Home | History | Annotate | Download | only in vtt 
      1 /*
      2  * Copyright (C) 2011 Google Inc.  All rights reserved.
      3  *
      4  * Redistribution and use in source and binary forms, with or without
      5  * modification, are permitted provided that the following conditions are
      6  * met:
      7  *
      8  *     * Redistributions of source code must retain the above copyright
      9  * notice, this list of conditions and the following disclaimer.
     10  *     * Redistributions in binary form must reproduce the above
     11  * copyright notice, this list of conditions and the following disclaimer
     12  * in the documentation and/or other materials provided with the
     13  * distribution.
     14  *     * Neither the name of Google Inc. nor the names of its
     15  * contributors may be used to endorse or promote products derived from
     16  * this software without specific prior written permission.
     17  *
     18  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
     19  * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
     20  * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
     21  * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
     22  * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     23  * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     24  * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
     25  * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
     26  * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
     27  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
     28  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
     29  */
     30 
     31 #ifndef VTTParser_h
     32 #define VTTParser_h
     33 
     34 #include "HTMLNames.h"
     35 #include "RuntimeEnabledFeatures.h"
     36 #include "core/dom/DocumentFragment.h"
     37 #include "core/fetch/TextResourceDecoder.h"
     38 #include "core/html/track/vtt/BufferedLineReader.h"
     39 #include "core/html/track/vtt/VTTCue.h"
     40 #include "core/html/track/vtt/VTTRegion.h"
     41 #include "core/html/track/vtt/VTTTokenizer.h"
     42 #include "wtf/PassOwnPtr.h"
     43 #include "wtf/text/StringBuilder.h"
     44 
     45 namespace WebCore {
     46 
     47 using namespace HTMLNames;
     48 
     49 class Document;
     50 
     51 class VTTParserClient {
     52 public:
     53     virtual ~VTTParserClient() { }
     54 
     55     virtual void newCuesParsed() = 0;
     56     virtual void newRegionsParsed() = 0;
     57     virtual void fileFailedToParse() = 0;
     58 };
     59 
     60 class VTTParser FINAL {
     61 public:
     62     enum ParseState {
     63         Initial,
     64         Header,
     65         Id,
     66         TimingsAndSettings,
     67         CueText,
     68         BadCue
     69     };
     70 
     71     static PassOwnPtr<VTTParser> create(VTTParserClient* client, Document& document)
     72     {
     73         return adoptPtr(new VTTParser(client, document));
     74     }
     75 
     76     static inline bool isRecognizedTag(const AtomicString& tagName)
     77     {
     78         return tagName == iTag
     79             || tagName == bTag
     80             || tagName == uTag
     81             || tagName == rubyTag
     82             || tagName == rtTag;
     83     }
     84 
     85     static inline bool isASpace(char c)
     86     {
     87         // WebVTT space characters are U+0020 SPACE, U+0009 CHARACTER TABULATION (tab), U+000A LINE FEED (LF), U+000C FORM FEED (FF), and U+000D CARRIAGE RETURN    (CR).
     88         return c == ' ' || c == '\t' || c == '\n' || c == '\f' || c == '\r';
     89     }
     90     static inline bool isValidSettingDelimiter(char c)
     91     {
     92         // ... a WebVTT cue consists of zero or more of the following components, in any order, separated from each other by one or more
     93         // U+0020 SPACE characters or U+0009 CHARACTER TABULATION (tab) characters.
     94         return c == ' ' || c == '\t';
     95     }
     96     static unsigned collectDigitsToInt(const String& input, unsigned* position, int& number);
     97     static String collectWord(const String&, unsigned*);
     98     static bool collectTimeStamp(const String&, unsigned*, double& timeStamp);
     99 
    100     // Useful functions for parsing percentage settings.
    101     static bool parseFloatPercentageValue(const String&, float&);
    102     static bool parseFloatPercentageValuePair(const String&, char, FloatPoint&);
    103 
    104     // Create the DocumentFragment representation of the WebVTT cue text.
    105     static PassRefPtr<DocumentFragment> createDocumentFragmentFromCueText(Document&, const String&);
    106 
    107     // Input data to the parser to parse.
    108     void parseBytes(const char* data, unsigned length);
    109     void flush();
    110 
    111     // Transfers ownership of last parsed cues to caller.
    112     void getNewCues(Vector<RefPtr<VTTCue> >&);
    113     void getNewRegions(Vector<RefPtr<VTTRegion> >&);
    114 
    115 private:
    116     VTTParser(VTTParserClient*, Document&);
    117 
    118     Document* m_document;
    119     ParseState m_state;
    120 
    121     void parse();
    122     void flushPendingCue();
    123     bool hasRequiredFileIdentifier(const String& line);
    124     ParseState collectCueId(const String&);
    125     ParseState collectTimingsAndSettings(const String&);
    126     ParseState collectCueText(const String&);
    127     ParseState recoverCue(const String&);
    128     ParseState ignoreBadCue(const String&);
    129 
    130     void createNewCue();
    131     void resetCueValues();
    132 
    133     void collectMetadataHeader(const String&);
    134     void createNewRegion(const String& headerValue);
    135 
    136     static void skipWhiteSpace(const String&, unsigned*);
    137 
    138     BufferedLineReader m_lineReader;
    139     OwnPtr<TextResourceDecoder> m_decoder;
    140     String m_currentId;
    141     double m_currentStartTime;
    142     double m_currentEndTime;
    143     StringBuilder m_currentContent;
    144     String m_currentSettings;
    145 
    146     VTTParserClient* m_client;
    147 
    148     Vector<RefPtr<VTTCue> > m_cuelist;
    149 
    150     Vector<RefPtr<VTTRegion> > m_regionList;
    151 };
    152 
    153 } // namespace WebCore
    154 
    155 #endif
    156