| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
07_bom_utf8.csv
|
csv
|
0.0 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
08_line_endings_crlf.csv
|
csv
|
0.0 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
09_line_endings_cr.csv
|
csv
|
0.0 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
10_line_endings_mixed.csv
|
csv
|
0.0 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
11_embedded_newlines.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
12_case_variations.csv
|
csv
|
0.2 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
13_non_latin_scripts.csv
|
csv
|
0.2 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
14_mojibake.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
15_whitespace_only_cells.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
16_dirty_headers.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
17_preserve_intended.csv
|
csv
|
0.2 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
18_empty_file.csv
|
csv
|
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
19_headers_only.csv
|
csv
|
0.0 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
20_kitchen_sink.csv
|
csv
|
0.3 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
21_excel_pollution.xlsx
|
|
7.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
22_quote_variants.csv
|
csv
|
3.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data |
23_csv_malformed.csv
|
csv
|
0.9 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E01_western_basic_utf8.csv
|
csv
|
0.2 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E02_western_basic_utf8bom.csv
|
csv
|
0.2 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E03_western_basic_cp1252.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E04_western_basic_latin1.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E05_western_basic_latin9.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E06_western_basic_macroman.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E07_western_basic_utf16le.csv
|
csv
|
0.3 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E08_western_basic_utf16be.csv
|
csv
|
0.3 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E09_western_basic_utf16le_nobom.csv
|
csv
|
0.3 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E10_western_extended_utf8.csv
|
csv
|
0.2 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E11_western_extended_cp1252.csv
|
csv
|
0.2 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E12_western_extended_utf16le.csv
|
csv
|
0.3 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E13_eastern_european_utf8.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E14_eastern_european_cp1250.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E15_eastern_european_iso88592.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E16_cyrillic_utf8.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E17_cyrillic_cp1251.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E18_cyrillic_koi8r.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E19_japanese_utf8.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E20_japanese_shiftjis.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E21_chinese_simplified_utf8.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E22_chinese_simplified_gb18030.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E23_chinese_traditional_utf8.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E24_chinese_traditional_big5.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E25_korean_utf8.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E26_korean_euckr.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E27_pathological_ascii_only.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E28_pathological_invalid_utf8.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E29_pathological_truncated_utf8.csv
|
csv
|
0.0 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E30_pathological_lying_bom.csv
|
csv
|
0.2 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
E31_pathological_mixed_concat.csv
|
csv
|
0.1 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
detector_baseline.csv
|
csv
|
2.9 KB
|
2026-05-01
|
Download
|
| Business/DataTools/test-case-code-page-variations/text_cleaner_test_corpus/test_data/encodings |
expected_detection.csv
|
csv
|
6.3 KB
|
2026-05-01
|
Download
|