我正在尝试索引 stackoverflow 数据。首先，我创建一个具有指定映射和设置的索引。
@classmethod
def create_index_with_set_map(cls, name, elasticsearch):
"""
create index with default mappings and settings(and analyzer).
Argument:
name -- The name of the index.
elasticsearch -- Elasticsearch instance for connection.
"""
mappings = "mappings": {
"properties": {
"Body": {
"type": "text",
"analyzer": "whitespace",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}}}
settings = {
"analysis": {
"analyzer": {
"default": {
"type": "whitespace"
}
}
}
}
body = {
"settings": settings,
"mappings": mappings
}
res = elasticsearch.indices.create(index=name, body=body)
print(res)
然后我尝试批量索引我的文档：
@classmethod
def start_index(cls, index_name, index_path, elasticsearch, doc_type):
"""
This function is using bulk index.
Argument:
index_name -- the name of index
index_path -- the path of xml file to index
elasticsearch -- Elasticsearch instance for connection
doc_type -- doc type
Returns:
"""
for lines in Parser.xml_reader(index_path):
actions = [
{
"_index": index_name,
"_type": doc_type,
"_id": Parser.post_parser(line)['Id'],
"_source": Parser.post_parser(line)
}
for line in lines if Parser.post_parser(line) is not None
]
helpers.bulk(elasticsearch, actions)
给定错误：（'500 个文档未能索引。'，[{'index'：{'_index'：'sof-question-answer2'，'_type'：'Stackoverflow'，'_id'：1'， 'status': 400, 'error': {'type': 'illegal_argument_exception', 'reason': 'Mapper for [Body] 与现有映射冲突：\n[mapper [Body] 有不同的 [analyzer]]'}， '数据'： ...}