mirror of
https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp.git
synced 2024-12-26 06:34:18 +00:00
115 lines
4.7 KiB
Python
Executable File
115 lines
4.7 KiB
Python
Executable File
#!/usr/bin/env python3.7
|
|
# coding=utf-8
|
|
|
|
from argparse import ArgumentParser
|
|
from xml.sax.saxutils import escape
|
|
import chardet
|
|
import spacy
|
|
import textwrap
|
|
import hashlib
|
|
|
|
|
|
SPACY_MODELS = {'de': 'de_core_news_sm',
|
|
'el': 'el_core_news_sm',
|
|
'en': 'en_core_web_sm',
|
|
'es': 'es_core_news_sm',
|
|
'fr': 'fr_core_news_sm',
|
|
'it': 'it_core_news_sm',
|
|
'nl': 'nl_core_news_sm',
|
|
'pt': 'pt_core_news_sm'}
|
|
|
|
|
|
# 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', metavar='txt-sourcefile')
|
|
parser.add_argument('o', metavar='vrt-destfile')
|
|
parser.add_argument('-l', '--language', choices=SPACY_MODELS.keys(),
|
|
required=True)
|
|
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.i, "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.i, 'rb') as input_file:
|
|
md5_hash = hashlib.md5()
|
|
for chunk in iter(lambda: input_file.read(128 * md5_hash.block_size), b''):
|
|
md5_hash.update(chunk)
|
|
md5_hash = md5_hash.hexdigest()
|
|
|
|
# Load the text contents from the input file
|
|
with open(args.i, 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
|
|
nlp = spacy.load(SPACY_MODELS[args.language])
|
|
|
|
|
|
# Create the output file in verticalized text format
|
|
# See: http://cwb.sourceforge.net/files/CWB_Encoding_Tutorial/node3.html
|
|
output_file_original_filename = args.o
|
|
output_file_stand_off_filename = args.o.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'
|
|
+ ' version="{}"\n'.format(spacy.__version__)
|
|
+ ' model="{}"\n'.format(SPACY_MODELS[args.language])
|
|
+ ' model_version="{}"\n'.format(nlp.meta['version'])
|
|
+ ' md5_hash_of_input="{}" />\n'.format(md5_hash))
|
|
|
|
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>')
|