diff --git a/swh/web/browse/views/content.py b/swh/web/browse/views/content.py index 4fd9361b..b8af32b8 100644 --- a/swh/web/browse/views/content.py +++ b/swh/web/browse/views/content.py @@ -1,331 +1,331 @@ # Copyright (C) 2017-2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information 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 from swh.model.hashutil import hash_to_hex from swh.web.common import query, service, highlightjs from swh.web.common.utils import ( reverse, gen_path_info, swh_object_icons ) from swh.web.common.exc import NotFoundExc, handle_view_exception from swh.web.browse.utils import ( request_content, prepare_content_for_display, content_display_max_size, get_snapshot_context, get_swh_persistent_ids, gen_link, gen_directory_link ) from swh.web.browse.browseurls import browse_route @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.*)', # noqa 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 e: diff_str = str(e) 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_type = request.GET.get('origin_type', None) 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(None, origin_type, origin_url) except Exception: 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._hljs_languages + available_languages = highlightjs.get_supported_languages() root_dir = None filename = None path_info = None directory_id = None directory_url = None query_params = {'origin': 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: dir_url = reverse('browse-directory', url_args={'sha1_git': root_dir, 'path': pi['path']}, query_params=query_params) breadcrumbs.append({'name': pi['name'], 'url': dir_url}) breadcrumbs.append({'name': filename, 'url': None}) if path and root_dir != path: dir_info = service.lookup_directory_with_path(root_dir, path) directory_id = dir_info['target'] elif root_dir != path: directory_id = root_dir if directory_id: directory_url = gen_directory_link(directory_id) query_params = {'filename': filename} content_raw_url = reverse('browse-content-raw', url_args={'query_string': query_string}, query_params=query_params) content_metadata = { 'sha1': content_data['checksums']['sha1'], 'sha1_git': content_data['checksums']['sha1_git'], 'sha256': content_data['checksums']['sha256'], 'blake2s256': content_data['checksums']['blake2s256'], 'mimetype': content_data['mimetype'], 'encoding': content_data['encoding'], 'size': filesizeformat(content_data['length']), 'language': content_data['language'], 'licenses': content_data['licenses'], 'filename': filename, 'directory': directory_id, 'context-independent directory': directory_url } if filename: content_metadata['filename'] = filename sha1_git = content_data['checksums']['sha1_git'] swh_ids = get_swh_persistent_ids([{'type': 'content', 'id': sha1_git}]) heading = 'Content - %s' % 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_name': 'Content', 'swh_object_metadata': content_metadata, 'content': content, 'content_size': content_data['length'], 'max_content_size': content_display_max_size, '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, '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/utils/snapshot_context.py b/swh/web/browse/views/utils/snapshot_context.py index 3a22f803..ce6e8cbf 100644 --- a/swh/web/browse/views/utils/snapshot_context.py +++ b/swh/web/browse/views/utils/snapshot_context.py @@ -1,921 +1,921 @@ # Copyright (C) 2018-2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information # Utility module implementing Django views for browsing the archive # in a snapshot context. # Its purpose is to factorize code for the views reachable from the # /origin/.* and /snapshot/.* endpoints. from django.shortcuts import render from django.template.defaultfilters import filesizeformat from django.utils.html import escape from swh.model.identifiers import snapshot_identifier from swh.web.browse.utils import ( get_snapshot_context, 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, get_readme_to_display, get_swh_persistent_ids, gen_snapshot_link, process_snapshot_branches ) from swh.web.common import service, highlightjs from swh.web.common.exc import ( handle_view_exception, NotFoundExc ) from swh.web.common.utils import ( reverse, gen_path_info, format_utc_iso_date, swh_object_icons ) _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'].endswith(branch_name)] if len(filtered_branches) > 0: return filtered_branches[0] elif branch_name == 'HEAD': filtered_branches = \ [b for b in branches if b['name'].endswith('master')] if len(filtered_branches) > 0: return filtered_branches[0] elif len(branches) > 0: 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: branches.append(snp_branch[0]) return snp_branch[0] return None def _get_release(releases, release_name): """ 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 len(filtered_releases) > 0: return filtered_releases[0] else: return None def _branch_not_found(branch_type, branch, branches, snapshot_id=None, origin_info=None, timestamp=None, visit_id=None): """ 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' else: branch_type = 'Release' branch_type_plural = 'releases' if snapshot_id and len(branches) == 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 len(branches) == 0: msg = 'Origin with type %s and url %s' \ ' for visit with id %s has an empty list' \ ' of %s!' % (origin_info['type'], origin_info['url'], visit_id, branch_type_plural) elif visit_id: msg = '%s %s associated to visit with' \ ' id %s for origin with type %s and url %s' \ ' not found!' % (branch_type, branch, visit_id, origin_info['type'], origin_info['url']) elif len(branches) == 0: msg = 'Origin with type %s and url %s' \ ' for visit with timestamp %s has an empty list' \ ' of %s!' % (origin_info['type'], origin_info['url'], timestamp, branch_type_plural) else: msg = '%s %s associated to visit with' \ ' timestamp %s for origin with type %s' \ ' and url %s not found!' % (branch_type, branch, timestamp, origin_info['type'], origin_info['url']) raise NotFoundExc(escape(msg)) def _process_snapshot_request(request, snapshot_id=None, origin_type=None, origin_url=None, timestamp=None, path=None, browse_context='directory'): """ Utility function to perform common input request processing for snapshot context views. """ visit_id = request.GET.get('visit_id', None) snapshot_context = get_snapshot_context(snapshot_id, origin_type, origin_url, timestamp, visit_id) swh_type = snapshot_context['swh_type'] origin_info = snapshot_context['origin_info'] branches = snapshot_context['branches'] releases = snapshot_context['releases'] url_args = snapshot_context['url_args'] query_params = snapshot_context['query_params'] if snapshot_context['visit_info']: timestamp = format_utc_iso_date(snapshot_context['visit_info']['date'], '%Y-%m-%dT%H:%M:%SZ') snapshot_context['timestamp'] = \ format_utc_iso_date(snapshot_context['visit_info']['date']) browse_view_name = 'browse-' + swh_type + '-' + browse_context root_sha1_git = None revision_id = request.GET.get('revision', None) release_name = request.GET.get('release', None) release_id = None branch_name = None snapshot_total_size = sum(snapshot_context['snapshot_size'].values()) if snapshot_total_size and revision_id: revision = service.lookup_revision(revision_id) root_sha1_git = revision['directory'] branches.append({'name': revision_id, 'revision': revision_id, 'directory': root_sha1_git, 'url': None}) branch_name = revision_id query_params['revision'] = revision_id elif snapshot_total_size and release_name: release = _get_release(releases, release_name) try: root_sha1_git = release['directory'] revision_id = release['target'] release_id = release['id'] query_params['release'] = release_name except Exception: _branch_not_found("release", release_name, releases, snapshot_id, origin_info, timestamp, visit_id) elif snapshot_total_size: branch_name = request.GET.get('branch', None) if branch_name: query_params['branch'] = branch_name branch = _get_branch(branches, branch_name or 'HEAD', snapshot_context['snapshot_id']) try: branch_name = branch['name'] revision_id = branch['revision'] root_sha1_git = branch['directory'] except Exception: _branch_not_found("branch", branch_name, branches, snapshot_id, origin_info, timestamp, visit_id) for b in branches: branch_url_args = dict(url_args) branch_query_params = dict(query_params) if 'release' in branch_query_params: del branch_query_params['release'] branch_query_params['branch'] = b['name'] if path: b['path'] = path branch_url_args['path'] = path b['url'] = reverse(browse_view_name, url_args=branch_url_args, query_params=branch_query_params) for r in releases: release_url_args = dict(url_args) release_query_params = dict(query_params) if 'branch' in release_query_params: del release_query_params['branch'] release_query_params['release'] = r['name'] if path: r['path'] = path release_url_args['path'] = path r['url'] = reverse(browse_view_name, url_args=release_url_args, query_params=release_query_params) snapshot_context['query_params'] = query_params snapshot_context['root_sha1_git'] = root_sha1_git snapshot_context['revision_id'] = revision_id snapshot_context['branch'] = branch_name snapshot_context['release'] = release_name snapshot_context['release_id'] = release_id return snapshot_context def browse_snapshot_directory(request, snapshot_id=None, origin_type=None, origin_url=None, timestamp=None, path=None): """ Django view implementation for browsing a directory in a snapshot context. """ try: snapshot_context = _process_snapshot_request(request, snapshot_id, origin_type, origin_url, timestamp, path, browse_context='directory') # noqa root_sha1_git = snapshot_context['root_sha1_git'] sha1_git = root_sha1_git if root_sha1_git and path: dir_info = service.lookup_directory_with_path(root_sha1_git, path) sha1_git = dir_info['target'] dirs = [] files = [] if sha1_git: dirs, files = get_directory_entries(sha1_git) except Exception as exc: return handle_view_exception(request, exc) swh_type = snapshot_context['swh_type'] origin_info = snapshot_context['origin_info'] visit_info = snapshot_context['visit_info'] url_args = snapshot_context['url_args'] query_params = snapshot_context['query_params'] revision_id = snapshot_context['revision_id'] snapshot_id = snapshot_context['snapshot_id'] path_info = gen_path_info(path) browse_view_name = 'browse-' + swh_type + '-directory' breadcrumbs = [] if root_sha1_git: breadcrumbs.append({'name': root_sha1_git[:7], 'url': reverse(browse_view_name, url_args=url_args, query_params=query_params)}) for pi in path_info: bc_url_args = dict(url_args) bc_url_args['path'] = pi['path'] breadcrumbs.append({'name': pi['name'], 'url': reverse(browse_view_name, url_args=bc_url_args, query_params=query_params)}) path = '' if path is None else (path + '/') for d in dirs: if d['type'] == 'rev': d['url'] = reverse('browse-revision', url_args={'sha1_git': d['target']}) else: bc_url_args = dict(url_args) bc_url_args['path'] = path + d['name'] d['url'] = reverse(browse_view_name, url_args=bc_url_args, query_params=query_params) sum_file_sizes = 0 readmes = {} browse_view_name = 'browse-' + swh_type + '-content' for f in files: bc_url_args = dict(url_args) bc_url_args['path'] = path + f['name'] f['url'] = reverse(browse_view_name, url_args=bc_url_args, query_params=query_params) if f['length'] is not None: sum_file_sizes += f['length'] f['length'] = filesizeformat(f['length']) if f['name'].lower().startswith('readme'): readmes[f['name']] = f['checksums']['sha1'] readme_name, readme_url, readme_html = get_readme_to_display(readmes) browse_view_name = 'browse-' + swh_type + '-log' history_url = None if snapshot_id != _empty_snapshot_id: history_url = reverse(browse_view_name, url_args=url_args, query_params=query_params) nb_files = None nb_dirs = None dir_path = None if root_sha1_git: nb_files = len(files) nb_dirs = len(dirs) sum_file_sizes = filesizeformat(sum_file_sizes) dir_path = '/' + path browse_dir_link = gen_directory_link(sha1_git) browse_rev_link = gen_revision_link(revision_id) browse_snp_link = gen_snapshot_link(snapshot_id) dir_metadata = {'directory': sha1_git, 'context-independent directory': browse_dir_link, 'number of regular files': nb_files, 'number of subdirectories': nb_dirs, 'sum of regular file sizes': sum_file_sizes, 'path': dir_path, 'revision': revision_id, 'context-independent revision': browse_rev_link, 'snapshot': snapshot_id, 'context-independent snapshot': browse_snp_link} if origin_info: dir_metadata['origin type'] = origin_info['type'] dir_metadata['origin url'] = origin_info['url'] dir_metadata['origin visit date'] = format_utc_iso_date(visit_info['date']) # noqa vault_cooking = { 'directory_context': True, 'directory_id': sha1_git, 'revision_context': True, 'revision_id': revision_id } swh_objects = [{'type': 'directory', 'id': sha1_git}, {'type': 'revision', 'id': revision_id}, {'type': 'snapshot', 'id': snapshot_id}] release_id = snapshot_context['release_id'] if release_id: swh_objects.append({'type': 'release', 'id': release_id}) swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) dir_path = '/'.join([bc['name'] for bc in breadcrumbs]) + '/' context_found = 'snapshot: %s' % snapshot_context['snapshot_id'] if origin_info: context_found = 'origin: %s' % origin_info['url'] heading = 'Directory - %s - %s - %s' %\ (dir_path, snapshot_context['branch'], context_found) return render(request, 'browse/directory.html', {'heading': heading, 'swh_object_name': 'Directory', 'swh_object_metadata': dir_metadata, 'dirs': dirs, 'files': files, 'breadcrumbs': breadcrumbs if root_sha1_git else [], 'top_right_link': { 'url': history_url, 'icon': swh_object_icons['revisions history'], 'text': 'History' }, 'readme_name': readme_name, 'readme_url': readme_url, 'readme_html': readme_html, 'snapshot_context': snapshot_context, 'vault_cooking': vault_cooking, 'show_actions_menu': True, 'swh_ids': swh_ids}) def browse_snapshot_content(request, snapshot_id=None, origin_type=None, origin_url=None, timestamp=None, path=None, selected_language=None): """ Django view implementation for browsing a content in a snapshot context. """ try: snapshot_context = _process_snapshot_request(request, snapshot_id, origin_type, origin_url, timestamp, path, browse_context='content') root_sha1_git = snapshot_context['root_sha1_git'] sha1_git = None query_string = None content_data = None split_path = path.split('/') filename = split_path[-1] filepath = path[:-len(filename)] if root_sha1_git: content_info = service.lookup_directory_with_path(root_sha1_git, path) sha1_git = content_info['target'] query_string = 'sha1_git:' + sha1_git content_data = request_content(query_string, raise_if_unavailable=False) if filepath: dir_info = service.lookup_directory_with_path(root_sha1_git, filepath) directory_id = dir_info['target'] else: directory_id = root_sha1_git except Exception as exc: return handle_view_exception(request, exc) swh_type = snapshot_context['swh_type'] url_args = snapshot_context['url_args'] query_params = snapshot_context['query_params'] revision_id = snapshot_context['revision_id'] origin_info = snapshot_context['origin_info'] visit_info = snapshot_context['visit_info'] snapshot_id = snapshot_context['snapshot_id'] content = None language = None mimetype = None if content_data and content_data['raw_data'] is not None: content_display_data = prepare_content_for_display( content_data['raw_data'], content_data['mimetype'], path) content = content_display_data['content_data'] language = content_display_data['language'] mimetype = content_display_data['mimetype'] # Override language with user-selected language if selected_language is not None: language = selected_language available_languages = None if mimetype and 'text/' in mimetype: - available_languages = highlightjs._hljs_languages + available_languages = highlightjs.get_supported_languages() browse_view_name = 'browse-' + swh_type + '-directory' breadcrumbs = [] path_info = gen_path_info(filepath) if root_sha1_git: breadcrumbs.append({'name': root_sha1_git[:7], 'url': reverse(browse_view_name, url_args=url_args, query_params=query_params)}) for pi in path_info: bc_url_args = dict(url_args) bc_url_args['path'] = pi['path'] breadcrumbs.append({'name': pi['name'], 'url': reverse(browse_view_name, url_args=bc_url_args, query_params=query_params)}) breadcrumbs.append({'name': filename, 'url': None}) browse_content_link = gen_content_link(sha1_git) content_raw_url = None if query_string: content_raw_url = reverse('browse-content-raw', url_args={'query_string': query_string}, query_params={'filename': filename}) browse_rev_link = gen_revision_link(revision_id) browse_dir_link = gen_directory_link(directory_id) content_metadata = { 'context-independent content': browse_content_link, 'path': None, 'filename': None, 'directory': directory_id, 'context-independent directory': browse_dir_link, 'revision': revision_id, 'context-independent revision': browse_rev_link, 'snapshot': snapshot_id } cnt_sha1_git = None content_size = None error_code = 200 error_description = '' error_message = '' if content_data: content_metadata['sha1'] = \ content_data['checksums']['sha1'] content_metadata['sha1_git'] = \ content_data['checksums']['sha1_git'] content_metadata['sha256'] = \ content_data['checksums']['sha256'] content_metadata['blake2s256'] = \ content_data['checksums']['blake2s256'] content_metadata['mimetype'] = content_data['mimetype'] content_metadata['encoding'] = content_data['encoding'] content_metadata['size'] = filesizeformat(content_data['length']) content_metadata['language'] = content_data['language'] content_metadata['licenses'] = content_data['licenses'] content_metadata['path'] = '/' + filepath content_metadata['filename'] = filename cnt_sha1_git = content_data['checksums']['sha1_git'] content_size = content_data['length'] error_code = content_data['error_code'] error_message = content_data['error_message'] error_description = content_data['error_description'] if origin_info: content_metadata['origin type'] = origin_info['type'] content_metadata['origin url'] = origin_info['url'] content_metadata['origin visit date'] = format_utc_iso_date(visit_info['date']) # noqa browse_snapshot_link = gen_snapshot_link(snapshot_id) content_metadata['context-independent snapshot'] = browse_snapshot_link swh_objects = [{'type': 'content', 'id': cnt_sha1_git}, {'type': 'revision', 'id': revision_id}, {'type': 'snapshot', 'id': snapshot_id}] release_id = snapshot_context['release_id'] if release_id: swh_objects.append({'type': 'release', 'id': release_id}) swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) content_path = '/'.join([bc['name'] for bc in breadcrumbs]) context_found = 'snapshot: %s' % snapshot_context['snapshot_id'] if origin_info: context_found = 'origin: %s' % origin_info['url'] heading = 'Content - %s - %s - %s' %\ (content_path, snapshot_context['branch'], context_found) return render(request, 'browse/content.html', {'heading': heading, 'swh_object_name': 'Content', 'swh_object_metadata': content_metadata, 'content': content, 'content_size': content_size, 'max_content_size': content_display_max_size, 'mimetype': mimetype, 'language': language, 'available_languages': available_languages, 'breadcrumbs': breadcrumbs if root_sha1_git else [], '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, 'error_code': error_code, 'error_message': error_message, 'error_description': error_description}, status=error_code) PER_PAGE = 100 def browse_snapshot_log(request, snapshot_id=None, origin_type=None, origin_url=None, timestamp=None): """ Django view implementation for browsing a revision history in a snapshot context. """ try: snapshot_context = _process_snapshot_request(request, snapshot_id, origin_type, origin_url, timestamp, browse_context='log') # noqa revision_id = snapshot_context['revision_id'] per_page = int(request.GET.get('per_page', PER_PAGE)) offset = int(request.GET.get('offset', 0)) revs_ordering = request.GET.get('revs_ordering', 'committer_date') session_key = 'rev_%s_log_ordering_%s' % (revision_id, revs_ordering) rev_log_session = request.session.get(session_key, None) rev_log = [] revs_walker_state = None if rev_log_session: rev_log = rev_log_session['rev_log'] revs_walker_state = rev_log_session['revs_walker_state'] if len(rev_log) < offset+per_page: revs_walker = \ service.get_revisions_walker(revs_ordering, revision_id, max_revs=offset+per_page+1, state=revs_walker_state) rev_log += [rev['id'] for rev in revs_walker] revs_walker_state = revs_walker.export_state() revs = rev_log[offset:offset+per_page] revision_log = service.lookup_revision_multiple(revs) request.session[session_key] = { 'rev_log': rev_log, 'revs_walker_state': revs_walker_state } except Exception as exc: return handle_view_exception(request, exc) swh_type = snapshot_context['swh_type'] origin_info = snapshot_context['origin_info'] visit_info = snapshot_context['visit_info'] url_args = snapshot_context['url_args'] query_params = snapshot_context['query_params'] snapshot_id = snapshot_context['snapshot_id'] query_params['per_page'] = per_page revs_ordering = request.GET.get('revs_ordering', '') query_params['revs_ordering'] = revs_ordering browse_view_name = 'browse-' + swh_type + '-log' 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 type'] = origin_info['type'] revision_metadata['origin url'] = origin_info['url'] revision_metadata['origin visit date'] = format_utc_iso_date(visit_info['date']) # noqa swh_objects = [{'type': 'revision', 'id': revision_id}, {'type': 'snapshot', 'id': snapshot_id}] release_id = snapshot_context['release_id'] if release_id: swh_objects.append({'type': 'release', 'id': release_id}) swh_ids = get_swh_persistent_ids(swh_objects, snapshot_context) context_found = 'snapshot: %s' % snapshot_context['snapshot_id'] if origin_info: context_found = 'origin: %s' % origin_info['url'] heading = 'Revision history - %s - %s' %\ (snapshot_context['branch'], context_found) return render(request, 'browse/revision-log.html', {'heading': heading, 'swh_object_name': 'Revisions history', 'swh_object_metadata': revision_metadata, 'revision_log': revision_log_data, 'revs_ordering': revs_ordering, 'next_log_url': next_log_url, 'prev_log_url': prev_log_url, 'breadcrumbs': None, 'top_right_link': None, 'snapshot_context': snapshot_context, 'vault_cooking': None, 'show_actions_menu': True, 'swh_ids': swh_ids}) def browse_snapshot_branches(request, snapshot_id=None, origin_type=None, origin_url=None, timestamp=None): """ Django view implementation for browsing a list of branches in a snapshot context. """ try: snapshot_context = _process_snapshot_request(request, snapshot_id, origin_type, origin_url, timestamp) branches_bc = request.GET.get('branches_breadcrumbs', '') branches_bc = \ branches_bc.split(',') if branches_bc else [] branches_from = branches_bc[-1] if branches_bc else '' swh_type = snapshot_context['swh_type'] origin_info = snapshot_context['origin_info'] url_args = snapshot_context['url_args'] query_params = snapshot_context['query_params'] browse_view_name = 'browse-' + swh_type + '-directory' 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_type': origin_type, 'origin': origin_info['url']}) query_params['branch'] = branch['name'] directory_url = reverse(browse_view_name, url_args=url_args, query_params=query_params) del query_params['branch'] branch['revision_url'] = revision_url branch['directory_url'] = directory_url browse_view_name = 'browse-' + swh_type + '-branches' 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 len(displayed_branches) > PER_PAGE: 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_type=None, origin_url=None, timestamp=None): """ Django view implementation for browsing a list of releases in a snapshot context. """ try: snapshot_context = _process_snapshot_request(request, snapshot_id, origin_type, origin_url, timestamp) rel_bc = request.GET.get('releases_breadcrumbs', '') rel_bc = \ rel_bc.split(',') if rel_bc else [] rel_from = rel_bc[-1] if rel_bc else '' swh_type = snapshot_context['swh_type'] origin_info = snapshot_context['origin_info'] url_args = snapshot_context['url_args'] query_params = snapshot_context['query_params'] snapshot = \ service.lookup_snapshot(snapshot_context['snapshot_id'], rel_from, PER_PAGE+1, target_types=['release', 'alias']) _, displayed_releases = process_snapshot_branches(snapshot) except Exception as exc: return handle_view_exception(request, exc) for release in displayed_releases: if snapshot_id: query_params_tgt = {'snapshot_id': snapshot_id} else: query_params_tgt = {'origin': origin_info['url']} release_url = reverse('browse-release', url_args={'sha1_git': release['id']}, query_params=query_params_tgt) target_url = '' if release['target_type'] == 'revision': target_url = reverse('browse-revision', url_args={'sha1_git': release['target']}, query_params=query_params_tgt) elif release['target_type'] == 'directory': target_url = reverse('browse-directory', url_args={'sha1_git': release['target']}, query_params=query_params_tgt) elif release['target_type'] == 'content': target_url = reverse('browse-content', url_args={'query_string': release['target']}, query_params=query_params_tgt) elif release['target_type'] == 'release': target_url = reverse('browse-release', url_args={'sha1_git': release['target']}, query_params=query_params_tgt) release['release_url'] = release_url release['target_url'] = target_url browse_view_name = 'browse-' + swh_type + '-releases' 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 len(displayed_releases) > PER_PAGE: 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/common/highlightjs.py b/swh/web/common/highlightjs.py index e9debf97..e2e3779b 100644 --- a/swh/web/common/highlightjs.py +++ b/swh/web/common/highlightjs.py @@ -1,298 +1,312 @@ # 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 functools + from pygments.lexers import ( get_all_lexers, get_lexer_for_filename ) # set of languages ids that can be highlighted # by highlight.js library _hljs_languages = set([ '1c', 'abnf', 'accesslog', 'actionscript', 'ada', 'angelscript', 'apache', 'applescript', 'arcade', 'arduino', 'armasm', 'asciidoc', 'aspectj', 'autohotkey', 'autoit', 'avrasm', 'awk', 'axapta', 'bash', 'basic', 'bnf', 'brainfuck', 'cal', 'capnproto', 'ceylon', 'clean', 'clojure', 'clojure-repl', 'cmake', 'coffeescript', 'coq', 'cos', 'cpp', 'crmsh', 'crystal', 'cs', 'csp', 'css', 'd', 'dart', 'delphi', 'diff', 'django', 'dns', 'dockerfile', 'dos', 'dsconfig', 'dts', 'dust', 'ebnf', 'elixir', 'elm', 'erb', 'erlang', 'erlang-repl', 'excel', 'fix', 'flix', 'fortran', 'fsharp', 'gams', 'gauss', 'gcode', 'gherkin', 'glsl', 'gml', 'go', 'golo', 'gradle', 'groovy', 'haml', 'handlebars', 'haskell', 'haxe', 'hsp', 'htmlbars', 'http', 'hy', 'inform7', 'ini', 'irpf90', 'isbl', 'java', 'javascript', 'jboss-cli', 'json', 'julia', 'julia-repl', 'kotlin', 'lasso', 'ldif', 'leaf', 'less', 'lisp', 'livecodeserver', 'livescript', 'llvm', 'lsl', 'lua', 'makefile', 'markdown', 'mathematica', 'matlab', 'maxima', 'mel', 'mercury', 'mipsasm', 'mizar', 'mojolicious', 'monkey', 'moonscript', 'n1ql', 'nginx', 'nimrod', 'nix', 'nsis', 'objectivec', 'ocaml', 'openscad', 'oxygene', 'parser3', 'perl', 'pf', 'pgsql', 'php', 'plaintext', 'pony', 'powershell', 'processing', 'profile', 'prolog', 'properties', 'protobuf', 'puppet', 'purebasic', 'python', 'q', 'qml', 'r', 'reasonml', 'rib', 'roboconf', 'routeros', 'rsl', 'ruby', 'ruleslanguage', 'rust', 'sas', 'scala', 'scheme', 'scilab', 'scss', 'shell', 'smali', 'smalltalk', 'sml', 'sqf', 'sql', 'stan', 'stata', 'step21', 'stylus', 'subunit', 'swift', 'taggerscript', 'tap', 'tcl', 'tex', 'thrift', 'tp', 'twig', 'typescript', 'vala', 'vbnet', 'vbscript', 'vbscript-html', 'verilog', 'vhdl', 'vim', 'x86asm', 'xl', 'xml', 'xquery', 'yaml', 'zephir' ]) # languages aliases defined in highlight.js _hljs_languages_aliases = { 'ado': 'stata', 'adoc': 'asciidoc', 'ahk': 'autohotkey', 'apacheconf': 'apache', 'arm': 'armasm', 'as': 'actionscript', 'asc': 'angelscript', 'atom': 'xml', 'bat': 'dos', 'bf': 'brainfuck', 'bind': 'dns', 'c': 'cpp', 'c++': 'cpp', 'capnp': 'capnproto', 'cc': 'cpp', 'clj': 'clojure', 'cls': 'cos', 'cmake.in': 'cmake', 'cmd': 'dos', 'coffee': 'coffeescript', 'console': 'shell', 'cr': 'crystal', 'craftcms': 'twig', 'crm': 'crmsh', 'csharp': 'cs', 'cson': 'coffeescript', 'dcl': 'clean', 'dfm': 'delphi', 'do': 'stata', 'docker': 'dockerfile', 'dpr': 'delphi', 'dst': 'dust', 'erl': 'erlang', 'f90': 'fortran', 'f95': 'fortran', 'feature': 'gherkin', 'freepascal': 'delphi', 'fs': 'fsharp', 'gemspec': 'ruby', 'GML': 'gml', 'gms': 'gams', 'golang': 'go', 'graph': 'roboconf', 'gss': 'gauss', 'gyp': 'python', 'h': 'cpp', 'h++': 'cpp', 'hbs': 'handlebars', 'hpp': 'cpp', 'hs': 'haskell', 'html': 'xml', 'html.handlebars': 'handlebars', 'html.hbs': 'handlebars', 'https': 'http', 'hx': 'haxe', 'hylang': 'hy', 'i7': 'inform7', 'iced': 'coffeescript', 'icl': 'clean', 'instances': 'roboconf', 'ipynb': 'json', 'irb': 'ruby', 'jinja': 'django', 'js': 'javascript', 'jsp': 'java', 'jsx': 'javascript', 'k': 'q', 'kdb': 'q', 'kt': 'kotlin', 'lassoscript': 'lasso', 'lazarus': 'delphi', 'lfm': 'delphi', 'lpr': 'delphi', 'ls': 'livescript', 'm': 'mercury', 'mak': 'makefile', 'md': 'markdown', 'mikrotik': 'routeros', 'mips': 'mipsasm', 'mk': 'makefile', 'mkd': 'markdown', 'mkdown': 'markdown', 'ml': 'ocaml', 'mm': 'objectivec', 'mma': 'mathematica', 'moo': 'mercury', 'moon': 'moonscript', 'nc': 'gcode', 'nginxconf': 'nginx', 'nim': 'nimrod', 'nixos': 'nix', 'obj-c': 'objectivec', 'objc': 'objectivec', 'osascript': 'applescript', 'p21': 'step21', 'pas': 'delphi', 'pascal': 'delphi', 'patch': 'diff', 'pb': 'purebasic', 'pbi': 'purebasic', 'pcmk': 'crmsh', 'pf.conf': 'pf', 'php3': 'php', 'php4': 'php', 'php5': 'php', 'php6': 'php', 'php7': 'php', 'pl': 'perl', 'plist': 'xml', 'pm': 'perl', 'podspec': 'ruby', 'postgres': 'pgsql', 'postgresql': 'pgsql', 'pp': 'puppet', 'ps': 'powershell', 'py': 'python', 'qt': 'qml', 'rb': 'ruby', 're': 'reasonml', 'rs': 'rust', 'rss': 'xml', 'rst': 'nohighlight', 'SAS': 'sas', 'scad': 'openscad', 'sci': 'scilab', 'sh': 'bash', 'st': 'smalltalk', 'step': 'step21', 'stp': 'step21', 'styl': 'stylus', 'sv': 'verilog', 'svh': 'verilog', 'tao': 'xl', 'thor': 'ruby', 'tk': 'tcl', 'toml': 'ini', 'ts': 'typescript', 'txt': 'nohighlight', 'v': 'verilog', 'vb': 'vbnet', 'vbs': 'vbscript', 'wildfly-cli': 'jboss-cli', 'xhtml': 'xml', 'xjb': 'xml', 'xls': 'excel', 'xlsx': 'excel', 'xpath': 'xquery', 'xq': 'xquery', 'xsd': 'xml', 'xsl': 'xml', 'YAML': 'yaml', 'yml': 'yaml', 'zep': 'zephir', 'zone': 'dns', 'zsh': 'bash' } # dictionary mapping pygment lexers to hljs languages _pygments_lexer_to_hljs_language = {} # dictionary mapping mime types to hljs languages _mime_type_to_hljs_language = { 'text/x-c': 'cpp', 'text/x-c++': 'cpp', 'text/x-msdos-batch': 'dos', 'text/x-lisp': 'lisp', 'text/x-shellscript': 'bash', } # dictionary mapping filenames to hljs languages _filename_to_hljs_language = { 'cmakelists.txt': 'cmake' } # function to fill the above dictionaries def _init_pygments_to_hljs_map(): if len(_pygments_lexer_to_hljs_language) == 0: for lexer in get_all_lexers(): lexer_name = lexer[0] lang_aliases = lexer[1] lang_mime_types = lexer[3] lang = None for lang_alias in lang_aliases: if lang_alias in _hljs_languages: lang = lang_alias _pygments_lexer_to_hljs_language[lexer_name] = lang_alias break if lang: for lang_mime_type in lang_mime_types: _mime_type_to_hljs_language[lang_mime_type] = lang def get_hljs_language_from_filename(filename): """Function that tries to associate a language supported by highlight.js from a filename. Args: filename: input filename Returns: highlight.js language id or None if no correspondence has been found """ _init_pygments_to_hljs_map() if filename: filename_lower = filename.lower() if filename_lower in _filename_to_hljs_language: return _filename_to_hljs_language[filename_lower] exts = filename_lower.split('.') # check if file extension matches an hljs language # also handle .ext.in cases for ext in reversed(exts[-2:]): if ext in _hljs_languages: return ext if ext in _hljs_languages_aliases: return _hljs_languages_aliases[ext] # otherwise use Pygments language database lexer = None # try to find a Pygment lexer try: lexer = get_lexer_for_filename(filename) except Exception: pass # if there is a correspondence between the lexer and an hljs # language, return it if lexer and lexer.name in _pygments_lexer_to_hljs_language: return _pygments_lexer_to_hljs_language[lexer.name] # otherwise, try to find a match between the file extensions # associated to the lexer and the hljs language aliases if lexer: exts = [ext.replace('*.', '') for ext in lexer.filenames] for ext in exts: if ext in _hljs_languages_aliases: return _hljs_languages_aliases[ext] return None def get_hljs_language_from_mime_type(mime_type): """Function that tries to associate a language supported by highlight.js from a mime type. Args: mime_type: input mime type Returns: highlight.js language id or None if no correspondence has been found """ _init_pygments_to_hljs_map() if mime_type and mime_type in _mime_type_to_hljs_language: return _mime_type_to_hljs_language[mime_type] return None + + +@functools.lru_cache() +def get_supported_languages(): + """ + Return the list of programming languages that can be highlighted using the + highlight.js library. + + Returns: + List[str]: the list of supported languages + """ + return sorted(list(_hljs_languages))