├── .gitignore ├── .idea ├── .gitignore ├── .name ├── codeStyleSettings.xml ├── encodings.xml ├── misc.xml ├── modules.xml ├── schema-matching.iml ├── scopes │ └── scope_settings.xml └── vcs.xml ├── LICENSE ├── Makefile ├── README.md ├── TODO.md ├── demo ├── 1-match.sh ├── 2-validate.sh ├── 3-compare-descriptions.sh └── data │ ├── abc.csv │ ├── abc_desc.txt │ ├── ck.csv │ ├── ck_desc.txt │ ├── cm.csv │ ├── cm_desc.txt │ ├── concarne.csv │ ├── concarne_desc.txt │ ├── gr1.csv │ ├── gr1_desc.txt │ ├── horst.csv │ ├── horst_desc.txt │ ├── maca.csv │ ├── maca_desc.txt │ ├── mk.csv │ ├── mk_desc.txt │ ├── original │ ├── 5Engines.csv │ └── 5Metadata.csv │ ├── rbg.csv │ ├── rbg_desc.txt │ ├── skynet.csv │ ├── skynet_desc.txt │ ├── xyz.csv │ ├── xyz_desc.txt │ ├── zauberfee.csv │ └── zauberfee_desc.txt ├── schema-matching ├── src ├── schema-matching.py └── schema_matching │ ├── __init__.py │ ├── __main__.py │ ├── actions │ ├── __init__.py │ ├── _argparser.py │ ├── collect.py │ ├── compare.py │ ├── match.py │ └── validate.py │ ├── collector │ ├── __init__.py │ ├── base.py │ ├── columntype.py │ ├── description │ │ ├── __init__.py │ │ ├── _argparser.py │ │ └── normal │ │ │ ├── L1.py │ │ │ ├── L2.py │ │ │ └── __init__.py │ ├── itemaverage.py │ ├── itemcount.py │ ├── itemfrequency.py │ ├── itemprobability.py │ ├── itemsum.py │ ├── letteraverage.py │ ├── lettercount.py │ ├── letterentropy.py │ ├── letterfrequency.py │ ├── letterprobability.py │ ├── lettervariance.py │ ├── maxitem.py │ ├── minitem.py │ ├── multiphase.py │ ├── probability.py │ ├── rows.py │ ├── set.py │ ├── tag.py │ ├── variance.py │ └── weight.py │ └── utilities │ ├── __init__.py │ ├── argparse.py │ ├── distribution.py │ ├── functional.py │ ├── iterator.py │ ├── misc.py │ ├── operator.py │ ├── string.py │ └── timelimit.py └── tests └── utilities └── test_distribution.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.py[co] 2 | -------------------------------------------------------------------------------- /.idea/.gitignore: -------------------------------------------------------------------------------- 1 | /workspace.xml 2 | /inspectionProfiles/ 3 | -------------------------------------------------------------------------------- /.idea/.name: -------------------------------------------------------------------------------- 1 | schema-matching -------------------------------------------------------------------------------- /.idea/codeStyleSettings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/.idea/codeStyleSettings.xml -------------------------------------------------------------------------------- /.idea/encodings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/.idea/encodings.xml -------------------------------------------------------------------------------- /.idea/misc.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/.idea/misc.xml -------------------------------------------------------------------------------- /.idea/modules.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/.idea/modules.xml -------------------------------------------------------------------------------- /.idea/schema-matching.iml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/.idea/schema-matching.iml -------------------------------------------------------------------------------- /.idea/scopes/scope_settings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/.idea/scopes/scope_settings.xml -------------------------------------------------------------------------------- /.idea/vcs.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/.idea/vcs.xml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/LICENSE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/README.md -------------------------------------------------------------------------------- /TODO.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/TODO.md -------------------------------------------------------------------------------- /demo/1-match.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/1-match.sh -------------------------------------------------------------------------------- /demo/2-validate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/2-validate.sh -------------------------------------------------------------------------------- /demo/3-compare-descriptions.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/3-compare-descriptions.sh -------------------------------------------------------------------------------- /demo/data/abc.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/abc.csv -------------------------------------------------------------------------------- /demo/data/abc_desc.txt: -------------------------------------------------------------------------------- 1 | 1,1 2 | 2,6 3 | 3,7 4 | 4,9 5 | 5,10 6 | 6,16 7 | 7,23 8 | -------------------------------------------------------------------------------- /demo/data/ck.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/ck.csv -------------------------------------------------------------------------------- /demo/data/ck_desc.txt: -------------------------------------------------------------------------------- 1 | 1,18 2 | 2,4 3 | 3,6 4 | 4,9 5 | 5,11 6 | 6,12 7 | 7,15 -------------------------------------------------------------------------------- /demo/data/cm.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/cm.csv -------------------------------------------------------------------------------- /demo/data/cm_desc.txt: -------------------------------------------------------------------------------- 1 | 1,2 2 | 2,6 3 | 3,7 4 | 4,9 5 | 5,16 6 | 6,19 -------------------------------------------------------------------------------- /demo/data/concarne.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/concarne.csv -------------------------------------------------------------------------------- /demo/data/concarne_desc.txt: -------------------------------------------------------------------------------- 1 | 1,9 2 | 2,4 3 | 3,15 4 | 4,20 5 | 5,14 -------------------------------------------------------------------------------- /demo/data/gr1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/gr1.csv -------------------------------------------------------------------------------- /demo/data/gr1_desc.txt: -------------------------------------------------------------------------------- 1 | 1,2 2 | 2,5 3 | 3,11 4 | 4,12 5 | 5,13 6 | 6,22 7 | -------------------------------------------------------------------------------- /demo/data/horst.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/horst.csv -------------------------------------------------------------------------------- /demo/data/horst_desc.txt: -------------------------------------------------------------------------------- 1 | 1,1 2 | 2,7 3 | 3,14 4 | 4,16 5 | 5,20 -------------------------------------------------------------------------------- /demo/data/maca.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/maca.csv -------------------------------------------------------------------------------- /demo/data/maca_desc.txt: -------------------------------------------------------------------------------- 1 | 1,1 2 | 2,2 3 | 3,5 4 | 4,9 5 | 5,14 6 | 6,15 7 | 7,22 8 | -------------------------------------------------------------------------------- /demo/data/mk.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/mk.csv -------------------------------------------------------------------------------- /demo/data/mk_desc.txt: -------------------------------------------------------------------------------- 1 | 1,1 2 | 2,4 3 | 3,6 4 | 4,7 5 | 5,12 6 | 6,2 -------------------------------------------------------------------------------- /demo/data/original/5Engines.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/original/5Engines.csv -------------------------------------------------------------------------------- /demo/data/original/5Metadata.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/original/5Metadata.csv -------------------------------------------------------------------------------- /demo/data/rbg.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/rbg.csv -------------------------------------------------------------------------------- /demo/data/rbg_desc.txt: -------------------------------------------------------------------------------- 1 | 1,18 2 | 2,19 3 | 3,4 4 | 4,3 5 | 5,14 6 | 6,7 7 | 7,11 8 | -------------------------------------------------------------------------------- /demo/data/skynet.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/skynet.csv -------------------------------------------------------------------------------- /demo/data/skynet_desc.txt: -------------------------------------------------------------------------------- 1 | 1,15 2 | 2,17 3 | 3,8 4 | 4,7 5 | 5,5 6 | 6,6 7 | 7,2 -------------------------------------------------------------------------------- /demo/data/xyz.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/xyz.csv -------------------------------------------------------------------------------- /demo/data/xyz_desc.txt: -------------------------------------------------------------------------------- 1 | 1,1 2 | 2,5 3 | 3,7 4 | 4,13 5 | 5,18 6 | 6,22 -------------------------------------------------------------------------------- /demo/data/zauberfee.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/demo/data/zauberfee.csv -------------------------------------------------------------------------------- /demo/data/zauberfee_desc.txt: -------------------------------------------------------------------------------- 1 | 1,2 2 | 2,3 3 | 3,6 4 | 4,8 5 | 5,13 6 | 6,7 7 | 7,16 8 | -------------------------------------------------------------------------------- /schema-matching: -------------------------------------------------------------------------------- 1 | src/schema-matching.py -------------------------------------------------------------------------------- /src/schema-matching.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema-matching.py -------------------------------------------------------------------------------- /src/schema_matching/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/__init__.py -------------------------------------------------------------------------------- /src/schema_matching/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/__main__.py -------------------------------------------------------------------------------- /src/schema_matching/actions/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/actions/__init__.py -------------------------------------------------------------------------------- /src/schema_matching/actions/_argparser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/actions/_argparser.py -------------------------------------------------------------------------------- /src/schema_matching/actions/collect.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/actions/collect.py -------------------------------------------------------------------------------- /src/schema_matching/actions/compare.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/actions/compare.py -------------------------------------------------------------------------------- /src/schema_matching/actions/match.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/actions/match.py -------------------------------------------------------------------------------- /src/schema_matching/actions/validate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/actions/validate.py -------------------------------------------------------------------------------- /src/schema_matching/collector/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/__init__.py -------------------------------------------------------------------------------- /src/schema_matching/collector/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/base.py -------------------------------------------------------------------------------- /src/schema_matching/collector/columntype.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/columntype.py -------------------------------------------------------------------------------- /src/schema_matching/collector/description/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/description/__init__.py -------------------------------------------------------------------------------- /src/schema_matching/collector/description/_argparser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/description/_argparser.py -------------------------------------------------------------------------------- /src/schema_matching/collector/description/normal/L1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/description/normal/L1.py -------------------------------------------------------------------------------- /src/schema_matching/collector/description/normal/L2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/description/normal/L2.py -------------------------------------------------------------------------------- /src/schema_matching/collector/description/normal/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/schema_matching/collector/itemaverage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/itemaverage.py -------------------------------------------------------------------------------- /src/schema_matching/collector/itemcount.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/itemcount.py -------------------------------------------------------------------------------- /src/schema_matching/collector/itemfrequency.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/itemfrequency.py -------------------------------------------------------------------------------- /src/schema_matching/collector/itemprobability.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/itemprobability.py -------------------------------------------------------------------------------- /src/schema_matching/collector/itemsum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/itemsum.py -------------------------------------------------------------------------------- /src/schema_matching/collector/letteraverage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/letteraverage.py -------------------------------------------------------------------------------- /src/schema_matching/collector/lettercount.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/lettercount.py -------------------------------------------------------------------------------- /src/schema_matching/collector/letterentropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/letterentropy.py -------------------------------------------------------------------------------- /src/schema_matching/collector/letterfrequency.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/letterfrequency.py -------------------------------------------------------------------------------- /src/schema_matching/collector/letterprobability.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/letterprobability.py -------------------------------------------------------------------------------- /src/schema_matching/collector/lettervariance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/lettervariance.py -------------------------------------------------------------------------------- /src/schema_matching/collector/maxitem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/maxitem.py -------------------------------------------------------------------------------- /src/schema_matching/collector/minitem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/minitem.py -------------------------------------------------------------------------------- /src/schema_matching/collector/multiphase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/multiphase.py -------------------------------------------------------------------------------- /src/schema_matching/collector/probability.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/probability.py -------------------------------------------------------------------------------- /src/schema_matching/collector/rows.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/rows.py -------------------------------------------------------------------------------- /src/schema_matching/collector/set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/set.py -------------------------------------------------------------------------------- /src/schema_matching/collector/tag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/tag.py -------------------------------------------------------------------------------- /src/schema_matching/collector/variance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/variance.py -------------------------------------------------------------------------------- /src/schema_matching/collector/weight.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/collector/weight.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/__init__.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/argparse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/argparse.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/distribution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/distribution.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/functional.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/iterator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/iterator.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/misc.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/operator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/operator.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/string.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/string.py -------------------------------------------------------------------------------- /src/schema_matching/utilities/timelimit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/src/schema_matching/utilities/timelimit.py -------------------------------------------------------------------------------- /tests/utilities/test_distribution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/davidfoerster/schema-matching/HEAD/tests/utilities/test_distribution.py --------------------------------------------------------------------------------