6

我想在“sqlalchemy”中使用正则表达式查询以及在“python sqlite”中完成，代码如下..

未完成的沙盒脚本是这样的：

import os
import re
import sqlite3

#
# python sqlite
#

DB_PATH = __name__ + '.db'

try:
    os.remove(DB_PATH)
except:
    pass


def re_fn(expr, item):
    reg = re.compile(expr, re.I)
    return reg.search(item) is not None

conn = sqlite3.connect(':memory:')
conn = sqlite3.connect(DB_PATH)
conn.create_function("REGEXP", 2, re_fn)
cursor = conn.cursor()

cursor.execute(
    'CREATE TABLE t1 (id INTEGER PRIMARY KEY, c1 TEXT)'
)
cursor.executemany(
    #'INSERT INTO t1 (c1) VALUES (?)', [('aaa"test"',),('blah',)]
    'INSERT INTO t1 (c1) VALUES (?)', [
        ('dupa / 1st Part',), ('cycki / 2nd Part',), ('fiut / 3rd Part',)
    ]
)
cursor.execute(
    #'SELECT c1 FROM t1 WHERE c1 REGEXP ?',['2|3\w+part']
    'SELECT c1 FROM t1 WHERE c1 REGEXP ?',['\d\w+ part']
)
conn.commit()
data=cursor.fetchall()
print(data)



#
# sqlalchemy
#

import sqlalchemy as sa
import sqlalchemy.orm as orm
from sqlalchemy.ext.declarative import declarative_base

DSN = 'sqlite:///' + DB_PATH
engine = sa.create_engine(DSN, convert_unicode=True)
db = orm.scoped_session(orm.sessionmaker(autocommit=False,
                                         autoflush=False,
                                         bind=engine))

Base = declarative_base(bind=engine)
meta = Base.metadata

class T1(Base):
    __table__ = sa.Table('t1', meta, autoload=True)

print(db.query(T1).all())

我发现应该在每个线程上注册 regexp 函数：

http://permalink.gmane.org/gmane.comp.web.pylons.general/12742

但我无法对我的脚本采用链接的解决方案 + 它已被弃用。

更新

我想查询这个：

cursor.execute(
    #'SELECT c1 FROM t1 WHERE c1 REGEXP ?',['2|3\w+part']
    'SELECT c1 FROM t1 WHERE c1 REGEXP ?',['\d\w+ part']
)

但在 sqlalchemy 中。

4

2 回答 2

13

我得到了答案。缺少一行的完整工作脚本是这样的：

import os
import re
import sqlite3

DB_PATH = __name__ + '.db'

try:
    os.remove(DB_PATH)
except:
    pass


def re_fn(expr, item):
    reg = re.compile(expr, re.I)
    return reg.search(item) is not None

conn = sqlite3.connect(':memory:')
conn = sqlite3.connect(DB_PATH)
conn.create_function("REGEXP", 2, re_fn)
cursor = conn.cursor()

cursor.execute(
    'CREATE TABLE t1 (id INTEGER PRIMARY KEY, c1 TEXT)'
)
cursor.executemany(
    #'INSERT INTO t1 (c1) VALUES (?)', [('aaa"test"',),('blah',)]
    'INSERT INTO t1 (c1) VALUES (?)', [
        ('dupa / 1st Part',), ('cycki / 2nd Part',), ('fiut / 3rd Part',)
    ]
)
SEARCH_TERM = '3rd part'
cursor.execute(
    #'SELECT c1 FROM t1 WHERE c1 REGEXP ?',['2|3\w+part']
    'SELECT c1 FROM t1 WHERE c1 REGEXP ?',[SEARCH_TERM]
)
conn.commit()
data=cursor.fetchall()
print(data)



#
# sqlalchemy
#

import sqlalchemy as sa
import sqlalchemy.orm as orm
from sqlalchemy.ext.declarative import declarative_base

DSN = 'sqlite:///' + DB_PATH

engine = sa.create_engine(DSN, convert_unicode=True)

conn = engine.connect()
conn.connection.create_function('regexp', 2, re_fn)

db = orm.scoped_session(orm.sessionmaker(autocommit=False,
                                         autoflush=False,
                                         bind=engine))

Base = declarative_base(bind=engine)
meta = Base.metadata

class T1(Base):
    __table__ = sa.Table('t1', meta, autoload=True)

print(db.query(T1.c1).filter(T1.c1.op('regexp')(SEARCH_TERM)).all())

以上适用于 sqlalchemy=0.6.3

在 sqlalchemy=0.7.8 我得到错误：

“sqlalchemy.exc.OperationalError：（OperationalError）没有这样的功能：正则表达式..”

也许是因为这个变化：

当指定基于文件的数据库时，方言将使用 NullPool 作为连接源。该池关闭并丢弃立即返回池的连接。基于 SQLite 文件的连接具有极低的开销，因此不需要池化。该方案还可以防止在不同的线程中再次使用连接，并且最适合 SQLite 的粗粒度文件锁定。在 0.7 版更改: 基于 SQLite 文件的数据库的 NullPool 默认选择。以前的版本默认为所有 SQLite 数据库选择 SingletonThreadPool。

来自：http ://docs.sqlalchemy.org/en/rel_0_7/dialects/sqlite.html?highlight=isolation_level#threading-pooling-behavior

解决方案是：在“开始”事件中添加正则表达式 fn，如下所示：

...

conn = engine.connect()
@sa.event.listens_for(engine, "begin")
def do_begin(conn):
    conn.connection.create_function('regexp', 2, re_fn)

db = orm.scoped_session(orm.sessionmaker(autocommit=False,
                                         autoflush=False,
                                         bind=engine))

...
于 2012-09-18T10:18:15.117 回答
0

差不多10年后...

它在 SQLAlchemy 1.4 中更容易工作：

stmt = select(table.c.some_column).where(
    table.c.some_column.regexp_match('^(b|c)')
)

来源：https ://docs.sqlalchemy.org/en/14/core/sqlelement.html#sqlalchemy.sql.expression.ColumnElement.regexp_match

于 2022-01-20T22:43:38.443 回答