Commits

offline  committed 79dd24e

added non modified files

  • Participants
  • Parent commits a504ab6

Comments (0)

Files changed (5)

File newtags/admin.py

+from django.contrib import admin
+from tagging.models import Tag, TaggedItem
+
+admin.site.register(TaggedItem)
+admin.site.register(Tag)

File newtags/forms.py

+"""
+Tagging components for Django's form library.
+"""
+from django import forms
+from django.utils.translation import ugettext as _
+
+from tagging import settings
+from tagging.models import Tag
+from tagging.utils import parse_tag_input
+
+class AdminTagForm(forms.ModelForm):
+    class Meta:
+        model = Tag
+
+    def clean_name(self):
+        value = self.cleaned_data['name']
+        tag_names = parse_tag_input(value)
+        if len(tag_names) > 1:
+            raise ValidationError(_('Multiple tags were given.'))
+        elif len(tag_names[0]) > settings.MAX_TAG_LENGTH:
+            raise forms.ValidationError(
+                _('A tag may be no more than %s characters long.') %
+                    settings.MAX_TAG_LENGTH)
+        return value
+
+class TagField(forms.CharField):
+    """
+    A ``CharField`` which validates that its input is a valid list of
+    tag names.
+    """
+    def clean(self, value):
+        value = super(TagField, self).clean(value)
+        if value == u'':
+            return value
+        for tag_name in parse_tag_input(value):
+            if len(tag_name) > settings.MAX_TAG_LENGTH:
+                raise forms.ValidationError(
+                    _('Each tag may be no more than %s characters long.') %
+                        settings.MAX_TAG_LENGTH)
+        return value

File newtags/models.py

+"""
+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.db.models.query import QuerySet
+from django.utils.translation import ugettext_lazy as _
+from django.db.models import Avg, Max, Min, Count
+
+from tagging import settings
+from tagging.utils import calculate_cloud, get_tag_list, get_queryset_and_model, parse_tag_input
+from tagging.utils import LOGARITHMIC
+import pdb
+qn = connection.ops.quote_name
+
+############
+# Managers #
+############
+
+class TagManager(models.Manager):
+    def update_tags(self, obj, tag_names):
+        """
+        Update tags associated with an object.
+        """
+        ctype = ContentType.objects.get_for_model(obj)
+        current_tags = list(self.filter(items__content_type__pk=ctype.pk,
+                                        items__object_id=obj.pk))
+        updated_tag_names = parse_tag_input(tag_names)
+        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 tag.name 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 = [tag.name 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(name=tag_name)
+                TaggedItem._default_manager.create(tag=tag, object=obj)
+
+    def add_tag(self, obj, tag_name):
+        """
+        Associates the given object with a tag.
+        """
+        tag_names = parse_tag_input(tag_name)
+        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(name=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, queryset, counts=False, order='-tag__name', min_count=None):
+        content_type = ContentType.objects.get_for_model(queryset.model)
+        queryset = TaggedItem.objects.filter(content_type=content_type).values('tag__name')
+        if counts:
+            queryset = queryset.annotate(count=Count('tag')).order_by('-tag__name')
+        return queryset
+
+
+
+    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)
+        return self.usage_for_queryset(queryset, counts, min_count)
+
+
+    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``.
+        """
+        return self._get_usage(queryset, counts, min_count)
+
+
+    def related_for_model(self, tags, model, counts=False, min_count=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``.
+        """
+
+        tags_id = set([tag.id for tag in tags])
+        tagged_items_id = set([tagged_item.object_id for tagged_item in TaggedItem.objects.filter(tag__id__in=tags_id)])
+        items_id = [item.id for item in model._default_manager.filter(pk__in=tagged_items_id)]
+        newtags_id = set([tagged_item.tag.id for tagged_item in TaggedItem.objects.filter(object_id__in=items_id)])
+        return Tag.objects.filter(pk__in=newtags_id)
+
+
+
+    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):
+        """
+        Create a ``QuerySet`` containing instances of the specified
+        model associated with a given tag or list of tags.
+        """
+        tags = get_tag_list(tags)
+        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):
+        """
+        Create a ``QuerySet`` containing instances of the specified
+        model associated with *all* of the given list of tags.
+        """
+        tags = get_tag_list(tags)
+        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):
+        """
+        Create a ``QuerySet`` containing instances of the specified
+        model associated with *any* of the given list of tags.
+        """
+        tags = get_tag_list(tags)
+        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.
+    """
+    name = models.CharField(_('name'), max_length=50, unique=True, db_index=True)
+
+    objects = TagManager()
+
+    class Meta:
+        ordering = ('name',)
+        verbose_name = _('tag')
+        verbose_name_plural = _('tags')
+
+    def __unicode__(self):
+        return self.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)

File newtags/settings.py

+"""
+Convenience module for access of custom tagging application settings,
+which enforces default settings when the main settings module does not
+contain the appropriate settings.
+"""
+from django.conf import settings
+
+# The maximum length of a tag's name.
+MAX_TAG_LENGTH = getattr(settings, 'MAX_TAG_LENGTH', 50)
+
+# Whether to force all tags to lowercase before they are saved to the
+# database.
+FORCE_LOWERCASE_TAGS = getattr(settings, 'FORCE_LOWERCASE_TAGS', False)

File newtags/utils.py

+"""
+Tagging utilities - from user tag input parsing to tag cloud
+calculation.
+"""
+import math
+import types
+
+from django.db.models.query import QuerySet
+from django.utils.encoding import force_unicode
+from django.utils.translation import ugettext as _
+
+# Python 2.3 compatibility
+try:
+    set
+except NameError:
+    from sets import Set as set
+
+def parse_tag_input(input):
+    """
+    Parses tag input, with multiple word input being activated and
+    delineated by commas and double quotes. Quotes take precedence, so
+    they may contain commas.
+
+    Returns a sorted list of unique tag names.
+    """
+    if not input:
+        return []
+
+    input = force_unicode(input)
+
+    # Special case - if there are no commas or double quotes in the
+    # input, we don't *do* a recall... I mean, we know we only need to
+    # split on spaces.
+    if u',' not in input and u'"' not in input:
+        words = list(set(split_strip(input, u' ')))
+        words.sort()
+        return words
+
+    words = []
+    buffer = []
+    # Defer splitting of non-quoted sections until we know if there are
+    # any unquoted commas.
+    to_be_split = []
+    saw_loose_comma = False
+    open_quote = False
+    i = iter(input)
+    try:
+        while 1:
+            c = i.next()
+            if c == u'"':
+                if buffer:
+                    to_be_split.append(u''.join(buffer))
+                    buffer = []
+                # Find the matching quote
+                open_quote = True
+                c = i.next()
+                while c != u'"':
+                    buffer.append(c)
+                    c = i.next()
+                if buffer:
+                    word = u''.join(buffer).strip()
+                    if word:
+                        words.append(word)
+                    buffer = []
+                open_quote = False
+            else:
+                if not saw_loose_comma and c == u',':
+                    saw_loose_comma = True
+                buffer.append(c)
+    except StopIteration:
+        # If we were parsing an open quote which was never closed treat
+        # the buffer as unquoted.
+        if buffer:
+            if open_quote and u',' in buffer:
+                saw_loose_comma = True
+            to_be_split.append(u''.join(buffer))
+    if to_be_split:
+        if saw_loose_comma:
+            delimiter = u','
+        else:
+            delimiter = u' '
+        for chunk in to_be_split:
+            words.extend(split_strip(chunk, delimiter))
+    words = list(set(words))
+    words.sort()
+    return words
+
+def split_strip(input, delimiter=u','):
+    """
+    Splits ``input`` on ``delimiter``, stripping each resulting string
+    and returning a list of non-empty strings.
+    """
+    if not input:
+        return []
+
+    words = [w.strip() for w in input.split(delimiter)]
+    return [w for w in words if w]
+
+def edit_string_for_tags(tags):
+    """
+    Given list of ``Tag`` instances, creates a string representation of
+    the list suitable for editing by the user, such that submitting the
+    given string representation back without changing it will give the
+    same list of tags.
+
+    Tag names which contain commas will be double quoted.
+
+    If any tag name which isn't being quoted contains whitespace, the
+    resulting string of tag names will be comma-delimited, otherwise
+    it will be space-delimited.
+    """
+    names = []
+    use_commas = False
+    for tag in tags:
+        name = tag['name']
+        if u',' in name:
+            names.append('"%s"' % name)
+            continue
+        elif u' ' in name:
+            if not use_commas:
+                use_commas = True
+        names.append(name)
+    if use_commas:
+        glue = u', '
+    else:
+        glue = u' '
+    return glue.join(names)
+
+def get_queryset_and_model(queryset_or_model):
+    """
+    Given a ``QuerySet`` or a ``Model``, returns a two-tuple of
+    (queryset, model).
+
+    If a ``Model`` is given, the ``QuerySet`` returned will be created
+    using its default manager.
+    """
+    try:
+        return queryset_or_model, queryset_or_model.model
+    except AttributeError:
+        return queryset_or_model._default_manager.all(), queryset_or_model
+
+def get_tag_list(tags):
+    """
+    Utility function for accepting tag input in a flexible manner.
+
+    If a ``Tag`` object is given, it will be returned in a list as
+    its single occupant.
+
+    If given, the tag names in the following will be used to create a
+    ``Tag`` ``QuerySet``:
+
+       * A string, which may contain multiple tag names.
+       * A list or tuple of strings corresponding to tag names.
+       * A list or tuple of integers corresponding to tag ids.
+
+    If given, the following will be returned as-is:
+
+       * A list or tuple of ``Tag`` objects.
+       * A ``Tag`` ``QuerySet``.
+
+    """
+    from tagging.models import Tag
+    if isinstance(tags, Tag):
+        return [tags]
+    elif isinstance(tags, QuerySet) and tags.model is Tag:
+        return tags
+    elif isinstance(tags, types.StringTypes):
+        return Tag.objects.filter(name__in=parse_tag_input(tags))
+    elif isinstance(tags, (types.ListType, types.TupleType)):
+        if len(tags) == 0:
+            return tags
+        contents = set()
+        for item in tags:
+            if isinstance(item, types.StringTypes):
+                contents.add('string')
+            elif isinstance(item, Tag):
+                contents.add('tag')
+            elif isinstance(item, (types.IntType, types.LongType)):
+                contents.add('int')
+        if len(contents) == 1:
+            if 'string' in contents:
+                return Tag.objects.filter(name__in=[force_unicode(tag) \
+                                                    for tag in tags])
+            elif 'tag' in contents:
+                return tags
+            elif 'int' in contents:
+                return Tag.objects.filter(id__in=tags)
+        else:
+            raise ValueError(_('If a list or tuple of tags is provided, they must all be tag names, Tag objects or Tag ids.'))
+    else:
+        raise ValueError(_('The tag input given was invalid.'))
+
+def get_tag(tag):
+    """
+    Utility function for accepting single tag input in a flexible
+    manner.
+
+    If a ``Tag`` object is given it will be returned as-is; if a
+    string or integer are given, they will be used to lookup the
+    appropriate ``Tag``.
+
+    If no matching tag can be found, ``None`` will be returned.
+    """
+    from tagging.models import Tag
+    if isinstance(tag, Tag):
+        return tag
+
+    try:
+        if isinstance(tag, types.StringTypes):
+            return Tag.objects.get(name=tag)
+        elif isinstance(tag, (types.IntType, types.LongType)):
+            return Tag.objects.get(id=tag)
+    except Tag.DoesNotExist:
+        pass
+
+    return None
+
+# Font size distribution algorithms
+LOGARITHMIC, LINEAR = 1, 2
+
+def _calculate_thresholds(min_weight, max_weight, steps):
+    delta = (max_weight - min_weight) / float(steps)
+    return [min_weight + i * delta for i in range(1, steps + 1)]
+
+def _calculate_tag_weight(weight, max_weight, distribution):
+    """
+    Logarithmic tag weight calculation is based on code from the
+    `Tag Cloud`_ plugin for Mephisto, by Sven Fuchs.
+
+    .. _`Tag Cloud`: http://www.artweb-design.de/projects/mephisto-plugin-tag-cloud
+    """
+    if distribution == LINEAR or max_weight == 1:
+        return weight
+    elif distribution == LOGARITHMIC:
+        return math.log(weight) * max_weight / math.log(max_weight)
+    raise ValueError(_('Invalid distribution algorithm specified: %s.') % distribution)
+
+def calculate_cloud(tags, steps=4, distribution=LOGARITHMIC):
+    """
+    Add a ``font_size`` attribute to each tag according to the
+    frequency of its use, as indicated by its ``count``
+    attribute.
+
+    ``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
+    one of ``tagging.utils.LOGARITHMIC`` or ``tagging.utils.LINEAR``.
+    """
+    if len(tags) > 0:
+        counts = [tag['count'] for tag in tags]
+        min_weight = float(min(counts))
+        max_weight = float(max(counts))
+        thresholds = _calculate_thresholds(min_weight, max_weight, steps)
+        for tag in tags:
+            font_set = False
+            tag_weight = _calculate_tag_weight(tag['count'], max_weight, distribution)
+            for i in range(steps):
+                if not font_set and tag_weight <= thresholds[i]:
+                    tag['font_size'] = i + 1
+                    font_set = True
+    return tags