RanchiMall/flo-token-tracking
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updated regex and tests for tokenamount parsing

Browse Source
This commit is contained in:
Vivek Teega 2023-03-22 11:19:32 +00:00
parent ea3985cb28
commit c4be19058f
2 changed files with 29 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
parsing.py
View File

@ -686,8 +686,14 @@ def checkSearchPattern(parsed_list, searchpattern):
def extractAmount_rule_new(text): def extractAmount_rule_new(text):
base_units = {'thousand': 10 ** 3, 'k': 10 ** 3, 'million': 10 ** 6, 'm': 10 ** 6, 'billion': 10 ** 9, 'b': 10 ** 9, 'trillion': 10 ** 12, 'lakh':10 ** 5, 'crore':10 ** 7, 'quadrillion':10 ** 15} base_units = {'thousand': 10 ** 3, 'k': 10 ** 3, 'lakh':10 ** 5, 'crore':10 ** 7, 'million': 10 ** 6, 'm': 10 ** 6, 'billion': 10 ** 9, 'b': 10 ** 9, 'trillion': 10 ** 12, 'quadrillion':10 ** 15}
amount_tuple = re.findall(r'(-?\d+(?:\.\d+)?)\s*(?=(?:[bmk]|thousand|million|billion|trillion|m|b|t|k|lakh|crore|quadrillion|\s))(billion|million|thousand|k|lakh|crore|quadrillion)?', text)
# appending whitespace because the regex does not recognize a number at the start & end of string ie. "send rmt# 45"
text = f" {text} "
text = text.replace("'", "")
text = text.replace('"', '')
amount_tuple = re.findall(r'(?<!\S)(-?\d+(?:\.\d+)?)\s*(?=(?:[bmk]|thousand|k|lakh|crore|million|m|billion|b|trillion|t|quadrillion|\s))(thousand|k|lakh|crore|million|m|billion|b|trillion|t|quadrillion)?\b', text)
if len(amount_tuple) > 1 or len(amount_tuple) == 0: if len(amount_tuple) > 1 or len(amount_tuple) == 0:
return False return False
else: else:
@ -706,11 +712,11 @@ def extractAmount_rule_new1(text, split_word=None, split_direction=None):
if split_direction=='post': if split_direction=='post':
text = text.split(split_word)[1] text = text.split(split_word)[1]
# appending dummy because the regex does not recognize a number at the start of a string # appending whitespace because the regex does not recognize a number at the start & end of string ie. "send rmt# 45"
# text = f"dummy {text}" text = f" {text} "
text = text.replace("'", "") text = text.replace("'", "")
text = text.replace('"', '') text = text.replace('"', '')
amount_tuple = re.findall(r'(-?\d+(?:\.\d+)?)\s*(?=(?:[bmk]|thousand|million|billion|trillion|m|b|t|k|lakh|crore|quadrillion|\s))(billion|million|thousand|k|lakh|crore|quadrillion)?', text) amount_tuple = re.findall(r'(?<!\S)(-?\d+(?:\.\d+)?)\s*(?=(?:[bmk]|thousand|k|lakh|crore|million|m|billion|b|trillion|t|quadrillion|\s))(thousand|k|lakh|crore|million|m|billion|b|trillion|t|quadrillion)?\b', text)
if len(amount_tuple) > 1 or len(amount_tuple) == 0: if len(amount_tuple) > 1 or len(amount_tuple) == 0:
return False return False
else: else:
@ -973,6 +979,7 @@ def parse_flodata(text, blockinfo, net):
first_classification = firstclassification_rawstring(processed_text) first_classification = firstclassification_rawstring(processed_text)
parsed_data = None parsed_data = None
if first_classification['categorization'] == 'tokensystem-C': if first_classification['categorization'] == 'tokensystem-C':
# Resolving conflict for 'tokensystem-C' # Resolving conflict for 'tokensystem-C'
tokenname = first_classification['wordlist'][0][:-1] tokenname = first_classification['wordlist'][0][:-1]
@ -1237,4 +1244,5 @@ def parse_flodata(text, blockinfo, net):
return outputreturn('noise') return outputreturn('noise')
return outputreturn('continuos-event-token-swap-incorporation', f"{contract_token}", f"{contract_name}", f"{contract_address}", f"{clean_text}", f"{contract_conditions['subtype']}", f"{contract_conditions['accepting_token']}", f"{contract_conditions['selling_token']}", f"{contract_conditions['priceType']}", f"{contract_conditions['price']}", stateF_mapping) return outputreturn('continuos-event-token-swap-incorporation', f"{contract_token}", f"{contract_name}", f"{contract_address}", f"{clean_text}", f"{contract_conditions['subtype']}", f"{contract_conditions['accepting_token']}", f"{contract_conditions['selling_token']}", f"{contract_conditions['priceType']}", f"{contract_conditions['price']}", stateF_mapping)
return outputreturn('noise') return outputreturn('noise')

15
test_parsing.py
View File

@ -109,6 +109,21 @@ class TestParsing(unittest.TestCase):
result = parsing.parse_flodata(text, TestParsing.blockinfo_stub, 'testnet') result = parsing.parse_flodata(text, TestParsing.blockinfo_stub, 'testnet')
expected_result = {'type': 'transfer', 'transferType': 'smartContract', 'flodata': 'transfer 6.20000 bioscope# to all-crowd-fund-7@', 'tokenIdentification': 'bioscope', 'tokenAmount': 6.2, 'contractName': 'all-crowd-fund-7'} expected_result = {'type': 'transfer', 'transferType': 'smartContract', 'flodata': 'transfer 6.20000 bioscope# to all-crowd-fund-7@', 'tokenIdentification': 'bioscope', 'tokenAmount': 6.2, 'contractName': 'all-crowd-fund-7'}
self.assertEqual(result, expected_result) self.assertEqual(result, expected_result)
text = 'transfer 6.20000 bioscope# to all-crowd-fund-7@ 24'
result = parsing.parse_flodata(text, TestParsing.blockinfo_stub, 'testnet')
expected_result = {'type': 'noise'}
self.assertEqual(result, expected_result)
text = 'transfer 6.20000 bioscope# to all-crowd-fund-7@ 24 '
result = parsing.parse_flodata(text, TestParsing.blockinfo_stub, 'testnet')
expected_result = {'type': 'noise'}
self.assertEqual(result, expected_result)
text = '6.20.000 transfer bioscope# to all-crowd-fund-7@ 24'
result = parsing.parse_flodata(text, TestParsing.blockinfo_stub, 'testnet')
expected_result = {'type': 'transfer', 'transferType': 'smartContract', 'flodata': '6.20.000 transfer bioscope# to all-crowd-fund-7@ 24', 'tokenIdentification': 'bioscope', 'tokenAmount': 24.0, 'contractName': 'all-crowd-fund-7'}
self.assertEqual(result, expected_result)
def test_onetimeevent_externaltrigger_creation(self): def test_onetimeevent_externaltrigger_creation(self):
# contractamount # contractamount