python中ht_python – 解析HTSQL时处理语法歧义

我正在编写一个语法来解析HTSQL语法,并坚持如何处理段和除法运算符的/字符重用.

described grammar并不是非常正式,所以我一直在关注Python实现的确切输出,从粗略的一瞥似乎是一个手写的解析器,而不是使用解析器生成器 – 作为参考解析器生成器我目前使用是

CL-YACC和

CL-LEX.(FWIW完整的东西

is here,虽然可能有点过时.)

由于“/ 1”被解析为'(:COLLECT(:INTEGER“1”))’,但是“/ 1/2”被解析为'(:COLLECT(:OPERATOR /) (:INTEGER“1”)(:INTEGER“2”)))’,即一个是段分隔符,另一个是分区; “/ 1 // 2”再次是'(:COLLECT(:OPERATOR /(:INTEGER“1”)(:COLLECT(:INTEGER“2”))))’.

问题是,如何在不借助切换到手动解析器的情况下在语法规范中处理这个问题?切换到不同的解析器生成器类(而不是LALR(1))会有帮助吗?

到目前为止,我已经尝试了不同的语法变体,但是对于整个语法来说,优先级是固定的这一事实也会干扰斜杠的两种解释.我尝试的另一种方法是在词法分析器中消除歧义,即以不同方式处理第一个斜杠(在每个“组”中)并返回不同的符号,例如, DIV – 然而,我找不到一个好的规则,并以某种方式怀疑它纯粹是通过查看词汇结构而存在.

最后,我很想通过完全脱离给定的解析器来解决这个问题,以使我的生活更轻松.从某种意义上说,更容易理解可预测的语法,你会认为这更令人满意吗?

图1,用于检查解析树的Python脚本:

import htsql

application = htsql.HTSQL("sqlite:///htsql_demo.sqlite")

global y

y = None

def p(string):

global y

with application:

y = htsql.core.syn.parse.parse(string)

return y

def l(name):

result = []

for c in name:

if c.isupper() and result:

result.append("-")

result.append(c)

return "".join(result)

def keyword(name):

return ":{}".format(name.upper())

def n(expression):

name = expression.__class__.__name__

name = name[:name.find("Syntax")]

return keyword(l(name))

def t(expression):

arguments = [n(expression)]

d = expression.__dict__

if "identifier" in d:

arguments.append(t(expression.identifier))

if "text" in d:

arguments.append("\"{}\"".format(expression.text))

if "symbol" in d:

if not isinstance(expression, (htsql.core.syn.syntax.ProjectSyntax, htsql.core.syn.syntax.FilterSyntax, htsql.core.syn.syntax.CollectSyntax, htsql.core.syn.syntax.DetachSyntax)):

arguments.append(expression.symbol)

if "arm" in d:

arguments.append(t(expression.arm))

if "larm" in d:

arguments.append(t(expression.larm))

if "rarm" in d:

arguments.append(t(expression.rarm))

if "arms" in d:

arguments.extend(t(x) for x in expression.arms)

if "rarms" in d:

arguments.extend(t(x) for x in expression.rarms)

return "({})".format(" ".join(arguments))

# t(p("/school"))

# '(:COLLECT (:IDENTIFIER "school"))

# t(p("/'school'"))

# '(:COLLECT (:STRING "school"))

图2,我当前的解析器,没有正确处理这个问题:

(defpackage #:cl-htsql

(:use #:cl #:alexandria #:cl-lex #:yacc)

(:import-from #:arnesi #:with-collector))

(eval-when (:compile-toplevel :load-toplevel :execute)

(defun maybe-intern (name &optional (package NIL package-p))

"If NAME is a SYMBOL, return it, otherwise INTERN it."

(cond

((symbolp name)

name)

(package-p

(intern name package))

(T

(intern name))))

(defmacro define-lexer (name &body patterns)

"Shortcut for DEFINE-STRING-LEXER."

`(define-string-lexer ,name

,@(mapcar

(lambda (pattern)

(etypecase pattern

((or symbol string)

(let ((symbol (maybe-intern pattern))

(pattern (string pattern)))

`(,pattern (return (values ',symbol ',symbol)))))

(list

(destructuring-bind (pattern &optional symbol value) pattern

(let* ((symbol (or symbol (intern pattern)))

(value (or value symbol)))

(etypecase symbol

(list

`(,pattern ,symbol))

(symbol

`(,pattern (return (values ',symbol ',value))))))))))

patterns))))

;; parser are results are to be treated immutable

(define-lexer string-lexer

/

("\\|" \|)

("\\&" &)

<=

>=

==

=

!==

!=

!~

!

~

<

>

@

("\\?" ?)

("\\." \.)

("\\(" \()

("\\)" \))

("\\+" +)

-

("\\*" *)

\:

("-?0|[1-9][0-9]*(\\.[0-9]*)?([eE][+-]?[0-9]+)?"

(return (cond

((find #\e $@)

(values 'float $@))

((find #\. $@)

(values 'decimal $@))

(T

(values 'integer $@)))))

("([^\"\\.\\?~\'=<>\\(\\)@\\|\\&/:])+" (return (values 'name $@)))

("\'([^\\\']|\\.)*?\'" (return (values 'string (string-trim "\'" $@))))

("\"([^\\\"]|\\.)*?\"" (return (values 'string (string-trim "\"" $@)))))

(define-parser *expression-parser*

(:muffle-conflicts (44 0))

(:start-symbol query)

(:terminals (|\|| #+(or)div & ! |.| ? / = != !== !~ ~ < > == <= >= \( \) + - * @ name integer decimal float string))

(:precedence ((:left @) (:left ~) (:left |.|) (:left + -) (:left * div) (:left = != == !== ~ !~ < <= > >=) (:left !) (:left &) (:left |\||) (:left ?) (:left /)))

(query

segment)

(segment

(/ segment (lambda (x y) (declare (ignore x)) (if (eq y :skip) '(:skip) `(:collect ,y))))

skip

group)

(skip

((constantly :skip)))

(group

(\( segment \) (lambda (x y z) (declare (ignore x z)) `(:group ,y)))

sieve)

(sieve

(segment ? segment (lambda (x y z) (declare (ignore y)) `(:filter ,x ,z)))

or)

(or

(segment |\|| segment (lambda (x y z) `(:operator ,y ,x ,z)))

and)

(and

(segment & segment (lambda (x y z) `(:operator ,y ,x ,z)))

not)

(not

(! segment (lambda (x y) `(:prefix ,x ,y)))

comparison)

(comparison

(segment = segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment != segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment ~ segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment !~ segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment == segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment !== segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment < segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment <= segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment > segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment >= segment (lambda (x y z) `(:operator ,y ,x ,z)))

addition)

(addition

(segment + segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment - segment (lambda (x y z) `(:operator ,y ,x ,z)))

multiplication)

(multiplication

(segment * segment (lambda (x y z) `(:operator ,y ,x ,z)))

(segment / segment (lambda (x y z) (declare (ignore y)) `(:operator / ,x ,z)))

composition)

(composition

(segment |.| segment (lambda (x y z) (declare (ignore y)) `(:compose ,x ,z)))

attach)

(attach

(segment @ segment (lambda (x y z) (declare (ignore y)) `(:attach ,x ,z)))

detach)

(detach

(@ segment (lambda (x y) (declare (ignore x)) `(:detach ,y)))

term)

(term

(name (lambda (x) `(:identifier ,x)))

(string (lambda (x) `(:string ,x)))

(number (lambda (x) `(:integer ,x)))

(integer (lambda (x) `(:integer ,x)))

(decimal (lambda (x) `(:decimal ,x)))

(float (lambda (x) `(:float ,x)))))

(defun make-lexer-for-source (source)

"Make a lexer for the SOURCE, either a STRING or a STREAM."

(etypecase source

(string (string-lexer source))

(stream

(flet ((ignore (c)

(declare (ignore c))))

(stream-lexer #'read-line #'string-lexer #'ignore #'ignore)))))

(defun lex-source (source)

"Debug helper to lex a SOURCE into a list of tokens."

(let ((lexer (make-lexer-for-source source)))

(loop

for (x y) = (multiple-value-list (funcall lexer))

while x

collect (list x y))))

(define-condition htsql-parse-error (simple-error) ())

(defun translate-yacc-error (error)

(make-condition

'htsql-parse-error

:format-control "Couldn't parse HTSQL query: ~A."

:format-arguments (list error)))

(defun parse-htsql-query (source)

"Parse SOURCE into a syntax tree. The SOURCE may be either a STRING or

a STREAM."

(handler-case

(parse-with-lexer

(make-lexer-for-source source)

*expression-parser*)

(yacc-parse-error (error)

(error (translate-yacc-error error)))))

;; > (parse-htsql-query "/1/")

;; (:OPERATOR / (:COLLECT (:INTEGER "1")) :SKIP)

;; > (parse-htsql-query "/1/2")

;; (:OPERATOR / (:COLLECT (:INTEGER "1")) (:INTEGER "2"))

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值