1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
###########################################################################
import sys
import os
local_src = os.path.dirname(os.path.abspath(__file__)) + '/../src'
if os.path.exists(local_src):
sys.path = [local_src] + sys.path
installed_src = os.path.join('@prefix@', 'lib', 'python@PYTHON_VERSION@',
'site-packages')
if os.path.exists(installed_src):
sys.path.insert(1, installed_src)
from PIL import Image
from ocrfeeder.util.constants import OCRFEEDER_STUDIO_VERSION
from ocrfeeder.util.graphics import getImageResolution
from ocrfeeder.util.configuration import ConfigurationManager
from ocrfeeder.feeder.ocrEngines import OcrEnginesManager
from ocrfeeder.studio.dataHolder import PageData
from ocrfeeder.feeder.layoutAnalysis import LayoutAnalysis
from ocrfeeder.feeder.documentGeneration import OdtGenerator, HtmlGenerator
from optparse import OptionParser
parser = OptionParser(usage = 'Usage: %prog -i IMAGE1 [IMAGE2, ...] -o FILE',
version = '%prog ' + OCRFEEDER_STUDIO_VERSION)
parser.add_option('-i', '--images', dest = 'images',
action = 'append', type = 'string', metavar = 'IMAGE1 [IMAGE2, ...]',
help = 'images to be recognized', default = [])
parser.add_option('-f', '--format', dest = 'format',
action = 'store', type = 'choice', default = 'odt',
help = 'format of the generated document', metavar = 'odt or html',
choices = ['odt', 'html'])
parser.add_option('-o', '--output', dest = 'output',
action = 'store', type = 'string',
help = 'the document to be generated')
parser.add_option('--window-size', dest = 'window_size', default = 'auto',
action = 'store', type = 'string', metavar= 'auto or an integer value',
help = 'the segmentation algorithm window size')
options, args = parser.parse_args()
if len(options.images) < 1:
parser.error('Please specify the images to be recognized.')
parser.print_help()
exit(0)
if options.output is None:
parser.error('Please specify the output file.')
parser.print_help()
exit(0)
images = options.images
window_size = options.window_size
if window_size == 'auto':
window_size = None
else:
try:
window_size = int(window_size)
except ValueError:
parser.error('Please use either "auto" or an integer value '
'for the window size.')
exit(0)
export_format = options.format
file_name = options.output
if not file_name:
parser.error('Please choose the output name.')
configuration_manager = ConfigurationManager()
ocr_engines_manager = OcrEnginesManager(configuration_manager)
ocr_engines_manager.makeEnginesFromFolder(configuration_manager.user_engines_folder)
ocr_engines = ocr_engines_manager.ocr_engines
if len(ocr_engines):
engine = ocr_engines[0]
else:
parser.error('No OCR engines configured.')
exit(0)
pages = []
for image in images:
if not os.path.isfile(image):
parser.error('The image "%s" is not a file or does not exist.' %\
image)
exit(0)
page_data = PageData(image)
data_boxes = []
image_obj = Image.open(image)
layout_analysis = LayoutAnalysis(engine[0],
window_size)
resolution = getImageResolution(image_obj)[1]
page_data.data_boxes = layout_analysis.recognize(image,
resolution)
pages.append(page_data)
document_generator = OdtGenerator(file_name)
if 'html' in export_format:
document_generator = HtmlGenerator(file_name)
for page in pages:
document_generator.addPage(page)
document_generator.save()
configuration_manager.removeTemporaryFolder()
|
