def _scrape(filename, mimetype):
scraper = OfficeScraper(filename=os.path.join(BASEPATH,
mimetype.replace("/", "_"),
filename),
mimetype=mimetype)
scraper.scrape_file()
return scraper.well_formed
def test_is_supported(mime, ver):
"""Test is_supported method."""
assert OfficeScraper.is_supported(mime, ver, True)
assert OfficeScraper.is_supported(mime, None, True)
assert not OfficeScraper.is_supported(mime, ver, False)
assert OfficeScraper.is_supported(mime, "foo", True)
assert not OfficeScraper.is_supported("foo", ver, True)
def test_no_wellformed():
"""Test scraper without well-formed check."""
scraper = OfficeScraper("tests/data/application_msword/valid_11.0.doc",
False)
scraper.scrape_file()
assert partial_message_included("Skipping scraper", scraper.messages())
assert scraper.well_formed is None
def test_is_supported(mime, ver):
"""
Test is_supported method.
:mime: MIME type
:ver: File format version
"""
assert OfficeScraper.is_supported(mime, ver, True)
assert OfficeScraper.is_supported(mime, None, True)
assert not OfficeScraper.is_supported(mime, ver, False)
assert OfficeScraper.is_supported(mime, "foo", True)
assert not OfficeScraper.is_supported("foo", ver, True)
def test_scraper_invalid_file(filename, mimetype, evaluate_scraper):
"""Test scraper with invalid files."""
result_dict = {
"purpose": "Test invalid file.",
"stdout_part": "",
"stderr_part": "source file could not be loaded"
}
correct = parse_results(filename, mimetype, result_dict, True)
scraper = OfficeScraper(correct.filename, True, correct.params)
scraper.scrape_file()
correct.streams[0]["version"] = "(:unav)"
correct.streams[0]["mimetype"] = "(:unav)"
evaluate_scraper(scraper, correct)
def test_forced_filetype(result_dict, filetype, evaluate_scraper):
"""
Test using user-supplied MIME-types and versions.
"""
filetype[six.text_type(
"correct_mimetype")] = "application/vnd.oasis.opendocument.spreadsheet"
correct = force_correct_filetype("valid_1.1.ods", result_dict, filetype,
["(:unav)"])
params = {
"mimetype": filetype["given_mimetype"],
"version": filetype["given_version"]
}
scraper = OfficeScraper(correct.filename, True, params)
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_scraper_invalid_file(filename, mimetype, evaluate_scraper):
"""
Test scraper with invalid files.
:filename: Test file name
:mimetype: File MIME type
"""
result_dict = {
"purpose": "Test invalid file.",
"stdout_part": "",
"stderr_part": "source file could not be loaded"
}
correct = parse_results(filename, mimetype, result_dict, True)
scraper = OfficeScraper(filename=correct.filename, mimetype=mimetype)
scraper.scrape_file()
correct.streams[0]["version"] = UNAV
correct.streams[0]["mimetype"] = UNAV
evaluate_scraper(scraper, correct)
def test_scraper_correct_application(filename, mimetype, application):
"""
Test that the correct LibreOffice application is selected.
If all necessary LibreOffice components are not installed, some files may
be scraped with a different application than intended (e.g. using Impress
for ODG files), and this may work, but it should not be relied on. This
test makes sure that all components are present and they are used for the
correct files.
:filename: Test file name
:mimetype: File MIME type
:application: Correct office application
"""
testfile = os.path.join("tests/data", mimetype.replace("/", "_"), filename)
scraper = OfficeScraper(filename=testfile, mimetype=mimetype)
scraper.scrape_file()
assert partial_message_included("using filter : {}".format(application),
scraper.messages())
def test_scraper_valid_file(filename, mimetype, evaluate_scraper):
"""
Test valid files with scraper.
:filename: Test file name
:mimetype: File MIME type
"""
correct = parse_results(filename, mimetype, {}, True)
scraper = OfficeScraper(filename=correct.filename, mimetype=mimetype)
scraper.scrape_file()
correct.update_mimetype(UNAV)
correct.update_version(UNAV)
evaluate_scraper(scraper, correct, False)
assert scraper.messages()
assert not scraper.errors()
def test_scraper_valid_file(filename, mimetype, evaluate_scraper):
"""Test valid files with scraper."""
result_dict = {
"purpose": "Test valid file.",
"stdout_part": "",
"stderr_part": ""
}
correct = parse_results(filename, mimetype, result_dict, True)
scraper = OfficeScraper(correct.filename, True, correct.params)
scraper.scrape_file()
correct.streams[0]["version"] = "(:unav)"
correct.streams[0]["mimetype"] = "(:unav)"
evaluate_scraper(scraper, correct, False)
assert scraper.messages()
assert not scraper.errors()