Page MenuHomeSoftware Heritage
Files F9340311

No OneTemporary
Actions

View Options

diff --git a/PKG-INFO b/PKG-INFO
index 4fb4f005..7de7aa75 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,129 +1,129 @@
Metadata-Version: 2.1
Name: swh.web
-Version: 0.0.279
+Version: 0.0.280
Summary: Software Heritage Web UI
Home-page: https://forge.softwareheritage.org/diffusion/DWUI/
Author: Software Heritage developers
Author-email: swh-devel@inria.fr
License: UNKNOWN
Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest
Project-URL: Funding, https://www.softwareheritage.org/donate
Project-URL: Source, https://forge.softwareheritage.org/source/swh-web
Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-web/
Description: # swh-web
This repository holds the development of Software Heritage web applications:
* swh-web API (https://archive.softwareheritage.org/api): enables to query the content of the archive through HTTP requests and get responses in JSON or YAML.
* swh-web browse (https://archive.softwareheritage.org/browse): graphical interface that eases the navigation in the archive.
Documentation about how to use these components but also the details of their URI schemes
can be found in the docs folder. The produced HTML documentation can be read and browsed
at https://docs.softwareheritage.org/devel/swh-web/index.html.
## Technical details
Those applications are powered by:
* [Django Web Framework](https://www.djangoproject.com/) on the backend side with the following extensions enabled:
* [django-rest-framework](http://www.django-rest-framework.org/)
* [django-webpack-loader](https://github.com/owais/django-webpack-loader)
* [django-js-reverse](http://django-js-reverse.readthedocs.io/en/latest/)
* [webpack](https://webpack.js.org/) on the frontend side for better static assets management, including:
* assets dependencies management and retrieval through [yarn](https://yarnpkg.com/en/)
* linting of custom javascript code (through [eslint](https://eslint.org/)) and stylesheets (through [stylelint](https://stylelint.io/))
* use of [es6](http://es6-features.org) syntax and advanced javascript feature like [async/await](https://javascript.info/async-await) or [fetch](https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API) thanks to [babel](https://babeljs.io/) (es6 to es5 transpiler and polyfills provider)
* assets minification (using [terser](https://github.com/terser-js/terser) and [cssnano](http://cssnano.co/)) but also dead code elimination for production use
## How to build, run and test
### Backend requirements
First you will need [Python 3](https://www.python.org) and a complete [swh development environment](https://forge.softwareheritage.org/source/swh-environment/) installed.
To run the backend, you need to have the following [Python 3 modules](requirements.txt) installed.
To run the backend tests, the following [Python 3 modules](requirements-test.txt) are also required to be installed.
One easy way to install them is to use the `pip` tool:
```
$ pip install -r requirements.txt -r requirements-test.txt
```
### Frontend requirements
To compile the frontend assets, you need to have [nodejs](https://nodejs.org/en/) >= 8.9.0 and [yarn](https://yarnpkg.com/en/) installed. If you are on Debian stretch, you can easily install an up to date nodejs from the [stretch-backports](https://backports.debian.org/Instructions/) repository.
Packages for yarn can be installed by following [these instructions](https://yarnpkg.com/en/docs/install#debian-stable).
Alternatively, you can install yarn with `npm install yarn`, and add `YARN=node_modules/yarn/bin/yarn` as argument whenever you run `make`.
Please note that the static assets bundles generated by webpack are not stored in the git repository. Follow the instructions below in order to generate them in order to be able to run the frontend part of the web applications.
### Make targets to execute the applications
Below is the list of available make targets that can be executed from the root directory of swh-web in order to build and/or execute the web applications under various configurations:
* **run-django-webpack-devserver**: Compile and serve not optimized (without mignification and dead code elimination) frontend static assets using [webpack-dev-server](https://github.com/webpack/webpack-dev-server) and run django server with development settings. This is the recommended target to use when developing swh-web as it enables automatic reloading of backend and frontend part of the applications when modifying source files (*.py, *.js, *.css, *.html).
* **run-django-webpack-dev**: Compile not optimized (no minification, no dead code elimination) frontend static assets using webpack and run django server with development settings. This is the recommended target when one only wants to develop the backend side of the application.
* **run-django-webpack-prod**: Compile optimized (with minification and dead code elimination) frontend static assets using webpack and run django server with production settings. This is useful to test the applications in production mode (with the difference that static assets are served by django). Production settings notably enable advanced django caching and you will need to have [memcached](https://memcached.org/) installed for that feature to work.
* **run-django-server-dev**: Run the django server with development settings but without compiling frontend static assets through webpack.
* **run-django-server-prod**: Run the django server with production settings but without compiling frontend static assets through webpack.
* **run-gunicorn-server**: Run the web applications with production settings in a [gunicorn](http://gunicorn.org/) worker as they will be in real production environment.
Once one of these targets executed, the web applications can be executed by pointing your browser to http://localhost:5004.
### Make targets to test the applications
Some make targets are also available to easily execute the backend and frontend tests of the Software Heritage web applications.
The backend tests are powered by the [pytest](https://docs.pytest.org/en/latest/) and [hypothesis](https://hypothesis.readthedocs.io/en/latest/) frameworks while the frontend ones rely on the use of the [cypress](https://www.cypress.io/) tool.
Below is the exhaustive list of those targets:
* **test**: execute the backend tests using a fast hypothesis profile (only one input example will be provided for each test)
* **test-full**: execute the backend tests using a slower hypothesis profile (one hundred of input examples will be provided for each test which helps spotting possible bugs)
* **test-frontend**: execute the frontend tests using cypress in headless mode but with some slow test suites disabled
* **test-frontend-full**: execute the frontend tests using cypress in headless mode with all test suites enabled
* **test-frontend-ui**: execute the frontend tests using the cypress GUI but with some slow test suites disabled
* **test-frontend-full-ui**: execute the frontend tests using the cypress GUI with all test suites enabled
### Yarn targets
Below is a list of available yarn targets in order to only execute the frontend static assets compilation (no web server will be executed):
* **build-dev**: compile not optimized (without mignification and dead code elimination) frontend static assets and store the results in the `swh/web/static` folder.
* **build**: compile optimized (with mignification and dead code elimination) frontend static assets and store the results in the `swh/web/static` folder.
**The build target must be executed prior performing the Debian packaging of swh-web** in order for the package to contain the optimized assets dedicated to production environment.
To execute these targets, issue the following command:
```
$ yarn <target_name>
```
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 5 - Production/Stable
Classifier: Framework :: Django
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Provides-Extra: testing
diff --git a/swh.web.egg-info/PKG-INFO b/swh.web.egg-info/PKG-INFO
index 4fb4f005..7de7aa75 100644
--- a/swh.web.egg-info/PKG-INFO
+++ b/swh.web.egg-info/PKG-INFO
@@ -1,129 +1,129 @@
Metadata-Version: 2.1
Name: swh.web
-Version: 0.0.279
+Version: 0.0.280
Summary: Software Heritage Web UI
Home-page: https://forge.softwareheritage.org/diffusion/DWUI/
Author: Software Heritage developers
Author-email: swh-devel@inria.fr
License: UNKNOWN
Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest
Project-URL: Funding, https://www.softwareheritage.org/donate
Project-URL: Source, https://forge.softwareheritage.org/source/swh-web
Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-web/
Description: # swh-web
This repository holds the development of Software Heritage web applications:
* swh-web API (https://archive.softwareheritage.org/api): enables to query the content of the archive through HTTP requests and get responses in JSON or YAML.
* swh-web browse (https://archive.softwareheritage.org/browse): graphical interface that eases the navigation in the archive.
Documentation about how to use these components but also the details of their URI schemes
can be found in the docs folder. The produced HTML documentation can be read and browsed
at https://docs.softwareheritage.org/devel/swh-web/index.html.
## Technical details
Those applications are powered by:
* [Django Web Framework](https://www.djangoproject.com/) on the backend side with the following extensions enabled:
* [django-rest-framework](http://www.django-rest-framework.org/)
* [django-webpack-loader](https://github.com/owais/django-webpack-loader)
* [django-js-reverse](http://django-js-reverse.readthedocs.io/en/latest/)
* [webpack](https://webpack.js.org/) on the frontend side for better static assets management, including:
* assets dependencies management and retrieval through [yarn](https://yarnpkg.com/en/)
* linting of custom javascript code (through [eslint](https://eslint.org/)) and stylesheets (through [stylelint](https://stylelint.io/))
* use of [es6](http://es6-features.org) syntax and advanced javascript feature like [async/await](https://javascript.info/async-await) or [fetch](https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API) thanks to [babel](https://babeljs.io/) (es6 to es5 transpiler and polyfills provider)
* assets minification (using [terser](https://github.com/terser-js/terser) and [cssnano](http://cssnano.co/)) but also dead code elimination for production use
## How to build, run and test
### Backend requirements
First you will need [Python 3](https://www.python.org) and a complete [swh development environment](https://forge.softwareheritage.org/source/swh-environment/) installed.
To run the backend, you need to have the following [Python 3 modules](requirements.txt) installed.
To run the backend tests, the following [Python 3 modules](requirements-test.txt) are also required to be installed.
One easy way to install them is to use the `pip` tool:
```
$ pip install -r requirements.txt -r requirements-test.txt
```
### Frontend requirements
To compile the frontend assets, you need to have [nodejs](https://nodejs.org/en/) >= 8.9.0 and [yarn](https://yarnpkg.com/en/) installed. If you are on Debian stretch, you can easily install an up to date nodejs from the [stretch-backports](https://backports.debian.org/Instructions/) repository.
Packages for yarn can be installed by following [these instructions](https://yarnpkg.com/en/docs/install#debian-stable).
Alternatively, you can install yarn with `npm install yarn`, and add `YARN=node_modules/yarn/bin/yarn` as argument whenever you run `make`.
Please note that the static assets bundles generated by webpack are not stored in the git repository. Follow the instructions below in order to generate them in order to be able to run the frontend part of the web applications.
### Make targets to execute the applications
Below is the list of available make targets that can be executed from the root directory of swh-web in order to build and/or execute the web applications under various configurations:
* **run-django-webpack-devserver**: Compile and serve not optimized (without mignification and dead code elimination) frontend static assets using [webpack-dev-server](https://github.com/webpack/webpack-dev-server) and run django server with development settings. This is the recommended target to use when developing swh-web as it enables automatic reloading of backend and frontend part of the applications when modifying source files (*.py, *.js, *.css, *.html).
* **run-django-webpack-dev**: Compile not optimized (no minification, no dead code elimination) frontend static assets using webpack and run django server with development settings. This is the recommended target when one only wants to develop the backend side of the application.
* **run-django-webpack-prod**: Compile optimized (with minification and dead code elimination) frontend static assets using webpack and run django server with production settings. This is useful to test the applications in production mode (with the difference that static assets are served by django). Production settings notably enable advanced django caching and you will need to have [memcached](https://memcached.org/) installed for that feature to work.
* **run-django-server-dev**: Run the django server with development settings but without compiling frontend static assets through webpack.
* **run-django-server-prod**: Run the django server with production settings but without compiling frontend static assets through webpack.
* **run-gunicorn-server**: Run the web applications with production settings in a [gunicorn](http://gunicorn.org/) worker as they will be in real production environment.
Once one of these targets executed, the web applications can be executed by pointing your browser to http://localhost:5004.
### Make targets to test the applications
Some make targets are also available to easily execute the backend and frontend tests of the Software Heritage web applications.
The backend tests are powered by the [pytest](https://docs.pytest.org/en/latest/) and [hypothesis](https://hypothesis.readthedocs.io/en/latest/) frameworks while the frontend ones rely on the use of the [cypress](https://www.cypress.io/) tool.
Below is the exhaustive list of those targets:
* **test**: execute the backend tests using a fast hypothesis profile (only one input example will be provided for each test)
* **test-full**: execute the backend tests using a slower hypothesis profile (one hundred of input examples will be provided for each test which helps spotting possible bugs)
* **test-frontend**: execute the frontend tests using cypress in headless mode but with some slow test suites disabled
* **test-frontend-full**: execute the frontend tests using cypress in headless mode with all test suites enabled
* **test-frontend-ui**: execute the frontend tests using the cypress GUI but with some slow test suites disabled
* **test-frontend-full-ui**: execute the frontend tests using the cypress GUI with all test suites enabled
### Yarn targets
Below is a list of available yarn targets in order to only execute the frontend static assets compilation (no web server will be executed):
* **build-dev**: compile not optimized (without mignification and dead code elimination) frontend static assets and store the results in the `swh/web/static` folder.
* **build**: compile optimized (with mignification and dead code elimination) frontend static assets and store the results in the `swh/web/static` folder.
**The build target must be executed prior performing the Debian packaging of swh-web** in order for the package to contain the optimized assets dedicated to production environment.
To execute these targets, issue the following command:
```
$ yarn <target_name>
```
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 5 - Production/Stable
Classifier: Framework :: Django
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Provides-Extra: testing
diff --git a/swh/web/common/archive.py b/swh/web/common/archive.py
index d3cb05fb..6bc8899f 100644
--- a/swh/web/common/archive.py
+++ b/swh/web/common/archive.py
@@ -1,1384 +1,1380 @@
-# Copyright (C) 2015-2020 The Software Heritage developers
+# Copyright (C) 2015-2021 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 collections import defaultdict
import itertools
import os
import re
from typing import Any, Dict, Iterable, Iterator, List, Optional, Set, Tuple, Union
from urllib.parse import urlparse
from swh.model import hashutil
from swh.model.identifiers import CONTENT, DIRECTORY, RELEASE, REVISION, SNAPSHOT
from swh.model.model import OriginVisit, Revision
from swh.storage.algos import diff, revisions_walker
from swh.storage.algos.origin import origin_get_latest_visit_status
from swh.storage.algos.snapshot import snapshot_get_latest, snapshot_resolve_alias
from swh.vault.exc import NotFoundExc as VaultNotFoundExc
from swh.web import config
from swh.web.common import converters, query
from swh.web.common.exc import BadInputExc, NotFoundExc
from swh.web.common.typing import (
OriginInfo,
OriginMetadataInfo,
OriginVisitInfo,
PagedResult,
)
search = config.search()
storage = config.storage()
vault = config.vault()
idx_storage = config.indexer_storage()
MAX_LIMIT = 50 # Top limit the users can ask for
def _first_element(lst):
"""Returns the first element in the provided list or None
if it is empty or None"""
return next(iter(lst or []), None)
def lookup_multiple_hashes(hashes):
"""Lookup the passed hashes in a single DB connection, using batch
processing.
Args:
An array of {filename: X, sha1: Y}, string X, hex sha1 string Y.
Returns:
The same array with elements updated with elem['found'] = true if
the hash is present in storage, elem['found'] = false if not.
"""
hashlist = [hashutil.hash_to_bytes(elem["sha1"]) for elem in hashes]
content_missing = storage.content_missing_per_sha1(hashlist)
missing = [hashutil.hash_to_hex(x) for x in content_missing]
for x in hashes:
x.update({"found": True})
for h in hashes:
if h["sha1"] in missing:
h["found"] = False
return hashes
def lookup_expression(expression, last_sha1, per_page):
"""Lookup expression in raw content.
Args:
expression (str): An expression to lookup through raw indexed
content
last_sha1 (str): Last sha1 seen
per_page (int): Number of results per page
Yields:
ctags whose content match the expression
"""
limit = min(per_page, MAX_LIMIT)
ctags = idx_storage.content_ctags_search(
expression, last_sha1=last_sha1, limit=limit
)
for ctag in ctags:
ctag = converters.from_swh(ctag, hashess={"id"})
ctag["sha1"] = ctag["id"]
ctag.pop("id")
yield ctag
def lookup_hash(q: str) -> Dict[str, Any]:
"""Check if the storage contains a given content checksum and return it if found.
Args:
q: query string of the form <hash_algo:hash>
Returns:
Dict with key found containing the hash info if the
hash is present, None if not.
"""
algo, hash_ = query.parse_hash(q)
found = _first_element(storage.content_find({algo: hash_}))
if found:
content = converters.from_content(found.to_dict())
else:
content = None
return {"found": content, "algo": algo}
def search_hash(q: str) -> Dict[str, bool]:
"""Search storage for a given content checksum.
Args:
q: query string of the form <hash_algo:hash>
Returns:
Dict with key found to True or False, according to
whether the checksum is present or not
"""
algo, hash_ = query.parse_hash(q)
found = _first_element(storage.content_find({algo: hash_}))
return {"found": found is not None}
def _lookup_content_sha1(q: str) -> Optional[bytes]:
"""Given a possible input, query for the content's sha1.
Args:
q: query string of the form <hash_algo:hash>
Returns:
binary sha1 if found or None
"""
algo, hash_ = query.parse_hash(q)
if algo != "sha1":
hashes = _first_element(storage.content_find({algo: hash_}))
if not hashes:
return None
return hashes.sha1
return hash_
def lookup_content_ctags(q):
"""Return ctags information from a specified content.
Args:
q: query string of the form <hash_algo:hash>
Yields:
ctags information (dict) list if the content is found.
"""
sha1 = _lookup_content_sha1(q)
if not sha1:
return None
ctags = list(idx_storage.content_ctags_get([sha1]))
if not ctags:
return None
for ctag in ctags:
yield converters.from_swh(ctag, hashess={"id"})
def lookup_content_filetype(q):
"""Return filetype information from a specified content.
Args:
q: query string of the form <hash_algo:hash>
Yields:
filetype information (dict) list if the content is found.
"""
sha1 = _lookup_content_sha1(q)
if not sha1:
return None
filetype = _first_element(list(idx_storage.content_mimetype_get([sha1])))
if not filetype:
return None
return converters.from_filetype(filetype.to_dict())
def lookup_content_language(q):
"""Always returns None.
This used to return language information from a specified content,
but this is currently disabled.
Args:
q: query string of the form <hash_algo:hash>
Yields:
language information (dict) list if the content is found.
"""
return None
def lookup_content_license(q):
"""Return license information from a specified content.
Args:
q: query string of the form <hash_algo:hash>
Yields:
license information (dict) list if the content is found.
"""
sha1 = _lookup_content_sha1(q)
if not sha1:
return None
licenses = list(idx_storage.content_fossology_license_get([sha1]))
if not licenses:
return None
license_dicts = [license.to_dict() for license in licenses]
for license_dict in license_dicts:
del license_dict["id"]
lic = {
"id": sha1,
"facts": license_dicts,
}
return converters.from_swh(lic, hashess={"id"})
def lookup_origin(origin: OriginInfo) -> OriginInfo:
"""Return information about the origin matching dict origin.
Args:
origin: origin's dict with 'url' key
Returns:
origin information as dict.
"""
origin_urls = [origin["url"]]
if origin["url"]:
# handle case when user provided an origin url with a trailing
# slash while the url in storage does not have it (e.g. GitHub)
if origin["url"].endswith("/"):
origin_urls.append(origin["url"][:-1])
# handle case when user provided an origin url without a trailing
# slash while the url in storage have it (e.g. Debian source package)
else:
origin_urls.append(f"{origin['url']}/")
try:
# handle case where the "://" character sequence was mangled into ":/"
parsed_url = urlparse(origin["url"])
if (
parsed_url.scheme
and not parsed_url.netloc
and origin["url"].startswith(f"{parsed_url.scheme}:/")
and not origin["url"].startswith(f"{parsed_url.scheme}://")
):
origin_urls.append(
origin["url"].replace(
f"{parsed_url.scheme}:/", f"{parsed_url.scheme}://"
)
)
except Exception:
pass
origins = [o for o in storage.origin_get(origin_urls) if o is not None]
if not origins:
msg = "Origin with url %s not found!" % origin["url"]
raise NotFoundExc(msg)
return converters.from_origin(origins[0].to_dict())
def lookup_origins(
page_token: Optional[str], limit: int = 100
) -> PagedResult[OriginInfo]:
"""Get list of archived software origins in a paginated way.
Origins are sorted by id before returning them
Args:
origin_from (int): The minimum id of the origins to return
origin_count (int): The maximum number of origins to return
Returns:
Page of OriginInfo
"""
page = storage.origin_list(page_token=page_token, limit=limit)
return PagedResult(
[converters.from_origin(o.to_dict()) for o in page.results],
next_page_token=page.next_page_token,
)
def search_origin(
url_pattern: str,
limit: int = 50,
with_visit: bool = False,
page_token: Optional[str] = None,
) -> Tuple[List[OriginInfo], Optional[str]]:
"""Search for origins whose urls contain a provided string pattern
or match a provided regular expression.
Args:
url_pattern: the string pattern to search for in origin urls
limit: the maximum number of found origins to return
page_token: opaque string used to get the next results of a search
Returns:
list of origin information as dict.
"""
if page_token:
assert isinstance(page_token, str)
if search:
page_result = search.origin_search(
url_pattern=url_pattern,
page_token=page_token,
with_visit=with_visit,
limit=limit,
)
origins = [converters.from_origin(ori_dict) for ori_dict in page_result.results]
else:
# Fallback to swh-storage if swh-search is not configured
search_words = [re.escape(word) for word in url_pattern.split()]
if len(search_words) >= 7:
url_pattern = ".*".join(search_words)
else:
pattern_parts = []
for permut in itertools.permutations(search_words):
pattern_parts.append(".*".join(permut))
url_pattern = "|".join(pattern_parts)
page_result = storage.origin_search(
url_pattern,
page_token=page_token,
with_visit=with_visit,
limit=limit,
regexp=True,
)
origins = [converters.from_origin(ori.to_dict()) for ori in page_result.results]
return (origins, page_result.next_page_token)
def search_origin_metadata(
fulltext: str, limit: int = 50
) -> Iterable[OriginMetadataInfo]:
"""Search for origins whose metadata match a provided string pattern.
Args:
fulltext: the string pattern to search for in origin metadata
limit: the maximum number of found origins to return
Returns:
Iterable of origin metadata information for existing origins
"""
matches = idx_storage.origin_intrinsic_metadata_search_fulltext(
conjunction=[fulltext], limit=limit
)
matches = [match.to_dict() for match in matches]
results = []
origins = storage.origin_get([match["id"] for match in matches])
for origin, match in zip(origins, matches):
if not origin:
continue
match["from_revision"] = hashutil.hash_to_hex(match["from_revision"])
del match["id"]
results.append(OriginMetadataInfo(url=origin.url, metadata=match))
return results
def lookup_origin_intrinsic_metadata(origin_url: str) -> Dict[str, Any]:
"""Return intrinsic metadata for origin whose origin matches given
origin.
Args:
origin_url: origin url
Raises:
NotFoundExc when the origin is not found
Returns:
origin metadata.
"""
origins = [origin_url]
origin_info = storage.origin_get(origins)[0]
if not origin_info:
raise NotFoundExc(f"Origin with url {origin_url} not found!")
match = _first_element(idx_storage.origin_intrinsic_metadata_get(origins))
result = {}
if match:
result = match.metadata
return result
def _to_sha1_bin(sha1_hex):
_, sha1_git_bin = query.parse_hash_with_algorithms_or_throws(
sha1_hex, ["sha1"], "Only sha1_git is supported." # HACK: sha1_git really
)
return sha1_git_bin
def _check_directory_exists(sha1_git, sha1_git_bin):
if len(list(storage.directory_missing([sha1_git_bin]))):
raise NotFoundExc("Directory with sha1_git %s not found" % sha1_git)
def lookup_directory(sha1_git):
"""Return information about the directory with id sha1_git.
Args:
sha1_git as string
Returns:
directory information as dict.
"""
empty_dir_sha1 = "4b825dc642cb6eb9a060e54bf8d69288fbee4904"
if sha1_git == empty_dir_sha1:
return []
sha1_git_bin = _to_sha1_bin(sha1_git)
_check_directory_exists(sha1_git, sha1_git_bin)
directory_entries = storage.directory_ls(sha1_git_bin)
return map(converters.from_directory_entry, directory_entries)
def lookup_directory_with_path(sha1_git: str, path: str) -> Dict[str, Any]:
"""Return directory information for entry with specified path w.r.t.
root directory pointed by sha1_git
Args:
sha1_git: sha1_git corresponding to the directory to which we
append paths to (hopefully) find the entry
path: the relative path to the entry starting from the root
directory pointed by sha1_git
Returns:
Directory entry information as dict.
Raises:
NotFoundExc if the directory entry is not found
"""
sha1_git_bin = _to_sha1_bin(sha1_git)
_check_directory_exists(sha1_git, sha1_git_bin)
paths = path.strip(os.path.sep).split(os.path.sep)
queried_dir = storage.directory_entry_get_by_path(
sha1_git_bin, [p.encode("utf-8") for p in paths]
)
if not queried_dir:
raise NotFoundExc(
f"Directory entry with path {path} from root directory {sha1_git} not found"
)
return converters.from_directory_entry(queried_dir)
def lookup_release(release_sha1_git: str) -> Dict[str, Any]:
"""Return information about the release with sha1 release_sha1_git.
Args:
release_sha1_git: The release's sha1 as hexadecimal
Returns:
Release information as dict.
Raises:
ValueError if the identifier provided is not of sha1 nature.
"""
sha1_git_bin = _to_sha1_bin(release_sha1_git)
release = _first_element(storage.release_get([sha1_git_bin]))
if not release:
raise NotFoundExc(f"Release with sha1_git {release_sha1_git} not found.")
return converters.from_release(release)
def lookup_release_multiple(sha1_git_list) -> Iterator[Optional[Dict[str, Any]]]:
"""Return information about the releases identified with
their sha1_git identifiers.
Args:
sha1_git_list: A list of release sha1_git identifiers
Returns:
Iterator of Release metadata information as dict.
Raises:
ValueError if the identifier provided is not of sha1 nature.
"""
sha1_bin_list = [_to_sha1_bin(sha1_git) for sha1_git in sha1_git_list]
releases = storage.release_get(sha1_bin_list)
for r in releases:
if r is not None:
yield converters.from_release(r)
else:
yield None
def lookup_revision(rev_sha1_git) -> Dict[str, Any]:
"""Return information about the revision with sha1 revision_sha1_git.
Args:
revision_sha1_git: The revision's sha1 as hexadecimal
Returns:
Revision information as dict.
Raises:
ValueError if the identifier provided is not of sha1 nature.
NotFoundExc if there is no revision with the provided sha1_git.
"""
sha1_git_bin = _to_sha1_bin(rev_sha1_git)
revision = storage.revision_get([sha1_git_bin])[0]
if not revision:
raise NotFoundExc(f"Revision with sha1_git {rev_sha1_git} not found.")
return converters.from_revision(revision)
def lookup_revision_multiple(sha1_git_list) -> Iterator[Optional[Dict[str, Any]]]:
"""Return information about the revisions identified with
their sha1_git identifiers.
Args:
sha1_git_list: A list of revision sha1_git identifiers
Yields:
revision information as dict if the revision exists, None otherwise.
Raises:
ValueError if the identifier provided is not of sha1 nature.
"""
sha1_bin_list = [_to_sha1_bin(sha1_git) for sha1_git in sha1_git_list]
revisions = storage.revision_get(sha1_bin_list)
for revision in revisions:
if revision is not None:
yield converters.from_revision(revision)
else:
yield None
def lookup_revision_message(rev_sha1_git) -> Dict[str, bytes]:
"""Return the raw message of the revision with sha1 revision_sha1_git.
Args:
revision_sha1_git: The revision's sha1 as hexadecimal
Returns:
Decoded revision message as dict {'message': <the_message>}
Raises:
ValueError if the identifier provided is not of sha1 nature.
NotFoundExc if the revision is not found, or if it has no message
"""
sha1_git_bin = _to_sha1_bin(rev_sha1_git)
revision = storage.revision_get([sha1_git_bin])[0]
if not revision:
raise NotFoundExc(f"Revision with sha1_git {rev_sha1_git} not found.")
if not revision.message:
raise NotFoundExc(f"No message for revision with sha1_git {rev_sha1_git}.")
return {"message": revision.message}
def _lookup_revision_id_by(origin, branch_name, timestamp):
def _get_snapshot_branch(snapshot, branch_name):
snapshot = lookup_snapshot(
visit["snapshot"], branches_from=branch_name, branches_count=10
)
branch = None
if branch_name in snapshot["branches"]:
branch = snapshot["branches"][branch_name]
return branch
if isinstance(origin, int):
origin = {"id": origin}
elif isinstance(origin, str):
origin = {"url": origin}
else:
raise TypeError('"origin" must be an int or a string.')
from swh.web.common.origin_visits import get_origin_visit
visit = get_origin_visit(origin, visit_ts=timestamp)
branch = _get_snapshot_branch(visit["snapshot"], branch_name)
rev_id = None
if branch and branch["target_type"] == "revision":
rev_id = branch["target"]
elif branch and branch["target_type"] == "alias":
branch = _get_snapshot_branch(visit["snapshot"], branch["target"])
if branch and branch["target_type"] == "revision":
rev_id = branch["target"]
if not rev_id:
raise NotFoundExc(
"Revision for origin %s and branch %s not found."
% (origin.get("url"), branch_name)
)
return rev_id
def lookup_revision_by(origin, branch_name="HEAD", timestamp=None):
"""Lookup revision by origin, snapshot branch name and visit timestamp.
If branch_name is not provided, lookup using 'HEAD' as default.
If timestamp is not provided, use the most recent.
Args:
origin (Union[int,str]): origin of the revision
branch_name (str): snapshot branch name
timestamp (str/int): origin visit time frame
Returns:
dict: The revision matching the criterions
Raises:
NotFoundExc if no revision corresponds to the criterion
"""
rev_id = _lookup_revision_id_by(origin, branch_name, timestamp)
return lookup_revision(rev_id)
def lookup_revision_log(rev_sha1_git, limit):
"""Lookup revision log by revision id.
Args:
rev_sha1_git (str): The revision's sha1 as hexadecimal
limit (int): the maximum number of revisions returned
Returns:
list: Revision log as list of revision dicts
Raises:
ValueError: if the identifier provided is not of sha1 nature.
swh.web.common.exc.NotFoundExc: if there is no revision with the
provided sha1_git.
"""
lookup_revision(rev_sha1_git)
sha1_git_bin = _to_sha1_bin(rev_sha1_git)
revision_entries = storage.revision_log([sha1_git_bin], limit)
return map(converters.from_revision, revision_entries)
def lookup_revision_log_by(origin, branch_name, timestamp, limit):
"""Lookup revision by origin, snapshot branch name and visit timestamp.
Args:
origin (Union[int,str]): origin of the revision
branch_name (str): snapshot branch
timestamp (str/int): origin visit time frame
limit (int): the maximum number of revisions returned
Returns:
list: Revision log as list of revision dicts
Raises:
swh.web.common.exc.NotFoundExc: if no revision corresponds to the
criterion
"""
rev_id = _lookup_revision_id_by(origin, branch_name, timestamp)
return lookup_revision_log(rev_id, limit)
def lookup_revision_with_context_by(
origin, branch_name, timestamp, sha1_git, limit=100
):
"""Return information about revision sha1_git, limited to the
sub-graph of all transitive parents of sha1_git_root.
sha1_git_root being resolved through the lookup of a revision by origin,
branch_name and ts.
In other words, sha1_git is an ancestor of sha1_git_root.
Args:
- origin: origin of the revision.
- branch_name: revision's branch.
- timestamp: revision's time frame.
- sha1_git: one of sha1_git_root's ancestors.
- limit: limit the lookup to 100 revisions back.
Returns:
Pair of (root_revision, revision).
Information on sha1_git if it is an ancestor of sha1_git_root
including children leading to sha1_git_root
Raises:
- BadInputExc in case of unknown algo_hash or bad hash.
- NotFoundExc if either revision is not found or if sha1_git is not an
ancestor of sha1_git_root.
"""
rev_root_id = _lookup_revision_id_by(origin, branch_name, timestamp)
rev_root_id_bin = hashutil.hash_to_bytes(rev_root_id)
rev_root = storage.revision_get([rev_root_id_bin])[0]
return (
converters.from_revision(rev_root) if rev_root else None,
lookup_revision_with_context(rev_root, sha1_git, limit),
)
def lookup_revision_with_context(
sha1_git_root: Union[str, Dict[str, Any], Revision], sha1_git: str, limit: int = 100
) -> Dict[str, Any]:
"""Return information about revision sha1_git, limited to the
sub-graph of all transitive parents of sha1_git_root.
In other words, sha1_git is an ancestor of sha1_git_root.
Args:
sha1_git_root: latest revision. The type is either a sha1 (as an hex
string) or a non converted dict.
sha1_git: one of sha1_git_root's ancestors
limit: limit the lookup to 100 revisions back
Returns:
Information on sha1_git if it is an ancestor of sha1_git_root
including children leading to sha1_git_root
Raises:
BadInputExc in case of unknown algo_hash or bad hash
NotFoundExc if either revision is not found or if sha1_git is not an
ancestor of sha1_git_root
"""
sha1_git_bin = _to_sha1_bin(sha1_git)
revision = storage.revision_get([sha1_git_bin])[0]
if not revision:
raise NotFoundExc(f"Revision {sha1_git} not found")
if isinstance(sha1_git_root, str):
sha1_git_root_bin = _to_sha1_bin(sha1_git_root)
revision_root = storage.revision_get([sha1_git_root_bin])[0]
if not revision_root:
raise NotFoundExc(f"Revision root {sha1_git_root} not found")
elif isinstance(sha1_git_root, Revision):
sha1_git_root_bin = sha1_git_root.id
else:
sha1_git_root_bin = sha1_git_root["id"]
revision_log = storage.revision_log([sha1_git_root_bin], limit)
parents: Dict[str, List[str]] = {}
children = defaultdict(list)
for rev in revision_log:
rev_id = rev["id"]
parents[rev_id] = []
for parent_id in rev["parents"]:
parents[rev_id].append(parent_id)
children[parent_id].append(rev_id)
if revision.id not in parents:
raise NotFoundExc(f"Revision {sha1_git} is not an ancestor of {sha1_git_root}")
revision_d = revision.to_dict()
revision_d["children"] = children[revision.id]
return converters.from_revision(revision_d)
def lookup_directory_with_revision(sha1_git, dir_path=None, with_data=False):
"""Return information on directory pointed by revision with sha1_git.
If dir_path is not provided, display top level directory.
Otherwise, display the directory pointed by dir_path (if it exists).
Args:
sha1_git: revision's hash.
dir_path: optional directory pointed to by that revision.
with_data: boolean that indicates to retrieve the raw data if the path
resolves to a content. Default to False (for the api)
Returns:
Information on the directory pointed to by that revision.
Raises:
BadInputExc in case of unknown algo_hash or bad hash.
NotFoundExc either if the revision is not found or the path referenced
does not exist.
NotImplementedError in case of dir_path exists but do not reference a
type 'dir' or 'file'.
"""
sha1_git_bin = _to_sha1_bin(sha1_git)
revision = storage.revision_get([sha1_git_bin])[0]
if not revision:
raise NotFoundExc(f"Revision {sha1_git} not found")
dir_sha1_git_bin = revision.directory
if dir_path:
paths = dir_path.strip(os.path.sep).split(os.path.sep)
entity = storage.directory_entry_get_by_path(
dir_sha1_git_bin, list(map(lambda p: p.encode("utf-8"), paths))
)
if not entity:
raise NotFoundExc(
"Directory or File '%s' pointed to by revision %s not found"
% (dir_path, sha1_git)
)
else:
entity = {"type": "dir", "target": dir_sha1_git_bin}
if entity["type"] == "dir":
directory_entries = storage.directory_ls(entity["target"]) or []
return {
"type": "dir",
"path": "." if not dir_path else dir_path,
"revision": sha1_git,
"content": list(map(converters.from_directory_entry, directory_entries)),
}
elif entity["type"] == "file": # content
content = _first_element(storage.content_find({"sha1_git": entity["target"]}))
if not content:
raise NotFoundExc(f"Content not found for revision {sha1_git}")
content_d = content.to_dict()
if with_data:
data = storage.content_get_data(content.sha1)
if data:
content_d["data"] = data
return {
"type": "file",
"path": "." if not dir_path else dir_path,
"revision": sha1_git,
"content": converters.from_content(content_d),
}
elif entity["type"] == "rev": # revision
revision = storage.revision_get([entity["target"]])[0]
return {
"type": "rev",
"path": "." if not dir_path else dir_path,
"revision": sha1_git,
"content": converters.from_revision(revision) if revision else None,
}
else:
raise NotImplementedError("Entity of type %s not implemented." % entity["type"])
def lookup_content(q: str) -> Dict[str, Any]:
"""Lookup the content designed by q.
Args:
q: The release's sha1 as hexadecimal
Raises:
NotFoundExc if the requested content is not found
"""
algo, hash_ = query.parse_hash(q)
c = _first_element(storage.content_find({algo: hash_}))
if not c:
hhex = hashutil.hash_to_hex(hash_)
raise NotFoundExc(f"Content with {algo} checksum equals to {hhex} not found!")
return converters.from_content(c.to_dict())
def lookup_content_raw(q: str) -> Dict[str, Any]:
"""Lookup the content defined by q.
Args:
q: query string of the form <hash_algo:hash>
Returns:
dict with 'sha1' and 'data' keys.
data representing its raw data decoded.
Raises:
NotFoundExc if the requested content is not found or
if the content bytes are not available in the storage
"""
c = lookup_content(q)
content_sha1_bytes = hashutil.hash_to_bytes(c["checksums"]["sha1"])
content_data = storage.content_get_data(content_sha1_bytes)
if content_data is None:
algo, hash_ = query.parse_hash(q)
raise NotFoundExc(
f"Bytes of content with {algo} checksum equals "
f"to {hashutil.hash_to_hex(hash_)} are not available!"
)
return converters.from_content({"sha1": content_sha1_bytes, "data": content_data})
def stat_counters():
"""Return the stat counters for Software Heritage
Returns:
A dict mapping textual labels to integer values.
"""
return storage.stat_counters()
def _lookup_origin_visits(
origin_url: str, last_visit: Optional[int] = None, limit: int = 10
) -> Iterator[OriginVisit]:
"""Yields the origin origins' visits.
Args:
origin_url (str): origin to list visits for
last_visit (int): last visit to lookup from
limit (int): Number of elements max to display
Yields:
OriginVisit for that origin
"""
limit = min(limit, MAX_LIMIT)
page_token: Optional[str]
if last_visit is not None:
page_token = str(last_visit)
else:
page_token = None
visit_page = storage.origin_visit_get(
origin_url, page_token=page_token, limit=limit
)
yield from visit_page.results
def lookup_origin_visits(
origin: str, last_visit: Optional[int] = None, per_page: int = 10
) -> Iterator[OriginVisitInfo]:
"""Yields the origin origins' visits.
Args:
origin: origin to list visits for
Yields:
Dictionaries of origin_visit for that origin
"""
for visit in _lookup_origin_visits(origin, last_visit=last_visit, limit=per_page):
visit_status = storage.origin_visit_status_get_latest(origin, visit.visit)
yield converters.from_origin_visit(
{**visit_status.to_dict(), "type": visit.type}
)
def lookup_origin_visit_latest(
origin_url: str,
require_snapshot: bool = False,
type: Optional[str] = None,
allowed_statuses: Optional[List[str]] = None,
) -> Optional[OriginVisitInfo]:
"""Return the origin's latest visit
Args:
origin_url: origin to list visits for
type: Optional visit type to filter on (e.g git, tar, dsc, svn,
hg, npm, pypi, ...)
allowed_statuses: list of visit statuses considered
to find the latest visit. For instance,
``allowed_statuses=['full']`` will only consider visits that
have successfully run to completion.
require_snapshot: filter out origins without a snapshot
Returns:
The origin visit info as dict if found
"""
- visit_and_status = origin_get_latest_visit_status(
+ visit_status = origin_get_latest_visit_status(
storage,
origin_url,
type=type,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
)
return (
- converters.from_origin_visit(
- {**visit_and_status[0].to_dict(), **visit_and_status[1].to_dict()}
- )
- if visit_and_status
- else None
+ converters.from_origin_visit(visit_status.to_dict()) if visit_status else None
)
def lookup_origin_visit(origin_url: str, visit_id: int) -> OriginVisitInfo:
"""Return information about visit visit_id with origin origin.
Args:
origin: origin concerned by the visit
visit_id: the visit identifier to lookup
Yields:
The dict origin_visit concerned
"""
visit = storage.origin_visit_get_by(origin_url, visit_id)
visit_status = storage.origin_visit_status_get_latest(origin_url, visit_id)
if not visit:
raise NotFoundExc(
f"Origin {origin_url} or its visit with id {visit_id} not found!"
)
return converters.from_origin_visit({**visit_status.to_dict(), "type": visit.type})
def lookup_snapshot_sizes(snapshot_id: str) -> Dict[str, int]:
"""Count the number of branches in the snapshot with the given id
Args:
snapshot_id (str): sha1 identifier of the snapshot
Returns:
dict: A dict whose keys are the target types of branches and
values their corresponding amount
"""
snapshot_id_bin = _to_sha1_bin(snapshot_id)
snapshot_sizes = dict.fromkeys(("alias", "release", "revision"), 0)
branch_counts = storage.snapshot_count_branches(snapshot_id_bin)
# remove possible None key returned by snapshot_count_branches
# when null branches are present in the snapshot
branch_counts.pop(None, None)
snapshot_sizes.update(branch_counts)
return snapshot_sizes
def lookup_snapshot(
snapshot_id, branches_from="", branches_count=1000, target_types=None
):
"""Return information about a snapshot, aka the list of named
branches found during a specific visit of an origin.
Args:
snapshot_id (str): sha1 identifier of the snapshot
branches_from (str): optional parameter used to skip branches
whose name is lesser than it before returning them
branches_count (int): optional parameter used to restrain
the amount of returned branches
target_types (list): optional parameter used to filter the
target types of branch to return (possible values that can be
contained in that list are `'content', 'directory',
'revision', 'release', 'snapshot', 'alias'`)
Returns:
A dict filled with the snapshot content.
"""
snapshot_id_bin = _to_sha1_bin(snapshot_id)
partial_branches = storage.snapshot_get_branches(
snapshot_id_bin, branches_from.encode(), branches_count, target_types
)
if not partial_branches:
raise NotFoundExc(f"Snapshot with id {snapshot_id} not found!")
return converters.from_partial_branches(partial_branches)
def lookup_latest_origin_snapshot(
origin: str, allowed_statuses: List[str] = None
) -> Optional[Dict[str, Any]]:
"""Return information about the latest snapshot of an origin.
.. warning:: At most 1000 branches contained in the snapshot
will be returned for performance reasons.
Args:
origin: URL or integer identifier of the origin
allowed_statuses: list of visit statuses considered
to find the latest snapshot for the visit. For instance,
``allowed_statuses=['full']`` will only consider visits that
have successfully run to completion.
Returns:
A dict filled with the snapshot content.
"""
snp = snapshot_get_latest(
storage, origin, allowed_statuses=allowed_statuses, branches_count=1000
)
return converters.from_snapshot(snp.to_dict()) if snp is not None else None
def lookup_snapshot_branch_name_from_tip_revision(
snapshot_id: str, revision_id: str
) -> Optional[str]:
"""Check if a revision corresponds to the tip of a snapshot branch
Args:
snapshot_id: hexadecimal representation of a snapshot id
revision_id: hexadecimal representation of a revision id
Returns:
The name of the first found branch or None otherwise
"""
per_page = 10000
branches_from = ""
snapshot: Dict[str, Any] = {"branches": {}}
branches = []
while not branches_from or len(snapshot["branches"]) == per_page + 1:
snapshot = lookup_snapshot(
snapshot_id,
target_types=[REVISION],
branches_from=branches_from,
branches_count=per_page + 1,
)
branches += [
{"name": k, "target": v["target"]} for k, v in snapshot["branches"].items()
]
branches_from = branches[-1]["name"]
for branch in branches:
if branch["target"] == revision_id:
return branch["name"]
return None
def lookup_snapshot_alias(
snapshot_id: str, alias_name: str
) -> Optional[Dict[str, Any]]:
"""Try to resolve a branch alias in a snapshot.
Args:
snapshot_id: hexadecimal representation of a snapshot id
alias_name: name of the branch alias to resolve
Returns:
Target branch information or None if the alias does not exist
or target a dangling branch.
"""
resolved_alias = snapshot_resolve_alias(
storage, _to_sha1_bin(snapshot_id), alias_name.encode()
)
return (
converters.from_swh(resolved_alias.to_dict(), hashess={"target"})
if resolved_alias is not None
else None
)
def lookup_revision_through(revision, limit=100):
"""Retrieve a revision from the criterion stored in revision dictionary.
Args:
revision: Dictionary of criterion to lookup the revision with.
Here are the supported combination of possible values:
- origin_url, branch_name, ts, sha1_git
- origin_url, branch_name, ts
- sha1_git_root, sha1_git
- sha1_git
Returns:
None if the revision is not found or the actual revision.
"""
if (
"origin_url" in revision
and "branch_name" in revision
and "ts" in revision
and "sha1_git" in revision
):
return lookup_revision_with_context_by(
revision["origin_url"],
revision["branch_name"],
revision["ts"],
revision["sha1_git"],
limit,
)
if "origin_url" in revision and "branch_name" in revision and "ts" in revision:
return lookup_revision_by(
revision["origin_url"], revision["branch_name"], revision["ts"]
)
if "sha1_git_root" in revision and "sha1_git" in revision:
return lookup_revision_with_context(
revision["sha1_git_root"], revision["sha1_git"], limit
)
if "sha1_git" in revision:
return lookup_revision(revision["sha1_git"])
# this should not happen
raise NotImplementedError("Should not happen!")
def lookup_directory_through_revision(revision, path=None, limit=100, with_data=False):
"""Retrieve the directory information from the revision.
Args:
revision: dictionary of criterion representing a revision to lookup
path: directory's path to lookup.
limit: optional query parameter to limit the revisions log (default to
100). For now, note that this limit could impede the transitivity
conclusion about sha1_git not being an ancestor of.
with_data: indicate to retrieve the content's raw data if path resolves
to a content.
Returns:
The directory pointing to by the revision criterions at path.
"""
rev = lookup_revision_through(revision, limit)
if not rev:
raise NotFoundExc("Revision with criterion %s not found!" % revision)
return (rev["id"], lookup_directory_with_revision(rev["id"], path, with_data))
def _vault_request(vault_fn, *args, **kwargs):
try:
return vault_fn(*args, **kwargs)
except VaultNotFoundExc:
return None
def vault_cook(obj_type, obj_id, email=None):
"""Cook a vault bundle.
"""
return _vault_request(vault.cook, obj_type, obj_id, email=email)
def vault_fetch(obj_type, obj_id):
"""Fetch a vault bundle.
"""
return _vault_request(vault.fetch, obj_type, obj_id)
def vault_progress(obj_type, obj_id):
"""Get the current progress of a vault bundle.
"""
return _vault_request(vault.progress, obj_type, obj_id)
def diff_revision(rev_id):
"""Get the list of file changes (insertion / deletion / modification /
renaming) for a particular revision.
"""
rev_sha1_git_bin = _to_sha1_bin(rev_id)
changes = diff.diff_revision(storage, rev_sha1_git_bin, track_renaming=True)
for change in changes:
change["from"] = converters.from_directory_entry(change["from"])
change["to"] = converters.from_directory_entry(change["to"])
if change["from_path"]:
change["from_path"] = change["from_path"].decode("utf-8")
if change["to_path"]:
change["to_path"] = change["to_path"].decode("utf-8")
return changes
class _RevisionsWalkerProxy(object):
"""
Proxy class wrapping a revisions walker iterator from
swh-storage and performing needed conversions.
"""
def __init__(self, rev_walker_type, rev_start, *args, **kwargs):
rev_start_bin = hashutil.hash_to_bytes(rev_start)
self.revisions_walker = revisions_walker.get_revisions_walker(
rev_walker_type, storage, rev_start_bin, *args, **kwargs
)
def export_state(self):
return self.revisions_walker.export_state()
def __next__(self):
return converters.from_revision(next(self.revisions_walker))
def __iter__(self):
return self
def get_revisions_walker(rev_walker_type, rev_start, *args, **kwargs):
"""
Utility function to instantiate a revisions walker of a given type,
see :mod:`swh.storage.algos.revisions_walker`.
Args:
rev_walker_type (str): the type of revisions walker to return,
possible values are: ``committer_date``, ``dfs``, ``dfs_post``,
``bfs`` and ``path``
rev_start (str): hexadecimal representation of a revision identifier
args (list): position arguments to pass to the revisions walker
constructor
kwargs (dict): keyword arguments to pass to the revisions walker
constructor
"""
# first check if the provided revision is valid
lookup_revision(rev_start)
return _RevisionsWalkerProxy(rev_walker_type, rev_start, *args, **kwargs)
def lookup_object(object_type: str, object_id: str) -> Dict[str, Any]:
"""
Utility function for looking up an object in the archive by its type
and id.
Args:
object_type (str): the type of object to lookup, either *content*,
*directory*, *release*, *revision* or *snapshot*
object_id (str): the *sha1_git* checksum identifier in hexadecimal
form of the object to lookup
Returns:
Dict[str, Any]: A dictionary describing the object or a list of
dictionary for the directory object type.
Raises:
swh.web.common.exc.NotFoundExc: if the object could not be found in
the archive
BadInputExc: if the object identifier is invalid
"""
if object_type == CONTENT:
return lookup_content(f"sha1_git:{object_id}")
elif object_type == DIRECTORY:
return {"id": object_id, "content": list(lookup_directory(object_id))}
elif object_type == RELEASE:
return lookup_release(object_id)
elif object_type == REVISION:
return lookup_revision(object_id)
elif object_type == SNAPSHOT:
return lookup_snapshot(object_id)
raise BadInputExc(
(
"Invalid swh object type! Valid types are "
f"{CONTENT}, {DIRECTORY}, {RELEASE} "
f"{REVISION} or {SNAPSHOT}."
)
)
def lookup_missing_hashes(grouped_swhids: Dict[str, List[bytes]]) -> Set[str]:
"""Lookup missing Software Heritage persistent identifier hash, using
batch processing.
Args:
A dictionary with:
keys: object types
values: object hashes
Returns:
A set(hexadecimal) of the hashes not found in the storage
"""
missing_hashes = []
for obj_type, obj_ids in grouped_swhids.items():
if obj_type == CONTENT:
missing_hashes.append(storage.content_missing_per_sha1_git(obj_ids))
elif obj_type == DIRECTORY:
missing_hashes.append(storage.directory_missing(obj_ids))
elif obj_type == REVISION:
missing_hashes.append(storage.revision_missing(obj_ids))
elif obj_type == RELEASE:
missing_hashes.append(storage.release_missing(obj_ids))
elif obj_type == SNAPSHOT:
missing_hashes.append(storage.snapshot_missing(obj_ids))
missing = set(
map(lambda x: hashutil.hash_to_hex(x), itertools.chain(*missing_hashes))
)
return missing
def lookup_origins_by_sha1s(sha1s: List[str]) -> Iterator[Optional[OriginInfo]]:
"""Lookup origins from the sha1 hash values of their URLs.
Args:
sha1s: list of sha1s hexadecimal representation
Yields:
origin information as dict
"""
sha1s_bytes = [hashutil.hash_to_bytes(sha1) for sha1 in sha1s]
origins = storage.origin_get_by_sha1(sha1s_bytes)
for origin in origins:
yield converters.from_origin(origin)
diff --git a/swh/web/tests/conftest.py b/swh/web/tests/conftest.py
index 788d5721..30dc3647 100644
--- a/swh/web/tests/conftest.py
+++ b/swh/web/tests/conftest.py
@@ -1,360 +1,358 @@
-# Copyright (C) 2018-2020 The Software Heritage developers
+# 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
import json
import os
import shutil
from subprocess import PIPE, run
import sys
from typing import Any, Dict, List, Optional
from hypothesis import HealthCheck
from hypothesis import __version_info__ as hypothesis_version
from hypothesis import settings
import pytest
from django.core.cache import cache
from rest_framework.test import APIClient, APIRequestFactory
from swh.model.hashutil import ALGORITHMS, hash_to_bytes
from swh.storage.algos.origin import origin_get_latest_visit_status
from swh.storage.algos.snapshot import snapshot_get_all_branches, snapshot_get_latest
from swh.web.common import converters
from swh.web.common.typing import OriginVisitInfo
from swh.web.tests.data import get_tests_data, override_storages
# Used to skip some tests
ctags_json_missing = (
shutil.which("ctags") is None
or b"+json" not in run(["ctags", "--version"], stdout=PIPE).stdout
)
fossology_missing = shutil.which("nomossa") is None
# Register some hypothesis profiles
settings.register_profile("default", settings())
suppress_health_check = [HealthCheck.too_slow, HealthCheck.filter_too_much]
if hypothesis_version >= (5, 49):
suppress_health_check.append(HealthCheck.function_scoped_fixture)
settings.register_profile(
"swh-web", settings(deadline=None, suppress_health_check=suppress_health_check,),
)
settings.register_profile(
"swh-web-fast",
settings(
deadline=None, max_examples=1, suppress_health_check=suppress_health_check,
),
)
def pytest_configure(config):
# Use fast hypothesis profile by default if none has been
# explicitly specified in pytest option
if config.getoption("--hypothesis-profile") is None:
settings.load_profile("swh-web-fast")
# Small hack in order to be able to run the unit tests
# without static assets generated by webpack.
# Those assets are not really needed for the Python tests
# but the django templates will fail to load due to missing
# generated file webpack-stats.json describing the js and css
# files to include.
# So generate a dummy webpack-stats.json file to overcome
# that issue.
test_dir = os.path.dirname(__file__)
# location of the static folder when running tests through tox
static_dir = os.path.join(sys.prefix, "share/swh/web/static")
if not os.path.exists(static_dir):
# location of the static folder when running tests locally with pytest
static_dir = os.path.join(test_dir, "../../../static")
webpack_stats = os.path.join(static_dir, "webpack-stats.json")
if os.path.exists(webpack_stats):
return
bundles_dir = os.path.join(test_dir, "../assets/src/bundles")
_, dirs, _ = next(os.walk(bundles_dir))
mock_webpack_stats = {"status": "done", "publicPath": "/static", "chunks": {}}
for bundle in dirs:
asset = "js/%s.js" % bundle
mock_webpack_stats["chunks"][bundle] = [
{
"name": asset,
"publicPath": "/static/%s" % asset,
"path": os.path.join(static_dir, asset),
}
]
with open(webpack_stats, "w") as outfile:
json.dump(mock_webpack_stats, outfile)
# Clear Django cache before each test
@pytest.fixture(autouse=True)
def django_cache_cleared():
cache.clear()
# Alias rf fixture from pytest-django
@pytest.fixture
def request_factory(rf):
return rf
# Fixture to get test client from Django REST Framework
@pytest.fixture(scope="module")
def api_client():
return APIClient()
# Fixture to get API request factory from Django REST Framework
@pytest.fixture(scope="module")
def api_request_factory():
return APIRequestFactory()
# Initialize tests data
@pytest.fixture(scope="session", autouse=True)
def tests_data():
data = get_tests_data(reset=True)
# Update swh-web configuration to use the in-memory storages
# instantiated in the tests.data module
override_storages(data["storage"], data["idx_storage"], data["search"])
return data
# Fixture to manipulate data from a sample archive used in the tests
@pytest.fixture(scope="session")
def archive_data(tests_data):
return _ArchiveData(tests_data)
# Fixture to manipulate indexer data from a sample archive used in the tests
@pytest.fixture(scope="session")
def indexer_data(tests_data):
return _IndexerData(tests_data)
# Custom data directory for requests_mock
@pytest.fixture
def datadir():
return os.path.join(os.path.abspath(os.path.dirname(__file__)), "resources")
class _ArchiveData:
"""
Helper class to manage data from a sample test archive.
It is initialized with a reference to an in-memory storage
containing raw tests data.
It is basically a proxy to Storage interface but it overrides some methods
to retrieve those tests data in a json serializable format in order to ease
tests implementation.
"""
def __init__(self, tests_data):
self.storage = tests_data["storage"]
def __getattr__(self, key):
if key == "storage":
raise AttributeError(key)
# Forward calls to non overridden Storage methods to wrapped
# storage instance
return getattr(self.storage, key)
def content_find(self, content: Dict[str, Any]) -> Dict[str, Any]:
cnt_ids_bytes = {
algo_hash: hash_to_bytes(content[algo_hash])
for algo_hash in ALGORITHMS
if content.get(algo_hash)
}
cnt = self.storage.content_find(cnt_ids_bytes)
return converters.from_content(cnt[0].to_dict()) if cnt else cnt
def content_get(self, cnt_id: str) -> Dict[str, Any]:
cnt_id_bytes = hash_to_bytes(cnt_id)
content = self.storage.content_get([cnt_id_bytes])[0]
if content:
content_d = content.to_dict()
content_d.pop("ctime", None)
else:
content_d = None
return converters.from_swh(
content_d, hashess={"sha1", "sha1_git", "sha256", "blake2s256"}
)
def content_get_data(self, cnt_id: str) -> Optional[Dict[str, Any]]:
cnt_id_bytes = hash_to_bytes(cnt_id)
cnt_data = self.storage.content_get_data(cnt_id_bytes)
if cnt_data is None:
return None
return converters.from_content({"data": cnt_data, "sha1": cnt_id_bytes})
def directory_get(self, dir_id):
return {"id": dir_id, "content": self.directory_ls(dir_id)}
def directory_ls(self, dir_id):
cnt_id_bytes = hash_to_bytes(dir_id)
dir_content = map(
converters.from_directory_entry, self.storage.directory_ls(cnt_id_bytes)
)
return list(dir_content)
def release_get(self, rel_id: str) -> Optional[Dict[str, Any]]:
rel_id_bytes = hash_to_bytes(rel_id)
rel_data = self.storage.release_get([rel_id_bytes])[0]
return converters.from_release(rel_data) if rel_data else None
def revision_get(self, rev_id: str) -> Optional[Dict[str, Any]]:
rev_id_bytes = hash_to_bytes(rev_id)
rev_data = self.storage.revision_get([rev_id_bytes])[0]
return converters.from_revision(rev_data) if rev_data else None
def revision_log(self, rev_id, limit=None):
rev_id_bytes = hash_to_bytes(rev_id)
return list(
map(
converters.from_revision,
self.storage.revision_log([rev_id_bytes], limit=limit),
)
)
def snapshot_get_latest(self, origin_url):
snp = snapshot_get_latest(self.storage, origin_url)
return converters.from_snapshot(snp.to_dict())
def origin_get(self, origin_urls):
origins = self.storage.origin_get(origin_urls)
return [converters.from_origin(o.to_dict()) for o in origins]
def origin_visit_get(self, origin_url):
next_page_token = None
visits = []
while True:
visit_page = self.storage.origin_visit_get(
origin_url, page_token=next_page_token
)
next_page_token = visit_page.next_page_token
for visit in visit_page.results:
visit_status = self.storage.origin_visit_status_get_latest(
origin_url, visit.visit
)
visits.append(
converters.from_origin_visit(
{**visit_status.to_dict(), "type": visit.type}
)
)
if not next_page_token:
break
return visits
def origin_visit_get_by(self, origin_url: str, visit_id: int) -> OriginVisitInfo:
visit = self.storage.origin_visit_get_by(origin_url, visit_id)
assert visit is not None
visit_status = self.storage.origin_visit_status_get_latest(origin_url, visit_id)
assert visit_status is not None
return converters.from_origin_visit(
{**visit_status.to_dict(), "type": visit.type}
)
def origin_visit_status_get_latest(
self,
origin_url,
type: Optional[str] = None,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
):
- visit_and_status = origin_get_latest_visit_status(
+ visit_status = origin_get_latest_visit_status(
self.storage,
origin_url,
type=type,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
)
return (
- converters.from_origin_visit(
- {**visit_and_status[0].to_dict(), **visit_and_status[1].to_dict()}
- )
- if visit_and_status
+ converters.from_origin_visit(visit_status.to_dict())
+ if visit_status
else None
)
def snapshot_get(self, snapshot_id):
snp = snapshot_get_all_branches(self.storage, hash_to_bytes(snapshot_id))
return converters.from_snapshot(snp.to_dict())
def snapshot_get_branches(
self, snapshot_id, branches_from="", branches_count=1000, target_types=None
):
partial_branches = self.storage.snapshot_get_branches(
hash_to_bytes(snapshot_id),
branches_from.encode(),
branches_count,
target_types,
)
return converters.from_partial_branches(partial_branches)
def snapshot_get_head(self, snapshot):
if snapshot["branches"]["HEAD"]["target_type"] == "alias":
target = snapshot["branches"]["HEAD"]["target"]
head = snapshot["branches"][target]["target"]
else:
head = snapshot["branches"]["HEAD"]["target"]
return head
def snapshot_count_branches(self, snapshot_id):
counts = dict.fromkeys(("alias", "release", "revision"), 0)
counts.update(self.storage.snapshot_count_branches(hash_to_bytes(snapshot_id)))
counts.pop(None, None)
return counts
class _IndexerData:
"""
Helper class to manage indexer tests data
It is initialized with a reference to an in-memory indexer storage
containing raw tests data.
It also defines class methods to retrieve those tests data in
a json serializable format in order to ease tests implementation.
"""
def __init__(self, tests_data):
self.idx_storage = tests_data["idx_storage"]
self.mimetype_indexer = tests_data["mimetype_indexer"]
self.license_indexer = tests_data["license_indexer"]
self.ctags_indexer = tests_data["ctags_indexer"]
def content_add_mimetype(self, cnt_id):
self.mimetype_indexer.run([hash_to_bytes(cnt_id)])
def content_get_mimetype(self, cnt_id):
mimetype = self.idx_storage.content_mimetype_get([hash_to_bytes(cnt_id)])[
0
].to_dict()
return converters.from_filetype(mimetype)
def content_add_license(self, cnt_id):
self.license_indexer.run([hash_to_bytes(cnt_id)])
def content_get_license(self, cnt_id):
cnt_id_bytes = hash_to_bytes(cnt_id)
licenses = self.idx_storage.content_fossology_license_get([cnt_id_bytes])
for license in licenses:
yield converters.from_swh(license.to_dict(), hashess={"id"})
def content_add_ctags(self, cnt_id):
self.ctags_indexer.run([hash_to_bytes(cnt_id)])
def content_get_ctags(self, cnt_id):
cnt_id_bytes = hash_to_bytes(cnt_id)
ctags = self.idx_storage.content_ctags_get([cnt_id_bytes])
for ctag in ctags:
yield converters.from_swh(ctag, hashess={"id"})
diff --git a/swh/web/tests/data.py b/swh/web/tests/data.py
index 84f38693..859ae47e 100644
--- a/swh/web/tests/data.py
+++ b/swh/web/tests/data.py
@@ -1,400 +1,402 @@
# Copyright (C) 2018-2020 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
import random
import time
from typing import Dict, List, Optional, Set
from swh.core.config import merge_configs
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_bytes, hash_to_hex
from swh.model.model import Content, Directory, Origin, OriginVisit, OriginVisitStatus
from swh.search import get_search
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,
)
from swh.web.common import archive
# Module used to initialize data that will be provided as tests input
# Configuration for git loader
_TEST_LOADER_CONFIG = {
"storage": {"cls": "memory",},
"save_data": False,
"max_content_size": 100 * 1024 * 1024,
}
# 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"],
},
{
"type": "git",
"url": "https://github.com/wcoder/highlightjs-line-numbers.js",
"archives": [
"highlightjs-line-numbers.js.zip",
"highlightjs-line-numbers.js_visit2.zip",
],
},
{
"type": "git",
"url": "repo_with_submodules",
"archives": ["repo_with_submodules.tgz"],
},
]
_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)
INDEXER_TOOL = {
"tool_name": "swh-web tests",
"tool_version": "1.0",
"tool_configuration": {},
}
ORIGIN_METADATA_KEY = "vcs"
ORIGIN_METADATA_VALUE = "git"
ORIGIN_MASTER_REVISION = {}
# Tests data initialization
def _init_tests_data():
# To hold reference to the memory storage
storage = None
# Create search instance
search = get_search("memory")
search.initialize()
search.origin_update({"url": origin["url"]} for origin in _TEST_ORIGINS)
# 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(
origin["url"],
archive_path=origin_repo_archive,
config=_TEST_LOADER_CONFIG,
)
if storage is None:
storage = loader.storage
else:
loader.storage = storage
- loader.load()
+ 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}])
for i in range(250):
url = "https://many.origins/%d" % (i + 1)
# storage.origin_add([{'url': url}])
storage.origin_add([Origin(url=url)])
search.origin_update([{"url": url, "has_visits": True}])
date = now()
visit = OriginVisit(origin=url, date=date, type="tar")
visit = storage.origin_visit_add([visit])[0]
visit_status = OriginVisitStatus(
origin=url,
visit=visit.visit,
date=date + timedelta(minutes=1),
+ type=visit.type,
status="full",
snapshot=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"),
)
storage.origin_visit_status_add([visit_status])
sha1s: Set[Sha1] = set()
directories = set()
revisions = set()
releases = set()
snapshots = set()
content_path = {}
# Get all objects loaded into the test archive
for origin in _TEST_ORIGINS:
snp = snapshot_get_latest(storage, 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":
revisions.add(branch_data.target)
if b"master" in branch_name:
# Add some origin intrinsic metadata for tests
origin_metadata = OriginIntrinsicMetadataRow(
id=origin["url"],
from_revision=branch_data.target,
indexer_configuration_id=idx_tool["id"],
metadata={ORIGIN_METADATA_KEY: ORIGIN_METADATA_VALUE},
mappings=[],
)
idx_storage.origin_intrinsic_metadata_add([origin_metadata])
ORIGIN_MASTER_REVISION[origin["url"]] = hash_to_hex(
branch_data.target
)
elif target_type == "release":
release = storage.release_get([branch_data.target])[0]
revisions.add(release.target)
releases.add(hash_to_hex(branch_data.target))
for rev_log in storage.revision_shortlog(set(revisions)):
rev_id = rev_log[0]
revisions.add(rev_id)
for rev in storage.revision_get(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")]
)
elif entry["type"] == "dir":
directories.add(hash_to_hex(entry["target"]))
_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)
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"],
"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"")])
# Return tests data
return {
"search": search,
"storage": storage,
"idx_storage": idx_storage,
"origins": _TEST_ORIGINS,
"contents": contents,
"directories": list(directories),
"releases": list(releases),
"revisions": list(map(hash_to_hex, revisions)),
"snapshots": list(snapshots),
"generated_checksums": set(),
}
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):
"""
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,}
)
archive.storage = storage
archive.idx_storage = idx_storage
archive.search = search
diff --git a/swh/web/tests/resources/contents/code/extensions/test.py b/swh/web/tests/resources/contents/code/extensions/test.py
index d0ecaf42..395ccba9 100644
--- a/swh/web/tests/resources/contents/code/extensions/test.py
+++ b/swh/web/tests/resources/contents/code/extensions/test.py
@@ -1,12 +1,12 @@
# flake8: noqa
-@requires_authorization
-def somefunc(param1='', param2=0):
- r'''A docstring'''
+
+def somefunc(param1="", param2=0):
+ r"""A docstring"""
if param1 > param2: # interesting
- print('Gre\'ater')
- return (param2 - param1 + 1 + 0b10l) or None
+ print("Gre'ater")
+ return (param2 - param1 + 1) or None
class SomeClass:
pass

File Metadata

Mime Type
text/x-diff
Expires
Jul 4 2025, 10:31 AM (4 w, 5 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3245604

Event Timeline

About · Developer information · Legal