main.py

from parse_nouns import parse_nouns
from parse_verbs import parse_verbs
import codecs
import xml.etree.ElementTree as ET


def writeOpening(filename):
    with codecs.open(filename, 'w', encoding="utf8") as fd:
        fd.write("lexiconAncora{\n")
    fd.close()


def writeEnding(filename):
    with codecs.open(filename, 'a', encoding="utf8") as fd:
        fd.write("}\n")
    fd.close()


def get_nouns():
    filename = 'UPF_AncoraDict_nouns.dic'
    roots = parse_nouns.getRoot()
    with open(filename, 'w') as fd:
        fd.write("lexiconAncora{\n")
    for root in roots:
        senses = parse_nouns.parseXML(root)
        for sense in senses:
            with open(filename, 'a') as fd:
                fd.write(sense.__str__().decode("utf-8"))
    with open(filename, 'a') as fd:             
        fd.write('}\n')


def get_verbs(path):
    if 'CAT' in path:
        language = '_CA'
        ancoranet_path = path+'ancoranet-ca.xml'
        files_path = path+'ancora-verb-ca/'
    else:
        language = ''
        ancoranet_path = path+'ancoranet-es.xml'
        files_path = path+'ancora-verb-es/'

    filename = 'UPF_AncoraDict_verbs{}.dic'.format(language)
    roots = parse_verbs.getRoot(files_path)
    root = ET.parse(ancoranet_path).getroot()
    map = parse_verbs.getAncoraInfo(root)

    with open(filename, 'w') as fd:
        fd.write("lexiconAncora{\n")
    for root_lex in roots:
        senses = parse_verbs.getSenses(root_lex, map)
        for sense in senses:
            try:
                if sense is not None:
                    with open(filename, 'a') as fd:
                        fd.write(sense.__str__().decode("utf-8"))
            except:
                if sense is not None:
                    with open(filename, 'a') as fd:
                        fd.write(sense.__str__())
    writeEnding(filename)


if __name__ == '__main__':
    language = input("Enter CAT or ES: ")
    path = 'Resources/OriginalFiles/{}/'.format(language)
    to_process = input("Enter noun or verb: ")
    if to_process == 'noun':
        if language == 'CAT':
            print('[ERROR] Nouns not available in catalan.')
        get_nouns()
    if to_process == 'verb':
        get_verbs(path)