diff --git a/swh/web/ui/templates/content.html b/swh/web/ui/templates/content.html index 406933db..2da5bd02 100644 --- a/swh/web/ui/templates/content.html +++ b/swh/web/ui/templates/content.html @@ -1,27 +1,28 @@ {% extends "layout.html" %} {% block title %}Content information{% endblock %} + {% block content %} {% if message is not none %} -

{{ message | safe }}

+

{{ message }}

{% endif %} {% if content is not none %} {% for key in ['sha1', 'sha256', 'sha1_git', 'status', 'length', 'ctime'] %}
{{ key }}
{{ content[key] }}
{% endfor %} {% if content['data_url'] is not none %}
data_url
Download data
{% endif %} {% if content['data'] is not none %}
data
{{ content['data'] }}
{% endif %} {% endif %} {% endblock %} diff --git a/swh/web/ui/tests/test_utils.py b/swh/web/ui/tests/test_utils.py index 6f424724..efe58d38 100644 --- a/swh/web/ui/tests/test_utils.py +++ b/swh/web/ui/tests/test_utils.py @@ -1,559 +1,560 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import dateutil import unittest from unittest.mock import patch, call from nose.tools import istest from swh.web.ui import utils class UtilsTestCase(unittest.TestCase): def setUp(self): self.url_map = [dict(rule='/other/', methods=set(['GET', 'POST', 'HEAD']), endpoint='foo'), dict(rule='/some/old/url/', methods=set(['GET', 'POST']), endpoint='blablafn'), dict(rule='/other/old/url/', methods=set(['GET', 'HEAD']), endpoint='bar'), dict(rule='/other', methods=set([]), endpoint=None), dict(rule='/other2', methods=set([]), endpoint=None)] @istest def filter_endpoints_1(self): # when actual_data = utils.filter_endpoints(self.url_map, '/some') # then self.assertEquals(actual_data, { '/some/old/url/': { 'methods': ['GET', 'POST'], 'endpoint': 'blablafn' } }) @istest def filter_endpoints_2(self): # when actual_data = utils.filter_endpoints(self.url_map, '/other', blacklist=['/other2']) # then # rules /other is skipped because its' exactly the prefix url # rules /other2 is skipped because it's blacklisted self.assertEquals(actual_data, { '/other/': { 'methods': ['GET', 'HEAD', 'POST'], 'endpoint': 'foo' }, '/other/old/url/': { 'methods': ['GET', 'HEAD'], 'endpoint': 'bar' } }) @istest def prepare_data_for_view_default_encoding(self): self.maxDiff = None # given inputs = [ { 'data': b'some blah data' }, { 'data': 1, 'data_url': '/api/1/some/api/call', }, { 'blah': 'foobar', 'blah_url': '/some/non/changed/api/call' }] # when actual_result = utils.prepare_data_for_view(inputs) # then self.assertEquals(actual_result, [ { 'data': 'some blah data', }, { 'data': 1, 'data_url': '/browse/some/api/call', }, { 'blah': 'foobar', 'blah_url': '/some/non/changed/api/call' } ]) @istest def prepare_data_for_view(self): self.maxDiff = None # given inputs = [ { 'data': b'some blah data' }, { 'data': 1, 'data_url': '/api/1/some/api/call', }, { 'blah': 'foobar', 'blah_url': '/some/non/changed/api/call' }] # when actual_result = utils.prepare_data_for_view(inputs, encoding='ascii') # then self.assertEquals(actual_result, [ { 'data': 'some blah data', }, { 'data': 1, 'data_url': '/browse/some/api/call', }, { 'blah': 'foobar', 'blah_url': '/some/non/changed/api/call' } ]) @istest def prepare_data_for_view_KO_cannot_decode(self): self.maxDiff = None # given inputs = { - 'data': 'hé dude!'.encode('utf-8'), + 'data': 'hé dude!'.encode('utf8'), } actual_result = utils.prepare_data_for_view(inputs, encoding='ascii') # then self.assertEquals(actual_result, { - 'data': "Cannot decode the data bytes, try and set another" - " encoding in the url or download directly the " + 'data': "Cannot decode the data bytes, try and set another " + "encoding in the url (e.g. ?encoding=utf8) or " + "download directly the " "content's raw data.", }) @istest def filter_field_keys_dict_unknown_keys(self): # when actual_res = utils.filter_field_keys( {'directory': 1, 'file': 2, 'link': 3}, {'directory1', 'file2'}) # then self.assertEqual(actual_res, {}) @istest def filter_field_keys_dict(self): # when actual_res = utils.filter_field_keys( {'directory': 1, 'file': 2, 'link': 3}, {'directory', 'link'}) # then self.assertEqual(actual_res, {'directory': 1, 'link': 3}) @istest def filter_field_keys_list_unknown_keys(self): # when actual_res = utils.filter_field_keys( [{'directory': 1, 'file': 2, 'link': 3}, {'1': 1, '2': 2, 'link': 3}], {'d'}) # then self.assertEqual(actual_res, [{}, {}]) @istest def filter_field_keys_list(self): # when actual_res = utils.filter_field_keys( [{'directory': 1, 'file': 2, 'link': 3}, {'dir': 1, 'fil': 2, 'lin': 3}], {'directory', 'dir'}) # then self.assertEqual(actual_res, [{'directory': 1}, {'dir': 1}]) @istest def filter_field_keys_other(self): # given input_set = {1, 2} # when actual_res = utils.filter_field_keys(input_set, {'a', '1'}) # then self.assertEqual(actual_res, input_set) @istest def fmap(self): self.assertEquals([2, 3, 4], utils.fmap(lambda x: x+1, [1, 2, 3])) self.assertEquals([11, 12, 13], list(utils.fmap(lambda x: x+10, map(lambda x: x, [1, 2, 3])))) self.assertEquals({'a': 2, 'b': 4}, utils.fmap(lambda x: x*2, {'a': 1, 'b': 2})) self.assertEquals(100, utils.fmap(lambda x: x*10, 10)) self.assertEquals({'a': [2, 6], 'b': 4}, utils.fmap(lambda x: x*2, {'a': [1, 3], 'b': 2})) @istest def person_to_string(self): self.assertEqual(utils.person_to_string(dict(name='raboof', email='foo@bar')), 'raboof ') @istest def parse_timestamp(self): input_timestamps = [ '2016-01-12', '2016-01-12T09:19:12+0100', 'Today is January 1, 2047 at 8:21:00AM', '1452591542', ] output_dates = [ datetime.datetime(2016, 1, 12, 0, 0), datetime.datetime(2016, 1, 12, 9, 19, 12, tzinfo=dateutil.tz.tzoffset(None, 3600)), datetime.datetime(2047, 1, 1, 8, 21), datetime.datetime(2016, 1, 12, 10, 39, 2), ] for ts, exp_date in zip(input_timestamps, output_dates): self.assertEquals(utils.parse_timestamp(ts), exp_date) @istest def enrich_release_0(self): # when actual_release = utils.enrich_release({}) # then self.assertEqual(actual_release, {}) @patch('swh.web.ui.utils.flask') @istest def enrich_release_1(self, mock_flask): # given mock_flask.url_for.return_value = '/api/1/content/sha1_git:123/' # when actual_release = utils.enrich_release({'target': '123', 'target_type': 'content'}) # then self.assertEqual(actual_release, { 'target': '123', 'target_type': 'content', 'target_url': '/api/1/content/sha1_git:123/' }) mock_flask.url_for.assert_called_once_with('api_content_metadata', q='sha1_git:123') @patch('swh.web.ui.utils.flask') @istest def enrich_release_2(self, mock_flask): # given mock_flask.url_for.return_value = '/api/1/dir/23/' # when actual_release = utils.enrich_release({'target': '23', 'target_type': 'directory'}) # then self.assertEqual(actual_release, { 'target': '23', 'target_type': 'directory', 'target_url': '/api/1/dir/23/' }) mock_flask.url_for.assert_called_once_with('api_directory', q='23') @patch('swh.web.ui.utils.flask') @istest def enrich_release_3(self, mock_flask): # given mock_flask.url_for.return_value = '/api/1/rev/3/' # when actual_release = utils.enrich_release({'target': '3', 'target_type': 'revision'}) # then self.assertEqual(actual_release, { 'target': '3', 'target_type': 'revision', 'target_url': '/api/1/rev/3/' }) mock_flask.url_for.assert_called_once_with('api_revision', sha1_git='3') @patch('swh.web.ui.utils.flask') @istest def enrich_release_4(self, mock_flask): # given mock_flask.url_for.return_value = '/api/1/rev/4/' # when actual_release = utils.enrich_release({'target': '4', 'target_type': 'release'}) # then self.assertEqual(actual_release, { 'target': '4', 'target_type': 'release', 'target_url': '/api/1/rev/4/' }) mock_flask.url_for.assert_called_once_with('api_release', sha1_git='4') @patch('swh.web.ui.utils.flask') @istest def enrich_directory_no_type(self, mock_flask): # when/then self.assertEqual(utils.enrich_directory({'id': 'dir-id'}), {'id': 'dir-id'}) # given mock_flask.url_for.return_value = '/api/content/sha1_git:123/' # when actual_directory = utils.enrich_directory({ 'id': 'dir-id', 'type': 'file', 'target': '123', }) # then self.assertEqual(actual_directory, { 'id': 'dir-id', 'type': 'file', 'target': '123', 'target_url': '/api/content/sha1_git:123/', }) mock_flask.url_for.assert_called_once_with('api_content_metadata', q='sha1_git:123') @patch('swh.web.ui.utils.flask') @istest def enrich_directory_with_context_and_type_file(self, mock_flask): # given mock_flask.url_for.return_value = '/api/content/sha1_git:123/' # when actual_directory = utils.enrich_directory({ 'id': 'dir-id', 'type': 'file', 'name': 'hy', 'target': '789', }, context_url='/api/revision/revsha1/directory/prefix/path/') # then self.assertEqual(actual_directory, { 'id': 'dir-id', 'type': 'file', 'name': 'hy', 'target': '789', 'target_url': '/api/content/sha1_git:123/', 'file_url': '/api/revision/revsha1/directory' '/prefix/path/hy/' }) mock_flask.url_for.assert_called_once_with('api_content_metadata', q='sha1_git:789') @patch('swh.web.ui.utils.flask') @istest def enrich_directory_with_context_and_type_dir(self, mock_flask): # given mock_flask.url_for.return_value = '/api/directory/456/' # when actual_directory = utils.enrich_directory({ 'id': 'dir-id', 'type': 'dir', 'name': 'emacs-42', 'target_type': 'file', 'target': '456', }, context_url='/api/revision/origin/2/directory/some/prefix/path/') # then self.assertEqual(actual_directory, { 'id': 'dir-id', 'type': 'dir', 'target_type': 'file', 'name': 'emacs-42', 'target': '456', 'target_url': '/api/directory/456/', 'dir_url': '/api/revision/origin/2/directory' '/some/prefix/path/emacs-42/' }) mock_flask.url_for.assert_called_once_with('api_directory', sha1_git='456') @istest def enrich_content_without_sha1(self): # when/then self.assertEqual(utils.enrich_content({'id': '123'}), {'id': '123'}) @patch('swh.web.ui.utils.flask') @istest def enrich_content_with_sha1(self, mock_flask): # given mock_flask.url_for.return_value = '/api/content/sha1:123/raw/' # when/then self.assertEqual(utils.enrich_content( {'id': '123', 'sha1': 'blahblah'}), {'id': '123', 'sha1': 'blahblah', 'data_url': '/api/content/sha1:123/raw/'}) mock_flask.url_for.assert_called_once_with('api_content_raw', q='blahblah') @istest def enrich_entity_identity(self): # when/then self.assertEqual(utils.enrich_content({'id': '123'}), {'id': '123'}) @patch('swh.web.ui.utils.flask') @istest def enrich_entity_with_sha1(self, mock_flask): # given def url_for_test(fn, **entity): return '/api/entity/' + entity['uuid'] + '/' mock_flask.url_for.side_effect = url_for_test # when actual_entity = utils.enrich_entity({ 'uuid': 'uuid-1', 'parent': 'uuid-parent', 'name': 'something' }) # then self.assertEqual(actual_entity, { 'uuid': 'uuid-1', 'uuid_url': '/api/entity/uuid-1/', 'parent': 'uuid-parent', 'parent_url': '/api/entity/uuid-parent/', 'name': 'something', }) mock_flask.url_for.assert_has_calls([call('api_entity_by_uuid', uuid='uuid-1'), call('api_entity_by_uuid', uuid='uuid-parent')]) @patch('swh.web.ui.utils.flask') @istest def enrich_revision_without_children_or_parent(self, mock_flask): # given def url_for_test(fn, **data): print(fn, data) if fn == 'api_revision': return '/api/revision/' + data['sha1_git'] + '/' elif fn == 'api_revision_log': return '/api/revision/' + data['sha1_git'] + '/log/' elif fn == 'api_directory': return '/api/directory/' + data['sha1_git'] + '/' mock_flask.url_for.side_effect = url_for_test # when actual_revision = utils.enrich_revision({ 'id': 'rev-id', 'directory': '123' }) # then self.assertEqual(actual_revision, { 'id': 'rev-id', 'directory': '123', 'url': '/api/revision/rev-id/', 'history_url': '/api/revision/rev-id/log/', 'directory_url': '/api/directory/123/' }) mock_flask.url_for.assert_has_calls([call('api_revision', sha1_git='rev-id'), call('api_revision_log', sha1_git='rev-id'), call('api_directory', sha1_git='123')]) @patch('swh.web.ui.utils.flask') @istest def enrich_revision_with_children_and_parent_no_dir(self, mock_flask): # given def url_for_test(fn, **data): print(fn, data) if fn == 'api_revision': return '/api/revision/' + data['sha1_git'] + '/' elif fn == 'api_revision_log': return '/api/revision/' + data['sha1_git'] + '/log/' else: return '/api/revision/' + data['sha1_git_root'] + '/history/' + data['sha1_git'] + '/' # noqa mock_flask.url_for.side_effect = url_for_test # when actual_revision = utils.enrich_revision({ 'id': 'rev-id', 'parents': ['123'], 'children': ['456'], }, context='sha1_git_root') # then self.assertEqual(actual_revision, { 'id': 'rev-id', 'url': '/api/revision/rev-id/', 'history_url': '/api/revision/rev-id/log/', 'parents': ['123'], 'parent_urls': ['/api/revision/sha1_git_root/history/123/'], 'children': ['456'], 'children_urls': ['/api/revision/sha1_git_root/history/456/'], }) mock_flask.url_for.assert_has_calls( [call('api_revision', sha1_git='rev-id'), call('api_revision_log', sha1_git='rev-id'), call('api_revision_history', sha1_git_root='sha1_git_root', sha1_git='123'), call('api_revision_history', sha1_git_root='sha1_git_root', sha1_git='456')]) diff --git a/swh/web/ui/utils.py b/swh/web/ui/utils.py index 31721c07..efda2a0a 100644 --- a/swh/web/ui/utils.py +++ b/swh/web/ui/utils.py @@ -1,234 +1,235 @@ # Copyright (C) 2015 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import flask import re from dateutil import parser def filter_endpoints(url_map, prefix_url_rule, blacklist=[]): """Filter endpoints by prefix url rule. Args: - url_map: Url Werkzeug.Map of rules - prefix_url_rule: prefix url string - blacklist: blacklist of some url Returns: Dictionary of url_rule with values methods and endpoint. The key is the url, the associated value is a dictionary of 'methods' (possible http methods) and 'endpoint' (python function) """ out = {} for r in url_map: rule = r['rule'] if rule == prefix_url_rule or rule in blacklist: continue if rule.startswith(prefix_url_rule): out[rule] = {'methods': sorted(map(str, r['methods'])), 'endpoint': r['endpoint']} return out def fmap(f, data): """Map f to data. Keep the initial data structure as original but map function f to each level. Args: f: function that expects one argument. data: data to traverse to apply the f function. list, map, dict or bare value. Returns: The same data-structure with modified values by the f function. """ if isinstance(data, map): return (fmap(f, x) for x in data) if isinstance(data, list): return [fmap(f, x) for x in data] if isinstance(data, dict): return {k: fmap(f, v) for (k, v) in data.items()} return f(data) def prepare_data_for_view(data, encoding='utf-8'): def prepare_data(s): # Note: can only be 'data' key with bytes of raw content if isinstance(s, bytes): try: return s.decode(encoding) except: - return "Cannot decode the data bytes, try and set another" \ - " encoding in the url or download directly the" \ - " content's raw data." + return "Cannot decode the data bytes, try and set another " \ + "encoding in the url (e.g. ?encoding=utf8) or " \ + "download directly the " \ + "content's raw data." if isinstance(s, str): return re.sub(r'/api/1/', r'/browse/', s) return s return fmap(prepare_data, data) def filter_field_keys(data, field_keys): """Given an object instance (directory or list), and a csv field keys to filter on. Return the object instance with filtered keys. Note: Returns obj as is if it's an instance of types not in (dictionary, list) Args: - data: one object (dictionary, list...) to filter. - field_keys: csv or set of keys to filter the object on Returns: obj filtered on field_keys """ if isinstance(data, map): return (filter_field_keys(x, field_keys) for x in data) if isinstance(data, list): return [filter_field_keys(x, field_keys) for x in data] if isinstance(data, dict): return {k: v for (k, v) in data.items() if k in field_keys} return data def person_to_string(person): """Map a person (person, committer, tagger, etc...) to a string. """ return ''.join([person['name'], ' <', person['email'], '>']) def parse_timestamp(timestamp): """Given a time or timestamp (as string), parse the result as datetime. Returns: datetime result of parsing values. Samples: - 2016-01-12 - 2016-01-12T09:19:12+0100 - Today is January 1, 2047 at 8:21:00AM - 1452591542 """ try: res = parser.parse(timestamp, ignoretz=False, fuzzy=True) except: res = datetime.datetime.fromtimestamp(float(timestamp)) return res def enrich_release(release): """Enrich a release with link to the 'target' of 'type' revision. """ if 'target' in release and 'target_type' in release: if release['target_type'] == 'revision': release['target_url'] = flask.url_for('api_revision', sha1_git=release['target']) elif release['target_type'] == 'release': release['target_url'] = flask.url_for('api_release', sha1_git=release['target']) elif release['target_type'] == 'content': release['target_url'] = flask.url_for( 'api_content_metadata', q='sha1_git:' + release['target']) elif release['target_type'] == 'directory': release['target_url'] = flask.url_for('api_directory', q=release['target']) return release def enrich_directory(directory, context_url=None): """Enrich directory with url to content or directory. """ if 'type' in directory: target_type = directory['type'] target = directory['target'] if target_type == 'file': directory['target_url'] = flask.url_for('api_content_metadata', q='sha1_git:%s' % target) if context_url: directory['file_url'] = context_url + directory['name'] + '/' else: directory['target_url'] = flask.url_for('api_directory', sha1_git=target) if context_url: directory['dir_url'] = context_url + directory['name'] + '/' return directory def enrich_content(content): """Enrich content with 'data', a link to its raw content. """ if 'sha1' in content: content['data_url'] = flask.url_for('api_content_raw', q=content['sha1']) return content def enrich_entity(entity): """Enrich entity with """ if 'uuid' in entity: entity['uuid_url'] = flask.url_for('api_entity_by_uuid', uuid=entity['uuid']) if 'parent' in entity and entity['parent']: entity['parent_url'] = flask.url_for('api_entity_by_uuid', uuid=entity['parent']) return entity def enrich_revision(revision, context=None): """Enrich revision with links where it makes sense (directory, parents). """ if not context: context = revision['id'] revision['url'] = flask.url_for('api_revision', sha1_git=revision['id']) revision['history_url'] = flask.url_for('api_revision_log', sha1_git=revision['id']) if 'directory' in revision: revision['directory_url'] = flask.url_for( 'api_directory', sha1_git=revision['directory']) if 'parents' in revision: parents = [] for parent in revision['parents']: parents.append(flask.url_for('api_revision_history', sha1_git_root=context, sha1_git=parent)) revision['parent_urls'] = parents if 'children' in revision: children = [] for child in revision['children']: children.append(flask.url_for('api_revision_history', sha1_git_root=context, sha1_git=child)) revision['children_urls'] = children return revision diff --git a/swh/web/ui/views.py b/swh/web/ui/views.py index 566d2798..4d3ff291 100644 --- a/swh/web/ui/views.py +++ b/swh/web/ui/views.py @@ -1,707 +1,751 @@ # Copyright (C) 2015 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 flask +from encodings.aliases import aliases from flask import render_template, request, url_for, redirect from flask.ext.api.decorators import set_renderers from flask.ext.api.renderers import HTMLRenderer from swh.core.hashutil import ALGORITHMS from swh.web.ui import service, utils, api from swh.web.ui.exc import BadInputExc, NotFoundExc from swh.web.ui.main import app hash_filter_keys = ALGORITHMS @app.route('/') @set_renderers(HTMLRenderer) def homepage(): """Home page """ flask.flash('This Web app is still work in progress, use at your own risk', 'warning') return render_template('home.html') @app.route('/about/') @set_renderers(HTMLRenderer) def about(): return render_template('about.html') @app.route('/search/', methods=['GET', 'POST']) @set_renderers(HTMLRenderer) def search(): """Search for hashes in swh-storage. One form to submit either: - hash query to look up in swh storage - some file content to upload, compute its hash and look it up in swh storage - both Returns: dict representing data to look for in swh storage. The following keys are returned: - file: File submitted for upload - filename: Filename submitted for upload - q: Query on hash to look for - message: Message detailing if data has been found or not. """ env = {'filename': None, 'q': None, 'file': None} data = None q = env['q'] file = env['file'] if request.method == 'GET': data = request.args elif request.method == 'POST': data = request.data # or hash and search a file file = request.files.get('filename') # could either be a query for sha1 hash q = data.get('q') messages = [] if q: env['q'] = q try: r = service.lookup_hash(q) messages.append('Content with hash %s%sfound!' % ( q, ' ' if r.get('found') else ' not ')) except BadInputExc as e: messages.append(str(e)) if file and file.filename: env['file'] = file try: uploaded_content = service.upload_and_search(file) filename = uploaded_content['filename'] sha1 = uploaded_content['sha1'] found = uploaded_content['found'] messages.append('File %s with hash %s%sfound!' % ( filename, sha1, ' ' if found else ' not ')) env.update({ 'filename': filename, 'sha1': sha1, }) except BadInputExc as e: messages.append(str(e)) env['q'] = q if q else '' env['messages'] = messages return render_template('upload_and_search.html', **env) @app.route('/browse/content/') @app.route('/browse/content//') @set_renderers(HTMLRenderer) def browse_content(q='5d448a06f02d9de748b6b0b9620cba1bed8480da'): """Given a hash and a checksum, display the content's meta-data. Args: q is of the form algo_hash:hash with algo_hash in (sha1, sha1_git, sha256) Returns: Information on one possible origin for such content. Raises: BadInputExc in case of unknown algo_hash or bad hash NotFoundExc if the content is not found. """ env = {'q': q, 'message': None, 'content': None} + + encoding = request.args.get('encoding', 'utf8') + if encoding not in aliases: + env['message'] = 'Encoding %s not supported.' \ + 'Supported Encodings: %s' % ( + encoding, list(aliases.keys())) + return render_template('content.html', **env) + try: content = api.api_content_metadata(q) content_raw = service.lookup_content_raw(q) if content_raw: content['data'] = content_raw['data'] - env['content'] = utils.prepare_data_for_view(content) + env['content'] = utils.prepare_data_for_view(content, + encoding=encoding) except (NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('content.html', **env) @app.route('/browse/content//raw/') def browse_content_raw(q): """Given a hash and a checksum, display the content's raw data. Args: q is of the form algo_hash:hash with algo_hash in (sha1, sha1_git, sha256) Returns: Information on one possible origin for such content. Raises: BadInputExc in case of unknown algo_hash or bad hash NotFoundExc if the content is not found. """ return redirect(url_for('api_content_raw', q=q)) def _origin_seen(q, data): """Given an origin, compute a message string with the right information. Args: origin: a dictionary with keys: - origin: a dictionary with type and url keys - occurrence: a dictionary with a validity range Returns: Message as a string """ origin_type = data['origin_type'] origin_url = data['origin_url'] revision = data['revision'] branch = data['branch'] path = data['path'] return """The content with hash %s has been seen on origin with type '%s' at url '%s'. The revision was identified at '%s' on branch '%s'. The file's path referenced was '%s'.""" % (q, origin_type, origin_url, revision, branch, path) # @app.route('/browse/content//origin/') @set_renderers(HTMLRenderer) def browse_content_with_origin( q='sha1:4320781056e5a735a39de0b8c229aea224590052'): """Show content information. Args: - q: query string of the form with `algo_hash` in sha1, sha1_git, sha256. This means that several different URLs (at least one per HASH_ALGO) will point to the same content sha: the sha with 'hash' format Returns: The content's information at for a given checksum. """ env = {'q': q} try: origin = api.api_content_checksum_to_origin(q) message = _origin_seen(q, origin) except (NotFoundExc, BadInputExc) as e: message = str(e) env['message'] = message return render_template('content-with-origin.html', **env) @app.route('/browse/directory/') @app.route('/browse/directory//') @set_renderers(HTMLRenderer) def browse_directory(sha1_git='dcf3289b576b1c8697f2a2d46909d36104208ba3'): """Show directory information. Args: - sha1_git: the directory's sha1 git identifier. Returns: The content's information at sha1_git """ env = {'sha1_git': sha1_git, 'files': []} try: directory_files = api.api_directory(sha1_git) env['message'] = "Listing for directory %s:" % sha1_git env['files'] = utils.prepare_data_for_view(directory_files) except (NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('directory.html', **env) @app.route('/browse/origin/') @app.route('/browse/origin//') @set_renderers(HTMLRenderer) def browse_origin(origin_id=1): """Browse origin with id id. """ env = {'origin_id': origin_id, 'origin': None} try: env['origin'] = api.api_origin(origin_id) except (NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('origin.html', **env) @app.route('/browse/person/') @app.route('/browse/person//') @set_renderers(HTMLRenderer) def browse_person(person_id=1): """Browse person with id id. """ env = {'person_id': person_id, 'person': None, 'message': None} try: env['person'] = api.api_person(person_id) except (NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('person.html', **env) @app.route('/browse/release/') @app.route('/browse/release//') @set_renderers(HTMLRenderer) def browse_release(sha1_git='1e951912027ea6873da6985b91e50c47f645ae1a'): """Browse release with sha1_git. """ env = {'sha1_git': sha1_git, 'message': None, 'release': None} try: rel = api.api_release(sha1_git) env['release'] = utils.prepare_data_for_view(rel) except (NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('release.html', **env) @app.route('/browse/revision/') @app.route('/browse/revision//') @set_renderers(HTMLRenderer) def browse_revision(sha1_git='d770e558e21961ad6cfdf0ff7df0eb5d7d4f0754'): """Browse revision with sha1_git. """ env = {'sha1_git': sha1_git, 'message': None, 'revision': None} try: rev = api.api_revision(sha1_git) env['revision'] = utils.prepare_data_for_view(rev) except (NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('revision.html', **env) @app.route('/browse/revision//log/') @set_renderers(HTMLRenderer) def browse_revision_log(sha1_git): """Browse revision with sha1_git. """ env = {'sha1_git': sha1_git, 'message': None, 'revisions': []} try: revisions = api.api_revision_log(sha1_git) env['revisions'] = map(utils.prepare_data_for_view, revisions) except (NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('revision-log.html', **env) @app.route('/browse/revision//history//') @set_renderers(HTMLRenderer) def browse_revision_history(sha1_git_root, sha1_git): """Display 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 of the browsed history. sha1_git: one of sha1_git_root's ancestors. 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 sha1_git_root (even if it is). Returns: Information on sha1_git if it is an ancestor of sha1_git_root including children leading to sha1_git_root. """ env = {'sha1_git_root': sha1_git_root, 'sha1_git': sha1_git, 'message': None, 'keys': [], 'revision': None} if sha1_git == sha1_git_root: return redirect(url_for('browse_revision', sha1_git=sha1_git)) try: revision = api.api_revision_history(sha1_git_root, sha1_git) env['revision'] = utils.prepare_data_for_view(revision) except (BadInputExc, NotFoundExc) as e: env['message'] = str(e) return render_template('revision.html', **env) @app.route('/browse/revision//directory/') @app.route('/browse/revision//directory//') @set_renderers(HTMLRenderer) def browse_revision_directory(sha1_git, path=None): """Browse directory from revision with sha1_git. """ env = { 'sha1_git': sha1_git, 'path': '.' if not path else path, 'message': None, 'result': None } + encoding = request.args.get('encoding', 'utf8') + if encoding not in aliases: + env['message'] = 'Encoding %s not supported.' \ + 'Supported Encodings: %s' % ( + encoding, list(aliases.keys())) + return render_template('revision-directory.html', **env) + try: result = api.api_revision_directory(sha1_git, path, with_data=True) - result['content'] = utils.prepare_data_for_view(result['content']) + result['content'] = utils.prepare_data_for_view(result['content'], + encoding=encoding) env['revision'] = result['revision'] env['result'] = result except (BadInputExc, NotFoundExc) as e: env['message'] = str(e) return render_template('revision-directory.html', **env) @app.route('/browse/revision/' '/history/' '/directory/') @app.route('/browse/revision/' '/history/' '/directory//') @set_renderers(HTMLRenderer) def browse_revision_history_directory(sha1_git_root, sha1_git, path=None): """Return information about directory pointed to by the revision defined as: revision sha1_git, limited to the sub-graph of all transitive parents of sha1_git_root. Args: sha1_git_root: latest revision of the browsed history. sha1_git: one of sha1_git_root's ancestors. path: optional directory pointed to by that revision. 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 sha1_git_root (even if it is). Returns: Information on the directory pointed to by that revision. 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 or the path referenced does not exist """ env = { 'sha1_git_root': sha1_git_root, 'sha1_git': sha1_git, 'path': '.' if not path else path, 'message': None, 'result': None } + encoding = request.args.get('encoding', 'utf8') + if encoding not in aliases: + env['message'] = 'Encoding %s not supported.' \ + 'Supported Encodings: %s' % ( + encoding, list(aliases.keys())) + return render_template('revision-directory.html', **env) + if sha1_git == sha1_git_root: return redirect(url_for('browse_revision_directory', sha1_git=sha1_git, - path=path), + path=path, + encoding=encoding), code=301) try: result = api.api_revision_history_directory(sha1_git_root, sha1_git, path, with_data=True) env['revision'] = result['revision'] - env['content'] = utils.prepare_data_for_view(result['content']) + env['content'] = utils.prepare_data_for_view(result['content'], + encoding=encoding) env['result'] = result except (BadInputExc, NotFoundExc) as e: env['message'] = str(e) return render_template('revision-directory.html', **env) @app.route('/browse/revision' '/origin/' '/history/' '/directory/') @app.route('/browse/revision' '/origin/' '/history/' '/directory//') @app.route('/browse/revision' '/origin/' '/branch/' '/history/' '/directory/') @app.route('/browse/revision' '/origin/' '/branch/' '/history/' '/directory//') @app.route('/browse/revision' '/origin/' '/ts/' '/history/' '/directory/') @app.route('/browse/revision' '/origin/' '/ts/' '/history/' '/directory//') @app.route('/browse/revision' '/origin/' '/branch/' '/ts/' '/history/' '/directory/') @app.route('/browse/revision' '/origin/' '/branch/' '/ts/' '/history/' '/directory//') @set_renderers(HTMLRenderer) def browse_directory_through_revision_with_origin_history( origin_id=1, branch_name="refs/heads/master", ts=None, sha1_git=None, path=None): env = { 'origin_id': origin_id, 'branch_name': branch_name, 'ts': ts, 'sha1_git': sha1_git, 'path': '.' if not path else path, 'message': None, 'result': None } + encoding = request.args.get('encoding', 'utf8') + if encoding not in aliases: + env['message'] = 'Encoding %s not supported.' \ + 'Supported Encodings: %s' % ( + encoding, list(aliases.keys())) + return render_template('revision-directory.html', **env) + try: result = api.api_directory_through_revision_with_origin_history( origin_id, branch_name, ts, sha1_git, path, with_data=True) env['revision'] = result['revision'] - env['content'] = utils.prepare_data_for_view(result['content']) + env['content'] = utils.prepare_data_for_view(result['content'], + encoding=encoding) env['result'] = result except (BadInputExc, NotFoundExc) as e: env['message'] = str(e) return render_template('revision-directory.html', **env) @app.route('/browse/revision' '/origin/') @app.route('/browse/revision' '/origin//') @app.route('/browse/revision' '/origin/' '/branch//') @app.route('/browse/revision' '/origin/' '/branch/' '/ts//') @app.route('/browse/revision' '/origin/' '/ts//') @set_renderers(HTMLRenderer) def browse_revision_with_origin(origin_id=1, branch_name="refs/heads/master", ts=None): """Instead of having to specify a (root) revision by SHA1_GIT, users might want to specify a place and a time. In SWH a "place" is an origin; a "time" is a timestamp at which some place has been observed by SWH crawlers. Args: origin_id: origin's identifier (default to 1). branch_name: the optional branch for the given origin (default to master). timestamp: optional timestamp (default to the nearest time crawl of timestamp). Returns: Information on the revision if found. Raises: BadInputExc in case of unknown algo_hash or bad hash. NotFoundExc if the revision is not found. """ env = {'message': None, 'revision': None} try: revision = api.api_revision_with_origin(origin_id, branch_name, ts) env['revision'] = utils.prepare_data_for_view(revision) except (ValueError, NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('revision.html', **env) @app.route('/browse/revision' '/origin/' '/history//') @app.route('/browse/revision' '/origin/' '/branch/' '/history//') @app.route('/browse/revision' '/origin/' '/branch/' '/ts/' '/history//') @set_renderers(HTMLRenderer) def browse_revision_history_through_origin(origin_id, branch_name='refs/heads/master', ts=None, sha1_git=None): """Return information about revision sha1_git, limited to the sub-graph of all transitive parents of the revision root identified by (origin_id, branch_name, ts). Given sha1_git_root such root revision's identifier, in other words, sha1_git is an ancestor of sha1_git_root. Args: origin_id: origin's identifier (default to 1). branch_name: the optional branch for the given origin (default to master). timestamp: optional timestamp (default to the nearest time crawl of timestamp). sha1_git: one of sha1_git_root's ancestors. 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 sha1_git_root (even if it is). Returns: Information on sha1_git if it is an ancestor of sha1_git_root including children leading to sha1_git_root. """ env = {'message': None, 'revision': None} try: revision = api.api_revision_history_through_origin( origin_id, branch_name, ts, sha1_git) env['revision'] = utils.prepare_data_for_view(revision) except (ValueError, BadInputExc, NotFoundExc) as e: env['message'] = str(e) return render_template('revision.html', **env) @app.route('/browse/revision' '/origin/' '/directory/') @app.route('/browse/revision' '/origin/' '/directory/') @app.route('/browse/revision' '/origin/' '/branch/' '/directory/') @app.route('/browse/revision' '/origin/' '/branch/' '/directory//') @app.route('/browse/revision' '/origin/' '/branch/' '/ts/' '/directory/') @app.route('/browse/revision' '/origin/' '/branch/' '/ts/' '/directory//') @set_renderers(HTMLRenderer) def browse_revision_directory_through_origin(origin_id, branch_name='refs/heads/master', ts=None, path=None): env = {'message': None, 'origin_id': origin_id, 'ts': ts, 'path': '.' if not path else path, 'result': None} + + encoding = request.args.get('encoding', 'utf8') + if encoding not in aliases: + env['message'] = 'Encoding %s not supported.' \ + 'Supported Encodings: %s' % ( + encoding, list(aliases.keys())) + return render_template('revision-directory.html', **env) + try: result = api.api_directory_through_revision_origin( origin_id, branch_name, ts, path, with_data=True) - result['content'] = utils.prepare_data_for_view(result['content']) + result['content'] = utils.prepare_data_for_view(result['content'], + encoding=encoding) env['revision'] = result['revision'] env['result'] = result except (ValueError, BadInputExc, NotFoundExc) as e: env['message'] = str(e) return render_template('revision-directory.html', **env) @app.route('/browse/entity/') @app.route('/browse/entity//') @set_renderers(HTMLRenderer) def browse_entity(uuid='5f4d4c51-498a-4e28-88b3-b3e4e8396cba'): env = {'entities': [], 'message': None} try: entities = api.api_entity_by_uuid(uuid) env['entities'] = entities except (NotFoundExc, BadInputExc) as e: env['message'] = str(e) return render_template('entity.html', **env)