diff --git a/hbase-shell/src/main/ruby/hbase/table.rb b/hbase-shell/src/main/ruby/hbase/table.rb index 7a334a08143..26bb84fc616 100644 --- a/hbase-shell/src/main/ruby/hbase/table.rb +++ b/hbase-shell/src/main/ruby/hbase/table.rb @@ -508,6 +508,13 @@ EOF # Normalize column names columns = [columns] if columns.class == String limit = args['LIMIT'] || -1 + replica_id = args[REGION_REPLICA_ID] + isolation_level = args[ISOLATION_LEVEL] + read_type = args[READ_TYPE] + allow_partial_results = args[ALLOW_PARTIAL_RESULTS].nil? ? false : args[ALLOW_PARTIAL_RESULTS] + batch = args[BATCH] || -1 + max_result_size = args[MAX_RESULT_SIZE] || -1 + unless columns.is_a?(Array) raise ArgumentError, 'COLUMNS must be specified as a String or an Array' end @@ -549,10 +556,16 @@ EOF scan.setMaxVersions(versions) if versions > 1 scan.setTimeRange(timerange[0], timerange[1]) if timerange scan.setRaw(raw) - scan.setCaching(limit) if limit > 0 + scan.setLimit(limit) if limit > 0 set_attributes(scan, attributes) if attributes set_authorizations(scan, authorizations) if authorizations scan.setConsistency(org.apache.hadoop.hbase.client.Consistency.valueOf(consistency)) if consistency + scan.setReplicaId(replica_id) if replica_id + scan.setIsolationLevel(org.apache.hadoop.hbase.client.IsolationLevel.valueOf(isolation_level)) if isolation_level + scan.setReadType(org.apache.hadoop.hbase.client::Scan::ReadType.valueOf(read_type)) if read_type + scan.setAllowPartialResults(allow_partial_results) if allow_partial_results + scan.setBatch(batch) if batch > 0 + scan.setMaxResultSize(max_result_size) if max_result_size > 0 else scan = org.apache.hadoop.hbase.client.Scan.new end @@ -571,7 +584,6 @@ EOF raise(ArgumentError, 'Scan argument should be org.apache.hadoop.hbase.client.Scan') \ unless scan.nil? || scan.is_a?(org.apache.hadoop.hbase.client.Scan) - limit = args['LIMIT'] || -1 maxlength = args.delete('MAXLENGTH') || -1 converter = args.delete(FORMATTER) || nil converter_class = args.delete(FORMATTER_CLASS) || 'org.apache.hadoop.hbase.util.Bytes' @@ -605,13 +617,8 @@ EOF res[key][column] = cell end end - # One more row processed count += 1 - if limit > 0 && count >= limit - # If we reached the limit, exit before the next call to hasNext - break - end end scanner.close diff --git a/hbase-shell/src/main/ruby/hbase_constants.rb b/hbase-shell/src/main/ruby/hbase_constants.rb index 98716853a1f..5c8ab87e19c 100644 --- a/hbase-shell/src/main/ruby/hbase_constants.rb +++ b/hbase-shell/src/main/ruby/hbase_constants.rb @@ -65,6 +65,11 @@ module HBaseConstants NUMREGIONS = 'NUMREGIONS'.freeze REGION_REPLICATION = 'REGION_REPLICATION'.freeze REGION_REPLICA_ID = 'REGION_REPLICA_ID'.freeze + ISOLATION_LEVEL = 'ISOLATION_LEVEL'.freeze + READ_TYPE = 'READ_TYPE'.freeze + ALLOW_PARTIAL_RESULTS = 'ALLOW_PARTIAL_RESULTS'.freeze + BATCH = 'BATCH'.freeze + MAX_RESULT_SIZE = 'MAX_RESULT_SIZE'.freeze CONFIGURATION = org.apache.hadoop.hbase.HConstants::CONFIGURATION ATTRIBUTES = 'ATTRIBUTES'.freeze VISIBILITY = 'VISIBILITY'.freeze diff --git a/hbase-shell/src/main/ruby/shell/commands/scan.rb b/hbase-shell/src/main/ruby/shell/commands/scan.rb index 96382f3195f..2dc377e4025 100644 --- a/hbase-shell/src/main/ruby/shell/commands/scan.rb +++ b/hbase-shell/src/main/ruby/shell/commands/scan.rb @@ -25,7 +25,9 @@ module Shell Scan a table; pass table name and optionally a dictionary of scanner specifications. Scanner specifications may include one or more of: TIMERANGE, FILTER, LIMIT, STARTROW, STOPROW, ROWPREFIXFILTER, TIMESTAMP, -MAXLENGTH or COLUMNS, CACHE or RAW, VERSIONS, ALL_METRICS or METRICS +MAXLENGTH, COLUMNS, CACHE, RAW, VERSIONS, ALL_METRICS, METRICS, +REGION_REPLICA_ID, ISOLATION_LEVEL, READ_TYPE, ALLOW_PARTIAL_RESULTS, +BATCH or MAX_RESULT_SIZE If no columns are specified, all columns will be scanned. To scan all members of a column family, leave the qualifier empty as in @@ -56,6 +58,8 @@ Some examples: hbase> scan 't1', {FILTER => org.apache.hadoop.hbase.filter.ColumnPaginationFilter.new(1, 0)} hbase> scan 't1', {CONSISTENCY => 'TIMELINE'} + hbase> scan 't1', {ISOLATION_LEVEL => 'READ_UNCOMMITTED'} + hbase> scan 't1', {MAX_RESULT_SIZE => 123456} For setting the Operation Attributes hbase> scan 't1', { COLUMNS => ['c1', 'c2'], ATTRIBUTES => {'mykey' => 'myvalue'}} hbase> scan 't1', { COLUMNS => ['c1', 'c2'], AUTHORIZATIONS => ['PRIVATE','SECRET']} @@ -72,6 +76,11 @@ Disabled by default. Example: hbase> scan 't1', {RAW => true, VERSIONS => 10} +There is yet another option -- READ_TYPE -- which instructs the scanner to +use a specific read type. Example: + + hbase> scan 't1', {READ_TYPE => 'PREAD'} + Besides the default 'toStringBinary' format, 'scan' supports custom formatting by column. A user can define a FORMATTER by adding it to the column name in the scan specification. The FORMATTER can be stipulated: diff --git a/hbase-shell/src/test/ruby/hbase/table_test.rb b/hbase-shell/src/test/ruby/hbase/table_test.rb index e2645d805af..2ac03e50a7a 100644 --- a/hbase-shell/src/test/ruby/hbase/table_test.rb +++ b/hbase-shell/src/test/ruby/hbase/table_test.rb @@ -602,6 +602,30 @@ module Hbase assert_nil(res['2']['x:b']) end + define_test 'scan should support REGION_REPLICA_ID' do + res = @test_table._scan_internal REGION_REPLICA_ID => 0 + assert_not_nil(res) + end + + define_test 'scan should support ISOLATION_LEVEL' do + res = @test_table._scan_internal ISOLATION_LEVEL => 'READ_COMMITTED' + assert_not_nil(res) + end + + define_test 'scan should support READ_TYPE parameter' do + res = @test_table._scan_internal READ_TYPE => 'PREAD' + assert_not_nil(res) + res = @test_table._scan_internal READ_TYPE => 'STREAM' + assert_not_nil(res) + res = @test_table._scan_internal READ_TYPE => 'DEFAULT' + assert_not_nil(res) + end + + define_test 'scan should support ALLOW_PARTIAL_RESULTS' do + res = @test_table._scan_internal ALLOW_PARTIAL_RESULTS => true + assert_not_nil(res) + end + define_test "scan should work with raw and version parameter" do # Create test table if it does not exist @test_name_raw = "hbase_shell_tests_raw_scan"