Integrity Check

Example

>>> # TEST PREPARATION
>>> import sys
>>> from io import StringIO
>>> from techminer2.thesaurus.user import InitializeThesaurus, IntegrityCheck

>>> # Redirecting stderr to avoid messages during doctests
>>> original_stderr = sys.stderr
>>> sys.stderr = StringIO()
>>> #

>>> # Reset the thesaurus to initial state
>>> InitializeThesaurus(thesaurus_file="demo.the.txt", field="raw_descriptors",
...     root_directory="examples/fintech/", quiet=True).run()

>>> # Creates, configures, an run the integrity checker
>>> checker = (
...     IntegrityCheck(use_colorama=False)
...     .with_thesaurus_file("demo.the.txt")
...     .with_field("raw_descriptors")
...     .where_root_directory_is("examples/fintech/")
... )
>>> checker.run()

>>> # Capture and print stderr output to test the code using doctest
>>> output = sys.stderr.getvalue()
>>> sys.stderr = original_stderr
>>> print(output)  
Checking thesaurus integrity...
  File : examples/fintech/data/thesaurus/demo.the.txt
  1791 terms checked
  Integrity check completed successfully