|
1
|
|
|
"""Package to convert PNG to TXT |
|
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
|
|
|
from os.path import join, isdir, split, dirname, basename, splitext, isfile |
|
17
|
|
|
from subprocess import check_output, STDOUT |
|
18
|
|
|
from os import listdir |
|
19
|
|
|
from shutil import move |
|
20
|
|
|
from pipeline.command import Command |
|
21
|
|
|
|
|
22
|
|
|
|
|
23
|
|
|
class PNGReader(Command): |
|
24
|
|
|
"""Command to convert PNG to TXT |
|
25
|
|
|
""" |
|
26
|
|
|
|
|
27
|
|
|
def __init__(self, filename, logger, config): |
|
28
|
|
|
super(PNGReader, self).__init__(filename, logger, config) |
|
29
|
|
|
|
|
30
|
|
|
self.proc_count = 1 |
|
31
|
|
|
self.ocropus_dir = self.config["command"]["ocropy"]["location"] |
|
32
|
|
|
self.rpred_model = self.config["command"]["ocropy"]["model"] |
|
33
|
|
|
self.python = ["python"] |
|
34
|
|
|
|
|
35
|
|
|
self.logger.info("PNG reader initialized") |
|
36
|
|
|
|
|
37
|
|
|
def execute(self): |
|
38
|
|
|
"""Execute the command |
|
39
|
|
|
""" |
|
40
|
|
|
self.logger.debug("::: PNG reading :::") |
|
41
|
|
|
# super(PNGReader, self).get_file() |
|
42
|
|
|
|
|
43
|
|
|
procs = str(self.proc_count) |
|
44
|
|
|
|
|
45
|
|
|
png_dir = join(self.unzipped, "png") |
|
46
|
|
|
txt_dir = join(self.unzipped, "txt") |
|
47
|
|
|
|
|
48
|
|
|
command_list = [ |
|
49
|
|
|
[join(self.ocropus_dir, 'ocropus-nlbin'), "-Q", procs, join(png_dir, '*.png')], |
|
50
|
|
|
[join(self.ocropus_dir, 'ocropus-gpageseg'), "-Q", procs, join(png_dir, '*.bin.png')], |
|
51
|
|
|
[join(self.ocropus_dir, 'ocropus-rpred'), "-Q", procs, "-m", self.rpred_model, |
|
52
|
|
|
join(png_dir, '*/*.bin.png')], |
|
53
|
|
|
] |
|
54
|
|
|
|
|
55
|
|
|
# Execute the list of command |
|
56
|
|
|
for command in command_list: |
|
57
|
|
|
try: |
|
58
|
|
|
self.logger.debug("> "+str(command)) |
|
59
|
|
|
|
|
60
|
|
|
cmdout = check_output(self.python+command, stderr=STDOUT) |
|
61
|
|
|
self.logger.info(cmdout) |
|
62
|
|
|
except Exception, e: |
|
63
|
|
|
print e |
|
64
|
|
|
self.logger.fatal("An exception has been caugth: "+str(e.message)) |
|
65
|
|
|
self.finalize() |
|
66
|
|
|
return 1 |
|
67
|
|
|
|
|
68
|
|
|
# Build the resulting text file from every line file |
|
69
|
|
|
txt_files = [join(png_dir, subdir, f) for subdir in listdir(png_dir) if isdir(join(png_dir, subdir)) |
|
70
|
|
|
for f in listdir(join(png_dir, subdir)) if f.endswith(".txt")] |
|
71
|
|
|
self.logger.debug(str(len(txt_files)) + " text file(s) found") |
|
72
|
|
|
|
|
73
|
|
|
for f in txt_files: |
|
74
|
|
|
dirs = split(dirname(f)) |
|
75
|
|
|
|
|
76
|
|
|
filename = basename(f) |
|
77
|
|
|
pagenum = dirs[-1].split("-")[-1] |
|
78
|
|
|
|
|
79
|
|
|
move(f, join(txt_dir, "segments", pagenum+"-"+filename)) |
|
80
|
|
|
|
|
81
|
|
|
txt_files = sorted([join(txt_dir, "segments", f) for f in listdir(join(txt_dir, "segments")) |
|
82
|
|
|
if f.endswith(".txt")]) |
|
83
|
|
|
|
|
84
|
|
|
text = "" |
|
85
|
|
|
for f in txt_files: |
|
86
|
|
|
with open(f, "r") as txt: |
|
87
|
|
|
lines = txt.readlines() |
|
88
|
|
|
|
|
89
|
|
|
for l in lines: |
|
90
|
|
|
text += l |
|
91
|
|
|
|
|
92
|
|
|
pdf_files = [join(self.unzipped, f) for f in listdir(self.unzipped) if isfile(join(self.unzipped, f)) and |
|
93
|
|
|
f.endswith(".pdf")] |
|
94
|
|
|
txt_filename = splitext(basename(pdf_files[0]))[0]+".txt" |
|
95
|
|
|
|
|
96
|
|
|
with open(join(txt_dir, txt_filename), "w") as output: |
|
97
|
|
|
output.write(text) |
|
98
|
|
|
|
|
99
|
|
|
self.finalize() |
|
100
|
|
|
return 0 |
|
101
|
|
|
|
|
102
|
|
|
def finalize(self): |
|
103
|
|
|
"""Finalize the job |
|
104
|
|
|
""" |
|
105
|
|
|
# super(PNGReader, self).store_file() |
|
106
|
|
|
self.logger.debug("::: PNG reading (END) :::") |
|
107
|
|
|
|
usnistgov /
ocr-pipeline
