All*_*cor 11 python django postgresql indexing similarity
django.contrib.postgres的新TrigramSimilarity功能非常适合我遇到的问题.我将它用于搜索栏以找到难以拼写的拉丁名字.问题是有超过200万个名字,搜索需要的时间比我想要的要长.
我想在postgres文档https://www.postgresql.org/docs/9.6/static/pgtrgm.html中创建一个关于三元组的索引.
但我不知道如何以Django API使用它的方式来做到这一点.对于postgres文本搜索,有关于如何创建索引的描述.但不是因为三元组的相似性. https://docs.djangoproject.com/en/1.11/ref/contrib/postgres/search/#performance
这就是我现在所拥有的:
class NCBI_names(models.Model):
tax_id = models.ForeignKey(NCBI_nodes, on_delete=models.CASCADE, default = 0)
name_txt = models.CharField(max_length=255, default = '')
name_class = models.CharField(max_length=32, db_index=True, default = '')
class Meta:
indexes = [GinIndex(fields=['name_txt'])]
然后在vieuw的get_queryset中我做:
class TaxonSearchListView(ListView):
#form_class=TaxonSearchForm
template_name='collectie/taxon_list.html'
paginate_by=20
model=NCBI_names
context_object_name = 'taxon_list'
def dispatch(self, request, *args, **kwargs):
query = request.GET.get('q')
if query:
try:
tax_id = self.model.objects.get(name_txt__iexact=query).tax_id.tax_id
return redirect('collectie:taxon_detail', tax_id)
except (self.model.DoesNotExist, self.model.MultipleObjectsReturned) as e:
return super(TaxonSearchListView, self).dispatch(request, *args, **kwargs)
else:
return super(TaxonSearchListView, self).dispatch(request, *args, **kwargs)
def get_queryset(self):
result = super(TaxonSearchListView, self).get_queryset()
#
query = self.request.GET.get('q')
if query:
result = result.exclude(name_txt__icontains = 'sp.')
result = result.annotate(similarity=TrigramSimilarity('name_txt', query)).filter(similarity__gt=0.3).order_by('-similarity')
return result
编辑将整个视图类放入
Tim*_*imB 12
我遇到了类似的问题,尝试使用pg_tgrm扩展来支持高效contains和icontainsDjango字段查找.
可能有更优雅的方式,但定义像这样的新索引类型对我有用:
from django.contrib.postgres.indexes import GinIndex
class TrigramIndex(GinIndex):
def get_sql_create_template_values(self, model, schema_editor, using):
fields = [model._meta.get_field(field_name) for field_name, order in self.fields_orders]
tablespace_sql = schema_editor._get_index_tablespace_sql(model, fields)
quote_name = schema_editor.quote_name
columns = [
('%s %s' % (quote_name(field.column), order)).strip() + ' gin_trgm_ops'
for field, (field_name, order) in zip(fields, self.fields_orders)
]
return {
'table': quote_name(model._meta.db_table),
'name': quote_name(self.name),
'columns': ', '.join(columns),
'using': using,
'extra': tablespace_sql,
}
只需一次修改就get_sql_create_template_values可以复制该方法Index.get_sql_create_template_values():添加+ ' gin_trgm_ops'.
对于您的用例,您将name_txt使用this TrigramIndex而不是a 来定义索引GinIndex.然后运行makemigrations,这将生成一个生成所需CREATE INDEXSQL 的迁移.
更新:
我看到你也在使用icontains以下方法进行查询:
result.exclude(name_txt__icontains = 'sp.')
Postgresql后端将把它变成这样的东西:
UPPER("NCBI_names"."name_txt"::text) LIKE UPPER('sp.')
然后因为这个而不会使用trigram索引UPPER().
我有同样的问题,最后继承数据库后端来解决它:
from django.db.backends.postgresql import base, operations
class DatabaseFeatures(base.DatabaseFeatures):
pass
class DatabaseOperations(operations.DatabaseOperations):
def lookup_cast(self, lookup_type, internal_type=None):
lookup = '%s'
# Cast text lookups to text to allow things like filter(x__contains=4)
if lookup_type in ('iexact', 'contains', 'icontains', 'startswith',
'istartswith', 'endswith', 'iendswith', 'regex', 'iregex'):
if internal_type in ('IPAddressField', 'GenericIPAddressField'):
lookup = "HOST(%s)"
else:
lookup = "%s::text"
return lookup
class DatabaseWrapper(base.DatabaseWrapper):
"""
Override the defaults where needed to allow use of trigram index
"""
ops_class = DatabaseOperations
def __init__(self, *args, **kwargs):
self.operators.update({
'icontains': 'ILIKE %s',
'istartswith': 'ILIKE %s',
'iendswith': 'ILIKE %s',
})
self.pattern_ops.update({
'icontains': "ILIKE '%%' || {} || '%%'",
'istartswith': "ILIKE {} || '%%'",
'iendswith': "ILIKE '%%' || {}",
})
super(DatabaseWrapper, self).__init__(*args, **kwargs)
要使 Django 2.2 使用索引进行icontains类似搜索：
子类 GinIndex 使索引不区分大小写（将所有字段值大写）：
from django.contrib.postgres.indexes import GinIndex
class UpperGinIndex(GinIndex):
def create_sql(self, model, schema_editor, using=''):
statement = super().create_sql(model, schema_editor, using=using)
quote_name = statement.parts['columns'].quote_name
def upper_quoted(column):
return f'UPPER({quote_name(column)})'
statement.parts['columns'].quote_name = upper_quoted
return statement
像这样将索引添加到您的模型中，包括name使用时所需的kwarg opclasses：
class MyModel(Model):
name = TextField(...)
class Meta:
indexes = [
UpperGinIndex(fields=['name'], name='mymodel_name_gintrgm', opclasses=['gin_trgm_ops'])
]
生成迁移并编辑生成的文件：
# Generated by Django 2.2.3 on 2019-07-15 10:46
from django.contrib.postgres.operations import TrigramExtension # <<< add this
from django.db import migrations
import myapp.models
class Migration(migrations.Migration):
operations = [
TrigramExtension(), # <<< add this
migrations.AddIndex(
model_name='mymodel',
index=myapp.models.UpperGinIndex(fields=['name'], name='mymodel_name_gintrgm', opclasses=['gin_trgm_ops']),
),
]
这已经有了答案，但在 Django 2.2 中，您可以更轻松地做到这一点：
class MyModel(models.Model):
name = models.TextField()
class Meta:
indexes = [GistIndex(name="gist_trgm_idx", fields=("name",), opclasses=("gist_trgm_ops",))]
或者，您可以使用GinIndex.
如果有人想要将多个列上的索引与空间连接（连接），您可以使用我对内置索引的修改。
创建索引，如 gin (("column1" || ' ' || "column2" || ' ' || ...) gin_trgm_ops)
class GinSpaceConcatIndex(GinIndex):
def get_sql_create_template_values(self, model, schema_editor, using):
fields = [model._meta.get_field(field_name) for field_name, order in self.fields_orders]
tablespace_sql = schema_editor._get_index_tablespace_sql(model, fields)
quote_name = schema_editor.quote_name
columns = [
('%s %s' % (quote_name(field.column), order)).strip()
for field, (field_name, order) in zip(fields, self.fields_orders)
]
return {
'table': quote_name(model._meta.db_table),
'name': quote_name(self.name),
'columns': "({}) gin_trgm_ops".format(" || ' ' || ".join(columns)),
'using': using,
'extra': tablespace_sql,
}
受到有关该主题的旧文章的启发，我进入了当前文章，该文章为a 提供了以下解决方案GistIndex：
更新：从Django-1.11开始，事情似乎更简单了，因为这个答案和Django文档很简单：
from django.contrib.postgres.indexes import GinIndex
class MyModel(models.Model):
the_field = models.CharField(max_length=512, db_index=True)
class Meta:
indexes = [GinIndex(fields=['the_field'])]
从Django-2.2开始，为此opclasses可以使用属性class Index(fields=(), name=None, db_tablespace=None, opclasses=())。
from django.contrib.postgres.indexes import GistIndex
class GistIndexTrgrmOps(GistIndex):
def create_sql(self, model, schema_editor):
# - this Statement is instantiated by the _create_index_sql()
# method of django.db.backends.base.schema.BaseDatabaseSchemaEditor.
# using sql_create_index template from
# django.db.backends.postgresql.schema.DatabaseSchemaEditor
# - the template has original value:
# "CREATE INDEX %(name)s ON %(table)s%(using)s (%(columns)s)%(extra)s"
statement = super().create_sql(model, schema_editor)
# - however, we want to use a GIST index to accelerate trigram
# matching, so we want to add the gist_trgm_ops index operator
# class
# - so we replace the template with:
# "CREATE INDEX %(name)s ON %(table)s%(using)s (%(columns)s gist_trgrm_ops)%(extra)s"
statement.template =\
"CREATE INDEX %(name)s ON %(table)s%(using)s (%(columns)s gist_trgm_ops)%(extra)s"
return statement
然后可以在模型类中使用以下代码：
class YourModel(models.Model):
some_field = models.TextField(...)
class Meta:
indexes = [
GistIndexTrgrmOps(fields=['some_field'])
]