comparison query_textgrids.py @ 1:be28ced5c4e0 draft

planemo upload commit f36456464c692ed9d39a9cf654d09fe793113cce-dirty

0:e9c8e6204679

from __future__ import print_function
import json
import argparse
import pyalveo
import sys
import os
import tgt

API_URL = 'https://app.alveo.edu.au' # TODO: export constants to a separate module

def parser():
    parser = argparse.ArgumentParser(description="Find matching segments in a TextGrid")
    parser.add_argument('--textgrid', required=True, action="store", type=str, help="TextGrid files (comma separated)")
    parser.add_argument('--identifier', required=True, action="store", type=str, help="Dataset identifiers (comma separated)")

    tgfiles = args.textgrid.split(',')
    identifiers = args.identifier.split(',')
    assert len(tgfiles) == len(identifiers), "number of textgrids must match number of identifiers"

    pairs = zip(tgfiles, identifiers)
    
    rows = []
    for tgfile, identifier in pairs:
        tg = tgt.read_textgrid(tgfile)
        tier = tg.get_tier_by_name(args.tier)
        matches = tier.get_annotations_with_text(args.regex, regex=True)

1:be28ced5c4e0

from __future__ import print_function
import json
import argparse
import sys
import os
import tgt


def parser():
    parser = argparse.ArgumentParser(description="Find matching segments in a TextGrid")
    parser.add_argument('--textgrid', required=True, action="store", type=str, help="TextGrid files (comma separated)")
    parser.add_argument('--identifier', required=True, action="store", type=str, help="Dataset identifiers (comma separated)")

    tgfiles = args.textgrid.split(',')
    identifiers = args.identifier.split(',')
    assert len(tgfiles) == len(identifiers), "number of textgrids must match number of identifiers"

    pairs = zip(tgfiles, identifiers)

    rows = []
    for tgfile, identifier in pairs:
        tg = tgt.read_textgrid(tgfile)
        tier = tg.get_tier_by_name(args.tier)
        matches = tier.get_annotations_with_text(args.regex, regex=True)