#!/usr/bin/env python

import argparse
import audioop
import goslate
import json
import logging
import math
import multiprocessing
import os
import requests
import subprocess
import sys
import tempfile
import wave

from progressbar import ProgressBar, Percentage, Bar, ETA

from autosub.constants import SOURCE_LANGUAGES, DESTINATION_LANGUAGES, \
                              GOOGLE_SPEECH_API_KEY, GOOGLE_SPEECH_API_URL
from autosub.formatters import FORMATTERS

translator = goslate.Goslate()

def percentile(arr, percent):
    arr = sorted(arr)
    k = (len(arr)-1) * percent
    f = math.floor(k)
    c = math.ceil(k)
    if f == c: return arr[int(k)]
    d0 = arr[int(f)] * (c-k)
    d1 = arr[int(c)] * (k-f)
    return d0+d1

def is_same_language(lang1, lang2):
    return lang1.split("-")[0] == lang2.split("-")[0]

class FLACConverter(object):
    def __init__(self, source_path, include_before=0.25, include_after=0.25):
        self.source_path = source_path
        self.include_before = include_before
        self.include_after = include_after

    def __call__(self, region):
        try:
            start, end = region
            start = max(0, start-self.include_before)
            end += self.include_after
            temp = tempfile.NamedTemporaryFile(suffix='.flac')
            command = ["ffmpeg", "-y", "-i", self.source_path,
                       "-ss", str(start), "-t", str(end-start),
                       "-loglevel", "error", temp.name]
            subprocess.check_output(command)
            return temp.read()

        except KeyboardInterrupt:
            return

class SpeechRecognizer(object):
    def __init__(self, language="en-US", rate=44100, retries=3, api_key=GOOGLE_SPEECH_API_KEY):
        self.language = language
        self.rate = rate
        self.api_key = api_key
        self.retries = retries

    def __call__(self, data):
        try:
          for i in range(self.retries):
              url = GOOGLE_SPEECH_API_URL.format(lang=self.language, key = self.api_key)
              headers = {"Content-Type": "audio/x-flac; rate=%d" % self.rate}
  
              try:
                  resp = requests.post(url, data=data, headers=headers)
              except requests.exceptions.ConnectionError:
                  continue
  
              for line in resp.content.split("\n"):
                  try:
                      line = json.loads(line)
                      return line['result'][0]['alternative'][0]['transcript'].capitalize()
                  except:
                      # no result
                      continue

        except KeyboardInterrupt:
            return

class Translator(object):
    def __init__(self, language):
        self.language = language

    def __call__(self, sentence):
        try:
            if not sentence: return
            return translator.translate(sentence, self.language).encode("utf8")

        except KeyboardInterrupt:
            return

def extract_audio(filename, channels=2, rate=16000):
    temp = tempfile.NamedTemporaryFile(suffix='.wav', delete=False)
    command = ["ffmpeg", "-y", "-i", filename, "-ac", str(channels), "-ar", str(rate), "-loglevel", "error", temp.name]
    subprocess.check_output(command)
    return temp.name, rate

def find_speech_regions(filename, frame_width=4096, min_region_size=0.5, max_region_size=6):
    reader = wave.open(filename)
    sample_width = reader.getsampwidth()
    rate = reader.getframerate()
    n_channels = reader.getnchannels()

    total_duration = reader.getnframes() / rate
    chunk_duration = float(frame_width) / rate

    n_chunks = int(total_duration/chunk_duration)
    energies = []

    for i in range(n_chunks):
        chunk = reader.readframes(frame_width)
        energies.append(audioop.rms(chunk, sample_width * n_channels))

    threshold = percentile(energies, 0.2)

    elapsed_time = 0

    regions = []
    region_start = None

    for energy in energies:
        elapsed_time += chunk_duration
        
        is_silence = energy <= threshold
        max_exceeded = region_start and elapsed_time-region_start >= max_region_size

        if (max_exceeded or is_silence) and region_start:
            if elapsed_time-region_start >= min_region_size:
                regions.append((region_start, elapsed_time))
            region_start = None

        elif (not region_start) and (not is_silence):
            region_start = elapsed_time

    return regions

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('source_path', help="Path to the video or audio file to subtitle")
    parser.add_argument('-C', '--concurrency', help="Number of concurrent API requests to make", type=int, default=10)
    parser.add_argument('-o', '--output', help="Output path for subtitles (by default, subtitles are saved in the same directory and name as the source path)")
    parser.add_argument('-F', '--format', help="Destination subtitle format", default="srt")
    parser.add_argument('-S', '--src-language', help="Language spoken in source file", default="en-US")
    parser.add_argument('-D', '--dst-language', help="Desired language for the subtitles", default="en")
    parser.add_argument('--list-formats', help="List all available subtitle formats", action='store_true')
    parser.add_argument('--list-src-languages', help="List all available source languages", action='store_true')
    parser.add_argument('--list-dst-languages', help="List all available destination languages", action='store_true')

    args = parser.parse_args()

    if args.list_formats:
        print("List of formats:")
        for subtitle_format in FORMATTERS.keys():
            print("\t{format}".format(format=subtitle_format))
        return 0

    if args.list_src_languages:
        print("List of source languages:")
        for code, language in SOURCE_LANGUAGES.items():
            print("{code}\t{language}".format(code=code, language=language))
        return 0

    if args.list_dst_languages:
        print("List of output languages:")
        for code, language in DESTINATION_LANGUAGES.items():
            print("{code}\t{language}".format(code=code, language=language))
        return 0

    if args.format not in FORMATTERS.keys():
        print("Subtitle format not supported. Run with --list-formats to see all supported formats.")
        return 1

    if args.src_language not in SOURCE_LANGUAGES.keys():
        print("Source language not supported. Run with --list-source-languages to see all supported languages.")
        return 1

    if args.dst_language not in DESTINATION_LANGUAGES.keys():
        print("Destination language not supported. Run with --list-destination-languages to see all supported languages.")
        return 1

    audio_filename, audio_rate = extract_audio(args.source_path)

    regions = find_speech_regions(audio_filename)

    pool = multiprocessing.Pool(args.concurrency)
    converter = FLACConverter(source_path=audio_filename)
    recognizer = SpeechRecognizer(language=args.src_language, rate=audio_rate)
    translator = Translator(args.dst_language)

    try:
        widgets=["Converting speech regions to FLAC files: ", Percentage(), ' ', Bar(), ' ', ETA()]
        pbar = ProgressBar(widgets=widgets, maxval=len(regions)).start()
        extracted_regions = []
        for i, extracted_region in enumerate(pool.imap(converter, regions)):
            extracted_regions.append(extracted_region)
            pbar.update(i)
        pbar.finish()

        widgets=["Performing speech recognition: ", Percentage(), ' ', Bar(), ' ', ETA()]        
        pbar = ProgressBar(widgets=widgets, maxval=len(regions)).start()
        transcripts = []
        for i, transcript in enumerate(pool.imap(recognizer, extracted_regions)):
            transcripts.append(transcript)
            pbar.update(i)
        pbar.finish()

        if not is_same_language(args.src_language, args.dst_language):
            prompt = "Translating from {0} to {1}: ".format(args.src_language, args.dst_language)
            widgets=[prompt, Percentage(), ' ', Bar(), ' ', ETA()]
            pbar = ProgressBar(widgets=widgets, maxval=len(regions)).start()
            translated_transcripts = []
            for i, transcript in enumerate(pool.imap(translator, transcripts)):
                translated_transcripts.append(transcript)
                pbar.update(i)
            pbar.finish()
            transcripts = translated_transcripts

    except KeyboardInterrupt:
        pbar.finish()
        pool.terminate()
        pool.join()
        print "Cancelling transcription"
        sys.exit(1)

    timed_subtitles = [(r, t) for r, t in zip(regions, transcripts) if t]
    formatter = FORMATTERS.get(args.format)
    formatted_subtitles = formatter(timed_subtitles)

    dest = args.output
            
    if not dest:
        base, ext = os.path.splitext(args.source_path)
        dest = "{base}.{format}".format(base=base, format=args.format)

    open(dest, 'wb').write(formatted_subtitles)

    print "Subtitles file created at {}".format(dest)

    os.remove(audio_filename)

    return 0

if __name__ == '__main__':
    sys.exit(main())

