Android教程網 >> Android技術 >> 關於Android編程 >> Android媒體掃描詳細解析之二(MediaScanner & MediaProvider)

Android媒體掃描詳細解析之二(MediaScanner & MediaProvider)

編輯：關於Android編程

上篇blog說到了經過對文件夾進行掃描如果後綴符合系統設定的一些格式，那麼就會進行文件內容掃描下面我們緊接著STEP 14中的

[cpp]
status_t StagefrightMediaScanner::processFile(
        const char *path, const char *mimeType,
        MediaScannerClient &client) {
    LOGV("processFile '%s'.", path);

    client.setLocale(locale());
    client.beginFile();

    const char *extension = strrchr(path, '.');

    if (!extension) {
        return UNKNOWN_ERROR;
    }

    if (!FileHasAcceptableExtension(extension)) {
        client.endFile();

        return UNKNOWN_ERROR;
    }

    if (!strcasecmp(extension, ".mid")
            || !strcasecmp(extension, ".smf")
            || !strcasecmp(extension, ".imy")
            || !strcasecmp(extension, ".midi")
            || !strcasecmp(extension, ".xmf")
            || !strcasecmp(extension, ".rtttl")
            || !strcasecmp(extension, ".rtx")
            || !strcasecmp(extension, ".ota")) {
        return HandleMIDI(path, &client);
    }

    if (mRetriever->setDataSource(path) == OK) {
        const char *value;
        if ((value = mRetriever->extractMetadata(
                        METADATA_KEY_MIMETYPE)) != NULL) {
            client.setMimeType(value);
        }

        struct KeyMap {
            const char *tag;
            int key;
        };
        static const KeyMap kKeyMap[] = {
            { "tracknumber", METADATA_KEY_CD_TRACK_NUMBER },
            { "discnumber", METADATA_KEY_DISC_NUMBER },
            { "album", METADATA_KEY_ALBUM },
            { "artist", METADATA_KEY_ARTIST },
            { "albumartist", METADATA_KEY_ALBUMARTIST },
            { "composer", METADATA_KEY_COMPOSER },
            { "genre", METADATA_KEY_GENRE },
            { "title", METADATA_KEY_TITLE },
            { "year", METADATA_KEY_YEAR },
            { "duration", METADATA_KEY_DURATION },
            { "writer", METADATA_KEY_WRITER },
            { "compilation", METADATA_KEY_COMPILATION },
        };
        static const size_t kNumEntries = sizeof(kKeyMap) / sizeof(kKeyMap[0]);

        for (size_t i = 0; i < kNumEntries; ++i) {
            const char *value;
            if ((value = mRetriever->extractMetadata(kKeyMap[i].key)) != NULL) {
                client.addStringTag(kKeyMap[i].tag, value);
            }
        }
    }

    client.endFile();

    return OK;
}

status_t StagefrightMediaScanner::processFile(
        const char *path, const char *mimeType,
        MediaScannerClient &client) {
    LOGV("processFile '%s'.", path);

client.setLocale(locale());
client.beginFile();

const char *extension = strrchr(path, '.');

    if (!extension) {
        return UNKNOWN_ERROR;
    }

if (!FileHasAcceptableExtension(extension)) {
client.endFile();

return UNKNOWN_ERROR;
}

    if (!strcasecmp(extension, ".mid")
            || !strcasecmp(extension, ".smf")
            || !strcasecmp(extension, ".imy")
            || !strcasecmp(extension, ".midi")
            || !strcasecmp(extension, ".xmf")
            || !strcasecmp(extension, ".rtttl")
            || !strcasecmp(extension, ".rtx")
            || !strcasecmp(extension, ".ota")) {
        return HandleMIDI(path, &client);
    }

    if (mRetriever->setDataSource(path) == OK) {
        const char *value;
        if ((value = mRetriever->extractMetadata(
                        METADATA_KEY_MIMETYPE)) != NULL) {
            client.setMimeType(value);
        }

        struct KeyMap {
            const char *tag;
            int key;
        };
        static const KeyMap kKeyMap[] = {
            { "tracknumber", METADATA_KEY_CD_TRACK_NUMBER },
            { "discnumber", METADATA_KEY_DISC_NUMBER },
            { "album", METADATA_KEY_ALBUM },
            { "artist", METADATA_KEY_ARTIST },
            { "albumartist", METADATA_KEY_ALBUMARTIST },
            { "composer", METADATA_KEY_COMPOSER },
            { "genre", METADATA_KEY_GENRE },
            { "title", METADATA_KEY_TITLE },
            { "year", METADATA_KEY_YEAR },
            { "duration", METADATA_KEY_DURATION },
            { "writer", METADATA_KEY_WRITER },
            { "compilation", METADATA_KEY_COMPILATION },
        };
        static const size_t kNumEntries = sizeof(kKeyMap) / sizeof(kKeyMap[0]);

        for (size_t i = 0; i < kNumEntries; ++i) {
            const char *value;
            if ((value = mRetriever->extractMetadata(kKeyMap[i].key)) != NULL) {
                client.addStringTag(kKeyMap[i].tag, value);
            }
        }
    }

client.endFile();

return OK;
}來進行代碼跟進說明，首先StagefrightMediaScanner是Stagefright的一部分，它負責媒體掃描工作，而stagefright是整個android系統media處理的框架，包括音視頻的播放。

mRetriever->setDataSource(path)，mRetriever是在StagefrightMediaScanner的構造函數中創建的

[cpp]
StagefrightMediaScanner::StagefrightMediaScanner()
: mRetriever(new MediaMetadataRetriever) {
}

StagefrightMediaScanner::StagefrightMediaScanner()
: mRetriever(new MediaMetadataRetriever) {
}STEP15

[cpp]
status_t MediaMetadataRetriever::setDataSource(const char* srcUrl)
{
    LOGV("setDataSource");
    Mutex::Autolock _l(mLock);
    if (mRetriever == 0) {
        LOGE("retriever is not initialized");
        return INVALID_OPERATION;
    }
    if (srcUrl == NULL) {
        LOGE("data source is a null pointer");
        return UNKNOWN_ERROR;
    }
    LOGV("data source (%s)", srcUrl);
    return mRetriever->setDataSource(srcUrl);
}

status_t MediaMetadataRetriever::setDataSource(const char* srcUrl)
{
    LOGV("setDataSource");
    Mutex::Autolock _l(mLock);
    if (mRetriever == 0) {
        LOGE("retriever is not initialized");
        return INVALID_OPERATION;
    }
    if (srcUrl == NULL) {
        LOGE("data source is a null pointer");
        return UNKNOWN_ERROR;
    }
    LOGV("data source (%s)", srcUrl);
    return mRetriever->setDataSource(srcUrl);
}
再看下MediaMetadataRetriever裡面的mRetriever也是在MediaMetadataRetriever的構造函數中創建的。並且是通過MediaPlayerService來創建，實際就是創建的StagefrightMetadataRetriever對象。緊接著看StagefrightMetadataRetriever的setDataSource函數

STEP15

[cpp]
status_t StagefrightMetadataRetriever::setDataSource(const char *uri) {
    LOGV("setDataSource(%s)", uri);

    mParsedMetaData = false;
    mMetaData.clear();
    delete mAlbumArt;
    mAlbumArt = NULL;

    mSource = DataSource::CreateFromURI(uri);

    if (mSource == NULL) {
        return UNKNOWN_ERROR;
    }

    mExtractor = MediaExtractor::Create(mSource);

    if (mExtractor == NULL) {
        mSource.clear();

        return UNKNOWN_ERROR;
    }

    return OK;
}

status_t StagefrightMetadataRetriever::setDataSource(const char *uri) {
LOGV("setDataSource(%s)", uri);

    mParsedMetaData = false;
    mMetaData.clear();
    delete mAlbumArt;
    mAlbumArt = NULL;

mSource = DataSource::CreateFromURI(uri);

    if (mSource == NULL) {
        return UNKNOWN_ERROR;
    }

mExtractor = MediaExtractor::Create(mSource);

if (mExtractor == NULL) {
mSource.clear();

return UNKNOWN_ERROR;
}

return OK;
}

有閱讀過stagefright源碼的同學可能看到這個地方就會感覺很熟悉，首先根據URI創建了一個DataSource DataSource::CreateFromURI(uri);DataSource我們實際可以將它理解為文件的源，它裡面會先把文件打開，然後對文件描述符進行讀取操作。

看源碼可以知道它會創建一個FileSource。然後根據這個DataSource創建一個MediaExtractor::Create(mSource); MediaExtractor就是文件解析器

STEP16

[cpp]
sp<MediaExtractor> MediaExtractor::Create(
        const sp<DataSource> &source, const char *mime) {
    sp<AMessage> meta;

    String8 tmp;
    if (mime == NULL) {
        float confidence;
        if (!source->sniff(&tmp, &confidence, &meta)) {
            LOGV("FAILED to autodetect media content.");

            return NULL;
        }

        mime = tmp.string();
        LOGV("Autodetected media content as '%s' with confidence %.2f",
             mime, confidence);
    }

    if (!strcasecmp(mime, MEDIA_MIMETYPE_CONTAINER_MPEG4)
            || !strcasecmp(mime, "audio/mp4")) {
        return new MPEG4Extractor(source);
    }
...
}
...
}

sp<MediaExtractor> MediaExtractor::Create(
const sp<DataSource> &source, const char *mime) {
sp<AMessage> meta;

    String8 tmp;
    if (mime == NULL) {
        float confidence;
        if (!source->sniff(&tmp, &confidence, &meta)) {
            LOGV("FAILED to autodetect media content.");

return NULL;
}

        mime = tmp.string();
        LOGV("Autodetected media content as '%s' with confidence %.2f",
             mime, confidence);
    }

    if (!strcasecmp(mime, MEDIA_MIMETYPE_CONTAINER_MPEG4)
            || !strcasecmp(mime, "audio/mp4")) {
        return new MPEG4Extractor(source);
    }
...
}
...
}這裡面有一個很關鍵的函數source->sniff(&tmp, &confidence, &meta)，字面上看就是嗅探的意思，非常形象，DataSource裡面有一個sniff函數

STEP 17

[cpp]
bool DataSource::sniff(
        String8 *mimeType, float *confidence, sp<AMessage> *meta) {
    *mimeType = "";
    *confidence = 0.0f;
    meta->clear();

    Mutex::Autolock autoLock(gSnifferMutex);
    for (List<SnifferFunc>::iterator it = gSniffers.begin();
         it != gSniffers.end(); ++it) {
        String8 newMimeType;
        float newConfidence;
        sp<AMessage> newMeta;
        if ((*it)(this, &newMimeType, &newConfidence, &newMeta)) {
            if (newConfidence > *confidence) {
                *mimeType = newMimeType;
                *confidence = newConfidence;
                *meta = newMeta;
            }
        }
    }

    return *confidence > 0.0;
}

bool DataSource::sniff(
        String8 *mimeType, float *confidence, sp<AMessage> *meta) {
    *mimeType = "";
    *confidence = 0.0f;
    meta->clear();

    Mutex::Autolock autoLock(gSnifferMutex);
    for (List<SnifferFunc>::iterator it = gSniffers.begin();
         it != gSniffers.end(); ++it) {
        String8 newMimeType;
        float newConfidence;
        sp<AMessage> newMeta;
        if ((*it)(this, &newMimeType, &newConfidence, &newMeta)) {
            if (newConfidence > *confidence) {
                *mimeType = newMimeType;
                *confidence = newConfidence;
                *meta = newMeta;
            }
        }
    }

return *confidence > 0.0;
}gSniffers是一個系統支持的一些媒體格式的嗅探器列表，函數的作用就是用這些嗅探器一個一個的試，並給出一個confidence 信任值，也就是說值越高，它就越可能是這種格式。而這些嗅探器是在StagefrightMetadataRetriever的構造函數中注冊的 DataSource::RegisterDefaultSniffers();

我們可以挑選其中的SniffMPEG4來看看，嗅探器都是在對應格式的文件解析器中，SniffMPEG4在MPEG4Extractor中。

[cpp]
bool SniffMPEG4(
        const sp<DataSource> &source, String8 *mimeType, float *confidence,
        sp<AMessage> *) {
    if (BetterSniffMPEG4(source, mimeType, confidence)) {
        return true;
    }

    if (LegacySniffMPEG4(source, mimeType, confidence)) {
        LOGW("Identified supported mpeg4 through LegacySniffMPEG4.");
        return true;
    }

    const char LegacyAtom[][8]={
        {"moov"},
        {"mvhd"},
        {"trak"},
     };
    uint8_t header[12];
    if (source->readAt(0, header, 12) != 12){
            return false;
    }
    for(int i=0; i<sizeof(LegacyAtom)/sizeof(LegacyAtom[0]);i++){
        if (!memcmp(LegacyAtom[i], &header[4], strlen(LegacyAtom[i]))) {
         *mimeType = MEDIA_MIMETYPE_CONTAINER_MPEG4;
            *confidence = 0.4f;
            return true;
        }
    }

    return false;
}

bool SniffMPEG4(
        const sp<DataSource> &source, String8 *mimeType, float *confidence,
        sp<AMessage> *) {
    if (BetterSniffMPEG4(source, mimeType, confidence)) {
        return true;
    }

    if (LegacySniffMPEG4(source, mimeType, confidence)) {
        LOGW("Identified supported mpeg4 through LegacySniffMPEG4.");
        return true;
    }

    const char LegacyAtom[][8]={
        {"moov"},
        {"mvhd"},
        {"trak"},
     };
    uint8_t header[12];
    if (source->readAt(0, header, 12) != 12){
            return false;
    }
    for(int i=0; i<sizeof(LegacyAtom)/sizeof(LegacyAtom[0]);i++){
        if (!memcmp(LegacyAtom[i], &header[4], strlen(LegacyAtom[i]))) {
      *mimeType = MEDIA_MIMETYPE_CONTAINER_MPEG4;
            *confidence = 0.4f;
            return true;
        }
    }

return false;
}
這裡面涉及到幾個函數BetterSniffMPEG4 LegacySniffMPEG4 這實際是一步一步來根據MEPG4的格式來試探這個文件是否符合MPEG4。

在這就不多講了，想看懂這兩個函數，你必須看MPEG4格式的標准文檔。

拿到打分後也就知道了media的format，然後就根據這個類型創建一個MediaExtractor。回到STEP14，mRetriever->setDataSource(path)所有動作已經完成，總結下就是根據android設備支持的媒體格式一個一個的試，然後得到一個和該文件最相符的格式。到此實際解析工作已經做完，下面一步是將得到的格式會送給java層，

[cpp]
if ((value = mRetriever->extractMetadata(
                        METADATA_KEY_MIMETYPE)) != NULL) {
            client.setMimeType(value);
        }

if ((value = mRetriever->extractMetadata(
                        METADATA_KEY_MIMETYPE)) != NULL) {
            client.setMimeType(value);
        }
就是完成這個動作。然後有一個kKeyMap，這些實際就是我們需要存儲於數據庫中的媒體信息，包括時長，專輯之類的東西。也是通過mRetriever->extractMetadata函數得到。

STEP18

[cpp]
const char *StagefrightMetadataRetriever::extractMetadata(int keyCode) {
    if (mExtractor == NULL) {
        return NULL;
    }

    if (!mParsedMetaData) {
        parseMetaData();

        mParsedMetaData = true;
    }

    ssize_t index = mMetaData.indexOfKey(keyCode);

    if (index < 0) {
        return NULL;
    }

    return strdup(mMetaData.valueAt(index).string());

const char *StagefrightMetadataRetriever::extractMetadata(int keyCode) {
    if (mExtractor == NULL) {
        return NULL;
    }

if (!mParsedMetaData) {
parseMetaData();

mParsedMetaData = true;
}

ssize_t index = mMetaData.indexOfKey(keyCode);

    if (index < 0) {
        return NULL;
    }

return strdup(mMetaData.valueAt(index).string());
首次調用肯定是進入parseMetaData，這個函數完成解析工作，將所有需要的媒體信息全部從文件中讀出來並保存到mMetaData這個鍵值對數組中。

具體解析工作也不說了，跟具體的格式相關。

下面最重要的一步就是將解析後得到的信息反饋給java層client.addStringTag(kKeyMap[i].tag, value);

STEP19

[cpp]
bool MediaScannerClient::addStringTag(const char* name, const char* value)
{
    if (mLocaleEncoding != kEncodingNone) {
        // don't bother caching strings that are all ASCII.
        // call handleStringTag directly instead.
        // check to see if value (which should be utf8) has any non-ASCII characters
        bool nonAscii = false;
        const char* chp = value;
        char ch;
        while ((ch = *chp++)) {
            if (ch & 0x80) {
                nonAscii = true;
                break;
            }
        }

        if (nonAscii) {
            // save the strings for later so they can be used for native encoding detection
            mNames->push_back(name);
            mValues->push_back(value);
            return true;
        }
        // else fall through
    }

    // autodetection is not necessary, so no need to cache the values
    // pass directly to the client instead
    return handleStringTag(name, value);
}

bool MediaScannerClient::addStringTag(const char* name, const char* value)
{
    if (mLocaleEncoding != kEncodingNone) {
        // don't bother caching strings that are all ASCII.
        // call handleStringTag directly instead.
        // check to see if value (which should be utf8) has any non-ASCII characters
        bool nonAscii = false;
        const char* chp = value;
        char ch;
        while ((ch = *chp++)) {
            if (ch & 0x80) {
                nonAscii = true;
                break;
            }
        }

        if (nonAscii) {
            // save the strings for later so they can be used for native encoding detection
            mNames->push_back(name);
            mValues->push_back(value);
            return true;
        }
        // else fall through
    }

    // autodetection is not necessary, so no need to cache the values
    // pass directly to the client instead
    return handleStringTag(name, value);
}
直接看handleStringTag根據上面的經驗，直接看java層的MyMediaScannerClient的handleStringTag函數

STEP 20

[java]

public void handleStringTag(String name, String value) {
            if (name.equalsIgnoreCase("title") || name.startsWith("title;")) {
                // Don't trim() here, to preserve the special \001 character
                // used to force sorting. The media provider will trim() before
                // inserting the title in to the database.
                mTitle = value;
            } else if (name.equalsIgnoreCase("artist") || name.startsWith("artist;")) {
                mArtist = value.trim();
            } else if (name.equalsIgnoreCase("albumartist") || name.startsWith("albumartist;")) {
                mAlbumArtist = value.trim();
            } else if (name.equalsIgnoreCase("album") || name.startsWith("album;")) {
                mAlbum = value.trim();
            } else if (name.equalsIgnoreCase("composer") || name.startsWith("composer;")) {
                mComposer = value.trim();
            } else if (name.equalsIgnoreCase("genre") || name.startsWith("genre;")) {
                // handle numeric genres, which PV sometimes encodes like "(20)"
                if (value.length() > 0) {
                    int genreCode = -1;
                    char ch = value.charAt(0);
                    if (ch == '(') {
                        genreCode = parseSubstring(value, 1, -1);
                    } else if (ch >= '0' && ch <= '9') {
                        genreCode = parseSubstring(value, 0, -1);
                    }
                    if (genreCode >= 0 && genreCode < ID3_GENRES.length) {
                        value = ID3_GENRES[genreCode];
                    } else if (genreCode == 255) {
                        // 255 is defined to be unknown
                        value = null;
                    }
                }
                mGenre = value;
            } else if (name.equalsIgnoreCase("year") || name.startsWith("year;")) {
                mYear = parseSubstring(value, 0, 0);
            } else if (name.equalsIgnoreCase("tracknumber") || name.startsWith("tracknumber;")) {
                // track number might be of the form "2/12"
                // we just read the number before the slash
                int num = parseSubstring(value, 0, 0);
                mTrack = (mTrack / 1000) * 1000 + num;
            } else if (name.equalsIgnoreCase("discnumber") ||
                    name.equals("set") || name.startsWith("set;")) {
                // set number might be of the form "1/3"
                // we just read the number before the slash
                int num = parseSubstring(value, 0, 0);
                mTrack = (num * 1000) + (mTrack % 1000);
            } else if (name.equalsIgnoreCase("duration")) {
                mDuration = parseSubstring(value, 0, 0);
            } else if (name.equalsIgnoreCase("writer") || name.startsWith("writer;")) {
                mWriter = value.trim();
            } else if (name.equalsIgnoreCase("compilation")) {
                mCompilation = parseSubstring(value, 0, 0);
            }
        }

STEP21

[java]
private Uri endFile(FileCacheEntry entry, boolean ringtones, boolean notifications,
                boolean alarms, boolean music, boolean podcasts)
                throws RemoteException {
          . . .
}

private Uri endFile(FileCacheEntry entry, boolean ringtones, boolean notifications,
                boolean alarms, boolean music, boolean podcasts)
                throws RemoteException {
          . . .
}
此函數篇幅太長，就不貼出來。有興趣的同學可以仔細瞧瞧這段代碼，它就是將前面解析出來的信息通過MediaProvider寫入數據庫的。

當然，寫入的時候會區分成好多個表，每個表都有不同的列，有興趣可以adb shell 進入你的android手機看看/data/data/com.android.providers.media/databases這個目錄下面是不是有幾個數據庫，internel.db、external.db等如果你熟練sqlite3命令可以看下這些數據庫中的內容，我看了下我手機中的外置卡數據庫中有哪些表

[plain]
qlite> .tables
.tables
album_art            audio                search
album_info           audio_genres         searchhelpertitle
albums               audio_genres_map     thumbnails
android_metadata     audio_meta           video
artist_info          audio_playlists      videothumbnails
artists              audio_playlists_map
artists_albums_map   images

sqlite> .tables
.tables
album_art            audio                search
album_info           audio_genres         searchhelpertitle
albums               audio_genres_map     thumbnails
android_metadata     audio_meta           video
artist_info          audio_playlists      videothumbnails
artists              audio_playlists_map
artists_albums_map   images看看有這麼多，分別存儲了不同種類的信息。

至於數據庫的操作以及ContentProvider的使用就不多說了，下面總結如下：

系統開機或者收到掛載消息後，MediaProvider程序會掃描sdcard（內外置區分），根據系統支持的文件類型的後綴先將文件過濾一遍，將得到的符合條件的文件再深入讀文件內容解析，看到底是什麼格式，並且將文件的一些重要信息讀取出來，最後保存於數據庫中，方便其他應用程序使用。我分析的是原生的android2.3的代碼，可能其他版本有所改變。這樣看的話，如果你把文件的後綴名改一下系統也許就掃描不出來了哦，大家可以試試！！！

上一頁:Android File類根據官方文檔理解
下一頁:Android實現圓形的圖片邊角

關於Android編程

Android編程入門 Android技術基礎 Android資訊關於Android編程 Android開發 Android開發環境 Android開發實例

相關文章