def filename(self, filepath):
filename = self.importer.file_name(cache.get_file(filepath))
# The current implementation of the archive command does not
# modify the filename returned by the importer. This preserves
# backward compatibility with the old implementation of the
# command.
return misc_utils.idify(filename) if filename else None
def filepath(importer, filepath: str) -> str:
"""Compute filing path for a document.
The path mirrors the structure of the accounts associated to the
documents and with a file name composed by the document date and
document name returned by the importer.
Args:
importer: The importer instance to handle the document.
filepath: Filesystem path to the document.
Returns:
Filing tree location where to store the document.
Raises:
beangulp.exceptions.Error: The canonical file name returned by
the importer contains a path separator charachter or seems to
contain a date.
"""
file = cache.get_file(filepath)
# Get the account corresponding to the file.
account = importer.file_account(file)
filename = importer.file_name(file) or os.path.basename(file.name)
date = importer.file_date(file) or utils.getmdate(file.name)
# The returned filename cannot contain the file path separator character.
if os.sep in filename:
raise Error("The filename contains path separator character.")
if re.match(r'\d\d\d\d-\d\d-\d\d', filename):
raise Error("The filename contains what looks like a date.")
# Remove whitespace and other funny characters from the filename.
# TODO(dnicolodi): This should probably be importer responsibility.
filename = misc_utils.idify(filename)
# Prepend account directory and date prefix.
filename = os.path.join(account.replace(':', os.sep),
f'{date:%Y-%m-%d}.{filename:}')
return filename
def file_one_file(filename, importers, destination, idify=False, logfile=None):
"""Move a single filename using its matched importers.
Args:
filename: A string, the name of the downloaded file to be processed.
importers: A list of importer instances that handle this file.
destination: A string, the root destination directory where the files are
to be filed. The files are organized there under a hierarchy mirroring
that of the chart of accounts.
idify: A flag, if true, remove whitespace and funky characters in the destination
filename.
logfile: A file object to write log entries to, or None, in which case no log is
written out.
Returns:
The full new destination filename on success, and None if there was an error.
"""
# Create an object to cache all the conversions between the importers
# and phases and what-not.
file = cache.get_file(filename)
# Get the account corresponding to the file.
file_accounts = []
for index, importer in enumerate(importers):
try:
account_ = importer.file_account(file)
except Exception as exc:
account_ = None
logging.exception("Importer %s.file_account() raised an unexpected error: %s",
importer.name(), exc)
if account_ is not None:
file_accounts.append(account_)
file_accounts_set = set(file_accounts)
if not file_accounts_set:
logging.error("No account provided by importers: {}".format(
", ".join(imp.name() for imp in importers)))
return None
if len(file_accounts_set) > 1:
logging.warning("Ambiguous accounts from many importers: {}".format(
', '.join(file_accounts_set)))
# Note: Don't exit; select the first matching importer's account.
file_account = file_accounts.pop(0)
# Given multiple importers, select the first one that was yielded to
# obtain the date and process the filename.
importer = importers[0]
# Compute the date from the last modified time.
mtime = path.getmtime(filename)
mtime_date = datetime.datetime.fromtimestamp(mtime).date()
# Try to get the file's date by calling a module support function. The
# module may be able to extract the date from the filename, from the
# contents of the file itself (e.g. scraping some text from the PDF
# contents, or grabbing the last line of a CSV file).
try:
date = importer.file_date(file)
except Exception as exc:
logging.exception("Importer %s.file_date() raised an unexpected error: %s",
importer.name(), exc)
date = None
if date is None:
# Fallback on the last modified time of the file.
date = mtime_date
date_source = 'mtime'
else:
date_source = 'contents'
# Apply filename renaming, if implemented.
# Otherwise clean up the filename.
try:
clean_filename = importer.file_name(file)
# Warn the importer implementor if a name is returned and it's an
# absolute filename.
if clean_filename and (path.isabs(clean_filename) or os.sep in clean_filename):
logging.error(("The importer '%s' file_name() method should return a relative "
"filename; the filename '%s' is absolute or contains path "
"separators"),
importer.name(), clean_filename)
except Exception as exc:
logging.exception("Importer %s.file_name() raised an unexpected error: %s",
importer.name(), exc)
clean_filename = None
if clean_filename is None:
# If no filename has been provided, use the basename.
clean_filename = path.basename(file.name)
elif re.match(r'\d\d\d\d-\d\d-\d\d', clean_filename):
logging.error("The importer '%s' file_name() method should not date the "
"returned filename. Implement file_date() instead.")
# We need a simple filename; remove the directory part if there is one.
clean_basename = path.basename(clean_filename)
# Remove whitespace if requested.
if idify:
clean_basename = misc_utils.idify(clean_basename)
# Prepend the date prefix.
new_filename = '{0:%Y-%m-%d}.{1}'.format(date, clean_basename)
# Prepend destination directory.
new_fullname = path.normpath(path.join(destination,
file_account.replace(account.sep, os.sep),
new_filename))
# Print the filename and which modules matched.
if logfile is not None:
logfile.write('Importer: {}\n'.format(importer.name() if importer else '-'))
logfile.write('Account: {}\n'.format(file_account))
logfile.write('Date: {} (from {})\n'.format(date, date_source))
logfile.write('Destination: {}\n'.format(new_fullname))
logfile.write('\n')
return new_fullname
def test_idify(self):
self.assertEqual('A_great_movie_for_us.mp4',
misc_utils.idify(' A great movie (for us) .mp4 '))
self.assertEqual('A____B.pdf', misc_utils.idify('A____B_._pdf'))
def filename(self, filepath):
return path.basename(misc_utils.idify(filepath))
