diff --git a/requirements-test.txt b/requirements-test.txt
index f2f50fc4..966983a9 100644
--- a/requirements-test.txt
+++ b/requirements-test.txt
@@ -1,18 +1,19 @@
decorator # dependency of swh.core[http]
djangorestframework-stubs
django-stubs
django-test-migrations
hypothesis
pytest < 7.0.0 # v7.0.0 removed _pytest.tmpdir.TempdirFactory, which is used by some of the pytest plugins we use
pytest-django
pytest-mock
pytest-postgresql
requests-mock != 1.9.0, != 1.9.1
swh.core[http] >= 0.0.95
swh.loader.git >= 0.8.0
swh-scheduler[testing] >= 0.5.0
swh.storage >= 0.1.1
+types-chardet
types-docutils
types-psycopg2
types-pyyaml
types-requests
diff --git a/requirements.txt b/requirements.txt
index e8bc3ef5..7bb1e6e1 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,25 +1,26 @@
# Add here external Python modules dependencies, one per line. Module names
# should match https://pypi.python.org/pypi names. For the full spec or
# dependency lines, see https://pip.readthedocs.org/en/1.1/requirements.html
beautifulsoup4
+chardet
cryptography
django < 3
django-cors-headers
django-js-reverse
djangorestframework
django-webpack-loader
docutils
htmlmin
iso8601
lxml
prometheus-client
pybadges >= 2.2.1
pygments
python-magic >= 0.4.0
python-memcached
pyyaml
requests
sentry-sdk
typing-extensions
psycopg2 < 2.9
diff --git a/swh/web/browse/utils.py b/swh/web/browse/utils.py
index a40777c2..8dfc4898 100644
--- a/swh/web/browse/utils.py
+++ b/swh/web/browse/utils.py
@@ -1,714 +1,734 @@
# Copyright (C) 2017-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU Affero General Public License version 3, or any later version
# See top-level LICENSE file for more information
import base64
import stat
import textwrap
+from typing import Tuple
+import chardet
import magic
import sentry_sdk
from django.core.cache import cache
from django.utils.html import escape
from django.utils.safestring import mark_safe
from swh.web.common import archive, highlightjs
from swh.web.common.exc import NotFoundExc
from swh.web.common.utils import (
browsers_supported_image_mimes,
format_utc_iso_date,
reverse,
rst_to_html,
)
from swh.web.config import get_config
def get_directory_entries(sha1_git):
"""Function that retrieves the content of a directory
from the archive.
The directories entries are first sorted in lexicographical order.
Sub-directories and regular files are then extracted.
Args:
sha1_git: sha1_git identifier of the directory
Returns:
A tuple whose first member corresponds to the sub-directories list
and second member the regular files list
Raises:
NotFoundExc if the directory is not found
"""
cache_entry_id = "directory_entries_%s" % sha1_git
cache_entry = cache.get(cache_entry_id)
if cache_entry:
return cache_entry
entries = list(archive.lookup_directory(sha1_git))
for e in entries:
e["perms"] = stat.filemode(e["perms"])
if e["type"] == "rev":
# modify dir entry name to explicitly show it points
# to a revision
e["name"] = "%s @ %s" % (e["name"], e["target"][:7])
dirs = [e for e in entries if e["type"] in ("dir", "rev")]
files = [e for e in entries if e["type"] == "file"]
dirs = sorted(dirs, key=lambda d: d["name"])
files = sorted(files, key=lambda f: f["name"])
cache.set(cache_entry_id, (dirs, files))
return dirs, files
def get_mimetype_and_encoding_for_content(content):
"""Function that returns the mime type and the encoding associated to
a content buffer using the magic module under the hood.
Args:
content (bytes): a content buffer
Returns:
A tuple (mimetype, encoding), for instance ('text/plain', 'us-ascii'),
associated to the provided content.
"""
m = magic.Magic(mime=True, mime_encoding=True)
mime_encoding = m.from_buffer(content)
mime_type, encoding = mime_encoding.split(";")
encoding = encoding.replace(" charset=", "")
return mime_type, encoding
# maximum authorized content size in bytes for HTML display
# with code highlighting
content_display_max_size = get_config()["content_display_max_size"]
-def _re_encode_content(mimetype, encoding, content_data):
- # encode textual content to utf-8 if needed
- if mimetype.startswith("text/"):
- # probably a malformed UTF-8 content, re-encode it
- # by replacing invalid chars with a substitution one
- if encoding == "unknown-8bit":
+def re_encode_content(
+ mimetype: str, encoding: str, content_data: bytes
+) -> Tuple[str, str, bytes]:
+ """Try to re-encode textual content if it is not encoded to UTF-8
+ for proper display in the browse Web UI.
+
+ Args:
+ mimetype: content mimetype as detected by python-magic
+ encoding: content encoding as detected by python-magic
+ content_data: raw content bytes
+
+ Returns:
+ A tuple with 3 members: content mimetype, content encoding (possibly updated
+ after processing), content raw bytes (possibly reencoded to UTF-8)
+ """
+ if mimetype.startswith("text/") and encoding not in ("us-ascii", "utf-8"):
+ # first check if chardet detects an encoding with confidence
+ result = chardet.detect(content_data)
+ if result["confidence"] >= 0.9:
+ encoding = result["encoding"]
+ content_data = content_data.decode(encoding).encode("utf-8")
+ elif encoding == "unknown-8bit":
+ # probably a malformed UTF-8 content, re-encode it
+ # by replacing invalid chars with a substitution one
content_data = content_data.decode("utf-8", "replace").encode("utf-8")
elif encoding not in ["utf-8", "binary"]:
content_data = content_data.decode(encoding, "replace").encode("utf-8")
elif mimetype.startswith("application/octet-stream"):
# file may detect a text content as binary
# so try to decode it for display
encodings = ["us-ascii", "utf-8"]
encodings += ["iso-8859-%s" % i for i in range(1, 17)]
for enc in encodings:
try:
content_data = content_data.decode(enc).encode("utf-8")
except Exception as exc:
sentry_sdk.capture_exception(exc)
else:
# ensure display in content view
encoding = enc
mimetype = "text/plain"
break
return mimetype, encoding, content_data
def request_content(
query_string, max_size=content_display_max_size, re_encode=True,
):
"""Function that retrieves a content from the archive.
Raw bytes content is first retrieved, then the content mime type.
If the mime type is not stored in the archive, it will be computed
using Python magic module.
Args:
query_string: a string of the form "[ALGO_HASH:]HASH" where
optional ALGO_HASH can be either ``sha1``, ``sha1_git``,
``sha256``, or ``blake2s256`` (default to ``sha1``) and HASH
the hexadecimal representation of the hash value
max_size: the maximum size for a content to retrieve (default to 1MB,
no size limit if None)
Returns:
A tuple whose first member corresponds to the content raw bytes
and second member the content mime type
Raises:
NotFoundExc if the content is not found
"""
content_data = archive.lookup_content(query_string)
filetype = None
language = None
# requests to the indexer db may fail so properly handle
# those cases in order to avoid content display errors
try:
filetype = archive.lookup_content_filetype(query_string)
language = archive.lookup_content_language(query_string)
except Exception as exc:
sentry_sdk.capture_exception(exc)
mimetype = "unknown"
encoding = "unknown"
if filetype:
mimetype = filetype["mimetype"]
encoding = filetype["encoding"]
if not max_size or content_data["length"] < max_size:
try:
content_raw = archive.lookup_content_raw(query_string)
except Exception as exc:
sentry_sdk.capture_exception(exc)
raise NotFoundExc(
"The bytes of the content are currently not available "
"in the archive."
)
else:
content_data["raw_data"] = content_raw["data"]
if not filetype:
mimetype, encoding = get_mimetype_and_encoding_for_content(
content_data["raw_data"]
)
if re_encode:
- mimetype, encoding, raw_data = _re_encode_content(
+ mimetype, encoding, raw_data = re_encode_content(
mimetype, encoding, content_data["raw_data"]
)
content_data["raw_data"] = raw_data
else:
content_data["raw_data"] = None
content_data["mimetype"] = mimetype
content_data["encoding"] = encoding
if language:
content_data["language"] = language["lang"]
else:
content_data["language"] = "not detected"
return content_data
def prepare_content_for_display(content_data, mime_type, path):
"""Function that prepares a content for HTML display.
The function tries to associate a programming language to a
content in order to perform syntax highlighting client-side
using highlightjs. The language is determined using either
the content filename or its mime type.
If the mime type corresponds to an image format supported
by web browsers, the content will be encoded in base64
for displaying the image.
Args:
content_data (bytes): raw bytes of the content
mime_type (string): mime type of the content
path (string): path of the content including filename
Returns:
A dict containing the content bytes (possibly different from the one
provided as parameter if it is an image) under the key 'content_data
and the corresponding highlightjs language class under the
key 'language'.
"""
language = None
if path:
language = highlightjs.get_hljs_language_from_filename(path.split("/")[-1])
if language is None:
language = highlightjs.get_hljs_language_from_mime_type(mime_type)
if language is None:
language = "plaintext"
if mime_type.startswith("image/"):
if mime_type in browsers_supported_image_mimes:
content_data = base64.b64encode(content_data).decode("ascii")
if mime_type.startswith("image/svg"):
mime_type = "image/svg+xml"
if mime_type.startswith("text/") or mime_type.startswith("application/"):
content_data = content_data.decode("utf-8", errors="replace")
return {"content_data": content_data, "language": language, "mimetype": mime_type}
def gen_link(url, link_text=None, link_attrs=None):
"""
Utility function for generating an HTML link to insert
in Django templates.
Args:
url (str): an url
link_text (str): optional text for the produced link,
if not provided the url will be used
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="url">link_text</a>'
"""
attrs = " "
if link_attrs:
for k, v in link_attrs.items():
attrs += '%s="%s" ' % (k, v)
if not link_text:
link_text = url
link = '<a%shref="%s">%s</a>' % (attrs, escape(url), escape(link_text))
return mark_safe(link)
def _snapshot_context_query_params(snapshot_context):
query_params = {}
if not snapshot_context:
return query_params
if snapshot_context and snapshot_context["origin_info"]:
origin_info = snapshot_context["origin_info"]
snp_query_params = snapshot_context["query_params"]
query_params = {"origin_url": origin_info["url"]}
if "timestamp" in snp_query_params:
query_params["timestamp"] = snp_query_params["timestamp"]
if "visit_id" in snp_query_params:
query_params["visit_id"] = snp_query_params["visit_id"]
if "snapshot" in snp_query_params and "visit_id" not in query_params:
query_params["snapshot"] = snp_query_params["snapshot"]
elif snapshot_context:
query_params = {"snapshot": snapshot_context["snapshot_id"]}
if snapshot_context["release"]:
query_params["release"] = snapshot_context["release"]
elif snapshot_context["branch"] and snapshot_context["branch"] not in (
"HEAD",
snapshot_context["revision_id"],
):
query_params["branch"] = snapshot_context["branch"]
elif snapshot_context["revision_id"]:
query_params["revision"] = snapshot_context["revision_id"]
return query_params
def gen_revision_url(revision_id, snapshot_context=None):
"""
Utility function for generating an url to a revision.
Args:
revision_id (str): a revision id
snapshot_context (dict): if provided, generate snapshot-dependent
browsing url
Returns:
str: The url to browse the revision
"""
query_params = _snapshot_context_query_params(snapshot_context)
# remove query parameters not needed for a revision view
query_params.pop("revision", None)
query_params.pop("release", None)
return reverse(
"browse-revision", url_args={"sha1_git": revision_id}, query_params=query_params
)
def gen_revision_link(
revision_id,
shorten_id=False,
snapshot_context=None,
link_text="Browse",
link_attrs={"class": "btn btn-default btn-sm", "role": "button"},
):
"""
Utility function for generating a link to a revision HTML view
to insert in Django templates.
Args:
revision_id (str): a revision id
shorten_id (boolean): whether to shorten the revision id to 7
characters for the link text
snapshot_context (dict): if provided, generate snapshot-dependent
browsing link
link_text (str): optional text for the generated link
(the revision id will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
str: An HTML link in the form '<a href="revision_url">revision_id</a>'
"""
if not revision_id:
return None
revision_url = gen_revision_url(revision_id, snapshot_context)
if shorten_id:
return gen_link(revision_url, revision_id[:7], link_attrs)
else:
if not link_text:
link_text = revision_id
return gen_link(revision_url, link_text, link_attrs)
def gen_directory_link(
sha1_git,
snapshot_context=None,
link_text="Browse",
link_attrs={"class": "btn btn-default btn-sm", "role": "button"},
):
"""
Utility function for generating a link to a directory HTML view
to insert in Django templates.
Args:
sha1_git (str): directory identifier
link_text (str): optional text for the generated link
(the directory id will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="directory_view_url">link_text</a>'
"""
if not sha1_git:
return None
query_params = _snapshot_context_query_params(snapshot_context)
directory_url = reverse(
"browse-directory", url_args={"sha1_git": sha1_git}, query_params=query_params
)
if not link_text:
link_text = sha1_git
return gen_link(directory_url, link_text, link_attrs)
def gen_snapshot_link(
snapshot_id,
snapshot_context=None,
link_text="Browse",
link_attrs={"class": "btn btn-default btn-sm", "role": "button"},
):
"""
Utility function for generating a link to a snapshot HTML view
to insert in Django templates.
Args:
snapshot_id (str): snapshot identifier
link_text (str): optional text for the generated link
(the snapshot id will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="snapshot_view_url">link_text</a>'
"""
query_params = _snapshot_context_query_params(snapshot_context)
snapshot_url = reverse(
"browse-snapshot",
url_args={"snapshot_id": snapshot_id},
query_params=query_params,
)
if not link_text:
link_text = snapshot_id
return gen_link(snapshot_url, link_text, link_attrs)
def gen_content_link(
sha1_git,
snapshot_context=None,
link_text="Browse",
link_attrs={"class": "btn btn-default btn-sm", "role": "button"},
):
"""
Utility function for generating a link to a content HTML view
to insert in Django templates.
Args:
sha1_git (str): content identifier
link_text (str): optional text for the generated link
(the content sha1_git will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="content_view_url">link_text</a>'
"""
if not sha1_git:
return None
query_params = _snapshot_context_query_params(snapshot_context)
content_url = reverse(
"browse-content",
url_args={"query_string": "sha1_git:" + sha1_git},
query_params=query_params,
)
if not link_text:
link_text = sha1_git
return gen_link(content_url, link_text, link_attrs)
def get_revision_log_url(revision_id, snapshot_context=None):
"""
Utility function for getting the URL for a revision log HTML view
(possibly in the context of an origin).
Args:
revision_id (str): revision identifier the history heads to
snapshot_context (dict): if provided, generate snapshot-dependent
browsing link
Returns:
The revision log view URL
"""
query_params = {}
if snapshot_context:
query_params = _snapshot_context_query_params(snapshot_context)
query_params["revision"] = revision_id
if snapshot_context and snapshot_context["origin_info"]:
revision_log_url = reverse("browse-origin-log", query_params=query_params)
elif snapshot_context:
url_args = {"snapshot_id": snapshot_context["snapshot_id"]}
del query_params["snapshot"]
revision_log_url = reverse(
"browse-snapshot-log", url_args=url_args, query_params=query_params
)
else:
revision_log_url = reverse(
"browse-revision-log", url_args={"sha1_git": revision_id}
)
return revision_log_url
def gen_revision_log_link(
revision_id,
snapshot_context=None,
link_text="Browse",
link_attrs={"class": "btn btn-default btn-sm", "role": "button"},
):
"""
Utility function for generating a link to a revision log HTML view
(possibly in the context of an origin) to insert in Django templates.
Args:
revision_id (str): revision identifier the history heads to
snapshot_context (dict): if provided, generate snapshot-dependent
browsing link
link_text (str): optional text to use for the generated link
(the revision id will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form
'<a href="revision_log_view_url">link_text</a>'
"""
if not revision_id:
return None
revision_log_url = get_revision_log_url(revision_id, snapshot_context)
if not link_text:
link_text = revision_id
return gen_link(revision_log_url, link_text, link_attrs)
def gen_person_mail_link(person, link_text=None):
"""
Utility function for generating a mail link to a person to insert
in Django templates.
Args:
person (dict): dictionary containing person data
(*name*, *email*, *fullname*)
link_text (str): optional text to use for the generated mail link
(the person name will be used by default)
Returns:
str: A mail link to the person or the person name if no email is
present in person data
"""
person_name = person["name"] or person["fullname"] or "None"
if link_text is None:
link_text = person_name
person_email = person["email"] if person["email"] else None
if person_email is None and "@" in person_name and " " not in person_name:
person_email = person_name
if person_email:
return gen_link(url="mailto:%s" % person_email, link_text=link_text)
else:
return person_name
def gen_release_link(
sha1_git,
snapshot_context=None,
link_text="Browse",
link_attrs={"class": "btn btn-default btn-sm", "role": "button"},
):
"""
Utility function for generating a link to a release HTML view
to insert in Django templates.
Args:
sha1_git (str): release identifier
link_text (str): optional text for the generated link
(the release id will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="release_view_url">link_text</a>'
"""
query_params = _snapshot_context_query_params(snapshot_context)
release_url = reverse(
"browse-release", url_args={"sha1_git": sha1_git}, query_params=query_params
)
if not link_text:
link_text = sha1_git
return gen_link(release_url, link_text, link_attrs)
def format_log_entries(revision_log, per_page, snapshot_context=None):
"""
Utility functions that process raw revision log data for HTML display.
Its purpose is to:
* add links to relevant browse views
* format date in human readable format
* truncate the message log
Args:
revision_log (list): raw revision log as returned by the swh-web api
per_page (int): number of log entries per page
snapshot_context (dict): if provided, generate snapshot-dependent
browsing link
"""
revision_log_data = []
for i, rev in enumerate(revision_log):
if i == per_page:
break
author_name = "None"
author_fullname = "None"
committer_fullname = "None"
if rev["author"]:
author_name = gen_person_mail_link(rev["author"])
author_fullname = rev["author"]["fullname"]
if rev["committer"]:
committer_fullname = rev["committer"]["fullname"]
author_date = format_utc_iso_date(rev["date"])
committer_date = format_utc_iso_date(rev["committer_date"])
tooltip = "revision %s\n" % rev["id"]
tooltip += "author: %s\n" % author_fullname
tooltip += "author date: %s\n" % author_date
tooltip += "committer: %s\n" % committer_fullname
tooltip += "committer date: %s\n\n" % committer_date
if rev["message"]:
tooltip += textwrap.indent(rev["message"], " " * 4)
revision_log_data.append(
{
"author": author_name,
"id": rev["id"][:7],
"message": rev["message"],
"date": author_date,
"commit_date": committer_date,
"url": gen_revision_url(rev["id"], snapshot_context),
"tooltip": tooltip,
}
)
return revision_log_data
# list of common readme names ordered by preference
# (lower indices have higher priority)
_common_readme_names = [
"readme.markdown",
"readme.md",
"readme.rst",
"readme.txt",
"readme",
]
def get_readme_to_display(readmes):
"""
Process a list of readme files found in a directory
in order to find the adequate one to display.
Args:
readmes: a list of dict where keys are readme file names and values
are readme sha1s
Returns:
A tuple (readme_name, readme_sha1)
"""
readme_name = None
readme_url = None
readme_sha1 = None
readme_html = None
lc_readmes = {k.lower(): {"orig_name": k, "sha1": v} for k, v in readmes.items()}
# look for readme names according to the preference order
# defined by the _common_readme_names list
for common_readme_name in _common_readme_names:
if common_readme_name in lc_readmes:
readme_name = lc_readmes[common_readme_name]["orig_name"]
readme_sha1 = lc_readmes[common_readme_name]["sha1"]
readme_url = reverse(
"browse-content-raw",
url_args={"query_string": readme_sha1},
query_params={"re_encode": "true"},
)
break
# otherwise pick the first readme like file if any
if not readme_name and len(readmes.items()) > 0:
readme_name = next(iter(readmes))
readme_sha1 = readmes[readme_name]
readme_url = reverse(
"browse-content-raw",
url_args={"query_string": readme_sha1},
query_params={"re_encode": "true"},
)
# convert rst README to html server side as there is
# no viable solution to perform that task client side
if readme_name and readme_name.endswith(".rst"):
cache_entry_id = "readme_%s" % readme_sha1
cache_entry = cache.get(cache_entry_id)
if cache_entry:
readme_html = cache_entry
else:
try:
rst_doc = request_content(readme_sha1)
readme_html = rst_to_html(rst_doc["raw_data"])
cache.set(cache_entry_id, readme_html)
except Exception as exc:
sentry_sdk.capture_exception(exc)
readme_html = "Readme bytes are not available"
return readme_name, readme_url, readme_html
diff --git a/swh/web/tests/browse/test_utils.py b/swh/web/tests/browse/test_utils.py
index 0c93c1d9..be40b22d 100644
--- a/swh/web/tests/browse/test_utils.py
+++ b/swh/web/tests/browse/test_utils.py
@@ -1,89 +1,101 @@
# Copyright (C) 2017-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU Affero General Public License version 3, or any later version
# See top-level LICENSE file for more information
import pytest
from swh.web.browse.utils import (
gen_link,
gen_person_mail_link,
gen_revision_link,
get_mimetype_and_encoding_for_content,
prepare_content_for_display,
+ re_encode_content,
)
from swh.web.common.utils import reverse
def test_get_mimetype_and_encoding_for_content():
text = b"Hello world!"
assert get_mimetype_and_encoding_for_content(text) == ("text/plain", "us-ascii",)
def test_gen_link():
assert (
gen_link("https://www.softwareheritage.org/", "swh")
== '<a href="https://www.softwareheritage.org/">swh</a>'
)
def test_gen_revision_link():
revision_id = "28a0bc4120d38a394499382ba21d6965a67a3703"
revision_url = reverse("browse-revision", url_args={"sha1_git": revision_id})
assert gen_revision_link(
revision_id, link_text=None, link_attrs=None
) == '<a href="%s">%s</a>' % (revision_url, revision_id)
assert gen_revision_link(
revision_id, shorten_id=True, link_attrs=None
) == '<a href="%s">%s</a>' % (revision_url, revision_id[:7])
def test_gen_person_mail_link():
person_full = {
"name": "John Doe",
"email": "john.doe@swh.org",
"fullname": "John Doe <john.doe@swh.org>",
}
assert gen_person_mail_link(person_full) == '<a href="mailto:%s">%s</a>' % (
person_full["email"],
person_full["name"],
)
link_text = "Mail"
assert gen_person_mail_link(
person_full, link_text=link_text
) == '<a href="mailto:%s">%s</a>' % (person_full["email"], link_text)
person_partial_email = {"name": None, "email": None, "fullname": "john.doe@swh.org"}
assert gen_person_mail_link(
person_partial_email
) == '<a href="mailto:%s">%s</a>' % (
person_partial_email["fullname"],
person_partial_email["fullname"],
)
person_partial = {
"name": None,
"email": None,
"fullname": "John Doe <john.doe@swh.org>",
}
assert gen_person_mail_link(person_partial) == person_partial["fullname"]
person_none = {"name": None, "email": None, "fullname": None}
assert gen_person_mail_link(person_none) == "None"
@pytest.mark.parametrize(
"path, expected_language",
[("CMakeLists.txt", "cmake"), ("path/CMakeLists.txt", "cmake")],
)
def test_prepare_content_display_language_for_filename(path, expected_language):
content_display = prepare_content_for_display(
content_data=b"", mime_type="", path=path
)
assert content_display["language"] == expected_language
+
+
+def test_re_encode_content_for_shift_jis_encoding():
+ data = b"/* \x8a\xd6\x98A\x82\xcc\x95\xb6\x8e\x9a\x83R\x81[\x83h\x95\xcf\x8a\xb7 */"
+ mime_type, encoding = get_mimetype_and_encoding_for_content(data)
+
+ _, encoding, re_encoded_data = re_encode_content(mime_type, encoding, data)
+
+ assert encoding == "SHIFT_JIS"
+ assert data.decode(encoding) == re_encoded_data.decode("utf-8")
+ assert re_encoded_data.decode("utf-8") == "/* 関連の文字コード変換 */"
diff --git a/swh/web/tests/browse/views/test_content.py b/swh/web/tests/browse/views/test_content.py
index e24d6a86..28688d0d 100644
--- a/swh/web/tests/browse/views/test_content.py
+++ b/swh/web/tests/browse/views/test_content.py
@@ -1,1076 +1,1076 @@
# Copyright (C) 2017-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU Affero General Public License version 3, or any later version
# See top-level LICENSE file for more information
import random
import re
import pytest
from django.utils.html import escape
from swh.model.hashutil import hash_to_bytes
from swh.model.model import ObjectType as ModelObjectType
from swh.model.model import Release, Snapshot, SnapshotBranch, TargetType
from swh.model.swhids import ObjectType
from swh.web.browse.snapshot_context import process_snapshot_branches
from swh.web.browse.utils import (
- _re_encode_content,
get_mimetype_and_encoding_for_content,
prepare_content_for_display,
+ re_encode_content,
)
from swh.web.common.exc import NotFoundExc
from swh.web.common.identifiers import gen_swhid
from swh.web.common.utils import (
format_utc_iso_date,
gen_path_info,
parse_iso8601_date_to_utc,
reverse,
)
from swh.web.tests.data import get_content
from swh.web.tests.django_asserts import assert_contains, assert_not_contains
from swh.web.tests.utils import check_html_get_response, check_http_get_response
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_text["sha1"]},
query_params={"path": content_text["path"]},
)
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_text)
mimetype = content_display["mimetype"]
if mimetype.startswith("text/"):
assert_contains(resp, '<code class="%s">' % content_display["language"])
assert_contains(resp, escape(content_display["content_data"]))
assert_contains(resp, url_raw)
swh_cnt_id = gen_swhid(ObjectType.CONTENT, sha1_git)
swh_cnt_id_url = reverse("browse-swhid", url_args={"swhid": swh_cnt_id})
assert_contains(resp, swh_cnt_id)
assert_contains(resp, swh_cnt_id_url)
assert_not_contains(resp, "swh-metadata-popover")
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"]
url = reverse("browse-content", url_args={"query_string": content["sha1"]})
url_raw = reverse(
"browse-content-raw", url_args={"query_string": content["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)
if content["encoding"] != "binary":
assert_contains(resp, '<code class="plaintext">')
assert_contains(resp, escape(content_display["content_data"]))
assert_contains(resp, url_raw)
swh_cnt_id = gen_swhid(ObjectType.CONTENT, sha1_git)
swh_cnt_id_url = reverse("browse-swhid", url_args={"swhid": swh_cnt_id})
assert_contains(resp, swh_cnt_id)
assert_contains(resp, swh_cnt_id_url)
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_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_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})
assert_contains(resp, swh_cnt_id_url)
assert_contains(resp, escape(content_display["content_data"]))
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_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_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)
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_unsupported_image_type_rendering["mimetype"]
encoding = content_unsupported_image_type_rendering["encoding"]
assert_contains(
resp,
(
f"Content with mime type {mimetype} and encoding {encoding} "
"cannot be displayed."
),
)
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_text["sha1"]},
query_params={"path": path},
)
resp = check_html_get_response(
client, url, status_code=200, template_used="browse/content.html"
)
assert_contains(resp, '<nav class="bread-crumbs')
content_display = _process_content_for_display(archive_data, content_text)
mimetype = content_display["mimetype"]
if mimetype.startswith("text/"):
hljs_language = content_text["hljs_language"]
assert_contains(resp, '<code class="%s">' % hljs_language)
assert_contains(resp, escape(content_display["content_data"]))
split_path = path.split("/")
root_dir_sha1 = split_path[0]
filename = split_path[-1]
path = path.replace(root_dir_sha1 + "/", "").replace(filename, "")
swhid_context = {
"anchor": gen_swhid(ObjectType.DIRECTORY, root_dir_sha1),
"path": f"/{path}{filename}",
}
swh_cnt_id = gen_swhid(
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)
assert_contains(resp, swh_cnt_id_url)
path_info = gen_path_info(path)
root_dir_url = reverse("browse-directory", url_args={"sha1_git": root_dir_sha1})
assert_contains(resp, '<li class="swh-path">', count=len(path_info) + 1)
assert_contains(
resp, '<a href="' + root_dir_url + '">' + root_dir_sha1[:7] + "</a>"
)
for p in path_info:
dir_url = reverse(
"browse-directory",
url_args={"sha1_git": root_dir_sha1},
query_params={"path": p["path"]},
)
assert_contains(resp, '<a href="' + dir_url + '">' + p["name"] + "</a>")
assert_contains(resp, "<li>" + filename + "</li>")
url_raw = reverse(
"browse-content-raw",
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_text["sha1"]},
query_params={"path": filename},
)
resp = check_html_get_response(
client, url, status_code=200, template_used="browse/content.html"
)
assert_not_contains(resp, '<nav class="bread-crumbs')
invalid_path = "%s/foo/bar/baz" % root_dir_sha1
url = reverse(
"browse-content",
url_args={"query_string": content_text["sha1"]},
query_params={"path": invalid_path},
)
resp = check_html_get_response(
client, url, status_code=404, template_used="error.html"
)
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_text["sha1"])["data"]
assert resp["Content-Type"] == "text/plain"
assert resp["Content-disposition"] == (
"filename=%s_%s" % ("sha1", content_text["sha1"])
)
assert resp.content == content_data
filename = content_text["path"].split("/")[-1]
url = reverse(
"browse-content-raw",
url_args={"query_string": content_text["sha1"]},
query_params={"filename": filename},
)
resp = check_http_get_response(
client, url, status_code=200, content_type="text/plain"
)
assert resp["Content-Type"] == "text/plain"
assert resp["Content-disposition"] == "filename=%s" % filename
assert resp.content == content_data
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_text_non_utf8["encoding"]
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_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_image_type["sha1"],
)
assert resp.content == content_data
url = reverse(
"browse-content-raw",
url_args={"query_string": content_image_type["sha1"]},
query_params={"filename": filename},
)
resp = check_http_get_response(
client, url, status_code=200, content_type="application/octet-stream"
)
assert resp["Content-Type"] == "application/octet-stream"
assert resp["Content-disposition"] == "attachment; filename=%s" % filename
assert resp.content == content_data
@pytest.mark.django_db
@pytest.mark.parametrize("staff_user_logged_in", [False, True])
def test_content_request_errors(
client, staff_user, invalid_sha1, unknown_content, staff_user_logged_in
):
if staff_user_logged_in:
client.force_login(staff_user)
url = reverse("browse-content", url_args={"query_string": invalid_sha1})
check_html_get_response(client, url, status_code=400, template_used="error.html")
url = reverse("browse-content", url_args={"query_string": unknown_content["sha1"]})
check_html_get_response(
client, url, status_code=404, template_used="browse/content.html"
)
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"])
mock_archive.lookup_content.return_value = content_data
mock_archive.lookup_content_filetype.side_effect = Exception()
mock_archive.lookup_content_raw.side_effect = NotFoundExc(
"Content bytes not available!"
)
url = reverse("browse-content", url_args={"query_string": content["sha1"]})
check_html_get_response(
client, url, status_code=404, template_used="browse/content.html"
)
def test_content_too_large(client, mocker):
mock_request_content = mocker.patch("swh.web.browse.views.content.request_content")
stub_content_too_large_data = {
"checksums": {
"sha1": "8624bcdae55baeef00cd11d5dfcfa60f68710a02",
"sha1_git": "94a9ed024d3859793618152ea559a168bbcbb5e2",
"sha256": (
"8ceb4b9ee5adedde47b31e975c1d90c73ad27b6b16" "5a1dcd80c7c545eb65b903"
),
"blake2s256": (
"38702b7168c7785bfe748b51b45d9856070ba90" "f9dc6d90f2ea75d4356411ffe"
),
},
"length": 30000000,
"raw_data": None,
"mimetype": "text/plain",
"encoding": "us-ascii",
"language": "not detected",
"licenses": "GPL",
"error_code": 200,
"error_message": "",
"error_description": "",
}
content_sha1 = stub_content_too_large_data["checksums"]["sha1"]
mock_request_content.return_value = stub_content_too_large_data
url = reverse("browse-content", url_args={"query_string": content_sha1})
url_raw = reverse("browse-content-raw", url_args={"query_string": content_sha1})
resp = check_html_get_response(
client, url, status_code=200, template_used="browse/content.html"
)
assert_contains(resp, "Content is too large to be displayed")
assert_contains(resp, url_raw)
def test_content_uppercase(client, content):
url = reverse(
"browse-content-uppercase-checksum",
url_args={"query_string": content["sha1"].upper()},
)
resp = check_html_get_response(client, url, status_code=302)
redirect_url = reverse("browse-content", url_args={"query_string": content["sha1"]})
assert resp["location"] == redirect_url
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_utf8_detected_as_binary
)
assert_contains(resp, escape(content_display["content_data"]))
def test_content_origin_snapshot_branch_browse(
client, archive_data, origin_with_multiple_visits
):
origin_url = origin_with_multiple_visits["url"]
visits = archive_data.origin_visit_get(origin_url)
visit = random.choice(visits)
snapshot = archive_data.snapshot_get(visit["snapshot"])
snapshot_sizes = archive_data.snapshot_count_branches(visit["snapshot"])
branches, releases, _ = process_snapshot_branches(snapshot)
branch_info = random.choice(branches)
directory = archive_data.revision_get(branch_info["revision"])["directory"]
directory_content = archive_data.directory_ls(directory)
directory_file = random.choice(
[e for e in directory_content if e["type"] == "file"]
)
url = reverse(
"browse-content",
url_args={"query_string": directory_file["checksums"]["sha1"]},
query_params={
"origin_url": origin_with_multiple_visits["url"],
"snapshot": snapshot["id"],
"branch": branch_info["name"],
"path": directory_file["name"],
},
)
resp = check_html_get_response(
client, url, status_code=200, template_used="browse/content.html"
)
_check_origin_snapshot_related_html(
resp, origin_with_multiple_visits, snapshot, snapshot_sizes, branches, releases
)
assert_contains(resp, directory_file["name"])
assert_contains(resp, f"Branch: <strong>{branch_info['name']}</strong>")
cnt_swhid = gen_swhid(
ObjectType.CONTENT,
directory_file["checksums"]["sha1_git"],
metadata={
"origin": origin_url,
"visit": gen_swhid(ObjectType.SNAPSHOT, snapshot["id"]),
"anchor": gen_swhid(ObjectType.REVISION, branch_info["revision"]),
"path": f"/{directory_file['name']}",
},
)
assert_contains(resp, cnt_swhid)
dir_swhid = gen_swhid(
ObjectType.DIRECTORY,
directory,
metadata={
"origin": origin_url,
"visit": gen_swhid(ObjectType.SNAPSHOT, snapshot["id"]),
"anchor": gen_swhid(ObjectType.REVISION, branch_info["revision"]),
},
)
assert_contains(resp, dir_swhid)
rev_swhid = gen_swhid(
ObjectType.REVISION,
branch_info["revision"],
metadata={
"origin": origin_url,
"visit": gen_swhid(ObjectType.SNAPSHOT, snapshot["id"]),
},
)
assert_contains(resp, rev_swhid)
snp_swhid = gen_swhid(
ObjectType.SNAPSHOT, snapshot["id"], metadata={"origin": origin_url,},
)
assert_contains(resp, snp_swhid)
def test_content_origin_snapshot_release_browse(
client, archive_data, origin_with_multiple_visits
):
origin_url = origin_with_multiple_visits["url"]
visits = archive_data.origin_visit_get(origin_url)
visit = random.choice(visits)
snapshot = archive_data.snapshot_get(visit["snapshot"])
snapshot_sizes = archive_data.snapshot_count_branches(visit["snapshot"])
branches, releases, _ = process_snapshot_branches(snapshot)
release_info = random.choice(releases)
directory_content = archive_data.directory_ls(release_info["directory"])
directory_file = random.choice(
[e for e in directory_content if e["type"] == "file"]
)
url = reverse(
"browse-content",
url_args={"query_string": directory_file["checksums"]["sha1"]},
query_params={
"origin_url": origin_url,
"snapshot": snapshot["id"],
"release": release_info["name"],
"path": directory_file["name"],
},
)
resp = check_html_get_response(
client, url, status_code=200, template_used="browse/content.html"
)
_check_origin_snapshot_related_html(
resp, origin_with_multiple_visits, snapshot, snapshot_sizes, branches, releases
)
assert_contains(resp, directory_file["name"])
assert_contains(resp, f"Release: <strong>{release_info['name']}</strong>")
cnt_swhid = gen_swhid(
ObjectType.CONTENT,
directory_file["checksums"]["sha1_git"],
metadata={
"origin": origin_url,
"visit": gen_swhid(ObjectType.SNAPSHOT, snapshot["id"]),
"anchor": gen_swhid(ObjectType.RELEASE, release_info["id"]),
"path": f"/{directory_file['name']}",
},
)
assert_contains(resp, cnt_swhid)
dir_swhid = gen_swhid(
ObjectType.DIRECTORY,
release_info["directory"],
metadata={
"origin": origin_url,
"visit": gen_swhid(ObjectType.SNAPSHOT, snapshot["id"]),
"anchor": gen_swhid(ObjectType.RELEASE, release_info["id"]),
},
)
assert_contains(resp, dir_swhid)
rev_swhid = gen_swhid(
ObjectType.REVISION,
release_info["target"],
metadata={
"origin": origin_url,
"visit": gen_swhid(ObjectType.SNAPSHOT, snapshot["id"]),
},
)
assert_contains(resp, rev_swhid)
rel_swhid = gen_swhid(
ObjectType.RELEASE,
release_info["id"],
metadata={
"origin": origin_url,
"visit": gen_swhid(ObjectType.SNAPSHOT, snapshot["id"]),
},
)
assert_contains(resp, rel_swhid)
snp_swhid = gen_swhid(
ObjectType.SNAPSHOT, snapshot["id"], metadata={"origin": origin_url,},
)
assert_contains(resp, snp_swhid)
def _check_origin_snapshot_related_html(
resp, origin, snapshot, snapshot_sizes, branches, releases
):
browse_origin_url = reverse(
"browse-origin", query_params={"origin_url": origin["url"]}
)
assert_contains(resp, f'href="{browse_origin_url}"')
origin_branches_url = reverse(
"browse-origin-branches",
query_params={"origin_url": origin["url"], "snapshot": snapshot["id"]},
)
assert_contains(resp, f'href="{escape(origin_branches_url)}"')
assert_contains(resp, f"Branches ({snapshot_sizes['revision']})")
origin_releases_url = reverse(
"browse-origin-releases",
query_params={"origin_url": origin["url"], "snapshot": snapshot["id"]},
)
assert_contains(resp, f'href="{escape(origin_releases_url)}"')
assert_contains(resp, f"Releases ({snapshot_sizes['release']})")
assert_contains(resp, '<li class="swh-branch">', count=len(branches))
assert_contains(resp, '<li class="swh-release">', count=len(releases))
def _process_content_for_display(archive_data, content):
content_data = archive_data.content_get_data(content["sha1"])
mime_type, encoding = get_mimetype_and_encoding_for_content(content_data["data"])
- mime_type, encoding, content_data = _re_encode_content(
+ mime_type, encoding, content_data = re_encode_content(
mime_type, encoding, content_data["data"]
)
content_display = prepare_content_for_display(
content_data, mime_type, content["path"]
)
assert type(content_display["content_data"]) == str
return content_display
def test_content_dispaly_empty_query_string_missing_path(client):
url = reverse("browse-content", query_params={"origin_url": "http://example.com"},)
resp = check_html_get_response(
client, url, status_code=400, template_used="error.html"
)
assert_contains(resp, "The path query parameter must be provided.", status_code=400)
def test_content_dispaly_empty_query_string_and_snapshot_origin(client):
url = reverse("browse-content", query_params={"path": "test.txt"},)
resp = check_html_get_response(client, url, status_code=400,)
assert_contains(
resp,
"The origin_url or snapshot query parameters must be provided.",
status_code=400,
)
def test_content_dispaly_empty_query_string_with_origin(
client, archive_data, origin_with_multiple_visits
):
origin_url = origin_with_multiple_visits["url"]
snapshot = archive_data.snapshot_get_latest(origin_url)
head_rev_id = archive_data.snapshot_get_head(snapshot)
head_rev = archive_data.revision_get(head_rev_id)
dir_content = archive_data.directory_ls(head_rev["directory"])
dir_files = [e for e in dir_content if e["type"] == "file"]
dir_file = random.choice(dir_files)
url = reverse(
"browse-content",
query_params={"origin_url": origin_url, "path": dir_file["name"],},
)
resp = check_html_get_response(client, url, status_code=302,)
redict_url = reverse(
"browse-content",
url_args={"query_string": f"sha1_git:{dir_file['checksums']['sha1_git']}"},
query_params={"origin_url": origin_url, "path": dir_file["name"],},
)
assert resp.url == redict_url
def test_content_dispaly_empty_query_string_with_snapshot(
client, archive_data, origin_with_multiple_visits
):
origin_url = origin_with_multiple_visits["url"]
snapshot = archive_data.snapshot_get_latest(origin_url)
head_rev_id = archive_data.snapshot_get_head(snapshot)
head_rev = archive_data.revision_get(head_rev_id)
dir_content = archive_data.directory_ls(head_rev["directory"])
dir_files = [e for e in dir_content if e["type"] == "file"]
dir_file = random.choice(dir_files)
url = reverse(
"browse-content",
query_params={"snapshot": snapshot["id"], "path": dir_file["name"],},
)
resp = check_html_get_response(client, url, status_code=302,)
redict_url = reverse(
"browse-content",
url_args={"query_string": f"sha1_git:{dir_file['checksums']['sha1_git']}"},
query_params={"snapshot": snapshot["id"], "path": dir_file["name"],},
)
assert resp.url == redict_url
def test_browse_origin_content_no_visit(client, mocker, origin):
mock_get_origin_visits = mocker.patch(
"swh.web.common.origin_visits.get_origin_visits"
)
mock_get_origin_visits.return_value = []
mock_archive = mocker.patch("swh.web.common.origin_visits.archive")
mock_archive.lookup_origin_visit_latest.return_value = None
url = reverse(
"browse-content", query_params={"origin_url": origin["url"], "path": "foo"},
)
resp = check_html_get_response(
client, url, status_code=404, template_used="error.html"
)
assert_contains(resp, "No valid visit", status_code=404)
assert not mock_get_origin_visits.called
def test_browse_origin_content_unknown_visit(client, mocker, origin):
mock_get_origin_visits = mocker.patch(
"swh.web.common.origin_visits.get_origin_visits"
)
mock_get_origin_visits.return_value = [{"visit": 1}]
url = reverse(
"browse-content",
query_params={"origin_url": origin["url"], "path": "foo", "visit_id": 2},
)
resp = check_html_get_response(
client, url, status_code=404, template_used="error.html"
)
assert re.search("Resource not found", resp.content.decode("utf-8"))
def test_browse_origin_content_not_found(client, origin):
url = reverse(
"browse-content",
query_params={"origin_url": origin["url"], "path": "/invalid/file/path"},
)
resp = check_html_get_response(
client, url, status_code=404, template_used="error.html"
)
assert re.search("Resource not found", resp.content.decode("utf-8"))
def test_browse_content_invalid_origin(client):
url = reverse(
"browse-content",
query_params={
"origin_url": "http://invalid-origin",
"path": "/invalid/file/path",
},
)
resp = check_html_get_response(
client, url, status_code=404, template_used="error.html"
)
assert re.search("Resource not found", resp.content.decode("utf-8"))
def test_origin_content_view(
client, archive_data, swh_scheduler, origin_with_multiple_visits
):
origin_visits = archive_data.origin_visit_get(origin_with_multiple_visits["url"])
def _get_archive_data(visit_idx):
snapshot = archive_data.snapshot_get(origin_visits[visit_idx]["snapshot"])
head_rev_id = archive_data.snapshot_get_head(snapshot)
head_rev = archive_data.revision_get(head_rev_id)
dir_content = archive_data.directory_ls(head_rev["directory"])
dir_files = [e for e in dir_content if e["type"] == "file"]
dir_file = random.choice(dir_files)
branches, releases, _ = process_snapshot_branches(snapshot)
return {
"branches": branches,
"releases": releases,
"root_dir_sha1": head_rev["directory"],
"content": get_content(dir_file["checksums"]["sha1"]),
"visit": origin_visits[visit_idx],
"snapshot_sizes": archive_data.snapshot_count_branches(snapshot["id"]),
}
tdata = _get_archive_data(-1)
_origin_content_view_test_helper(
client,
archive_data,
origin_with_multiple_visits,
origin_visits[-1],
tdata["snapshot_sizes"],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
)
_origin_content_view_test_helper(
client,
archive_data,
origin_with_multiple_visits,
origin_visits[-1],
tdata["snapshot_sizes"],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
timestamp=tdata["visit"]["date"],
)
_origin_content_view_test_helper(
client,
archive_data,
origin_with_multiple_visits,
origin_visits[-1],
tdata["snapshot_sizes"],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
snapshot_id=tdata["visit"]["snapshot"],
)
tdata = _get_archive_data(0)
_origin_content_view_test_helper(
client,
archive_data,
origin_with_multiple_visits,
origin_visits[0],
tdata["snapshot_sizes"],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
visit_id=tdata["visit"]["visit"],
)
_origin_content_view_test_helper(
client,
archive_data,
origin_with_multiple_visits,
origin_visits[0],
tdata["snapshot_sizes"],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
snapshot_id=tdata["visit"]["snapshot"],
)
def _origin_content_view_test_helper(
client,
archive_data,
origin_info,
origin_visit,
snapshot_sizes,
origin_branches,
origin_releases,
root_dir_sha1,
content,
visit_id=None,
timestamp=None,
snapshot_id=None,
):
content_path = "/".join(content["path"].split("/")[1:])
if not visit_id and not snapshot_id:
visit_id = origin_visit["visit"]
query_params = {"origin_url": origin_info["url"], "path": content_path}
if timestamp:
query_params["timestamp"] = timestamp
if visit_id:
query_params["visit_id"] = visit_id
elif snapshot_id:
query_params["snapshot"] = snapshot_id
url = reverse(
"browse-content",
url_args={"query_string": f"sha1_git:{content['sha1_git']}"},
query_params=query_params,
)
resp = check_html_get_response(
client, url, status_code=200, template_used="browse/content.html"
)
assert type(content["data"]) == str
assert_contains(resp, '<code class="%s">' % content["hljs_language"])
assert_contains(resp, escape(content["data"]))
split_path = content_path.split("/")
filename = split_path[-1]
path = content_path.replace(filename, "")[:-1]
path_info = gen_path_info(path)
del query_params["path"]
if timestamp:
query_params["timestamp"] = format_utc_iso_date(
parse_iso8601_date_to_utc(timestamp).isoformat(), "%Y-%m-%dT%H:%M:%SZ"
)
root_dir_url = reverse(
"browse-directory",
url_args={"sha1_git": root_dir_sha1},
query_params=query_params,
)
assert_contains(resp, '<li class="swh-path">', count=len(path_info) + 1)
assert_contains(resp, '<a href="%s">%s</a>' % (root_dir_url, root_dir_sha1[:7]))
for p in path_info:
query_params["path"] = p["path"]
dir_url = reverse("browse-origin-directory", query_params=query_params)
assert_contains(resp, '<a href="%s">%s</a>' % (dir_url, p["name"]))
assert_contains(resp, "<li>%s</li>" % filename)
query_string = "sha1_git:" + content["sha1_git"]
url_raw = reverse(
"browse-content-raw",
url_args={"query_string": query_string},
query_params={"filename": filename},
)
assert_contains(resp, url_raw)
if "path" in query_params:
del query_params["path"]
origin_branches_url = reverse("browse-origin-branches", query_params=query_params)
assert_contains(resp, f'href="{escape(origin_branches_url)}"')
assert_contains(resp, f"Branches ({snapshot_sizes['revision']})")
origin_releases_url = reverse("browse-origin-releases", query_params=query_params)
assert_contains(resp, f'href="{escape(origin_releases_url)}">')
assert_contains(resp, f"Releases ({snapshot_sizes['release']})")
assert_contains(resp, '<li class="swh-branch">', count=len(origin_branches))
query_params["path"] = content_path
for branch in origin_branches:
root_dir_branch_url = reverse(
"browse-origin-content",
query_params={"branch": branch["name"], **query_params},
)
assert_contains(resp, '<a href="%s">' % root_dir_branch_url)
assert_contains(resp, '<li class="swh-release">', count=len(origin_releases))
query_params["branch"] = None
for release in origin_releases:
root_dir_release_url = reverse(
"browse-origin-content",
query_params={"release": release["name"], **query_params},
)
assert_contains(resp, '<a href="%s">' % root_dir_release_url)
url = reverse(
"browse-content",
url_args={"query_string": query_string},
query_params=query_params,
)
resp = check_html_get_response(
client, url, status_code=200, template_used="browse/content.html"
)
snapshot = archive_data.snapshot_get(origin_visit["snapshot"])
head_rev_id = archive_data.snapshot_get_head(snapshot)
swhid_context = {
"origin": origin_info["url"],
"visit": gen_swhid(ObjectType.SNAPSHOT, snapshot["id"]),
"anchor": gen_swhid(ObjectType.REVISION, head_rev_id),
"path": f"/{content_path}",
}
swh_cnt_id = gen_swhid(
ObjectType.CONTENT, content["sha1_git"], metadata=swhid_context
)
swh_cnt_id_url = reverse("browse-swhid", url_args={"swhid": swh_cnt_id})
assert_contains(resp, swh_cnt_id)
assert_contains(resp, swh_cnt_id_url)
assert_contains(resp, "swh-take-new-snapshot")
_check_origin_link(resp, origin_info["url"])
assert_not_contains(resp, "swh-metadata-popover")
def _check_origin_link(resp, origin_url):
browse_origin_url = reverse(
"browse-origin", query_params={"origin_url": origin_url}
)
assert_contains(resp, f'href="{browse_origin_url}"')
@pytest.mark.django_db
@pytest.mark.parametrize("staff_user_logged_in", [False, True])
def test_browse_content_snapshot_context_release_directory_target(
client, staff_user, archive_data, directory_with_files, staff_user_logged_in
):
if staff_user_logged_in:
client.force_login(staff_user)
release_name = "v1.0.0"
release = Release(
name=release_name.encode(),
message=f"release {release_name}".encode(),
target=hash_to_bytes(directory_with_files),
target_type=ModelObjectType.DIRECTORY,
synthetic=True,
)
archive_data.release_add([release])
snapshot = Snapshot(
branches={
release_name.encode(): SnapshotBranch(
target=release.id, target_type=TargetType.RELEASE
),
},
)
archive_data.snapshot_add([snapshot])
dir_content = archive_data.directory_ls(directory_with_files)
file_entry = random.choice(
[entry for entry in dir_content if entry["type"] == "file"]
)
sha1_git = file_entry["checksums"]["sha1_git"]
browse_url = reverse(
"browse-content",
url_args={"query_string": f"sha1_git:{sha1_git}"},
query_params={
"path": file_entry["name"],
"release": release_name,
"snapshot": snapshot.id.hex(),
},
)
check_html_get_response(
client, browse_url, status_code=200, template_used="browse/content.html"
)
diff --git a/swh/web/tests/data.py b/swh/web/tests/data.py
index f9051bd1..c5201a30 100644
--- a/swh/web/tests/data.py
+++ b/swh/web/tests/data.py
@@ -1,544 +1,544 @@
# Copyright (C) 2018-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU Affero General Public License version 3, or any later version
# See top-level LICENSE file for more information
from copy import deepcopy
from datetime import timedelta
import os
from pathlib import Path
import random
import time
from typing import Dict, List, Optional, Set
from swh.core.config import merge_configs
from swh.counters import get_counters
from swh.indexer.ctags import CtagsIndexer
from swh.indexer.fossology_license import FossologyLicenseIndexer
from swh.indexer.mimetype import MimetypeIndexer
from swh.indexer.storage import get_indexer_storage
from swh.indexer.storage.model import OriginIntrinsicMetadataRow
from swh.loader.git.from_disk import GitLoaderFromArchive
from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_hex
from swh.model.model import (
Content,
Directory,
Origin,
OriginVisit,
OriginVisitStatus,
Snapshot,
)
from swh.model.swhids import CoreSWHID, ObjectType, QualifiedSWHID
from swh.search import get_search
from swh.storage import get_storage
from swh.storage.algos.dir_iterators import dir_iterator
from swh.storage.algos.snapshot import snapshot_get_latest
from swh.storage.interface import Sha1
from swh.storage.utils import now
from swh.web import config
from swh.web.browse.utils import (
- _re_encode_content,
get_mimetype_and_encoding_for_content,
prepare_content_for_display,
+ re_encode_content,
)
from swh.web.common import archive
# Module used to initialize data that will be provided as tests input
# Base content indexer configuration
_TEST_INDEXER_BASE_CONFIG = {
"storage": {"cls": "memory"},
"objstorage": {"cls": "memory", "args": {},},
"indexer_storage": {"cls": "memory", "args": {},},
}
def random_sha1():
return hash_to_hex(bytes(random.randint(0, 255) for _ in range(20)))
def random_sha256():
return hash_to_hex(bytes(random.randint(0, 255) for _ in range(32)))
def random_blake2s256():
return hash_to_hex(bytes(random.randint(0, 255) for _ in range(32)))
def random_content():
return {
"sha1": random_sha1(),
"sha1_git": random_sha1(),
"sha256": random_sha256(),
"blake2s256": random_blake2s256(),
}
_TEST_MIMETYPE_INDEXER_CONFIG = merge_configs(
_TEST_INDEXER_BASE_CONFIG,
{
"tools": {
"name": "file",
"version": "1:5.30-1+deb9u1",
"configuration": {"type": "library", "debian-package": "python3-magic"},
}
},
)
_TEST_LICENSE_INDEXER_CONFIG = merge_configs(
_TEST_INDEXER_BASE_CONFIG,
{
"workdir": "/tmp/swh/indexer.fossology.license",
"tools": {
"name": "nomos",
"version": "3.1.0rc2-31-ga2cbb8c",
"configuration": {"command_line": "nomossa <filepath>",},
},
},
)
_TEST_CTAGS_INDEXER_CONFIG = merge_configs(
_TEST_INDEXER_BASE_CONFIG,
{
"workdir": "/tmp/swh/indexer.ctags",
"languages": {"c": "c"},
"tools": {
"name": "universal-ctags",
"version": "~git7859817b",
"configuration": {
"command_line": """ctags --fields=+lnz --sort=no --links=no """
"""--output-format=json <filepath>"""
},
},
},
)
# Lightweight git repositories that will be loaded to generate
# input data for tests
_TEST_ORIGINS = [
{
"type": "git",
"url": "https://github.com/memononen/libtess2",
"archives": ["libtess2.zip"],
"metadata": {
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"description": (
"Game and tools oriented refactored version of GLU tessellator."
),
},
},
{
"type": "git",
"url": "https://github.com/wcoder/highlightjs-line-numbers.js",
"archives": [
"highlightjs-line-numbers.js.zip",
"highlightjs-line-numbers.js_visit2.zip",
],
"metadata": {
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"description": "Line numbering plugin for Highlight.js",
},
},
{
"type": "git",
"url": "repo_with_submodules",
"archives": ["repo_with_submodules.tgz"],
"metadata": {
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"description": "This is just a sample repository with submodules",
},
},
]
_contents = {}
def _add_extra_contents(storage, contents):
pbm_image_data = b"""P1
# PBM example
24 7
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 1 1 1 1 0 0 1 1 1 1 0 0 1 1 1 1 0 0 1 1 1 1 0
0 1 0 0 0 0 0 1 0 0 0 0 0 1 0 0 0 0 0 1 0 0 1 0
0 1 1 1 0 0 0 1 1 1 0 0 0 1 1 1 0 0 0 1 1 1 1 0
0 1 0 0 0 0 0 1 0 0 0 0 0 1 0 0 0 0 0 1 0 0 0 0
0 1 0 0 0 0 0 1 1 1 1 0 0 1 1 1 1 0 0 1 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0"""
# add file with mimetype image/x-portable-bitmap in the archive content
pbm_content = Content.from_data(pbm_image_data)
storage.content_add([pbm_content])
contents.add(pbm_content.sha1)
# add file with mimetype application/pgp-keys in the archive content
gpg_path = os.path.join(
os.path.dirname(__file__), "resources/contents/other/extensions/public.gpg"
)
gpg_content = Content.from_data(Path(gpg_path).read_bytes())
storage.content_add([gpg_content])
contents.add(gpg_content.sha1)
INDEXER_TOOL = {
"tool_name": "swh-web tests",
"tool_version": "1.0",
"tool_configuration": {},
}
ORIGIN_METADATA_KEY = "keywords"
ORIGIN_METADATA_VALUE = "git"
ORIGIN_MASTER_REVISION = {}
def _add_origin(
storage, search, counters, origin_url, visit_type="git", snapshot_branches={}
):
storage.origin_add([Origin(url=origin_url)])
search.origin_update(
[{"url": origin_url, "has_visits": True, "visit_types": [visit_type]}]
)
counters.add("origin", [origin_url])
date = now()
visit = OriginVisit(origin=origin_url, date=date, type=visit_type)
visit = storage.origin_visit_add([visit])[0]
counters.add("origin_visit", [f"{visit.unique_key()}"])
snapshot = Snapshot.from_dict({"branches": snapshot_branches})
storage.snapshot_add([snapshot])
counters.add("snapshot", [snapshot.id])
visit_status = OriginVisitStatus(
origin=origin_url,
visit=visit.visit,
date=date + timedelta(minutes=1),
type=visit.type,
status="full",
snapshot=snapshot.id,
)
storage.origin_visit_status_add([visit_status])
counters.add("origin_visit_status", [f"{visit_status.unique_key()}"])
# Tests data initialization
def _init_tests_data():
# To hold reference to the memory storage
storage = get_storage("memory")
# Create search instance
search = get_search("memory")
search.initialize()
search.origin_update({"url": origin["url"]} for origin in _TEST_ORIGINS)
# create the counters instance
counters = get_counters("memory")
# Create indexer storage instance that will be shared by indexers
idx_storage = get_indexer_storage("memory")
# Declare a test tool for origin intrinsic metadata tests
idx_tool = idx_storage.indexer_configuration_add([INDEXER_TOOL])[0]
INDEXER_TOOL["id"] = idx_tool["id"]
# Load git repositories from archives
for origin in _TEST_ORIGINS:
for i, archive_ in enumerate(origin["archives"]):
if i > 0:
# ensure visit dates will be different when simulating
# multiple visits of an origin
time.sleep(1)
origin_repo_archive = os.path.join(
os.path.dirname(__file__), "resources/repos/%s" % archive_
)
loader = GitLoaderFromArchive(
storage, origin["url"], archive_path=origin_repo_archive,
)
result = loader.load()
assert result["status"] == "eventful"
ori = storage.origin_get([origin["url"]])[0]
origin.update(ori.to_dict()) # add an 'id' key if enabled
search.origin_update(
[{"url": origin["url"], "has_visits": True, "visit_types": ["git"]}]
)
for i in range(250):
_add_origin(
storage,
search,
counters,
origin_url=f"https://many.origins/{i+1}",
visit_type="tar",
)
sha1s: Set[Sha1] = set()
directories = set()
revisions = set()
releases = set()
snapshots = set()
swhids = []
content_path = {}
# Get all objects loaded into the test archive
common_metadata = {ORIGIN_METADATA_KEY: ORIGIN_METADATA_VALUE}
for origin in _TEST_ORIGINS:
origin_revisions = set()
snp = snapshot_get_latest(storage, origin["url"])
swhids.append(
QualifiedSWHID(
object_type=ObjectType.SNAPSHOT, object_id=snp.id, origin=origin["url"]
)
)
snapshots.add(hash_to_hex(snp.id))
for branch_name, branch_data in snp.branches.items():
target_type = branch_data.target_type.value
if target_type == "revision":
origin_revisions.add(branch_data.target)
swhids.append(
QualifiedSWHID(
object_type=ObjectType.REVISION,
object_id=branch_data.target,
origin=origin["url"],
visit=CoreSWHID(
object_type=ObjectType.SNAPSHOT, object_id=snp.id
),
)
)
if b"master" in branch_name:
# Add some origin intrinsic metadata for tests
metadata = common_metadata
metadata.update(origin.get("metadata", {}))
origin_metadata = OriginIntrinsicMetadataRow(
id=origin["url"],
from_revision=branch_data.target,
indexer_configuration_id=idx_tool["id"],
metadata=metadata,
mappings=[],
)
idx_storage.origin_intrinsic_metadata_add([origin_metadata])
search.origin_update(
[{"url": origin["url"], "intrinsic_metadata": metadata}]
)
ORIGIN_MASTER_REVISION[origin["url"]] = hash_to_hex(
branch_data.target
)
elif target_type == "release":
release = storage.release_get([branch_data.target])[0]
origin_revisions.add(release.target)
releases.add(hash_to_hex(branch_data.target))
swhids.append(
QualifiedSWHID(
object_type=ObjectType.RELEASE,
object_id=branch_data.target,
origin=origin["url"],
visit=CoreSWHID(
object_type=ObjectType.SNAPSHOT, object_id=snp.id
),
)
)
for rev_log in storage.revision_shortlog(origin_revisions):
rev_id = rev_log[0]
revisions.add(rev_id)
for rev in storage.revision_get(sorted(origin_revisions)):
if rev is None:
continue
dir_id = rev.directory
directories.add(hash_to_hex(dir_id))
for entry in dir_iterator(storage, dir_id):
if entry["type"] == "file":
sha1s.add(entry["sha1"])
content_path[entry["sha1"]] = "/".join(
[hash_to_hex(dir_id), entry["path"].decode("utf-8")]
)
swhids.append(
QualifiedSWHID(
object_type=ObjectType.CONTENT,
object_id=entry["sha1_git"],
origin=origin["url"],
visit=CoreSWHID(
object_type=ObjectType.SNAPSHOT, object_id=snp.id
),
anchor=CoreSWHID(
object_type=ObjectType.REVISION, object_id=rev.id
),
path=b"/" + entry["path"],
)
)
elif entry["type"] == "dir":
directories.add(hash_to_hex(entry["target"]))
swhids.append(
QualifiedSWHID(
object_type=ObjectType.DIRECTORY,
object_id=entry["target"],
origin=origin["url"],
visit=CoreSWHID(
object_type=ObjectType.SNAPSHOT, object_id=snp.id
),
anchor=CoreSWHID(
object_type=ObjectType.REVISION, object_id=rev.id
),
path=b"/" + entry["path"] + b"/",
)
)
_add_extra_contents(storage, sha1s)
# Get all checksums for each content
result: List[Optional[Content]] = storage.content_get(list(sha1s))
contents: List[Dict] = []
for content in result:
assert content is not None
sha1 = hash_to_hex(content.sha1)
content_metadata = {
algo: hash_to_hex(getattr(content, algo)) for algo in DEFAULT_ALGORITHMS
}
path = ""
if content.sha1 in content_path:
path = content_path[content.sha1]
cnt_data = storage.content_get_data(content.sha1)
assert cnt_data is not None
mimetype, encoding = get_mimetype_and_encoding_for_content(cnt_data)
- _, _, cnt_data = _re_encode_content(mimetype, encoding, cnt_data)
+ _, _, cnt_data = re_encode_content(mimetype, encoding, cnt_data)
content_display_data = prepare_content_for_display(cnt_data, mimetype, path)
content_metadata.update(
{
"path": path,
"mimetype": mimetype,
"encoding": encoding,
"hljs_language": content_display_data["language"],
"raw_data": cnt_data,
"data": content_display_data["content_data"],
}
)
_contents[sha1] = content_metadata
contents.append(content_metadata)
# Add the empty directory to the test archive
storage.directory_add([Directory(entries=())])
# Add empty content to the test archive
storage.content_add([Content.from_data(data=b"")])
# Add fake git origin with pull request branches
_add_origin(
storage,
search,
counters,
origin_url="https://git.example.org/project",
snapshot_branches={
b"refs/heads/master": {
"target_type": "revision",
"target": next(iter(revisions)),
},
**{
f"refs/pull/{i}".encode(): {
"target_type": "revision",
"target": next(iter(revisions)),
}
for i in range(300)
},
},
)
counters.add("revision", revisions)
counters.add("release", releases)
counters.add("directory", directories)
counters.add("content", [content["sha1"] for content in contents])
# Return tests data
return {
"search": search,
"storage": storage,
"idx_storage": idx_storage,
"counters": counters,
"origins": _TEST_ORIGINS,
"contents": list(sorted(contents, key=lambda c: c["sha1"])),
"directories": list(sorted(directories)),
"releases": list(sorted(releases)),
"revisions": list(sorted(map(hash_to_hex, revisions))),
"snapshots": list(sorted(snapshots)),
"swhids": swhids,
}
def _init_indexers(tests_data):
# Instantiate content indexers that will be used in tests
# and force them to use the memory storages
indexers = {}
for idx_name, idx_class, idx_config in (
("mimetype_indexer", MimetypeIndexer, _TEST_MIMETYPE_INDEXER_CONFIG),
("license_indexer", FossologyLicenseIndexer, _TEST_LICENSE_INDEXER_CONFIG),
("ctags_indexer", CtagsIndexer, _TEST_CTAGS_INDEXER_CONFIG),
):
idx = idx_class(config=idx_config)
idx.storage = tests_data["storage"]
idx.objstorage = tests_data["storage"].objstorage
idx.idx_storage = tests_data["idx_storage"]
idx.register_tools(idx.config["tools"])
indexers[idx_name] = idx
return indexers
def get_content(content_sha1):
return _contents.get(content_sha1)
_tests_data = None
_current_tests_data = None
_indexer_loggers = {}
def get_tests_data(reset=False):
"""
Initialize tests data and return them in a dict.
"""
global _tests_data, _current_tests_data
if _tests_data is None:
_tests_data = _init_tests_data()
indexers = _init_indexers(_tests_data)
for (name, idx) in indexers.items():
# pytest makes the loggers use a temporary file; and deepcopy
# requires serializability. So we remove them, and add them
# back after the copy.
_indexer_loggers[name] = idx.log
del idx.log
_tests_data.update(indexers)
if reset or _current_tests_data is None:
_current_tests_data = deepcopy(_tests_data)
for (name, logger) in _indexer_loggers.items():
_current_tests_data[name].log = logger
return _current_tests_data
def override_storages(storage, idx_storage, search, counters):
"""
Helper function to replace the storages from which archive data
are fetched.
"""
swh_config = config.get_config()
swh_config.update(
{
"storage": storage,
"indexer_storage": idx_storage,
"search": search,
"counters": counters,
}
)
archive.storage = storage
archive.idx_storage = idx_storage
archive.search = search
archive.counters = counters