From 465f9512b710ee2fe03c3caf65bfdccdce3544ae Mon Sep 17 00:00:00 2001
From: Cojocaru Alexandru <xojoc@gmx.com>
Date: Tue, 7 May 2013 13:47:15 +0100
Subject: cut: improve performance, especially with --output-delimiter

Use a sentinel value that's checked implicitly, rather than
a bit array, to determine if an item should be output.

Benchmark results for this change are:

$ yes abcdfeg | head -n1MB > big-file

$ for c in orig sentinel; do
    src/cut-$c 2>/dev/null
    echo -ne "\n== $c =="
    time src/cut-$c -b1,3 big-file > /dev/null
  done
== orig ==
real    0m0.049s
user    0m0.044s
sys     0m0.005s

== sentinel ==
real    0m0.035s
user    0m0.032s
sys     0m0.002s

 ## Again with --output-delimiter ##
$ for c in orig sentinel; do
    src/cut-$c 2>/dev/null
    echo -ne "\n== $c =="
    time src/cut-$c -b1,3 --output-delimiter=: big-file > /dev/null
  done
== orig ==
real    0m0.106s
user    0m0.103s
sys     0m0.002s

== sentinel ==
real    0m0.055s
user    0m0.052s
sys     0m0.003s

eol_range_start: Removed. 'n-' is no longer treated specially,
and instead SIZE_MAX is set for the 'hi' limit, and tested implicitly.
complement_rp: Used to complement 'rp' when '--complement' is specified.
ADD_RANGE_PAIR: Macro renamed to 'add_range_pair' function.
* tests/misc/cut-huge-range.sh: Adjust to the SENTINEL value.
Also remove the overlapping range test as this is no longer
dependent on large ranges and also is already handled with
the EOL-subsumed-3 test in cut.pl.
---
 tests/misc/cut-huge-range.sh | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

(limited to 'tests')

diff --git a/tests/misc/cut-huge-range.sh b/tests/misc/cut-huge-range.sh
index 9905cd758..e9190a2c2 100755
--- a/tests/misc/cut-huge-range.sh
+++ b/tests/misc/cut-huge-range.sh
@@ -21,19 +21,22 @@ print_ver_ cut
 require_ulimit_v_
 getlimits_
 
+# Ensure we can cut up to our sentinel value.
+# This is currently SIZE_MAX, but could be raised to UINTMAX_MAX
+# if we didn't allocate memory for each line as a unit.
+CUT_MAX=$(expr $SIZE_MAX - 1)
+
 # From coreutils-8.10 through 8.20, this would make cut try to allocate
 # a 256MiB bit vector.  With a 20MB limit on VM, the following would fail.
-(ulimit -v 20000; : | cut -b$INT_MAX- > err 2>&1) || fail=1
+(ulimit -v 20000; : | cut -b$CUT_MAX- > err 2>&1) || fail=1
 
 # Up to and including coreutils-8.21, cut would allocate possibly needed
-# memory upfront.  Subsequently memory is allocated as required.
-(ulimit -v 20000; : | cut -b1-$INT_MAX >> err 2>&1) || fail=1
-
-# Ensure ranges are merged correctly when large range logic is in effect
-echo 1 > exp
-(dd bs=1MB if=/dev/zero count=1; echo '1') |
-cut -b1-1000000,2-3,4-5,1000001 2>>err | tail -c2 > out || fail=1
-compare exp out || fail=1
+# memory upfront.  Subsequently extra memory is no longer needed.
+(ulimit -v 20000; : | cut -b1-$CUT_MAX >> err 2>&1) || fail=1
+
+# Explicitly disallow values above CUT_MAX
+(ulimit -v 20000; : | cut -b$SIZE_MAX 2>/dev/null) && fail=1
+(ulimit -v 20000; : | cut -b$SIZE_OFLOW 2>/dev/null) && fail=1
 
 compare /dev/null err || fail=1
 
-- 
cgit v1.2.3-54-g00ecf