D6455.diff
No OneTemporary
Actions

Size

41 KB

Subscribers

None

D6455.diff
View Options

	diff --git a/swh/web/tests/api/test_apiresponse.py b/swh/web/tests/api/test_apiresponse.py
	--- a/swh/web/tests/api/test_apiresponse.py
	+++ b/swh/web/tests/api/test_apiresponse.py
	@@ -22,7 +22,7 @@
	from swh.web.common.identifiers import gen_swhid
	from swh.web.common.utils import reverse
	from swh.web.tests.django_asserts import assert_contains
	-from swh.web.tests.strategies import content, directory, revision
	+from swh.web.tests.strategies import directory, revision
	from swh.web.tests.utils import check_http_get_response, check_http_post_response


	@@ -153,7 +153,7 @@
	assert "Traceback" in resp.data["traceback"]


	-@given(content(), directory(), revision())
	+@given(directory(), revision())
	def test_api_endpoints_have_cors_headers(client, content, directory, revision):
	url = reverse("api-1-stat-counters")

	diff --git a/swh/web/tests/api/test_utils.py b/swh/web/tests/api/test_utils.py
	--- a/swh/web/tests/api/test_utils.py
	+++ b/swh/web/tests/api/test_utils.py
	@@ -11,14 +11,7 @@
	from swh.web.api import utils
	from swh.web.common.origin_visits import get_origin_visits
	from swh.web.common.utils import resolve_branch_alias, reverse
	-from swh.web.tests.strategies import (
	- content,
	- directory,
	- origin,
	- release,
	- revision,
	- snapshot,
	-)
	+from swh.web.tests.strategies import directory, origin, release, revision, snapshot

	url_map = [
	{
	@@ -227,7 +220,6 @@
	assert utils.enrich_content({"id": "123"}) == {"id": "123"}


	-@given(content())
	def test_enrich_content_with_hashes(api_request_factory, content):

	for algo in DEFAULT_ALGORITHMS:
	@@ -262,7 +254,6 @@
	assert enriched_content == content_data


	-@given(content())
	def test_enrich_content_with_hashes_and_top_level_url(api_request_factory, content):

	for algo in DEFAULT_ALGORITHMS:
	diff --git a/swh/web/tests/api/views/test_content.py b/swh/web/tests/api/views/test_content.py
	--- a/swh/web/tests/api/views/test_content.py
	+++ b/swh/web/tests/api/views/test_content.py
	@@ -3,13 +3,11 @@
	# License: GNU Affero General Public License version 3, or any later version
	# See top-level LICENSE file for more information

	-from hypothesis import given
	import pytest

	from swh.web.common.utils import reverse
	from swh.web.tests.conftest import ctags_json_missing, fossology_missing
	from swh.web.tests.data import random_content
	-from swh.web.tests.strategies import content, contents_with_ctags
	from swh.web.tests.utils import (
	check_api_get_responses,
	check_api_post_responses,
	@@ -17,7 +15,6 @@
	)


	-@given(content())
	def test_api_content_filetype(api_client, indexer_data, content):
	indexer_data.content_add_mimetype(content["sha1"])
	url = reverse(
	@@ -68,7 +65,6 @@
	@pytest.mark.skipif(
	ctags_json_missing, reason="requires ctags with json output support"
	)
	-@given(contents_with_ctags())
	def test_api_content_symbol(api_client, indexer_data, contents_with_ctags):
	expected_data = {}
	for content_sha1 in contents_with_ctags["sha1s"]:
	@@ -136,7 +132,6 @@
	@pytest.mark.skipif(
	ctags_json_missing, reason="requires ctags with json output support"
	)
	-@given(content())
	def test_api_content_ctags(api_client, indexer_data, content):
	indexer_data.content_add_ctags(content["sha1"])
	url = reverse(
	@@ -155,7 +150,6 @@


	@pytest.mark.skipif(fossology_missing, reason="requires fossology-nomossa installed")
	-@given(content())
	def test_api_content_license(api_client, indexer_data, content):
	indexer_data.content_add_license(content["sha1"])
	url = reverse(
	@@ -191,7 +185,6 @@
	}


	-@given(content())
	def test_api_content_metadata(api_client, archive_data, content):
	url = reverse("api-1-content", {"q": "sha1:%s" % content["sha1"]})
	rv = check_api_get_responses(api_client, url, status_code=200)
	@@ -236,7 +229,6 @@
	}


	-@given(content())
	def test_api_content_raw_text(api_client, archive_data, content):
	url = reverse("api-1-content-raw", url_args={"q": "sha1:%s" % content["sha1"]})

	@@ -250,7 +242,6 @@
	assert rv.content == expected_data["data"]


	-@given(content())
	def test_api_content_raw_text_with_filename(api_client, archive_data, content):
	url = reverse(
	"api-1-content-raw",
	@@ -264,7 +255,6 @@
	assert rv.content == expected_data["data"]


	-@given(content())
	def test_api_check_content_known(api_client, content):
	url = reverse("api-1-content-known", url_args={"q": content["sha1"]})
	rv = check_api_get_responses(api_client, url, status_code=200)
	@@ -274,7 +264,6 @@
	}


	-@given(content())
	def test_api_check_content_known_post(api_client, content):
	url = reverse("api-1-content-known")
	rv = check_api_post_responses(
	@@ -298,7 +287,6 @@
	}


	-@given(content())
	def test_api_content_uppercase(api_client, content):
	url = reverse(
	"api-1-content-uppercase-checksum", url_args={"q": content["sha1"].upper()}
	diff --git a/swh/web/tests/api/views/test_identifiers.py b/swh/web/tests/api/views/test_identifiers.py
	--- a/swh/web/tests/api/views/test_identifiers.py
	+++ b/swh/web/tests/api/views/test_identifiers.py
	@@ -10,7 +10,6 @@
	from swh.web.common.utils import reverse
	from swh.web.tests.data import random_sha1
	from swh.web.tests.strategies import (
	- content,
	directory,
	origin,
	release,
	@@ -25,9 +24,9 @@
	from swh.web.tests.utils import check_api_get_responses, check_api_post_responses


	-@given(origin(), content(), directory(), release(), revision(), snapshot())
	+@given(origin(), directory(), release(), revision(), snapshot())
	def test_swhid_resolve_success(
	- api_client, client, origin, content, directory, release, revision, snapshot
	+ api_client, client, content, origin, directory, release, revision, snapshot
	):

	for obj_type, obj_id in (
	@@ -116,7 +115,7 @@
	check_api_get_responses(api_client, url, status_code=400)


	-@given(content(), directory(), release(), revision(), snapshot())
	+@given(directory(), release(), revision(), snapshot())
	def test_api_known_swhid_all_present(
	api_client, content, directory, release, revision, snapshot
	):
	@@ -135,7 +134,7 @@
	assert resp.data == {swhid: {"known": True} for swhid in input_swhids}


	-@given(content(), directory())
	+@given(directory())
	def test_api_known_swhid_some_present(api_client, content, directory):
	content_ = gen_swhid(ObjectType.CONTENT, content["sha1_git"])
	directory_ = gen_swhid(ObjectType.DIRECTORY, directory)
	diff --git a/swh/web/tests/api/views/test_release.py b/swh/web/tests/api/views/test_release.py
	--- a/swh/web/tests/api/views/test_release.py
	+++ b/swh/web/tests/api/views/test_release.py
	@@ -17,7 +17,7 @@
	)
	from swh.web.common.utils import reverse
	from swh.web.tests.data import random_sha1
	-from swh.web.tests.strategies import content, directory, release
	+from swh.web.tests.strategies import directory, release
	from swh.web.tests.utils import check_api_get_responses, check_http_get_response


	@@ -39,7 +39,7 @@
	assert rv.data == expected_release


	-@given(content(), directory(), release())
	+@given(directory(), release())
	def test_api_release_target_type_not_a_revision(
	api_client, archive_data, content, directory, release
	):
	diff --git a/swh/web/tests/api/views/test_revision.py b/swh/web/tests/api/views/test_revision.py
	--- a/swh/web/tests/api/views/test_revision.py
	+++ b/swh/web/tests/api/views/test_revision.py
	@@ -17,7 +17,7 @@
	from swh.web.api.utils import enrich_content, enrich_directory_entry, enrich_revision
	from swh.web.common.utils import reverse
	from swh.web.tests.data import random_sha1
	-from swh.web.tests.strategies import content, new_person, new_swh_date, revision
	+from swh.web.tests.strategies import new_person, new_swh_date, revision
	from swh.web.tests.utils import check_api_get_responses, check_http_get_response


	@@ -132,7 +132,7 @@
	}


	-@given(content(), new_person(), new_swh_date())
	+@given(new_person(), new_swh_date())
	def test_api_revision_directory_ok_returns_content(
	api_client, archive_data, content, person, date
	):
	diff --git a/swh/web/tests/browse/views/test_content.py b/swh/web/tests/browse/views/test_content.py
	--- a/swh/web/tests/browse/views/test_content.py
	+++ b/swh/web/tests/browse/views/test_content.py
	@@ -21,14 +21,6 @@
	from swh.web.common.utils import gen_path_info, reverse
	from swh.web.tests.django_asserts import assert_contains, assert_not_contains
	from swh.web.tests.strategies import (
	- content,
	- content_application_no_highlight,
	- content_image_type,
	- content_text,
	- content_text_no_highlight,
	- content_text_non_utf8,
	- content_unsupported_image_type_rendering,
	- content_utf8_detected_as_binary,
	invalid_sha1,
	origin_with_multiple_visits,
	unknown_content,
	@@ -36,23 +28,24 @@
	from swh.web.tests.utils import check_html_get_response, check_http_get_response


	-@given(content_text())
	-def test_content_view_text(client, archive_data, content):
	- sha1_git = content["sha1_git"]
	+def test_content_view_text(client, archive_data, content_text):
	+ sha1_git = content_text["sha1_git"]

	url = reverse(
	"browse-content",
	- url_args={"query_string": content["sha1"]},
	- query_params={"path": content["path"]},
	+ url_args={"query_string": content_text["sha1"]},
	+ query_params={"path": content_text["path"]},
	)

	- url_raw = reverse("browse-content-raw", url_args={"query_string": content["sha1"]})
	+ url_raw = reverse(
	+ "browse-content-raw", url_args={"query_string": content_text["sha1"]}
	+ )

	resp = check_html_get_response(
	client, url, status_code=200, template_used="browse/content.html"
	)

	- content_display = _process_content_for_display(archive_data, content)
	+ content_display = _process_content_for_display(archive_data, content_text)
	mimetype = content_display["mimetype"]

	if mimetype.startswith("text/"):
	@@ -67,9 +60,10 @@
	assert_not_contains(resp, "swh-metadata-popover")


	-@given(content_application_no_highlight(), content_text_no_highlight())
	-def test_content_view_no_highlight(client, archive_data, content_app, content_text):
	- for content_ in (content_app, content_text):
	+def test_content_view_no_highlight(
	+ client, archive_data, content_application_no_highlight, content_text_no_highlight
	+):
	+ for content_ in (content_application_no_highlight, content_text_no_highlight):
	content = content_
	sha1_git = content["sha1_git"]

	@@ -96,17 +90,18 @@
	assert_contains(resp, swh_cnt_id_url)


	-@given(content_text_non_utf8())
	-def test_content_view_no_utf8_text(client, archive_data, content):
	- sha1_git = content["sha1_git"]
	+def test_content_view_no_utf8_text(client, archive_data, content_text_non_utf8):
	+ sha1_git = content_text_non_utf8["sha1_git"]

	- url = reverse("browse-content", url_args={"query_string": content["sha1"]})
	+ url = reverse(
	+ "browse-content", url_args={"query_string": content_text_non_utf8["sha1"]}
	+ )

	resp = check_html_get_response(
	client, url, status_code=200, template_used="browse/content.html"
	)

	- content_display = _process_content_for_display(archive_data, content)
	+ content_display = _process_content_for_display(archive_data, content_text_non_utf8)

	swh_cnt_id = gen_swhid(ObjectType.CONTENT, sha1_git)
	swh_cnt_id_url = reverse("browse-swhid", url_args={"swhid": swh_cnt_id})
	@@ -114,33 +109,40 @@
	assert_contains(resp, escape(content_display["content_data"]))


	-@given(content_image_type())
	-def test_content_view_image(client, archive_data, content):
	- url = reverse("browse-content", url_args={"query_string": content["sha1"]})
	+def test_content_view_image(client, archive_data, content_image_type):
	+ url = reverse(
	+ "browse-content", url_args={"query_string": content_image_type["sha1"]}
	+ )

	- url_raw = reverse("browse-content-raw", url_args={"query_string": content["sha1"]})
	+ url_raw = reverse(
	+ "browse-content-raw", url_args={"query_string": content_image_type["sha1"]}
	+ )

	resp = check_html_get_response(
	client, url, status_code=200, template_used="browse/content.html"
	)

	- content_display = _process_content_for_display(archive_data, content)
	+ content_display = _process_content_for_display(archive_data, content_image_type)
	mimetype = content_display["mimetype"]
	content_data = content_display["content_data"]
	assert_contains(resp, '<img src="data:%s;base64,%s"/>' % (mimetype, content_data))
	assert_contains(resp, url_raw)


	-@given(content_unsupported_image_type_rendering())
	-def test_content_view_image_no_rendering(client, archive_data, content):
	- url = reverse("browse-content", url_args={"query_string": content["sha1"]})
	+def test_content_view_image_no_rendering(
	+ client, archive_data, content_unsupported_image_type_rendering
	+):
	+ url = reverse(
	+ "browse-content",
	+ url_args={"query_string": content_unsupported_image_type_rendering["sha1"]},
	+ )

	resp = check_html_get_response(
	client, url, status_code=200, template_used="browse/content.html"
	)

	- mimetype = content["mimetype"]
	- encoding = content["encoding"]
	+ mimetype = content_unsupported_image_type_rendering["mimetype"]
	+ encoding = content_unsupported_image_type_rendering["encoding"]
	assert_contains(
	resp,
	(
	@@ -150,13 +152,12 @@
	)


	-@given(content_text())
	-def test_content_view_text_with_path(client, archive_data, content):
	- path = content["path"]
	+def test_content_view_text_with_path(client, archive_data, content_text):
	+ path = content_text["path"]

	url = reverse(
	"browse-content",
	- url_args={"query_string": content["sha1"]},
	+ url_args={"query_string": content_text["sha1"]},
	query_params={"path": path},
	)

	@@ -166,11 +167,11 @@

	assert_contains(resp, '<nav class="bread-crumbs')

	- content_display = _process_content_for_display(archive_data, content)
	+ content_display = _process_content_for_display(archive_data, content_text)
	mimetype = content_display["mimetype"]

	if mimetype.startswith("text/"):
	- hljs_language = content["hljs_language"]
	+ hljs_language = content_text["hljs_language"]
	assert_contains(resp, '<code class="%s">' % hljs_language)
	assert_contains(resp, escape(content_display["content_data"]))

	@@ -186,7 +187,7 @@
	}

	swh_cnt_id = gen_swhid(
	- ObjectType.CONTENT, content["sha1_git"], metadata=swhid_context
	+ ObjectType.CONTENT, content_text["sha1_git"], metadata=swhid_context
	)
	swh_cnt_id_url = reverse("browse-swhid", url_args={"swhid": swh_cnt_id})
	assert_contains(resp, swh_cnt_id)
	@@ -214,14 +215,14 @@

	url_raw = reverse(
	"browse-content-raw",
	- url_args={"query_string": content["sha1"]},
	+ url_args={"query_string": content_text["sha1"]},
	query_params={"filename": filename},
	)
	assert_contains(resp, url_raw)

	url = reverse(
	"browse-content",
	- url_args={"query_string": content["sha1"]},
	+ url_args={"query_string": content_text["sha1"]},
	query_params={"path": filename},
	)

	@@ -234,7 +235,7 @@
	invalid_path = "%s/foo/bar/baz" % root_dir_sha1
	url = reverse(
	"browse-content",
	- url_args={"query_string": content["sha1"]},
	+ url_args={"query_string": content_text["sha1"]},
	query_params={"path": invalid_path},
	)

	@@ -243,25 +244,26 @@
	)


	-@given(content_text())
	-def test_content_raw_text(client, archive_data, content):
	- url = reverse("browse-content-raw", url_args={"query_string": content["sha1"]})
	+def test_content_raw_text(client, archive_data, content_text):
	+ url = reverse("browse-content-raw", url_args={"query_string": content_text["sha1"]})

	resp = check_http_get_response(
	client, url, status_code=200, content_type="text/plain"
	)

	- content_data = archive_data.content_get_data(content["sha1"])["data"]
	+ content_data = archive_data.content_get_data(content_text["sha1"])["data"]

	assert resp["Content-Type"] == "text/plain"
	- assert resp["Content-disposition"] == ("filename=%s_%s" % ("sha1", content["sha1"]))
	+ assert resp["Content-disposition"] == (
	+ "filename=%s_%s" % ("sha1", content_text["sha1"])
	+ )
	assert resp.content == content_data

	- filename = content["path"].split("/")[-1]
	+ filename = content_text["path"].split("/")[-1]

	url = reverse(
	"browse-content-raw",
	- url_args={"query_string": content["sha1"]},
	+ url_args={"query_string": content_text["sha1"]},
	query_params={"filename": filename},
	)

	@@ -274,38 +276,40 @@
	assert resp.content == content_data


	-@given(content_text_non_utf8())
	-def test_content_raw_no_utf8_text(client, content):
	- url = reverse("browse-content-raw", url_args={"query_string": content["sha1"]})
	+def test_content_raw_no_utf8_text(client, content_text_non_utf8):
	+ url = reverse(
	+ "browse-content-raw", url_args={"query_string": content_text_non_utf8["sha1"]}
	+ )

	resp = check_http_get_response(
	client, url, status_code=200, content_type="text/plain"
	)
	_, encoding = get_mimetype_and_encoding_for_content(resp.content)
	- assert encoding == content["encoding"]
	+ assert encoding == content_text_non_utf8["encoding"]


	-@given(content_image_type())
	-def test_content_raw_bin(client, archive_data, content):
	- url = reverse("browse-content-raw", url_args={"query_string": content["sha1"]})
	+def test_content_raw_bin(client, archive_data, content_image_type):
	+ url = reverse(
	+ "browse-content-raw", url_args={"query_string": content_image_type["sha1"]}
	+ )

	resp = check_http_get_response(
	client, url, status_code=200, content_type="application/octet-stream"
	)

	- filename = content["path"].split("/")[-1]
	- content_data = archive_data.content_get_data(content["sha1"])["data"]
	+ filename = content_image_type["path"].split("/")[-1]
	+ content_data = archive_data.content_get_data(content_image_type["sha1"])["data"]

	assert resp["Content-Type"] == "application/octet-stream"
	assert resp["Content-disposition"] == "attachment; filename=%s_%s" % (
	"sha1",
	- content["sha1"],
	+ content_image_type["sha1"],
	)
	assert resp.content == content_data

	url = reverse(
	"browse-content-raw",
	- url_args={"query_string": content["sha1"]},
	+ url_args={"query_string": content_image_type["sha1"]},
	query_params={"filename": filename},
	)

	@@ -329,7 +333,6 @@
	)


	-@given(content())
	def test_content_bytes_missing(client, archive_data, mocker, content):
	mock_archive = mocker.patch("swh.web.browse.utils.archive")
	content_data = archive_data.content_get(content["sha1"])
	@@ -387,7 +390,6 @@
	assert_contains(resp, url_raw)


	-@given(content())
	def test_content_uppercase(client, content):
	url = reverse(
	"browse-content-uppercase-checksum",
	@@ -401,15 +403,21 @@
	assert resp["location"] == redirect_url


	-@given(content_utf8_detected_as_binary())
	-def test_content_utf8_detected_as_binary_display(client, archive_data, content):
	- url = reverse("browse-content", url_args={"query_string": content["sha1"]})
	+def test_content_utf8_detected_as_binary_display(
	+ client, archive_data, content_utf8_detected_as_binary
	+):
	+ url = reverse(
	+ "browse-content",
	+ url_args={"query_string": content_utf8_detected_as_binary["sha1"]},
	+ )

	resp = check_html_get_response(
	client, url, status_code=200, template_used="browse/content.html"
	)

	- content_display = _process_content_for_display(archive_data, content)
	+ content_display = _process_content_for_display(
	+ archive_data, content_utf8_detected_as_binary
	+ )

	assert_contains(resp, escape(content_display["content_data"]))

	diff --git a/swh/web/tests/browse/views/test_identifiers.py b/swh/web/tests/browse/views/test_identifiers.py
	--- a/swh/web/tests/browse/views/test_identifiers.py
	+++ b/swh/web/tests/browse/views/test_identifiers.py
	@@ -13,18 +13,10 @@
	from swh.web.common.identifiers import gen_swhid
	from swh.web.common.utils import reverse
	from swh.web.tests.django_asserts import assert_contains
	-from swh.web.tests.strategies import (
	- content,
	- directory,
	- origin,
	- release,
	- revision,
	- snapshot,
	-)
	+from swh.web.tests.strategies import directory, origin, release, revision, snapshot
	from swh.web.tests.utils import check_html_get_response


	-@given(content())
	def test_content_id_browse(client, content):
	cnt_sha1_git = content["sha1_git"]
	swhid = gen_swhid(ObjectType.CONTENT, cnt_sha1_git)
	@@ -149,7 +141,6 @@
	check_html_get_response(client, url, status_code=400)


	-@given(content())
	def test_content_id_optional_parts_browse(client, archive_data, content):
	cnt_sha1_git = content["sha1_git"]
	origin_url = "https://github.com/user/repo"
	diff --git a/swh/web/tests/common/test_archive.py b/swh/web/tests/common/test_archive.py
	--- a/swh/web/tests/common/test_archive.py
	+++ b/swh/web/tests/common/test_archive.py
	@@ -31,11 +31,7 @@
	from swh.web.tests.data import random_content, random_sha1
	from swh.web.tests.strategies import (
	ancestor_revisions,
	- content,
	- contents,
	- contents_with_ctags,
	directory,
	- empty_content,
	empty_directory,
	invalid_sha1,
	new_origin,
	@@ -59,7 +55,6 @@
	)


	-@given(contents())
	def test_lookup_multiple_hashes_all_present(contents):
	input_data = []
	expected_output = []
	@@ -70,7 +65,7 @@
	assert archive.lookup_multiple_hashes(input_data) == expected_output


	-@given(contents(), unknown_contents())
	+@given(unknown_contents())
	def test_lookup_multiple_hashes_some_missing(contents, unknown_contents):
	input_contents = list(itertools.chain(contents, unknown_contents))
	random.shuffle(input_contents)
	@@ -92,7 +87,6 @@
	assert actual_lookup == {"found": None, "algo": "sha1_git"}


	-@given(content())
	def test_lookup_hash_exist(archive_data, content):
	actual_lookup = archive.lookup_hash("sha1:%s" % content["sha1"])

	@@ -109,7 +103,6 @@
	assert {"found": False} == actual_lookup


	-@given(content())
	def test_search_hash_exist(content):
	actual_lookup = archive.search_hash("sha1:%s" % content["sha1"])

	@@ -119,7 +112,6 @@
	@pytest.mark.skipif(
	ctags_json_missing, reason="requires ctags with json output support"
	)
	-@given(contents_with_ctags())
	def test_lookup_content_ctags(indexer_data, contents_with_ctags):
	content_sha1 = random.choice(contents_with_ctags["sha1s"])
	indexer_data.content_add_ctags(content_sha1)
	@@ -142,7 +134,6 @@
	assert actual_ctags == []


	-@given(content())
	def test_lookup_content_filetype(indexer_data, content):
	indexer_data.content_add_mimetype(content["sha1"])
	actual_filetype = archive.lookup_content_filetype(content["sha1"])
	@@ -151,7 +142,6 @@
	assert actual_filetype == expected_filetype


	-@given(contents_with_ctags())
	def test_lookup_expression(indexer_data, contents_with_ctags):
	per_page = 10
	expected_ctags = []
	@@ -187,7 +177,6 @@


	@pytest.mark.skipif(fossology_missing, reason="requires fossology-nomossa installed")
	-@given(content())
	def test_lookup_content_license(indexer_data, content):
	indexer_data.content_add_license(content["sha1"])
	actual_license = archive.lookup_content_license(content["sha1"])
	@@ -627,7 +616,6 @@
	)


	-@given(content())
	def test_lookup_content_raw(archive_data, content):
	actual_content = archive.lookup_content_raw("sha256:%s" % content["sha256"])

	@@ -636,8 +624,7 @@
	assert actual_content == expected_content


	-@given(empty_content())
	-def test_lookup_empty_content_raw(archive_data, empty_content):
	+def test_lookup_empty_content_raw(empty_content):
	content_raw = archive.lookup_content_raw(f"sha1_git:{empty_content['sha1_git']}")
	assert content_raw["data"] == b""

	@@ -654,7 +641,6 @@
	)


	-@given(content())
	def test_lookup_content_with_sha1(archive_data, content):
	actual_content = archive.lookup_content(f"sha1:{content['sha1']}")

	@@ -663,7 +649,6 @@
	assert actual_content == expected_content


	-@given(content())
	def test_lookup_content_with_sha256(archive_data, content):
	actual_content = archive.lookup_content(f"sha256:{content['sha256']}")

	@@ -850,7 +835,7 @@
	)


	-@given(content(), directory(), release(), revision(), snapshot())
	+@given(directory(), release(), revision(), snapshot())
	def test_lookup_known_objects(
	archive_data, content, directory, release, revision, snapshot
	):
	@@ -955,8 +940,8 @@
	}


	-@given(content(), directory())
	-def test_lookup_missing_hashes_some_present(archive_data, content, directory):
	+@given(directory())
	+def test_lookup_missing_hashes_some_present(content, directory):
	missing_rev = random_sha1()
	missing_rel = random_sha1()
	missing_snp = random_sha1()
	diff --git a/swh/web/tests/common/test_identifiers.py b/swh/web/tests/common/test_identifiers.py
	--- a/swh/web/tests/common/test_identifiers.py
	+++ b/swh/web/tests/common/test_identifiers.py
	@@ -26,7 +26,6 @@
	from swh.web.common.utils import reverse
	from swh.web.tests.data import random_sha1
	from swh.web.tests.strategies import (
	- content,
	directory,
	directory_with_files,
	directory_with_subdirs,
	@@ -38,7 +37,6 @@
	)


	-@given(content())
	def test_gen_swhid(content):
	swh_object_type = ObjectType.CONTENT
	sha1_git = content["sha1_git"]
	@@ -74,7 +72,7 @@
	assert e.match("Invalid swh object type")


	-@given(content(), directory(), release(), revision(), snapshot())
	+@given(directory(), release(), revision(), snapshot())
	def test_resolve_swhid_legacy(content, directory, release, revision, snapshot):
	for obj_type, obj_id in (
	(ObjectType.CONTENT, content["sha1_git"]),
	@@ -111,7 +109,7 @@
	resolve_swhid(f"swh:1:ori:{random_sha1()}")


	-@given(content(), directory(), release(), revision(), snapshot())
	+@given(directory(), release(), revision(), snapshot())
	def test_get_swhid(content, directory, release, revision, snapshot):
	for obj_type, obj_id in (
	(ObjectType.CONTENT, content["sha1_git"]),
	@@ -130,7 +128,7 @@
	get_swhid("foo")


	-@given(content(), directory(), release(), revision(), snapshot())
	+@given(directory(), release(), revision(), snapshot())
	def test_group_swhids(content, directory, release, revision, snapshot):
	swhids = []
	expected = {}
	diff --git a/swh/web/tests/conftest.py b/swh/web/tests/conftest.py
	--- a/swh/web/tests/conftest.py
	+++ b/swh/web/tests/conftest.py
	@@ -6,6 +6,7 @@
	from datetime import timedelta
	import json
	import os
	+import random
	import shutil
	from subprocess import PIPE, run
	import sys
	@@ -20,7 +21,14 @@
	from django.test.utils import setup_databases # type: ignore
	from rest_framework.test import APIClient, APIRequestFactory

	-from swh.model.hashutil import ALGORITHMS, hash_to_bytes
	+from swh.model.hashutil import (
	+ ALGORITHMS,
	+ DEFAULT_ALGORITHMS,
	+ hash_to_bytes,
	+ hash_to_hex,
	+)
	+from swh.model.model import Content
	+from swh.model.swhids import ObjectType
	from swh.scheduler.tests.common import TASK_TYPES
	from swh.storage.algos.origin import origin_get_latest_visit_status
	from swh.storage.algos.snapshot import snapshot_get_all_branches, snapshot_get_latest
	@@ -28,6 +36,7 @@
	from swh.web.common import converters
	from swh.web.common.origin_save import get_scheduler_load_task_types
	from swh.web.common.typing import OriginVisitInfo
	+from swh.web.common.utils import browsers_supported_image_mimes
	from swh.web.config import get_config
	from swh.web.tests.data import get_tests_data, override_storages

	@@ -155,6 +164,197 @@
	return data


	+def _known_swh_objects(tests_data, object_type):
	+ return tests_data[object_type]
	+
	+
	+@pytest.fixture(scope="function")
	+def content(tests_data):
	+ """Fixture returning a random content ingested into the test archive.
	+ """
	+ return random.choice(_known_swh_objects(tests_data, "contents"))
	+
	+
	+@pytest.fixture(scope="function")
	+def contents(tests_data):
	+ """Fixture returning random contents ingested into the test archive.
	+ """
	+ return random.choices(
	+ _known_swh_objects(tests_data, "contents"), k=random.randint(2, 8)
	+ )
	+
	+
	+@pytest.fixture(scope="function")
	+def empty_content():
	+ """Fixture returning the empty content ingested into the test archive.
	+ """
	+ empty_content = Content.from_data(data=b"").to_dict()
	+ for algo in DEFAULT_ALGORITHMS:
	+ empty_content[algo] = hash_to_hex(empty_content[algo])
	+ return empty_content
	+
	+
	+@pytest.fixture(scope="function")
	+def content_text(tests_data):
	+ """
	+ Fixture returning a random textual content ingested into the test archive.
	+ """
	+ return random.choice(
	+ list(
	+ filter(
	+ lambda c: c["mimetype"].startswith("text/"),
	+ _known_swh_objects(tests_data, "contents"),
	+ )
	+ )
	+ )
	+
	+
	+@pytest.fixture(scope="function")
	+def content_text_non_utf8(tests_data):
	+ """Fixture returning a random textual content not encoded to UTF-8 ingested
	+ into the test archive.
	+ """
	+ return random.choice(
	+ list(
	+ filter(
	+ lambda c: c["mimetype"].startswith("text/")
	+ and c["encoding"] not in ("utf-8", "us-ascii"),
	+ _known_swh_objects(tests_data, "contents"),
	+ )
	+ )
	+ )
	+
	+
	+@pytest.fixture(scope="function")
	+def content_application_no_highlight(tests_data):
	+ """Fixture returning a random textual content with mimetype
	+ starting with application/ and no detected programming language to
	+ highlight ingested into the test archive.
	+ """
	+ return random.choice(
	+ list(
	+ filter(
	+ lambda c: c["mimetype"].startswith("application/")
	+ and c["encoding"] != "binary"
	+ and c["hljs_language"] == "nohighlight",
	+ _known_swh_objects(tests_data, "contents"),
	+ )
	+ )
	+ )
	+
	+
	+@pytest.fixture(scope="function")
	+def content_text_no_highlight(tests_data):
	+ """Fixture returning a random textual content with no detected
	+ programming language to highlight ingested into the test archive.
	+ """
	+ return random.choice(
	+ list(
	+ filter(
	+ lambda c: c["mimetype"].startswith("text/")
	+ and c["hljs_language"] == "nohighlight",
	+ _known_swh_objects(tests_data, "contents"),
	+ )
	+ )
	+ )
	+
	+
	+@pytest.fixture(scope="function")
	+def content_image_type(tests_data):
	+ """Fixture returning a random image content ingested into the test archive.
	+ """
	+ return random.choice(
	+ list(
	+ filter(
	+ lambda c: c["mimetype"] in browsers_supported_image_mimes,
	+ _known_swh_objects(tests_data, "contents"),
	+ )
	+ )
	+ )
	+
	+
	+@pytest.fixture(scope="function")
	+def content_unsupported_image_type_rendering(tests_data):
	+ """Fixture returning a random image content ingested into the test archive that
	+ can not be rendered by browsers.
	+ """
	+ return random.choice(
	+ list(
	+ filter(
	+ lambda c: c["mimetype"].startswith("image/")
	+ and c["mimetype"] not in browsers_supported_image_mimes,
	+ _known_swh_objects(tests_data, "contents"),
	+ )
	+ )
	+ )
	+
	+
	+@pytest.fixture(scope="function")
	+def content_utf8_detected_as_binary(tests_data):
	+ """Fixture returning a random textual content detected as binary
	+ by libmagic while they are valid UTF-8 encoded files.
	+ """
	+
	+ def utf8_binary_detected(content):
	+ if content["encoding"] != "binary":
	+ return False
	+ try:
	+ content["raw_data"].decode("utf-8")
	+ except Exception:
	+ return False
	+ else:
	+ return True
	+
	+ return random.choice(
	+ list(filter(utf8_binary_detected, _known_swh_objects(tests_data, "contents")))
	+ )
	+
	+
	+@pytest.fixture(scope="function")
	+def contents_with_ctags():
	+ """
	+ Fixture returning contents ingested into the test archive.
	+ Those contents are ctags compatible, that is running ctags on those lay results.
	+ """
	+ return {
	+ "sha1s": [
	+ "0ab37c02043ebff946c1937523f60aadd0844351",
	+ "15554cf7608dde6bfefac7e3d525596343a85b6f",
	+ "2ce837f1489bdfb8faf3ebcc7e72421b5bea83bd",
	+ "30acd0b47fc25e159e27a980102ddb1c4bea0b95",
	+ "4f81f05aaea3efb981f9d90144f746d6b682285b",
	+ "5153aa4b6e4455a62525bc4de38ed0ff6e7dd682",
	+ "59d08bafa6a749110dfb65ba43a61963d5a5bf9f",
	+ "7568285b2d7f31ae483ae71617bd3db873deaa2c",
	+ "7ed3ee8e94ac52ba983dd7690bdc9ab7618247b4",
	+ "8ed7ef2e7ff9ed845e10259d08e4145f1b3b5b03",
	+ "9b3557f1ab4111c8607a4f2ea3c1e53c6992916c",
	+ "9c20da07ed14dc4fcd3ca2b055af99b2598d8bdd",
	+ "c20ceebd6ec6f7a19b5c3aebc512a12fbdc9234b",
	+ "e89e55a12def4cd54d5bff58378a3b5119878eb7",
	+ "e8c0654fe2d75ecd7e0b01bee8a8fc60a130097e",
	+ "eb6595e559a1d34a2b41e8d4835e0e4f98a5d2b5",
	+ ],
	+ "symbol_name": "ABS",
	+ }
	+
	+
	+@pytest.fixture(scope="function")
	+def content_swhid(tests_data):
	+ """
	+ Fixture returning a qualified SWHID for a random content object
	+ ingested into the test archive.
	+ """
	+ return random.choice(
	+ list(
	+ filter(
	+ lambda swhid: swhid.object_type == ObjectType.CONTENT,
	+ _known_swh_objects(tests_data, "swhids"),
	+ )
	+ )
	+ )
	+
	+
	# Fixture to manipulate data from a sample archive used in the tests
	@pytest.fixture(scope="function")
	def archive_data(tests_data):
	diff --git a/swh/web/tests/misc/test_badges.py b/swh/web/tests/misc/test_badges.py
	--- a/swh/web/tests/misc/test_badges.py
	+++ b/swh/web/tests/misc/test_badges.py
	@@ -14,7 +14,6 @@
	from swh.web.misc.badges import _badge_config, _get_logo_data
	from swh.web.tests.django_asserts import assert_contains
	from swh.web.tests.strategies import (
	- content,
	directory,
	invalid_sha1,
	new_origin,
	@@ -31,7 +30,6 @@
	from swh.web.tests.utils import check_http_get_response


	-@given(content())
	def test_content_badge(client, content):
	_test_badge_endpoints(client, "content", content["sha1_git"])

	diff --git a/swh/web/tests/misc/test_iframe.py b/swh/web/tests/misc/test_iframe.py
	--- a/swh/web/tests/misc/test_iframe.py
	+++ b/swh/web/tests/misc/test_iframe.py
	@@ -8,16 +8,10 @@
	from swh.model.hashutil import hash_to_bytes
	from swh.model.swhids import CoreSWHID, ObjectType
	from swh.web.common.utils import reverse
	-from swh.web.tests.strategies import (
	- content_swhid,
	- directory_swhid,
	- revision_swhid,
	- unknown_directory,
	-)
	+from swh.web.tests.strategies import directory_swhid, revision_swhid, unknown_directory
	from swh.web.tests.utils import check_html_get_response


	-@given(content_swhid())
	def test_content_swhid_iframe(client, content_swhid):
	url = reverse("swhid-iframe", url_args={"swhid": str(content_swhid)})
	check_html_get_response(
	@@ -25,7 +19,6 @@
	)


	-@given(content_swhid())
	def test_content_core_swhid_iframe(client, content_swhid):
	content_core_swhid = CoreSWHID(
	object_type=content_swhid.object_type, object_id=content_swhid.object_id
	@@ -74,7 +67,6 @@
	)


	-@given(content_swhid())
	def test_swhid_iframe_unknown_error(client, mocker, content_swhid):
	mocker.patch("swh.web.misc.iframe.get_swhid").side_effect = Exception("Error")
	url = reverse("swhid-iframe", url_args={"swhid": str(content_swhid)})
	diff --git a/swh/web/tests/strategies.py b/swh/web/tests/strategies.py
	--- a/swh/web/tests/strategies.py
	+++ b/swh/web/tests/strategies.py
	@@ -20,11 +20,10 @@
	text,
	)

	-from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex
	+from swh.model.hashutil import hash_to_bytes, hash_to_hex
	from swh.model.hypothesis_strategies import origins as new_origin_strategy
	from swh.model.hypothesis_strategies import snapshots as new_snapshot
	from swh.model.model import (
	- Content,
	Directory,
	Person,
	Revision,
	@@ -34,7 +33,6 @@
	from swh.model.swhids import ObjectType
	from swh.storage.algos.revisions_walker import get_revisions_walker
	from swh.storage.algos.snapshot import snapshot_get_latest
	-from swh.web.common.utils import browsers_supported_image_mimes
	from swh.web.tests.data import get_tests_data

	# Module dedicated to the generation of input data for tests through
	@@ -76,114 +74,6 @@
	return binary(min_size=32, max_size=32).map(hash_to_hex)


	-def content():
	- """
	- Hypothesis strategy returning a random content ingested
	- into the test archive.
	- """
	- return _known_swh_object("contents")
	-
	-
	-def contents():
	- """
	- Hypothesis strategy returning random contents ingested
	- into the test archive.
	- """
	- return lists(content(), min_size=2, max_size=8)
	-
	-
	-def empty_content():
	- """
	- Hypothesis strategy returning the empty content ingested
	- into the test archive.
	- """
	- empty_content = Content.from_data(data=b"").to_dict()
	- for algo in DEFAULT_ALGORITHMS:
	- empty_content[algo] = hash_to_hex(empty_content[algo])
	- return just(empty_content)
	-
	-
	-def content_text():
	- """
	- Hypothesis strategy returning random textual contents ingested
	- into the test archive.
	- """
	- return content().filter(lambda c: c["mimetype"].startswith("text/"))
	-
	-
	-def content_text_non_utf8():
	- """
	- Hypothesis strategy returning random textual contents not encoded
	- to UTF-8 ingested into the test archive.
	- """
	- return content().filter(
	- lambda c: c["mimetype"].startswith("text/")
	- and c["encoding"] not in ("utf-8", "us-ascii")
	- )
	-
	-
	-def content_application_no_highlight():
	- """
	- Hypothesis strategy returning random textual contents with mimetype
	- starting with application/ and no detected programming language to
	- highlight ingested into the test archive.
	- """
	- return content().filter(
	- lambda c: c["mimetype"].startswith("application/")
	- and c["encoding"] != "binary"
	- and c["hljs_language"] == "nohighlight"
	- )
	-
	-
	-def content_text_no_highlight():
	- """
	- Hypothesis strategy returning random textual contents with no detected
	- programming language to highlight ingested into the test archive.
	- """
	- return content().filter(
	- lambda c: c["mimetype"].startswith("text/")
	- and c["hljs_language"] == "nohighlight"
	- )
	-
	-
	-def content_image_type():
	- """
	- Hypothesis strategy returning random image contents ingested
	- into the test archive.
	- """
	- return content().filter(lambda c: c["mimetype"] in browsers_supported_image_mimes)
	-
	-
	-def content_unsupported_image_type_rendering():
	- """
	- Hypothesis strategy returning random image contents ingested
	- into the test archive that can not be rendered by browsers.
	- """
	- return content().filter(
	- lambda c: c["mimetype"].startswith("image/")
	- and c["mimetype"] not in browsers_supported_image_mimes
	- )
	-
	-
	-def content_utf8_detected_as_binary():
	- """
	- Hypothesis strategy returning random textual contents detected as binary
	- by libmagic while they are valid UTF-8 encoded files.
	- """
	-
	- def utf8_binary_detected(content):
	- if content["encoding"] != "binary":
	- return False
	- try:
	- content["raw_data"].decode("utf-8")
	- except Exception:
	- return False
	- else:
	- return True
	-
	- return content().filter(utf8_binary_detected)
	-
	-
	@composite
	def new_content(draw):
	blake2s256_hex = draw(sha256())
	@@ -604,37 +494,6 @@
	# that can not be generated and thus are hardcoded.


	-def contents_with_ctags():
	- """
	- Hypothesis strategy returning contents ingested into the test
	- archive. Those contents are ctags compatible, that is running
	- ctags on those lay results.
	- """
	- return just(
	- {
	- "sha1s": [
	- "0ab37c02043ebff946c1937523f60aadd0844351",
	- "15554cf7608dde6bfefac7e3d525596343a85b6f",
	- "2ce837f1489bdfb8faf3ebcc7e72421b5bea83bd",
	- "30acd0b47fc25e159e27a980102ddb1c4bea0b95",
	- "4f81f05aaea3efb981f9d90144f746d6b682285b",
	- "5153aa4b6e4455a62525bc4de38ed0ff6e7dd682",
	- "59d08bafa6a749110dfb65ba43a61963d5a5bf9f",
	- "7568285b2d7f31ae483ae71617bd3db873deaa2c",
	- "7ed3ee8e94ac52ba983dd7690bdc9ab7618247b4",
	- "8ed7ef2e7ff9ed845e10259d08e4145f1b3b5b03",
	- "9b3557f1ab4111c8607a4f2ea3c1e53c6992916c",
	- "9c20da07ed14dc4fcd3ca2b055af99b2598d8bdd",
	- "c20ceebd6ec6f7a19b5c3aebc512a12fbdc9234b",
	- "e89e55a12def4cd54d5bff58378a3b5119878eb7",
	- "e8c0654fe2d75ecd7e0b01bee8a8fc60a130097e",
	- "eb6595e559a1d34a2b41e8d4835e0e4f98a5d2b5",
	- ],
	- "symbol_name": "ABS",
	- }
	- )
	-
	-
	def revision_with_submodules():
	"""
	Hypothesis strategy returning a revision that is known to
	@@ -657,14 +516,6 @@
	return _known_swh_object("swhids")


	-def content_swhid():
	- """
	- Hypothesis strategy returning a qualified SWHID for a content object
	- ingested into the test archive.
	- """
	- return swhid().filter(lambda swhid: swhid.object_type == ObjectType.CONTENT)
	-
	-
	def directory_swhid():
	"""
	Hypothesis strategy returning a qualified SWHID for a directory object

File Metadata

Mime Type: text/plain
Expires: Wed, Dec 18, 4:11 AM (22 h, 59 m ago)
Storage Engine: blob
Storage Format: Raw Data
Storage Handle: 3219097

D6455.diffNo OneTemporaryActions

D6455.diffView Options

File Metadata

Event Timeline

D6455.diff
No OneTemporary
Actions

D6455.diff
View Options