rynewang:fix-cut-newline-delimiter-only-delimited - Branch - uutils/coreutils

cut: fix -s flag ignored when delimiter is newline

#10037

Comparing

rynewang:fix-cut-newline-delimiter-only-delimited

(

43986aa

) with

main

(

130f780

)

+4%

Improvements: 1

Untouched: 138

Skipped: 37

Benchmarks

Skipped (37)

Improved

tsort_input_parsing_heavy[5000]

src/uu/tsort/benches/tsort_bench.rs

+4%

73.1 ms70.2 ms

Passed

du_max_depth_balanced_tree[(6, 4, 10)]

src/uu/du/benches/du_bench.rs

+1%

33 ms32.7 ms

sort_mixed_data[500000]

src/uu/sort/benches/sort_bench.rs

+1%

317.3 ms314.8 ms

dd_copy_1m_blocks

src/uu/dd/benches/dd_bench.rs

+1%

1.5 ms1.5 ms

du_wide_tree[(5000, 500)]

src/uu/du/benches/du_bench.rs

+1%

11.2 ms11.2 ms

dd_copy_64k_blocks

src/uu/dd/benches/dd_bench.rs

603.7 µs601.4 µs

dd_copy_8k_blocks

src/uu/dd/benches/dd_bench.rs

1 ms1 ms

sort_unique_utf8_locale

src/uu/sort/benches/sort_locale_utf8_bench.rs

37.7 ms37.7 ms

dd_copy_with_skip

src/uu/dd/benches/dd_bench.rs

2.2 ms2.2 ms

dd_copy_4k_blocks

src/uu/dd/benches/dd_bench.rs

1.3 ms1.3 ms

b64_decode_synthetic

src/uu/base64/benches/base64_bench.rs

165.6 µs165.5 µs

cp_recursive_deep_tree[(120, 4)]

src/uu/cp/benches/cp_bench.rs

13.6 ms13.6 ms

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

77.9 ms77.9 ms

b64_decode_ignore_garbage_synthetic

src/uu/base64/benches/base64_bench.rs

162.6 µs162.5 µs

sort_mixed_utf8_locale

src/uu/sort/benches/sort_locale_utf8_bench.rs

37.4 ms37.4 ms

factor_multiple_u64s[2]

src/uu/factor/benches/factor_bench.rs

211.1 ms211 ms

shuf_lines[100000]

src/uu/shuf/benches/shuf_bench.rs

31.6 ms31.6 ms

sort_german_de_locale

src/uu/sort/benches/sort_locale_de_bench.rs

37.9 ms37.9 ms

tsort_complex_dag[50000]

src/uu/tsort/benches/tsort_bench.rs

86.4 ms86.4 ms

sort_german_c_locale

src/uu/sort/benches/sort_locale_c_bench.rs

37.9 ms37.9 ms

sort_case_insensitive[500000]

src/uu/sort/benches/sort_bench.rs

265.9 ms265.9 ms

ls_recursive_deep_tree[(200, 2)]

src/uu/ls/benches/ls_bench.rs

2.2 ms2.2 ms

ls_recursive_long_all_deep_tree[(100, 4)]

src/uu/ls/benches/ls_bench.rs

3.2 ms3.2 ms

mv_force_overwrite

src/uu/mv/benches/mv_bench.rs

143.8 ms143.8 ms

ls_recursive_long_all_mixed_tree

src/uu/ls/benches/ls_bench.rs

2.8 ms2.8 ms

join_french_locale

src/uu/join/benches/join_bench.rs

12.8 ms12.8 ms

uniq_case_insensitive[10000]

src/uu/uniq/benches/uniq_bench.rs

1.6 ms1.6 ms

shuf_input_range[1000000]

src/uu/shuf/benches/shuf_bench.rs

163.5 ms163.5 ms

ls_recursive_balanced_tree[(6, 4, 15)]

src/uu/ls/benches/ls_bench.rs

55.3 ms55.3 ms

cksum_sha3

src/uu/cksum/benches/cksum_bench.rs

1.8 s1.8 s

split_lines

src/uu/split/benches/split_bench.rs

5.7 ms5.7 ms

uniq_heavy_duplicates[10000]

src/uu/uniq/benches/uniq_bench.rs

1.9 ms1.9 ms

uniq_with_count[10000]

src/uu/uniq/benches/uniq_bench.rs

1.8 ms1.8 ms

ls_recursive_wide_tree[(10000, 1000)]

src/uu/ls/benches/ls_bench.rs

51.5 ms51.5 ms

numfmt_to_iec[10000]

src/uu/numfmt/benches/numfmt_bench.rs

33.8 ms33.8 ms

numfmt_to_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

33.8 ms33.8 ms

dd_copy_default

src/uu/dd/benches/dd_bench.rs

14 ms14 ms

sort_long_line[160000]

src/uu/sort/benches/sort_bench.rs

1.7 ms1.7 ms

cut_fields_tab

src/uu/cut/benches/cut_bench.rs

34.1 ms34.1 ms

numfmt_from_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

32.8 ms32.8 ms

numfmt_round_modes[("down", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

cut_fields_custom_delim

src/uu/cut/benches/cut_bench.rs

40.8 ms40.8 ms

sort_numeric[500000]

src/uu/sort/benches/sort_bench.rs

1.2 s1.2 s

numfmt_round_modes[("up", 10000)]

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

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

src/uu/numfmt/benches/numfmt_bench.rs

34.3 ms34.3 ms

numfmt_large_numbers_si[10000]

src/uu/numfmt/benches/numfmt_bench.rs

32.5 ms32.5 ms

cksum_sha2

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

numfmt_to_si_precision[10000]

src/uu/numfmt/benches/numfmt_bench.rs

35.3 ms35.3 ms

join_partial_overlap

src/uu/join/benches/join_bench.rs

10.5 ms10.5 ms

numfmt_padding[(10000, 50)]

src/uu/numfmt/benches/numfmt_bench.rs

48 ms48 ms

expand_many_lines[100000]

src/uu/expand/benches/expand_bench.rs

148.6 ms148.6 ms

sort_dictionary_order[500000]

src/uu/sort/benches/sort_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

nl_many_lines[100000]

src/uu/nl/benches/nl_bench.rs

44.9 ms44.9 ms

unexpand_large_file[10]

src/uu/unexpand/benches/unexpand_bench.rs

529 ms529 ms

unexpand_many_lines[100000]

src/uu/unexpand/benches/unexpand_bench.rs

252.3 ms252.3 ms

wc_bytes_lines_synthetic[2000]

src/uu/wc/benches/wc_bench.rs

120.2 ms120.2 ms

expand_custom_tabstops[50000]

src/uu/expand/benches/expand_bench.rs

36.9 ms36.9 ms

sort_reverse_utf8_locale

src/uu/sort/benches/sort_locale_utf8_bench.rs

37.6 ms37.6 ms

fold_many_lines[100000]

src/uu/fold/benches/fold_bench.rs

80.4 ms80.4 ms

fold_custom_width[50000]

src/uu/fold/benches/fold_bench.rs

33 ms33 ms

wc_words_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

48 ms48 ms

sort_mixed_c_locale

src/uu/sort/benches/sort_locale_c_bench.rs

37.2 ms37.2 ms

wc_default_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

50.4 ms50.4 ms

nl_large_file[10]

src/uu/nl/benches/nl_bench.rs

57.1 ms57.1 ms

seq_formatted

src/uu/seq/benches/seq_bench.rs

96.1 ms96.1 ms

cksum_sha256

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

seq_custom_separator

src/uu/seq/benches/seq_bench.rs

28.7 ms28.7 ms

cut_characters

src/uu/cut/benches/cut_bench.rs

7.4 ms7.4 ms

join_custom_separator

src/uu/join/benches/join_bench.rs

12.1 ms12.1 ms

file_custom_format

src/uu/date/benches/date_bench.rs

13.3 ms13.3 ms

file_iso_dates

src/uu/date/benches/date_bench.rs

13.9 ms13.9 ms

seq_integers

src/uu/seq/benches/seq_bench.rs

26.1 ms26.1 ms

cksum_sha512

src/uu/cksum/benches/cksum_bench.rs

1.1 s1.1 s

cksum_sha384

src/uu/cksum/benches/cksum_bench.rs

1.1 s1.1 s

sort_ascii_c_locale

src/uu/sort/benches/sort_locale_c_bench.rs

20.3 ms20.3 ms

mv_single_file

src/uu/mv/benches/mv_bench.rs

135 ms135 ms

wc_lines_variable_length[(50, 500)]

src/uu/wc/benches/wc_bench.rs

3.4 ms3.4 ms

sort_ascii_utf8_locale

src/uu/sort/benches/sort_locale_utf8_bench.rs

20.1 ms20.1 ms

file_tz_abbreviations

src/uu/date/benches/date_bench.rs

18.6 ms18.6 ms

seq_with_step

src/uu/seq/benches/seq_bench.rs

13.3 ms13.3 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 ms2.9 ms

cksum_sha224

src/uu/cksum/benches/cksum_bench.rs

1.7 s1.7 s

wc_lines_extreme_line_lengths[(100000, 200)]

src/uu/wc/benches/wc_bench.rs

1.6 ms1.6 ms

ls_recursive_long_all_wide_tree[(15000, 1500)]

src/uu/ls/benches/ls_bench.rs

139.5 ms139.5 ms

cksum_sm3

src/uu/cksum/benches/cksum_bench.rs

1.6 s1.6 s

ls_recursive_mixed_tree

src/uu/ls/benches/ls_bench.rs

1.4 ms1.4 ms

cut_bytes

src/uu/cut/benches/cut_bench.rs

8.4 ms8.4 ms

sort_accented_data[500000]

src/uu/sort/benches/sort_bench.rs

351.8 ms351.8 ms

tsort_tree_dag[(10, 3)]

src/uu/tsort/benches/tsort_bench.rs

34.7 ms34.7 ms

rm_multiple_files

src/uu/rm/benches/rm_bench.rs

2.2 ms2.2 ms

join_full_match

src/uu/join/benches/join_bench.rs

12.8 ms12.8 ms

sort_numeric_utf8_locale

src/uu/sort/benches/sort_locale_utf8_bench.rs

22.8 ms22.8 ms

split_bytes

src/uu/split/benches/split_bench.rs

508.9 µs509 µs

split_number_chunks

src/uu/split/benches/split_bench.rs

293.8 µs293.8 µs

rm_force_files

src/uu/rm/benches/rm_bench.rs

2 ms2 ms

seq_large_integers

src/uu/seq/benches/seq_bench.rs

2.2 ms2.2 ms

cksum_sha1

src/uu/cksum/benches/cksum_bench.rs

723 ms723.1 ms

split_numeric_suffix

src/uu/split/benches/split_bench.rs

5.9 ms5.9 ms

wc_chars_large_line_count[100000]

src/uu/wc/benches/wc_bench.rs

1 ms1 ms

tsort_wide_dag[100000]

src/uu/tsort/benches/tsort_bench.rs

131.7 ms131.7 ms

tsort_linear_chain[1000000]

src/uu/tsort/benches/tsort_bench.rs

1.6 s1.6 s

sort_ascii_only[500000]

src/uu/sort/benches/sort_bench.rs

343 ms343 ms

b64_encode_synthetic

src/uu/base64/benches/base64_bench.rs

161.2 µs161.2 µs

rm_single_file

src/uu/rm/benches/rm_bench.rs

118.9 ms118.9 ms

shuf_repeat_sampling[50000]

src/uu/shuf/benches/shuf_bench.rs

5.1 ms5.1 ms

cksum_md5

src/uu/cksum/benches/cksum_bench.rs

317.9 ms318 ms

sort_key_field[500000]

src/uu/sort/benches/sort_bench.rs

690.4 ms690.6 ms

cksum_bsd

src/uu/cksum/benches/cksum_bench.rs

128.3 ms128.3 ms

mv_multiple_to_dir

src/uu/mv/benches/mv_bench.rs

12.9 ms12.9 ms

cp_preserve_metadata[(5, 4, 10)]

src/uu/cp/benches/cp_bench.rs

74.9 ms74.9 ms

ls_recursive_long_all_balanced_tree[(6, 4, 15)]

src/uu/ls/benches/ls_bench.rs

129.7 ms129.7 ms

wc_bytes_synthetic[500]

src/uu/wc/benches/wc_bench.rs

185.7 µs185.8 µs

complex_relative_date

src/uu/date/benches/date_bench.rs

243.4 µs243.5 µs

cksum_blake2b

src/uu/cksum/benches/cksum_bench.rs

192.7 ms192.8 ms

single_date_now

src/uu/date/benches/date_bench.rs

184.4 µs184.5 µs

cp_recursive_wide_tree[(6000, 800)]

src/uu/cp/benches/cp_bench.rs

189.4 ms189.5 ms

cksum_blake3

src/uu/cksum/benches/cksum_bench.rs

224.9 µs225.1 µs

cksum_sysv

src/uu/cksum/benches/cksum_bench.rs

48.2 ms48.3 ms

dd_copy_separate_blocks

src/uu/dd/benches/dd_bench.rs

43.9 ms43.9 ms

sort_case_sensitive[500000]

src/uu/sort/benches/sort_bench.rs

163 ms163.1 ms

rm_recursive_tree

src/uu/rm/benches/rm_bench.rs

11.7 ms11.8 ms

sort_reverse_locale[500000]

src/uu/sort/benches/sort_bench.rs

350.9 ms351.4 ms

du_all_wide_tree[(5000, 500)]

src/uu/du/benches/du_bench.rs

18 ms18.1 ms

sort_unique_locale[500000]

src/uu/sort/benches/sort_bench.rs

483.3 ms484.4 ms

du_summarize_balanced_tree[(5, 4, 10)]

src/uu/du/benches/du_bench.rs

8.4 ms8.4 ms

cksum_default

src/uu/cksum/benches/cksum_bench.rs

16.8 ms16.8 ms

cksum_raw_output

src/uu/cksum/benches/cksum_bench.rs

16.8 ms16.8 ms

du_deep_tree[(100, 3)]

src/uu/du/benches/du_bench.rs

1.2 ms1.2 ms

cp_large_file[16]

src/uu/cp/benches/cp_bench.rs

361.8 µs363 µs

cksum_crc32b

src/uu/cksum/benches/cksum_bench.rs

13.2 ms13.2 ms

cksum_multiple_files

src/uu/cksum/benches/cksum_bench.rs

25.2 ms25.3 ms

dd_copy_with_seek

src/uu/dd/benches/dd_bench.rs

2.3 ms2.3 ms

cksum_crc

src/uu/cksum/benches/cksum_bench.rs

16.8 ms16.9 ms

dd_copy_partial

src/uu/dd/benches/dd_bench.rs

-1%

550.5 µs558 µs

Commits

Click on a commit to change the comparison range

Base

main

130f780

-0.03%

cut: fix -s flag ignored when delimiter is newline When using newline as the delimiter (-d $'\n') with -s (only-delimited), cut should suppress lines that do not contain the delimiter. However, cut_fields_newline_char_delim() was not checking the only_delimited flag, causing it to always output even when -s was specified. The fix uses read_until() instead of split() to read segments. Unlike split(), read_until() includes the delimiter in the buffer when found, allowing us to detect whether a delimiter was actually present or if we just hit EOF. This commit: - Adds only_delimited parameter to cut_fields_newline_char_delim() - Uses read_until() to detect delimiter presence while reading - If no delimiter found and only_delimited is true, returns early - Adds test case for newline delimiter with -s flag Fixes #10012

3e15738

6 days ago

by rynewang

+0.03%

cut: simplify newline delimiter handling - Use read_to_end + split instead of read_until loop - Use Vec<&[u8]> instead of Vec<Vec<u8>> (no extra allocations) - Rename found_delimiter to has_delimiter - Check has_delimiter before removing trailing empty segment - Only write trailing newline if we output something - Remove unused BufRead import - Add tests for edge cases: just newline, empty input

526b5d8

5 days ago

by rynewang

+4.1%

cut: use streaming DelimReader for newline delimiter Address PR review comments: - Replace read_to_end() with streaming DelimReader iterator - DelimReader uses read_until() and tracks delimiter per segment - Only collect selected fields, not entire input - Remove b"".as_slice() check (DelimReader doesn't create trailing empties) - Simplify output with split_first() join pattern

43986aa

3 days ago

by rynewang

Home Terms Privacy Docs