nlp/spacy-nlp

#!/usr/bin/env python3.7
# coding=utf-8

from argparse import ArgumentParser
from xml.sax.saxutils import escape
import chardet
import hashlib
import os
import spacy
import textwrap

SPACY_MODELS = {'de': 'de_core_news_md',
                'el': 'el_core_news_md',
                'en': 'en_core_web_md',
                'es': 'es_core_news_md',
                'fr': 'fr_core_news_md',
                'it': 'it_core_news_md',
                'nl': 'nl_core_news_md',
                'pt': 'pt_core_news_md'}
SPACY_MODELS_VERSION = os.environ.get('SPACY_MODELS_VERSION')
SPACY_VERSION = os.environ.get('SPACY_VERSION')

# Parse the given arguments
parser = ArgumentParser(description=('Tag a text file with spaCy and save it '
                                     'as a verticalized text file.'))
parser.add_argument('-i', '--input', metavar='txt-sourcefile', required=True)
parser.add_argument('-o', '--output', metavar='vrt-destfile', required=True)
parser.add_argument('-l', '--language', choices=SPACY_MODELS.keys(), required=True)  # noqa
parser.add_argument('--check-encoding', action='store_true')
args = parser.parse_args()


# If requested: Check the encoding of the text contents from the input file
# Else: Use utf-8
if args.check_encoding:
    with open(args.input, "rb") as input_file:
        bytes = input_file.read()
        encoding = chardet.detect(bytes)['encoding']
else:
    encoding = 'utf-8'


# hashing in chunks to avoid full RAM with huge files.
with open(args.input, 'rb') as input_file:
    source_md5 = hashlib.md5()
    for chunk in iter(lambda: input_file.read(128 * source_md5.block_size), b''):
        source_md5.update(chunk)
    source_md5 = source_md5.hexdigest()

# Load the text contents from the input file
with open(args.input, encoding=encoding) as input_file:
    text = input_file.read()
    # spaCys NLP is limited to strings with maximum 1 million characters at
    # once. So we split it into suitable chunks.
    text_chunks = textwrap.wrap(text, 1000000, break_long_words=False)
    # the text variable potentially occupies a lot of system memory and is no
    # longer needed...
    del text


# Setup the spaCy toolkit by loading the chosen language model
model = SPACY_MODELS[args.language]
nlp = spacy.load(model)


# Create the output file in verticalized text format
# See: http://cwb.sourceforge.net/files/CWB_Encoding_Tutorial/node3.html
output_file_original_filename = args.output
output_file_stand_off_filename = args.output.replace('.vrt', '.stand-off.vrt')
common_xml = ('<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\n'
              + '<corpus>\n'
              + '<text>\n'
              + '<nlp name="spaCy:{}"\n'.format(SPACY_VERSION)
              + '     model="{}:{}"\n'.format(model, SPACY_MODELS_VERSION)
              + '     source-md5="{}" />\n'.format(source_md5))

with open(output_file_original_filename, 'w+') as output_file_original, \
     open(output_file_stand_off_filename, 'w+') as output_file_stand_off:

    output_file_original.write(common_xml)
    output_file_stand_off.write(common_xml)
    text_offset = 0
    for text_chunk in text_chunks:
        doc = nlp(text_chunk)
        for sent in doc.sents:
            output_file_original.write('<s>\n')
            output_file_stand_off.write('<s>\n')
            space_flag = False
            # Skip whitespace tokens
            sent_no_space = [token for token in sent
                             if not token.text.isspace()]
            # No space variant for cwb original .vrt file input.
            for token in sent_no_space:
                output_file_original.write('{}'.format(escape(token.text))
                                           + '\t{}'.format(escape(token.lemma_))
                                           + '\t{}'.format(token.pos_)
                                           + '\t{}'.format(token.tag_)
                                           + '\t{}\n'.format(token.ent_type_ or 'NULL'))
            # Stand off variant with spaces.
            for token in sent:
                token_start = token.idx + text_offset
                token_end = token.idx + len(token.text) + text_offset
                output_file_stand_off.write('{}:{}'.format(token_start,
                                                           token_end)
                                            + '\t{}'.format(escape(token.lemma_))
                                            + '\t{}'.format(token.pos_)
                                            + '\t{}'.format(token.tag_)
                                            + '\t{}\n'.format(token.ent_type_ or 'NULL'))
            output_file_original.write('</s>\n')
            output_file_stand_off.write('</s>\n')
        text_offset = token_end + 1
    output_file_original.write('</text>\n</corpus>')
    output_file_stand_off.write('</text>\n</corpus>')