.github/workflows: use rye in CI

Use rye instead of poetry in CI.

.drone.yml

@@ -1,3 +1,33 @@
+---
+kind: pipeline
+type: docker
+name: python311
+
+steps:
+- name: test
+  image: python:3.11-slim
+  commands:
+  - id
+  - python -V
+  - apt update && apt install -y gcc g++ libicu-dev pkg-config git
+  - python -m pip install poetry
+  - poetry install
+  - poetry run pytest
+  # Basic test
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+  # Basic test with unsafe fixes
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
+  # Geography test
+  - poetry run csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv
+  # Geography test with unsafe fixes
+  - poetry run csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv -u
+  # Test with experimental checks
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e
+  # Test with AGROVOC validation
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject
+  # Test with AGROVOC validation (and dropping invalid)
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject -d
+
 ---
 kind: pipeline
 type: docker
@@ -9,24 +39,24 @@ steps:
   commands:
   - id
   - python -V
-  - apt update && apt install -y gcc g++ libicu-dev pkg-config
-  - pip install -r requirements-dev.txt
-  - pytest
-  - python setup.py install
+  - apt update && apt install -y gcc g++ libicu-dev pkg-config git
+  - python -m pip install poetry
+  - poetry install
+  - poetry run pytest
   # Basic test
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv
   # Basic test with unsafe fixes
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
   # Geography test
-  - csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv
+  - poetry run csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv
   # Geography test with unsafe fixes
-  - csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv -u
+  - poetry run csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv -u
   # Test with experimental checks
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e
+  - poetry run 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
+  - poetry run 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
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject -d
 
 ---
 kind: pipeline
@@ -39,53 +69,23 @@ steps:
   commands:
   - id
   - python -V
-  - apt update && apt install -y gcc g++ libicu-dev pkg-config
-  - pip install -r requirements-dev.txt
-  - pytest
-  - python setup.py install
+  - apt update && apt install -y gcc g++ libicu-dev pkg-config git
+  - python -m pip install poetry
+  - poetry install
+  - poetry run pytest
   # Basic test
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv
   # Basic test with unsafe fixes
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
+  - poetry run csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
   # Geography test
-  - csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv
+  - poetry run csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv
   # Geography test with unsafe fixes
-  - csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv -u
+  - poetry run csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv -u
   # Test with experimental checks
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -e
+  - poetry run 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
+  - poetry run 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
-type: docker
-name: python38
-
-steps:
-- name: test
-  image: python:3.8-slim
-  commands:
-  - id
-  - python -V
-  - apt update && apt install -y gcc g++ libicu-dev pkg-config
-  - pip install -r requirements-dev.txt
-  - pytest
-  - python setup.py install
-  # Basic test
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv
-  # Basic test with unsafe fixes
-  - csv-metadata-quality -i data/test.csv -o /tmp/test.csv -u
-  # Geography test
-  - csv-metadata-quality -i data/test-geography.csv -o /tmp/test.csv
-  # Geography test with unsafe fixes
-  - csv-metadata-quality -i data/test-geography.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
+  - poetry run 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

@@ -12,39 +12,30 @@ on:
 jobs:
   build:
 
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
 
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v2
+    - uses: actions/checkout@v4
+    - name: Install rye
+      uses: eifinger/setup-rye@v4
       with:
-        python-version: '3.10'
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install flake8 pytest
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-        if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
-    - name: Lint with flake8
+        version: 'latest'
+    - run: rye sync
+    - name: Lint
       run: |
         # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+        rye lint
     - name: Test with pytest
-      run: |
-        pytest
+      run: rye test
     - name: Test CLI
       run: |
-        python setup.py install
         # Basic test
-        csv-metadata-quality -i data/test.csv -o /tmp/test.csv
+        rye run 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
+        rye run 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
+        rye run 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
+        rye run 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
+        rye run csv-metadata-quality -i data/test.csv -o /tmp/test.csv --agrovoc-fields dcterms.subject -d

.python-version

@@ -0,0 +1 @@
+3.12

CHANGELOG.md

@@ -4,7 +4,44 @@ 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).
 
-## [0.6.0] = 2022-09-02
+## Unreleased
+### Added
+- Ability to normalize DOIs to https://doi.org URI format
+
+### Fixed
+- Fixed regex so we don't run the invalid multi-value separator fix on
+`dcterms.bibliographicCitation` fields
+- Fixed regex so we run the comma space fix on `dcterms.bibliographicCitation`
+fields
+- Don't crash the country/region checker/fixer when a title field is missing
+
+### Changed
+- Don't run newline fix on description fields
+- Install requests-cache in main run() function instead of check.agrovoc() function so we only incur the overhead once
+- Use py3langid instead of langid, see: [How to make language detection with langid.py faster](https://adrien.barbaresi.eu/blog/language-detection-langid-py-faster.html)
+
+### Updated
+- Python dependencies, including Pandas 2.0.0 and [Arrow-backed dtypes](https://datapythonista.me/blog/pandas-20-and-the-arrow-revolution-part-i)
+- SPDX license list
+
+## [0.6.1] - 2023-02-23
+### Fixed
+- Missing region check should ignore subregion field, if it exists
+
+### Changed
+- Use SPDX license data from SPDX themselves instead of spdx-license-list
+because it is deprecated and outdated
+- Require Python 3.9+
+- Don't run `fix.separators()` on title or abstract fields
+- Don't run whitespace or newline fixes on abstract fields
+- Ignore some common non-SPDX licenses
+- Ignore `__description` suffix in filenames meant for SAFBuilder when checking
+for uncommon file extensions
+
+### Updated
+- Python dependencies
+
+## [0.6.0] - 2022-09-02
 ### Changed
 - Perform fix for "unnecessary" Unicode characters after we try to fix encoding
 issues with ftfy

MANIFEST.in

@@ -0,0 +1 @@
+include csv_metadata_quality/data/licenses.json

README.md

@@ -8,7 +8,7 @@
 
 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, unnecessary Unicode, AGROVOC terms, etc.
 
-Requires Python 3.8 or greater. CSV support comes from the [Pandas](https://pandas.pydata.org/) library.
+Requires Python 3.9 or greater. CSV support comes from the [Pandas](https://pandas.pydata.org/) library.
 
 If you use the DSpace CSV metadata quality checker please cite:
 
@@ -31,6 +31,7 @@ If you use the DSpace CSV metadata quality checker please cite:
 - Check for countries with missing regions (and attempt to fix with `--unsafe-fixes`)
 - Remove duplicate metadata values
 - Check for duplicate items, using the title, type, and date issued as an indicator
+- [Normalize DOIs](https://www.crossref.org/documentation/member-setup/constructing-your-dois/) to https://doi.org URI format
 
 ## Installation
 The easiest way to install CSV Metadata Quality is with [poetry](https://python-poetry.org):
@@ -125,9 +126,7 @@ This currently uses the [Python langid](https://github.com/saffsd/langid.py) lib
 - Better logging, for example with INFO, WARN, and ERR levels
 - Verbose, debug, or quiet options
 - Warn if an author is shorter than 3 characters?
-- Validate DOIs? Normalize to https://doi.org format? Or use just the DOI part: 10.1016/j.worlddev.2010.06.006
 - Warn if two items use the same file in `filename` column
-- Add an option to drop invalid AGROVOC subjects?
 - Add tests for application invocation, ie `tests/test_app.py`?
 - Validate ISSNs or journal titles against CrossRef API?
 - Add configurable field validation, like specify a field name and a validation file?
@@ -137,7 +136,7 @@ This currently uses the [Python langid](https://github.com/saffsd/langid.py) lib
   - Warn if item is Open Access, but missing a license
   - Warn if item has an ISSN but no journal title
   - Update journal titles from ISSN
-- Migrate to https://github.com/spdx/license-list-data
+- Migrate from Pandas to Polars
 
 ## License
 This work is licensed under the [GPLv3](https://www.gnu.org/licenses/gpl-3.0.en.html).

csv_metadata_quality/app.py

@@ -1,11 +1,14 @@
 # SPDX-License-Identifier: GPL-3.0-only
 
 import argparse
+import os
 import re
 import signal
 import sys
+from datetime import timedelta
 
 import pandas as pd
+import requests_cache
 from colorama import Fore
 
 import csv_metadata_quality.check as check
@@ -74,7 +77,7 @@ def run(argv):
     signal.signal(signal.SIGINT, signal_handler)
 
     # Read all fields as strings so dates don't get converted from 1998 to 1998.0
-    df = pd.read_csv(args.input_file, dtype=str)
+    df = pd.read_csv(args.input_file, dtype_backend="pyarrow", dtype="str")
 
     # Check if the user requested to skip any fields
     if args.exclude_fields:
@@ -82,7 +85,20 @@ def run(argv):
         # user should be careful to no include spaces here.
         exclude = args.exclude_fields.split(",")
     else:
-        exclude = list()
+        exclude = []
+
+    # enable transparent request cache with thirty days expiry
+    expire_after = timedelta(days=30)
+    # Allow overriding the location of the requests cache, just in case we are
+    # running in an environment where we can't write to the current working di-
+    # rectory (for example from csv-metadata-quality-web).
+    REQUESTS_CACHE_DIR = os.environ.get("REQUESTS_CACHE_DIR", ".")
+    requests_cache.install_cache(
+        f"{REQUESTS_CACHE_DIR}/agrovoc-response-cache", expire_after=expire_after
+    )
+
+    # prune old cache entries
+    requests_cache.delete()
 
     for column in df.columns:
         if column in exclude:
@@ -90,17 +106,21 @@ def run(argv):
 
             continue
 
-        # Fix: whitespace
-        df[column] = df[column].apply(fix.whitespace, field_name=column)
-
-        # Fix: newlines
         if args.unsafe_fixes:
-            df[column] = df[column].apply(fix.newlines, field_name=column)
+            # Skip whitespace and newline fixes on abstracts and descriptions
+            # because there are too many with legitimate multi-line metadata.
+            match = re.match(r"^.*?(abstract|description).*$", column)
+            if match is None:
+                # Fix: whitespace
+                df[column] = df[column].apply(fix.whitespace, field_name=column)
+
+                # Fix: newlines
+                df[column] = df[column].apply(fix.newlines, field_name=column)
 
         # Fix: missing space after comma. Only run on author and citation
         # fields for now, as this problem is mostly an issue in names.
         if args.unsafe_fixes:
-            match = re.match(r"^.*?(author|citation).*$", column)
+            match = re.match(r"^.*?(author|[Cc]itation).*$", column)
             if match is not None:
                 df[column] = df[column].apply(fix.comma_space, field_name=column)
 
@@ -121,10 +141,19 @@ def run(argv):
         # 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
-        df[column] = df[column].apply(fix.whitespace, field_name=column)
+        # Fix: normalize DOIs
+        match = re.match(r"^.*?identifier\.doi.*$", column)
+        if match is not None:
+            df[column] = df[column].apply(fix.normalize_dois)
+
+        # Fix: invalid and unnecessary multi-value separators. Skip the title
+        # and abstract fields because "|" is used to indicate something like
+        # a subtitle.
+        match = re.match(r"^.*?(abstract|[Cc]itation|title).*$", column)
+        if match is None:
+            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, field_name=column)
 
         # Fix: duplicate metadata values
         df[column] = df[column].apply(fix.duplicates, field_name=column)

csv_metadata_quality/check.py

@@ -1,21 +1,18 @@
 # SPDX-License-Identifier: GPL-3.0-only
 
 import logging
-import os
 import re
-from datetime import datetime, timedelta
+from datetime import datetime
 
 import country_converter as coco
 import pandas as pd
 import requests
-import requests_cache
-import spdx_license_list
 from colorama import Fore
 from pycountry import languages
 from stdnum import isbn as stdnum_isbn
 from stdnum import issn as stdnum_issn
 
-from csv_metadata_quality.util import is_mojibake
+from csv_metadata_quality.util import is_mojibake, load_spdx_licenses
 
 
 def issn(field):
@@ -34,7 +31,6 @@ def issn(field):
 
     # Try to split multi-value field on "||" separator
     for value in field.split("||"):
-
         if not stdnum_issn.is_valid(value):
             print(f"{Fore.RED}Invalid ISSN: {Fore.RESET}{value}")
 
@@ -57,7 +53,6 @@ def isbn(field):
 
     # Try to split multi-value field on "||" separator
     for value in field.split("||"):
-
         if not stdnum_isbn.is_valid(value):
             print(f"{Fore.RED}Invalid ISBN: {Fore.RESET}{value}")
 
@@ -138,7 +133,7 @@ def suspicious_characters(field, field_name):
         return
 
     # List of suspicious characters, for example:  ́ˆ~`
-    suspicious_characters = ["\u00B4", "\u02C6", "\u007E", "\u0060"]
+    suspicious_characters = ["\u00b4", "\u02c6", "\u007e", "\u0060"]
 
     for character in suspicious_characters:
         # Find the position of the suspicious character in the string
@@ -174,7 +169,6 @@ def language(field):
 
     # Try to split multi-value field on "||" separator
     for value in field.split("||"):
-
         # After splitting, check if language value is 2 or 3 characters so we
         # can check it against ISO 639-1 or ISO 639-3 accordingly.
         if len(value) == 2:
@@ -207,25 +201,12 @@ def agrovoc(field, field_name, drop):
     if pd.isna(field):
         return
 
-    # enable transparent request cache with thirty days expiry
-    expire_after = timedelta(days=30)
-    # Allow overriding the location of the requests cache, just in case we are
-    # running in an environment where we can't write to the current working di-
-    # rectory (for example from csv-metadata-quality-web).
-    REQUESTS_CACHE_DIR = os.environ.get("REQUESTS_CACHE_DIR", ".")
-    requests_cache.install_cache(
-        f"{REQUESTS_CACHE_DIR}/agrovoc-response-cache", expire_after=expire_after
-    )
-
-    # prune old cache entries
-    # requests_cache.remove_expired_responses()
-
     # Initialize an empty list to hold the validated AGROVOC values
-    values = list()
+    values = []
 
     # Try to split multi-value field on "||" separator
     for value in field.split("||"):
-        request_url = "http://agrovoc.uniroma2.it/agrovoc/rest/v1/agrovoc/search"
+        request_url = "https://agrovoc.uniroma2.it/agrovoc/rest/v1/agrovoc/search"
         request_params = {"query": value}
 
         request = requests.get(request_url, params=request_params)
@@ -287,6 +268,11 @@ def filename_extension(field):
 
     # Iterate over all values
     for value in values:
+        # Strip filename descriptions that are meant for SAF Bundler, for
+        # example: Annual_Report_2020.pdf__description:Report
+        if "__description" in value:
+            value = value.split("__")[0]
+
         # Assume filename extension does not match
         filename_extension_match = False
 
@@ -313,13 +299,26 @@ def spdx_license_identifier(field):
     Prints the value if it is invalid.
     """
 
+    # List of common non-SPDX licenses to ignore
+    # See: https://ilri.github.io/cgspace-submission-guidelines/dcterms-license/dcterms-license.txt
+    ignore_licenses = {
+        "All rights reserved; no re-use allowed",
+        "All rights reserved; self-archive copy only",
+        "Copyrighted; Non-commercial educational use only",
+        "Copyrighted; Non-commercial use only",
+        "Copyrighted; all rights reserved",
+        "Other",
+    }
+
     # Skip fields with missing values
-    if pd.isna(field):
+    if pd.isna(field) or field in ignore_licenses:
         return
 
+    spdx_licenses = load_spdx_licenses()
+
     # Try to split multi-value field on "||" separator
     for value in field.split("||"):
-        if value not in spdx_license_list.LICENSES:
+        if value not in spdx_licenses:
             print(f"{Fore.YELLOW}Non-SPDX license identifier: {Fore.RESET}{value}")
 
     return
@@ -359,7 +358,7 @@ def duplicate_items(df):
 
     if items_count_unique < items_count_total:
         # Create a list to hold our items while we check for duplicates
-        items = list()
+        items = []
 
         for index, row in df.iterrows():
             item_title_type_date = f"{row[title_column_name]}{row[type_column_name]}{row[date_column_name]}"
@@ -512,9 +511,9 @@ def countries_match_regions(row, exclude):
         if match is not None:
             country_column_name = label
 
-        # Find the name of the region column
+        # Find the name of the region column, but make sure it's not subregion!
         match = re.match(r"^.*?region.*$", label)
-        if match is not None:
+        if match is not None and "sub" not in label:
             region_column_name = label
 
         # Find the name of the title column
@@ -540,7 +539,7 @@ def countries_match_regions(row, exclude):
         if row[region_column_name] is not None:
             regions = row[region_column_name].split("||")
         else:
-            regions = list()
+            regions = []
 
         for country in countries:
             # Look up the UN M.49 regions for this country code. CoCo seems to
@@ -549,8 +548,13 @@ def countries_match_regions(row, exclude):
             un_region = cc.convert(names=country, to="UNRegion")
 
             if un_region != "not found" and un_region not in regions:
-                print(
-                    f"{Fore.YELLOW}Missing region ({un_region}): {Fore.RESET}{row[title_column_name]}"
-                )
+                try:
+                    print(
+                        f"{Fore.YELLOW}Missing region ({country} → {un_region}): {Fore.RESET}{row[title_column_name]}"
+                    )
+                except KeyError:
+                    print(
+                        f"{Fore.YELLOW}Missing region ({country} → {un_region}): {Fore.RESET}<title field not present>"
+                    )
 
     return

csv_metadata_quality/experimental.py

@@ -2,8 +2,8 @@
 
 import re
 
-import langid
 import pandas as pd
+import py3langid as langid
 from colorama import Fore
 from pycountry import languages
 
@@ -20,7 +20,7 @@ def correct_language(row, exclude):
     # Initialize some variables at global scope so that we can set them in the
     # loop scope below and still be able to access them afterwards.
     language = ""
-    sample_strings = list()
+    sample_strings = []
     title = None
 
     # Iterate over the labels of the current row's values. Before we transposed

csv_metadata_quality/fix.py

@@ -23,7 +23,7 @@ def whitespace(field, field_name):
         return
 
     # Initialize an empty list to hold the cleaned values
-    values = list()
+    values = []
 
     # Try to split multi-value field on "||" separator
     for value in field.split("||"):
@@ -64,7 +64,7 @@ def separators(field, field_name):
         return
 
     # Initialize an empty list to hold the cleaned values
-    values = list()
+    values = []
 
     # Try to split multi-value field on "||" separator
     for value in field.split("||"):
@@ -175,7 +175,7 @@ def duplicates(field, field_name):
     values = field.split("||")
 
     # Initialize an empty list to hold the de-duplicated values
-    new_values = list()
+    new_values = []
 
     # Iterate over all values
     for value in values:
@@ -327,9 +327,9 @@ def countries_match_regions(row, exclude):
         if match is not None:
             country_column_name = label
 
-        # Find the name of the region column
+        # Find the name of the region column, but make sure it's not subregion!
         match = re.match(r"^.*?region.*$", label)
-        if match is not None:
+        if match is not None and "sub" not in label:
             region_column_name = label
 
         # Find the name of the title column
@@ -355,10 +355,10 @@ def countries_match_regions(row, exclude):
         if row[region_column_name] is not None:
             regions = row[region_column_name].split("||")
         else:
-            regions = list()
+            regions = []
 
         # An empty list for our regions so we can keep track for all countries
-        missing_regions = list()
+        missing_regions = []
 
         for country in countries:
             # Look up the UN M.49 regions for this country code. CoCo seems to
@@ -370,9 +370,17 @@ def countries_match_regions(row, exclude):
             # it doesn't already exist in regions.
             if un_region != "not found" and un_region not in regions:
                 if un_region not in missing_regions:
-                    print(
-                        f"{Fore.YELLOW}Adding missing region ({un_region}): {Fore.RESET}{row[title_column_name]}"
-                    )
+                    try:
+                        print(
+                            f"{Fore.YELLOW}Adding missing region ({un_region}): {Fore.RESET}{row[title_column_name]}"
+                        )
+                    except KeyError:
+                        # If there is no title column in the CSV we will print
+                        # the fix without the title instead of crashing.
+                        print(
+                            f"{Fore.YELLOW}Adding missing region ({un_region}): {Fore.RESET}<title field not present>"
+                        )
+
                     missing_regions.append(un_region)
 
         if len(missing_regions) > 0:
@@ -387,3 +395,88 @@ def countries_match_regions(row, exclude):
                 row[region_column_name] = "||".join(missing_regions)
 
     return row
+
+
+def normalize_dois(field):
+    """Normalize DOIs.
+
+    DOIs are meant to be globally unique identifiers. They are case insensitive,
+    but in order to compare them robustly they should be normalized to a common
+    format:
+
+        - strip leading and trailing whitespace
+        - lowercase all ASCII characters
+        - convert all variations to https://doi.org/10.xxxx/xxxx URI format
+
+    Return string with normalized DOI.
+
+    See: https://www.crossref.org/documentation/member-setup/constructing-your-dois/
+    """
+
+    # Skip fields with missing values
+    if pd.isna(field):
+        return
+
+    # Try to split multi-value field on "||" separator
+    values = field.split("||")
+
+    # Initialize an empty list to hold the de-duplicated values
+    new_values = []
+
+    # Iterate over all values (most items will only have one DOI)
+    for value in values:
+        # Strip leading and trailing whitespace
+        new_value = value.strip()
+
+        new_value = new_value.lower()
+
+        # Convert to HTTPS
+        pattern = re.compile(r"^http://")
+        match = re.findall(pattern, new_value)
+
+        if match:
+            new_value = re.sub(pattern, "https://", new_value)
+
+        # Convert dx.doi.org to doi.org
+        pattern = re.compile(r"dx\.doi\.org")
+        match = re.findall(pattern, new_value)
+
+        if match:
+            new_value = re.sub(pattern, "doi.org", new_value)
+
+        # Convert www.doi.org to doi.org
+        pattern = re.compile(r"www\.doi\.org")
+        match = re.findall(pattern, new_value)
+
+        if match:
+            new_value = re.sub(pattern, "doi.org", new_value)
+
+        # Convert erroneous %2f to /
+        pattern = re.compile("%2f")
+        match = re.findall(pattern, new_value)
+
+        if match:
+            new_value = re.sub(pattern, "/", new_value)
+
+        # Replace values like doi: 10.11648/j.jps.20140201.14
+        pattern = re.compile(r"^doi: 10\.")
+        match = re.findall(pattern, new_value)
+
+        if match:
+            new_value = re.sub(pattern, "https://doi.org/10.", new_value)
+
+        # Replace values like 10.3390/foods12010115
+        pattern = re.compile(r"^10\.")
+        match = re.findall(pattern, new_value)
+
+        if match:
+            new_value = re.sub(pattern, "https://doi.org/10.", new_value)
+
+        if new_value != value:
+            print(f"{Fore.GREEN}Normalized DOI: {Fore.RESET}{value}")
+
+        new_values.append(new_value)
+
+    new_field = "||".join(new_values)
+
+    return new_field

csv_metadata_quality/util.py

@@ -1,5 +1,9 @@
 # SPDX-License-Identifier: GPL-3.0-only
 
+
+import json
+import os
+
 from ftfy.badness import is_bad
 
 
@@ -49,3 +53,13 @@ def is_mojibake(field):
     else:
         # Encodable as CP-1252, Mojibake alert level high
         return True
+
+
+def load_spdx_licenses():
+    """Returns a Python list of SPDX short license identifiers."""
+
+    with open(os.path.join(os.path.dirname(__file__), "data/licenses.json")) as f:
+        licenses = json.load(f)
+
+    # List comprehension to extract the license ID for each license
+    return [license["licenseId"] for license in licenses["licenses"]]

csv_metadata_quality/version.py

@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-3.0-only
 
-VERSION = "0.6.0"
+VERSION = "0.6.1"

data/abstract-check.csv

@@ -0,0 +1,17 @@
+id,dc.title,dcterms.abstract
+1,Normal item,This is an abstract
+2,Leading whitespace, This is an abstract
+3,Trailing whitespace,This is an abstract 
+4,Consecutive whitespace,This is  an abstract
+5,Newline,"This
+is an abstract"
+6,Newline with leading whitespace," This
+ is an abstract"
+7,Newline with trailing whitespace,"This 
+is an abstract "
+8,Newline with consecutive whitespace,"This
+is an  abstract"
+9,Multiple newlines,"This
+is
+an
+abstract"

data/test.csv

@@ -1,38 +1,43 @@
-dc.title,dcterms.issued,dc.identifier.issn,dc.identifier.isbn,dcterms.language,dcterms.subject,cg.coverage.country,filename,dcterms.license,dcterms.type,dcterms.bibliographicCitation,cg.identifier.doi,cg.coverage.region
- Leading space,2019-07-29,,,,,,,,,,,
-Trailing space ,2019-07-29,,,,,,,,,,,
-Excessive  space,2019-07-29,,,,,,,,,,,
-Miscellaenous ||whitespace | issues ,2019-07-29,,,,,,,,,,,
-Duplicate||Duplicate,2019-07-29,,,,,,,,,,,
-Invalid ISSN,2019-07-29,2321-2302,,,,,,,,,,
-Invalid ISBN,2019-07-29,,978-0-306-40615-6,,,,,,,,,
-Multiple valid ISSNs,2019-07-29,0378-5955||0024-9319,,,,,,,,,,
-Multiple valid ISBNs,2019-07-29,,99921-58-10-7||978-0-306-40615-7,,,,,,,,,
-Invalid date,2019-07-260,,,,,,,,,,,
-Multiple dates,2019-07-26||2019-01-10,,,,,,,,,,,
-Invalid multi-value separator,2019-07-29,0378-5955|0024-9319,,,,,,,,,,
-Unnecessary Unicode​,2019-07-29,,,,,,,,,,,
-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,,,,LIVESTOCK||FOREST,,,,,,,
+dc.title,dcterms.issued,dc.identifier.issn,dc.identifier.isbn,dcterms.language,dcterms.subject,cg.coverage.country,filename,dcterms.license,dcterms.type,dcterms.bibliographicCitation,cg.identifier.doi,cg.coverage.region,cg.coverage.subregion
+ Leading space,2019-07-29,,,,,,,,,,,,
+Trailing space ,2019-07-29,,,,,,,,,,,,
+Excessive  space,2019-07-29,,,,,,,,,,,,
+Miscellaenous ||whitespace | issues ,2019-07-29,,,,,,,,,,,,
+Duplicate||Duplicate,2019-07-29,,,,,,,,,,,,
+Invalid ISSN,2019-07-29,2321-2302,,,,,,,,,,,
+Invalid ISBN,2019-07-29,,978-0-306-40615-6,,,,,,,,,,
+Multiple valid ISSNs,2019-07-29,0378-5955||0024-9319,,,,,,,,,,,
+Multiple valid ISBNs,2019-07-29,,99921-58-10-7||978-0-306-40615-7,,,,,,,,,,
+Invalid date,2019-07-260,,,,,,,,,,,,
+Multiple dates,2019-07-26||2019-01-10,,,,,,,,,,,,
+Invalid multi-value separator,2019-07-29,0378-5955|0024-9319,,,,,,,,,,,
+Unnecessary Unicode​,2019-07-29,,,,,,,,,,,,
+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,,,,LIVESTOCK||FOREST,,,,,,,,
 Newline (LF),2019-07-30,,,,"TANZA
-NIA",,,,,,,
-Missing date,,,,,,,,,,,,
-Invalid country,2019-08-01,,,,,KENYAA,,,,,,
-Uncommon filename extension,2019-08-10,,,,,,file.pdf.lck,,,,,
-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,,,,,,,,,,,
-Unnecessary multi-value separator,2021-01-03,0378-5955||,,,,,,,,,,
-Invalid SPDX license identifier,2021-03-11,,,,,,,CC-BY,,,,
-Duplicate Title,2021-03-17,,,,,,,,Report,,,
-Duplicate Title,2021-03-17,,,,,,,,Report,,,
-Mojibake,2021-03-18,,,,Publicaçao CIAT,,,,Report,,,
-"DOI in citation, but missing cg.identifier.doi",2021-10-06,,,,,,,,,"Orth, A. 2021. DOI in citation, but missing cg.identifier.doi. doi: 10.1186/1743-422X-9-218",,
-Title missing from citation,2021-12-05,,,,,,,,,"Orth, A. 2021. Title missing f rom citation.",,
-Country missing region,2021-12-08,,,,,Kenya,,,,,,
+NIA",,,,,,,,
+Missing date,,,,,,,,,,,,,
+Invalid country,2019-08-01,,,,,KENYAA,,,,,,,
+Uncommon filename extension,2019-08-10,,,,,,file.pdf.lck,,,,,,
+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,,,,,,,,,,,,
+Unnecessary multi-value separator,2021-01-03,0378-5955||,,,,,,,,,,,
+Invalid SPDX license identifier,2021-03-11,,,,,,,CC-BY,,,,,
+Duplicate Title,2021-03-17,,,,,,,,Report,,,,
+Duplicate Title,2021-03-17,,,,,,,,Report,,,,
+Mojibake,2021-03-18,,,,Publicaçao CIAT,,,,Report,,,,
+"DOI in citation, but missing cg.identifier.doi",2021-10-06,,,,,,,,,"Orth, A. 2021. DOI in citation, but missing cg.identifier.doi. doi: 10.1186/1743-422X-9-218",,,
+Title missing from citation,2021-12-05,,,,,,,,,"Orth, A. 2021. Title missing f rom citation.",,,
+Country missing region,2021-12-08,,,,,Kenya,,,,,,,
+Subregion field shouldn’t trigger region checks,2022-12-07,,,,,Kenya,,,,,,Eastern Africa,Baringo
+DOI with HTTP and dx.doi.org,2024-04-23,,,,,,,,,,http://dx.doi.org/10.1016/j.envc.2023.100794,,
+DOI with colon,2024-04-23,,,,,,,,,,doi: 10.11648/j.jps.20140201.14,,
+Upper case bare DOI,2024-04-23,,,,,,,,,,10.19103/AS.2018.0043.16,,
+DOI with %2f,2024-06-25,,,,,,,,,,https://doi.org/10.1016%2fj.envc.2023.100794,,

pyproject.toml

@@ -1,36 +1,64 @@
-[tool.poetry]
+[project]
 name = "csv-metadata-quality"
-version = "0.6.0"
+version = "0.6.1"
 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"
+authors = [
+    { name = "Alan Orth", email = "alan.orth@gmail.com" }
+]
+license= { file = "LICENSE.txt" }
+dependencies = [
+    "pandas[feather,performance]~=2.2",
+    "python-stdnum~=1.20",
+    "requests~=2.32",
+    "requests-cache~=1.2.1",
+    "colorama~=0.4",
+    "ftfy~=6.2.0",
+    "country-converter~=1.2",
+    "pycountry~=24.6.1",
+    "py3langid~=0.3",
+]
+readme = "README.md"
+requires-python = ">= 3.9"
+
+classifiers = [
+  "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+  "Natural Language :: English",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: Implementation :: CPython",
+]
+
+[project.urls]
 repository = "https://github.com/ilri/csv-metadata-quality"
 homepage = "https://github.com/ilri/csv-metadata-quality"
 
-[tool.poetry.scripts]
+[project.scripts]
 csv-metadata-quality = 'csv_metadata_quality.__main__:main'
 
-[tool.poetry.dependencies]
-python = "^3.8"
-pandas = "^1.4.0"
-python-stdnum = "^1.13"
-requests = "^2.28.1"
-requests-cache = "^0.9.6"
-pycountry = "^22.3.5"
-langid = "^1.1.6"
-colorama = "^0.4.5"
-spdx-license-list = "^0.5.2"
-ftfy = "^6.1.1"
-country-converter = "^0.7.7"
-
-[tool.poetry.dev-dependencies]
-pytest = "^7.1.3"
-flake8 = "^5.0.4"
-pytest-clarity = "^1.0.1"
-black = "^22.8.0"
-isort = "^5.10.1"
-csvkit = "^1.0.7"
-
+# So rye doesn't fall back to setuptools
+# See: https://packaging.python.org/en/latest/tutorials/packaging-projects/#choosing-build-backend
 [build-system]
-requires = ["poetry>=0.12"]
-build-backend = "poetry.masonry.api"
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.rye]
+managed = true
+dev-dependencies = [
+    "pytest~=8.3",
+    "pytest-clarity~=1.0",
+    "isort~=5.13",
+    "csvkit~=2.0",
+    "ipython~=8.26",
+    "fixit~=2.1",
+]
+
+# So hatch doesn't try to build other top-level directories like "data"
+[tool.hatch.build.targets.wheel]
+packages = ["csv_metadata_quality"]
+
+[tool.isort]
+profile = "black"
+line_length=88

renovate.json

@@ -0,0 +1,9 @@
+{
+  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
+  "extends": [
+    "config:base"
+  ],
+  "pip_requirements": {
+      "enabled": false
+  }
+}

requirements-dev.lock

@@ -0,0 +1,188 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+#   with-sources: false
+#   generate-hashes: false
+#   universal: false
+
+-e file:.
+agate==1.10.2
+    # via agate-dbf
+    # via agate-excel
+    # via agate-sql
+    # via csvkit
+agate-dbf==0.2.3
+    # via csvkit
+agate-excel==0.4.1
+    # via csvkit
+agate-sql==0.7.2
+    # via csvkit
+asttokens==2.4.1
+    # via stack-data
+attrs==23.2.0
+    # via cattrs
+    # via requests-cache
+babel==2.15.0
+    # via agate
+bottleneck==1.3.8
+    # via pandas
+cattrs==23.2.3
+    # via requests-cache
+certifi==2024.2.2
+    # via requests
+charset-normalizer==3.3.2
+    # via requests
+click==8.1.7
+    # via fixit
+    # via moreorless
+colorama==0.4.6
+    # via csv-metadata-quality
+country-converter==1.2
+    # via csv-metadata-quality
+csvkit==2.0.1
+dbfread==2.0.7
+    # via agate-dbf
+decorator==5.1.1
+    # via ipython
+et-xmlfile==1.1.0
+    # via openpyxl
+executing==2.0.1
+    # via stack-data
+fixit==2.1.0
+ftfy==6.2.0
+    # via csv-metadata-quality
+greenlet==3.0.3
+    # via sqlalchemy
+idna==3.7
+    # via requests
+iniconfig==2.0.0
+    # via pytest
+ipython==8.26.0
+isodate==0.6.1
+    # via agate
+isort==5.13.2
+jedi==0.19.1
+    # via ipython
+leather==0.4.0
+    # via agate
+libcst==1.4.0
+    # via fixit
+llvmlite==0.43.0
+    # via numba
+markdown-it-py==3.0.0
+    # via rich
+matplotlib-inline==0.1.7
+    # via ipython
+mdurl==0.1.2
+    # via markdown-it-py
+moreorless==0.4.0
+    # via fixit
+numba==0.60.0
+    # via pandas
+numexpr==2.10.0
+    # via pandas
+numpy==2.0.0
+    # via bottleneck
+    # via numba
+    # via numexpr
+    # via pandas
+    # via py3langid
+    # via pyarrow
+olefile==0.47
+    # via agate-excel
+openpyxl==3.1.2
+    # via agate-excel
+    # via csvkit
+packaging==24.0
+    # via fixit
+    # via pytest
+pandas==2.2.2
+    # via country-converter
+    # via csv-metadata-quality
+parsedatetime==2.6
+    # via agate
+parso==0.8.4
+    # via jedi
+pathspec==0.12.1
+    # via trailrunner
+pexpect==4.9.0
+    # via ipython
+platformdirs==4.2.2
+    # via requests-cache
+pluggy==1.5.0
+    # via pytest
+pprintpp==0.4.0
+    # via pytest-clarity
+prompt-toolkit==3.0.43
+    # via ipython
+ptyprocess==0.7.0
+    # via pexpect
+pure-eval==0.2.2
+    # via stack-data
+py3langid==0.3.0
+    # via csv-metadata-quality
+pyarrow==16.1.0
+    # via pandas
+pycountry==24.6.1
+    # via csv-metadata-quality
+pygments==2.18.0
+    # via ipython
+    # via rich
+pytest==8.3.2
+    # via pytest-clarity
+pytest-clarity==1.0.1
+python-dateutil==2.9.0.post0
+    # via pandas
+python-slugify==8.0.4
+    # via agate
+python-stdnum==1.20
+    # via csv-metadata-quality
+pytimeparse==1.1.8
+    # via agate
+pytz==2024.1
+    # via pandas
+pyyaml==6.0.1
+    # via libcst
+requests==2.32.2
+    # via csv-metadata-quality
+    # via requests-cache
+requests-cache==1.2.1
+    # via csv-metadata-quality
+rich==13.7.1
+    # via pytest-clarity
+six==1.16.0
+    # via asttokens
+    # via isodate
+    # via python-dateutil
+    # via url-normalize
+sqlalchemy==2.0.30
+    # via agate-sql
+    # via csvkit
+stack-data==0.6.3
+    # via ipython
+text-unidecode==1.3
+    # via python-slugify
+trailrunner==1.4.0
+    # via fixit
+traitlets==5.14.3
+    # via ipython
+    # via matplotlib-inline
+typing-extensions==4.11.0
+    # via sqlalchemy
+tzdata==2024.1
+    # via pandas
+url-normalize==1.4.3
+    # via requests-cache
+urllib3==2.2.1
+    # via requests
+    # via requests-cache
+wcwidth==0.2.13
+    # via ftfy
+    # via prompt-toolkit
+xlrd==2.0.1
+    # via agate-excel
+    # via csvkit

requirements-dev.txt

@@ -1,68 +0,0 @@
-agate-dbf==0.2.2 ; python_version >= "3.8" and python_version < "4.0"
-agate-excel==0.2.5 ; python_version >= "3.8" and python_version < "4.0"
-agate-sql==0.5.8 ; python_version >= "3.8" and python_version < "4.0"
-agate==1.6.3 ; python_version >= "3.8" and python_version < "4.0"
-appdirs==1.4.4 ; python_version >= "3.8" and python_version < "4.0"
-attrs==22.1.0 ; python_version >= "3.8" and python_version < "4.0"
-babel==2.10.3 ; python_version >= "3.8" and python_version < "4.0"
-black==22.8.0 ; python_version >= "3.8" and python_version < "4.0"
-cattrs==22.1.0 ; python_version >= "3.8" and python_version < "4.0"
-certifi==2022.6.15 ; python_version >= "3.8" and python_version < "4"
-charset-normalizer==2.1.1 ; python_version >= "3.8" and python_version < "4"
-click==8.1.3 ; python_version >= "3.8" and python_version < "4.0"
-colorama==0.4.5 ; python_version >= "3.8" and python_version < "4.0"
-commonmark==0.9.1 ; python_version >= "3.8" and python_version < "4.0"
-country-converter==0.7.7 ; python_version >= "3.8" and python_version < "4.0"
-csvkit==1.0.7 ; python_version >= "3.8" and python_version < "4.0"
-dbfread==2.0.7 ; python_version >= "3.8" and python_version < "4.0"
-et-xmlfile==1.1.0 ; python_version >= "3.8" and python_version < "4.0"
-exceptiongroup==1.0.0rc9 ; python_version >= "3.8" and python_version <= "3.10"
-flake8==5.0.4 ; python_version >= "3.8" and python_version < "4.0"
-ftfy==6.1.1 ; python_version >= "3.8" and python_version < "4"
-future==0.18.2 ; python_version >= "3.8" and python_version < "4.0"
-greenlet==1.1.3 ; python_version >= "3.8" and (platform_machine == "aarch64" or platform_machine == "ppc64le" or platform_machine == "x86_64" or platform_machine == "amd64" or platform_machine == "AMD64" or platform_machine == "win32" or platform_machine == "WIN32") and python_version < "4.0"
-idna==3.3 ; python_version >= "3.8" and python_version < "4"
-iniconfig==1.1.1 ; python_version >= "3.8" and python_version < "4.0"
-isodate==0.6.1 ; python_version >= "3.8" and python_version < "4.0"
-isort==5.10.1 ; python_version >= "3.8" and python_version < "4.0"
-langid==1.1.6 ; python_version >= "3.8" and python_version < "4.0"
-leather==0.3.4 ; python_version >= "3.8" and python_version < "4.0"
-mccabe==0.7.0 ; python_version >= "3.8" and python_version < "4.0"
-mypy-extensions==0.4.3 ; python_version >= "3.8" and python_version < "4.0"
-numpy==1.23.2 ; python_version < "4.0" and python_version >= "3.8"
-olefile==0.46 ; python_version >= "3.8" and python_version < "4.0"
-openpyxl==3.0.10 ; python_version >= "3.8" and python_version < "4.0"
-packaging==21.3 ; python_version >= "3.8" and python_version < "4.0"
-pandas==1.4.4 ; python_version >= "3.8" and python_version < "4.0"
-parsedatetime==2.4 ; python_version >= "3.8" and python_version < "4.0"
-pathspec==0.10.1 ; python_version >= "3.8" and python_version < "4.0"
-platformdirs==2.5.2 ; python_version >= "3.8" and python_version < "4.0"
-pluggy==1.0.0 ; python_version >= "3.8" and python_version < "4.0"
-pprintpp==0.4.0 ; python_version >= "3.8" and python_version < "4.0"
-py==1.11.0 ; python_version >= "3.8" and python_version < "4.0"
-pycodestyle==2.9.1 ; python_version >= "3.8" and python_version < "4.0"
-pycountry==22.3.5 ; python_version >= "3.8" and python_version < "4"
-pyflakes==2.5.0 ; python_version >= "3.8" and python_version < "4.0"
-pygments==2.13.0 ; python_version >= "3.8" and python_version < "4.0"
-pyparsing==3.0.9 ; python_version >= "3.8" and python_version < "4.0"
-pytest-clarity==1.0.1 ; python_version >= "3.8" and python_version < "4.0"
-pytest==7.1.3 ; python_version >= "3.8" and python_version < "4.0"
-python-dateutil==2.8.2 ; python_version >= "3.8" and python_version < "4.0"
-python-slugify==6.1.2 ; python_version >= "3.8" and python_version < "4.0"
-python-stdnum==1.17 ; python_version >= "3.8" and python_version < "4.0"
-pytimeparse==1.1.8 ; python_version >= "3.8" and python_version < "4.0"
-pytz==2022.2.1 ; python_version >= "3.8" and python_version < "4.0"
-requests-cache==0.9.6 ; python_version >= "3.8" and python_version < "4.0"
-requests==2.28.1 ; python_version >= "3.8" and python_version < "4"
-rich==12.5.1 ; python_version >= "3.8" and python_version < "4.0"
-setuptools==65.3.0 ; python_version >= "3.8" and python_version < "4"
-six==1.16.0 ; python_version >= "3.8" and python_version < "4.0"
-spdx-license-list==0.5.2 ; python_version >= "3.8" and python_version < "4.0"
-sqlalchemy==1.4.40 ; python_version >= "3.8" and python_version < "4.0"
-text-unidecode==1.3 ; python_version >= "3.8" and python_version < "4.0"
-tomli==2.0.1 ; python_version >= "3.8" and python_version < "4.0"
-typing-extensions==4.3.0 ; python_version >= "3.8" and python_version < "3.10"
-url-normalize==1.4.3 ; python_version >= "3.8" and python_version < "4.0"
-urllib3==1.26.12 ; python_version >= "3.8" and python_version < "4"
-wcwidth==0.2.5 ; python_version >= "3.8" and python_version < "4"
-xlrd==2.0.1 ; python_version >= "3.8" and python_version < "4.0"

requirements.lock

@@ -0,0 +1,78 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+#   with-sources: false
+#   generate-hashes: false
+#   universal: false
+
+-e file:.
+attrs==23.2.0
+    # via cattrs
+    # via requests-cache
+bottleneck==1.3.8
+    # via pandas
+cattrs==23.2.3
+    # via requests-cache
+certifi==2024.2.2
+    # via requests
+charset-normalizer==3.3.2
+    # via requests
+colorama==0.4.6
+    # via csv-metadata-quality
+country-converter==1.2
+    # via csv-metadata-quality
+ftfy==6.2.0
+    # via csv-metadata-quality
+idna==3.7
+    # via requests
+llvmlite==0.43.0
+    # via numba
+numba==0.60.0
+    # via pandas
+numexpr==2.10.0
+    # via pandas
+numpy==2.0.0
+    # via bottleneck
+    # via numba
+    # via numexpr
+    # via pandas
+    # via py3langid
+    # via pyarrow
+pandas==2.2.2
+    # via country-converter
+    # via csv-metadata-quality
+platformdirs==4.2.2
+    # via requests-cache
+py3langid==0.3.0
+    # via csv-metadata-quality
+pyarrow==16.1.0
+    # via pandas
+pycountry==24.6.1
+    # via csv-metadata-quality
+python-dateutil==2.9.0.post0
+    # via pandas
+python-stdnum==1.20
+    # via csv-metadata-quality
+pytz==2024.1
+    # via pandas
+requests==2.32.2
+    # via csv-metadata-quality
+    # via requests-cache
+requests-cache==1.2.1
+    # via csv-metadata-quality
+six==1.16.0
+    # via python-dateutil
+    # via url-normalize
+tzdata==2024.1
+    # via pandas
+url-normalize==1.4.3
+    # via requests-cache
+urllib3==2.2.1
+    # via requests
+    # via requests-cache
+wcwidth==0.2.13
+    # via ftfy

requirements.txt

@@ -1,25 +0,0 @@
-appdirs==1.4.4 ; python_version >= "3.8" and python_version < "4.0"
-attrs==22.1.0 ; python_version >= "3.8" and python_version < "4.0"
-cattrs==22.1.0 ; python_version >= "3.8" and python_version < "4.0"
-certifi==2022.6.15 ; python_version >= "3.8" and python_version < "4"
-charset-normalizer==2.1.1 ; python_version >= "3.8" and python_version < "4"
-colorama==0.4.5 ; python_version >= "3.8" and python_version < "4.0"
-country-converter==0.7.7 ; python_version >= "3.8" and python_version < "4.0"
-exceptiongroup==1.0.0rc9 ; python_version >= "3.8" and python_version <= "3.10"
-ftfy==6.1.1 ; python_version >= "3.8" and python_version < "4"
-idna==3.3 ; python_version >= "3.8" and python_version < "4"
-langid==1.1.6 ; python_version >= "3.8" and python_version < "4.0"
-numpy==1.23.2 ; python_version < "4.0" and python_version >= "3.8"
-pandas==1.4.4 ; python_version >= "3.8" and python_version < "4.0"
-pycountry==22.3.5 ; python_version >= "3.8" and python_version < "4"
-python-dateutil==2.8.2 ; python_version >= "3.8" and python_version < "4.0"
-python-stdnum==1.17 ; python_version >= "3.8" and python_version < "4.0"
-pytz==2022.2.1 ; python_version >= "3.8" and python_version < "4.0"
-requests-cache==0.9.6 ; python_version >= "3.8" and python_version < "4.0"
-requests==2.28.1 ; python_version >= "3.8" and python_version < "4"
-setuptools==65.3.0 ; python_version >= "3.8" and python_version < "4"
-six==1.16.0 ; python_version >= "3.8" and python_version < "4.0"
-spdx-license-list==0.5.2 ; python_version >= "3.8" and python_version < "4.0"
-url-normalize==1.4.3 ; python_version >= "3.8" and python_version < "4.0"
-urllib3==1.26.12 ; python_version >= "3.8" and python_version < "4"
-wcwidth==0.2.5 ; python_version >= "3.8" and python_version < "4"

setup.cfg

@@ -1,6 +0,0 @@
-[isort]
-multi_line_output=3
-include_trailing_comma=True
-force_grid_wrap=0
-use_parentheses=True
-line_length=88

setup.py

@@ -1,37 +0,0 @@
-import setuptools
-
-with open("README.md", "r") as fh:
-    long_description = fh.read()
-
-install_requires = [
-    "pandas",
-    "python-stdnum",
-    "requests",
-    "requests-cache",
-    "pycountry",
-    "langid",
-]
-
-setuptools.setup(
-    name="csv-metadata-quality",
-    version="0.6.0",
-    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.",
-    license="GPLv3",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    url="https://github.com/alanorth/csv-metadata-quality",
-    classifiers=[
-        "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",
-    ],
-    packages=["csv_metadata_quality"],
-    entry_points={
-        "console_scripts": ["csv-metadata-quality = csv_metadata_quality.__main__:main"]
-    },
-    install_requires=install_requires,
-)

tests/test_check.py

@@ -25,7 +25,7 @@ def test_check_valid_issn():
 
     result = check.issn(value)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_invalid_isbn(capsys):
@@ -46,7 +46,7 @@ def test_check_valid_isbn():
 
     result = check.isbn(value)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_missing_date(capsys):
@@ -102,7 +102,7 @@ def test_check_valid_date():
 
     result = check.date(value, field_name)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_suspicious_characters(capsys):
@@ -128,7 +128,7 @@ def test_check_valid_iso639_1_language():
 
     result = check.language(value)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_valid_iso639_3_language():
@@ -138,7 +138,7 @@ def test_check_valid_iso639_3_language():
 
     result = check.language(value)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_invalid_iso639_1_language(capsys):
@@ -249,7 +249,7 @@ def test_check_common_filename_extension():
 
     result = check.filename_extension(value)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_incorrect_iso_639_1_language(capsys):
@@ -257,7 +257,7 @@ def test_check_incorrect_iso_639_1_language(capsys):
 
     title = "A randomised vaccine field trial in Kenya demonstrates protection against wildebeest-associated malignant catarrhal fever in cattle"
     language = "es"
-    exclude = list()
+    exclude = []
 
     # Create a dictionary to mimic Pandas series
     row = {"dc.title": title, "dc.language.iso": language}
@@ -277,7 +277,7 @@ def test_check_incorrect_iso_639_3_language(capsys):
 
     title = "A randomised vaccine field trial in Kenya demonstrates protection against wildebeest-associated malignant catarrhal fever in cattle"
     language = "spa"
-    exclude = list()
+    exclude = []
 
     # Create a dictionary to mimic Pandas series
     row = {"dc.title": title, "dc.language.iso": language}
@@ -297,7 +297,7 @@ def test_check_correct_iso_639_1_language():
 
     title = "A randomised vaccine field trial in Kenya demonstrates protection against wildebeest-associated malignant catarrhal fever in cattle"
     language = "en"
-    exclude = list()
+    exclude = []
 
     # Create a dictionary to mimic Pandas series
     row = {"dc.title": title, "dc.language.iso": language}
@@ -305,7 +305,7 @@ def test_check_correct_iso_639_1_language():
 
     result = experimental.correct_language(series, exclude)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_correct_iso_639_3_language():
@@ -313,7 +313,7 @@ def test_check_correct_iso_639_3_language():
 
     title = "A randomised vaccine field trial in Kenya demonstrates protection against wildebeest-associated malignant catarrhal fever in cattle"
     language = "eng"
-    exclude = list()
+    exclude = []
 
     # Create a dictionary to mimic Pandas series
     row = {"dc.title": title, "dc.language.iso": language}
@@ -321,7 +321,7 @@ def test_check_correct_iso_639_3_language():
 
     result = experimental.correct_language(series, exclude)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_valid_spdx_license_identifier():
@@ -331,7 +331,7 @@ def test_check_valid_spdx_license_identifier():
 
     result = check.spdx_license_identifier(license)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_invalid_spdx_license_identifier(capsys):
@@ -339,7 +339,7 @@ def test_check_invalid_spdx_license_identifier(capsys):
 
     license = "CC-BY-SA"
 
-    result = check.spdx_license_identifier(license)
+    check.spdx_license_identifier(license)
 
     captured = capsys.readouterr()
     assert (
@@ -362,7 +362,7 @@ def test_check_duplicate_item(capsys):
     }
     df = pd.DataFrame(data=d)
 
-    result = check.duplicate_items(df)
+    check.duplicate_items(df)
 
     captured = capsys.readouterr()
     assert (
@@ -379,7 +379,7 @@ def test_check_no_mojibake():
 
     result = check.mojibake(field, field_name)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_mojibake(capsys):
@@ -388,7 +388,7 @@ def test_check_mojibake(capsys):
     field = "CIAT Publicaçao"
     field_name = "dcterms.isPartOf"
 
-    result = check.mojibake(field, field_name)
+    check.mojibake(field, field_name)
 
     captured = capsys.readouterr()
     assert (
@@ -407,18 +407,18 @@ def test_check_doi_field():
     # the citation and a DOI field.
     d = {"cg.identifier.doi": doi, "dcterms.bibliographicCitation": citation}
     series = pd.Series(data=d)
-    exclude = list()
+    exclude = []
 
     result = check.citation_doi(series, exclude)
 
-    assert result == None
+    assert result is None
 
 
 def test_check_doi_only_in_citation(capsys):
     """Test an item with a DOI in its citation, but no DOI field."""
 
     citation = "Orth, A. 2021. Testing all the things. doi: 10.1186/1743-422X-9-218"
-    exclude = list()
+    exclude = []
 
     # Emulate a column in a transposed dataframe (which is just a series), with
     # an empty DOI field and a citation containing a DOI.
@@ -439,7 +439,7 @@ def test_title_in_citation():
 
     title = "Testing all the things"
     citation = "Orth, A. 2021. Testing all the things."
-    exclude = list()
+    exclude = []
 
     # Emulate a column in a transposed dataframe (which is just a series), with
     # the title and citation.
@@ -448,7 +448,7 @@ def test_title_in_citation():
 
     result = check.title_in_citation(series, exclude)
 
-    assert result == None
+    assert result is None
 
 
 def test_title_not_in_citation(capsys):
@@ -456,7 +456,7 @@ def test_title_not_in_citation(capsys):
 
     title = "Testing all the things"
     citation = "Orth, A. 2021. Testing all teh things."
-    exclude = list()
+    exclude = []
 
     # Emulate a column in a transposed dataframe (which is just a series), with
     # the title and citation.
@@ -477,7 +477,7 @@ def test_country_matches_region():
 
     country = "Kenya"
     region = "Eastern Africa"
-    exclude = list()
+    exclude = []
 
     # Emulate a column in a transposed dataframe (which is just a series)
     d = {"cg.coverage.country": country, "cg.coverage.region": region}
@@ -485,7 +485,7 @@ def test_country_matches_region():
 
     result = check.countries_match_regions(series, exclude)
 
-    assert result == None
+    assert result is None
 
 
 def test_country_not_matching_region(capsys):
@@ -495,7 +495,7 @@ def test_country_not_matching_region(capsys):
     country = "Kenya"
     region = ""
     missing_region = "Eastern Africa"
-    exclude = list()
+    exclude = []
 
     # Emulate a column in a transposed dataframe (which is just a series)
     d = {
@@ -510,5 +510,5 @@ def test_country_not_matching_region(capsys):
     captured = capsys.readouterr()
     assert (
         captured.out
-        == f"{Fore.YELLOW}Missing region ({missing_region}): {Fore.RESET}{title}\n"
+        == f"{Fore.YELLOW}Missing region ({country} → {missing_region}): {Fore.RESET}{title}\n"
     )

tests/test_fix.py

@@ -131,7 +131,7 @@ def test_fix_country_not_matching_region():
     country = "Kenya"
     region = ""
     missing_region = "Eastern Africa"
-    exclude = list()
+    exclude = []
 
     # Emulate a column in a transposed dataframe (which is just a series)
     d = {
@@ -152,3 +152,11 @@ def test_fix_country_not_matching_region():
     series_correct = pd.Series(data=d_correct)
 
     pd.testing.assert_series_equal(result, series_correct)
+
+
+def test_fix_normalize_dois():
+    """Test normalizing a DOI."""
+
+    value = "doi: 10.11648/j.jps.20140201.14"
+
+    assert fix.normalize_dois(value) == "https://doi.org/10.11648/j.jps.20140201.14"