clean-whitespace testing

This commit is contained in:
John Kerl 2018-10-14 14:17:20 -04:00
parent dbef8bb0f8
commit cdfee0cda8
4 changed files with 198 additions and 0 deletions

View file

@ -1091,6 +1091,172 @@ a=zee,b=wye,i=8,x=0.5985540091064224,y=0.976181385699006
a=pan,b=wye,i=10,x=0.5026260055412137,y=0.9526183602969864
================================================================
WHITESPACE-REDUCTION
mlr --icsv --ojson cat ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b ": 2, " c": 3 }
{ "n": 2, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 3, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 4, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 5, "a": "xy", "b ": 2, " c": 3 }
{ "n": 6, "a": " xy", "b ": 2, " c": 3 }
{ "n": 7, "a": " xy", "b ": 2, " c": 3 }
{ "n": 8, "a": " xy", "b ": 2, " c": 3 }
{ "n": 9, "a": "xy", "b ": 2, " c": 3 }
{ "n": 10, "a": " xy ", "b ": 2, " c": 3 }
{ "n": 11, "a": " xy ", "b ": 2, " c": 3 }
{ "n": 12, "a": " xy ", "b ": 2, " c": 3 }
{ "n": 13, "a": "", "b ": 2, " c": 3 }
{ "n": 14, "a": " ", "b ": 2, " c": 3 }
{ "n": 15, "a": " ", "b ": 2, " c": 3 }
{ "n": 16, "a": " ", "b ": 2, " c": 3 }
mlr --icsv --ojson put $a = lstrip($a) ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b ": 2, " c": 3 }
{ "n": 2, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 3, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 4, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 5, "a": "xy", "b ": 2, " c": 3 }
{ "n": 6, "a": "xy", "b ": 2, " c": 3 }
{ "n": 7, "a": "xy", "b ": 2, " c": 3 }
{ "n": 8, "a": "xy", "b ": 2, " c": 3 }
{ "n": 9, "a": "xy", "b ": 2, " c": 3 }
{ "n": 10, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 11, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 12, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 13, "a": "", "b ": 2, " c": 3 }
{ "n": 14, "a": "", "b ": 2, " c": 3 }
{ "n": 15, "a": "", "b ": 2, " c": 3 }
{ "n": 16, "a": "", "b ": 2, " c": 3 }
mlr --icsv --ojson put $a = rstrip($a) ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b ": 2, " c": 3 }
{ "n": 2, "a": "xy", "b ": 2, " c": 3 }
{ "n": 3, "a": "xy", "b ": 2, " c": 3 }
{ "n": 4, "a": "xy", "b ": 2, " c": 3 }
{ "n": 5, "a": "xy", "b ": 2, " c": 3 }
{ "n": 6, "a": " xy", "b ": 2, " c": 3 }
{ "n": 7, "a": " xy", "b ": 2, " c": 3 }
{ "n": 8, "a": " xy", "b ": 2, " c": 3 }
{ "n": 9, "a": "xy", "b ": 2, " c": 3 }
{ "n": 10, "a": " xy", "b ": 2, " c": 3 }
{ "n": 11, "a": " xy", "b ": 2, " c": 3 }
{ "n": 12, "a": " xy", "b ": 2, " c": 3 }
{ "n": 13, "a": "", "b ": 2, " c": 3 }
{ "n": 14, "a": "", "b ": 2, " c": 3 }
{ "n": 15, "a": "", "b ": 2, " c": 3 }
{ "n": 16, "a": "", "b ": 2, " c": 3 }
mlr --icsv --ojson put $a = strip($a) ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b ": 2, " c": 3 }
{ "n": 2, "a": "xy", "b ": 2, " c": 3 }
{ "n": 3, "a": "xy", "b ": 2, " c": 3 }
{ "n": 4, "a": "xy", "b ": 2, " c": 3 }
{ "n": 5, "a": "xy", "b ": 2, " c": 3 }
{ "n": 6, "a": "xy", "b ": 2, " c": 3 }
{ "n": 7, "a": "xy", "b ": 2, " c": 3 }
{ "n": 8, "a": "xy", "b ": 2, " c": 3 }
{ "n": 9, "a": "xy", "b ": 2, " c": 3 }
{ "n": 10, "a": "xy", "b ": 2, " c": 3 }
{ "n": 11, "a": "xy", "b ": 2, " c": 3 }
{ "n": 12, "a": "xy", "b ": 2, " c": 3 }
{ "n": 13, "a": "", "b ": 2, " c": 3 }
{ "n": 14, "a": "", "b ": 2, " c": 3 }
{ "n": 15, "a": "", "b ": 2, " c": 3 }
{ "n": 16, "a": "", "b ": 2, " c": 3 }
mlr --icsv --ojson put $a = collapse_whitespace($a) ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b ": 2, " c": 3 }
{ "n": 2, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 3, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 4, "a": "xy ", "b ": 2, " c": 3 }
{ "n": 5, "a": "xy", "b ": 2, " c": 3 }
{ "n": 6, "a": " xy", "b ": 2, " c": 3 }
{ "n": 7, "a": " xy", "b ": 2, " c": 3 }
{ "n": 8, "a": " xy", "b ": 2, " c": 3 }
{ "n": 9, "a": "xy", "b ": 2, " c": 3 }
{ "n": 10, "a": " xy ", "b ": 2, " c": 3 }
{ "n": 11, "a": " xy ", "b ": 2, " c": 3 }
{ "n": 12, "a": " xy ", "b ": 2, " c": 3 }
{ "n": 13, "a": "", "b ": 2, " c": 3 }
{ "n": 14, "a": " ", "b ": 2, " c": 3 }
{ "n": 15, "a": " ", "b ": 2, " c": 3 }
{ "n": 16, "a": " ", "b ": 2, " c": 3 }
mlr --icsv --ojson put $a = clean_whitespace($a) ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b ": 2, " c": 3 }
{ "n": 2, "a": "xy", "b ": 2, " c": 3 }
{ "n": 3, "a": "xy", "b ": 2, " c": 3 }
{ "n": 4, "a": "xy", "b ": 2, " c": 3 }
{ "n": 5, "a": "xy", "b ": 2, " c": 3 }
{ "n": 6, "a": "xy", "b ": 2, " c": 3 }
{ "n": 7, "a": "xy", "b ": 2, " c": 3 }
{ "n": 8, "a": "xy", "b ": 2, " c": 3 }
{ "n": 9, "a": "xy", "b ": 2, " c": 3 }
{ "n": 10, "a": "xy", "b ": 2, " c": 3 }
{ "n": 11, "a": "xy", "b ": 2, " c": 3 }
{ "n": 12, "a": "xy", "b ": 2, " c": 3 }
{ "n": 13, "a": "", "b ": 2, " c": 3 }
{ "n": 14, "a": "", "b ": 2, " c": 3 }
{ "n": 15, "a": "", "b ": 2, " c": 3 }
{ "n": 16, "a": "", "b ": 2, " c": 3 }
mlr --icsv --ojson clean-whitespace -k ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b": 2, "c": 3 }
{ "n": 2, "a": "xy ", "b": 2, "c": 3 }
{ "n": 3, "a": "xy ", "b": 2, "c": 3 }
{ "n": 4, "a": "xy ", "b": 2, "c": 3 }
{ "n": 5, "a": "xy", "b": 2, "c": 3 }
{ "n": 6, "a": " xy", "b": 2, "c": 3 }
{ "n": 7, "a": " xy", "b": 2, "c": 3 }
{ "n": 8, "a": " xy", "b": 2, "c": 3 }
{ "n": 9, "a": "xy", "b": 2, "c": 3 }
{ "n": 10, "a": " xy ", "b": 2, "c": 3 }
{ "n": 11, "a": " xy ", "b": 2, "c": 3 }
{ "n": 12, "a": " xy ", "b": 2, "c": 3 }
{ "n": 13, "a": "", "b": 2, "c": 3 }
{ "n": 14, "a": " ", "b": 2, "c": 3 }
{ "n": 15, "a": " ", "b": 2, "c": 3 }
{ "n": 16, "a": " ", "b": 2, "c": 3 }
mlr --icsv --ojson clean-whitespace -v ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b ": 2, " c": 3 }
{ "n": 2, "a": "xy", "b ": 2, " c": 3 }
{ "n": 3, "a": "xy", "b ": 2, " c": 3 }
{ "n": 4, "a": "xy", "b ": 2, " c": 3 }
{ "n": 5, "a": "xy", "b ": 2, " c": 3 }
{ "n": 6, "a": "xy", "b ": 2, " c": 3 }
{ "n": 7, "a": "xy", "b ": 2, " c": 3 }
{ "n": 8, "a": "xy", "b ": 2, " c": 3 }
{ "n": 9, "a": "xy", "b ": 2, " c": 3 }
{ "n": 10, "a": "xy", "b ": 2, " c": 3 }
{ "n": 11, "a": "xy", "b ": 2, " c": 3 }
{ "n": 12, "a": "xy", "b ": 2, " c": 3 }
{ "n": 13, "a": "", "b ": 2, " c": 3 }
{ "n": 14, "a": "", "b ": 2, " c": 3 }
{ "n": 15, "a": "", "b ": 2, " c": 3 }
{ "n": 16, "a": "", "b ": 2, " c": 3 }
mlr --icsv --ojson clean-whitespace ./reg_test/input/clean-whitespace.csv
{ "n": 1, "a": "xy", "b": 2, "c": 3 }
{ "n": 2, "a": "xy", "b": 2, "c": 3 }
{ "n": 3, "a": "xy", "b": 2, "c": 3 }
{ "n": 4, "a": "xy", "b": 2, "c": 3 }
{ "n": 5, "a": "xy", "b": 2, "c": 3 }
{ "n": 6, "a": "xy", "b": 2, "c": 3 }
{ "n": 7, "a": "xy", "b": 2, "c": 3 }
{ "n": 8, "a": "xy", "b": 2, "c": 3 }
{ "n": 9, "a": "xy", "b": 2, "c": 3 }
{ "n": 10, "a": "xy", "b": 2, "c": 3 }
{ "n": 11, "a": "xy", "b": 2, "c": 3 }
{ "n": 12, "a": "xy", "b": 2, "c": 3 }
{ "n": 13, "a": "", "b": 2, "c": 3 }
{ "n": 14, "a": "", "b": 2, "c": 3 }
{ "n": 15, "a": "", "b": 2, "c": 3 }
{ "n": 16, "a": "", "b": 2, "c": 3 }
================================================================
SORT

View file

@ -27,6 +27,7 @@ EXTRA_DIST= \
c.pprint \
capture-lengths.dkvp \
capture.dkvp \
clean-whitespace.csv \
comments \
d.csv \
d.pprint \

View file

@ -0,0 +1,17 @@
n,a,b , c
1,xy,2,3
2,xy ,2,3
3,xy ,2,3
4,xy ,2,3
5,xy,2,3
6, xy,2,3
7, xy,2,3
8, xy,2,3
9,xy,2,3
10, xy ,2,3
11, xy ,2,3
12, xy ,2,3
13,,2,3
14, ,2,3
15, ,2,3
16, ,2,3
1 n a b c
2 1 xy 2 3
3 2 xy 2 3
4 3 xy 2 3
5 4 xy 2 3
6 5 xy 2 3
7 6 xy 2 3
8 7 xy 2 3
9 8 xy 2 3
10 9 xy 2 3
11 10 xy 2 3
12 11 xy 2 3
13 12 xy 2 3
14 13 2 3
15 14 2 3
16 15 2 3
17 16 2 3

View file

@ -337,6 +337,20 @@ run_mlr decimate -g a -n 2 $indir/abixy
run_mlr decimate -g a -b -n 2 $indir/abixy
run_mlr decimate -g a -e -n 2 $indir/abixy
# ----------------------------------------------------------------
announce WHITESPACE-REDUCTION
run_mlr --icsv --ojson cat $indir/clean-whitespace.csv
run_mlr --icsv --ojson put '$a = lstrip($a)' $indir/clean-whitespace.csv
run_mlr --icsv --ojson put '$a = rstrip($a)' $indir/clean-whitespace.csv
run_mlr --icsv --ojson put '$a = strip($a)' $indir/clean-whitespace.csv
run_mlr --icsv --ojson put '$a = collapse_whitespace($a)' $indir/clean-whitespace.csv
run_mlr --icsv --ojson put '$a = clean_whitespace($a)' $indir/clean-whitespace.csv
run_mlr --icsv --ojson clean-whitespace -k $indir/clean-whitespace.csv
run_mlr --icsv --ojson clean-whitespace -v $indir/clean-whitespace.csv
run_mlr --icsv --ojson clean-whitespace $indir/clean-whitespace.csv
# ----------------------------------------------------------------
announce SORT