| # 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 CoNLL09_Token |
| import my_utils.file_utils as fu |
| |
| |
| TIGER_CORPUS = "/home/daza/datasets/TIGER_conll/tiger_release_aug07.corrected.16012013.conll09" |
| |
| |
| if __name__ == "__main__": |
| file_has_next, chunk_ix = True, 0 |
| CHUNK_SIZE = 10000 |
| |
| # ===================================================================================== |
| # LOGGING INFO ... |
| # ===================================================================================== |
| logger = logging.getLogger(__name__) |
| console_hdlr = logging.StreamHandler(sys.stdout) |
| file_hdlr = logging.FileHandler(filename=f"logs/Parse_Tiger_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(TIGER_CORPUS) |
| while file_has_next: |
| raw_text, file_has_next, n_sents = fu.get_file_chunk(line_generator, chunk_size=CHUNK_SIZE, token_class=CoNLL09_Token) |
| total_processed_sents += n_sents |
| if len(raw_text) > 0: |
| fu.turku_parse_file(raw_text, TIGER_CORPUS, 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 {TIGER_CORPUS} took {(end - start)} seconds!") |
| |
| |