Android媒体扫描详细解析之二(MediaScanner & MediaProvider)
上篇blog说到了经过对文件夹进行扫描如果后缀符合系统设定的一些格式，那么就会进行文件内容扫描下面我们紧接着STEP 14中的
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;
}mRetriever->setDataSource(path)，mRetriever是在StagefrightMediaScanner的构造函数中创建的
StagefrightMediaScanner::StagefrightMediaScanner()
: mRetriever(new MediaMetadataRetriever) {
}
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里面的mRetriever也是在 MediaMetadataRetriever的构造函数中创建的。并且是通过MediaPlayerService来创建，实际就是创建的StagefrightMetadataRetriever对象。紧接着看StagefrightMetadataRetriever的setDataSource函数
STEP15
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;
}
有阅读过stagefright源码的同学可能看到这个地方就会感觉很熟悉，首先根据URI创建了一个DataSource DataSource::CreateFromURI(uri);DataSource我们实际可以将它理解为文件的源，它里面会先把文件打开，然后对文件描述符进行读取操作。
看源码可以知道它会创建一个FileSource。然后根据这个DataSource创建一个MediaExtractor::Create(mSource); MediaExtractor就是文件解析器
STEP16
sp MediaExtractor::Create(
const sp &source, const char *mime) {
sp 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);
}
...
}
...
} STEP 17
bool DataSource::sniff(
String8 *mimeType, float *confidence, sp *meta) {
*mimeType = "";
*confidence = 0.0f;
meta->clear();
Mutex::Autolock autoLock(gSnifferMutex);
for (List::iterator it = gSniffers.begin();
it != gSniffers.end(); ++it) {
String8 newMimeType;
float newConfidence;
sp newMeta;
if ((*it)(this, &newMimeType, &newConfidence, &newMeta)) {
if (newConfidence > *confidence) {
*mimeType = newMimeType;
*confidence = newConfidence;
*meta = newMeta;
}
}
}
return *confidence > 0.0;
} 我们可以挑选其中的SniffMPEG4来看看，嗅探器都是在对应格式的文件解析器中，SniffMPEG4在MPEG4Extractor中。
bool SniffMPEG4(
const sp &source, String8 *mimeType, float *confidence,
sp *) {
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 在这就不多讲了，想看懂这两个函数，你必须看MPEG4格式的标准文档。
拿到打分后也就知道了media的format，然后就根据这个类型创建一个MediaExtractor。回到STEP14，mRetriever->setDataSource(path)所有动作已经完成，总结下就是根据android设备支持的媒体格式一个一个的试，然后得到一个和该文件最相符的格式。到此实际解析工作已经做完，下面一步是将得到的格式会送给java层，
if ((value = mRetriever->extractMetadata(
METADATA_KEY_MIMETYPE)) != NULL) {
client.setMimeType(value);
}就是完成这个动作。然后有一个kKeyMap，这些实际就是我们需要存储于数据库中的媒体信息，包括时长，专辑之类的东西。也是通过mRetriever->extractMetadata函数得到。
STEP18
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());首次调用肯定是进入parseMetaData，这个函数完成解析工作，将所有需要的媒体信息全部从文件中读出来并保存到mMetaData这个键值对数组中。
具体解析工作也不说了，跟具体的格式相关。
下面最重要的一步就是将解析后得到的信息反馈给java层client.addStringTag(kKeyMap[i].tag, value);
STEP19
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);
}
STEP 20
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
private Uri endFile(FileCacheEntry entry, boolean ringtones, boolean notifications,
boolean alarms, boolean music, boolean podcasts)
throws RemoteException {
. . .
}此函数篇幅太长，就不贴出来。有兴趣的同学可以仔细瞧瞧这段代码，它就是将前面解析出来的信息通过MediaProvider写入数据库的。
当然，写入的时候会区分成好多个表，每个表都有不同的列，有兴趣可以adb shell 进入你的android手机看看/data/data/com.android.providers.media/databases这个目录下面是不是有几个数据库，internel.db、external.db等如果你熟练sqlite3命令可以看下这些数据库中的内容，我看了下我手机中的外置卡数据库中有哪些表
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至于数据库的操作以及ContentProvider的使用就不多说了，下面总结如下：
系统开机或者收到挂载消息后，MediaProvider程序会扫描sdcard（内外置区分），根据系统支持的文件类型的后缀先将文件过滤一遍，将得到的符合条件的文件再深入读文件内容解析，看到底是什么格式，并且将文件的一些重要信息读取出来，最后保存于数据库中，方便其他应用程序使用。我分析的是原生的android2.3的代码，可能其他版本有所改变。这样看的话，如果你把文件的后缀名改一下系统也许就扫描不出来了哦，大家可以试试！！！