在Java中创建大型csv文件变得非常缓慢

我在尝试从另一个csv文件开始创建csv文件时遇到性能问题。 以下是原始文件的外观：

country,state,co,olt,olu,splitter,ont,cpe,cpe.latitude,cpe.longitude,cpe.customer_class,cpe.phone,cpe.ip,cpe.subscriber_id
COUNTRY-0001,STATE-0001,CO-0001,OLT-0001,OLU0001,SPLITTER-0001,ONT-0001,CPE-0001,28.21487,77.451775,ALL,SIP:+674100002743@IMS.COMCAST.NET,SIP:E28EDADA06B2@IMS.COMCAST.NET,CPE_SUBSCRIBER_ID-QHLHW4
COUNTRY-0001,STATE-0002,CO-0002,OLT-0002,OLU0002,SPLITTER-0002,ONT-0002,CPE-0002,28.294018,77.068924,ALL,SIP:+796107443092@IMS.COMCAST.NET,SIP:58DD999D6466@IMS.COMCAST.NET,CPE_SUBSCRIBER_ID-AH8NJQ

可能会有数百万条这样的线路，我已经检测到1.280.000条线路的问题

这是算法：

File csvInputFile = new File(csv_path);
int blockSize = 409600;
brCsvInputFile = new BufferedReader(frCsvInputFile, blockSize);

String line = null;
StringBuilder sbIntermediate = new StringBuilder();
skipFirstLine(brCsvInputFile);
while ((line = brCsvInputFile.readLine()) != null) {
    createIntermediateStringBuffer(sbIntermediate, line.split(REGEX_COMMA));
}


private static void skipFirstLine(BufferedReader br) throws IOException {
    String line = br.readLine();
    String[] splitLine = line.split(REGEX_COMMA);
    LOGGER.debug("First line detected! ");
    createIndex(splitLine);
    createIntermediateIndex(splitLine);
}

private static void createIndex(String[] splitLine) {
    LOGGER.debug("START method createIndex.");
    for (int i = 0; i < splitLine.length; i++)
        headerIndex.put(splitLine[i], i);
    printMap(headerIndex);
    LOGGER.debug("COMPLETED method createIndex.");
}

    private static void createIntermediateIndex(String[] splitLine) {

    LOGGER.debug("START method createIntermediateIndex.");
    com.tekcomms.c2d.xml.model.v2.Metadata_element[] metadata_element = null;
    String[] servicePath = newTopology.getElement().getEntity().getService_path().getLevel();

    if (newTopology.getElement().getMetadata() != null)
        metadata_element = newTopology.getElement().getMetadata().getMetadata_element();

    LOGGER.debug(servicePath.toString());
    LOGGER.debug(metadata_element.toString());

    headerIntermediateIndex.clear();
    int indexIntermediateId = 0;
    for (int i = 0; i < servicePath.length; i++) {
        String level = servicePath[i];
        LOGGER.debug("level is: " + level);
        headerIntermediateIndex.put(level, indexIntermediateId);
        indexIntermediateId++;
        // its identificator is going to be located to the next one
        headerIntermediateIndex.put(level + "ID", indexIntermediateId);
        indexIntermediateId++;
    }
    // adding cpe.latitude,cpe.longitude,cpe.customer_class, it could be
    // better if it would be metadata as well.
    String labelLatitude = newTopology.getElement().getEntity().getLatitude();
    // indexIntermediateId++;
    headerIntermediateIndex.put(labelLatitude, indexIntermediateId);
    String labelLongitude = newTopology.getElement().getEntity().getLongitude();
    indexIntermediateId++;
    headerIntermediateIndex.put(labelLongitude, indexIntermediateId);
    String labelCustomerClass = newTopology.getElement().getCustomer_class();
    indexIntermediateId++;
    headerIntermediateIndex.put(labelCustomerClass, indexIntermediateId);

    // adding metadata
    // cpe.phone,cpe.ip,cpe.subscriber_id,cpe.vendor,cpe.model,cpe.customer_status,cpe.contact_telephone,cpe.address,
    // cpe.city,cpe.state,cpe.zip,cpe.bootfile,cpe.software_version,cpe.hardware_version
    // now i need to iterate over each Metadata_element belonging to
    // topology.element.metadata
    // are there any metadata?
    if (metadata_element != null && metadata_element.length != 0)
        for (int j = 0; j < metadata_element.length; j++) {
            String label = metadata_element[j].getLabel();
            label = label.toLowerCase();
            LOGGER.debug(" ==label: " + label + " index_pos: " + j);
            indexIntermediateId++;
            headerIntermediateIndex.put(label, indexIntermediateId);
        }

    printMap(headerIntermediateIndex);
    LOGGER.debug("COMPLETED method createIntermediateIndex.");
}

File csvInputFile=新文件（csv\u路径）；
int blockSize=409600；
brCsvInputFile=新的BufferedReader（frCsvInputFile，blockSize）；
字符串行=null；
StringBuilder sbIntermediate=新建StringBuilder（）；
skipFirstLine（brCsvInputFile）；
而（（line=brCsvInputFile.readLine（））！=null）{
createIntermediateStringBuffer（sbIntermediate，line.split（REGEX_逗号））；
}
私有静态void skipFirstLine（BufferedReader br）引发IOException{
String line=br.readLine（）；
String[]splitLine=line.split（REGEX_逗号）；
debug（“检测到第一行！”）；
创建索引（分割线）；
创建中间索引（分割线）；
}
私有静态void createIndex（字符串[]拆分行）{
debug（“启动方法createIndex”）；
对于（int i=0；i

读取整个数据集，1.280.000行需要800毫秒！所以问题在于这种方法

    private static void createIntermediateStringBuffer(StringBuilder sbIntermediate, String[] splitLine) throws ClassCastException,
        NullPointerException {

    LOGGER.debug("START method createIntermediateStringBuffer.");
    long start, end;
    start = System.currentTimeMillis();
    ArrayList<String> hashes = new ArrayList<String>();
    com.tekcomms.c2d.xml.model.v2.Metadata_element[] metadata_element = null;

    String[] servicePath = newTopology.getElement().getEntity().getService_path().getLevel();
    LOGGER.debug(servicePath.toString());

    if (newTopology.getElement().getMetadata() != null) {
        metadata_element = newTopology.getElement().getMetadata().getMetadata_element();
        LOGGER.debug(metadata_element.toString());
    }

    for (int i = 0; i < servicePath.length; i++) {
        String level = servicePath[i];
        LOGGER.debug("level is: " + level);
        if (splitLine.length > getPositionFromIndex(level)) {
            String name = splitLine[getPositionFromIndex(level)];
            sbIntermediate.append(name);
            hashes.add(name);
            sbIntermediate.append(REGEX_COMMA).append(HashUtils.calculateHash(hashes)).append(REGEX_COMMA);
            LOGGER.debug(" ==sbIntermediate: " + sbIntermediate.toString());
        }
    }

    //      end=System.currentTimeMillis();
    //      LOGGER.info("COMPLETED adding name hash. " + (end - start) + " ms. " + (end - start) / 1000 + " seg.");
    // adding cpe.latitude,cpe.longitude,cpe.customer_class, it should be
    // better if it would be metadata as well.
    String labelLatitude = newTopology.getElement().getEntity().getLatitude();
    if (splitLine.length > getPositionFromIndex(labelLatitude)) {
        String lat = splitLine[getPositionFromIndex(labelLatitude)];
        sbIntermediate.append(lat).append(REGEX_COMMA);
    }

    String labelLongitude = newTopology.getElement().getEntity().getLongitude();
    if (splitLine.length > getPositionFromIndex(labelLongitude)) {
        String lon = splitLine[getPositionFromIndex(labelLongitude)];
        sbIntermediate.append(lon).append(REGEX_COMMA);
    }
    String labelCustomerClass = newTopology.getElement().getCustomer_class();
    if (splitLine.length > getPositionFromIndex(labelCustomerClass)) {
        String customerClass = splitLine[getPositionFromIndex(labelCustomerClass)];
        sbIntermediate.append(customerClass).append(REGEX_COMMA);
    }
    //      end=System.currentTimeMillis();
    //      LOGGER.info("COMPLETED adding lat,lon,customer. " + (end - start) + " ms. " + (end - start) / 1000 + " seg.");
    // watch out metadata are optional, it can appear as a void chain!
    if (metadata_element != null && metadata_element.length != 0)
        for (int j = 0; j < metadata_element.length; j++) {
            String label = metadata_element[j].getLabel();
            LOGGER.debug(" ==label: " + label + " index_pos: " + j);
            if (splitLine.length > getPositionFromIndex(label)) {
                String actualValue = splitLine[getPositionFromIndex(label)];
                if (!"".equals(actualValue))
                    sbIntermediate.append(actualValue).append(REGEX_COMMA);
                else
                    sbIntermediate.append("").append(REGEX_COMMA);
            } else
                sbIntermediate.append("").append(REGEX_COMMA);
            LOGGER.debug(" ==sbIntermediate: " + sbIntermediate.toString());
        }//for
    sbIntermediate.append("\n");
    end = System.currentTimeMillis();
    LOGGER.info("COMPLETED method createIntermediateStringBuffer. " + (end - start) + " ms. ");
}

private static void createIntermediateStringBuffer（StringBuilder sbIntermediate，String[]splitLine）抛出ClassCastException，
NullPointerException{
debug（“START方法createIntermediateStringBuffer”）；
漫长的开始，漫长的结束；
start=System.currentTimeMillis（）；
ArrayList哈希=新的ArrayList（）；
com.tekcomms.c2d.xml.model.v2.Metadata\u element[]Metadata\u element=null；
字符串[]servicePath=newTopology.getElement（）.getEntity（）.getService_path（）.getLevel（）；
debug（servicePath.toString（））；
if（newTopology.getElement（）.getMetadata（）！=null）{
metadata_element=newTopology.getElement（）.getMetadata（）.getMetadata_element（）；
debug（metadata_element.toString（））；
}
for（int i=0；igetPositionFromIndex（级别））{
字符串名称=拆分行[getPositionFromIndex（级别）]；
sbIntermediate.append（名称）；
添加（名称）；
sbIntermediate.append（REGEX_逗号）.append（HashUtils.calculateHash（hashes））.append（REGEX_逗号）；
debug（“==sbIntermediate:+sbIntermediate.toString（））；
}
}
//end=System.currentTimeMillis（）；
//info（“已完成添加名称哈希。”+（end-start）+“ms.”+（end-start）/1000+“seg.”）；
//添加cpe.latitude、cpe.longitude、cpe.customer_类，应该是
//最好是元数据。
字符串Labellative=newTopology.getElement（）.getEntity（）.getLatitude（）；
if（splitLine.length>getPositionFromIndex（Labellative））{
字符串lat=分割线[getPositionFromIndex（Labellative）]；
sbIntermediate.append（lat.append）（REGEX_逗号）；
}
字符串labellongitute=newTopology.getElement（）.getEntity（）.getLongitude（）；
if（splitLine.length>getPositionFromIndex（标签长度））{
字符串lon=分割线[getPositionFromIndex（标签长度）]；
sbIntermediate.append（lon）.append（REGEX_
for (int i = 0; i < servicePath.length; i++) {
        String level = servicePath[i];
        LOGGER.debug("level is: " + level);
        if (splitLine.length > getPositionFromIndex(level)) {
            String name = splitLine[getPositionFromIndex(level)];
            sbIntermediate.append(name);
            hashes.add(name);
            sbIntermediate.append(REGEX_COMMA).append(HashUtils.calculateHash(hashes)).append(REGEX_COMMA);
            LOGGER.debug(" ==sbIntermediate: " + sbIntermediate.toString());
        }
    }

line.split(REGEX_COMMA)