前言
DiskLruCache作为google认证通过的硬盘缓存实现方案，除了知道用法，还是有必要深究一下内部实现，有助于写出高质量的代码，以及清晰的框架实现思路。
源码解析
用过DiskLruCache的都知道，有journal这个文件的存在，内容一般如下：
libcore.io.DiskLruCache
1
1
1
DIRTY e37775b7868532e0d2986b1ff384c078
CLEAN e37775b7868532e0d2986b1ff384c078 152313
至于代表什么，等下再说
open()
观察源码发现，DiskLruCache的构造方法是private修饰，这也就是告诉我们，不能通过new DiskLruCache来获取实例，构造方法如下：
private DiskLruCache(File directory, int appVersion, int valueCount, long maxSize) {
this.directory = directory;
this.appVersion = appVersion;
this.journalFile = new File(directory, JOURNAL_FILE);
this.journalFileTmp = new File(directory, JOURNAL_FILE_TEMP);
this.journalFileBackup = new File(directory, JOURNAL_FILE_BACKUP);
this.valueCount = valueCount;
this.maxSize = maxSize;
}
但是提供了open()方法，供我们获取DiskLruCache的实例，open方法如下：
/**
* Opens the cache in {@code directory}, creating a cache if none exists
* there.
*
* @param directory a writable directory
* @param valueCount the number of values per cache entry. Must be positive.
* @param maxSize the maximum number of bytes this cache should use to store
* @throws IOException if reading or writing the cache directory fails
*/
public static DiskLruCache open(File directory, int appVersion, int valueCount, long maxSize)
throws IOException {
if (maxSize <= 0) {
throw new IllegalArgumentException("maxSize <= 0");
}
if (valueCount <= 0) {
throw new IllegalArgumentException("valueCount <= 0");
}
// If a bkp file exists, use it instead.
//看备份文件是否存在
File backupFile = new File(directory, JOURNAL_FILE_BACKUP);
//如果备份文件存在，并且日志文件也存在，就把备份文件删除
//如果备份文件存在，日志文件不存在，就把备份文件重命名为日志文件
if (backupFile.exists()) {
File journalFile = new File(directory, JOURNAL_FILE);
// If journal file also exists just delete backup file.
//
if (journalFile.exists()) {
backupFile.delete();
} else {
renameTo(backupFile, journalFile, false);
}
}
// Prefer to pick up where we left off.
//初始化DiskLruCache,包括，大小，版本，路径，key对应多少value
DiskLruCache cache = new DiskLruCache(directory, appVersion, valueCount, maxSize);
//如果日志文件存在，就开始赌文件信息，并返回
//主要就是构建entry列表
if (cache.journalFile.exists()) {
try {
cache.readJournal();
cache.processJournal();
return cache;
} catch (IOException journalIsCorrupt) {
System.out
.println("DiskLruCache "
+ directory
+ " is corrupt: "
+ journalIsCorrupt.getMessage()
+ ", removing");
cache.delete();
}
}
//不存在就新建一个
// Create a new empty cache.
directory.mkdirs();
cache = new DiskLruCache(directory, appVersion, valueCount, maxSize);
cache.rebuildJournal();
return cache;
}
open函数不难理解，一是，如果日志文件存在，直接去构建entry列表；二是，如果不存在，就构建日志文件。
先来看第二条分支：构建文件：
rebuildJournal（）
//这个就是我们可以直接在disk里面看到的journal文件 主要就是对他的操作
private final File journalFile;
//journal文件的temp 缓存文件，一般都是先构建这个缓存文件，等待构建完成以后将这个缓存文件重新命名为journal
private final File journalFileTmp;
/**
* Creates a new journal that omits redundant information. This replaces the
* current journal if it exists.
*/
private synchronized void rebuildJournal() throws IOException {
if (journalWriter != null) {
journalWriter.close();
}
//指向journalFileTmp这个日志文件的缓存
Writer writer = new BufferedWriter(
new OutputStreamWriter(new FileOutputStream(journalFileTmp), Util.US_ASCII));
try {
writer.write(MAGIC);
writer.write("\n");
writer.write(VERSION_1);
writer.write("\n");
writer.write(Integer.toString(appVersion));
writer.write("\n");
writer.write(Integer.toString(valueCount));
writer.write("\n");
writer.write("\n");
for (Entry entry : lruEntries.values()) {
if (entry.currentEditor != null) {
writer.write(DIRTY + ' ' + entry.key + '\n');
} else {
writer.write(CLEAN + ' ' + entry.key + entry.getLengths() + '\n');
}
}
} finally {
writer.close();
}
if (journalFile.exists()) {
renameTo(journalFile, journalFileBackup, true);
}
//所以这个地方 构建日志文件的流程主要就是先构建出日志文件的缓存文件，如果缓存构建成功 那就直接重命名这个缓存文件，这样做好处在哪里？
renameTo(journalFileTmp, journalFile, false);
journalFileBackup.delete();
//这里也是把写入日志文件的writer初始化
journalWriter = new BufferedWriter(
new OutputStreamWriter(new FileOutputStream(journalFile, true), Util.US_ASCII));
}
这里就分析完毕了，再来看当日志文件存在的时候，做了什么
readJournal（）
private void readJournal() throws IOException {
StrictLineReader reader = new StrictLineReader(new FileInputStream(journalFile), Util.US_ASCII);
try {
//读日志文件的头信息
String magic = reader.readLine();
String version = reader.readLine();
String appVersionString = reader.readLine();
String valueCountString = reader.readLine();
String blank = reader.readLine();
if (!MAGIC.equals(magic)
|| !VERSION_1.equals(version)
|| !Integer.toString(appVersion).equals(appVersionString)
|| !Integer.toString(valueCount).equals(valueCountString)
|| !"".equals(blank)) {
throw new IOException("unexpected journal header: [" + magic + ", " + version + ", "
+ valueCountString + ", " + blank + "]");
}
//这里开始，就开始读取日志信息
int lineCount = 0;
while (true) {
try {
//构建LruEntries entry列表
readJournalLine(reader.readLine());
lineCount++;
} catch (EOFException endOfJournal) {
break;
}
}
redundantOpCount = lineCount - lruEntries.size();
// If we ended on a truncated line, rebuild the journal before appending to it.
if (reader.hasUnterminatedLine()) {
rebuildJournal();
} else {
//初始化写入文件的writer
journalWriter = new BufferedWriter(new OutputStreamWriter(
new FileOutputStream(journalFile, true), Util.US_ASCII));
}
} finally {
Util.closeQuietly(reader);
}
}
然后看下这个函数里面的几个主要变量：
//每个entry对应的缓存文件的格式 一般为1，也就是一个key,对应几个缓存，一般设为1，key-value一一对应的关系
private final int valueCount;
private long size = 0;
//这个是专门用于写入日志文件的writer
private Writer journalWriter;
//这个集合应该不陌生了，
private final LinkedHashMap<String, Entry> lruEntries =
new LinkedHashMap<String, Entry>(0, 0.75f, true);
//这个值大于一定数目时 就会触发对journal文件的清理了
private int redundantOpCount;
下面就看下entry这个实体类的内部结构
private final class Entry {
private final String key;
/**
* Lengths of this entry's files.
* 这个entry中 每个文件的长度，这个数组的长度为valueCount 一般都是1
*/
private final long[] lengths;
/**
* True if this entry has ever been published.
* 曾经被发布过 那他的值就是true
*/
private boolean readable;
/**
* The ongoing edit or null if this entry is not being edited.
* 这个entry对应的editor
*/
private Editor currentEditor;
@Override
public String toString() {
return "Entry{" +
"key='" + key + '\'' +
", lengths=" + Arrays.toString(lengths) +
", readable=" + readable +
", currentEditor=" + currentEditor +
", sequenceNumber=" + sequenceNumber +
'}';
}
/**
* The sequence number of the most recently committed edit to this entry.
* 最近编辑他的序列号
*/
private long sequenceNumber;
private Entry(String key) {
this.key = key;
this.lengths = new long[valueCount];
}
public String getLengths() throws IOException {
StringBuilder result = new StringBuilder();
for (long size : lengths) {
result.append(' ').append(size);
}
return result.toString();
}
/**
* Set lengths using decimal numbers like "10123".
*/
private void setLengths(String[] strings) throws IOException {
if (strings.length != valueCount) {
throw invalidLengths(strings);
}
try {
for (int i = 0; i < strings.length; i++) {
lengths[i] = Long.parseLong(strings[i]);
}
} catch (NumberFormatException e) {
throw invalidLengths(strings);
}
}
private IOException invalidLengths(String[] strings) throws IOException {
throw new IOException("unexpected journal line: " + java.util.Arrays.toString(strings));
}
//臨時文件創建成功了以後 就會重命名為正式文件了
public File getCleanFile(int i) {
Log.v("getCleanFile","getCleanFile path=="+new File(directory, key + "." + i).getAbsolutePath());
return new File(directory, key + "." + i);
}
//tmp开头的都是临时文件
public File getDirtyFile(int i) {
Log.v("getDirtyFile","getDirtyFile path=="+new File(directory, key + "." + i + ".tmp").getAbsolutePath());
return new File(directory, key + "." + i + ".tmp");
}
}
好，到了这里，我们DiskLruCache的open函数的主要流程就基本走完了，那么就再走2个流程结束本篇的源码分析，当然了，一个是GET操作，一个是SAVE操作了。
我们先看get操作
get()
/**
* Returns a snapshot of the entry named {@code key}, or null if it doesn't
* exist is not currently readable. If a value is returned, it is moved to
* the head of the LRU queue.
* 通过key获取对应的snapshot
*/
public synchronized Snapshot get(String key) throws IOException {
checkNotClosed();
validateKey(key);
Entry entry = lruEntries.get(key);
if (entry == null) {
return null;
}
if (!entry.readable) {
return null;
}
// Open all streams eagerly to guarantee that we see a single published
// snapshot. If we opened streams lazily then the streams could come
// from different edits.
InputStream[] ins = new InputStream[valueCount];
try {
for (int i = 0; i < valueCount; i++) {
ins[i] = new FileInputStream(entry.getCleanFile(i));
}
} catch (FileNotFoundException e) {
// A file must have been deleted manually!
for (int i = 0; i < valueCount; i++) {
if (ins[i] != null) {
Util.closeQuietly(ins[i]);
} else {
break;
}
}
return null;
}
redundantOpCount++;
//在取得需要的文件以后 记得在日志文件里增加一条记录 并检查是否需要重新构建日志文件
journalWriter.append(READ + ' ' + key + '\n');
if (journalRebuildRequired()) {
executorService.submit(cleanupCallable);
}
return new Snapshot(key, entry.sequenceNumber, ins, entry.lengths);
}
再看一下，validateKey
validateKey
private void validateKey(String key) {
Matcher matcher = LEGAL_KEY_PATTERN.matcher(key);
if (!matcher.matches()) {
throw new IllegalArgumentException("keys must match regex "
+ STRING_KEY_PATTERN + ": \"" + key + "\"");
}
}
这里是对存储entry的map的key做了正则验证，所以key一定要用md5加密，因为有些特殊字符验证不能通过。
然后看这句代码对应的：
if (journalRebuildRequired()) {
executorService.submit(cleanupCallable);
}
对应的回调函数是：
/** This cache uses a single background thread to evict entries. */
final ThreadPoolExecutor executorService =
new ThreadPoolExecutor(0, 1, 60L, TimeUnit.SECONDS, new LinkedBlockingQueue<Runnable>());
private final Callable<Void> cleanupCallable = new Callable<Void>() {
public Void call() throws Exception {
synchronized (DiskLruCache.this) {
if (journalWriter == null) {
return null; // Closed.
}
trimToSize();
if (journalRebuildRequired()) {
rebuildJournal();
redundantOpCount = 0;
}
}
return null;
}
};
其中的trimTOSize():
trimTOSize()
private void trimToSize() throws IOException {
while (size > maxSize) {
Map.Entry<String, Entry> toEvict = lruEntries.entrySet().iterator().next();
remove(toEvict.getKey());
}
}
就是检测总缓存是否超过了限制数量,
再来看journalRebuildRequired函数
journalRebuildRequired（）
/**
* We only rebuild the journal when it will halve the size of the journal
* and eliminate at least 2000 ops.
*/
private boolean journalRebuildRequired() {
final int redundantOpCompactThreshold = 2000;
return redundantOpCount >= redundantOpCompactThreshold //
&& redundantOpCount >= lruEntries.size();
}
就是校验redundantOpCount是否超出了范围，如果是，就重构日志文件。
最后看get函数的返回值 new Snapshot()
/** A snapshot of the values for an entry. */
//这个类持有该entry中每个文件的inputStream 通过这个inputStream 可以读取他的内容
public final class Snapshot implements Closeable {
private final String key;
private final long sequenceNumber;
private final InputStream[] ins;
private final long[] lengths;
private Snapshot(String key, long sequenceNumber, InputStream[] ins, long[] lengths) {
this.key = key;
this.sequenceNumber = sequenceNumber;
this.ins = ins;
this.lengths = lengths;
}
/**
* Returns an editor for this snapshot's entry, or null if either the
* entry has changed since this snapshot was created or if another edit
* is in progress.
*/
public Editor edit() throws IOException {
return DiskLruCache.this.edit(key, sequenceNumber);
}
/** Returns the unbuffered stream with the value for {@code index}. */
public InputStream getInputStream(int index) {
return ins[index];
}
/** Returns the string value for {@code index}. */
public String getString(int index) throws IOException {
return inputStreamToString(getInputStream(index));
}
/** Returns the byte length of the value for {@code index}. */
public long getLength(int index) {
return lengths[index];
}
public void close() {
for (InputStream in : ins) {
Util.closeQuietly(in);
}
}
}
到这里就明白了get最终返回的其实就是entry根据key 来取的snapshot对象，这个对象直接把inputStream暴露给外面。
最后再看看save的过程，
public Editor edit(String key) throws IOException {
return edit(key, ANY_SEQUENCE_NUMBER);
}
//根据传进去的key 创建一个entry 并且将这个key加入到entry的那个map里 然后创建一个对应的editor
//同时在日志文件里加入一条对该key的dirty记录
private synchronized Editor edit(String key, long expectedSequenceNumber) throws IOException {
//因为这里涉及到写文件 所以要先校验一下写日志文件的writer 是否被正确的初始化
checkNotClosed();
//这个地方是校验 我们的key的，通常来说 假设我们要用这个缓存来存一张图片的话，我们的key 通常是用这个图片的
//网络地址 进行md5加密，而对这个key的格式在这里是有要求的 所以这一步就是验证key是否符合规范
validateKey(key);
Entry entry = lruEntries.get(key);
if (expectedSequenceNumber != ANY_SEQUENCE_NUMBER && (entry == null
|| entry.sequenceNumber != expectedSequenceNumber)) {
return null; // Snapshot is stale.
}
if (entry == null) {
entry = new Entry(key);
lruEntries.put(key, entry);
} else if (entry.currentEditor != null) {
return null; // Another edit is in progress.
}
Editor editor = new Editor(entry);
entry.currentEditor = editor;
// Flush the journal before creating files to prevent file leaks.
journalWriter.write(DIRTY + ' ' + key + '\n');
journalWriter.flush();
return editor;
}
然后取得输出流
public OutputStream newOutputStream(int index) throws IOException {
if (index < 0 || index >= valueCount) {
throw new IllegalArgumentException("Expected index " + index + " to "
+ "be greater than 0 and less than the maximum value count "
+ "of " + valueCount);
}
synchronized (DiskLruCache.this) {
if (entry.currentEditor != this) {
throw new IllegalStateException();
}
if (!entry.readable) {
written[index] = true;
}
File dirtyFile = entry.getDirtyFile(index);
FileOutputStream outputStream;
try {
outputStream = new FileOutputStream(dirtyFile);
} catch (FileNotFoundException e) {
// Attempt to recreate the cache directory.
directory.mkdirs();
try {
outputStream = new FileOutputStream(dirtyFile);
} catch (FileNotFoundException e2) {
// We are unable to recover. Silently eat the writes.
return NULL_OUTPUT_STREAM;
}
}
return new FaultHidingOutputStream(outputStream);
}
}
注意这个index 其实一般传0 就可以了，DiskLruCache 认为 一个key 下面可以对应多个文件，这些文件 用一个数组来存储，所以正常情况下 我们都是
一个key 对应一个缓存文件 所以传0
//tmp开头的都是临时文件
public File getDirtyFile(int i) {
return new File(directory, key + "." + i + ".tmp");
}
然后你这边就能看到，这个输出流，实际上是tmp 也就是缓存文件的 .tmp 也就是缓存文件的 缓存文件 输出流。
这个流 我们写完毕以后 就要commit
public void commit() throws IOException {
if (hasErrors) {
completeEdit(this, false);
remove(entry.key); // The previous entry is stale.
} else {
completeEdit(this, true);
}
committed = true;
}
/这个就是根据缓存文件的大小 更新disklrucache的总大小 然后再日志文件里对该key加入clean的log
//最后判断是否超过最大的maxSize 以便对缓存进行清理
private synchronized void completeEdit(Editor editor, boolean success) throws IOException {
Entry entry = editor.entry;
if (entry.currentEditor != editor) {
throw new IllegalStateException();
}
// If this edit is creating the entry for the first time, every index must have a value.
if (success && !entry.readable) {
for (int i = 0; i < valueCount; i++) {
if (!editor.written[i]) {
editor.abort();
throw new IllegalStateException("Newly created entry didn't create value for index " + i);
}
if (!entry.getDirtyFile(i).exists()) {
editor.abort();
return;
}
}
}
for (int i = 0; i < valueCount; i++) {
File dirty = entry.getDirtyFile(i);
if (success) {
if (dirty.exists()) {
File clean = entry.getCleanFile(i);
dirty.renameTo(clean);
long oldLength = entry.lengths[i];
long newLength = clean.length();
entry.lengths[i] = newLength;
size = size - oldLength + newLength;
}
} else {
deleteIfExists(dirty);
}
}
redundantOpCount++;
entry.currentEditor = null;
if (entry.readable | success) {
entry.readable = true;
journalWriter.write(CLEAN + ' ' + entry.key + entry.getLengths() + '\n');
if (success) {
entry.sequenceNumber = nextSequenceNumber++;
}
} else {
lruEntries.remove(entry.key);
journalWriter.write(REMOVE + ' ' + entry.key + '\n');
}
journalWriter.flush();
if (size > maxSize || journalRebuildRequired()) {
executorService.submit(cleanupCallable);
}
}
大家看那个32-40行，就是你commit以后 就会把tmp文件转正 ，重命名为 真正的缓存文件了。
这个里面的流程和日志文件的rebuild 是差不多的，都是为了防止写文件的出问题。所以做了这样的冗余处理。
1374
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
