def run_filetype_test(filename, result_dict, filetype, evaluate_scraper,
allowed_mimetypes=[]):
"""
Runs scraper result evaluation for a scraper with forced MIME type/version
:filename: Name of the file, not containing the tests/data/mime_type/ part
:result_dict: Result dict to be given to Correct
:filetype: A dict containing the forced, expected and real file types under
the following keys:
* given_mimetype: the forced MIME type
* given_version: the forced version
* expected_mimetype: the expected resulting MIME type
* expected_version: the expected resulting version
* correct_mimetype: the real MIME type of the file
"""
correct = force_correct_filetype(filename, result_dict,
filetype, allowed_mimetypes)
if correct.mimetype == "application/xhtml+xml":
correct.streams[0]["stream_type"] = "text"
if filetype["given_mimetype"]:
mimetype_guess = filetype["given_mimetype"]
else:
mimetype_guess = filetype["correct_mimetype"]
params = {"mimetype": filetype["given_mimetype"],
"version": filetype["given_version"],
"mimetype_guess": mimetype_guess}
scraper = PilScraper(correct.filename, True, params)
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_is_supported(mime, ver):
"""
Test is_supported method.
:mime: MIME type
:ver: File format version
"""
assert PilScraper.is_supported(mime, ver, True)
assert PilScraper.is_supported(mime, None, True)
assert PilScraper.is_supported(mime, ver, False)
assert PilScraper.is_supported(mime, "foo", True)
assert not PilScraper.is_supported("foo", ver, True)
def test_scraper_gif(filename, result_dict, evaluate_scraper):
"""Test scraper with gif files."""
correct = parse_results(filename, "image/gif",
result_dict, True)
# GIF is an index image
if correct.well_formed:
correct.streams[0]["samples_per_pixel"] = "1"
for stream in correct.streams.values():
stream["version"] = "(:unav)"
if correct.well_formed:
correct.stdout_part = VALID_MSG
correct.stderr_part = ""
else:
correct.stdout_part = ""
correct.stderr_part = INVALID_MSG
scraper = PilScraper(correct.filename, True, correct.params)
scraper.scrape_file()
if correct.well_formed:
evaluate_scraper(scraper, correct)
else:
assert not scraper.well_formed
assert partial_message_included(correct.stdout_part, scraper.messages())
assert partial_message_included(correct.stderr_part, scraper.errors())
assert not scraper.streams
def test_scraper_tif(filename, result_dict, evaluate_scraper):
"""
Test scraper with tiff files.
:filename: Test file name
:result_dict: Result dict containing the test purpose, parts of
expected results of stdout and stderr, and expected streams
"""
correct = parse_results(filename, "image/tiff",
result_dict, True)
if correct.well_formed:
correct.stdout_part = VALID_MSG
correct.stderr_part = ""
else:
correct.stdout_part = ""
correct.stderr_part = INVALID_MSG
scraper = PilScraper(filename=correct.filename, mimetype="image/tiff")
scraper.scrape_file()
if correct.well_formed:
for index, _ in enumerate(correct.streams):
correct.streams[index]["version"] = UNAV
evaluate_scraper(scraper, correct)
else:
assert not scraper.well_formed
assert partial_message_included(correct.stdout_part,
scraper.messages())
assert partial_message_included(correct.stderr_part,
scraper.errors())
assert not scraper.streams
def test_scraper_gif(filename, result_dict, evaluate_scraper):
"""
Test scraper with gif files.
:filename: Test file name
:result_dict: Result dict containing the test purpose, parts of
expected results of stdout and stderr, and expected streams
"""
correct = parse_results(filename, "image/gif", result_dict, True)
# GIF is an index image
if correct.well_formed:
correct.streams[0]["samples_per_pixel"] = "1"
for stream in correct.streams.values():
stream["version"] = UNAV
if correct.well_formed:
correct.stdout_part = VALID_MSG
correct.stderr_part = ""
else:
correct.stdout_part = ""
correct.stderr_part = INVALID_MSG
scraper = PilScraper(filename=correct.filename, mimetype="image/gif")
scraper.scrape_file()
if correct.well_formed:
evaluate_scraper(scraper, correct)
else:
assert not scraper.well_formed
assert partial_message_included(correct.stdout_part,
scraper.messages())
assert partial_message_included(correct.stderr_part,
scraper.errors())
assert not scraper.streams
def test_scraper_jp2(filename, result_dict, evaluate_scraper):
"""Test scraper with jp2 files."""
correct = parse_results(filename, "image/jp2",
result_dict, True)
if correct.well_formed:
correct.stdout_part = VALID_MSG
correct.stderr_part = ""
else:
correct.stdout_part = ""
correct.stderr_part = INVALID_MSG
scraper = PilScraper(correct.filename, True, correct.params)
scraper.scrape_file()
if correct.well_formed:
evaluate_scraper(scraper, correct)
else:
assert not scraper.well_formed
assert partial_message_included(correct.stdout_part, scraper.messages())
assert partial_message_included(correct.stderr_part, scraper.errors())
assert not scraper.streams
def test_scraper_tif(filename, result_dict, evaluate_scraper):
"""Test scraper with tiff files."""
correct = parse_results(filename, "image/tiff",
result_dict, True)
if correct.well_formed:
correct.stdout_part = VALID_MSG
correct.stderr_part = ""
else:
correct.stdout_part = ""
correct.stderr_part = INVALID_MSG
scraper = PilScraper(correct.filename, True, correct.params)
scraper.scrape_file()
if correct.well_formed:
for index in range(0, len(correct.streams)):
correct.streams[index]["version"] = "(:unav)"
evaluate_scraper(scraper, correct)
else:
assert not scraper.well_formed
assert partial_message_included(correct.stdout_part, scraper.messages())
assert partial_message_included(correct.stderr_part, scraper.errors())
assert not scraper.streams
def test_no_wellformed():
"""Test scraper without well-formed check."""
scraper = PilScraper("tests/data/image_gif/valid_1987a.gif", False)
scraper.scrape_file()
assert not partial_message_included("Skipping scraper", scraper.messages())
assert scraper.well_formed is None