systems/parse_turku.py

# TODO: write a client to make multiple requests to the server!
import subprocess, json, time
import requests, glob, logging
import os.path, sys
from lib.CoNLL_Annotation import get_token_type
import my_utils.file_utils as fu
import argparse


if __name__ == "__main__":
    
    """
    EXECUTE:
        
        python systems/parse_turku.py --corpus_name DE_GSD --gld_token_type CoNLLUP_Token \
            -i /home/daza/datasets/ud-treebanks-v2.2/UD_German-GSD/de_gsd-ud-test.conllu
        
        python systems/parse_turku.py --corpus_name TigerTestOld --gld_token_type CoNLLUP_Token \
        -i /home/daza/datasets/TIGER_conll/data_splits/test/Tiger.OldOrth.test.conll
            
    """
    
    parser = argparse.ArgumentParser()
    parser.add_argument("-i", "--input_file", help="Input Corpus", required=True)
    parser.add_argument("-o", "--output_file", help="Output Parsed Corpus", default=None)
    parser.add_argument("-n", "--corpus_name", help="Corpus Name", default="Corpus")
    parser.add_argument("-gtt", "--gld_token_type", help="CoNLL Format of the Gold Data", default="CoNLL09_Token")
    parser.add_argument("-c", "--comment_str", help="CoNLL Format of comentaries inside the file", default="#")
    args = parser.parse_args()
    
    file_has_next, chunk_ix = True, 0
    CHUNK_SIZE = 10000
    
    output_file = args.input_file if not args.output_file else args.output_file
    
    # =====================================================================================
    #                    LOGGING INFO ...
    # =====================================================================================
    logger = logging.getLogger(__name__)
    console_hdlr = logging.StreamHandler(sys.stdout)
    file_hdlr = logging.FileHandler(filename=f"logs/Parse_{args.corpus_name}_Turku.log")
    logging.basicConfig(level=logging.INFO, handlers=[console_hdlr, file_hdlr])
    logger.info(f"Chunking TIGER Corpus in chunks of {CHUNK_SIZE} Sentences")
    
    # =====================================================================================
    #                    PROCESS (PARSE) TIGER Corpus ...
    # =====================================================================================
    start = time.time()
    total_processed_sents = 0
    line_generator = fu.file_generator(args.input_file)
    while file_has_next:
        raw_text, file_has_next, n_sents = fu.get_file_chunk(line_generator, chunk_size=CHUNK_SIZE, token_class=get_token_type(args.gld_token_type), comment_str=args.comment_str)
        total_processed_sents += n_sents
        if len(raw_text) > 0:
            fu.turku_parse_file(raw_text, output_file, chunk_ix)
            now = time.time()
            elapsed = (now - start)
            logger.info(f"Time Elapsed: {elapsed}. Processed {total_processed_sents}. [{total_processed_sents/elapsed} Sents/sec]\n") # Toks/Sec???
        chunk_ix += 1
        if chunk_ix == 10: break      
    end = time.time()
    logger.info(f"Processing File {args.corpus_name} took {(end - start)} seconds!")