Skip to content

Fold RawToken into Token and remove the old Token. #16

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 1 commit into from
Feb 24, 2022
Merged

Fold RawToken into Token and remove the old Token. #16

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
4 changes: 1 addition & 3 deletions Tokenize/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,11 +37,9 @@ Each `Token` is represented by where it starts and ends, what string it contains
The API for a `Token` (non exported from the `Tokenize.Tokens` module) is.

```julia
startpos(t)::Tuple{Int, Int} # row and column where the token start
endpos(t)::Tuple{Int, Int} # row and column where the token ends
startbyte(T)::Int # byte offset where the token start
endbyte(t)::Int # byte offset where the token ends
untokenize(t)::String # string representation of the token
untokenize(t, str)::String # string representation of the token
kind(t)::Token.Kind # kind of the token
exactkind(t)::Token.Kind # exact kind of the token
```
Expand Down
6 changes: 2 additions & 4 deletions Tokenize/benchmark/lex_base.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ using Tokenize
using BenchmarkTools
using Printf

function speed_test(::Type{T}=Tokenize.Tokens.Token) where T <: Tokenize.Tokens.AbstractToken
function speed_test()
tot_files = 0
tot_tokens = 0
tot_errors = 0
Expand All @@ -14,7 +14,7 @@ function speed_test(::Type{T}=Tokenize.Tokens.Token) where T <: Tokenize.Tokens.
tot_files += 1
file = joinpath(root, file)
str = read(file, String)::String
l = tokenize(str, T)
l = tokenize(str)
while !Tokenize.Lexers.eof(l)
t = Tokenize.Lexers.next_token(l)
tot_tokens += 1
Expand All @@ -31,8 +31,6 @@ end

tot_files, tot_tokens, tot_errors = speed_test()
tot_time_token = @belapsed speed_test()
tot_time_rawtoken = @belapsed speed_test(Tokenize.Tokens.RawToken)
println("Lexed ", tot_files, " files, with a total of ", tot_tokens,
" tokens with ", tot_errors, " errors")
println("Time Token: ", @sprintf("%3.4f", tot_time_token), " seconds")
println("Time RawToken: ", @sprintf("%3.4f", tot_time_rawtoken), " seconds")
108 changes: 43 additions & 65 deletions Tokenize/src/_precompile.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,87 +8,65 @@ function _precompile_()
precompile(Tokenize.Tokens.Token, (Tokenize.Tokens.Kind,Tuple{Int,Int},Tuple{Int,Int},Int,Int,String))
precompile(Tokenize.Tokens.Token, ())
precompile(Tokenize.Tokens.kind, (Tokenize.Tokens.Token,))
precompile(Tokenize.Tokens.startpos, (Tokenize.Tokens.Token,))
precompile(Tokenize.Tokens.endpos, (Tokenize.Tokens.Token,))
precompile(Tokenize.Tokens.untokenize, (Tokenize.Tokens.Token,))
precompile(Tokenize.Tokens.untokenize, (Tokenize.Tokens.RawToken,String))
precompile(Tokenize.Tokens.untokenize, (Array{Tokenize.Tokens.Token, 1},))
precompile(Tokenize.Tokens.untokenize, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))

precompile(Tokenize.Lexers.is_cat_id_start, (Char, Int32,))
precompile(Tokenize.Lexers.is_identifier_char, (Char,))
precompile(Tokenize.Lexers.is_identifier_start_char, (Char,))
precompile(Tokenize.Lexers.peekchar, (GenericIOBuffer{Array{UInt8, 1}},))
precompile(Tokenize.Lexers.dpeekchar, (GenericIOBuffer{Array{UInt8, 1}},))
precompile(Tokenize.Lexers.readchar, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.readchar, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken},))
precompile(Tokenize.Lexers.next_token, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.readchar, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.next_token, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))

precompile(Tokenize.Lexers.ishex, (Char,))
precompile(Tokenize.Lexers.isbinary, (Char,))
precompile(Tokenize.Lexers.isoctal, (Char,))
precompile(Tokenize.Lexers.iswhitespace, (Char,))
precompile(Tokenize.Lexers.Lexer, (String,))
precompile(Tokenize.Lexers.Lexer, (String,Type{Tokenize.Tokens.Token}))
precompile(Tokenize.Lexers.Lexer, (String,Type{Tokenize.Tokens.RawToken}))
precompile(Tokenize.Lexers.Lexer, (GenericIOBuffer{Array{UInt8, 1}},Type{Tokenize.Tokens.Token}))
precompile(Tokenize.Lexers.Lexer, (GenericIOBuffer{Array{UInt8, 1}},Type{Tokenize.Tokens.RawToken}))
precompile(Tokenize.Lexers.Lexer, (GenericIOBuffer{Array{UInt8, 1}},))
precompile(Tokenize.Lexers.tokenize, (String,))

precompile(Tokenize.Lexers.iterate, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.iterate, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken},))
precompile(Tokenize.Lexers.iterate, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token}, Bool,))
precompile(Tokenize.Lexers.iterate, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken}, Bool,))
precompile(Tokenize.Lexers.iterate, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token}, Bool,))
precompile(Tokenize.Lexers.iterate, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken}, Bool,))
precompile(Tokenize.Lexers.startpos, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.startpos, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken},))
precompile(Tokenize.Lexers.startpos!, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},Int))
precompile(Tokenize.Lexers.startpos!, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken},Int))
precompile(Tokenize.Lexers.start_token!, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.start_token!, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken},))
precompile(Tokenize.Lexers.iterate, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, Bool,))
precompile(Tokenize.Lexers.iterate, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, Bool,))
precompile(Tokenize.Lexers.startpos, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.startpos!, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},Int))
precompile(Tokenize.Lexers.start_token!, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))

precompile(Tokenize.Lexers.lex_greater, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_prime, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_digit, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},Tokenize.Tokens.Kind))
precompile(Tokenize.Lexers.lex_identifier, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, Char,))
precompile(Tokenize.Lexers.lex_less, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_forwardslash, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_minus, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_xor, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_equal, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_bar, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_quote, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_plus, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_dot, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_exclaim, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_colon, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_percent, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_comment, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_comment, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},Bool))
precompile(Tokenize.Lexers.lex_division, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_circumflex, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_backslash, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_star, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))
precompile(Tokenize.Lexers.lex_amper, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},))

precompile(Tokenize.Lexers.lex_whitespace, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},Char))

precompile(Tokenize.Lexers.lex_greater, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_prime, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_digit, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},Tokenize.Tokens.Kind))
precompile(Tokenize.Lexers.lex_identifier, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token}, Char,))
precompile(Tokenize.Lexers.lex_less, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_forwardslash, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_minus, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_xor, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_equal, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_bar, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_quote, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_plus, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_dot, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_exclaim, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_colon, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_percent, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_comment, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_comment, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},Bool))
precompile(Tokenize.Lexers.lex_division, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_circumflex, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_backslash, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_star, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))
precompile(Tokenize.Lexers.lex_amper, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))

precompile(Tokenize.Lexers.lex_whitespace, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},))

precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token}, Char,))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token}, String,))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},typeof( Base.isdigit),))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},typeof( Tokenize.Lexers.iswhitespace),))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},typeof( Tokenize.Lexers.is_identifier_char),))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token},typeof(Tokenize.Lexers.ishex),))
precompile(Tokenize.Lexers.accept_batch, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token}, typeof(Tokenize.Lexers.iswhitespace),))
precompile(Tokenize.Lexers.accept_batch, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.Token}, typeof(Tokenize.Lexers.isdigit),))

precompile(Tokenize.Lexers.accept_batch, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken}, typeof(Tokenize.Lexers.iswhitespace),))
precompile(Tokenize.Lexers.accept_batch, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken}, typeof(Tokenize.Lexers.isdigit),))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}},Tokenize.Tokens.RawToken}, Char,))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, Char,))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, String,))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},typeof( Base.isdigit),))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},typeof( Tokenize.Lexers.iswhitespace),))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},typeof( Tokenize.Lexers.is_identifier_char),))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}},typeof(Tokenize.Lexers.ishex),))
precompile(Tokenize.Lexers.accept_batch, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, typeof(Tokenize.Lexers.iswhitespace),))
precompile(Tokenize.Lexers.accept_batch, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, typeof(Tokenize.Lexers.isdigit),))

precompile(Tokenize.Lexers.accept_batch, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, typeof(Tokenize.Lexers.iswhitespace),))
precompile(Tokenize.Lexers.accept_batch, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, typeof(Tokenize.Lexers.isdigit),))
precompile(Tokenize.Lexers.accept, (Tokenize.Lexers.Lexer{GenericIOBuffer{Array{UInt8, 1}}}, Char,))

precompile(Tokenize.Lexers.readchar, (GenericIOBuffer{Array{UInt8, 1}},))
end
Loading