mirror of
https://github.com/ilri/csv-metadata-quality.git
synced 2024-12-22 20:22:18 +01:00
Alan Orth
898bb412c3
This detects whether text has likely been encoded in one encoding
and decoded in another, perhaps multiple times. This often results
in display of "mojibake" characters.
For example, a file encoded in UTF-8 is opened as CP-1252 (Windows
Latin codepage) in Microsoft Excel, and saved again as UTF-8. You
will see strings like this in the resulting file:
- CIAT Publicaçao
- CIAT Publicación
The correct version of these in UTF-8 would be:
- CIAT Publicaçao
- CIAT Publicación
I use a code snippet from Martijn Pieters on StackOverflow to de-
tect whether a string is "weird" as determined by the excellent
"fixes text for you" (ftfy) Python library, then check if a weird
string encodes as CP-1252 or not. If so, I can try to fix it.
See: https://stackoverflow.com/questions/29071995/identify-garbage-unicode-string-using-python
38 lines
988 B
TOML
38 lines
988 B
TOML
[tool.poetry]
|
|
name = "csv-metadata-quality"
|
|
version = "0.4.7"
|
|
description="A simple, but opinionated CSV quality checking and fixing pipeline for CSVs in the DSpace ecosystem."
|
|
authors = ["Alan Orth <alan.orth@gmail.com>"]
|
|
license="GPL-3.0-only"
|
|
repository = "https://github.com/ilri/csv-metadata-quality"
|
|
homepage = "https://github.com/ilri/csv-metadata-quality"
|
|
|
|
[tool.poetry.scripts]
|
|
csv-metadata-quality = 'csv_metadata_quality.__main__:main'
|
|
|
|
[tool.poetry.dependencies]
|
|
python = "^3.7.1"
|
|
pandas = "^1.0.4"
|
|
python-stdnum = "^1.13"
|
|
xlrd = "^1.2.0"
|
|
requests = "^2.23.0"
|
|
requests-cache = "^0.5.2"
|
|
pycountry = "^19.8.18"
|
|
langid = "^1.1.6"
|
|
colorama = "^0.4.4"
|
|
spdx-license-list = "^0.5.2"
|
|
ftfy = "^5.9"
|
|
|
|
[tool.poetry.dev-dependencies]
|
|
pytest = "^6.1.1"
|
|
ipython = { version = "^7.18.1", python = "^3.7" }
|
|
flake8 = "^3.8.4"
|
|
pytest-clarity = "^0.3.0-alpha.0"
|
|
black = "20.8b1"
|
|
isort = "^5.5.4"
|
|
csvkit = "^1.0.5"
|
|
|
|
[build-system]
|
|
requires = ["poetry>=0.12"]
|
|
build-backend = "poetry.masonry.api"
|