Convert a Markdown transcript exported by oTranscribe to a format importable by Atlas TI.

convert-otrans.py

'''
author: Thor Galle <@th0rgall>
original version: April 3, 2020
last updated: April 9, 2020

A script to convert a Markdown transcript exported from https://otranscribe.com/ to something importable in Atlas TI v8.

USAGE: python convert-otrans.py <input_file> [output_file]

[output_file] defaults to out.txt

Note: oTranscribe text is assumed to start with a timestamp on each line

EXAMPLE
=======

Sample text before (input)
--------------
02:03 I think it's just the way it should be when it comes to.. online streaming services

02:06 T: Yes, so you've seen this before?

02:08 Uhuh. I don't know what the other buttons do though. It's like (un) .. oh ok, now I see

Sample text after (output)
------------
[00:02:03]Participant: I think it’s just the way it should be when it comes to.. online streaming services
[00:02:06]Thor: Yes, so you’ve seen this before?
[00:02:08]Participant: Uhuh. I don’t know what the other buttons do though. It’s like [unclear] .. oh ok, now I see

HOW IT WORKS
=============
This scripts works by:
1. Cleaning and transforming the oTranscribe output so that it works for Atlas TI 
2. Replacing some shorthand formulations I used with their full equivalents via regular expressions
The rules:
        T: => Thor:             (replace with your own name using the variables in the code below)
        for other lines, it inserts Participant: 
        (un) => [unclear]
        (un: is it this?) => [unclear: is it this?]

Customize as needed!

Update April 9, 2020: changed to implement specification recommendations from Atlas TI tech support
        see https://www.notion.so/thorgalle/Importing-plain-text-transcripts-into-Atlas-TI-3ee3c89ce0f94c2c9199e2e1711e57b4
        for a discussion

'''

import sys, re, traceback

TYPOGRAPHIC_SINGLE_QUOTE = '’'
TYPOGRAPHIC_DOUBLE_QUOTE_BEGIN = '“'
TYPOGRAPHIC_DOUBLE_QUOTE_BEGIN = '”'
INTERVIEWER_NAME = 'Thor'
INTERVIEWER_SHORT = 'T'
PARTICIPANT_NAME = 'Participant'
OUTPUT_DEFAULT = 'output.txt'
OTRANS_TIMESTAMP_REGEX = re.compile(r'(\d{1,2}:\d{2})')

# get the input & output files
def getFileNames():
        inputFile = None
        outputFile = OUTPUT_DEFAULT
        if (len(sys.argv) > 1):
                inputFile = sys.argv[1]
                if (len(sys.argv) > 2):
                        outputFile = sys.argv[2]
        return (inputFile, outputFile)


# rules for replacing text parts
def getReplaceTuples():
        singleQuoteR = (re.compile(r"'"), r'%s' % TYPOGRAPHIC_SINGLE_QUOTE)
        # TODO: this should converting to double quotes, but that requires more complex logic to detect start/end of a double quotation
        # and dealing with edge cases 
        doubleQuoteR = (re.compile(r'"'), TYPOGRAPHIC_SINGLE_QUOTE) 
        timeStampsR  = (OTRANS_TIMESTAMP_REGEX, r'[00:\1]')
        ampersandR  = (re.compile(r"\s?&\s?"), r' and ')
        unclearR1  = (re.compile(r'(\(un\))'), r'[unclear]')
        unclearR2  = (re.compile(r'\(un:([^\)]*)\)'), r'[unclear: \1]')
        interviewerR = (re.compile(r'(\s*%s:)' % INTERVIEWER_SHORT, re.I), r'%s:' % INTERVIEWER_NAME)
        colR = (re.compile(r'(\(collision\))'), r'[collision]')
        participantR = (re.compile(r'(\d{2}\])(\s*)(?!%s|\s)' % INTERVIEWER_NAME), r'\1%s: ' % PARTICIPANT_NAME)
        regexes = [singleQuoteR, ampersandR, doubleQuoteR, timeStampsR, unclearR1, unclearR2, interviewerR, colR, participantR]
        return regexes

def isValidLine(line):
        # empty line -> not valid
        if len(line) == 0: 
                return False
        # no timestamp -> not valid
        elif not OTRANS_TIMESTAMP_REGEX.match(line):
                return False 
        return True

def replaceLine(line):
        outLine  = line
        for i in getReplaceTuples():
                outLine = i[0].sub(i[1], outLine)
        return outLine

def main():
        (inputFile, outputFile) = getFileNames()
        with open(inputFile) as f:
                content = [line.strip() for line in f.readlines()]
                content = [replaceLine(l) for l in content if isValidLine(l)]
                with open(outputFile, 'w') as fo:
                        fo.writelines("%s\n" % l for l in content)

main()