# clear debug output of previous runs
clearinfo

form Settings
#    sentence Interval_tiers Mary John
#    sentence Point_tiers bell
#    optionmenu If_TextGrid_already_exists: 1
#        option skip the sound file
#       option create a TextGrid with a different filename
#        option open and edit the existing TextGrid
    word Sound_file_extension .wav
    comment Press OK to choose a directory of sound files to annotate.

endform

# select directory to read from
directory$ = chooseDirectory$: "Choose a directory with 'sound_file_extension$'
... files to annotate."
@getFiles: directory$, sound_file_extension$

# Create the output file and write the first line.
outputPath$ = directory$+"/formants.csv"
#appendInfoLine: outputPath$
writeFileLine: "'outputPath$'", "file,midpoint,duration,phoneme,F1_20,F1_50,F1_80,F2_20,F2_50,F2_80,F3_20,F3_50,F3_80"

# loop through files
for i to getFiles.length
    soundfile = Read from file: getFiles.files$ [i]
    @getTextGrid: getFiles.files$ [i]
     selectObject: soundfile, getTextGrid.textgrid

     # Do analysis here
     # Extract the names of the Praat objects
     thisSound$ = selected$("Sound")
     thisTextGrid$ = selected$("TextGrid")
     # Extract the number of intervals in the phoneme tier
     select TextGrid 'thisTextGrid$'
     numberOfPhonemes = Get number of intervals: 1
     appendInfoLine: "There are ", numberOfPhonemes, " intervals."

     # Create the Formant Object
     select Sound 'thisSound$'
     To Formant (burg)... 0 5 5000 0.025 50
     # Loop through each interval on the phoneme tier.
     for thisInterval from 1 to numberOfPhonemes
         #appendInfoLine: thisInterval

         # Get the label of the interval
         select TextGrid 'thisTextGrid$'
         thisPhoneme$ = Get label of interval: 1, thisInterval
         # check for monophthongs
	# can't do this elegantly due to the limits of Praat Scripts
	#monophthongs$# = { "AA", "AE" }
	#if index_regex (thisPhoneme$, "(AA|AE)")
	#lexical_set$ = "a1|a2|a3|a4|a5|aa|ai1|ai2|ai3|ai4|ai5|an1|an2|an3|an4|an5|ang1|ang2|ang3|ang4|ang5|ao1|ao2|ao3|ao4|ao5|b|c|ch|d|e1|e2|e3|e4|e5|ee|ei1|ei2|ei3|ei4|ei5|en1|en2|en3|en4|en5|eng1|eng2|eng3|eng4|eng5|er2|er3|er4|er5|f|g|h|i1|i2|i3|i4|i5|ia1|ia2|ia3|ia4|ia5|ian1|ian2|ian3|ian4|ian5|iang1|iang2|iang3|iang4|iang5|iao1|iao2|iao3|iao4|iao5|ie1|ie2|ie3|ie4|ie5|ii|in1|in2|in3|in4|in5|ing1|ing2|ing3|ing4|ing5|iong1|iong2|iong3|iong4|iong5|iu1|iu2|iu3|iu4|iu5|ix1|ix2|ix3|ix4|ix5|iy1|iy2|iy3|iy4|iy5|iz4|iz5|j|k|l|m|n|o1|o2|o3|o4|o5|ong1|ong2|ong3|ong4|ong5|oo|ou1|ou2|ou3|ou4|ou5|p|q|r|s|sh|t|u1|u2|u3|u4|u5|ua1|ua2|ua3|ua4|ua5|uai1|uai2|uai3|uai4|uai5|uan1|uan2|uan3|uan4|uan5|uang1|uang2|uang3|uang4|uang5|ueng1|ueng3|ueng4|ueng5|ui1|ui2|ui3|ui4|ui5|un1|un2|un3|un4|un5|uo1|uo2|uo3|uo4|uo5|uu|v1|v2|v3|v4|v5|van1|van2|van3|van4|van5|ve1|ve2|ve3|ve4|ve5|vn1|vn2|vn3|vn4|vn5|vv|x|z|zh"
	#lexical_set$= "AA|AE|AH|AO|AW|AX|AY|EH|ER|EY|IH|IX|IY|OW|OY|UH|UW|UX"
	lexical_set$="AH|IH|IY|ER|EH|AE|AA|AO|UW|UH"
	if index_regex (thisPhoneme$, "'lexical_set$'")
	#if startsWith(thisPhoneme$, "AA") = 1 or startsWith(thisPhoneme$, "AE") = 1 

         	#appendInfoLine: thisPhoneme$
    
	         # Find the midpoint.
		# we're using proportional distance now (20, 50, 80 percent duration) 
	         thisPhonemeStartTime = Get start point: 1, thisInterval
	         thisPhonemeEndTime   = Get end point:  1, thisInterval
	         duration = thisPhonemeEndTime - thisPhonemeStartTime
		point20 = thisPhonemeStartTime + 0.2 * duration
		point80 = thisPhonemeStartTime + 0.8 * duration
	         point50 = thisPhonemeStartTime + duration/2
    
	         # Extract formant measurements
	         select Formant 'thisSound$'
	        f1_20 = Get value at time... 1 point20 Hertz Linear
		f1_50 = Get value at time... 1 point50 Hertz Linear
		f1_80 = Get value at time... 1 point80 Hertz Linear
		f2_20 = Get value at time... 2 point20 Hertz Linear
		f2_50 = Get value at time... 2 point50 Hertz Linear
		f2_80 = Get value at time... 2 point80 Hertz Linear
		f3_20 = Get value at time... 3 point20 Hertz Linear
		f3_50 = Get value at time... 3 point50 Hertz Linear
		f3_80 = Get value at time... 3 point80 Hertz Linear
	         #f2 = Get value at time... 2 midpoint Hertz Linear
	         #f3 = Get value at time... 3 midpoint Hertz Linear

	         # Get the word interval and then the label
	         select TextGrid 'thisTextGrid$'
	         # thisWordInterval = Get interval at time: 1, point50
	         # thisWord$ = Get label of interval: 1, thisWordInterval

	         # Save to a spreadsheet
	         appendFileLine: "'outputPath$'", 
			    ...thisSound$, ",",
			    ...point50, ",",
			    ...duration, ",",
			    ...thisPhoneme$, ",",
			    ...f1_20, ",", 
			    ...f1_50, ",", 
			    ...f1_80, ",", 
			    ...f2_20, ",", 
			    ...f2_50, ",", 
			    ...f2_80, ",", 
			    ...f3_20, ",", 
			    ...f3_50, ",", 
			    ...f3_80
#			    ...f2, ",", 
#			    ...f3
	endif

     endfor
     # This is stupid, but I don't know a better way to remove the formant object
     select Formant 'thisSound$'
     Remove
     removeObject: getTextGrid.textgrid
     removeObject: soundfile
endfor



procedure getTextGrid: .soundfile$
    .path$ = replace$: .soundfile$, sound_file_extension$, ".TextGrid", 0
    .textgrid = Read from file: .path$
endproc

procedure getFiles: .dir$, .ext$
    .obj = Create Strings as file list: "files", .dir$ + "/*" + .ext$
    .length = Get number of strings

    for .i to .length
        .fname$ = Get string: .i
        .files$ [.i] = .dir$ + "/" + .fname$

    endfor

    removeObject: .obj

endproc