如何在 django (1.8) 迁移中删除索引 varchar_pattern_ops？

Question

创建具有models.varchar(...) 字段的模型时，将创建varchar_pattern_ops 索引。

这是postgresql中生成的表

              Table "public.logger_btilog"
      Column      |           Type           | Modifiers 
------------------+--------------------------+-----------
 md5hash          | text                     | 
 id               | integer                  | not null
Indexes:
    "logger_btilog_pkey" PRIMARY KEY, btree (id)
    "logger_btilog_md5hash_6454d7bb20588b61_like" btree (md5hash varchar_pattern_ops)

我想在迁移中删除 varchar_pattern_ops 索引，并在该字段中添加哈希索引。

我试过这样做：

# models.py
class Btilog(models.Model):
    md5hash = models.TextField(db_index=False)
    [...]

并且在迁移中也强制添加db_field=False

# 0013_migration.py
# -*- coding: utf-8 -*-
from __future__ import unicode_literals

from django.db import models, migrations


class Migration(migrations.Migration):

    dependencies = [
        ('logger', '0014_btilog_id'),
    ]

    operations = [
        # this should remove all indexes for md5hash, but it does not work
        migrations.AlterField(
            model_name='btilog',
            name='md5hash',
            field=models.TextField(null=True, blank=True, db_index=False),
        ),
        migrations.RunSQL(
            "create index logger_btilog_md5hash_hashindex on logger_btilog using hash(md5hash);",
            "drop index logger_btilog_md5hash_hashindex;"
        ),
]

运行迁移后，这是数据库中的索引

                              relation                              |  size   
--------------------------------------------------------------------+---------
 public.logger_btilog                                               | 7185 MB
 public.logger_btilog_md5hash_6454d7bb20588b61_like                 | 1442 MB
 public.logger_btilog_md5hash_hashindex                             | 1024 MB
 public.logger_btilog_pkey                                          | 548 MB

请注意，public.logger_btilog_md5hash_6454d7bb20588b61_like 是我要删除的索引。这个索引是由 django 自动添加的，见this

关于该索引的更多信息

vtfx=# \d logger_btilog_md5hash_6454d7bb20588b61_like
Index "public.logger_btilog_md5hash_6454d7bb20588b61_like"
 Column  | Type | Definition 
---------+------+------------
 md5hash | text | md5hash
btree, for table "public.logger_btilog"

脚注：我对哈希索引的使用并不感到困惑，我只想在md5hash 字段中搜索=（严格相等）where，然后（随便）使用hash 索引是最快的，并且比btree 索引（django 的默认值）占用更少的空间

Answer 1

答案更新通知：

• django

• django >= 1.11：使用@Cesar Canassa 的答案

好的，我在这里找到了一些信息https://docs.djangoproject.com/en/1.8/_modules/django/db/backends/base/schema/#BaseDatabaseSchemaEditor.alter_field

并使用SchemaEditor 进行手动RunPython 迁移以删除varchar_pattern_ops 索引

# -*- coding: utf-8 -*-
from __future__ import unicode_literals

from django.db import models, migrations


import re
def drop_md5hash_varchar_pattern_ops_index(apps, schemaEditor):
    # code based on https://docs.djangoproject.com/en/1.8/_modules/django/db/backends/base/schema/#BaseDatabaseSchemaEditor.alter_field
    model = apps.get_model("logger", "Btilog")
    index_names = schemaEditor._constraint_names(model, index=True)
    for index_name in index_names:
        if re.search('logger_btilog_md5hash_.+_like', index_name):
            print 'dropping index {}'.format(index_name)
            schemaEditor.execute(schemaEditor._delete_constraint_sql(schemaEditor.sql_delete_index, model, index_name))


class Migration(migrations.Migration):
    dependencies = [
        ('logger', '0012_auto_20150529_1745'),
    ]

    operations = [
        # Remove the annoying index using a hack
        migrations.RunPython(
            drop_md5hash_varchar_pattern_ops_index
        ),
    ]

Answer 2

您可以使用 Django 1.11 中添加的新 Model Meta indexes 选项完全避免创建 varchar_pattern_ops“LIKE”索引。例如，不要像这样编写模型：

class MyModel(models.Model):
    my_field = models.CharField(max_length=64, db_index=True)

您需要使用 Model Meta 选项设置索引：

class MyModel(models.Model):
    my_field = models.CharField(max_length=64)

    class Meta:
        indexes = [
            models.Index(fields=['my_field'])
        ]

这样做，Django 将不会创建重复索引。

Answer 3

我正在使用 Django 3.0.11，我遇到了同样的问题。我不希望 _like 索引作为主键，因为它仅用于连接和精确匹配。

如果字段是主键，手动定义索引将无济于事。所以我想出了类似于第一个答案的hacky解决方案。

from django.db import migrations, models


def drop_pattern_ops_index(schema_editor, model, field):
    indexes = schema_editor._model_indexes_sql(model)
    for index in indexes:
        columns = index.parts["columns"].columns
        opclasses = index.parts["columns"].opclasses
        if field in columns and len(columns) == 1:
            # Django uses varchar_pattern_ops or text_pattern_ops
            if "pattern_ops" in opclasses[0]:
                drop_sql = schema_editor._delete_index_sql(
                    model, str(index.parts["name"]).strip('"')
                )
                # Indexes creation is always deferred in migration 
                # so we have to execute remove at the end
                schema_editor.deferred_sql.extend([drop_sql])
                break


def drop_extra_indexes(apps, schema_editor):
    model = apps.get_model("com_erp", "TestModel")
    drop_pattern_ops_index(schema_editor, model, "code")


class Migration(migrations.Migration):
    operations = [
        migrations.CreateModel(
            name="TestModel",
            fields=[
                ("code", models.TextField(primary_key=True, serialize=False)),
                ("name", models.TextField()),
            ],
            options={"db_table": "test_table",},
        ),
        migrations.RunPython(drop_extra_indexes, migrations.RunPython.noop),
    ]