Merge branch 'metadata'

mediagoblin/db/migrations.py

@@ -31,6 +31,7 @@ from mediagoblin.db.migration_tools import (
     RegisterMigration, inspect_table, replace_table_hack)
 from mediagoblin.db.models import (MediaEntry, Collection, MediaComment, User, 
         Privilege)
+from mediagoblin.db.extratypes import JSONEncoded, MutationDict
 
 MIGRATIONS = {}
 
@@ -720,3 +721,15 @@ def drop_MediaEntry_collected(db):
     media_collected.drop()
 
     db.commit()
+
+@RegisterMigration(20, MIGRATIONS)
+def add_metadata_column(db):
+    metadata = MetaData(bind=db.bind)
+
+    media_entry = inspect_table(metadata, 'core__media_entries')
+
+    col = Column('media_metadata', MutationDict.as_mutable(JSONEncoded),
+        default=MutationDict())
+    col.create(media_entry)
+
+    db.commit()

mediagoblin/db/models.py

@@ -264,6 +264,8 @@ class MediaEntry(Base, MediaEntryMixin):
         cascade="all, delete-orphan"
         )
     collections = association_proxy("collections_helper", "in_collection")
+    media_metadata = Column(MutationDict.as_mutable(JSONEncoded),
+        default=MutationDict())
 
     ## TODO
     # fail_error

mediagoblin/edit/forms.py

@@ -15,10 +15,12 @@
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 import wtforms
+from jsonschema import Draft4Validator
 
 from mediagoblin.tools.text import tag_length_validator
 from mediagoblin.tools.translate import lazy_pass_to_ugettext as _
 from mediagoblin.tools.licenses import licenses_as_choices
+from mediagoblin.tools.metadata import DEFAULT_SCHEMA, DEFAULT_CHECKER
 from mediagoblin.auth.tools import normalize_user_or_email_field
 
 
@@ -122,3 +124,38 @@ class ChangeEmailForm(wtforms.Form):
         [wtforms.validators.Required()],
         description=_(
             "Enter your password to prove you own this account."))
+
+class MetaDataValidator(object):
+    """
+    Custom validator which runs form data in a MetaDataForm through a jsonschema
+    validator and passes errors recieved in jsonschema to wtforms.
+
+    :param  schema              The json schema to validate the data against. By
+                                default this uses the DEFAULT_SCHEMA from
+                                mediagoblin.tools.metadata.
+    :param  format_checker      The FormatChecker object that limits which types
+                                jsonschema can recognize. By default this uses
+                                DEFAULT_CHECKER from mediagoblin.tools.metadata.
+    """
+    def __init__(self, schema=DEFAULT_SCHEMA, format_checker=DEFAULT_CHECKER):
+        self.schema = schema
+        self.format_checker = format_checker
+
+    def __call__(self, form, field):
+        metadata_dict = {field.data:form.value.data}
+        validator = Draft4Validator(self.schema,
+                        format_checker=self.format_checker)
+        errors = [e.message
+            for e in validator.iter_errors(metadata_dict)]
+        if len(errors) >= 1:
+            raise wtforms.validators.ValidationError(
+                errors.pop())
+
+class MetaDataForm(wtforms.Form):
+    identifier = wtforms.TextField(_(u'Identifier'),[MetaDataValidator()])
+    value = wtforms.TextField(_(u'Value'))
+
+class EditMetaDataForm(wtforms.Form):
+    media_metadata = wtforms.FieldList(
+        wtforms.FormField(MetaDataForm, ""),
+    )

mediagoblin/edit/views.py

@@ -17,8 +17,10 @@
 from datetime import datetime
 
 from itsdangerous import BadSignature
+from pyld import jsonld
 from werkzeug.exceptions import Forbidden
 from werkzeug.utils import secure_filename
+from jsonschema import ValidationError, Draft4Validator
 
 from mediagoblin import messages
 from mediagoblin import mg_globals
@@ -29,8 +31,11 @@ from mediagoblin.edit import forms
 from mediagoblin.edit.lib import may_edit_media
 from mediagoblin.decorators import (require_active_login, active_user_from_url,
                             get_media_entry_by_id, user_may_alter_collection,
-                            get_user_collection)
+                            get_user_collection, user_has_privilege,
+                            user_not_banned)
 from mediagoblin.tools.crypto import get_timed_signer_url
+from mediagoblin.tools.metadata import (compact_and_validate, DEFAULT_CHECKER,
+                                        DEFAULT_SCHEMA)
 from mediagoblin.tools.mail import email_debug_message
 from mediagoblin.tools.response import (render_to_response,
                                         redirect, redirect_obj, render_404)
@@ -432,3 +437,30 @@ def change_email(request):
         'mediagoblin/edit/change_email.html',
         {'form': form,
          'user': user})
+
+@user_has_privilege(u'admin')
+@require_active_login
+@get_media_entry_by_id
+def edit_metadata(request, media):
+    form = forms.EditMetaDataForm(request.form)
+    if request.method == "POST" and form.validate():
+        metadata_dict = dict([(row['identifier'],row['value'])
+                            for row in form.media_metadata.data])
+        json_ld_metadata = None
+        json_ld_metadata = compact_and_validate(metadata_dict)
+        media.media_metadata = json_ld_metadata
+        media.save()
+        return redirect_obj(request, media)      
+
+    if len(form.media_metadata) == 0:
+        for identifier, value in media.media_metadata.iteritems():
+            if identifier == "@context": continue
+            form.media_metadata.append_entry({
+                'identifier':identifier,
+                'value':value})
+
+    return render_to_response(
+        request,
+        'mediagoblin/edit/metadata.html',
+        {'form':form,
+         'media':media})

mediagoblin/gmg_commands/__init__.py

@@ -57,6 +57,10 @@ SUBCOMMAND_MAP = {
         'setup': 'mediagoblin.gmg_commands.deletemedia:parser_setup',
         'func': 'mediagoblin.gmg_commands.deletemedia:deletemedia',
         'help': 'Delete media entries'},
+    'batchaddmedia': {
+        'setup': 'mediagoblin.gmg_commands.batchaddmedia:parser_setup',
+        'func': 'mediagoblin.gmg_commands.batchaddmedia:batchaddmedia',
+        'help': 'Add many media entries at once'},
     # 'theme': {
     #     'setup': 'mediagoblin.gmg_commands.theme:theme_parser_setup',
     #     'func': 'mediagoblin.gmg_commands.theme:theme',

mediagoblin/gmg_commands/batchaddmedia.py

@@ -0,0 +1,193 @@
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import os
+import requests
+from csv import reader as csv_reader
+from urlparse import urlparse
+
+from mediagoblin.gmg_commands import util as commands_util
+from mediagoblin.submit.lib import (
+    submit_media, get_upload_file_limits,
+    FileUploadLimit, UserUploadLimit, UserPastUploadLimit)
+from mediagoblin.tools.metadata import compact_and_validate
+from mediagoblin.tools.translate import pass_to_ugettext as _
+from jsonschema.exceptions import ValidationError
+
+
+def parser_setup(subparser):
+    subparser.description = """\
+This command allows the administrator to upload many media files at once."""
+    subparser.epilog = _(u"""For more information about how to properly run this
+script (and how to format the metadata csv file), read the MediaGoblin
+documentation page on command line uploading
+<http://docs.mediagoblin.org/siteadmin/commandline-upload.html>""")
+    subparser.add_argument(
+        'username',
+        help=_(u"Name of user these media entries belong to"))
+    subparser.add_argument(
+        'metadata_path',
+        help=_(
+u"""Path to the csv file containing metadata information."""))
+    subparser.add_argument(
+        '--celery',
+        action='store_true',
+        help=_(u"Don't process eagerly, pass off to celery"))
+
+
+def batchaddmedia(args):
+    # Run eagerly unless explicetly set not to
+    if not args.celery:
+        os.environ['CELERY_ALWAYS_EAGER'] = 'true'
+
+    app = commands_util.setup_app(args)
+
+    files_uploaded, files_attempted = 0, 0
+
+    # get the user
+    user = app.db.User.query.filter_by(username=args.username.lower()).first()
+    if user is None:
+        print _(u"Sorry, no user by username '{username}' exists".format(
+                    username=args.username))
+        return
+
+    upload_limit, max_file_size = get_upload_file_limits(user)
+    temp_files = []
+
+    if os.path.isfile(args.metadata_path):
+        metadata_path = args.metadata_path
+
+    else:
+        error = _(u'File at {path} not found, use -h flag for help'.format(
+                    path=args.metadata_path))
+        print error
+        return
+
+    abs_metadata_filename = os.path.abspath(metadata_path)
+    abs_metadata_dir = os.path.dirname(abs_metadata_filename)
+    upload_limit, max_file_size = get_upload_file_limits(user)
+
+    def maybe_unicodeify(some_string):
+        # this is kinda terrible
+        if some_string is None:
+            return None
+        else:
+            return unicode(some_string)
+
+    with file(abs_metadata_filename, 'r') as all_metadata:
+        contents = all_metadata.read()
+        media_metadata = parse_csv_file(contents)
+
+    for media_id, file_metadata in media_metadata.iteritems():
+        files_attempted += 1
+        # In case the metadata was not uploaded initialize an empty dictionary.
+        json_ld_metadata = compact_and_validate({})
+
+        # Get all metadata entries starting with 'media' as variables and then
+        # delete them because those are for internal use only.
+        original_location = file_metadata['location']
+
+        ### Pull the important media information for mediagoblin from the
+        ### metadata, if it is provided.
+        title = file_metadata.get('title') or file_metadata.get('dc:title')
+        description = (file_metadata.get('description') or
+            file_metadata.get('dc:description'))
+
+        license = file_metadata.get('license')
+        try:
+            json_ld_metadata = compact_and_validate(file_metadata)
+        except ValidationError, exc:
+            error = _(u"""Error with media '{media_id}' value '{error_path}': {error_msg}
+Metadata was not uploaded.""".format(
+                media_id=media_id,
+                error_path=exc.path[0],
+                error_msg=exc.message))
+            print error
+            continue
+
+        url = urlparse(original_location)
+        filename = url.path.split()[-1]
+
+        if url.scheme == 'http':
+            res = requests.get(url.geturl(), stream=True)
+            media_file = res.raw
+
+        elif url.scheme == '':
+            path = url.path
+            if os.path.isabs(path):
+                file_abs_path = os.path.abspath(path)
+            else:
+                file_path = os.path.join(abs_metadata_dir, path)
+                file_abs_path = os.path.abspath(file_path)
+            try:
+                media_file = file(file_abs_path, 'r')
+            except IOError:
+                print _(u"""\
+FAIL: Local file {filename} could not be accessed.
+{filename} will not be uploaded.""".format(filename=filename))
+                continue
+        try:
+            submit_media(
+                mg_app=app,
+                user=user,
+                submitted_file=media_file,
+                filename=filename,
+                title=maybe_unicodeify(title),
+                description=maybe_unicodeify(description),
+                license=maybe_unicodeify(license),
+                metadata=json_ld_metadata,
+                tags_string=u"",
+                upload_limit=upload_limit, max_file_size=max_file_size)
+            print _(u"""Successfully submitted {filename}!
+Be sure to look at the Media Processing Panel on your website to be sure it
+uploaded successfully.""".format(filename=filename))
+            files_uploaded += 1
+        except FileUploadLimit:
+            print _(
+u"FAIL: This file is larger than the upload limits for this site.")
+        except UserUploadLimit:
+            print _(
+"FAIL: This file will put this user past their upload limits.")
+        except UserPastUploadLimit:
+            print _("FAIL: This user is already past their upload limits.")
+    print _(
+"{files_uploaded} out of {files_attempted} files successfully submitted".format(
+        files_uploaded=files_uploaded,
+        files_attempted=files_attempted))
+
+
+def parse_csv_file(file_contents):
+    """
+    The helper function which converts the csv file into a dictionary where each
+    item's key is the provided value 'id' and each item's value is another
+    dictionary.
+    """
+    list_of_contents = file_contents.split('\n')
+    key, lines = (list_of_contents[0].split(','),
+                  list_of_contents[1:])
+    objects_dict = {}
+
+    # Build a dictionary
+    for index, line in enumerate(lines):
+        if line.isspace() or line == '': continue
+        values = csv_reader([line]).next()
+        line_dict = dict([(key[i], val)
+            for i, val in enumerate(values)])
+        media_id = line_dict.get('id') or index
+        objects_dict[media_id] = (line_dict)
+
+    return objects_dict
+

mediagoblin/plugins/metadata_display/__init__.py

@@ -0,0 +1,41 @@
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+import os
+from pkg_resources import resource_filename
+
+from mediagoblin.plugins.metadata_display.lib import add_rdfa_to_readable_to_media_home
+from mediagoblin.tools import pluginapi
+from mediagoblin.tools.staticdirect import PluginStatic
+
+PLUGIN_DIR = os.path.dirname(__file__)
+
+def setup_plugin():
+    # Register the template path.
+    pluginapi.register_template_path(os.path.join(PLUGIN_DIR, 'templates'))
+
+    pluginapi.register_template_hooks(
+        {"media_sideinfo": "mediagoblin/plugins/metadata_display/metadata_table.html",
+         "head": "mediagoblin/plugins/metadata_display/bits/metadata_extra_head.html"})
+
+
+hooks = {
+    'setup': setup_plugin,
+    'static_setup': lambda: PluginStatic(
+        'metadata_display',
+        resource_filename('mediagoblin.plugins.metadata_display', 'static')
+     ),
+    'media_home_context':add_rdfa_to_readable_to_media_home
+    }

mediagoblin/plugins/metadata_display/lib.py

@@ -0,0 +1,31 @@
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+def rdfa_to_readable(rdfa_predicate):
+    """
+    A simple script to convert rdfa resource descriptors into a form more
+    accessible for humans.
+    """
+    readable = rdfa_predicate.split(u":")[1].capitalize()
+    return readable
+
+def add_rdfa_to_readable_to_media_home(context):
+    """
+    A context hook which adds the 'rdfa_to_readable' filter to
+    the media home page.
+    """
+    context['rdfa_to_readable'] = rdfa_to_readable
+    return context

mediagoblin/plugins/metadata_display/static/css/metadata_display.css

@@ -0,0 +1,14 @@
+table.metadata_info {
+  font-size:85%;
+  margin-left:10px;
+}
+
+table.metadata_info th {
+  font-weight: bold;
+  border-spacing: 10px;
+  text-align: left;
+}
+table.metadata_info td {
+  padding: 4px 8px;
+}
+

mediagoblin/plugins/metadata_display/templates/mediagoblin/plugins/metadata_display/bits/metadata_extra_head.html

@@ -0,0 +1,3 @@
+    <link rel="stylesheet" type="text/css"
+          href="{{ request.staticdirect('css/metadata_display.css',
+                                        'metadata_display') }}"/>

mediagoblin/plugins/metadata_display/templates/mediagoblin/plugins/metadata_display/metadata_table.html

@@ -0,0 +1,42 @@
+{#
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#}
+{% block metadata_information_table %}
+{%- set metadata=media.media_metadata %}
+{%- set metadata_context=metadata['@context'] %}
+{%- if metadata %}
+  <h3>{% trans %}Metadata{% endtrans %}</h3>
+  {#- NOTE: In some smart future where the context is more extensible,
+        we will need to add to the prefix here-#}
+  <table class="metadata_info">
+    {%- for key, value in metadata.iteritems() if not key=='@context' %}
+      {% if value -%}
+        <tr>
+          <th>{{ rdfa_to_readable(key) }}</th>
+          <td property="{{ key }}">{{ value }}</td>
+        </tr>
+      {%- endif -%}
+    {%- endfor %}
+  </table>
+{% endif %}
+{% if request.user and request.user.has_privilege('admin') %}
+  <a href="{{ request.urlgen('mediagoblin.edit.metadata',
+                    user=media.get_uploader.username,
+                    media_id=media.id) }}">
+  {% trans %}Edit Metadata{% endtrans %}</a>
+{% endif %}
+{% endblock %}

mediagoblin/plugins/metadata_display/templates/mediagoblin/plugins/metadata_display/metadata_table.html.orig

@@ -0,0 +1,60 @@
+{#
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#}
+
+<<<<<<< HEAD:mediagoblin/templates/mediagoblin/utils/metadata_table.html
+{%- macro render_table(request, media_entry, format_predicate) %}
+  {%- set metadata=media_entry.media_metadata %}
+  {%- set metadata_context=metadata['@context'] %}
+  {%- if metadata %}
+      <h3>{% trans %}Metadata Information{% endtrans %}</h3>
+      <table class="metadata_info">
+        {%- for key, value in metadata.iteritems() if (
+            not key=='@context' and value) %}
+            <tr {% if loop.index%2 == 1 %}class="highlight"{% endif %}>
+              <th>{{ format_predicate(key) }}</th>
+              <td property="{{ key }}">
+                {{ value }}</td>
+            </tr>
+        {%- endfor %}
+      </table>
+  {% endif %}
+  {% if request.user and request.user.has_privilege('admin') %}
+      <a href="{{ request.urlgen('mediagoblin.edit.metadata',
+                    user=media_entry.get_uploader.username,
+                    media_id=media_entry.id) }}">
+        {% trans %}Edit Metadata{% endtrans %}</a>
+  {% endif %}
+{%- endmacro %}
+=======
+{%- set metadata=media.media_metadata %}
+{%- set metadata_context=metadata['@context'] %}
+{%- if metadata %}
+  {#- NOTE: In some smart future where the context is more extensible,
+        we will need to add to the prefix here-#}
+  <table>
+    {%- for key, value in metadata.iteritems() if not key=='@context' %}
+      {% if value -%}
+        <tr>
+          <td>{{ rdfa_to_readable(key) }}</td>
+          <td property="{{ key }}">{{ value }}</td>
+        </tr>
+      {%- endif -%}
+    {%- endfor %}
+  </table>
+{% endif %}
+>>>>>>> acfcaf6366bd4695c1c37c7aa8ff5a176b412e2a:mediagoblin/plugins/metadata_display/templates/mediagoblin/plugins/metadata_display/metadata_table.html

mediagoblin/routing.py

@@ -28,7 +28,7 @@ _log = logging.getLogger(__name__)
 def get_url_map():
     add_route('index', '/', 'mediagoblin.views:root_view')
     add_route('terms_of_service','/terms_of_service',
-        'mediagoblin.views:terms_of_service')
+        'mediagoblin.views:terms_of_service'),
     mount('/auth', auth_routes)
     mount('/mod', moderation_routes)
 

mediagoblin/static/css/base.css

@@ -609,7 +609,6 @@ a img.media_image {
   cursor: -moz-zoom-in;
   cursor: zoom-in;
 }
-
 /* icons */
 
 img.media_icon {
@@ -938,3 +937,16 @@ p.verifier {
     none repeat scroll 0% 0% rgb(221, 221, 221);
     padding: 1em 0px;
 }
+
+/* for the media metadata editing table */
+table.metadata_editor {
+    margin: 10px auto;
+    width: 800px;
+}
+
+table.metadata_editor tr td {
+    width:350px;
+}
+table.metadata_editor tr td.form_field_input input {
+    width:350px;
+}

mediagoblin/static/metadata/rdfa11.jsonld

@@ -0,0 +1,48 @@
+{
+  "@context": {
+    "cat": "http://www.w3.org/ns/dcat#",
+    "qb": "http://purl.org/linked-data/cube#",
+    "grddl": "http://www.w3.org/2003/g/data-view#",
+    "ma": "http://www.w3.org/ns/ma-ont#",
+    "owl": "http://www.w3.org/2002/07/owl#",
+    "rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
+    "rdfa": "http://www.w3.org/ns/rdfa#",
+    "rdfs": "http://www.w3.org/2000/01/rdf-schema#",
+    "rif": "http://www.w3.org/2007/rif#",
+    "rr": "http://www.w3.org/ns/r2rml#",
+    "skos": "http://www.w3.org/2004/02/skos/core#",
+    "skosxl": "http://www.w3.org/2008/05/skos-xl#",
+    "wdr": "http://www.w3.org/2007/05/powder#",
+    "void": "http://rdfs.org/ns/void#",
+    "wdrs": "http://www.w3.org/2007/05/powder-s#",
+    "xhv": "http://www.w3.org/1999/xhtml/vocab#",
+    "xml": "http://www.w3.org/XML/1998/namespace",
+    "xsd": "http://www.w3.org/2001/XMLSchema#",
+    "prov": "http://www.w3.org/ns/prov#",
+    "sd": "http://www.w3.org/ns/sparql-service-description#",
+    "org": "http://www.w3.org/ns/org#",
+    "gldp": "http://www.w3.org/ns/people#",
+    "cnt": "http://www.w3.org/2008/content#",
+    "dcat": "http://www.w3.org/ns/dcat#",
+    "earl": "http://www.w3.org/ns/earl#",
+    "ht": "http://www.w3.org/2006/http#",
+    "ptr": "http://www.w3.org/2009/pointers#",
+    "cc": "http://creativecommons.org/ns#",
+    "ctag": "http://commontag.org/ns#",
+    "dc": "http://purl.org/dc/terms/",
+    "dc11": "http://purl.org/dc/elements/1.1/",
+    "dcterms": "http://purl.org/dc/terms/",
+    "foaf": "http://xmlns.com/foaf/0.1/",
+    "gr": "http://purl.org/goodrelations/v1#",
+    "ical": "http://www.w3.org/2002/12/cal/icaltzd#",
+    "og": "http://ogp.me/ns#",
+    "rev": "http://purl.org/stuff/rev#",
+    "sioc": "http://rdfs.org/sioc/ns#",
+    "v": "http://rdf.data-vocabulary.org/#",
+    "vcard": "http://www.w3.org/2006/vcard/ns#",
+    "schema": "http://schema.org/",
+    "describedby": "http://www.w3.org/2007/05/powder-s#describedby",
+    "license": "http://www.w3.org/1999/xhtml/vocab#license",
+    "role": "http://www.w3.org/1999/xhtml/vocab#role"
+  }
+}

mediagoblin/submit/lib.py

@@ -98,7 +98,7 @@ class UserPastUploadLimit(UploadLimitError):
 
 def submit_media(mg_app, user, submitted_file, filename,
                  title=None, description=None,
-                 license=None, tags_string=u"",
+                 license=None, metadata=None, tags_string=u"",
                  upload_limit=None, max_file_size=None,
                  callback_url=None,
                  # If provided we'll do the feed_url update, otherwise ignore
@@ -142,6 +142,8 @@ def submit_media(mg_app, user, submitted_file, filename,
 
     entry.license = license or None
 
+    entry.media_metadata = metadata or {}
+
     # Process the user's folksonomy "tags"
     entry.tags = convert_to_tag_list_of_dicts(tags_string)
 

mediagoblin/templates/mediagoblin/edit/metadata.html

@@ -0,0 +1,94 @@
+{#
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#}
+{%- extends "mediagoblin/base.html" %}
+{% import "/mediagoblin/utils/wtforms.html" as wtforms_util %}
+{% block mediagoblin_head %}
+  <script>
+    function add_new_row(table_id, row_number, input_prefix) {
+        new_row = $('<tr>').append(
+                      $('<td>').attr(
+                      'class','form_field_input').append(
+                          $('<input>').attr('name',
+                          input_prefix + row_number + "-identifier").attr('id',
+                          input_prefix + row_number + "-identifier")
+                      )
+                  ).append(
+                      $('<td>').attr(
+                      'class','form_field_input').append(
+                          $('<input>').attr('name',
+                          input_prefix + row_number + "-value").attr('id',
+                          input_prefix + row_number + "-value")
+                      )
+                  );
+        $(table_id).append(new_row);
+    }
+    function clear_empty_rows(list_id) {
+        $('table'+list_id+' tr').each(function(row){
+            id_input = $(this).find('td').find('input');
+            value_input = $(this).find('td').next().find('input');
+            if ((value_input.attr('value') == "") &&
+                    (id_input.attr('value') == "")) {
+                $(this).remove();
+            }
+        })
+    }
+
+    $(document).ready(function(){
+        var metadata_lines = {{ form.media_metadata | length }};
+        $("#add_new_metadata_row").click(function(){
+            add_new_row("#metadata_list",
+                        metadata_lines,
+                        'media_metadata-');
+            metadata_lines += 1;
+        })
+
+        $("#clear_empty_rows").click(function(){
+            clear_empty_rows("#metadata_list");
+        })
+    })
+  </script>
+{% endblock %}
+{% block mediagoblin_content %}
+  <h2>{% trans media_name=media.title -%}
+    Metadata for "{{ media_name }}"{% endtrans %}</h2>
+  <form action="" method="POST" id="metadata_form">
+
+<!-- This table holds all the information about the media entry's metadata -->
+  <h3>{% trans %}MetaData{% endtrans %}</h3>
+  <table class="metadata_editor" id="metadata_list" >
+    {{ wtforms_util.render_fieldlist_as_table_rows(form.media_metadata) }}
+  </table>
+
+<!-- These are the buttons you use to control the form -->
+  <table class="metadata_editor" id="buttons_bottom">
+    <tr>
+      <td><input type=button value="{% trans %}Add new Row{% endtrans %}"
+        class="button_action" id="add_new_metadata_row" />
+      </td>
+      <td><input type=submit value="{% trans %}Update Metadata{% endtrans %}"
+        class="button_action_highlight" /></td>
+    </tr>
+    <tr>
+      <td><input type=button value="{% trans %}Clear empty Rows{% endtrans %}"
+        class="button_action" id="clear_empty_rows" /></td>
+    </tr>
+  </table>
+  {{ csrf_token }}
+  </form>
+
+{% endblock mediagoblin_content %}

mediagoblin/templates/mediagoblin/user_pages/media.html

@@ -230,9 +230,6 @@
 
     {% template_hook("media_sideinfo") %}
 
-    {% block mediagoblin_sidebar %}
-    {% endblock %}
-
   </div><!--end media_sidebar-->
 
   <div class="clear"></div>

mediagoblin/templates/mediagoblin/utils/wtforms.html

@@ -70,23 +70,56 @@
 {# Auto-render a form as a table #}
 {% macro render_table(form) -%}
   {% for field in form %}
-    <tr>
-      <th>{{ field.label.text }}</th>
-      <td>
-        {{field}}
-        {% if field.errors %}
-          <br />
-          <ul class="errors">
-            {% for error in field.errors %}
-              <li>{{error}}</li>
-            {% endfor %}
-          </ul>
-        {% endif %}
-      </td>
-    </tr>
+    render_field_as_table_row(field)
   {% endfor %}
 {%- endmacro %}
 
+{% macro render_form_as_table_row(form) %}
+  <tr>
+  {%- for field in form %}
+    <td class="form_field_input">
+      {{field}}
+    </td>
+  {%- endfor %}
+  </tr>
+  <tr>
+  {%- for field in form %}
+      {% for error in field.errors %}
+      <tr>
+        <td>
+          <p class="form_field_error">{{error}}</p>
+        </td>
+      </tr>
+      {%- endfor %}
+  {%- endfor %}
+{%- endmacro %}
+
+{% macro render_field_as_table_row(field) %}
+  <tr>
+    <th>{{ field.label.text }}</th>
+    <td>
+      {{field}}
+    </td>
+  </tr>
+  {% for error in field.errors %}
+  <tr>
+    <td>
+      <p class="form_field_error">{{error}}</p>
+    </td>
+  </tr>
+  {%- endfor %}
+{% endmacro %}
+
+{% macro render_fieldlist_as_table_rows(fieldlist) %}
+  {% for field in fieldlist -%}
+    {%- if field.type == 'FormField' %}
+        {{ render_form_as_table_row(field) }}
+    {%- else %}
+        {{ render_field_as_table_row(field) }}
+    {%- endif %}
+  {% endfor -%}
+{% endmacro %}
+
 {# Render a boolean field #}
 {% macro render_bool(field) %}
   <div class="boolean">

mediagoblin/tests/test_edit.py

@@ -14,11 +14,11 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-import urlparse
+import urlparse, os, pytest
 
 from mediagoblin import mg_globals
-from mediagoblin.db.models import User
-from mediagoblin.tests.tools import fixture_add_user
+from mediagoblin.db.models import User, MediaEntry
+from mediagoblin.tests.tools import fixture_add_user, fixture_media_entry
 from mediagoblin import auth
 from mediagoblin.tools import template, mail
 
@@ -174,3 +174,81 @@ class TestUserEdit(object):
         email = User.query.filter_by(username='chris').first().email
         assert email == 'new@example.com'
 # test changing the url inproperly
+
+class TestMetaDataEdit:
+    @pytest.fixture(autouse=True)
+    def setup(self, test_app):
+        # set up new user
+        self.user_password = u'toast'
+        self.user = fixture_add_user(password = self.user_password,
+                               privileges=[u'active',u'admin'])
+        self.test_app = test_app
+
+    def login(self, test_app):
+        test_app.post(
+            '/auth/login/', {
+                'username': self.user.username,
+                'password': self.user_password})
+
+    def do_post(self, data, *context_keys, **kwargs):
+        url = kwargs.pop('url', '/submit/')
+        do_follow = kwargs.pop('do_follow', False)
+        template.clear_test_template_context()
+        response = self.test_app.post(url, data, **kwargs)
+        if do_follow:
+            response.follow()
+        context_data = template.TEMPLATE_TEST_CONTEXT
+        for key in context_keys:
+            context_data = context_data[key]
+        return response, context_data
+
+    def test_edit_metadata(self, test_app):
+        media_entry = fixture_media_entry(uploader=self.user.id,
+            state=u'processed')
+        media_slug = "/u/{username}/m/{media_id}/metadata/".format(
+                username = str(self.user.username),
+                media_id = str(media_entry.id))
+
+        self.login(test_app)
+        response = test_app.get(media_slug)
+        assert response.status == '200 OK'
+        assert media_entry.media_metadata == {}
+        # First test adding in  metadata
+        ################################
+        response, context = self.do_post({
+            "media_metadata-0-identifier":"dc:title",
+            "media_metadata-0-value":"Some title",
+            "media_metadata-1-identifier":"dc:creator",
+            "media_metadata-1-value":"Me"},url=media_slug)
+
+        media_entry = MediaEntry.query.first()
+        new_metadata = media_entry.media_metadata
+        assert new_metadata != {}
+        assert new_metadata.get("dc:title") == "Some title"
+        assert new_metadata.get("dc:creator") == "Me"
+        # Now test removing the metadata
+        ################################
+        response, context = self.do_post({
+            "media_metadata-0-identifier":"dc:title",
+            "media_metadata-0-value":"Some title"},url=media_slug)
+
+        media_entry = MediaEntry.query.first()
+        new_metadata = media_entry.media_metadata
+        assert new_metadata.get("dc:title") == "Some title"
+        assert new_metadata.get("dc:creator") is None
+        # Now test adding bad metadata
+        ###############################
+        response, context = self.do_post({
+            "media_metadata-0-identifier":"dc:title",
+            "media_metadata-0-value":"Some title",
+            "media_metadata-1-identifier":"dc:creator",
+            "media_metadata-1-value":"Me",
+            "media_metadata-2-identifier":"dc:created",
+            "media_metadata-2-value":"On the worst day"},url=media_slug)
+
+        media_entry = MediaEntry.query.first()
+        old_metadata = new_metadata
+        new_metadata = media_entry.media_metadata
+        assert new_metadata == old_metadata
+        assert ("u&#39;On the worst day&#39; is not a &#39;date-time&#39;" in
+            response.body)

mediagoblin/tests/test_metadata.py

@@ -0,0 +1,78 @@
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import pytest
+from mediagoblin.tools.metadata import compact_and_validate
+from jsonschema import ValidationError
+
+class TestMetadataFunctionality:
+
+    @pytest.fixture(autouse=True)
+    def _setup(self, test_app):
+        self.test_app = test_app
+
+    def testCompactAndValidate(self):
+        # First, test out a well formatted piece of metadata
+        ######################################################
+        test_metadata = {
+            'dc:title':'My Pet Bunny',
+            'dc:description':'A picture displaying how cute my pet bunny is.',
+            'location':'/home/goblin/Pictures/bunny.png',
+            'license':'http://www.gnu.org/licenses/gpl.txt'
+        }
+        jsonld_metadata =compact_and_validate(test_metadata)
+        assert jsonld_metadata
+        assert jsonld_metadata.get('dc:title') == 'My Pet Bunny'
+        # Free floating nodes should be removed
+        assert jsonld_metadata.get('location') is None
+        assert jsonld_metadata.get('@context') == \
+            u"http://www.w3.org/2013/json-ld-context/rdfa11"
+
+        # Next, make sure that various badly formatted metadata
+        # will be rejected.
+        #######################################################
+        #,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.
+        # Metadata with a non-URI license should fail :
+        #`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'
+        metadata_fail_1 = {
+            'dc:title':'My Pet Bunny',
+            'dc:description':'A picture displaying how cute my pet bunny is.',
+            'location':'/home/goblin/Pictures/bunny.png',
+            'license':'All Rights Reserved.'
+        }
+        jsonld_fail_1 = None
+        try:
+            jsonld_fail_1 = compact_and_validate(metadata_fail_1)
+        except ValidationError, e:
+            assert e.message == "'All Rights Reserved.' is not a 'uri'"
+        assert jsonld_fail_1 == None
+        #,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,.,
+        # Metadata with an ivalid date-time dc:created should fail :
+        #`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`'`''
+        metadata_fail_2 = {
+            'dc:title':'My Pet Bunny',
+            'dc:description':'A picture displaying how cute my pet bunny is.',
+            'location':'/home/goblin/Pictures/bunny.png',
+            'license':'http://www.gnu.org/licenses/gpl.txt',
+            'dc:created':'The other day'
+        }
+        jsonld_fail_2 = None
+        try:
+            jsonld_fail_2 = compact_and_validate(metadata_fail_2)
+        except ValidationError, e:
+            assert e.message == "'The other day' is not a 'date-time'"
+        assert jsonld_fail_2 == None
+

mediagoblin/tools/metadata.py

@@ -0,0 +1,222 @@
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+
+import os
+import copy
+import json
+import re
+from pkg_resources import resource_filename
+
+import dateutil.parser
+from pyld import jsonld
+from jsonschema import validate, FormatChecker, draft4_format_checker
+from jsonschema.compat import str_types
+
+from mediagoblin.tools.pluginapi import hook_handle
+
+
+
+########################################################
+## Set up the MediaGoblin format checker for json-schema
+########################################################
+
+URL_REGEX = re.compile(
+    r'^[a-z]+://([^/:]+|([0-9]{1,3}\.){3}[0-9]{1,3})(:[0-9]+)?(\/.*)?$',
+    re.IGNORECASE)
+
+def is_uri(instance):
+    """
+    jsonschema uri validator
+    """
+    if not isinstance(instance, str_types):
+        return True
+
+    return URL_REGEX.match(instance)
+
+def is_datetime(instance):
+    """
+    Is a date or datetime readable string.
+    """
+    if not isinstance(instance, str_types):
+        return True
+
+    return dateutil.parser.parse(instance)
+
+
+class DefaultChecker(FormatChecker):
+    """
+    Default MediaGoblin format checker... extended to include a few extra things
+    """
+    checkers = copy.deepcopy(draft4_format_checker.checkers)
+
+
+DefaultChecker.checkers[u"uri"] = (is_uri, ())
+DefaultChecker.checkers[u"date-time"] = (is_datetime, (ValueError, TypeError))
+DEFAULT_CHECKER = DefaultChecker()
+
+# Crappy default schema, checks for things we deem important
+
+DEFAULT_SCHEMA = {
+    "$schema": "http://json-schema.org/schema#",
+
+    "type": "object",
+    "properties": {
+        "license": {
+            "format": "uri",
+            "type": "string",
+        },
+        "dcterms:created": {
+            "format": "date-time",
+            "type": "string",
+        },
+        "dc:created": {
+            "format": "date-time",
+            "type": "string",
+        }
+    },
+}
+
+
+def load_resource(package, resource_path):
+    """
+    Load a resource, return it as a string.
+
+    Args:
+    - package: package or module name.  Eg "mediagoblin.media_types.audio"
+    - resource_path: path to get to this resource, a list of
+      directories and finally a filename.  Will be joined with
+      os.path.sep.
+    """
+    filename = resource_filename(package, os.path.sep.join(resource_path))
+    return file(filename).read()
+
+def load_resource_json(package, resource_path):
+    """
+    Load a resource json file, return a dictionary.
+
+    Args:
+    - package: package or module name.  Eg "mediagoblin.media_types.audio"
+    - resource_path: path to get to this resource, a list of
+      directories and finally a filename.  Will be joined with
+      os.path.sep.
+    """
+    return json.loads(load_resource(package, resource_path))
+
+
+##################################
+## Load the MediaGoblin core files
+##################################
+
+
+BUILTIN_CONTEXTS = {
+    "http://www.w3.org/2013/json-ld-context/rdfa11": load_resource(
+        "mediagoblin", ["static", "metadata", "rdfa11.jsonld"])}
+
+
+_CONTEXT_CACHE = {}
+
+def load_context(url):
+    """
+    A self-aware document loader.  For those contexts MediaGoblin
+    stores internally, load them from disk.
+    """
+    if url in _CONTEXT_CACHE:
+        return _CONTEXT_CACHE[url]
+
+    # See if it's one of our basic ones
+    document = BUILTIN_CONTEXTS.get(url, None)
+
+    # No?  See if we have an internal schema for this
+    if document is None:
+        document = hook_handle(("context_url_data", url))
+
+    # Okay, if we've gotten a document by now... let's package it up
+    if document is not None:
+        document = {'contextUrl': None,
+                    'documentUrl': url,
+                    'document': document}
+
+    # Otherwise, use jsonld.load_document
+    else:
+        document = jsonld.load_document(url)
+
+    # cache
+    _CONTEXT_CACHE[url] = document
+    return document
+
+
+DEFAULT_CONTEXT = "http://www.w3.org/2013/json-ld-context/rdfa11"
+
+def compact_json(metadata, context=DEFAULT_CONTEXT):
+    """
+    Compact json with supplied context.
+
+    Note: Free floating" nodes are removed (eg a key just named
+    "bazzzzzz" which isn't specified in the context... something like
+    bazzzzzz:blerp will stay though.  This is jsonld.compact behavior.
+    """
+    compacted = jsonld.compact(
+        metadata, context,
+        options={
+            "documentLoader": load_context,
+            # This allows for things like "license" and etc to be preserved
+            "expandContext": context,
+            "keepFreeFloatingNodes": False})
+
+    return compacted
+
+
+def compact_and_validate(metadata, context=DEFAULT_CONTEXT,
+                         schema=DEFAULT_SCHEMA):
+    """
+    compact json with supplied context, check against schema for errors
+
+    raises an exception (jsonschema.exceptions.ValidationError) if
+    there's an error.
+
+    Note: Free floating" nodes are removed (eg a key just named
+    "bazzzzzz" which isn't specified in the context... something like
+    bazzzzzz:blerp will stay though.  This is jsonld.compact behavior.
+
+    You may wish to do this validation yourself... this is just for convenience.
+    """
+    compacted = compact_json(metadata, context)
+    validate(metadata, schema, format_checker=DEFAULT_CHECKER)
+
+    return compacted
+
+
+def expand_json(metadata, context=DEFAULT_CONTEXT):
+    """
+    Expand json, but be sure to use our documentLoader.
+
+    By default this expands with DEFAULT_CONTEXT, but if you do not need this,
+    you can safely set this to None.
+
+    # @@: Is the above a good idea?  Maybe it should be set to None by
+    #   default.
+    """
+    options = {
+        "documentLoader": load_context}
+    if context is not None:
+        options["expandContext"] = context
+    return jsonld.expand(metadata, options=options)
+
+
+def rdfa_to_readable(rdfa_predicate):
+    readable = rdfa_predicate.split(u":")[1].capitalize()
+    return readable

mediagoblin/user_pages/routing.py

@@ -101,3 +101,7 @@ add_route('mediagoblin.edit.edit_media',
 add_route('mediagoblin.edit.attachments',
           '/u/<string:user>/m/<int:media_id>/attachments/',
           'mediagoblin.edit.views:edit_attachments')
+
+add_route('mediagoblin.edit.metadata',
+          '/u/<string:user>/m/<int:media_id>/metadata/',
+          'mediagoblin.edit.views:edit_metadata')