&引用;OutOfMemoryError:Java堆空间;我的程序出错了
请看一下下面的代码&引用;OutOfMemoryError:Java堆空间;我的程序出错了,java,linux,amazon-ec2,out-of-memory,heap,Java,Linux,Amazon Ec2,Out Of Memory,Heap,请看一下下面的代码 public void createHash() throws IOException { System.out.println("Hash Creation Started"); StringBuffer hashIndex = new StringBuffer(""); AmazonS3 s3 = new AmazonS3Client(new ClasspathPropertiesFileCredentialsProvider());
public void createHash() throws IOException
{
System.out.println("Hash Creation Started");
StringBuffer hashIndex = new StringBuffer("");
AmazonS3 s3 = new AmazonS3Client(new ClasspathPropertiesFileCredentialsProvider());
Region usWest2 = Region.getRegion(Regions.US_EAST_1);
s3.setRegion(usWest2);
strBuffer = new StringBuffer("");
try
{
//List all the Buckets
List<Bucket>buckets = s3.listBuckets();
for(int i=0;i<buckets.size();i++)
{
System.out.println("- "+(buckets.get(i)).getName());
}
//Downloading the Object
System.out.println("Downloading Object");
S3Object s3Object = s3.getObject(new GetObjectRequest("JsonBucket", "Articles_4.json"));
System.out.println("Content-Type: " + s3Object.getObjectMetadata().getContentType());
//Read the JSON File
BufferedReader reader = new BufferedReader(new InputStreamReader(s3Object.getObjectContent()));
while (true) {
String line = reader.readLine();
if (line == null) break;
// System.out.println(" " + line);
strBuffer.append(line);
}
JSONTokener jTokener = new JSONTokener(strBuffer.toString());
jsonArray = new JSONArray(jTokener);
System.out.println("Json array length: "+jsonArray.length());
for(int i=0;i<jsonArray.length();i++)
{
JSONObject jsonObject1 = jsonArray.getJSONObject(i);
//Add Title and Body Together to the list
String titleAndBodyContainer = jsonObject1.getString("title")+" "+jsonObject1.getString("body");
//Remove full stops and commas
titleAndBodyContainer = titleAndBodyContainer.replaceAll("\\.(?=\\s|$)", " ");
titleAndBodyContainer = titleAndBodyContainer.replaceAll(",", " ");
titleAndBodyContainer = titleAndBodyContainer.toLowerCase();
//Create a word list without duplicated words
StringBuilder result = new StringBuilder();
HashSet<String> set = new HashSet<String>();
for(String s : titleAndBodyContainer.split(" ")) {
if (!set.contains(s)) {
result.append(s);
result.append(" ");
set.add(s);
}
}
//System.out.println(result.toString());
//Re-Arranging everything into Alphabetic Order
String testString = "acarus acarpous accession absently missy duckweed settling";
String testHash = "058 057 05@ 03o dwr 6ug i^&";
String[]finalWordHolder = (result.toString()).split(" ");
Arrays.sort(finalWordHolder);
//Navigate through text and create the Hash
for(int arrayCount=0;arrayCount<finalWordHolder.length;arrayCount++)
{
Iterator iter = completedWordMap.entrySet().iterator();
while(iter.hasNext())
{
Map.Entry mEntry = (Map.Entry)iter.next();
String key = (String)mEntry.getKey();
String value = (String)mEntry.getValue();
if(finalWordHolder[arrayCount].equals(value))
{
hashIndex.append(key); //Adding Hash Keys
//hashIndex.append(" ");
}
}
}
//System.out.println(hashIndex.toString().trim());
jsonObject1.put("hash_index", hashIndex.toString().trim()); //Add the Hash to the JSON Object
jsonObject1.put("primary_key", i); //Create the primary key
jsonObjectHolder.add(jsonObject1); //Add the JSON Object to the JSON collection
System.out.println("JSON Number: "+i);
}
System.out.println("Hash Creation Completed");
}
catch(Exception e)
{
e.printStackTrace();
}
}
public void createHash()引发IOException
{
System.out.println(“哈希创建已启动”);
StringBuffer hashIndex=新的StringBuffer(“”);
AmazonS3 s3=新的AmazonS3客户端(新的类路径属性FileCredentialsProvider());
Region usWest2=Region.getRegion(Regions.US_EAST_1);
s3.设置区域(usWest2);
strBuffer=新的StringBuffer(“”);
尝试
{
//列出所有的桶
ListBucket=s3.ListBucket();
对于(int i=0;i构造StringBuffer
对象以在JSONTokener
内部传递它是一个非常糟糕的主意。此类具有直接来自Reader
或InputStream
的构造函数,因此您的代码应该是这样的:
JSONTokener jTokener=newjsontokener(newbufferedreader(newinputstreamreader)(s3Object.getObjectContent()))
您的java堆内存已经用完。在32位系统上,您可以将堆内存增加到4gb。如果您在64位系统上,您可以更高。如果您在32位系统上要求超过4gb,您将从java获得无效值,它将退出
下面是如何在64位系统上使用cmd命令将内存堆设置为6gb:
java -Xmx6144M -d64
您正在循环之外声明hashIndex
StringBuffer hashIndex = new StringBuffer("");
...
for(int i=0;i<jsonArray.length();i++) {
hashIndex.append(...);
stringbufferhashindex=newstringbuffer(“”);
...
对于(int i=0;我认为所有建议增加堆大小的答案都应该删除。这样的建议就像指示断肢的受害者在哪里获取更多血液。这是否意味着这会导致内存问题?只是好奇而已?加载了所有数据的字符串缓冲区肯定会占用额外的空间。答案是一个组合关于你和@Lance Java。如果我能选择两者作为选择答案,我很高兴:)增加Java堆空间绝不是一个解决办法,只是暂时的权宜之计。@Hexafrance:我不喜欢提供否决票,但我同意你的看法。我正在浏览600亿条记录,因此Java堆大小意味着“什么都没有”@gloryofsucces我没有否决这个答案,尽管我会看到背后的理由。技术正确性+1。答案是你和@Andremoniy的组合。如果我能选择两者作为选择答案,我很高兴:)