def testGetTablesImagesFromProtectPDF(self):
"""Test if protect pdf returns False when try to extract tables and images"""
data = open('./data/test_protect.pdf').read()
pdfgranulator = PDFGranulator(self.tmp_url, data, 'pdf', **self.kw)
tables_matrix = pdfgranulator.getTablesMatrix()
image_list = pdfgranulator.getImageItemList()
self.assertEqual(tables_matrix, False)
self.assertEqual(image_list, False)
def testGetImageItemList(self):
"""Test if getImageItemList() returns the right images list"""
data = open('./data/test.pdf').read()
pdfgranulator = PDFGranulator(self.tmp_url, data, 'pdf', **self.kw)
image_list = pdfgranulator.getImageItemList()
self.assertEquals(image_list[0][0], '001-pag001.png')
self.assertEquals(image_list[-1][0], '012-pag004.jpg')
self.assertEquals(len(image_list), 12)
def testGetTable(self):
"""Test if getTable() returns table by id"""
data = open('./data/granulate_test.pdf').read()
pdfgranulator = PDFGranulator(self.tmp_url, data, 'pdf', **self.kw)
table = pdfgranulator.getTable('Tabela 1 - pag 1')
self.assertEqual(table, '<html><body><h1> Tabela 1 - pag 1 </h1><table>'+
'<tr><td> Name </td><td> Phone </td><td> Email </td></tr>'+
'<tr><td> Hugo </td><td> +55 (22) 8888-8888 </td><td> [email protected] </td></tr>'+
'<tr><td> Rafael </td><td>+55 (22) 9999-9999 </br>+55 (22) 9999-9999 '+
'</br>+55 (22) 9999-9999 </br></td><td> [email protected] </td></tr></table></body></html>')
def testGetTablesMatrix(self):
"""Test if getTablesMatrix() returns matrix with all tables"""
data = open('./data/granulate_test.pdf').read()
pdfgranulator = PDFGranulator(self.tmp_url, data, 'pdf', **self.kw)
tables_matrix = pdfgranulator.getTablesMatrix()
self.assertEqual(tables_matrix,
{'Tabela 2: Soccer Teams - pag 2': [
['Name', 'Country'], ['Goytacaz', 'Brazil'], ['PSG', 'France'], ['Chelsea', 'England '], ['Barcelona', 'Spain']],
'Tabela 1 - pag 1': [
['Name', 'Phone', 'Email'],
['Hugo', '+55 (22) 8888-8888', '*****@*****.**'],
['Rafael', ['+55 (22) 9999-9999', '+55 (22) 9999-9999', '+55 (22) 9999-9999'], '*****@*****.**']],
'Table 1: Prices table from Mon Restaurant - pag 1': [
['Product', 'Price'], ['Pizza', 'R$ 25,00'], ['Petit Gateau', 'R$ 10,00'], ['Feijoada', 'R$ 30,00']]})
def granulateFile(self, data, source_format="odt"):
"""This function allows BD NSI's project to completely granulate
document file"""
if source_format.lower() == "pdf":
pdfgranulator = PDFGranulator(self._path_tmp_dir, decodestring(data), 'pdf',
**self.kw)
table_list = pdfgranulator.getTableItemList()
grains = []
if table_list != 'PDF Protect or have no Table Item List':
tables = []
for item in table_list:
table = pdfgranulator.getTable(item)
tables.append(table)
grains = map(encodestring, tables)
images = pdfgranulator.getImageItemList()
if images != False:
# XXX - encodestring cant convert list
grains += map(encodestring, str(images))
# XXX - if has no grains
if grains == []:
return "This PDF is protect or has no grains"
return grains
else:
try:
document = self._getOOGranulator(data, source_format)
table_list = document.getTableItemList()
tables = []
for table in table_list:
tables.append(document.getTable(table[0], 'odt'))
grains = tables
image_list = document.getImageItemList()
images = []
for image in image_list:
images.append(document.getImage(image[0]))
grains += image
return map(encodestring,grains)
except:
raise NotImplementedError
def testGetTableItemList(self):
"""Test if getTableItemList() returns list of tables' id"""
data = open('./data/granulate_test.pdf').read()
pdfgranulator = PDFGranulator(self.tmp_url, data, 'pdf', **self.kw)
table_list = pdfgranulator.getTableItemList()
self.assertEqual(table_list, ['Tabela 2: Soccer Teams - pag 2', 'Tabela 1 - pag 1', 'Table 1: Prices table from Mon Restaurant - pag 1'])
