django-tagging / tagging / models.py

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
"""
Models and managers for generic tagging.
"""
# Python 2.3 compatibility
try:
    set
except NameError:
    from sets import Set as set

from django.contrib.contenttypes import generic
from django.contrib.contenttypes.models import ContentType
from django.db import connection, models
from django.utils.translation import ugettext_lazy as _

from tagging import settings
from tagging.utils import calculate_cloud, get_tag_list, get_tag_parts, get_queryset_and_model, normalize_tag_part, parse_tag_input
from tagging.utils import LOGARITHMIC

qn = connection.ops.quote_name

############
# Managers #
############

class TagManager(models.Manager):
    def update_tags(self, obj, tag_names, default_namespace=None, q=None):
        """
        Update tags associated with an object.

        Accepts a ``default_namespace`` parameter that is assigned to tags
        with no namespace specified.
        """
        ctype = ContentType.objects.get_for_model(obj)
        current_tags = self.filter(items__content_type__pk=ctype.pk,
            items__object_id=obj.pk)
        if q is not None:
            current_tags = current_tags.filter(q)
        current_tags = list(current_tags)
        updated_tag_names = parse_tag_input(tag_names,
            default_namespace=default_namespace)
        if settings.FORCE_LOWERCASE_TAGS:
            updated_tag_names = [t.lower() for t in updated_tag_names]

        # Remove tags which no longer apply
        tags_for_removal = [tag for tag in current_tags \
                            if unicode(tag) not in updated_tag_names]
        if len(tags_for_removal):
            TaggedItem._default_manager.filter(content_type__pk=ctype.pk,
                object_id=obj.pk, tag__in=tags_for_removal).delete()
        # Add new tags
        current_tag_names = [unicode(tag) for tag in current_tags]
        for tag_name in updated_tag_names:
            if tag_name not in current_tag_names:
                tag, created = self.get_or_create(**get_tag_parts(tag_name))
                TaggedItem._default_manager.create(tag=tag, object=obj)

    def add_tag(self, obj, tag_name, default_namespace=None):
        """
        Associates the given object with a tag.

        Accepts a ``default_namespace`` parameter that is assigned to a tag
        with no namespace specified.
        """
        tag_names = parse_tag_input(tag_name,
            default_namespace=default_namespace)
        if not len(tag_names):
            raise AttributeError(_('No tags were given: "%s".') % tag_name)
        if len(tag_names) > 1:
            raise AttributeError(_('Multiple tags were given: "%s".') % tag_name)
        tag_name = tag_names[0]
        if settings.FORCE_LOWERCASE_TAGS:
            tag_name = tag_name.lower()
        tag, created = self.get_or_create(**get_tag_parts(tag_name))
        ctype = ContentType.objects.get_for_model(obj)
        TaggedItem._default_manager.get_or_create(
            tag=tag, content_type=ctype, object_id=obj.pk)

    def get_for_object(self, obj):
        """
        Create a queryset matching all tags associated with the given
        object.
        """
        ctype = ContentType.objects.get_for_model(obj)
        return self.filter(items__content_type__pk=ctype.pk,
                           items__object_id=obj.pk)

    def _get_usage(self, model, counts=False, min_count=None, extra_joins=None, extra_criteria=None, params=None):
        """
        Perform the custom SQL query for ``usage_for_model`` and
        ``usage_for_queryset``.
        """
        if min_count is not None: counts = True

        model_table = qn(model._meta.db_table)
        model_pk = '%s.%s' % (model_table, qn(model._meta.pk.column))
        query = """
        SELECT DISTINCT %(tag)s.id, %(tag)s.namespace, %(tag)s.name, %(tag)s.value%(count_sql)s
        FROM
            %(tag)s
            INNER JOIN %(tagged_item)s
                ON %(tag)s.id = %(tagged_item)s.tag_id
            INNER JOIN %(model)s
                ON %(tagged_item)s.object_id = %(model_pk)s
            %%s
        WHERE %(tagged_item)s.content_type_id = %(content_type_id)s
            %%s
        GROUP BY %(tag)s.id, %(tag)s.namespace, %(tag)s.name, %(tag)s.value
        %%s
        ORDER BY %(tag)s.namespace, %(tag)s.name, %(tag)s.value ASC""" % {
            'tag': qn(self.model._meta.db_table),
            'count_sql': counts and (', COUNT(%s)' % model_pk) or '',
            'tagged_item': qn(TaggedItem._meta.db_table),
            'model': model_table,
            'model_pk': model_pk,
            'content_type_id': ContentType.objects.get_for_model(model).pk,
        }

        min_count_sql = ''
        if min_count is not None:
            min_count_sql = 'HAVING COUNT(%s) >= %%s' % model_pk
            params.append(min_count)

        cursor = connection.cursor()
        cursor.execute(query % (extra_joins, extra_criteria, min_count_sql), params)
        tags = []
        for row in cursor.fetchall():
            t = self.model(*row[:4])
            if counts:
                t.count = row[4]
            tags.append(t)
        return tags

    def usage_for_model(self, model, counts=False, min_count=None, filters=None):
        """
        Obtain a list of tags associated with instances of the given
        Model class.

        If ``counts`` is True, a ``count`` attribute will be added to
        each tag, indicating how many times it has been used against
        the Model class in question.

        If ``min_count`` is given, only tags which have a ``count``
        greater than or equal to ``min_count`` will be returned.
        Passing a value for ``min_count`` implies ``counts=True``.

        To limit the tags (and counts, if specified) returned to those
        used by a subset of the Model's instances, pass a dictionary
        of field lookups to be applied to the given Model as the
        ``filters`` argument.
        """
        if filters is None: filters = {}

        queryset = model._default_manager.filter()
        for f in filters.items():
            queryset.query.add_filter(f)
        usage = self.usage_for_queryset(queryset, counts, min_count)

        return usage

    def usage_for_queryset(self, queryset, counts=False, min_count=None):
        """
        Obtain a list of tags associated with instances of a model
        contained in the given queryset.

        If ``counts`` is True, a ``count`` attribute will be added to
        each tag, indicating how many times it has been used against
        the Model class in question.

        If ``min_count`` is given, only tags which have a ``count``
        greater than or equal to ``min_count`` will be returned.
        Passing a value for ``min_count`` implies ``counts=True``.
        """

        if getattr(queryset.query, 'get_compiler', None):
            # Django 1.2 and up compatible (multiple databases)
            compiler = queryset.query.get_compiler(using='default')
            extra_joins = ' '.join(compiler.get_from_clause()[0][1:])
            where, params = queryset.query.where.as_sql(compiler.quote_name_unless_alias, compiler.connection)
        else:
            # Django 1.1 and down compatible (single database)
            extra_joins = ' '.join(queryset.query.get_from_clause()[0][1:])
            where, params = queryset.query.where.as_sql()

        if where:
            extra_criteria = 'AND %s' % where
        else:
            extra_criteria = ''
        return self._get_usage(queryset.model, counts, min_count, extra_joins, extra_criteria, params)

    def related_for_model(self, tags, model, counts=False, min_count=None,
                          wildcard=None, default_namespace=None):
        """
        Obtain a list of tags related to a given list of tags - that
        is, other tags used by items which have all the given tags.

        If ``counts`` is True, a ``count`` attribute will be added to
        each tag, indicating the number of items which have it in
        addition to the given list of tags.

        If ``min_count`` is given, only tags which have a ``count``
        greater than or equal to ``min_count`` will be returned.
        Passing a value for ``min_count`` implies ``counts=True``.
        """
        if min_count is not None: counts = True
        tags = get_tag_list(tags,
            wildcard=wildcard, default_namespace=default_namespace)
        tag_count = len(tags)
        tagged_item_table = qn(TaggedItem._meta.db_table)
        query = """
        SELECT %(tag)s.id, %(tag)s.namespace, %(tag)s.name, %(tag)s.value%(count_sql)s
        FROM %(tagged_item)s INNER JOIN %(tag)s ON %(tagged_item)s.tag_id = %(tag)s.id
        WHERE %(tagged_item)s.content_type_id = %(content_type_id)s
          AND %(tagged_item)s.object_id IN
          (
              SELECT %(tagged_item)s.object_id
              FROM %(tagged_item)s, %(tag)s
              WHERE %(tagged_item)s.content_type_id = %(content_type_id)s
                AND %(tag)s.id = %(tagged_item)s.tag_id
                AND %(tag)s.id IN (%(tag_id_placeholders)s)
              GROUP BY %(tagged_item)s.object_id
              HAVING COUNT(%(tagged_item)s.object_id) = %(tag_count)s
          )
          AND %(tag)s.id NOT IN (%(tag_id_placeholders)s)
        GROUP BY %(tag)s.id, %(tag)s.namespace, %(tag)s.name, %(tag)s.value
        %(min_count_sql)s
        ORDER BY %(tag)s.name ASC""" % {
            'tag': qn(self.model._meta.db_table),
            'count_sql': counts and ', COUNT(%s.object_id)' % tagged_item_table or '',
            'tagged_item': tagged_item_table,
            'content_type_id': ContentType.objects.get_for_model(model).pk,
            'tag_id_placeholders': ','.join(['%s'] * tag_count),
            'tag_count': tag_count,
            'min_count_sql': min_count is not None and ('HAVING COUNT(%s.object_id) >= %%s' % tagged_item_table) or '',
        }

        params = [tag.pk for tag in tags] * 2
        if min_count is not None:
            params.append(min_count)

        cursor = connection.cursor()
        cursor.execute(query, params)
        related = []
        for row in cursor.fetchall():
            tag = self.model(*row[:4])
            if counts is True:
                tag.count = row[4]
            related.append(tag)
        return related

    def cloud_for_model(self, model, steps=4, distribution=LOGARITHMIC,
                        filters=None, min_count=None):
        """
        Obtain a list of tags associated with instances of the given
        Model, giving each tag a ``count`` attribute indicating how
        many times it has been used and a ``font_size`` attribute for
        use in displaying a tag cloud.

        ``steps`` defines the range of font sizes - ``font_size`` will
        be an integer between 1 and ``steps`` (inclusive).

        ``distribution`` defines the type of font size distribution
        algorithm which will be used - logarithmic or linear. It must
        be either ``tagging.utils.LOGARITHMIC`` or
        ``tagging.utils.LINEAR``.

        To limit the tags displayed in the cloud to those associated
        with a subset of the Model's instances, pass a dictionary of
        field lookups to be applied to the given Model as the
        ``filters`` argument.

        To limit the tags displayed in the cloud to those with a
        ``count`` greater than or equal to ``min_count``, pass a value
        for the ``min_count`` argument.
        """
        tags = list(self.usage_for_model(model, counts=True, filters=filters,
                                         min_count=min_count))
        return calculate_cloud(tags, steps, distribution)

class TaggedItemManager(models.Manager):
    """
    FIXME There's currently no way to get the ``GROUP BY`` and ``HAVING``
          SQL clauses required by many of this manager's methods into
          Django's ORM.

          For now, we manually execute a query to retrieve the PKs of
          objects we're interested in, then use the ORM's ``__in``
          lookup to return a ``QuerySet``.

          Now that the queryset-refactor branch is in the trunk, this can be
          tidied up significantly.
    """
    def get_by_model(self, queryset_or_model, tags,
                     wildcard=None, default_namespace=None):
        """
        Create a ``QuerySet`` containing instances of the specified
        model associated with a given tag or list of tags.

        The ``wildcard`` and the ``default_namespace`` parameters are
        allowed. For more details see the ``get_tag_list`` function.
        """
        tags = get_tag_list(tags,
            wildcard=wildcard, default_namespace=default_namespace)
        tag_count = len(tags)
        if tag_count == 0:
            # No existing tags were given
            queryset, model = get_queryset_and_model(queryset_or_model)
            return model._default_manager.none()
        elif tag_count == 1:
            # Optimisation for single tag - fall through to the simpler
            # query below.
            tag = tags[0]
        else:
            return self.get_intersection_by_model(queryset_or_model, tags)

        queryset, model = get_queryset_and_model(queryset_or_model)
        content_type = ContentType.objects.get_for_model(model)
        opts = self.model._meta
        tagged_item_table = qn(opts.db_table)
        return queryset.extra(
            tables=[opts.db_table],
            where=[
                '%s.content_type_id = %%s' % tagged_item_table,
                '%s.tag_id = %%s' % tagged_item_table,
                '%s.%s = %s.object_id' % (qn(model._meta.db_table),
                                          qn(model._meta.pk.column),
                                          tagged_item_table)
            ],
            params=[content_type.pk, tag.pk],
        )

    def get_intersection_by_model(self, queryset_or_model, tags,
                                  wildcard=None, default_namespace=None):
        """
        Create a ``QuerySet`` containing instances of the specified
        model associated with *all* of the given list of tags.

        The ``wildcard`` and the ``default_namespace`` parameters are
        allowed. For more details see the ``get_tag_list`` function.
        """
        tags = get_tag_list(tags,
            wildcard=wildcard, default_namespace=default_namespace)
        tag_count = len(tags)
        queryset, model = get_queryset_and_model(queryset_or_model)

        if not tag_count:
            return model._default_manager.none()

        model_table = qn(model._meta.db_table)
        # This query selects the ids of all objects which have all the
        # given tags.
        query = """
        SELECT %(model_pk)s
        FROM %(model)s, %(tagged_item)s
        WHERE %(tagged_item)s.content_type_id = %(content_type_id)s
          AND %(tagged_item)s.tag_id IN (%(tag_id_placeholders)s)
          AND %(model_pk)s = %(tagged_item)s.object_id
        GROUP BY %(model_pk)s
        HAVING COUNT(%(model_pk)s) = %(tag_count)s""" % {
            'model_pk': '%s.%s' % (model_table, qn(model._meta.pk.column)),
            'model': model_table,
            'tagged_item': qn(self.model._meta.db_table),
            'content_type_id': ContentType.objects.get_for_model(model).pk,
            'tag_id_placeholders': ','.join(['%s'] * tag_count),
            'tag_count': tag_count,
        }

        cursor = connection.cursor()
        cursor.execute(query, [tag.pk for tag in tags])
        object_ids = [row[0] for row in cursor.fetchall()]
        if len(object_ids) > 0:
            return queryset.filter(pk__in=object_ids)
        else:
            return model._default_manager.none()

    def get_union_by_model(self, queryset_or_model, tags,
                           wildcard=None, default_namespace=None):
        """
        Create a ``QuerySet`` containing instances of the specified
        model associated with *any* of the given list of tags.

        The ``wildcard`` and the ``default_namespace`` parameters are
        allowed. For more details see the ``get_tag_list`` function.
        """
        tags = get_tag_list(tags,
            wildcard=wildcard, default_namespace=default_namespace)
        tag_count = len(tags)
        queryset, model = get_queryset_and_model(queryset_or_model)

        if not tag_count:
            return model._default_manager.none()

        model_table = qn(model._meta.db_table)
        # This query selects the ids of all objects which have any of
        # the given tags.
        query = """
        SELECT %(model_pk)s
        FROM %(model)s, %(tagged_item)s
        WHERE %(tagged_item)s.content_type_id = %(content_type_id)s
          AND %(tagged_item)s.tag_id IN (%(tag_id_placeholders)s)
          AND %(model_pk)s = %(tagged_item)s.object_id
        GROUP BY %(model_pk)s""" % {
            'model_pk': '%s.%s' % (model_table, qn(model._meta.pk.column)),
            'model': model_table,
            'tagged_item': qn(self.model._meta.db_table),
            'content_type_id': ContentType.objects.get_for_model(model).pk,
            'tag_id_placeholders': ','.join(['%s'] * tag_count),
        }

        cursor = connection.cursor()
        cursor.execute(query, [tag.pk for tag in tags])
        object_ids = [row[0] for row in cursor.fetchall()]
        if len(object_ids) > 0:
            return queryset.filter(pk__in=object_ids)
        else:
            return model._default_manager.none()

    def get_related(self, obj, queryset_or_model, num=None):
        """
        Retrieve a list of instances of the specified model which share
        tags with the model instance ``obj``, ordered by the number of
        shared tags in descending order.

        If ``num`` is given, a maximum of ``num`` instances will be
        returned.
        """
        queryset, model = get_queryset_and_model(queryset_or_model)
        model_table = qn(model._meta.db_table)
        content_type = ContentType.objects.get_for_model(obj)
        related_content_type = ContentType.objects.get_for_model(model)
        query = """
        SELECT %(model_pk)s, COUNT(related_tagged_item.object_id) AS %(count)s
        FROM %(model)s, %(tagged_item)s, %(tag)s, %(tagged_item)s related_tagged_item
        WHERE %(tagged_item)s.object_id = %%s
          AND %(tagged_item)s.content_type_id = %(content_type_id)s
          AND %(tag)s.id = %(tagged_item)s.tag_id
          AND related_tagged_item.content_type_id = %(related_content_type_id)s
          AND related_tagged_item.tag_id = %(tagged_item)s.tag_id
          AND %(model_pk)s = related_tagged_item.object_id"""
        if content_type.pk == related_content_type.pk:
            # Exclude the given instance itself if determining related
            # instances for the same model.
            query += """
          AND related_tagged_item.object_id != %(tagged_item)s.object_id"""
        query += """
        GROUP BY %(model_pk)s
        ORDER BY %(count)s DESC
        %(limit_offset)s"""
        query = query % {
            'model_pk': '%s.%s' % (model_table, qn(model._meta.pk.column)),
            'count': qn('count'),
            'model': model_table,
            'tagged_item': qn(self.model._meta.db_table),
            'tag': qn(self.model._meta.get_field('tag').rel.to._meta.db_table),
            'content_type_id': content_type.pk,
            'related_content_type_id': related_content_type.pk,
            # Hardcoding this for now just to get tests working again - this
            # should now be handled by the query object.
            'limit_offset': num is not None and 'LIMIT %s' or '',
        }

        cursor = connection.cursor()
        params = [obj.pk]
        if num is not None:
            params.append(num)
        cursor.execute(query, params)
        object_ids = [row[0] for row in cursor.fetchall()]
        if len(object_ids) > 0:
            # Use in_bulk here instead of an id__in lookup, because id__in would
            # clobber the ordering.
            object_dict = queryset.in_bulk(object_ids)
            return [object_dict[object_id] for object_id in object_ids \
                    if object_id in object_dict]
        else:
            return []

##########
# Models #
##########

class Tag(models.Model):
    """
    A tag.
    """
    namespace = models.CharField(_('namespace'), max_length=50, null=True, blank=True, db_index=True)
    name      = models.CharField(_('name'), max_length=50, db_index=True)
    value     = models.CharField(_('value'), max_length=50, null=True, blank=True, db_index=True)

    objects = TagManager()

    class Meta:
        unique_together = (('namespace', 'name', 'value'),)
        ordering = ('namespace', 'name', 'value')
        verbose_name = _('tag')
        verbose_name_plural = _('tags')

    def __unicode__(self):
        name = normalize_tag_part(self.name)
        if self.namespace:
            name = '%s:%s' % (normalize_tag_part(self.namespace), name)
        if self.value:
            name = '%s=%s' % (name, normalize_tag_part(self.value))
        return name

class TaggedItem(models.Model):
    """
    Holds the relationship between a tag and the item being tagged.
    """
    tag          = models.ForeignKey(Tag, verbose_name=_('tag'), related_name='items')
    content_type = models.ForeignKey(ContentType, verbose_name=_('content type'))
    object_id    = models.PositiveIntegerField(_('object id'), db_index=True)
    object       = generic.GenericForeignKey('content_type', 'object_id')

    objects = TaggedItemManager()

    class Meta:
        # Enforce unique tag association per object
        unique_together = (('tag', 'content_type', 'object_id'),)
        verbose_name = _('tagged item')
        verbose_name_plural = _('tagged items')

    def __unicode__(self):
        return u'%s [%s]' % (self.object, self.tag)
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.