twitter / elephant-bird
File Size

The distribution of size of files (measured in lines of code).

Intro
Learn more...
File Size Overall
0% | 0% | 20% | 34% | 45%
Legend:
1001+
501-1000
201-500
101-200
1-100


explore: grouped by folders | grouped by size | sunburst | 3D view
File Size per Extension
1001+
501-1000
201-500
101-200
1-100
java0% | 0% | 20% | 34% | 44%
proto0% | 0% | 0% | 0% | 100%
xml0% | 0% | 0% | 0% | 100%
File Size per Logical Decomposition
primary
1001+
501-1000
201-500
101-200
1-100
core0% | 0% | 30% | 30% | 39%
pig0% | 0% | 13% | 40% | 45%
mahout0% | 0% | 100% | 0% | 0%
hadoop-compat0% | 0% | 100% | 0% | 0%
rcfile0% | 0% | 0% | 55% | 44%
lucene0% | 0% | 0% | 78% | 21%
hive0% | 0% | 0% | 44% | 55%
pig-lucene0% | 0% | 0% | 63% | 36%
crunch0% | 0% | 0% | 0% | 100%
cascading20% | 0% | 0% | 0% | 100%
cascading30% | 0% | 0% | 0% | 100%
cascading-protobuf0% | 0% | 0% | 0% | 100%
repo0% | 0% | 0% | 0% | 100%
Longest Files (Top 50)
File# lines# units
ThriftToDynamicProto.java
in core/src/main/java/com/twitter/elephantbird/util
408 25
Protobufs.java
in core/src/main/java/com/twitter/elephantbird/util
356 31
ThriftToPig.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
349 21
SplitUtil.java
in core/src/main/java/com/twitter/elephantbird/util
349 27
VectorWritableConverter.java
in mahout/src/main/java/com/twitter/elephantbird/pig/mahout
333 21
DeprecatedInputFormatWrapper.java
in core/src/main/java/com/twitter/elephantbird/mapred/input
308 30
ProtobufToPig.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
284 17
ThriftUtils.java
in core/src/main/java/com/twitter/elephantbird/util
267 11
HadoopCompat.java
in hadoop-compat/src/main/java/com/twitter/elephantbird/util
249 21
TStructDescriptor.java
in core/src/main/java/com/twitter/elephantbird/thrift
236 31
MapReduceInputFormatWrapper.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
205 20
Invoker.java
in pig/src/main/java/com/twitter/elephantbird/pig/piggybank
200 8
ThriftProtocolWrapper.java
in core/src/main/java/com/twitter/elephantbird/thrift
198 44
LuceneIndexInputFormat.java
in lucene/src/main/java/com/twitter/elephantbird/mapreduce/input
197 22
SequenceFileStorage.java
in pig/src/main/java/com/twitter/elephantbird/pig/store
186 15
PigToThrift.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
184 11
PigToProtobuf.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
177 11
MultiInputFormat.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
163 8
ProtobufStructObjectInspector.java
in hive/src/main/java/com/twitter/elephantbird/hive/serde
163 15
RCFileThriftOutputFormat.java
in rcfile/src/main/java/com/twitter/elephantbird/mapreduce/output
162 9
SequenceFileLoader.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
161 13
LzoInputFormat.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
160 10
RCFilePigStorage.java
in rcfile/src/main/java/com/twitter/elephantbird/pig/store
154 10
JsonLoader.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
153 9
HadoopUtils.java
in core/src/main/java/com/twitter/elephantbird/util
146 10
RCFileThriftInputFormat.java
in rcfile/src/main/java/com/twitter/elephantbird/mapreduce/input
139 9
LuceneIndexOutputFormat.java
in lucene/src/main/java/com/twitter/elephantbird/mapreduce/output
139 10
LuceneHdfsDirectory.java
in lucene/src/main/java/com/twitter/elephantbird/mapreduce/input
136 17
RCFileProtobufInputFormat.java
in rcfile/src/main/java/com/twitter/elephantbird/mapreduce/input
134 9
Inflection.java
in core/src/main/java/com/twitter/elephantbird/util
132 13
Base64Codec.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
132 1
ExecuteOnClusterTool.java
in core/src/main/java/com/twitter/elephantbird/util
130 14
BinaryBlockReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/io
128 13
LzoRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
127 9
CompositeRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input/combine
126 10
BinaryWritable.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/io
126 13
CompositeInputSplit.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input/combine
124 13
SequenceFileConfig.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
120 8
LzoBinaryB64LineRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
118 9
LzoBaseLoadFunc.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
117 15
AbstractLazyTuple.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
115 17
LuceneIndexRecordReader.java
in lucene/src/main/java/com/twitter/elephantbird/mapreduce/input
114 9
LzoBinaryBlockRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
112 9
Strings.java
in core/src/main/java/com/twitter/elephantbird/util
110 15
RCFileUtil.java
in rcfile/src/main/java/com/twitter/elephantbird/util
108 3
FilterLoadFunc.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
107 17
RawSequenceFileRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
107 6
LocationAsTuple.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
105 12
LuceneIndexLoader.java
in pig-lucene/src/main/java/com/twitter/elephantbird/pig/load
105 7
WritableLoadCaster.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
104 25
Files With Most Units (Top 50)
File# lines# units
ThriftProtocolWrapper.java
in core/src/main/java/com/twitter/elephantbird/thrift
198 44
Protobufs.java
in core/src/main/java/com/twitter/elephantbird/util
356 31
TStructDescriptor.java
in core/src/main/java/com/twitter/elephantbird/thrift
236 31
DeprecatedInputFormatWrapper.java
in core/src/main/java/com/twitter/elephantbird/mapred/input
308 30
SplitUtil.java
in core/src/main/java/com/twitter/elephantbird/util
349 27
WritableLoadCaster.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
104 25
ThriftToDynamicProto.java
in core/src/main/java/com/twitter/elephantbird/util
408 25
LuceneIndexInputFormat.java
in lucene/src/main/java/com/twitter/elephantbird/mapreduce/input
197 22
ThriftToPig.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
349 21
HadoopCompat.java
in hadoop-compat/src/main/java/com/twitter/elephantbird/util
249 21
VectorWritableConverter.java
in mahout/src/main/java/com/twitter/elephantbird/pig/mahout
333 21
MapReduceInputFormatWrapper.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
205 20
TextConverter.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
81 17
ProtobufToPig.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
284 17
AbstractLazyTuple.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
115 17
FilterLoadFunc.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
107 17
LuceneHdfsDirectory.java
in lucene/src/main/java/com/twitter/elephantbird/mapreduce/input
136 17
LzoBaseLoadFunc.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
117 15
SequenceFileStorage.java
in pig/src/main/java/com/twitter/elephantbird/pig/store
186 15
Strings.java
in core/src/main/java/com/twitter/elephantbird/util
110 15
ProtobufStructObjectInspector.java
in hive/src/main/java/com/twitter/elephantbird/hive/serde
163 15
IntWritableConverter.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
74 14
LongWritableConverter.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
74 14
ExecuteOnClusterTool.java
in core/src/main/java/com/twitter/elephantbird/util
130 14
WritableStoreCaster.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
103 13
SequenceFileLoader.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
161 13
Inflection.java
in core/src/main/java/com/twitter/elephantbird/util
132 13
CompositeInputSplit.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input/combine
124 13
BinaryBlockReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/io
128 13
BinaryWritable.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/io
126 13
LzoTextDelimited.java
in cascading3/src/main/java/com/twitter/elephantbird/cascading3/scheme
61 13
LzoTextDelimited.java
in cascading2/src/main/java/com/twitter/elephantbird/cascading2/scheme
58 13
EBTypes.java
in crunch/src/main/java/com/twitter/elephantbird/crunch
89 13
LocationAsTuple.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
105 12
PigToProtobuf.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
177 11
PigToThrift.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
184 11
PathFilters.java
in core/src/main/java/com/twitter/elephantbird/util
76 11
ThriftUtils.java
in core/src/main/java/com/twitter/elephantbird/util
267 11
DelegateCombineFileInputFormat.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input/combine
94 11
RCFilePigStorage.java
in rcfile/src/main/java/com/twitter/elephantbird/pig/store
154 10
ColumnarMetadata.java
in rcfile/src/main/java/com/twitter/elephantbird/util
90 10
LuceneIndexOutputFormat.java
in lucene/src/main/java/com/twitter/elephantbird/mapreduce/output
139 10
HadoopUtils.java
in core/src/main/java/com/twitter/elephantbird/util
146 10
HdfsUtils.java
in core/src/main/java/com/twitter/elephantbird/util
96 10
CompositeRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input/combine
126 10
LzoInputFormat.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
160 10
LzoW3CLogRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
99 10
RCFileProtobufInputFormat.java
in rcfile/src/main/java/com/twitter/elephantbird/mapreduce/input
134 9
RCFileThriftInputFormat.java
in rcfile/src/main/java/com/twitter/elephantbird/mapreduce/input
139 9
RCFileThriftOutputFormat.java
in rcfile/src/main/java/com/twitter/elephantbird/mapreduce/output
162 9
Files With Long Lines (Top 34)

There are 34 files with lines longer than 120 characters. In total, there are 67 long lines.

File# lines# units# long lines
ProtobufToPig.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
284 17 14
ThriftToPig.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
349 21 3
PigUtil.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
80 8 3
ProtobufPigLoader.java
in pig/src/main/java/com/twitter/elephantbird/pig/load
54 4 2
InvokeForLong.java
in pig/src/main/java/com/twitter/elephantbird/pig/piggybank
15 4 2
InvokeForString.java
in pig/src/main/java/com/twitter/elephantbird/pig/piggybank
15 4 2
InvokeForDouble.java
in pig/src/main/java/com/twitter/elephantbird/pig/piggybank
15 4 2
InvokeForFloat.java
in pig/src/main/java/com/twitter/elephantbird/pig/piggybank
15 4 2
InvokeForInt.java
in pig/src/main/java/com/twitter/elephantbird/pig/piggybank
15 4 2
LzoProtobufBlockPigStorage.java
in pig/src/main/java/com/twitter/elephantbird/pig/store
49 4 2
LzoProtobufB64LinePigStorage.java
in pig/src/main/java/com/twitter/elephantbird/pig/store
49 4 2
Protobufs.java
in core/src/main/java/com/twitter/elephantbird/util
356 31 2
LzoThriftScheme.java
in cascading3/src/main/java/com/twitter/elephantbird/cascading3/scheme
38 4 2
LzoTextLine.java
in cascading3/src/main/java/com/twitter/elephantbird/cascading3/scheme
42 8 2
LzoTextDelimited.java
in cascading3/src/main/java/com/twitter/elephantbird/cascading3/scheme
61 13 2
LzoProtobufScheme.java
in cascading3/src/main/java/com/twitter/elephantbird/cascading3/scheme
38 4 2
LzoTextLine.java
in cascading2/src/main/java/com/twitter/elephantbird/cascading2/scheme
39 8 2
LzoTextDelimited.java
in cascading2/src/main/java/com/twitter/elephantbird/cascading2/scheme
58 13 2
CombinedWritableSequenceFile.java
in cascading2/src/main/java/com/twitter/elephantbird/cascading2/scheme
22 3 2
PigToProtobuf.java
in pig/src/main/java/com/twitter/elephantbird/pig/util
177 11 1
JsonStringToMap.java
in pig/src/main/java/com/twitter/elephantbird/pig/piggybank
63 3 1
DeprecatedInputFormatWrapper.java
in core/src/main/java/com/twitter/elephantbird/mapred/input
308 30 1
DeprecatedOutputFormatWrapper.java
in core/src/main/java/com/twitter/elephantbird/mapred/output
95 9 1
CompositeRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input/combine
126 10 1
CompositeInputSplit.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input/combine
124 13 1
LzoProtobufBlockRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
14 1 1
LzoProtobufB64LineRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
14 1 1
LzoThriftB64LineRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
14 1 1
LzoThriftBlockRecordReader.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/input
14 1 1
BinaryBlockWriter.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/io
62 7 1
LzoProtobufB64LineOutputFormat.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/output
35 4 1
LzoThriftB64LineOutputFormat.java
in core/src/main/java/com/twitter/elephantbird/mapreduce/output
33 3 1
CombinedSequenceFile.java
in cascading3/src/main/java/com/twitter/elephantbird/cascading3/scheme
52 3 1
CombinedSequenceFile.java
in cascading2/src/main/java/com/twitter/elephantbird/cascading2/scheme
54 4 1