python - 如何用 EBNF 表达这种格式？

Question

我有以下数据:

dbCon= {
    main = {
        database = "db1",
        hostname = "db1.serv.com",
        maxConnCount = "5",
        port = "3306",
        slaves = [
            {
                charset = "utf8",
                client = "MYSQL",
                compression = "true",
                database = "db1_a",
                hostname = "db1-a.serv.com",
                maxConnCount = "5",
                port = "3306",
            }
            {
                charset = "utf8",
                client = "MYSQL",
                compression = "true",
                database = "db1_b",
                hostname = "db1-b.serv.com",
                maxConnCount = "5",
                port = "3306",
            }
        ]
        username = "user-1"
    }
}

我尝试使用 Grako 将其转换为 JSON，但无法正确获取 EBNF 格式。这是我所拥有的:

import grako
import json

grammar_ebnf = """
    final = @:({ any } | { bracketed } | { braced });
    braced = '{' @:( { bracketed } | { braced } | { any } ) '}' ;
    bracketed = '[' @:( { braced } | { bracketed } | { any } ) ']' ;
    any = /^[^\[\{\]\}\n]+/ ;
"""

model = grako.genmodel("final", grammar_ebnf)
with open('out.txt') as f:
    ast = model.parse(f.read())
    print (json.dumps(ast, indent = 4))

但是，这只是打印出来:

[
    "dbCon = "
]

我哪里出错了？我从来没有用过Grako。我只是希望能够将其解析为可用/可访问的内容，而无需设计静态解析器以防格式发生变化。如果格式稍后发生变化，更新 EBNF 似乎比重新设计整个解析器更容易。

Answer 1

仅通过一个示例很难确定真正的语法是什么，但希望这足以让您能够完成对其的调整以处理任何奇怪的情况。

我们需要Semantics类来处理将键/值对及其列表转换为字典的操作。小心使用@:否则可以完成这项工作。

作为建议，在语法中命名规则时，请按照它们的本质(列表、字典等)而不是它们的外观(大括号、方括号)来命名。另外，一开始就把事情分成很多规则。您稍后可以随时合并它们。

#!/usr/bin/python

import grako
import json

grammar = """
final = kvpair;
kvpair = key '=' value;
key = /[^\s=]+/;
value = @:(dict | list | string) [','];
list = '[' @:{ value } ']';
string = '"' @:/[^"]*/ '"';
dict = '{' @:{ kvpair } '}';
"""

class Semantics(object):
    def kvpair(self, arg):
        key, ignore, value = arg
        return { key: value }
    def dict(self, arg):
        d = { }
        for v in arg:
            d.update(v)
        return d

model = grako.genmodel("final", grammar)

with open('out.txt') as f:
    ast = model.parse(f.read(), semantics=Semantics())
    print json.dumps(ast, indent=4)

这会产生以下输出:

{
    "dbCon": {
        "main": {
            "username": "user-1",
            "maxConnCount": "5",
            "slaves": [
                {
                    "maxConnCount": "5",
                    "hostname": "db1-a.serv.com",
                    "compression": "true",
                    "database": "db1_a",
                    "charset": "utf8",
                    "port": "3306",
                    "client": "MYSQL"
                },
                {
                    "maxConnCount": "5",
                    "hostname": "db1-b.serv.com",
                    "compression": "true",
                    "database": "db1_b",
                    "charset": "utf8",
                    "port": "3306",
                    "client": "MYSQL"
                }
            ],
            "database": "db1",
            "hostname": "db1.serv.com",
            "port": "3306"
        }
    }
}