Page MenuHomeSoftware Heritage
Files F9342820

No OneTemporary
Actions

View Options

diff --git a/swh/web/common/origin_visits.py b/swh/web/common/origin_visits.py
index 8f63d5b1..54b8cecc 100644
--- a/swh/web/common/origin_visits.py
+++ b/swh/web/common/origin_visits.py
@@ -1,193 +1,197 @@
# Copyright (C) 2018-2019 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 math
from typing import List, Optional
from django.core.cache import cache
+from swh.web.common import service
from swh.web.common.exc import NotFoundExc
from swh.web.common.typing import OriginInfo, OriginVisitInfo
from swh.web.common.utils import parse_iso8601_date_to_utc
def get_origin_visits(origin_info: OriginInfo) -> List[OriginVisitInfo]:
"""Function that returns the list of visits for a swh origin.
That list is put in cache in order to speedup the navigation
in the swh web browse ui.
The returned visits are sorted according to their date in
ascending order.
Args:
origin_info: dict describing the origin to fetch visits from
Returns:
A list of dict describing the origin visits
Raises:
swh.web.common.exc.NotFoundExc: if the origin is not found
"""
from swh.web.common import service
if "url" in origin_info:
origin_url = origin_info["url"]
else:
origin_url = service.lookup_origin(origin_info)["url"]
cache_entry_id = "origin_visits_%s" % origin_url
cache_entry = cache.get(cache_entry_id)
if cache_entry:
last_visit = cache_entry[-1]["visit"]
new_visits = list(
service.lookup_origin_visits(origin_url, last_visit=last_visit)
)
if not new_visits:
last_snp = service.lookup_latest_origin_snapshot(origin_url)
if not last_snp or last_snp["id"] == cache_entry[-1]["snapshot"]:
return cache_entry
origin_visits = []
per_page = service.MAX_LIMIT
last_visit = None
while 1:
visits = list(
service.lookup_origin_visits(
origin_url, last_visit=last_visit, per_page=per_page
)
)
origin_visits += visits
if len(visits) < per_page:
break
else:
if not last_visit:
last_visit = per_page
else:
last_visit += per_page
def _visit_sort_key(visit):
ts = parse_iso8601_date_to_utc(visit["date"]).timestamp()
return ts + (float(visit["visit"]) / 10e3)
origin_visits = sorted(origin_visits, key=lambda v: _visit_sort_key(v))
cache.set(cache_entry_id, origin_visits)
return origin_visits
def get_origin_visit(
origin_info: OriginInfo,
visit_ts: Optional[str] = None,
visit_id: Optional[int] = None,
snapshot_id: Optional[str] = None,
) -> OriginVisitInfo:
"""Function that returns information about a visit for a given origin.
If a timestamp is provided, the closest visit from that
timestamp is returned.
If a snapshot identifier is provided, the first visit with that snapshot
is returned.
If no search hints are provided, return the most recent full visit with
a valid snapshot or the most recent partial visit with a valid snapshot
otherwise.
Args:
origin_info: a dict filled with origin information
visit_ts: an ISO 8601 datetime string to parse
snapshot_id: a snapshot identifier
Returns:
A dict containing the visit info.
Raises:
swh.web.common.exc.NotFoundExc: if no visit can be found
"""
-
- if not visit_ts and not visit_id and not snapshot_id:
- from swh.web.common import service
-
- # returns the latest full visit with a valid snapshot
+ # returns the latest full visit with a valid snapshot
+ visit = service.lookup_origin_visit_latest(
+ origin_info["url"], allowed_statuses=["full"], require_snapshot=True
+ )
+ if not visit:
+ # or the latest partial visit with a valid snapshot otherwise
visit = service.lookup_origin_visit_latest(
- origin_info["url"], allowed_statuses=["full"], require_snapshot=True
+ origin_info["url"], allowed_statuses=["partial"], require_snapshot=True
)
- if not visit:
- # or the latest partial visit with a valid snapshot otherwise
- visit = service.lookup_origin_visit_latest(
- origin_info["url"], allowed_statuses=["partial"], require_snapshot=True
- )
+
+ if not visit_ts and not visit_id and not snapshot_id:
if visit:
return visit
else:
raise NotFoundExc(
f"No valid visit for origin with url {origin_info['url']} found!"
)
+ # no need to fetch all visits list and search in it if the latest
+ # visit matches some criteria
+ if visit and (visit["snapshot"] == snapshot_id or visit["visit"] == visit_id):
+ return visit
+
visits = get_origin_visits(origin_info)
if not visits:
raise NotFoundExc(
f"No visits associated to origin with url {origin_info['url']}!"
)
if snapshot_id:
visits = [v for v in visits if v["snapshot"] == snapshot_id]
if len(visits) == 0:
raise NotFoundExc(
(
"Visit for snapshot with id %s for origin with"
" url %s not found!" % (snapshot_id, origin_info["url"])
)
)
return visits[0]
if visit_id:
visits = [v for v in visits if v["visit"] == int(visit_id)]
if len(visits) == 0:
raise NotFoundExc(
(
"Visit with id %s for origin with"
" url %s not found!" % (visit_id, origin_info["url"])
)
)
return visits[0]
if visit_ts:
target_visit_ts = math.floor(parse_iso8601_date_to_utc(visit_ts).timestamp())
# Find the visit with date closest to the target (in absolute value)
(abs_time_delta, visit_idx) = min(
(
(math.floor(parse_iso8601_date_to_utc(visit["date"]).timestamp()), i)
for (i, visit) in enumerate(visits)
),
key=lambda ts_and_i: abs(ts_and_i[0] - target_visit_ts),
)
if visit_idx is not None:
visit = visits[visit_idx]
# If multiple visits have the same date, select the one with
# the largest id.
while (
visit_idx < len(visits) - 1
and visit["date"] == visits[visit_idx + 1]["date"]
):
visit_idx = visit_idx + 1
visit = visits[visit_idx]
return visit
else:
raise NotFoundExc(
(
"Visit with timestamp %s for origin with "
"url %s not found!" % (visit_ts, origin_info["url"])
)
)
return visits[-1]
diff --git a/swh/web/common/service.py b/swh/web/common/service.py
index a8773ae4..cfc25947 100644
--- a/swh/web/common/service.py
+++ b/swh/web/common/service.py
@@ -1,1338 +1,1339 @@
# Copyright (C) 2015-2020 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
import itertools
import os
import re
from collections import defaultdict
from typing import Any, Dict, List, Set, Iterable, Iterator, Optional, Tuple
from swh.model import hashutil
from swh.model.identifiers import CONTENT, DIRECTORY, RELEASE, REVISION, SNAPSHOT
from swh.model.model import OriginVisit
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
from swh.vault.exc import NotFoundExc as VaultNotFoundExc
from swh.web import config
from swh.web.common import converters
from swh.web.common import query
from swh.web.common.exc import BadInputExc, NotFoundExc
-from swh.web.common.origin_visits import get_origin_visit
from swh.web.common.typing import (
OriginInfo,
OriginVisitInfo,
OriginMetadataInfo,
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)
def lookup_content_language(q):
"""Return language information from a specified content.
Args:
q: query string of the form <hash_algo:hash>
Yields:
language information (dict) list if the content is found.
"""
sha1 = _lookup_content_sha1(q)
if not sha1:
return None
lang = _first_element(list(idx_storage.content_language_get([sha1])))
if not lang:
return None
return converters.from_swh(lang, hashess={"id"})
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
lic = _first_element(idx_storage.content_fossology_license_get([sha1]))
if not lic:
return None
return converters.from_swh({"id": sha1, "facts": lic[sha1]}, 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']}/")
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
)
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, path_string):
"""Return directory information for entry with path path_string w.r.t.
root directory pointed by directory_sha1_git
Args:
- directory_sha1_git: sha1_git corresponding to the directory
to which we append paths to (hopefully) find the entry
- the relative path to the entry starting from the directory pointed by
directory_sha1_git
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_string.strip(os.path.sep).split(os.path.sep)
queried_dir = storage.directory_entry_get_by_path(
sha1_git_bin, list(map(lambda p: p.encode("utf-8"), paths))
)
if not queried_dir:
raise NotFoundExc(
("Directory entry with path %s from %s not found") % (path_string, sha1_git)
)
return converters.from_directory_entry(queried_dir)
def lookup_release(release_sha1_git):
"""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("Release with sha1_git %s not found." % release_sha1_git)
return converters.from_release(release)
def lookup_release_multiple(sha1_git_list):
"""Return information about the revisions identified with
their sha1_git identifiers.
Args:
sha1_git_list: A list of revision sha1_git identifiers
Returns:
Release 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) or []
return (converters.from_release(r) for r in releases)
def lookup_revision(rev_sha1_git):
"""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 = _first_element(storage.revision_get([sha1_git_bin]))
if not revision:
raise NotFoundExc("Revision with sha1_git %s not found." % rev_sha1_git)
return converters.from_revision(revision)
def lookup_revision_multiple(sha1_git_list):
"""Return information about the revisions identified with
their sha1_git identifiers.
Args:
sha1_git_list: A list of revision sha1_git identifiers
Returns:
Iterator of revisions 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)
revisions = storage.revision_get(sha1_bin_list) or []
return (converters.from_revision(r) for r in revisions)
def lookup_revision_message(rev_sha1_git):
"""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 = _first_element(storage.revision_get([sha1_git_bin]))
if not revision:
raise NotFoundExc("Revision with sha1_git %s not found." % rev_sha1_git)
if "message" not in revision:
raise NotFoundExc("No message for revision with sha1_git %s." % rev_sha1_git)
res = {"message": revision["message"]}
return res
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 = _first_element(storage.revision_get([rev_root_id_bin]))
return (
converters.from_revision(rev_root),
lookup_revision_with_context(rev_root, sha1_git, limit),
)
def lookup_revision_with_context(sha1_git_root, sha1_git, limit=100):
"""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 = _first_element(storage.revision_get([sha1_git_bin]))
if not revision:
raise NotFoundExc("Revision %s not found" % sha1_git)
if isinstance(sha1_git_root, str):
sha1_git_root_bin = _to_sha1_bin(sha1_git_root)
revision_root = _first_element(storage.revision_get([sha1_git_root_bin]))
if not revision_root:
raise NotFoundExc("Revision root %s not found" % sha1_git_root)
else:
sha1_git_root_bin = sha1_git_root["id"]
revision_log = storage.revision_log([sha1_git_root_bin], limit)
parents = {}
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(
"Revision %s is not an ancestor of %s" % (sha1_git, sha1_git_root)
)
revision["children"] = children[revision["id"]]
return converters.from_revision(revision)
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 = _first_element(storage.revision_get([sha1_git_bin]))
if not revision:
raise NotFoundExc("Revision %s not found" % sha1_git)
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 = next(storage.revision_get([entity["target"]]))
return {
"type": "rev",
"path": "." if not dir_path else dir_path,
"revision": sha1_git,
"content": converters.from_revision(revision),
}
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 not content_data:
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(
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
)
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):
"""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 = storage.snapshot_count_branches(snapshot_id_bin)
if "revision" not in snapshot_sizes:
snapshot_sizes["revision"] = 0
if "release" not in snapshot_sizes:
snapshot_sizes["release"] = 0
# adjust revision / release count for display if aliases are defined
if "alias" in snapshot_sizes:
aliases = lookup_snapshot(
snapshot_id, branches_count=snapshot_sizes["alias"], target_types=["alias"]
)
for alias in aliases["branches"].values():
try:
for target_type in ("revision", "release"):
snapshot = lookup_snapshot(
snapshot_id,
branches_from=alias["target"],
branches_count=1,
target_types=[target_type],
)
if snapshot and alias["target"] in snapshot["branches"]:
snapshot_sizes[target_type] += 1
except NotFoundExc:
# aliased revision or release is missing in the snapshot
pass
del snapshot_sizes["alias"]
# remove possible None key returned by snapshot_count_branches
# when null branches are present in the snapshot
snapshot_sizes.pop(None, None)
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_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.directory_missing(obj_ids))
elif obj_type == SNAPSHOT:
missing_hashes.append(storage.directory_missing(obj_ids))
missing = set(
map(lambda x: hashutil.hash_to_hex(x), itertools.chain(*missing_hashes))
)
return missing
diff --git a/swh/web/tests/browse/views/test_origin.py b/swh/web/tests/browse/views/test_origin.py
index f42e2833..26a21557 100644
--- a/swh/web/tests/browse/views/test_origin.py
+++ b/swh/web/tests/browse/views/test_origin.py
@@ -1,1244 +1,1248 @@
# Copyright (C) 2017-2020 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
import random
import re
import string
from django.utils.html import escape
from hypothesis import given
from swh.storage.utils import now
from swh.model.hashutil import hash_to_bytes
from swh.model.identifiers import CONTENT, DIRECTORY, RELEASE, REVISION, SNAPSHOT
from swh.model.model import (
Snapshot,
SnapshotBranch,
TargetType,
OriginVisit,
OriginVisitStatus,
)
from swh.web.browse.snapshot_context import process_snapshot_branches
from swh.web.common.exc import NotFoundExc
from swh.web.common.identifiers import gen_swhid
from swh.web.common.utils import (
reverse,
gen_path_info,
format_utc_iso_date,
parse_iso8601_date_to_utc,
)
from swh.web.tests.data import get_content, random_sha1
from swh.web.tests.django_asserts import assert_contains, assert_template_used
from swh.web.tests.strategies import (
origin,
origin_with_multiple_visits,
new_origin,
new_snapshot,
visit_dates,
revisions,
origin_with_releases,
release as existing_release,
unknown_revision,
)
@given(origin_with_multiple_visits())
def test_origin_visits_browse(client, archive_data, origin):
url = reverse("browse-origin-visits", query_params={"origin_url": origin["url"]})
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "browse/origin-visits.html")
url = reverse("browse-origin-visits", query_params={"origin_url": origin["url"]})
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "browse/origin-visits.html")
visits = archive_data.origin_visit_get(origin["url"])
for v in visits:
vdate = format_utc_iso_date(v["date"], "%Y-%m-%dT%H:%M:%SZ")
browse_dir_url = reverse(
"browse-origin-directory",
query_params={"origin_url": origin["url"], "timestamp": vdate},
)
assert_contains(resp, browse_dir_url)
_check_origin_link(resp, origin["url"])
@given(origin_with_multiple_visits())
def test_origin_content_view(client, archive_data, origin):
origin_visits = archive_data.origin_visit_get(origin["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],
}
tdata = _get_archive_data(-1)
_origin_content_view_test_helper(
client,
archive_data,
origin,
origin_visits[-1],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
)
_origin_content_view_test_helper(
client,
archive_data,
origin,
origin_visits[-1],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
timestamp=tdata["visit"]["date"],
)
_origin_content_view_test_helper(
client,
archive_data,
origin,
origin_visits[-1],
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,
origin_visits[0],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
visit_id=tdata["visit"]["visit"],
)
_origin_content_view_test_helper(
client,
archive_data,
origin,
origin_visits[0],
tdata["branches"],
tdata["releases"],
tdata["root_dir_sha1"],
tdata["content"],
snapshot_id=tdata["visit"]["snapshot"],
)
@given(origin())
def test_origin_root_directory_view(client, archive_data, origin):
origin_visits = archive_data.origin_visit_get(origin["url"])
visit = origin_visits[-1]
snapshot = archive_data.snapshot_get(visit["snapshot"])
head_rev_id = archive_data.snapshot_get_head(snapshot)
head_rev = archive_data.revision_get(head_rev_id)
root_dir_sha1 = head_rev["directory"]
dir_content = archive_data.directory_ls(root_dir_sha1)
branches, releases = process_snapshot_branches(snapshot)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
dir_content,
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
dir_content,
visit_id=visit["visit"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
dir_content,
timestamp=visit["date"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
dir_content,
snapshot_id=visit["snapshot"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
dir_content,
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
dir_content,
visit_id=visit["visit"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
dir_content,
timestamp=visit["date"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
dir_content,
snapshot_id=visit["snapshot"],
)
@given(origin())
def test_origin_sub_directory_view(client, archive_data, origin):
origin_visits = archive_data.origin_visit_get(origin["url"])
visit = origin_visits[-1]
snapshot = archive_data.snapshot_get(visit["snapshot"])
head_rev_id = archive_data.snapshot_get_head(snapshot)
head_rev = archive_data.revision_get(head_rev_id)
root_dir_sha1 = head_rev["directory"]
subdirs = [
e for e in archive_data.directory_ls(root_dir_sha1) if e["type"] == "dir"
]
branches, releases = process_snapshot_branches(snapshot)
if len(subdirs) == 0:
return
subdir = random.choice(subdirs)
subdir_content = archive_data.directory_ls(subdir["target"])
subdir_path = subdir["name"]
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
subdir_content,
path=subdir_path,
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
subdir_content,
path=subdir_path,
visit_id=visit["visit"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
subdir_content,
path=subdir_path,
timestamp=visit["date"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
subdir_content,
path=subdir_path,
snapshot_id=visit["snapshot"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
subdir_content,
path=subdir_path,
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
subdir_content,
path=subdir_path,
visit_id=visit["visit"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
subdir_content,
path=subdir_path,
timestamp=visit["date"],
)
_origin_directory_view_test_helper(
client,
archive_data,
origin,
visit,
branches,
releases,
root_dir_sha1,
subdir_content,
path=subdir_path,
snapshot_id=visit["snapshot"],
)
@given(origin())
def test_origin_branches(client, archive_data, origin):
origin_visits = archive_data.origin_visit_get(origin["url"])
visit = origin_visits[-1]
snapshot = archive_data.snapshot_get(visit["snapshot"])
snapshot_content = process_snapshot_branches(snapshot)
_origin_branches_test_helper(client, origin, snapshot_content)
_origin_branches_test_helper(
client, origin, snapshot_content, snapshot_id=visit["snapshot"]
)
@given(origin())
def test_origin_releases(client, archive_data, origin):
origin_visits = archive_data.origin_visit_get(origin["url"])
visit = origin_visits[-1]
snapshot = archive_data.snapshot_get(visit["snapshot"])
snapshot_content = process_snapshot_branches(snapshot)
_origin_releases_test_helper(client, origin, snapshot_content)
_origin_releases_test_helper(
client, origin, snapshot_content, snapshot_id=visit["snapshot"]
)
@given(
new_origin(),
new_snapshot(min_size=4, max_size=4),
visit_dates(),
revisions(min_size=3, max_size=3),
)
def test_origin_snapshot_null_branch(
client, archive_data, new_origin, new_snapshot, visit_dates, revisions
):
snp_dict = new_snapshot.to_dict()
archive_data.origin_add([new_origin])
for i, branch in enumerate(snp_dict["branches"].keys()):
if i == 0:
snp_dict["branches"][branch] = None
else:
snp_dict["branches"][branch] = {
"target_type": "revision",
"target": hash_to_bytes(revisions[i - 1]),
}
archive_data.snapshot_add([Snapshot.from_dict(snp_dict)])
visit = archive_data.origin_visit_add(
[OriginVisit(origin=new_origin.url, date=visit_dates[0], type="git",)]
)[0]
visit_status = OriginVisitStatus(
origin=new_origin.url,
visit=visit.visit,
date=now(),
status="partial",
snapshot=snp_dict["id"],
)
archive_data.origin_visit_status_add([visit_status])
url = reverse(
"browse-origin-directory", query_params={"origin_url": new_origin.url}
)
rv = client.get(url)
assert rv.status_code == 200
@given(
new_origin(),
new_snapshot(min_size=4, max_size=4),
visit_dates(),
revisions(min_size=4, max_size=4),
)
def test_origin_snapshot_invalid_branch(
client, archive_data, new_origin, new_snapshot, visit_dates, revisions
):
snp_dict = new_snapshot.to_dict()
archive_data.origin_add([new_origin])
for i, branch in enumerate(snp_dict["branches"].keys()):
snp_dict["branches"][branch] = {
"target_type": "revision",
"target": hash_to_bytes(revisions[i]),
}
archive_data.snapshot_add([Snapshot.from_dict(snp_dict)])
visit = archive_data.origin_visit_add(
[OriginVisit(origin=new_origin.url, date=visit_dates[0], type="git",)]
)[0]
visit_status = OriginVisitStatus(
origin=new_origin.url,
visit=visit.visit,
date=now(),
status="full",
snapshot=snp_dict["id"],
)
archive_data.origin_visit_status_add([visit_status])
url = reverse(
"browse-origin-directory",
query_params={"origin_url": new_origin.url, "branch": "invalid_branch"},
)
rv = client.get(url)
assert rv.status_code == 404
@given(new_origin())
def test_browse_visits_origin_not_found(client, new_origin):
url = reverse("browse-origin-visits", query_params={"origin_url": new_origin.url})
resp = client.get(url)
assert resp.status_code == 404
assert_template_used(resp, "error.html")
assert_contains(
resp, f"Origin with url {new_origin.url} not found", status_code=404
)
@given(origin())
def test_browse_origin_directory_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_service = mocker.patch("swh.web.common.origin_visits.service")
+ mock_service.lookup_origin_visit_latest.return_value = None
url = reverse("browse-origin-directory", query_params={"origin_url": origin["url"]})
resp = client.get(url)
assert resp.status_code == 404
assert_template_used(resp, "error.html")
- assert_contains(resp, "No visit", status_code=404)
- assert mock_get_origin_visits.called
+ assert_contains(resp, "No valid visit", status_code=404)
+ assert not mock_get_origin_visits.called
@given(origin())
def test_browse_origin_directory_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-origin-directory",
query_params={"origin_url": origin["url"], "visit_id": 2},
)
resp = client.get(url)
assert resp.status_code == 404
assert_template_used(resp, "error.html")
assert re.search("Visit.*not found", resp.content.decode("utf-8"))
assert mock_get_origin_visits.called
@given(origin())
def test_browse_origin_directory_not_found(client, origin):
url = reverse(
"browse-origin-directory",
query_params={"origin_url": origin["url"], "path": "/invalid/dir/path/"},
)
resp = client.get(url)
assert resp.status_code == 404
assert_template_used(resp, "error.html")
assert re.search("Directory.*not found", resp.content.decode("utf-8"))
@given(origin())
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_service = mocker.patch("swh.web.common.origin_visits.service")
+ mock_service.lookup_origin_visit_latest.return_value = None
url = reverse(
"browse-origin-content",
query_params={"origin_url": origin["url"], "path": "foo"},
)
resp = client.get(url)
assert resp.status_code == 404
assert_template_used(resp, "error.html")
- assert_contains(resp, "No visit", status_code=404)
- assert mock_get_origin_visits.called
+ assert_contains(resp, "No valid visit", status_code=404)
+ assert not mock_get_origin_visits.called
@given(origin())
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-origin-content",
query_params={"origin_url": origin["url"], "path": "foo", "visit_id": 2},
)
resp = client.get(url)
assert resp.status_code == 404
assert_template_used(resp, "error.html")
assert re.search("Visit.*not found", resp.content.decode("utf-8"))
assert mock_get_origin_visits.called
@given(origin())
def test_browse_origin_content_directory_empty_snapshot(client, mocker, origin):
mock_snapshot_service = mocker.patch("swh.web.browse.snapshot_context.service")
mock_get_origin_visit_snapshot = mocker.patch(
"swh.web.browse.snapshot_context.get_origin_visit_snapshot"
)
mock_get_origin_visit_snapshot.return_value = ([], [])
mock_snapshot_service.lookup_origin.return_value = origin
mock_snapshot_service.lookup_snapshot_sizes.return_value = {
"revision": 0,
"release": 0,
}
for browse_context in ("content", "directory"):
url = reverse(
f"browse-origin-{browse_context}",
query_params={"origin_url": origin["url"], "path": "baz"},
)
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, f"browse/{browse_context}.html")
assert re.search("snapshot.*is empty", resp.content.decode("utf-8"))
assert mock_get_origin_visit_snapshot.called
assert mock_snapshot_service.lookup_origin.called
assert mock_snapshot_service.lookup_snapshot_sizes.called
@given(origin())
def test_browse_origin_content_not_found(client, origin):
url = reverse(
"browse-origin-content",
query_params={"origin_url": origin["url"], "path": "/invalid/file/path"},
)
resp = client.get(url)
assert resp.status_code == 404
assert_template_used(resp, "error.html")
assert re.search("Directory entry.*not found", resp.content.decode("utf-8"))
@given(origin())
def test_browse_directory_snapshot_not_found(client, mocker, origin):
mock_get_snapshot_context = mocker.patch(
"swh.web.browse.snapshot_context.get_snapshot_context"
)
mock_get_snapshot_context.side_effect = NotFoundExc("Snapshot not found")
url = reverse("browse-origin-directory", query_params={"origin_url": origin["url"]})
resp = client.get(url)
assert resp.status_code == 404
assert_template_used(resp, "error.html")
assert_contains(resp, "Snapshot not found", status_code=404)
assert mock_get_snapshot_context.called
@given(origin())
def test_origin_empty_snapshot(client, mocker, origin):
mock_service = mocker.patch("swh.web.browse.snapshot_context.service")
mock_get_origin_visit_snapshot = mocker.patch(
"swh.web.browse.snapshot_context.get_origin_visit_snapshot"
)
mock_get_origin_visit_snapshot.return_value = ([], [])
mock_service.lookup_snapshot_sizes.return_value = {
"revision": 0,
"release": 0,
}
mock_service.lookup_origin.return_value = origin
url = reverse("browse-origin-directory", query_params={"origin_url": origin["url"]})
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "browse/directory.html")
resp_content = resp.content.decode("utf-8")
assert re.search("snapshot.*is empty", resp_content)
assert not re.search("swh-tr-link", resp_content)
assert mock_get_origin_visit_snapshot.called
assert mock_service.lookup_snapshot_sizes.called
@given(new_origin())
def test_origin_empty_snapshot_null_revision(client, archive_data, new_origin):
snapshot = Snapshot(
branches={
b"HEAD": SnapshotBranch(
target="refs/head/master".encode(), target_type=TargetType.ALIAS,
),
b"refs/head/master": None,
}
)
archive_data.origin_add([new_origin])
archive_data.snapshot_add([snapshot])
visit = archive_data.origin_visit_add(
[OriginVisit(origin=new_origin.url, date=now(), type="git",)]
)[0]
visit_status = OriginVisitStatus(
origin=new_origin.url,
visit=visit.visit,
date=now(),
status="partial",
snapshot=snapshot.id,
)
archive_data.origin_visit_status_add([visit_status])
url = reverse(
"browse-origin-directory", query_params={"origin_url": new_origin.url},
)
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "browse/directory.html")
resp_content = resp.content.decode("utf-8")
assert re.search("snapshot.*is empty", resp_content)
assert not re.search("swh-tr-link", resp_content)
@given(origin_with_releases())
def test_origin_release_browse(client, archive_data, origin):
snapshot = archive_data.snapshot_get_latest(origin["url"])
release = [
b for b in snapshot["branches"].values() if b["target_type"] == "release"
][-1]
release_data = archive_data.release_get(release["target"])
revision_data = archive_data.revision_get(release_data["target"])
url = reverse(
"browse-origin-directory",
query_params={"origin_url": origin["url"], "release": release_data["name"]},
)
resp = client.get(url)
assert resp.status_code == 200
assert_contains(resp, release_data["name"])
assert_contains(resp, release["target"])
swhid_context = {
"origin": origin["url"],
"visit": gen_swhid(SNAPSHOT, snapshot["id"]),
"anchor": gen_swhid(RELEASE, release_data["id"]),
"path": "/",
}
swh_dir_id = gen_swhid(
DIRECTORY, revision_data["directory"], metadata=swhid_context
)
swh_dir_id_url = reverse("browse-swhid", url_args={"swhid": swh_dir_id})
assert_contains(resp, swh_dir_id)
assert_contains(resp, swh_dir_id_url)
@given(origin_with_releases())
def test_origin_release_browse_not_found(client, origin):
invalid_release_name = "swh-foo-bar"
url = reverse(
"browse-origin-directory",
query_params={"origin_url": origin["url"], "release": invalid_release_name},
)
resp = client.get(url)
assert resp.status_code == 404
assert re.search(
f"Release {invalid_release_name}.*not found", resp.content.decode("utf-8")
)
@given(new_origin(), unknown_revision())
def test_origin_browse_directory_branch_with_non_resolvable_revision(
client, archive_data, new_origin, unknown_revision
):
branch_name = "master"
snapshot = Snapshot(
branches={
branch_name.encode(): SnapshotBranch(
target=hash_to_bytes(unknown_revision), target_type=TargetType.REVISION,
)
}
)
archive_data.origin_add([new_origin])
archive_data.snapshot_add([snapshot])
visit = archive_data.origin_visit_add(
[OriginVisit(origin=new_origin.url, date=now(), type="git",)]
)[0]
visit_status = OriginVisitStatus(
origin=new_origin.url,
visit=visit.visit,
date=now(),
status="partial",
snapshot=snapshot.id,
)
archive_data.origin_visit_status_add([visit_status])
url = reverse(
"browse-origin-directory",
query_params={"origin_url": new_origin.url, "branch": branch_name},
)
resp = client.get(url)
assert resp.status_code == 200
assert_contains(
resp, f"Revision {unknown_revision } could not be found in the archive."
)
@given(origin())
def test_origin_content_no_path(client, origin):
url = reverse("browse-origin-content", query_params={"origin_url": origin["url"]})
resp = client.get(url)
assert resp.status_code == 400
assert_contains(
resp, "The path of a content must be given as query parameter.", status_code=400
)
def test_origin_views_no_url_query_parameter(client):
for browse_context in (
"content",
"directory",
"log",
"branches",
"releases",
"visits",
):
url = reverse(f"browse-origin-{browse_context}")
resp = client.get(url)
assert resp.status_code == 400
assert_contains(
resp, "An origin URL must be provided as query parameter.", status_code=400
)
def _origin_content_view_test_helper(
client,
archive_data,
origin_info,
origin_visit,
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-origin-content", query_params=query_params)
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "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-origin-directory", 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 ({len(origin_branches)})")
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 ({len(origin_releases)})")
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-origin-content", query_params=query_params)
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "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(SNAPSHOT, snapshot["id"]),
"anchor": gen_swhid(REVISION, head_rev_id),
"path": f"/{content_path}",
}
swh_cnt_id = gen_swhid(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"])
def _origin_directory_view_test_helper(
client,
archive_data,
origin_info,
origin_visit,
origin_branches,
origin_releases,
root_directory_sha1,
directory_entries,
visit_id=None,
timestamp=None,
snapshot_id=None,
path=None,
):
dirs = [e for e in directory_entries if e["type"] in ("dir", "rev")]
files = [e for e in directory_entries if e["type"] == "file"]
if not visit_id and not snapshot_id:
visit_id = origin_visit["visit"]
query_params = {"origin_url": origin_info["url"]}
if timestamp:
query_params["timestamp"] = timestamp
elif visit_id:
query_params["visit_id"] = visit_id
else:
query_params["snapshot"] = snapshot_id
if path:
query_params["path"] = path
url = reverse("browse-origin-directory", query_params=query_params)
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "browse/directory.html")
assert resp.status_code == 200
assert_template_used(resp, "browse/directory.html")
assert_contains(resp, '<td class="swh-directory">', count=len(dirs))
assert_contains(resp, '<td class="swh-content">', count=len(files))
if timestamp:
query_params["timestamp"] = format_utc_iso_date(
parse_iso8601_date_to_utc(timestamp).isoformat(), "%Y-%m-%dT%H:%M:%SZ"
)
for d in dirs:
if d["type"] == "rev":
dir_url = reverse("browse-revision", url_args={"sha1_git": d["target"]})
else:
dir_path = d["name"]
if path:
dir_path = "%s/%s" % (path, d["name"])
query_params["path"] = dir_path
dir_url = reverse("browse-origin-directory", query_params=query_params,)
assert_contains(resp, dir_url)
for f in files:
file_path = f["name"]
if path:
file_path = "%s/%s" % (path, f["name"])
query_params["path"] = file_path
file_url = reverse("browse-origin-content", query_params=query_params)
assert_contains(resp, file_url)
if "path" in query_params:
del query_params["path"]
root_dir_branch_url = reverse("browse-origin-directory", query_params=query_params)
nb_bc_paths = 1
if path:
nb_bc_paths = len(path.split("/")) + 1
assert_contains(resp, '<li class="swh-path">', count=nb_bc_paths)
assert_contains(
resp, '<a href="%s">%s</a>' % (root_dir_branch_url, root_directory_sha1[:7])
)
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 ({len(origin_branches)})")
origin_releases_url = reverse("browse-origin-releases", query_params=query_params)
nb_releases = len(origin_releases)
if nb_releases > 0:
assert_contains(resp, f'href="{escape(origin_releases_url)}"')
assert_contains(resp, f"Releases ({nb_releases})")
if path:
query_params["path"] = path
assert_contains(resp, '<li class="swh-branch">', count=len(origin_branches))
for branch in origin_branches:
query_params["branch"] = branch["name"]
root_dir_branch_url = reverse(
"browse-origin-directory", query_params=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:
query_params["release"] = release["name"]
root_dir_release_url = reverse(
"browse-origin-directory", query_params=query_params
)
assert_contains(resp, 'href="%s"' % root_dir_release_url)
assert_contains(resp, "vault-cook-directory")
assert_contains(resp, "vault-cook-revision")
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(SNAPSHOT, snapshot["id"]),
"anchor": gen_swhid(REVISION, head_rev_id),
"path": f"/{path}" if path else "/",
}
swh_dir_id = gen_swhid(
DIRECTORY, directory_entries[0]["dir_id"], metadata=swhid_context
)
swh_dir_id_url = reverse("browse-swhid", url_args={"swhid": swh_dir_id})
assert_contains(resp, swh_dir_id)
assert_contains(resp, swh_dir_id_url)
assert_contains(resp, "swh-take-new-snapshot")
_check_origin_link(resp, origin_info["url"])
def _origin_branches_test_helper(
client, origin_info, origin_snapshot, snapshot_id=None
):
query_params = {"origin_url": origin_info["url"], "snapshot": snapshot_id}
url = reverse("browse-origin-branches", query_params=query_params)
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "browse/branches.html")
origin_branches = origin_snapshot[0]
origin_releases = origin_snapshot[1]
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 ({len(origin_branches)})")
origin_releases_url = reverse("browse-origin-releases", query_params=query_params)
nb_releases = len(origin_releases)
if nb_releases > 0:
assert_contains(resp, f'href="{escape(origin_releases_url)}">')
assert_contains(resp, f"Releases ({nb_releases})")
assert_contains(resp, '<tr class="swh-branch-entry', count=len(origin_branches))
for branch in origin_branches:
browse_branch_url = reverse(
"browse-origin-directory",
query_params={"branch": branch["name"], **query_params},
)
assert_contains(resp, '<a href="%s">' % escape(browse_branch_url))
browse_revision_url = reverse(
"browse-revision",
url_args={"sha1_git": branch["revision"]},
query_params=query_params,
)
assert_contains(resp, '<a href="%s">' % escape(browse_revision_url))
_check_origin_link(resp, origin_info["url"])
def _origin_releases_test_helper(
client, origin_info, origin_snapshot, snapshot_id=None
):
query_params = {"origin_url": origin_info["url"], "snapshot": snapshot_id}
url = reverse("browse-origin-releases", query_params=query_params)
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "browse/releases.html")
origin_branches = origin_snapshot[0]
origin_releases = origin_snapshot[1]
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 ({len(origin_branches)})")
origin_releases_url = reverse("browse-origin-releases", query_params=query_params)
nb_releases = len(origin_releases)
if nb_releases > 0:
assert_contains(resp, f'href="{escape(origin_releases_url)}"')
assert_contains(resp, f"Releases ({nb_releases})")
assert_contains(resp, '<tr class="swh-release-entry', count=nb_releases)
for release in origin_releases:
browse_release_url = reverse(
"browse-release",
url_args={"sha1_git": release["id"]},
query_params=query_params,
)
browse_revision_url = reverse(
"browse-revision",
url_args={"sha1_git": release["target"]},
query_params=query_params,
)
assert_contains(resp, '<a href="%s">' % escape(browse_release_url))
assert_contains(resp, '<a href="%s">' % escape(browse_revision_url))
_check_origin_link(resp, origin_info["url"])
@given(
new_origin(), visit_dates(), revisions(min_size=10, max_size=10), existing_release()
)
def test_origin_branches_pagination_with_alias(
client, archive_data, mocker, new_origin, visit_dates, revisions, existing_release
):
"""
When a snapshot contains a branch or a release alias, pagination links
in the branches / releases view should be displayed.
"""
mocker.patch("swh.web.browse.snapshot_context.PER_PAGE", len(revisions) / 2)
snp_dict = {"branches": {}, "id": hash_to_bytes(random_sha1())}
for i in range(len(revisions)):
branch = "".join(random.choices(string.ascii_lowercase, k=8))
snp_dict["branches"][branch.encode()] = {
"target_type": "revision",
"target": hash_to_bytes(revisions[i]),
}
release = "".join(random.choices(string.ascii_lowercase, k=8))
snp_dict["branches"][b"RELEASE_ALIAS"] = {
"target_type": "alias",
"target": release.encode(),
}
snp_dict["branches"][release.encode()] = {
"target_type": "release",
"target": hash_to_bytes(existing_release),
}
archive_data.origin_add([new_origin])
archive_data.snapshot_add([Snapshot.from_dict(snp_dict)])
visit = archive_data.origin_visit_add(
[OriginVisit(origin=new_origin.url, date=visit_dates[0], type="git",)]
)[0]
visit_status = OriginVisitStatus(
origin=new_origin.url,
visit=visit.visit,
date=now(),
status="full",
snapshot=snp_dict["id"],
)
archive_data.origin_visit_status_add([visit_status])
url = reverse("browse-origin-branches", query_params={"origin_url": new_origin.url})
resp = client.get(url)
assert resp.status_code == 200
assert_template_used(resp, "browse/branches.html")
assert_contains(resp, '<ul class="pagination')
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}"')
diff --git a/swh/web/tests/common/test_origin_visits.py b/swh/web/tests/common/test_origin_visits.py
index 3b4569f5..3033db65 100644
--- a/swh/web/tests/common/test_origin_visits.py
+++ b/swh/web/tests/common/test_origin_visits.py
@@ -1,235 +1,258 @@
# Copyright (C) 2018-2019 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 datetime import timedelta
from hypothesis import given
import pytest
from swh.model.hashutil import hash_to_hex
from swh.model.model import OriginVisit, OriginVisitStatus
from swh.storage.utils import now
from swh.web.common.exc import NotFoundExc
from swh.web.common.origin_visits import get_origin_visits, get_origin_visit
from swh.web.common.typing import OriginInfo
-from swh.web.tests.strategies import new_origin, new_snapshots
+from swh.web.tests.strategies import (
+ new_origin,
+ new_snapshots,
+ origin_with_multiple_visits,
+)
@given(new_snapshots(3))
def test_get_origin_visits(mocker, snapshots):
mock_service = mocker.patch("swh.web.common.service")
mock_service.MAX_LIMIT = 2
def _lookup_origin_visits(*args, **kwargs):
if kwargs["last_visit"] is None:
return [
{
"visit": 1,
"date": "2017-05-06T00:59:10+00:00",
"status": "full",
"snapshot": hash_to_hex(snapshots[0].id),
"type": "git",
},
{
"visit": 2,
"date": "2017-08-06T00:59:10+00:00",
"status": "full",
"snapshot": hash_to_hex(snapshots[1].id),
"type": "git",
},
]
else:
return [
{
"visit": 3,
"date": "2017-09-06T00:59:10+00:00",
"status": "full",
"snapshot": hash_to_hex(snapshots[2].id),
"type": "git",
}
]
mock_service.lookup_origin_visits.side_effect = _lookup_origin_visits
origin_info = {
"url": "https://github.com/foo/bar",
}
origin_visits = get_origin_visits(origin_info)
assert len(origin_visits) == 3
@given(new_snapshots(5))
def test_get_origin_visit(mocker, snapshots):
mock_origin_visits = mocker.patch("swh.web.common.origin_visits.get_origin_visits")
origin_info = {
"url": "https://github.com/foo/bar",
}
visits = [
{
"status": "full",
"date": "2015-07-09T21:09:24+00:00",
"visit": 1,
"origin": "https://github.com/foo/bar",
"type": "git",
"snapshot": hash_to_hex(snapshots[0].id),
},
{
"status": "full",
"date": "2016-02-23T18:05:23.312045+00:00",
"visit": 2,
"origin": "https://github.com/foo/bar",
"type": "git",
"snapshot": hash_to_hex(snapshots[1].id),
},
{
"status": "full",
"date": "2016-03-28T01:35:06.554111+00:00",
"visit": 3,
"origin": "https://github.com/foo/bar",
"type": "git",
"snapshot": hash_to_hex(snapshots[2].id),
},
{
"status": "full",
"date": "2016-06-18T01:22:24.808485+00:00",
"visit": 4,
"origin": "https://github.com/foo/bar",
"type": "git",
"snapshot": hash_to_hex(snapshots[3].id),
},
{
"status": "full",
"date": "2016-08-14T12:10:00.536702+00:00",
"visit": 5,
"origin": "https://github.com/foo/bar",
"type": "git",
"snapshot": hash_to_hex(snapshots[4].id),
},
]
mock_origin_visits.return_value = visits
visit_id = 12
with pytest.raises(NotFoundExc) as e:
visit = get_origin_visit(origin_info, visit_id=visit_id)
assert e.match("Visit with id %s" % visit_id)
assert e.match("url %s" % origin_info["url"])
visit = get_origin_visit(origin_info, visit_id=2)
assert visit == visits[1]
visit = get_origin_visit(origin_info, visit_ts="2016-02-23T18:05:23.312045+00:00")
assert visit == visits[1]
visit = get_origin_visit(origin_info, visit_ts="2016-02-20")
assert visit == visits[1]
visit = get_origin_visit(origin_info, visit_ts="2016-06-18T01:22")
assert visit == visits[3]
visit = get_origin_visit(origin_info, visit_ts="2016-06-18 01:22")
assert visit == visits[3]
visit = get_origin_visit(origin_info, visit_ts="2014-01-01")
assert visit == visits[0]
visit = get_origin_visit(origin_info, visit_ts="2018-01-01")
assert visit == visits[-1]
@given(new_origin(), new_snapshots(6))
def test_get_origin_visit_return_first_valid_full_visit(
archive_data, new_origin, new_snapshots
):
visits = []
archive_data.origin_add([new_origin])
# create 6 visits, the first three have full status while the
# last three have partial status and set a null snapshot for
# the last four visits
for i, snp in enumerate(new_snapshots):
visit_date = now() + timedelta(days=i * 10)
visit = archive_data.origin_visit_add(
[OriginVisit(origin=new_origin.url, date=visit_date, type="git",)]
)[0]
archive_data.snapshot_add([new_snapshots[i]])
visit_status = OriginVisitStatus(
origin=new_origin.url,
visit=visit.visit,
date=visit_date + timedelta(minutes=5),
status="full" if i < 3 else "partial",
snapshot=new_snapshots[i].id if i < 2 else None,
)
if i < 2:
archive_data.origin_visit_status_add([visit_status])
visits.append(visit.visit)
# should return the second visit
expected_visit = archive_data.origin_visit_get_by(new_origin.url, visits[1])
assert get_origin_visit((OriginInfo(url=new_origin.url))) == expected_visit
@given(new_origin(), new_snapshots(6))
def test_get_origin_visit_non_resolvable_snapshots(
archive_data, new_origin, new_snapshots
):
visits = []
archive_data.origin_add([new_origin])
# create 6 full visits, the first three have resolvable snapshots
# while the last three have non resolvable snapshots
for i, snp in enumerate(new_snapshots):
visit_date = now() + timedelta(days=i * 10)
visit = archive_data.origin_visit_add(
[OriginVisit(origin=new_origin.url, date=visit_date, type="git",)]
)[0]
archive_data.snapshot_add([new_snapshots[i]])
visit_status = OriginVisitStatus(
origin=new_origin.url,
visit=visit.visit,
date=visit_date + timedelta(minutes=5),
status="full",
snapshot=new_snapshots[i].id,
)
if i < 3:
archive_data.origin_visit_status_add([visit_status])
visits.append(visit.visit)
# should return the third visit
expected_visit = archive_data.origin_visit_get_by(new_origin.url, visits[2])
assert get_origin_visit((OriginInfo(url=new_origin.url))) == expected_visit
@given(new_origin(), new_snapshots(6))
def test_get_origin_visit_return_first_valid_partial_visit(
archive_data, new_origin, new_snapshots
):
visits = []
archive_data.origin_add([new_origin])
# create 6 visits, the first three have full status but null snapshot
# while the last three have partial status with valid snapshot
for i, snp in enumerate(new_snapshots):
visit_date = now() + timedelta(days=i * 10)
visit = archive_data.origin_visit_add(
[OriginVisit(origin=new_origin.url, date=visit_date, type="git",)]
)[0]
archive_data.snapshot_add([new_snapshots[i]])
visit_status = OriginVisitStatus(
origin=new_origin.url,
visit=visit.visit,
date=visit_date + timedelta(minutes=5),
status="full" if i < 3 else "partial",
snapshot=new_snapshots[i].id if i > 2 else None,
)
if i > 2:
archive_data.origin_visit_status_add([visit_status])
visits.append(visit.visit)
# should return the last visit
expected_visit = archive_data.origin_visit_get_by(new_origin.url, visits[-1])
assert get_origin_visit((OriginInfo(url=new_origin.url))) == expected_visit
+
+
+@given(origin_with_multiple_visits())
+def test_get_origin_visit_latest_snapshot(mocker, origin):
+ origin_visits = get_origin_visits(origin)
+ first_visit = origin_visits[0]
+ latest_visit = origin_visits[-1]
+ mock_get_origin_visits = mocker.patch(
+ "swh.web.common.origin_visits.get_origin_visits"
+ )
+ mock_get_origin_visits.return_value = origin_visits
+
+ visit = get_origin_visit(origin, snapshot_id=latest_visit["snapshot"])
+ assert visit == latest_visit
+ assert not mock_get_origin_visits.called
+
+ visit = get_origin_visit(origin, snapshot_id=first_visit["snapshot"])
+ assert visit == first_visit
+ assert mock_get_origin_visits.called

File Metadata

Mime Type
text/x-diff
Expires
Fri, Jul 4, 1:02 PM (1 w, 2 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3235876

Event Timeline

About · Developer information · Legal