[英]ElasticSearch and Python : Issue with search function
我正在嘗試將ElasticSearch 6.4
首次用於以Python/Django
編寫的現有Web應用程序。 我有一些問題,我想了解為什么以及如何解決這些問題。
###########
#現有:
###########
在我的應用程序中,可以上傳文檔文件(例如.pdf或.doc)。 然后,我在我的應用程序中有了一個搜索功能,該功能可以在上載ElasticSearch索引的文檔時進行搜索。
文檔標題始終以相同的方式書寫:
YEAR - DOC_TYPE - ORGANISATION - document_title.extension
例如 :
1970_ANNUAL_REPORT_APP-TEST_1342 - loremipsum.pdf
搜索功能始終在doc_type = ANNUAL_REPORT
。 因為存在多個doc_type(ANNUAL_REPORT,OTHERS等)。
##################
#我的環境:#
##################
根據我的ElasticSearch部分,這是一些數據。 我也在學習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
對於上面的示例,如果我搜索以下文檔: 1970_ANNUAL_REPORT_APP-TEST_1342 - loremipsum.pdf
,則有:
$ 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"
}
}
現在,將搜索部分放入Web應用程序中,我希望通過以下搜索找到該文檔: 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
但是當q=1970
,結果為0
如果我寫:
response = self.es.search(
index='app', doc_type='annual-report',
q="q*", _source_exclude=['data'], size=5000)
它返回我的文檔,但標題或文檔內容中也包含許多沒有1970
的文檔。
#################
#我的全局代碼:#
#################
這是管理索引功能的全局類:
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))
當他提交時,我的文檔已被索引,感謝帶信號的Django表單:
@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)
這是我所做的,並且似乎可以正常工作:
def search_in_annual(self, q):
try:
response = self.es.search(
index='app', doc_type='annual-report', q=q, _source_exclude=['data'], size=5000)
if response['hits']['total'] == 0:
response = self.es.search(
index='app', doc_type='annual-report',
body={
"query":
{"prefix": {"title": 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
它可以搜索標題,前綴和內容以找到我的文檔。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.