diff --git a/swh/web/browse/utils.py b/swh/web/browse/utils.py index f28e5539..bdc67163 100644 --- a/swh/web/browse/utils.py +++ b/swh/web/browse/utils.py @@ -1,282 +1,294 @@ # Copyright (C) 2017 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import base64 import dateutil import magic import math +import stat from django.core.cache import cache from swh.web.common import highlightjs, service from swh.web.common.exc import NotFoundExc def get_directory_entries(sha1_git): """Function that retrieves the content of a SWH directory from the SWH archive. The directories entries are first sorted in lexicographical order. Sub-directories and regular files are then extracted. Args: sha1_git: sha1_git identifier of the directory Returns: A tuple whose first member corresponds to the sub-directories list and second member the regular files list Raises: NotFoundExc if the directory is not found """ + cache_entry_id = 'directory_entries_%s' % sha1_git + cache_entry = cache.get(cache_entry_id) + + if cache_entry: + return cache_entry + entries = list(service.lookup_directory(sha1_git)) entries = sorted(entries, key=lambda e: e['name']) + for entry in entries: + entry['perms'] = stat.filemode(entry['perms']) dirs = [e for e in entries if e['type'] == 'dir'] files = [e for e in entries if e['type'] == 'file'] + + cache.set(cache_entry_id, (dirs, files)) + return dirs, files def gen_path_info(path): """Function to generate path data navigation for use with a breadcrumb in the swh web ui. For instance, from a path /folder1/folder2/folder3, it returns the following list:: [{'name': 'folder1', 'path': 'folder1'}, {'name': 'folder2', 'path': 'folder1/folder2'}, {'name': 'folder3', 'path': 'folder1/folder2/folder3'}] Args: path: a filesystem path Returns: A list of path data for navigation as illustrated above. """ path_info = [] if path: sub_paths = path.strip('/').split('/') path_from_root = '' for p in sub_paths: path_from_root += '/' + p path_info.append({'name': p, 'path': path_from_root.strip('/')}) return path_info def get_mimetype_for_content(content): """Function that returns the mime type associated to a content buffer using the magic module under the hood. Args: content (bytes): a content buffer Returns: The mime type (e.g. text/plain) associated to the provided content. """ return magic.detect_from_content(content).mime_type def request_content(query_string): """Function that retrieves a SWH content from the SWH archive. Raw bytes content is first retrieved, then the content mime type. If the mime type is not stored in the archive, it will be computed using Python magic module. Args: 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 Returns: A tuple whose first member corresponds to the content raw bytes and second member the content mime type Raises: NotFoundExc if the content is not found """ content_raw = service.lookup_content_raw(query_string) content_data = content_raw['data'] mime_type = service.lookup_content_filetype(query_string) if mime_type: mime_type = mime_type['mimetype'] else: mime_type = get_mimetype_for_content(content_data) return content_data, mime_type _browsers_supported_image_mimes = set(['image/gif', 'image/png', 'image/jpeg', 'image/bmp', 'image/webp']) def prepare_content_for_display(content_data, mime_type, path): """Function that prepares a content for HTML display. The function tries to associate a programming language to a content in order to perform syntax highlighting client-side using highlightjs. The language is determined using either the content filename or its mime type. If the mime type corresponds to an image format supported by web browsers, the content will be encoded in base64 for displaying the image. Args: content_data (bytes): raw bytes of the content mime_type (string): mime type of the content path (string): path of the content including filename Returns: A dict containing the content bytes (possibly different from the one provided as parameter if it is an image) under the key 'content_data and the corresponding highlightjs language class under the key 'language'. """ language = highlightjs.get_hljs_language_from_filename(path) if not language: language = highlightjs.get_hljs_language_from_mime_type(mime_type) if not language: language = 'nohighlight-swh' elif mime_type.startswith('application/'): mime_type = mime_type.replace('application/', 'text/') if mime_type.startswith('image/'): if mime_type in _browsers_supported_image_mimes: content_data = base64.b64encode(content_data) else: content_data = None return {'content_data': content_data, 'language': language} def get_origin_visits(origin_id): """Function that returns the list of visits for a swh origin. That list is put in cache in order to speedup the navigation in the swh web browse ui. Args: origin_id (int): the id of the swh origin to fetch visits from Returns: A list of dict describing the origin visits:: [{'date': , 'origin': , 'status': <'full' | 'partial'>, 'visit': }, ... ] Raises: NotFoundExc if the origin is not found """ cache_entry_id = 'origin_%s_visits' % origin_id cache_entry = cache.get(cache_entry_id) if cache_entry: return cache_entry origin_visits = [] per_page = service.MAX_LIMIT last_visit = None while 1: visits = list(service.lookup_origin_visits(origin_id, last_visit=last_visit, per_page=per_page)) origin_visits += visits if len(visits) < per_page: break else: if not last_visit: last_visit = per_page else: last_visit += per_page cache.set(cache_entry_id, origin_visits) return origin_visits def get_origin_visit_branches(origin_id, visit_id=None, visit_ts=None): """Function that returns the list of branches associated to a swh origin for a given visit. The visit can be expressed by its id or its timestamp. 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. Args: origin_id (int): the id of the swh origin to fetch branches from visit_id (int): the id of the origin visit visit_ts (Unix timestamp): the timestamp of the origin visit Returns: A list of dict describing the origin branches for the given visit:: [{'name': , 'revision': , 'directory': }, ... ] Raises: NotFoundExc if the origin or its visit are not found """ if not visit_id and visit_ts: visits = get_origin_visits(origin_id) for visit in visits: ts = dateutil.parser.parse(visit['date']).timestamp() ts = str(math.floor(ts)) if ts == visit_ts: return get_origin_visit_branches(origin_id, visit['visit']) raise NotFoundExc( 'Visit with timestamp %s for origin with id %s not found!' % (visit_ts, origin_id)) cache_entry_id = 'origin_%s_visit_%s_branches' % (origin_id, visit_id) cache_entry = cache.get(cache_entry_id) if cache_entry: return cache_entry origin_visit_data = service.lookup_origin_visit(origin_id, visit_id) branches = [] revision_ids = [] occurrences = origin_visit_data['occurrences'] for key in sorted(occurrences.keys()): if occurrences[key]['target_type'] == 'revision': branches.append({'name': key, 'revision': occurrences[key]['target']}) revision_ids.append(occurrences[key]['target']) revisions = service.lookup_revision_multiple(revision_ids) branches_to_remove = [] for idx, revision in enumerate(revisions): if revision: branches[idx]['directory'] = revision['directory'] else: branches_to_remove.append(branches[idx]) for b in branches_to_remove: branches.remove(b) cache.set(cache_entry_id, branches) return branches diff --git a/swh/web/templates/directory.html b/swh/web/templates/directory.html index 8e20e2ca..1414a39a 100644 --- a/swh/web/templates/directory.html +++ b/swh/web/templates/directory.html @@ -1,41 +1,47 @@ {% extends "layout.html" %} {% block title %}Directory browse{% endblock %} {% block content %}
Directory sha1 git: {{ dir_sha1_git }}
{% include "content-directory-top-navigation.html" %}
+ + {% for d in dirs %} + + {% endfor %} {% for f in files %} + + {% endfor %}
FileModeSize Sha1 git
{{ d.name }} {{ d.perms }} {{ d.target }}
{{ f.name }} {{ f.perms }}{{ f.length }} {{ f.target }}
{% endblock %} diff --git a/swh/web/tests/browse/views/test_origin.py b/swh/web/tests/browse/views/test_origin.py index 0f788604..d355b604 100644 --- a/swh/web/tests/browse/views/test_origin.py +++ b/swh/web/tests/browse/views/test_origin.py @@ -1,353 +1,353 @@ # Copyright (C) 2017 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from unittest.mock import patch from nose.tools import istest, nottest from django.test import TestCase from django.utils.html import escape from swh.web.common.utils import reverse from .data.origin_test_data import ( origin_info_test_data, origin_visits_test_data, stub_content_origin_id, stub_content_origin_visit_id, stub_content_origin_visit_ts, stub_content_origin_branch, stub_content_origin_visits, stub_content_origin_branches, stub_origin_id, stub_visit_id, stub_origin_visits, stub_origin_branches, stub_origin_root_directory_entries, stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_path, stub_origin_sub_directory_entries, stub_visit_ts ) from .data.content_test_data import ( stub_content_root_dir, stub_content_text_data, stub_content_text_sha1, stub_content_text_path ) from swh.web.browse.utils import ( gen_path_info ) class SwhBrowseOriginTest(TestCase): @patch('swh.web.browse.views.origin.get_origin_visits') @patch('swh.web.browse.views.origin.service') @istest def test_origin_browse(self, mock_service, mock_get_origin_visits): mock_service.lookup_origin.return_value = origin_info_test_data mock_get_origin_visits.return_value = origin_visits_test_data url = reverse('browse-origin', kwargs={'origin_id': origin_info_test_data['id']}) resp = self.client.get(url) self.assertEquals(resp.status_code, 200) self.assertTemplateUsed('origin.html') self.assertContains(resp, '%s' % origin_info_test_data['id']) self.assertContains(resp, '%s' % origin_info_test_data['type']) # noqa self.assertContains(resp, '%s' % (origin_info_test_data['url'], origin_info_test_data['url'])) self.assertContains(resp, '', count=len(origin_visits_test_data)) for visit in origin_visits_test_data: browse_url = reverse('browse-origin-directory', kwargs={'origin_id': visit['origin'], 'visit_id': visit['visit']}) self.assertContains(resp, '%s' % (browse_url, browse_url)) @nottest def origin_content_view_test(self, origin_id, origin_visits, origin_branches, origin_branch, root_dir_sha1, content_sha1, content_path, content_data, content_language, visit_id=None, ts=None): url_args = {'origin_id': origin_id, 'path': content_path} if not visit_id: visit_id = origin_visits[-1]['visit'] if ts: url_args['ts'] = ts else: url_args['visit_id'] = visit_id url = reverse('browse-origin-content', kwargs=url_args) resp = self.client.get(url) self.assertEquals(resp.status_code, 200) self.assertTemplateUsed('content.html') self.assertContains(resp, '' % content_language) self.assertContains(resp, escape(content_data)) split_path = content_path.split('/') filename = split_path[-1] path = content_path.replace(filename, '')[:-1] path_info = gen_path_info(path) del url_args['path'] root_dir_url = reverse('browse-origin-directory', kwargs=url_args, query_params={'branch': origin_branch}) self.assertContains(resp, '
  • ', count=len(path_info)+1) self.assertContains(resp, '%s' % (root_dir_url, root_dir_sha1[:7])) for p in path_info: url_args['path'] = p['path'] dir_url = reverse('browse-origin-directory', kwargs=url_args, query_params={'branch': origin_branch}) self.assertContains(resp, '%s' % (dir_url, p['name'])) self.assertContains(resp, '
  • %s
    • ' % filename) query_string = 'sha1_git:' + content_sha1 url_raw = reverse('browse-content-raw', kwargs={'query_string': query_string}, query_params={'filename': filename}) self.assertContains(resp, url_raw) self.assertContains(resp, '
  • ', count=len(origin_branches)) url_args['path'] = content_path for branch in origin_branches: root_dir_branch_url = \ reverse('browse-origin-content', kwargs=url_args, query_params={'branch': branch['name']}) self.assertContains(resp, '%s' % (root_dir_branch_url, branch['name'])) @patch('swh.web.browse.views.origin.get_origin_visits') @patch('swh.web.browse.views.origin.get_origin_visit_branches') @patch('swh.web.browse.views.origin.service') @patch('swh.web.browse.views.origin.request_content') @istest def origin_content_view(self, mock_request_content, mock_service, mock_get_origin_visit_branches, mock_get_origin_visits): mock_get_origin_visits.return_value = stub_content_origin_visits mock_get_origin_visit_branches.return_value = stub_content_origin_branches # noqa mock_service.lookup_directory_with_path.return_value = \ {'target': stub_content_text_sha1} mock_request_content.return_value = stub_content_text_data, 'text/x-c++' # noqa self.origin_content_view_test(stub_content_origin_id, stub_content_origin_visits, stub_content_origin_branches, stub_content_origin_branch, stub_content_root_dir, stub_content_text_sha1, stub_content_text_path, stub_content_text_data, 'cpp') self.origin_content_view_test(stub_content_origin_id, stub_content_origin_visits, stub_content_origin_branches, stub_content_origin_branch, stub_content_root_dir, stub_content_text_sha1, stub_content_text_path, stub_content_text_data, 'cpp', visit_id=stub_content_origin_visit_id) self.origin_content_view_test(stub_content_origin_id, stub_content_origin_visits, stub_content_origin_branches, stub_content_origin_branch, stub_content_root_dir, stub_content_text_sha1, stub_content_text_path, stub_content_text_data, 'cpp', ts=stub_content_origin_visit_ts) @nottest def origin_directory_view(self, origin_id, origin_visits, origin_branches, origin_branch, root_directory_sha1, directory_entries, visit_id=None, ts=None, path=None): dirs = [e for e in directory_entries if e['type'] == 'dir'] files = [e for e in directory_entries if e['type'] == 'file'] if not visit_id: visit_id = origin_visits[-1]['visit'] url_args = {'origin_id': origin_id} if ts: url_args['ts'] = ts else: url_args['visit_id'] = visit_id if path: url_args['path'] = path url = reverse('browse-origin-directory', kwargs=url_args) resp = self.client.get(url) self.assertEquals(resp.status_code, 200) self.assertTemplateUsed('directory.html') self.assertContains(resp, '', count=len(dirs)) self.assertContains(resp, '', count=len(files)) for d in dirs: dir_path = d['name'] if path: dir_path = "%s/%s" % (path, d['name']) dir_url_args = dict(url_args) dir_url_args['path'] = dir_path dir_url = reverse('browse-origin-directory', kwargs=dir_url_args, query_params={'branch': origin_branch}) # noqa self.assertContains(resp, dir_url) for f in files: file_path = f['name'] if path: file_path = "%s/%s" % (path, f['name']) file_url_args = dict(url_args) file_url_args['path'] = file_path file_url = reverse('browse-origin-content', kwargs=file_url_args, query_params={'branch': origin_branch}) # noqa self.assertContains(resp, file_url) if 'path' in url_args: del url_args['path'] root_dir_branch_url = \ reverse('browse-origin-directory', kwargs=url_args, query_params={'branch': origin_branch}) nb_bc_paths = 1 if path: nb_bc_paths = len(path.split('/')) + 1 self.assertContains(resp, '
  • ', count=nb_bc_paths) self.assertContains(resp, '%s' % (root_dir_branch_url, root_directory_sha1[:7])) self.assertContains(resp, '
  • ', count=len(origin_branches)) if path: url_args['path'] = path for branch in origin_branches: root_dir_branch_url = \ reverse('browse-origin-directory', kwargs=url_args, query_params={'branch': branch['name']}) self.assertContains(resp, '%s' % (root_dir_branch_url, branch['name'])) @patch('swh.web.browse.views.origin.get_origin_visits') @patch('swh.web.browse.views.origin.get_origin_visit_branches') @patch('swh.web.browse.utils.service') @istest def origin_root_directory_view(self, mock_service, mock_get_origin_visit_branches, mock_get_origin_visits): mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_branches.return_value = stub_origin_branches mock_service.lookup_directory.return_value = \ stub_origin_root_directory_entries self.origin_directory_view(stub_origin_id, stub_origin_visits, stub_origin_branches, stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_root_directory_entries) self.origin_directory_view(stub_origin_id, stub_origin_visits, stub_origin_branches, stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_root_directory_entries, visit_id=stub_visit_id) self.origin_directory_view(stub_origin_id, stub_origin_visits, stub_origin_branches, stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_root_directory_entries, ts=stub_visit_ts) @patch('swh.web.browse.views.origin.get_origin_visits') @patch('swh.web.browse.views.origin.get_origin_visit_branches') @patch('swh.web.browse.utils.service') @patch('swh.web.browse.views.origin.service') @istest def origin_sub_directory_view(self, mock_origin_service, mock_utils_service, mock_get_origin_visit_branches, mock_get_origin_visits): mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_branches.return_value = stub_origin_branches mock_utils_service.lookup_directory.return_value = \ stub_origin_sub_directory_entries mock_origin_service.lookup_directory_with_path.return_value = \ - {'target': '120c39eeb566c66a77ce0e904d29dfde42228adc'} + {'target': '120c39eeb566c66a77ce0e904d29dfde42228adb'} self.origin_directory_view(stub_origin_id, stub_origin_visits, stub_origin_branches, stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_entries, path=stub_origin_sub_directory_path) self.origin_directory_view(stub_origin_id, stub_origin_visits, stub_origin_branches, stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_entries, visit_id=stub_visit_id, path=stub_origin_sub_directory_path) self.origin_directory_view(stub_origin_id, stub_origin_visits, stub_origin_branches, stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_entries, ts=stub_visit_ts, path=stub_origin_sub_directory_path)