|
1
|
|
|
"""Package to clean TXT files |
|
2
|
|
|
|
|
3
|
|
|
.. Authors: |
|
4
|
|
|
Philippe Dessauw |
|
5
|
|
|
[email protected] |
|
6
|
|
|
|
|
7
|
|
|
.. Sponsor: |
|
8
|
|
|
Alden Dima |
|
9
|
|
|
[email protected] |
|
10
|
|
|
Information Systems Group |
|
11
|
|
|
Software and Systems Division |
|
12
|
|
|
Information Technology Laboratory |
|
13
|
|
|
National Institute of Standards and Technology |
|
14
|
|
|
http://www.nist.gov/itl/ssd/is |
|
15
|
|
|
""" |
|
16
|
|
|
import codecs |
|
17
|
|
|
from os.path import join, isfile, splitext, basename |
|
18
|
|
|
from os import listdir |
|
19
|
|
|
from denoiser import Denoiser |
|
20
|
|
|
from pipeline.command import Command |
|
21
|
|
|
|
|
22
|
|
|
|
|
23
|
|
|
class TXTDenoiser(Command): |
|
24
|
|
|
"""Command to clean TXT files |
|
25
|
|
|
""" |
|
26
|
|
|
|
|
27
|
|
|
def __init__(self, filename, logger, config): |
|
28
|
|
|
super(TXTDenoiser, self).__init__(filename, logger, config) |
|
29
|
|
|
self.denoiser = Denoiser(config) |
|
30
|
|
|
|
|
31
|
|
|
def execute(self): |
|
32
|
|
|
"""Execute the command |
|
33
|
|
|
""" |
|
34
|
|
|
try: |
|
35
|
|
|
self.logger.debug("::: Text cleaning :::") |
|
36
|
|
|
super(TXTDenoiser, self).get_file() |
|
37
|
|
|
|
|
38
|
|
|
txt_dir = join(self.unzipped, "txt") |
|
39
|
|
|
txt_files = [join(txt_dir, f) for f in listdir(txt_dir) if isfile(join(txt_dir, f)) and f.endswith(".txt")] |
|
40
|
|
|
|
|
41
|
|
|
if len(txt_files) != 1: |
|
42
|
|
|
self.logger.error("Incorrect number of text files") |
|
43
|
|
|
self.finalize() |
|
44
|
|
|
return -1 |
|
45
|
|
|
|
|
46
|
|
|
text_data = self.denoiser.cleanse(txt_files[0], False) |
|
47
|
|
|
|
|
48
|
|
|
# Writing classified lines |
|
49
|
|
|
base_filename = splitext(basename(txt_files[0]))[0] |
|
50
|
|
|
clean_filename = join(txt_dir, base_filename+".clean.txt") |
|
51
|
|
|
garbage_filename = join(txt_dir, base_filename+".grbge.txt") |
|
52
|
|
|
unclassified_filename = join(txt_dir, base_filename+".unclss.txt") |
|
53
|
|
|
|
|
54
|
|
|
with codecs.open(clean_filename, "wb", encoding="utf-8") as clean_file: |
|
55
|
|
|
for line in text_data.get_clean_lines(): |
|
56
|
|
|
clean_file.write(line+"\n") |
|
57
|
|
|
|
|
58
|
|
|
with codecs.open(garbage_filename, "wb", encoding="utf-8") as garbage_file: |
|
59
|
|
|
for line in text_data.get_garbage_lines(): |
|
60
|
|
|
garbage_file.write(line+"\n") |
|
61
|
|
|
|
|
62
|
|
|
if len(text_data.get_unclassified_lines()) > 0: |
|
63
|
|
|
with codecs.open(unclassified_filename, "wb", encoding="utf-8") as unclassified_file: |
|
64
|
|
|
for line in text_data.get_unclassified_lines(): |
|
65
|
|
|
unclassified_file.write(line+"\n") |
|
66
|
|
|
except Exception, e: |
|
67
|
|
|
print e |
|
68
|
|
|
|
|
69
|
|
|
self.logger.error("Cleaner has stopped unexpectedly: "+e.message) |
|
70
|
|
|
self.finalize() |
|
71
|
|
|
return -2 |
|
72
|
|
|
|
|
73
|
|
|
self.finalize() |
|
74
|
|
|
return 0 |
|
75
|
|
|
|
|
76
|
|
|
def finalize(self): |
|
77
|
|
|
"""Finalize the job |
|
78
|
|
|
""" |
|
79
|
|
|
super(TXTDenoiser, self).store_file() |
|
80
|
|
|
self.logger.debug("::: Text cleaning (END) :::") |
|
81
|
|
|
|
usnistgov /
ocr-pipeline
