0.前言

最近寫論文用到了比較出名的DBLP數(shù)據(jù)集，詳細介紹見DBLP官網(wǎng)

DBLP數(shù)據(jù)集下載地址

DBLP是以XML的形式給出的闷哆，類似于

<?xml version="1.0" encoding="ISO-8859-1"?>
<!DOCTYPE dblp SYSTEM "dblp.dtd">
<dblp>
    <article mdate="2017-05-28" key="journals/acta/Saxena96">
        <author>Sanjeev Saxena</author>
        <title>Parallel Integer Sorting and Simulation Amongst CRCW Models.</title>
        <pages>607-619</pages>
        <year>1996</year>
        <volume>33</volume>
        <journal>Acta Inf.</journal>
        <number>7</number>
        <url>db/journals/acta/acta33.html#Saxena96</url>
        <ee>https://doi.org/10.1007/BF03036466</ee>
    </article>

......
<dblp>

此處將實驗數(shù)據(jù)處理的過程整理如下：

1.需求

DBLP現(xiàn)在的數(shù)據(jù)量太大了（截止到2018-07-12 22:38梳凛，2G+）冲杀，根本用不了那么多，而且在XML中不方便處理套才。
現(xiàn)在的需求是：

根據(jù)需求將一定量的數(shù)據(jù)導入到數(shù)據(jù)庫（此處以mysql為例）

2.處理

經(jīng)分析不難想到，問題的解決分為兩步：

1.按照需求將文件截取一部分（有人也許會說慕淡，這都是廢話背伴，誰都知道，單獨列為一步， 是因為一般的編輯器傻寂，還真打不開2G+的xml）
2.xml導入數(shù)據(jù)庫

2.1截取部分文件

截取文件息尺，我推薦的軟件是UltraEdit，至于如何破解疾掰，此處不做過多贅述

開始

結(jié)束

然后截取你需要的數(shù)據(jù)拷貝到新的文件里即可搂誉，需要注意的是：
新文件的末尾別忘了拷貝結(jié)束標簽</dblp>

新文件的末尾

2.2數(shù)據(jù)導入數(shù)據(jù)庫

技術(shù)選型: java的DM4J + mysql

(1)數(shù)據(jù)庫建表

/*
 Navicat Premium Data Transfer

 Source Server Type    : MySQL
 Source Server Version : 50527
 Source Host           : localhost:3306
 Source Schema         : mypaper

 Target Server Type    : MySQL
 Target Server Version : 50527
 File Encoding         : 65001
*/

SET NAMES utf8mb4;
SET FOREIGN_KEY_CHECKS = 0;

-- ----------------------------
-- Table structure for paper
-- ----------------------------
DROP TABLE IF EXISTS `paper`;
CREATE TABLE `paper`  (
  `id` int(32) UNSIGNED ZEROFILL NOT NULL AUTO_INCREMENT,
  `author` varchar(1024) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `title` varchar(1024) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `mdate` varchar(512) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `key` varchar(512) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `pages` varchar(512) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `year` varchar(64) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `volume` varchar(512) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `journal` varchar(512) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `number` varchar(64) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `url` varchar(512) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  `ee` varchar(512) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL,
  PRIMARY KEY (`id`) USING BTREE
) ENGINE = InnoDB AUTO_INCREMENT = 243354 CHARACTER SET = utf8 COLLATE = utf8_general_ci ROW_FORMAT = Compact;

SET FOREIGN_KEY_CHECKS = 1;

（2）java處理

實體類：

package org.stone6762.domain;

/**
 * @ClassName:MyPaper
 * @author Stone6762
 * @Description:
 */
public class MyPaper {

    private String author;
    private String title;
    private String mdate;
    private String key;
    private String pages;
    private String year;
    private String volume;
    private String journal;
    private String number;
    private String url;
    private String ee;

    public String getAuthor() {
        return author;
    }

    public void setAuthor(String author) {
        this.author = author;
    }

    public String getTitle() {
        return title;
    }

    public void setTitle(String title) {
        this.title = title;
    }

    public String getMdate() {
        return mdate;
    }

    public void setMdate(String mdate) {
        this.mdate = mdate;
    }

    public String getKey() {
        return key;
    }

    public void setKey(String key) {
        this.key = key;
    }

    public String getPages() {
        return pages;
    }

    public void setPages(String pages) {
        this.pages = pages;
    }

    public String getYear() {
        return year;
    }

    public void setYear(String year) {
        this.year = year;
    }

    public String getVolume() {
        return volume;
    }

    public void setVolume(String volume) {
        this.volume = volume;
    }

    public String getJournal() {
        return journal;
    }

    public void setJournal(String journal) {
        this.journal = journal;
    }

    public String getNumber() {
        return number;
    }

    public void setNumber(String number) {
        this.number = number;
    }

    public String getUrl() {
        return url;
    }

    public void setUrl(String url) {
        this.url = url;
    }

    public String getEe() {
        return ee;
    }

    public void setEe(String ee) {
        this.ee = ee;
    }

    @Override
    public String toString() {
        return "MyPaper [author=" + author + ", title=" + title + ", mdate=" + mdate + ", key=" + key + ", pages="
                + pages + ", year=" + year + ", volume=" + volume + ", journal=" + journal + ", number=" + number
                + ", url=" + url + ", ee=" + ee + "]";
    }

}

xml解析工具

package org.stone6762.utils;

import java.io.File;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import org.stone6762.domain.MyPaper;

/**
 * @Title:XML2Bean.java 
 * @author Stone6762  
 * @Description:
 */
public class XML2Bean {

    public static List<MyPaper> getPapersFromXML(File file) {
        List<MyPaper> paperList = null;
        MyPaper paper = null;
        SAXReader reader = new SAXReader();
        try {
            Document document = reader.read(file);
            Element paperstore = document.getRootElement();
            Iterator storeit = paperstore.elementIterator();

            paperList = new ArrayList<MyPaper>();
            while (storeit.hasNext()) {

                paper = new MyPaper();
                Element paperElement = (Element) storeit.next();
                // 遍歷paperElement的屬性
                List<Attribute> attributes = paperElement.attributes();
                for (Attribute attribute : attributes) {
                    if (attribute.getName().equals("mdate")) {
                        String mdate = attribute.getValue();
                        paper.setMdate(mdate);
                    }
                    if (attribute.getName().equals("key")) {
                        String key = attribute.getValue();
                        paper.setKey(key);
                    }
                }

                Iterator paperit = paperElement.elementIterator();
                while (paperit.hasNext()) {
                    Element child = (Element) paperit.next();
                    String nodeName = child.getName();
                    if (nodeName.equals("author")) {
                        String author = child.getStringValue();
                        paper.setAuthor(author);
                    } else if (nodeName.equals("title")) {
                        String title = child.getStringValue();
                        paper.setTitle(title);
                    } else if (nodeName.equals("pages")) {
                        String pages = child.getStringValue();
                        paper.setPages(pages);

                    } else if (nodeName.equals("year")) {
                        String year = child.getStringValue();
                        paper.setYear(year);
                    } else if (nodeName.equals("volume")) {
                        String volume = child.getStringValue();
                        paper.setVolume(volume);
                    } else if (nodeName.equals("journal")) {
                        String journal = child.getStringValue();
                        paper.setJournal(journal);
                    } else if (nodeName.equals("number")) {
                        String number = child.getStringValue();
                        paper.setNumber(number);
                    } else if (nodeName.equals("url")) {
                        String url = child.getStringValue();
                        paper.setUrl(url);
                    } else if (nodeName.equals("ee")) {
                        String ee = child.getStringValue();
                        paper.setEe(ee);
                    }
                }
                paperList.add(paper);
                paper = null;
            }
        } catch (DocumentException e) {
            e.printStackTrace();
        }
        return paperList;
    }
}

導入數(shù)據(jù)庫

package org.stone6762.main;

import java.io.File;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.PreparedStatement;
import java.util.List;

import org.stone6762.domain.MyPaper;
import org.stone6762.utils.XML2Bean;

/**
 * @ClassName:Main
 * @author Stone6762
 * @Description:
 */
public class Main {

    private static String USERNAME = "root";
    private static String PASSWORD = "root";
    private static String DRIVER = "com.mysql.jdbc.Driver";
    private static String URL = "jdbc:mysql://localhost:3306/mypaper";

    private static Connection con = null;
    private static PreparedStatement pstmt = null;

    public static void main(String[] args) throws Exception {

        Class.forName(DRIVER);
        System.out.println("注冊驅(qū)動成功！");
        con = DriverManager.getConnection(URL, USERNAME, PASSWORD);
        System.out.println("獲取連接成功静檬！");

        String sql = "INSERT INTO paper (paper.author, " 
                + "paper.ee," 
                + "paper.journal," 
                + "paper.key,"
                + "paper.mdate," 
                + "paper.number," 
                + "paper.pages," 
                + "paper.title," 
                + "paper.url," 
                + "paper.volume,"
                + "paper.year )VALUES (?,?,?,?,?,?,?,?,?,?,? )";


        pstmt = con.prepareStatement(sql);

        List<MyPaper> papers = XML2Bean.getPapersFromXML(new File("ref/DBCP_1_1.xml"));

        for (int i = 0; i < papers.size(); i++) {
            MyPaper myPaper = papers.get(i);
            pstmt.setObject(1, myPaper.getAuthor());
            pstmt.setObject(2, myPaper.getEe());
            pstmt.setObject(3, myPaper.getJournal());
            pstmt.setObject(4, myPaper.getKey());
            pstmt.setObject(5, myPaper.getMdate());
            pstmt.setObject(6, myPaper.getNumber());
            pstmt.setObject(7, myPaper.getPages());
            pstmt.setObject(8, myPaper.getTitle());
            pstmt.setObject(9, myPaper.getUrl());
            pstmt.setObject(10, myPaper.getVolume());
            pstmt.setObject(11, myPaper.getYear());
            pstmt.executeUpdate();
            System.out.println(i+"插入成功炭懊！");
        }

    }
}

3.結(jié)果展示

部分數(shù)據(jù)

單條數(shù)據(jù)