Skip to content

add more specific error for invalid identifier start chars #421

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

Merged
c42f merged 2 commits into from
Jul 30, 2024
+8 −3
Merged

add more specific error for invalid identifier start chars #421

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
24591de
add more specific error for invalid identifier start chars
JeffBezanson Feb 25, 2024
1d144bd
Tweak ErrorIdentifierStart message + add diagnostics test.
c42f Jul 23, 2024
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
2 changes: 2 additions & 0 deletions src/kinds.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,6 +212,7 @@ register_kinds!(JuliaSyntax, 0, [
"ErrorOverLongCharacter"
"ErrorInvalidUTF8"
"ErrorInvisibleChar"
"ErrorIdentifierStart"
"ErrorUnknownCharacter"
"ErrorBidiFormatting"
# Generic error
Expand Down Expand Up @@ -1175,6 +1176,7 @@ const _token_error_descriptions = Dict{Kind, String}(
K"ErrorOverLongCharacter"=>"character literal contains multiple characters",
K"ErrorInvalidUTF8"=>"invalid UTF-8 sequence",
K"ErrorInvisibleChar"=>"invisible character",
K"ErrorIdentifierStart" => "identifier cannot begin with character",
K"ErrorUnknownCharacter"=>"unknown unicode character",
K"ErrorBidiFormatting"=>"unbalanced bidirectional unicode formatting",
K"ErrorInvalidOperator" => "invalid operator",
Expand Down
2 changes: 1 addition & 1 deletion src/parse_stream.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1051,7 +1051,7 @@ function validate_tokens(stream::ParseStream)
elseif is_error(k) && k != K"error"
# Emit messages for non-generic token errors
tokstr = String(txtbuf[tokrange])
msg = if k in KSet"ErrorInvisibleChar ErrorUnknownCharacter"
msg = if k in KSet"ErrorInvisibleChar ErrorUnknownCharacter ErrorIdentifierStart"
"$(_token_error_descriptions[k]) $(repr(tokstr[1]))"
elseif k in KSet"ErrorInvalidUTF8 ErrorBidiFormatting"
"$(_token_error_descriptions[k]) $(repr(tokstr))"
Expand Down
5 changes: 3 additions & 2 deletions src/tokenize.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -538,8 +538,9 @@ function _next_token(l::Lexer, c)
return emit(l, k)
else
emit(l,
!isvalid(c) ? K"ErrorInvalidUTF8" :
is_invisible_char(c) ? K"ErrorInvisibleChar" :
!isvalid(c) ? K"ErrorInvalidUTF8" :
is_invisible_char(c) ? K"ErrorInvisibleChar" :
is_identifier_char(c) ? K"ErrorIdentifierStart" :
K"ErrorUnknownCharacter")
end
end
Expand Down
1 change: 1 addition & 0 deletions test/diagnostics.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ end
@test diagnostic("a$(c)b") ==
Diagnostic(2, 1+sizeof(string(c)), :error, "invisible character $(repr(c))")
end
@test diagnostic("₁") == Diagnostic(1, 3, :error, "identifier cannot begin with character '₁'")
@test diagnostic(":⥻") == Diagnostic(2, 4, :error, "unknown unicode character '⥻'")

@test diagnostic("\"X \u202a X\"") == Diagnostic(2, 8, :error, "unbalanced bidirectional unicode formatting \"X \\u202a X\"")
Expand Down
1 change: 1 addition & 0 deletions test/tokenize.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1009,6 +1009,7 @@ end

@testset "invalid UTF-8 characters" begin
@test onlytok("\x00") == K"ErrorUnknownCharacter"
@test onlytok("₁") == K"ErrorIdentifierStart"

bad_chars = [
first("\xe2") # malformed
Expand Down