A basic model class representing Apache Solr. Abstracts the select, delete, update, and commit operations.
Select operation returns Python object parsed from a JSON-formatted response.
Python, 69 lines
Download
Copy to clipboard1 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 | """Simple model of Apache Solr 1.4 and 3.x"""
import json
import urllib
import urllib2
import lxml.etree as etree
class Solr(object):
"""Thin abstraction layer around Apache Solr"""
def __init__(self, url):
self.url = url
def select(self, params):
"""Search Solr, return URL and JSON response."""
params['wt'] = 'json'
url = self.url + '/select?' + urllib.urlencode(params)
conn = urllib2.urlopen(url)
return url, json.load(conn)
def delete(self, query, commit=False):
"""Delete documents matching `query` from Solr, return (URL, status)"""
params = {}
if commit:
params['commit'] = 'true'
url = self.url + '/update?' + urllib.urlencode(params)
request = urllib2.Request(url)
request.add_header('Content-Type', 'text/xml; charset=utf-8')
request.add_data('<delete><query>{0}</query></delete>'.format(query))
response = urllib2.urlopen(request).read()
status = etree.XML(response).findtext('lst/int')
return url, status
def update(self, docs, commitwithin=None):
"""Post list of docs to Solr, return URL and status.
Opptionall tell Solr to "commitwithin" that many milliseconds."""
url = self.url + '/update'
add_xml = etree.Element('add')
if commitwithin is not None:
add_xml.set('commitWithin', str(commitwithin))
for doc in docs:
xdoc = etree.SubElement(add_xml, 'doc')
for key, value in doc.iteritems():
if value:
field = etree.Element('field', name=key)
field.text = (value if isinstance(value, unicode)
else str(value))
xdoc.append(field)
request = urllib2.Request(url)
request.add_header('Content-Type', 'text/xml; charset=utf-8')
request.add_data(etree.tostring(add_xml, pretty_print=True))
response = urllib2.urlopen(request).read()
status = etree.XML(response).findtext('lst/int')
return url, status
def commit(self, waitsearcher=False, waitflush=False):
"""Commit uncommitted changes to Solr immediately, without waiting."""
commit_xml = etree.Element('commit')
commit_xml.set('waitFlush', str(waitflush))
commit_xml.set('waitSearcher', str(waitsearcher))
url = self.url + '/update'
request = urllib2.Request(url)
request.add_header('Content-Type', 'text/xml; charset=utf-8')
request.add_data(etree.tostring(commit_xml, pretty_print=True))
response = urllib2.urlopen(request).read()
status = etree.XML(response).findtext('lst/int')
return url, status
|
There are several full-fledged Python libraries for interfacing to Apache Solr.
But sometimes all you need is a little code to build an appropriate HTTP request and parse the response. In that case, using this class could save you some time.
