成员变量
DBConnection dbc = new DBConnection();
MD5 md5 = new MD5();
int offset;
Page page;
String rootDirectory;
成员函数
带参构造函数RawsAnalyzer(String rootName)
this.rootDirectory = rootName;
page = new Page();
createPageIndex()
ArrayList<String> fileNames = getSubFile(rootDirectory);
循环执行createPageIndex(fileName)
createPageIndex(String fileName)，重载函数
fileReader = new FileReader(fileName);读入文件
bfReader = new BufferedReader(fileReader)；文件字符缓冲流
按行循环读入
url = readRawHead(bfReader);
content = readRawContent(bfReader);
contentMD5 = md5.getMD5ofStr(content);
page.setPage(url, oldOffset, contentMD5, fileName);
page.add2DB(dbc);
readRawHead(BufferedReader bfReader)
得到urlLine
readRawContent(BufferedReader bfReader)
static ArrayList<String> getSubFile(String fileName)：得到文件的绝对路径
main()函数
RawsAnalyzer analyzer = new RawsAnalyzer("Raws");
analyzer.createPageIndex();
