diff --git a/swh/web/assets/src/bundles/origin/visits-calendar.js b/swh/web/assets/src/bundles/origin/visits-calendar.js index 0be1ee22..92dd919e 100644 --- a/swh/web/assets/src/bundles/origin/visits-calendar.js +++ b/swh/web/assets/src/bundles/origin/visits-calendar.js @@ -1,140 +1,140 @@ /** * 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 Calendar from 'js-year-calendar'; import 'js-year-calendar/dist/js-year-calendar.css'; let minSize = 15; let maxSize = 28; let currentPopover = null; let visitsByDate = {}; function closePopover() { if (currentPopover) { $(currentPopover).popover('hide'); currentPopover = null; } } // function to update the visits calendar view based on the selected year export function updateCalendar(year, filteredVisits, yearClickedCallback) { visitsByDate = {}; let maxNbVisitsByDate = 0; let minDate, maxDate; for (let i = 0; i < filteredVisits.length; ++i) { filteredVisits[i]['startDate'] = filteredVisits[i]['date']; filteredVisits[i]['endDate'] = filteredVisits[i]['startDate']; let date = new Date(filteredVisits[i]['date']); date.setHours(0, 0, 0, 0); let dateStr = date.toDateString(); if (!visitsByDate.hasOwnProperty(dateStr)) { visitsByDate[dateStr] = [filteredVisits[i]]; } else { visitsByDate[dateStr].push(filteredVisits[i]); } maxNbVisitsByDate = Math.max(maxNbVisitsByDate, visitsByDate[dateStr].length); if (i === 0) { minDate = maxDate = date; } else { if (date.getTime() < minDate.getTime()) { minDate = date; } if (date.getTime() > maxDate.getTime()) { maxDate = date; } } } closePopover(); new Calendar('#swh-visits-calendar', { dataSource: filteredVisits, style: 'custom', minDate: minDate, maxDate: maxDate, startYear: year, renderEnd: e => yearClickedCallback(e.currentYear), customDataSourceRenderer: (element, date, events) => { let dateStr = date.toDateString(); let nbVisits = visitsByDate[dateStr].length; let t = nbVisits / maxNbVisitsByDate; if (maxNbVisitsByDate === 1) { t = 0; } let size = minSize + t * (maxSize - minSize); let offsetX = (maxSize - size) / 2 - parseInt($(element).css('padding-left')); let offsetY = (maxSize - size) / 2 - parseInt($(element).css('padding-top')) + 1; let cellWrapper = $('
'); cellWrapper.css('position', 'relative'); let dayNumber = $('
'); dayNumber.text($(element).text()); let circle = $('
'); let r = 0; let g = 0; for (let i = 0; i < nbVisits; ++i) { let visit = visitsByDate[dateStr][i]; if (visit.status === 'full') { g += 255; } else if (visit.status === 'partial') { r += 255; g += 255; } else { r += 255; } } r /= nbVisits; g /= nbVisits; circle.css('background-color', 'rgba(' + r + ', ' + g + ', 0, 0.3)'); circle.css('width', size + 'px'); circle.css('height', size + 'px'); circle.css('border-radius', size + 'px'); circle.css('position', 'absolute'); circle.css('top', offsetY + 'px'); circle.css('left', offsetX + 'px'); cellWrapper.append(dayNumber); cellWrapper.append(circle); $(element)[0].innerHTML = $(cellWrapper)[0].outerHTML; }, mouseOnDay: e => { if (currentPopover !== e.element) { closePopover(); } let dateStr = e.date.toDateString(); if (visitsByDate.hasOwnProperty(dateStr)) { let visits = visitsByDate[dateStr]; let content = '
' + e.date.toDateString() + '
'; content += ''; $(e.element).popover({ trigger: 'manual', container: 'body', html: true, content: content }); $(e.element).popover('show'); currentPopover = e.element; } } }); $('#swh-visits-timeline').mouseenter(() => { closePopover(); }); $('#swh-visits-list').mouseenter(() => { closePopover(); }); $('#swh-visits-calendar.calendar table td').css('width', maxSize + 'px'); $('#swh-visits-calendar.calendar table td').css('height', maxSize + 'px'); $('#swh-visits-calendar.calendar table td').css('padding', '0px'); } diff --git a/swh/web/assets/src/bundles/origin/visits-reporting.js b/swh/web/assets/src/bundles/origin/visits-reporting.js index 75c3016a..4c803e02 100644 --- a/swh/web/assets/src/bundles/origin/visits-reporting.js +++ b/swh/web/assets/src/bundles/origin/visits-reporting.js @@ -1,138 +1,138 @@ /** * Copyright (C) 2018 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 {createVisitsHistogram} from './visits-histogram'; import {updateCalendar} from './visits-calendar'; import './visits-reporting.css'; // will hold all visits let allVisits; // will hold filtered visits to display let filteredVisits; // will hold currently displayed year let currentYear; // function to gather full visits function filterFullVisits(differentSnapshots) { let filteredVisits = []; for (let i = 0; i < allVisits.length; ++i) { if (allVisits[i].status !== 'full') continue; if (!differentSnapshots) { filteredVisits.push(allVisits[i]); } else if (filteredVisits.length === 0) { filteredVisits.push(allVisits[i]); } else { let lastVisit = filteredVisits[filteredVisits.length - 1]; if (allVisits[i].snapshot !== lastVisit.snapshot) { filteredVisits.push(allVisits[i]); } } } return filteredVisits; } // function to update the visits list view based on the selected year function updateVisitsList(year) { $('#swh-visits-list').children().remove(); let visitsByYear = []; for (let i = 0; i < filteredVisits.length; ++i) { if (filteredVisits[i].date.getUTCFullYear() === year) { visitsByYear.push(filteredVisits[i]); } } let visitsCpt = 0; let nbVisitsByRow = 4; let visitsListHtml = '
'; for (let i = 0; i < visitsByYear.length; ++i) { if (visitsCpt > 0 && visitsCpt % nbVisitsByRow === 0) { visitsListHtml += '
'; } visitsListHtml += '
'; visitsListHtml += '' + visitsByYear[i].fmt_date + ''; + ' visit" href="' + visitsByYear[i].url + '">' + visitsByYear[i].formatted_date + ''; visitsListHtml += '
'; ++visitsCpt; } visitsListHtml += '
'; $('#swh-visits-list').append($(visitsListHtml)); } function yearChangedCalendar(year) { currentYear = year; updateVisitsList(year); createVisitsHistogram('.d3-wrapper', filteredVisits, currentYear, yearClickedTimeline); } // callback when the user selects a year through the visits histogram function yearClickedTimeline(year) { currentYear = year; updateCalendar(year, filteredVisits, yearChangedCalendar); updateVisitsList(year); } // function to update the visits views (histogram, calendar, list) function updateDisplayedVisits() { if (filteredVisits.length === 0) { return; } if (!currentYear) { currentYear = filteredVisits[filteredVisits.length - 1].date.getUTCFullYear(); } createVisitsHistogram('.d3-wrapper', filteredVisits, currentYear, yearClickedTimeline); updateCalendar(currentYear, filteredVisits, yearChangedCalendar); updateVisitsList(currentYear); } // callback when the user only wants to see full visits pointing // to different snapshots (default) export function showFullVisitsDifferentSnapshots(event) { filteredVisits = filterFullVisits(true); updateDisplayedVisits(); } // callback when the user only wants to see full visits export function showFullVisits(event) { filteredVisits = filterFullVisits(false); updateDisplayedVisits(); } // callback when the user wants to see all visits (including partial, ongoing and failed ones) export function showAllVisits(event) { filteredVisits = allVisits; updateDisplayedVisits(); } export function initVisitsReporting(visits) { $(document).ready(() => { allVisits = visits; // process input visits let firstFullVisit; allVisits.forEach((v, i) => { // Turn Unix epoch into Javascript Date object v.date = new Date(Math.floor(v.date * 1000)); - let visitLink = '' + v.fmt_date + ''; + let visitLink = '' + v.formatted_date + ''; if (v.status === 'full') { if (!firstFullVisit) { firstFullVisit = v; $('#swh-first-full-visit').append($(visitLink)); if (allVisits.length === 1) { $('#swh-last-full-visit')[0].innerHTML = visitLink; } } else { $('#swh-last-full-visit')[0].innerHTML = visitLink; } } if (i === allVisits.length - 1) { $('#swh-last-visit').append($(visitLink)); } }); // display full visits pointing to different snapshots by default showFullVisitsDifferentSnapshots(); }); } diff --git a/swh/web/browse/snapshot_context.py b/swh/web/browse/snapshot_context.py index a8cb018a..bcd6bcbd 100644 --- a/swh/web/browse/snapshot_context.py +++ b/swh/web/browse/snapshot_context.py @@ -1,1390 +1,1401 @@ # 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 # Utility module for browsing the archive in a snapshot context. from collections import defaultdict +from copy import copy +from typing import Any, Dict, List, Optional, Union, Tuple from django.core.cache import cache from django.shortcuts import render from django.template.defaultfilters import filesizeformat from django.utils.html import escape import sentry_sdk from swh.model.identifiers import persistent_identifier, snapshot_identifier from swh.web.browse.utils import ( get_directory_entries, gen_directory_link, gen_revision_link, request_content, gen_content_link, prepare_content_for_display, content_display_max_size, format_log_entries, gen_revision_log_link, gen_release_link, get_readme_to_display, get_swh_persistent_ids, gen_snapshot_link, ) from swh.web.common import service, highlightjs from swh.web.common.exc import handle_view_exception, NotFoundExc from swh.web.common.origin_visits import get_origin_visit +from swh.web.common.typing import ( + OriginInfo, + QueryParameters, + SnapshotBranchInfo, + SnapshotReleaseInfo, + SnapshotContext, +) from swh.web.common.utils import ( reverse, gen_path_info, format_utc_iso_date, swh_object_icons, ) from swh.web.config import get_config _empty_snapshot_id = snapshot_identifier({"branches": {}}) def _get_branch(branches, branch_name, snapshot_id): """ Utility function to get a specific branch from a branches list. Its purpose is to get the default HEAD branch as some software origin (e.g those with svn type) does not have it. In that latter case, check if there is a master branch instead and returns it. """ filtered_branches = [b for b in branches if b["name"] == branch_name] if filtered_branches: return filtered_branches[0] elif branch_name == "HEAD": filtered_branches = [b for b in branches if b["name"].endswith("master")] if filtered_branches: return filtered_branches[0] elif branches: return branches[0] else: # case where a large branches list has been truncated snp = service.lookup_snapshot( snapshot_id, branches_from=branch_name, branches_count=1, target_types=["revision", "alias"], ) snp_branch, _ = process_snapshot_branches(snp) if snp_branch and snp_branch[0]["name"] == branch_name: branches.append(snp_branch[0]) return snp_branch[0] def _get_release(releases, release_name, snapshot_id): """ Utility function to get a specific release from a releases list. Returns None if the release can not be found in the list. """ filtered_releases = [r for r in releases if r["name"] == release_name] if filtered_releases: return filtered_releases[0] else: # case where a large branches list has been truncated for branch_name in (release_name, f"refs/tags/{release_name}"): snp = service.lookup_snapshot( snapshot_id, branches_from=branch_name, branches_count=1, target_types=["release"], ) _, snp_release = process_snapshot_branches(snp) if snp_release and snp_release[0]["name"] == release_name: releases.append(snp_release[0]) return snp_release[0] def _branch_not_found( branch_type, branch, snapshot_id, snapshot_sizes, origin_info, timestamp, visit_id ): """ Utility function to raise an exception when a specified branch/release can not be found. """ if branch_type == "branch": branch_type = "Branch" branch_type_plural = "branches" target_type = "revision" else: branch_type = "Release" branch_type_plural = "releases" target_type = "release" if snapshot_id and snapshot_sizes[target_type] == 0: msg = "Snapshot with id %s has an empty list" " of %s!" % ( snapshot_id, branch_type_plural, ) elif snapshot_id: msg = "%s %s for snapshot with id %s" " not found!" % ( branch_type, branch, snapshot_id, ) elif visit_id and snapshot_sizes[target_type] == 0: msg = ( "Origin with url %s" " for visit with id %s has an empty list" " of %s!" % (origin_info["url"], visit_id, branch_type_plural) ) elif visit_id: msg = ( "%s %s associated to visit with" " id %s for origin with url %s" " not found!" % (branch_type, branch, visit_id, origin_info["url"]) ) elif snapshot_sizes[target_type] == 0: msg = ( "Origin with url %s" " for visit with timestamp %s has an empty list" " of %s!" % (origin_info["url"], timestamp, branch_type_plural) ) else: msg = ( "%s %s associated to visit with" " timestamp %s for origin with " "url %s not found!" % (branch_type, branch, timestamp, origin_info["url"]) ) raise NotFoundExc(escape(msg)) -def process_snapshot_branches(snapshot): +def process_snapshot_branches( + snapshot: Dict[str, Any] +) -> Tuple[List[SnapshotBranchInfo], List[SnapshotReleaseInfo]]: """ Process a dictionary describing snapshot branches: extract those targeting revisions and releases, put them in two different lists, then sort those lists in lexicographical order of the branches' names. Args: - snapshot_branches (dict): A dict describing the branches of a snapshot - as returned for instance by + snapshot: A dict describing a snapshot as returned for instance by :func:`swh.web.common.service.lookup_snapshot` Returns: - tuple: A tuple whose first member is the sorted list of branches - targeting revisions and second member the sorted list of branches - targeting releases + A tuple whose first member is the sorted list of branches + targeting revisions and second member the sorted list of branches + targeting releases """ snapshot_branches = snapshot["branches"] - branches = {} - branch_aliases = {} - releases = {} + branches: Dict[str, SnapshotBranchInfo] = {} + branch_aliases: Dict[str, str] = {} + releases: Dict[str, SnapshotReleaseInfo] = {} revision_to_branch = defaultdict(set) revision_to_release = defaultdict(set) release_to_branch = defaultdict(set) for branch_name, target in snapshot_branches.items(): if not target: # FIXME: display branches with an unknown target anyway continue target_id = target["target"] target_type = target["target_type"] if target_type == "revision": - branches[branch_name] = { - "name": branch_name, - "revision": target_id, - } + branches[branch_name] = SnapshotBranchInfo( + name=branch_name, + revision=target_id, + date=None, + directory=None, + message=None, + url=None, + ) revision_to_branch[target_id].add(branch_name) elif target_type == "release": release_to_branch[target_id].add(branch_name) elif target_type == "alias": branch_aliases[branch_name] = target_id # FIXME: handle pointers to other object types - def _enrich_release_branch(branch, release): - releases[branch] = { - "name": release["name"], - "branch_name": branch, - "date": format_utc_iso_date(release["date"]), - "id": release["id"], - "message": release["message"], - "target_type": release["target_type"], - "target": release["target"], - } + def _add_release_info(branch, release): + releases[branch] = SnapshotReleaseInfo( + name=release["name"], + branch_name=branch, + date=format_utc_iso_date(release["date"]), + directory=None, + id=release["id"], + message=release["message"], + target_type=release["target_type"], + target=release["target"], + url=None, + ) - def _enrich_revision_branch(branch, revision): - branches[branch].update( - { - "revision": revision["id"], - "directory": revision["directory"], - "date": format_utc_iso_date(revision["date"]), - "message": revision["message"], - } + def _add_branch_info(branch, revision): + branches[branch] = SnapshotBranchInfo( + name=branch, + revision=revision["id"], + directory=revision["directory"], + date=format_utc_iso_date(revision["date"]), + message=revision["message"], + url=None, ) releases_info = service.lookup_release_multiple(release_to_branch.keys()) for release in releases_info: branches_to_update = release_to_branch[release["id"]] for branch in branches_to_update: - _enrich_release_branch(branch, release) + _add_release_info(branch, release) if release["target_type"] == "revision": revision_to_release[release["target"]].update(branches_to_update) revisions = service.lookup_revision_multiple( set(revision_to_branch.keys()) | set(revision_to_release.keys()) ) for revision in revisions: if not revision: continue for branch in revision_to_branch[revision["id"]]: - _enrich_revision_branch(branch, revision) + _add_branch_info(branch, revision) for release in revision_to_release[revision["id"]]: releases[release]["directory"] = revision["directory"] for branch_alias, branch_target in branch_aliases.items(): if branch_target in branches: - branches[branch_alias] = dict(branches[branch_target]) + branches[branch_alias] = copy(branches[branch_target]) else: snp = service.lookup_snapshot( snapshot["id"], branches_from=branch_target, branches_count=1 ) if snp and branch_target in snp["branches"]: if snp["branches"][branch_target] is None: continue target_type = snp["branches"][branch_target]["target_type"] target = snp["branches"][branch_target]["target"] if target_type == "revision": branches[branch_alias] = snp["branches"][branch_target] revision = service.lookup_revision(target) - _enrich_revision_branch(branch_alias, revision) + _add_branch_info(branch_alias, revision) elif target_type == "release": release = service.lookup_release(target) - _enrich_release_branch(branch_alias, release) + _add_release_info(branch_alias, release) if branch_alias in branches: branches[branch_alias]["name"] = branch_alias ret_branches = list(sorted(branches.values(), key=lambda b: b["name"])) ret_releases = list(sorted(releases.values(), key=lambda b: b["name"])) return ret_branches, ret_releases -def get_snapshot_content(snapshot_id): +def get_snapshot_content( + snapshot_id: str, +) -> Tuple[List[SnapshotBranchInfo], List[SnapshotReleaseInfo]]: """Returns the lists of branches and releases associated to a swh snapshot. That list is put in cache in order to speedup the navigation in the swh-web/browse ui. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. Args: - snapshot_id (str): hexadecimal representation of the snapshot - identifier + snapshot_id: hexadecimal representation of the snapshot identifier Returns: A tuple with two members. The first one is a list of dict describing the snapshot branches. The second one is a list of dict describing the snapshot releases. Raises: NotFoundExc if the snapshot does not exist """ cache_entry_id = "swh_snapshot_%s" % snapshot_id cache_entry = cache.get(cache_entry_id) if cache_entry: return cache_entry["branches"], cache_entry["releases"] - branches = [] - releases = [] + branches: List[SnapshotBranchInfo] = [] + releases: List[SnapshotReleaseInfo] = [] snapshot_content_max_size = get_config()["snapshot_content_max_size"] if snapshot_id: snapshot = service.lookup_snapshot( snapshot_id, branches_count=snapshot_content_max_size ) branches, releases = process_snapshot_branches(snapshot) cache.set(cache_entry_id, {"branches": branches, "releases": releases,}) return branches, releases def get_origin_visit_snapshot( - origin_info, visit_ts=None, visit_id=None, snapshot_id=None -): - """Returns the lists of branches and releases - associated to a swh origin for a given visit. - The visit is expressed by a timestamp. In the latter case, - the closest visit from the provided timestamp will be used. + origin_info: OriginInfo, + visit_ts: Optional[Union[int, str]] = None, + visit_id: Optional[int] = None, + snapshot_id: Optional[str] = None, +) -> Tuple[List[SnapshotBranchInfo], List[SnapshotReleaseInfo]]: + """Returns the lists of branches and releases associated to an origin for + a given visit. + + The visit is expressed by either: + + * a snapshot identifier + * a timestamp, if no visit with that exact timestamp is found, + the closest one from the provided timestamp will be used. + If no visit parameter is provided, it returns the list of branches found for the latest visit. + That list is put in cache in order to speedup the navigation in the swh-web/browse ui. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. Args: - origin_info (dict): a dict filled with origin information - (id, url, type) - visit_ts (int or str): an ISO date string or Unix timestamp to parse - visit_id (int): optional visit id for disambiguation in case - several visits have the same timestamp + origin_info: a dict filled with origin information + visit_ts: an ISO date string or Unix timestamp to parse + visit_id: visit id for disambiguation in case several visits have + the same timestamp + snapshot_id: if provided, visit associated to the snapshot will be processed Returns: A tuple with two members. The first one is a list of dict describing the origin branches for the given visit. The second one is a list of dict describing the origin releases for the given visit. Raises: NotFoundExc if the origin or its visit are not found """ visit_info = get_origin_visit(origin_info, visit_ts, visit_id, snapshot_id) return get_snapshot_content(visit_info["snapshot"]) def get_snapshot_context( - snapshot_id=None, origin_url=None, timestamp=None, visit_id=None -): + snapshot_id: Optional[str] = None, + origin_url: Optional[str] = None, + timestamp: Optional[str] = None, + visit_id: Optional[int] = None, + branch_name: Optional[str] = None, + release_name: Optional[str] = None, + revision_id: Optional[str] = None, + path: Optional[str] = None, + browse_context: str = "directory", +) -> SnapshotContext: """ Utility function to compute relevant information when navigating the archive in a snapshot context. The snapshot is either referenced by its id or it will be retrieved from an origin visit. Args: - snapshot_id (str): hexadecimal representation of a snapshot identifier, - all other parameters will be ignored if it is provided - origin_url (str): the origin_url - (e.g. https://github.com/(user)/(repo)/) - timestamp (str): a datetime string for retrieving the closest + snapshot_id: hexadecimal representation of a snapshot identifier + origin_url: an origin_url + timestamp: a datetime string for retrieving the closest visit of the origin - visit_id (int): optional visit id for disambiguation in case + visit_id: optional visit id for disambiguation in case of several visits with the same timestamp + branch_name: optional branch name set when browsing the snapshot in + that scope (will default to "HEAD" if not provided) + release_name: optional release name set when browsing the snapshot in + that scope + revision_id: optional revision identifier set when browsing the snapshot in + that scope + path: optional path of the object currently browsed in the snapshot + browse_context: indicates which type of object is currently browsed Returns: - A dict with the following entries: - * origin_info: dict containing origin information - * visit_info: dict containing visit information - * branches: the list of branches for the origin found - during the visit - * releases: the list of releases for the origin found - during the visit - * origin_browse_url: the url to browse the origin - * origin_branches_url: the url to browse the origin branches - * origin_releases_url': the url to browse the origin releases - * origin_visit_url: the url to browse the snapshot of the origin - found during the visit - * url_args: dict containing url arguments to use when browsing in - the context of the origin and its visit + A dict filled with snapshot context information. Raises: swh.web.common.exc.NotFoundExc: if no snapshot is found for the visit of an origin. """ + assert origin_url is not None or snapshot_id is not None origin_info = None visit_info = None - url_args = None - query_params = {} - branches = [] - releases = [] - browse_url = None - visit_url = None - branches_url = None - releases_url = None - swh_type = "snapshot" + url_args = {} + query_params: QueryParameters = {} + origin_visits_url = None if origin_url: - swh_type = "origin" origin_info = service.lookup_origin({"url": origin_url}) visit_info = get_origin_visit(origin_info, timestamp, visit_id, snapshot_id) - fmt_date = format_utc_iso_date(visit_info["date"]) - visit_info["fmt_date"] = fmt_date + formatted_date = format_utc_iso_date(visit_info["date"]) + visit_info["formatted_date"] = formatted_date snapshot_id = visit_info["snapshot"] if not snapshot_id: raise NotFoundExc( "No snapshot associated to the visit of origin " - "%s on %s" % (escape(origin_url), fmt_date) + "%s on %s" % (escape(origin_url), formatted_date) ) # provided timestamp is not necessarily equals to the one # of the retrieved visit, so get the exact one in order - # use it in the urls generated below + # to use it in the urls generated below if timestamp: timestamp = visit_info["date"] branches, releases = get_origin_visit_snapshot( origin_info, timestamp, visit_id, snapshot_id ) url_args = {"origin_url": origin_info["url"]} - query_params = {"visit_id": visit_id} + query_params = {} + if visit_id is not None: + query_params["visit_id"] = visit_id - browse_url = reverse("browse-origin-visits", url_args=url_args) + origin_visits_url = reverse("browse-origin-visits", url_args=url_args) if timestamp: - url_args["timestamp"] = format_utc_iso_date(timestamp, "%Y-%m-%dT%H:%M:%S") + url_args["timestamp"] = format_utc_iso_date(timestamp, "%Y-%m-%dT%H:%M:%SZ") visit_url = reverse( "browse-origin-directory", url_args=url_args, query_params=query_params ) visit_info["url"] = visit_url branches_url = reverse( "browse-origin-branches", url_args=url_args, query_params=query_params ) releases_url = reverse( "browse-origin-releases", url_args=url_args, query_params=query_params ) - elif snapshot_id: + else: + assert snapshot_id is not None branches, releases = get_snapshot_content(snapshot_id) url_args = {"snapshot_id": snapshot_id} - browse_url = reverse("browse-snapshot", url_args=url_args) branches_url = reverse("browse-snapshot-branches", url_args=url_args) releases_url = reverse("browse-snapshot-releases", url_args=url_args) releases = list(reversed(releases)) snapshot_sizes = service.lookup_snapshot_sizes(snapshot_id) is_empty = sum(snapshot_sizes.values()) == 0 swh_snp_id = persistent_identifier("snapshot", snapshot_id) - return { - "swh_type": swh_type, - "swh_object_id": swh_snp_id, - "snapshot_id": snapshot_id, - "snapshot_sizes": snapshot_sizes, - "is_empty": is_empty, - "origin_info": origin_info, - "visit_info": visit_info, - "branches": branches, - "releases": releases, - "branch": None, - "release": None, - "browse_url": browse_url, - "branches_url": branches_url, - "releases_url": releases_url, - "url_args": url_args, - "query_params": query_params, - } - - -def _process_snapshot_request( - request, - snapshot_id=None, - origin_url=None, - timestamp=None, - path=None, - browse_context="directory", -): - """ - Utility function to perform common input request processing - for snapshot context views. - """ - - visit_id = request.GET.get("visit_id", None) - - snapshot_context = get_snapshot_context( - snapshot_id, origin_url, timestamp, visit_id - ) - - swh_type = snapshot_context["swh_type"] - origin_info = snapshot_context["origin_info"] - branches = snapshot_context["branches"] - releases = snapshot_context["releases"] - url_args = snapshot_context["url_args"] - query_params = snapshot_context["query_params"] - - if snapshot_context["visit_info"]: - timestamp = format_utc_iso_date( - snapshot_context["visit_info"]["date"], "%Y-%m-%dT%H:%M:%SZ" - ) - snapshot_context["timestamp"] = format_utc_iso_date( - snapshot_context["visit_info"]["date"] - ) + if visit_info: + timestamp = format_utc_iso_date(visit_info["date"]) - browse_view_name = "browse-" + swh_type + "-" + browse_context + if origin_info: + browse_view_name = f"browse-origin-{browse_context}" + else: + browse_view_name = f"browse-snapshot-{browse_context}" - root_sha1_git = None - revision_id = request.GET.get("revision", None) - release_name = request.GET.get("release", None) release_id = None - branch_name = None + root_directory = None - snapshot_sizes = snapshot_context["snapshot_sizes"] snapshot_total_size = sum(snapshot_sizes.values()) - if snapshot_total_size and revision_id: + if snapshot_total_size and revision_id is not None: revision = service.lookup_revision(revision_id) - root_sha1_git = revision["directory"] + root_directory = revision["directory"] branches.append( - { - "name": revision_id, - "revision": revision_id, - "directory": root_sha1_git, - "url": None, - } + SnapshotBranchInfo( + name=revision_id, + revision=revision_id, + directory=root_directory, + date=revision["date"], + message=revision["message"], + url=None, + ) ) branch_name = revision_id query_params["revision"] = revision_id elif snapshot_total_size and release_name: - release = _get_release(releases, release_name, snapshot_context["snapshot_id"]) + release = _get_release(releases, release_name, snapshot_id) try: - root_sha1_git = release["directory"] + root_directory = release["directory"] revision_id = release["target"] release_id = release["id"] query_params["release"] = release_name except Exception as exc: sentry_sdk.capture_exception(exc) _branch_not_found( "release", release_name, snapshot_id, snapshot_sizes, origin_info, timestamp, visit_id, ) elif snapshot_total_size: - branch_name = request.GET.get("branch", None) if branch_name: query_params["branch"] = branch_name - branch = _get_branch( - branches, branch_name or "HEAD", snapshot_context["snapshot_id"] - ) + branch = _get_branch(branches, branch_name or "HEAD", snapshot_id) try: branch_name = branch["name"] revision_id = branch["revision"] - root_sha1_git = branch["directory"] + root_directory = branch["directory"] except Exception as exc: sentry_sdk.capture_exception(exc) _branch_not_found( "branch", branch_name, snapshot_id, snapshot_sizes, origin_info, timestamp, visit_id, ) for b in branches: branch_url_args = dict(url_args) branch_query_params = dict(query_params) - if "release" in branch_query_params: - del branch_query_params["release"] - branch_query_params["branch"] = b["name"] + branch_query_params.pop("release", None) + if b["name"] != b["revision"]: + branch_query_params.pop("revision", None) + branch_query_params["branch"] = b["name"] if path: - b["path"] = path branch_url_args["path"] = path b["url"] = reverse( browse_view_name, url_args=branch_url_args, query_params=branch_query_params ) for r in releases: release_url_args = dict(url_args) release_query_params = dict(query_params) - if "branch" in release_query_params: - del release_query_params["branch"] + release_query_params.pop("branch", None) + release_query_params.pop("revision", None) release_query_params["release"] = r["name"] if path: - r["path"] = path release_url_args["path"] = path r["url"] = reverse( browse_view_name, url_args=release_url_args, query_params=release_query_params, ) - snapshot_context["query_params"] = query_params - snapshot_context["root_sha1_git"] = root_sha1_git - snapshot_context["revision_id"] = revision_id - snapshot_context["branch"] = branch_name - snapshot_context["release"] = release_name - snapshot_context["release_id"] = release_id + return SnapshotContext( + branch=branch_name, + branches=branches, + branches_url=branches_url, + is_empty=is_empty, + origin_info=origin_info, + origin_visits_url=origin_visits_url, + release=release_name, + release_id=release_id, + query_params=query_params, + releases=releases, + releases_url=releases_url, + revision_id=revision_id, + root_directory=root_directory, + snapshot_id=snapshot_id, + snapshot_sizes=snapshot_sizes, + snapshot_swhid=swh_snp_id, + url_args=url_args, + visit_info=visit_info, + ) + + +def _build_breadcrumbs(snapshot_context: SnapshotContext, path: str): + origin_info = snapshot_context["origin_info"] + url_args = snapshot_context["url_args"] + query_params = snapshot_context["query_params"] + root_directory = snapshot_context["root_directory"] - return snapshot_context + path_info = gen_path_info(path) + + if origin_info: + browse_view_name = "browse-origin-directory" + else: + browse_view_name = "browse-snapshot-directory" + + breadcrumbs = [] + if root_directory: + breadcrumbs.append( + { + "name": root_directory[:7], + "url": reverse( + browse_view_name, url_args=url_args, query_params=query_params + ), + } + ) + for pi in path_info: + bc_url_args = dict(url_args) + bc_url_args["path"] = pi["path"] + breadcrumbs.append( + { + "name": pi["name"], + "url": reverse( + browse_view_name, url_args=bc_url_args, query_params=query_params + ), + } + ) + return breadcrumbs def browse_snapshot_directory( request, snapshot_id=None, origin_url=None, timestamp=None, path=None ): """ Django view implementation for browsing a directory in a snapshot context. """ try: - snapshot_context = _process_snapshot_request( - request, - snapshot_id, - origin_url, - timestamp, - path, + snapshot_context = get_snapshot_context( + snapshot_id=snapshot_id, + origin_url=origin_url, + timestamp=timestamp, + visit_id=request.GET.get("visit_id"), + path=path, browse_context="directory", + branch_name=request.GET.get("branch"), + release_name=request.GET.get("release"), + revision_id=request.GET.get("revision"), ) - root_sha1_git = snapshot_context["root_sha1_git"] - sha1_git = root_sha1_git - if root_sha1_git and path: - dir_info = service.lookup_directory_with_path(root_sha1_git, path) + root_directory = snapshot_context["root_directory"] + sha1_git = root_directory + if root_directory and path: + dir_info = service.lookup_directory_with_path(root_directory, path) sha1_git = dir_info["target"] dirs = [] files = [] if sha1_git: dirs, files = get_directory_entries(sha1_git) except Exception as exc: return handle_view_exception(request, exc) - swh_type = snapshot_context["swh_type"] origin_info = snapshot_context["origin_info"] visit_info = snapshot_context["visit_info"] url_args = snapshot_context["url_args"] query_params = snapshot_context["query_params"] revision_id = snapshot_context["revision_id"] snapshot_id = snapshot_context["snapshot_id"] - path_info = gen_path_info(path) + if origin_info: + browse_view_name = "browse-origin-directory" + else: + browse_view_name = "browse-snapshot-directory" - browse_view_name = "browse-" + swh_type + "-directory" - - breadcrumbs = [] - if root_sha1_git: - breadcrumbs.append( - { - "name": root_sha1_git[:7], - "url": reverse( - browse_view_name, url_args=url_args, query_params=query_params - ), - } - ) - for pi in path_info: - bc_url_args = dict(url_args) - bc_url_args["path"] = pi["path"] - breadcrumbs.append( - { - "name": pi["name"], - "url": reverse( - browse_view_name, url_args=bc_url_args, query_params=query_params - ), - } - ) + breadcrumbs = _build_breadcrumbs(snapshot_context, path) path = "" if path is None else (path + "/") for d in dirs: if d["type"] == "rev": d["url"] = reverse("browse-revision", url_args={"sha1_git": d["target"]}) else: bc_url_args = dict(url_args) bc_url_args["path"] = path + d["name"] d["url"] = reverse( browse_view_name, url_args=bc_url_args, query_params=query_params ) sum_file_sizes = 0 readmes = {} - browse_view_name = "browse-" + swh_type + "-content" + if origin_info: + browse_view_name = "browse-origin-content" + else: + browse_view_name = "browse-snapshot-content" for f in files: bc_url_args = dict(url_args) bc_url_args["path"] = path + f["name"] f["url"] = reverse( browse_view_name, url_args=bc_url_args, query_params=query_params ) if f["length"] is not None: sum_file_sizes += f["length"] f["length"] = filesizeformat(f["length"]) if f["name"].lower().startswith("readme"): readmes[f["name"]] = f["checksums"]["sha1"] readme_name, readme_url, readme_html = get_readme_to_display(readmes) - browse_view_name = "browse-" + swh_type + "-log" + if origin_info: + browse_view_name = "browse-origin-log" + else: + browse_view_name = "browse-snapshot-log" history_url = None if snapshot_id != _empty_snapshot_id: history_url = reverse( browse_view_name, url_args=url_args, query_params=query_params ) nb_files = None nb_dirs = None dir_path = None - if root_sha1_git: + if root_directory: nb_files = len(files) nb_dirs = len(dirs) sum_file_sizes = filesizeformat(sum_file_sizes) dir_path = "/" + path browse_dir_link = gen_directory_link(sha1_git) browse_rev_link = gen_revision_link(revision_id) browse_snp_link = gen_snapshot_link(snapshot_id) dir_metadata = { "directory": sha1_git, "context-independent directory": browse_dir_link, "number of regular files": nb_files, "number of subdirectories": nb_dirs, "sum of regular file sizes": sum_file_sizes, "path": dir_path, "revision": revision_id, "context-independent revision": browse_rev_link, "snapshot": snapshot_id, "context-independent snapshot": browse_snp_link, } if origin_info: dir_metadata["origin url"] = origin_info["url"] dir_metadata["origin visit date"] = format_utc_iso_date(visit_info["date"]) dir_metadata["origin visit type"] = visit_info["type"] vault_cooking = { "directory_context": True, "directory_id": sha1_git, "revision_context": True, "revision_id": revision_id, } swh_objects = [ {"type": "directory", "id": sha1_git}, {"type": "revision", "id": revision_id}, {"type": "snapshot", "id": snapshot_id}, ] release_id = snapshot_context["release_id"] if release_id: swh_objects.append({"type": "release", "id": release_id}) browse_rel_link = gen_release_link(release_id) dir_metadata["release"] = release_id dir_metadata["context-independent release"] = browse_rel_link swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) dir_path = "/".join([bc["name"] for bc in breadcrumbs]) + "/" context_found = "snapshot: %s" % snapshot_context["snapshot_id"] if origin_info: context_found = "origin: %s" % origin_info["url"] heading = "Directory - %s - %s - %s" % ( dir_path, snapshot_context["branch"], context_found, ) top_right_link = None if not snapshot_context["is_empty"]: top_right_link = { "url": history_url, "icon": swh_object_icons["revisions history"], "text": "History", } return render( request, "browse/directory.html", { "heading": heading, "swh_object_name": "Directory", "swh_object_metadata": dir_metadata, "dirs": dirs, "files": files, - "breadcrumbs": breadcrumbs if root_sha1_git else [], + "breadcrumbs": breadcrumbs if root_directory else [], "top_right_link": top_right_link, "readme_name": readme_name, "readme_url": readme_url, "readme_html": readme_html, "snapshot_context": snapshot_context, "vault_cooking": vault_cooking, "show_actions_menu": True, "swh_ids": swh_ids, }, ) def browse_snapshot_content( request, snapshot_id=None, origin_url=None, timestamp=None, path=None, selected_language=None, ): """ Django view implementation for browsing a content in a snapshot context. """ try: - snapshot_context = _process_snapshot_request( - request, snapshot_id, origin_url, timestamp, path, browse_context="content" + snapshot_context = get_snapshot_context( + snapshot_id=snapshot_id, + origin_url=origin_url, + timestamp=timestamp, + visit_id=request.GET.get("visit_id"), + path=path, + browse_context="content", + branch_name=request.GET.get("branch"), + release_name=request.GET.get("release"), + revision_id=request.GET.get("revision"), ) - root_sha1_git = snapshot_context["root_sha1_git"] + root_directory = snapshot_context["root_directory"] sha1_git = None query_string = None content_data = None directory_id = None split_path = path.split("/") filename = split_path[-1] filepath = path[: -len(filename)] - if root_sha1_git: - content_info = service.lookup_directory_with_path(root_sha1_git, path) + if root_directory: + content_info = service.lookup_directory_with_path(root_directory, path) sha1_git = content_info["target"] query_string = "sha1_git:" + sha1_git content_data = request_content(query_string, raise_if_unavailable=False) if filepath: - dir_info = service.lookup_directory_with_path(root_sha1_git, filepath) + dir_info = service.lookup_directory_with_path(root_directory, filepath) directory_id = dir_info["target"] else: - directory_id = root_sha1_git + directory_id = root_directory except Exception as exc: return handle_view_exception(request, exc) - swh_type = snapshot_context["swh_type"] - url_args = snapshot_context["url_args"] - query_params = snapshot_context["query_params"] revision_id = snapshot_context["revision_id"] origin_info = snapshot_context["origin_info"] visit_info = snapshot_context["visit_info"] snapshot_id = snapshot_context["snapshot_id"] content = None language = None mimetype = None if content_data and content_data["raw_data"] is not None: content_display_data = prepare_content_for_display( content_data["raw_data"], content_data["mimetype"], path ) content = content_display_data["content_data"] language = content_display_data["language"] mimetype = content_display_data["mimetype"] # Override language with user-selected language if selected_language is not None: language = selected_language available_languages = None if mimetype and "text/" in mimetype: available_languages = highlightjs.get_supported_languages() - browse_view_name = "browse-" + swh_type + "-directory" - - breadcrumbs = [] - - path_info = gen_path_info(filepath) - if root_sha1_git: - breadcrumbs.append( - { - "name": root_sha1_git[:7], - "url": reverse( - browse_view_name, url_args=url_args, query_params=query_params - ), - } - ) - for pi in path_info: - bc_url_args = dict(url_args) - bc_url_args["path"] = pi["path"] - breadcrumbs.append( - { - "name": pi["name"], - "url": reverse( - browse_view_name, url_args=bc_url_args, query_params=query_params - ), - } - ) + breadcrumbs = _build_breadcrumbs(snapshot_context, filepath) breadcrumbs.append({"name": filename, "url": None}) browse_content_link = gen_content_link(sha1_git) content_raw_url = None if query_string: content_raw_url = reverse( "browse-content-raw", url_args={"query_string": query_string}, query_params={"filename": filename}, ) browse_rev_link = gen_revision_link(revision_id) browse_dir_link = gen_directory_link(directory_id) content_metadata = { "context-independent content": browse_content_link, "path": None, "filename": None, "directory": directory_id, "context-independent directory": browse_dir_link, "revision": revision_id, "context-independent revision": browse_rev_link, "snapshot": snapshot_id, } cnt_sha1_git = None content_size = None error_code = 200 error_description = "" error_message = "" if content_data: for checksum in content_data["checksums"].keys(): content_metadata[checksum] = content_data["checksums"][checksum] content_metadata["mimetype"] = content_data["mimetype"] content_metadata["encoding"] = content_data["encoding"] content_metadata["size"] = filesizeformat(content_data["length"]) content_metadata["language"] = content_data["language"] content_metadata["licenses"] = content_data["licenses"] content_metadata["path"] = "/" + filepath content_metadata["filename"] = filename cnt_sha1_git = content_data["checksums"]["sha1_git"] content_size = content_data["length"] error_code = content_data["error_code"] error_message = content_data["error_message"] error_description = content_data["error_description"] if origin_info: content_metadata["origin url"] = origin_info["url"] content_metadata["origin visit date"] = format_utc_iso_date(visit_info["date"]) content_metadata["origin visit type"] = visit_info["type"] browse_snapshot_link = gen_snapshot_link(snapshot_id) content_metadata["context-independent snapshot"] = browse_snapshot_link swh_objects = [ {"type": "content", "id": cnt_sha1_git}, {"type": "directory", "id": directory_id}, {"type": "revision", "id": revision_id}, {"type": "snapshot", "id": snapshot_id}, ] release_id = snapshot_context["release_id"] if release_id: swh_objects.append({"type": "release", "id": release_id}) browse_rel_link = gen_release_link(release_id) content_metadata["release"] = release_id content_metadata["context-independent release"] = browse_rel_link swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) content_path = "/".join([bc["name"] for bc in breadcrumbs]) context_found = "snapshot: %s" % snapshot_context["snapshot_id"] if origin_info: context_found = "origin: %s" % origin_info["url"] heading = "Content - %s - %s - %s" % ( content_path, snapshot_context["branch"], context_found, ) top_right_link = None if not snapshot_context["is_empty"]: top_right_link = { "url": content_raw_url, "icon": swh_object_icons["content"], "text": "Raw File", } return render( request, "browse/content.html", { "heading": heading, "swh_object_name": "Content", "swh_object_metadata": content_metadata, "content": content, "content_size": content_size, "max_content_size": content_display_max_size, "mimetype": mimetype, "language": language, "available_languages": available_languages, - "breadcrumbs": breadcrumbs if root_sha1_git else [], + "breadcrumbs": breadcrumbs if root_directory else [], "top_right_link": top_right_link, "snapshot_context": snapshot_context, "vault_cooking": None, "show_actions_menu": True, "swh_ids": swh_ids, "error_code": error_code, "error_message": error_message, "error_description": error_description, }, status=error_code, ) PER_PAGE = 100 def browse_snapshot_log(request, snapshot_id=None, origin_url=None, timestamp=None): """ Django view implementation for browsing a revision history in a snapshot context. """ try: - snapshot_context = _process_snapshot_request( - request, snapshot_id, origin_url, timestamp, browse_context="log" + snapshot_context = get_snapshot_context( + snapshot_id=snapshot_id, + origin_url=origin_url, + timestamp=timestamp, + visit_id=request.GET.get("visit_id"), + browse_context="log", + branch_name=request.GET.get("branch"), + release_name=request.GET.get("release"), + revision_id=request.GET.get("revision"), ) revision_id = snapshot_context["revision_id"] per_page = int(request.GET.get("per_page", PER_PAGE)) offset = int(request.GET.get("offset", 0)) revs_ordering = request.GET.get("revs_ordering", "committer_date") session_key = "rev_%s_log_ordering_%s" % (revision_id, revs_ordering) rev_log_session = request.session.get(session_key, None) rev_log = [] revs_walker_state = None if rev_log_session: rev_log = rev_log_session["rev_log"] revs_walker_state = rev_log_session["revs_walker_state"] if len(rev_log) < offset + per_page: revs_walker = service.get_revisions_walker( revs_ordering, revision_id, max_revs=offset + per_page + 1, state=revs_walker_state, ) rev_log += [rev["id"] for rev in revs_walker] revs_walker_state = revs_walker.export_state() revs = rev_log[offset : offset + per_page] revision_log = service.lookup_revision_multiple(revs) request.session[session_key] = { "rev_log": rev_log, "revs_walker_state": revs_walker_state, } except Exception as exc: return handle_view_exception(request, exc) - swh_type = snapshot_context["swh_type"] origin_info = snapshot_context["origin_info"] visit_info = snapshot_context["visit_info"] url_args = snapshot_context["url_args"] query_params = snapshot_context["query_params"] snapshot_id = snapshot_context["snapshot_id"] query_params["per_page"] = per_page revs_ordering = request.GET.get("revs_ordering", "") query_params["revs_ordering"] = revs_ordering - browse_view_name = "browse-" + swh_type + "-log" + if origin_info: + browse_view_name = "browse-origin-log" + else: + browse_view_name = "browse-snapshot-log" prev_log_url = None if len(rev_log) > offset + per_page: query_params["offset"] = offset + per_page prev_log_url = reverse( browse_view_name, url_args=url_args, query_params=query_params ) next_log_url = None if offset != 0: query_params["offset"] = offset - per_page next_log_url = reverse( browse_view_name, url_args=url_args, query_params=query_params ) revision_log_data = format_log_entries(revision_log, per_page, snapshot_context) browse_rev_link = gen_revision_link(revision_id) browse_log_link = gen_revision_log_link(revision_id) browse_snp_link = gen_snapshot_link(snapshot_id) revision_metadata = { "context-independent revision": browse_rev_link, "context-independent revision history": browse_log_link, "context-independent snapshot": browse_snp_link, "snapshot": snapshot_id, } if origin_info: revision_metadata["origin url"] = origin_info["url"] revision_metadata["origin visit date"] = format_utc_iso_date(visit_info["date"]) revision_metadata["origin visit type"] = visit_info["type"] swh_objects = [ {"type": "revision", "id": revision_id}, {"type": "snapshot", "id": snapshot_id}, ] release_id = snapshot_context["release_id"] if release_id: swh_objects.append({"type": "release", "id": release_id}) browse_rel_link = gen_release_link(release_id) revision_metadata["release"] = release_id revision_metadata["context-independent release"] = browse_rel_link swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) context_found = "snapshot: %s" % snapshot_context["snapshot_id"] if origin_info: context_found = "origin: %s" % origin_info["url"] heading = "Revision history - %s - %s" % (snapshot_context["branch"], context_found) return render( request, "browse/revision-log.html", { "heading": heading, "swh_object_name": "Revisions history", "swh_object_metadata": revision_metadata, "revision_log": revision_log_data, "revs_ordering": revs_ordering, "next_log_url": next_log_url, "prev_log_url": prev_log_url, "breadcrumbs": None, "top_right_link": None, "snapshot_context": snapshot_context, "vault_cooking": None, "show_actions_menu": True, "swh_ids": swh_ids, }, ) def browse_snapshot_branches( request, snapshot_id=None, origin_url=None, timestamp=None ): """ Django view implementation for browsing a list of branches in a snapshot context. """ try: - snapshot_context = _process_snapshot_request( - request, snapshot_id, origin_url, timestamp + + snapshot_context = get_snapshot_context( + snapshot_id=snapshot_id, + origin_url=origin_url, + timestamp=timestamp, + visit_id=request.GET.get("visit_id"), ) branches_bc = request.GET.get("branches_breadcrumbs", "") branches_bc = branches_bc.split(",") if branches_bc else [] branches_from = branches_bc[-1] if branches_bc else "" - swh_type = snapshot_context["swh_type"] origin_info = snapshot_context["origin_info"] url_args = snapshot_context["url_args"] query_params = snapshot_context["query_params"] - browse_view_name = "browse-" + swh_type + "-directory" + if origin_info: + browse_view_name = "browse-origin-directory" + else: + browse_view_name = "browse-snapshot-directory" snapshot = service.lookup_snapshot( snapshot_context["snapshot_id"], branches_from, PER_PAGE + 1, target_types=["revision", "alias"], ) displayed_branches, _ = process_snapshot_branches(snapshot) except Exception as exc: return handle_view_exception(request, exc) for branch in displayed_branches: if snapshot_id: revision_url = reverse( "browse-revision", url_args={"sha1_git": branch["revision"]}, query_params={"snapshot_id": snapshot_id}, ) else: revision_url = reverse( "browse-revision", url_args={"sha1_git": branch["revision"]}, query_params={"origin": origin_info["url"]}, ) query_params["branch"] = branch["name"] directory_url = reverse( browse_view_name, url_args=url_args, query_params=query_params ) del query_params["branch"] branch["revision_url"] = revision_url branch["directory_url"] = directory_url - browse_view_name = "browse-" + swh_type + "-branches" + if origin_info: + browse_view_name = "browse-origin-branches" + else: + browse_view_name = "browse-snapshot-branches" prev_branches_url = None next_branches_url = None if branches_bc: query_params_prev = dict(query_params) query_params_prev["branches_breadcrumbs"] = ",".join(branches_bc[:-1]) prev_branches_url = reverse( browse_view_name, url_args=url_args, query_params=query_params_prev ) elif branches_from: prev_branches_url = reverse( browse_view_name, url_args=url_args, query_params=query_params ) if snapshot["next_branch"] is not None: query_params_next = dict(query_params) next_branch = displayed_branches[-1]["name"] del displayed_branches[-1] branches_bc.append(next_branch) query_params_next["branches_breadcrumbs"] = ",".join(branches_bc) next_branches_url = reverse( browse_view_name, url_args=url_args, query_params=query_params_next ) heading = "Branches - " if origin_info: heading += "origin: %s" % origin_info["url"] else: heading += "snapshot: %s" % snapshot_id return render( request, "browse/branches.html", { "heading": heading, "swh_object_name": "Branches", "swh_object_metadata": {}, "top_right_link": None, "displayed_branches": displayed_branches, "prev_branches_url": prev_branches_url, "next_branches_url": next_branches_url, "snapshot_context": snapshot_context, }, ) def browse_snapshot_releases( request, snapshot_id=None, origin_url=None, timestamp=None ): """ Django view implementation for browsing a list of releases in a snapshot context. """ try: - snapshot_context = _process_snapshot_request( - request, snapshot_id, origin_url, timestamp + snapshot_context = get_snapshot_context( + snapshot_id=snapshot_id, + origin_url=origin_url, + timestamp=timestamp, + visit_id=request.GET.get("visit_id"), ) rel_bc = request.GET.get("releases_breadcrumbs", "") rel_bc = rel_bc.split(",") if rel_bc else [] rel_from = rel_bc[-1] if rel_bc else "" - swh_type = snapshot_context["swh_type"] origin_info = snapshot_context["origin_info"] url_args = snapshot_context["url_args"] query_params = snapshot_context["query_params"] snapshot = service.lookup_snapshot( snapshot_context["snapshot_id"], rel_from, PER_PAGE + 1, target_types=["release", "alias"], ) _, displayed_releases = process_snapshot_branches(snapshot) except Exception as exc: return handle_view_exception(request, exc) for release in displayed_releases: if snapshot_id: query_params_tgt = {"snapshot_id": snapshot_id} else: query_params_tgt = {"origin": origin_info["url"]} release_url = reverse( "browse-release", url_args={"sha1_git": release["id"]}, query_params=query_params_tgt, ) target_url = "" if release["target_type"] == "revision": target_url = reverse( "browse-revision", url_args={"sha1_git": release["target"]}, query_params=query_params_tgt, ) elif release["target_type"] == "directory": target_url = reverse( "browse-directory", url_args={"sha1_git": release["target"]}, query_params=query_params_tgt, ) elif release["target_type"] == "content": target_url = reverse( "browse-content", url_args={"query_string": release["target"]}, query_params=query_params_tgt, ) elif release["target_type"] == "release": target_url = reverse( "browse-release", url_args={"sha1_git": release["target"]}, query_params=query_params_tgt, ) release["release_url"] = release_url release["target_url"] = target_url - browse_view_name = "browse-" + swh_type + "-releases" + if origin_info: + browse_view_name = "browse-origin-releases" + else: + browse_view_name = "browse-snapshot-releases" prev_releases_url = None next_releases_url = None if rel_bc: query_params_prev = dict(query_params) query_params_prev["releases_breadcrumbs"] = ",".join(rel_bc[:-1]) prev_releases_url = reverse( browse_view_name, url_args=url_args, query_params=query_params_prev ) elif rel_from: prev_releases_url = reverse( browse_view_name, url_args=url_args, query_params=query_params ) if snapshot["next_branch"] is not None: query_params_next = dict(query_params) next_rel = displayed_releases[-1]["branch_name"] del displayed_releases[-1] rel_bc.append(next_rel) query_params_next["releases_breadcrumbs"] = ",".join(rel_bc) next_releases_url = reverse( browse_view_name, url_args=url_args, query_params=query_params_next ) heading = "Releases - " if origin_info: heading += "origin: %s" % origin_info["url"] else: heading += "snapshot: %s" % snapshot_id return render( request, "browse/releases.html", { "heading": heading, "top_panel_visible": False, "top_panel_collapsible": False, "swh_object_name": "Releases", "swh_object_metadata": {}, "top_right_link": None, "displayed_releases": displayed_releases, "prev_releases_url": prev_releases_url, "next_releases_url": next_releases_url, "snapshot_context": snapshot_context, "vault_cooking": None, "show_actions_menu": False, }, ) diff --git a/swh/web/browse/views/origin.py b/swh/web/browse/views/origin.py index dadbd7ae..f2b4c9d0 100644 --- a/swh/web/browse/views/origin.py +++ b/swh/web/browse/views/origin.py @@ -1,189 +1,189 @@ # Copyright (C) 2017-2019 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 django.shortcuts import render, redirect from swh.web.browse.browseurls import browse_route from swh.web.browse.snapshot_context import ( browse_snapshot_directory, browse_snapshot_content, browse_snapshot_log, browse_snapshot_branches, browse_snapshot_releases, get_snapshot_context, ) from swh.web.common import service from swh.web.common.exc import handle_view_exception from swh.web.common.origin_visits import get_origin_visits from swh.web.common.utils import reverse, format_utc_iso_date, parse_timestamp @browse_route( r"origin/(?P.+)/visit/(?P.+)/directory/", r"origin/(?P.+)/visit/(?P.+)/directory/(?P.+)/", r"origin/(?P.+)/directory/", r"origin/(?P.+)/directory/(?P.+)/", view_name="browse-origin-directory", ) def origin_directory_browse(request, origin_url, timestamp=None, path=None): """Django view for browsing the content of a directory associated to an origin for a given visit. The url scheme that points to it is the following: * :http:get:`/browse/origin/(origin_url)/directory/[(path)/]` * :http:get:`/browse/origin/(origin_url)/visit/(timestamp)/directory/[(path)/]` """ return browse_snapshot_directory( request, origin_url=origin_url, timestamp=timestamp, path=path ) @browse_route( r"origin/(?P.+)/visit/(?P.+)/content/(?P.+)/", r"origin/(?P.+)/content/(?P.+)/", view_name="browse-origin-content", ) def origin_content_browse(request, origin_url, path=None, timestamp=None): """Django view that produces an HTML display of a content associated to an origin for a given visit. The url scheme that points to it is the following: * :http:get:`/browse/origin/(origin_url)/content/(path)/` * :http:get:`/browse/origin/(origin_url)/visit/(timestamp)/content/(path)/` """ language = request.GET.get("language", None) return browse_snapshot_content( request, origin_url=origin_url, timestamp=timestamp, path=path, selected_language=language, ) PER_PAGE = 20 @browse_route( r"origin/(?P.+)/visit/(?P.+)/log/", r"origin/(?P.+)/log/", view_name="browse-origin-log", ) def origin_log_browse(request, origin_url, timestamp=None): """Django view that produces an HTML display of revisions history (aka the commit log) associated to a software origin. The url scheme that points to it is the following: * :http:get:`/browse/origin/(origin_url)/log/` * :http:get:`/browse/origin/(origin_url)/visit/(timestamp)/log/` """ return browse_snapshot_log(request, origin_url=origin_url, timestamp=timestamp) @browse_route( r"origin/(?P.+)/visit/(?P.+)/branches/", r"origin/(?P.+)/branches/", view_name="browse-origin-branches", ) def origin_branches_browse(request, origin_url, timestamp=None): """Django view that produces an HTML display of the list of branches associated to an origin for a given visit. The url scheme that points to it is the following: * :http:get:`/browse/origin/(origin_url)/branches/` * :http:get:`/browse/origin/(origin_url)/visit/(timestamp)/branches/` """ return browse_snapshot_branches(request, origin_url=origin_url, timestamp=timestamp) @browse_route( r"origin/(?P.+)/visit/(?P.+)/releases/", r"origin/(?P.+)/releases/", view_name="browse-origin-releases", ) def origin_releases_browse(request, origin_url, timestamp=None): """Django view that produces an HTML display of the list of releases associated to an origin for a given visit. The url scheme that points to it is the following: * :http:get:`/browse/origin/(origin_url)/releases/` * :http:get:`/browse/origin/(origin_url)/visit/(timestamp)/releases/` """ return browse_snapshot_releases(request, origin_url=origin_url, timestamp=timestamp) @browse_route(r"origin/(?P.+)/visits/", view_name="browse-origin-visits") def origin_visits_browse(request, origin_url): """Django view that produces an HTML display of visits reporting for a given origin. The url that points to it is :http:get:`/browse/origin/(origin_url)/visits/`. """ try: origin_info = service.lookup_origin({"url": origin_url}) origin_visits = get_origin_visits(origin_info) snapshot_context = get_snapshot_context(origin_url=origin_url) except Exception as exc: return handle_view_exception(request, exc) for i, visit in enumerate(origin_visits): url_date = format_utc_iso_date(visit["date"], "%Y-%m-%dT%H:%M:%SZ") - visit["fmt_date"] = format_utc_iso_date(visit["date"]) + visit["formatted_date"] = format_utc_iso_date(visit["date"]) query_params = {} if i < len(origin_visits) - 1: if visit["date"] == origin_visits[i + 1]["date"]: query_params = {"visit_id": visit["visit"]} if i > 0: if visit["date"] == origin_visits[i - 1]["date"]: query_params = {"visit_id": visit["visit"]} snapshot = visit["snapshot"] if visit["snapshot"] else "" - visit["browse_url"] = reverse( + visit["url"] = reverse( "browse-origin-directory", url_args={"origin_url": origin_url, "timestamp": url_date}, query_params=query_params, ) if not snapshot: visit["snapshot"] = "" visit["date"] = parse_timestamp(visit["date"]).timestamp() heading = "Origin visits - %s" % origin_url return render( request, "browse/origin-visits.html", { "heading": heading, "swh_object_name": "Visits", "swh_object_metadata": origin_info, "origin_visits": origin_visits, "origin_info": origin_info, "snapshot_context": snapshot_context, "vault_cooking": None, "show_actions_menu": False, }, ) @browse_route(r"origin/(?P.+)/", view_name="browse-origin") def origin_browse(request, origin_url): """Django view that redirects to the display of the latest archived snapshot for a given software origin. """ last_snapshot_url = reverse( "browse-origin-directory", url_args={"origin_url": origin_url} ) return redirect(last_snapshot_url) diff --git a/swh/web/common/converters.py b/swh/web/common/converters.py index e510e9ac..94b668d9 100644 --- a/swh/web/common/converters.py +++ b/swh/web/common/converters.py @@ -1,387 +1,389 @@ # Copyright (C) 2015-2019 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 datetime import json +from typing import Dict, Any -from swh.model import hashutil from swh.core.utils import decode_with_escape +from swh.model import hashutil +from swh.web.common.typing import OriginInfo, OriginVisitInfo def _group_checksums(data): """Groups checksums values computed from hash functions used in swh and stored in data dict under a single entry 'checksums' """ if data: checksums = {} for hash in hashutil.ALGORITHMS: if hash in data and data[hash]: checksums[hash] = data[hash] del data[hash] if len(checksums) > 0: data["checksums"] = checksums def fmap(f, data): """Map f to data at each level. This must keep the origin data structure type: - map -> map - dict -> dict - list -> list - None -> None Args: f: function that expects one argument. data: data to traverse to apply the f function. list, map, dict or bare value. Returns: The same data-structure with modified values by the f function. """ if data is None: return data if isinstance(data, map): return map(lambda y: fmap(f, y), (x for x in data)) if isinstance(data, list): return [fmap(f, x) for x in data] if isinstance(data, dict): return {k: fmap(f, v) for (k, v) in data.items()} return f(data) def from_swh( dict_swh, hashess={}, bytess={}, dates={}, blacklist={}, removables_if_empty={}, empty_dict={}, empty_list={}, convert={}, convert_fn=lambda x: x, ): """Convert from a swh dictionary to something reasonably json serializable. Args: dict_swh: the origin dictionary needed to be transformed hashess: list/set of keys representing hashes values (sha1, sha256, sha1_git, etc...) as bytes. Those need to be transformed in hexadecimal string bytess: list/set of keys representing bytes values which needs to be decoded blacklist: set of keys to filter out from the conversion convert: set of keys whose associated values need to be converted using convert_fn convert_fn: the conversion function to apply on the value of key in 'convert' The remaining keys are copied as is in the output. Returns: dictionary equivalent as dict_swh only with its keys converted. """ def convert_hashes_bytes(v): """v is supposedly a hash as bytes, returns it converted in hex. """ if isinstance(v, bytes): return hashutil.hash_to_hex(v) return v def convert_bytes(v): """v is supposedly a bytes string, decode as utf-8. FIXME: Improve decoding policy. If not utf-8, break! """ if isinstance(v, bytes): return v.decode("utf-8") return v def convert_date(v): """ Args: v (dict or datatime): either: - a dict with three keys: - timestamp (dict or integer timestamp) - offset - negative_utc - or, a datetime We convert it to a human-readable string """ if not v: return v if isinstance(v, datetime.datetime): return v.isoformat() tz = datetime.timezone(datetime.timedelta(minutes=v["offset"])) swh_timestamp = v["timestamp"] if isinstance(swh_timestamp, dict): date = datetime.datetime.fromtimestamp(swh_timestamp["seconds"], tz=tz) else: date = datetime.datetime.fromtimestamp(swh_timestamp, tz=tz) datestr = date.isoformat() if v["offset"] == 0 and v["negative_utc"]: # remove the rightmost + and replace it with a - return "-".join(datestr.rsplit("+", 1)) return datestr if not dict_swh: return dict_swh new_dict = {} for key, value in dict_swh.items(): if key in blacklist or (key in removables_if_empty and not value): continue if key in dates: new_dict[key] = convert_date(value) elif key in convert: new_dict[key] = convert_fn(value) elif isinstance(value, dict): new_dict[key] = from_swh( value, hashess=hashess, bytess=bytess, dates=dates, blacklist=blacklist, removables_if_empty=removables_if_empty, empty_dict=empty_dict, empty_list=empty_list, convert=convert, convert_fn=convert_fn, ) elif key in hashess: new_dict[key] = fmap(convert_hashes_bytes, value) elif key in bytess: try: new_dict[key] = fmap(convert_bytes, value) except UnicodeDecodeError: if "decoding_failures" not in new_dict: new_dict["decoding_failures"] = [key] else: new_dict["decoding_failures"].append(key) new_dict[key] = fmap(decode_with_escape, value) elif key in empty_dict and not value: new_dict[key] = {} elif key in empty_list and not value: new_dict[key] = [] else: new_dict[key] = value _group_checksums(new_dict) return new_dict -def from_origin(origin): +def from_origin(origin: Dict[str, Any]) -> OriginInfo: """Convert from a swh origin to an origin dictionary. """ return from_swh(origin) def from_release(release): """Convert from a swh release to a json serializable release dictionary. Args: release (dict): dictionary with keys: - id: identifier of the revision (sha1 in bytes) - revision: identifier of the revision the release points to (sha1 in bytes) comment: release's comment message (bytes) name: release's name (string) author: release's author identifier (swh's id) synthetic: the synthetic property (boolean) Returns: dict: Release dictionary with the following keys: - id: hexadecimal sha1 (string) - revision: hexadecimal sha1 (string) - comment: release's comment message (string) - name: release's name (string) - author: release's author identifier (swh's id) - synthetic: the synthetic property (boolean) """ return from_swh( release, hashess={"id", "target"}, bytess={"message", "name", "fullname", "email"}, dates={"date"}, ) class SWHMetadataEncoder(json.JSONEncoder): """Special json encoder for metadata field which can contain bytes encoded value. """ def default(self, obj): if isinstance(obj, bytes): try: return obj.decode("utf-8") except UnicodeDecodeError: # fallback to binary representation to avoid display errors return repr(obj) # Let the base class default method raise the TypeError return json.JSONEncoder.default(self, obj) def convert_revision_metadata(metadata): """Convert json specific dict to a json serializable one. """ if not metadata: return {} return json.loads(json.dumps(metadata, cls=SWHMetadataEncoder)) def from_revision(revision): """Convert from a swh revision to a json serializable revision dictionary. Args: revision (dict): dict with keys: - id: identifier of the revision (sha1 in bytes) - directory: identifier of the directory the revision points to (sha1 in bytes) - author_name, author_email: author's revision name and email - committer_name, committer_email: committer's revision name and email - message: revision's message - date, date_offset: revision's author date - committer_date, committer_date_offset: revision's commit date - parents: list of parents for such revision - synthetic: revision's property nature - type: revision's type (git, tar or dsc at the moment) - metadata: if the revision is synthetic, this can reference dynamic properties. Returns: dict: Revision dictionary with the same keys as inputs, except: - sha1s are in hexadecimal strings (id, directory) - bytes are decoded in string (author_name, committer_name, author_email, committer_email) Remaining keys are left as is """ revision = from_swh( revision, hashess={"id", "directory", "parents", "children"}, bytess={"name", "fullname", "email"}, convert={"metadata"}, convert_fn=convert_revision_metadata, dates={"date", "committer_date"}, ) if revision: if "parents" in revision: revision["merge"] = len(revision["parents"]) > 1 if "message" in revision: try: revision["message"] = revision["message"].decode("utf-8") except UnicodeDecodeError: revision["message_decoding_failed"] = True revision["message"] = None return revision def from_content(content): """Convert swh content to serializable content dictionary. """ return from_swh( content, hashess={"sha1", "sha1_git", "sha256", "blake2s256"}, blacklist={"ctime"}, convert={"status"}, convert_fn=lambda v: "absent" if v == "hidden" else v, ) def from_person(person): """Convert swh person to serializable person dictionary. """ return from_swh(person, bytess={"name", "fullname", "email"}) -def from_origin_visit(visit): +def from_origin_visit(visit: Dict[str, Any]) -> OriginVisitInfo: """Convert swh origin_visit to serializable origin_visit dictionary. """ ov = from_swh( visit, hashess={"target", "snapshot"}, bytess={"branch"}, dates={"date"}, empty_dict={"metadata"}, ) return ov def from_snapshot(snapshot): """Convert swh snapshot to serializable snapshot dictionary. """ sv = from_swh(snapshot, hashess={"id", "target"}, bytess={"next_branch"}) if sv and "branches" in sv: sv["branches"] = {decode_with_escape(k): v for k, v in sv["branches"].items()} for k, v in snapshot["branches"].items(): # alias target existing branch names, not a sha1 if v and v["target_type"] == "alias": branch = decode_with_escape(k) target = decode_with_escape(v["target"]) sv["branches"][branch]["target"] = target return sv def from_directory_entry(dir_entry): """Convert swh directory to serializable directory dictionary. """ return from_swh( dir_entry, hashess={"dir_id", "sha1_git", "sha1", "sha256", "blake2s256", "target"}, bytess={"name"}, removables_if_empty={"sha1", "sha1_git", "sha256", "blake2s256", "status"}, convert={"status"}, convert_fn=lambda v: "absent" if v == "hidden" else v, ) def from_filetype(content_entry): """Convert swh content to serializable dictionary containing keys 'id', 'encoding', and 'mimetype'. """ return from_swh(content_entry, hashess={"id"}) diff --git a/swh/web/common/origin_visits.py b/swh/web/common/origin_visits.py index 5346a5bd..e37eedaa 100644 --- a/swh/web/common/origin_visits.py +++ b/swh/web/common/origin_visits.py @@ -1,175 +1,162 @@ # 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, Union from django.core.cache import cache from swh.web.common.exc import NotFoundExc +from swh.web.common.typing import OriginInfo, OriginVisitInfo from swh.web.common.utils import parse_timestamp -def get_origin_visits(origin_info): +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. Args: - origin_info (dict): dict describing the origin to fetch visits from + origin_info: dict describing the origin to fetch visits from Returns: - list: A list of dict describing the origin visits with the - following keys: - - * **date**: UTC visit date in ISO format, - * **origin**: the origin url - * **status**: the visit status, either **full**, **partial** - or **ongoing** - * **visit**: the visit id - * **type**: the visit type + 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_timestamp(visit["date"]).timestamp() return ts + (float(visit["visit"]) / 10e3) - for v in origin_visits: - if "metadata" in v: - del v["metadata"] - origin_visits = [dict(t) for t in set([tuple(d.items()) for d in origin_visits])] 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, visit_ts=None, visit_id=None, snapshot_id=None): - """Function that returns information about a visit for - a given origin. +def get_origin_visit( + origin_info: OriginInfo, + visit_ts: Optional[Union[int, str]] = None, + visit_id: Optional[int] = None, + snapshot_id: Optional[str] = None, +) -> OriginVisitInfo: + """Function that returns information about a visit for a given origin. The visit is retrieved from a provided timestamp. The closest visit from that timestamp is selected. Args: - origin_info (dict): a dict filled with origin information - visit_ts (int or str): an ISO date string or Unix timestamp to parse + origin_info: a dict filled with origin information + visit_ts: an ISO date string or Unix timestamp to parse Returns: - A dict containing the visit info as described below:: - - {'origin': 'https://forge.softwareheritage.org/source/swh-web/', - 'date': '2017-10-08T11:54:25.582463+00:00', - 'metadata': {}, - 'visit': 25, - 'status': 'full'} - + A dict containing the visit info. """ visits = get_origin_visits(origin_info) if not visits: raise NotFoundExc( ("No visit associated to origin with" " url %s!" % origin_info["url"]) ) if snapshot_id: - visit = [v for v in visits if v["snapshot"] == snapshot_id] - if len(visit) == 0: + 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 visit[0] + return visits[0] if visit_id: - visit = [v for v in visits if v["visit"] == int(visit_id)] - if len(visit) == 0: + 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 visit[0] + return visits[0] if not visit_ts: # returns the latest visit with a valid snapshot when no timestamp is provided for v in reversed(visits): if v["snapshot"] is not None: return v return visits[-1] target_visit_ts = math.floor(parse_timestamp(visit_ts).timestamp()) # Find the visit with date closest to the target (in absolute value) (abs_time_delta, visit_idx) = min( ( (math.floor(parse_timestamp(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"]) ) ) diff --git a/swh/web/common/service.py b/swh/web/common/service.py index 7c5b0a48..5ec88012 100644 --- a/swh/web/common/service.py +++ b/swh/web/common/service.py @@ -1,1228 +1,1242 @@ # 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 +from typing import Any, Dict, List, Set, Iterator, Optional, Tuple from swh.model import hashutil from swh.storage.algos import diff, revisions_walker from swh.model.identifiers import CONTENT, DIRECTORY, RELEASE, REVISION, SNAPSHOT +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 import config +from swh.web.common.typing import OriginInfo, OriginVisitInfo + 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(l): """Returns the first element in the provided list or None if it is empty or None""" return next(iter(l 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): """Checks if the storage contains a given content checksum Args: query string of the form 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})) return {"found": converters.from_content(found), "algo": algo} def search_hash(q): """Checks if the storage contains a given content checksum Args: query string of the form 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): """Given a possible input, query for the content's sha1. Args: q: query string of the form 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 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 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 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 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: Dict[str, str]) -> Dict[str, str]: +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. """ origins = [origin] 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("/"): origins.append({"url": 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: origins.append({"url": f"{origin['url']}/"}) # Check all possible origin urls for orig in origins: origin_info = storage.origin_get(orig) if origin_info: break if not origin_info: msg = "Origin with url %s not found!" % origin["url"] raise NotFoundExc(msg) return converters.from_origin(origin_info) -def lookup_origins(origin_from=1, origin_count=100): +def lookup_origins( + origin_from: int = 1, origin_count: int = 100 +) -> Iterator[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 Yields: origins information as dicts """ origins = storage.origin_get_range(origin_from, origin_count) return map(converters.from_origin, origins) -def search_origin(url_pattern, limit=50, with_visit=False, page_token=None): +def search_origin( + url_pattern: str, limit: int = 50, with_visit: bool = False, page_token: Any = None +) -> Tuple[List[OriginInfo], Any]: """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 search: results = search.origin_search( url_pattern=url_pattern, count=limit, page_token=page_token, with_visit=with_visit, ) origins = list(map(converters.from_origin, results["results"])) return (origins, results["next_page_token"]) else: # Fallback to swh-storage if swh-search is not configured offset = int(page_token) if page_token else 0 regexp = True 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) - origins = storage.origin_search(url_pattern, offset, limit, regexp, with_visit) - origins = list(map(converters.from_origin, origins)) + origins_raw = storage.origin_search( + url_pattern, offset, limit, regexp, with_visit + ) + origins = list(map(converters.from_origin, origins_raw)) if len(origins) >= limit: page_token = str(offset + len(origins)) else: page_token = None return (origins, page_token) def search_origin_metadata(fulltext, limit=50): """Search for origins whose metadata match a provided string pattern. Args: fulltext: the string pattern to search for in origin metadata offset: number of found origins to skip before returning results limit: the maximum number of found origins to return Returns: list of origin metadata as dict. """ matches = idx_storage.origin_intrinsic_metadata_search_fulltext( conjunction=[fulltext], limit=limit ) results = [] for match in matches: match["from_revision"] = hashutil.hash_to_hex(match["from_revision"]) origin = storage.origin_get({"url": match["id"]}) del match["id"] result = converters.from_origin(origin) if result: result["metadata"] = match results.append(result) return results def lookup_origin_intrinsic_metadata(origin_dict): """Return intrinsic metadata for origin whose origin matches given origin. Args: origin_dict: origin's dict with keys ('type' AND 'url') Returns: origin metadata. """ origin_info = storage.origin_get(origin_dict) if not origin_info: msg = "Origin with url %s not found!" % origin_dict["url"] raise NotFoundExc(msg) origins = [origin_info["url"]] 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: - Generator of revisions information as dict. + 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': } 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.') 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("Content not found for revision %s" % sha1_git) if with_data: c = _first_element(storage.content_get([content["sha1"]])) content["data"] = c["data"] return { "type": "file", "path": "." if not dir_path else dir_path, "revision": sha1_git, "content": converters.from_content(content), } 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): """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: raise NotFoundExc( "Content with %s checksum equals to %s not found!" % (algo, hashutil.hash_to_hex(hash)) ) return converters.from_content(c) def lookup_content_raw(q): """Lookup the content defined by q. Args: q: query string of the form 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 = _first_element(storage.content_get([content_sha1_bytes])) if not content: algo, hash = query.parse_hash(q) raise NotFoundExc( "Bytes of content with %s checksum equals to %s " "are not available!" % (algo, hashutil.hash_to_hex(hash)) ) return converters.from_content(content) 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, last_visit=None, limit=10): +def _lookup_origin_visits( + origin_url: str, last_visit: Optional[int] = None, limit: int = 10 +) -> Iterator[Dict[str, Any]]: """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: Dictionaries of origin_visit for that origin """ limit = min(limit, MAX_LIMIT) for visit in storage.origin_visit_get( origin_url, last_visit=last_visit, limit=limit ): visit["origin"] = origin_url yield visit -def lookup_origin_visits(origin, last_visit=None, per_page=10): +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 """ visits = _lookup_origin_visits(origin, last_visit=last_visit, limit=per_page) for visit in visits: yield converters.from_origin_visit(visit) -def lookup_origin_visit_latest(origin_url, require_snapshot): +def lookup_origin_visit_latest( + origin_url: str, require_snapshot: bool +) -> OriginVisitInfo: """Return the origin's latest visit Args: origin_url (str): origin to list visits for require_snapshot (bool): filter out origins without a snapshot Returns: dict: The origin_visit concerned """ visit = storage.origin_visit_get_latest( origin_url, require_snapshot=require_snapshot ) return converters.from_origin_visit(visit) -def lookup_origin_visit(origin_url, visit_id): +def lookup_origin_visit(origin_url: str, visit_id: int) -> OriginVisitInfo: """Return information about visit visit_id with origin origin. Args: origin (str): 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) if not visit: raise NotFoundExc( "Origin %s or its visit " "with id %s not found!" % (origin_url, visit_id) ) visit["origin"] = origin_url return converters.from_origin_visit(visit) 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(): if lookup_snapshot( snapshot_id, branches_from=alias["target"], branches_count=1, target_types=["revision"], ): snapshot_sizes["revision"] += 1 else: snapshot_sizes["release"] += 1 del snapshot_sizes["alias"] 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) snapshot = storage.snapshot_get_branches( snapshot_id_bin, branches_from.encode(), branches_count, target_types ) if not snapshot: raise NotFoundExc("Snapshot with id %s not found!" % snapshot_id) return converters.from_snapshot(snapshot) def lookup_latest_origin_snapshot(origin, allowed_statuses=None): """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. """ snapshot = storage.snapshot_get_latest(origin, allowed_statuses) return converters.from_snapshot(snapshot) 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_cook(obj_type, obj_id, email=None): """Cook a vault bundle. """ return vault.cook(obj_type, obj_id, email=email) def vault_fetch(obj_type, obj_id): """Fetch a vault bundle. """ return vault.fetch(obj_type, obj_id) def vault_progress(obj_type, obj_id): """Get the current progress of a vault bundle. """ return 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_pids: Dict[str, List[bytes]]) -> Set[str]: """Lookup missing Software Heritage persistent identifier hash, using batch processing. Args: A dictionary with: keys: persistent identifier type values: list(bytes) persistent identifier hash Returns: A set(hexadecimal) of the hashes not found in the storage """ missing_hashes = [] for obj_type, obj_ids in grouped_pids.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/common/typing.py b/swh/web/common/typing.py index 01ba4af4..675df851 100644 --- a/swh/web/common/typing.py +++ b/swh/web/common/typing.py @@ -1,10 +1,112 @@ # Copyright (C) 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 typing import Any, Dict, Union +from typing import Any, Dict, List, Optional, Union +from typing_extensions import TypedDict from django.http import QueryDict QueryParameters = Union[Dict[str, Any], QueryDict] + + +class OriginInfo(TypedDict): + url: str + """URL of the origin""" + + +class OriginVisitInfo(TypedDict): + date: str + """date of the visit in iso format""" + formatted_date: str + """formatted date of the visit""" + metadata: Dict[str, Any] + """metadata associated to the visit""" + origin: str + """visited origin URL""" + snapshot: str + """snapshot identifier computed during the visit""" + status: str + """status of the visit ("ongoing", "full" or "partial") """ + type: str + """visit type (git, hg, debian, ...)""" + url: str + """URL to browse the snapshot""" + visit: int + """visit identifier""" + + +class SnapshotBranchInfo(TypedDict): + date: Optional[str] + """"author date of branch heading revision""" + directory: Optional[str] + """directory associated to branch heading revision""" + message: Optional[str] + """message of branch heading revision""" + name: Optional[str] + """branch name""" + revision: str + """branch heading revision""" + url: Optional[str] + """optional browse URL (content, directory, ...) scoped to branch""" + + +class SnapshotReleaseInfo(TypedDict): + branch_name: str + """branch name associated to release in snapshot""" + date: str + """release date""" + directory: Optional[str] + """optional directory associatd to the release""" + id: str + """release identifier""" + message: str + """release message""" + name: str + """release name""" + target: str + """release target""" + target_type: str + """release target_type""" + url: Optional[str] + """optional browse URL (content, directory, ...) scoped to release""" + + +class SnapshotContext(TypedDict): + branch: Optional[str] + """optional branch name set when browsing snapshot int that scope""" + branches: List[SnapshotBranchInfo] + """list of snapshot branches (possibly truncated)""" + branches_url: str + """snapshot branches list browse URL""" + is_empty: bool + """indicates if the snapshot is empty""" + origin_info: Optional[OriginInfo] + """optional origin info associated to the snapshot""" + origin_visits_url: Optional[str] + """optional origin visits URL""" + query_params: QueryParameters + """common query parameters when browsing snapshot content""" + release: Optional[str] + """optional release name set when browsing snapshot int that scope""" + release_id: Optional[str] + """optional release identifier set when browsing snapshot int that scope""" + releases: List[SnapshotReleaseInfo] + """list of snapshot releases (possibly truncated)""" + releases_url: str + """snapshot releases list browse URL""" + revision_id: Optional[str] + """optional revision identifier set when browsing snapshot int that scope""" + root_directory: Optional[str] + """optional root directory identifier set when browsing snapshot content""" + snapshot_id: str + """snapshot identifier""" + snapshot_sizes: Dict[str, int] + """snapshot sizes grouped by branch target type""" + snapshot_swhid: str + """snapshot SWHID""" + url_args: Dict[str, Any] + """common URL arguments when browsing snapshot content""" + visit_info: Optional[OriginVisitInfo] + """optional origin visit info associated to the snapshot""" diff --git a/swh/web/templates/browse/browse.html b/swh/web/templates/browse/browse.html index a478ba33..f0a864b8 100644 --- a/swh/web/templates/browse/browse.html +++ b/swh/web/templates/browse/browse.html @@ -1,63 +1,63 @@ {% extends "./layout.html" %} {% comment %} Copyright (C) 2017-2018 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 {% endcomment %} {% load swh_templatetags %} {% block title %}{{ heading }} – Software Heritage archive{% endblock %} {% block navbar-content %} {% if snapshot_context %}

Browse archived {{ swh_object_name.lower }} {% if snapshot_context.origin_info %} for origin {{ snapshot_context.origin_info.url }} {% if snapshot_context.origin_info.url|slice:"0:4" == "http" %} {% endif %} {% else %} for snapshot - - {{ snapshot_context.swh_object_id }} + + {{ snapshot_context.snapshot_swhid }} {% endif %}

{% else %}

Browse archived {{ swh_object_name.lower }} {{ swh_object_id }}

{% endif %} {% endblock %} {% block browse-content %} {% block swh-browse-before-content %} {% if snapshot_context %} {% include "includes/snapshot-context.html" %} {% endif %} {% endblock %} {% block swh-browse-content %}{% endblock %} {% block swh-browse-after-content %}{% endblock %} {% endblock %} diff --git a/swh/web/templates/includes/snapshot-context.html b/swh/web/templates/includes/snapshot-context.html index 58b563dc..b5b9bb75 100644 --- a/swh/web/templates/includes/snapshot-context.html +++ b/swh/web/templates/includes/snapshot-context.html @@ -1,31 +1,31 @@ {% comment %} Copyright (C) 2017-2018 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 {% endcomment %} {% load swh_templatetags %}

\ No newline at end of file diff --git a/swh/web/tests/browse/test_snapshot_context.py b/swh/web/tests/browse/test_snapshot_context.py index a14d2ed2..63531163 100644 --- a/swh/web/tests/browse/test_snapshot_context.py +++ b/swh/web/tests/browse/test_snapshot_context.py @@ -1,65 +1,329 @@ # Copyright (C) 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 + from hypothesis import given -from swh.web.browse.snapshot_context import get_origin_visit_snapshot -from swh.web.common.utils import format_utc_iso_date -from swh.web.tests.strategies import origin_with_multiple_visits +from swh.web.browse.snapshot_context import ( + get_origin_visit_snapshot, + get_snapshot_content, + get_snapshot_context, +) +from swh.web.common.identifiers import get_swh_persistent_id +from swh.web.common.origin_visits import get_origin_visit, get_origin_visits +from swh.web.common.typing import ( + SnapshotBranchInfo, + SnapshotReleaseInfo, + SnapshotContext, +) +from swh.web.common.utils import format_utc_iso_date, reverse +from swh.web.tests.strategies import origin_with_multiple_visits, snapshot @given(origin_with_multiple_visits()) def test_get_origin_visit_snapshot_simple(archive_data, origin): visits = archive_data.origin_visit_get(origin["url"]) for visit in visits: snapshot = archive_data.snapshot_get(visit["snapshot"]) branches = [] releases = [] def _process_branch_data(branch, branch_data): if branch_data["target_type"] == "revision": rev_data = archive_data.revision_get(branch_data["target"]) branches.append( - { - "name": branch, - "revision": branch_data["target"], - "directory": rev_data["directory"], - "date": format_utc_iso_date(rev_data["date"]), - "message": rev_data["message"], - } + SnapshotBranchInfo( + name=branch, + revision=branch_data["target"], + directory=rev_data["directory"], + date=format_utc_iso_date(rev_data["date"]), + message=rev_data["message"], + url=None, + ) ) elif branch_data["target_type"] == "release": rel_data = archive_data.release_get(branch_data["target"]) rev_data = archive_data.revision_get(rel_data["target"]) releases.append( - { - "name": rel_data["name"], - "branch_name": branch, - "date": format_utc_iso_date(rel_data["date"]), - "id": rel_data["id"], - "message": rel_data["message"], - "target_type": rel_data["target_type"], - "target": rel_data["target"], - "directory": rev_data["directory"], - } + SnapshotReleaseInfo( + name=rel_data["name"], + branch_name=branch, + date=format_utc_iso_date(rel_data["date"]), + id=rel_data["id"], + message=rel_data["message"], + target_type=rel_data["target_type"], + target=rel_data["target"], + directory=rev_data["directory"], + url=None, + ) ) for branch in sorted(snapshot["branches"].keys()): branch_data = snapshot["branches"][branch] if branch_data["target_type"] == "alias": target_data = snapshot["branches"][branch_data["target"]] _process_branch_data(branch, target_data) else: _process_branch_data(branch, branch_data) assert branches and releases, "Incomplete test data." origin_visit_branches = get_origin_visit_snapshot( origin, visit_id=visit["visit"] ) assert origin_visit_branches == (branches, releases) + + +@given(snapshot()) +def test_get_snapshot_context_no_origin(archive_data, snapshot): + + for browse_context, kwargs in ( + ("content", {"snapshot_id": snapshot, "path": "/some/path"}), + ("directory", {"snapshot_id": snapshot}), + ("log", {"snapshot_id": snapshot}), + ): + + url_args = {"snapshot_id": snapshot} + + snapshot_context = get_snapshot_context(**kwargs, browse_context=browse_context) + + branches, releases = get_snapshot_content(snapshot) + releases = list(reversed(releases)) + revision_id = None + root_directory = None + for branch in branches: + if branch["name"] == "HEAD": + revision_id = branch["revision"] + root_directory = branch["directory"] + branch["url"] = reverse( + f"browse-snapshot-{browse_context}", + url_args=kwargs, + query_params={"branch": branch["name"]}, + ) + for release in releases: + release["url"] = reverse( + f"browse-snapshot-{browse_context}", + url_args=kwargs, + query_params={"release": release["name"]}, + ) + + branches_url = reverse("browse-snapshot-branches", url_args=url_args) + releases_url = reverse("browse-snapshot-releases", url_args=url_args) + is_empty = not branches and not releases + snapshot_swhid = get_swh_persistent_id("snapshot", snapshot) + snapshot_sizes = {"revision": len(branches), "release": len(releases)} + + expected = SnapshotContext( + branch="HEAD", + branches=branches, + branches_url=branches_url, + is_empty=is_empty, + origin_info=None, + origin_visits_url=None, + release=None, + release_id=None, + query_params={}, + releases=releases, + releases_url=releases_url, + revision_id=revision_id, + root_directory=root_directory, + snapshot_id=snapshot, + snapshot_sizes=snapshot_sizes, + snapshot_swhid=snapshot_swhid, + url_args=url_args, + visit_info=None, + ) + + assert snapshot_context == expected + + _check_branch_release_revision_parameters( + archive_data, expected, browse_context, kwargs, branches, releases + ) + + +@given(origin_with_multiple_visits()) +def test_get_snapshot_context_with_origin(archive_data, origin): + + origin_visits = get_origin_visits(origin) + + timestamp = format_utc_iso_date(origin_visits[0]["date"], "%Y-%m-%dT%H:%M:%SZ") + visit_id = origin_visits[1]["visit"] + + for browse_context, kwargs in ( + ("content", {"origin_url": origin["url"], "path": "/some/path"}), + ("directory", {"origin_url": origin["url"]}), + ("log", {"origin_url": origin["url"]}), + ("directory", {"origin_url": origin["url"], "timestamp": timestamp,},), + ("directory", {"origin_url": origin["url"], "visit_id": visit_id,},), + ): + + visit_id = kwargs["visit_id"] if "visit_id" in kwargs else None + visit_ts = kwargs["timestamp"] if "timestamp" in kwargs else None + visit_info = get_origin_visit( + {"url": kwargs["origin_url"]}, visit_ts=visit_ts, visit_id=visit_id + ) + + snapshot = visit_info["snapshot"] + + snapshot_context = get_snapshot_context(**kwargs, browse_context=browse_context) + + url_args = dict(kwargs) + url_args.pop("visit_id", None) + + query_params = {} + if "visit_id" in kwargs: + query_params["visit_id"] = kwargs["visit_id"] + + branches, releases = get_snapshot_content(snapshot) + releases = list(reversed(releases)) + revision_id = None + root_directory = None + for branch in branches: + if branch["name"] == "HEAD": + revision_id = branch["revision"] + root_directory = branch["directory"] + branch["url"] = reverse( + f"browse-origin-{browse_context}", + url_args=url_args, + query_params={"branch": branch["name"], **query_params}, + ) + for release in releases: + release["url"] = reverse( + f"browse-origin-{browse_context}", + url_args=url_args, + query_params={"release": release["name"], **query_params}, + ) + + url_args.pop("path", None) + + branches_url = reverse( + "browse-origin-branches", url_args=url_args, query_params=query_params + ) + releases_url = reverse( + "browse-origin-releases", url_args=url_args, query_params=query_params + ) + origin_visits_url = reverse( + "browse-origin-visits", url_args={"origin_url": kwargs["origin_url"]} + ) + is_empty = not branches and not releases + snapshot_swhid = get_swh_persistent_id("snapshot", snapshot) + snapshot_sizes = {"revision": len(branches), "release": len(releases)} + + visit_info["url"] = reverse( + "browse-origin-directory", url_args=url_args, query_params=query_params + ) + visit_info["formatted_date"] = format_utc_iso_date(visit_info["date"]) + + expected = SnapshotContext( + branch="HEAD", + branches=branches, + branches_url=branches_url, + is_empty=is_empty, + origin_info={"url": origin["url"]}, + origin_visits_url=origin_visits_url, + release=None, + release_id=None, + query_params=query_params, + releases=releases, + releases_url=releases_url, + revision_id=revision_id, + root_directory=root_directory, + snapshot_id=snapshot, + snapshot_sizes=snapshot_sizes, + snapshot_swhid=snapshot_swhid, + url_args=url_args, + visit_info=visit_info, + ) + + assert snapshot_context == expected + + _check_branch_release_revision_parameters( + archive_data, expected, browse_context, kwargs, branches, releases + ) + + +def _check_branch_release_revision_parameters( + archive_data, base_expected_context, browse_context, kwargs, branches, releases, +): + branch = random.choice(branches) + + snapshot_context = get_snapshot_context( + **kwargs, browse_context=browse_context, branch_name=branch["name"] + ) + + query_params = {} + if "visit_id" in kwargs: + query_params["visit_id"] = kwargs["visit_id"] + + expected_branch = dict(base_expected_context) + expected_branch["branch"] = branch["name"] + expected_branch["revision_id"] = branch["revision"] + expected_branch["root_directory"] = branch["directory"] + expected_branch["query_params"] = {"branch": branch["name"], **query_params} + + assert snapshot_context == expected_branch + + if releases: + + release = random.choice(releases) + + snapshot_context = get_snapshot_context( + **kwargs, browse_context=browse_context, release_name=release["name"] + ) + + expected_release = dict(base_expected_context) + expected_release["branch"] = None + expected_release["release"] = release["name"] + expected_release["release_id"] = release["id"] + if release["target_type"] == "revision": + expected_release["revision_id"] = release["target"] + expected_release["root_directory"] = release["directory"] + expected_release["query_params"] = {"release": release["name"], **query_params} + + assert snapshot_context == expected_release + + revision_log = archive_data.revision_log(branch["revision"]) + revision = revision_log[-1] + + snapshot_context = get_snapshot_context( + **kwargs, browse_context=browse_context, revision_id=revision["id"] + ) + + if "origin_url" in kwargs: + view_name = f"browse-origin-{browse_context}" + else: + view_name = f"browse-snapshot-{browse_context}" + + kwargs.pop("visit_id", None) + + revision_browse_url = reverse( + view_name, + url_args=kwargs, + query_params={"revision": revision["id"], **query_params}, + ) + + branches.append( + SnapshotBranchInfo( + name=revision["id"], + revision=revision["id"], + directory=revision["directory"], + date=revision["date"], + message=revision["message"], + url=revision_browse_url, + ) + ) + + expected_revision = dict(base_expected_context) + expected_revision["branch"] = revision["id"] + expected_revision["branches"] = branches + expected_revision["revision_id"] = revision["id"] + expected_revision["root_directory"] = revision["directory"] + expected_revision["query_params"] = {"revision": revision["id"], **query_params} + + assert snapshot_context == expected_revision diff --git a/swh/web/tests/browse/views/test_origin.py b/swh/web/tests/browse/views/test_origin.py index a1a6711f..2d04857e 100644 --- a/swh/web/tests/browse/views/test_origin.py +++ b/swh/web/tests/browse/views/test_origin.py @@ -1,1063 +1,1063 @@ # 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.model.hashutil import hash_to_bytes from swh.model.model import Snapshot from swh.web.browse.snapshot_context import process_snapshot_branches from swh.web.common.exc import NotFoundExc from swh.web.common.identifiers import get_swh_persistent_id from swh.web.common.utils import ( reverse, gen_path_info, format_utc_iso_date, parse_timestamp, ) from swh.web.config import get_config 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, ) @given(origin_with_multiple_visits()) def test_origin_visits_browse(client, archive_data, origin): url = reverse("browse-origin-visits", url_args={"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", url_args={"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", url_args={"origin_url": origin["url"], "timestamp": vdate}, ) assert_contains(resp, browse_dir_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, origin, origin_visits, tdata["branches"], tdata["releases"], tdata["root_dir_sha1"], tdata["content"], ) _origin_content_view_test_helper( client, origin, origin_visits, tdata["branches"], tdata["releases"], tdata["root_dir_sha1"], tdata["content"], timestamp=tdata["visit"]["date"], ) visit_unix_ts = parse_timestamp(tdata["visit"]["date"]).timestamp() visit_unix_ts = int(visit_unix_ts) _origin_content_view_test_helper( client, origin, origin_visits, tdata["branches"], tdata["releases"], tdata["root_dir_sha1"], tdata["content"], timestamp=visit_unix_ts, ) tdata = _get_archive_data(0) _origin_content_view_test_helper( client, origin, origin_visits, tdata["branches"], tdata["releases"], tdata["root_dir_sha1"], tdata["content"], visit_id=tdata["visit"]["visit"], ) @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) visit_unix_ts = parse_timestamp(visit["date"]).timestamp() visit_unix_ts = int(visit_unix_ts) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, dir_content ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, dir_content, visit_id=visit["visit"], ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, dir_content, timestamp=visit_unix_ts, ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, dir_content, timestamp=visit["date"], ) origin = dict(origin) del origin["type"] _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, dir_content ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, dir_content, visit_id=visit["visit"], ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, dir_content, timestamp=visit_unix_ts, ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, dir_content, timestamp=visit["date"], ) @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) visit_unix_ts = parse_timestamp(visit["date"]).timestamp() visit_unix_ts = int(visit_unix_ts) 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, origin, origin_visits, branches, releases, root_dir_sha1, subdir_content, path=subdir_path, ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, subdir_content, path=subdir_path, visit_id=visit["visit"], ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, subdir_content, path=subdir_path, timestamp=visit_unix_ts, ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, subdir_content, path=subdir_path, timestamp=visit["date"], ) origin = dict(origin) del origin["type"] _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, subdir_content, path=subdir_path, ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, subdir_content, path=subdir_path, visit_id=visit["visit"], ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, subdir_content, path=subdir_path, timestamp=visit_unix_ts, ) _origin_directory_view_test_helper( client, origin, origin_visits, branches, releases, root_dir_sha1, subdir_content, path=subdir_path, timestamp=visit["date"], ) @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 = dict(origin) origin["type"] = None _origin_branches_test_helper(client, origin, snapshot_content) @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 = dict(origin) origin["type"] = None _origin_releases_test_helper(client, origin, snapshot_content) @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() new_origin = archive_data.origin_add([new_origin])[0] 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(new_origin["url"], visit_dates[0], type="git") archive_data.origin_visit_update( new_origin["url"], visit.visit, status="partial", snapshot=snp_dict["id"] ) url = reverse("browse-origin-directory", url_args={"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() new_origin = archive_data.origin_add([new_origin])[0] 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(new_origin["url"], visit_dates[0], type="git") archive_data.origin_visit_update( new_origin["url"], visit.visit, status="full", snapshot=snp_dict["id"] ) url = reverse( "browse-origin-directory", url_args={"origin_url": new_origin["url"]}, query_params={"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", url_args={"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 = [] url = reverse("browse-origin-directory", url_args={"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 @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", url_args={"origin_url": origin["url"]}, query_params={"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", url_args={"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 = [] url = reverse( "browse-origin-content", url_args={"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 @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", url_args={"origin_url": origin["url"], "path": "foo"}, query_params={"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_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, } url = reverse( "browse-origin-content", url_args={"origin_url": origin["url"], "path": "baz"} ) resp = client.get(url) assert resp.status_code == 200 assert_template_used(resp, "browse/content.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", url_args={"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", url_args={"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", url_args={"origin_url": "bar"}) + url = reverse("browse-origin-directory", url_args={"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(origin_with_releases()) def test_origin_release_browse(client, archive_data, origin): # for swh.web.browse.snapshot_context.get_snapshot_content to only return one branch config = get_config() snapshot_max_size = int(config["snapshot_content_max_size"]) config["snapshot_content_max_size"] = 1 try: 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"]) url = reverse( "browse-origin-directory", url_args={"origin_url": origin["url"]}, query_params={"release": release_data["name"]}, ) resp = client.get(url) assert resp.status_code == 200 assert_contains(resp, release_data["name"]) assert_contains(resp, release["target"]) finally: config["snapshot_content_max_size"] = snapshot_max_size @given(origin_with_releases()) def test_origin_release_browse_not_found(client, origin): invalid_release_name = "swh-foo-bar" url = reverse( "browse-origin-directory", url_args={"origin_url": origin["url"]}, query_params={"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") ) def _origin_content_view_test_helper( client, origin_info, origin_visits, origin_branches, origin_releases, root_dir_sha1, content, visit_id=None, timestamp=None, ): content_path = "/".join(content["path"].split("/")[1:]) url_args = {"origin_url": origin_info["url"], "path": content_path} if not visit_id: visit_id = origin_visits[-1]["visit"] query_params = {} if timestamp: url_args["timestamp"] = timestamp if visit_id: query_params["visit_id"] = visit_id url = reverse("browse-origin-content", url_args=url_args, 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, '' % 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 url_args["path"] if timestamp: url_args["timestamp"] = format_utc_iso_date( - parse_timestamp(timestamp).isoformat(), "%Y-%m-%dT%H:%M:%S" + parse_timestamp(timestamp).isoformat(), "%Y-%m-%dT%H:%M:%SZ" ) root_dir_url = reverse( "browse-origin-directory", url_args=url_args, query_params=query_params ) assert_contains(resp, '
  • ', count=len(path_info) + 1) assert_contains(resp, '%s' % (root_dir_url, root_dir_sha1[:7])) for p in path_info: url_args["path"] = p["path"] dir_url = reverse( "browse-origin-directory", url_args=url_args, query_params=query_params ) assert_contains(resp, '%s' % (dir_url, p["name"])) assert_contains(resp, "
  • %s
  • " % 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 "args" in url_args: del url_args["path"] origin_branches_url = reverse( "browse-origin-branches", url_args=url_args, query_params=query_params ) assert_contains( resp, 'Branches (%s)' % (origin_branches_url, len(origin_branches)), ) origin_releases_url = reverse( "browse-origin-releases", url_args=url_args, query_params=query_params ) assert_contains( resp, 'Releases (%s)' % (origin_releases_url, len(origin_releases)), ) assert_contains(resp, '
  • ', count=len(origin_branches)) url_args["path"] = content_path for branch in origin_branches: query_params["branch"] = branch["name"] root_dir_branch_url = reverse( "browse-origin-content", url_args=url_args, query_params=query_params ) assert_contains(resp, '' % root_dir_branch_url) assert_contains(resp, '
  • ', 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-content", url_args=url_args, query_params=query_params ) assert_contains(resp, '' % root_dir_release_url) url = reverse("browse-origin-content", url_args=url_args, query_params=query_params) resp = client.get(url) assert resp.status_code == 200 assert_template_used(resp, "browse/content.html") swh_cnt_id = get_swh_persistent_id("content", content["sha1_git"]) swh_cnt_id_url = reverse("browse-swh-id", url_args={"swh_id": swh_cnt_id}) assert_contains(resp, swh_cnt_id) assert_contains(resp, swh_cnt_id_url) assert_contains(resp, "swh-take-new-snapshot") def _origin_directory_view_test_helper( client, origin_info, origin_visits, origin_branches, origin_releases, root_directory_sha1, directory_entries, visit_id=None, timestamp=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: visit_id = origin_visits[-1]["visit"] url_args = {"origin_url": origin_info["url"]} query_params = {} if timestamp: url_args["timestamp"] = timestamp else: query_params["visit_id"] = visit_id if path: url_args["path"] = path url = reverse( "browse-origin-directory", url_args=url_args, 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, '', count=len(dirs)) assert_contains(resp, '', count=len(files)) if timestamp: url_args["timestamp"] = format_utc_iso_date( - parse_timestamp(timestamp).isoformat(), "%Y-%m-%dT%H:%M:%S" + parse_timestamp(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"]) dir_url_args = dict(url_args) dir_url_args["path"] = dir_path dir_url = reverse( "browse-origin-directory", url_args=dir_url_args, 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"]) file_url_args = dict(url_args) file_url_args["path"] = file_path file_url = reverse( "browse-origin-content", url_args=file_url_args, query_params=query_params ) assert_contains(resp, file_url) if "path" in url_args: del url_args["path"] root_dir_branch_url = reverse( "browse-origin-directory", url_args=url_args, query_params=query_params ) nb_bc_paths = 1 if path: nb_bc_paths = len(path.split("/")) + 1 assert_contains(resp, '
  • ', count=nb_bc_paths) assert_contains( resp, '%s' % (root_dir_branch_url, root_directory_sha1[:7]) ) origin_branches_url = reverse( "browse-origin-branches", url_args=url_args, query_params=query_params ) assert_contains( resp, 'Branches (%s)' % (origin_branches_url, len(origin_branches)), ) origin_releases_url = reverse( "browse-origin-releases", url_args=url_args, query_params=query_params ) nb_releases = len(origin_releases) if nb_releases > 0: assert_contains( resp, 'Releases (%s)' % (origin_releases_url, nb_releases) ) if path: url_args["path"] = path assert_contains(resp, '
  • ', count=len(origin_branches)) for branch in origin_branches: query_params["branch"] = branch["name"] root_dir_branch_url = reverse( "browse-origin-directory", url_args=url_args, query_params=query_params ) assert_contains(resp, '' % root_dir_branch_url) assert_contains(resp, '
  • ', 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", url_args=url_args, query_params=query_params ) assert_contains(resp, '' % root_dir_release_url) assert_contains(resp, "vault-cook-directory") assert_contains(resp, "vault-cook-revision") swh_dir_id = get_swh_persistent_id("directory", directory_entries[0]["dir_id"]) swh_dir_id_url = reverse("browse-swh-id", url_args={"swh_id": swh_dir_id}) assert_contains(resp, swh_dir_id) assert_contains(resp, swh_dir_id_url) assert_contains(resp, "swh-take-new-snapshot") def _origin_branches_test_helper(client, origin_info, origin_snapshot): url_args = {"origin_url": origin_info["url"]} url = reverse("browse-origin-branches", url_args=url_args) 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", url_args=url_args) assert_contains( resp, 'Branches (%s)' % (origin_branches_url, len(origin_branches)), ) origin_releases_url = reverse("browse-origin-releases", url_args=url_args) nb_releases = len(origin_releases) if nb_releases > 0: assert_contains( resp, 'Releases (%s)' % (origin_releases_url, nb_releases) ) assert_contains(resp, '' % escape(browse_branch_url)) browse_revision_url = reverse( "browse-revision", url_args={"sha1_git": branch["revision"]}, query_params={"origin": origin_info["url"]}, ) assert_contains(resp, '' % escape(browse_revision_url)) def _origin_releases_test_helper(client, origin_info, origin_snapshot): url_args = {"origin_url": origin_info["url"]} url = reverse("browse-origin-releases", url_args=url_args) 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", url_args=url_args) assert_contains( resp, 'Branches (%s)' % (origin_branches_url, len(origin_branches)), ) origin_releases_url = reverse("browse-origin-releases", url_args=url_args) nb_releases = len(origin_releases) if nb_releases > 0: assert_contains( resp, 'Releases (%s)' % (origin_releases_url, nb_releases) ) assert_contains(resp, '' % escape(browse_release_url)) assert_contains(resp, '' % escape(browse_revision_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), } new_origin = archive_data.origin_add([new_origin])[0] archive_data.snapshot_add([Snapshot.from_dict(snp_dict)]) visit = archive_data.origin_visit_add(new_origin["url"], visit_dates[0], type="git") archive_data.origin_visit_update( new_origin["url"], visit.visit, status="full", snapshot=snp_dict["id"] ) url = reverse("browse-origin-branches", url_args={"origin_url": new_origin["url"]}) resp = client.get(url) assert resp.status_code == 200 assert_template_used(resp, "browse/branches.html") assert_contains(resp, '