我正尝试将ElasticSearch 6.4与在Python/Django中编写的现有Web应用程序一起使用。我有一些问题，我想了解为什么以及如何解决这些问题。
###########
＃现有：＃
###########
在我的应用程序中，可以上传文档文件（例如.pdf或.doc）。然后，我在我的应用程序中有了一个搜索功能，该功能可以在上载ElasticSearch索引的文档时进行搜索。
文档标题始终以相同的方式书写：
YEAR - DOC_TYPE - ORGANISATION - document_title.extension
例如：
1970_ANNUAL_REPORT_APP-TEST_1342 - loremipsum.pdf
搜索功能始终在doc_type = ANNUAL_REPORT之间完成。因为存在多种doc_type（ANNUAL_REPORT，OTHERS等）。
##################
＃我的环境：＃
##################
根据我的ElasticSearch部分，这是一些数据。我也在学习ES命令。
$ curl -XGET http://127.0.0.1:9200/_cat/indices?v
health status index uuid pri rep docs.count docs.deleted store.size pri.store.size
yellow open app 5T0HZTbmQU2-ZNJXlNb-zg 5 1 742 2 396.4kb 396.4kb
所以我的索引是app
对于上面的示例，如果我搜索此文档：1970_ANNUAL_REPORT_APP-TEST_1342 - loremipsum.pdf，则具有：
$ curl -XGET http://127.0.0.1:9200/app/annual-report/1343?pretty
{
"_index" : "app",
"_type" : "annual-report",
"_id" : "1343",
"_version" : 33,
"found" : true,
"_source" : {
"attachment" : {
"date" : "2010-03-04T12:08:00Z",
"content_type" : "application/pdf",
"author" : "manshanden",
"language" : "et",
"title" : "Microsoft Word - Test document Word.doc",
"content" : "some text ...",
"content_length" : 3926
},
"relative_path" : "app_docs/APP-TEST/1970_ANNUAL_REPORT_APP-TEST_1342.pdf",
"title" : "1970_ANNUAL_REPORT_APP-TEST_1342 - loremipsum.pdf"
}
}
现在，在我的Web应用程序的搜索部分中，我希望通过以下搜索找到此文档：1970。
def search_in_annual(self, q):
try:
response = self.es.search(
index='app', doc_type='annual-report',
q=q, _source_exclude=['data'], size=5000)
except ConnectionError:
return -1, None
total = 0
hits = []
if response:
for hit in response["hits"]["hits"]:
hits.append({
'id': hit['_id'],
'title': hit['_source']['title'],
'file': hit['_source']['relative_path'],
})
total = response["hits"]["total"]
return total, hits
但是当q=1970时，结果为0
如果我写：
response = self.es.search(
index='app', doc_type='annual-report',
q="q*", _source_exclude=['data'], size=5000)
它返回我的文档，但也返回很多文档，在标题或文档内容中都没有1970。
#################
＃我的全局代码：＃
#################
这是管理索引功能的全局类：
class EdqmES(object):
host = 'localhost'
port = 9200
es = None
def __init__(self, *args, **kwargs):
self.host = kwargs.pop('host', self.host)
self.port = kwargs.pop('port', self.port)
# Connect to ElasticSearch server
self.es = Elasticsearch([{
'host': self.host,
'port': self.port
}])
def __str__(self):
return self.host + ':' + self.port
@staticmethod
def file_encode(filename):
with open(filename, "rb") as f:
return b64encode(f.read()).decode('utf-8')
def create_pipeline(self):
body = {
"description": "Extract attachment information",
"processors": [
{"attachment": {
"field": "data",
"target_field": "attachment",
"indexed_chars": -1
}},
{"remove": {"field": "data"}}
]
}
self.es.index(
index='_ingest',
doc_type='pipeline',
id='attachment',
body=body
)
def index_document(self, doc, bulk=False):
filename = doc.get_filename()
try:
data = self.file_encode(filename)
except IOError:
data = ''
print('ERROR with ' + filename)
# TODO: log error
item_body = {
'_id': doc.id,
'data': data,
'relative_path': str(doc.file),
'title': doc.title,
}
if bulk:
return item_body
result1 = self.es.index(
index='app', doc_type='annual-report',
id=doc.id,
pipeline='attachment',
body=item_body,
request_timeout=60
)
print(result1)
return result1
def index_annual_reports(self):
list_docs = Document.objects.filter(category=Document.OPT_ANNUAL)
print(list_docs.count())
self.create_pipeline()
bulk = []
inserted = 0
for doc in list_docs:
inserted += 1
bulk.append(self.index_document(doc, True))
if inserted == 20:
inserted = 0
try:
print(helpers.bulk(self.es, bulk, index='app',
doc_type='annual-report',
pipeline='attachment',
request_timeout=60))
except BulkIndexError as err:
print(err)
bulk = []
if inserted:
print(helpers.bulk(
self.es, bulk, index='app',
doc_type='annual-report',
pipeline='attachment', request_timeout=60))
我的文档在提交时被索引，这要感谢带有信号的Django表单：
@receiver(signals.post_save, sender=Document, dispatch_uid='add_new_doc')
def add_document_handler(sender, instance=None, created=False, **kwargs):
""" When a document is created index new annual report (only) with Elasticsearch and update conformity date if the
document is a new declaration of conformity
:param sender: Class which is concerned
:type sender: the model class
:param instance: Object which was just saved
:type instance: model instance
:param created: True for a creation, False for an update
:type created: boolean
:param kwargs: Additional parameter of the signal
:type kwargs: dict
"""
if not created:
return
# Index only annual reports
elif instance.category == Document.OPT_ANNUAL:
es = EdqmES()
es.index_document(instance)
答案 0 :(得分：0)
这是我所做的，并且似乎可以正常工作：
{"changed": false, "module_stderr": "Shared connection to 127.0.0.1 closed.
", "module_stdout": "
Traceback (most recent call last):
File "/tmp/ansible_i8T24e/ansible_module_rabbitmq_queue.py", line 285, in <module>
main()
File "/tmp/ansible_i8T24e/ansible_module_rabbitmq_queue.py", line 178, in main
r = requests.get(url, auth=(module.params['login_user'], module.params['login_password']))
File "/usr/lib/python2.7/dist-packages/requests/api.py", line 70, in get
return request('get', url, params=params, **kwargs)
File "/usr/lib/python2.7/dist-packages/requests/api.py", line 56, in request
return session.request(method=method, url=url, **kwargs)
File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 488, in request
resp = self.send(prep, **send_kwargs)
File "/usr/lib/python2.7/dist-packages/requests/sessions.py", line 609, in send
r = adapter.send(request, **kwargs)
File "/usr/lib/python2.7/dist-packages/requests/adapters.py", line 487,in send
raise ConnectionError(e, request=request)
requests.exceptions.ConnectionError: HTTPConnectionPool(host='127.0.0.1', port=15672): Max retries exceeded with url: /api/queues/%2F/feedfiles (Caused by NewConnectionError('<requests.packages.urllib3.connection.HTTPConnection object at 0x7fcfdaf8e7d0>: Failed to establish a new connection: [Errno 111] Connection refused',))
", "msg": "MODULE FAILURE", "rc": 1}
它可以搜索标题，前缀和内容，以查找我的文档。