mirror of
https://github.com/ilri/csv-metadata-quality.git
synced 2025-05-10 15:16:01 +02:00
Compare commits
47 Commits
Author | SHA1 | Date | |
---|---|---|---|
cb07d357d4
|
|||
65cd48a26f
|
|||
0f883f640c
|
|||
f4c5c5781e
|
|||
6aa784ad8c
|
|||
7b8da94f41
|
|||
2a1566af62
|
|||
5fcaa63bd5
|
|||
aa9e23b46c
|
|||
73acb1661f
|
|||
2a068fddc4
|
|||
c6c2f13e88
|
|||
56f16e37ed
|
|||
0c44b967b6
|
|||
8a267bb40b
|
|||
8fda8f1ef1
|
|||
5e471813e8
|
|||
79244b9ac3
|
|||
5e81a33482
|
|||
28b5996aa6
|
|||
40ba9bae6c
|
|||
0b2d211455
|
|||
7f1df0b47c
|
|||
365ecda324
|
|||
550ce7fb7e
|
|||
705127fd28
|
|||
894e0a196d
|
|||
87181bc7b8
|
|||
8de5d862b6
|
|||
49e3543878
|
|||
403b253762
|
|||
c5fbaf407a
|
|||
4f81f6c83c
|
|||
4b9d1e060f
|
|||
c8a71e3143
|
|||
7964d98ca5
|
|||
64ffc2f1da
|
|||
7b1bc29a92
|
|||
f0110d8e74
|
|||
86498deee8
|
|||
251647a15f
|
|||
0bd28e22ec
|
|||
63fdce7d13
|
|||
f068c0e16a
|
|||
79b8f62a85
|
|||
6c1e132531
|
|||
c0f3c866bd
|
12
.build.yml
12
.build.yml
@ -1,19 +1,15 @@
|
||||
image: archlinux
|
||||
packages:
|
||||
- python-pipenv
|
||||
- python-poetry
|
||||
sources:
|
||||
- https://git.sr.ht/~alanorth/csv-metadata-quality
|
||||
tasks:
|
||||
- setup: |
|
||||
cd csv-metadata-quality
|
||||
pipenv install --dev
|
||||
poetry install
|
||||
- pytest: |
|
||||
cd csv-metadata-quality
|
||||
pipenv run pytest
|
||||
poetry run pytest
|
||||
- testcli: |
|
||||
cd csv-metadata-quality
|
||||
pipenv run pip install .
|
||||
pipenv run csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e -u --agrovoc-fields dc.subject,cg.coverage.country
|
||||
environment:
|
||||
PIPENV_NOSPIN: 'True'
|
||||
PIPENV_HIDE_EMOJIS: 'True'
|
||||
poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e -u --agrovoc-fields dc.subject,cg.coverage.country
|
||||
|
11
.travis.yml
11
.travis.yml
@ -1,11 +1,16 @@
|
||||
dist: xenial
|
||||
dist: bionic
|
||||
language: python
|
||||
python:
|
||||
- "3.6"
|
||||
- "3.7"
|
||||
- "3.8"
|
||||
- "3.8-dev" # 3.8 development branch
|
||||
jobs:
|
||||
allow_failures:
|
||||
- python: "3.8-dev"
|
||||
install:
|
||||
- "pip install pipenv --upgrade-strategy=only-if-needed"
|
||||
- "pipenv install --dev"
|
||||
- "pip install -r requirements.txt"
|
||||
- "pip install -r requirements-dev.txt"
|
||||
script: pytest
|
||||
|
||||
# vim: ts=2 sw=2 et
|
||||
|
29
CHANGELOG.md
29
CHANGELOG.md
@ -4,6 +4,35 @@ All notable changes to this project will be documented in this file.
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
||||
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
||||
|
||||
## [0.4.2] - 2020-07-06
|
||||
### Changed
|
||||
- Add field name to the output for more fixes and checks to help identify where
|
||||
the error is
|
||||
- Minor optimizations to AGROVOC subject lookup
|
||||
- Use Poetry instead of Pipenv
|
||||
|
||||
### Updated
|
||||
- Update python dependencies to latest versions
|
||||
|
||||
## [0.4.1] - 2020-01-15
|
||||
### Changed
|
||||
- Reduce minimum Python version to 3.6 by working around the `is_normalized()`
|
||||
that only works in Python >= 3.8
|
||||
|
||||
## [0.4.0] - 2020-01-15
|
||||
### Added
|
||||
- Unicode normalization (enable with `--unsafe-fixes`, see README.md)
|
||||
|
||||
### Updated
|
||||
- Update python dependencies to latest versions, including numpy 1.18.1, pandas
|
||||
1.0.0rc0, flake8 3.7.9, pytest 5.3.2, and black 19.10b0
|
||||
- Regenerate requirements.txt and requirements-dev.txt
|
||||
|
||||
### Changed
|
||||
- Use Python 3.8.0 for pipenv
|
||||
- Use Ubuntu 18.04 "Bionic" for TravisCI builds
|
||||
- Test Python 3.8 in TravisCI builds
|
||||
|
||||
## [0.3.1] - 2019-10-01
|
||||
## Changed
|
||||
- Replace non-breaking spaces (U+00A0) with space instead of removing them
|
||||
|
29
Pipfile
29
Pipfile
@ -1,29 +0,0 @@
|
||||
[[source]]
|
||||
name = "pypi"
|
||||
url = "https://pypi.org/simple"
|
||||
verify_ssl = true
|
||||
|
||||
[dev-packages]
|
||||
pytest = "*"
|
||||
ipython = "*"
|
||||
flake8 = "*"
|
||||
pytest-clarity = "*"
|
||||
black = "*"
|
||||
isort = "*"
|
||||
csvkit = "*"
|
||||
|
||||
[packages]
|
||||
pandas = "*"
|
||||
python-stdnum = "*"
|
||||
xlrd = "*"
|
||||
requests = "*"
|
||||
requests-cache = "*"
|
||||
pycountry = "*"
|
||||
csv-metadata-quality = {editable = true,path = "."}
|
||||
langid = "*"
|
||||
|
||||
[requires]
|
||||
python_version = "3.7"
|
||||
|
||||
[pipenv]
|
||||
allow_prereleases = true
|
555
Pipfile.lock
generated
555
Pipfile.lock
generated
@ -1,555 +0,0 @@
|
||||
{
|
||||
"_meta": {
|
||||
"hash": {
|
||||
"sha256": "59562d8c59eb09e23b49475d6901687edbf605f5b84e283e90cc8e2de518641f"
|
||||
},
|
||||
"pipfile-spec": 6,
|
||||
"requires": {
|
||||
"python_version": "3.7"
|
||||
},
|
||||
"sources": [
|
||||
{
|
||||
"name": "pypi",
|
||||
"url": "https://pypi.org/simple",
|
||||
"verify_ssl": true
|
||||
}
|
||||
]
|
||||
},
|
||||
"default": {
|
||||
"certifi": {
|
||||
"hashes": [
|
||||
"sha256:e4f3620cfea4f83eedc95b24abd9cd56f3c4b146dd0177e83a21b4eb49e21e50",
|
||||
"sha256:fd7c7c74727ddcf00e9acd26bba8da604ffec95bf1c2144e67aff7a8b50e6cef"
|
||||
],
|
||||
"version": "==2019.9.11"
|
||||
},
|
||||
"chardet": {
|
||||
"hashes": [
|
||||
"sha256:84ab92ed1c4d4f16916e05906b6b75a6c0fb5db821cc65e70cbd64a3e2a5eaae",
|
||||
"sha256:fc323ffcaeaed0e0a02bf4d117757b98aed530d9ed4531e3e15460124c106691"
|
||||
],
|
||||
"version": "==3.0.4"
|
||||
},
|
||||
"csv-metadata-quality": {
|
||||
"editable": true,
|
||||
"path": "."
|
||||
},
|
||||
"idna": {
|
||||
"hashes": [
|
||||
"sha256:c357b3f628cf53ae2c4c05627ecc484553142ca23264e593d327bcde5e9c3407",
|
||||
"sha256:ea8b7f6188e6fa117537c3df7da9fc686d485087abf6ac197f9c46432f7e4a3c"
|
||||
],
|
||||
"version": "==2.8"
|
||||
},
|
||||
"langid": {
|
||||
"hashes": [
|
||||
"sha256:044bcae1912dab85c33d8e98f2811b8f4ff1213e5e9a9e9510137b84da2cb293"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==1.1.6"
|
||||
},
|
||||
"numpy": {
|
||||
"hashes": [
|
||||
"sha256:05dbfe72684cc14b92568de1bc1f41e5f62b00f714afc9adee42f6311738091f",
|
||||
"sha256:0d82cb7271a577529d07bbb05cb58675f2deb09772175fab96dc8de025d8ac05",
|
||||
"sha256:10132aa1fef99adc85a905d82e8497a580f83739837d7cbd234649f2e9b9dc58",
|
||||
"sha256:12322df2e21f033a60c80319c25011194cd2a21294cc66fee0908aeae2c27832",
|
||||
"sha256:16f19b3aa775dddc9814e02a46b8e6ae6a54ed8cf143962b4e53f0471dbd7b16",
|
||||
"sha256:3d0b0989dd2d066db006158de7220802899a1e5c8cf622abe2d0bd158fd01c2c",
|
||||
"sha256:438a3f0e7b681642898fd7993d38e2bf140a2d1eafaf3e89bb626db7f50db355",
|
||||
"sha256:5fd214f482ab53f2cea57414c5fb3e58895b17df6e6f5bca5be6a0bb6aea23bb",
|
||||
"sha256:73615d3edc84dd7c4aeb212fa3748fb83217e00d201875a47327f55363cef2df",
|
||||
"sha256:7bd355ad7496f4ce1d235e9814ec81ee3d28308d591c067ce92e49f745ba2c2f",
|
||||
"sha256:7d077f2976b8f3de08a0dcf5d72083f4af5411e8fddacd662aae27baa2601196",
|
||||
"sha256:a4092682778dc48093e8bda8d26ee8360153e2047826f95a3f5eae09f0ae3abf",
|
||||
"sha256:b458de8624c9f6034af492372eb2fee41a8e605f03f4732f43fc099e227858b2",
|
||||
"sha256:e70fc8ff03a961f13363c2c95ef8285e0cf6a720f8271836f852cc0fa64e97c8",
|
||||
"sha256:ee8e9d7cad5fe6dde50ede0d2e978d81eafeaa6233fb0b8719f60214cf226578",
|
||||
"sha256:f4a4f6aba148858a5a5d546a99280f71f5ee6ec8182a7d195af1a914195b21a2"
|
||||
],
|
||||
"version": "==1.17.2"
|
||||
},
|
||||
"pandas": {
|
||||
"hashes": [
|
||||
"sha256:18d91a9199d1dfaa01ad645f7540370ba630bdcef09daaf9edf45b4b1bca0232",
|
||||
"sha256:3f26e5da310a0c0b83ea50da1fd397de2640b02b424aa69be7e0784228f656c9",
|
||||
"sha256:4182e32f4456d2c64619e97c58571fa5ca0993d1e8c2d9ca44916185e1726e15",
|
||||
"sha256:426e590e2eb0e60f765271d668a30cf38b582eaae5ec9b31229c8c3c10c5bc21",
|
||||
"sha256:5eb934a8f0dc358f0e0cdf314072286bbac74e4c124b64371395e94644d5d919",
|
||||
"sha256:717928808043d3ea55b9bcde636d4a52d2236c246f6df464163a66ff59980ad8",
|
||||
"sha256:8145f97c5ed71827a6ec98ceaef35afed1377e2d19c4078f324d209ff253ecb5",
|
||||
"sha256:8744c84c914dcc59cbbb2943b32b7664df1039d99e834e1034a3372acb89ea4d",
|
||||
"sha256:c1ac1d9590d0c9314ebf01591bd40d4c03d710bfc84a3889e5263c97d7891dee",
|
||||
"sha256:cb2e197b7b0687becb026b84d3c242482f20cbb29a9981e43604eb67576da9f6",
|
||||
"sha256:d4001b71ad2c9b84ff18b182cea22b7b6cbf624216da3ea06fb7af28d1f93165",
|
||||
"sha256:d8930772adccb2882989ab1493fa74bd87d47c8ac7417f5dd3dd834ba8c24dc9",
|
||||
"sha256:dfbb0173ee2399bc4ed3caf2d236e5c0092f948aafd0a15fbe4a0e77ee61a958",
|
||||
"sha256:eebfbba048f4fa8ac711b22c78516e16ff8117d05a580e7eeef6b0c2be554c18",
|
||||
"sha256:f1b21bc5cf3dbea53d33615d1ead892dfdae9d7052fa8898083bec88be20dcd2"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==0.25.1"
|
||||
},
|
||||
"pycountry": {
|
||||
"hashes": [
|
||||
"sha256:3c57aa40adcf293d59bebaffbe60d8c39976fba78d846a018dc0c2ec9c6cb3cb"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==19.8.18"
|
||||
},
|
||||
"python-dateutil": {
|
||||
"hashes": [
|
||||
"sha256:7e6584c74aeed623791615e26efd690f29817a27c73085b78e4bad02493df2fb",
|
||||
"sha256:c89805f6f4d64db21ed966fda138f8a5ed7a4fdbc1a8ee329ce1b74e3c74da9e"
|
||||
],
|
||||
"version": "==2.8.0"
|
||||
},
|
||||
"python-stdnum": {
|
||||
"hashes": [
|
||||
"sha256:d5f0af1bee9ddd9a20b398b46ce062dbd4d41fcc9646940f2667256a44df3854",
|
||||
"sha256:f445ec32bf5246c90389204cabba465f494545371c29a83fa2d30e6c872a6763"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==1.11"
|
||||
},
|
||||
"pytz": {
|
||||
"hashes": [
|
||||
"sha256:26c0b32e437e54a18161324a2fca3c4b9846b74a8dccddd843113109e1116b32",
|
||||
"sha256:c894d57500a4cd2d5c71114aaab77dbab5eabd9022308ce5ac9bb93a60a6f0c7"
|
||||
],
|
||||
"version": "==2019.2"
|
||||
},
|
||||
"requests": {
|
||||
"hashes": [
|
||||
"sha256:11e007a8a2aa0323f5a921e9e6a2d7e4e67d9877e85773fba9ba6419025cbeb4",
|
||||
"sha256:9cf5292fcd0f598c671cfc1e0d7d1a7f13bb8085e9a590f48c010551dc6c4b31"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==2.22.0"
|
||||
},
|
||||
"requests-cache": {
|
||||
"hashes": [
|
||||
"sha256:813023269686045f8e01e2289cc1e7e9ae5ab22ddd1e2849a9093ab3ab7270eb",
|
||||
"sha256:81e13559baee64677a7d73b85498a5a8f0639e204517b5d05ff378e44a57831a"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==0.5.2"
|
||||
},
|
||||
"six": {
|
||||
"hashes": [
|
||||
"sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
|
||||
"sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
|
||||
],
|
||||
"version": "==1.12.0"
|
||||
},
|
||||
"urllib3": {
|
||||
"hashes": [
|
||||
"sha256:3de946ffbed6e6746608990594d08faac602528ac7015ac28d33cee6a45b7398",
|
||||
"sha256:9a107b99a5393caf59c7aa3c1249c16e6879447533d0887f4336dde834c7be86"
|
||||
],
|
||||
"version": "==1.25.6"
|
||||
},
|
||||
"xlrd": {
|
||||
"hashes": [
|
||||
"sha256:546eb36cee8db40c3eaa46c351e67ffee6eeb5fa2650b71bc4c758a29a1b29b2",
|
||||
"sha256:e551fb498759fa3a5384a94ccd4c3c02eb7c00ea424426e212ac0c57be9dfbde"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==1.2.0"
|
||||
}
|
||||
},
|
||||
"develop": {
|
||||
"agate": {
|
||||
"hashes": [
|
||||
"sha256:48d6f80b35611c1ba25a642cbc5b90fcbdeeb2a54711c4a8d062ee2809334d1c",
|
||||
"sha256:c93aaa500b439d71e4a5cf088d0006d2ce2c76f1950960c8843114e5f361dfd3"
|
||||
],
|
||||
"version": "==1.6.1"
|
||||
},
|
||||
"agate-dbf": {
|
||||
"hashes": [
|
||||
"sha256:00c93c498ec9a04cc587bf63dd7340e67e2541f0df4c9a7259d7cb3dd4ce372f"
|
||||
],
|
||||
"version": "==0.2.1"
|
||||
},
|
||||
"agate-excel": {
|
||||
"hashes": [
|
||||
"sha256:8f255ef2c87c436b7132049e1dd86c8e08bf82d8c773aea86f3069b461a17d52"
|
||||
],
|
||||
"version": "==0.2.3"
|
||||
},
|
||||
"agate-sql": {
|
||||
"hashes": [
|
||||
"sha256:9277490ba8b8e7c747a9ae3671f52fe486784b48d4a14e78ca197fb0e36f281b"
|
||||
],
|
||||
"version": "==0.5.4"
|
||||
},
|
||||
"appdirs": {
|
||||
"hashes": [
|
||||
"sha256:9e5896d1372858f8dd3344faf4e5014d21849c756c8d5701f78f8a103b372d92",
|
||||
"sha256:d8b24664561d0d34ddfaec54636d502d7cea6e29c3eaf68f3df6180863e2166e"
|
||||
],
|
||||
"version": "==1.4.3"
|
||||
},
|
||||
"atomicwrites": {
|
||||
"hashes": [
|
||||
"sha256:03472c30eb2c5d1ba9227e4c2ca66ab8287fbfbbda3888aa93dc2e28fc6811b4",
|
||||
"sha256:75a9445bac02d8d058d5e1fe689654ba5a6556a1dfd8ce6ec55a0ed79866cfa6"
|
||||
],
|
||||
"version": "==1.3.0"
|
||||
},
|
||||
"attrs": {
|
||||
"hashes": [
|
||||
"sha256:69c0dbf2ed392de1cb5ec704444b08a5ef81680a61cb899dc08127123af36a79",
|
||||
"sha256:f0b870f674851ecbfbbbd364d6b5cbdff9dcedbc7f3f5e18a6891057f21fe399"
|
||||
],
|
||||
"version": "==19.1.0"
|
||||
},
|
||||
"babel": {
|
||||
"hashes": [
|
||||
"sha256:af92e6106cb7c55286b25b38ad7695f8b4efb36a90ba483d7f7a6628c46158ab",
|
||||
"sha256:e86135ae101e31e2c8ec20a4e0c5220f4eed12487d5cf3f78be7e98d3a57fc28"
|
||||
],
|
||||
"version": "==2.7.0"
|
||||
},
|
||||
"backcall": {
|
||||
"hashes": [
|
||||
"sha256:38ecd85be2c1e78f77fd91700c76e14667dc21e2713b63876c0eb901196e01e4",
|
||||
"sha256:bbbf4b1e5cd2bdb08f915895b51081c041bac22394fdfcfdfbe9f14b77c08bf2"
|
||||
],
|
||||
"version": "==0.1.0"
|
||||
},
|
||||
"black": {
|
||||
"hashes": [
|
||||
"sha256:09a9dcb7c46ed496a9850b76e4e825d6049ecd38b611f1224857a79bd985a8cf",
|
||||
"sha256:68950ffd4d9169716bcb8719a56c07a2f4485354fec061cdd5910aa07369731c"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==19.3b0"
|
||||
},
|
||||
"click": {
|
||||
"hashes": [
|
||||
"sha256:2335065e6395b9e67ca716de5f7526736bfa6ceead690adf616d925bdc622b13",
|
||||
"sha256:5b94b49521f6456670fdb30cd82a4eca9412788a93fa6dd6df72c94d5a8ff2d7"
|
||||
],
|
||||
"version": "==7.0"
|
||||
},
|
||||
"csvkit": {
|
||||
"hashes": [
|
||||
"sha256:1353a383531bee191820edfb88418c13dfe1cdfa9dd3dc46f431c05cd2a260a0"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==1.0.4"
|
||||
},
|
||||
"dbfread": {
|
||||
"hashes": [
|
||||
"sha256:07c8a9af06ffad3f6f03e8fe91ad7d2733e31a26d2b72c4dd4cfbae07ee3b73d",
|
||||
"sha256:f604def58c59694fa0160d7be5d0b8d594467278d2bb6a47d46daf7162c84cec"
|
||||
],
|
||||
"version": "==2.0.7"
|
||||
},
|
||||
"decorator": {
|
||||
"hashes": [
|
||||
"sha256:86156361c50488b84a3f148056ea716ca587df2f0de1d34750d35c21312725de",
|
||||
"sha256:f069f3a01830ca754ba5258fde2278454a0b5b79e0d7f5c13b3b97e57d4acff6"
|
||||
],
|
||||
"version": "==4.4.0"
|
||||
},
|
||||
"entrypoints": {
|
||||
"hashes": [
|
||||
"sha256:589f874b313739ad35be6e0cd7efde2a4e9b6fea91edcc34e58ecbb8dbe56d19",
|
||||
"sha256:c70dd71abe5a8c85e55e12c19bd91ccfeec11a6e99044204511f9ed547d48451"
|
||||
],
|
||||
"version": "==0.3"
|
||||
},
|
||||
"et-xmlfile": {
|
||||
"hashes": [
|
||||
"sha256:614d9722d572f6246302c4491846d2c393c199cfa4edc9af593437691683335b"
|
||||
],
|
||||
"version": "==1.0.1"
|
||||
},
|
||||
"flake8": {
|
||||
"hashes": [
|
||||
"sha256:19241c1cbc971b9962473e4438a2ca19749a7dd002dd1a946eaba171b4114548",
|
||||
"sha256:8e9dfa3cecb2400b3738a42c54c3043e821682b9c840b0448c0503f781130696"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==3.7.8"
|
||||
},
|
||||
"future": {
|
||||
"hashes": [
|
||||
"sha256:67045236dcfd6816dc439556d009594abf643e5eb48992e36beac09c2ca659b8"
|
||||
],
|
||||
"version": "==0.17.1"
|
||||
},
|
||||
"importlib-metadata": {
|
||||
"hashes": [
|
||||
"sha256:aa18d7378b00b40847790e7c27e11673d7fed219354109d0e7b9e5b25dc3ad26",
|
||||
"sha256:d5f18a79777f3aa179c145737780282e27b508fc8fd688cb17c7a813e8bd39af"
|
||||
],
|
||||
"markers": "python_version < '3.8'",
|
||||
"version": "==0.23"
|
||||
},
|
||||
"ipython": {
|
||||
"hashes": [
|
||||
"sha256:c4ab005921641e40a68e405e286e7a1fcc464497e14d81b6914b4fd95e5dee9b",
|
||||
"sha256:dd76831f065f17bddd7eaa5c781f5ea32de5ef217592cf019e34043b56895aa1"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==7.8.0"
|
||||
},
|
||||
"ipython-genutils": {
|
||||
"hashes": [
|
||||
"sha256:72dd37233799e619666c9f639a9da83c34013a73e8bbc79a7a6348d93c61fab8",
|
||||
"sha256:eb2e116e75ecef9d4d228fdc66af54269afa26ab4463042e33785b887c628ba8"
|
||||
],
|
||||
"version": "==0.2.0"
|
||||
},
|
||||
"isodate": {
|
||||
"hashes": [
|
||||
"sha256:2e364a3d5759479cdb2d37cce6b9376ea504db2ff90252a2e5b7cc89cc9ff2d8",
|
||||
"sha256:aa4d33c06640f5352aca96e4b81afd8ab3b47337cc12089822d6f322ac772c81"
|
||||
],
|
||||
"version": "==0.6.0"
|
||||
},
|
||||
"isort": {
|
||||
"hashes": [
|
||||
"sha256:54da7e92468955c4fceacd0c86bd0ec997b0e1ee80d97f67c35a78b719dccab1",
|
||||
"sha256:6e811fcb295968434526407adb8796944f1988c5b65e8139058f2014cbe100fd"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==4.3.21"
|
||||
},
|
||||
"jdcal": {
|
||||
"hashes": [
|
||||
"sha256:1abf1305fce18b4e8aa248cf8fe0c56ce2032392bc64bbd61b5dff2a19ec8bba",
|
||||
"sha256:472872e096eb8df219c23f2689fc336668bdb43d194094b5cc1707e1640acfc8"
|
||||
],
|
||||
"version": "==1.4.1"
|
||||
},
|
||||
"jedi": {
|
||||
"hashes": [
|
||||
"sha256:786b6c3d80e2f06fd77162a07fed81b8baa22dde5d62896a790a331d6ac21a27",
|
||||
"sha256:ba859c74fa3c966a22f2aeebe1b74ee27e2a462f56d3f5f7ca4a59af61bfe42e"
|
||||
],
|
||||
"version": "==0.15.1"
|
||||
},
|
||||
"leather": {
|
||||
"hashes": [
|
||||
"sha256:076d1603b5281488285718ce1a5ce78cf1027fe1e76adf9c548caf83c519b988",
|
||||
"sha256:e0bb36a6d5f59fbf3c1a6e75e7c8bee29e67f06f5b48c0134407dde612eba5e2"
|
||||
],
|
||||
"version": "==0.3.3"
|
||||
},
|
||||
"mccabe": {
|
||||
"hashes": [
|
||||
"sha256:ab8a6258860da4b6677da4bd2fe5dc2c659cff31b3ee4f7f5d64e79735b80d42",
|
||||
"sha256:dd8d182285a0fe56bace7f45b5e7d1a6ebcbf524e8f3bd87eb0f125271b8831f"
|
||||
],
|
||||
"version": "==0.6.1"
|
||||
},
|
||||
"more-itertools": {
|
||||
"hashes": [
|
||||
"sha256:409cd48d4db7052af495b09dec721011634af3753ae1ef92d2b32f73a745f832",
|
||||
"sha256:92b8c4b06dac4f0611c0729b2f2ede52b2e1bac1ab48f089c7ddc12e26bb60c4"
|
||||
],
|
||||
"version": "==7.2.0"
|
||||
},
|
||||
"openpyxl": {
|
||||
"hashes": [
|
||||
"sha256:340a1ab2069764559b9d58027a43a24db18db0e25deb80f81ecb8ca7ee5253db"
|
||||
],
|
||||
"version": "==3.0.0"
|
||||
},
|
||||
"packaging": {
|
||||
"hashes": [
|
||||
"sha256:28b924174df7a2fa32c1953825ff29c61e2f5e082343165438812f00d3a7fc47",
|
||||
"sha256:d9551545c6d761f3def1677baf08ab2a3ca17c56879e70fecba2fc4dde4ed108"
|
||||
],
|
||||
"version": "==19.2"
|
||||
},
|
||||
"parsedatetime": {
|
||||
"hashes": [
|
||||
"sha256:3d817c58fb9570d1eec1dd46fa9448cd644eeed4fb612684b02dfda3a79cb84b",
|
||||
"sha256:9ee3529454bf35c40a77115f5a596771e59e1aee8c53306f346c461b8e913094"
|
||||
],
|
||||
"version": "==2.4"
|
||||
},
|
||||
"parso": {
|
||||
"hashes": [
|
||||
"sha256:63854233e1fadb5da97f2744b6b24346d2750b85965e7e399bec1620232797dc",
|
||||
"sha256:666b0ee4a7a1220f65d367617f2cd3ffddff3e205f3f16a0284df30e774c2a9c"
|
||||
],
|
||||
"version": "==0.5.1"
|
||||
},
|
||||
"pexpect": {
|
||||
"hashes": [
|
||||
"sha256:2094eefdfcf37a1fdbfb9aa090862c1a4878e5c7e0e7e7088bdb511c558e5cd1",
|
||||
"sha256:9e2c1fd0e6ee3a49b28f95d4b33bc389c89b20af6a1255906e90ff1262ce62eb"
|
||||
],
|
||||
"markers": "sys_platform != 'win32'",
|
||||
"version": "==4.7.0"
|
||||
},
|
||||
"pickleshare": {
|
||||
"hashes": [
|
||||
"sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca",
|
||||
"sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56"
|
||||
],
|
||||
"version": "==0.7.5"
|
||||
},
|
||||
"pluggy": {
|
||||
"hashes": [
|
||||
"sha256:0db4b7601aae1d35b4a033282da476845aa19185c1e6964b25cf324b5e4ec3e6",
|
||||
"sha256:fa5fa1622fa6dd5c030e9cad086fa19ef6a0cf6d7a2d12318e10cb49d6d68f34"
|
||||
],
|
||||
"version": "==0.13.0"
|
||||
},
|
||||
"prompt-toolkit": {
|
||||
"hashes": [
|
||||
"sha256:11adf3389a996a6d45cc277580d0d53e8a5afd281d0c9ec71b28e6f121463780",
|
||||
"sha256:2519ad1d8038fd5fc8e770362237ad0364d16a7650fb5724af6997ed5515e3c1",
|
||||
"sha256:977c6583ae813a37dc1c2e1b715892461fcbdaa57f6fc62f33a528c4886c8f55"
|
||||
],
|
||||
"version": "==2.0.9"
|
||||
},
|
||||
"ptyprocess": {
|
||||
"hashes": [
|
||||
"sha256:923f299cc5ad920c68f2bc0bc98b75b9f838b93b599941a6b63ddbc2476394c0",
|
||||
"sha256:d7cc528d76e76342423ca640335bd3633420dc1366f258cb31d05e865ef5ca1f"
|
||||
],
|
||||
"version": "==0.6.0"
|
||||
},
|
||||
"py": {
|
||||
"hashes": [
|
||||
"sha256:64f65755aee5b381cea27766a3a147c3f15b9b6b9ac88676de66ba2ae36793fa",
|
||||
"sha256:dc639b046a6e2cff5bbe40194ad65936d6ba360b52b3c3fe1d08a82dd50b5e53"
|
||||
],
|
||||
"version": "==1.8.0"
|
||||
},
|
||||
"pycodestyle": {
|
||||
"hashes": [
|
||||
"sha256:95a2219d12372f05704562a14ec30bc76b05a5b297b21a5dfe3f6fac3491ae56",
|
||||
"sha256:e40a936c9a450ad81df37f549d676d127b1b66000a6c500caa2b085bc0ca976c"
|
||||
],
|
||||
"version": "==2.5.0"
|
||||
},
|
||||
"pyflakes": {
|
||||
"hashes": [
|
||||
"sha256:17dbeb2e3f4d772725c777fabc446d5634d1038f234e77343108ce445ea69ce0",
|
||||
"sha256:d976835886f8c5b31d47970ed689944a0262b5f3afa00a5a7b4dc81e5449f8a2"
|
||||
],
|
||||
"version": "==2.1.1"
|
||||
},
|
||||
"pygments": {
|
||||
"hashes": [
|
||||
"sha256:71e430bc85c88a430f000ac1d9b331d2407f681d6f6aec95e8bcfbc3df5b0127",
|
||||
"sha256:881c4c157e45f30af185c1ffe8d549d48ac9127433f2c380c24b84572ad66297"
|
||||
],
|
||||
"version": "==2.4.2"
|
||||
},
|
||||
"pyparsing": {
|
||||
"hashes": [
|
||||
"sha256:6f98a7b9397e206d78cc01df10131398f1c8b8510a2f4d97d9abd82e1aacdd80",
|
||||
"sha256:d9338df12903bbf5d65a0e4e87c2161968b10d2e489652bb47001d82a9b028b4"
|
||||
],
|
||||
"version": "==2.4.2"
|
||||
},
|
||||
"pytest": {
|
||||
"hashes": [
|
||||
"sha256:813b99704b22c7d377bbd756ebe56c35252bb710937b46f207100e843440b3c2",
|
||||
"sha256:cc6620b96bc667a0c8d4fa592a8c9c94178a1bd6cc799dbb057dfd9286d31a31"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==5.1.3"
|
||||
},
|
||||
"pytest-clarity": {
|
||||
"hashes": [
|
||||
"sha256:3f40d5ae7cb21cc95e622fc4f50d9466f80ae0f91460225b8c95c07afbf93e20"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==0.2.0a1"
|
||||
},
|
||||
"python-slugify": {
|
||||
"hashes": [
|
||||
"sha256:575d03256a132fc1efb4c52966c6eb11c57a13b071618f0b26076057a23f6937"
|
||||
],
|
||||
"version": "==3.0.4"
|
||||
},
|
||||
"pytimeparse": {
|
||||
"hashes": [
|
||||
"sha256:04b7be6cc8bd9f5647a6325444926c3ac34ee6bc7e69da4367ba282f076036bd",
|
||||
"sha256:e86136477be924d7e670646a98561957e8ca7308d44841e21f5ddea757556a0a"
|
||||
],
|
||||
"version": "==1.1.8"
|
||||
},
|
||||
"pytz": {
|
||||
"hashes": [
|
||||
"sha256:26c0b32e437e54a18161324a2fca3c4b9846b74a8dccddd843113109e1116b32",
|
||||
"sha256:c894d57500a4cd2d5c71114aaab77dbab5eabd9022308ce5ac9bb93a60a6f0c7"
|
||||
],
|
||||
"version": "==2019.2"
|
||||
},
|
||||
"six": {
|
||||
"hashes": [
|
||||
"sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
|
||||
"sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
|
||||
],
|
||||
"version": "==1.12.0"
|
||||
},
|
||||
"sqlalchemy": {
|
||||
"hashes": [
|
||||
"sha256:2f8ff566a4d3a92246d367f2e9cd6ed3edeef670dcd6dda6dfdc9efed88bcd80"
|
||||
],
|
||||
"version": "==1.3.8"
|
||||
},
|
||||
"termcolor": {
|
||||
"hashes": [
|
||||
"sha256:1d6d69ce66211143803fbc56652b41d73b4a400a2891d7bf7a1cdf4c02de613b"
|
||||
],
|
||||
"version": "==1.1.0"
|
||||
},
|
||||
"text-unidecode": {
|
||||
"hashes": [
|
||||
"sha256:1311f10e8b895935241623731c2ba64f4c455287888b18189350b67134a822e8",
|
||||
"sha256:bad6603bb14d279193107714b288be206cac565dfa49aa5b105294dd5c4aab93"
|
||||
],
|
||||
"version": "==1.3"
|
||||
},
|
||||
"toml": {
|
||||
"hashes": [
|
||||
"sha256:229f81c57791a41d65e399fc06bf0848bab550a9dfd5ed66df18ce5f05e73d5c",
|
||||
"sha256:235682dd292d5899d361a811df37e04a8828a5b1da3115886b73cf81ebc9100e"
|
||||
],
|
||||
"version": "==0.10.0"
|
||||
},
|
||||
"traitlets": {
|
||||
"hashes": [
|
||||
"sha256:262089114405f22f4833be96b31e143ab906d7764a22c04c71fee0bbda4787ba",
|
||||
"sha256:6ad5b30dacd5e2424c46cc94a0aeab990d98ae17d181acea2cc4272ac3409fca"
|
||||
],
|
||||
"version": "==4.3.3.dev0"
|
||||
},
|
||||
"wcwidth": {
|
||||
"hashes": [
|
||||
"sha256:3df37372226d6e63e1b1e1eda15c594bca98a22d33a23832a90998faa96bc65e",
|
||||
"sha256:f4ebe71925af7b40a864553f761ed559b43544f8f71746c2d756c7fe788ade7c"
|
||||
],
|
||||
"version": "==0.1.7"
|
||||
},
|
||||
"xlrd": {
|
||||
"hashes": [
|
||||
"sha256:546eb36cee8db40c3eaa46c351e67ffee6eeb5fa2650b71bc4c758a29a1b29b2",
|
||||
"sha256:e551fb498759fa3a5384a94ccd4c3c02eb7c00ea424426e212ac0c57be9dfbde"
|
||||
],
|
||||
"index": "pypi",
|
||||
"version": "==1.2.0"
|
||||
},
|
||||
"zipp": {
|
||||
"hashes": [
|
||||
"sha256:3718b1cbcd963c7d4c5511a8240812904164b7f381b647143a89d3b98f9bcd8e",
|
||||
"sha256:f06903e9f1f43b12d371004b4ac7b06ab39a44adc747266928ae6debfa7b3335"
|
||||
],
|
||||
"version": "==0.6.0"
|
||||
}
|
||||
}
|
||||
}
|
19
README.md
19
README.md
@ -1,7 +1,7 @@
|
||||
# CSV Metadata Quality [](https://travis-ci.org/ilri/csv-metadata-quality) [](https://builds.sr.ht/~alanorth/csv-metadata-quality?)
|
||||
A simple, but opinionated metadata quality checker and fixer designed to work with CSVs in the DSpace ecosystem (though it could theoretically work on any CSV that uses Dublin Core fields as columns). The implementation is essentially a pipeline of checks and fixes that begins with splitting multi-value fields on the standard DSpace "||" separator, trimming leading/trailing whitespace, and then proceeding to more specialized cases like ISSNs, ISBNs, languages, etc.
|
||||
|
||||
Requires Python 3.6 or greater. CSV and Excel support comes from the [Pandas](https://pandas.pydata.org/) library, though your mileage may vary with Excel because this is much less tested.
|
||||
Requires Python 3.8 or greater. CSV and Excel support comes from the [Pandas](https://pandas.pydata.org/) library, though your mileage may vary with Excel because this is much less tested.
|
||||
|
||||
## Functionality
|
||||
|
||||
@ -15,18 +15,19 @@ Requires Python 3.6 or greater. CSV and Excel support comes from the [Pandas](ht
|
||||
- Remove unnecessary Unicode like [non-breaking spaces](https://en.wikipedia.org/wiki/Non-breaking_space), [replacement characters](https://en.wikipedia.org/wiki/Specials_(Unicode_block)#Replacement_character), etc
|
||||
- Check for "suspicious" characters that indicate encoding or copy/paste issues, for example "foreˆt" should be "forêt"
|
||||
- Remove duplicate metadata values
|
||||
- Perform [Unicode normalization](https://withblue.ink/2019/03/11/why-you-need-to-normalize-unicode-strings.html) on strings using `--unsafe-fixes`
|
||||
|
||||
## Installation
|
||||
The easiest way to install CSV Metadata Quality is with [pipenv](https://github.com/pypa/pipenv):
|
||||
The easiest way to install CSV Metadata Quality is with [poetry](https://python-poetry.org):
|
||||
|
||||
```
|
||||
$ git clone https://github.com/ilri/csv-metadata-quality.git
|
||||
$ cd csv-metadata-quality
|
||||
$ pipenv install
|
||||
$ pipenv shell
|
||||
$ poetry install
|
||||
$ poetry shell
|
||||
```
|
||||
|
||||
Otherwise, if you don't have pipenv, you can use a vanilla Python virtual environment:
|
||||
Otherwise, if you don't have poetry, you can use a vanilla Python virtual environment:
|
||||
|
||||
```
|
||||
$ git clone https://github.com/ilri/csv-metadata-quality.git
|
||||
@ -58,6 +59,14 @@ This is considered "unsafe" because it is *theoretically* possible for a single
|
||||
### Newlines
|
||||
This is considered "unsafe" because some systems give special importance to vertical space and render it properly. DSpace does not support rendering newlines in its XMLUI and has, at times, suffered from parsing errors that cause the import process to fail if an input file had newlines. The `--unsafe-fixes` option strips Unix line feeds (U+000A).
|
||||
|
||||
### Unicode Normalization
|
||||
[Unicode](https://en.wikipedia.org/wiki/Unicode) is a standard for encoding text. As the standard aims to support most of the world's languages, characters can often be represented in different ways and still be valid Unicode. This leads to interesting problems that can be confusing unless you know what's going on behind the scenes. For example, the characters `é` and `é` *look* the same, but are not — technically they refer to different code points in the Unicode standard:
|
||||
|
||||
- `é` is the Unicode code point `U+00E9`
|
||||
- `é` is the Unicode code points `U+0065` + `U+0301`
|
||||
|
||||
Read more about [Unicode normalization](https://withblue.ink/2019/03/11/why-you-need-to-normalize-unicode-strings.html).
|
||||
|
||||
## AGROVOC Validation
|
||||
You can enable validation of metadata values in certain fields against the AGROVOC REST API with the `--agrovoc-fields` option. For example, in addition to agricultural subjects, many countries and regions are also present AGROVOC. Enable this validation by specifying a comma-separated list of fields:
|
||||
|
||||
|
@ -21,7 +21,8 @@ def parse_args(argv):
|
||||
parser.add_argument(
|
||||
"--experimental-checks",
|
||||
"-e",
|
||||
help="Enable experimental checks like language detection", action="store_true"
|
||||
help="Enable experimental checks like language detection",
|
||||
action="store_true",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--input-file",
|
||||
@ -81,7 +82,7 @@ def run(argv):
|
||||
continue
|
||||
|
||||
# Fix: whitespace
|
||||
df[column] = df[column].apply(fix.whitespace)
|
||||
df[column] = df[column].apply(fix.whitespace, field_name=column)
|
||||
|
||||
# Fix: newlines
|
||||
if args.unsafe_fixes:
|
||||
@ -94,23 +95,28 @@ def run(argv):
|
||||
if match is not None:
|
||||
df[column] = df[column].apply(fix.comma_space, field_name=column)
|
||||
|
||||
# Fix: perform Unicode normalization (NFC) to convert decomposed
|
||||
# characters into their canonical forms.
|
||||
if args.unsafe_fixes:
|
||||
df[column] = df[column].apply(fix.normalize_unicode, field_name=column)
|
||||
|
||||
# Fix: unnecessary Unicode
|
||||
df[column] = df[column].apply(fix.unnecessary_unicode)
|
||||
|
||||
# Check: invalid multi-value separator
|
||||
df[column] = df[column].apply(check.separators)
|
||||
df[column] = df[column].apply(check.separators, field_name=column)
|
||||
|
||||
# Check: suspicious characters
|
||||
df[column] = df[column].apply(check.suspicious_characters, field_name=column)
|
||||
|
||||
# Fix: invalid multi-value separator
|
||||
if args.unsafe_fixes:
|
||||
df[column] = df[column].apply(fix.separators)
|
||||
df[column] = df[column].apply(fix.separators, field_name=column)
|
||||
# Run whitespace fix again after fixing invalid separators
|
||||
df[column] = df[column].apply(fix.whitespace)
|
||||
df[column] = df[column].apply(fix.whitespace, field_name=column)
|
||||
|
||||
# Fix: duplicate metadata values
|
||||
df[column] = df[column].apply(fix.duplicates)
|
||||
df[column] = df[column].apply(fix.duplicates, field_name=column)
|
||||
|
||||
# Check: invalid AGROVOC subject
|
||||
if args.agrovoc_fields:
|
||||
|
@ -51,7 +51,7 @@ def isbn(field):
|
||||
return field
|
||||
|
||||
|
||||
def separators(field):
|
||||
def separators(field, field_name):
|
||||
"""Check for invalid multi-value separators (ie "|" or "|||").
|
||||
|
||||
Prints the field with the invalid multi-value separator.
|
||||
@ -70,7 +70,7 @@ def separators(field):
|
||||
match = re.findall(r"^.*?\|.*$", value)
|
||||
|
||||
if match:
|
||||
print(f"Invalid multi-value separator: {field}")
|
||||
print(f"Invalid multi-value separator ({field_name}): {field}")
|
||||
|
||||
return field
|
||||
|
||||
@ -221,22 +221,21 @@ def agrovoc(field, field_name):
|
||||
if pd.isna(field):
|
||||
return
|
||||
|
||||
# enable transparent request cache with thirty days expiry
|
||||
expire_after = timedelta(days=30)
|
||||
requests_cache.install_cache(
|
||||
"agrovoc-response-cache", expire_after=expire_after
|
||||
)
|
||||
|
||||
# prune old cache entries
|
||||
requests_cache.core.remove_expired_responses()
|
||||
|
||||
# Try to split multi-value field on "||" separator
|
||||
for value in field.split("||"):
|
||||
request_url = (
|
||||
f"http://agrovoc.uniroma2.it/agrovoc/rest/v1/agrovoc/search?query={value}"
|
||||
)
|
||||
request_url = "http://agrovoc.uniroma2.it/agrovoc/rest/v1/agrovoc/search"
|
||||
request_params = {"query": value}
|
||||
|
||||
# enable transparent request cache with thirty days expiry
|
||||
expire_after = timedelta(days=30)
|
||||
requests_cache.install_cache(
|
||||
"agrovoc-response-cache", expire_after=expire_after
|
||||
)
|
||||
|
||||
request = requests.get(request_url)
|
||||
|
||||
# prune old cache entries
|
||||
requests_cache.core.remove_expired_responses()
|
||||
request = requests.get(request_url, params=request_params)
|
||||
|
||||
if request.status_code == requests.codes.ok:
|
||||
data = request.json()
|
||||
|
@ -3,7 +3,7 @@ import re
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def whitespace(field):
|
||||
def whitespace(field, field_name):
|
||||
"""Fix whitespace issues.
|
||||
|
||||
Return string with leading, trailing, and consecutive whitespace trimmed.
|
||||
@ -26,7 +26,7 @@ def whitespace(field):
|
||||
match = re.findall(pattern, value)
|
||||
|
||||
if match:
|
||||
print(f"Removing excessive whitespace: {value}")
|
||||
print(f"Removing excessive whitespace ({field_name}): {value}")
|
||||
value = re.sub(pattern, " ", value)
|
||||
|
||||
# Save cleaned value
|
||||
@ -38,7 +38,7 @@ def whitespace(field):
|
||||
return new_field
|
||||
|
||||
|
||||
def separators(field):
|
||||
def separators(field, field_name):
|
||||
"""Fix for invalid multi-value separators (ie "|")."""
|
||||
|
||||
# Skip fields with missing values
|
||||
@ -55,7 +55,7 @@ def separators(field):
|
||||
match = re.findall(pattern, value)
|
||||
|
||||
if match:
|
||||
print(f"Fixing invalid multi-value separator: {value}")
|
||||
print(f"Fixing invalid multi-value separator ({field_name}): {value}")
|
||||
|
||||
value = re.sub(pattern, "||", value)
|
||||
|
||||
@ -121,7 +121,7 @@ def unnecessary_unicode(field):
|
||||
return field
|
||||
|
||||
|
||||
def duplicates(field):
|
||||
def duplicates(field, field_name):
|
||||
"""Remove duplicate metadata values."""
|
||||
|
||||
# Skip fields with missing values
|
||||
@ -140,7 +140,7 @@ def duplicates(field):
|
||||
if value not in new_values:
|
||||
new_values.append(value)
|
||||
else:
|
||||
print(f"Removing duplicate value: {value}")
|
||||
print(f"Removing duplicate value ({field_name}): {value}")
|
||||
|
||||
# Create a new field consisting of all values joined with "||"
|
||||
new_field = "||".join(new_values)
|
||||
@ -201,3 +201,27 @@ def comma_space(field, field_name):
|
||||
field = re.sub(r",(\w)", r", \1", field)
|
||||
|
||||
return field
|
||||
|
||||
|
||||
def normalize_unicode(field, field_name):
|
||||
"""Fix occurrences of decomposed Unicode characters by normalizing them
|
||||
with NFC to their canonical forms, for example:
|
||||
|
||||
Ouédraogo, Mathieu → Ouédraogo, Mathieu
|
||||
|
||||
Return normalized string.
|
||||
"""
|
||||
|
||||
from csv_metadata_quality.util import is_nfc
|
||||
from unicodedata import normalize
|
||||
|
||||
# Skip fields with missing values
|
||||
if pd.isna(field):
|
||||
return
|
||||
|
||||
# Check if the current string is using normalized Unicode (NFC)
|
||||
if not is_nfc(field):
|
||||
print(f"Normalizing Unicode ({field_name}): {field}")
|
||||
field = normalize("NFC", field)
|
||||
|
||||
return field
|
||||
|
14
csv_metadata_quality/util.py
Normal file
14
csv_metadata_quality/util.py
Normal file
@ -0,0 +1,14 @@
|
||||
def is_nfc(field):
|
||||
"""Utility function to check whether a string is using normalized Unicode.
|
||||
Python's built-in unicodedata library has the is_normalized() function, but
|
||||
it was only introduced in Python 3.8. By using a simple utility function we
|
||||
are able to run on Python >= 3.6 again.
|
||||
|
||||
See: https://docs.python.org/3/library/unicodedata.html
|
||||
|
||||
Return boolean.
|
||||
"""
|
||||
|
||||
from unicodedata import normalize
|
||||
|
||||
return field == normalize("NFC", field)
|
@ -1 +1 @@
|
||||
VERSION = "0.3.1"
|
||||
VERSION = "0.4.2"
|
||||
|
@ -26,3 +26,5 @@ Unneccesary unicode (U+002D + U+00AD),2019-08-10,,978-92-9043-823-6,,,,
|
||||
"Missing space,after comma",2019-08-27,,,,,,
|
||||
Incorrect ISO 639-1 language,2019-09-26,,,es,,,
|
||||
Incorrect ISO 639-3 language,2019-09-26,,,spa,,,
|
||||
Composéd Unicode,2020-01-14,,,,,,
|
||||
Decomposéd Unicode,2020-01-14,,,,,,
|
||||
|
|
1130
poetry.lock
generated
Normal file
1130
poetry.lock
generated
Normal file
File diff suppressed because it is too large
Load Diff
31
pyproject.toml
Normal file
31
pyproject.toml
Normal file
@ -0,0 +1,31 @@
|
||||
[tool.poetry]
|
||||
name = "csv-metadata-quality"
|
||||
version = "0.4.2"
|
||||
description="A simple, but opinionated CSV quality checking and fixing pipeline for CSVs in the DSpace ecosystem."
|
||||
authors = ["Alan Orth <alan.orth@gmail.com>"]
|
||||
license="GPL-3.0-only"
|
||||
repository = "https://github.com/ilri/csv-metadata-quality"
|
||||
homepage = "https://github.com/ilri/csv-metadata-quality"
|
||||
|
||||
[tool.poetry.dependencies]
|
||||
python = "^3.8"
|
||||
pandas = "^1.0.4"
|
||||
python-stdnum = "^1.13"
|
||||
xlrd = "^1.2.0"
|
||||
requests = "^2.23.0"
|
||||
requests-cache = "^0.5.2"
|
||||
pycountry = "^19.8.18"
|
||||
langid = "^1.1.6"
|
||||
|
||||
[tool.poetry.dev-dependencies]
|
||||
pytest = "^5.4.2"
|
||||
ipython = "^7.15.0"
|
||||
flake8 = "^3.8.2"
|
||||
pytest-clarity = "^0.3.0-alpha.0"
|
||||
black = "^19.10b0"
|
||||
isort = "^4.3.21"
|
||||
csvkit = "^1.0.5"
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry>=0.12"]
|
||||
build-backend = "poetry.masonry.api"
|
@ -1,57 +1,300 @@
|
||||
-i https://pypi.org/simple
|
||||
agate-dbf==0.2.1
|
||||
agate-excel==0.2.3
|
||||
agate-sql==0.5.4
|
||||
agate==1.6.1
|
||||
appdirs==1.4.3
|
||||
atomicwrites==1.3.0
|
||||
attrs==19.1.0
|
||||
babel==2.7.0
|
||||
backcall==0.1.0
|
||||
black==19.3b0
|
||||
click==7.0
|
||||
csvkit==1.0.4
|
||||
dbfread==2.0.7
|
||||
decorator==4.4.0
|
||||
entrypoints==0.3
|
||||
et-xmlfile==1.0.1
|
||||
flake8==3.7.8
|
||||
future==0.17.1
|
||||
importlib-metadata==0.23 ; python_version < '3.8'
|
||||
ipython-genutils==0.2.0
|
||||
ipython==7.8.0
|
||||
isodate==0.6.0
|
||||
isort==4.3.21
|
||||
jdcal==1.4.1
|
||||
jedi==0.15.1
|
||||
leather==0.3.3
|
||||
mccabe==0.6.1
|
||||
more-itertools==7.2.0
|
||||
openpyxl==3.0.0
|
||||
packaging==19.2
|
||||
parsedatetime==2.4
|
||||
parso==0.5.1
|
||||
pexpect==4.7.0 ; sys_platform != 'win32'
|
||||
pickleshare==0.7.5
|
||||
pluggy==0.13.0
|
||||
prompt-toolkit==2.0.9
|
||||
ptyprocess==0.6.0
|
||||
py==1.8.0
|
||||
pycodestyle==2.5.0
|
||||
pyflakes==2.1.1
|
||||
pygments==2.4.2
|
||||
pyparsing==2.4.2
|
||||
pytest-clarity==0.2.0a1
|
||||
pytest==5.1.3
|
||||
python-slugify==3.0.4
|
||||
pytimeparse==1.1.8
|
||||
pytz==2019.2
|
||||
six==1.12.0
|
||||
sqlalchemy==1.3.8
|
||||
termcolor==1.1.0
|
||||
text-unidecode==1.3
|
||||
toml==0.10.0
|
||||
traitlets==4.3.3.dev0
|
||||
wcwidth==0.1.7
|
||||
xlrd==1.2.0
|
||||
zipp==0.6.0
|
||||
agate==1.6.1 \
|
||||
--hash=sha256:48d6f80b35611c1ba25a642cbc5b90fcbdeeb2a54711c4a8d062ee2809334d1c \
|
||||
--hash=sha256:c93aaa500b439d71e4a5cf088d0006d2ce2c76f1950960c8843114e5f361dfd3
|
||||
agate-dbf==0.2.1 \
|
||||
--hash=sha256:00c93c498ec9a04cc587bf63dd7340e67e2541f0df4c9a7259d7cb3dd4ce372f \
|
||||
--hash=sha256:f618fadb413d41468c90d72fca945681d82d9e4d1b3d89f9bda52e607b828c0b
|
||||
agate-excel==0.2.3 \
|
||||
--hash=sha256:8f255ef2c87c436b7132049e1dd86c8e08bf82d8c773aea86f3069b461a17d52
|
||||
agate-sql==0.5.4 \
|
||||
--hash=sha256:9277490ba8b8e7c747a9ae3671f52fe486784b48d4a14e78ca197fb0e36f281b
|
||||
appdirs==1.4.4 \
|
||||
--hash=sha256:a841dacd6b99318a741b166adb07e19ee71a274450e68237b4650ca1055ab128 \
|
||||
--hash=sha256:7d5d0167b2b1ba821647616af46a749d1c653740dd0d2415100fe26e27afdf41
|
||||
appnope==0.1.0; sys_platform == "darwin" \
|
||||
--hash=sha256:5b26757dc6f79a3b7dc9fab95359328d5747fcb2409d331ea66d0272b90ab2a0 \
|
||||
--hash=sha256:8b995ffe925347a2138d7ac0fe77155e4311a0ea6d6da4f5128fe4b3cbe5ed71
|
||||
atomicwrites==1.4.0; sys_platform == "win32" \
|
||||
--hash=sha256:6d1784dea7c0c8d4a5172b6c620f40b6e4cbfdf96d783691f2e1302a7b88e197 \
|
||||
--hash=sha256:ae70396ad1a434f9c7046fd2dd196fc04b12f9e91ffb859164193be8b6168a7a
|
||||
attrs==19.3.0 \
|
||||
--hash=sha256:08a96c641c3a74e44eb59afb61a24f2cb9f4d7188748e76ba4bb5edfa3cb7d1c \
|
||||
--hash=sha256:f7b7ce16570fe9965acd6d30101a28f62fb4a7f9e926b3bbc9b61f8b04247e72
|
||||
babel==2.8.0 \
|
||||
--hash=sha256:d670ea0b10f8b723672d3a6abeb87b565b244da220d76b4dba1b66269ec152d4 \
|
||||
--hash=sha256:1aac2ae2d0d8ea368fa90906567f5c08463d98ade155c0c4bfedd6a0f7160e38
|
||||
backcall==0.2.0 \
|
||||
--hash=sha256:fbbce6a29f263178a1f7915c1940bde0ec2b2a967566fe1c65c1dfb7422bd255 \
|
||||
--hash=sha256:5cbdbf27be5e7cfadb448baf0aa95508f91f2bbc6c6437cd9cd06e2a4c215e1e
|
||||
black==19.10b0 \
|
||||
--hash=sha256:1b30e59be925fafc1ee4565e5e08abef6b03fe455102883820fe5ee2e4734e0b \
|
||||
--hash=sha256:c2edb73a08e9e0e6f65a0e6af18b059b8b1cdd5bef997d7a0b181df93dc81539
|
||||
certifi==2020.6.20 \
|
||||
--hash=sha256:8fc0819f1f30ba15bdb34cceffb9ef04d99f420f68eb75d901e9560b8749fc41 \
|
||||
--hash=sha256:5930595817496dd21bb8dc35dad090f1c2cd0adfaf21204bf6732ca5d8ee34d3
|
||||
chardet==3.0.4 \
|
||||
--hash=sha256:fc323ffcaeaed0e0a02bf4d117757b98aed530d9ed4531e3e15460124c106691 \
|
||||
--hash=sha256:84ab92ed1c4d4f16916e05906b6b75a6c0fb5db821cc65e70cbd64a3e2a5eaae
|
||||
click==7.1.2 \
|
||||
--hash=sha256:dacca89f4bfadd5de3d7489b7c8a566eee0d3676333fbb50030263894c38c0dc \
|
||||
--hash=sha256:d2b5255c7c6349bc1bd1e59e08cd12acbbd63ce649f2588755783aa94dfb6b1a
|
||||
colorama==0.4.3; sys_platform == "win32" \
|
||||
--hash=sha256:7d73d2a99753107a36ac6b455ee49046802e59d9d076ef8e47b61499fa29afff \
|
||||
--hash=sha256:e96da0d330793e2cb9485e9ddfd918d456036c7149416295932478192f4436a1
|
||||
csvkit==1.0.5 \
|
||||
--hash=sha256:7bd390f4d300e45dc9ed67a32af762a916bae7d9a85087a10fd4f64ce65fd5b9
|
||||
dbfread==2.0.7 \
|
||||
--hash=sha256:f604def58c59694fa0160d7be5d0b8d594467278d2bb6a47d46daf7162c84cec \
|
||||
--hash=sha256:07c8a9af06ffad3f6f03e8fe91ad7d2733e31a26d2b72c4dd4cfbae07ee3b73d
|
||||
decorator==4.4.2 \
|
||||
--hash=sha256:41fa54c2a0cc4ba648be4fd43cff00aedf5b9465c9bf18d64325bc225f08f760 \
|
||||
--hash=sha256:e3a62f0520172440ca0dcc823749319382e377f37f140a0b99ef45fecb84bfe7
|
||||
et-xmlfile==1.0.1 \
|
||||
--hash=sha256:614d9722d572f6246302c4491846d2c393c199cfa4edc9af593437691683335b
|
||||
flake8==3.8.3 \
|
||||
--hash=sha256:15e351d19611c887e482fb960eae4d44845013cc142d42896e9862f775d8cf5c \
|
||||
--hash=sha256:f04b9fcbac03b0a3e58c0ab3a0ecc462e023a9faf046d57794184028123aa208
|
||||
idna==2.10 \
|
||||
--hash=sha256:b97d804b1e9b523befed77c48dacec60e6dcb0b5391d57af6a65a312a90648c0 \
|
||||
--hash=sha256:b307872f855b18632ce0c21c5e45be78c0ea7ae4c15c828c20788b26921eb3f6
|
||||
ipython==7.16.1 \
|
||||
--hash=sha256:2dbcc8c27ca7d3cfe4fcdff7f45b27f9a8d3edfa70ff8024a71c7a8eb5f09d64 \
|
||||
--hash=sha256:9f4fcb31d3b2c533333893b9172264e4821c1ac91839500f31bd43f2c59b3ccf
|
||||
ipython-genutils==0.2.0 \
|
||||
--hash=sha256:72dd37233799e619666c9f639a9da83c34013a73e8bbc79a7a6348d93c61fab8 \
|
||||
--hash=sha256:eb2e116e75ecef9d4d228fdc66af54269afa26ab4463042e33785b887c628ba8
|
||||
isodate==0.6.0 \
|
||||
--hash=sha256:aa4d33c06640f5352aca96e4b81afd8ab3b47337cc12089822d6f322ac772c81 \
|
||||
--hash=sha256:2e364a3d5759479cdb2d37cce6b9376ea504db2ff90252a2e5b7cc89cc9ff2d8
|
||||
isort==4.3.21 \
|
||||
--hash=sha256:6e811fcb295968434526407adb8796944f1988c5b65e8139058f2014cbe100fd \
|
||||
--hash=sha256:54da7e92468955c4fceacd0c86bd0ec997b0e1ee80d97f67c35a78b719dccab1
|
||||
jdcal==1.4.1 \
|
||||
--hash=sha256:1abf1305fce18b4e8aa248cf8fe0c56ce2032392bc64bbd61b5dff2a19ec8bba \
|
||||
--hash=sha256:472872e096eb8df219c23f2689fc336668bdb43d194094b5cc1707e1640acfc8
|
||||
jedi==0.17.1 \
|
||||
--hash=sha256:1ddb0ec78059e8e27ec9eb5098360b4ea0a3dd840bedf21415ea820c21b40a22 \
|
||||
--hash=sha256:807d5d4f96711a2bcfdd5dfa3b1ae6d09aa53832b182090b222b5efb81f52f63
|
||||
langid==1.1.6 \
|
||||
--hash=sha256:044bcae1912dab85c33d8e98f2811b8f4ff1213e5e9a9e9510137b84da2cb293
|
||||
leather==0.3.3 \
|
||||
--hash=sha256:e0bb36a6d5f59fbf3c1a6e75e7c8bee29e67f06f5b48c0134407dde612eba5e2 \
|
||||
--hash=sha256:076d1603b5281488285718ce1a5ce78cf1027fe1e76adf9c548caf83c519b988
|
||||
mccabe==0.6.1 \
|
||||
--hash=sha256:ab8a6258860da4b6677da4bd2fe5dc2c659cff31b3ee4f7f5d64e79735b80d42 \
|
||||
--hash=sha256:dd8d182285a0fe56bace7f45b5e7d1a6ebcbf524e8f3bd87eb0f125271b8831f
|
||||
more-itertools==8.4.0 \
|
||||
--hash=sha256:68c70cc7167bdf5c7c9d8f6954a7837089c6a36bf565383919bb595efb8a17e5 \
|
||||
--hash=sha256:b78134b2063dd214000685165d81c154522c3ee0a1c0d4d113c80361c234c5a2
|
||||
numpy==1.19.0 \
|
||||
--hash=sha256:63d971bb211ad3ca37b2adecdd5365f40f3b741a455beecba70fd0dde8b2a4cb \
|
||||
--hash=sha256:b6aaeadf1e4866ca0fdf7bb4eed25e521ae21a7947c59f78154b24fc7abbe1dd \
|
||||
--hash=sha256:13af0184177469192d80db9bd02619f6fa8b922f9f327e077d6f2a6acb1ce1c0 \
|
||||
--hash=sha256:356f96c9fbec59974a592452ab6a036cd6f180822a60b529a975c9467fcd5f23 \
|
||||
--hash=sha256:fa1fe75b4a9e18b66ae7f0b122543c42debcf800aaafa0212aaff3ad273c2596 \
|
||||
--hash=sha256:cbe326f6d364375a8e5a8ccb7e9cd73f4b2f6dc3b2ed205633a0db8243e2a96a \
|
||||
--hash=sha256:a2e3a39f43f0ce95204beb8fe0831199542ccab1e0c6e486a0b4947256215632 \
|
||||
--hash=sha256:7b852817800eb02e109ae4a9cef2beda8dd50d98b76b6cfb7b5c0099d27b52d4 \
|
||||
--hash=sha256:d97a86937cf9970453c3b62abb55a6475f173347b4cde7f8dcdb48c8e1b9952d \
|
||||
--hash=sha256:a86c962e211f37edd61d6e11bb4df7eddc4a519a38a856e20a6498c319efa6b0 \
|
||||
--hash=sha256:d34fbb98ad0d6b563b95de852a284074514331e6b9da0a9fc894fb1cdae7a79e \
|
||||
--hash=sha256:658624a11f6e1c252b2cd170d94bf28c8f9410acab9f2fd4369e11e1cd4e1aaf \
|
||||
--hash=sha256:4d054f013a1983551254e2379385e359884e5af105e3efe00418977d02f634a7 \
|
||||
--hash=sha256:26a45798ca2a4e168d00de75d4a524abf5907949231512f372b217ede3429e98 \
|
||||
--hash=sha256:3c40c827d36c6d1c3cf413694d7dc843d50997ebffbc7c87d888a203ed6403a7 \
|
||||
--hash=sha256:be62aeff8f2f054eff7725f502f6228298891fd648dc2630e03e44bf63e8cee0 \
|
||||
--hash=sha256:dd53d7c4a69e766e4900f29db5872f5824a06827d594427cf1a4aa542818b796 \
|
||||
--hash=sha256:30a59fb41bb6b8c465ab50d60a1b298d1cd7b85274e71f38af5a75d6c475d2d2 \
|
||||
--hash=sha256:df1889701e2dfd8ba4dc9b1a010f0a60950077fb5242bb92c8b5c7f1a6f2668a \
|
||||
--hash=sha256:33c623ef9ca5e19e05991f127c1be5aeb1ab5cdf30cb1c5cf3960752e58b599b \
|
||||
--hash=sha256:26f509450db547e4dfa3ec739419b31edad646d21fb8d0ed0734188b35ff6b27 \
|
||||
--hash=sha256:7b57f26e5e6ee2f14f960db46bd58ffdca25ca06dd997729b1b179fddd35f5a3 \
|
||||
--hash=sha256:a8705c5073fe3fcc297fb8e0b31aa794e05af6a329e81b7ca4ffecab7f2b95ef \
|
||||
--hash=sha256:c2edbb783c841e36ca0fa159f0ae97a88ce8137fb3a6cd82eae77349ba4b607b \
|
||||
--hash=sha256:8cde829f14bd38f6da7b2954be0f2837043e8b8d7a9110ec5e318ae6bf706610 \
|
||||
--hash=sha256:76766cc80d6128750075378d3bb7812cf146415bd29b588616f72c943c00d598
|
||||
openpyxl==3.0.4 \
|
||||
--hash=sha256:6e62f058d19b09b95d20ebfbfb04857ad08d0833190516c1660675f699c6186f \
|
||||
--hash=sha256:d88dd1480668019684c66cfff3e52a5de4ed41e9df5dd52e008cbf27af0dbf87
|
||||
packaging==20.4 \
|
||||
--hash=sha256:998416ba6962ae7fbd6596850b80e17859a5753ba17c32284f67bfff33784181 \
|
||||
--hash=sha256:4357f74f47b9c12db93624a82154e9b120fa8293699949152b22065d556079f8
|
||||
pandas==1.0.5 \
|
||||
--hash=sha256:faa42a78d1350b02a7d2f0dbe3c80791cf785663d6997891549d0f86dc49125e \
|
||||
--hash=sha256:9c31d52f1a7dd2bb4681d9f62646c7aa554f19e8e9addc17e8b1b20011d7522d \
|
||||
--hash=sha256:8778a5cc5a8437a561e3276b85367412e10ae9fff07db1eed986e427d9a674f8 \
|
||||
--hash=sha256:9871ef5ee17f388f1cb35f76dc6106d40cb8165c562d573470672f4cdefa59ef \
|
||||
--hash=sha256:35b670b0abcfed7cad76f2834041dcf7ae47fd9b22b63622d67cdc933d79f453 \
|
||||
--hash=sha256:c9410ce8a3dee77653bc0684cfa1535a7f9c291663bd7ad79e39f5ab58f67ab3 \
|
||||
--hash=sha256:02f1e8f71cd994ed7fcb9a35b6ddddeb4314822a0e09a9c5b2d278f8cb5d4096 \
|
||||
--hash=sha256:b3c4f93fcb6e97d993bf87cdd917883b7dab7d20c627699f360a8fb49e9e0b91 \
|
||||
--hash=sha256:5759edf0b686b6f25a5d4a447ea588983a33afc8a0081a0954184a4a87fd0dd7 \
|
||||
--hash=sha256:ab8173a8efe5418bbe50e43f321994ac6673afc5c7c4839014cf6401bbdd0705 \
|
||||
--hash=sha256:13f75fb18486759da3ff40f5345d9dd20e7d78f2a39c5884d013456cec9876f0 \
|
||||
--hash=sha256:5a7cf6044467c1356b2b49ef69e50bf4d231e773c3ca0558807cdba56b76820b \
|
||||
--hash=sha256:ae961f1f0e270f1e4e2273f6a539b2ea33248e0e3a11ffb479d757918a5e03a9 \
|
||||
--hash=sha256:f69e0f7b7c09f1f612b1f8f59e2df72faa8a6b41c5a436dde5b615aaf948f107 \
|
||||
--hash=sha256:4c73f373b0800eb3062ffd13d4a7a2a6d522792fa6eb204d67a4fad0a40f03dc \
|
||||
--hash=sha256:69c5d920a0b2a9838e677f78f4dde506b95ea8e4d30da25859db6469ded84fa8
|
||||
parsedatetime==2.6 \
|
||||
--hash=sha256:cb96edd7016872f58479e35879294258c71437195760746faffedb692aef000b \
|
||||
--hash=sha256:4cb368fbb18a0b7231f4d76119165451c8d2e35951455dfee97c62a87b04d455
|
||||
parso==0.7.0 \
|
||||
--hash=sha256:158c140fc04112dc45bca311633ae5033c2c2a7b732fa33d0955bad8152a8dd0 \
|
||||
--hash=sha256:908e9fae2144a076d72ae4e25539143d40b8e3eafbaeae03c1bfe226f4cdf12c
|
||||
pathspec==0.8.0 \
|
||||
--hash=sha256:7d91249d21749788d07a2d0f94147accd8f845507400749ea19c1ec9054a12b0 \
|
||||
--hash=sha256:da45173eb3a6f2a5a487efba21f050af2b41948be6ab52b6a1e3ff22bb8b7061
|
||||
pexpect==4.8.0; sys_platform != "win32" \
|
||||
--hash=sha256:0b48a55dcb3c05f3329815901ea4fc1537514d6ba867a152b581d69ae3710937 \
|
||||
--hash=sha256:fc65a43959d153d0114afe13997d439c22823a27cefceb5ff35c2178c6784c0c
|
||||
pickleshare==0.7.5 \
|
||||
--hash=sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56 \
|
||||
--hash=sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca
|
||||
pluggy==0.13.1 \
|
||||
--hash=sha256:966c145cd83c96502c3c3868f50408687b38434af77734af1e9ca461a4081d2d \
|
||||
--hash=sha256:15b2acde666561e1298d71b523007ed7364de07029219b604cf808bfa1c765b0
|
||||
prompt-toolkit==3.0.5 \
|
||||
--hash=sha256:df7e9e63aea609b1da3a65641ceaf5bc7d05e0a04de5bd45d05dbeffbabf9e04 \
|
||||
--hash=sha256:563d1a4140b63ff9dd587bda9557cffb2fe73650205ab6f4383092fb882e7dc8
|
||||
ptyprocess==0.6.0; sys_platform != "win32" \
|
||||
--hash=sha256:d7cc528d76e76342423ca640335bd3633420dc1366f258cb31d05e865ef5ca1f \
|
||||
--hash=sha256:923f299cc5ad920c68f2bc0bc98b75b9f838b93b599941a6b63ddbc2476394c0
|
||||
py==1.9.0 \
|
||||
--hash=sha256:366389d1db726cd2fcfc79732e75410e5fe4d31db13692115529d34069a043c2 \
|
||||
--hash=sha256:9ca6883ce56b4e8da7e79ac18787889fa5206c79dcc67fb065376cd2fe03f342
|
||||
pycodestyle==2.6.0 \
|
||||
--hash=sha256:2295e7b2f6b5bd100585ebcb1f616591b652db8a741695b3d8f5d28bdc934367 \
|
||||
--hash=sha256:c58a7d2815e0e8d7972bf1803331fb0152f867bd89adf8a01dfd55085434192e
|
||||
pycountry==19.8.18 \
|
||||
--hash=sha256:3c57aa40adcf293d59bebaffbe60d8c39976fba78d846a018dc0c2ec9c6cb3cb
|
||||
pyflakes==2.2.0 \
|
||||
--hash=sha256:0d94e0e05a19e57a99444b6ddcf9a6eb2e5c68d3ca1e98e90707af8152c90a92 \
|
||||
--hash=sha256:35b2d75ee967ea93b55750aa9edbbf72813e06a66ba54438df2cfac9e3c27fc8
|
||||
pygments==2.6.1 \
|
||||
--hash=sha256:ff7a40b4860b727ab48fad6360eb351cc1b33cbf9b15a0f689ca5353e9463324 \
|
||||
--hash=sha256:647344a061c249a3b74e230c739f434d7ea4d8b1d5f3721bc0f3558049b38f44
|
||||
pyparsing==2.4.7 \
|
||||
--hash=sha256:ef9d7589ef3c200abe66653d3f1ab1033c3c419ae9b9bdb1240a85b024efc88b \
|
||||
--hash=sha256:c203ec8783bf771a155b207279b9bccb8dea02d8f0c9e5f8ead507bc3246ecc1
|
||||
pytest==5.4.3 \
|
||||
--hash=sha256:5c0db86b698e8f170ba4582a492248919255fcd4c79b1ee64ace34301fb589a1 \
|
||||
--hash=sha256:7979331bfcba207414f5e1263b5a0f8f521d0f457318836a7355531ed1a4c7d8
|
||||
pytest-clarity==0.3.0a0 \
|
||||
--hash=sha256:5cc99e3d9b7969dfe17e5f6072d45a917c59d363b679686d3c958a1ded2e4dcf
|
||||
python-dateutil==2.8.1 \
|
||||
--hash=sha256:73ebfe9dbf22e832286dafa60473e4cd239f8592f699aa5adaf10050e6e1823c \
|
||||
--hash=sha256:75bb3f31ea686f1197762692a9ee6a7550b59fc6ca3a1f4b5d7e32fb98e2da2a
|
||||
python-slugify==4.0.1 \
|
||||
--hash=sha256:69a517766e00c1268e5bbfc0d010a0a8508de0b18d30ad5a1ff357f8ae724270
|
||||
python-stdnum==1.13 \
|
||||
--hash=sha256:120f83d33fb8b8be1b282f20dd755a892d5facf84f54fa21f75bbd2633128160 \
|
||||
--hash=sha256:3d5d4430579cba88211d3ba4855a16faff235352a25a01d6ab70024686a75823
|
||||
pytimeparse==1.1.8 \
|
||||
--hash=sha256:04b7be6cc8bd9f5647a6325444926c3ac34ee6bc7e69da4367ba282f076036bd \
|
||||
--hash=sha256:e86136477be924d7e670646a98561957e8ca7308d44841e21f5ddea757556a0a
|
||||
pytz==2020.1 \
|
||||
--hash=sha256:a494d53b6d39c3c6e44c3bec237336e14305e4f29bbf800b599253057fbb79ed \
|
||||
--hash=sha256:c35965d010ce31b23eeb663ed3cc8c906275d6be1a34393a1d73a41febf4a048
|
||||
regex==2020.6.8 \
|
||||
--hash=sha256:fbff901c54c22425a5b809b914a3bfaf4b9570eee0e5ce8186ac71eb2025191c \
|
||||
--hash=sha256:112e34adf95e45158c597feea65d06a8124898bdeac975c9087fe71b572bd938 \
|
||||
--hash=sha256:92d8a043a4241a710c1cf7593f5577fbb832cf6c3a00ff3fc1ff2052aff5dd89 \
|
||||
--hash=sha256:bae83f2a56ab30d5353b47f9b2a33e4aac4de9401fb582b55c42b132a8ac3868 \
|
||||
--hash=sha256:b2ba0f78b3ef375114856cbdaa30559914d081c416b431f2437f83ce4f8b7f2f \
|
||||
--hash=sha256:95fa7726d073c87141f7bbfb04c284901f8328e2d430eeb71b8ffdd5742a5ded \
|
||||
--hash=sha256:e3cdc9423808f7e1bb9c2e0bdb1c9dc37b0607b30d646ff6faf0d4e41ee8fee3 \
|
||||
--hash=sha256:c78e66a922de1c95a208e4ec02e2e5cf0bb83a36ceececc10a72841e53fbf2bd \
|
||||
--hash=sha256:08997a37b221a3e27d68ffb601e45abfb0093d39ee770e4257bd2f5115e8cb0a \
|
||||
--hash=sha256:2f6f211633ee8d3f7706953e9d3edc7ce63a1d6aad0be5dcee1ece127eea13ae \
|
||||
--hash=sha256:55b4c25cbb3b29f8d5e63aeed27b49fa0f8476b0d4e1b3171d85db891938cc3a \
|
||||
--hash=sha256:89cda1a5d3e33ec9e231ece7307afc101b5217523d55ef4dc7fb2abd6de71ba3 \
|
||||
--hash=sha256:690f858d9a94d903cf5cada62ce069b5d93b313d7d05456dbcd99420856562d9 \
|
||||
--hash=sha256:1700419d8a18c26ff396b3b06ace315b5f2a6e780dad387e4c48717a12a22c29 \
|
||||
--hash=sha256:654cb773b2792e50151f0e22be0f2b6e1c3a04c5328ff1d9d59c0398d37ef610 \
|
||||
--hash=sha256:52e1b4bef02f4040b2fd547357a170fc1146e60ab310cdbdd098db86e929b387 \
|
||||
--hash=sha256:cf59bbf282b627130f5ba68b7fa3abdb96372b24b66bdf72a4920e8153fc7910 \
|
||||
--hash=sha256:5aaa5928b039ae440d775acea11d01e42ff26e1561c0ffcd3d805750973c6baf \
|
||||
--hash=sha256:97712e0d0af05febd8ab63d2ef0ab2d0cd9deddf4476f7aa153f76feef4b2754 \
|
||||
--hash=sha256:6ad8663c17db4c5ef438141f99e291c4d4edfeaacc0ce28b5bba2b0bf273d9b5 \
|
||||
--hash=sha256:e9b64e609d37438f7d6e68c2546d2cb8062f3adb27e6336bc129b51be20773ac
|
||||
requests==2.24.0 \
|
||||
--hash=sha256:fe75cc94a9443b9246fc7049224f75604b113c36acb93f87b80ed42c44cbb898 \
|
||||
--hash=sha256:b3559a131db72c33ee969480840fff4bb6dd111de7dd27c8ee1f820f4f00231b
|
||||
requests-cache==0.5.2 \
|
||||
--hash=sha256:813023269686045f8e01e2289cc1e7e9ae5ab22ddd1e2849a9093ab3ab7270eb \
|
||||
--hash=sha256:81e13559baee64677a7d73b85498a5a8f0639e204517b5d05ff378e44a57831a
|
||||
six==1.15.0 \
|
||||
--hash=sha256:8b74bedcbbbaca38ff6d7491d76f2b06b3592611af620f8426e82dddb04a5ced \
|
||||
--hash=sha256:30639c035cdb23534cd4aa2dd52c3bf48f06e5f4a941509c8bafd8ce11080259
|
||||
sqlalchemy==1.3.18 \
|
||||
--hash=sha256:f11c2437fb5f812d020932119ba02d9e2bc29a6eca01a055233a8b449e3e1e7d \
|
||||
--hash=sha256:0ec575db1b54909750332c2e335c2bb11257883914a03bc5a3306a4488ecc772 \
|
||||
--hash=sha256:f57be5673e12763dd400fea568608700a63ce1c6bd5bdbc3cc3a2c5fdb045274 \
|
||||
--hash=sha256:8cac7bb373a5f1423e28de3fd5fc8063b9c8ffe8957dc1b1a59cb90453db6da1 \
|
||||
--hash=sha256:adad60eea2c4c2a1875eb6305a0b6e61a83163f8e233586a4d6a55221ef984fe \
|
||||
--hash=sha256:57aa843b783179ab72e863512e14bdcba186641daf69e4e3a5761d705dcc35b1 \
|
||||
--hash=sha256:621f58cd921cd71ba6215c42954ffaa8a918eecd8c535d97befa1a8acad986dd \
|
||||
--hash=sha256:fc728ece3d5c772c196fd338a99798e7efac7a04f9cb6416299a3638ee9a94cd \
|
||||
--hash=sha256:736d41cfebedecc6f159fc4ac0769dc89528a989471dc1d378ba07d29a60ba1c \
|
||||
--hash=sha256:427273b08efc16a85aa2b39892817e78e3ed074fcb89b2a51c4979bae7e7ba98 \
|
||||
--hash=sha256:cbe1324ef52ff26ccde2cb84b8593c8bf930069dfc06c1e616f1bfd4e47f48a3 \
|
||||
--hash=sha256:8fd452dc3d49b3cc54483e033de6c006c304432e6f84b74d7b2c68afa2569ae5 \
|
||||
--hash=sha256:e89e0d9e106f8a9180a4ca92a6adde60c58b1b0299e1b43bd5e0312f535fbf33 \
|
||||
--hash=sha256:6ac2558631a81b85e7fb7a44e5035347938b0a73f5fdc27a8566777d0792a6a4 \
|
||||
--hash=sha256:87fad64529cde4f1914a5b9c383628e1a8f9e3930304c09cf22c2ae118a1280e \
|
||||
--hash=sha256:e4624d7edb2576cd72bb83636cd71c8ce544d8e272f308bd80885056972ca299 \
|
||||
--hash=sha256:89494df7f93b1836cae210c42864b292f9b31eeabca4810193761990dc689cce \
|
||||
--hash=sha256:716754d0b5490bdcf68e1e4925edc02ac07209883314ad01a137642ddb2056f1 \
|
||||
--hash=sha256:50c4ee32f0e1581828843267d8de35c3298e86ceecd5e9017dc45788be70a864 \
|
||||
--hash=sha256:d98bc827a1293ae767c8f2f18be3bb5151fd37ddcd7da2a5f9581baeeb7a3fa1 \
|
||||
--hash=sha256:0942a3a0df3f6131580eddd26d99071b48cfe5aaf3eab2783076fbc5a1c1882e \
|
||||
--hash=sha256:16593fd748944726540cd20f7e83afec816c2ac96b082e26ae226e8f7e9688cf \
|
||||
--hash=sha256:c26f95e7609b821b5f08a72dab929baa0d685406b953efd7c89423a511d5c413 \
|
||||
--hash=sha256:512a85c3c8c3995cc91af3e90f38f460da5d3cade8dc3a229c8e0879037547c9 \
|
||||
--hash=sha256:d05c4adae06bd0c7f696ae3ec8d993ed8ffcc4e11a76b1b35a5af8a099bd2284 \
|
||||
--hash=sha256:109581ccc8915001e8037b73c29590e78ce74be49ca0a3630a23831f9e3ed6c7 \
|
||||
--hash=sha256:8619b86cb68b185a778635be5b3e6018623c0761dde4df2f112896424aa27bd8 \
|
||||
--hash=sha256:da2fb75f64792c1fc64c82313a00c728a7c301efe6a60b7a9fe35b16b4368ce7
|
||||
termcolor==1.1.0 \
|
||||
--hash=sha256:1d6d69ce66211143803fbc56652b41d73b4a400a2891d7bf7a1cdf4c02de613b
|
||||
text-unidecode==1.3 \
|
||||
--hash=sha256:bad6603bb14d279193107714b288be206cac565dfa49aa5b105294dd5c4aab93 \
|
||||
--hash=sha256:1311f10e8b895935241623731c2ba64f4c455287888b18189350b67134a822e8
|
||||
toml==0.10.1 \
|
||||
--hash=sha256:bda89d5935c2eac546d648028b9901107a595863cb36bae0c73ac804a9b4ce88 \
|
||||
--hash=sha256:926b612be1e5ce0634a2ca03470f95169cf16f939018233a670519cb4ac58b0f
|
||||
traitlets==4.3.3 \
|
||||
--hash=sha256:70b4c6a1d9019d7b4f6846832288f86998aa3b9207c6821f3578a6a6a467fe44 \
|
||||
--hash=sha256:d023ee369ddd2763310e4c3eae1ff649689440d4ae59d7485eb4cfbbe3e359f7
|
||||
typed-ast==1.4.1 \
|
||||
--hash=sha256:73d785a950fc82dd2a25897d525d003f6378d1cb23ab305578394694202a58c3 \
|
||||
--hash=sha256:aaee9905aee35ba5905cfb3c62f3e83b3bec7b39413f0a7f19be4e547ea01ebb \
|
||||
--hash=sha256:0c2c07682d61a629b68433afb159376e24e5b2fd4641d35424e462169c0a7919 \
|
||||
--hash=sha256:4083861b0aa07990b619bd7ddc365eb7fa4b817e99cf5f8d9cf21a42780f6e01 \
|
||||
--hash=sha256:269151951236b0f9a6f04015a9004084a5ab0d5f19b57de779f908621e7d8b75 \
|
||||
--hash=sha256:24995c843eb0ad11a4527b026b4dde3da70e1f2d8806c99b7b4a7cf491612652 \
|
||||
--hash=sha256:fe460b922ec15dd205595c9b5b99e2f056fd98ae8f9f56b888e7a17dc2b757e7 \
|
||||
--hash=sha256:4e3e5da80ccbebfff202a67bf900d081906c358ccc3d5e3c8aea42fdfdfd51c1 \
|
||||
--hash=sha256:249862707802d40f7f29f6e1aad8d84b5aa9e44552d2cc17384b209f091276aa \
|
||||
--hash=sha256:8ce678dbaf790dbdb3eba24056d5364fb45944f33553dd5869b7580cdbb83614 \
|
||||
--hash=sha256:c9e348e02e4d2b4a8b2eedb48210430658df6951fa484e59de33ff773fbd4b41 \
|
||||
--hash=sha256:bcd3b13b56ea479b3650b82cabd6b5343a625b0ced5429e4ccad28a8973f301b \
|
||||
--hash=sha256:d5d33e9e7af3b34a40dc05f498939f0ebf187f07c385fd58d591c533ad8562fe \
|
||||
--hash=sha256:0666aa36131496aed8f7be0410ff974562ab7eeac11ef351def9ea6fa28f6355 \
|
||||
--hash=sha256:d205b1b46085271b4e15f670058ce182bd1199e56b317bf2ec004b6a44f911f6 \
|
||||
--hash=sha256:6daac9731f172c2a22ade6ed0c00197ee7cc1221aa84cfdf9c31defeb059a907 \
|
||||
--hash=sha256:498b0f36cc7054c1fead3d7fc59d2150f4d5c6c56ba7fb150c013fbc683a8d2d \
|
||||
--hash=sha256:715ff2f2df46121071622063fc7543d9b1fd19ebfc4f5c8895af64a77a8c852c \
|
||||
--hash=sha256:fc0fea399acb12edbf8a628ba8d2312f583bdbdb3335635db062fa98cf71fca4 \
|
||||
--hash=sha256:d43943ef777f9a1c42bf4e552ba23ac77a6351de620aa9acf64ad54933ad4d34 \
|
||||
--hash=sha256:8c8aaad94455178e3187ab22c8b01a3837f8ee50e09cf31f1ba129eb293ec30b
|
||||
urllib3==1.25.9 \
|
||||
--hash=sha256:88206b0eb87e6d677d424843ac5209e3fb9d0190d0ee169599165ec25e9d9115 \
|
||||
--hash=sha256:3018294ebefce6572a474f0604c2021e33b3fd8006ecd11d62107a5d2a963527
|
||||
wcwidth==0.2.5 \
|
||||
--hash=sha256:beb4802a9cebb9144e99086eff703a642a13d6a0052920003a230f3294bbe784 \
|
||||
--hash=sha256:c4d647b99872929fdb7bdcaa4fbe7f01413ed3d98077df798530e5b04f116c83
|
||||
xlrd==1.2.0 \
|
||||
--hash=sha256:e551fb498759fa3a5384a94ccd4c3c02eb7c00ea424426e212ac0c57be9dfbde \
|
||||
--hash=sha256:546eb36cee8db40c3eaa46c351e67ffee6eeb5fa2650b71bc4c758a29a1b29b2
|
||||
|
@ -1,17 +1,81 @@
|
||||
-i https://pypi.org/simple
|
||||
-e .
|
||||
certifi==2019.9.11
|
||||
chardet==3.0.4
|
||||
idna==2.8
|
||||
langid==1.1.6
|
||||
numpy==1.17.2
|
||||
pandas==0.25.1
|
||||
pycountry==19.8.18
|
||||
python-dateutil==2.8.0
|
||||
python-stdnum==1.11
|
||||
pytz==2019.2
|
||||
requests-cache==0.5.2
|
||||
requests==2.22.0
|
||||
six==1.12.0
|
||||
urllib3==1.25.6
|
||||
xlrd==1.2.0
|
||||
certifi==2020.6.20 \
|
||||
--hash=sha256:8fc0819f1f30ba15bdb34cceffb9ef04d99f420f68eb75d901e9560b8749fc41 \
|
||||
--hash=sha256:5930595817496dd21bb8dc35dad090f1c2cd0adfaf21204bf6732ca5d8ee34d3
|
||||
chardet==3.0.4 \
|
||||
--hash=sha256:fc323ffcaeaed0e0a02bf4d117757b98aed530d9ed4531e3e15460124c106691 \
|
||||
--hash=sha256:84ab92ed1c4d4f16916e05906b6b75a6c0fb5db821cc65e70cbd64a3e2a5eaae
|
||||
idna==2.10 \
|
||||
--hash=sha256:b97d804b1e9b523befed77c48dacec60e6dcb0b5391d57af6a65a312a90648c0 \
|
||||
--hash=sha256:b307872f855b18632ce0c21c5e45be78c0ea7ae4c15c828c20788b26921eb3f6
|
||||
langid==1.1.6 \
|
||||
--hash=sha256:044bcae1912dab85c33d8e98f2811b8f4ff1213e5e9a9e9510137b84da2cb293
|
||||
numpy==1.19.0 \
|
||||
--hash=sha256:63d971bb211ad3ca37b2adecdd5365f40f3b741a455beecba70fd0dde8b2a4cb \
|
||||
--hash=sha256:b6aaeadf1e4866ca0fdf7bb4eed25e521ae21a7947c59f78154b24fc7abbe1dd \
|
||||
--hash=sha256:13af0184177469192d80db9bd02619f6fa8b922f9f327e077d6f2a6acb1ce1c0 \
|
||||
--hash=sha256:356f96c9fbec59974a592452ab6a036cd6f180822a60b529a975c9467fcd5f23 \
|
||||
--hash=sha256:fa1fe75b4a9e18b66ae7f0b122543c42debcf800aaafa0212aaff3ad273c2596 \
|
||||
--hash=sha256:cbe326f6d364375a8e5a8ccb7e9cd73f4b2f6dc3b2ed205633a0db8243e2a96a \
|
||||
--hash=sha256:a2e3a39f43f0ce95204beb8fe0831199542ccab1e0c6e486a0b4947256215632 \
|
||||
--hash=sha256:7b852817800eb02e109ae4a9cef2beda8dd50d98b76b6cfb7b5c0099d27b52d4 \
|
||||
--hash=sha256:d97a86937cf9970453c3b62abb55a6475f173347b4cde7f8dcdb48c8e1b9952d \
|
||||
--hash=sha256:a86c962e211f37edd61d6e11bb4df7eddc4a519a38a856e20a6498c319efa6b0 \
|
||||
--hash=sha256:d34fbb98ad0d6b563b95de852a284074514331e6b9da0a9fc894fb1cdae7a79e \
|
||||
--hash=sha256:658624a11f6e1c252b2cd170d94bf28c8f9410acab9f2fd4369e11e1cd4e1aaf \
|
||||
--hash=sha256:4d054f013a1983551254e2379385e359884e5af105e3efe00418977d02f634a7 \
|
||||
--hash=sha256:26a45798ca2a4e168d00de75d4a524abf5907949231512f372b217ede3429e98 \
|
||||
--hash=sha256:3c40c827d36c6d1c3cf413694d7dc843d50997ebffbc7c87d888a203ed6403a7 \
|
||||
--hash=sha256:be62aeff8f2f054eff7725f502f6228298891fd648dc2630e03e44bf63e8cee0 \
|
||||
--hash=sha256:dd53d7c4a69e766e4900f29db5872f5824a06827d594427cf1a4aa542818b796 \
|
||||
--hash=sha256:30a59fb41bb6b8c465ab50d60a1b298d1cd7b85274e71f38af5a75d6c475d2d2 \
|
||||
--hash=sha256:df1889701e2dfd8ba4dc9b1a010f0a60950077fb5242bb92c8b5c7f1a6f2668a \
|
||||
--hash=sha256:33c623ef9ca5e19e05991f127c1be5aeb1ab5cdf30cb1c5cf3960752e58b599b \
|
||||
--hash=sha256:26f509450db547e4dfa3ec739419b31edad646d21fb8d0ed0734188b35ff6b27 \
|
||||
--hash=sha256:7b57f26e5e6ee2f14f960db46bd58ffdca25ca06dd997729b1b179fddd35f5a3 \
|
||||
--hash=sha256:a8705c5073fe3fcc297fb8e0b31aa794e05af6a329e81b7ca4ffecab7f2b95ef \
|
||||
--hash=sha256:c2edbb783c841e36ca0fa159f0ae97a88ce8137fb3a6cd82eae77349ba4b607b \
|
||||
--hash=sha256:8cde829f14bd38f6da7b2954be0f2837043e8b8d7a9110ec5e318ae6bf706610 \
|
||||
--hash=sha256:76766cc80d6128750075378d3bb7812cf146415bd29b588616f72c943c00d598
|
||||
pandas==1.0.5 \
|
||||
--hash=sha256:faa42a78d1350b02a7d2f0dbe3c80791cf785663d6997891549d0f86dc49125e \
|
||||
--hash=sha256:9c31d52f1a7dd2bb4681d9f62646c7aa554f19e8e9addc17e8b1b20011d7522d \
|
||||
--hash=sha256:8778a5cc5a8437a561e3276b85367412e10ae9fff07db1eed986e427d9a674f8 \
|
||||
--hash=sha256:9871ef5ee17f388f1cb35f76dc6106d40cb8165c562d573470672f4cdefa59ef \
|
||||
--hash=sha256:35b670b0abcfed7cad76f2834041dcf7ae47fd9b22b63622d67cdc933d79f453 \
|
||||
--hash=sha256:c9410ce8a3dee77653bc0684cfa1535a7f9c291663bd7ad79e39f5ab58f67ab3 \
|
||||
--hash=sha256:02f1e8f71cd994ed7fcb9a35b6ddddeb4314822a0e09a9c5b2d278f8cb5d4096 \
|
||||
--hash=sha256:b3c4f93fcb6e97d993bf87cdd917883b7dab7d20c627699f360a8fb49e9e0b91 \
|
||||
--hash=sha256:5759edf0b686b6f25a5d4a447ea588983a33afc8a0081a0954184a4a87fd0dd7 \
|
||||
--hash=sha256:ab8173a8efe5418bbe50e43f321994ac6673afc5c7c4839014cf6401bbdd0705 \
|
||||
--hash=sha256:13f75fb18486759da3ff40f5345d9dd20e7d78f2a39c5884d013456cec9876f0 \
|
||||
--hash=sha256:5a7cf6044467c1356b2b49ef69e50bf4d231e773c3ca0558807cdba56b76820b \
|
||||
--hash=sha256:ae961f1f0e270f1e4e2273f6a539b2ea33248e0e3a11ffb479d757918a5e03a9 \
|
||||
--hash=sha256:f69e0f7b7c09f1f612b1f8f59e2df72faa8a6b41c5a436dde5b615aaf948f107 \
|
||||
--hash=sha256:4c73f373b0800eb3062ffd13d4a7a2a6d522792fa6eb204d67a4fad0a40f03dc \
|
||||
--hash=sha256:69c5d920a0b2a9838e677f78f4dde506b95ea8e4d30da25859db6469ded84fa8
|
||||
pycountry==19.8.18 \
|
||||
--hash=sha256:3c57aa40adcf293d59bebaffbe60d8c39976fba78d846a018dc0c2ec9c6cb3cb
|
||||
python-dateutil==2.8.1 \
|
||||
--hash=sha256:73ebfe9dbf22e832286dafa60473e4cd239f8592f699aa5adaf10050e6e1823c \
|
||||
--hash=sha256:75bb3f31ea686f1197762692a9ee6a7550b59fc6ca3a1f4b5d7e32fb98e2da2a
|
||||
python-stdnum==1.13 \
|
||||
--hash=sha256:120f83d33fb8b8be1b282f20dd755a892d5facf84f54fa21f75bbd2633128160 \
|
||||
--hash=sha256:3d5d4430579cba88211d3ba4855a16faff235352a25a01d6ab70024686a75823
|
||||
pytz==2020.1 \
|
||||
--hash=sha256:a494d53b6d39c3c6e44c3bec237336e14305e4f29bbf800b599253057fbb79ed \
|
||||
--hash=sha256:c35965d010ce31b23eeb663ed3cc8c906275d6be1a34393a1d73a41febf4a048
|
||||
requests==2.24.0 \
|
||||
--hash=sha256:fe75cc94a9443b9246fc7049224f75604b113c36acb93f87b80ed42c44cbb898 \
|
||||
--hash=sha256:b3559a131db72c33ee969480840fff4bb6dd111de7dd27c8ee1f820f4f00231b
|
||||
requests-cache==0.5.2 \
|
||||
--hash=sha256:813023269686045f8e01e2289cc1e7e9ae5ab22ddd1e2849a9093ab3ab7270eb \
|
||||
--hash=sha256:81e13559baee64677a7d73b85498a5a8f0639e204517b5d05ff378e44a57831a
|
||||
six==1.15.0 \
|
||||
--hash=sha256:8b74bedcbbbaca38ff6d7491d76f2b06b3592611af620f8426e82dddb04a5ced \
|
||||
--hash=sha256:30639c035cdb23534cd4aa2dd52c3bf48f06e5f4a941509c8bafd8ce11080259
|
||||
urllib3==1.25.9 \
|
||||
--hash=sha256:88206b0eb87e6d677d424843ac5209e3fb9d0190d0ee169599165ec25e9d9115 \
|
||||
--hash=sha256:3018294ebefce6572a474f0604c2021e33b3fd8006ecd11d62107a5d2a963527
|
||||
xlrd==1.2.0 \
|
||||
--hash=sha256:e551fb498759fa3a5384a94ccd4c3c02eb7c00ea424426e212ac0c57be9dfbde \
|
||||
--hash=sha256:546eb36cee8db40c3eaa46c351e67ffee6eeb5fa2650b71bc4c758a29a1b29b2
|
||||
|
25
setup.py
25
setup.py
@ -4,17 +4,17 @@ with open("README.md", "r") as fh:
|
||||
long_description = fh.read()
|
||||
|
||||
install_requires = [
|
||||
'pandas',
|
||||
'python-stdnum',
|
||||
'requests',
|
||||
'requests-cache',
|
||||
'pycountry',
|
||||
'langid'
|
||||
"pandas",
|
||||
"python-stdnum",
|
||||
"requests",
|
||||
"requests-cache",
|
||||
"pycountry",
|
||||
"langid",
|
||||
]
|
||||
|
||||
setuptools.setup(
|
||||
name="csv-metadata-quality",
|
||||
version="0.3.1",
|
||||
version="0.4.2",
|
||||
author="Alan Orth",
|
||||
author_email="aorth@mjanja.ch",
|
||||
description="A simple, but opinionated CSV quality checking and fixing pipeline for CSVs in the DSpace ecosystem.",
|
||||
@ -25,15 +25,14 @@ setuptools.setup(
|
||||
classifiers=[
|
||||
"Programming Language :: Python :: 3.6",
|
||||
"Programming Language :: Python :: 3.7",
|
||||
"Programming Language :: Python :: 3.8",
|
||||
"License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
|
||||
"Operating System :: OS Independent",
|
||||
"Development Status :: 4 - Beta"
|
||||
"Development Status :: 4 - Beta",
|
||||
],
|
||||
packages=['csv_metadata_quality'],
|
||||
packages=["csv_metadata_quality"],
|
||||
entry_points={
|
||||
'console_scripts': [
|
||||
'csv-metadata-quality = csv_metadata_quality.__main__:main'
|
||||
]
|
||||
"console_scripts": ["csv-metadata-quality = csv_metadata_quality.__main__:main"]
|
||||
},
|
||||
install_requires=install_requires
|
||||
install_requires=install_requires,
|
||||
)
|
||||
|
@ -1,6 +1,7 @@
|
||||
import pandas as pd
|
||||
|
||||
import csv_metadata_quality.check as check
|
||||
import csv_metadata_quality.experimental as experimental
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def test_check_invalid_issn(capsys):
|
||||
@ -50,10 +51,12 @@ def test_check_invalid_separators(capsys):
|
||||
|
||||
value = "Alan|Orth"
|
||||
|
||||
check.separators(value)
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
check.separators(value, field_name)
|
||||
|
||||
captured = capsys.readouterr()
|
||||
assert captured.out == f"Invalid multi-value separator: {value}\n"
|
||||
assert captured.out == f"Invalid multi-value separator ({field_name}): {value}\n"
|
||||
|
||||
|
||||
def test_check_valid_separators():
|
||||
@ -61,7 +64,9 @@ def test_check_valid_separators():
|
||||
|
||||
value = "Alan||Orth"
|
||||
|
||||
result = check.separators(value)
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
result = check.separators(value, field_name)
|
||||
|
||||
assert result == value
|
||||
|
||||
|
@ -6,7 +6,9 @@ def test_fix_leading_whitespace():
|
||||
|
||||
value = " Alan"
|
||||
|
||||
assert fix.whitespace(value) == "Alan"
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
assert fix.whitespace(value, field_name) == "Alan"
|
||||
|
||||
|
||||
def test_fix_trailing_whitespace():
|
||||
@ -14,7 +16,9 @@ def test_fix_trailing_whitespace():
|
||||
|
||||
value = "Alan "
|
||||
|
||||
assert fix.whitespace(value) == "Alan"
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
assert fix.whitespace(value, field_name) == "Alan"
|
||||
|
||||
|
||||
def test_fix_excessive_whitespace():
|
||||
@ -22,7 +26,9 @@ def test_fix_excessive_whitespace():
|
||||
|
||||
value = "Alan Orth"
|
||||
|
||||
assert fix.whitespace(value) == "Alan Orth"
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
assert fix.whitespace(value, field_name) == "Alan Orth"
|
||||
|
||||
|
||||
def test_fix_invalid_separators():
|
||||
@ -30,7 +36,9 @@ def test_fix_invalid_separators():
|
||||
|
||||
value = "Alan|Orth"
|
||||
|
||||
assert fix.separators(value) == "Alan||Orth"
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
assert fix.separators(value, field_name) == "Alan||Orth"
|
||||
|
||||
|
||||
def test_fix_unnecessary_unicode():
|
||||
@ -46,7 +54,9 @@ def test_fix_duplicates():
|
||||
|
||||
value = "Kenya||Kenya"
|
||||
|
||||
assert fix.duplicates(value) == "Kenya"
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
assert fix.duplicates(value, field_name) == "Kenya"
|
||||
|
||||
|
||||
def test_fix_newlines():
|
||||
@ -66,3 +76,25 @@ def test_fix_comma_space():
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
assert fix.comma_space(value, field_name) == "Orth, Alan S."
|
||||
|
||||
|
||||
def test_fix_normalized_unicode():
|
||||
"""Test fixing a string that is already in its normalized (NFC) Unicode form."""
|
||||
|
||||
# string using the normalized canonical form of é
|
||||
value = "Ouédraogo, Mathieu"
|
||||
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
assert fix.normalize_unicode(value, field_name) == "Ouédraogo, Mathieu"
|
||||
|
||||
|
||||
def test_fix_decomposed_unicode():
|
||||
"""Test fixing a string that contains Unicode string."""
|
||||
|
||||
# string using the decomposed form of é
|
||||
value = "Ouédraogo, Mathieu"
|
||||
|
||||
field_name = "dc.contributor.author"
|
||||
|
||||
assert fix.normalize_unicode(value, field_name) == "Ouédraogo, Mathieu"
|
||||
|
Reference in New Issue
Block a user