NeoAnd/knowledge
1
0
Fork 0
mirror of https://github.com/OCA/knowledge.git synced 2025-07-26 18:38:41 -06:00
Code Issues Actions Packages Projects Releases Wiki Activity

Improve logger messages

Browse Source
This commit is contained in:
Carlos Almeida 2017-06-06 14:13:14 +01:00
parent f7903b10da
commit f80491a589
2 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
document_ocr/models/ir_attachment.py
View File

@ -177,6 +177,7 @@ class IrAttachment(models.Model):
return content return content
def _index_ocr(self, bin_data): def _index_ocr(self, bin_data):
_logger.info('OCR IMAGE "%s"...', self.datas_fname)
process = subprocess.Popen( process = subprocess.Popen(
['tesseract', 'stdin', 'stdout', '-l', self.language], ['tesseract', 'stdin', 'stdout', '-l', self.language],
stdin=subprocess.PIPE, stdout=subprocess.PIPE, stdin=subprocess.PIPE, stdout=subprocess.PIPE,
@ -237,7 +238,6 @@ class IrAttachment(models.Model):
buf = u'%s\n-- %d --\n%s' % ( buf = u'%s\n-- %d --\n%s' % (
buf, pagenum + 1, index_content.decode('utf8')) buf, pagenum + 1, index_content.decode('utf8'))
else: else:
_logger.info('OCR PDF "%s"...', self.datas_fname)
pdf_image = convert_bin_to_image(self, bin_data) pdf_image = convert_bin_to_image(self, bin_data)
index_content = self._index_ocr(pdf_image) index_content = self._index_ocr(pdf_image)
buf = u'%s\n%s' % (buf, index_content.decode('utf8')) buf = u'%s\n%s' % (buf, index_content.decode('utf8'))

10
document_ocr/tests/test_document_ocr.py
View File

@ -23,13 +23,17 @@ class TestDocumentOcr(TransactionCase):
data = StringIO() data = StringIO()
test_image.save(data, 'png') test_image.save(data, 'png')
attachment = self.env['ir.attachment'].create({ attachment = self.env['ir.attachment'].create({
'name': 'testattachment'}) 'name': 'testattachment',
'datas_fname': 'test_png.pdf'})
result = attachment._index( result = attachment._index(
data.getvalue(), 'test.png', None) data.getvalue(), 'test.png', None)
self.assertEqual(result.strip(), 'Hello world') self.assertEqual(result.strip(), 'Hello world')
# should also work for pdfs # should also work for pdfs
data = StringIO() data = StringIO()
test_image.save(data, 'pdf', resolution=300) test_image.save(data, 'pdf', resolution=300)
attachment = self.env['ir.attachment'].create({
'name': 'testattachment',
'datas_fname': 'test_pdf.pdf'})
result = attachment._index( result = attachment._index(
data.getvalue(), 'test.pdf', None) data.getvalue(), 'test.pdf', None)
self.assertEqual(result.strip(), 'Hello world') self.assertEqual(result.strip(), 'Hello world')
@ -38,6 +42,7 @@ class TestDocumentOcr(TransactionCase):
'document_ocr.synchronous', 'False') 'document_ocr.synchronous', 'False')
attachment = self.env['ir.attachment'].create({ attachment = self.env['ir.attachment'].create({
'name': 'testattachment', 'name': 'testattachment',
'datas_fname': 'test_cron.pdf',
'datas': data.getvalue().encode('base64'), 'datas': data.getvalue().encode('base64'),
}) })
self.assertEqual(attachment.index_content, _MARKER_PHRASE) self.assertEqual(attachment.index_content, _MARKER_PHRASE)
@ -49,6 +54,9 @@ class TestDocumentOcr(TransactionCase):
data = StringIO() data = StringIO()
test_image = Image.new('1', (200, 30)) test_image = Image.new('1', (200, 30))
test_image.save(data, 'palm') test_image.save(data, 'palm')
attachment = self.env['ir.attachment'].create({
'name': 'testattachment',
'datas_fname': 'test_err.palm'})
result = attachment._index( result = attachment._index(
data.getvalue(), 'test.palm', None) data.getvalue(), 'test.palm', None)
self.assertEqual(result, '') self.assertEqual(result, '')