python - Impyla 从 Flask 插入 SQL : Syntax error (Identifier Binding)

Question

最近我设置了一个 Flask POST 端点，通过 Impyla 模块将数据写入 Impala DB。

环境:CentOS 上的 Python 3.6.5。

Impala版本:impalad版本2.6.0-cdh5.8.0

api.py:

from flask import Flask, request, abort, Response
from flask_cors import CORS
import json
from impala.dbapi import connect
import sys
import re
from datetime import datetime


app = application = Flask(__name__)
CORS(app)


conn = connect(host='datanode2', port=21050,
            user='user', database='testdb')


@app.route("/api/endpoint", methods=['POST'])
def post_data():
    # if not request.json:
    #     abort(400)

    params = request.get_json(force=True)  # getting request data
    print(">>>>>> ", params, flush=True)

    params['log_time'] = datetime.now().strftime("%Y-%m-%d %H-%M-%S")
    # params['page_url'] = re.sub(
    #     '[^a-zA-Z0-9-_*.]', '', re.sub(':', '_', params['page_url']))

    try:
        cursor = conn.cursor()

        sql = "INSERT INTO table ( page_title, page_url, log_time, machine, clicks, id ) VALUES (%s, %s, %s, %s, %s, %s)"
        values = (params['page_title'], params['page_url'], params['log_time'],
                params['machine'], params['clicks'], params['id'])
        print(">>>>>> " + sql % values, file=sys.stderr, flush=True)

        cursor.execute(sql, values)

        print(
            f">>>>>> Data Written Successfully", file=sys.stderr, flush=True)
        return Response(json.dumps({'success': True}), 201, mimetype="application/json")
    except Exception as e:
        print(e, file=sys.stderr, flush=True)
        return Response(json.dumps({'success': False}), 400, mimetype="application/json")


if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5008, debug=True)

请求.py:

import requests as r

url = "http://123.234.345.456:30001/"
# url =  "https://stackoverflow.com/questions/ask"

res = r.post('http://localhost:5008/api/endpoint', 
            json={             
                "page_title": "Home",   
                "page_url": url,
                "machine": "Mac OS",
                "clicks": 16,
                "id": "60cd1d79-eda7-44c2-a4ec-ffdd5d6ac3db"         
            }
        )

if res.ok:
    print(res.json())
else:
    print('Error!')

我使用 python api.py 运行 Flask api，然后使用 python req.py 进行测试。

flask 服务器出现此错误:

>>>>>>  {'page_title': 'Home', 'page_url': 'http://123.234.345.456:30001/', 'machine': 'Mac OS', 'clicks': 16, 'id': '60cd1d79-eda7-44c2-a4ec-ffdd5d6ac3db'}
>>>>>> INSERT INTO table ( page_title, page_url, log_time, machine, clicks, id ) VALUES (Home, http://123.234.345.456:30001/, 2018-12-12 16-14-04, Mac OS, 16, 60cd1d79-eda7-44c2-a4ec-ffdd5d6ac3db)
AnalysisException: Syntax error in line 1:
..., 'http://123.234.345.456'2018-12-12 16-14-04'0001/', ...
                         ^
Encountered: INTEGER LITERAL
Expected: AND, AS, ASC, BETWEEN, CROSS, DESC, DIV, ELSE, END, FOLLOWING, FROM, FULL, GROUP, HAVING, ILIKE, IN, INNER, IREGEXP, IS, JOIN, LEFT, LIKE, LIMIT, NOT, NULLS, OFFSET, OR, ORDER, PRECEDING, RANGE, REGEXP, RIGHT, RLIKE, ROWS, THEN, UNION, WHEN, WHERE, COMMA, IDENTIFIER

CAUSED BY: Exception: Syntax error

这个错误有点烦人:

1. 我尝试直接在 impala-shell 中插入 sql 命令并且它有效。

2. 当 page_url 是唯一参数时，它也可以正常工作。

所以这是某种条件字符转义问题？我通过使用一些正则表达式调整 url 设法绕过了这个问题(取消注释第 27 - 28 行)。但这真的很烦人，我不想因此而清理我的数据。

当我检查其他人的试验时，认为在每个插入值中添加一对引号会起作用。但是，当使用字符串格式时，我该如何执行此操作，并且它必须在 cursor.execute(sql, value) 之前进行？

Answer 1

经过一番努力，并得到 Parameter substitution issue #317 的 @Scratch'N'Purr 和 @msafiullah 的大力帮助，我设法让它发挥作用。这有点复杂，所以我将发布完整的文档代码:

错误原因:通过 Impyla API 出现冒号转义问题。

解决方案:使用自定义的转义函数来处理数据，并采用sql注入(inject)(Python的字符串格式化方式来替换参数)而不是标准的Python DB API，例如: cursor.execute(sql，值)。

api.py:

from flask import Flask, request, abort, Response
from flask_cors import CORS
import json
from impala.dbapi import connect
from impala.util import _escape
import sys    
from datetime import datetime
import six

app = application = Flask(__name__)
CORS(app)


conn = connect(host='datanode2', port=21050,
            user='user', database='testdb')


def parameterize(value): # by msafiullah
    if value is None:
        return "NULL"
    elif isinstance(value, six.string_types):
        return "'" + _escape(value) + "'"
    else:
        return str(value)


@app.route("/api/endpoint", methods=['POST'])
def post_data():
    if not request.json:
        abort(400)

    params = request.get_json(force=True)  # getting request data
    print(">>>>>> ", params, flush=True)

    params['log_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")

    try:
        cursor = conn.cursor()

        sql = 'INSERT INTO table ( page_title, page_url, log_time, machine, clicks, id ) VALUES ( CAST({} AS VARCHAR(64)), {}, {}, CAST({} AS VARCHAR(32)) , {}, CAST({} AS VARCHAR(32)))'\
                .format(parameterize(params['page_title']), parameterize(params['page_url']), parameterize(params['log_time']), parameterize(params['machine']), params['clicks'], parameterize(params['id']))
        print(">>>>>> " + sql, file=sys.stderr, flush=True)

        cursor.execute(sql)

        print(
            f">>>>>> Data Written Successfully", file=sys.stderr, flush=True)
        return Response(json.dumps({'success': True}), 201, mimetype="application/json")
    except Exception as e:
        print(e, file=sys.stderr, flush=True)
        return Response(json.dumps({'success': False}), 400, mimetype="application/json")


if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5008, debug=True)

req.py 与 Question 相同。

表架构:

CREATE TABLE if not exists table (
    id VARCHAR(36),
    machine VARCHAR(32),
    clicks INT,
    page_title VARCHAR(64),
    page_url STRING,
    log_time TIMESTAMP
);

Flask 的服务器输出:

>>>>>>  {'page_title': 'Home', 'page_url': 'http://123.234.345.456:30001/', 'machine': 'Mac OS', 'clicks': 16, 'id': '60cd1d79-eda7-44c2-a4ec-ffdd5d6ac3db'}
>>>>>> INSERT INTO table ( page_title, page_url, log_time, machine, clicks, id ) VALUES ( CAST('Home' AS VARCHAR(64)), 'http://123.234.345.456:30001/', '2018-12-14 17:27:29', CAST('Mac OS' AS VARCHAR(32)) , 16, CAST('60cd1d79-eda7-44c2-a4ec-ffdd5d6ac3db' AS VARCHAR(32)))
>>>>>> Data Written Successfully
127.0.0.1 - - [14/Dec/2018 17:27:29] "POST /api/endpoint HTTP/1.1" 201 -

在 Impala-shell 内，select * from table 将给出:

+----------------------------------+--------+--------------+------------+----------------------------------------------------------------------+---------------------+
| id                               | machine | clicks      | page_title | page_url                                                             | log_time            |
+----------------------------------+--------+--------------+------------+----------------------------------------------------------------------+---------------------+
| 60cd1d79-eda7-44c2-a4ec-ffdd5d6a | Mac OS | 16           | Home       | http://123.234.345.456:30001/                                        | 2018-12-14 17:27:29 |
+----------------------------------+--------+--------------+------------+----------------------------------------------------------------------+---------------------+

基本上，只有数字(例如INT类型)不需要经过parameterize()清理/转义过程。其他类型，例如 VARCHAR、CHAR、STRING、TIMESTAMP(因为冒号)应正确转义为通过 Impyla API 安全插入。