Java IBM Domino中的大数据检索

我试图从IBMDominoV9.0收集帐户数据和组数据

我为收集数据而编写的代码使用了lotus.domino.View API。这段代码对于一个小数据集来说效果很好，我为40个用户运行了这段代码，结果很好。当我运行代码为10k用户提取数据时，提取数据大约需要3-4小时，这是不可接受的

你能给我推荐一些其他的API吗？我们可以用它更快地检索数据

我目前使用的代码如下：

private static void testUserDataRetrieval(String host, String userName, String password) throws Exception{
    Session s = NotesFactory.createSession(host, userName, password);
    Database db = s.getDatabase(s.getServerName(), "names");
    File outFile = new File("C:\\Users\\vishva\\Desktop\\dominoExtract.txt");
    FileWriter writer = new FileWriter(outFile);
    View view = db.getView("($Users)");
    ViewEntryCollection entryCollection = view.getAllEntries();
    writer.write("\n--------------------------------- Printing data for view:"+view.getName()+"("+view.getEntryCount()+")--------------------------------------------");
    Vector<Object> columnNames = view.getColumnNames();
    for(int i = 0; i< entryCollection.getCount(); i++){
        ViewEntry entry = entryCollection.getNextEntry();
        if(entry == null) continue;
        Vector<Object> colValues = entry.getColumnValues();
        for(int j = 0; j < columnNames.size(); j++)
            writer.write("\n"+columnNames.get(j)+":"+colValues.get(j));
        writer.write("\n*****************************************");
    }
    writer.flush();
    writer.close();
}

---

请让我知道我应该使用哪个其他API来提高数据检索的速度？

首先：您读取for循环每次运行时的收集计数。这使得它非常慢。for循环根本不是必需的。第二：你从不回收物品。在使用domino对象时，这是必须的，否则代码消耗内存的速度将超出您的想象：

private static void testUserDataRetrieval(String host, String userName, String password) throws Exception{
  Session s = NotesFactory.createSession(host, userName, password);
  Database db = s.getDatabase(s.getServerName(), "names");
  File outFile = new File("C:\\Users\\vishva\\Desktop\\dominoExtract.txt");
  FileWriter writer = new FileWriter(outFile);
  View view = db.getView("($Users)");
  ViewEntryCollection entryCollection = view.getAllEntries();
  writer.write("\n--------------------------------- Printing data for view:"+view.getName()+"("+view.getEntryCount()+")--------------------------------------------");
  Vector<Object> columnNames = view.getColumnNames();
  ViewEntry entry = entryCollection.getFirstEntry();
  ViewEntry entryNext;
  while(entry != null) {
    Vector<Object> colValues = entry.getColumnValues();
    for(int j = 0; j < columnNames.size(); j++)
        writer.write("\n"+columnNames.get(j)+":"+colValues.get(j));
    writer.write("\n*****************************************");
    entryNext = entryCollection.getNextEntry();
    entry.recycle();
    entry = entryNext ;
  }

writer.flush();
writer.close();

---

}

默认情况下，视图对象的isAutoUpdate属性设置为true。这意味着它可以处理在后端发生的任何更改，而不仅仅是给您一个一次性快照。添加以下内容：

view.setAutoUpdate(false);

---

此外，您可能还应该研究如何使用ViewNavigator类。有关从Domino8.5.2开始该类性能改进的详细文章，请参阅。它是由首席开发人员为这些类编写的。还有很多有趣的细节，请参见本页。

感谢大家的意见。 为了检索用户，我后来试用了LDAP API，效果很好。我能够在23秒内检索到10万个帐户，这是可以接受的。我使用的代码如下

    private void extractDominoDataViaLdap(){
    String [] args = new String[]{"192.168.21.156","Administrator","password","","C:\\Users\\vishva\\Desktop"};
    String server = args[0];
    String userName = args[1];
    String password = args[2];
    String baseDN = args[3];
    String fileLocation = args[4];
    // Set up environment for creating initial context
    Hashtable<String, Object> env = new Hashtable<String, Object>(11);
    env.put(Context.INITIAL_CONTEXT_FACTORY,"com.sun.jndi.ldap.LdapCtxFactory");
    env.put(Context.PROVIDER_URL, "ldap://"+server+":389");

    long time = System.currentTimeMillis();
    // Authenticate as S. User and password "mysecret"
    env.put(Context.SECURITY_AUTHENTICATION, "simple");
    env.put(Context.SECURITY_PRINCIPAL, userName);
    env.put(Context.SECURITY_CREDENTIALS, password);
    FileWriter writer = null;
    BufferedWriter out = null;
    try {
        DirContext ctx = new InitialDirContext(env);
        //fetching user data
        // Create the search controls
        SearchControls searchCtls = new SearchControls();
        // Specify the attributes to return
        String returnedAtts[] = {"FullName","dn","displayname","givenName","sn","location","mail","mailfile","mailserver"};
        searchCtls.setReturningAttributes(returnedAtts);
        // Specify the search scope
        searchCtls.setSearchScope(SearchControls.SUBTREE_SCOPE);
        searchCtls.setCountLimit(0);
        // specify the LDAP search filter
        String searchFilter = "objectClass=inetOrgPerson";

        // Specify the Base for the search
        String searchBase = baseDN;

        // Search for objects using the filter
        NamingEnumeration<SearchResult> answer = ctx.search(searchBase,searchFilter, searchCtls);

        writer = new FileWriter(fileLocation+"\\users.csv");
        out = new BufferedWriter(writer);
        for(String attr : returnedAtts)
            out.write(attr+",");
        out.write("\n");
        int count = 0;
        // Loop through the search results
        while (answer.hasMoreElements()) {
            ++count;
            SearchResult sr = (SearchResult) answer.next();
            Attributes attrs = sr.getAttributes();
            StringBuilder sb = new StringBuilder();
            for(String attr : returnedAtts)
                sb.append("\""+((attrs.get(attr) != null)?attrs.get(attr).get():"")+"\"").append(",");
            out.write(sb.toString()+"\n");
            out.flush();
        }
        System.out.println("# of users returned: "+count);
        out.close();
        writer.close();
    }
}

---

让选民解释一下