#!/bin/bash
INITIAL_MEMORY=${INITIAL_MEMORY:-315mb}
MAX_THREADS=${MAX_THREADS:-1}
EMSDK=${EMSDK:-../emsdk}
JOBS=${JOBS:-$(nproc)}

if [ "$EMSDK" != ../emsdk ] && [ ! -d "$EMSDK" ]; then
  echo "Invalid emsdk path"
  exit 1
fi
if [ "$MAX_THREADS" -lt 1 ]; then
  echo "MAX_THREADS must be greater than or equal to 1"
  exit 1
fi
if [ "$JOBS" -lt 1 ]; then
  echo "JOBS must be greater than or equal to 1"
  exit 1
fi
if ! [[ $INITIAL_MEMORY =~ ^[0-9]+([kmgt]b)?$ ]]; then
  echo "INITIAL_MEMORY valid suffixes are kb, mb, gb, tb, none (bytes)"
  exit 1
fi
if [ "$EMSDK" = ../emsdk ] && [ ! -d "$EMSDK" ]; then
  echo "Installing emsdk + Emscripten..."
  git clone --depth=1 https://github.com/emscripten-core/emsdk.git ../emsdk &&
  cd ../emsdk &&
  ./emsdk install 3.1.67 &&
  ./emsdk activate 3.1.67
fi
. $(realpath "$EMSDK")/emsdk_env.sh &&
export PATH=:$PATH:$(realpath "$EMSDK")/upstream/bin &&

cd .. &&
SRC=$(realpath src)
KALDI=$(realpath kaldi)
VOSK=$(realpath vosk)
OPENFST=$(realpath openfst)
CLAPACK_WASM=$(realpath clapack-wasm)

if [ ! -d "$OPENFST" ]; then
  rm -rf /tmp/openfst &&
  git clone --depth=1 https://github.com/alphacep/openfst /tmp/openfst &&
  cd /tmp/openfst &&
  autoreconf -is &&
  CXXFLAGS="-r -O3 -fno-rtti -flto -msimd128 -matomics -mbulk-memory -mreference-types -mnontrapping-fptoint -mextended-const -msign-ext -mmutable-globals -flto" emconfigure ./configure --prefix="$OPENFST" --enable-static --disable-shared --enable-lookahead-fsts --enable-ngram-fsts --disable-bin &&
  emmake make -j"$JOBS" install &&
  echo "PACKAGE_VERSION = 1.8.0" >> "$OPENFST"/Makefile
fi

if [ ! -d "$CLAPACK_WASM" ]; then
  git clone --depth=1 https://gitlab.inria.fr/multispeech/kaldi.web/clapack-wasm.git "$CLAPACK_WASM" &&
  cd "$CLAPACK_WASM" &&
  git apply "$SRC"/Clapack-wasm.patch &&
  bash install_repo.sh emcc
fi

if [ ! -d "$KALDI" ]; then
  git clone -b vosk --depth=1 https://github.com/alphacep/kaldi "$KALDI" &&
  cd "$KALDI"/src &&
  git apply "$SRC"/Kaldi.patch &&
  CXXFLAGS="-O3 -UHAVE_EXECINFO_H -DEMSCRIPTEN_HAS_UNBOUND_TYPE_NAMES=0 -flto -msimd128 -matomics -mbulk-memory -mreference-types -mnontrapping-fptoint -mextended-const -msign-ext -mmutable-globals -Wno-unused-variable -Wno-unused-but-set-variable -g0" LDFLAGS="-lembind" emconfigure ./configure --use-cuda=no --with-cudadecoder=no --static --static-math=yes --static-fst=yes --debug-level=0 --fst-root="$OPENFST" --clapack-root="$CLAPACK_WASM" --host=WASM &&
  emmake make -j"$JOBS" online2 rnnlm
fi

if [ ! -d "$VOSK" ]; then
  git clone -b v0.3.50 --depth=1 https://github.com/alphacep/vosk-api "$VOSK" &&
  cd "$VOSK"/src &&
  git apply "$SRC"/Vosk.patch &&
  VOSK_FILES="recognizer.cc language_model.cc model.cc spk_model.cc vosk_api.cc" &&
  em++ -O3 -flto -msimd128 -matomics -mbulk-memory -mreference-types -mnontrapping-fptoint -mextended-const -msign-ext -mmutable-globals -Wno-deprecated -I. -I"$KALDI"/src -I"$OPENFST"/include $VOSK_FILES -c &&
  emar -rcs vosk.a ${VOSK_FILES//.cc/.o}
fi

cd "$SRC" &&
  em++ Util.cc CommonModel.cc Recognizer.cc Bindings.cc -O3 -DEMSCRIPTEN_HAS_UNBOUND_TYPE_NAMES=0 -fno-rtti -DMAX_WORKERS="$MAX_THREADS" -sWASMFS -sWASM_BIGINT -sMODULARIZE -sWASM_EXNREF -sTEXTDECODER=2 -sWASM_WORKERS=2 -sEVAL_CTORS=2 -sINITIAL_MEMORY="$INITIAL_MEMORY" -sALLOW_MEMORY_GROWTH -sPOLYFILL=0 -sEXIT_RUNTIME=0 -sINVOKE_RUN=0 -sSUPPORT_LONGJMP=0 -sEXPORTED_FUNCTIONS=_malloc -sEXPORT_NAME=loadVosklet -sMALLOC=emmalloc -sEXPORTED_RUNTIME_METHODS=UTF8ToString -sENVIRONMENT=web,worker -I. -I"$VOSK"/src -L"$KALDI"/src -l:online2/kaldi-online2.a -l:decoder/kaldi-decoder.a -l:ivector/kaldi-ivector.a -l:gmm/kaldi-gmm.a -l:tree/kaldi-tree.a -l:feat/kaldi-feat.a -l:cudamatrix/kaldi-cudamatrix.a -l:lat/kaldi-lat.a -l:lm/kaldi-lm.a -l:rnnlm/kaldi-rnnlm.a -l:hmm/kaldi-hmm.a -l:nnet3/kaldi-nnet3.a -l:transform/kaldi-transform.a -l:matrix/kaldi-matrix.a -l:fstext/kaldi-fstext.a -l:util/kaldi-util.a -l:base/kaldi-base.a -L"$OPENFST"/lib -l:libfst.a -l:libfstngram.a -L"$CLAPACK_WASM" -l:CBLAS/lib/cblas.a -l:CLAPACK-3.2.1/lapack.a -l:CLAPACK-3.2.1/libcblaswr.a -l:f2c_BLAS-3.8.0/blas.a -l:libf2c/libf2c.a -L"$VOSK"/src -l:vosk.a -lembind -flto -msimd128 -matomics -mbulk-memory -mreference-types -mnontrapping-fptoint -mextended-const -msign-ext -mmutable-globals --pre-js Wrapper.js -o ../Vosklet.js
cd .. &&
rm -f Vosklet.worker.js

cp Vosklet.js Examples/Vosklet.js &&
cp Vosklet.wasm Examples/Vosklet.wasm &&

# Can't serve files from raw.githubusercontent with Content-Encoding: gzip header so the browser won't decompress automatically. Manually decompressing instead.
sed -i 's/.pipeThrough(new CompressionStream("gzip"))//;s/teed\[1\]/teed[1].pipeThrough(new DecompressionStream("gzip"))/' Examples/Vosklet.js &&

rm -rf /tmp/openfst