setup.py: denote that Python 3.10 works

I have been using Python 3.10 for months, and already added it to
the CI builds.

.drone.yml

@@ -13,7 +13,16 @@ steps:
   - pip install -r requirements-dev.txt
   - pytest
   - python setup.py install
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e -u --agrovoc-fields dcterms.subject,cg.coverage.country
+  # Basic test
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+  # Test with unsafe fixes
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
+  # Test with experimental checks
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e
+  # Test with AGROVOC validation
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject
+  # Test with AGROVOC validation (and dropping invalid)
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject -d
 
 ---
 kind: pipeline
@@ -30,7 +39,16 @@ steps:
   - pip install -r requirements-dev.txt
   - pytest
   - python setup.py install
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e -u --agrovoc-fields dcterms.subject,cg.coverage.country
+  # Basic test
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+  # Test with unsafe fixes
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
+  # Test with experimental checks
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e
+  # Test with AGROVOC validation
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject
+  # Test with AGROVOC validation (and dropping invalid)
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject -d
 
 ---
 kind: pipeline
@@ -47,7 +65,16 @@ steps:
   - pip install -r requirements-dev.txt
   - pytest
   - python setup.py install
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e -u --agrovoc-fields dcterms.subject,cg.coverage.country
+  # Basic test
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+  # Test with unsafe fixes
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
+  # Test with experimental checks
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e
+  # Test with AGROVOC validation
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject
+  # Test with AGROVOC validation (and dropping invalid)
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject -d
 
 ---
 kind: pipeline
@@ -64,6 +91,15 @@ steps:
   - pip install -r requirements-dev.txt
   - pytest
   - python setup.py install
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e -u --agrovoc-fields dcterms.subject,cg.coverage.country
+  # Basic test
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+  # Test with unsafe fixes
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
+  # Test with experimental checks
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e
+  # Test with AGROVOC validation
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject
+  # Test with AGROVOC validation (and dropping invalid)
+  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject -d
 
 # vim: ts=2 sw=2 et

.github/workflows/python-app.yml

@@ -38,4 +38,13 @@ jobs:
     - name: Test CLI
       run: |
         python setup.py install
-        csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e -u --agrovoc-fields dcterms.subject,cg.coverage.country
+        # Basic test
+        csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+        # Test with unsafe fixes
+        csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
+        # Test with experimental checks
+        csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e
+        # Test with AGROVOC validation
+        csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject
+        # Test with AGROVOC validation (and dropping invalid)
+        csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject -d

CHANGELOG.md

@@ -4,6 +4,20 @@ 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).
 
+## Unreleased
+### Changed
+- Perform fix for "unnecessary" Unicode characters after we try to fix encoding
+issues with ftfy
+- ftfy heuristics to use `is_bad()` instead of `sequence_weirdness()`
+- ftfy `fix_text()` to *not* change “smart quotes” to "ASCII quotes"
+
+### Updated
+- Python dependencies
+
+### Added
+- Ability to drop invalid AGROVOC values with `-d` when checking AGROVOC values
+with `-a <field.name>`
+
 ## [0.5.0] - 2021-12-08
 ### Added
 - Ability to check for, and fix, "mojibake" characters using [ftfy](https://github.com/LuminosoInsight/python-ftfy)

csv_metadata_quality/app.py

@@ -21,6 +21,12 @@ def parse_args(argv):
         "-a",
         help="Comma-separated list of fields to validate against AGROVOC, for example: dcterms.subject,cg.coverage.country",
     )
+    parser.add_argument(
+        "--drop-invalid-agrovoc",
+        "-d",
+        help="After validating metadata values against AGROVOC, drop invalid values.",
+        action="store_true",
+    )
     parser.add_argument(
         "--experimental-checks",
         "-e",
@@ -103,9 +109,6 @@ def run(argv):
         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: suspicious characters
         df[column].apply(check.suspicious_characters, field_name=column)
 
@@ -115,6 +118,9 @@ def run(argv):
         else:
             df[column].apply(check.mojibake, field_name=column)
 
+        # Fix: unnecessary Unicode
+        df[column] = df[column].apply(fix.unnecessary_unicode)
+
         # Fix: invalid and unnecessary multi-value separators
         df[column] = df[column].apply(fix.separators, field_name=column)
         # Run whitespace fix again after fixing invalid separators
@@ -123,12 +129,14 @@ def run(argv):
         # Fix: duplicate metadata values
         df[column] = df[column].apply(fix.duplicates, field_name=column)
 
-        # Check: invalid AGROVOC subject
+        # Check: invalid AGROVOC subject and optionally drop them
         if args.agrovoc_fields:
             # Identify fields the user wants to validate against AGROVOC
             for field in args.agrovoc_fields.split(","):
                 if column == field:
-                    df[column].apply(check.agrovoc, field_name=column)
+                    df[column] = df[column].apply(
+                        check.agrovoc, field_name=column, drop=args.drop_invalid_agrovoc
+                    )
 
         # Check: invalid language
         match = re.match(r"^.*?language.*$", column)

csv_metadata_quality/check.py

@@ -188,7 +188,7 @@ def language(field):
     return
 
 
-def agrovoc(field, field_name):
+def agrovoc(field, field_name, drop):
     """Check subject terms against AGROVOC REST API.
 
     Function constructor expects the field as well as the field name because
@@ -219,6 +219,9 @@ def agrovoc(field, field_name):
     # prune old cache entries
     requests_cache.remove_expired_responses()
 
+    # Initialize an empty list to hold the validated AGROVOC values
+    values = list()
+
     # Try to split multi-value field on "||" separator
     for value in field.split("||"):
         request_url = "http://agrovoc.uniroma2.it/agrovoc/rest/v1/agrovoc/search"
@@ -231,9 +234,25 @@ def agrovoc(field, field_name):
 
             # check if there are any results
             if len(data["results"]) == 0:
-                print(f"{Fore.RED}Invalid AGROVOC ({field_name}): {Fore.RESET}{value}")
+                if drop:
+                    print(
+                        f"{Fore.GREEN}Dropping invalid AGROVOC ({field_name}): {Fore.RESET}{value}"
+                    )
+                else:
+                    print(
+                        f"{Fore.RED}Invalid AGROVOC ({field_name}): {Fore.RESET}{value}"
+                    )
 
-    return
+                    # value is invalid AGROVOC, but we are not dropping
+                    values.append(value)
+            else:
+                # value is valid AGROVOC so save it
+                values.append(value)
+
+    # Create a new field consisting of all values joined with "||"
+    new_field = "||".join(values)
+
+    return new_field
 
 
 def filename_extension(field):

csv_metadata_quality/fix.py

@@ -5,7 +5,7 @@ from unicodedata import normalize
 
 import pandas as pd
 from colorama import Fore
-from ftfy import fix_text
+from ftfy import TextFixerConfig, fix_text
 
 from csv_metadata_quality.util import is_mojibake, is_nfc
 
@@ -104,6 +104,7 @@ def unnecessary_unicode(field):
     Replaces unnecessary Unicode characters like:
         - Soft hyphen (U+00AD) → hyphen
         - No-break space (U+00A0) → space
+        - Thin space (U+2009) → space
 
     Return string with characters removed or replaced.
     """
@@ -148,6 +149,16 @@ def unnecessary_unicode(field):
         )
         field = re.sub(pattern, "-", field)
 
+    # Check for thin spaces (U+2009)
+    pattern = re.compile(r"\u2009")
+    match = re.findall(pattern, field)
+
+    if match:
+        print(
+            f"{Fore.GREEN}Replacing unnecessary Unicode (U+2009): {Fore.RESET}{field}"
+        )
+        field = re.sub(pattern, " ", field)
+
     return field
 
 
@@ -269,9 +280,12 @@ def mojibake(field, field_name):
     if pd.isna(field):
         return field
 
+    # We don't want ftfy to change “smart quotes” to "ASCII quotes"
+    config = TextFixerConfig(uncurl_quotes=False)
+
     if is_mojibake(field):
         print(f"{Fore.GREEN}Fixing encoding issue ({field_name}): {Fore.RESET}{field}")
 
-        return fix_text(field)
+        return fix_text(field, config)
     else:
         return field

csv_metadata_quality/util.py

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-3.0-only
 
-from ftfy.badness import sequence_weirdness
+from ftfy.badness import is_bad
 
 
 def is_nfc(field):
@@ -38,7 +38,7 @@ def is_mojibake(field):
 
     Return boolean.
     """
-    if not sequence_weirdness(field):
+    if not is_bad(field):
         # Nothing weird, should be okay
         return False
     try:

csv_metadata_quality/version.py

@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-3.0-only
 
-VERSION = "0.5.0"
+VERSION = "0.6.0-dev"

data/test.csv

@@ -16,7 +16,7 @@ Suspicious character||foreˆt,2019-07-29,,,,,,,,,,,
 Invalid ISO 639-1 (alpha 2) language,2019-07-29,,,jp,,,,,,,,
 Invalid ISO 639-3 (alpha 3) language,2019-07-29,,,chi,,,,,,,,
 Invalid language,2019-07-29,,,Span,,,,,,,,
-Invalid AGROVOC subject,2019-07-29,,,,FOREST,,,,,,,
+Invalid AGROVOC subject,2019-07-29,,,,LIVESTOCK||FOREST,,,,,,,
 Newline (LF),2019-07-30,,,,"TANZA
 NIA",,,,,,,
 Missing date,,,,,,,,,,,,

poetry.lock

@@ -262,15 +262,18 @@ pyflakes = ">=2.3.0,<2.4.0"
 
 [[package]]
 name = "ftfy"
-version = "5.9"
+version = "6.0.3"
 description = "Fixes some problems with Unicode text after the fact"
 category = "main"
 optional = false
-python-versions = ">=3.5"
+python-versions = ">=3.6"
 
 [package.dependencies]
 wcwidth = "*"
 
+[package.extras]
+docs = ["furo", "sphinx"]
+
 [[package]]
 name = "future"
 version = "0.18.2"
@@ -357,7 +360,7 @@ test = ["nose (>=0.10.1)", "requests", "testpath", "pygments", "nbformat", "ipyk
 
 [[package]]
 name = "isodate"
-version = "0.6.0"
+version = "0.6.1"
 description = "An ISO 8601 date/time/duration parser and formatter"
 category = "dev"
 optional = false
@@ -492,7 +495,7 @@ pyparsing = ">=2.0.2,<3.0.5 || >3.0.5"
 
 [[package]]
 name = "pandas"
-version = "1.3.4"
+version = "1.3.5"
 description = "Powerful data structures for data analysis, time series, and statistics"
 category = "main"
 optional = false
@@ -598,7 +601,7 @@ python-versions = "*"
 
 [[package]]
 name = "prompt-toolkit"
-version = "3.0.23"
+version = "3.0.24"
 description = "Library for building powerful interactive command lines in Python"
 category = "dev"
 optional = false
@@ -795,7 +798,7 @@ test = ["black (==20.8b1)", "flake8", "flake8-comprehensions", "flake8-polyfill"
 
 [[package]]
 name = "rich"
-version = "10.15.2"
+version = "10.16.1"
 description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal"
 category = "dev"
 optional = false
@@ -876,7 +879,7 @@ python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
 
 [[package]]
 name = "tomli"
-version = "1.2.2"
+version = "1.2.3"
 description = "A lil' TOML parser"
 category = "dev"
 optional = false
@@ -964,7 +967,7 @@ testing = ["pytest (>=4.6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytes
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.7.1"
-content-hash = "2e53197acdff785ea46adcb5ca22650efdecc6693a434a0f56a4f2b958442a78"
+content-hash = "a2ac1525ab60dc0758408867f5d651b2a3e40eb6a090b9eb7fad4a885a7965af"
 
 [metadata.files]
 agate = [
@@ -1051,7 +1054,7 @@ flake8 = [
     {file = "flake8-3.9.2.tar.gz", hash = "sha256:07528381786f2a6237b061f6e96610a4167b226cb926e2aa2b6b1d78057c576b"},
 ]
 ftfy = [
-    {file = "ftfy-5.9.tar.gz", hash = "sha256:8c4fb2863c0b82eae2ab3cf353d9ade268dfbde863d322f78d6a9fd5cefb31e9"},
+    {file = "ftfy-6.0.3.tar.gz", hash = "sha256:ba71121a9c8d7790d3e833c6c1021143f3e5c4118293ec3afb5d43ed9ca8e72b"},
 ]
 future = [
     {file = "future-0.18.2.tar.gz", hash = "sha256:b1bead90b70cf6ec3f0710ae53a525360fa360d306a86583adc6bf83a4db537d"},
@@ -1125,8 +1128,8 @@ ipython = [
     {file = "ipython-7.30.1.tar.gz", hash = "sha256:cb6aef731bf708a7727ab6cde8df87f0281b1427d41e65d62d4b68934fa54e97"},
 ]
 isodate = [
-    {file = "isodate-0.6.0-py2.py3-none-any.whl", hash = "sha256:aa4d33c06640f5352aca96e4b81afd8ab3b47337cc12089822d6f322ac772c81"},
+    {file = "isodate-0.6.1-py2.py3-none-any.whl", hash = "sha256:0751eece944162659049d35f4f549ed815792b38793f07cf73381c1c87cbed96"},
-    {file = "isodate-0.6.0.tar.gz", hash = "sha256:2e364a3d5759479cdb2d37cce6b9376ea504db2ff90252a2e5b7cc89cc9ff2d8"},
+    {file = "isodate-0.6.1.tar.gz", hash = "sha256:48c5881de7e8b0a0d648cb024c8062dc84e7b840ed81e864c7614fd3c127bde9"},
 ]
 isort = [
     {file = "isort-5.10.1-py3-none-any.whl", hash = "sha256:6f62d78e2f89b4500b080fe3a81690850cd254227f27f75c3a0c491a1f351ba7"},
@@ -1201,30 +1204,31 @@ packaging = [
     {file = "packaging-21.3.tar.gz", hash = "sha256:dd47c42927d89ab911e606518907cc2d3a1f38bbd026385970643f9c5b8ecfeb"},
 ]
 pandas = [
-    {file = "pandas-1.3.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:9707bdc1ea9639c886b4d3be6e2a45812c1ac0c2080f94c31b71c9fa35556f9b"},
+    {file = "pandas-1.3.5-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:62d5b5ce965bae78f12c1c0df0d387899dd4211ec0bdc52822373f13a3a022b9"},
-    {file = "pandas-1.3.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c2f44425594ae85e119459bb5abb0748d76ef01d9c08583a667e3339e134218e"},
+    {file = "pandas-1.3.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:adfeb11be2d54f275142c8ba9bf67acee771b7186a5745249c7d5a06c670136b"},
-    {file = "pandas-1.3.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:372d72a3d8a5f2dbaf566a5fa5fa7f230842ac80f29a931fb4b071502cf86b9a"},
+    {file = "pandas-1.3.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:60a8c055d58873ad81cae290d974d13dd479b82cbb975c3e1fa2cf1920715296"},
-    {file = "pandas-1.3.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d99d2350adb7b6c3f7f8f0e5dfb7d34ff8dd4bc0a53e62c445b7e43e163fce63"},
+    {file = "pandas-1.3.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd541ab09e1f80a2a1760032d665f6e032d8e44055d602d65eeea6e6e85498cb"},
-    {file = "pandas-1.3.4-cp310-cp310-win_amd64.whl", hash = "sha256:4acc28364863127bca1029fb72228e6f473bb50c32e77155e80b410e2068eeac"},
+    {file = "pandas-1.3.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2651d75b9a167cc8cc572cf787ab512d16e316ae00ba81874b560586fa1325e0"},
-    {file = "pandas-1.3.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c2646458e1dce44df9f71a01dc65f7e8fa4307f29e5c0f2f92c97f47a5bf22f5"},
+    {file = "pandas-1.3.5-cp310-cp310-win_amd64.whl", hash = "sha256:aaf183a615ad790801fa3cf2fa450e5b6d23a54684fe386f7e3208f8b9bfbef6"},
-    {file = "pandas-1.3.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5298a733e5bfbb761181fd4672c36d0c627320eb999c59c65156c6a90c7e1b4f"},
+    {file = "pandas-1.3.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:344295811e67f8200de2390093aeb3c8309f5648951b684d8db7eee7d1c81fb7"},
-    {file = "pandas-1.3.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:22808afb8f96e2269dcc5b846decacb2f526dd0b47baebc63d913bf847317c8f"},
+    {file = "pandas-1.3.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:552020bf83b7f9033b57cbae65589c01e7ef1544416122da0c79140c93288f56"},
-    {file = "pandas-1.3.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b528e126c13816a4374e56b7b18bfe91f7a7f6576d1aadba5dee6a87a7f479ae"},
+    {file = "pandas-1.3.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5cce0c6bbeb266b0e39e35176ee615ce3585233092f685b6a82362523e59e5b4"},
-    {file = "pandas-1.3.4-cp37-cp37m-win32.whl", hash = "sha256:fe48e4925455c964db914b958f6e7032d285848b7538a5e1b19aeb26ffaea3ec"},
+    {file = "pandas-1.3.5-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7d28a3c65463fd0d0ba8bbb7696b23073efee0510783340a44b08f5e96ffce0c"},
-    {file = "pandas-1.3.4-cp37-cp37m-win_amd64.whl", hash = "sha256:eaca36a80acaacb8183930e2e5ad7f71539a66805d6204ea88736570b2876a7b"},
+    {file = "pandas-1.3.5-cp37-cp37m-win32.whl", hash = "sha256:a62949c626dd0ef7de11de34b44c6475db76995c2064e2d99c6498c3dba7fe58"},
-    {file = "pandas-1.3.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:42493f8ae67918bf129869abea8204df899902287a7f5eaf596c8e54e0ac7ff4"},
+    {file = "pandas-1.3.5-cp37-cp37m-win_amd64.whl", hash = "sha256:8025750767e138320b15ca16d70d5cdc1886e8f9cc56652d89735c016cd8aea6"},
-    {file = "pandas-1.3.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a388960f979665b447f0847626e40f99af8cf191bce9dc571d716433130cb3a7"},
+    {file = "pandas-1.3.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:fe95bae4e2d579812865db2212bb733144e34d0c6785c0685329e5b60fcb85dd"},
-    {file = "pandas-1.3.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ba0aac1397e1d7b654fccf263a4798a9e84ef749866060d19e577e927d66e1b"},
+    {file = "pandas-1.3.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f261553a1e9c65b7a310302b9dbac31cf0049a51695c14ebe04e4bfd4a96f02"},
-    {file = "pandas-1.3.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f567e972dce3bbc3a8076e0b675273b4a9e8576ac629149cf8286ee13c259ae5"},
+    {file = "pandas-1.3.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b6dbec5f3e6d5dc80dcfee250e0a2a652b3f28663492f7dab9a24416a48ac39"},
-    {file = "pandas-1.3.4-cp38-cp38-win32.whl", hash = "sha256:c1aa4de4919358c5ef119f6377bc5964b3a7023c23e845d9db7d9016fa0c5b1c"},
+    {file = "pandas-1.3.5-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d3bc49af96cd6285030a64779de5b3688633a07eb75c124b0747134a63f4c05f"},
-    {file = "pandas-1.3.4-cp38-cp38-win_amd64.whl", hash = "sha256:dd324f8ee05925ee85de0ea3f0d66e1362e8c80799eb4eb04927d32335a3e44a"},
+    {file = "pandas-1.3.5-cp38-cp38-win32.whl", hash = "sha256:b6b87b2fb39e6383ca28e2829cddef1d9fc9e27e55ad91ca9c435572cdba51bf"},
-    {file = "pandas-1.3.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d47750cf07dee6b55d8423471be70d627314277976ff2edd1381f02d52dbadf9"},
+    {file = "pandas-1.3.5-cp38-cp38-win_amd64.whl", hash = "sha256:a395692046fd8ce1edb4c6295c35184ae0c2bbe787ecbe384251da609e27edcb"},
-    {file = "pandas-1.3.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2d1dc09c0013d8faa7474574d61b575f9af6257ab95c93dcf33a14fd8d2c1bab"},
+    {file = "pandas-1.3.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bd971a3f08b745a75a86c00b97f3007c2ea175951286cdda6abe543e687e5f2f"},
-    {file = "pandas-1.3.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10e10a2527db79af6e830c3d5842a4d60383b162885270f8cffc15abca4ba4a9"},
+    {file = "pandas-1.3.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:37f06b59e5bc05711a518aa10beaec10942188dccb48918bb5ae602ccbc9f1a0"},
-    {file = "pandas-1.3.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:35c77609acd2e4d517da41bae0c11c70d31c87aae8dd1aabd2670906c6d2c143"},
+    {file = "pandas-1.3.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c21778a688d3712d35710501f8001cdbf96eb70a7c587a3d5613573299fdca6"},
-    {file = "pandas-1.3.4-cp39-cp39-win32.whl", hash = "sha256:003ba92db58b71a5f8add604a17a059f3068ef4e8c0c365b088468d0d64935fd"},
+    {file = "pandas-1.3.5-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3345343206546545bc26a05b4602b6a24385b5ec7c75cb6059599e3d56831da2"},
-    {file = "pandas-1.3.4-cp39-cp39-win_amd64.whl", hash = "sha256:a51528192755f7429c5bcc9e80832c517340317c861318fea9cea081b57c9afd"},
+    {file = "pandas-1.3.5-cp39-cp39-win32.whl", hash = "sha256:c69406a2808ba6cf580c2255bcf260b3f214d2664a3a4197d0e640f573b46fd3"},
-    {file = "pandas-1.3.4.tar.gz", hash = "sha256:a2aa18d3f0b7d538e21932f637fbfe8518d085238b429e4790a35e1e44a96ffc"},
+    {file = "pandas-1.3.5-cp39-cp39-win_amd64.whl", hash = "sha256:32e1a26d5ade11b547721a72f9bfc4bd113396947606e00d5b4a5b79b3dcb006"},
+    {file = "pandas-1.3.5.tar.gz", hash = "sha256:1e4285f5de1012de20ca46b188ccf33521bff61ba5c5ebd78b4fb28e5416a9f1"},
 ]
 parsedatetime = [
     {file = "parsedatetime-2.4-py2-none-any.whl", hash = "sha256:9ee3529454bf35c40a77115f5a596771e59e1aee8c53306f346c461b8e913094"},
@@ -1259,8 +1263,8 @@ pprintpp = [
     {file = "pprintpp-0.4.0.tar.gz", hash = "sha256:ea826108e2c7f49dc6d66c752973c3fc9749142a798d6b254e1e301cfdbc6403"},
 ]
 prompt-toolkit = [
-    {file = "prompt_toolkit-3.0.23-py3-none-any.whl", hash = "sha256:5f29d62cb7a0ecacfa3d8ceea05a63cd22500543472d64298fc06ddda906b25d"},
+    {file = "prompt_toolkit-3.0.24-py3-none-any.whl", hash = "sha256:e56f2ff799bacecd3e88165b1e2f5ebf9bcd59e80e06d395fa0cc4b8bd7bb506"},
-    {file = "prompt_toolkit-3.0.23.tar.gz", hash = "sha256:7053aba00895473cb357819358ef33f11aa97e4ac83d38efb123e5649ceeecaf"},
+    {file = "prompt_toolkit-3.0.24.tar.gz", hash = "sha256:1bb05628c7d87b645974a1bad3f17612be0c29fa39af9f7688030163f680bad6"},
 ]
 ptyprocess = [
     {file = "ptyprocess-0.7.0-py2.py3-none-any.whl", hash = "sha256:4b41f3967fce3af57cc7e94b888626c18bf37a083e3651ca8feeb66d492fef35"},
@@ -1325,8 +1329,8 @@ requests-cache = [
     {file = "requests_cache-0.6.4-py2.py3-none-any.whl", hash = "sha256:1102daa13a804abe23fad62d694e7dee58d6063a35d94bf6e8c9821e22e5a78b"},
 ]
 rich = [
-    {file = "rich-10.15.2-py3-none-any.whl", hash = "sha256:43b2c6ad51f46f6c94992aee546f1c177719f4e05aff8f5ea4d2efae3ebdac89"},
+    {file = "rich-10.16.1-py3-none-any.whl", hash = "sha256:bbe04dd6ac09e4b00d22cb1051aa127beaf6e16c3d8687b026e96d3fca6aad52"},
-    {file = "rich-10.15.2.tar.gz", hash = "sha256:1dded089b79dd042b3ab5cd63439a338e16652001f0c16e73acdcf4997ad772d"},
+    {file = "rich-10.16.1.tar.gz", hash = "sha256:4949e73de321784ef6664ebbc854ac82b20ff60b2865097b93f3b9b41e30da27"},
 ]
 six = [
     {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
@@ -1377,8 +1381,8 @@ toml = [
     {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
 ]
 tomli = [
-    {file = "tomli-1.2.2-py3-none-any.whl", hash = "sha256:f04066f68f5554911363063a30b108d2b5a5b1a010aa8b6132af78489fe3aade"},
+    {file = "tomli-1.2.3-py3-none-any.whl", hash = "sha256:e3069e4be3ead9668e21cb9b074cd948f7b3113fd9c8bba083f48247aab8b11c"},
-    {file = "tomli-1.2.2.tar.gz", hash = "sha256:c6ce0015eb38820eaf32b5db832dbc26deb3dd427bd5f6556cf0acac2c214fee"},
+    {file = "tomli-1.2.3.tar.gz", hash = "sha256:05b6166bff487dc068d322585c7ea4ef78deed501cc124060e0f238e89a9231f"},
 ]
 traitlets = [
     {file = "traitlets-5.1.1-py3-none-any.whl", hash = "sha256:2d313cc50a42cd6c277e7d7dc8d4d7fedd06a2c215f78766ae7b1a66277e0033"},

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "csv-metadata-quality"
-version = "0.5.0"
+version = "0.6.0-dev"
 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"
@@ -21,7 +21,7 @@ pycountry = "^19.8.18"
 langid = "^1.1.6"
 colorama = "^0.4.4"
 spdx-license-list = "^0.5.2"
-ftfy = "^5.9"
+ftfy = "^6.0"
 SQLAlchemy = ">=1.3.3,<1.4.23"
 country-converter = "^0.7.4"
 

requirements-dev.txt

@@ -19,14 +19,14 @@ dbfread==2.0.7
 decorator==5.1.0; python_version >= "3.7" and python_version < "4.0"
 et-xmlfile==1.1.0; python_version >= "3.6"
 flake8==3.9.2; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
-ftfy==5.9; python_version >= "3.5"
+ftfy==6.0.3; python_version >= "3.6"
 future==0.18.2; python_version >= "2.6" and python_full_version < "3.0.0" or python_full_version >= "3.3.0"
 greenlet==1.1.2; python_version >= "3" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3"
 idna==3.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
 importlib-metadata==4.8.2; python_full_version >= "3.6.2" and python_version < "3.8" and python_version >= "3.6" and (python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6") and (python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.6.0" and python_version < "3.8" and python_version >= "3.6")
 iniconfig==1.1.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
 ipython==7.30.1; python_version >= "3.7" and python_version < "4.0"
-isodate==0.6.0
+isodate==0.6.1
 isort==5.10.1; python_full_version >= "3.6.1" and python_version < "4.0"
 itsdangerous==2.0.1; python_version >= "3.6"
 jedi==0.18.1; python_version >= "3.7" and python_version < "4.0"
@@ -39,7 +39,7 @@ numpy==1.21.1
 olefile==0.46; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0"
 openpyxl==3.0.9; python_version >= "3.6"
 packaging==21.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
-pandas==1.3.4; python_full_version >= "3.7.1"
+pandas==1.3.5; python_full_version >= "3.7.1"
 parsedatetime==2.4
 parso==0.8.3; python_version >= "3.7" and python_version < "4.0"
 pathspec==0.9.0; python_full_version >= "3.6.2"
@@ -48,7 +48,7 @@ pickleshare==0.7.5; python_version >= "3.7" and python_version < "4.0"
 platformdirs==2.4.0; python_version >= "3.6" and python_full_version >= "3.6.2"
 pluggy==1.0.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
 pprintpp==0.4.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0"
-prompt-toolkit==3.0.23; python_version >= "3.7" and python_version < "4.0" and python_full_version >= "3.6.2"
+prompt-toolkit==3.0.24; python_version >= "3.7" and python_version < "4.0" and python_full_version >= "3.6.2"
 ptyprocess==0.7.0; python_version >= "3.7" and python_version < "4.0" and sys_platform != "win32"
 py==1.11.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6"
 pycodestyle==2.7.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
@@ -65,13 +65,13 @@ pytimeparse==1.1.8
 pytz==2021.3; python_full_version >= "3.7.1"
 requests-cache==0.6.4; python_version >= "3.6"
 requests==2.26.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.6.0")
-rich==10.15.2; python_full_version >= "3.6.2" and python_full_version < "4.0.0" and (python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0")
+rich==10.16.1; python_full_version >= "3.6.2" and python_full_version < "4.0.0" and (python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0")
 six==1.16.0; python_full_version >= "3.7.1" and python_version >= "3.6" and (python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.3.0")
 spdx-license-list==0.5.2
 sqlalchemy==1.4.22; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.6.0")
 text-unidecode==1.3; python_version >= "3.6"
 toml==0.10.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
-tomli==1.2.2; python_version >= "3.6" and python_full_version >= "3.6.2"
+tomli==1.2.3; python_version >= "3.6" and python_full_version >= "3.6.2"
 traitlets==5.1.1; python_version >= "3.7" and python_version < "4.0"
 typed-ast==1.5.1; python_version < "3.8" and implementation_name == "cpython" and python_full_version >= "3.6.2" and python_version >= "3.6"
 typing-extensions==4.0.1

requirements.txt

@@ -1,201 +1,27 @@
-certifi==2021.10.8; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6" \
+certifi==2021.10.8; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
-    --hash=sha256:d62a0163eb4c2344ac042ab2bdf75399a71a2d8c7d47eac2e2ee91b9d6339569 \
+charset-normalizer==2.0.9; python_full_version >= "3.6.0" and python_version >= "3.6"
-    --hash=sha256:78884e7c1d4b00ce3cea67b44566851c4343c120abd683433ce934a68ea58872
+colorama==0.4.4; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
-charset-normalizer==2.0.9; python_full_version >= "3.6.0" and python_version >= "3.6" \
+country-converter==0.7.4
-    --hash=sha256:b0b883e8e874edfdece9c28f314e3dd5badf067342e42fb162203335ae61aa2c \
+ftfy==6.0.3; python_version >= "3.6"
-    --hash=sha256:1eecaa09422db5be9e29d7fc65664e6c33bd06f9ced7838578ba40d58bdf3721
+greenlet==1.1.2; python_version >= "3" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3"
-colorama==0.4.4; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0") \
+idna==3.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
-    --hash=sha256:9f47eda37229f68eee03b24b9748937c7dc3868f906e8ba69fbcbdd3bc5dc3e2 \
+importlib-metadata==4.8.2; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.6.0" and python_version < "3.8" and python_version >= "3.6"
-    --hash=sha256:5941b2b48a20143d2267e95b1c2a7603ce057ee39fd88e7329b0c292aa16869b
+itsdangerous==2.0.1; python_version >= "3.6"
-country-converter==0.7.4 \
+langid==1.1.6
-    --hash=sha256:0291cc91c4a4efe7f128a11c8c6e4cb761f7fea7cde2517f8677c7c56da334d3
+numpy==1.21.1
-ftfy==5.9; python_version >= "3.5" \
+pandas==1.3.5; python_full_version >= "3.7.1"
-    --hash=sha256:8c4fb2863c0b82eae2ab3cf353d9ade268dfbde863d322f78d6a9fd5cefb31e9
+pycountry==19.8.18
-greenlet==1.1.2; python_version >= "3" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3" \
+python-dateutil==2.8.2; python_full_version >= "3.7.1"
-    --hash=sha256:58df5c2a0e293bf665a51f8a100d3e9956febfbf1d9aaf8c0677cf70218910c6 \
+python-stdnum==1.17
-    --hash=sha256:aec52725173bd3a7b56fe91bc56eccb26fbdff1386ef123abb63c84c5b43b63a \
+pytz==2021.3; python_full_version >= "3.7.1"
-    --hash=sha256:833e1551925ed51e6b44c800e71e77dacd7e49181fdc9ac9a0bf3714d515785d \
+requests-cache==0.6.4; python_version >= "3.6"
-    --hash=sha256:aa5b467f15e78b82257319aebc78dd2915e4c1436c3c0d1ad6f53e47ba6e2713 \
+requests==2.26.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.6.0")
-    --hash=sha256:40b951f601af999a8bf2ce8c71e8aaa4e8c6f78ff8afae7b808aae2dc50d4c40 \
+six==1.16.0; python_full_version >= "3.7.1" and python_version >= "3.6"
-    --hash=sha256:95e69877983ea39b7303570fa6760f81a3eec23d0e3ab2021b7144b94d06202d \
+spdx-license-list==0.5.2
-    --hash=sha256:356b3576ad078c89a6107caa9c50cc14e98e3a6c4874a37c3e0273e4baf33de8 \
+sqlalchemy==1.4.22; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.6.0")
-    --hash=sha256:8639cadfda96737427330a094476d4c7a56ac03de7265622fcf4cfe57c8ae18d \
+typing-extensions==4.0.1; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.6.0" and python_version < "3.8" and python_version >= "3.6"
-    --hash=sha256:97e5306482182170ade15c4b0d8386ded995a07d7cc2ca8f27958d34d6736497 \
+url-normalize==1.4.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6"
-    --hash=sha256:e6a36bb9474218c7a5b27ae476035497a6990e21d04c279884eb10d9b290f1b1 \
+urllib3==1.26.7; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version < "4" and python_version >= "3.6"
-    --hash=sha256:abb7a75ed8b968f3061327c433a0fbd17b729947b400747c334a9c29a9af6c58 \
+wcwidth==0.2.5; python_version >= "3.6"
-    --hash=sha256:14d4f3cd4e8b524ae9b8aa567858beed70c392fdec26dbdb0a8a418392e71708 \
+xlrd==1.2.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.4.0")
-    --hash=sha256:17ff94e7a83aa8671a25bf5b59326ec26da379ace2ebc4411d690d80a7fbcf23 \
+zipp==3.6.0; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.6.0" and python_version < "3.8" and python_version >= "3.6"
-    --hash=sha256:9f3cba480d3deb69f6ee2c1825060177a22c7826431458c697df88e6aeb3caee \
-    --hash=sha256:fa877ca7f6b48054f847b61d6fa7bed5cebb663ebc55e018fda12db09dcc664c \
-    --hash=sha256:7cbd7574ce8e138bda9df4efc6bf2ab8572c9aff640d8ecfece1b006b68da963 \
-    --hash=sha256:903bbd302a2378f984aef528f76d4c9b1748f318fe1294961c072bdc7f2ffa3e \
-    --hash=sha256:049fe7579230e44daef03a259faa24511d10ebfa44f69411d99e6a184fe68073 \
-    --hash=sha256:dd0b1e9e891f69e7675ba5c92e28b90eaa045f6ab134ffe70b52e948aa175b3c \
-    --hash=sha256:7418b6bfc7fe3331541b84bb2141c9baf1ec7132a7ecd9f375912eca810e714e \
-    --hash=sha256:f9d29ca8a77117315101425ec7ec2a47a22ccf59f5593378fc4077ac5b754fce \
-    --hash=sha256:21915eb821a6b3d9d8eefdaf57d6c345b970ad722f856cd71739493ce003ad08 \
-    --hash=sha256:eff9d20417ff9dcb0d25e2defc2574d10b491bf2e693b4e491914738b7908168 \
-    --hash=sha256:32ca72bbc673adbcfecb935bb3fb1b74e663d10a4b241aaa2f5a75fe1d1f90aa \
-    --hash=sha256:f0214eb2a23b85528310dad848ad2ac58e735612929c8072f6093f3585fd342d \
-    --hash=sha256:b92e29e58bef6d9cfd340c72b04d74c4b4e9f70c9fa7c78b674d1fec18896dc4 \
-    --hash=sha256:fdcec0b8399108577ec290f55551d926d9a1fa6cad45882093a7a07ac5ec147b \
-    --hash=sha256:93f81b134a165cc17123626ab8da2e30c0455441d4ab5576eed73a64c025b25c \
-    --hash=sha256:1e12bdc622676ce47ae9abbf455c189e442afdde8818d9da983085df6312e7a1 \
-    --hash=sha256:8c790abda465726cfb8bb08bd4ca9a5d0a7bd77c7ac1ca1b839ad823b948ea28 \
-    --hash=sha256:f276df9830dba7a333544bd41070e8175762a7ac20350786b322b714b0e654f5 \
-    --hash=sha256:64e6175c2e53195278d7388c454e0b30997573f3f4bd63697f88d855f7a6a1fc \
-    --hash=sha256:b11548073a2213d950c3f671aa88e6f83cda6e2fb97a8b6317b1b5b33d850e06 \
-    --hash=sha256:9633b3034d3d901f0a46b7939f8c4d64427dfba6bbc5a36b1a67364cf148a1b0 \
-    --hash=sha256:eb6ea6da4c787111adf40f697b4e58732ee0942b5d3bd8f435277643329ba627 \
-    --hash=sha256:f3acda1924472472ddd60c29e5b9db0cec629fbe3c5c5accb74d6d6d14773478 \
-    --hash=sha256:e859fcb4cbe93504ea18008d1df98dee4f7766db66c435e4882ab35cf70cac43 \
-    --hash=sha256:00e44c8afdbe5467e4f7b5851be223be68adb4272f44696ee71fe46b7036a711 \
-    --hash=sha256:ec8c433b3ab0419100bd45b47c9c8551248a5aee30ca5e9d399a0b57ac04651b \
-    --hash=sha256:288c6a76705dc54fba69fbcb59904ae4ad768b4c768839b8ca5fdadec6dd8cfd \
-    --hash=sha256:8d2f1fb53a421b410751887eb4ff21386d119ef9cde3797bf5e7ed49fb51a3b3 \
-    --hash=sha256:166eac03e48784a6a6e0e5f041cfebb1ab400b394db188c48b3a84737f505b67 \
-    --hash=sha256:572e1787d1460da79590bf44304abbc0a2da944ea64ec549188fa84d89bba7ab \
-    --hash=sha256:be5f425ff1f5f4b3c1e33ad64ab994eed12fc284a6ea71c5243fd564502ecbe5 \
-    --hash=sha256:b1692f7d6bc45e3200844be0dba153612103db241691088626a33ff1f24a0d88 \
-    --hash=sha256:7227b47e73dedaa513cdebb98469705ef0d66eb5a1250144468e9c3097d6b59b \
-    --hash=sha256:7ff61ff178250f9bb3cd89752df0f1dd0e27316a8bd1465351652b1b4a4cdfd3 \
-    --hash=sha256:f70a9e237bb792c7cc7e44c531fd48f5897961701cdaa06cf22fc14965c496cf \
-    --hash=sha256:013d61294b6cd8fe3242932c1c5e36e5d1db2c8afb58606c5a67efce62c1f5fd \
-    --hash=sha256:e30f5ea4ae2346e62cedde8794a56858a67b878dd79f7df76a0767e356b1744a
-idna==3.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6" \
-    --hash=sha256:84d9dd047ffa80596e0f246e2eab0b391788b0503584e8945f2368256d2735ff \
-    --hash=sha256:9d643ff0a55b762d5cdb124b8eaa99c66322e2157b69160bc32796e824360e6d
-importlib-metadata==4.8.2; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.6.0" and python_version < "3.8" and python_version >= "3.6" \
-    --hash=sha256:53ccfd5c134223e497627b9815d5030edf77d2ed573922f7a0b8f8bb81a1c100 \
-    --hash=sha256:75bdec14c397f528724c1bfd9709d660b33a4d2e77387a3358f20b848bb5e5fb
-itsdangerous==2.0.1; python_version >= "3.6" \
-    --hash=sha256:5174094b9637652bdb841a3029700391451bd092ba3db90600dea710ba28e97c \
-    --hash=sha256:9e724d68fc22902a1435351f84c3fb8623f303fffcc566a4cb952df8c572cff0
-langid==1.1.6 \
-    --hash=sha256:044bcae1912dab85c33d8e98f2811b8f4ff1213e5e9a9e9510137b84da2cb293
-numpy==1.21.1 \
-    --hash=sha256:38e8648f9449a549a7dfe8d8755a5979b45b3538520d1e735637ef28e8c2dc50 \
-    --hash=sha256:fd7d7409fa643a91d0a05c7554dd68aa9c9bb16e186f6ccfe40d6e003156e33a \
-    --hash=sha256:a75b4498b1e93d8b700282dc8e655b8bd559c0904b3910b144646dbbbc03e062 \
-    --hash=sha256:1412aa0aec3e00bc23fbb8664d76552b4efde98fb71f60737c83efbac24112f1 \
-    --hash=sha256:e46ceaff65609b5399163de5893d8f2a82d3c77d5e56d976c8b5fb01faa6b671 \
-    --hash=sha256:c6a2324085dd52f96498419ba95b5777e40b6bcbc20088fddb9e8cbb58885e8e \
-    --hash=sha256:73101b2a1fef16602696d133db402a7e7586654682244344b8329cdcbbb82172 \
-    --hash=sha256:7a708a79c9a9d26904d1cca8d383bf869edf6f8e7650d85dbc77b041e8c5a0f8 \
-    --hash=sha256:95b995d0c413f5d0428b3f880e8fe1660ff9396dcd1f9eedbc311f37b5652e16 \
-    --hash=sha256:635e6bd31c9fb3d475c8f44a089569070d10a9ef18ed13738b03049280281267 \
-    --hash=sha256:4a3d5fb89bfe21be2ef47c0614b9c9c707b7362386c9a3ff1feae63e0267ccb6 \
-    --hash=sha256:8a326af80e86d0e9ce92bcc1e65c8ff88297de4fa14ee936cb2293d414c9ec63 \
-    --hash=sha256:791492091744b0fe390a6ce85cc1bf5149968ac7d5f0477288f78c89b385d9af \
-    --hash=sha256:0318c465786c1f63ac05d7c4dbcecd4d2d7e13f0959b01b534ea1e92202235c5 \
-    --hash=sha256:9a513bd9c1551894ee3d31369f9b07460ef223694098cf27d399513415855b68 \
-    --hash=sha256:91c6f5fc58df1e0a3cc0c3a717bb3308ff850abdaa6d2d802573ee2b11f674a8 \
-    --hash=sha256:978010b68e17150db8765355d1ccdd450f9fc916824e8c4e35ee620590e234cd \
-    --hash=sha256:9749a40a5b22333467f02fe11edc98f022133ee1bfa8ab99bda5e5437b831214 \
-    --hash=sha256:d7a4aeac3b94af92a9373d6e77b37691b86411f9745190d2c351f410ab3a791f \
-    --hash=sha256:d9e7912a56108aba9b31df688a4c4f5cb0d9d3787386b87d504762b6754fbb1b \
-    --hash=sha256:25b40b98ebdd272bc3020935427a4530b7d60dfbe1ab9381a39147834e985eac \
-    --hash=sha256:8a92c5aea763d14ba9d6475803fc7904bda7decc2a0a68153f587ad82941fec1 \
-    --hash=sha256:05a0f648eb28bae4bcb204e6fd14603de2908de982e761a2fc78efe0f19e96e1 \
-    --hash=sha256:f01f28075a92eede918b965e86e8f0ba7b7797a95aa8d35e1cc8821f5fc3ad6a \
-    --hash=sha256:88c0b89ad1cc24a5efbb99ff9ab5db0f9a86e9cc50240177a571fbe9c2860ac2 \
-    --hash=sha256:01721eefe70544d548425a07c80be8377096a54118070b8a62476866d5208e33 \
-    --hash=sha256:2d4d1de6e6fb3d28781c73fbde702ac97f03d79e4ffd6598b880b2d95d62ead4 \
-    --hash=sha256:dff4af63638afcc57a3dfb9e4b26d434a7a602d225b42d746ea7fe2edf1342fd
-pandas==1.3.4; python_full_version >= "3.7.1" \
-    --hash=sha256:9707bdc1ea9639c886b4d3be6e2a45812c1ac0c2080f94c31b71c9fa35556f9b \
-    --hash=sha256:c2f44425594ae85e119459bb5abb0748d76ef01d9c08583a667e3339e134218e \
-    --hash=sha256:372d72a3d8a5f2dbaf566a5fa5fa7f230842ac80f29a931fb4b071502cf86b9a \
-    --hash=sha256:d99d2350adb7b6c3f7f8f0e5dfb7d34ff8dd4bc0a53e62c445b7e43e163fce63 \
-    --hash=sha256:4acc28364863127bca1029fb72228e6f473bb50c32e77155e80b410e2068eeac \
-    --hash=sha256:c2646458e1dce44df9f71a01dc65f7e8fa4307f29e5c0f2f92c97f47a5bf22f5 \
-    --hash=sha256:5298a733e5bfbb761181fd4672c36d0c627320eb999c59c65156c6a90c7e1b4f \
-    --hash=sha256:22808afb8f96e2269dcc5b846decacb2f526dd0b47baebc63d913bf847317c8f \
-    --hash=sha256:b528e126c13816a4374e56b7b18bfe91f7a7f6576d1aadba5dee6a87a7f479ae \
-    --hash=sha256:fe48e4925455c964db914b958f6e7032d285848b7538a5e1b19aeb26ffaea3ec \
-    --hash=sha256:eaca36a80acaacb8183930e2e5ad7f71539a66805d6204ea88736570b2876a7b \
-    --hash=sha256:42493f8ae67918bf129869abea8204df899902287a7f5eaf596c8e54e0ac7ff4 \
-    --hash=sha256:a388960f979665b447f0847626e40f99af8cf191bce9dc571d716433130cb3a7 \
-    --hash=sha256:5ba0aac1397e1d7b654fccf263a4798a9e84ef749866060d19e577e927d66e1b \
-    --hash=sha256:f567e972dce3bbc3a8076e0b675273b4a9e8576ac629149cf8286ee13c259ae5 \
-    --hash=sha256:c1aa4de4919358c5ef119f6377bc5964b3a7023c23e845d9db7d9016fa0c5b1c \
-    --hash=sha256:dd324f8ee05925ee85de0ea3f0d66e1362e8c80799eb4eb04927d32335a3e44a \
-    --hash=sha256:d47750cf07dee6b55d8423471be70d627314277976ff2edd1381f02d52dbadf9 \
-    --hash=sha256:2d1dc09c0013d8faa7474574d61b575f9af6257ab95c93dcf33a14fd8d2c1bab \
-    --hash=sha256:10e10a2527db79af6e830c3d5842a4d60383b162885270f8cffc15abca4ba4a9 \
-    --hash=sha256:35c77609acd2e4d517da41bae0c11c70d31c87aae8dd1aabd2670906c6d2c143 \
-    --hash=sha256:003ba92db58b71a5f8add604a17a059f3068ef4e8c0c365b088468d0d64935fd \
-    --hash=sha256:a51528192755f7429c5bcc9e80832c517340317c861318fea9cea081b57c9afd \
-    --hash=sha256:a2aa18d3f0b7d538e21932f637fbfe8518d085238b429e4790a35e1e44a96ffc
-pycountry==19.8.18 \
-    --hash=sha256:3c57aa40adcf293d59bebaffbe60d8c39976fba78d846a018dc0c2ec9c6cb3cb
-python-dateutil==2.8.2; python_full_version >= "3.7.1" \
-    --hash=sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86 \
-    --hash=sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9
-python-stdnum==1.17 \
-    --hash=sha256:374e2b5e13912ccdbf50b0b23fca2c3e0531174805c32d74e145f37756328340 \
-    --hash=sha256:a46e6cf9652807314d369b654b255c86a59f93d18be2834f3d567ed1a346c547
-pytz==2021.3; python_full_version >= "3.7.1" \
-    --hash=sha256:3672058bc3453457b622aab7a1c3bfd5ab0bdae451512f6cf25f64ed37f5b87c \
-    --hash=sha256:acad2d8b20a1af07d4e4c9d2e9285c5ed9104354062f275f3fcd88dcef4f1326
-requests-cache==0.6.4; python_version >= "3.6" \
-    --hash=sha256:dd9120a4ab7b8128cba9b6b120d8b5560d566a3cd0f828cced3d3fd60a42ec40 \
-    --hash=sha256:1102daa13a804abe23fad62d694e7dee58d6063a35d94bf6e8c9821e22e5a78b
-requests==2.26.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.6.0") \
-    --hash=sha256:6c1246513ecd5ecd4528a0906f910e8f0f9c6b8ec72030dc9fd154dc1a6efd24 \
-    --hash=sha256:b8aa58f8cf793ffd8782d3d8cb19e66ef36f7aba4353eec859e74678b01b07a7
-six==1.16.0; python_full_version >= "3.7.1" and python_version >= "3.6" \
-    --hash=sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254 \
-    --hash=sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926
-spdx-license-list==0.5.2 \
-    --hash=sha256:1b338470c7b403dbecceca563a316382c7977516128ca6c1e8f7078e3ed6e7b0 \
-    --hash=sha256:952996f72ab807972dc2278bb9b91e5294767211e51f09aad9c0e2ff5b82a31b
-sqlalchemy==1.4.22; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.6.0") \
-    --hash=sha256:488608953385d6c127d2dcbc4b11f8d7f2f30b89f6bd27c01b042253d985cc2f \
-    --hash=sha256:5d856cc50fd26fc8dd04892ed5a5a3d7eeb914fea2c2e484183e2d84c14926e0 \
-    --hash=sha256:a00d9c6d3a8afe1d1681cd8a5266d2f0ed684b0b44bada2ca82403b9e8b25d39 \
-    --hash=sha256:5908ea6c652a050d768580d01219c98c071e71910ab8e7b42c02af4010608397 \
-    --hash=sha256:b7fb937c720847879c7402fe300cfdb2aeff22349fa4ea3651bca4e2d6555939 \
-    --hash=sha256:9bfe882d5a1bbde0245dca0bd48da0976bd6634cf2041d2fdf0417c5463e40e5 \
-    --hash=sha256:eedd76f135461cf237534a6dc0d1e0f6bb88a1dc193678fab48a11d223462da5 \
-    --hash=sha256:6a16c7c4452293da5143afa3056680db2d187b380b3ef4d470d4e29885720de3 \
-    --hash=sha256:44d23ea797a5e0be71bc5454b9ae99158ea0edc79e2393c6e9a2354de88329c0 \
-    --hash=sha256:a5e14cb0c0a4ac095395f24575a0e7ab5d1be27f5f9347f1762f21505e3ba9f1 \
-    --hash=sha256:bc34a007e604091ca3a4a057525efc4cefd2b7fe970f44d20b9cfa109ab1bddb \
-    --hash=sha256:756f5d2f5b92d27450167247fb574b09c4cd192a3f8c2e493b3e518a204ee543 \
-    --hash=sha256:9fcbb4b4756b250ed19adc5e28c005b8ed56fdb5c21efa24c6822c0575b4964d \
-    --hash=sha256:09dbb4bc01a734ccddbf188deb2a69aede4b3c153a72b6d5c6900be7fb2945b1 \
-    --hash=sha256:f028ef6a1d828bc754852a022b2160e036202ac8658a6c7d34875aafd14a9a15 \
-    --hash=sha256:68393d3fd31469845b6ba11f5b4209edbea0b58506be0e077aafbf9aa2e21e11 \
-    --hash=sha256:891927a49b2363a4199763a9d436d97b0b42c65922a4ea09025600b81a00d17e \
-    --hash=sha256:fd2102a8f8a659522719ed73865dff3d3cc76eb0833039dc473e0ad3041d04be \
-    --hash=sha256:4014978de28163cd8027434916a92d0f5bb1a3a38dff5e8bf8bff4d9372a9117 \
-    --hash=sha256:f814d80844969b0d22ea63663da4de5ca1c434cfbae226188901e5d368792c17 \
-    --hash=sha256:d09a760b0a045b4d799102ae7965b5491ccf102123f14b2a8cc6c01d1021a2d9 \
-    --hash=sha256:26daa429f039e29b1e523bf763bfab17490556b974c77b5ca7acb545b9230e9a \
-    --hash=sha256:12bac5fa1a6ea870bdccb96fe01610641dd44ebe001ed91ef7fcd980e9702db5 \
-    --hash=sha256:39b5d36ab71f73c068cdcf70c38075511de73616e6c7fdd112d6268c2704d9f5 \
-    --hash=sha256:5102b9face693e8b2db3b2539c7e1a5d9a5b4dc0d79967670626ffd2f710d6e6 \
-    --hash=sha256:c9373ef67a127799027091fa53449125351a8c943ddaa97bec4e99271dbb21f4 \
-    --hash=sha256:36a089dc604032d41343d86290ce85d4e6886012eea73faa88001260abf5ff81 \
-    --hash=sha256:b48148ceedfb55f764562e04c00539bb9ea72bf07820ca15a594a9a049ff6b0e \
-    --hash=sha256:1fdae7d980a2fa617d119d0dc13ecb5c23cc63a8b04ffcb5298f2c59d86851e9 \
-    --hash=sha256:ec1be26cdccd60d180359a527d5980d959a26269a2c7b1b327a1eea0cab37ed8
-typing-extensions==4.0.1; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.6.0" and python_version < "3.8" and python_version >= "3.6" \
-    --hash=sha256:7f001e5ac290a0c0401508864c7ec868be4e701886d5b573a9528ed3973d9d3b \
-    --hash=sha256:4ca091dea149f945ec56afb48dae714f21e8692ef22a395223bcd328961b6a0e
-url-normalize==1.4.3; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.6" \
-    --hash=sha256:d23d3a070ac52a67b83a1c59a0e68f8608d1cd538783b401bc9de2c0fac999b2 \
-    --hash=sha256:ec3c301f04e5bb676d333a7fa162fa977ad2ca04b7e652bfc9fac4e405728eed
-urllib3==1.26.7; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version < "4" and python_version >= "3.6" \
-    --hash=sha256:c4fdf4019605b6e5423637e01bc9fe4daef873709a7973e195ceba0a62bbc844 \
-    --hash=sha256:4987c65554f7a2dbf30c18fd48778ef124af6fab771a377103da0585e2336ece
-wcwidth==0.2.5; python_version >= "3.5" \
-    --hash=sha256:beb4802a9cebb9144e99086eff703a642a13d6a0052920003a230f3294bbe784 \
-    --hash=sha256:c4d647b99872929fdb7bdcaa4fbe7f01413ed3d98077df798530e5b04f116c83
-xlrd==1.2.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.4.0") \
-    --hash=sha256:e551fb498759fa3a5384a94ccd4c3c02eb7c00ea424426e212ac0c57be9dfbde \
-    --hash=sha256:546eb36cee8db40c3eaa46c351e67ffee6eeb5fa2650b71bc4c758a29a1b29b2
-zipp==3.6.0; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.6.0" and python_version < "3.8" and python_version >= "3.6" \
-    --hash=sha256:9fe5ea21568a0a70e50f273397638d39b03353731e6cbbb3fd8502a33fec40bc \
-    --hash=sha256:71c644c5369f4a6e07636f0aa966270449561fcea2e3d6747b8d23efaa9d7832

setup.py

@@ -14,7 +14,7 @@ install_requires = [
 
 setuptools.setup(
     name="csv-metadata-quality",
-    version="0.5.0",
+    version="0.6.0-dev",
     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.",
@@ -26,6 +26,7 @@ setuptools.setup(
         "Programming Language :: Python :: 3.7",
         "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
         "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
         "Operating System :: OS Independent",
     ],

tests/test_check.py

@@ -179,18 +179,41 @@ def test_check_invalid_language(capsys):
 
 
 def test_check_invalid_agrovoc(capsys):
-    """Test invalid AGROVOC subject."""
+    """Test invalid AGROVOC subject. Invalid values *will not* be dropped."""
 
-    value = "FOREST"
+    valid_agrovoc = "LIVESTOCK"
+    invalid_agrovoc = "FOREST"
+    value = f"{valid_agrovoc}||{invalid_agrovoc}"
     field_name = "dcterms.subject"
+    drop = False
 
-    check.agrovoc(value, field_name)
+    new_value = check.agrovoc(value, field_name, drop)
 
     captured = capsys.readouterr()
     assert (
         captured.out
-        == f"{Fore.RED}Invalid AGROVOC ({field_name}): {Fore.RESET}{value}\n"
+        == f"{Fore.RED}Invalid AGROVOC ({field_name}): {Fore.RESET}{invalid_agrovoc}\n"
     )
+    assert new_value == value
+
+
+def test_check_invalid_agrovoc_dropped(capsys):
+    """Test invalid AGROVOC subjects. Invalid values *will* be dropped."""
+
+    valid_agrovoc = "LIVESTOCK"
+    invalid_agrovoc = "FOREST"
+    value = f"{valid_agrovoc}||{invalid_agrovoc}"
+    field_name = "dcterms.subject"
+    drop = True
+
+    new_value = check.agrovoc(value, field_name, drop)
+
+    captured = capsys.readouterr()
+    assert (
+        captured.out
+        == f"{Fore.GREEN}Dropping invalid AGROVOC ({field_name}): {Fore.RESET}{invalid_agrovoc}\n"
+    )
+    assert new_value == valid_agrovoc
 
 
 def test_check_valid_agrovoc():
@@ -198,10 +221,11 @@ def test_check_valid_agrovoc():
 
     value = "FORESTS"
     field_name = "dcterms.subject"
+    drop = False
 
-    result = check.agrovoc(value, field_name)
+    result = check.agrovoc(value, field_name, drop)
 
-    assert result == None
+    assert result == "FORESTS"
 
 
 def test_check_uncommon_filename_extension(capsys):