilla.mozilla.org/show_bug.cgi?id=1727750 . Differential Revision: https://phabricator.services.mozilla.com/D125808
2021-12-08 14:34:20 +03:00
MOZ_ASSERT(mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity
.Length() == 1,
"Unexpected charset source string");
nsCharsetSource enumSource =
(nsCharsetSource)
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity
.First();
aExecutor->SetDocumentCharsetAndSource(WrapNotNull(mEncoding),
enumSource);
if (mCommitEncodingSpeculation) {
aExecutor->CommitToInternalEncoding();
}
} break;
case eSpeculativeLoadSetDocumentMode: {
NS_ASSERTION(mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity
.Length() == 1,
"Unexpected document mode string");
nsHtml5DocumentMode mode =
(nsHtml5DocumentMode)
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity
.First();
aExecutor->SetDocumentMode(mode);
} break;
case eSpeculativeLoadPreconnect:
aExecutor->Preconnect(mUrlOrSizes, mCrossOrigin);
break;
case eSpeculativeLoadFont:
aExecutor->PreloadFont(mUrlOrSizes, mCrossOrigin, mMedia,
mReferrerPolicyOrIntegrity);
break;
case eSpeculativeLoadFetch:
aExecutor->PreloadFetch(mUrlOrSizes, mCrossOrigin, mMedia,
mReferrerPolicyOrIntegrity);
break;
Bug 1701828 - meta charset rewrite. r=smaug Implements https://github.com/whatwg/html/issues/6962 . Improves performance when <meta charset> occurs in head but after the first kilobyte and aligns behavior better with WebKit and Blink. The main change is to avoid reloads when meta appears within head but after the first kilobyte. Prior to this change, Gecko reloaded in that case (in compliance with the spec!) even though WebKit and Blink did not. Differences from WebKit and Blink: * WebKit and Blink honor <meta charset> in <noscript>. This implementation does not. * WebKit and Blink look for meta as if the tree builder was unaware of foreign content. This implementation is foreign content-aware. This makes a difference for CDATA sections that contain a > before the meta as well as style and script elements within foreign content. This could happen if the CDATA section that has mysteriously been introduced around a what looks like a meta tag also contains another prior tag-looking run of text. * This implementation processes rel=preload and speculative loads that are seen before <meta charset> has been seen. WebKit and Blink instead first look for the meta and rewind before starting speculative parsing. * Unlike WebKit, if there is neither an honored meta nor syntax resembling an XML declaration, detection from content takes place (as in Blink). * Unlike Blink, if there is neither an honored meta nor syntax resembling an XML declaration, the detection from content is not dependent of network buffer boundaries. * Unlike Blink, detection from content can trigger a reload at the end of the stream if the guess made at that point differs from the first guess. (See below for the definition of the input to the first guess.) Differences from the old spec and Gecko previously: * Meta inside script and RCDATA elements is no longer honored. * Late meta is now ignored and no longer triggers a reload. * Later meta counts as early enough meta: In addition to the previous meta within the first 1024 bytes, now a meta that started within the first 1024 bytes counts as early enough. Additionally, if by then there hasn't been a template start tag and head hasn't ended, meta occurring before the earlier of the end of the head or a template start tag counts as early enough. * Meta now counts as not-late even if the encoding label has numeric character reference escapes. * Syntax resembling an XML declaration longer than a kilobyte is honored if there is no honored meta. * If there is neither an honored meta nor syntax resembling an XML declaration, the initial chardetng scan is potentially longer than before: the first 1024 bytes, the token spanning the 1024-byte boundary if there is such a token, and, if by then head hasn't ended and there hasn't been a template start tag until the end of the template start tag or the end of the token that causes head to end, ever comes first. However, if the token implying the end of the head is a text token, bytes only to the end of the previous non-text token is considered. (This definition avoids depending on network buffer boundaries.) * XML View Source now uses the code for syntax resembling an XML declaration instead of expat for extracting the internal encoding label. Reftest are added as both WPT and Gecko reftests in order to test both http: and file: URL scenarios. The Gecko tests retain the WPT <link> tags in order to use the exact same bytes. An encoding declaration has been added to a number of old tests that didn't intend to test the new speculation behavior especially in the context of https://bugzilla.mozilla.org/show_bug.cgi?id=1727750 . Differential Revision: https://phabricator.services.mozilla.com/D125808
2021-12-08 14:34:20 +03:00
case eSpeculativeLoadMaybeComplainAboutCharset: {
MOZ_ASSERT(mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity
.Length() == 2,
"Unexpected line number string");
uint32_t high =
(uint32_t)
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity
.CharAt(0);
uint32_t low =
(uint32_t)
mTypeOrCharsetSourceOrDocumentModeOrMetaCSPOrSizesOrIntegrity
.CharAt(1);
uint32_t line = (high << 16) | low;
aExecutor->MaybeComplainAboutCharset(mMsgId, mIsError, (int32_t)line);
} break;
default:
MOZ_ASSERT_UNREACHABLE("Bogus speculative load.");
break;
}
}