#!/bin/sh
# Veskslop TTS command-provider wrapper for MicroslopSam.
#
# Recommended Veskslop configuration:
#   VESKSLOP_TTS_CMD="<repo>/setup/vekslop-tts.sh {out} {text_file}"
#   VESKSLOP_TTS_VOICES="$(setup/vekslop-tts.sh --voices)"
#
# Inputs:
#   $1 {out}        output WAV path
#   $2 {text_file}  UTF-8 text file
#   $3...           optional: voice id, speed multiplier, pitch semitones
#   env             VESKSLOP_TTS_VOICE, VESKSLOP_TTS_SPEED, VESKSLOP_TTS_PITCH
#
# Output: 48 kHz mono s16le WAV, trimmed, faded, loudness-normalized.
set -eu

HERE=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
ROOT=$(CDPATH= cd -- "$HERE/.." && pwd)
export WINEPREFIX=${WINEPREFIX:-$HOME/.wine-microslopsam}
export WINEARCH=win32

# VESKSLOP_TTS_VOICES entries: id|Name|gender|language[|flags]
# `no-pitch` marks voices whose engine ignores pitch (Flextalk).
VOICES="sam|Sam|male|en,mary|Mary|female|en,mike|Mike|male|en,keith-bell|Keith Bell|male|en|no-pitch,kerry-watson|Kerry Watson|female|en|no-pitch,mike-telephone|Mike (for Telephone)|male|en,mary-telephone|Mary (for Telephone)|female|en,mike-hall|Mike in Hall|male|en,mike-stadium|Mike in Stadium|male|en,mike-space|Mike in Space|male|en,mary-hall|Mary in Hall|female|en,mary-stadium|Mary in Stadium|female|en,mary-space|Mary in Space|female|en"

if [ "${1:-}" = "--voices" ]; then
    echo "$VOICES"
    exit 0
fi

OUT=${1:?missing out path}
TEXTFILE=${2:?missing text file}
VOICE=${VESKSLOP_TTS_VOICE:-${3:-sam}}
SPEED=${VESKSLOP_TTS_SPEED:-${4:-}}
PITCH=${VESKSLOP_TTS_PITCH:-${5:-}}

case "$VOICE" in
    sam)            ENGVOICE="Sam" ;;
    mary)           ENGVOICE="Mary" ;;
    mike)           ENGVOICE="Mike" ;;
    keith-bell)     ENGVOICE="Keith Bell" ;;
    kerry-watson)   ENGVOICE="Kerry Watson" ;;
    mike-telephone) ENGVOICE="Mike (for Telephone)" ;;
    mary-telephone) ENGVOICE="Mary (for Telephone)" ;;
    mike-hall)      ENGVOICE="Mike in Hall" ;;
    mike-stadium)   ENGVOICE="Mike in Stadium" ;;
    mike-space)     ENGVOICE="Mike in Space" ;;
    mary-hall)      ENGVOICE="Mary in Hall" ;;
    mary-stadium)   ENGVOICE="Mary in Stadium" ;;
    mary-space)     ENGVOICE="Mary in Space" ;;
    *)              ENGVOICE="Sam" ;;
esac

# Engine units. Measured naturals: MSTTS ~150, Flextalk ~300 (words/min scale).
# Flextalk ignores ITTSAttributes pitch (verified byte-identical output).
case "$ENGVOICE" in
    "Keith Bell"|"Kerry Watson") NAT_SPEED=300; SMAX=390 ;;
    *)                           NAT_SPEED=150; SMAX=450 ;;
esac
SET_ARGS=""
if [ -n "$SPEED" ]; then
    S=$(awk -v m="$SPEED" -v n="$NAT_SPEED" 'BEGIN{printf "%d", n*m+0.5}')
    [ "$S" -lt 50 ] && S=50
    [ "$S" -gt "$SMAX" ] && S=$SMAX
    SET_ARGS="$SET_ARGS -s $S"
fi
if [ -n "$PITCH" ]; then
    case "$ENGVOICE" in
        "Keith Bell"|"Kerry Watson") : ;;
        *)
            P=$(awk -v st="$PITCH" 'BEGIN{printf "%d", 100 + st*6.25}')
            [ "$P" -lt 50 ] && P=50
            [ "$P" -gt 200 ] && P=200
            SET_ARGS="$SET_ARGS -p $P" ;;
    esac
fi

# The daemon does not export DISPLAY; keep a private Xvfb for the engine.
if [ -z "${DISPLAY:-}" ]; then
    if ! [ -S /tmp/.X11-unix/X77 ]; then
        Xvfb :77 -screen 0 1024x768x24 >/dev/null 2>&1 &
        sleep 1
    fi
    export DISPLAY=:77
fi

TMP=$(mktemp -d)
trap 'rm -rf "$TMP"' EXIT
RAW="$TMP/raw.wav"
TXT="$TMP/text.cp1252"

# SAPI4 is ANSI/CP1252; transliterate UTF-8 (emoji become '?').
if command -v iconv >/dev/null 2>&1; then
    iconv -f UTF-8 -t WINDOWS-1252//TRANSLIT "$TEXTFILE" > "$TXT" 2>/dev/null \
        || cp "$TEXTFILE" "$TXT"
else
    cp "$TEXTFILE" "$TXT"
fi

HOST="$ROOT/build/sapi4host-winlib.exe"
if [ ! -x "$HOST" ]; then HOST="$ROOT/build/sapi4host.exe"; fi
if [ ! -x "$HOST" ]; then echo "engine host not built" >&2; exit 1; fi
if ! command -v ffmpeg >/dev/null 2>&1; then echo "ffmpeg not found" >&2; exit 1; fi

# shellcheck disable=SC2086
if ! "$HOST" -v "$ENGVOICE" -t "$(cat "$TXT")" -o "$RAW" $SET_ARGS \
        >/dev/null 2>"$TMP/err"; then
    head -c 400 "$TMP/err" >&2
    exit 1
fi
[ -s "$RAW" ] || { echo "engine produced no audio" >&2; exit 1; }

SIL="silenceremove=start_periods=1:start_duration=0.05:start_silence=0.03:start_threshold=-50dB"
PRE="highpass=f=40,$SIL,afade=t=in:st=0:d=0.008,areverse,$SIL,afade=t=in:st=0:d=0.008,areverse"
LN="loudnorm=I=-16:TP=-3:LRA=11"

# Two-pass loudnorm: measure first, then apply with the measured values.
M=$(ffmpeg -hide_banner -nostats -i "$RAW" -af "$PRE,$LN:print_format=json" \
        -f null - 2>&1 || true)
I=$(printf '%s' "$M" | sed -n 's/.*"input_i" *: *"\([^"]*\)".*/\1/p')
TP=$(printf '%s' "$M" | sed -n 's/.*"input_tp" *: *"\([^"]*\)".*/\1/p')
LRA=$(printf '%s' "$M" | sed -n 's/.*"input_lra" *: *"\([^"]*\)".*/\1/p')
TH=$(printf '%s' "$M" | sed -n 's/.*"input_thresh" *: *"\([^"]*\)".*/\1/p')
OFF=$(printf '%s' "$M" | sed -n 's/.*"target_offset" *: *"\([^"]*\)".*/\1/p')
if [ -n "$I" ] && [ -n "$TP" ] && [ -n "$LRA" ] && [ -n "$TH" ] && [ -n "$OFF" ]; then
    LN="$LN:measured_I=$I:measured_TP=$TP:measured_LRA=$LRA:measured_thresh=$TH:offset=$OFF:linear=true"
fi

TMPOUT="$TMP/out.wav"
if ! ffmpeg -hide_banner -nostats -y -i "$RAW" -af "$PRE,$LN" \
        -ar 48000 -ac 1 -c:a pcm_s16le "$TMPOUT" >/dev/null 2>"$TMP/ff"; then
    head -c 400 "$TMP/ff" >&2
    exit 1
fi
[ -s "$TMPOUT" ] || { echo "post-processing produced no audio" >&2; exit 1; }
mv -f "$TMPOUT" "$OUT"