taguniversalmachine
Help with NimbleParsec
Hi,
I am trying to define a parser for a simple grammar and I am getting hung up on something that I think is simple but I can’t figure out.
The grammar has two main structures, a definition and an invocation, of the form:
invocationname($a$b)(c<>d<>)
definitionname[(a<>b<>)($c$d)somestuff:someotherstuff]
I have the invocation one working, but for some reason even though the definition structure is very similar, I get an error that it is expecting the opening bracket, even though I am sending it.
The whole parser definition is here, and I will copy my interaction with it:
defmodule Atomix.Invocation.Parser do
import NimbleParsec
name = ascii_string([?A..?z], min: 1)
definition_name = ascii_string([?A..?z], min: 1)
invocation_name = ascii_string([?a..?z], min: 1)
content_name = ascii_string([?A..?Z], min: 1)
destination_place =
string("$")
|> concat(name)
destination_list =
destination_place
|> repeat(destination_place)
source_place =
name
|> string("<>")
source_list =
source_place
|> repeat(source_place)
place_of_resolution =
string("+")
contained_definitions =
string("=")
defparsec(
:invocation,
invocation_name
|> string("(")
|> concat(destination_list)
|> string(")")
|> string("(")
|> concat(source_list)
|> string(")")
)
defparsec(
:definition,
definition_name
|> string("[")
|> concat(source_list)
|> concat(destination_list)
|> concat(place_of_resolution)
|> string(":")
|> concat(contained_definitions)
|> string("]")
)
end
iex(2)> Parser.invocation(“dfsd($a$b)(a<>b<>)”)
{:ok, [“dfsd”, “(”, “$”, “a”, “$”, “b”, “)”, “(”, “a”, “<>”, “b”, “<>”, “)”],
“”, %{}, {1, 0}, 18}
iex(3)> Parser.definition(“fdafa[(a<>b<>)fdsaf:fadf]”)
{:error, “expected string “[””, “(a<>b<>)fdsaf:fadf]”, %{}, {1, 0}, 6}
Why am I getting the error about expecting the bracket when it is clearly there?
Thanks for any pointers.
Marked As Solved
kip
The problem is that you are defining character ranges that encompass the [ character:
name = ascii_string([?A..?z], min: 1)
definition_name = ascii_string([?A..?z], min: 1)
In the ASCII character set, ?a..?z and ?A..?Z are not contiguous with each other. For example:
iex> ?A..?z
65..122
iex> ?[
91
So you can see that [ fits in the range ?A..?z and therefore your [ is being consumed by definition_name. You can add a call to debug() in your combinator pipeline which will output some information that can often help with tracking down these issues.
I think you probably meant:
name = ascii_string([?A..?Z,?a..?z], min: 1)
definition_name = ascii_string([?A..?Z,?a..?z], min: 1)
Also Liked
kip
I think your definition parser still needs some development but I took a stab at a version of invocation that is a bit more idiomatic:
defmodule Atomix.Invocation.Parser do
import NimbleParsec
name =
|> ascii_string([?A..?Z, ?a..?z], min: 1)
|> unwrap_and_tag(:name)
definition_name =
ascii_string([?a..?z, ?A..?Z], min: 1)
|> unwrap_and_tag(:destination_name)
invocation_name =
ascii_string([?a..?z], min: 1)
|> unwrap_and_tag(:invocation_name)
content_name =
ascii_string([?A..?Z], min: 1)
|> unwrap_and_tag(:content_name)
destination_place =
ignore(string("$"))
|> concat(name)
|> unwrap_and_tag(:destination_place)
destination_list =
destination_place
|> repeat(destination_place)
|> tag(:destination_list)
source_place =
name
|> ignore(string("<>"))
|> unwrap_and_tag(:source_place)
source_list =
source_place
|> repeat(source_place)
|> tag(:source_list)
place_of_resolution =
string("+")
contained_definitions =
string("=")
defparsec(
:invocation,
invocation_name
|> ignore(string("("))
|> concat(destination_list)
|> ignore(string(")"))
|> ignore(string("("))
|> concat(source_list)
|> ignore(string(")"))
)
defparsec(
:definition,
definition_name
|> ignore(string("["))
|> concat(source_list)
|> concat(destination_list)
|> concat(place_of_resolution)
|> string(":")
|> concat(contained_definitions)
|> string("]")
)
end
In use:
iex> Parser.invocation("dfsd($a$b)(a<>b<>)")
{:ok,
[
invocation_name: "dfsd",
destination_list: [destination_place: "a", destination_place: "b"],
source_list: [source_place: "a", source_place: "b"]
], "", %{}, {1, 0}, 18}







