mirror of https://github.com/searxng/searxng
Add recoll engine (#2325)
recoll is a local search engine based on Xapian: http://www.lesbonscomptes.com/recoll/ By itself recoll does not offer web or API access, this can be achieved using recoll-webui: https://framagit.org/medoc92/recollwebui.git This engine uses a custom 'files' result template set `base_url` to the location where recoll-webui can be reached set `dl_prefix` to a location where the file hierarchy as indexed by recoll can be reached set `search_dir` to the part of the indexed file hierarchy to be searched, use an empty string to search the entire search domainpull/1/head
parent
93c2603561
commit
4a36a3044d
@ -0,0 +1,50 @@
|
|||||||
|
.. _engine recoll:
|
||||||
|
|
||||||
|
======
|
||||||
|
Recoll
|
||||||
|
======
|
||||||
|
|
||||||
|
.. sidebar:: info
|
||||||
|
|
||||||
|
- `Recoll <https://www.lesbonscomptes.com/recoll/>`_
|
||||||
|
- `recoll-webui <https://framagit.org/medoc92/recollwebui.git>`_
|
||||||
|
|
||||||
|
Recoll_ is a desktop full-text search tool based on Xapian. By itself Recoll_
|
||||||
|
does not offer web or API access, this can be achieved using recoll-webui_
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Configuration
|
||||||
|
=============
|
||||||
|
|
||||||
|
You must configure the following settings:
|
||||||
|
|
||||||
|
``base_url``:
|
||||||
|
Location where recoll-webui can be reached.
|
||||||
|
|
||||||
|
``mount_prefix``:
|
||||||
|
Location where the file hierarchy is mounted on your *local* filesystem.
|
||||||
|
|
||||||
|
``dl_prefix``:
|
||||||
|
Location where the file hierarchy as indexed by recoll can be reached.
|
||||||
|
|
||||||
|
``search_dir``:
|
||||||
|
Part of the indexed file hierarchy to be search, if empty the full domain is
|
||||||
|
searched.
|
||||||
|
|
||||||
|
|
||||||
|
Example
|
||||||
|
=======
|
||||||
|
|
||||||
|
Scenario:
|
||||||
|
|
||||||
|
#. Recoll indexes a local filesystem mounted in ``/export/documents/reference``,
|
||||||
|
#. the Recoll search inteface can be reached at https://recoll.example.org/ and
|
||||||
|
#. the contents of this filesystem can be reached though https://download.example.org/reference
|
||||||
|
|
||||||
|
.. code:: yaml
|
||||||
|
|
||||||
|
base_url: https://recoll.example.org/
|
||||||
|
mount_prefix: /export/documents
|
||||||
|
dl_prefix: https://download.example.org
|
||||||
|
search_dir: ''
|
@ -0,0 +1,104 @@
|
|||||||
|
"""
|
||||||
|
Recoll (local search engine)
|
||||||
|
|
||||||
|
@using-api yes
|
||||||
|
@results JSON
|
||||||
|
@stable yes
|
||||||
|
@parse url, content, size, abstract, author, mtype, subtype, time, \
|
||||||
|
filename, label, type, embedded
|
||||||
|
"""
|
||||||
|
|
||||||
|
from datetime import date, timedelta
|
||||||
|
from json import loads
|
||||||
|
from urllib.parse import urlencode, quote
|
||||||
|
|
||||||
|
# engine dependent config
|
||||||
|
time_range_support = True
|
||||||
|
|
||||||
|
# parameters from settings.yml
|
||||||
|
base_url = None
|
||||||
|
search_dir = ''
|
||||||
|
mount_prefix = None
|
||||||
|
dl_prefix = None
|
||||||
|
|
||||||
|
# embedded
|
||||||
|
embedded_url = '<{ttype} controls height="166px" ' +\
|
||||||
|
'src="{url}" type="{mtype}"></{ttype}>'
|
||||||
|
|
||||||
|
|
||||||
|
# helper functions
|
||||||
|
def get_time_range(time_range):
|
||||||
|
sw = {
|
||||||
|
'day': 1,
|
||||||
|
'week': 7,
|
||||||
|
'month': 30,
|
||||||
|
'year': 365
|
||||||
|
}
|
||||||
|
|
||||||
|
offset = sw.get(time_range, 0)
|
||||||
|
if not offset:
|
||||||
|
return ''
|
||||||
|
|
||||||
|
return (date.today() - timedelta(days=offset)).isoformat()
|
||||||
|
|
||||||
|
|
||||||
|
# do search-request
|
||||||
|
def request(query, params):
|
||||||
|
search_after = get_time_range(params['time_range'])
|
||||||
|
search_url = base_url + 'json?{query}&highlight=0'
|
||||||
|
params['url'] = search_url.format(query=urlencode({
|
||||||
|
'query': query,
|
||||||
|
'after': search_after,
|
||||||
|
'dir': search_dir}))
|
||||||
|
|
||||||
|
return params
|
||||||
|
|
||||||
|
|
||||||
|
# get response from search-request
|
||||||
|
def response(resp):
|
||||||
|
results = []
|
||||||
|
|
||||||
|
response_json = loads(resp.text)
|
||||||
|
|
||||||
|
if not response_json:
|
||||||
|
return []
|
||||||
|
|
||||||
|
for result in response_json.get('results', []):
|
||||||
|
title = result['label']
|
||||||
|
url = result['url'].replace('file://' + mount_prefix, dl_prefix)
|
||||||
|
content = '{}'.format(result['snippet'])
|
||||||
|
|
||||||
|
# append result
|
||||||
|
item = {'url': url,
|
||||||
|
'title': title,
|
||||||
|
'content': content,
|
||||||
|
'template': 'files.html'}
|
||||||
|
|
||||||
|
if result['size']:
|
||||||
|
item['size'] = int(result['size'])
|
||||||
|
|
||||||
|
for parameter in ['filename', 'abstract', 'author', 'mtype', 'time']:
|
||||||
|
if result[parameter]:
|
||||||
|
item[parameter] = result[parameter]
|
||||||
|
|
||||||
|
# facilitate preview support for known mime types
|
||||||
|
if 'mtype' in result and '/' in result['mtype']:
|
||||||
|
(mtype, subtype) = result['mtype'].split('/')
|
||||||
|
item['mtype'] = mtype
|
||||||
|
item['subtype'] = subtype
|
||||||
|
|
||||||
|
if mtype in ['audio', 'video']:
|
||||||
|
item['embedded'] = embedded_url.format(
|
||||||
|
ttype=mtype,
|
||||||
|
url=quote(url.encode('utf8'), '/:'),
|
||||||
|
mtype=result['mtype'])
|
||||||
|
|
||||||
|
if mtype in ['image'] and subtype in ['bmp', 'gif', 'jpeg', 'png']:
|
||||||
|
item['img_src'] = url
|
||||||
|
|
||||||
|
results.append(item)
|
||||||
|
|
||||||
|
if 'nres' in response_json:
|
||||||
|
results.append({'number_of_results': response_json['nres']})
|
||||||
|
|
||||||
|
return results
|
@ -0,0 +1,55 @@
|
|||||||
|
{% from 'oscar/macros.html' import result_header, result_sub_header, result_footer_nocache, result_footer_nocache_rtl, icon with context %}
|
||||||
|
|
||||||
|
{{ result_header(result, favicons) }}
|
||||||
|
{{ result_sub_header(result) }}
|
||||||
|
|
||||||
|
{% if result.embedded %}
|
||||||
|
<small> • <a class="text-info btn-collapse collapsed cursor-pointer media-loader disabled_if_nojs" data-toggle="collapse" data-target="#result-media-{{ index }}" data-btn-text-collapsed="{{ _('show media') }}" data-btn-text-not-collapsed="{{ _('hide media') }}">
|
||||||
|
{% if result.mtype == 'audio' %}{{ icon('music') }}
|
||||||
|
{% elif result.mtype == 'video' %} {{ icon('film') }}
|
||||||
|
{% endif %} {{ _('show media') }}</a></small>
|
||||||
|
{% endif %}
|
||||||
|
|
||||||
|
{% if result.embedded %}
|
||||||
|
<div id="result-media-{{ index }}" class="collapse">
|
||||||
|
{{ result.embedded|safe }}
|
||||||
|
</div>
|
||||||
|
{% endif %}
|
||||||
|
|
||||||
|
{% if result.abstract %}<p class="result-content result-abstract">{{ result.abstract|safe }}</p>{% endif %}
|
||||||
|
|
||||||
|
{% if result.img_src %}
|
||||||
|
<div class="container-fluid">
|
||||||
|
<div class="row">
|
||||||
|
<img src="{{ image_proxify(result.img_src) }}" alt="{{ result.title|striptags }}" title="{{ result.title|striptags }}" style="width: auto; max-height: 60px; min-height: 60px;" class="col-xs-2 col-sm-4 col-md-4 result-content">
|
||||||
|
{% if result.content %}<p class="result-content col-xs-8 col-sm-8 col-md-8">{{ result.content|safe }}</p>{% endif %}
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
{% else %}
|
||||||
|
{% if result.content %}<p class="result-content">{{ result.content|safe }}</p>{% endif %}
|
||||||
|
{% endif %}
|
||||||
|
|
||||||
|
<table class="result-metadata result-content">
|
||||||
|
{% if result.author %}<tr><td>{{ _('Author') }}</td><td>{{ result.author|safe }}</td></tr>{% endif %}
|
||||||
|
|
||||||
|
{% if result.filename %}<tr><td>{{ _('Filename') }}</td><td>{{ result.filename|safe }}</td></tr>{% endif %}
|
||||||
|
|
||||||
|
{% if result.size %}<tr><td>{{ _('Filesize') }}</td><td>
|
||||||
|
{% if result.size < 1024 %}{{ result.size }} {{ _('Bytes') }}
|
||||||
|
{% elif result.size < 1024*1024 %}{{ '{0:0.2f}'.format(result.size/1024) }} {{ _('kiB') }}
|
||||||
|
{% elif result.size < 1024*1024*1024 %}{{ '{0:0.2f}'.format(result.size/1024/1024) }} {{ _('MiB') }}
|
||||||
|
{% elif result.size < 1024*1024*1024*1024 %}{{ '{0:0.2f}'.format(result.size/1024/1024/1024) }} {{ _('GiB') }}
|
||||||
|
{% else %}{{ '{0:0.2f}'.format(result.size/1024/1024/1024/1024) }} {{ _('TiB') }}{% endif %}
|
||||||
|
</td></tr>
|
||||||
|
{% endif %}
|
||||||
|
|
||||||
|
{% if result.time %}<tr><td>{{ _('Date') }}</td><td>{{ result.time|safe }}</td></tr>{% endif %}
|
||||||
|
|
||||||
|
{% if result.mtype %}<tr><td>{{ _('Type') }}</td><td>{{ result.mtype|safe }}/{{ result.subtype|safe }}</td></tr>{% endif %}
|
||||||
|
</table>
|
||||||
|
|
||||||
|
{% if rtl %}
|
||||||
|
{{ result_footer_nocache_rtl(result) }}
|
||||||
|
{% else %}
|
||||||
|
{{ result_footer_nocache(result) }}
|
||||||
|
{% endif %}
|
Loading…
Reference in New Issue