mattsu2020:sort_fix_rebased - Branch - uutils/coreutils

sort:fails to reorder binary lines containing NUL bytes

#9306

Comparing

mattsu2020:sort_fix_rebased

(

774fe29

) with

main

(

cc103ec

)

-4%

Regressions: 1

Untouched: 126

Skipped: 6

Benchmarks

Skipped (6)

Failed

sort_numeric

src/uu/sort/benches/sort_locale_bench.rs

Regression

-4%

23.9 ms*24.8 ms

Passed

tsort_input_parsing_heavy[5000]

src/uu/tsort/benches/tsort_bench.rs

+2%

84.1 ms*82.8 ms

du_wide_tree[(5000, 500)]

src/uu/du/benches/du_bench.rs

+1%

11.4 ms11.3 ms

cp_large_file[16]

src/uu/cp/benches/cp_bench.rs

+1%

363.3 µs361.2 µs

du_summarize_balanced_tree[(5, 4, 10)]

src/uu/du/benches/du_bench.rs

8.5 ms8.5 ms

cp_preserve_metadata[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

75 ms74.8 ms

du_max_depth_balanced_tree[(6, 4, 10)]

src/uu/du/benches/du_bench.rs

33.2 ms33.2 ms

b64_decode_synthetic

src/uu/base64/benches/base64_bench.rs

166.3 µs*166.1 µs

ls_recursive_mixed_tree

src/uu/ls/benches/ls_bench.rs

1.5 ms*1.5 ms

ls_recursive_long_all_balanced_tree[(6, 4, 15)]

src/uu/ls/benches/ls_bench.rs

134.9 ms*134.8 ms

ls_recursive_balanced_tree[(6, 4, 15)]

src/uu/ls/benches/ls_bench.rs

56.1 ms*56.1 ms

ls_recursive_wide_tree[(10000, 1000)]

src/uu/ls/benches/ls_bench.rs

52 ms*51.9 ms

b64_decode_ignore_garbage_synthetic

src/uu/base64/benches/base64_bench.rs

163.2 µs*163.1 µs

ls_recursive_long_all_deep_tree[(100, 4)]

src/uu/ls/benches/ls_bench.rs

3.3 ms*3.3 ms

b64_encode_synthetic

src/uu/base64/benches/base64_bench.rs

161.8 µs*161.8 µs

cp_recursive_balanced_tree[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

72.3 ms72.3 ms

cp_archive_balanced_tree[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

78 ms78 ms

mv_multiple_to_dir

src/uu/mv/benches/mv_bench.rs

12.8 ms12.8 ms

wc_bytes_synthetic[500]

src/uu/wc/benches/wc_bench.rs

181.6 µs*181.5 µs

factor_multiple_u64s[2]

src/uu/factor/benches/factor_bench.rs

212.4 ms212.4 ms

hashsum_sha512

src/uu/hashsum/benches/hashsum_bench.rs

110.8 ms*110.8 ms

mv_single_file

src/uu/mv/benches/mv_bench.rs

135.6 ms135.5 ms

split_lines

src/uu/split/benches/split_bench.rs

5.7 ms5.7 ms

shuf_lines[100000]

src/uu/shuf/benches/shuf_bench.rs

31.6 ms31.6 ms

shuf_repeat_sampling[50000]

src/uu/shuf/benches/shuf_bench.rs

5.1 ms5.1 ms

cksum_sha512

src/uu/cksum/benches/cksum_bench.rs

1.1 s*1.1 s

cksum_sha384

src/uu/cksum/benches/cksum_bench.rs

1.1 s*1.1 s

mv_force_overwrite

src/uu/mv/benches/mv_bench.rs

144.3 ms144.3 ms

wc_chars_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

1 ms*1 ms

uniq_case_insensitive[10000]

src/uu/uniq/benches/uniq_bench.rs

1.8 ms1.8 ms

rm_single_file

src/uu/rm/benches/rm_bench.rs

119.4 ms119.4 ms

cksum_sha2

src/uu/cksum/benches/cksum_bench.rs

1.7 s*1.7 s

rm_multiple_files

src/uu/rm/benches/rm_bench.rs

2.2 ms2.2 ms

cksum_sha3

src/uu/cksum/benches/cksum_bench.rs

1.8 s*1.8 s

rm_force_files

src/uu/rm/benches/rm_bench.rs

2 ms2 ms

mv_directory

src/uu/mv/benches/mv_bench.rs

3.5 ms3.5 ms

wc_lines_large_line_count[500000]

src/uu/wc/benches/wc_bench.rs

2.9 ms*2.9 ms

wc_lines_variable_length[(50, 500)]

src/uu/wc/benches/wc_bench.rs

3.4 ms*3.4 ms

uniq_with_count[10000]

src/uu/uniq/benches/uniq_bench.rs

1.9 ms1.9 ms

cut_fields_tab

src/uu/cut/benches/cut_bench.rs

34.1 ms34.1 ms

numfmt_round_modes[("up", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

numfmt_to_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

33.8 ms33.8 ms

uniq_heavy_duplicates[10000]

src/uu/uniq/benches/uniq_bench.rs

2 ms2 ms

numfmt_round_modes[("down", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

rm_recursive_tree

src/uu/rm/benches/rm_bench.rs

13.6 ms13.6 ms

numfmt_from_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

32.7 ms32.7 ms

numfmt_to_si_precision[10000]

src/uu/numfmt/benches/numfmt_bench.rs

35.3 ms35.3 ms

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

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

nl_many_lines[100000]

src/uu/nl/benches/nl_bench.rs

44.9 ms44.9 ms

numfmt_to_iec[10000]

src/uu/numfmt/benches/numfmt_bench.rs

33.8 ms33.8 ms

wc_words_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

48 ms*47.9 ms

numfmt_large_numbers_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

32.5 ms32.5 ms

nl_large_file[10]

src/uu/nl/benches/nl_bench.rs

57.1 ms57.1 ms

numfmt_padding[(10000, 50)]

src/uu/numfmt/benches/numfmt_bench.rs

48 ms48 ms

wc_default_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

50.4 ms*50.4 ms

hashsum_sha256_check

src/uu/hashsum/benches/hashsum_bench.rs

172.9 ms*172.9 ms

hashsum_md5

src/uu/hashsum/benches/hashsum_bench.rs

32 ms*32 ms

unexpand_large_file[10]

src/uu/unexpand/benches/unexpand_bench.rs

567.6 ms567.6 ms

unexpand_many_lines[100000]

src/uu/unexpand/benches/unexpand_bench.rs

270.7 ms270.7 ms

expand_many_lines[100000]

src/uu/expand/benches/expand_bench.rs

149.7 ms149.7 ms

hashsum_md5_check

src/uu/hashsum/benches/hashsum_bench.rs

32 ms*32 ms

hashsum_sha1

src/uu/hashsum/benches/hashsum_bench.rs

72.5 ms*72.5 ms

cksum_shake256

src/uu/cksum/benches/cksum_bench.rs

1.9 s*1.9 s

cksum_shake128

src/uu/cksum/benches/cksum_bench.rs

1.5 s*1.5 s

wc_words_synthetic[2000]

src/uu/wc/benches/wc_bench.rs

11.4 s*11.4 s

hashsum_sha256

src/uu/hashsum/benches/hashsum_bench.rs

173 ms*173 ms

wc_bytes_lines_synthetic[2000]

src/uu/wc/benches/wc_bench.rs

120.2 ms*120.2 ms

fold_many_lines[100000]

src/uu/fold/benches/fold_bench.rs

80.4 ms80.4 ms

cut_fields_custom_delim

src/uu/cut/benches/cut_bench.rs

40.8 ms40.8 ms

fold_custom_width[50000]

src/uu/fold/benches/fold_bench.rs

33 ms33 ms

seq_formatted

src/uu/seq/benches/seq_bench.rs

96.1 ms96.1 ms

expand_custom_tabstops[50000]

src/uu/expand/benches/expand_bench.rs

37.1 ms37.1 ms

cksum_sha256

src/uu/cksum/benches/cksum_bench.rs

1.7 s*1.7 s

cksum_sm3

src/uu/cksum/benches/cksum_bench.rs

1.6 s*1.6 s

seq_custom_separator

src/uu/seq/benches/seq_bench.rs

28.7 ms28.7 ms

seq_integers

src/uu/seq/benches/seq_bench.rs

26.1 ms26.1 ms

ls_recursive_long_all_wide_tree[(15000, 1500)]

src/uu/ls/benches/ls_bench.rs

143.2 ms*143.2 ms

seq_with_step

src/uu/seq/benches/seq_bench.rs

13.3 ms13.3 ms

cut_bytes

src/uu/cut/benches/cut_bench.rs

8.4 ms8.4 ms

wc_lines_extreme_line_lengths[(100000, 200)]

src/uu/wc/benches/wc_bench.rs

1.6 ms*1.6 ms

cksum_md5

src/uu/cksum/benches/cksum_bench.rs

317.9 ms*317.9 ms

cksum_sha224

src/uu/cksum/benches/cksum_bench.rs

1.7 s*1.7 s

cksum_blake2b

src/uu/cksum/benches/cksum_bench.rs

192.7 ms*192.8 ms

cut_characters

src/uu/cut/benches/cut_bench.rs

7.4 ms7.4 ms

ls_recursive_long_all_mixed_tree

src/uu/ls/benches/ls_bench.rs

2.9 ms*2.9 ms

shuf_input_range[1000000]

src/uu/shuf/benches/shuf_bench.rs

229.4 ms229.4 ms

cksum_sha1

src/uu/cksum/benches/cksum_bench.rs

723.1 ms*723.2 ms

seq_large_integers

src/uu/seq/benches/seq_bench.rs

2.2 ms2.2 ms

split_numeric_suffix

src/uu/split/benches/split_bench.rs

5.9 ms5.9 ms

cp_recursive_wide_tree[(6000, 800)]

src/uu/cp/benches/cp_bench.rs

189.5 ms189.5 ms

du_all_wide_tree[(5000, 500)]

src/uu/du/benches/du_bench.rs

18.1 ms18.1 ms

split_bytes

src/uu/split/benches/split_bench.rs

510.1 µs510.2 µs

split_number_chunks

src/uu/split/benches/split_bench.rs

294.5 µs294.6 µs

cksum_bsd

src/uu/cksum/benches/cksum_bench.rs

128.3 ms*128.4 ms

ls_recursive_deep_tree[(200, 2)]

src/uu/ls/benches/ls_bench.rs

2.2 ms*2.2 ms

cksum_blake3

src/uu/cksum/benches/cksum_bench.rs

208 µs*208.1 µs

cp_recursive_deep_tree[(120, 4)]

src/uu/cp/benches/cp_bench.rs

13.6 ms13.7 ms

du_deep_tree[(100, 3)]

src/uu/du/benches/du_bench.rs

1.2 ms1.2 ms

cksum_sysv

src/uu/cksum/benches/cksum_bench.rs

48.2 ms*48.3 ms

tsort_complex_dag[50000]

src/uu/tsort/benches/tsort_bench.rs

84 ms*84.1 ms

cksum_multiple_files

src/uu/cksum/benches/cksum_bench.rs

25.3 ms*25.4 ms

cksum_crc

src/uu/cksum/benches/cksum_bench.rs

16.9 ms*17 ms

cksum_default

src/uu/cksum/benches/cksum_bench.rs

16.9 ms*17 ms

tsort_linear_chain[1000000]

src/uu/tsort/benches/tsort_bench.rs

1.5 s*1.5 s

sort_mixed_data[500000]

src/uu/sort/benches/sort_bench.rs

328.4 ms*329.1 ms

tsort_wide_dag[100000]

src/uu/tsort/benches/tsort_bench.rs

133.2 ms*133.6 ms

cksum_crc32b

src/uu/cksum/benches/cksum_bench.rs

13.3 ms*13.4 ms

sort_unique_locale[500000]

src/uu/sort/benches/sort_bench.rs

494.2 ms*495.7 ms

tsort_tree_dag[(10, 3)]

src/uu/tsort/benches/tsort_bench.rs

34.1 ms*34.2 ms

sort_german_locale

src/uu/sort/benches/sort_locale_bench.rs

39.3 ms*39.5 ms

cksum_raw_output

src/uu/cksum/benches/cksum_bench.rs

16.9 ms*17 ms

sort_accented_data[500000]

src/uu/sort/benches/sort_bench.rs

362.6 ms*364.3 ms

sort_unique_mixed

src/uu/sort/benches/sort_locale_bench.rs

39.4 ms*39.6 ms

sort_german_c_locale

src/uu/sort/benches/sort_locale_bench.rs

38.4 ms*38.6 ms

sort_reverse_mixed

src/uu/sort/benches/sort_locale_bench.rs

39.1 ms*39.3 ms

sort_ascii_only[500000]

src/uu/sort/benches/sort_bench.rs

353.8 ms*355.5 ms

sort_mixed_c_locale

src/uu/sort/benches/sort_locale_bench.rs

-1%

38.3 ms*38.5 ms

sort_mixed_utf8_locale

src/uu/sort/benches/sort_locale_bench.rs

-1%

38.8 ms*39 ms

sort_reverse_locale[500000]

src/uu/sort/benches/sort_bench.rs

-1%

361.8 ms*363.9 ms

sort_case_sensitive[500000]

src/uu/sort/benches/sort_bench.rs

-1%

173.8 ms*175.5 ms

sort_long_line[160000]

src/uu/sort/benches/sort_bench.rs

-1%

1.7 ms*1.7 ms

sort_dictionary_order[500000]

src/uu/sort/benches/sort_bench.rs

-1%

1.1 s*1.1 s

sort_ascii_utf8_locale

src/uu/sort/benches/sort_locale_bench.rs

-2%

43.1 ms*43.8 ms

sort_ascii_c_locale

src/uu/sort/benches/sort_locale_bench.rs

-2%

21.5 ms*21.9 ms

sort_key_field[500000]

src/uu/sort/benches/sort_bench.rs

-2%

702.4 ms*715.1 ms

sort_numeric[500000]

src/uu/sort/benches/sort_bench.rs

-2%

1.2 s*1.2 s

sort_case_insensitive[500000]

src/uu/sort/benches/sort_bench.rs

-2%

276.7 ms*282.7 ms

Commits

Click on a commit to change the comparison range

Base

main

cc103ec

-34.41%

refactor(sort): replace named lifetime with anonymous one in LineData impl Use '_' instead of 'a' for the lifetime parameter in the impl block to simplify and modernize the code without changing behavior.

b245685

1 month ago

by mattsu2020

+34.31%

refactor(sort): simplify lexicographic comparison by removing UTF-8 cache Remove the unused utf8_cache field from LineData struct and related code for caching UTF-8 strings during line parsing. This simplifies the lexicographic comparison logic in compare_by to always perform byte-level comparison, reducing code complexity and potential maintenance overhead without affecting sorting functionality. The previous cache was intended for faster lexical sorting but is no longer needed.

e54fe82

22 days ago

by mattsu2020

+0.01%

Merge branch 'main' into sort_fix_rebased

2841c8a

22 days ago

by mattsu2020

-3.59%

Merge branch 'sort_fix_rebased' of https://github.com/mattsu2020/coreutils into sort_fix_rebased

774fe29

9 hours ago

by mattsu2020

Home Terms Privacy Docs