Page MenuHomeSoftware Heritage
Files F9123339

No OneTemporary
Actions

View Options

diff --git a/swh/web/browse/utils.py b/swh/web/browse/utils.py
index 624d7d15c..f642e6fd9 100644
--- a/swh/web/browse/utils.py
+++ b/swh/web/browse/utils.py
@@ -1,966 +1,1007 @@
# 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 base64
import magic
import math
import stat
from django.core.cache import cache
from django.utils.safestring import mark_safe
from importlib import reload
from swh.web.common import highlightjs, service
from swh.web.common.exc import NotFoundExc
from swh.web.common.utils import (
reverse, format_utc_iso_date, parse_timestamp
)
from swh.web.config import get_config
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 get_mimetype_and_encoding_for_content(content):
"""Function that returns the mime type and the encoding associated to
a content buffer using the magic module under the hood.
Args:
content (bytes): a content buffer
Returns:
A tuple (mimetype, encoding), for instance ('text/plain', 'us-ascii'),
associated to the provided content.
"""
while True:
try:
magic_result = magic.detect_from_content(content)
mime_type = magic_result.mime_type
encoding = magic_result.encoding
break
except Exception as exc:
# workaround an issue with the magic module who can fail
# if detect_from_content is called multiple times in
# a short amount of time
reload(magic)
return mime_type, encoding
# maximum authorized content size in bytes for HTML display
# with code highlighting
content_display_max_size = get_config()['content_display_max_size']
def request_content(query_string, max_size=content_display_max_size):
"""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
max_size: the maximum size for a content to retrieve (default to 1MB,
no size limit if None)
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_data = service.lookup_content(query_string)
filetype = service.lookup_content_filetype(query_string)
language = service.lookup_content_language(query_string)
license = service.lookup_content_license(query_string)
mimetype = 'unknown'
encoding = 'unknown'
if filetype:
mimetype = filetype['mimetype']
encoding = filetype['encoding']
if not max_size or content_data['length'] < max_size:
content_raw = service.lookup_content_raw(query_string)
content_data['raw_data'] = content_raw['data']
if not filetype:
mimetype, encoding = \
get_mimetype_and_encoding_for_content(content_data['raw_data'])
# encode textual content to utf-8 if needed
if mimetype.startswith('text/'):
# probably a malformed UTF-8 content, reencode it
# by replacing invalid chars with a substitution one
if encoding == 'unknown-8bit':
content_data['raw_data'] = \
content_data['raw_data'].decode('utf-8', 'replace')\
.encode('utf-8')
elif 'ascii' not in encoding and encoding not in ['utf-8', 'binary']: # noqa
content_data['raw_data'] = \
content_data['raw_data'].decode(encoding, 'replace')\
.encode('utf-8')
else:
content_data['raw_data'] = None
content_data['mimetype'] = mimetype
content_data['encoding'] = encoding
if language:
content_data['language'] = language['lang']
else:
content_data['language'] = 'not detected'
if license:
content_data['licenses'] = ', '.join(license['licenses'])
else:
content_data['licenses'] = 'not detected'
return content_data
_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_info):
"""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': <UTC visit date in ISO format>,
'origin': <origin id>,
'status': <'full' | 'partial'>,
'visit': <visit id>
},
...
]
Raises:
NotFoundExc if the origin is not found
"""
cache_entry_id = 'origin_%s_visits' % origin_info['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_info['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
def _visit_sort_key(visit):
ts = parse_timestamp(visit['date']).timestamp()
return ts + (float(visit['visit']) / 10e3)
for v in origin_visits:
if 'metadata' in v:
del v['metadata']
origin_visits = [dict(t) for t in set([tuple(d.items())
for d in origin_visits])]
origin_visits = sorted(origin_visits, key=lambda v: _visit_sort_key(v))
cache.set(cache_entry_id, origin_visits)
return origin_visits
def get_origin_visit(origin_info, visit_ts=None, visit_id=None,
snapshot_id=None):
"""Function that returns information about a SWH visit for
a given origin.
The visit is retrieved from a provided timestamp.
The closest visit from that timestamp is selected.
Args:
origin_info (dict): a dict filled with origin information
(id, url, type)
visit_ts (int or str): an ISO date string or Unix timestamp to parse
Returns:
A dict containing the visit info as described below::
{'origin': 2,
'date': '2017-10-08T11:54:25.582463+00:00',
'metadata': {},
'visit': 25,
'status': 'full'}
"""
visits = get_origin_visits(origin_info)
if not visits:
raise NotFoundExc('No SWH visit associated to origin with'
' type %s and url %s!' % (origin_info['type'],
origin_info['url']))
if snapshot_id:
visit = [v for v in visits if v['snapshot'] == snapshot_id]
if len(visit) == 0:
raise NotFoundExc(
'Visit for snapshot with id %s for origin with type %s'
' and url %s not found!' % (snapshot_id, origin_info['type'],
origin_info['url']))
return visit[0]
if visit_id:
visit = [v for v in visits if v['visit'] == int(visit_id)]
if len(visit) == 0:
raise NotFoundExc(
'Visit with id %s for origin with type %s'
' and url %s not found!' % (visit_id, origin_info['type'],
origin_info['url']))
return visit[0]
if not visit_ts:
# returns the latest full visit when no timestamp is provided
for v in reversed(visits):
if v['status'] == 'full':
return v
return visits[-1]
parsed_visit_ts = math.floor(parse_timestamp(visit_ts).timestamp())
visit_idx = None
for i, visit in enumerate(visits):
ts = math.floor(parse_timestamp(visit['date']).timestamp())
if i == 0 and parsed_visit_ts <= ts:
return visit
elif i == len(visits) - 1:
if parsed_visit_ts >= ts:
return visit
else:
next_ts = math.floor(
parse_timestamp(visits[i+1]['date']).timestamp())
if parsed_visit_ts >= ts and parsed_visit_ts < next_ts:
if (parsed_visit_ts - ts) < (next_ts - parsed_visit_ts):
visit_idx = i
break
else:
visit_idx = i+1
break
if visit_idx:
visit = visits[visit_idx]
while visit_idx < len(visits) - 1 and \
visit['date'] == visits[visit_idx+1]['date']:
visit_idx = visit_idx + 1
visit = visits[visit_idx]
return visit
else:
raise NotFoundExc(
'Visit with timestamp %s for origin with type %s and url %s not found!' % # noqa
(visit_ts, origin_info['type'], origin_info['url']))
def get_snapshot_content(snapshot_id):
"""Returns the lists of branches and releases
associated to a swh snapshot.
That list is put in cache in order to speedup the navigation
in the swh-web/browse ui.
Args:
snapshot_id (str): hexadecimal representation of the snapshot
identifier
Returns:
A tuple with two members. The first one is a list of dict describing
the snapshot branches. The second one is a list of dict describing the
snapshot releases.
Raises:
NotFoundExc if the snapshot does not exist
"""
cache_entry_id = 'swh_snapshot_%s' % snapshot_id
cache_entry = cache.get(cache_entry_id)
if cache_entry:
return cache_entry['branches'], cache_entry['releases']
branches = []
releases = []
if snapshot_id:
revision_ids = []
releases_ids = []
snapshot = service.lookup_snapshot(snapshot_id)
snapshot_branches = snapshot['branches']
for key in sorted(snapshot_branches.keys()):
if not snapshot_branches[key]:
continue
if snapshot_branches[key]['target_type'] == 'revision':
branches.append({'name': key,
'revision': snapshot_branches[key]['target']})
revision_ids.append(snapshot_branches[key]['target'])
elif snapshot_branches[key]['target_type'] == 'release':
releases_ids.append(snapshot_branches[key]['target'])
releases_info = service.lookup_release_multiple(releases_ids)
for release in releases_info:
releases.append({'name': release['name'],
'date': format_utc_iso_date(release['date']),
'id': release['id'],
'message': release['message'],
'target_type': release['target_type'],
'target': release['target']})
revision_ids.append(release['target'])
revisions = service.lookup_revision_multiple(revision_ids)
branches_to_remove = []
for idx, revision in enumerate(revisions):
if idx < len(branches):
if revision:
branches[idx]['directory'] = revision['directory']
branches[idx]['date'] = format_utc_iso_date(revision['date']) # noqa
branches[idx]['message'] = revision['message']
else:
branches_to_remove.append(branches[idx])
else:
rel_idx = idx - len(branches)
if revision:
releases[rel_idx]['directory'] = revision['directory']
for b in branches_to_remove:
branches.remove(b)
cache.set(cache_entry_id, {'branches': branches, 'releases': releases})
return branches, releases
def get_origin_visit_snapshot(origin_info, visit_ts=None, visit_id=None,
snapshot_id=None):
"""Returns the lists of branches and releases
associated to a swh origin for a given visit.
The visit is expressed by a timestamp. In the latter case,
the closest visit from the provided timestamp will be used.
If no visit parameter is provided, it returns the list of branches
found for the latest visit.
That list is put in cache in order to speedup the navigation
in the swh-web/browse ui.
Args:
origin_info (dict): a dict filled with origin information
(id, url, type)
visit_ts (int or str): an ISO date string or Unix timestamp to parse
visit_id (int): optional visit id for desambiguation in case
several visits have the same timestamp
Returns:
A tuple with two members. The first one is a list of dict describing
the origin branches for the given visit.
The second one is a list of dict describing the origin releases
for the given visit.
Raises:
NotFoundExc if the origin or its visit are not found
"""
visit_info = get_origin_visit(origin_info, visit_ts, visit_id, snapshot_id)
return get_snapshot_content(visit_info['snapshot'])
def gen_link(url, link_text, link_attrs={}):
"""
Utility function for generating an HTML link to insert
in Django templates.
Args:
url (str): an url
link_text (str): the text for the produced link
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="url">link_text</a>'
"""
attrs = ' '
for k, v in link_attrs.items():
attrs += '%s="%s" ' % (k, v)
link = '<a%shref="%s">%s</a>' % (attrs, url, link_text)
return mark_safe(link)
def gen_person_link(person_id, person_name, link_attrs={}):
"""
Utility function for generating a link to a SWH person HTML view
to insert in Django templates.
Args:
person_id (int): a SWH person id
person_name (str): the associated person name
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="person_view_url">person_name</a>'
"""
person_url = reverse('browse-person', kwargs={'person_id': person_id})
return gen_link(person_url, person_name, link_attrs)
def gen_revision_link(revision_id, shorten_id=False, snapshot_context=None,
link_text=None, link_attrs={}):
"""
Utility function for generating a link to a SWH revision HTML view
to insert in Django templates.
Args:
revision_id (str): a SWH revision id
shorten_id (boolean): wheter to shorten the revision id to 7
characters for the link text
snapshot_context (dict): if provided, generate snapshot-dependent
browsing link
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="revision_view_url">revision_id</a>'
"""
query_params = None
if snapshot_context and snapshot_context['origin_info']:
origin_info = snapshot_context['origin_info']
query_params = {'origin_type': origin_info['type'],
'origin_url': origin_info['url']}
if 'timestamp' in snapshot_context['url_args']:
query_params['timestamp'] = \
snapshot_context['url_args']['timestamp']
if 'visit_id' in snapshot_context['query_params']:
query_params['visit_id'] = \
snapshot_context['query_params']['visit_id']
elif snapshot_context:
query_params = {'snapshot_id': snapshot_context['snapshot_id']}
revision_url = reverse('browse-revision',
kwargs={'sha1_git': revision_id},
query_params=query_params)
if shorten_id:
return gen_link(revision_url, revision_id[:7], link_attrs)
else:
if not link_text:
link_text = revision_id
return gen_link(revision_url, link_text, link_attrs)
def gen_origin_link(origin_info, link_attrs={}):
"""
Utility function for generating a link to a SWH origin HTML view
to insert in Django templates.
Args:
origin_info (dict): a dicted filled with origin information
(id, type, url)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="origin_view_url">Origin: origin_url</a>'
""" # noqa
origin_browse_url = reverse('browse-origin',
kwargs={'origin_type': origin_info['type'],
'origin_url': origin_info['url']})
return gen_link(origin_browse_url,
'Origin: ' + origin_info['url'], link_attrs)
def gen_directory_link(sha1_git, link_text=None, link_attrs={}):
"""
Utility function for generating a link to a SWH directory HTML view
to insert in Django templates.
Args:
sha1_git (str): directory identifier
link_text (str): optional text for the generated link
(the generated url will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="directory_view_url">link_text</a>'
"""
directory_url = reverse('browse-directory',
kwargs={'sha1_git': sha1_git})
if not link_text:
link_text = directory_url
return gen_link(directory_url, link_text, link_attrs)
def gen_snapshot_link(snapshot_id, link_text=None, link_attrs={}):
"""
Utility function for generating a link to a SWH snapshot HTML view
to insert in Django templates.
Args:
snapshot_id (str): snapshot identifier
link_text (str): optional text for the generated link
(the generated url will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="snapshot_view_url">link_text</a>'
"""
snapshot_url = reverse('browse-snapshot',
kwargs={'snapshot_id': snapshot_id})
if not link_text:
link_text = snapshot_url
return gen_link(snapshot_url, link_text, link_attrs)
def gen_snapshot_directory_link(snapshot_context, revision_id=None,
link_text=None, link_attrs={}):
"""
Utility function for generating a link to a SWH directory HTML view
in the context of a snapshot to insert in Django templates.
Args:
snapshot_context (dict): the snapshot information
revision_id (str): optional revision identifier in order
to use the associated directory
link_text (str): optional text to use for the generated link
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form
'<a href="origin_directory_view_url">origin_directory_view_url</a>'
"""
query_params = {'revision': revision_id}
if snapshot_context['origin_info']:
origin_info = snapshot_context['origin_info']
url_args = {'origin_type': origin_info['type'],
'origin_url': origin_info['url']}
if 'timestamp' in snapshot_context['url_args']:
url_args['timestamp'] = \
snapshot_context['url_args']['timestamp']
if 'visit_id' in snapshot_context['query_params']:
query_params['visit_id'] = \
snapshot_context['query_params']['visit_id']
directory_url = reverse('browse-origin-directory',
kwargs=url_args,
query_params=query_params)
else:
url_args = {'snapshot_id': snapshot_context['snapshot_id']}
directory_url = reverse('browse-snapshot-directory',
kwargs=url_args,
query_params=query_params)
if not link_text:
link_text = directory_url
return gen_link(directory_url, link_text, link_attrs)
def gen_content_link(sha1_git, link_text=None, link_attrs={}):
"""
Utility function for generating a link to a SWH content HTML view
to insert in Django templates.
Args:
sha1_git (str): content identifier
link_text (str): optional text for the generated link
(the generated url will be used by default)
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form '<a href="content_view_url">link_text</a>'
"""
content_url = reverse('browse-content',
kwargs={'query_string': 'sha1_git:' + sha1_git})
if not link_text:
link_text = content_url
return gen_link(content_url, link_text, link_attrs)
def get_revision_log_url(revision_id, snapshot_context=None):
"""
Utility function for getting the URL for a SWH revision log HTML view
(possibly in the context of an origin).
Args:
revision_id (str): revision identifier the history heads to
snapshot_context (dict): if provided, generate snapshot-dependent
browsing link
Returns:
The SWH revision log view URL
"""
query_params = {'revision': revision_id}
if snapshot_context and snapshot_context['origin_info']:
origin_info = snapshot_context['origin_info']
url_args = {'origin_type': origin_info['type'],
'origin_url': origin_info['url']}
if 'timestamp' in snapshot_context['url_args']:
url_args['timestamp'] = \
snapshot_context['url_args']['timestamp']
if 'visit_id' in snapshot_context['query_params']:
query_params['visit_id'] = \
snapshot_context['query_params']['visit_id']
revision_log_url = reverse('browse-origin-log',
kwargs=url_args,
query_params=query_params)
elif snapshot_context:
url_args = {'snapshot_id': snapshot_context['snapshot_id']}
revision_log_url = reverse('browse-snapshot-log',
kwargs=url_args,
query_params=query_params)
else:
revision_log_url = reverse('browse-revision-log',
kwargs={'sha1_git': revision_id})
return revision_log_url
def gen_revision_log_link(revision_id, snapshot_context=None, link_text=None,
link_attrs={}):
"""
Utility function for generating a link to a SWH revision log HTML view
(possibly in the context of an origin) to insert in Django templates.
Args:
revision_id (str): revision identifier the history heads to
snapshot_context (dict): if provided, generate snapshot-dependent
browsing link
link_text (str): optional text to use for the generated link
link_attrs (dict): optional attributes (e.g. class)
to add to the link
Returns:
An HTML link in the form
'<a href="revision_log_view_url">link_text</a>'
"""
revision_log_url = get_revision_log_url(revision_id, snapshot_context)
if not link_text:
link_text = revision_log_url
return gen_link(revision_log_url, link_text, link_attrs)
def _format_log_entries(revision_log, per_page, snapshot_context=None):
revision_log_data = []
for i, log in enumerate(revision_log):
if i == per_page:
break
revision_log_data.append(
{'author': gen_person_link(log['author']['id'],
log['author']['name']),
'revision': gen_revision_link(log['id'], True, snapshot_context),
'message': log['message'],
'date': format_utc_iso_date(log['date']),
'directory': log['directory']})
return revision_log_data
def prepare_revision_log_for_display(revision_log, per_page, revs_breadcrumb,
snapshot_context=None):
"""
Utility functions that process raw revision log data for HTML display.
Its purpose is to:
* add links to relevant SWH browse views
* format date in human readable format
* truncate the message log
It also computes the data needed to generate the links for navigating back
and forth in the history log.
Args:
revision_log (list): raw revision log as returned by the SWH web api
per_page (int): number of log entries per page
revs_breadcrumb (str): breadcrumbs of revisions navigated so far,
in the form 'rev1[/rev2/../revN]'. Each revision corresponds to
the first one displayed in the HTML view for history log.
snapshot_context (dict): if provided, generate snapshot-dependent
browsing link
"""
current_rev = revision_log[0]['id']
next_rev = None
prev_rev = None
next_revs_breadcrumb = None
prev_revs_breadcrumb = None
if len(revision_log) == per_page + 1:
prev_rev = revision_log[-1]['id']
prev_rev_bc = current_rev
if snapshot_context:
prev_rev_bc = prev_rev
if revs_breadcrumb:
revs = revs_breadcrumb.split('/')
next_rev = revs[-1]
if len(revs) > 1:
next_revs_breadcrumb = '/'.join(revs[:-1])
if len(revision_log) == per_page + 1:
prev_revs_breadcrumb = revs_breadcrumb + '/' + prev_rev_bc
else:
prev_revs_breadcrumb = prev_rev_bc
return {'revision_log_data': _format_log_entries(revision_log, per_page,
snapshot_context),
'prev_rev': prev_rev,
'prev_revs_breadcrumb': prev_revs_breadcrumb,
'next_rev': next_rev,
'next_revs_breadcrumb': next_revs_breadcrumb}
# list of origin types that can be found in the swh archive
# TODO: retrieve it dynamically in an efficient way instead
# of hardcoding it
_swh_origin_types = ['git', 'svn', 'deb', 'hg', 'ftp', 'deposit']
def get_origin_info(origin_url, origin_type=None):
"""
Get info about a SWH origin.
Its main purpose is to automatically find an origin type
when it is not provided as parameter.
Args:
origin_url (str): complete url of a SWH origin
origin_type (str): optionnal origin type
Returns:
A dict with the following entries:
* type: the origin type
* url: the origin url
* id: the SWH internal id of the origin
"""
if origin_type:
return service.lookup_origin({'type': origin_type,
'url': origin_url})
else:
for origin_type in _swh_origin_types:
origin_info = service.lookup_origin({'type': origin_type,
'url': origin_url})
if origin_info:
return origin_info
return None
def get_snapshot_context(snapshot_id=None, origin_type=None, origin_url=None,
timestamp=None, visit_id=None):
"""
Utility function to compute relevant information when navigating
the SWH archive in a snapshot context. The snapshot is either
referenced by its id or it will be retrieved from an origin visit.
Args:
snapshot_id (str): hexadecimal representation of a snapshot identifier,
all other parameters will be ignored if it is provided
origin_type (str): the origin type (git, svn, deposit, ...)
origin_url (str): the origin_url (e.g. https://github.com/(user)/(repo)/)
timestamp (str): a datetime string for retrieving the closest
SWH visit of the origin
visit_id (int): optional visit id for disambiguation in case
of several visits with the same timestamp
Returns:
A dict with the following entries:
* origin_info: dict containing origin information
* visit_info: dict containing SWH visit information
* branches: the list of branches for the origin found
during the visit
* releases: the list of releases for the origin found
during the visit
* origin_browse_url: the url to browse the origin
* origin_branches_url: the url to browse the origin branches
* origin_releases_url': the url to browse the origin releases
* origin_visit_url: the url to browse the snapshot of the origin
found during the visit
* url_args: dict containg url arguments to use when browsing in
the context of the origin and its visit
""" # noqa
origin_info = None
visit_info = None
url_args = None
query_params = {}
branches = []
releases = []
browse_url = None
visit_url = None
branches_url = None
releases_url = None
swh_type = 'snapshot'
if origin_url:
swh_type = 'origin'
origin_info = get_origin_info(origin_url, origin_type)
origin_info['type'] = origin_type
visit_info = get_origin_visit(origin_info, timestamp, visit_id,
snapshot_id)
visit_info['fmt_date'] = format_utc_iso_date(visit_info['date'])
snapshot_id = visit_info['snapshot']
# provided timestamp is not necessarily equals to the one
# of the retrieved visit, so get the exact one in order
# use it in the urls generated below
if timestamp:
timestamp = visit_info['date']
branches, releases = \
get_origin_visit_snapshot(origin_info, timestamp, visit_id,
snapshot_id)
url_args = {'origin_type': origin_info['type'],
'origin_url': origin_info['url']}
query_params = {'visit_id': visit_id}
browse_url = reverse('browse-origin-visits',
kwargs=url_args)
if timestamp:
url_args['timestamp'] = format_utc_iso_date(timestamp,
'%Y-%m-%dT%H:%M:%S')
visit_url = reverse('browse-origin-directory',
kwargs=url_args,
query_params=query_params)
visit_info['url'] = visit_url
branches_url = reverse('browse-origin-branches',
kwargs=url_args,
query_params=query_params)
releases_url = reverse('browse-origin-releases',
kwargs=url_args,
query_params=query_params)
elif snapshot_id:
branches, releases = get_snapshot_content(snapshot_id)
url_args = {'snapshot_id': snapshot_id}
browse_url = reverse('browse-snapshot',
kwargs=url_args)
branches_url = reverse('browse-snapshot-branches',
kwargs=url_args)
releases_url = reverse('browse-snapshot-releases',
kwargs=url_args)
releases = list(reversed(releases))
return {
'swh_type': swh_type,
'snapshot_id': snapshot_id,
'origin_info': origin_info,
'visit_info': visit_info,
'branches': branches,
'releases': releases,
'branch': None,
'release': None,
'browse_url': browse_url,
'branches_url': branches_url,
'releases_url': releases_url,
'url_args': url_args,
'query_params': query_params
}
+
+
+_common_readme_names = [
+ "readme",
+ "readme.markdown",
+ "readme.md",
+ "readme.txt",
+ "readme.rst"
+]
+
+
+def get_readme_to_display(readmes):
+ """
+ Process a list of readme files found in a directory
+ in order to find the adequate one to display.
+
+ Args:
+ readmes: a list of dict where keys are readme file names and values
+ are readme sha1s
+
+ Returns:
+ A tuple (readme_name, readme_sha1)
+ """
+ readme_name = None
+ readme_url = None
+ # try to find a readme file with a common name
+ for name, readme_sha1 in readmes.items():
+ if name.lower() in _common_readme_names:
+ readme_name = name
+ readme_url = reverse('browse-content-raw',
+ kwargs={'query_string': readme_sha1})
+ break
+
+ # otherwise pick the first readme like file if any
+ if not readme_name and len(readmes.items()) > 0:
+ readme_name = next(iter(readmes))
+ readme_sha1 = readmes[readme_name]
+ readme_url = reverse('browse-content-raw',
+ kwargs={'query_string': readme_sha1})
+
+ return readme_name, readme_url
diff --git a/swh/web/browse/views/directory.py b/swh/web/browse/views/directory.py
index 4057377e2..2b021a30f 100644
--- a/swh/web/browse/views/directory.py
+++ b/swh/web/browse/views/directory.py
@@ -1,118 +1,117 @@
# 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
from django.shortcuts import render
from django.template.defaultfilters import filesizeformat
from swh.web.common import service
from swh.web.common.utils import reverse, gen_path_info
from swh.web.common.exc import handle_view_exception
from swh.web.browse.utils import (
- get_directory_entries, get_snapshot_context
+ get_directory_entries, get_snapshot_context,
+ get_readme_to_display
)
from swh.web.browse.browseurls import browse_route
@browse_route(r'directory/(?P<sha1_git>[0-9a-f]+)/',
r'directory/(?P<sha1_git>[0-9a-f]+)/(?P<path>.+)/',
view_name='browse-directory')
def directory_browse(request, sha1_git, path=None):
"""Django view for browsing the content of a SWH directory identified
by its sha1_git value.
The url that points to it is :http:get:`/browse/directory/(sha1_git)/[(path)/]`
""" # noqa
root_sha1_git = sha1_git
try:
if path:
dir_info = service.lookup_directory_with_path(sha1_git, path)
sha1_git = dir_info['target']
dirs, files = get_directory_entries(sha1_git)
origin_type = request.GET.get('origin_type', None)
origin_url = request.GET.get('origin_url', None)
if not origin_url:
origin_url = request.GET.get('origin', None)
snapshot_context = None
if origin_url:
snapshot_context = get_snapshot_context(None, origin_type,
origin_url)
if snapshot_context:
snapshot_context['visit_info'] = None
except Exception as exc:
return handle_view_exception(request, exc)
path_info = gen_path_info(path)
breadcrumbs = []
breadcrumbs.append({'name': root_sha1_git[:7],
'url': reverse('browse-directory',
kwargs={'sha1_git': root_sha1_git})})
for pi in path_info:
breadcrumbs.append({'name': pi['name'],
'url': reverse('browse-directory',
kwargs={'sha1_git': root_sha1_git,
'path': pi['path']})})
path = '' if path is None else (path + '/')
for d in dirs:
d['url'] = reverse('browse-directory',
kwargs={'sha1_git': root_sha1_git,
'path': path + d['name']})
sum_file_sizes = 0
- readme_name = None
- readme_url = None
+ readmes = {}
for f in files:
query_string = 'sha1_git:' + f['target']
f['url'] = reverse('browse-content',
kwargs={'query_string': query_string},
query_params={'path': root_sha1_git + '/' +
path + f['name']})
sum_file_sizes += f['length']
f['length'] = filesizeformat(f['length'])
if f['name'].lower().startswith('readme'):
- readme_name = f['name']
- readme_sha1 = f['checksums']['sha1']
- readme_url = reverse('browse-content-raw',
- kwargs={'query_string': readme_sha1})
+ readmes[f['name']] = f['checksums']['sha1']
+
+ readme_name, readme_url = get_readme_to_display(readmes)
sum_file_sizes = filesizeformat(sum_file_sizes)
dir_metadata = {'id': sha1_git,
'number of regular files': len(files),
'number of subdirectories': len(dirs),
'sum of regular file sizes': sum_file_sizes}
vault_cooking = {
'directory_context': True,
'directory_id': sha1_git,
'revision_context': False,
'revision_id': None
}
return render(request, 'directory.html',
{'empty_browse': False,
'heading': 'Directory',
'top_panel_visible': True,
'top_panel_collapsible': True,
'top_panel_text': 'Directory metadata',
'swh_object_metadata': dir_metadata,
'main_panel_visible': True,
'dirs': dirs,
'files': files,
'breadcrumbs': breadcrumbs,
'top_right_link': None,
'top_right_link_text': None,
'readme_name': readme_name,
'readme_url': readme_url,
'snapshot_context': snapshot_context,
'vault_cooking': vault_cooking,
'show_actions_menu': True})
diff --git a/swh/web/browse/views/revision.py b/swh/web/browse/views/revision.py
index ea5829923..f11187f7f 100644
--- a/swh/web/browse/views/revision.py
+++ b/swh/web/browse/views/revision.py
@@ -1,466 +1,464 @@
# 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 hashlib
import json
from django.http import HttpResponse
from django.shortcuts import render
from django.template.defaultfilters import filesizeformat
from django.utils.safestring import mark_safe
from swh.web.common import service
from swh.web.common.utils import reverse, format_utc_iso_date, gen_path_info
from swh.web.common.exc import handle_view_exception
from swh.web.browse.browseurls import browse_route
from swh.web.browse.utils import (
gen_link, gen_person_link, gen_revision_link,
prepare_revision_log_for_display,
get_snapshot_context, gen_snapshot_directory_link,
get_revision_log_url, get_directory_entries,
gen_directory_link, request_content, prepare_content_for_display,
- content_display_max_size, gen_snapshot_link
+ content_display_max_size, gen_snapshot_link, get_readme_to_display
)
def _gen_content_url(revision, query_string, path, snapshot_context):
if snapshot_context:
url_args = snapshot_context['url_args']
url_args['path'] = path
query_params = snapshot_context['query_params']
query_params['revision'] = revision['id']
content_url = reverse('browse-origin-content',
kwargs=url_args,
query_params=query_params)
else:
content_path = '%s/%s' % (revision['directory'], path)
content_url = reverse('browse-content',
kwargs={'query_string': query_string},
query_params={'path': content_path})
return content_url
def _gen_diff_link(idx, diff_anchor, link_text):
if idx < _max_displayed_file_diffs:
return gen_link(diff_anchor, link_text)
else:
return link_text
# TODO: put in conf
_max_displayed_file_diffs = 1000
def _gen_revision_changes_list(revision, changes, snapshot_context):
"""
Returns a HTML string describing the file changes
introduced in a revision.
As this string will be displayed in the browse revision view,
links to adequate file diffs are also generated.
Args:
revision (str): hexadecimal representation of a revision identifier
changes (list): list of file changes in the revision
snapshot_context (dict): optional origin context used to reverse
the content urls
Returns:
A string to insert in a revision HTML view.
"""
changes_msg = []
for i, change in enumerate(changes):
hasher = hashlib.sha1()
from_query_string = ''
to_query_string = ''
diff_id = 'diff-'
if change['from']:
from_query_string = 'sha1_git:' + change['from']['target']
diff_id += change['from']['target'] + '-' + change['from_path']
diff_id += '-'
if change['to']:
to_query_string = 'sha1_git:' + change['to']['target']
diff_id += change['to']['target'] + change['to_path']
change['path'] = change['to_path'] or change['from_path']
url_args = {'from_query_string': from_query_string,
'to_query_string': to_query_string}
query_params = {'path': change['path']}
change['diff_url'] = reverse('diff-contents',
kwargs=url_args,
query_params=query_params)
hasher.update(diff_id.encode('utf-8'))
diff_id = hasher.hexdigest()
change['id'] = diff_id
panel_diff_link = '#panel_' + diff_id
if change['type'] == 'modify':
change['content_url'] = \
_gen_content_url(revision, to_query_string,
change['to_path'], snapshot_context)
changes_msg.append('modified: %s' %
_gen_diff_link(i, panel_diff_link,
change['to_path']))
elif change['type'] == 'insert':
change['content_url'] = \
_gen_content_url(revision, to_query_string,
change['to_path'], snapshot_context)
changes_msg.append('new file: %s' %
_gen_diff_link(i, panel_diff_link,
change['to_path']))
elif change['type'] == 'delete':
parent = service.lookup_revision(revision['parents'][0])
change['content_url'] = \
_gen_content_url(parent,
from_query_string,
change['from_path'], snapshot_context)
changes_msg.append('deleted: %s' %
_gen_diff_link(i, panel_diff_link,
change['from_path']))
elif change['type'] == 'rename':
change['content_url'] = \
_gen_content_url(revision, to_query_string,
change['to_path'], snapshot_context)
link_text = change['from_path'] + ' &rarr; ' + change['to_path']
changes_msg.append('renamed: %s' %
_gen_diff_link(i, panel_diff_link, link_text))
if not changes:
changes_msg.append('No changes')
return mark_safe('\n'.join(changes_msg))
@browse_route(r'revision/(?P<sha1_git>[0-9a-f]+)/diff/',
view_name='diff-revision')
def _revision_diff(request, sha1_git):
"""
Browse internal endpoint to compute revision diff
"""
try:
revision = service.lookup_revision(sha1_git)
snapshot_context = None
origin_type = request.GET.get('origin_type', None)
origin_url = request.GET.get('origin_url', None)
if not origin_url:
origin_url = request.GET.get('origin', None)
timestamp = request.GET.get('timestamp', None)
visit_id = request.GET.get('visit_id', None)
if origin_url:
snapshot_context = get_snapshot_context(None, origin_type,
origin_url,
timestamp, visit_id)
except Exception as exc:
return handle_view_exception(request, exc)
changes = service.diff_revision(sha1_git)
changes_msg = _gen_revision_changes_list(revision, changes,
snapshot_context)
diff_data = {
'total_nb_changes': len(changes),
'changes': changes[:_max_displayed_file_diffs],
'changes_msg': changes_msg
}
diff_data_json = json.dumps(diff_data, separators=(',', ': '))
return HttpResponse(diff_data_json, content_type='application/json')
@browse_route(r'revision/(?P<sha1_git>[0-9a-f]+)/',
view_name='browse-revision')
def revision_browse(request, sha1_git):
"""
Django view that produces an HTML display of a SWH revision
identified by its id.
The url that points to it is :http:get:`/browse/revision/(sha1_git)/`.
"""
try:
revision = service.lookup_revision(sha1_git)
origin_info = None
snapshot_context = None
origin_type = request.GET.get('origin_type', None)
origin_url = request.GET.get('origin_url', None)
if not origin_url:
origin_url = request.GET.get('origin', None)
timestamp = request.GET.get('timestamp', None)
visit_id = request.GET.get('visit_id', None)
snapshot_id = request.GET.get('snapshot_id', None)
path = request.GET.get('path', None)
dir_id = None
dirs, files = None, None
content_data = None
if origin_url:
snapshot_context = get_snapshot_context(None, origin_type,
origin_url,
timestamp, visit_id)
origin_info = snapshot_context['origin_info']
snapshot_id = snapshot_context['snapshot_id']
elif snapshot_id:
snapshot_context = get_snapshot_context(snapshot_id)
if path:
path_info = \
service.lookup_directory_with_path(revision['directory'], path)
if path_info['type'] == 'dir':
dir_id = path_info['target']
else:
query_string = 'sha1_git:' + path_info['target']
content_data = request_content(query_string)
else:
dir_id = revision['directory']
if dir_id:
path = '' if path is None else (path + '/')
dirs, files = get_directory_entries(dir_id)
except Exception as exc:
return handle_view_exception(request, exc)
revision_data = {}
revision_data['author'] = gen_person_link(
revision['author']['id'], revision['author']['name'])
revision_data['committer'] = gen_person_link(
revision['committer']['id'], revision['committer']['name'])
revision_data['committer date'] = format_utc_iso_date(
revision['committer_date'])
revision_data['date'] = format_utc_iso_date(revision['date'])
if snapshot_context:
revision_data['snapshot id'] = snapshot_id
revision_data['directory'] = \
gen_snapshot_directory_link(snapshot_context, sha1_git,
link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm', # noqa
'role': 'button'})
else:
revision_data['directory'] = \
gen_directory_link(revision['directory'], link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
revision_data['id'] = sha1_git
revision_data['merge'] = revision['merge']
revision_data['metadata'] = json.dumps(revision['metadata'],
sort_keys=True,
indent=4, separators=(',', ': '))
if origin_info:
revision_data['context-independent revision'] = \
gen_revision_link(sha1_git, link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
revision_data['origin id'] = origin_info['id']
revision_data['origin type'] = origin_info['type']
revision_data['origin url'] = gen_link(origin_info['url'],
origin_info['url'])
browse_snapshot_link = \
gen_snapshot_link(snapshot_id, link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
revision_data['snapshot'] = browse_snapshot_link
parents = ''
for p in revision['parents']:
parent_link = gen_revision_link(p, snapshot_context=snapshot_context)
parents += parent_link + '<br/>'
revision_data['parents'] = mark_safe(parents)
revision_data['synthetic'] = revision['synthetic']
revision_data['type'] = revision['type']
message_lines = revision['message'].split('\n')
parents_links = '<b>%s parent%s</b> ' % \
(len(revision['parents']),
'' if len(revision['parents']) == 1 else 's')
parents_links += '<i class="octicon octicon-git-commit fa-fw"></i> '
for p in revision['parents']:
parent_link = gen_revision_link(p, shorten_id=True,
snapshot_context=snapshot_context)
parents_links += parent_link
if p != revision['parents'][-1]:
parents_links += ' + '
path_info = gen_path_info(path)
query_params = {'snapshot_id': snapshot_id,
'origin_type': origin_type,
'origin_url': origin_url,
'timestamp': timestamp,
'visit_id': visit_id}
breadcrumbs = []
breadcrumbs.append({'name': revision['directory'][:7],
'url': reverse('browse-revision',
kwargs={'sha1_git': sha1_git},
query_params=query_params)})
for pi in path_info:
query_params['path'] = pi['path']
breadcrumbs.append({'name': pi['name'],
'url': reverse('browse-revision',
kwargs={'sha1_git': sha1_git},
query_params=query_params)})
vault_cooking = {
'directory_context': False,
'directory_id': None,
'revision_context': True,
'revision_id': sha1_git
}
content = None
content_size = None
mimetype = None
language = None
- readme_name = None
- readme_url = None
+ readmes = {}
if content_data:
breadcrumbs[-1]['url'] = None
content_size = content_data['length']
mimetype = content_data['mimetype']
if content_data['raw_data']:
content_display_data = prepare_content_for_display(
content_data['raw_data'], content_data['mimetype'], path)
content = content_display_data['content_data']
language = content_display_data['language']
query_params = {}
if path:
query_params['filename'] = path_info[-1]['name']
top_right_link = reverse('browse-content-raw',
kwargs={'query_string': query_string},
query_params=query_params)
top_right_link_text = mark_safe(
'<i class="fa fa-file-text fa-fw" aria-hidden="true">'
'</i>Raw File')
else:
for d in dirs:
query_params['path'] = path + d['name']
d['url'] = reverse('browse-revision',
kwargs={'sha1_git': sha1_git},
query_params=query_params)
for f in files:
query_params['path'] = path + f['name']
f['url'] = reverse('browse-revision',
kwargs={'sha1_git': sha1_git},
query_params=query_params)
f['length'] = filesizeformat(f['length'])
if f['name'].lower().startswith('readme'):
- readme_name = f['name']
- readme_sha1 = f['checksums']['sha1']
- readme_url = reverse('browse-content-raw',
- kwargs={'query_string': readme_sha1})
+ readmes[f['name']] = f['checksums']['sha1']
+
+ readme_name, readme_url = get_readme_to_display(readmes)
top_right_link = get_revision_log_url(sha1_git, snapshot_context)
top_right_link_text = mark_safe(
'<i class="fa fa-history fa-fw" aria-hidden="true"></i>'
'History')
vault_cooking['directory_context'] = True
vault_cooking['directory_id'] = dir_id
diff_revision_url = reverse('diff-revision', kwargs={'sha1_git': sha1_git},
query_params={'origin_type': origin_type,
'origin_url': origin_url,
'timestamp': timestamp,
'visit_id': visit_id})
return render(request, 'revision.html',
{'empty_browse': False,
'heading': 'Revision',
'top_panel_visible': True,
'top_panel_collapsible': True,
'top_panel_text': 'Revision metadata',
'swh_object_metadata': revision_data,
'message_header': message_lines[0],
'message_body': '\n'.join(message_lines[1:]),
'parents_links': mark_safe(parents_links),
'main_panel_visible': True,
'snapshot_context': snapshot_context,
'dirs': dirs,
'files': files,
'content': content,
'content_size': content_size,
'max_content_size': content_display_max_size,
'mimetype': mimetype,
'language': language,
'readme_name': readme_name,
'readme_url': readme_url,
'breadcrumbs': breadcrumbs,
'top_right_link': top_right_link,
'top_right_link_text': top_right_link_text,
'vault_cooking': vault_cooking,
'diff_revision_url': diff_revision_url,
'show_actions_menu': True})
NB_LOG_ENTRIES = 20
@browse_route(r'revision/(?P<sha1_git>[0-9a-f]+)/log/',
view_name='browse-revision-log')
def revision_log_browse(request, sha1_git):
"""
Django view that produces an HTML display of the history
log for a SWH revision identified by its id.
The url that points to it is :http:get:`/browse/revision/(sha1_git)/log/`.
""" # noqa
try:
per_page = int(request.GET.get('per_page', NB_LOG_ENTRIES))
revision_log = service.lookup_revision_log(sha1_git,
limit=per_page+1)
revision_log = list(revision_log)
except Exception as exc:
return handle_view_exception(request, exc)
revs_breadcrumb = request.GET.get('revs_breadcrumb', None)
revision_log_display_data = prepare_revision_log_for_display(
revision_log, per_page, revs_breadcrumb)
prev_rev = revision_log_display_data['prev_rev']
prev_revs_breadcrumb = revision_log_display_data['prev_revs_breadcrumb']
prev_log_url = None
if prev_rev:
prev_log_url = \
reverse('browse-revision-log',
kwargs={'sha1_git': prev_rev},
query_params={'revs_breadcrumb': prev_revs_breadcrumb,
'per_page': per_page})
next_rev = revision_log_display_data['next_rev']
next_revs_breadcrumb = revision_log_display_data['next_revs_breadcrumb']
next_log_url = None
if next_rev:
next_log_url = \
reverse('browse-revision-log',
kwargs={'sha1_git': next_rev},
query_params={'revs_breadcrumb': next_revs_breadcrumb,
'per_page': per_page})
revision_log_data = revision_log_display_data['revision_log_data']
for log in revision_log_data:
log['directory'] = gen_directory_link(
log['directory'],
link_text='<i class="fa fa-folder-open fa-fw" aria-hidden="true">'
'</i>Browse files',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
return render(request, 'revision-log.html',
{'empty_browse': False,
'heading': 'Revision history',
'top_panel_visible': False,
'top_panel_collapsible': False,
'top_panel_text': 'Revision history',
'swh_object_metadata': None,
'main_panel_visible': True,
'revision_log': revision_log_data,
'next_log_url': next_log_url,
'prev_log_url': prev_log_url,
'breadcrumbs': None,
'top_right_link': None,
'top_right_link_text': None,
'snapshot_context': None,
'vault_cooking': None,
'show_actions_menu': False})
diff --git a/swh/web/browse/views/utils/snapshot_context.py b/swh/web/browse/views/utils/snapshot_context.py
index c3f2af38c..ea24f8cd2 100644
--- a/swh/web/browse/views/utils/snapshot_context.py
+++ b/swh/web/browse/views/utils/snapshot_context.py
@@ -1,762 +1,760 @@
# Copyright (C) 2018 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU Affero General Public License version 3, or any later version
# See top-level LICENSE file for more information
# Utility module implementing Django views for browsing the SWH 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.utils.safestring import mark_safe
from django.template.defaultfilters import filesizeformat
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,
prepare_revision_log_for_display, gen_snapshot_directory_link,
- gen_revision_log_link, gen_link
+ gen_revision_log_link, gen_link, get_readme_to_display
)
from swh.web.common import service
from swh.web.common.exc import (
handle_view_exception, NotFoundExc
)
from swh.web.common.utils import (
reverse, gen_path_info, format_utc_iso_date
)
def _get_branch(branches, branch_name):
"""
Utility function to get a specific branch from a branches list.
Its purpose is to get the default HEAD branch as some SWH 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]
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(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']
browse_view_name = 'browse-' + swh_type + '-' + browse_context
for b in branches:
branch_url_args = dict(url_args)
branch_query_params = dict(query_params)
branch_query_params['branch'] = b['name']
if path:
b['path'] = path
branch_url_args['path'] = path
b['url'] = reverse(browse_view_name,
kwargs=branch_url_args,
query_params=branch_query_params)
for r in releases:
release_url_args = dict(url_args)
release_query_params = dict(query_params)
release_query_params['release'] = r['name']
if path:
r['path'] = path
release_url_args['path'] = path
r['url'] = reverse(browse_view_name,
kwargs=release_url_args,
query_params=release_query_params)
root_sha1_git = None
revision_id = request.GET.get('revision', None)
release_name = request.GET.get('release', None)
branch_name = None
if 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 release_name:
release = _get_release(releases, release_name)
if release:
root_sha1_git = release['directory']
revision_id = release['target']
query_params['release'] = release_name
else:
_branch_not_found("release", release_name, releases, snapshot_id,
origin_info, timestamp, visit_id)
else:
branch_name = request.GET.get('branch', None)
if branch_name:
query_params['branch'] = branch_name
branch = _get_branch(branches, branch_name or 'HEAD')
if branch:
branch_name = branch['name']
root_sha1_git = branch['directory']
revision_id = branch['revision']
else:
_branch_not_found("branch", branch_name, branches, snapshot_id,
origin_info, timestamp, visit_id)
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
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 path:
dir_info = service.lookup_directory_with_path(root_sha1_git, path)
sha1_git = dir_info['target']
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 = []
breadcrumbs.append({'name': root_sha1_git[:7],
'url': reverse(browse_view_name,
kwargs=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,
kwargs=bc_url_args,
query_params=query_params)})
path = '' if path is None else (path + '/')
for d in dirs:
bc_url_args = dict(url_args)
bc_url_args['path'] = path + d['name']
d['url'] = reverse(browse_view_name,
kwargs=bc_url_args,
query_params=query_params)
sum_file_sizes = 0
- readme_name = None
- readme_url = None
+ 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,
kwargs=bc_url_args,
query_params=query_params)
sum_file_sizes += f['length']
f['length'] = filesizeformat(f['length'])
if f['name'].lower().startswith('readme'):
- readme_name = f['name']
- readme_sha1 = f['checksums']['sha1']
- readme_url = reverse('browse-content-raw',
- kwargs={'query_string': readme_sha1})
+ readmes[f['name']] = f['checksums']['sha1']
+
+ readme_name, readme_url = get_readme_to_display(readmes)
browse_view_name = 'browse-' + swh_type + '-log'
history_url = reverse(browse_view_name,
kwargs=url_args,
query_params=query_params)
sum_file_sizes = filesizeformat(sum_file_sizes)
browse_dir_link = \
gen_directory_link(sha1_git, link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
browse_rev_link = \
gen_revision_link(revision_id,
snapshot_context=snapshot_context,
link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
dir_metadata = {'id': sha1_git,
'context-independent directory': browse_dir_link,
'number of regular files': len(files),
'number of subdirectories': len(dirs),
'sum of regular file sizes': sum_file_sizes,
'path': '/' + path,
'revision id': revision_id,
'revision': browse_rev_link,
'snapshot id': snapshot_id}
if origin_info:
dir_metadata['origin id'] = origin_info['id']
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
dir_metadata['origin visit id'] = visit_info['visit']
snapshot_context_url = reverse('browse-snapshot-directory',
kwargs={'snapshot_id': snapshot_id},
query_params=request.GET)
browse_snapshot_link = \
gen_link(snapshot_context_url, link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
dir_metadata['snapshot context'] = browse_snapshot_link
vault_cooking = {
'directory_context': True,
'directory_id': sha1_git,
'revision_context': True,
'revision_id': revision_id
}
return render(request, 'directory.html',
{'empty_browse': False,
'heading': 'Directory',
'top_panel_visible': True,
'top_panel_collapsible': True,
'top_panel_text': 'Directory metadata',
'swh_object_metadata': dir_metadata,
'main_panel_visible': True,
'dirs': dirs,
'files': files,
'breadcrumbs': breadcrumbs,
'top_right_link': history_url,
'top_right_link_text': mark_safe(
'<i class="fa fa-history fa-fw" aria-hidden="true"></i>'
'History'
),
'readme_name': readme_name,
'readme_url': readme_url,
'snapshot_context': snapshot_context,
'vault_cooking': vault_cooking,
'show_actions_menu': True})
def browse_snapshot_content(request, snapshot_id=None, origin_type=None,
origin_url=None, timestamp=None, path=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']
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)
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
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']
filename = None
path_info = None
browse_view_name = 'browse-' + swh_type + '-directory'
breadcrumbs = []
split_path = path.split('/')
filename = split_path[-1]
path_info = gen_path_info(path[:-len(filename)])
breadcrumbs.append({'name': root_sha1_git[:7],
'url': reverse(browse_view_name,
kwargs=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,
kwargs=bc_url_args,
query_params=query_params)})
breadcrumbs.append({'name': filename,
'url': None})
browse_content_link = \
gen_content_link(sha1_git, link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
content_raw_url = reverse('browse-content-raw',
kwargs={'query_string': query_string},
query_params={'filename': filename})
browse_rev_link = \
gen_revision_link(revision_id,
snapshot_context=snapshot_context,
link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
content_metadata = {
'context-independent content': browse_content_link,
'sha1 checksum': content_data['checksums']['sha1'],
'sha1_git checksum': content_data['checksums']['sha1_git'],
'sha256 checksum': content_data['checksums']['sha256'],
'blake2s256 checksum': content_data['checksums']['blake2s256'],
'mime type': content_data['mimetype'],
'encoding': content_data['encoding'],
'size': filesizeformat(content_data['length']),
'language': content_data['language'],
'licenses': content_data['licenses'],
'path': '/' + path[:-len(filename)],
'filename': filename,
'revision id': revision_id,
'revision': browse_rev_link,
'snapshot id': snapshot_id
}
if origin_info:
content_metadata['origin id'] = origin_info['id']
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
content_metadata['origin visit id'] = visit_info['visit']
browse_snapshot_url = reverse('browse-snapshot-content',
kwargs={'snapshot_id': snapshot_id,
'path': path},
query_params=request.GET)
browse_snapshot_link = \
gen_link(browse_snapshot_url, link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
content_metadata['snapshot context'] = browse_snapshot_link
return render(request, 'content.html',
{'empty_browse': False,
'heading': 'Content',
'top_panel_visible': True,
'top_panel_collapsible': True,
'top_panel_text': 'Content metadata',
'swh_object_metadata': content_metadata,
'main_panel_visible': True,
'content': content,
'content_size': content_data['length'],
'max_content_size': content_display_max_size,
'mimetype': content_data['mimetype'],
'language': language,
'breadcrumbs': breadcrumbs,
'top_right_link': content_raw_url,
'top_right_link_text': mark_safe(
'<i class="fa fa-file-text fa-fw" aria-hidden="true">'
'</i>Raw File'),
'snapshot_context': snapshot_context,
'vault_cooking': None,
'show_actions_menu': False})
PER_PAGE = 20
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']
current_rev = revision_id
per_page = int(request.GET.get('per_page', PER_PAGE))
revs_breadcrumb = request.GET.get('revs_breadcrumb', None)
if revs_breadcrumb:
current_rev = revs_breadcrumb.split('/')[-1]
revision_log = service.lookup_revision_log(current_rev,
limit=per_page+1)
revision_log = list(revision_log)
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
revision_log_display_data = prepare_revision_log_for_display(
revision_log, per_page, revs_breadcrumb, snapshot_context)
browse_view_name = 'browse-' + swh_type + '-log'
prev_rev = revision_log_display_data['prev_rev']
prev_revs_breadcrumb = revision_log_display_data['prev_revs_breadcrumb']
prev_log_url = None
query_params['revs_breadcrumb'] = prev_revs_breadcrumb
if prev_rev:
prev_log_url = \
reverse(browse_view_name,
kwargs=url_args,
query_params=query_params)
next_rev = revision_log_display_data['next_rev']
next_revs_breadcrumb = revision_log_display_data['next_revs_breadcrumb']
next_log_url = None
query_params['revs_breadcrumb'] = next_revs_breadcrumb
if next_rev:
next_log_url = \
reverse(browse_view_name,
kwargs=url_args,
query_params=query_params)
revision_log_data = revision_log_display_data['revision_log_data']
for i, log in enumerate(revision_log_data):
params = {
'revision': revision_log[i]['id'],
}
if 'visit_id' in query_params:
params['visit_id'] = query_params['visit_id']
log['directory'] = gen_snapshot_directory_link(
snapshot_context, revision_log[i]['id'],
link_text='<i class="fa fa-folder-open fa-fw" aria-hidden="true">'
'</i>Browse files',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
browse_log_link = \
gen_revision_log_link(revision_id, link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
revision_metadata = {
'context-independent revision history': browse_log_link,
'snapshot id': snapshot_id
}
if origin_info:
revision_metadata['origin id'] = origin_info['id']
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
revision_metadata['origin visit id'] = visit_info['visit']
browse_snapshot_url = reverse('browse-snapshot-log',
kwargs={'snapshot_id': snapshot_id},
query_params=request.GET)
browse_snapshot_link = \
gen_link(browse_snapshot_url, link_text='Browse',
link_attrs={'class': 'btn btn-default btn-sm',
'role': 'button'})
revision_metadata['snapshot context'] = browse_snapshot_link
return render(request, 'revision-log.html',
{'empty_browse': False,
'heading': 'Revision history',
'top_panel_visible': True,
'top_panel_collapsible': True,
'top_panel_text': 'Revision history metadata',
'swh_object_metadata': revision_metadata,
'main_panel_visible': True,
'revision_log': revision_log_data,
'next_log_url': next_log_url,
'prev_log_url': prev_log_url,
'breadcrumbs': None,
'top_right_link': None,
'top_right_link_text': None,
'snapshot_context': snapshot_context,
'vault_cooking': None,
'show_actions_menu': False})
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)
except Exception as exc:
return handle_view_exception(request, exc)
branches_offset = int(request.GET.get('branches_offset', 0))
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'
branches = snapshot_context['branches']
displayed_branches = \
branches[branches_offset:branches_offset+PER_PAGE]
for branch in displayed_branches:
if snapshot_id:
revision_url = reverse('browse-revision',
kwargs={'sha1_git': branch['revision']},
query_params={'snapshot_id': snapshot_id})
else:
revision_url = reverse('browse-revision',
kwargs={'sha1_git': branch['revision']},
query_params={'origin_type': origin_info['type'], # noqa
'origin_url': origin_info['url']}) # noqa
query_params['branch'] = branch['name']
directory_url = reverse(browse_view_name,
kwargs=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
next_offset = branches_offset + PER_PAGE
prev_offset = branches_offset - PER_PAGE
if next_offset < len(branches):
query_params['branches_offset'] = next_offset
next_branches_url = reverse(browse_view_name,
kwargs=url_args, query_params=query_params)
query_params['branches_offset'] = None
if prev_offset >= 0:
if prev_offset != 0:
query_params['branches_offset'] = prev_offset
prev_branches_url = reverse(browse_view_name,
kwargs=url_args, query_params=query_params)
return render(request, 'branches.html',
{'empty_browse': False,
'heading': 'Origin branches',
'top_panel_visible': False,
'top_panel_collapsible': False,
'top_panel_text': 'Branches list',
'swh_object_metadata': {},
'main_panel_visible': True,
'top_right_link': None,
'top_right_link_text': 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)
except Exception as exc:
return handle_view_exception(request, exc)
releases_offset = int(request.GET.get('releases_offset', 0))
swh_type = snapshot_context['swh_type']
origin_info = snapshot_context['origin_info']
url_args = snapshot_context['url_args']
query_params = snapshot_context['query_params']
releases = snapshot_context['releases']
displayed_releases = \
releases[releases_offset:releases_offset+PER_PAGE]
for release in displayed_releases:
if snapshot_id:
release_url = reverse('browse-release',
kwargs={'sha1_git': release['id']},
query_params={'snapshot_id': snapshot_id})
else:
release_url = reverse('browse-release',
kwargs={'sha1_git': release['id']},
query_params={'origin_type': origin_info['type'], # noqa
'origin_url': origin_info['url']}) # noqa
query_params['release'] = release['name']
del query_params['release']
release['release_url'] = release_url
browse_view_name = 'browse-' + swh_type + '-releases'
prev_releases_url = None
next_releases_url = None
next_offset = releases_offset + PER_PAGE
prev_offset = releases_offset - PER_PAGE
if next_offset < len(releases):
query_params['releases_offset'] = next_offset
next_releases_url = reverse(browse_view_name,
kwargs=url_args, query_params=query_params)
query_params['releases_offset'] = None
if prev_offset >= 0:
if prev_offset != 0:
query_params['releases_offset'] = prev_offset
prev_releases_url = reverse(browse_view_name,
kwargs=url_args, query_params=query_params)
return render(request, 'releases.html',
{'empty_browse': False,
'heading': 'Origin releases',
'top_panel_visible': False,
'top_panel_collapsible': False,
'top_panel_text': 'Releases list',
'swh_object_metadata': {},
'main_panel_visible': True,
'top_right_link': None,
'top_right_link_text': 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})

File Metadata

Mime Type
text/x-diff
Expires
Sat, Jun 21, 5:20 PM (1 w, 3 d ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3303472

Event Timeline

About · Developer information · Legal