Elastic search v Djangu česky

elasticsearch_started

you@computer:~$ elasticsearch --config=/usr/local/opt/elasticsearch/config/elasticsearch.yml

[2014-11-10 10:41:49,409][INFO ][node                     ] [Toad-In-Waiting] version[1.3.4], pid[99851], build[a70f3cc/2014-09-30T09:07:17Z]
[2014-11-10 10:41:49,411][INFO ][node                     ] [Toad-In-Waiting] initializing ...
[2014-11-10 10:41:58,357][INFO ][node                     ] [Toad-In-Waiting] initialized
[2014-11-10 10:41:58,358][INFO ][node                     ] [Toad-In-Waiting] starting ...
[2014-11-10 10:41:58,491][INFO ][transport                ] [Toad-In-Waiting] bound_address {inet[/127.0.0.1:9300]}, publish_address {inet[/127.0.0.1:9300]}
[2014-11-10 10:41:58,511][INFO ][discovery                ] [Toad-In-Waiting] xaralis/oIhw_OW3Trim_30_TOz_Mw
[2014-11-10 10:42:01,527][INFO ][cluster.service          ] [Toad-In-Waiting] new_master [Toad-In-Waiting][oIhw_OW3Trim_30_TOz_Mw][matrix][inet[/127.0.0.1:9300]], reason: zen-disco-join (elected_as_master)
[2014-11-10 10:42:01,558][INFO ][http                     ] [Toad-In-Waiting] bound_address {inet[/127.0.0.1:9200]}, publish_address {inet[/127.0.0.1:9200]}
[2014-11-10 10:42:01,559][INFO ][node                     ] [Toad-In-Waiting] started

elasticstack_settings.py

ELASTICSEARCH_INDEX_SETTINGS = {
    'settings': {
        'analysis': {
            'analyzer' : {
                'cs_hunspell': {
                    'type': 'custom',
                    'tokenizer': 'standard',
                    'filter': ['stopwords_CZ', 'lowercase', 'hunspell_CZ', 'asciifolding', 'stopwords_CZ', 'remove_duplicities']
                }
            },
            'filter': {
                'stopwords_CZ': {
                    'type': 'stop',
                    'stopwords': ["právě", "že", "_czech_"],
                    'ignore_case': True
                },
                'hunspell_CZ': {
                    'type': 'hunspell',
                    'locale': 'cs_CZ',
                    'dedup': True,
                    'recursion_level': 0
                },
                'remove_duplicities': {
                    'type': 'unique',
                    'only_on_same_position': True
                }
            }
        }
    }
}

ELASTICSEARCH_DEFAULT_ANALYZER = 'cs_hunspell'

haystack_connections.py

HAYSTACK_CONNECTIONS = {
    'default': {
        'ENGINE': 'elasticstack.backends.ConfigurableElasticSearchEngine',
        'URL': '127.0.0.1:9200',
        'INDEX_NAME': 'my_custom_index',
    },
}

installed_apps.py

INSTALLED_APPS = [
    ...
    'haystack',
    'elasticstack',
    ...
]

page_text.txt

{{ object.title }}
{{ object.author.get_full_name }}
{{ object.perex|striptags }}
{{ object.content|striptags }}

rebuild_index

you@computer:/projects/myproject$ python manage.py rebuild_index --noinput

Removing all documents from your index because you said so.
All documents removed.
Indexing 164 Stránky

search.html

{% extends 'base.html' %}

{% block content %}
    <h2>Vyhledávání</h2>

    <form method="get" action=".">
        <table>
            {{ form.as_table }}
            <tr>
                <td>&nbsp;</td>
                <td>
                    <input type="submit" value="Hledat">
                </td>
            </tr>
        </table>

        {% if query %}
            <h3>Výsledky</h3>

            {% for result in page.object_list %}
                <p>
                    <a href="{{ result.object.get_absolute_url }}">{{ result.object.title }}</a>
                </p>
            {% empty %}
                <p>Nic nebylo nalezeno.</p>
            {% endfor %}

            {% if page.has_previous or page.has_next %}
                <div>
                    {% if page.has_previous %}<a href="?q={{ query }}&amp;page={{ page.previous_page_number }}">{% endif %}&laquo; Předchozí{% if page.has_previous %}</a>{% endif %}
                    |
                    {% if page.has_next %}<a href="?q={{ query }}&amp;page={{ page.next_page_number }}">{% endif %}Následující &raquo;{% if page.has_next %}</a>{% endif %}
                </div>
            {% endif %}
        {% endif %}
    </form>
{% endblock %}

search_indexes.py

from haystack import indexes
from myproject.app import models

class PageIndex(indexes.SearchIndex, indexes.Indexable):
    text = indexes.CharField(document=True, use_template=True)
    title = indexes.CharField(model_attr='title', boost=5)

    def get_model(self):
        return models.Page

    def index_queryset(self, using=None):
        return self.get_model().objects.published()

urls.py

...
(r'^vyhledavani/', include('haystack.urls')),
...