1
0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2025-11-09 08:59:08 +01:00

1 Commits

Author SHA1 Message Date
renovate[bot]
97e603fc87 chore(deps): lock file maintenance 2025-10-21 13:55:51 +00:00
4 changed files with 500 additions and 404 deletions

View File

@@ -7,7 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## Unreleased ## Unreleased
### Changed ### Changed
- New AGROVOC REST API URL - New AGROVOC REST API URL
- Use urllib from Python stdlib instead of manual replacement for unquoting URLs
## [0.7.0] - 2025-01-31 ## [0.7.0] - 2025-01-31
### Added ### Added

View File

@@ -45,11 +45,10 @@ build-backend = "uv_build"
[dependency-groups] [dependency-groups]
dev = [ dev = [
"pytest~=9.0", "pytest~=8.3",
"isort~=6.0", "isort~=6.0",
"csvkit~=2.0", "csvkit~=2.0",
"ipython~=8.31", "ipython~=8.31",
"black~=25.9",
] ]
[tool.isort] [tool.isort]

View File

@@ -3,7 +3,6 @@
import logging import logging
import re import re
from unicodedata import normalize from unicodedata import normalize
from urllib.parse import unquote
import country_converter as coco import country_converter as coco
import pandas as pd import pandas as pd
@@ -452,8 +451,12 @@ def normalize_dois(field):
if match: if match:
new_value = re.sub(pattern, "doi.org", new_value) new_value = re.sub(pattern, "doi.org", new_value)
# Replace %xx escapes with their single-character equivalent. # Convert erroneous %2f to /
new_value = unquote(new_value) 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 # Replace values like doi: 10.11648/j.jps.20140201.14
pattern = re.compile(r"^doi: 10\.") pattern = re.compile(r"^doi: 10\.")

891
uv.lock generated

File diff suppressed because it is too large Load Diff