from fileReader import FileReader
reader = FileReader()
to_find = ["Trademarks and Trade Names."] # words for searching
complete_path = "v5_signage_bad4.docx" # complete path to file location, can be pdf or word
# header_only=True means it will return only headings
result = reader.find(path=complete_path, to_find=to_find, headers_only=True)
for line in result:
print line
def create_table(filename, clauses):
reader = FileReader()
complete_path = filename
l = []
name = splitext(filename)[0]
document = Document()
document.add_heading('Clause Extraction', 0)
table = document.add_table(rows=1, cols=6)
table.style = 'TableGrid'
hdr_cells = table.rows[0].cells
hdr_cells = table.rows[0].cells
hdr_cells[0].text = 'Amended No.'
hdr_cells[1].text = 'Clause No.'
hdr_cells[2].text = 'ClauseName'
hdr_cells[3].text = 'Lease required amendment'
hdr_cells[4].text = 'Required action'
hdr_cells[5].text = 'Lessor response to amendment Agreed/Not agreed'
index = 0
total_index = 1
#4 Clauses to Extract
for clause in clauses:
t = {}
t['index'] = total_index
t['action'] = clause['action']
t['clausename'] = clause['clause_name']
t['reason'] = clause['reason']
t['agree'] = ""
to_find = [clause['clause_name']]
row_cells = table.add_row().cells
row_cells[0].text = str(t['index'])
row_cells[1].text = ""
row_cells[2].text = t['clausename']
row_cells[3].text = t['reason']
row_cells[5].text = t['agree']
row_cells[4].text = t['action']
total_index += 1
if (clause['text']):
cleaned_string = ''.join(c for c in clause['text']
if valid_xml_char_ordinal(c))
f = remove_clause_number(cleaned_string)
index += 1
t['keep'] = 0
clause_no = ""
# lst = {}
try:
temp_no = 0
clause_no = re.match(
r"([0-9]+\.[0-9]+\.[0-9]+|[0-9]+\.[0-9]+|[0-9]+\.)",
cleaned_string)
if (clause_no != None):
clause_no = clause_no.group()
temp_no = int(clause_no.replace('.', ''))
else:
clause_no = ""
lst = reader.find_with(clause['text'], [clause['key_text']],
headers_only=False)
if (len(lst) > 0 and len(lst[0]) > 0):
try:
if (string.ascii_letters.find(lst[0].replace(
"(", "").replace(')',
'').replace('.',
'')[:-1]) == 0):
clause_no = clause_no + ','.join(lst)
elif (int(lst[0].replace("(", "").replace(
')', '').replace('.', '')) != temp_no):
clause_no = clause_no + ','.join(lst)
else:
clause_no = ','.join(lst)
except ValueError:
clause_no = clause_no + ','.join(lst)
except Exception as e:
print e
print(complete_path)
result = reader.find(path=complete_path,
to_find=to_find,
headers_only=True)
print result
try:
clause_no = result[0]
except:
clause_no = ""
print(clause_no)
if (clause_no != None and clause_no != ""):
t['clause_no'] = clause_no
row_cells[1].text = t['clause_no']
l.append(t)
else:
t['clause_no'] = ""
t['keep'] = 1
l.append(t)
document.add_page_break()
document.save(settings.BASE_DIR + '/leasingai/ai/temp/' + name + '.docx')
return l
