Update extraction algorithm

    if file_name.endswith(".mmax"):

        print(file_name)

        #print(file_name)

        file_root = file_name[:-5]

    comp_count = 0

    ment_count = 0

    for line in conll:

        if line.startswith("#begin document"):

    stack = list()

    coref_stack = dict()

    for line in conll:

        if line.startswith("#begin document"):

            pass

        elif line.startswith("#end document"):

            if comp_count > 0:

                for m in mentions:

                    print(m)

            return (ment_count, comp_count, mentions)

            pass

        elif line == "\n":

            stack = list()

        else:

                    rules = list()

                    rules.append(start[3]=="JJR")

                    rules.append(text[start[0]].lower() == "more" 

                                 and len(poss) > start[0]+1 

                                 and poss[start[0]+1] == "JJ")

            word_id += 1

    return (ment_count, comp_count, mentions)

    return mentions

def to_mmax(source_path, target_directory_path):

    """ Source must be in conll format

    """

    name = os.path.splitext(os.path.basename(source_path))

    base_name = name[0]

    print("\n[NCR] Extracting entities from \033[1m{}\033[0m.".format("".join(name)))

    mentions = from_conll(source_path)

    comp_from_list = [m.comp_from for m in mentions]

    len_mentions = sum(bool(c) for c in comp_from_list)

    new_name = "{:0>2}_{}".format(len_mentions, base_name)

    if any(comp_from_list):

        mmax = open(os.path.join(target_directory_path,  new_name+".mmax"), "w")

        mmax.write("""<?xml version="1.0"?>

<mmax_project>

<!--<sentences>002_htc_text.xml</sentences>-->

<turns></turns>

<words>{}</words>

<gestures></gestures>

<keyactions></keyactions>

</mmax_project>

""".format(new_name+"_words.xml"))

        mmax.close()

        target_path = os.path.join(target_directory_path, "Basedata", new_name+"_words.xml")

        source = open(source_path, 'r')

        target = open(target_path, 'w')

        word_id = 0

        target.write(r"""<?xml version='1.0' encoding='UTF-8'?>

<!DOCTYPE words SYSTEM "words.dtd">

<words>""")

        for line in source:

            if line.startswith("#begin document"):

                pass

            elif line.startswith("#end document"):

                pass

            elif line == "\n":

                pass

            else:

                naked_line = line.strip()

                split_line = naked_line.split()

                token = split_line[3]

                if token == "&":

                    token = r"&"

                token = re.sub("<", "&lt;", token)

                token = re.sub(">", ">", token)

                target.write(r'<word id="word_'+str(word_id)+r'">'+token+r'</word>'+'\n')

                word_id += 1

        target.write(r"</words>")

        print("[NCR] Writing \033[92m{:>4}\033[0m token(s) to \033[1m{}_words.xml\033[0m.".format(word_id, new_name))

        markable_id = 0

        entity_level_path = os.path.join(target_directory_path+"Markables", new_name+"_entity_level.xml")

        entity_level = open(entity_level_path, 'w')

        entity_level.write(r"""<?xml version='1.0'?>

<!DOCTYPE markables SYSTEM "markables.dtd">

<markables xmlns="www.comp.leeds.ac.uk/markert/entity">""")

        coref_level_path = os.path.join(target_directory_path+"Markables", new_name+"_coref_level.xml")

        coref_level = open(coref_level_path, 'w')

        coref_level.write(r"""<?xml version='1.0'?>

<!DOCTYPE markables SYSTEM "markables.dtd">

<markables xmlns="www.eml.org/NameSpaces/coref">""")

        coref_chains = set()

        for mention in mentions:

            if mention.comp_from:

                entity_level.write(r'<markable id="markable_'+str(markable_id)+r'" information_status="mediated" mediated_type="comparative" comparative_type="withintext" span="word_'+str(mention.span[0])+r'..word_'+str(mention.span[1])+r'" mmax_level="entity" />'+'\n')

                markable_id += 1

            else:

                entity_level.write(r'<markable id="markable_'+str(markable_id)+r'" span="word_'+str(mention.span[0])+r'..word_'+str(mention.span[1])+r'" mmax_level="entity" />'+'\n')

                markable_id += 1

            if mention.coref_set:

                coref_chains.add(mention.coref_set)

                coref_level.write(r'<markable id="markable_'+str(markable_id)+r'" span="word_'+str(mention.span[0])+r'..word_'+str(mention.span[1])+r'" coref_set="set_'+str(mention.coref_set)+r'" mmax_level="coref" />'+'\n')

                markable_id += 1

            else:

                pass

        entity_level.write(r'</markables>')

        coref_level.write(r'</markables>')

        entity_level.close()

        coref_level.close()

        print("[NCR] Writing \033[92m{:>4}\033[0m mention(s) to \033[1m{}_entity_level.xml\033[0m.".format(len_mentions, new_name))

        print("[NCR] Writing \033[92m{:>4}\033[0m coreference chain(s) to \033[1m{}_coref_level.xml\033[0m.".format(len(coref_chains), new_name))

    else:

        print("[NCR] \033[1m{}\033[96m does not contain any comparatives.\033[0m".format(base_name))

if __name__ == "__main__":

    files = []

    for x in os.walk(root):

        for y in x[2]:

            print(y)

            #print(y)

            if y.endswith(".v4_gold_conll"):

                files.append(x[0]+"/"+y)

    mcount = 0

    ccount = 0

    dist = np.zeros(26)

    for f in files:

        plus_m, plus_c, mentions = from_conll(f)

        if plus_c > 0:

            dist[plus_c] += 1

            mcount += plus_m

            ccount += plus_c

    print(mcount, ccount)

    print(dist[1:])

        to_mmax(f, "/home/students/zimmermann/Projects/ncr/annotation/Entity/")

            return '\033[92m'+plain_repr+'\033[0m'

        else:

            return plain_repr