#################################################### # count-tokens-in-TextGrid-and-romanized-text.praat #################################################### romanizedText$ = "alltext.out.dialect" textgridFolder$ = "tg" outFile$ = "compare-token-counts.txt" Read Strings from raw text file... 'romanizedText$' Rename... romTextObj numLines = Get number of strings Create Strings as file list... textgridListObj 'textgridFolder$'/*.TextGrid Sort numFiles = Get number of strings if numLines <> numFiles exit numLines and numFiles do not match! endif for iLine to numLines select Strings romTextObj lineText$ = Get string... iLine tokenCount = 0 indexOfSpace = index(lineText$," ") lenLineText = length(lineText$) while (indexOfSpace <>0) tokenCount = tokenCount + 1 lineText$ = right$(lineText$,(lenLineText-indexOfSpace)) lenLineText = length(lineText$) indexOfSpace = index(lineText$," ") endwhile tokenCount = tokenCount + 1 textgridName$ = Get string... iLine Read from file... 'textgridFolder$'/'textgridName$' Rename... textgridObj numIntervals = Get number of intervals... 1 Remove tokenCount2 = numIntervals -2 if tokenCount = tokenCount2 status$ = "same" else status$ = "DIFFERENT" endif fileappend 'outFile$' 'iLine''tab$''textgridName$''tab$' ...'tokenCount''tab$''tokenCount2''tab$''status$''newline$' endfor select Strings romTextObj plus Strings textgridListObj Remove ########## END