使用pyparsing解析网络设备命令
network device command parsing with pyparsing
我正在使用 pyparsing 开发网络设备命令解析器。
我分析定义命令格式如下：
cli ::= string + (next)*
next ::= string|range|group|simple_recursive|selective_recursive|infinite_recursive|keywords
keywords ::= "WORD"
| "LINE"
| "A.B.C.D"
| "A.B.C.D/M"
| "X:X::X:X"
| "X:X::X:X/M"
| "HH:MM:SS"
| "AA:NN"
| "XX:XX:XX:XX:XX:XX"
| "MULTILINE"
inner_recur ::= next + (next)* + ("|")* | ("|" + next + (next)*)*
string ::= alphanums + "_" + "-"
range ::= "<" + nums + "-" nums + ">"
group ::= "(" + inner_recur + ")"
simple_recursive ::= "." + range
selective_recursive ::= "{" + inner_recur + "}"
infinite_recursive ::= "[" + inner_recur + "]"
并实施写入：
# string ::= alphanums + "_" + "-"
string_ = Word(alphanums + "_" + "-").setResultsName("string")
#print(string_.parseString("option82"))
# range ::= "<" + nums + "-" nums + ">"
range_ = Combine(Literal("<") + Word(nums) + Literal("-") + Word(nums) + Literal(">")).setResultsName("range")
#print(range_.parseString("<24-1004>"))
# simple_recursive ::= "." + range
simple_recursive_ = Combine(Literal(".") + range_).setResultsName("simple_recursive")
#print(simple_recursive_.parseString(".<1-60045>"))
# keywords ::= "WORD" | "LINE" | "A.B.C.D" | "A.B.C.D/M" | "X:X::X:X" | "X:X::X:X/M" | "HH:MM:SS" | "AA:NN" | "XX:XX:XX:XX:XX:XX" | "MULTILINE"
keywords_ = Keyword("X:X::X:X/M").setResultsName("X:X::X:/M") | Keyword("A.B.C.D/M").setResultsName("A.B.C.D/M") | Keyword("A.B.C.D").setResultsName("A.B.C.D") | Keyword("X:X::X:X").setResultsName("X:X::X:X") | Keyword("HH:MM:SS").setResultsName("HH:MM:SS") | Keyword("AA:NN").setResultsName("AA:NN") | Keyword("XX:XX:XX:XX:XX:XX").setResultsName("XX:XX:XX:XX:XX:XX") | Keyword("MULTILINE").setResultsName("MULTILINE") | Keyword("WORD").setResultsName("WORD") | Keyword("LINE").setResultsName("LINE")
#print(keywords_.parseString("A.B.C.D").asXML())
#next_ = Forward()
inner_recur = Forward()
# group ::= "(" + inner_recur + ")"
group_ = Combine(Literal("(") + inner_recur + Literal(")"))
# selective_recursive ::= "{" + inner_recur + "}"
selective_recursive_ = Combine(Literal("{") + inner_recur + Literal("}"))
# infinite_recursive ::= "[" + inner_recur + "]"
infinite_recursive_ = Combine(Literal("[") + inner_recur + Literal("]"))
# next ::= string|range|group|simple_recursive|selective_recursive|infinite_recursive|keywords
next_ = keywords_ | string_ | simple_recursive_ | range_ | group_ | selective_recursive_ | infinite_recursive_
# inner_recur ::= next + (next)* + ("|")* | ("|" + next + (next)*)*
inner_recur << next_ + ZeroOrMore(next_) + ZeroOrMore(Literal("|") | ZeroOrMore(Literal("|") + next_ + OneOrMore(next_)))
# cli ::= string + (next)*
cli_ = string_ + ZeroOrMore(next_)
为了测试我的解析器，我尝试输入数据
>>> test = cli_.parseString("bgp as .<1-200>")
>>> print(test)
>>> ['bgp', 'as', ['.<1-200>']]
test = cli_.parseString("bgp as <1-200> <1-255> <1-255> WORD A.B.C.D A.B.C.D/M (A|(B|C))")
print(test)
>>>
test = cli_.parseString("test (A|<1-200>|(B|{a|b|c} aaa)")
test = cli_.parseString("test (A|<1-200>|(B|{a|b|c|})|)")
解析第二个数据时，引发了无限递归。我不明白这种情况，有什么解决办法...
我期待结果：
['bgp', 'as', ['<1-200>'], ['<1-255>'], ['<1-255>'], 'WORD',
'A.B.C.D', 'A.B.C.D/M', ['A', ['B', 'C']]]
我的格式或代码有什么问题？和点被修改？
虽然您在编写代码之前用概念 BNF 术语定义语法迈出了良好的第一步，但我在理解您的语法方面遇到了一些困难。对我来说，罪魁祸首似乎是这一部分：
inner_recur ::= next + (next)* + ("|")* | ("|" + next + (next)*)*
从您发布的示例来看，您似乎正在尝试使用“|”定义某种中缀符号作为操作员。
根据您的测试，您似乎还需要在任何分组 ()、[] 或 {} 中支持多个 inner_recur 术语。
此外，请阅读文档 (https://pyparsing-docs.readthedocs.io/en/latest/pyparsing.html) 以更清楚地了解 setResultsName 和 setName 之间的区别。我很确定在你的解析器中，你一直在使用 setResultsName 但真的想要 setName。与在您真正想要 Group.
时使用 Combine 类似
最后，我使用 runTests 重写了您的测试代码，发现您在第三次测试中 () 不匹配。
这是您的解析器，其中包含这些更改：
# string ::= alphanums + "_" + "-"
string_ = Word(alphanums + "_" + "-").setResultsName("string")
#print(string_.parseString("option82"))
# range ::= "<" + nums + "-" nums + ">"
range_ = Group(Literal("<") + Word(nums) + Literal("-") + Word(nums) + Literal(">")).setResultsName("range")
#print(range_.parseString("<24-1004>"))
# simple_recursive ::= "." + range
simple_recursive_ = Group(Literal(".") + range_).setResultsName("simple_recursive")
#print(simple_recursive_.parseString(".<1-60045>"))
# keywords ::= "WORD" | "LINE" | "A.B.C.D" | "A.B.C.D/M" | "X:X::X:X" | "X:X::X:X/M" | "HH:MM:SS" | "AA:NN" | "XX:XX:XX:XX:XX:XX" | "MULTILINE"
keywords_ = Keyword("X:X::X:X/M").setResultsName("X:X::X:/M") | Keyword("A.B.C.D/M").setResultsName("A.B.C.D/M") | Keyword("A.B.C.D").setResultsName("A.B.C.D") | Keyword("X:X::X:X").setResultsName("X:X::X:X") | Keyword("HH:MM:SS").setResultsName("HH:MM:SS") | Keyword("AA:NN").setResultsName("AA:NN") | Keyword("XX:XX:XX:XX:XX:XX").setResultsName("XX:XX:XX:XX:XX:XX") | Keyword("MULTILINE").setResultsName("MULTILINE") | Keyword("WORD").setResultsName("WORD") | Keyword("LINE").setResultsName("LINE")
#print(keywords_.parseString("A.B.C.D").asXML())
#next_ = Forward()
inner_recur = Forward()
# group ::= "(" + inner_recur + ")"
group_ = Group(Literal("(") + OneOrMore(inner_recur) + Literal(")"))
# selective_recursive ::= "{" + inner_recur + "}"
selective_recursive_ = Group(Literal("{") + OneOrMore(inner_recur) + Literal("}"))
# infinite_recursive ::= "[" + inner_recur + "]"
infinite_recursive_ = Group(Literal("[") + OneOrMore(inner_recur) + Literal("]"))
# next ::= string|range|group|simple_recursive|selective_recursive|infinite_recursive|keywords
next_ = keywords_ | string_ | simple_recursive_ | range_ | group_ | selective_recursive_ | infinite_recursive_
#~ next_.setName("next_").setDebug()
# inner_recur ::= next + (next)* + ("|")* | ("|" + next + (next)*)*
#~ inner_recur <<= OneOrMore(next_) + ZeroOrMore(Literal("|")) | ZeroOrMore(Literal("|") + OneOrMore(next_))
inner_recur <<= Group(infixNotation(next_,
[
(None, 2, opAssoc.LEFT),
('|', 2, opAssoc.LEFT),
]) + Optional('|'))
# cli ::= string + (next)*
cli_ = string_ + ZeroOrMore(next_)
tests = """\
bgp as .<1-200>
bgp as <1-200> <1-255> <1-255> WORD A.B.C.D A.B.C.D/M (A|(B|C))
test (A|<1-200>|(B|{a|b|c} aaa))
test (A|<1-200>|(B|{a|b|c|})|)
"""
cli_.runTests(tests)
给出：
bgp as .<1-200>
['bgp', 'as', ['.', ['<', '1', '-', '200', '>']]]
- simple_recursive: ['.', ['<', '1', '-', '200', '>']]
- range: ['<', '1', '-', '200', '>']
- string: 'as'
bgp as <1-200> <1-255> <1-255> WORD A.B.C.D A.B.C.D/M (A|(B|C))
['bgp', 'as', ['<', '1', '-', '200', '>'], ['<', '1', '-', '255', '>'], ['<', '1', '-', '255', '>'], 'WORD', 'A.B.C.D', 'A.B.C.D/M', ['(', [['A', '|', ['(', [['B', '|', 'C']], ')']]], ')']]
- A.B.C.D: 'A.B.C.D'
- A.B.C.D/M: 'A.B.C.D/M'
- WORD: 'WORD'
- range: ['<', '1', '-', '255', '>']
- string: 'as'
test (A|<1-200>|(B|{a|b|c} aaa))
['test', ['(', [['A', '|', ['<', '1', '-', '200', '>'], '|', ['(', [['B', '|', [['{', [['a', '|', 'b', '|', 'c']], '}'], 'aaa']]], ')']]], ')']]
- string: 'test'
test (A|<1-200>|(B|{a|b|c|})|)
['test', ['(', [['A', '|', ['<', '1', '-', '200', '>'], '|', ['(', [['B', '|', ['{', [['a', '|', 'b', '|', 'c'], '|'], '}']]], ')']], '|'], ')']]
- string: 'test'
这在某些地方可能不合时宜，但我希望它能给您一些推进项目的想法。
我正在使用 pyparsing 开发网络设备命令解析器。
我分析定义命令格式如下：
cli ::= string + (next)*
next ::= string|range|group|simple_recursive|selective_recursive|infinite_recursive|keywords
keywords ::= "WORD"
| "LINE"
| "A.B.C.D"
| "A.B.C.D/M"
| "X:X::X:X"
| "X:X::X:X/M"
| "HH:MM:SS"
| "AA:NN"
| "XX:XX:XX:XX:XX:XX"
| "MULTILINE"
inner_recur ::= next + (next)* + ("|")* | ("|" + next + (next)*)*
string ::= alphanums + "_" + "-"
range ::= "<" + nums + "-" nums + ">"
group ::= "(" + inner_recur + ")"
simple_recursive ::= "." + range
selective_recursive ::= "{" + inner_recur + "}"
infinite_recursive ::= "[" + inner_recur + "]"
并实施写入：
# string ::= alphanums + "_" + "-"
string_ = Word(alphanums + "_" + "-").setResultsName("string")
#print(string_.parseString("option82"))
# range ::= "<" + nums + "-" nums + ">"
range_ = Combine(Literal("<") + Word(nums) + Literal("-") + Word(nums) + Literal(">")).setResultsName("range")
#print(range_.parseString("<24-1004>"))
# simple_recursive ::= "." + range
simple_recursive_ = Combine(Literal(".") + range_).setResultsName("simple_recursive")
#print(simple_recursive_.parseString(".<1-60045>"))
# keywords ::= "WORD" | "LINE" | "A.B.C.D" | "A.B.C.D/M" | "X:X::X:X" | "X:X::X:X/M" | "HH:MM:SS" | "AA:NN" | "XX:XX:XX:XX:XX:XX" | "MULTILINE"
keywords_ = Keyword("X:X::X:X/M").setResultsName("X:X::X:/M") | Keyword("A.B.C.D/M").setResultsName("A.B.C.D/M") | Keyword("A.B.C.D").setResultsName("A.B.C.D") | Keyword("X:X::X:X").setResultsName("X:X::X:X") | Keyword("HH:MM:SS").setResultsName("HH:MM:SS") | Keyword("AA:NN").setResultsName("AA:NN") | Keyword("XX:XX:XX:XX:XX:XX").setResultsName("XX:XX:XX:XX:XX:XX") | Keyword("MULTILINE").setResultsName("MULTILINE") | Keyword("WORD").setResultsName("WORD") | Keyword("LINE").setResultsName("LINE")
#print(keywords_.parseString("A.B.C.D").asXML())
#next_ = Forward()
inner_recur = Forward()
# group ::= "(" + inner_recur + ")"
group_ = Combine(Literal("(") + inner_recur + Literal(")"))
# selective_recursive ::= "{" + inner_recur + "}"
selective_recursive_ = Combine(Literal("{") + inner_recur + Literal("}"))
# infinite_recursive ::= "[" + inner_recur + "]"
infinite_recursive_ = Combine(Literal("[") + inner_recur + Literal("]"))
# next ::= string|range|group|simple_recursive|selective_recursive|infinite_recursive|keywords
next_ = keywords_ | string_ | simple_recursive_ | range_ | group_ | selective_recursive_ | infinite_recursive_
# inner_recur ::= next + (next)* + ("|")* | ("|" + next + (next)*)*
inner_recur << next_ + ZeroOrMore(next_) + ZeroOrMore(Literal("|") | ZeroOrMore(Literal("|") + next_ + OneOrMore(next_)))
# cli ::= string + (next)*
cli_ = string_ + ZeroOrMore(next_)
为了测试我的解析器，我尝试输入数据
>>> test = cli_.parseString("bgp as .<1-200>")
>>> print(test)
>>> ['bgp', 'as', ['.<1-200>']]
test = cli_.parseString("bgp as <1-200> <1-255> <1-255> WORD A.B.C.D A.B.C.D/M (A|(B|C))")
print(test)
>>>
test = cli_.parseString("test (A|<1-200>|(B|{a|b|c} aaa)")
test = cli_.parseString("test (A|<1-200>|(B|{a|b|c|})|)")
解析第二个数据时，引发了无限递归。我不明白这种情况，有什么解决办法...
我期待结果：
['bgp', 'as', ['<1-200>'], ['<1-255>'], ['<1-255>'], 'WORD', 'A.B.C.D', 'A.B.C.D/M', ['A', ['B', 'C']]]
我的格式或代码有什么问题？和点被修改？
虽然您在编写代码之前用概念 BNF 术语定义语法迈出了良好的第一步，但我在理解您的语法方面遇到了一些困难。对我来说，罪魁祸首似乎是这一部分：
inner_recur ::= next + (next)* + ("|")* | ("|" + next + (next)*)*
从您发布的示例来看，您似乎正在尝试使用“|”定义某种中缀符号作为操作员。
根据您的测试，您似乎还需要在任何分组 ()、[] 或 {} 中支持多个 inner_recur 术语。
此外，请阅读文档 (https://pyparsing-docs.readthedocs.io/en/latest/pyparsing.html) 以更清楚地了解 setResultsName 和 setName 之间的区别。我很确定在你的解析器中，你一直在使用 setResultsName 但真的想要 setName。与在您真正想要 Group.
Combine 类似
最后，我使用 runTests 重写了您的测试代码，发现您在第三次测试中 () 不匹配。
这是您的解析器，其中包含这些更改：
# string ::= alphanums + "_" + "-"
string_ = Word(alphanums + "_" + "-").setResultsName("string")
#print(string_.parseString("option82"))
# range ::= "<" + nums + "-" nums + ">"
range_ = Group(Literal("<") + Word(nums) + Literal("-") + Word(nums) + Literal(">")).setResultsName("range")
#print(range_.parseString("<24-1004>"))
# simple_recursive ::= "." + range
simple_recursive_ = Group(Literal(".") + range_).setResultsName("simple_recursive")
#print(simple_recursive_.parseString(".<1-60045>"))
# keywords ::= "WORD" | "LINE" | "A.B.C.D" | "A.B.C.D/M" | "X:X::X:X" | "X:X::X:X/M" | "HH:MM:SS" | "AA:NN" | "XX:XX:XX:XX:XX:XX" | "MULTILINE"
keywords_ = Keyword("X:X::X:X/M").setResultsName("X:X::X:/M") | Keyword("A.B.C.D/M").setResultsName("A.B.C.D/M") | Keyword("A.B.C.D").setResultsName("A.B.C.D") | Keyword("X:X::X:X").setResultsName("X:X::X:X") | Keyword("HH:MM:SS").setResultsName("HH:MM:SS") | Keyword("AA:NN").setResultsName("AA:NN") | Keyword("XX:XX:XX:XX:XX:XX").setResultsName("XX:XX:XX:XX:XX:XX") | Keyword("MULTILINE").setResultsName("MULTILINE") | Keyword("WORD").setResultsName("WORD") | Keyword("LINE").setResultsName("LINE")
#print(keywords_.parseString("A.B.C.D").asXML())
#next_ = Forward()
inner_recur = Forward()
# group ::= "(" + inner_recur + ")"
group_ = Group(Literal("(") + OneOrMore(inner_recur) + Literal(")"))
# selective_recursive ::= "{" + inner_recur + "}"
selective_recursive_ = Group(Literal("{") + OneOrMore(inner_recur) + Literal("}"))
# infinite_recursive ::= "[" + inner_recur + "]"
infinite_recursive_ = Group(Literal("[") + OneOrMore(inner_recur) + Literal("]"))
# next ::= string|range|group|simple_recursive|selective_recursive|infinite_recursive|keywords
next_ = keywords_ | string_ | simple_recursive_ | range_ | group_ | selective_recursive_ | infinite_recursive_
#~ next_.setName("next_").setDebug()
# inner_recur ::= next + (next)* + ("|")* | ("|" + next + (next)*)*
#~ inner_recur <<= OneOrMore(next_) + ZeroOrMore(Literal("|")) | ZeroOrMore(Literal("|") + OneOrMore(next_))
inner_recur <<= Group(infixNotation(next_,
[
(None, 2, opAssoc.LEFT),
('|', 2, opAssoc.LEFT),
]) + Optional('|'))
# cli ::= string + (next)*
cli_ = string_ + ZeroOrMore(next_)
tests = """\
bgp as .<1-200>
bgp as <1-200> <1-255> <1-255> WORD A.B.C.D A.B.C.D/M (A|(B|C))
test (A|<1-200>|(B|{a|b|c} aaa))
test (A|<1-200>|(B|{a|b|c|})|)
"""
cli_.runTests(tests)
给出：
bgp as .<1-200>
['bgp', 'as', ['.', ['<', '1', '-', '200', '>']]]
- simple_recursive: ['.', ['<', '1', '-', '200', '>']]
- range: ['<', '1', '-', '200', '>']
- string: 'as'
bgp as <1-200> <1-255> <1-255> WORD A.B.C.D A.B.C.D/M (A|(B|C))
['bgp', 'as', ['<', '1', '-', '200', '>'], ['<', '1', '-', '255', '>'], ['<', '1', '-', '255', '>'], 'WORD', 'A.B.C.D', 'A.B.C.D/M', ['(', [['A', '|', ['(', [['B', '|', 'C']], ')']]], ')']]
- A.B.C.D: 'A.B.C.D'
- A.B.C.D/M: 'A.B.C.D/M'
- WORD: 'WORD'
- range: ['<', '1', '-', '255', '>']
- string: 'as'
test (A|<1-200>|(B|{a|b|c} aaa))
['test', ['(', [['A', '|', ['<', '1', '-', '200', '>'], '|', ['(', [['B', '|', [['{', [['a', '|', 'b', '|', 'c']], '}'], 'aaa']]], ')']]], ')']]
- string: 'test'
test (A|<1-200>|(B|{a|b|c|})|)
['test', ['(', [['A', '|', ['<', '1', '-', '200', '>'], '|', ['(', [['B', '|', ['{', [['a', '|', 'b', '|', 'c'], '|'], '}']]], ')']], '|'], ')']]
- string: 'test'
这在某些地方可能不合时宜，但我希望它能给您一些推进项目的想法。