1
2
3
4
5
6
7
8
9
10
11
12
13
|
#!/bin/bash
export LC_COLLATE=C # case-sensitive file glob
for i in ../data/[a-zHR]*.sor # skip Suzhou.sor (multiline regex support needs for conditional text, yet)
do
echo === $i ===
# check first 1000 numbers in all languages, checking also the conditional lines
PYTHONPATH=../src python3 test.py $i <(seq 0 2000) /dev/stdout $(grep -Eo '\[:.....:]' $i | tr -d '[]:' | sort | uniq) |
awk -v fil="$i" '
/Language:/{delete a; lang=$2}
/^$/{print "Missing output: " fil " (input number: " NR%2000", language: " lang ")";next}
a[$0]==1{print "Duplicate: $0 (input number: " NR%2000 ", language: " lang ")"}
{a[$0]=1}'
done
|
