def test_print_extracted_entries_duplictes(self):
entries, error, options = parser.parse_string(
textwrap.dedent('''
1970-01-01 * "Test"
Assets:Tests 10.00 USD
1970-01-01 * "Test"
Assets:Tests 10.00 USD '''))
# Mark the second entry as duplicate
entries[1].meta[extract.DUPLICATE] = True
extracted = [
('/path/to/test.csv', entries),
]
output = io.StringIO()
extract.print_extracted_entries(extracted, output)
self.assertEqual(
output.getvalue(),
textwrap.dedent('''\
;; -*- mode: beancount -*-
**** /path/to/test.csv
1970-01-01 * "Test"
Assets:Tests 10.00 USD
; 1970-01-01 * "Test"
; Assets:Tests 10.00 USD
'''))
def test_print_extracted_entries(self):
entries, error, options = parser.parse_string(
textwrap.dedent('''
1970-01-01 * "Test"
Assets:Tests 10.00 USD'''))
extracted = [
('/path/to/test.csv', entries),
('/path/to/empty.pdf', []),
]
output = io.StringIO()
extract.print_extracted_entries(extracted, output)
self.assertEqual(
output.getvalue(),
textwrap.dedent('''\
;; -*- mode: beancount -*-
**** /path/to/test.csv
1970-01-01 * "Test"
Assets:Tests 10.00 USD
**** /path/to/empty.pdf
'''))
def test_print_extracted_entries(self, mock_extract_from_file):
entries, _, __ = parser.parse_string("""
2016-02-01 * "A"
Assets:Account1 11.11 USD
Assets:Account2 -11.11 USD
2016-02-01 * "B"
Assets:Account1 22.22 USD
Assets:Account3 -22.22 USD
""")
mock_extract_from_file.return_value = entries
entries[-2].meta[extract.DUPLICATE_META] = True
oss = io.StringIO()
extract.print_extracted_entries(entries, oss)
self.assertEqual(
textwrap.dedent("""\
; 2016-02-01 * "A"
; Assets:Account1 11.11 USD
; Assets:Account2 -11.11 USD
2016-02-01 * "B"
Assets:Account1 22.22 USD
Assets:Account3 -22.22 USD
""").strip(),
oss.getvalue().strip())
def _extract(ctx, src, output, existing, reverse, failfast, quiet):
"""Extract transactions from documents.
Walk the SRC list of files or directories and extract the ledger
entries from each file identified by one of the configured
importers. The entries are written to the specified output file
or to the standard output in Beancount ledger format in sections
associated to the source document.
"""
verbosity = -quiet
log = utils.logger(verbosity, err=True)
errors = exceptions.ExceptionsTrap(log)
# Load the ledger, if one is specified.
existing_entries = loader.load_file(existing)[0] if existing else []
extracted = []
for filename in _walk(src, log):
with errors:
importer = identify.identify(ctx.importers, filename)
if not importer:
log('') # Newline.
continue
# Signal processing of this document.
log(' ...', nl=False)
# Extract entries.
entries = extract.extract_from_file(importer, filename,
existing_entries)
extracted.append((filename, entries))
log(' OK', fg='green')
if failfast and errors:
break
# Invoke hooks.
hooks = [extract.find_duplicate_entries
] if ctx.hooks is None else ctx.hooks
for func in hooks:
extracted = func(extracted, existing_entries)
# Reverse sort order, if requested.
if reverse:
for filename, entries in extracted:
entries.reverse()
# Serialize entries.
extract.print_extracted_entries(extracted, output)
if errors:
sys.exit(1)