mirror of
https://github.com/vel21ripn/nDPI.git
synced 2026-05-04 09:50:16 +00:00
c35a5ca087
Reformatted shell scripts according to [ShellCheck](https://github.com/koalaman/shellcheck/). I. Most common changes: 1. https://github.com/koalaman/shellcheck/wiki/SC2086 `$var` → `"$var"` Note: this isn't always necessary and I've been careful not to substitute where it wasn't necessary in meaning. 2. https://github.com/koalaman/shellcheck/wiki/SC2006 `` `command` `` → `$(command)` 3. https://github.com/koalaman/shellcheck/wiki/SC2004 `$(( $a + $b ))` → `$(( a + b ))` 4. https://github.com/koalaman/shellcheck/wiki/SC2164 `cd "$dir"` → `cd "$dir" || exit 1` 5. https://github.com/koalaman/shellcheck/wiki/SC2166 `[ check1 -o check2 ]` → `[ check1 ] || [ check2 ]` 6. https://github.com/koalaman/shellcheck/wiki/SC2002 `cat "${file}" | wc -c` → `< "${file}" wc -c` Note: this looks a bit uglier but works faster. II. Some special changes: 1. In file `utils/common.sh`: https://github.com/koalaman/shellcheck/wiki/SC2112 This script is interpreted by `sh`, not by `bash`, but uses the keyword `function`. So I replaced `#!/usr/bin/env sh` to `#!/usr/bin/env bash`. 2. After that I thought of replacing all shebangs to `#!/usr/bin/env bash` for consistency and cross-platform compatibility, especially since most of the files already use bash. 3. But in cases when it was `#!/bin/sh -e` or `#!/bin/bash -eu` another problem appears: https://github.com/koalaman/shellcheck/wiki/SC2096 So I decided to make all shebangs look uniform: ``` #!/usr/bin/env bash set -e (or set -eu) (if needed) ``` 4. In file `tests/ossfuzz.sh`: https://github.com/koalaman/shellcheck/wiki/SC2162 `read i` → `read -r i` Note: I think that there is no need in special treatment for backslashes, but I could be wrong. 5. In file `tests/do.sh.in`: https://github.com/koalaman/shellcheck/wiki/SC2035 `ls *.*cap*` → `ls -- *.*cap*` 6. In file `utils/verify_dist_tarball.sh`: https://github.com/koalaman/shellcheck/wiki/SC2268 `[ "x${TARBALL}" = x ]` → `[ -z "${TARBALL}" ]` 7. In file `utils/check_symbols.sh`: https://github.com/koalaman/shellcheck/wiki/SC2221 `'[ndpi_utils.o]'|'[ndpi_memory.o]'|'[roaring.o]')` → `'[ndpi_utils.o]'|'[ndpi_memory.o]')` 8. In file `autogen.sh`: https://github.com/koalaman/shellcheck/wiki/SC2145 `echo "./configure $@"` → `echo "./configure $*"` https://github.com/koalaman/shellcheck/wiki/SC2068 `./configure $@` → `./configure "$@"` III. `LIST6_MERGED` and `LIST_MERGED6` There were typos with this variables in files `utils/aws_ip_addresses_download.sh`, `utils/aws_ip_addresses_download.sh` and `utils/microsoft_ip_addresses_download.sh` where variable `LIST6_MERGED` was defined, but `LIST_MERGED6` was removed by `rm`. I changed all `LIST_MERGED6` to `LIST6_MERGED`. Not all changes are absolutely necessary, but some may save you from future bugs.
65 lines
2.3 KiB
Bash
Executable file
65 lines
2.3 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
|
|
cd "$(dirname "${0}")" || exit 1
|
|
|
|
# Baseline performances ------------------------------------------------------------------------------------------------
|
|
# Important notes: BASE values must be integers examples and represents percentage (e.g. 79%, 98%).
|
|
BASE_ACCURACY=69
|
|
BASE_PRECISION=89
|
|
BASE_RECALL=40
|
|
# ----------------------------------------------------------------------------------------------------------------------
|
|
|
|
DGA_EVALUATE="./dga/dga_evaluate"
|
|
DGA_DATA="dga/test_dga.csv"
|
|
NON_DGA_DATA="dga/test_non_dga.csv"
|
|
DGA_DATA_SIZE=0
|
|
NON_DGA_DATA_SIZE=0
|
|
DATA_SIZE=0
|
|
RC=0
|
|
|
|
get_evaluation_data_size() {
|
|
DGA_DATA_SIZE=$(wc -l dga/test_dga.csv | awk '{split($0,a," "); print a[1]}')
|
|
NON_DGA_DATA_SIZE=$(wc -l dga/test_non_dga.csv | awk '{split($0,a," "); print a[1]}')
|
|
DATA_SIZE=$(( NON_DGA_DATA_SIZE + DGA_DATA_SIZE ))
|
|
}
|
|
|
|
evaluate_ndpi_dga_detection() {
|
|
# DGA detection is a binary classification problem, We evaluate the following metrics:
|
|
# Accuracy: (TP + TN) / (TP + TN + FN + FP)
|
|
# Precision: TP / (TP + FP)
|
|
# Recall: TP / (TP + FN)
|
|
|
|
TP=$($DGA_EVALUATE dga/test_dga.csv)
|
|
FN=$(( DGA_DATA_SIZE - TP ))
|
|
FP=$($DGA_EVALUATE dga/test_non_dga.csv)
|
|
TN=$(( NON_DGA_DATA_SIZE - FP ))
|
|
|
|
ACCURACY=$(echo "print(int(((${TP} + ${TN})/(${TP} + ${TN} + ${FP} + ${FN}))*100))" | python3)
|
|
PRECISION=$(echo "print(int(((${TP})/(${TP} + ${FP}))*100))" | python3)
|
|
RECALL=$(echo "print(int(((${TP})/(${TP} + ${FN}))*100))" | python3)
|
|
|
|
# In case modified version of classification algorithm decreases performances, test do not pass.
|
|
if [ "$ACCURACY" -lt "$BASE_ACCURACY" ]; then
|
|
printf "ERROR: Your modifications decreased DGA classifier accuracy: 0.${BASE_ACCURACY} decreased to 0.${ACCURACY}!\n"
|
|
RC=1
|
|
fi
|
|
if [ "$PRECISION" -lt "$BASE_PRECISION" ]; then
|
|
printf "ERROR: Your modifications decreased DGA classifier precision: 0.${BASE_PRECISION} decreased to 0.${PRECISION}!\n"
|
|
RC=1
|
|
fi
|
|
if [ "$RECALL" -lt "$BASE_RECALL" ]; then
|
|
printf "ERROR: Your modifications decreased DGA classifier recall: 0.${BASE_RECALL} decreased to 0.${RECALL}!\n"
|
|
RC=1
|
|
fi
|
|
|
|
# Finally we print the current performances, upgrade BASE_ metrics in case you improved it.
|
|
echo "DGA detection performances report:"
|
|
echo "Accuracy=0.$ACCURACY"
|
|
echo "Precision=0.$PRECISION"
|
|
echo "Recall=0.$RECALL"
|
|
}
|
|
|
|
get_evaluation_data_size
|
|
evaluate_ndpi_dga_detection
|
|
|
|
exit $RC
|