Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

AST: parse a.b as (. a b) #325

Merged
merged 1 commit into from
Jul 8, 2023
Merged

AST: parse a.b as (. a b) #325

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/src/reference.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,7 @@ class of tokenization errors and lets the parser deal with them.

### Improvements for AST inconsistencies

* Field access syntax like `a.b` is parsed as `(. a b)` rather than `(. a (quote b))` to avoid the inconsistency between this and actual quoted syntax literals like `:(b)` and `quote b end` ([#342](https://github.com/JuliaLang/JuliaSyntax.jl/issues/324))
* Dotted call syntax like `f.(a,b)` and `a .+ b` has been made consistent with the `K"dotcall"` head (#90)
* Standalone dotted operators are always parsed as `(. op)`. For example `.*(x,y)` is parsed as `(call (. *) x y)` (#240)
* The `K"="` kind is used for keyword syntax rather than `kw`, to avoid various inconsistencies and ambiguities (#103)
Expand Down
15 changes: 11 additions & 4 deletions src/expr.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,10 +259,17 @@ function _internal_node_to_Expr(source, srcrange, head, childranges, childheads,
args[1] = Symbol(".", args[1])
end
end
elseif k == K"." && length(args) == 1 && is_operator(childheads[1])
# Hack: Here we preserve the head of the operator to determine whether
# we need to coalesce it with the dot into a single symbol later on.
args[1] = (childheads[1], args[1])
elseif k == K"."
if length(args) == 2
a2 = args[2]
if !@isexpr(a2, :quote) && !(a2 isa QuoteNode)
args[2] = QuoteNode(a2)
end
elseif length(args) == 1 && is_operator(childheads[1])
# Hack: Here we preserve the head of the operator to determine whether
# we need to coalesce it with the dot into a single symbol later on.
args[1] = (childheads[1], args[1])
end
elseif k == K"ref" || k == K"curly"
# Move parameters blocks to args[2]
_reorder_parameters!(args, 2)
Expand Down
66 changes: 29 additions & 37 deletions src/parser.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1437,7 +1437,7 @@ end
# * Adjoint suffix like a'
# * String macros like a"str" b"""str""" c`str` d```str```
#
# f(a).g(b) ==> (call (. (call f a) (quote g)) b)
# f(a).g(b) ==> (call (. (call f a) g) b)
#
# flisp: parse-call-chain, parse-call-with-initial-ex
function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
Expand All @@ -1448,7 +1448,7 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
end
# source range of the @-prefixed part of a macro
macro_atname_range = nothing
# $A.@x ==> (macrocall (. ($ A) (quote @x)))
# $A.@x ==> (macrocall (. ($ A) @x))
maybe_strmac = true
# We record the last component of chains of dot-separated identifiers so we
# know which identifier was the macro name.
Expand All @@ -1470,22 +1470,22 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
# [@foo x] ==> (vect (macrocall @foo x))
# [@foo] ==> (vect (macrocall @foo))
# @var"#" a ==> (macrocall (var @#) a)
# A.@x y ==> (macrocall (. A (quote @x)) y)
# A.@var"#" a ==> (macrocall (. A (quote (var @#))) a)
# A.@x y ==> (macrocall (. A @x) y)
# A.@var"#" a ==> (macrocall (. A (var @#)) a)
# @+x y ==> (macrocall @+ x y)
# A.@.x ==> (macrocall (. A (quote @.)) x)
# A.@.x ==> (macrocall (. A @.) x)
fix_macro_name_kind!(ps, macro_name_position)
let ps = with_space_sensitive(ps)
# Space separated macro arguments
# A.@foo a b ==> (macrocall (. A (quote @foo)) a b)
# @A.foo a b ==> (macrocall (. A (quote @foo)) a b)
# A.@foo a b ==> (macrocall (. A @foo) a b)
# @A.foo a b ==> (macrocall (. A @foo) a b)
n_args = parse_space_separated_exprs(ps)
is_doc_macro = peek_behind(ps, macro_name_position).orig_kind == K"doc"
if is_doc_macro && n_args == 1
# Parse extended @doc args on next line
# @doc x\ny ==> (macrocall @doc x y)
# A.@doc x\ny ==> (macrocall (. A (quote @doc)) doc x y)
# @A.doc x\ny ==> (macrocall (. A (quote @doc)) doc x y)
# A.@doc x\ny ==> (macrocall (. A @doc) doc x y)
# @A.doc x\ny ==> (macrocall (. A @doc) doc x y)
# @doc x y\nz ==> (macrocall @doc x y)
#
# Excluded cases
Expand Down Expand Up @@ -1518,8 +1518,8 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
end
if is_macrocall
# @x(a, b) ==> (macrocall-p @x a b)
# A.@x(y) ==> (macrocall-p (. A (quote @x)) y)
# A.@x(y).z ==> (. (macrocall-p (. A (quote @x)) y) (quote z))
# A.@x(y) ==> (macrocall-p (. A @x) y)
# A.@x(y).z ==> (. (macrocall-p (. A @x) y) z)
fix_macro_name_kind!(ps, macro_name_position)
is_macrocall = false
macro_atname_range = nothing
Expand All @@ -1535,8 +1535,8 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
# @S[a,b] ==> (macrocall @S (vect a b))
# @S[a b] ==> (macrocall @S (hcat a b))
# @S[a; b] ==> (macrocall @S (vcat a b))
# A.@S[a] ==> (macrocall (. A (quote @S)) (vect a))
# @S[a].b ==> (. (macrocall @S (vect a)) (quote b))
# A.@S[a] ==> (macrocall (. A @S) (vect a))
# @S[a].b ==> (. (macrocall @S (vect a)) b)
#v1.7: @S[a ;; b] ==> (macrocall @S (ncat-2 a b))
#v1.6: @S[a ;; b] ==> (macrocall @S (error (ncat-2 a b)))
fix_macro_name_kind!(ps, macro_name_position)
Expand Down Expand Up @@ -1565,14 +1565,14 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
check_ncat_compat(ps, mark, ckind)
end
elseif k == K"."
# x .y ==> (. x (error-t) (quote y))
# x .y ==> (. x (error-t) y)
bump_disallowed_space(ps)
emark = position(ps)
if !isnothing(macro_atname_range)
# Allow `@` in macrocall only in first and last position
# A.B.@x ==> (macrocall (. (. A (quote B)) (quote @x)))
# @A.B.x ==> (macrocall (. (. A (quote B)) (quote @x)))
# A.@B.x ==> (macrocall (. (. A (error-t) B) (quote @x)))
# A.B.@x ==> (macrocall (. (. A B) @x))
# @A.B.x ==> (macrocall (. (. A B) @x))
# A.@B.x ==> (macrocall (. (. A B (error-t)) @x))
emit_diagnostic(ps, macro_atname_range...,
error="`@` must appear on first or last macro name component")
bump(ps, TRIVIA_FLAG, error="Unexpected `.` after macro name")
Expand Down Expand Up @@ -1603,28 +1603,23 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
emit(ps, m, K"quote", COLON_QUOTE)
emit(ps, mark, K".")
elseif k == K"$"
# f.$x ==> (. f (inert ($ x)))
# f.$(x+y) ==> (. f (inert ($ (call + x y))))
# A.$B.@x ==> (macrocall (. (. A (inert ($ B))) (quote @x)))
# @A.$x a ==> (macrocall (. A (inert (error x))) a)
# f.$x ==> (. f ($ x))
# f.$(x+y) ==> (. f ($ (call + x y)))
# A.$B.@x ==> (macrocall (. (. A ($ B)) @x))
# @A.$x a ==> (macrocall (. A (error x)) a)
m = position(ps)
bump(ps, TRIVIA_FLAG)
parse_atom(ps)
emit(ps, m, K"$")
macro_name_position = position(ps)
# We need `inert` rather than `quote` here for subtle reasons:
# We need the expression expander to "see through" the quote
# around the `$x` in `:(f.$x)`, so that the `$x` is expanded
# even though it's double quoted.
emit(ps, m, K"inert")
emit(ps, mark, K".")
elseif k == K"@"
# A macro call after some prefix A has been consumed
# A.@x ==> (macrocall (. A (quote @x)))
# A.@x a ==> (macrocall (. A (quote @x)) a)
# A.@x ==> (macrocall (. A @x))
# A.@x a ==> (macrocall (. A @x) a)
m = position(ps)
if is_macrocall
# @A.B.@x a ==> (macrocall (. (. A (quote B)) (quote (error-t) @x)) a)
# @A.B.@x a ==> (macrocall (. (. A B) (error-t) @x) a)
bump(ps, TRIVIA_FLAG, error="repeated `@` in macro module path")
else
bump(ps, TRIVIA_FLAG)
Expand All @@ -1633,7 +1628,6 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
parse_macro_name(ps)
macro_name_position = position(ps)
macro_atname_range = (m, position(ps))
emit(ps, m, K"quote")
emit(ps, mark, K".")
elseif k == K"'"
# TODO: Reclaim dotted postfix operators :-)
Expand All @@ -1643,12 +1637,10 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
error="the .' operator for transpose is discontinued")
else
# Field/property syntax
# f.x.y ==> (. (. f (quote x)) (quote y))
m = position(ps)
# f.x.y ==> (. (. f x) y)
parse_atom(ps, false)
macro_name_position = position(ps)
maybe_strmac_1 = true
emit(ps, m, K"quote")
emit(ps, mark, K".")
end
elseif k == K"'" && !preceding_whitespace(t)
Expand All @@ -1665,8 +1657,8 @@ function parse_call_chain(ps::ParseState, mark, is_macrocall=false)
parse_call_arglist(ps, K"}")
if is_macrocall
# @S{a,b} ==> (macrocall S (braces a b))
# A.@S{a} ==> (macrocall (. A (quote @S)) (braces a))
# @S{a}.b ==> (. (macrocall @S (braces a)) (quote b))
# A.@S{a} ==> (macrocall (. A @S) (braces a))
# @S{a}.b ==> (. (macrocall @S (braces a)) b)
fix_macro_name_kind!(ps, macro_name_position)
emit(ps, m, K"braces")
emit(ps, mark, K"macrocall")
Expand Down Expand Up @@ -2118,7 +2110,7 @@ function parse_function_signature(ps::ParseState, is_function::Bool)
# function ()(x) end ==> (function (call (tuple-p) x) (block))
emit(ps, mark, K"tuple", PARENS_FLAG)
else
# function (A).f() end ==> (function (call (. (parens A) (quote f))) (block))
# function (A).f() end ==> (function (call (. (parens A) f)) (block))
# function (:)() end ==> (function (call (parens :)) (block))
# function (x::T)() end ==> (function (call (parens (::-i x T))) (block))
# function (::T)() end ==> (function (call (parens (::-pre T))) (block))
Expand Down Expand Up @@ -2147,7 +2139,7 @@ function parse_function_signature(ps::ParseState, is_function::Bool)
# Parse function argument list
# function f(x,y) end ==> (function (call f x y) (block))
# function f{T}() end ==> (function (call (curly f T)) (block))
# function A.f() end ==> (function (call (. A (quote f))) (block))
# function A.f() end ==> (function (call (. A f)) (block))
parse_call_chain(ps, mark)
if peek_behind(ps).kind != K"call"
# function f body end ==> (function (error f) (block body))
Expand Down
13 changes: 10 additions & 3 deletions test/expr.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,6 @@
# Compatibility hack for VERSION >= v"1.4"
# https://github.com/JuliaLang/julia/pull/34077
@test parseatom(":true") == Expr(:quote, true)

# Handling of K"inert"
@test parsestmt("a.\$b") == Expr(:., :a, QuoteNode(Expr(:$, :b)))
end

@testset "Line numbers" begin
Expand Down Expand Up @@ -386,6 +383,16 @@
Expr(:tuple, Expr(:parameters, Expr(:kw, :a, 1)))
end

@testset "Field access syntax" begin
@test parsestmt("a.b") == Expr(:., :a, QuoteNode(:b))
@test parsestmt("a.\$b") == Expr(:., :a, QuoteNode(Expr(:$, :b)))
@test parsestmt("a.:b") == Expr(:., :a, QuoteNode(:b))
@test parsestmt("a.@b x") == Expr(:macrocall,
Expr(:., :a, QuoteNode(Symbol("@b"))),
LineNumberNode(1),
:x)
end

@testset "dotcall / dotted operators" begin
@test parsestmt("f.(x,y)") == Expr(:., :f, Expr(:tuple, :x, :y))
@test parsestmt("f.(x=1)") == Expr(:., :f, Expr(:tuple, Expr(:kw, :x, 1)))
Expand Down
60 changes: 30 additions & 30 deletions test/parser.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -312,8 +312,8 @@ tests = [
"\$f(x)" => "(call (\$ f) x)"
".&(x,y)" => "(call (. &) x y)"
# parse_call_chain
"f(a).g(b)" => "(call (. (call f a) (quote g)) b)"
"\$A.@x" => "(macrocall (. (\$ A) (quote @x)))"
"f(a).g(b)" => "(call (. (call f a) g) b)"
"\$A.@x" => "(macrocall (. (\$ A) @x))"

# non-errors in space sensitive contexts
"[f (x)]" => "(hcat f (parens x))"
Expand All @@ -322,25 +322,25 @@ tests = [
"@foo a b" => "(macrocall @foo a b)"
"@foo (x)" => "(macrocall @foo (parens x))"
"@foo (x,y)" => "(macrocall @foo (tuple-p x y))"
"A.@foo a b" => "(macrocall (. A (quote @foo)) a b)"
"@A.foo a b" => "(macrocall (. A (quote @foo)) a b)"
"A.@foo a b" => "(macrocall (. A @foo) a b)"
"@A.foo a b" => "(macrocall (. A @foo) a b)"
"[@foo x]" => "(vect (macrocall @foo x))"
"[@foo]" => "(vect (macrocall @foo))"
"@var\"#\" a" => "(macrocall (var @#) a)"
"@(A) x" => "(macrocall (parens @A) x)"
"A.@x y" => "(macrocall (. A (quote @x)) y)"
"A.@var\"#\" a"=> "(macrocall (. A (quote (var @#))) a)"
"A.@x y" => "(macrocall (. A @x) y)"
"A.@var\"#\" a"=> "(macrocall (. A (var @#)) a)"
"@+x y" => "(macrocall @+ x y)"
"A.@.x" => "(macrocall (. A (quote @.)) x)"
"A.@.x" => "(macrocall (. A @.) x)"
# Macro names
"@! x" => "(macrocall @! x)"
"@.. x" => "(macrocall @.. x)"
"@\$ y" => "(macrocall @\$ y)"
"@[x] y z" => "(macrocall (error (vect x)) y z)"
# Special @doc parsing rules
"@doc x\ny" => "(macrocall @doc x y)"
"A.@doc x\ny" => "(macrocall (. A (quote @doc)) x y)"
"@A.doc x\ny" => "(macrocall (. A (quote @doc)) x y)"
"A.@doc x\ny" => "(macrocall (. A @doc) x y)"
"@A.doc x\ny" => "(macrocall (. A @doc) x y)"
"@doc x y\nz" => "(macrocall @doc x y)"
"@doc x\n\ny" => "(macrocall @doc x)"
"@doc x\nend" => "(macrocall @doc x)"
Expand All @@ -352,8 +352,8 @@ tests = [
"(a=1)()" => "(call (parens (= a 1)))"
"f (a)" => "(call f (error-t) a)"
"@x(a, b)" => "(macrocall-p @x a b)"
"A.@x(y)" => "(macrocall-p (. A (quote @x)) y)"
"A.@x(y).z" => "(. (macrocall-p (. A (quote @x)) y) (quote z))"
"A.@x(y)" => "(macrocall-p (. A @x) y)"
"A.@x(y).z" => "(. (macrocall-p (. A @x) y) z)"
# do
"f() do\nend" => "(do (call f) (tuple) (block))"
"f() do ; body end" => "(do (call f) (tuple) (block body))"
Expand All @@ -364,8 +364,8 @@ tests = [
"@S[a,b]" => "(macrocall @S (vect a b))"
"@S[a b]" => "(macrocall @S (hcat a b))"
"@S[a; b]" => "(macrocall @S (vcat a b))"
"A.@S[a]" => "(macrocall (. A (quote @S)) (vect a))"
"@S[a].b" => "(. (macrocall @S (vect a)) (quote b))"
"A.@S[a]" => "(macrocall (. A @S) (vect a))"
"@S[a].b" => "(. (macrocall @S (vect a)) b)"
((v=v"1.7",), "@S[a ;; b]") => "(macrocall @S (ncat-2 a b))"
((v=v"1.6",), "@S[a ;; b]") => "(macrocall @S (error (ncat-2 a b)))"
"a[i]" => "(ref a i)"
Expand All @@ -383,9 +383,9 @@ tests = [

# Dotted forms
# Allow `@` in macrocall only in first and last position
"A.B.@x" => "(macrocall (. (. A (quote B)) (quote @x)))"
"@A.B.x" => "(macrocall (. (. A (quote B)) (quote @x)))"
"A.@B.x" => "(macrocall (. (. A (quote B)) (error-t) (quote @x)))"
"A.B.@x" => "(macrocall (. (. A B) @x))"
"@A.B.x" => "(macrocall (. (. A B) @x))"
"A.@B.x" => "(macrocall (. (. A B) (error-t) @x))"
"@M.(x)" => "(macrocall (dotcall @M (error-t) x))"
"f.(a,b)" => "(dotcall f a b)"
"f.(a=1; b=2)" => "(dotcall f (= a 1) (parameters (= b 2)))"
Expand All @@ -395,27 +395,27 @@ tests = [
"A.:+" => "(. A (quote-: +))"
"A.:.+" => "(. A (quote-: (. +)))"
"A.: +" => "(. A (quote-: (error-t) +))"
"f.\$x" => "(. f (inert (\$ x)))"
"f.\$(x+y)" => "(. f (inert (\$ (parens (call-i x + y)))))"
"A.\$B.@x" => "(macrocall (. (. A (inert (\$ B))) (quote @x)))"
"@A.\$x a" => "(macrocall (. A (inert (error x))) a)"
"A.@x" => "(macrocall (. A (quote @x)))"
"A.@x a" => "(macrocall (. A (quote @x)) a)"
"@A.B.@x a" => "(macrocall (. (. A (quote B)) (quote (error-t) @x)) a)"
"f.\$x" => "(. f (\$ x))"
"f.\$(x+y)" => "(. f (\$ (parens (call-i x + y))))"
"A.\$B.@x" => "(macrocall (. (. A (\$ B)) @x))"
"@A.\$x a" => "(macrocall (. A (error x)) a)"
"A.@x" => "(macrocall (. A @x))"
"A.@x a" => "(macrocall (. A @x) a)"
"@A.B.@x a" => "(macrocall (. (. A B) (error-t) @x) a)"
# .' discontinued
"f.'" => "(wrapper f (error-t '))"
# Field/property syntax
"f.x.y" => "(. (. f (quote x)) (quote y))"
"x .y" => "(. x (error-t) (quote y))"
"f.x.y" => "(. (. f x) y)"
"x .y" => "(. x (error-t) y)"
# Adjoint
"f'" => "(call-post f ')"
"f'ᵀ" => "(call-post f 'ᵀ)"
# Curly calls
"S {a}" => "(curly S (error-t) a)"
"A.@S{a}" => "(macrocall (. A (quote @S)) (braces a))"
"A.@S{a}" => "(macrocall (. A @S) (braces a))"
"@S{a,b}" => "(macrocall @S (braces a b))"
"A.@S{a}" => "(macrocall (. A (quote @S)) (braces a))"
"@S{a}.b" => "(. (macrocall @S (braces a)) (quote b))"
"A.@S{a}" => "(macrocall (. A @S) (braces a))"
"@S{a}.b" => "(. (macrocall @S (braces a)) b)"
"S{a,b}" => "(curly S a b)"
# String macros
"x\"str\"" => """(macrocall @x_str (string-r "str"))"""
Expand Down Expand Up @@ -554,7 +554,7 @@ tests = [
"function (x=1) end" => "(function (tuple-p (= x 1)) (block))"
"function (;x=1) end" => "(function (tuple-p (parameters (= x 1))) (block))"
"function ()(x) end" => "(function (call (tuple-p) x) (block))"
"function (A).f() end" => "(function (call (. (parens A) (quote f))) (block))"
"function (A).f() end" => "(function (call (. (parens A) f)) (block))"
"function (:)() end" => "(function (call (parens :)) (block))"
"function (x::T)() end"=> "(function (call (parens (::-i x T))) (block))"
"function (::g(x))() end" => "(function (call (parens (::-pre (call g x)))) (block))"
Expand All @@ -575,7 +575,7 @@ tests = [
# Function argument list
"function f(x,y) end" => "(function (call f x y) (block))"
"function f{T}() end" => "(function (call (curly f T)) (block))"
"function A.f() end" => "(function (call (. A (quote f))) (block))"
"function A.f() end" => "(function (call (. A f)) (block))"
"function f body end" => "(function (error f) (block body))"
"function f()::T end" => "(function (::-i (call f) T) (block))"
"function f()::g(T) end" => "(function (::-i (call f) (call g T)) (block))"
Expand Down