Merge branch 'remotes/gullydwarf-cfdv/f360_tagging' (early part) into mergetags

Conflicts:
	mediagoblin/config_spec.ini
	mediagoblin/edit/views.py
	mediagoblin/util.py

mediagoblin/config_spec.ini

@@ -24,6 +24,11 @@ email_sender_address = string(default="notice@mediagoblin.example.org")
 # Set to false to disable registrations
 allow_registration = boolean(default=True)
 
+# tag parsing
+tags_delimiter = string(default=",")
+tags_case_sensitive = boolean(default=False)
+tags_max_length = integer(default=50)
+
 # By default not set, but you might want something like:
 # "%(here)s/user_dev/templates/"
 local_templates = string()

mediagoblin/db/indexes.py

@@ -90,6 +90,21 @@ MEDIAENTRY_INDEXES = {
         # Indexing on uploaders and when media entries are created.
         # Used for showing a user gallery, etc.
         'index': [('uploader', ASCENDING),
+                  ('created', DESCENDING)]},
+
+    'state_uploader_tags_created': {
+        # Indexing on processed?, media uploader, associated tags, and timestamp
+        # Used for showing media items matching a tag search, most recent first.
+        'index': [('state', ASCENDING),
+                  ('uploader', ASCENDING),
+                  ('tags.slug', DESCENDING),
+                  ('created', DESCENDING)]},
+
+    'state_tags_created': {
+        # Indexing on processed?, media tags, and timestamp (across all users)
+        # This is used for a front page tag search.
+        'index': [('state', ASCENDING),
+                  ('tags.slug', DESCENDING),
                   ('created', DESCENDING)]}}
 
 

mediagoblin/db/models.py

@@ -184,7 +184,7 @@ class MediaEntry(Document):
         'media_type': unicode,
         'media_data': dict, # extra data relevant to this media_type
         'plugin_data': dict, # plugins can dump stuff here.
-        'tags': [unicode],
+        'tags': [dict],
         'state': unicode,
 
         # For now let's assume there can only be one main file queued

mediagoblin/edit/forms.py

@@ -16,6 +16,7 @@
 
 
 import wtforms
+from mediagoblin.util import tag_length_validator, TOO_LONG_TAG_WARNING
 
 
 class EditForm(wtforms.Form):
@@ -26,6 +27,9 @@ class EditForm(wtforms.Form):
         'Slug',
         [wtforms.validators.Required(message="The slug can't be empty")])
     description = wtforms.TextAreaField('Description of this work')
+    tags = wtforms.TextField(
+        'Tags',
+        [tag_length_validator])
 
 class EditProfileForm(wtforms.Form):
     bio = wtforms.TextAreaField('Bio',

mediagoblin/edit/views.py

@@ -16,10 +16,13 @@
 
 
 from webob import exc
+from string import split
 
 from mediagoblin import messages
+from mediagoblin import mg_globals
 from mediagoblin.util import (
-    render_to_response, redirect, cleaned_markdown_conversion)
+    render_to_response, redirect, clean_html, convert_to_tag_list_of_dicts,
+    media_tags_as_string, cleaned_markdown_conversion)
 from mediagoblin.edit import forms
 from mediagoblin.edit.lib import may_edit_media
 from mediagoblin.decorators import require_active_login, get_user_media_entry
@@ -34,7 +37,8 @@ def edit_media(request, media):
     form = forms.EditForm(request.POST,
         title = media['title'],
         slug = media['slug'],
-        description = media['description'])
+        description = media['description'],
+        tags = media_tags_as_string(media['tags']))
 
     if request.method == 'POST' and form.validate():
         # Make sure there isn't already a MediaEntry with such a slug
@@ -50,6 +54,8 @@ def edit_media(request, media):
         else:
             media['title'] = request.POST['title']
             media['description'] = request.POST.get('description')
+            media['tags'] = convert_to_tag_list_of_dicts(
+                                   request.POST.get('tags'))
             
             media['description_html'] = cleaned_markdown_conversion(
                 media['description'])

mediagoblin/submit/forms.py

@@ -16,6 +16,7 @@
 
 
 import wtforms
+from mediagoblin.util import tag_length_validator, TOO_LONG_TAG_WARNING
 
 
 class SubmitStartForm(wtforms.Form):
@@ -24,3 +25,6 @@ class SubmitStartForm(wtforms.Form):
         [wtforms.validators.Length(min=0, max=500)])
     description = wtforms.TextAreaField('Description of this work')
     file = wtforms.FileField('File')
+    tags = wtforms.TextField(
+        'Tags',
+        [tag_length_validator])

mediagoblin/submit/views.py

@@ -16,11 +16,13 @@
 
 from os.path import splitext
 from cgi import FieldStorage
+from string import split
 
 from werkzeug.utils import secure_filename
 
 from mediagoblin.util import (
-    render_to_response, redirect, cleaned_markdown_conversion)
+    render_to_response, redirect, cleaned_markdown_conversion, \
+    convert_to_tag_list_of_dicts)
 from mediagoblin.decorators import require_active_login
 from mediagoblin.submit import forms as submit_forms, security
 from mediagoblin.process_media import process_media_initial
@@ -59,6 +61,10 @@ def submit_start(request):
             entry['media_type'] = u'image' # heh
             entry['uploader'] = request.user['_id']
 
+            # Process the user's folksonomy "tags"
+            entry['tags'] = convert_to_tag_list_of_dicts(
+                                request.POST.get('tags'))
+
             # Save, just so we can get the entry id for the sake of using
             # it to generate the file path
             entry.save(validate=False)

mediagoblin/templates/mediagoblin/submit/start.html

@@ -25,6 +25,7 @@
     <div class="grid_8 prefix_1 suffix_1 form_box">
       <h1>Submit yer media</h1>
       {{ wtforms_util.render_field_div(submit_form.file) }}
+      {{ wtforms_util.render_field_div(submit_form.tags) }}
       {{ wtforms_util.render_field_div(submit_form.title) }}
       {{ wtforms_util.render_textarea_div(submit_form.description) }}
       <div class="form_submit_buttons">

mediagoblin/templates/mediagoblin/user_pages/media.html

@@ -116,6 +116,9 @@
           </p>
         {% endif %}
       </p>
+      {% if media.tags %}
+        {% include "mediagoblin/utils/tags.html" %}
+      {% endif %}
     </div>
   {% else %}
     <p>Sorry, no such media found.<p/>

mediagoblin/templates/mediagoblin/utils/tags.html

@@ -0,0 +1,25 @@
+{#
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2011 Free Software Foundation, Inc
+#
+# 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 tags_content -%}
+  <ul class="mediaentry_tags">
+    {% for tag in media.tags %}
+      <li class="tag">{{ tag['name'] }}</li>
+    {% endfor %}
+  </ul>
+{% endblock %}

mediagoblin/util.py

@@ -25,6 +25,7 @@ import re
 import urllib
 from math import ceil, floor
 import copy
+import wtforms
 
 from babel.localedata import exists
 import jinja2
@@ -384,8 +385,66 @@ def clean_html(html):
     return HTML_CLEANER.clean_html(html)
 
 
-MARKDOWN_INSTANCE = markdown.Markdown(safe_mode='escape')
+def convert_to_tag_list_of_dicts(tag_string):
+    """
+    Filter input from incoming string containing user tags,
 
+    Strips trailing, leading, and internal whitespace, and also converts
+    the "tags" text into an array of tags
+    """
+    taglist = []
+    if tag_string:
+
+        # Strip out internal, trailing, and leading whitespace
+        stripped_tag_string = u' '.join(tag_string.strip().split())
+
+        # Split the tag string into a list of tags
+        for tag in stripped_tag_string.split(
+                                       mg_globals.app_config['tags_delimiter']):
+
+            # Ignore empty or duplicate tags
+            if tag.strip() and tag.strip() not in [t['name'] for t in taglist]:
+
+                if mg_globals.app_config['tags_case_sensitive']:
+                    taglist.append({'name': tag.strip(),
+                                    'slug': slugify(tag.strip())})
+                else:
+                    taglist.append({'name': tag.strip().lower(),
+                                    'slug': slugify(tag.strip().lower())})
+    return taglist
+
+
+def media_tags_as_string(media_entry_tags):
+    """
+    Generate a string from a media item's tags, stored as a list of dicts
+
+    This is the opposite of convert_to_tag_list_of_dicts
+    """
+    media_tag_string = ''
+    if media_entry_tags:
+        media_tag_string = mg_globals.app_config['tags_delimiter'].join(
+                                      [tag['name'] for tag in media_entry_tags])
+    return media_tag_string
+
+TOO_LONG_TAG_WARNING = \
+    u'Tags must be shorter than %s characters.  Tags that are too long: %s'
+
+def tag_length_validator(form, field):
+    """
+    Make sure tags do not exceed the maximum tag length.
+    """
+    tags = convert_to_tag_list_of_dicts(field.data)
+    too_long_tags = [
+        tag['name'] for tag in tags
+        if len(tag['name']) > mg_globals.app_config['tags_max_length']]
+
+    if too_long_tags:
+        raise wtforms.ValidationError(
+            TOO_LONG_TAG_WARNING % (mg_globals.app_config['tags_max_length'], \
+                                    ', '.join(too_long_tags)))
+
+
+MARKDOWN_INSTANCE = markdown.Markdown(safe_mode='escape')
 
 def cleaned_markdown_conversion(text):
     """