lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

Refactor hoodie-common and create right abstractions for Hoodie Storage V2.0

Browse Source 
The following is the gist of changes done

- All low-level operation of creating a commit code was in HoodieClient which made it hard to share code if there was a compaction commit.
- HoodieTableMetadata contained a mix of metadata and filtering files. (Also few operations required FileSystem to be passed in because those were called from TaskExecutors and others had FileSystem as a global variable). Since merge-on-read requires a lot of that code, but will have to change slightly on how it operates on the metadata and how it filters the files. The two set of operation are split into HoodieTableMetaClient and TableFileSystemView.
- Everything (active commits, archived commits, cleaner log, save point log and in future delta and compaction commits) in HoodieTableMetaClient is a HoodieTimeline. Timeline is a series of instants, which has an in-built concept of inflight and completed commit markers.
- A timeline can be queries for ranges, contains and also use to create new datapoint (create a new commit etc). Commit (and all the above metadata) creation/deletion is streamlined in a timeline
- Multiple timelines can be merged into a single timeline, giving us an audit timeline to whatever happened in a hoodie dataset. This also helps with #55.
- Move to java 8 and introduce java 8 succinct syntax in refactored code
This commit is contained in:
Prasanna Rajaperumal
2017-01-04 14:40:26 -08:00
parent 283269e57f
commit 8ee777a9bb
76 changed files with 3480 additions and 1932 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
hoodie-cli/src/main/java/com/uber/hoodie/cli/utils/CommitUtil.java
View File

@@ -17,20 +17,20 @@
package com.uber.hoodie.cli.utils;
import com.uber.hoodie.common.model.HoodieCommitMetadata;
import com.uber.hoodie.common.model.HoodieTableMetadata;
import com.uber.hoodie.common.table.HoodieTableMetaClient;
import com.uber.hoodie.common.table.HoodieTimeline;
import java.io.IOException;
import java.util.List;
import java.util.SortedMap;
import java.util.TreeMap;
public class CommitUtil {
public static long countNewRecords(HoodieTableMetadata target, List<String> commitsToCatchup)
public static long countNewRecords(HoodieTableMetaClient target, List<String> commitsToCatchup)
throws IOException {
long totalNew = 0;
SortedMap<String, HoodieCommitMetadata> meta = target.getAllCommitMetadata();
HoodieTimeline timeline = target.getActiveCommitTimeline();
timeline = timeline.reload();
for(String commit:commitsToCatchup) {
HoodieCommitMetadata c = meta.get(commit);
HoodieCommitMetadata c = HoodieCommitMetadata.fromBytes(timeline.readInstantDetails(commit).get());
totalNew += c.fetchTotalRecordsWritten() - c.fetchTotalUpdateRecordsWritten();
}
return totalNew;

14
hoodie-cli/src/main/java/com/uber/hoodie/cli/utils/HiveUtil.java
View File

@@ -16,7 +16,7 @@
package com.uber.hoodie.cli.utils;
import com.uber.hoodie.common.model.HoodieTableMetadata;
import com.uber.hoodie.common.table.HoodieTableMetaClient;
import org.apache.commons.dbcp.BasicDataSource;
import org.joda.time.DateTime;
@@ -53,7 +53,7 @@ public class HiveUtil {
return ds;
}
public static long countRecords(String jdbcUrl, HoodieTableMetadata source, String dbName, String user, String pass) throws SQLException {
public static long countRecords(String jdbcUrl, HoodieTableMetaClient source, String dbName, String user, String pass) throws SQLException {
Connection conn = HiveUtil.getConnection(jdbcUrl, user, pass);
ResultSet rs = null;
Statement stmt = conn.createStatement();
@@ -62,13 +62,13 @@ public class HiveUtil {
stmt.execute("set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat" );
stmt.execute("set hive.stats.autogather=false" );
rs = stmt.executeQuery(
"select count(`_hoodie_commit_time`) as cnt from " + dbName + "." + source
"select count(`_hoodie_commit_time`) as cnt from " + dbName + "." + source.getTableConfig()
.getTableName());
long count = -1;
if(rs.next()) {
count = rs.getLong("cnt");
}
System.out.println("Total records in " + source.getTableName() + " is " + count);
System.out.println("Total records in " + source.getTableConfig().getTableName() + " is " + count);
return count;
} finally {
if (rs != null) {
@@ -80,7 +80,7 @@ public class HiveUtil {
}
}
public static long countRecords(String jdbcUrl, HoodieTableMetadata source, String srcDb,
public static long countRecords(String jdbcUrl, HoodieTableMetaClient source, String srcDb,
int partitions, String user, String pass) throws SQLException {
DateTime dateTime = DateTime.now();
String endDateStr =
@@ -94,7 +94,7 @@ public class HiveUtil {
return countRecords(jdbcUrl, source, srcDb, startDateStr, endDateStr, user, pass);
}
private static long countRecords(String jdbcUrl, HoodieTableMetadata source, String srcDb, String startDateStr,
private static long countRecords(String jdbcUrl, HoodieTableMetaClient source, String srcDb, String startDateStr,
String endDateStr, String user, String pass) throws SQLException {
Connection conn = HiveUtil.getConnection(jdbcUrl, user, pass);
ResultSet rs = null;
@@ -104,7 +104,7 @@ public class HiveUtil {
stmt.execute("set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat");
stmt.execute("set hive.stats.autogather=false");
rs = stmt.executeQuery(
"select count(`_hoodie_commit_time`) as cnt from " + srcDb + "." + source
"select count(`_hoodie_commit_time`) as cnt from " + srcDb + "." + source.getTableConfig()
.getTableName() + " where datestr>'" + startDateStr + "' and datestr<='"
+ endDateStr + "'");
if(rs.next()) {