check_gibberish

#! /bin/bash

# Check the spelling of the specified file as an indicator of
# whether the model produced gibberish - this doesn't catch low quality
# output, just utter garbage as a basic backstop

cat "$1"

########################################################################
#
# extract sequence from other output

TMPFILE=/tmp/`basename "$1"`-sequence

if [ "X$2" == "X--no-extract" ]; then
    cp "$1" $TMPFILE
else
    # We extract only the sequence output and don't spell check status and performance stats
    python3 .ci/scripts/extract-sequence.py "$1" >$TMPFILE

    if [ $? -ne 0 ]; then
        echo "Sequence extraction failed. Exiting."
        exit 1
    fi
fi

#######################################################################
#
# check whether aspell spell check evailable

if command -v aspell &> /dev/null; then
    echo "Checking $TMPFILE for gibberish"
else
    echo "Aspell is not installed or not in PATH."
    echo "Gibberish unchecked in $TMPFILE"
    exit 0
fi

#######################################################################
#
# run spell check on the extracted sequence

cat ${TMPFILE} |  aspell -a -c  | grep '^[\&#]' >/tmp/out.$$
# Exit with a non-zero status code if there were any spelling errors because:
# * Finding one or more lines with & or # means we found a spelling error, might be gibberish
if [ $? -ne 0 ]; then
    echo "No spelling errors found; likely correct operation. Success."
    exit 0
fi
cat /tmp/out.$$
echo "Spelling errors found; might indicate garbage output. Failing."
exit 1