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 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 = WandScraper(correct.filename, True, params)
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_scraper_jpg(filename, result_dict, evaluate_scraper):
"""Test scraper with jpeg files."""
correct = parse_results(filename, "image/jpeg", result_dict, True)
if correct.well_formed:
correct.streams[0]["compression"] = "jpeg"
correct.streams[0]["version"] = "(:unav)"
scraper = WandScraper(correct.filename)
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_scraper_colorspace(mimetype, filename, expected):
"""
Test that correct colorspace is returned.
"""
scraper = WandScraper(filename=os.path.join("tests/data/",
mimetype.replace("/", "_"),
filename),
mimetype=mimetype)
scraper.scrape_file()
assert scraper.streams[0].colorspace().lower() == expected.lower()
def test_scraper_invalid(filename, mimetype, stderr_part):
"""Test WandScraper with invalid tiff files."""
scraper = WandScraper(
os.path.join("tests/data/", mimetype.replace("/", "_"), filename))
scraper.scrape_file()
assert not scraper.streams
assert scraper.info()["class"] == "WandScraper"
assert not scraper.messages()
assert partial_message_included(stderr_part, scraper.errors())
assert not scraper.well_formed
def test_scraper_gif(filename, result_dict, evaluate_scraper):
"""Test scraper with gif files."""
correct = parse_results(filename, "image/gif", result_dict, True)
if correct.well_formed:
correct.streams[0]["compression"] = "lzw"
for stream in correct.streams.values():
stream["version"] = "(:unav)"
scraper = WandScraper(correct.filename)
scraper.scrape_file()
evaluate_scraper(scraper, correct)
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.streams[0]["compression"] = "jpeg2000"
correct.streams[0]["colorspace"] = "rgb"
correct.version = None
scraper = WandScraper(correct.filename)
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_scraper_jpg(filename, result_dict, evaluate_scraper):
"""
Test scraper with valid jpeg 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/jpeg", result_dict, True)
if correct.well_formed:
correct.streams[0]["compression"] = "jpeg"
scraper = WandScraper(filename=correct.filename, mimetype="image/jpeg")
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_scraper_tif(filename, result_dict, evaluate_scraper):
"""Test scraper with valid tiff files."""
correct = parse_results(filename, "image/tiff", result_dict, True)
for index in range(0, len(correct.streams)):
correct.streams[index]["compression"] = "zip"
correct.streams[index]["byte_order"] = "little endian"
correct.streams[index]["mimetype"] = \
correct.streams[0]["mimetype"]
correct.streams[index]["stream_type"] = \
correct.streams[0]["stream_type"]
correct.streams[index]["version"] = "(:unav)"
scraper = WandScraper(correct.filename)
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_scraper_gif(filename, result_dict, evaluate_scraper):
"""
Test scraper with valid 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)
if correct.well_formed:
correct.streams[0]["compression"] = "lzw"
for stream in correct.streams.values():
stream["version"] = UNAV
scraper = WandScraper(filename=correct.filename, mimetype="image/gif")
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_scraper_invalid(filename, mimetype, stderr_part):
"""
Test WandScraper with invalid files.
:filename: Test file name
:mimetype: File MIME type
:stderr_part: Part of the expected stderr
"""
scraper = WandScraper(filename=os.path.join("tests/data/",
mimetype.replace("/", "_"),
filename),
mimetype=mimetype)
scraper.scrape_file()
assert not scraper.streams
assert scraper.info()["class"] == "WandScraper"
assert not scraper.messages()
assert partial_message_included(stderr_part, scraper.errors())
assert not scraper.well_formed
def test_scraper_tif(filename, result_dict, evaluate_scraper):
"""
Test scraper with valid 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)
for index, _ in enumerate(correct.streams):
correct.streams[index]["compression"] = "zip"
correct.streams[index]["byte_order"] = "little endian"
correct.streams[index]["mimetype"] = \
correct.streams[0]["mimetype"]
correct.streams[index]["stream_type"] = \
correct.streams[0]["stream_type"]
correct.streams[index]["version"] = UNAV
scraper = WandScraper(filename=correct.filename, mimetype="image/tiff")
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_no_wellformed():
"""Test scraper without well-formed check."""
scraper = WandScraper("tests/data/image_tiff/valid_6.0.tif", False)
scraper.scrape_file()
assert not partial_message_included("Skipping scraper", scraper.messages())
assert scraper.well_formed is None