LICENSE.txt
MANIFEST.in
RELEASE-VERSION
setup.py
version.py
configs/john-smith-broken-for-test.yaml
configs/john-smith-kvlayer.yaml
configs/john-smith-lingpipe-from-chunk.yaml
configs/john-smith-lingpipe.yaml
configs/john-smith-nltk-from-chunk.yaml
configs/john-smith-serif-streamcorpus_generate_serifxml.yaml
configs/john-smith-serif-streamcorpus_one_step.yaml
configs/john-smith-serif-streamcorpus_read_serifxml.yaml
configs/john-smith-serif.yaml
configs/john-smith-small-chunks.yaml
configs/john-smith-with-labels-from-tsv.yaml
configs/john-smith.yaml
configs/kba-s3-to-local.yaml
configs/kba-streamcorpus-2013-v0_3_0-clean_visible-local.yaml
configs/kba-streamcorpus-2013-v0_3_0-clean_visible.yaml
configs/streamcorpus-2014-v0_3_0-clean_visible.yaml
data/john-smith/original/0/960114.114
data/john-smith/original/0/960228.375
data/john-smith/original/0/960402.459
data/john-smith/original/0/960402.464
data/john-smith/original/0/960513.222
data/john-smith/original/0/960703.505
data/john-smith/original/0/960826.274
data/john-smith/original/0/960826.295
data/john-smith/original/0/960829.192
data/john-smith/original/0/960912.658
data/john-smith/original/0/961014.500
data/john-smith/original/0/970116.458
data/john-smith/original/0/970218.938
data/john-smith/original/0/970307.114
data/john-smith/original/0/970401.380
data/john-smith/original/0/970426.225
data/john-smith/original/0/970703.406
data/john-smith/original/0/970711.171
data/john-smith/original/0/970827.638
data/john-smith/original/0/970926.528
data/john-smith/original/1/960701.288
data/john-smith/original/1/960701.76
data/john-smith/original/1/961106.964
data/john-smith/original/1/970630.222
data/john-smith/original/1/970630.99
data/john-smith/original/10/970416.398
data/john-smith/original/11/960822.669
data/john-smith/original/12/960810.116
data/john-smith/original/13/960919.533
data/john-smith/original/13/960920.10
data/john-smith/original/13/960920.114
data/john-smith/original/13/960920.17
data/john-smith/original/14/970317.818
data/john-smith/original/15/970813.237
data/john-smith/original/15/971222.150
data/john-smith/original/15/971222.198
data/john-smith/original/15/971222.210
data/john-smith/original/16/960103.529
data/john-smith/original/16/960103.581
data/john-smith/original/16/960304.885
data/john-smith/original/16/960409.394
data/john-smith/original/16/960409.428
data/john-smith/original/16/960520.528
data/john-smith/original/16/960524.317
data/john-smith/original/16/960524.444
data/john-smith/original/16/960530.355
data/john-smith/original/16/960530.93
data/john-smith/original/16/960624.442
data/john-smith/original/16/960624.471
data/john-smith/original/16/960624.533
data/john-smith/original/16/960624.618
data/john-smith/original/16/960731.338
data/john-smith/original/16/960731.417
data/john-smith/original/16/960822.556
data/john-smith/original/16/960822.562
data/john-smith/original/16/960822.722
data/john-smith/original/16/960917.516
data/john-smith/original/16/960918.379
data/john-smith/original/16/960924.456
data/john-smith/original/16/961003.573
data/john-smith/original/16/961003.621
data/john-smith/original/16/961016.293
data/john-smith/original/16/961027.277
data/john-smith/original/16/961027.297
data/john-smith/original/16/961029.626
data/john-smith/original/16/970108.585
data/john-smith/original/16/970109.669
data/john-smith/original/16/970109.769
data/john-smith/original/16/970110.704
data/john-smith/original/16/970114.515
data/john-smith/original/16/970127.279
data/john-smith/original/16/970127.308
data/john-smith/original/16/970127.316
data/john-smith/original/16/970127.624
data/john-smith/original/16/970217.365
data/john-smith/original/16/970218.1640
data/john-smith/original/16/970218.497
data/john-smith/original/16/970324.797
data/john-smith/original/16/970325.13
data/john-smith/original/16/970325.270
data/john-smith/original/16/970414.153
data/john-smith/original/16/970414.193
data/john-smith/original/16/970414.241
data/john-smith/original/16/970417.432
data/john-smith/original/16/970523.145
data/john-smith/original/16/970523.185
data/john-smith/original/16/970523.288
data/john-smith/original/16/970523.338
data/john-smith/original/16/970523.455
data/john-smith/original/16/970523.483
data/john-smith/original/16/970523.591
data/john-smith/original/16/970529.127
data/john-smith/original/16/970529.136
data/john-smith/original/16/970529.141
data/john-smith/original/16/970529.234
data/john-smith/original/16/970529.313
data/john-smith/original/16/970529.543
data/john-smith/original/16/970530.167
data/john-smith/original/16/970630.489
data/john-smith/original/16/970804.144
data/john-smith/original/16/970804.189
data/john-smith/original/16/970804.215
data/john-smith/original/16/970804.477
data/john-smith/original/16/970804.497
data/john-smith/original/16/970814.683
data/john-smith/original/16/970815.375
data/john-smith/original/16/970822.631
data/john-smith/original/16/970910.420
data/john-smith/original/16/970910.536
data/john-smith/original/16/970911.195
data/john-smith/original/16/971001.204
data/john-smith/original/16/971001.822
data/john-smith/original/16/971014.163
data/john-smith/original/16/971014.228
data/john-smith/original/16/971014.322
data/john-smith/original/16/971014.359
data/john-smith/original/16/971015.530
data/john-smith/original/16/971018.154
data/john-smith/original/16/971102.190
data/john-smith/original/16/971104.255
data/john-smith/original/16/971104.358
data/john-smith/original/16/971104.433
data/john-smith/original/16/971105.177
data/john-smith/original/16/971218.333
data/john-smith/original/16/971225.136
data/john-smith/original/17/970108.268
data/john-smith/original/18/970111.202
data/john-smith/original/19/970227.644
data/john-smith/original/2/970708.4
data/john-smith/original/20/970723.737
data/john-smith/original/21/970908.758
data/john-smith/original/22/960328.241
data/john-smith/original/23/970420.80
data/john-smith/original/24/970519.188
data/john-smith/original/24/970519.191
data/john-smith/original/24/970520.114
data/john-smith/original/24/970520.117
data/john-smith/original/24/970521.155
data/john-smith/original/24/970521.158
data/john-smith/original/24/970523.237
data/john-smith/original/24/970523.245
data/john-smith/original/24/970527.468
data/john-smith/original/25/971110.688
data/john-smith/original/26/960108.526
data/john-smith/original/27/961230.449
data/john-smith/original/27/961231.74
data/john-smith/original/28/960402.646
data/john-smith/original/28/960413.55
data/john-smith/original/28/970428.580
data/john-smith/original/28/970501.411
data/john-smith/original/28/970501.453
data/john-smith/original/28/970501.523
data/john-smith/original/28/970501.531
data/john-smith/original/28/970501.623
data/john-smith/original/28/970501.727
data/john-smith/original/28/970502.111
data/john-smith/original/28/970502.122
data/john-smith/original/28/970502.29
data/john-smith/original/28/970502.5
data/john-smith/original/28/970502.74
data/john-smith/original/28/970504.25
data/john-smith/original/29/960311.408
data/john-smith/original/3/960304.742
data/john-smith/original/30/960222.707
data/john-smith/original/30/960223.15
data/john-smith/original/30/960607.349
data/john-smith/original/30/960711.352
data/john-smith/original/30/960724.711
data/john-smith/original/30/960725.443
data/john-smith/original/30/960730.608
data/john-smith/original/30/960731.718
data/john-smith/original/30/960731.768
data/john-smith/original/30/960802.2
data/john-smith/original/30/960802.34
data/john-smith/original/30/970210.851
data/john-smith/original/30/970611.447
data/john-smith/original/30/970731.768
data/john-smith/original/30/970801.676
data/john-smith/original/30/970803.131
data/john-smith/original/30/970804.26
data/john-smith/original/30/970804.32
data/john-smith/original/30/970808.564
data/john-smith/original/30/970808.668
data/john-smith/original/30/970809.30
data/john-smith/original/30/970811.688
data/john-smith/original/31/970612.420
data/john-smith/original/31/970909.422
data/john-smith/original/32/961028.9
data/john-smith/original/33/960318.662
data/john-smith/original/34/970221.681
data/john-smith/original/4/970701.861
data/john-smith/original/4/970708.827
data/john-smith/original/5/970823.176
data/john-smith/original/6/961011.655
data/john-smith/original/7/971001.979
data/john-smith/original/8/970429.552
data/john-smith/original/9/970730.527
examples/john_smith_custom_reader.py
streamcorpus_pipeline/__init__.py
streamcorpus_pipeline/_clean_html.py
streamcorpus_pipeline/_clean_visible.py
streamcorpus_pipeline/_convert_kba_json.py
streamcorpus_pipeline/_dedup.py
streamcorpus_pipeline/_docx_to_text.py
streamcorpus_pipeline/_dump_label_stats.py
streamcorpus_pipeline/_exceptions.py
streamcorpus_pipeline/_filters.py
streamcorpus_pipeline/_find.py
streamcorpus_pipeline/_get_name_info.py
streamcorpus_pipeline/_getch.py
streamcorpus_pipeline/_guess_media_type.py
streamcorpus_pipeline/_handle_unconvertible_spinn3r.py
streamcorpus_pipeline/_hyperlink_labels.py
streamcorpus_pipeline/_john_smith.py
streamcorpus_pipeline/_kvlayer.py
streamcorpus_pipeline/_language.py
streamcorpus_pipeline/_lingpipe.py
streamcorpus_pipeline/_local_storage.py
streamcorpus_pipeline/_memory.py
streamcorpus_pipeline/_name_matcher.py
streamcorpus_pipeline/_pdf_to_text.py
streamcorpus_pipeline/_pipeline.py
streamcorpus_pipeline/_pycassa_simple_table.py
streamcorpus_pipeline/_rejester.py
streamcorpus_pipeline/_run_lingpipe.py
streamcorpus_pipeline/_s3_storage.py
streamcorpus_pipeline/_serif.py
streamcorpus_pipeline/_spinn3r_feed_storage.py
streamcorpus_pipeline/_taggers.py
streamcorpus_pipeline/_tarball_export.py
streamcorpus_pipeline/_tokenizer.py
streamcorpus_pipeline/_truncate.py
streamcorpus_pipeline/_upgrade_streamcorpus.py
streamcorpus_pipeline/_upgrade_streamcorpus_v0_3_0.py
streamcorpus_pipeline/_yaml_files_list.py
streamcorpus_pipeline/config.py
streamcorpus_pipeline/convert_entities.py
streamcorpus_pipeline/load.py
streamcorpus_pipeline/make_namespace_string.py
streamcorpus_pipeline/run.py
streamcorpus_pipeline/stages.py
streamcorpus_pipeline/text_profile_signature.py
streamcorpus_pipeline/util.py
streamcorpus_pipeline.egg-info/PKG-INFO
streamcorpus_pipeline.egg-info/SOURCES.txt
streamcorpus_pipeline.egg-info/dependency_links.txt
streamcorpus_pipeline.egg-info/entry_points.txt
streamcorpus_pipeline.egg-info/requires.txt
streamcorpus_pipeline.egg-info/top_level.txt
streamcorpus_pipeline/_spinn3r/__init__.py
streamcorpus_pipeline/_spinn3r/contentExtension_pb2.py
streamcorpus_pipeline/_spinn3r/protoStream_pb2.py
streamcorpus_pipeline/_spinn3r/spinn3rApi_pb2.py
streamcorpus_pipeline/tests/__init__.py
streamcorpus_pipeline/tests/_test_data.py
streamcorpus_pipeline/tests/test_clean_html.py
streamcorpus_pipeline/tests/test_dedup.py
streamcorpus_pipeline/tests/test_fpat_matcher.py
streamcorpus_pipeline/tests/test_hyperlink_labels.py
streamcorpus_pipeline/tests/test_kvlayer.py
streamcorpus_pipeline/tests/test_language.py
streamcorpus_pipeline/tests/test_lingpipe.py
streamcorpus_pipeline/tests/test_local_storage.py
streamcorpus_pipeline/tests/test_memory.py
streamcorpus_pipeline/tests/test_pipeline.py
streamcorpus_pipeline/tests/test_pipeline_rejester.py
streamcorpus_pipeline/tests/test_pipeline_run.py
streamcorpus_pipeline/tests/test_spinn3r_feed_storage.py
streamcorpus_pipeline/tests/test_taggers.py
streamcorpus_pipeline/tests/test_text_profile_signature.py
streamcorpus_pipeline/tests/test_tokenizer.py
streamcorpus_pipeline/tests/test_upgrade_streamcorpus_v0_3_0.py
streamcorpus_pipeline/tests/test_yaml_files_list.py