import os
import sys

import numpy as np
import pypyodbc


## user define
forced_alignment_module = 'C:\\Users\\Aki\\source\\repos\\forced-alignment'
dir_same_utterance = 'd:\\OneDrive\\Research\\rug\\experiments\\same_utterance'
wav_dir      = dir_same_utterance + '\\wav_with_cities'
script_dir   = dir_same_utterance + '\\script'
fileMDB		 = dir_same_utterance + '\\feature\\DialectClassification.accdb'
table		 = 'ForcedAlignmentResult'
regionLabels = ['Groningen_and_Drenthe', 'Limburg', 'Oost_Overijsel-Gelderland']

# these lines are not necessary once forced-alignment is intalled as a package.
sys.path.append(forced_alignment_module)
from forced_alignment import forced_alignment


## delete all automatically generated pronunciations
#from forced_alignment import pronunciations
#pronunciations.delete_all_g2p_entries()


## make database connection
param = r"Driver={Microsoft Access Driver (*.mdb, *.accdb)};dbq=" + fileMDB + ";"
conn = pypyodbc.connect(param)
cursor = conn.cursor()

SQLstring1 = 'INSERT INTO ' + table + ' (filename, region, word_id, pronunciation) '


## forced-alignment to all the wav files in dir_same_utterance  
word_id_start = 1
for sentenceID in range(1, 11):
	sentenceIDstr = format(sentenceID, '02')

	# get script
	script_file = script_dir + '\\script' + sentenceIDstr + '.txt'
	with open(script_file, 'r') as fin:
		script = fin.readline()

		# loop over three regions
		for region in regionLabels:
			
			# loop over the wav_subdir
			wav_subdir = wav_dir + '\\' + sentenceIDstr + '\\' + region
			wav_files = os.listdir(wav_subdir)
			file_nr = 0
			for wav_file in wav_files:
				file_nr += 1
				filename = wav_file.replace('.wav', '')
				wav_file_fullpath = wav_subdir + '\\' + wav_file

				# forced-alignment
				print('{0} {1}: {2} ({3}/{4})'.format(sentenceIDstr, region, wav_file, file_nr, len(wav_files)))
				fa = forced_alignment(wav_file_fullpath, script)

				# send pronunciation variant to database
				word_id = word_id_start
				for row	in fa:
					word	 = row[0]
					phonemes = np.array(row[1])

					## get pronunciation variant
					pronvar_ = phonemes[:, 2]
					pronvar_[np.where(pronvar_=='ssil')]='' # remove 'ssil'
					pronvar = ''.join(pronvar_)

					## insert the result into the database.  
					SQLstring2 = 'VALUES (\'' + filename + '\',\'' + region + '\',\'' + str(word_id) + '\',\'' + pronvar + '\')'
					SQLstring  = SQLstring1 + SQLstring2 
					cursor.execute(SQLstring)
					conn.commit()

					word_id = word_id + 1
	
	word_id_start += script.count(' ')+1

conn.close()