diff --git a/cypress/integration/persistent-identifiers.spec.js b/cypress/integration/persistent-identifiers.spec.js index 5327a2c2..f8071eb8 100644 --- a/cypress/integration/persistent-identifiers.spec.js +++ b/cypress/integration/persistent-identifiers.spec.js @@ -1,270 +1,270 @@ /** * Copyright (C) 2019-2020 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 */ let origin, originBadgeUrl, originBrowseUrl; let url, urlPrefix; let browsedObjectMetadata; let cntPid, cntPidWithOrigin, cntPidWithOriginAndLines; let dirPid, dirPidWithOrigin; let relPid, relPidWithOrigin; let revPid, revPidWithOrigin; let snpPid, snpPidWithOrigin; let testsData; const firstSelLine = 6; const lastSelLine = 12; describe('Persistent Identifiers Tests', function() { before(function() { origin = this.origin[1]; url = `${this.Urls.browse_origin_content()}?origin_url=${origin.url}&path=${origin.content[0].path}`; url = `${url}&release=${origin.release}#L${firstSelLine}-L${lastSelLine}`; originBadgeUrl = this.Urls.swh_badge('origin', origin.url); originBrowseUrl = `${this.Urls.browse_origin()}?origin_url=${origin.url}`; cy.visit(url).window().then(win => { urlPrefix = `${win.location.protocol}//${win.location.hostname}`; if (win.location.port) { urlPrefix += `:${win.location.port}`; } browsedObjectMetadata = win.swh.webapp.getBrowsedSwhObjectMetadata(); cntPid = `swh:1:cnt:${browsedObjectMetadata.sha1_git}`; cntPidWithOrigin = `${cntPid};origin=${origin.url}`; cntPidWithOriginAndLines = `${cntPidWithOrigin};lines=${firstSelLine}-${lastSelLine}`; dirPid = `swh:1:dir:${browsedObjectMetadata.directory}`; dirPidWithOrigin = `${dirPid};origin=${origin.url}`; revPid = `swh:1:rev:${browsedObjectMetadata.revision}`; revPidWithOrigin = `${revPid};origin=${origin.url}`; relPid = `swh:1:rel:${browsedObjectMetadata.release}`; relPidWithOrigin = `${relPid};origin=${origin.url}`; snpPid = `swh:1:snp:${browsedObjectMetadata.snapshot}`; snpPidWithOrigin = `${snpPid};origin=${origin.url}`; testsData = [ { 'objectType': 'content', 'objectPids': [cntPidWithOriginAndLines, cntPidWithOrigin, cntPid], 'badgeUrl': this.Urls.swh_badge('content', browsedObjectMetadata.sha1_git), 'badgePidUrl': this.Urls.swh_badge_pid(cntPidWithOriginAndLines), 'browseUrl': this.Urls.browse_swh_id(cntPidWithOriginAndLines) }, { 'objectType': 'directory', 'objectPids': [dirPidWithOrigin, dirPid], 'badgeUrl': this.Urls.swh_badge('directory', browsedObjectMetadata.directory), 'badgePidUrl': this.Urls.swh_badge_pid(dirPidWithOrigin), 'browseUrl': this.Urls.browse_swh_id(dirPidWithOrigin) }, { 'objectType': 'release', 'objectPids': [relPidWithOrigin, relPid], 'badgeUrl': this.Urls.swh_badge('release', browsedObjectMetadata.release), 'badgePidUrl': this.Urls.swh_badge_pid(relPidWithOrigin), 'browseUrl': this.Urls.browse_swh_id(relPidWithOrigin) }, { 'objectType': 'revision', 'objectPids': [revPidWithOrigin, revPid], 'badgeUrl': this.Urls.swh_badge('revision', browsedObjectMetadata.revision), 'badgePidUrl': this.Urls.swh_badge_pid(revPidWithOrigin), 'browseUrl': this.Urls.browse_swh_id(revPidWithOrigin) }, { 'objectType': 'snapshot', 'objectPids': [snpPidWithOrigin, snpPid], 'badgeUrl': this.Urls.swh_badge('snapshot', browsedObjectMetadata.snapshot), 'badgePidUrl': this.Urls.swh_badge_pid(snpPidWithOrigin), 'browseUrl': this.Urls.browse_swh_id(snpPidWithOrigin) } ]; }); }); beforeEach(function() { cy.visit(url); }); it('should open and close identifiers tab when clicking on handle', function() { cy.get('#swh-identifiers') .should('have.class', 'ui-slideouttab-ready'); cy.get('.ui-slideouttab-handle') .click(); cy.get('#swh-identifiers') .should('have.class', 'ui-slideouttab-open'); cy.get('.ui-slideouttab-handle') .click(); cy.get('#swh-identifiers') .should('not.have.class', 'ui-slideouttab-open'); }); it('should display identifiers with permalinks for browsed objects', function() { cy.get('.ui-slideouttab-handle') .click(); for (let td of testsData) { cy.get(`a[href="#swh-id-tab-${td.objectType}"]`) .click(); cy.get(`#swh-id-tab-${td.objectType}`) .should('be.visible'); cy.get(`#swh-id-tab-${td.objectType} .swh-id`) .contains(td.objectPids[0]) .should('have.attr', 'href', this.Urls.browse_swh_id(td.objectPids[0])); } }); it('should update content identifier metadata when toggling option checkboxes', function() { cy.get('.ui-slideouttab-handle') .click(); cy.get(`#swh-id-tab-content .swh-id`) .contains(cntPidWithOriginAndLines) .should('have.attr', 'href', this.Urls.browse_swh_id(cntPidWithOriginAndLines)); cy.get('#swh-id-tab-content .swh-id-option-lines') .click(); cy.get(`#swh-id-tab-content .swh-id`) .contains(cntPidWithOrigin) .should('have.attr', 'href', this.Urls.browse_swh_id(cntPidWithOrigin)); cy.get('#swh-id-tab-content .swh-id-option-origin') .click(); cy.get(`#swh-id-tab-content .swh-id`) .contains(cntPid) .should('have.attr', 'href', this.Urls.browse_swh_id(cntPid)); cy.get('#swh-id-tab-content .swh-id-option-origin') .click(); cy.get(`#swh-id-tab-content .swh-id`) .contains(cntPidWithOrigin) .should('have.attr', 'href', this.Urls.browse_swh_id(cntPidWithOrigin)); cy.get('#swh-id-tab-content .swh-id-option-lines') .click(); cy.get(`#swh-id-tab-content .swh-id`) .contains(cntPidWithOriginAndLines) .should('have.attr', 'href', this.Urls.browse_swh_id(cntPidWithOriginAndLines)); }); it('should update other object identifiers metadata when toggling option checkboxes', function() { cy.get('.ui-slideouttab-handle') .click(); for (let td of testsData) { // already tested if (td.objectType === 'content') continue; cy.get(`a[href="#swh-id-tab-${td.objectType}"]`) .click(); cy.get(`#swh-id-tab-${td.objectType} .swh-id`) .contains(td.objectPids[0]) .should('have.attr', 'href', this.Urls.browse_swh_id(td.objectPids[0])); cy.get(`#swh-id-tab-${td.objectType} .swh-id-option-origin`) .click(); cy.get(`#swh-id-tab-${td.objectType} .swh-id`) .contains(td.objectPids[1]) .should('have.attr', 'href', this.Urls.browse_swh_id(td.objectPids[1])); cy.get(`#swh-id-tab-${td.objectType} .swh-id-option-origin`) .click(); cy.get(`#swh-id-tab-${td.objectType} .swh-id`) .contains(td.objectPids[0]) .should('have.attr', 'href', this.Urls.browse_swh_id(td.objectPids[0])); } }); it('should display swh badges in identifiers tab for browsed objects', function() { cy.get('.ui-slideouttab-handle') .click(); const originBadgeUrl = this.Urls.swh_badge('origin', origin.url); for (let td of testsData) { cy.get(`a[href="#swh-id-tab-${td.objectType}"]`) .click(); cy.get(`#swh-id-tab-${td.objectType} .swh-badge-origin`) .should('have.attr', 'src', originBadgeUrl); cy.get(`#swh-id-tab-${td.objectType} .swh-badge-${td.objectType}`) .should('have.attr', 'src', td.badgeUrl); } }); it('should display badge integration info when clicking on it', function() { cy.get('.ui-slideouttab-handle') .click(); for (let td of testsData) { cy.get(`a[href="#swh-id-tab-${td.objectType}"]`) .click(); cy.get(`#swh-id-tab-${td.objectType} .swh-badge-origin`) .click() .wait(500); for (let badgeType of ['html', 'md', 'rst']) { cy.get(`.modal .swh-badge-${badgeType}`) .contains(`${urlPrefix}${originBrowseUrl}`) .contains(`${urlPrefix}${originBadgeUrl}`); } cy.get('.modal.show .close') .click() .wait(500); cy.get(`#swh-id-tab-${td.objectType} .swh-badge-${td.objectType}`) .click() .wait(500); for (let badgeType of ['html', 'md', 'rst']) { cy.get(`.modal .swh-badge-${badgeType}`) .contains(`${urlPrefix}${td.browseUrl}`) .contains(`${urlPrefix}${td.badgePidUrl}`); } cy.get('.modal.show .close') .click() .wait(500); } }); it('should be possible to retrieve SWHIDs context from JavaScript', function() { cy.window().then(win => { const swhIdsContext = win.swh.webapp.getSwhIdsContext(); for (let testData of testsData) { assert.isTrue(swhIdsContext.hasOwnProperty(testData.objectType)); - assert.equal(swhIdsContext[testData.objectType].swh_id, + assert.equal(swhIdsContext[testData.objectType].swhid, testData.objectPids.slice(-1)[0]); } }); }); }); diff --git a/swh/web/assets/src/bundles/webapp/webapp-utils.js b/swh/web/assets/src/bundles/webapp/webapp-utils.js index 9d56f3b5..d175f1d9 100644 --- a/swh/web/assets/src/bundles/webapp/webapp-utils.js +++ b/swh/web/assets/src/bundles/webapp/webapp-utils.js @@ -1,312 +1,315 @@ /** - * Copyright (C) 2018-2019 The Software Heritage developers + * Copyright (C) 2018-2020 The Software Heritage developers * See the AUTHORS file at the top-level directory of this distribution * License: GNU Affero General Public License version 3, or any later version * See top-level LICENSE file for more information */ import objectFitImages from 'object-fit-images'; import {selectText} from 'utils/functions'; import {BREAKPOINT_MD} from 'utils/constants'; let collapseSidebar = false; let previousSidebarState = localStorage.getItem('remember.lte.pushmenu'); if (previousSidebarState !== undefined) { collapseSidebar = previousSidebarState === 'sidebar-collapse'; } $(document).on('DOMContentLoaded', () => { // set state to collapsed on smaller devices if ($(window).width() < BREAKPOINT_MD) { collapseSidebar = true; } // restore previous sidebar state (collapsed/expanded) if (collapseSidebar) { // hack to avoid animated transition for collapsing sidebar // when loading a page let sidebarTransition = $('.main-sidebar, .main-sidebar:before').css('transition'); let sidebarEltsTransition = $('.sidebar .nav-link p, .main-sidebar .brand-text, .sidebar .user-panel .info').css('transition'); $('.main-sidebar, .main-sidebar:before').css('transition', 'none'); $('.sidebar .nav-link p, .main-sidebar .brand-text, .sidebar .user-panel .info').css('transition', 'none'); $('body').addClass('sidebar-collapse'); $('.swh-words-logo-swh').css('visibility', 'visible'); // restore transitions for user navigation setTimeout(() => { $('.main-sidebar, .main-sidebar:before').css('transition', sidebarTransition); $('.sidebar .nav-link p, .main-sidebar .brand-text, .sidebar .user-panel .info').css('transition', sidebarEltsTransition); }); } }); $(document).on('collapsed.lte.pushmenu', event => { if ($('body').width() >= BREAKPOINT_MD) { $('.swh-words-logo-swh').css('visibility', 'visible'); } }); $(document).on('shown.lte.pushmenu', event => { $('.swh-words-logo-swh').css('visibility', 'hidden'); }); function ensureNoFooterOverflow() { $('body').css('padding-bottom', $('footer').outerHeight() + 'px'); } $(document).ready(() => { // redirect to last browse page if any when clicking on the 'Browse' entry // in the sidebar $(`.swh-browse-link`).click(event => { let lastBrowsePage = sessionStorage.getItem('last-browse-page'); if (lastBrowsePage) { event.preventDefault(); window.location = lastBrowsePage; } }); const mainSideBar = $('.main-sidebar'); function updateSidebarState() { const body = $('body'); if (body.hasClass('sidebar-collapse') && !mainSideBar.hasClass('swh-sidebar-collapsed')) { mainSideBar.removeClass('swh-sidebar-expanded'); mainSideBar.addClass('swh-sidebar-collapsed'); $('.swh-words-logo-swh').css('visibility', 'visible'); } else if (!body.hasClass('sidebar-collapse') && !mainSideBar.hasClass('swh-sidebar-expanded')) { mainSideBar.removeClass('swh-sidebar-collapsed'); mainSideBar.addClass('swh-sidebar-expanded'); $('.swh-words-logo-swh').css('visibility', 'hidden'); } // ensure correct sidebar state when loading a page if (body.hasClass('hold-transition')) { setTimeout(() => { updateSidebarState(); }); } } // set sidebar state after collapse / expand animation mainSideBar.on('transitionend', evt => { updateSidebarState(); }); updateSidebarState(); // ensure footer do not overflow main content for mobile devices // or after resizing the browser window ensureNoFooterOverflow(); $(window).resize(function() { ensureNoFooterOverflow(); if ($('body').hasClass('sidebar-collapse') && $('body').width() >= BREAKPOINT_MD) { $('.swh-words-logo-swh').css('visibility', 'visible'); } }); // activate css polyfill 'object-fit: contain' in old browsers objectFitImages(); // reparent the modals to the top navigation div in order to be able // to display them $('.swh-browse-top-navigation').append($('.modal')); let selectedCode = null; function getCodeOrPreEltUnderPointer(e) { let elts = document.elementsFromPoint(e.clientX, e.clientY); for (let elt of elts) { if (elt.nodeName === 'CODE' || elt.nodeName === 'PRE') { return elt; } } return null; } // click handler to set focus on code block for copy $(document).click(e => { selectedCode = getCodeOrPreEltUnderPointer(e); }); function selectCode(event, selectedCode) { if (selectedCode) { let hljsLnCodeElts = $(selectedCode).find('.hljs-ln-code'); if (hljsLnCodeElts.length) { selectText(hljsLnCodeElts[0], hljsLnCodeElts[hljsLnCodeElts.length - 1]); } else { selectText(selectedCode.firstChild, selectedCode.lastChild); } event.preventDefault(); } } // select the whole text of focused code block when user // double clicks or hits Ctrl+A $(document).dblclick(e => { if ((e.ctrlKey || e.metaKey)) { selectCode(e, getCodeOrPreEltUnderPointer(e)); } }); $(document).keydown(e => { if ((e.ctrlKey || e.metaKey) && e.key === 'a') { selectCode(e, selectedCode); } }); // show/hide back-to-top button let scrollThreshold = 0; scrollThreshold += $('.swh-top-bar').height() || 0; scrollThreshold += $('.navbar').height() || 0; $(window).scroll(() => { if ($(window).scrollTop() > scrollThreshold) { $('#back-to-top').css('display', 'block'); } else { $('#back-to-top').css('display', 'none'); } }); }); export function initPage(page) { $(document).ready(() => { // set relevant sidebar link to page active $(`.swh-${page}-item`).addClass('active'); $(`.swh-${page}-link`).addClass('active'); // triggered when unloading the current page $(window).on('unload', () => { // backup current browse page if (page === 'browse') { sessionStorage.setItem('last-browse-page', window.location); } }); }); } export function initHomePage() { $(document).ready(() => { $('.swh-coverage-list').iFrameResize({heightCalculationMethod: 'taggedElement'}); fetch(Urls.stat_counters()) .then(response => response.json()) .then(data => { if (data.stat_counters.content) { $('#swh-contents-count').html(data.stat_counters.content.toLocaleString()); $('#swh-revisions-count').html(data.stat_counters.revision.toLocaleString()); $('#swh-origins-count').html(data.stat_counters.origin.toLocaleString()); $('#swh-directories-count').html(data.stat_counters.directory.toLocaleString()); $('#swh-persons-count').html(data.stat_counters.person.toLocaleString()); $('#swh-releases-count').html(data.stat_counters.release.toLocaleString()); } if (data.stat_counters_history.content) { swh.webapp.drawHistoryCounterGraph('#swh-contents-count-history', data.stat_counters_history.content); swh.webapp.drawHistoryCounterGraph('#swh-revisions-count-history', data.stat_counters_history.revision); swh.webapp.drawHistoryCounterGraph('#swh-origins-count-history', data.stat_counters_history.origin); } else { $('#swh-contents-count-history').hide(); $('#swh-revisions-count-history').hide(); $('#swh-origins-count-history').hide(); } }); }); initPage('home'); } export function showModalMessage(title, message) { $('#swh-web-modal-message .modal-title').text(title); $('#swh-web-modal-message .modal-content p').text(message); $('#swh-web-modal-message').modal('show'); } export function showModalConfirm(title, message, callback) { $('#swh-web-modal-confirm .modal-title').text(title); $('#swh-web-modal-confirm .modal-content p').text(message); $('#swh-web-modal-confirm #swh-web-modal-confirm-ok-btn').bind('click', () => { callback(); $('#swh-web-modal-confirm').modal('hide'); $('#swh-web-modal-confirm #swh-web-modal-confirm-ok-btn').unbind('click'); }); $('#swh-web-modal-confirm').modal('show'); } export function showModalHtml(title, html) { $('#swh-web-modal-html .modal-title').text(title); $('#swh-web-modal-html .modal-body').html(html); $('#swh-web-modal-html').modal('show'); } export function addJumpToPagePopoverToDataTable(dataTableElt) { dataTableElt.on('draw.dt', function() { $('.paginate_button.disabled').css('cursor', 'pointer'); $('.paginate_button.disabled').on('click', event => { const pageInfo = dataTableElt.page.info(); let content = ' / ${pageInfo.pages}`; $(event.target).popover({ 'title': 'Jump to page', 'content': content, 'html': true, 'placement': 'top', 'sanitizeFn': swh.webapp.filterXSS }); $(event.target).popover('show'); $('.jump-to-page').on('change', function() { $('.paginate_button.disabled').popover('hide'); const pageNumber = parseInt($(this).val()) - 1; dataTableElt.page(pageNumber).draw('page'); }); }); }); dataTableElt.on('preXhr.dt', () => { $('.paginate_button.disabled').popover('hide'); }); } let swhObjectIcons; export function setSwhObjectIcons(icons) { swhObjectIcons = icons; } export function getSwhObjectIcon(swhObjectType) { return swhObjectIcons[swhObjectType]; } let browsedSwhObjectMetadata = {}; export function setBrowsedSwhObjectMetadata(metadata) { browsedSwhObjectMetadata = metadata; } export function getBrowsedSwhObjectMetadata() { return browsedSwhObjectMetadata; } // This will contain a mapping between an archived object type // and its related SWHID metadata for each object reachable from // the current browse view. // SWHID metadata contain the following keys: // * object_type: type of archived object // * object_id: sha1 object identifier -// * swh_id: SWH persistent identifier without contextual info -// * swh_id_url: URL to resolve SWH persistent identifier without contextual info +// * swhid: SWH persistent identifier without contextual info +// * swhid_url: URL to resolve SWH persistent identifier without contextual info +// * context: object describing SWHID context +// * swhid_with_context: SWH persistent identifier with contextual info +// * swhid_with_context_url: URL to resolve SWH persistent identifier with contextual info let swhidsContext_ = {}; export function setSwhIdsContext(swhidsContext) { swhidsContext_ = {}; for (let swhidContext of swhidsContext) { swhidsContext_[swhidContext.object_type] = swhidContext; } } export function getSwhIdsContext() { return swhidsContext_; } diff --git a/swh/web/browse/snapshot_context.py b/swh/web/browse/snapshot_context.py index de1f3947..997ef36e 100644 --- a/swh/web/browse/snapshot_context.py +++ b/swh/web/browse/snapshot_context.py @@ -1,1421 +1,1429 @@ # Copyright (C) 2018-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information # 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, CONTENT, DIRECTORY, + REVISION, + RELEASE, + SNAPSHOT, ) 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, gen_snapshot_link, ) from swh.web.common import service, highlightjs from swh.web.common.exc import handle_view_exception, NotFoundExc, BadInputExc -from swh.web.common.identifiers import get_swh_persistent_ids +from swh.web.common.identifiers import get_swhids_info from swh.web.common.origin_visits import get_origin_visit from swh.web.common.typing import ( OriginInfo, SnapshotBranchInfo, SnapshotReleaseInfo, SnapshotContext, ContentMetadata, DirectoryMetadata, + SWHObjectInfo, ) 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: 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: A dict describing a snapshot as returned for instance by :func:`swh.web.common.service.lookup_snapshot` Returns: 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: 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] = 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 _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 _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: _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"]]: _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] = 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) _add_branch_info(branch_alias, revision) elif target_type == "release": release = service.lookup_release(target) _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: 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: 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: 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: 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: 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: 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: 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: 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 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 = {} query_params: Dict[str, Any] = {} origin_visits_url = None if origin_url: origin_info = service.lookup_origin({"url": origin_url}) visit_info = get_origin_visit(origin_info, timestamp, visit_id, snapshot_id) 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), formatted_date) ) # provided timestamp is not necessarily equals to the one # of the retrieved visit, so get the exact one in order # 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 ) query_params["origin_url"] = origin_info["url"] origin_visits_url = reverse("browse-origin-visits", query_params=query_params) if visit_id is not None: query_params["visit_id"] = visit_id if timestamp is not None: query_params["timestamp"] = format_utc_iso_date( timestamp, "%Y-%m-%dT%H:%M:%SZ" ) visit_url = reverse("browse-origin-directory", query_params=query_params) visit_info["url"] = visit_url branches_url = reverse("browse-origin-branches", query_params=query_params) releases_url = reverse("browse-origin-releases", query_params=query_params) else: assert snapshot_id is not None branches, releases = get_snapshot_content(snapshot_id) url_args = {"snapshot_id": snapshot_id} 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) if visit_info: timestamp = format_utc_iso_date(visit_info["date"]) if origin_info: browse_view_name = f"browse-origin-{browse_context}" else: browse_view_name = f"browse-snapshot-{browse_context}" release_id = None root_directory = None snapshot_total_size = sum(snapshot_sizes.values()) if path is not None: query_params["path"] = path if snapshot_total_size and revision_id is not None: revision = service.lookup_revision(revision_id) root_directory = revision["directory"] branches.append( 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_id) try: 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: if branch_name: query_params["branch"] = branch_name branch = _get_branch(branches, branch_name or "HEAD", snapshot_id) try: branch_name = branch["name"] revision_id = branch["revision"] 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_query_params = dict(query_params) branch_query_params.pop("release", None) if b["name"] != b["revision"]: branch_query_params.pop("revision", None) branch_query_params["branch"] = b["name"] b["url"] = reverse( browse_view_name, url_args=url_args, query_params=branch_query_params ) for r in releases: release_query_params = dict(query_params) release_query_params.pop("branch", None) release_query_params.pop("revision", None) release_query_params["release"] = r["name"] r["url"] = reverse( browse_view_name, url_args=url_args, query_params=release_query_params, ) 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 = dict(snapshot_context["query_params"]) root_directory = snapshot_context["root_directory"] 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: query_params.pop("path", None) breadcrumbs.append( { "name": root_directory[:7], "url": reverse( browse_view_name, url_args=url_args, query_params=query_params ), } ) for pi in path_info: query_params["path"] = pi["path"] breadcrumbs.append( { "name": pi["name"], "url": reverse( browse_view_name, url_args=url_args, query_params=query_params ), } ) return breadcrumbs def _check_origin_url(snapshot_id, origin_url): if snapshot_id is None and origin_url is None: raise BadInputExc("An origin URL must be provided as query parameter.") 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: _check_origin_url(snapshot_id, origin_url) 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_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) origin_info = snapshot_context["origin_info"] visit_info = snapshot_context["visit_info"] url_args = snapshot_context["url_args"] query_params = dict(snapshot_context["query_params"]) revision_id = snapshot_context["revision_id"] snapshot_id = snapshot_context["snapshot_id"] if origin_info: browse_view_name = "browse-origin-directory" else: browse_view_name = "browse-snapshot-directory" 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: query_params["path"] = path + d["name"] d["url"] = reverse( browse_view_name, url_args=url_args, query_params=query_params ) sum_file_sizes = 0 readmes = {} if origin_info: browse_view_name = "browse-origin-content" else: browse_view_name = "browse-snapshot-content" for f in files: query_params["path"] = path + f["name"] f["url"] = reverse( browse_view_name, url_args=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) 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_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) revision_found = True if sha1_git is None and revision_id is not None: try: service.lookup_revision(revision_id) except NotFoundExc: revision_found = False swh_objects = [ - {"type": "directory", "id": sha1_git}, - {"type": "revision", "id": revision_id}, - {"type": "snapshot", "id": snapshot_id}, + SWHObjectInfo(object_type=DIRECTORY, object_id=sha1_git), + SWHObjectInfo(object_type=REVISION, object_id=revision_id), + SWHObjectInfo(object_type=SNAPSHOT, object_id=snapshot_id), ] visit_date = None visit_type = None if visit_info: visit_date = format_utc_iso_date(visit_info["date"]) visit_type = visit_info["type"] release_id = snapshot_context["release_id"] browse_rel_link = None if release_id: - swh_objects.append({"type": "release", "id": release_id}) + swh_objects.append(SWHObjectInfo(object_type=RELEASE, object_id=release_id)) browse_rel_link = gen_release_link(release_id) dir_metadata = DirectoryMetadata( object_type=DIRECTORY, + object_id=sha1_git, directory=sha1_git, directory_url=browse_dir_link, nb_files=nb_files, nb_dirs=nb_dirs, sum_file_sizes=sum_file_sizes, + root_directory=root_directory, path=dir_path, revision=revision_id, revision_found=revision_found, revision_url=browse_rev_link, release=release_id, release_url=browse_rel_link, snapshot=snapshot_id, snapshot_url=browse_snp_link, origin_url=origin_url, visit_date=visit_date, visit_type=visit_type, ) vault_cooking = { "directory_context": True, "directory_id": sha1_git, "revision_context": True, "revision_id": revision_id, } - swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) + swhids_info = get_swhids_info(swh_objects, snapshot_context, dir_metadata) 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_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, + "swhids_info": swhids_info, }, ) 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: _check_origin_url(snapshot_id, origin_url) if path is None: raise BadInputExc("The path of a content must be given as query parameter.") 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_directory = snapshot_context["root_directory"] sha1_git = None query_string = None content_data = {} directory_id = None split_path = path.split("/") filename = split_path[-1] filepath = path[: -len(filename)] 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_directory, filepath) directory_id = dir_info["target"] else: directory_id = root_directory except Exception as exc: return handle_view_exception(request, exc) revision_id = snapshot_context["revision_id"] origin_info = snapshot_context["origin_info"] visit_info = snapshot_context["visit_info"] snapshot_id = snapshot_context["snapshot_id"] if content_data.get("raw_data") is not None: content_display_data = prepare_content_for_display( content_data["raw_data"], content_data["mimetype"], path ) content_data.update(content_display_data) # Override language with user-selected language if selected_language is not None: content_data["language"] = selected_language available_languages = None if content_data.get("mimetype") is not None and "text/" in content_data["mimetype"]: available_languages = highlightjs.get_supported_languages() 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_checksums = content_data.get("checksums", {}) swh_objects = [ - {"type": "content", "id": content_checksums.get("sha1_git")}, - {"type": "directory", "id": directory_id}, - {"type": "revision", "id": revision_id}, - {"type": "snapshot", "id": snapshot_id}, + SWHObjectInfo(object_type=CONTENT, object_id=content_checksums.get("sha1_git")), + SWHObjectInfo(object_type=DIRECTORY, object_id=directory_id), + SWHObjectInfo(object_type=REVISION, object_id=revision_id), + SWHObjectInfo(object_type=SNAPSHOT, object_id=snapshot_id), ] visit_date = None visit_type = None if visit_info: visit_date = format_utc_iso_date(visit_info["date"]) visit_type = visit_info["type"] release_id = snapshot_context["release_id"] browse_rel_link = None if release_id: - swh_objects.append({"type": "release", "id": release_id}) + swh_objects.append(SWHObjectInfo(object_type=RELEASE, object_id=release_id)) browse_rel_link = gen_release_link(release_id) content_metadata = ContentMetadata( object_type=CONTENT, + object_id=content_checksums.get("sha1_git"), sha1=content_checksums.get("sha1"), sha1_git=content_checksums.get("sha1_git"), sha256=content_checksums.get("sha256"), blake2s256=content_checksums.get("blake2s256"), content_url=browse_content_link, mimetype=content_data.get("mimetype"), encoding=content_data.get("encoding"), size=filesizeformat(content_data.get("length", 0)), language=content_data.get("language"), licenses=content_data.get("licenses"), + root_directory=root_directory, path=f"/{filepath}", filename=filename, directory=directory_id, directory_url=browse_dir_link, revision=revision_id, revision_url=browse_rev_link, release=release_id, release_url=browse_rel_link, snapshot=snapshot_id, snapshot_url=gen_snapshot_link(snapshot_id), origin_url=origin_url, visit_date=visit_date, visit_type=visit_type, ) - swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) + swhids_info = get_swhids_info(swh_objects, snapshot_context, content_metadata) 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_data.get("content_data"), "content_size": content_data.get("length"), "max_content_size": content_display_max_size, "filename": filename, "encoding": content_data.get("encoding"), "mimetype": content_data.get("mimetype"), "language": content_data.get("language"), "available_languages": available_languages, "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, + "swhids_info": swhids_info, "error_code": content_data.get("error_code"), "error_message": content_data.get("error_message"), "error_description": content_data.get("error_description"), }, status=content_data.get("error_code", 200), ) 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: _check_origin_url(snapshot_id, origin_url) 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) 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 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}, + SWHObjectInfo(object_type=REVISION, object_id=revision_id), + SWHObjectInfo(object_type=SNAPSHOT, object_id=snapshot_id), ] release_id = snapshot_context["release_id"] if release_id: - swh_objects.append({"type": "release", "id": release_id}) + swh_objects.append(SWHObjectInfo(object_type=RELEASE, object_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) + swhids_info = get_swhids_info(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, + "swhids_info": swhids_info, }, ) 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: _check_origin_url(snapshot_id, origin_url) 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 "" origin_info = snapshot_context["origin_info"] url_args = snapshot_context["url_args"] query_params = snapshot_context["query_params"] 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_url": 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 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: _check_origin_url(snapshot_id, origin_url) 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 "" 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_url": 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 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/content.py b/swh/web/browse/views/content.py index 83534d72..3ffe5f79 100644 --- a/swh/web/browse/views/content.py +++ b/swh/web/browse/views/content.py @@ -1,371 +1,376 @@ # 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 difflib import json from distutils.util import strtobool from django.http import HttpResponse from django.shortcuts import render from django.template.defaultfilters import filesizeformat import sentry_sdk from swh.model.hashutil import hash_to_hex from swh.model.identifiers import CONTENT from swh.web.browse.browseurls import browse_route from swh.web.browse.snapshot_context import get_snapshot_context from swh.web.browse.utils import ( request_content, prepare_content_for_display, content_display_max_size, gen_link, gen_directory_link, ) from swh.web.common import query, service, highlightjs from swh.web.common.exc import NotFoundExc, handle_view_exception -from swh.web.common.identifiers import get_swh_persistent_ids -from swh.web.common.typing import ContentMetadata +from swh.web.common.identifiers import get_swhids_info +from swh.web.common.typing import ContentMetadata, SWHObjectInfo from swh.web.common.utils import reverse, gen_path_info, swh_object_icons @browse_route( r"content/(?P[0-9a-z_:]*[0-9a-f]+.)/raw/", view_name="browse-content-raw", checksum_args=["query_string"], ) def content_raw(request, query_string): """Django view that produces a raw display of a content identified by its hash value. The url that points to it is :http:get:`/browse/content/[(algo_hash):](hash)/raw/` """ try: re_encode = bool(strtobool(request.GET.get("re_encode", "false"))) algo, checksum = query.parse_hash(query_string) checksum = hash_to_hex(checksum) content_data = request_content(query_string, max_size=None, re_encode=re_encode) except Exception as exc: return handle_view_exception(request, exc) filename = request.GET.get("filename", None) if not filename: filename = "%s_%s" % (algo, checksum) if ( content_data["mimetype"].startswith("text/") or content_data["mimetype"] == "inode/x-empty" ): response = HttpResponse(content_data["raw_data"], content_type="text/plain") response["Content-disposition"] = "filename=%s" % filename else: response = HttpResponse( content_data["raw_data"], content_type="application/octet-stream" ) response["Content-disposition"] = "attachment; filename=%s" % filename return response _auto_diff_size_limit = 20000 @browse_route( r"content/(?P.*)/diff/(?P.*)", view_name="diff-contents", ) def _contents_diff(request, from_query_string, to_query_string): """ Browse endpoint used to compute unified diffs between two contents. Diffs are generated only if the two contents are textual. By default, diffs whose size are greater than 20 kB will not be generated. To force the generation of large diffs, the 'force' boolean query parameter must be used. Args: request: input django http request from_query_string: a string of the form "[ALGO_HASH:]HASH" where optional ALGO_HASH can be either ``sha1``, ``sha1_git``, ``sha256``, or ``blake2s256`` (default to ``sha1``) and HASH the hexadecimal representation of the hash value identifying the first content to_query_string: same as above for identifying the second content Returns: A JSON object containing the unified diff. """ diff_data = {} content_from = None content_to = None content_from_size = 0 content_to_size = 0 content_from_lines = [] content_to_lines = [] force = request.GET.get("force", "false") path = request.GET.get("path", None) language = "nohighlight" force = bool(strtobool(force)) if from_query_string == to_query_string: diff_str = "File renamed without changes" else: try: text_diff = True if from_query_string: content_from = request_content(from_query_string, max_size=None) content_from_display_data = prepare_content_for_display( content_from["raw_data"], content_from["mimetype"], path ) language = content_from_display_data["language"] content_from_size = content_from["length"] if not ( content_from["mimetype"].startswith("text/") or content_from["mimetype"] == "inode/x-empty" ): text_diff = False if text_diff and to_query_string: content_to = request_content(to_query_string, max_size=None) content_to_display_data = prepare_content_for_display( content_to["raw_data"], content_to["mimetype"], path ) language = content_to_display_data["language"] content_to_size = content_to["length"] if not ( content_to["mimetype"].startswith("text/") or content_to["mimetype"] == "inode/x-empty" ): text_diff = False diff_size = abs(content_to_size - content_from_size) if not text_diff: diff_str = "Diffs are not generated for non textual content" language = "nohighlight" elif not force and diff_size > _auto_diff_size_limit: diff_str = "Large diffs are not automatically computed" language = "nohighlight" else: if content_from: content_from_lines = ( content_from["raw_data"].decode("utf-8").splitlines(True) ) if content_from_lines and content_from_lines[-1][-1] != "\n": content_from_lines[-1] += "[swh-no-nl-marker]\n" if content_to: content_to_lines = ( content_to["raw_data"].decode("utf-8").splitlines(True) ) if content_to_lines and content_to_lines[-1][-1] != "\n": content_to_lines[-1] += "[swh-no-nl-marker]\n" diff_lines = difflib.unified_diff(content_from_lines, content_to_lines) diff_str = "".join(list(diff_lines)[2:]) except Exception as exc: sentry_sdk.capture_exception(exc) diff_str = str(exc) diff_data["diff_str"] = diff_str diff_data["language"] = language diff_data_json = json.dumps(diff_data, separators=(",", ": ")) return HttpResponse(diff_data_json, content_type="application/json") @browse_route( r"content/(?P[0-9a-z_:]*[0-9a-f]+.)/", view_name="browse-content", checksum_args=["query_string"], ) def content_display(request, query_string): """Django view that produces an HTML display of a content identified by its hash value. The url that points to it is :http:get:`/browse/content/[(algo_hash):](hash)/` """ try: algo, checksum = query.parse_hash(query_string) checksum = hash_to_hex(checksum) content_data = request_content(query_string, raise_if_unavailable=False) origin_url = request.GET.get("origin_url", None) selected_language = request.GET.get("language", None) if not origin_url: origin_url = request.GET.get("origin", None) snapshot_context = None if origin_url: try: snapshot_context = get_snapshot_context(origin_url=origin_url) except NotFoundExc: raw_cnt_url = reverse( "browse-content", url_args={"query_string": query_string} ) error_message = ( "The Software Heritage archive has a content " "with the hash you provided but the origin " "mentioned in your request appears broken: %s. " "Please check the URL and try again.\n\n" "Nevertheless, you can still browse the content " "without origin information: %s" % (gen_link(origin_url), gen_link(raw_cnt_url)) ) raise NotFoundExc(error_message) if snapshot_context: snapshot_context["visit_info"] = None except Exception as exc: return handle_view_exception(request, exc) path = request.GET.get("path", None) content = None language = None mimetype = None if 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() root_dir = None filename = None path_info = None directory_id = None directory_url = None query_params = {"origin_url": origin_url} breadcrumbs = [] if path: split_path = path.split("/") root_dir = split_path[0] filename = split_path[-1] if root_dir != path: path = path.replace(root_dir + "/", "") path = path[: -len(filename)] path_info = gen_path_info(path) dir_url = reverse( "browse-directory", url_args={"sha1_git": root_dir}, query_params=query_params, ) breadcrumbs.append({"name": root_dir[:7], "url": dir_url}) for pi in path_info: query_params["path"] = pi["path"] dir_url = reverse( "browse-directory", url_args={"sha1_git": root_dir}, query_params=query_params, ) breadcrumbs.append({"name": pi["name"], "url": dir_url}) breadcrumbs.append({"name": filename, "url": None}) if path and root_dir != path: try: dir_info = service.lookup_directory_with_path(root_dir, path) directory_id = dir_info["target"] except Exception as exc: return handle_view_exception(request, exc) elif root_dir != path: directory_id = root_dir + else: + root_dir = None if directory_id: directory_url = gen_directory_link(directory_id) query_params = {"filename": filename} content_checksums = content_data["checksums"] content_url = reverse( "browse-content", url_args={"query_string": f'sha1_git:{content_checksums["sha1_git"]}'}, ) content_raw_url = reverse( "browse-content-raw", url_args={"query_string": query_string}, query_params=query_params, ) content_metadata = ContentMetadata( object_type=CONTENT, + object_id=content_checksums["sha1_git"], sha1=content_checksums["sha1"], sha1_git=content_checksums["sha1_git"], sha256=content_checksums["sha256"], blake2s256=content_checksums["blake2s256"], content_url=content_url, mimetype=content_data["mimetype"], encoding=content_data["encoding"], size=filesizeformat(content_data["length"]), language=content_data["language"], licenses=content_data["licenses"], - path=path, - filename=filename, + root_directory=root_dir, + path=f"/{path}" if path else "", + filename=filename or "", directory=directory_id, directory_url=directory_url, revision=None, release=None, snapshot=None, origin_url=origin_url, ) - swh_ids = get_swh_persistent_ids( - [{"type": "content", "id": content_checksums["sha1_git"]}] + swhids_info = get_swhids_info( + [SWHObjectInfo(object_type=CONTENT, object_id=content_checksums["sha1_git"])], + extra_context=content_metadata, ) heading = "Content - %s" % content_checksums["sha1_git"] if breadcrumbs: content_path = "/".join([bc["name"] for bc in breadcrumbs]) heading += " - %s" % content_path return render( request, "browse/content.html", { "heading": heading, - "swh_object_id": swh_ids[0]["swh_id"], + "swh_object_id": swhids_info[0]["swhid"], "swh_object_name": "Content", "swh_object_metadata": content_metadata, "content": content, "content_size": content_data["length"], "max_content_size": content_display_max_size, "filename": filename, "encoding": content_data["encoding"], "mimetype": mimetype, "language": language, "available_languages": available_languages, "breadcrumbs": breadcrumbs, "top_right_link": { "url": content_raw_url, "icon": swh_object_icons["content"], "text": "Raw File", }, "snapshot_context": snapshot_context, "vault_cooking": None, "show_actions_menu": True, - "swh_ids": swh_ids, + "swhids_info": swhids_info, "error_code": content_data["error_code"], "error_message": content_data["error_message"], "error_description": content_data["error_description"], }, status=content_data["error_code"], ) diff --git a/swh/web/browse/views/directory.py b/swh/web/browse/views/directory.py index f4aa4a6c..6da5d18d 100644 --- a/swh/web/browse/views/directory.py +++ b/swh/web/browse/views/directory.py @@ -1,237 +1,237 @@ # 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 os from django.http import HttpResponse from django.shortcuts import render, redirect from django.template.defaultfilters import filesizeformat import sentry_sdk from swh.model.identifiers import DIRECTORY from swh.web.browse.browseurls import browse_route from swh.web.browse.snapshot_context import get_snapshot_context from swh.web.browse.utils import ( get_directory_entries, get_readme_to_display, gen_link, ) from swh.web.common import service from swh.web.common.exc import handle_view_exception, NotFoundExc -from swh.web.common.identifiers import get_swh_persistent_ids -from swh.web.common.typing import DirectoryMetadata +from swh.web.common.identifiers import get_swhids_info +from swh.web.common.typing import DirectoryMetadata, SWHObjectInfo from swh.web.common.utils import reverse, gen_path_info def _directory_browse(request, sha1_git, path=None): root_sha1_git = sha1_git try: if path: dir_info = service.lookup_directory_with_path(sha1_git, path) sha1_git = dir_info["target"] dirs, files = get_directory_entries(sha1_git) origin_url = request.GET.get("origin_url", None) if not origin_url: origin_url = request.GET.get("origin", None) snapshot_context = None if origin_url: try: snapshot_context = get_snapshot_context(origin_url=origin_url) except NotFoundExc: raw_dir_url = reverse( "browse-directory", url_args={"sha1_git": sha1_git} ) error_message = ( "The Software Heritage archive has a directory " "with the hash you provided but the origin " "mentioned in your request appears broken: %s. " "Please check the URL and try again.\n\n" "Nevertheless, you can still browse the directory " "without origin information: %s" % (gen_link(origin_url), gen_link(raw_dir_url)) ) raise NotFoundExc(error_message) if snapshot_context: snapshot_context["visit_info"] = None except Exception as exc: return handle_view_exception(request, exc) path_info = gen_path_info(path) query_params = {"origin_url": origin_url} breadcrumbs = [] breadcrumbs.append( { "name": root_sha1_git[:7], "url": reverse( "browse-directory", url_args={"sha1_git": root_sha1_git}, query_params=query_params, ), } ) for pi in path_info: breadcrumbs.append( { "name": pi["name"], "url": reverse( "browse-directory", url_args={"sha1_git": root_sha1_git}, query_params={"path": pi["path"], **query_params}, ), } ) 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"]}, query_params=query_params, ) else: d["url"] = reverse( "browse-directory", url_args={"sha1_git": root_sha1_git}, query_params={"path": path + d["name"], **query_params}, ) sum_file_sizes = 0 readmes = {} for f in files: query_string = "sha1_git:" + f["target"] f["url"] = reverse( "browse-content", url_args={"query_string": query_string}, query_params={ "path": root_sha1_git + "/" + path + f["name"], "origin_url": origin_url, }, ) 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) sum_file_sizes = filesizeformat(sum_file_sizes) dir_metadata = DirectoryMetadata( object_type=DIRECTORY, + object_id=sha1_git, directory=sha1_git, nb_files=len(files), nb_dirs=len(dirs), sum_file_sizes=sum_file_sizes, - path=path or None, + root_directory=root_sha1_git, + path=f"/{path}" if path else "", revision=None, revision_found=None, release=None, snapshot=None, ) vault_cooking = { "directory_context": True, "directory_id": sha1_git, "revision_context": False, "revision_id": None, } - swh_objects = [{"type": "directory", "id": sha1_git}] + swh_objects = [SWHObjectInfo(object_type=DIRECTORY, object_id=sha1_git)] - swh_ids = get_swh_persistent_ids( - swh_objects=swh_objects, snapshot_context=snapshot_context - ) + swhids_info = get_swhids_info(swh_objects, snapshot_context, dir_metadata) heading = "Directory - %s" % sha1_git if breadcrumbs: dir_path = "/".join([bc["name"] for bc in breadcrumbs]) + "/" heading += " - %s" % dir_path return render( request, "browse/directory.html", { "heading": heading, - "swh_object_id": swh_ids[0]["swh_id"], + "swh_object_id": swhids_info[0]["swhid"], "swh_object_name": "Directory", "swh_object_metadata": dir_metadata, "dirs": dirs, "files": files, "breadcrumbs": breadcrumbs, "top_right_link": None, "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, + "swhids_info": swhids_info, }, ) @browse_route( r"directory/(?P[0-9a-f]+)/", view_name="browse-directory", checksum_args=["sha1_git"], ) def directory_browse(request, sha1_git): """Django view for browsing the content of a directory identified by its sha1_git value. The url that points to it is :http:get:`/browse/directory/(sha1_git)/` """ return _directory_browse(request, sha1_git, request.GET.get("path")) @browse_route( r"directory/(?P[0-9a-f]+)/(?P.+)/", view_name="browse-directory-legacy", checksum_args=["sha1_git"], ) def directory_browse_legacy(request, sha1_git, path): """Django view for browsing the content of a directory identified by its sha1_git value. The url that points to it is :http:get:`/browse/directory/(sha1_git)/(path)/` """ return _directory_browse(request, sha1_git, path) @browse_route( r"directory/resolve/content-path/(?P[0-9a-f]+)/", view_name="browse-directory-resolve-content-path", checksum_args=["sha1_git"], ) def _directory_resolve_content_path(request, sha1_git): """ Internal endpoint redirecting to data url for a specific file path relative to a root directory. """ try: path = os.path.normpath(request.GET.get("path")) if not path.startswith("../"): dir_info = service.lookup_directory_with_path(sha1_git, path) if dir_info["type"] == "file": sha1 = dir_info["checksums"]["sha1"] data_url = reverse( "browse-content-raw", url_args={"query_string": sha1} ) return redirect(data_url) except Exception as exc: sentry_sdk.capture_exception(exc) return HttpResponse(status=404) diff --git a/swh/web/browse/views/release.py b/swh/web/browse/views/release.py index 9e2e29db..bbd4cda7 100644 --- a/swh/web/browse/views/release.py +++ b/swh/web/browse/views/release.py @@ -1,235 +1,236 @@ # 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 from django.shortcuts import render import sentry_sdk from swh.model.identifiers import CONTENT, DIRECTORY, RELEASE, REVISION, SNAPSHOT from swh.web.browse.browseurls import browse_route from swh.web.browse.snapshot_context import get_snapshot_context from swh.web.browse.utils import ( gen_revision_link, gen_link, gen_snapshot_link, gen_directory_link, gen_content_link, gen_release_link, gen_person_mail_link, ) from swh.web.common import service from swh.web.common.exc import NotFoundExc, handle_view_exception -from swh.web.common.identifiers import get_swh_persistent_ids -from swh.web.common.typing import ReleaseMetadata +from swh.web.common.identifiers import get_swhids_info +from swh.web.common.typing import ReleaseMetadata, SWHObjectInfo from swh.web.common.utils import reverse, format_utc_iso_date @browse_route( r"release/(?P[0-9a-f]+)/", view_name="browse-release", checksum_args=["sha1_git"], ) def release_browse(request, sha1_git): """ Django view that produces an HTML display of a release identified by its id. The url that points to it is :http:get:`/browse/release/(sha1_git)/`. """ try: release = service.lookup_release(sha1_git) snapshot_context = {} origin_info = None snapshot_id = request.GET.get("snapshot_id", None) origin_url = request.GET.get("origin_url", None) if not origin_url: origin_url = request.GET.get("origin", None) timestamp = request.GET.get("timestamp", None) visit_id = request.GET.get("visit_id", None) if origin_url: try: snapshot_context = get_snapshot_context( snapshot_id, origin_url, timestamp, visit_id ) except NotFoundExc: raw_rel_url = reverse("browse-release", url_args={"sha1_git": sha1_git}) error_message = ( "The Software Heritage archive has a release " "with the hash you provided but the origin " "mentioned in your request appears broken: %s. " "Please check the URL and try again.\n\n" "Nevertheless, you can still browse the release " "without origin information: %s" % (gen_link(origin_url), gen_link(raw_rel_url)) ) raise NotFoundExc(error_message) origin_info = snapshot_context["origin_info"] elif snapshot_id: snapshot_context = get_snapshot_context(snapshot_id) except Exception as exc: return handle_view_exception(request, exc) target_url = None if release["target_type"] == REVISION: target_url = gen_revision_link(release["target"]) elif release["target_type"] == CONTENT: target_url = gen_content_link(release["target"]) elif release["target_type"] == DIRECTORY: target_url = gen_directory_link(release["target"]) elif release["target_type"] == RELEASE: target_url = gen_release_link(release["target"]) snapshot_id = None browse_snp_link = None if snapshot_context: snapshot_id = snapshot_context["snapshot_id"] browse_snp_link = gen_snapshot_link(snapshot_id) release_metadata = ReleaseMetadata( object_type=RELEASE, + object_id=sha1_git, release=sha1_git, release_url=gen_release_link(release["id"]), author=release["author"]["fullname"] if release["author"] else "None", author_url=gen_person_mail_link(release["author"]) if release["author"] else "None", date=format_utc_iso_date(release["date"]), name=release["name"], synthetic=release["synthetic"], target=release["target"], target_type=release["target_type"], target_url=target_url, snapshot=snapshot_context.get("snapshot_id", None), snapshot_url=browse_snp_link, origin_url=origin_url, ) release_note_lines = [] if release["message"]: release_note_lines = release["message"].split("\n") vault_cooking = None rev_directory = None target_link = None if release["target_type"] == REVISION: target_link = gen_revision_link( release["target"], snapshot_context=snapshot_context, link_text=None, link_attrs=None, ) try: revision = service.lookup_revision(release["target"]) rev_directory = revision["directory"] vault_cooking = { "directory_context": True, "directory_id": rev_directory, "revision_context": True, "revision_id": release["target"], } except Exception as exc: sentry_sdk.capture_exception(exc) elif release["target_type"] == DIRECTORY: target_link = gen_directory_link( release["target"], snapshot_context=snapshot_context, link_text=None, link_attrs=None, ) try: # check directory exists service.lookup_directory(release["target"]) vault_cooking = { "directory_context": True, "directory_id": release["target"], "revision_context": False, "revision_id": None, } except Exception as exc: sentry_sdk.capture_exception(exc) elif release["target_type"] == CONTENT: target_link = gen_content_link( release["target"], snapshot_context=snapshot_context, link_text=None, link_attrs=None, ) elif release["target_type"] == RELEASE: target_link = gen_release_link( release["target"], snapshot_context=snapshot_context, link_text=None, link_attrs=None, ) rev_directory_url = None if rev_directory is not None: if origin_info: rev_directory_url = reverse( "browse-origin-directory", query_params={ "origin_url": origin_info["url"], "release": release["name"], }, ) elif snapshot_id: rev_directory_url = reverse( "browse-snapshot-directory", url_args={"snapshot_id": snapshot_id}, query_params={"release": release["name"]}, ) else: rev_directory_url = reverse( "browse-directory", url_args={"sha1_git": rev_directory} ) directory_link = None if rev_directory_url is not None: directory_link = gen_link(rev_directory_url, rev_directory) release["directory_link"] = directory_link release["target_link"] = target_link - swh_objects = [{"type": RELEASE, "id": sha1_git}] + swh_objects = [SWHObjectInfo(object_type=RELEASE, object_id=sha1_git)] if snapshot_context: snapshot_id = snapshot_context["snapshot_id"] if snapshot_id: - swh_objects.append({"type": SNAPSHOT, "id": snapshot_id}) + swh_objects.append(SWHObjectInfo(object_type=SNAPSHOT, object_id=snapshot_id)) - swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) + swhids_info = get_swhids_info(swh_objects, snapshot_context) note_header = "None" if len(release_note_lines) > 0: note_header = release_note_lines[0] release["note_header"] = note_header release["note_body"] = "\n".join(release_note_lines[1:]) heading = "Release - %s" % release["name"] if snapshot_context: context_found = "snapshot: %s" % snapshot_context["snapshot_id"] if origin_info: context_found = "origin: %s" % origin_info["url"] heading += " - %s" % context_found return render( request, "browse/release.html", { "heading": heading, - "swh_object_id": swh_ids[0]["swh_id"], + "swh_object_id": swhids_info[0]["swhid"], "swh_object_name": "Release", "swh_object_metadata": release_metadata, "release": release, "snapshot_context": snapshot_context, "show_actions_menu": True, "breadcrumbs": None, "vault_cooking": vault_cooking, "top_right_link": None, - "swh_ids": swh_ids, + "swhids_info": swhids_info, }, ) diff --git a/swh/web/browse/views/revision.py b/swh/web/browse/views/revision.py index 68ded5c1..04570d19 100644 --- a/swh/web/browse/views/revision.py +++ b/swh/web/browse/views/revision.py @@ -1,577 +1,591 @@ # 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 hashlib import json import textwrap from django.http import HttpResponse from django.shortcuts import render from django.template.defaultfilters import filesizeformat from django.utils.safestring import mark_safe -from swh.model.identifiers import persistent_identifier, REVISION +from swh.model.identifiers import ( + persistent_identifier, + CONTENT, + DIRECTORY, + REVISION, + SNAPSHOT, +) from swh.web.browse.browseurls import browse_route from swh.web.browse.snapshot_context import get_snapshot_context from swh.web.browse.utils import ( gen_link, gen_revision_link, gen_revision_url, get_revision_log_url, get_directory_entries, gen_directory_link, request_content, prepare_content_for_display, content_display_max_size, gen_snapshot_link, get_readme_to_display, format_log_entries, gen_person_mail_link, ) from swh.web.common import service from swh.web.common.exc import NotFoundExc, handle_view_exception -from swh.web.common.identifiers import get_swh_persistent_ids -from swh.web.common.typing import RevisionMetadata +from swh.web.common.identifiers import get_swhids_info +from swh.web.common.typing import RevisionMetadata, SWHObjectInfo from swh.web.common.utils import ( reverse, format_utc_iso_date, gen_path_info, swh_object_icons, ) def _gen_content_url(revision, query_string, path, snapshot_context): if snapshot_context: query_params = snapshot_context["query_params"] query_params["path"] = path query_params["revision"] = revision["id"] content_url = reverse("browse-origin-content", query_params=query_params) else: content_path = "%s/%s" % (revision["directory"], path) content_url = reverse( "browse-content", url_args={"query_string": query_string}, query_params={"path": content_path}, ) return content_url def _gen_diff_link(idx, diff_anchor, link_text): if idx < _max_displayed_file_diffs: return gen_link(diff_anchor, link_text) else: return link_text # TODO: put in conf _max_displayed_file_diffs = 1000 def _gen_revision_changes_list(revision, changes, snapshot_context): """ Returns a HTML string describing the file changes introduced in a revision. As this string will be displayed in the browse revision view, links to adequate file diffs are also generated. Args: revision (str): hexadecimal representation of a revision identifier changes (list): list of file changes in the revision snapshot_context (dict): optional origin context used to reverse the content urls Returns: A string to insert in a revision HTML view. """ changes_msg = [] for i, change in enumerate(changes): hasher = hashlib.sha1() from_query_string = "" to_query_string = "" diff_id = "diff-" if change["from"]: from_query_string = "sha1_git:" + change["from"]["target"] diff_id += change["from"]["target"] + "-" + change["from_path"] diff_id += "-" if change["to"]: to_query_string = "sha1_git:" + change["to"]["target"] diff_id += change["to"]["target"] + change["to_path"] change["path"] = change["to_path"] or change["from_path"] url_args = { "from_query_string": from_query_string, "to_query_string": to_query_string, } query_params = {"path": change["path"]} change["diff_url"] = reverse( "diff-contents", url_args=url_args, query_params=query_params ) hasher.update(diff_id.encode("utf-8")) diff_id = hasher.hexdigest() change["id"] = diff_id panel_diff_link = "#panel_" + diff_id if change["type"] == "modify": change["content_url"] = _gen_content_url( revision, to_query_string, change["to_path"], snapshot_context ) changes_msg.append( "modified: %s" % _gen_diff_link(i, panel_diff_link, change["to_path"]) ) elif change["type"] == "insert": change["content_url"] = _gen_content_url( revision, to_query_string, change["to_path"], snapshot_context ) changes_msg.append( "new file: %s" % _gen_diff_link(i, panel_diff_link, change["to_path"]) ) elif change["type"] == "delete": parent = service.lookup_revision(revision["parents"][0]) change["content_url"] = _gen_content_url( parent, from_query_string, change["from_path"], snapshot_context ) changes_msg.append( "deleted: %s" % _gen_diff_link(i, panel_diff_link, change["from_path"]) ) elif change["type"] == "rename": change["content_url"] = _gen_content_url( revision, to_query_string, change["to_path"], snapshot_context ) link_text = change["from_path"] + " → " + change["to_path"] changes_msg.append( "renamed: %s" % _gen_diff_link(i, panel_diff_link, link_text) ) if not changes: changes_msg.append("No changes") return mark_safe("\n".join(changes_msg)) @browse_route( r"revision/(?P[0-9a-f]+)/diff/", view_name="diff-revision", checksum_args=["sha1_git"], ) def _revision_diff(request, sha1_git): """ Browse internal endpoint to compute revision diff """ try: revision = service.lookup_revision(sha1_git) snapshot_context = None origin_url = request.GET.get("origin_url", None) if not origin_url: origin_url = request.GET.get("origin", None) timestamp = request.GET.get("timestamp", None) visit_id = request.GET.get("visit_id", None) if origin_url: snapshot_context = get_snapshot_context( origin_url=origin_url, timestamp=timestamp, visit_id=visit_id ) except Exception as exc: return handle_view_exception(request, exc) changes = service.diff_revision(sha1_git) changes_msg = _gen_revision_changes_list(revision, changes, snapshot_context) diff_data = { "total_nb_changes": len(changes), "changes": changes[:_max_displayed_file_diffs], "changes_msg": changes_msg, } diff_data_json = json.dumps(diff_data, separators=(",", ": ")) return HttpResponse(diff_data_json, content_type="application/json") NB_LOG_ENTRIES = 100 @browse_route( r"revision/(?P[0-9a-f]+)/log/", view_name="browse-revision-log", checksum_args=["sha1_git"], ) def revision_log_browse(request, sha1_git): """ Django view that produces an HTML display of the history log for a revision identified by its id. The url that points to it is :http:get:`/browse/revision/(sha1_git)/log/` """ try: per_page = int(request.GET.get("per_page", NB_LOG_ENTRIES)) offset = int(request.GET.get("offset", 0)) revs_ordering = request.GET.get("revs_ordering", "committer_date") session_key = "rev_%s_log_ordering_%s" % (sha1_git, 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, sha1_git, 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) revs_ordering = request.GET.get("revs_ordering", "") prev_log_url = None if len(rev_log) > offset + per_page: prev_log_url = reverse( "browse-revision-log", url_args={"sha1_git": sha1_git}, query_params={ "per_page": per_page, "offset": offset + per_page, "revs_ordering": revs_ordering, }, ) next_log_url = None if offset != 0: next_log_url = reverse( "browse-revision-log", url_args={"sha1_git": sha1_git}, query_params={ "per_page": per_page, "offset": offset - per_page, "revs_ordering": revs_ordering, }, ) revision_log_data = format_log_entries(revision_log, per_page) swh_rev_id = persistent_identifier("revision", sha1_git) return render( request, "browse/revision-log.html", { "heading": "Revision history", "swh_object_id": swh_rev_id, "swh_object_name": "Revisions history", "swh_object_metadata": None, "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": None, "vault_cooking": None, "show_actions_menu": True, - "swh_ids": None, + "swhids_info": None, }, ) @browse_route( r"revision/(?P[0-9a-f]+)/", view_name="browse-revision", checksum_args=["sha1_git"], ) def revision_browse(request, sha1_git): """ Django view that produces an HTML display of a revision identified by its id. The url that points to it is :http:get:`/browse/revision/(sha1_git)/`. """ try: revision = service.lookup_revision(sha1_git) origin_info = None snapshot_context = None origin_url = request.GET.get("origin_url", None) if not origin_url: origin_url = request.GET.get("origin", None) timestamp = request.GET.get("timestamp", None) visit_id = request.GET.get("visit_id", None) snapshot_id = request.GET.get("snapshot_id", None) path = request.GET.get("path", None) dir_id = None dirs, files = None, None content_data = {} if origin_url: try: snapshot_context = get_snapshot_context( origin_url=origin_url, timestamp=timestamp, visit_id=visit_id ) except NotFoundExc: raw_rev_url = reverse( "browse-revision", url_args={"sha1_git": sha1_git} ) error_message = ( "The Software Heritage archive has a revision " "with the hash you provided but the origin " "mentioned in your request appears broken: %s. " "Please check the URL and try again.\n\n" "Nevertheless, you can still browse the revision " "without origin information: %s" % (gen_link(origin_url), gen_link(raw_rev_url)) ) raise NotFoundExc(error_message) origin_info = snapshot_context["origin_info"] snapshot_id = snapshot_context["snapshot_id"] elif snapshot_id: snapshot_context = get_snapshot_context(snapshot_id) if path: file_info = service.lookup_directory_with_path(revision["directory"], path) if file_info["type"] == "dir": dir_id = file_info["target"] else: query_string = "sha1_git:" + file_info["target"] content_data = request_content(query_string, raise_if_unavailable=False) else: dir_id = revision["directory"] if dir_id: path = "" if path is None else (path + "/") dirs, files = get_directory_entries(dir_id) except Exception as exc: return handle_view_exception(request, exc) revision_metadata = RevisionMetadata( object_type=REVISION, + object_id=sha1_git, revision=sha1_git, revision_url=gen_revision_link(sha1_git), author=revision["author"]["fullname"] if revision["author"] else "None", author_url=gen_person_mail_link(revision["author"]) if revision["author"] else "None", committer=revision["committer"]["fullname"] if revision["committer"] else "None", committer_url=gen_person_mail_link(revision["committer"]) if revision["committer"] else "None", committer_date=format_utc_iso_date(revision["committer_date"]), date=format_utc_iso_date(revision["date"]), directory=revision["directory"], directory_url=gen_directory_link(revision["directory"]), merge=revision["merge"], metadata=json.dumps( revision["metadata"], sort_keys=True, indent=4, separators=(",", ": ") ), parents=revision["parents"], synthetic=revision["synthetic"], type=revision["type"], snapshot=snapshot_id, snapshot_url=gen_snapshot_link(snapshot_id) if snapshot_id else None, origin_url=origin_url, ) message_lines = ["None"] if revision["message"]: message_lines = revision["message"].split("\n") parents = [] for p in revision["parents"]: parent_url = gen_revision_url(p, snapshot_context) parents.append({"id": p, "url": parent_url}) path_info = gen_path_info(path) query_params = { "snapshot_id": snapshot_id, "origin_url": origin_url, "timestamp": timestamp, "visit_id": visit_id, } breadcrumbs = [] breadcrumbs.append( { "name": revision["directory"][:7], "url": reverse( "browse-revision", url_args={"sha1_git": sha1_git}, query_params=query_params, ), } ) for pi in path_info: query_params["path"] = pi["path"] breadcrumbs.append( { "name": pi["name"], "url": reverse( "browse-revision", url_args={"sha1_git": sha1_git}, query_params=query_params, ), } ) vault_cooking = { "directory_context": False, "directory_id": None, "revision_context": True, "revision_id": sha1_git, } - swh_objects = [{"type": "revision", "id": sha1_git}] + swh_objects = [SWHObjectInfo(object_type=REVISION, object_id=sha1_git)] content = None content_size = None filename = None mimetype = None language = None readme_name = None readme_url = None readme_html = None readmes = {} error_code = 200 error_message = "" error_description = "" + extra_context = dict(revision_metadata) + if path: + extra_context["path"] = f"/{path}" + if content_data: breadcrumbs[-1]["url"] = None content_size = content_data["length"] mimetype = content_data["mimetype"] if content_data["raw_data"]: 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"] query_params = {} if path: filename = path_info[-1]["name"] query_params["filename"] = filename + extra_context["filename"] = filename top_right_link = { "url": reverse( "browse-content-raw", url_args={"query_string": query_string}, query_params=query_params, ), "icon": swh_object_icons["content"], "text": "Raw File", } - swh_objects.append({"type": "content", "id": file_info["target"]}) + swh_objects.append( + SWHObjectInfo(object_type=CONTENT, object_id=file_info["target"]) + ) error_code = content_data["error_code"] error_message = content_data["error_message"] error_description = content_data["error_description"] else: for d in dirs: if d["type"] == "rev": d["url"] = reverse( "browse-revision", url_args={"sha1_git": d["target"]} ) else: query_params["path"] = path + d["name"] d["url"] = reverse( "browse-revision", url_args={"sha1_git": sha1_git}, query_params=query_params, ) for f in files: query_params["path"] = path + f["name"] f["url"] = reverse( "browse-revision", url_args={"sha1_git": sha1_git}, query_params=query_params, ) if f["length"] is not None: 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) top_right_link = { "url": get_revision_log_url(sha1_git, snapshot_context), "icon": swh_object_icons["revisions history"], "text": "History", } vault_cooking["directory_context"] = True vault_cooking["directory_id"] = dir_id - swh_objects.append({"type": "directory", "id": dir_id}) + swh_objects.append(SWHObjectInfo(object_type=DIRECTORY, object_id=dir_id)) diff_revision_url = reverse( "diff-revision", url_args={"sha1_git": sha1_git}, query_params={ "origin_url": origin_url, "timestamp": timestamp, "visit_id": visit_id, }, ) if snapshot_id: - swh_objects.append({"type": "snapshot", "id": snapshot_id}) + swh_objects.append(SWHObjectInfo(object_type=SNAPSHOT, object_id=snapshot_id)) - swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) + swhids_info = get_swhids_info(swh_objects, snapshot_context, extra_context) heading = "Revision - %s - %s" % ( sha1_git[:7], textwrap.shorten(message_lines[0], width=70), ) if snapshot_context: context_found = "snapshot: %s" % snapshot_context["snapshot_id"] if origin_info: context_found = "origin: %s" % origin_info["url"] heading += " - %s" % context_found return render( request, "browse/revision.html", { "heading": heading, - "swh_object_id": swh_ids[0]["swh_id"], + "swh_object_id": swhids_info[0]["swhid"], "swh_object_name": "Revision", "swh_object_metadata": revision_metadata, "message_header": message_lines[0], "message_body": "\n".join(message_lines[1:]), "parents": parents, "snapshot_context": snapshot_context, "dirs": dirs, "files": files, "content": content, "content_size": content_size, "max_content_size": content_display_max_size, "filename": filename, "encoding": content_data.get("encoding"), "mimetype": mimetype, "language": language, "readme_name": readme_name, "readme_url": readme_url, "readme_html": readme_html, "breadcrumbs": breadcrumbs, "top_right_link": top_right_link, "vault_cooking": vault_cooking, "diff_revision_url": diff_revision_url, "show_actions_menu": True, - "swh_ids": swh_ids, + "swhids_info": swhids_info, "error_code": error_code, "error_message": error_message, "error_description": error_description, }, status=error_code, ) diff --git a/swh/web/common/identifiers.py b/swh/web/common/identifiers.py index b7dbcc60..fb0a016b 100644 --- a/swh/web/common/identifiers.py +++ b/swh/web/common/identifiers.py @@ -1,246 +1,320 @@ # 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 Dict, Iterable, List, Optional +from urllib.parse import quote +from typing import Any, Dict, Iterable, List, Optional from typing_extensions import TypedDict from django.http import QueryDict from swh.model.exceptions import ValidationError from swh.model.hashutil import hash_to_bytes from swh.model.identifiers import ( persistent_identifier, parse_persistent_identifier, CONTENT, DIRECTORY, ORIGIN, RELEASE, REVISION, SNAPSHOT, PersistentId, ) from swh.web.common.exc import BadInputExc -from swh.web.common.typing import QueryParameters -from swh.web.common.utils import swh_object_icons, reverse +from swh.web.common.typing import ( + QueryParameters, + SnapshotContext, + SWHObjectInfo, + SWHIDInfo, + SWHIDContext, +) +from swh.web.common.utils import reverse def get_swh_persistent_id( - object_type: str, object_id: str, scheme_version: int = 1 + object_type: str, + object_id: str, + scheme_version: int = 1, + metadata: SWHIDContext = {}, ) -> str: """ Returns the persistent identifier for a swh object based on: * the object type * the object id * the swh identifiers scheme version Args: object_type: the swh object type (content/directory/release/revision/snapshot) object_id: the swh object id (hexadecimal representation of its hash value) scheme_version: the scheme version of the swh persistent identifiers Returns: the swh object persistent identifier Raises: BadInputExc: if the provided parameters do not enable to generate a valid identifier """ try: - swh_id = persistent_identifier(object_type, object_id, scheme_version) + swh_id = persistent_identifier(object_type, object_id, scheme_version, metadata) except ValidationError as e: raise BadInputExc( "Invalid object (%s) for swh persistent id. %s" % (object_id, e) ) else: return swh_id ResolvedPersistentId = TypedDict( "ResolvedPersistentId", {"swh_id_parsed": PersistentId, "browse_url": Optional[str]} ) def resolve_swh_persistent_id( swh_id: str, query_params: Optional[QueryParameters] = None ) -> ResolvedPersistentId: """ Try to resolve a Software Heritage persistent id into an url for browsing the targeted object. Args: swh_id: a Software Heritage persistent identifier query_params: optional dict filled with query parameters to append to the browse url Returns: a dict with the following keys: * **swh_id_parsed**: the parsed identifier * **browse_url**: the url for browsing the targeted object """ swh_id_parsed = get_persistent_identifier(swh_id) object_type = swh_id_parsed.object_type object_id = swh_id_parsed.object_id browse_url = None query_dict = QueryDict("", mutable=True) if query_params and len(query_params) > 0: for k in sorted(query_params.keys()): query_dict[k] = query_params[k] if "origin" in swh_id_parsed.metadata: query_dict["origin_url"] = swh_id_parsed.metadata["origin"] if object_type == CONTENT: query_string = "sha1_git:" + object_id fragment = "" if "lines" in swh_id_parsed.metadata: lines = swh_id_parsed.metadata["lines"].split("-") fragment += "#L" + lines[0] if len(lines) > 1: fragment += "-L" + lines[1] browse_url = ( reverse( "browse-content", url_args={"query_string": query_string}, query_params=query_dict, ) + fragment ) elif object_type == DIRECTORY: browse_url = reverse( "browse-directory", url_args={"sha1_git": object_id}, query_params=query_dict, ) elif object_type == RELEASE: browse_url = reverse( "browse-release", url_args={"sha1_git": object_id}, query_params=query_dict ) elif object_type == REVISION: browse_url = reverse( "browse-revision", url_args={"sha1_git": object_id}, query_params=query_dict ) elif object_type == SNAPSHOT: browse_url = reverse( "browse-snapshot", url_args={"snapshot_id": object_id}, query_params=query_dict, ) elif object_type == ORIGIN: raise BadInputExc( ( "Origin PIDs (Persistent Identifiers) are not " "publicly resolvable because they are for " "internal usage only" ) ) return {"swh_id_parsed": swh_id_parsed, "browse_url": browse_url} def get_persistent_identifier(persistent_id: str) -> PersistentId: """Check if a persistent identifier is valid. Args: persistent_id: A string representing a Software Heritage persistent identifier. Raises: BadInputExc: if the provided persistent identifier can not be parsed. Return: A persistent identifier object. """ try: pid_object = parse_persistent_identifier(persistent_id) except ValidationError as ve: raise BadInputExc("Error when parsing identifier: %s" % " ".join(ve.messages)) else: return pid_object def group_swh_persistent_identifiers( persistent_ids: Iterable[PersistentId], ) -> Dict[str, List[bytes]]: """ Groups many Software Heritage persistent identifiers into a dictionary depending on their type. Args: persistent_ids: an iterable of Software Heritage persistent identifier objects Returns: A dictionary with: keys: persistent identifier types values: persistent identifiers id """ pids_by_type: Dict[str, List[bytes]] = { CONTENT: [], DIRECTORY: [], REVISION: [], RELEASE: [], SNAPSHOT: [], } for pid in persistent_ids: obj_id = pid.object_id obj_type = pid.object_type pids_by_type[obj_type].append(hash_to_bytes(obj_id)) return pids_by_type -def get_swh_persistent_ids(swh_objects, snapshot_context=None): +def get_swhids_info( + swh_objects: Iterable[SWHObjectInfo], + snapshot_context: Optional[SnapshotContext] = None, + extra_context: Optional[Dict[str, Any]] = None, +) -> List[SWHIDInfo]: """ Returns a list of dict containing info related to persistent identifiers of swh objects. Args: - swh_objects (list): a list of dict with the following keys: - - * type: swh object type - (content/directory/release/revision/snapshot) - * id: swh object id - - snapshot_context (dict): optional parameter describing the snapshot in - which the object has been found + swh_objects: an iterable of dict describing archived objects + snapshot_context: optional dict parameter describing the snapshot in + which the objects have been found + extra_context: optional dict filled with extra contextual info about + the objects Returns: - list: a list of dict with the following keys: - * object_type: the swh object type - (content/directory/release/revision/snapshot) - * object_icon: the swh object icon to use in HTML views - * swh_id: the computed swh object persistent identifier - * swh_id_url: the url resolving the persistent identifier - * show_options: boolean indicating if the persistent id options - must be displayed in persistent ids HTML view + a list of dict containing persistent identifiers info + """ - swh_ids = [] + swhids_info = [] for swh_object in swh_objects: - if not swh_object["id"]: + if not swh_object["object_id"]: + swhids_info.append( + SWHIDInfo( + object_type=swh_object["object_type"], + object_id="", + swhid="", + swhid_url="", + context={}, + swhid_with_context=None, + swhid_with_context_url=None, + ) + ) continue - swh_id = get_swh_persistent_id(swh_object["type"], swh_object["id"]) - show_options = swh_object["type"] == "content" or ( - snapshot_context and snapshot_context["origin_info"] is not None - ) + object_type = swh_object["object_type"] + object_id = swh_object["object_id"] + swhid_context: SWHIDContext = {} + if snapshot_context: + if snapshot_context["origin_info"] is not None: + swhid_context["origin"] = quote( + snapshot_context["origin_info"]["url"], safe="/?:@&" + ) + if object_type != SNAPSHOT: + swhid_context["visit"] = get_swh_persistent_id( + SNAPSHOT, snapshot_context["snapshot_id"] + ) + if object_type not in (RELEASE, REVISION, SNAPSHOT): + if snapshot_context["release_id"] is not None: + swhid_context["anchor"] = get_swh_persistent_id( + RELEASE, snapshot_context["release_id"] + ) + elif snapshot_context["revision_id"] is not None: + swhid_context["anchor"] = get_swh_persistent_id( + REVISION, snapshot_context["revision_id"] + ) + + if object_type in (CONTENT, DIRECTORY): + if ( + extra_context + and "revision" in extra_context + and extra_context["revision"] + ): + swhid_context["anchor"] = get_swh_persistent_id( + REVISION, extra_context["revision"] + ) + elif ( + extra_context + and "root_directory" in extra_context + and extra_context["root_directory"] + and ( + object_type != DIRECTORY + or extra_context["root_directory"] != object_id + ) + ): + swhid_context["anchor"] = get_swh_persistent_id( + DIRECTORY, extra_context["root_directory"] + ) + path = None + if extra_context and "path" in extra_context: + path = extra_context["path"] + if "filename" in extra_context and object_type == CONTENT: + path += extra_context["filename"] + if path: + swhid_context["path"] = quote(path, safe="/?:@&") + + swhid = get_swh_persistent_id(object_type, object_id) + swhid_url = reverse("browse-swh-id", url_args={"swh_id": swhid}) + + swhid_with_context = None + swhid_with_context_url = None + if swhid_context: + swhid_with_context = get_swh_persistent_id( + object_type, object_id, metadata=swhid_context + ) + swhid_with_context_url = reverse( + "browse-swh-id", url_args={"swh_id": swhid_with_context} + ) - object_icon = swh_object_icons[swh_object["type"]] - - swh_ids.append( - { - "object_type": swh_object["type"], - "object_id": swh_object["id"], - "object_icon": object_icon, - "swh_id": swh_id, - "swh_id_url": reverse("browse-swh-id", url_args={"swh_id": swh_id}), - "show_options": show_options, - } + swhids_info.append( + SWHIDInfo( + object_type=object_type, + object_id=object_id, + swhid=swhid, + swhid_url=swhid_url, + context=swhid_context, + swhid_with_context=swhid_with_context, + swhid_with_context_url=swhid_with_context_url, + ) ) - return swh_ids + return swhids_info diff --git a/swh/web/common/typing.py b/swh/web/common/typing.py index b2a7c07e..51b78556 100644 --- a/swh/web/common/typing.py +++ b/swh/web/common/typing.py @@ -1,184 +1,206 @@ # 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, 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""" -class SWHObjectMetadata(TypedDict, total=False): +class SWHObjectInfo(TypedDict): object_type: str + object_id: str + + +class SWHIDContext(TypedDict, total=False): + origin: str + anchor: str + visit: str + path: str + lines: str + + +class SWHIDInfo(SWHObjectInfo): + swhid: str + swhid_url: str + context: SWHIDContext + swhid_with_context: Optional[str] + swhid_with_context_url: Optional[str] + + +class SWHObjectInfoMetadata(TypedDict, total=False): origin_url: Optional[str] visit_date: Optional[str] visit_type: Optional[str] directory_url: Optional[str] revision_url: Optional[str] release_url: Optional[str] snapshot_url: Optional[str] -class ContentMetadata(SWHObjectMetadata): +class ContentMetadata(SWHObjectInfo, SWHObjectInfoMetadata): sha1: str sha1_git: str sha256: str blake2s256: str content_url: str mimetype: str encoding: str size: str language: str licenses: str path: Optional[str] filename: Optional[str] directory: Optional[str] + root_directory: Optional[str] revision: Optional[str] release: Optional[str] snapshot: Optional[str] -class DirectoryMetadata(SWHObjectMetadata): +class DirectoryMetadata(SWHObjectInfo, SWHObjectInfoMetadata): directory: str nb_files: int nb_dirs: int sum_file_sizes: str + root_directory: Optional[str] path: str revision: Optional[str] revision_found: Optional[bool] release: Optional[str] snapshot: Optional[str] -class ReleaseMetadata(SWHObjectMetadata): +class ReleaseMetadata(SWHObjectInfo, SWHObjectInfoMetadata): release: str author: str author_url: str date: str name: str synthetic: bool target: str target_type: str target_url: str snapshot: Optional[str] -class RevisionMetadata(SWHObjectMetadata): +class RevisionMetadata(SWHObjectInfo, SWHObjectInfoMetadata): revision: str author: str author_url: str committer: str committer_url: str date: str committer_date: str directory: str merge: bool metadata: str parents: List[str] synthetic: bool type: str snapshot: Optional[str] diff --git a/swh/web/templates/includes/show-swh-ids.html b/swh/web/templates/includes/show-swh-ids.html index b81e61da..94686846 100644 --- a/swh/web/templates/includes/show-swh-ids.html +++ b/swh/web/templates/includes/show-swh-ids.html @@ -1,106 +1,108 @@ {% comment %} -Copyright (C) 2017-2019 The Software Heritage developers +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 {% endcomment %} {% load swh_templatetags %} -{% if swh_ids %} +{% if swhids_info %}