staticanalysis

.travis.yml

@@ -21,6 +21,7 @@ addons:
       - gfortran-4.9
       - liblapack-dev
       - clang-3.8
+      - shellcheck
 
 branches:
   only:

egs/wsj/s5/local/append_utterances.sh

@@ -7,10 +7,10 @@
 pad_silence=0.5
 # End configuration section.
 
-echo "$0 $@"
+echo "$0 $*"
 
 [ -f ./path.sh ] && . ./path.sh
-. parse_options.sh || exit 1;
+. utils/parse_options.sh || exit 1;
 
 if [ $# -ne 2 ]; then
   echo "Usage: $0 [options] <input-dir> <output-dir>"
@@ -27,8 +27,12 @@ for f in spk2gender spk2utt text utt2spk wav.scp; do
 done
 
 # Checks if sox is on the path.
-sox=`which sox`
-[ $? -ne 0 ] && "sox: command not found." && exit 1;
+#sox=`which sox`
+#[ $? -ne 0 ] && "sox: command not found." && exit 1;
+if ! sox=`which sox`; then
+  echo "sox: command not found";
+  exit 1;
+fi
 sph2pipe=$KALDI_ROOT/tools/sph2pipe_v2.5/sph2pipe
 [ ! -x $sph2pipe ] && "sph2pipe: command not found." && exit 1;
 

egs/wsj/s5/local/chain/compare_wer.sh

@@ -59,7 +59,7 @@ set_names() {
 
 
 echo -n "# System               "
-for x in $*; do   printf "% 10s" " $(basename $x)";   done
+for x in "$@"; do   printf "% 10s" " $(basename $x)";   done
 echo
 
 strings=(
@@ -74,7 +74,7 @@ strings=(
 
 for n in 0 1 2 3 4 5 6 7; do
    echo -n "${strings[$n]}"
-   for x in $*; do
+   for x in "$@"; do
      set_names $x  # sets $dirname and $epoch_infix
      decode_names=(tgpr_dev93 tg_dev93 bd_tgpr_dev93 bd_tgpr_dev93_fg tgpr_eval92 tg_eval92 bd_tgpr_eval92 bd_tgpr_eval92_fg)
 
@@ -84,7 +84,7 @@ for n in 0 1 2 3 4 5 6 7; do
    echo
    if $include_looped; then
      echo -n "#             [looped:]    "
-     for x in $*; do
+     for x in "$@"; do
        set_names $x  # sets $dirname and $epoch_infix
        wer=$(cat $dirname/decode_looped_${decode_names[$n]}/scoring_kaldi/best_wer | utils/best_wer.sh | awk '{print $2}')
        printf "% 10s" $wer
@@ -93,7 +93,7 @@ for n in 0 1 2 3 4 5 6 7; do
    fi
    if $include_online; then
      echo -n "#             [online:]    "
-     for x in $*; do
+     for x in "$@"; do
        set_names $x  # sets $dirname and $epoch_infix
        wer=$(cat ${dirname}_online/decode_${decode_names[$n]}/scoring_kaldi/best_wer | utils/best_wer.sh | awk '{print $2}')
        printf "% 10s" $wer
@@ -109,28 +109,28 @@ fi
 
 
 echo -n "# Final train prob     "
-for x in $*; do
+for x in "$@"; do
   prob=$(grep Overall $x/log/compute_prob_train.final.log | grep -v xent | awk '{printf("%.4f", $8)}')
   printf "% 10s" $prob
 done
 echo
 
 echo -n "# Final valid prob     "
-for x in $*; do
+for x in "$@"; do
   prob=$(grep Overall $x/log/compute_prob_valid.final.log | grep -v xent | awk '{printf("%.4f", $8)}')
   printf "% 10s" $prob
 done
 echo
 
 echo -n "# Final train prob (xent)"
-for x in $*; do
+for x in "$@"; do
   prob=$(grep Overall $x/log/compute_prob_train.final.log | grep -w xent | awk '{printf("%.4f", $8)}')
   printf "% 10s" $prob
 done
 echo
 
 echo -n "# Final valid prob (xent)"
-for x in $*; do
+for x in "$@"; do
   prob=$(grep Overall $x/log/compute_prob_valid.final.log | grep -w xent | awk '{printf("%.4f", $8)}')
   printf "% 10s" $prob
 done

egs/wsj/s5/local/chain/tuning/run_cnn_tdnn_1a.sh

@@ -66,7 +66,7 @@ remove_egs=true
 test_online_decoding=false  # if true, it will run the last decoding stage.
 
 # End configuration section.
-echo "$0 $@"  # Print the command line for logging
+echo "$0 $*"  # Print the command line for logging
 
 
 . ./cmd.sh
@@ -219,7 +219,7 @@ fi
 if [ $stage -le 16 ]; then
   if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $dir/egs/storage ]; then
     utils/create_split_dir.pl \
-     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/tedlium-$(date +'%m_%d_%H_%M')/s5_r2/$dir/egs/storage $dir/egs/storage
+     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/tedlium-"$(date +'%m_%d_%H_%M')"/s5_r2/$dir/egs/storage $dir/egs/storage
   fi
 
   steps/nnet3/chain/train.py --stage=$train_stage \

egs/wsj/s5/local/chain/tuning/run_cnn_tdnn_1b.sh

@@ -69,7 +69,7 @@ remove_egs=true
 test_online_decoding=false  # if true, it will run the last decoding stage.
 
 # End configuration section.
-echo "$0 $@"  # Print the command line for logging
+echo "$0 $*"  # Print the command line for logging
 
 
 . ./cmd.sh
@@ -222,7 +222,7 @@ fi
 if [ $stage -le 16 ]; then
   if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $dir/egs/storage ]; then
     utils/create_split_dir.pl \
-     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/tedlium-$(date +'%m_%d_%H_%M')/s5_r2/$dir/egs/storage $dir/egs/storage
+     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/tedlium-"$(date +'%m_%d_%H_%M')"/s5_r2/$dir/egs/storage $dir/egs/storage
   fi
 
   steps/nnet3/chain/train.py --stage=$train_stage \

egs/wsj/s5/local/chain/tuning/run_tdnn_1a.sh

@@ -82,7 +82,7 @@ remove_egs=true
 test_online_decoding=false  # if true, it will run the last decoding stage.
 
 # End configuration section.
-echo "$0 $@"  # Print the command line for logging
+echo "$0 $*"  # Print the command line for logging
 
 
 . ./cmd.sh
@@ -226,7 +226,7 @@ fi
 if [ $stage -le 16 ]; then
   if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $dir/egs/storage ]; then
     utils/create_split_dir.pl \
-     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/wsj-$(date +'%m_%d_%H_%M')/s5/$dir/egs/storage $dir/egs/storage
+     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/wsj-"$(date +'%m_%d_%H_%M')"/s5/$dir/egs/storage $dir/egs/storage
   fi
 
   steps/nnet3/chain/train.py --stage=$train_stage \

egs/wsj/s5/local/chain/tuning/run_tdnn_1b.sh

@@ -57,7 +57,7 @@ remove_egs=true
 test_online_decoding=false  # if true, it will run the last decoding stage.
 
 # End configuration section.
-echo "$0 $@"  # Print the command line for logging
+echo "$0 $*"  # Print the command line for logging
 
 
 . ./cmd.sh
@@ -201,7 +201,7 @@ fi
 if [ $stage -le 16 ]; then
   if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $dir/egs/storage ]; then
     utils/create_split_dir.pl \
-     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/wsj-$(date +'%m_%d_%H_%M')/s5/$dir/egs/storage $dir/egs/storage
+     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/wsj-"$(date +'%m_%d_%H_%M')"/s5/$dir/egs/storage $dir/egs/storage
   fi
 
   steps/nnet3/chain/train.py --stage=$train_stage \

egs/wsj/s5/local/chain/tuning/run_tdnn_lstm_1a.sh

@@ -80,7 +80,7 @@ remove_egs=true
 test_online_decoding=false  # if true, it will run the last decoding stage.
 
 # End configuration section.
-echo "$0 $@"  # Print the command line for logging
+echo "$0 $*"  # Print the command line for logging
 
 
 . ./cmd.sh
@@ -225,7 +225,7 @@ fi
 if [ $stage -le 16 ]; then
   if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $dir/egs/storage ]; then
     utils/create_split_dir.pl \
-     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/tedlium-$(date +'%m_%d_%H_%M')/s5_r2/$dir/egs/storage $dir/egs/storage
+     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/tedlium-"$(date +'%m_%d_%H_%M')"/s5_r2/$dir/egs/storage $dir/egs/storage
   fi
 
   steps/nnet3/chain/train.py --stage=$train_stage \

egs/wsj/s5/local/cstr_wsj_data_prep.sh

@@ -9,7 +9,7 @@ set -e
 # - Arnab Ghoshal, 29/05/12
 
 if [ $# -ne 1 ]; then
-  printf "\nUSAGE: %s <corpus-directory>\n\n" `basename $0`
+  printf "\nUSAGE: %s <corpus-directory>\n\n" "`basename $0`"
   echo "The argument should be a the top-level WSJ corpus directory."
   echo "It is assumed that there will be a 'wsj0' and a 'wsj1' subdirectory"
   echo "within the top-level corpus directory."
@@ -169,7 +169,7 @@ prune-lm --threshold=1e-7 $lmdir/lm_tg_5k.arpa.gz $lmdir/lm_tgpr_5k.arpa || exit
 gzip -f $lmdir/lm_tgpr_5k.arpa || exit 1;
 
 
-if [ ! -f wsj0-train-spkrinfo.txt ] || [ `cat wsj0-train-spkrinfo.txt | wc -l` -ne 134 ]; then
+if [ ! -f wsj0-train-spkrinfo.txt ] || [ "`cat wsj0-train-spkrinfo.txt | wc -l`" -ne 134 ]; then
   rm -f wsj0-train-spkrinfo.txt
   wget https://catalog.ldc.upenn.edu/docs/LDC93S6A/wsj0-train-spkrinfo.txt \
     || ( echo "Getting wsj0-train-spkrinfo.txt from backup location" && \

egs/wsj/s5/local/cstr_wsj_extend_dict.sh

@@ -14,7 +14,7 @@
 
 dict_suffix=
 
-echo "$0 $@"  # Print the command line for logging
+echo "$0 $*"  # Print the command line for logging
 . utils/parse_options.sh || exit 1;
 
 if [ $# -ne 1 ]; then
@@ -57,7 +57,7 @@ echo "Getting training data [this should take at least a few seconds; if not, th
 # oov.counts below (before adding this rule).
 
 touch $dir/cleaned.gz
-if [ `du -m $dir/cleaned.gz | cut -f 1` -eq 73 ]; then
+if [ "`du -m $dir/cleaned.gz | cut -f 1`" -eq 73 ]; then
   echo "Not getting cleaned data in $dir/cleaned.gz again [already exists]";
 else
  gunzip -c $srcdir/lng_modl/lm_train/np_data/{87,88,89}/*.z \
@@ -126,7 +126,7 @@ reverse_dict.pl $dir/f/oovs > $dir/b/oovs
 # that it finds.
 for d in $dir/f $dir/b; do
  (
-   cd $d
+   cd $d || exit 1;
    cat dict | get_rules.pl 2>get_rules.log >rules
    get_rule_hierarchy.pl rules >hierarchy
    awk '{print $1}' dict | get_candidate_prons.pl rules dict | \
@@ -165,7 +165,7 @@ head $dir/oovlist.not_handled.counts
 echo "Count of OOVs we handled is `awk '{x+=$1} END{print x}' $dir/oovlist.handled.counts`"
 echo "Count of OOVs we couldn't handle is `awk '{x+=$1} END{print x}' $dir/oovlist.not_handled.counts`"
 echo "Count of OOVs we didn't handle due to low count is" \
-    `awk -v thresh=$mincount '{if ($1 < thresh) x+=$1; } END{print x;}' $dir/oov.counts`
+    "`awk -v thresh=$mincount '{if ($1 < thresh) x+=$1; } END{print x;}' $dir/oov.counts`"
 # The two files created above are for humans to look at, as diagnostics.
 
 cat <<EOF | cat - $dir/dict.cmu $dir/dict.oovs_merged | sort | uniq > $dir/lexicon.txt

egs/wsj/s5/local/nnet3/compare_wer.sh

@@ -59,7 +59,7 @@ set_names() {
 
 
 echo -n "# System               "
-for x in $*; do   printf "% 10s" " $(basename $x)";   done
+for x in "$@"; do   printf "% 10s" " $(basename $x)";   done
 echo
 
 strings=(
@@ -74,7 +74,7 @@ strings=(
 
 for n in 0 1 2 3 4 5 6 7; do
    echo -n "${strings[$n]}"
-   for x in $*; do
+   for x in "$@"; do
      set_names $x  # sets $dirname and $epoch_infix
      decode_names=(tgpr_dev93 tg_dev93 bd_tgpr_dev93 bd_tgpr_dev93_fg tgpr_eval92 tg_eval92 bd_tgpr_eval92 bd_tgpr_eval92_fg)
 
@@ -84,7 +84,7 @@ for n in 0 1 2 3 4 5 6 7; do
    echo
    if $include_looped; then
      echo -n "#             [looped:]    "
-     for x in $*; do
+     for x in "$@"; do
        set_names $x  # sets $dirname and $epoch_infix
        wer=$(cat $dirname/decode_looped_${decode_names[$n]}$epoch_infix/scoring_kaldi/best_wer | utils/best_wer.sh | awk '{print $2}')
        printf "% 10s" $wer
@@ -93,7 +93,7 @@ for n in 0 1 2 3 4 5 6 7; do
    fi
    if $include_online; then
      echo -n "#             [online:]    "
-     for x in $*; do
+     for x in "$@"; do
        set_names $x  # sets $dirname and $epoch_infix
        wer=$(cat ${dirname}_online/decode_${decode_names[$n]}$epoch_infix/scoring_kaldi/best_wer | utils/best_wer.sh | awk '{print $2}')
        printf "% 10s" $wer
@@ -109,28 +109,28 @@ fi
 
 
 echo -n "# Final train prob     "
-for x in $*; do
+for x in "$@"; do
   prob=$(grep Overall $x/log/compute_prob_train.{final,combined}.log 2>/dev/null | grep log-like | awk '{printf("%.4f", $8)}')
   printf "% 10s" $prob
 done
 echo
 
 echo -n "# Final valid prob     "
-for x in $*; do
+for x in "$@"; do
   prob=$(grep Overall $x/log/compute_prob_valid.{final,combined}.log 2>/dev/null | grep log-like | awk '{printf("%.4f", $8)}')
   printf "% 10s" $prob
 done
 echo
 
 echo -n "# Final train acc      "
-for x in $*; do
+for x in "$@"; do
   prob=$(grep Overall $x/log/compute_prob_train.{final,combined}.log 2>/dev/null | grep accuracy | awk '{printf("%.4f", $8)}')
   printf "% 10s" $prob
 done
 echo
 
 echo -n "# Final valid acc      "
-for x in $*; do
+for x in "$@"; do
   prob=$(grep Overall $x/log/compute_prob_valid.{final,combined}.log 2>/dev/null | grep accuracy | awk '{printf("%.4f", $8)}')
   printf "% 10s" $prob
 done

egs/wsj/s5/local/nnet3/run_ivector_common.sh

@@ -57,7 +57,7 @@ if [ $stage -le 2 ]; then
   # them overwrite each other.
   mfccdir=data/${train_set}_sp_hires/data
   if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $mfccdir/storage ]; then
-    utils/create_split_dir.pl /export/b0{5,6,7,8}/$USER/kaldi-data/egs/wsj-$(date +'%m_%d_%H_%M')/s5/$mfccdir/storage $mfccdir/storage
+    utils/create_split_dir.pl /export/b0{5,6,7,8}/$USER/kaldi-data/egs/wsj-"$(date +'%m_%d_%H_%M')"/s5/$mfccdir/storage $mfccdir/storage
   fi
 
   for datadir in ${train_set}_sp ${test_sets}; do
@@ -84,7 +84,7 @@ if [ $stage -le 3 ]; then
 
   # train a diagonal UBM using a subset of about a quarter of the data
   num_utts_total=$(wc -l <data/${train_set}_sp_hires/utt2spk)
-  num_utts=$[$num_utts_total/4]
+  num_utts=$((num_utts_total/4))
   utils/data/subset_data_dir.sh data/${train_set}_sp_hires \
       $num_utts ${temp_data_root}/${train_set}_sp_hires_subset
 
@@ -120,7 +120,7 @@ if [ $stage -le 5 ]; then
   # valid for the non-'max2' data; the utterance list is the same.
   ivectordir=exp/nnet3${nnet3_affix}/ivectors_${train_set}_sp_hires
   if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $ivectordir/storage ]; then
-    utils/create_split_dir.pl /export/b0{5,6,7,8}/$USER/kaldi-data/egs/wsj-$(date +'%m_%d_%H_%M')/s5/$ivectordir/storage $ivectordir/storage
+    utils/create_split_dir.pl /export/b0{5,6,7,8}/$USER/kaldi-data/egs/wsj-"$(date +'%m_%d_%H_%M')"/s5/$ivectordir/storage $ivectordir/storage
   fi
 
   # We now extract iVectors on the speed-perturbed training data .  With

egs/wsj/s5/local/nnet3/run_lstm.sh

@@ -46,7 +46,7 @@ frames_per_chunk=
 
 #End configuration section
 
-echo "$0 $@" # Print the command line for logging
+echo "$0 $*" # Print the command line for logging
 
 . ./cmd.sh
 . ./path.sh
@@ -70,7 +70,7 @@ local/nnet3/run_ivector_common.sh --stage $stage || exit 1;
 if [ $stage -le 8 ]; then
   if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d $dir/egs/storage ]; then
     utils/create_split_dir.pl \
-     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/wsj-$(date +'%m_%d_%H_%M')/s5/$dir/egs/storage $dir/egs/storage
+     /export/b0{3,4,5,6}/$USER/kaldi-data/egs/wsj-"$(date +'%m_%d_%H_%M')"/s5/$dir/egs/storage $dir/egs/storage
   fi
 
   steps/nnet3/lstm/train.sh --stage $train_stage \

egs/wsj/s5/local/nnet3/run_lstm_discriminative.sh

@@ -119,8 +119,8 @@ fi
 model_left_context=`nnet3-am-info $srcdir/final.mdl | grep "left-context:" | awk '{print $2}'`
 model_right_context=`nnet3-am-info $srcdir/final.mdl | grep "right-context:" | awk '{print $2}'`
 
-left_context=$[model_left_context + extra_left_context]
-right_context=$[model_right_context + extra_right_context]
+left_context=$((model_left_context + extra_left_context))
+right_context=$((model_right_context + extra_right_context))
 
 frame_subsampling_opt=
 if [ -f $srcdir/frame_subsampling_factor ]; then
@@ -135,7 +135,7 @@ if [ -z "$degs_dir" ]; then
   if [ $stage -le 3 ]; then
     if [[ $(hostname -f) == *.clsp.jhu.edu ]] && [ ! -d ${srcdir}_degs/storage ]; then
       utils/create_split_dir.pl \
-        /export/b0{1,2,12,13}/$USER/kaldi-data/egs/swbd-$(date +'%m_%d_%H_%M')/s5/${srcdir}_degs/storage ${srcdir}_degs/storage
+        /export/b0{1,2,12,13}/$USER/kaldi-data/egs/swbd-"$(date +'%m_%d_%H_%M')"/s5/${srcdir}_degs/storage ${srcdir}_degs/storage
     fi
     # have a higher maximum num-jobs if
     if [ -d ${srcdir}_degs/storage ]; then max_jobs=10; else max_jobs=5; fi