mirrored from git://git.sv.gnu.org/coreutils.git
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
shuf: use reservoir-sampling for large or unknown sized inputs
Reservoir sampling optimizes selecting K random lines from large or unknown-sized input: http://en.wikipedia.org/wiki/Reservoir_sampling Note this also avoids reading any input when -n0 is specified. * src/shuf.c (main): Use reservoir-sampling when the number of output lines is known, and the input size is large or unknown. (input_size): A new function to get the input size for regular files. (read_input_reservoir_sampling): New function to read lines from input, keeping only K lines in memory, replacing lines with decreasing prob. (write_permuted_output_reservoir): New function to output reservoir. * tests/misc/shuf-reservoir.sh: An expensive_ test using valgrind to exercise the reservoir-sampling code. * tests/local.mk: Reference new test. * NEWS: Mention the improvement.
- Loading branch information
Showing
4 changed files
with
244 additions
and
7 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,69 @@ | ||
#!/bin/sh | ||
# Exercise shuf's reservoir-sampling code | ||
# NOTE: | ||
# These tests do not check valid randomness, | ||
# they just check memory allocation related code. | ||
|
||
# Copyright (C) 2013 Free Software Foundation, Inc. | ||
|
||
# This program is free software: you can redistribute it and/or modify | ||
# it under the terms of the GNU General Public License as published by | ||
# the Free Software Foundation, either version 3 of the License, or | ||
# (at your option) any later version. | ||
|
||
# This program is distributed in the hope that it will be useful, | ||
# but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
# GNU General Public License for more details. | ||
|
||
# You should have received a copy of the GNU General Public License | ||
# along with this program. If not, see <http://www.gnu.org/licenses/>. | ||
|
||
. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src | ||
print_ver_ shuf | ||
expensive_ | ||
require_valgrind_ | ||
|
||
# Run "shuf" with specific number of input lines and output lines | ||
# Check the output for expected number of lines. | ||
run_shuf_n() | ||
{ | ||
INPUT_LINES="$1" | ||
OUTPUT_LINES="$2" | ||
|
||
# Critical memory-related bugs will cause a segfault here | ||
# (with varying numbres of input/output lines) | ||
seq "$INPUT_LINES" | valgrind --leak-check=full --error-exitcode=1 \ | ||
shuf -n "$OUTPUT_LINES" -o "out_${INPUT_LINES}_${OUTPUT_LINES}" || return 1 | ||
|
||
EXPECTED_LINES="$OUTPUT_LINES" | ||
test "$INPUT_LINES" -lt "$OUTPUT_LINES" && EXPECTED_LINES="$INPUT_LINES" | ||
|
||
# There is no sure way to verify shuffled output (as it is random). | ||
# Ensure we have the correct number of all numeric lines non duplicated lines. | ||
GOOD_LINES=$(grep '^[0-9][0-9]*$' "out_${INPUT_LINES}_${OUTPUT_LINES}" | | ||
sort -un | wc -l) || framework_failure_ | ||
LINES=$(wc -l < "out_${INPUT_LINES}_${OUTPUT_LINES}") || framework_failure_ | ||
|
||
test "$EXPECTED_LINES" -eq "$GOOD_LINES" || return 1 | ||
test "$EXPECTED_LINES" -eq "$LINES" || return 1 | ||
|
||
return 0 | ||
} | ||
|
||
# Test multiple combinations of input lines and output lines. | ||
# (e.g. small number of input lines and large number of output lines, | ||
# and vice-versa. Also, each reservoir allocation uses a 1024-lines batch, | ||
# so test 1023/1024/1025 and related values). | ||
TEST_LINES="0 1 5 1023 1024 1025 3071 3072 3073" | ||
|
||
for IN_N in $TEST_LINES; do | ||
for OUT_N in $TEST_LINES; do | ||
run_shuf_n "$IN_N" "$OUT_N" || { | ||
fail=1 | ||
echo "shuf-reservoir-sampling failed with IN_N=$IN_N OUT_N=$OUT_N" >&2; | ||
} | ||
done | ||
done | ||
|
||
Exit $fail |