diff --git a/debian/control b/debian/control index eeef307a..8c90b8a2 100644 --- a/debian/control +++ b/debian/control @@ -1,42 +1,42 @@ Source: swh-web Maintainer: Software Heritage developers Section: python Priority: optional Build-Depends: curl, debhelper (>= 9), dh-python (>= 2), python3-all, python3-bs4, python3-django (>= 1.10.7~), python3-djangorestframework (>= 3.4.0~), python3-django-webpack-loader, python3-django-js-reverse, python3-docutils, python3-htmlmin, python3-magic (>= 0.3.0~), python3-lxml, python3-nose, python3-pygments, python3-pypandoc, python3-setuptools, python3-sphinx, python3-sphinxcontrib.httpdomain, python3-yaml, python3-swh.core (>= 0.0.40~), python3-swh.model (>= 0.0.25~), - python3-swh.storage (>= 0.0.101~), + python3-swh.storage (>= 0.0.104~), python3-swh.indexer.storage (>= 0.0.52~), python3-swh.vault (>= 0.0.20~) Standards-Version: 3.9.6 Homepage: https://forge.softwareheritage.org/diffusion/DWUI/ Package: python3-swh.web Architecture: all Depends: python3-swh.core (>= 0.0.40~), python3-swh.model (>= 0.0.25~), - python3-swh.storage (>= 0.0.101~), + python3-swh.storage (>= 0.0.104~), python3-swh.indexer.storage (>= 0.0.52~), python3-swh.vault (>= 0.0.20~), ${misc:Depends}, ${python3:Depends} Description: Software Heritage Web Applications diff --git a/requirements-swh.txt b/requirements-swh.txt index b0a32103..6a9cafe3 100644 --- a/requirements-swh.txt +++ b/requirements-swh.txt @@ -1,5 +1,5 @@ swh.core >= 0.0.40 swh.model >= 0.0.25 -swh.storage >= 0.0.101 +swh.storage >= 0.0.104 swh.vault >= 0.0.20 swh.indexer >= 0.0.52 diff --git a/swh/web/api/views/origin.py b/swh/web/api/views/origin.py index db13c3c2..ca100671 100644 --- a/swh/web/api/views/origin.py +++ b/swh/web/api/views/origin.py @@ -1,337 +1,341 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information from distutils.util import strtobool from swh.web.common import service from swh.web.common.utils import ( reverse, get_origin_visits ) from swh.web.api import utils from swh.web.api.apidoc import api_doc from swh.web.api.apiurls import api_route from swh.web.api.views.utils import api_lookup def _enrich_origin(origin): if 'id' in origin: o = origin.copy() o['origin_visits_url'] = \ reverse('origin-visits', kwargs={'origin_id': origin['id']}) return o return origin @api_route(r'/origin/(?P[0-9]+)/', 'origin') @api_route(r'/origin/(?P[a-z]+)/url/(?P.+)', 'origin') @api_doc('/origin/') def api_origin(request, origin_id=None, origin_type=None, origin_url=None): """ .. http:get:: /api/1/origin/(origin_id)/ Get information about a software origin. :param int origin_id: a SWH origin identifier :>json number id: the origin unique identifier :>json string origin_visits_url: link to in order to get information about the SWH visits for that origin :>json string type: the type of software origin (*git*, *svn*, *hg*, *deb*, *ftp*, ...) :>json string url: the origin canonical url :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Example:** .. parsed-literal:: :swh_web_api:`origin/1/` .. http:get:: /api/1/origin/(origin_type)/url/(origin_url)/ Get information about a software origin. :param string origin_type: the origin type (*git*, *svn*, *hg*, *deb*, *ftp*, ...) :param string origin_url: the origin url :>json number id: the origin unique identifier :>json string origin_visits_url: link to in order to get information about the SWH visits for that origin :>json string type: the type of software origin (*git*, *svn*, *hg*, *deb*, *ftp*, ...) :>json string url: the origin canonical url :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Example:** .. parsed-literal:: :swh_web_api:`origin/git/url/https://github.com/python/cpython/` """ # noqa ori_dict = { 'id': origin_id, 'type': origin_type, 'url': origin_url } ori_dict = {k: v for k, v in ori_dict.items() if ori_dict[k]} if 'id' in ori_dict: error_msg = 'Origin with id %s not found.' % ori_dict['id'] else: error_msg = 'Origin with type %s and URL %s not found' % ( ori_dict['type'], ori_dict['url']) return api_lookup( service.lookup_origin, ori_dict, notfound_msg=error_msg, enrich_fn=_enrich_origin) @api_route(r'/origin/search/(?P.+)/', 'origin-search') @api_doc('/origin/search/') def api_origin_search(request, url_pattern): """ .. http:get:: /api/1/origin/search/(url_pattern)/ Search for software origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. :param string url_pattern: a string pattern or a regular expression :query int offset: the number of found origins to skip before returning results :query int limit: the maximum number of found origins to return :query boolean regexp: if true, consider provided pattern as a regular expression and search origins whose urls match it + :query boolean with_visit: if true, only return origins with at least one visit + by Software heritage :>jsonarr number id: the origin unique identifier :>jsonarr string origin_visits_url: link to in order to get information about the SWH visits for that origin :>jsonarr string type: the type of software origin (*git*, *svn*, *hg*, *deb*, *ftp*, ...) :>jsonarr string url: the origin canonical url :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error **Example:** .. parsed-literal:: :swh_web_api:`origin/search/python/?limit=2` """ # noqa result = {} offset = int(request.query_params.get('offset', '0')) limit = int(request.query_params.get('limit', '70')) regexp = request.query_params.get('regexp', 'false') + with_visit = request.query_params.get('with_visit', 'false') results = api_lookup(service.search_origin, url_pattern, offset, limit, - bool(strtobool(regexp)), enrich_fn=_enrich_origin) + bool(strtobool(regexp)), bool(strtobool(with_visit)), + enrich_fn=_enrich_origin) nb_results = len(results) if nb_results == limit: query_params = {} query_params['offset'] = offset + limit query_params['limit'] = limit query_params['regexp'] = regexp result['headers'] = { 'link-next': reverse('origin-search', kwargs={'url_pattern': url_pattern}, query_params=query_params) } result.update({ 'results': results }) return result @api_route(r'/origin/(?P[0-9]+)/visits/', 'origin-visits') @api_doc('/origin/visits/') def api_origin_visits(request, origin_id): """ .. http:get:: /api/1/origin/(origin_id)/visits/ Get information about all visits of a software origin. Visits are returned sorted in descending order according to their date. :param int origin_id: a SWH origin identifier :query int per_page: specify the number of visits to list, for pagination purposes :query int last_visit: visit to start listing from, for pagination purposes :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request :resheader Link: indicates that a subsequent result page is available and contains the url pointing to it :>jsonarr string date: ISO representation of the visit date (in UTC) :>jsonarr number id: the unique identifier of the origin :>jsonarr string origin_visit_url: link to :http:get:`/api/1/origin/(origin_id)/visit/(visit_id)/` in order to get information about the visit :>jsonarr string snapshot: the snapshot identifier of the visit :>jsonarr string snapshot_url: link to :http:get:`/api/1/snapshot/(snapshot_id)/` in order to get information about the snapshot of the visit :>jsonarr string status: status of the visit (either *full*, *partial* or *ongoing*) :>jsonarr number visit: the unique identifier of the visit **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Example:** .. parsed-literal:: :swh_web_api:`origin/1/visits/` """ # noqa result = {} per_page = int(request.query_params.get('per_page', '10')) last_visit = request.query_params.get('last_visit') if last_visit: last_visit = int(last_visit) def _lookup_origin_visits( origin_id, last_visit=last_visit, per_page=per_page): all_visits = get_origin_visits({'id': origin_id}) all_visits.reverse() visits = [] if not last_visit: visits = all_visits[:per_page] else: for i, v in enumerate(all_visits): if v['visit'] == last_visit: visits = all_visits[i+1:i+1+per_page] break for v in visits: yield v def _enrich_origin_visit(origin_visit): ov = origin_visit.copy() ov['origin_visit_url'] = reverse('origin-visit', kwargs={'origin_id': origin_id, 'visit_id': ov['visit']}) snapshot = ov['snapshot'] if snapshot: ov['snapshot_url'] = reverse('snapshot', kwargs={'snapshot_id': snapshot}) else: ov['snapshot_url'] = None return ov results = api_lookup(_lookup_origin_visits, origin_id, notfound_msg='No origin {} found'.format(origin_id), enrich_fn=_enrich_origin_visit) if results: nb_results = len(results) if nb_results == per_page: new_last_visit = results[-1]['visit'] query_params = {} query_params['last_visit'] = new_last_visit if request.query_params.get('per_page'): query_params['per_page'] = per_page result['headers'] = { 'link-next': reverse('origin-visits', kwargs={'origin_id': origin_id}, query_params=query_params) } result.update({ 'results': results }) return result @api_route(r'/origin/(?P[0-9]+)/visit/(?P[0-9]+)/', 'origin-visit') @api_doc('/origin/visit/') def api_origin_visit(request, origin_id, visit_id): """ .. http:get:: /api/1/origin/(origin_id)/visit/(visit_id)/ Get information about a specific visit of a software origin. :param int origin_id: a SWH origin identifier :param int visit_id: a visit identifier :reqheader Accept: the requested response content type, either *application/json* (default) or *application/yaml* :resheader Content-Type: this depends on :http:header:`Accept` header of request :>json string date: ISO representation of the visit date (in UTC) :>json object occurrences: object containing all branches associated to the origin found during the visit, for each of them the associated SWH target type and id are given but also a link to get information about that target :>json number origin: the origin unique identifier :>json string origin_url: link to get information about the origin :>jsonarr string snapshot: the snapshot identifier of the visit :>jsonarr string snapshot_url: link to :http:get:`/api/1/snapshot/(snapshot_id)/` in order to get information about the snapshot of the visit :>json string status: status of the visit (either *full*, *partial* or *ongoing*) :>json number visit: the unique identifier of the visit **Allowed HTTP Methods:** :http:method:`get`, :http:method:`head`, :http:method:`options` :statuscode 200: no error :statuscode 404: requested origin or visit can not be found in the SWH archive **Example:** .. parsed-literal:: :swh_web_api:`origin/1500/visit/1/` """ # noqa def _enrich_origin_visit(origin_visit): ov = origin_visit.copy() ov['origin_url'] = reverse('origin', kwargs={'origin_id': ov['origin']}) snapshot = ov['snapshot'] if snapshot: ov['snapshot_url'] = reverse('snapshot', kwargs={'snapshot_id': snapshot}) else: ov['snapshot_url'] = None # TODO: remove that piece of code once the snapshot migration # is totally effective in storage (no more occurrences) if 'occurrences' in ov: ov['occurrences'] = { k: utils.enrich_object(v) if v else None for k, v in ov['occurrences'].items() } return ov return api_lookup( service.lookup_origin_visit, origin_id, visit_id, notfound_msg=('No visit {} for origin {} found' .format(visit_id, origin_id)), enrich_fn=_enrich_origin_visit) diff --git a/swh/web/assets/src/bundles/browse/origin-search.js b/swh/web/assets/src/bundles/browse/origin-search.js index 2dc6fcbc..2631a2b9 100644 --- a/swh/web/assets/src/bundles/browse/origin-search.js +++ b/swh/web/assets/src/bundles/browse/origin-search.js @@ -1,205 +1,206 @@ /** * Copyright (C) 2018 The Software Heritage developers * See the AUTHORS file at the top-level directory of this distribution * License: GNU Affero General Public License version 3, or any later version * See top-level LICENSE file for more information */ import {heapsPermute} from 'utils/heaps-permute'; import {handleFetchError} from 'utils/functions'; let originPatterns; let perPage = 20; let limit = perPage * 10; let offset = 0; let currentData = null; let inSearch = false; function fixTableRowsStyle() { setTimeout(() => { $('#origin-search-results tbody tr').removeAttr('style'); }); } function clearOriginSearchResultsTable() { $('#origin-search-results tbody tr').remove(); } function populateOriginSearchResultsTable(data, offset) { let localOffset = offset % limit; if (data.length > 0) { $('#swh-origin-search-results').show(); $('#swh-no-result').hide(); clearOriginSearchResultsTable(); let table = $('#origin-search-results tbody'); for (let i = localOffset; i < localOffset + perPage && i < data.length; ++i) { let elem = data[i]; let tableRow = ''; tableRow += '' + elem.type + ''; let browseUrl = Urls.browse_origin(elem.url); tableRow += '' + browseUrl + ''; tableRow += ''; tableRow += ''; table.append(tableRow); // get async latest visit snapshot and update visit status icon let latestSnapshotUrl = Urls.browse_origin_latest_snapshot(elem.id); fetch(latestSnapshotUrl) .then(response => response.json()) .then(data => { let originId = elem.id; $('#visit-status-origin-' + originId).children().remove(); if (data) { $('#visit-status-origin-' + originId).append(''); } else { $('#visit-status-origin-' + originId).append(''); } }); } fixTableRowsStyle(); } else { $('#swh-origin-search-results').hide(); $('#swh-no-result').text('No origins matching the search criteria were found.'); $('#swh-no-result').show(); } if (data.length - localOffset < perPage || (data.length < limit && (localOffset + perPage) === data.length)) { $('#origins-next-results-button').addClass('disabled'); } else { $('#origins-next-results-button').removeClass('disabled'); } if (offset > 0) { $('#origins-prev-results-button').removeClass('disabled'); } else { $('#origins-prev-results-button').addClass('disabled'); } inSearch = false; if (typeof Storage !== 'undefined') { sessionStorage.setItem('last-swh-origin-search-offset', offset); } setTimeout(() => { window.scrollTo(0, 0); }); } function escapeStringRegexp(str) { let matchOperatorsRe = /[|\\{}()[\]^$+*?.]/g; return str.replace(matchOperatorsRe, '\\\\\\$&'); } function searchOrigins(patterns, limit, searchOffset, offset) { originPatterns = patterns; let patternsArray = patterns.trim().replace(/\s+/g, ' ').split(' '); for (let i = 0; i < patternsArray.length; ++i) { patternsArray[i] = escapeStringRegexp(patternsArray[i]); } let patternsPermut = []; heapsPermute(patternsArray, p => patternsPermut.push(p.join('.*'))); let regex = patternsPermut.join('|'); - let searchUrl = Urls.browse_origin_search(regex) + `?limit=${limit}&offset=${searchOffset}®exp=true`; + let withVisit = $('#swh-search-origins-with-visit').prop('checked'); + let searchUrl = Urls.browse_origin_search(regex) + `?limit=${limit}&offset=${searchOffset}®exp=true&with_visit=${withVisit}`; clearOriginSearchResultsTable(); $('.swh-loading').addClass('show'); fetch(searchUrl) .then(handleFetchError) .then(response => response.json()) .then(data => { currentData = data; if (typeof Storage !== 'undefined') { sessionStorage.setItem('last-swh-origin-url-patterns', patterns); sessionStorage.setItem('last-swh-origin-search-results', JSON.stringify(data)); sessionStorage.setItem('last-swh-origin-search-offset', offset); } $('.swh-loading').removeClass('show'); populateOriginSearchResultsTable(data, offset); }) .catch(() => { $('.swh-loading').removeClass('show'); inSearch = false; }); } export function initOriginSearch() { $(document).ready(() => { if (typeof Storage !== 'undefined') { originPatterns = sessionStorage.getItem('last-swh-origin-url-patterns'); let data = sessionStorage.getItem('last-swh-origin-search-results'); offset = sessionStorage.getItem('last-swh-origin-search-offset'); if (data) { $('#origins-url-patterns').val(originPatterns); offset = parseInt(offset); currentData = JSON.parse(data); populateOriginSearchResultsTable(currentData, offset); } } $('#search_origins').submit(event => { event.preventDefault(); $('#swh-no-result').hide(); let patterns = $('#origins-url-patterns').val(); offset = 0; inSearch = true; // first try to resolve a swh persistent identifier let resolvePidUrl = Urls.resolve_swh_pid(patterns); fetch(resolvePidUrl) .then(handleFetchError) .then(response => response.json()) .then(data => { // pid has been successfully resolved, // so redirect to browse page window.location = data.browse_url; }) .catch(response => { // pid resolving failed if (patterns.startsWith('swh:')) { // display a useful error message if the input // looks like a swh pid response.json().then(data => { $('#swh-origin-search-results').hide(); $('.swh-search-pagination').hide(); $('#swh-no-result').text(data.reason); $('#swh-no-result').show(); }); } else { // otherwise, proceed with origins search $('#swh-origin-search-results').show(); $('.swh-search-pagination').show(); searchOrigins(patterns, limit, offset, offset); } }); }); $('#origins-next-results-button').click(event => { if ($('#origins-next-results-button').hasClass('disabled') || inSearch) { return; } inSearch = true; offset += perPage; if (!currentData || (offset >= limit && offset % limit === 0)) { searchOrigins(originPatterns, limit, offset, offset); } else { populateOriginSearchResultsTable(currentData, offset); } event.preventDefault(); }); $('#origins-prev-results-button').click(event => { if ($('#origins-prev-results-button').hasClass('disabled') || inSearch) { return; } inSearch = true; offset -= perPage; if (!currentData || (offset > 0 && (offset + perPage) % limit === 0)) { searchOrigins(originPatterns, limit, (offset + perPage) - limit, offset); } else { populateOriginSearchResultsTable(currentData, offset); } event.preventDefault(); }); $(document).on('shown.bs.tab', 'a[data-toggle="tab"]', e => { if (e.currentTarget.text.trim() === 'Search') { fixTableRowsStyle(); } }); }); } diff --git a/swh/web/browse/views/origin.py b/swh/web/browse/views/origin.py index 52e85da2..7cc322f6 100644 --- a/swh/web/browse/views/origin.py +++ b/swh/web/browse/views/origin.py @@ -1,239 +1,241 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import json from distutils.util import strtobool from django.http import HttpResponse from django.shortcuts import render, redirect from swh.web.common import service from swh.web.common.utils import ( reverse, format_utc_iso_date, parse_timestamp, get_origin_visits ) from swh.web.common.exc import handle_view_exception from swh.web.browse.utils import ( get_origin_info ) from swh.web.browse.browseurls import browse_route from .utils.snapshot_context import ( browse_snapshot_directory, browse_snapshot_content, browse_snapshot_log, browse_snapshot_branches, browse_snapshot_releases ) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/directory/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/directory/(?P.+)/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/directory/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/directory/(?P.+)/', # noqa r'origin/(?P.+)/visit/(?P.+)/directory/', # noqa r'origin/(?P.+)/visit/(?P.+)/directory/(?P.+)/', # noqa r'origin/(?P.+)/directory/', # noqa r'origin/(?P.+)/directory/(?P.+)/', # noqa view_name='browse-origin-directory') def origin_directory_browse(request, origin_url, origin_type=None, timestamp=None, path=None): """Django view for browsing the content of a SWH directory associated to an origin for a given visit. The url scheme that points to it is the following: * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/directory/[(path)/]` * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/directory/[(path)/]` """ # noqa return browse_snapshot_directory( request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp, path=path) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/content/(?P.+)/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/content/(?P.+)/', # noqa r'origin/(?P.+)/visit/(?P.+)/content/(?P.+)/', # noqa r'origin/(?P.+)/content/(?P.+)/', # noqa view_name='browse-origin-content') def origin_content_browse(request, origin_url, origin_type=None, path=None, timestamp=None): """Django view that produces an HTML display of a SWH content associated to an origin for a given visit. The url scheme that points to it is the following: * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/content/(path)/` * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/content/(path)/` """ # noqa return browse_snapshot_content(request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp, path=path) PER_PAGE = 20 @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/log/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/log/', r'origin/(?P.+)/visit/(?P.+)/log/', # noqa r'origin/(?P.+)/log/', view_name='browse-origin-log') def origin_log_browse(request, origin_url, origin_type=None, timestamp=None): """Django view that produces an HTML display of revisions history (aka the commit log) associated to a SWH origin. The url scheme that points to it is the following: * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/log/` * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/log/` """ # noqa return browse_snapshot_log(request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/branches/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/branches/', # noqa r'origin/(?P.+)/visit/(?P.+)/branches/', # noqa r'origin/(?P.+)/branches/', # noqa view_name='browse-origin-branches') def origin_branches_browse(request, origin_url, origin_type=None, timestamp=None): """Django view that produces an HTML display of the list of branches associated to an origin for a given visit. The url scheme that points to it is the following: * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/branches/` * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/branches/` """ # noqa return browse_snapshot_branches(request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/releases/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/releases/', # noqa r'origin/(?P.+)/visit/(?P.+)/releases/', # noqa r'origin/(?P.+)/releases/', # noqa view_name='browse-origin-releases') def origin_releases_browse(request, origin_url, origin_type=None, timestamp=None): """Django view that produces an HTML display of the list of releases associated to an origin for a given visit. The url scheme that points to it is the following: * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/releases/` * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/releases/` """ # noqa return browse_snapshot_releases(request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visits/', r'origin/(?P.+)/visits/', view_name='browse-origin-visits') def origin_visits_browse(request, origin_url, origin_type=None): """Django view that produces an HTML display of visits reporting for a swh origin identified by its id or its url. The url that points to it is :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visits/`. """ # noqa try: origin_info = get_origin_info(origin_url, origin_type) origin_visits = get_origin_visits(origin_info) except Exception as exc: return handle_view_exception(request, exc) origin_info['last swh visit browse url'] = \ reverse('browse-origin-directory', kwargs={'origin_url': origin_url, 'origin_type': origin_type}) for i, visit in enumerate(origin_visits): url_date = format_utc_iso_date(visit['date'], '%Y-%m-%dT%H:%M:%SZ') visit['fmt_date'] = format_utc_iso_date(visit['date']) query_params = {} if i < len(origin_visits) - 1: if visit['date'] == origin_visits[i+1]['date']: query_params = {'visit_id': visit['visit']} if i > 0: if visit['date'] == origin_visits[i-1]['date']: query_params = {'visit_id': visit['visit']} snapshot = visit['snapshot'] if visit['snapshot'] else '' visit['browse_url'] = reverse('browse-origin-directory', kwargs={'origin_type': origin_type, 'origin_url': origin_url, 'timestamp': url_date}, query_params=query_params) if not snapshot: visit['snapshot'] = '' visit['date'] = parse_timestamp(visit['date']).timestamp() heading = 'Origin visits - %s' % origin_url return render(request, 'browse/origin-visits.html', {'heading': heading, 'swh_object_name': 'Visits', 'swh_object_metadata': origin_info, 'origin_visits': origin_visits, 'origin_info': origin_info, 'browse_url_base': '/browse/origin/%s/url/%s/' % (origin_type, origin_url), 'vault_cooking': None, 'show_actions_menu': False}) @browse_route(r'origin/search/(?P.+)/', view_name='browse-origin-search') def _origin_search(request, url_pattern): """Internal browse endpoint to search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. """ offset = int(request.GET.get('offset', '0')) limit = int(request.GET.get('limit', '50')) regexp = request.GET.get('regexp', 'false') + with_visit = request.GET.get('with_visit', 'false') url_pattern = url_pattern.replace('///', '\\') results = service.search_origin(url_pattern, offset, limit, - bool(strtobool(regexp))) + bool(strtobool(regexp)), + bool(strtobool(with_visit))) results = json.dumps(list(results), sort_keys=True, indent=4, separators=(',', ': ')) return HttpResponse(results, content_type='application/json') @browse_route(r'origin/(?P[0-9]+)/latest_snapshot/', view_name='browse-origin-latest-snapshot') def _origin_latest_snapshot(request, origin_id): """ Internal browse endpoint used to check if an origin has already been visited by Software Heritage and has at least one full visit. """ result = service.lookup_latest_origin_snapshot(origin_id, allowed_statuses=['full']) result = json.dumps(result, sort_keys=True, indent=4, separators=(',', ': ')) return HttpResponse(result, content_type='application/json') @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/', r'origin/(?P.+)/', view_name='browse-origin') def origin_browse(request, origin_url, origin_type=None): """Django view that redirects to the display of the latest archived snapshot for a given software origin. """ # noqa last_snapshot_url = reverse('browse-origin-directory', kwargs={'origin_type': origin_type, 'origin_url': origin_url}) return redirect(last_snapshot_url) diff --git a/swh/web/common/service.py b/swh/web/common/service.py index 9adabb14..5594adc3 100644 --- a/swh/web/common/service.py +++ b/swh/web/common/service.py @@ -1,948 +1,950 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import os from collections import defaultdict from swh.model import hashutil from swh.web.common import converters from swh.web.common import query from swh.web.common.exc import NotFoundExc from swh.web import config storage = config.storage() vault = config.vault() idx_storage = config.indexer_storage() MAX_LIMIT = 50 # Top limit the users can ask for def _first_element(l): """Returns the first element in the provided list or None if it is empty or None""" return next(iter(l or []), None) def lookup_multiple_hashes(hashes): """Lookup the passed hashes in a single DB connection, using batch processing. Args: An array of {filename: X, sha1: Y}, string X, hex sha1 string Y. Returns: The same array with elements updated with elem['found'] = true if the hash is present in storage, elem['found'] = false if not. """ hashlist = [hashutil.hash_to_bytes(elem['sha1']) for elem in hashes] content_missing = storage.content_missing_per_sha1(hashlist) missing = [hashutil.hash_to_hex(x) for x in content_missing] for x in hashes: x.update({'found': True}) for h in hashes: if h['sha1'] in missing: h['found'] = False return hashes def lookup_expression(expression, last_sha1, per_page): """Lookup expression in raw content. Args: expression (str): An expression to lookup through raw indexed content last_sha1 (str): Last sha1 seen per_page (int): Number of results per page Returns: List of ctags whose content match the expression """ limit = min(per_page, MAX_LIMIT) ctags = idx_storage.content_ctags_search(expression, last_sha1=last_sha1, limit=limit) for ctag in ctags: ctag = converters.from_swh(ctag, hashess={'id'}) ctag['sha1'] = ctag['id'] ctag.pop('id') yield ctag def lookup_hash(q): """Checks if the storage contains a given content checksum Args: query string of the form Returns: Dict with key found containing the hash info if the hash is present, None if not. """ algo, hash = query.parse_hash(q) found = storage.content_find({algo: hash}) return {'found': found, 'algo': algo} def search_hash(q): """Checks if the storage contains a given content checksum Args: query string of the form Returns: Dict with key found to True or False, according to whether the checksum is present or not """ algo, hash = query.parse_hash(q) found = storage.content_find({algo: hash}) return {'found': found is not None} def lookup_content_provenance(q): """Return provenance information from a specified content. Args: q: query string of the form Yields: provenance information (dict) list if the content is found. """ algo, hash = query.parse_hash(q) provenances = storage.content_find_provenance({algo: hash}) if not provenances: return None return (converters.from_provenance(p) for p in provenances) def _lookup_content_sha1(q): """Given a possible input, query for the content's sha1. Args: q: query string of the form Returns: binary sha1 if found or None """ algo, hash = query.parse_hash(q) if algo != 'sha1': hashes = storage.content_find({algo: hash}) if not hashes: return None return hashes['sha1'] return hash def lookup_content_ctags(q): """Return ctags information from a specified content. Args: q: query string of the form Yields: ctags information (dict) list if the content is found. """ sha1 = _lookup_content_sha1(q) if not sha1: return None ctags = list(idx_storage.content_ctags_get([sha1])) if not ctags: return None for ctag in ctags: yield converters.from_swh(ctag, hashess={'id'}) def lookup_content_filetype(q): """Return filetype information from a specified content. Args: q: query string of the form Yields: filetype information (dict) list if the content is found. """ sha1 = _lookup_content_sha1(q) if not sha1: return None filetype = _first_element(list(idx_storage.content_mimetype_get([sha1]))) if not filetype: return None return converters.from_filetype(filetype) def lookup_content_language(q): """Return language information from a specified content. Args: q: query string of the form Yields: language information (dict) list if the content is found. """ sha1 = _lookup_content_sha1(q) if not sha1: return None lang = _first_element(list(idx_storage.content_language_get([sha1]))) if not lang: return None return converters.from_swh(lang, hashess={'id'}) def lookup_content_license(q): """Return license information from a specified content. Args: q: query string of the form Yields: license information (dict) list if the content is found. """ sha1 = _lookup_content_sha1(q) if not sha1: return None lic = _first_element(idx_storage.content_fossology_license_get([sha1])) if not lic: return None return converters.from_swh({'id': sha1, 'facts': lic[sha1]}, hashess={'id'}) def lookup_origin(origin): """Return information about the origin matching dict origin. Args: origin: origin's dict with keys either 'id' or ('type' AND 'url') Returns: origin information as dict. """ origin_info = storage.origin_get(origin) if not origin_info: if 'id' in origin and origin['id']: msg = 'Origin with id %s not found!' % origin['id'] else: msg = 'Origin with type %s and url %s not found!' % \ (origin['type'], origin['url']) raise NotFoundExc(msg) return converters.from_origin(origin_info) -def search_origin(url_pattern, offset=0, limit=50, regexp=False): +def search_origin(url_pattern, offset=0, limit=50, regexp=False, + with_visit=False): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. Args: url_pattern: the string pattern to search for in origin urls offset: number of found origins to skip before returning results limit: the maximum number of found origins to return Returns: lisf of origin information as dict. """ - origins = storage.origin_search(url_pattern, offset, limit, regexp) + origins = storage.origin_search(url_pattern, offset, limit, regexp, + with_visit) return map(converters.from_origin, origins) def lookup_person(person_id): """Return information about the person with id person_id. Args: person_id as string Returns: person information as dict. Raises: NotFoundExc if there is no person with the provided id. """ person = _first_element(storage.person_get([person_id])) if not person: raise NotFoundExc('Person with id %s not found' % person_id) return converters.from_person(person) def _to_sha1_bin(sha1_hex): _, sha1_git_bin = query.parse_hash_with_algorithms_or_throws( sha1_hex, ['sha1'], # HACK: sha1_git really 'Only sha1_git is supported.') return sha1_git_bin def lookup_directory(sha1_git): """Return information about the directory with id sha1_git. Args: sha1_git as string Returns: directory information as dict. """ empty_dir_sha1 = '4b825dc642cb6eb9a060e54bf8d69288fbee4904' if sha1_git == empty_dir_sha1: return [] sha1_git_bin = _to_sha1_bin(sha1_git) directory_entries = storage.directory_ls(sha1_git_bin) if directory_entries: return map(converters.from_directory_entry, directory_entries) else: raise NotFoundExc('Directory with sha1_git %s not found' % sha1_git) def lookup_directory_with_path(directory_sha1_git, path_string): """Return directory information for entry with path path_string w.r.t. root directory pointed by directory_sha1_git Args: - directory_sha1_git: sha1_git corresponding to the directory to which we append paths to (hopefully) find the entry - the relative path to the entry starting from the directory pointed by directory_sha1_git Raises: NotFoundExc if the directory entry is not found """ sha1_git_bin = _to_sha1_bin(directory_sha1_git) paths = path_string.strip(os.path.sep).split(os.path.sep) queried_dir = storage.directory_entry_get_by_path( sha1_git_bin, list(map(lambda p: p.encode('utf-8'), paths))) if not queried_dir: raise NotFoundExc(('Directory entry with path %s from %s not found') % (path_string, directory_sha1_git)) return converters.from_directory_entry(queried_dir) def lookup_release(release_sha1_git): """Return information about the release with sha1 release_sha1_git. Args: release_sha1_git: The release's sha1 as hexadecimal Returns: Release information as dict. Raises: ValueError if the identifier provided is not of sha1 nature. """ sha1_git_bin = _to_sha1_bin(release_sha1_git) release = _first_element(storage.release_get([sha1_git_bin])) if not release: raise NotFoundExc('Release with sha1_git %s not found.' % release_sha1_git) return converters.from_release(release) def lookup_release_multiple(sha1_git_list): """Return information about the revisions identified with their sha1_git identifiers. Args: sha1_git_list: A list of revision sha1_git identifiers Returns: Release information as dict. Raises: ValueError if the identifier provided is not of sha1 nature. """ sha1_bin_list = (_to_sha1_bin(sha1_git) for sha1_git in sha1_git_list) releases = storage.release_get(sha1_bin_list) or [] return (converters.from_release(r) for r in releases) def lookup_revision(rev_sha1_git): """Return information about the revision with sha1 revision_sha1_git. Args: revision_sha1_git: The revision's sha1 as hexadecimal Returns: Revision information as dict. Raises: ValueError if the identifier provided is not of sha1 nature. NotFoundExc if there is no revision with the provided sha1_git. """ sha1_git_bin = _to_sha1_bin(rev_sha1_git) revision = _first_element(storage.revision_get([sha1_git_bin])) if not revision: raise NotFoundExc('Revision with sha1_git %s not found.' % rev_sha1_git) return converters.from_revision(revision) def lookup_revision_multiple(sha1_git_list): """Return information about the revisions identified with their sha1_git identifiers. Args: sha1_git_list: A list of revision sha1_git identifiers Returns: Generator of revisions information as dict. Raises: ValueError if the identifier provided is not of sha1 nature. """ sha1_bin_list = (_to_sha1_bin(sha1_git) for sha1_git in sha1_git_list) revisions = storage.revision_get(sha1_bin_list) or [] return (converters.from_revision(r) for r in revisions) def lookup_revision_message(rev_sha1_git): """Return the raw message of the revision with sha1 revision_sha1_git. Args: revision_sha1_git: The revision's sha1 as hexadecimal Returns: Decoded revision message as dict {'message': } Raises: ValueError if the identifier provided is not of sha1 nature. NotFoundExc if the revision is not found, or if it has no message """ sha1_git_bin = _to_sha1_bin(rev_sha1_git) revision = _first_element(storage.revision_get([sha1_git_bin])) if not revision: raise NotFoundExc('Revision with sha1_git %s not found.' % rev_sha1_git) if 'message' not in revision: raise NotFoundExc('No message for revision with sha1_git %s.' % rev_sha1_git) res = {'message': revision['message']} return res def lookup_revision_by(origin_id, branch_name="refs/heads/master", timestamp=None): """Lookup revisions by origin_id, branch_name and timestamp. If: - branch_name is not provided, lookup using 'refs/heads/master' as default. - ts is not provided, use the most recent Args: - origin_id: origin of the revision. - branch_name: revision's branch. - timestamp: revision's time frame. Yields: The revisions matching the criterions. Raises: NotFoundExc if no revision corresponds to the criterion """ res = _first_element(storage.revision_get_by(origin_id, branch_name, timestamp=timestamp, limit=1)) if not res: raise NotFoundExc('Revision for origin %s and branch %s not found.' % (origin_id, branch_name)) return converters.from_revision(res) def lookup_revision_log(rev_sha1_git, limit): """Return information about the revision with sha1 revision_sha1_git. Args: revision_sha1_git: The revision's sha1 as hexadecimal limit: the maximum number of revisions returned Returns: Revision information as dict. Raises: ValueError if the identifier provided is not of sha1 nature. NotFoundExc if there is no revision with the provided sha1_git. """ sha1_git_bin = _to_sha1_bin(rev_sha1_git) revision_entries = storage.revision_log([sha1_git_bin], limit) if not revision_entries: raise NotFoundExc('Revision with sha1_git %s not found.' % rev_sha1_git) return map(converters.from_revision, revision_entries) def lookup_revision_log_by(origin_id, branch_name, timestamp, limit): """Return information about the revision with sha1 revision_sha1_git. Args: origin_id: origin of the revision branch_name: revision's branch timestamp: revision's time frame limit: the maximum number of revisions returned Returns: Revision information as dict. Raises: NotFoundExc if no revision corresponds to the criterion """ revision_entries = storage.revision_log_by(origin_id, branch_name, timestamp, limit=limit) if not revision_entries: return None return map(converters.from_revision, revision_entries) def lookup_revision_with_context_by(origin_id, branch_name, ts, sha1_git, limit=100): """Return information about revision sha1_git, limited to the sub-graph of all transitive parents of sha1_git_root. sha1_git_root being resolved through the lookup of a revision by origin_id, branch_name and ts. In other words, sha1_git is an ancestor of sha1_git_root. Args: - origin_id: origin of the revision. - branch_name: revision's branch. - timestamp: revision's time frame. - sha1_git: one of sha1_git_root's ancestors. - limit: limit the lookup to 100 revisions back. Returns: Pair of (root_revision, revision). Information on sha1_git if it is an ancestor of sha1_git_root including children leading to sha1_git_root Raises: - BadInputExc in case of unknown algo_hash or bad hash. - NotFoundExc if either revision is not found or if sha1_git is not an ancestor of sha1_git_root. """ rev_root = _first_element(storage.revision_get_by(origin_id, branch_name, timestamp=ts, limit=1)) if not rev_root: raise NotFoundExc('Revision with (origin_id: %s, branch_name: %s' ', ts: %s) not found.' % (origin_id, branch_name, ts)) return (converters.from_revision(rev_root), lookup_revision_with_context(rev_root, sha1_git, limit)) def lookup_revision_with_context(sha1_git_root, sha1_git, limit=100): """Return information about revision sha1_git, limited to the sub-graph of all transitive parents of sha1_git_root. In other words, sha1_git is an ancestor of sha1_git_root. Args: sha1_git_root: latest revision. The type is either a sha1 (as an hex string) or a non converted dict. sha1_git: one of sha1_git_root's ancestors limit: limit the lookup to 100 revisions back Returns: Information on sha1_git if it is an ancestor of sha1_git_root including children leading to sha1_git_root Raises: BadInputExc in case of unknown algo_hash or bad hash NotFoundExc if either revision is not found or if sha1_git is not an ancestor of sha1_git_root """ sha1_git_bin = _to_sha1_bin(sha1_git) revision = _first_element(storage.revision_get([sha1_git_bin])) if not revision: raise NotFoundExc('Revision %s not found' % sha1_git) if isinstance(sha1_git_root, str): sha1_git_root_bin = _to_sha1_bin(sha1_git_root) revision_root = _first_element(storage.revision_get([sha1_git_root_bin])) # noqa if not revision_root: raise NotFoundExc('Revision root %s not found' % sha1_git_root) else: sha1_git_root_bin = sha1_git_root['id'] revision_log = storage.revision_log([sha1_git_root_bin], limit) parents = {} children = defaultdict(list) for rev in revision_log: rev_id = rev['id'] parents[rev_id] = [] for parent_id in rev['parents']: parents[rev_id].append(parent_id) children[parent_id].append(rev_id) if revision['id'] not in parents: raise NotFoundExc('Revision %s is not an ancestor of %s' % (sha1_git, sha1_git_root)) revision['children'] = children[revision['id']] return converters.from_revision(revision) def lookup_directory_with_revision(sha1_git, dir_path=None, with_data=False): """Return information on directory pointed by revision with sha1_git. If dir_path is not provided, display top level directory. Otherwise, display the directory pointed by dir_path (if it exists). Args: sha1_git: revision's hash. dir_path: optional directory pointed to by that revision. with_data: boolean that indicates to retrieve the raw data if the path resolves to a content. Default to False (for the api) Returns: Information on the directory pointed to by that revision. Raises: BadInputExc in case of unknown algo_hash or bad hash. NotFoundExc either if the revision is not found or the path referenced does not exist. NotImplementedError in case of dir_path exists but do not reference a type 'dir' or 'file'. """ sha1_git_bin = _to_sha1_bin(sha1_git) revision = _first_element(storage.revision_get([sha1_git_bin])) if not revision: raise NotFoundExc('Revision %s not found' % sha1_git) dir_sha1_git_bin = revision['directory'] if dir_path: paths = dir_path.strip(os.path.sep).split(os.path.sep) entity = storage.directory_entry_get_by_path( dir_sha1_git_bin, list(map(lambda p: p.encode('utf-8'), paths))) if not entity: raise NotFoundExc( "Directory or File '%s' pointed to by revision %s not found" % (dir_path, sha1_git)) else: entity = {'type': 'dir', 'target': dir_sha1_git_bin} if entity['type'] == 'dir': directory_entries = storage.directory_ls(entity['target']) or [] return {'type': 'dir', 'path': '.' if not dir_path else dir_path, 'revision': sha1_git, 'content': map(converters.from_directory_entry, directory_entries)} elif entity['type'] == 'file': # content content = storage.content_find({'sha1_git': entity['target']}) if with_data: c = _first_element(storage.content_get([content['sha1']])) content['data'] = c['data'] return {'type': 'file', 'path': '.' if not dir_path else dir_path, 'revision': sha1_git, 'content': converters.from_content(content)} else: raise NotImplementedError('Entity of type %s not implemented.' % entity['type']) def lookup_content(q): """Lookup the content designed by q. Args: q: The release's sha1 as hexadecimal Raises: NotFoundExc if the requested content is not found """ algo, hash = query.parse_hash(q) c = storage.content_find({algo: hash}) if not c: raise NotFoundExc('Content with %s checksum equals to %s not found!' % (algo, hashutil.hash_to_hex(hash))) return converters.from_content(c) def lookup_content_raw(q): """Lookup the content defined by q. Args: q: query string of the form Returns: dict with 'sha1' and 'data' keys. data representing its raw data decoded. Raises: NotFoundExc if the requested content is not found or if the content bytes are not available in the storage """ c = lookup_content(q) content = _first_element(storage.content_get([c['checksums']['sha1']])) if not content: algo, hash = query.parse_hash(q) raise NotFoundExc('Bytes of content with %s checksum equals to %s ' 'are not available!' % (algo, hashutil.hash_to_hex(hash))) return converters.from_content(content) def stat_counters(): """Return the stat counters for Software Heritage Returns: A dict mapping textual labels to integer values. """ return storage.stat_counters() def _lookup_origin_visits(origin_id, last_visit=None, limit=10): """Yields the origin origin_ids' visits. Args: origin_id (int): origin to list visits for last_visit (int): last visit to lookup from limit (int): Number of elements max to display Yields: Dictionaries of origin_visit for that origin """ limit = min(limit, MAX_LIMIT) yield from storage.origin_visit_get( origin_id, last_visit=last_visit, limit=limit) def lookup_origin_visits(origin_id, last_visit=None, per_page=10): """Yields the origin origin_ids' visits. Args: origin_id: origin to list visits for Yields: Dictionaries of origin_visit for that origin """ visits = _lookup_origin_visits(origin_id, last_visit=last_visit, limit=per_page) for visit in visits: yield converters.from_origin_visit(visit) def lookup_origin_visit(origin_id, visit_id): """Return information about visit visit_id with origin origin_id. Args: origin_id: origin concerned by the visit visit_id: the visit identifier to lookup Yields: The dict origin_visit concerned """ visit = storage.origin_visit_get_by(origin_id, visit_id) if not visit: raise NotFoundExc('Origin with id %s or its visit ' 'with id %s not found!' % (origin_id, visit_id)) return converters.from_origin_visit(visit) def lookup_snapshot(snapshot_id): """Return information about a snapshot, aka the list of named branches found during a specific visit of an origin. Args: snapshot_id: sha1 identifier of the snapshot Returns: A dict filled with the snapshot content. """ snapshot_id_bin = _to_sha1_bin(snapshot_id) snapshot = storage.snapshot_get(snapshot_id_bin) if not snapshot: raise NotFoundExc('Snapshot with id %s not found!' % snapshot_id) return converters.from_snapshot(snapshot) def lookup_latest_origin_snapshot(origin_id, allowed_statuses=None): """Return information about the latest snapshot of an origin. Args: origin_id: integer identifier of the origin allowed_statuses: list of visit statuses considered to find the latest snapshot for the visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. Returns: A dict filled with the snapshot content. """ snapshot = storage.snapshot_get_latest(origin_id, allowed_statuses) return converters.from_snapshot(snapshot) def lookup_entity_by_uuid(uuid): """Return the entity's hierarchy from its uuid. Args: uuid: entity's identifier. Returns: List of hierarchy entities from the entity with uuid. """ uuid = query.parse_uuid4(uuid) for entity in storage.entity_get(uuid): entity = converters.from_swh(entity, convert={'last_seen', 'uuid'}, convert_fn=lambda x: str(x)) yield entity def lookup_revision_through(revision, limit=100): """Retrieve a revision from the criterion stored in revision dictionary. Args: revision: Dictionary of criterion to lookup the revision with. Here are the supported combination of possible values: - origin_id, branch_name, ts, sha1_git - origin_id, branch_name, ts - sha1_git_root, sha1_git - sha1_git Returns: None if the revision is not found or the actual revision. """ if 'origin_id' in revision and \ 'branch_name' in revision and \ 'ts' in revision and \ 'sha1_git' in revision: return lookup_revision_with_context_by(revision['origin_id'], revision['branch_name'], revision['ts'], revision['sha1_git'], limit) if 'origin_id' in revision and \ 'branch_name' in revision and \ 'ts' in revision: return lookup_revision_by(revision['origin_id'], revision['branch_name'], revision['ts']) if 'sha1_git_root' in revision and \ 'sha1_git' in revision: return lookup_revision_with_context(revision['sha1_git_root'], revision['sha1_git'], limit) if 'sha1_git' in revision: return lookup_revision(revision['sha1_git']) # this should not happen raise NotImplementedError('Should not happen!') def lookup_directory_through_revision(revision, path=None, limit=100, with_data=False): """Retrieve the directory information from the revision. Args: revision: dictionary of criterion representing a revision to lookup path: directory's path to lookup. limit: optional query parameter to limit the revisions log (default to 100). For now, note that this limit could impede the transitivity conclusion about sha1_git not being an ancestor of. with_data: indicate to retrieve the content's raw data if path resolves to a content. Returns: The directory pointing to by the revision criterions at path. """ rev = lookup_revision_through(revision, limit) if not rev: raise NotFoundExc('Revision with criterion %s not found!' % revision) return (rev['id'], lookup_directory_with_revision(rev['id'], path, with_data)) def vault_cook(obj_type, obj_id, email=None): """Cook a vault bundle. """ return vault.cook(obj_type, obj_id, email=email) def vault_fetch(obj_type, obj_id): """Fetch a vault bundle. """ return vault.fetch(obj_type, obj_id) def vault_progress(obj_type, obj_id): """Get the current progress of a vault bundle. """ return vault.progress(obj_type, obj_id) def diff_revision(rev_id): """Get the list of file changes (insertion / deletion / modification / renaming) for a particular revision. """ rev_sha1_git_bin = _to_sha1_bin(rev_id) changes = storage.diff_revision(rev_sha1_git_bin, track_renaming=True) for change in changes: change['from'] = converters.from_directory_entry(change['from']) change['to'] = converters.from_directory_entry(change['to']) if change['from_path']: change['from_path'] = change['from_path'].decode('utf-8') if change['to_path']: change['to_path'] = change['to_path'].decode('utf-8') return changes diff --git a/swh/web/templates/browse/search.html b/swh/web/templates/browse/search.html index 8ba17e04..7d3d1b24 100644 --- a/swh/web/templates/browse/search.html +++ b/swh/web/templates/browse/search.html @@ -1,61 +1,66 @@ {% extends "./layout.html" %} {% comment %} Copyright (C) 2017-2018 The Software Heritage developers See the AUTHORS file at the top-level directory of this distribution License: GNU Affero General Public License version 3, or any later version See top-level LICENSE file for more information {% endcomment %} {% load static %} {% block navbar-content %}

Search software origins to browse

{% endblock %} {% block browse-content %}
+
+ + +

Searching origins ...

{% endblock %} \ No newline at end of file