From 566c2b45cf60a60edf28149740aad4facc3a7755 Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Fri, 2 Sep 2022 16:14:24 +0300 Subject: [PATCH] Remove Excel support I never used this and it seems xlrd doesn't even support .xlsx any- more anyways. If this was needed I could theoretically use openpyxl but I'd rather just stick to CSV. --- CHANGELOG.md | 4 ++++ README.md | 2 +- csv_metadata_quality/app.py | 2 +- pyproject.toml | 1 - 4 files changed, 6 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index aa4bced..a33f03b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -21,6 +21,10 @@ with `-a ` - Ability to add missing UN M.49 regions when both country and region columns are present. Enable with `-u` (unsafe fixes) for now. +### Removed +- Support for reading Excel files (both `.xls` and `.xlsx`) as it was completely +untested + ## [0.5.0] - 2021-12-08 ### Added - Ability to check for, and fix, "mojibake" characters using [ftfy](https://github.com/LuminosoInsight/python-ftfy) diff --git a/README.md b/README.md index 8543024..9e754cf 100644 --- a/README.md +++ b/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 and Excel support comes from the [Pandas](https://pandas.pydata.org/) library, though your mileage may vary with Excel because this is much less tested. +Requires Python 3.8 or greater. CSV support comes from the [Pandas](https://pandas.pydata.org/) library. If you use the DSpace CSV metadata quality checker please cite: diff --git a/csv_metadata_quality/app.py b/csv_metadata_quality/app.py index 9be5b5a..0bcc61f 100644 --- a/csv_metadata_quality/app.py +++ b/csv_metadata_quality/app.py @@ -36,7 +36,7 @@ def parse_args(argv): parser.add_argument( "--input-file", "-i", - help="Path to input file. Can be UTF-8 CSV or Excel XLSX.", + help="Path to input file. Must be a UTF-8 CSV.", required=True, type=argparse.FileType("r", encoding="UTF-8"), ) diff --git a/pyproject.toml b/pyproject.toml index bec0cc5..07321b9 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -14,7 +14,6 @@ csv-metadata-quality = 'csv_metadata_quality.__main__:main' python = "^3.8" pandas = "^1.4.0" python-stdnum = "^1.13" -xlrd = "^1.2.0" requests = "^2.27.1" requests-cache = "^0.9.1" pycountry = "^22.1.10"