python中sql解析库sqlparse基本操作指南

def parse(sql, encoding=None):
    """Parse sql and return a list of statements.

    :param sql: A string containing one or more SQL statements.
    :param encoding: The encoding of the statement (optional).
    :returns: A tuple of :class:`~sqlparse.sql.Statement` instances.
    """
    return tuple(parsestream(sql, encoding))

import sqlparse

SQL = """CREATE TABLE foo (
                 id integer primary key comment 'id_comm',
                 title varchar(200) not null comment 'id_comm',
                 description text comment 'id_comm');"""

parsed = sqlparse.parse(SQL)[0]

print(parsed)

def format(sql, encoding=None, **options):
    """Format *sql* according to *options*.

    Available options are documented in :ref:`formatting`.

    In addition to the formatting options this function accepts the
    keyword "encoding" which determines the encoding of the statement.

    :returns: The formatted SQL statement as string.
    """

import sqlparse

sql = """select * from tbl where id > 10;"""

format = sqlparse.format(sql, reindent=True, keyword_case='upper')

print(format)

# SELECT *
# FROM tbl
# WHERE id > 10;

def split(sql, encoding=None):
    """Split *sql* into single statements.

    :param sql: A string containing one or more SQL statements.
    :param encoding: The encoding of the statement (optional).
    :returns: A list of strings.
    """

import sqlparse

sql = """select * from tbl where id > 10;select * from tbl where id > 20;"""

split = sqlparse.split(sql)

print(split)
# ['select * from tbl where id > 10;', 'select * from tbl where id > 20;']

def parsestream(stream, encoding=None):
    """Parses sql statements from file-like object.

    :param stream: A file-like object.
    :param encoding: The encoding of the stream contents (optional).
    :returns: A generator of :class:`~sqlparse.sql.Statement` instances.
    """

with open('../static/pre_sql.sql', 'r', encoding='utf-8') as file:
    for statement in sqlparse.parse(file):
        print(statement)

class Token:
    """Base class for all other classes in this module.

    It represents a single token and has two instance attributes:
    ``value`` is the unchanged value of the token and ``ttype`` is
    the type of the token.
    """
    
    def __init__(self, ttype, value):
    value = str(value)
    self.value = value
    self.ttype = ttype
    self.parent = None
    self.is_group = False
    self.is_keyword = ttype in T.Keyword
    self.is_whitespace = self.ttype in T.Whitespace
    self.normalized = value.upper() if self.is_keyword else value

# Special token types
Text = Token.Text
Whitespace = Text.Whitespace
Newline = Whitespace.Newline
Error = Token.Error
# Text that doesn't belong to this lexer (e.g. HTML in PHP)
Other = Token.Other

# Common token types for source code
Keyword = Token.Keyword
Name = Token.Name
Literal = Token.Literal
String = Literal.String
Number = Literal.Number
Punctuation = Token.Punctuation
Operator = Token.Operator
Comparison = Operator.Comparison
Wildcard = Token.Wildcard
Comment = Token.Comment
Assignment = Token.Assignment

# Generic types for non-source code
Generic = Token.Generic
Command = Generic.Command

# String and some others are not direct children of Token.
# alias them:
Token.Token = Token
Token.String = String
Token.Number = Number

# SQL specific tokens
DML = Keyword.DML
DDL = Keyword.DDL
CTE = Keyword.CTE

sql = 'select 1 as id, name, case when name = "" then 3 else 4 end as score from tbl where id > 10 limit 100'

stmts = sqlparse.parse(sql)[0].tokens

for stmt in stmts:

    print(f"{type(stmt)}::{stmt.ttype}::",stmt)
# <class 'sqlparse.sql.Token'>::Token.Keyword.DML:: select
# <class 'sqlparse.sql.Token'>::Token.Text.Whitespace::  
# <class 'sqlparse.sql.IdentifierList'>::None:: 1 as id, name, case when name = "" then 3 else 4 end as score
# <class 'sqlparse.sql.Token'>::Token.Text.Whitespace::  
# <class 'sqlparse.sql.Token'>::Token.Keyword:: from
# <class 'sqlparse.sql.Token'>::Token.Text.Whitespace::  
# <class 'sqlparse.sql.Identifier'>::None:: tbl
# <class 'sqlparse.sql.Token'>::Token.Text.Whitespace::  
# <class 'sqlparse.sql.Where'>::None:: where id > 10 
# <class 'sqlparse.sql.Token'>::Token.Keyword:: limit
# <class 'sqlparse.sql.Token'>::Token.Text.Whitespace::  
# <class 'sqlparse.sql.Token'>::Token.Literal.Number.Integer:: 100

import sqlparse
import re

sql = 'insert into table inser_tbl partition (dt = dt) select 1 as id, name, case when （name = "" or name = "") then 3 else 4 end as score from tbl where id > 10 limit 100'

stmts = sqlparse.parse(sql)[0].tokens

cols = []
tbls = []
froms = []
wheres = []
last_key = ''
for stmt in stmts:
    if stmt.value == 'insert' or stmt.value == 'select' or stmt.value == 'from':
        last_key = stmt.value
    # 剔除空格和换行
    if stmt.ttype is sqlparse.tokens.Text.Whitespace:
        continue
    # 关键字
    elif stmt.ttype is sqlparse.tokens.Keyword.DML:
        dml = stmt.value
        last_key = dml
    # 字段
    elif isinstance(stmt, sqlparse.sql.IdentifierList):
        # 判断上一个是什么类型
        if last_key == 'select':
            for identifier in stmt.get_identifiers():
                col_name = identifier.value
                if re.search('as', col_name, re.I):
                    col_name = re.search('as (.*)', col_name, re.I).group(1).strip()
                cols.append(col_name)
        elif last_key == 'from':
            for identifier in stmt.get_identifiers():
                froms.append(identifier.value)
        else:
            for identifier in stmt.get_identifiers():
                tbls.append(identifier.value)
    elif isinstance(stmt, sqlparse.sql.Identifier):
        if last_key == 'select':
            cols.append(stmt.value)
        elif last_key == 'from':
            froms.append(stmt.value)
        else:
            tbls.append(stmt.value)
    elif isinstance(stmt, sqlparse.sql.Where):
        wheres.append(stmt.value)
    # 表名
print("cols:", cols)
print("tbls:", tbls)
print("froms:", froms)
print("wheres:", wheres)

# cols: ['id', 'name', 'score']
# tbls: ['inser_tbl']
# froms: ['tbl']
# wheres: ['where id > 10 ']