def test_matches(self):
name = "2018-04-27.trades.doc.csv"
result = expand_file(name)
self.assertEqual(result.date, datetime.datetime(year=2018, month=4, day=27))
self.assertEqual(result.ext, 'csv')
self.assertEqual(result.document, 'doc')
self.assertEqual(result.slug, 'trades')
def identify(self, file: FileMemo) -> bool:
try:
fd = expand_file(file.name)
if fd.slug:
return True
except:
return False
def test_matche3(self):
name = "2020-01-03-aviator.pdf"
result = expand_file(name)
self.assertEqual(
result.date,
datetime.datetime(year=2020, month=1, day=3))
self.assertEqual(result.ext, 'pdf')
self.assertEqual(result.slug, 'aviator')
self.assertEqual(result.document, None)
def test_matche4(self):
name = "2018-09-27-ledger-USD-deposit.csv"
result = expand_file(name)
self.assertEqual(
result.date,
datetime.datetime(year=2018, month=9, day=27)
)
self.assertEqual(result.ext, 'csv')
self.assertEqual(result.slug, 'ledger-usd-deposit')
self.assertEqual(result.document, None)
def test_since_date_seq(self):
file = pathlib.Path("2018-09-27.s2018-09-01.nbi-1857.export.2.csv")
result = expand_file(file)
self.assertEqual(
result,
FileDetails(
file_name=file.name,
date=datetime.datetime(year=2018, month=9, day=27),
from_date=datetime.datetime(year=2018, month=9, day=1),
slug="nbi-1857",
ext="csv",
file=file,
document='export',
seq=2
)
)
def test_with_match_seq(self):
return
file = pathlib.Path("2020-01-20.paraiso-meralco.statment.pdf")
result = expand_file(file)
assert (
result ==
FileDetails(
file_name=file.name,
date=datetime.datetime(year=2020, month=1, day=20),
from_date=None,
slug="paraiso-meralco",
ext="pdf",
file=file,
document='statement',
seq=0
)
)
self.assertEqual(file.name, result.make_name)
def file_name(self, file):
"""Returns the name without the date portion"""
logger.debug(f"file_name({file})")
fd = expand_file(file)
return f"{fd.slug}.{fd.document}.{fd.ext}".lower()
def file_date(self, file) -> datetime.datetime:
logger.debug(f"file_date({file}")
fd = expand_file(file)
return fd.date
def file_account(self, file):
logger.debug(f"file_account({file}")
fd = expand_file(file)
if fd is None:
return None
return self.slugs[fd.slug]
def filing_handler(source_directories: typing.List[pathlib.Path],
destination: pathlib.Path,
slugs: typing.Dict[str, str],
dry_run=False):
"""Recurse through a list of source directories looking for filing matching a regular expression format:
Args:
source_directories (list): Source Folders to search
destination: Single target folder, we will create Assests/Liabilities under this
slugs: slug dict to use.
dry_run: if True we dont' do any real work, just print out details
Returns:
None -- Moves files instead
"""
for folder in source_directories:
for file in folder.rglob("*"):
match = expand_file(file)
if match is None:
continue
account = slugs.get(match.slug, None)
if not account:
account = slugs.get(match.slug.replace('-', ''), None)
if not account:
logger.info(
f"Unable to find matching account for slug {match.slug}. [{match.file}]"
f"\n{pprint.pformat(slugs)}")
continue
sub_directory = account.replace(':', '/')
target_directory = destination.joinpath(sub_directory)
# Just incase
target_file = target_directory.joinpath(match.make_name)
count = 0
if target_file == file:
# noop
continue
# Rename duplicate files
possible_target: pathlib.Path = target_file
sep = '.'
while possible_target.exists():
print(f"Found matching file {possible_target}")
count += 1
possible_target = target_file.parent.joinpath(
target_file.stem + sep + str(count) + target_file.suffix)
if not dry_run:
if not (target_directory.exists()
and target_directory.is_dir()):
print(f"mkdir {target_directory}")
target_directory.mkdir(parents=True, exist_ok=True)
file.rename(possible_target)
print(f"MOVED {file} -> {possible_target}")
else:
if not (target_directory.exists()
and target_directory.is_dir()):
logger.info(f"DRY: mkdir {target_directory}")
print(f"DRY: mkdir {target_directory}")
logger.info(f"DRY: mv {file} -> {possible_target}")
print(f"mv {file} -> {possible_target}")