假设我有一个像这样的python-rply代码(摘自here):
from rply import ParserGenerator, LexerGenerator
from rply.token import BaseBox
lg = LexerGenerator()
# Add takes a rule name, and a regular expression that defines the rule.
lg.add("PLUS", r"\+")
lg.add("MINUS", r"-")
lg.add("NUMBER", r"\d+")
lg.ignore(r"\s+")
# This is a list of the token names. precedence is an optional list of
# tuples which specifies order of operation for avoiding ambiguity.
# precedence must be one of "left", "right", "nonassoc".
# cache_id is an optional string which specifies an ID to use for
# caching. It should *always* be safe to use caching,
# RPly will automatically detect when your grammar is
# changed and refresh the cache for you.
pg = ParserGenerator(["NUMBER", "PLUS", "MINUS"],
precedence=[("left", ['PLUS', 'MINUS'])], cache_id="myparser")
@pg.production("main : expr")
def main(p):
# p is a list, of each of the pieces on the right hand side of the
# grammar rule
return p[0]
@pg.production("expr : expr PLUS expr")
@pg.production("expr : expr MINUS expr")
def expr_op(p):
lhs = p[0].getint()
rhs = p[2].getint()
if p[1].gettokentype() == "PLUS":
return BoxInt(lhs + rhs)
elif p[1].gettokentype() == "MINUS":
return BoxInt(lhs - rhs)
else:
raise AssertionError("This is impossible, abort the time machine!")
@pg.production("expr : NUMBER")
def expr_num(p):
return BoxInt(int(p[0].getstr()))
lexer = lg.build()
parser = pg.build()
class BoxInt(BaseBox):
def __init__(self, value):
self.value = value
def getint(self):
return self.value
这是一个简单的代码,因此当您键入以下内容时:
parser.parse(lexer.lex("1 + 3"))
它将执行,为您提供4
作为输出和答案。这是一个有效的代码,但仍需要改进。调用@pg.production
进行加法和减法的代码部分效率不高;我的意思是,如果您要添加更多的运算符,它将变得非常局促。有没有一种好的方法可以使该零件的非狭窄版本看起来像这样:
@pg.production("expr : expr PLUS expr")
def plus(p):
lhs = p[0].getint()
rhs = p[2].getint()
if p[1].gettokentype() == "PLUS":
return BoxInt(lhs + rhs)
else:
raise AssertionError("This is impossible, abort the time machine!")
@pg.production("expr : expr MINUS expr")
def minus(p):
lhs = p[0].getint()
rhs = p[2].getint()
if p[1].gettokentype() == "MINUS":
return BoxInt(lhs - rhs)
else:
raise AssertionError("This is impossible, abort the time machine!")
答案 0 :(得分:1)
如果您拆分功能以使每个产品都有其自己的功能-这实际上是最佳实践-那么,绝对没有必要检查操作符的令牌类型。您知道这是什么原因,因为解析器的逻辑意味着仅在与生产匹配时调用该函数。
因此,您可以编写紧凑的代码:
[
{
addresses=address,
bestName=null,
reasonListed=null,
countryDetails=country,
matchReAlert=null,
phones=null,
resultDate=0,
acceptListID=acceptlist,
bestNameScore=0,
error=null,
bestCountry=null,
trueMatch=null,
doBs=null,
file={
published=3123123213,
build=111,
name=file1,
id=456,
type=txt,
custom=true
},
entityDetails={
akAs=null,
addresses={
entityAddress=[
{
stateProvinceDistrict=null,
country=India,
comments=null,
city=Hyderabad,
postalCode=500001,
street1=null,
id=0,
street2=null,
type=null
}
]
},
dateListed=null,
comments=null,
gender=MALE,
listReferenceNumber=null,
reasonListed=reason,
entityType=IND,
additionalInfo={
entityAdditionalInfo=[
{
comments=null,
id=0,
type=DOB,
value=12-12-1989
}
]
},
name=null,
iDs=null,
phones=null
},
entityName=In,
falsePositive=null,
gatewayOFACScreeningIndicatorMatch=null,
previousResultID=null,
conflicts=null,
iDs=null,
entityScore=0,
id=456,
addedToAcceptList=true,
matchXML=null,
secondaryOFACScreeningIndicatorMatch=null,
entityUniqueID=null,
autoFalsePositive=null,
bestCountryScore=null,
citizenships=null,
checkSum=0,
addressName=true,
ofacInfo=null,
bestAddressIsPartial=null,
bestCountryType=null
},
{
addresses=address,
bestName=null,
reasonListed=null,
countryDetails=country,
matchReAlert=null,
phones=null,
resultDate=0,
acceptListID=acceptlist,
bestNameScore=0,
error=null,
bestCountry=null,
trueMatch=null,
doBs=null,
file={
published=3123123213,
build=111,
name=file1,
id=789,
type=txt,
custom=true
},
entityDetails={
akAs=null,
addresses={
entityAddress=[
{
stateProvinceDistrict=null,
country=India,
comments=null,
city=Hyderabad,
postalCode=500001,
street1=null,
id=0,
street2=null,
type=null
}
]
},
dateListed=null,
comments=null,
gender=MALE,
listReferenceNumber=null,
reasonListed=reason,
entityType=IND,
additionalInfo={
entityAdditionalInfo=[
{
comments=null,
id=0,
type=DOB,
value=12-12-1989
}
]
},
name=null,
iDs=null,
phones=null
},
entityName=In,
falsePositive=null,
gatewayOFACScreeningIndicatorMatch=null,
previousResultID=null,
conflicts=null,
iDs=null,
entityScore=0,
id=789,
addedToAcceptList=true,
matchXML=null,
secondaryOFACScreeningIndicatorMatch=null,
entityUniqueID=null,
autoFalsePositive=null,
bestCountryScore=null,
citizenships=null,
checkSum=0,
addressName=true,
ofacInfo=null,
bestAddressIsPartial=null,
bestCountryType=null
},
{
addresses=address,
bestName=null,
reasonListed=null,
countryDetails=country,
matchReAlert=null,
phones=null,
resultDate=0,
acceptListID=acceptlist,
bestNameScore=0,
error=null,
bestCountry=null,
trueMatch=null,
doBs=null,
file={
published=3123123213,
build=111,
name=file1,
id=123,
type=txt,
custom=true
},
entityDetails={
akAs=null,
addresses={
entityAddress=[
{
stateProvinceDistrict=null,
country=India,
comments=null,
city=Hyderabad,
postalCode=500001,
street1=null,
id=0,
street2=null,
type=null
}
]
},
dateListed=null,
comments=null,
gender=MALE,
listReferenceNumber=null,
reasonListed=reason,
entityType=IND,
additionalInfo={
entityAdditionalInfo=[
{
comments=null,
id=0,
type=DOB,
value=12-12-1989
}
]
},
name=null,
iDs=null,
phones=null
},
entityName=In,
falsePositive=null,
gatewayOFACScreeningIndicatorMatch=null,
previousResultID=null,
conflicts=null,
iDs=null,
entityScore=0,
id=123,
addedToAcceptList=true,
matchXML=null,
secondaryOFACScreeningIndicatorMatch=null,
entityUniqueID=null,
autoFalsePositive=null,
bestCountryScore=null,
citizenships=null,
checkSum=0,
addressName=true,
ofacInfo=null,
bestAddressIsPartial=null,
bestCountryType=null
}
]