blyxxyz:lossy-string-cleanup - Branch - uutils/coreutils

Remove lossy OS string conversions

#9337

Comparing

blyxxyz:lossy-string-cleanup

(

301165a

) with

main

(

909553a

)

-5%

Improvements: 1

Regressions: 3

Untouched: 122

Skipped: 6

Benchmarks

Skipped (6)

Failed

sort_reverse_mixed

src/uu/sort/benches/sort_locale_bench.rs

Regression

-3%

38.1 ms39.1 ms

tsort_input_parsing_heavy[5000]

src/uu/tsort/benches/tsort_bench.rs

Regression

-3%

81.7 ms84.6 ms

mv_force_overwrite

src/uu/mv/benches/mv_bench.rs

Regression

-5%

125.2 ms131.6 ms

Improved

sort_ascii_c_locale

src/uu/sort/benches/sort_locale_bench.rs

+5%

22.5 ms21.5 ms

Passed

du_summarize_balanced_tree[(5, 4, 10)]

src/uu/du/benches/du_bench.rs

+2%

8.4 ms8.3 ms

sort_long_line[160000]

src/uu/sort/benches/sort_bench.rs

+1%

1.7 ms1.6 ms

du_max_depth_balanced_tree[(6, 4, 10)]

src/uu/du/benches/du_bench.rs

+1%

32.9 ms32.5 ms

expand_many_lines[100000]

src/uu/expand/benches/expand_bench.rs

+1%

149.9 ms148 ms

sort_numeric

src/uu/sort/benches/sort_locale_bench.rs

+1%

23.5 ms23.2 ms

du_wide_tree[(5000, 500)]

src/uu/du/benches/du_bench.rs

+1%

11.2 ms11.2 ms

sort_mixed_data[500000]

src/uu/sort/benches/sort_bench.rs

+1%

327.3 ms325.2 ms

unexpand_large_file[10]

src/uu/unexpand/benches/unexpand_bench.rs

+1%

549.3 ms546.1 ms

unexpand_many_lines[100000]

src/uu/unexpand/benches/unexpand_bench.rs

+1%

262 ms260.5 ms

cksum_raw_output

src/uu/cksum/benches/cksum_bench.rs

17.3 ms17.2 ms

expand_custom_tabstops[50000]

src/uu/expand/benches/expand_bench.rs

37 ms36.8 ms

split_number_chunks

src/uu/split/benches/split_bench.rs

275.4 µs274.2 µs

rm_force_files

src/uu/rm/benches/rm_bench.rs

2.1 ms2.1 ms

ls_recursive_long_all_wide_tree[(15000, 1500)]

src/uu/ls/benches/ls_bench.rs

142.1 ms141.7 ms

cksum_multiple_files

src/uu/cksum/benches/cksum_bench.rs

25.9 ms25.8 ms

split_bytes

src/uu/split/benches/split_bench.rs

505.8 µs504.5 µs

cksum_crc32b

src/uu/cksum/benches/cksum_bench.rs

13.7 ms13.7 ms

cksum_default

src/uu/cksum/benches/cksum_bench.rs

17.3 ms17.3 ms

du_deep_tree[(100, 3)]

src/uu/du/benches/du_bench.rs

1.2 ms1.2 ms

ls_recursive_wide_tree[(10000, 1000)]

src/uu/ls/benches/ls_bench.rs

52.6 ms52.5 ms

numfmt_padding[(10000, 50)]

src/uu/numfmt/benches/numfmt_bench.rs

48.3 ms48.1 ms

rm_single_file

src/uu/rm/benches/rm_bench.rs

106.5 ms106.3 ms

sort_dictionary_order[500000]

src/uu/sort/benches/sort_bench.rs

1.1 s1.1 s

sort_case_sensitive[500000]

src/uu/sort/benches/sort_bench.rs

174.2 ms173.9 ms

ls_recursive_long_all_balanced_tree[(6, 4, 15)]

src/uu/ls/benches/ls_bench.rs

135.9 ms135.7 ms

cp_large_file[16]

src/uu/cp/benches/cp_bench.rs

342.5 µs342 µs

ls_recursive_long_all_deep_tree[(100, 4)]

src/uu/ls/benches/ls_bench.rs

3.2 ms3.2 ms

tsort_complex_dag[50000]

src/uu/tsort/benches/tsort_bench.rs

84.7 ms84.6 ms

cksum_crc

src/uu/cksum/benches/cksum_bench.rs

17.3 ms17.3 ms

tsort_wide_dag[100000]

src/uu/tsort/benches/tsort_bench.rs

134.7 ms134.6 ms

split_numeric_suffix

src/uu/split/benches/split_bench.rs

5.9 ms5.9 ms

tsort_tree_dag[(10, 3)]

src/uu/tsort/benches/tsort_bench.rs

34.4 ms34.4 ms

ls_recursive_long_all_mixed_tree

src/uu/ls/benches/ls_bench.rs

2.8 ms2.8 ms

tsort_linear_chain[1000000]

src/uu/tsort/benches/tsort_bench.rs

1.5 s1.5 s

ls_recursive_mixed_tree

src/uu/ls/benches/ls_bench.rs

1.4 ms1.4 ms

split_lines

src/uu/split/benches/split_bench.rs

5.7 ms5.7 ms

numfmt_from_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

32.7 ms32.7 ms

b64_decode_ignore_garbage_synthetic

src/uu/base64/benches/base64_bench.rs

149.4 µs149.3 µs

cp_archive_balanced_tree[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

77.9 ms77.9 ms

shuf_lines[100000]

src/uu/shuf/benches/shuf_bench.rs

26.9 ms26.9 ms

cksum_bsd

src/uu/cksum/benches/cksum_bench.rs

128.3 ms128.3 ms

ls_recursive_deep_tree[(200, 2)]

src/uu/ls/benches/ls_bench.rs

2.2 ms2.2 ms

sort_german_c_locale

src/uu/sort/benches/sort_locale_bench.rs

38.4 ms38.4 ms

sort_accented_data[500000]

src/uu/sort/benches/sort_bench.rs

362.5 ms362.4 ms

sort_unique_locale[500000]

src/uu/sort/benches/sort_bench.rs

493.9 ms493.9 ms

numfmt_to_iec[10000]

src/uu/numfmt/benches/numfmt_bench.rs

33.7 ms33.7 ms

wc_lines_large_line_count[500000]

src/uu/wc/benches/wc_bench.rs

2.9 ms2.9 ms

shuf_input_range[1000000]

src/uu/shuf/benches/shuf_bench.rs

229.1 ms229.1 ms

sort_case_insensitive[500000]

src/uu/sort/benches/sort_bench.rs

278.6 ms278.6 ms

wc_bytes_lines_synthetic[2000]

src/uu/wc/benches/wc_bench.rs

120.2 ms120.2 ms

wc_words_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

47.9 ms47.9 ms

cksum_blake2b

src/uu/cksum/benches/cksum_bench.rs

192.9 ms192.9 ms

cksum_sha384

src/uu/cksum/benches/cksum_bench.rs

1.1 s1.1 s

cksum_shake256

src/uu/cksum/benches/cksum_bench.rs

1.9 s1.9 s

cksum_shake128

src/uu/cksum/benches/cksum_bench.rs

1.5 s1.5 s

wc_words_synthetic[2000]

src/uu/wc/benches/wc_bench.rs

11.4 s11.4 s

cksum_sha512

src/uu/cksum/benches/cksum_bench.rs

1.1 s1.1 s

fold_custom_width[50000]

src/uu/fold/benches/fold_bench.rs

32.9 ms32.9 ms

hashsum_sha256_check

src/uu/hashsum/benches/hashsum_bench.rs

173.6 ms173.6 ms

sort_ascii_utf8_locale

src/uu/sort/benches/sort_locale_bench.rs

43.1 ms43.1 ms

numfmt_round_modes[("towards-zero", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.2 ms34.2 ms

fold_many_lines[100000]

src/uu/fold/benches/fold_bench.rs

80.1 ms80.1 ms

hashsum_sha256

src/uu/hashsum/benches/hashsum_bench.rs

173.6 ms173.6 ms

wc_default_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

50.4 ms50.4 ms

ls_recursive_balanced_tree[(6, 4, 15)]

src/uu/ls/benches/ls_bench.rs

55.6 ms55.6 ms

numfmt_to_si_precision[10000]

src/uu/numfmt/benches/numfmt_bench.rs

35.4 ms35.4 ms

seq_formatted

src/uu/seq/benches/seq_bench.rs

97.2 ms97.2 ms

shuf_repeat_sampling[50000]

src/uu/shuf/benches/shuf_bench.rs

4.6 ms4.6 ms

cut_fields_custom_delim

src/uu/cut/benches/cut_bench.rs

40.7 ms40.7 ms

seq_custom_separator

src/uu/seq/benches/seq_bench.rs

28.7 ms28.7 ms

numfmt_round_modes[("down", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.2 ms34.2 ms

numfmt_large_numbers_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

32.4 ms32.4 ms

numfmt_round_modes[("up", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.1 ms34.1 ms

cksum_sha256

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

cksum_sha224

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

hashsum_md5_check

src/uu/hashsum/benches/hashsum_bench.rs

32 ms32 ms

cksum_sm3

src/uu/cksum/benches/cksum_bench.rs

1.6 s1.6 s

seq_with_step

src/uu/seq/benches/seq_bench.rs

13.3 ms13.3 ms

cksum_sha3

src/uu/cksum/benches/cksum_bench.rs

1.8 s1.8 s

cut_fields_tab

src/uu/cut/benches/cut_bench.rs

34.1 ms34.1 ms

sort_ascii_only[500000]

src/uu/sort/benches/sort_bench.rs

353.6 ms353.6 ms

cksum_sha2

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

hashsum_sha512

src/uu/hashsum/benches/hashsum_bench.rs

110.8 ms110.8 ms

cksum_sha1

src/uu/cksum/benches/cksum_bench.rs

723 ms723.1 ms

seq_integers

src/uu/seq/benches/seq_bench.rs

26.1 ms26.1 ms

hashsum_sha1

src/uu/hashsum/benches/hashsum_bench.rs

72.5 ms72.5 ms

cut_characters

src/uu/cut/benches/cut_bench.rs

7.5 ms7.5 ms

cksum_md5

src/uu/cksum/benches/cksum_bench.rs

317.9 ms317.9 ms

rm_multiple_files

src/uu/rm/benches/rm_bench.rs

2.2 ms2.2 ms

sort_numeric[500000]

src/uu/sort/benches/sort_bench.rs

1.2 s1.2 s

uniq_heavy_duplicates[10000]

src/uu/uniq/benches/uniq_bench.rs

1.9 ms1.9 ms

wc_lines_extreme_line_lengths[(100000, 200)]

src/uu/wc/benches/wc_bench.rs

1.6 ms1.6 ms

cut_bytes

src/uu/cut/benches/cut_bench.rs

8.5 ms8.5 ms

wc_lines_variable_length[(50, 500)]

src/uu/wc/benches/wc_bench.rs

3.4 ms3.4 ms

sort_mixed_c_locale

src/uu/sort/benches/sort_locale_bench.rs

38.2 ms38.3 ms

nl_large_file[10]

src/uu/nl/benches/nl_bench.rs

100.9 ms100.9 ms

uniq_case_insensitive[10000]

src/uu/uniq/benches/uniq_bench.rs

1.7 ms1.7 ms

cksum_sysv

src/uu/cksum/benches/cksum_bench.rs

48.2 ms48.2 ms

hashsum_md5

src/uu/hashsum/benches/hashsum_bench.rs

32 ms32.1 ms

sort_mixed_utf8_locale

src/uu/sort/benches/sort_locale_bench.rs

38.8 ms38.8 ms

nl_many_lines[100000]

src/uu/nl/benches/nl_bench.rs

79.7 ms79.8 ms

uniq_with_count[10000]

src/uu/uniq/benches/uniq_bench.rs

1.9 ms1.9 ms

cp_preserve_metadata[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

75 ms75.1 ms

cp_recursive_balanced_tree[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

72.4 ms72.5 ms

sort_reverse_locale[500000]

src/uu/sort/benches/sort_bench.rs

361 ms361.5 ms

cp_recursive_wide_tree[(6000, 800)]

src/uu/cp/benches/cp_bench.rs

189.7 ms190 ms

du_all_wide_tree[(5000, 500)]

src/uu/du/benches/du_bench.rs

18.2 ms18.2 ms

wc_chars_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

994.4 µs996.2 µs

numfmt_to_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

33.6 ms33.7 ms

rm_recursive_tree

src/uu/rm/benches/rm_bench.rs

13.6 ms13.6 ms

cp_recursive_deep_tree[(120, 4)]

src/uu/cp/benches/cp_bench.rs

13.6 ms13.7 ms

cksum_blake3

src/uu/cksum/benches/cksum_bench.rs

187.3 µs187.7 µs

mv_directory

src/uu/mv/benches/mv_bench.rs

3.5 ms3.5 ms

mv_multiple_to_dir

src/uu/mv/benches/mv_bench.rs

13.1 ms13.1 ms

sort_key_field[500000]

src/uu/sort/benches/sort_bench.rs

699.9 ms702.6 ms

b64_encode_synthetic

src/uu/base64/benches/base64_bench.rs

146.2 µs146.8 µs

factor_multiple_u64s[2]

src/uu/factor/benches/factor_bench.rs

178.2 ms179 ms

b64_decode_synthetic

src/uu/base64/benches/base64_bench.rs

-1%

149.1 µs150.1 µs

mv_single_file

src/uu/mv/benches/mv_bench.rs

-1%

129.7 ms130.6 ms

wc_bytes_synthetic[500]

src/uu/wc/benches/wc_bench.rs

-1%

164.1 µs165.6 µs

sort_unique_mixed

src/uu/sort/benches/sort_locale_bench.rs

-2%

38.6 ms39.3 ms

sort_german_locale

src/uu/sort/benches/sort_locale_bench.rs

-2%

38.4 ms39.1 ms

Commits

Click on a commit to change the comparison range

Base

main

909553a

-4.83%

Do not use `.display()`/`.to_string_lossy()` unnecessarily This comes up a lot for quoted strings in messages: OS strings can be quoted directly and this prevents information loss. This commit removes ~60% of the calls to these methods (modulo tests). Some of the remaining calls are benign, for example because they convert solely to check for the presence of ASCII characters. Others are nontrivial to improve.

e402404

5 days ago

by blyxxyz

ls: Use `maybe_quote` for loop error message (fixes GNU test)

54dccea

5 days ago

by blyxxyz

-0.03%

Merge remote-tracking branch 'origin/main' into lossy-string-cleanup

301165a

3 days ago

by blyxxyz

Home Terms Privacy Docs