def test_no_wellformed():
"""Test scraper without well-formed check."""
scraper = GhostscriptScraper("tests/data/application_pdf/valid_1.4.pdf",
False)
scraper.scrape_file()
assert partial_message_included("Skipping scraper", scraper.messages())
assert scraper.well_formed is None
def test_jpeg2000_inside_pdf(evaluate_scraper):
"""
Test scraping a pdf file containing JPEG2000 image.
Default Ghostscript installation on CentOS 7 does not support pdf files
containing JPXDecode data. This test verifies that the installed version is
recent enough.
"""
filename = "valid_1.7_jpeg2000.pdf"
mimetype = "application/pdf"
result_dict = {
"purpose": "Test pdf with JPEG2000 inside it.",
"stdout_part": "Well-formed and valid",
"stderr_part": ""
}
correct = parse_results(filename, mimetype, result_dict, True)
scraper = GhostscriptScraper(correct.filename, True)
scraper.scrape_file()
# Ghostscript cannot handle version or MIME type
correct.version = "(:unav)"
correct.streams[0]["version"] = "(:unav)"
correct.mimetype = "(:unav)"
correct.streams[0]["mimetype"] = "(:unav)"
evaluate_scraper(scraper, correct, eval_output=False)
def test_is_supported():
"""Test is_supported method."""
mime = "application/pdf"
ver = "1.7"
assert GhostscriptScraper.is_supported(mime, ver, True)
assert GhostscriptScraper.is_supported(mime, None, True)
assert not GhostscriptScraper.is_supported(mime, ver, False)
assert not GhostscriptScraper.is_supported(mime, "foo", True)
assert not GhostscriptScraper.is_supported("foo", ver, True)
def test_forcing_filetype(filename, result_dict, filetype, evaluate_scraper):
"""Test forcing scraper to use a given MIME type and/or version."""
correct = force_correct_filetype(filename, result_dict, filetype,
"(:unav)")
params = {
"mimetype": filetype["given_mimetype"],
"version": filetype["given_version"]
}
scraper = GhostscriptScraper(correct.filename, True, params)
scraper.scrape_file()
evaluate_scraper(scraper, correct)
def test_scraper_pdf(filename, result_dict, evaluate_scraper):
"""
Test Ghostscript scraper.
:filename: Test filename. Character X is replaced with versions 1.7,
A-1a, A-2b, and A-3b. All of these files must be found.
:result_dict: Result dict containing the test purpose, and parts of
expected results of stdout and stderr
"""
for ver in ["1.7", "A-1a", "A-2b", "A-3b"]:
filename = filename.replace("X", ver)
correct = parse_results(filename, "application/pdf", result_dict, True)
scraper = GhostscriptScraper(filename=correct.filename,
mimetype="application/pdf")
scraper.scrape_file()
# Ghostscript cannot handle version or MIME type
correct.streams[0]["version"] = UNAV
correct.streams[0]["mimetype"] = UNAV
evaluate_scraper(scraper, correct, eval_output=False)
if scraper.well_formed:
assert not partial_message_included("Error", scraper.messages())
assert not scraper.errors()
else:
assert partial_message_included(correct.stderr_part,
scraper.errors())
assert partial_message_included(correct.stdout_part,
scraper.messages())
def test_scraper_pdf(filename, result_dict, evaluate_scraper):
"""Test scraper."""
for ver in ["1.7", "A-1a", "A-2b", "A-3b"]:
filename = filename.replace("X", ver)
correct = parse_results(filename, "application/pdf", result_dict, True)
scraper = GhostscriptScraper(correct.filename, True, correct.params)
scraper.scrape_file()
# Ghostscript cannot handle version or MIME type
correct.version = "(:unav)"
correct.streams[0]["version"] = "(:unav)"
correct.mimetype = "(:unav)"
correct.streams[0]["mimetype"] = "(:unav)"
evaluate_scraper(scraper, correct, eval_output=False)
if scraper.well_formed:
assert not partial_message_included("Error", scraper.messages())
assert not scraper.errors()
else:
assert partial_message_included(correct.stderr_part,
scraper.errors())
assert partial_message_included(correct.stdout_part,
scraper.messages())