1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317
|
/* -*- Mode: C++; tab-width: 2; 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/. */
/**
* MODULE NOTES:
*
* This class does two primary jobs:
* 1) It iterates the tokens provided during the
* tokenization process, identifing where elements
* begin and end (doing validation and normalization).
* 2) It controls and coordinates with an instance of
* the IContentSink interface, to coordinate the
* the production of the content model.
*
* The basic operation of this class assumes that an HTML
* document is non-normalized. Therefore, we don't process
* the document in a normalized way. Don't bother to look
* for methods like: doHead() or doBody().
*
* Instead, in order to be backward compatible, we must
* scan the set of tokens and perform this basic set of
* operations:
* 1) Determine the token type (easy, since the tokens know)
* 2) Determine the appropriate section of the HTML document
* each token belongs in (HTML,HEAD,BODY,FRAMESET).
* 3) Insert content into our document (via the sink) into
* the correct section.
* 4) In the case of tags that belong in the BODY, we must
* ensure that our underlying document state reflects
* the appropriate context for our tag.
*
* For example,if we see a <TR>, we must ensure our
* document contains a table into which the row can
* be placed. This may result in "implicit containers"
* created to ensure a well-formed document.
*
*/
#ifndef NS_PARSER__
#define NS_PARSER__
#include "nsIParser.h"
#include "nsDeque.h"
#include "CParserContext.h"
#include "nsHTMLTags.h"
#include "nsIContentSink.h"
#include "nsCOMArray.h"
#include "nsCycleCollectionParticipant.h"
#include "nsWeakReference.h"
#include "mozilla/Maybe.h"
#include "mozilla/UniquePtr.h"
class nsIDTD;
class nsIRunnable;
#ifdef _MSC_VER
# pragma warning(disable : 4275)
#endif
class nsParser final : public nsIParser,
public nsIStreamListener,
public nsSupportsWeakReference {
/**
* Destructor
* @update gess5/11/98
*/
virtual ~nsParser();
public:
/**
* Called on module init
*/
static nsresult Init();
/**
* Called on module shutdown
*/
static void Shutdown();
NS_DECL_CYCLE_COLLECTING_ISUPPORTS
NS_DECL_CYCLE_COLLECTION_CLASS_AMBIGUOUS(nsParser, nsIParser)
/**
* default constructor
* @update gess5/11/98
*/
nsParser();
/**
* Select given content sink into parser for parser output
* @update gess5/11/98
* @param aSink is the new sink to be used by parser
* @return old sink, or nullptr
*/
NS_IMETHOD_(void) SetContentSink(nsIContentSink* aSink) override;
/**
* retrive the sink set into the parser
* @update gess5/11/98
* @param aSink is the new sink to be used by parser
* @return old sink, or nullptr
*/
NS_IMETHOD_(nsIContentSink*) GetContentSink(void) override;
/**
* Call this method once you've created a parser, and want to instruct it
* about the command which caused the parser to be constructed. For example,
* this allows us to select a DTD which can do, say, view-source.
*
* @update gess 3/25/98
* @param aCommand -- ptrs to string that contains command
* @return nada
*/
NS_IMETHOD_(void) GetCommand(nsCString& aCommand) override;
NS_IMETHOD_(void) SetCommand(const char* aCommand) override;
NS_IMETHOD_(void) SetCommand(eParserCommands aParserCommand) override;
/**
* Call this method once you've created a parser, and want to instruct it
* about what charset to load
*
* @update ftang 4/23/99
* @param aCharset- the charset of a document
* @param aCharsetSource- the source of the charset
* @param aChannelHadCharset- ignored
* @return nada
*/
virtual void SetDocumentCharset(NotNull<const Encoding*> aCharset,
int32_t aSource,
bool aForceAutoDetection) override;
NotNull<const Encoding*> GetDocumentCharset(int32_t& aSource) {
aSource = mCharsetSource;
return mCharset;
}
/**
* Cause parser to parse input from given URL
*/
NS_IMETHOD Parse(nsIURI* aURL) override;
/**
* This method gets called when you want to parse a fragment of XML surrounded
* by the context |aTagStack|. It requires that the parser have been given a
* fragment content sink.
*
* @param aSourceBuffer The XML that hasn't been parsed yet.
* @param aTagStack The context of the source buffer.
*/
nsresult ParseFragment(const nsAString& aSourceBuffer,
nsTArray<nsString>& aTagStack);
NS_IMETHOD ContinueInterruptedParsing() override;
NS_IMETHOD_(void) BlockParser() override;
NS_IMETHOD_(void) UnblockParser() override;
NS_IMETHOD_(void) ContinueInterruptedParsingAsync() override;
NS_IMETHOD Terminate(void) override;
/**
* Call this to query whether the parser is enabled or not.
*
* @update vidur 4/12/99
* @return current state
*/
NS_IMETHOD_(bool) IsParserEnabled() override;
/**
* Call this to query whether the parser thinks it's done with parsing.
*
* @update rickg 5/12/01
* @return complete state
*/
NS_IMETHOD_(bool) IsComplete() override;
/**
* This method gets called (automatically) during incremental parsing
* @update gess5/11/98
* @return TRUE if all went well, otherwise FALSE
*/
virtual nsresult ResumeParse(bool allowIteration = true,
bool aIsFinalChunk = false,
bool aCanInterrupt = true);
//*********************************************
// These methods are callback methods used by
// net lib to let us know about our inputstream.
//*********************************************
// nsIRequestObserver methods:
NS_DECL_NSIREQUESTOBSERVER
// nsIStreamListener methods:
NS_DECL_NSISTREAMLISTENER
/**
* Get the nsIStreamListener for this parser
*/
virtual nsIStreamListener* GetStreamListener() override;
void SetSinkCharset(NotNull<const Encoding*> aCharset);
/**
* Return true.
*/
virtual bool IsInsertionPointDefined() override;
/**
* No-op.
*/
void IncrementScriptNestingLevel() final;
/**
* No-op.
*/
void DecrementScriptNestingLevel() final;
bool HasNonzeroScriptNestingLevel() const final;
/**
* Always false.
*/
virtual bool IsScriptCreated() override;
/**
* This is called when the final chunk has been
* passed to the parser and the content sink has
* interrupted token processing. It schedules
* a ParserContinue PL_Event which will ask the parser
* to HandleParserContinueEvent when it is handled.
* @update kmcclusk6/1/2001
*/
nsresult PostContinueEvent();
/**
* Fired when the continue parse event is triggered.
* @update kmcclusk 5/18/98
*/
void HandleParserContinueEvent(class nsParserContinueEvent*);
void Reset() {
MOZ_ASSERT(!mIsAboutBlank,
"Only the XML fragment parsing case is supposed to call this.");
Cleanup();
mUnusedInput.Truncate();
Initialize();
}
bool IsScriptExecuting() { return mSink && mSink->IsScriptExecuting(); }
void ContinueParsingDocumentAfterCurrentScript() {
if (mSink) {
mSink->ContinueParsingDocumentAfterCurrentScript();
}
}
// Returns Nothing() if we haven't determined yet what the parser is being
// used for. Else returns whether this parser is used for parsing XML.
mozilla::Maybe<bool> IsForParsingXML() {
if (!mParserContext || mParserContext->mDTDMode == eDTDMode_autodetect) {
return mozilla::Nothing();
}
return mozilla::Some(mParserContext->mDocType == eXML);
}
protected:
void Initialize();
void Cleanup();
/**
*
* @update gess5/18/98
* @param
* @return
*/
nsresult WillBuildModel();
/**
* Called when parsing is done.
*/
void DidBuildModel();
private:
/**
* Pushes XML fragment parsing data to expat without an input stream.
*/
nsresult Parse(const nsAString& aSourceBuffer, bool aLastCall);
protected:
//*********************************************
// And now, some data members...
//*********************************************
mozilla::UniquePtr<CParserContext> mParserContext;
nsCOMPtr<nsIDTD> mDTD;
nsCOMPtr<nsIContentSink> mSink;
nsIRunnable* mContinueEvent; // weak ref
eParserCommands mCommand;
nsresult mInternalState;
nsresult mStreamStatus;
int32_t mCharsetSource;
uint16_t mFlags;
uint32_t mBlocked;
nsString mUnusedInput;
NotNull<const Encoding*> mCharset;
nsCString mCommandStr;
bool mProcessingNetworkData;
bool mOnStopPending;
bool mIsAboutBlank;
};
#endif
|