implement char escapes #20
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -410,23 +410,74 @@ literalInt = | |
| |> P.inContext InLiteralInt | ||
|
|
||
|
|
||
| -- for literalChar and, in the future, literalString | ||
| stringHelp = | ||
|
There was a problem hiding this comment. I'd probably rather name this There was a problem hiding this comment.
|
||
| P.oneOf | ||
| [ P.succeed (identity) | ||
|
There was a problem hiding this comment. probably unneeded parens for the identity |
||
| |. P.token (P.Token "\\" ExpectingEscapeBackslash) | ||
| |= P.oneOf | ||
| [ P.map (\_ -> '\"') (P.token (P.Token "\"" ExpectingEscapeCharacter)) | ||
| , P.map (\_ -> '\'') (P.token (P.Token "'" ExpectingEscapeCharacter)) | ||
| , P.map (\_ -> '\n') (P.token (P.Token "n" ExpectingEscapeCharacter)) | ||
| , P.map (\_ -> '\t') (P.token (P.Token "t" ExpectingEscapeCharacter)) | ||
| , P.map (\_ -> '\r') (P.token (P.Token "r" ExpectingEscapeCharacter)) | ||
|
There was a problem hiding this comment. I'm still thinking about these ParserProblems. The problem with this current solution is that the error messages will only be able to show five times the same thing ("I expected escape character, escape character, ...") Please parameterize this one ( There was a problem hiding this comment. How about something like below? The above behavior would interpret |= P.oneOf
- [ P.map (\_ -> '\"') (P.token (P.Token "\"" ExpectingEscapeCharacter))
- , P.map (\_ -> '\'') (P.token (P.Token "'" ExpectingEscapeCharacter))
- , P.map (\_ -> '\n') (P.token (P.Token "n" ExpectingEscapeCharacter))
- , P.map (\_ -> '\t') (P.token (P.Token "t" ExpectingEscapeCharacter))
- , P.map (\_ -> '\r') (P.token (P.Token "r" ExpectingEscapeCharacter))
+ [ P.map (\_ -> '\"') (Parser.token "\""))
+ , P.map (\_ -> '\'') (Parser.token "'"))
+ , P.map (\_ -> '\n') (Parser.token "n"))
+ , P.map (\_ -> '\t') (Parser.token "t"))
+ , P.map (\_ -> '\r') (Parser.token "r"))
, P.succeed identity
|. P.token (P.Token "u" ExpectingEscapeCharacter)
|. P.token (P.Token "{" ExpectingUnicodeEscapeLeftBrace)
|= unicode
|. P.token (P.Token "}" ExpectingUnicodeEscapeRightBrace)
+ , P.problem ExpectingValidEscapeChar
]
The problem is that I don't think in either solutions, both the current one in the PR and the diff above, the compiler would print out one of those token errors. Rather, it would either skip the There was a problem hiding this comment. current PR state: https://ellie-app.com/5Z9tkd2hGSQa1 If you think this still overlooks some corner case, please shout! :) There was a problem hiding this comment. Oops, my bad! |
||
| , P.succeed identity | ||
| |. P.token (P.Token "u" ExpectingEscapeCharacter) | ||
| |. P.token (P.Token "{" ExpectingUnicodeEscapeLeftBrace) | ||
| |= unicode | ||
| |. P.token (P.Token "}" ExpectingUnicodeEscapeRightBrace) | ||
| ] | ||
| , P.succeed identity | ||
| |= P.getChompedString (P.chompIf (always True) ExpectingChar) | ||
| |> P.andThen (\string -> | ||
| string | ||
| |> String.uncons | ||
| |> Maybe.map (Tuple.first >> P.succeed) | ||
| |> Maybe.withDefault (P.problem (CompilerBug "Multiple characters chomped in `literalChar`")) | ||
|
There was a problem hiding this comment. This message is not entirely correct, we're not inside |
||
| ) | ||
| ] | ||
|
|
||
|
|
||
| literalChar : Parser_ Literal | ||
| literalChar = | ||
| (P.succeed identity | ||
| |. P.symbol (P.Token "'" ExpectingSingleQuote) | ||
| |= stringHelp | ||
| |. P.symbol (P.Token "'" ExpectingSingleQuote) | ||
| ) | ||
| |> P.map (\n -> Char n) | ||
|
|
||
|
|
||
| unicode : Parser_ Char | ||
| unicode = | ||
| P.getChompedString (P.chompWhile Char.isHexDigit) | ||
| |> P.andThen codeToChar | ||
|
|
||
|
|
||
| codeToChar : String -> Parser_ Char | ||
| codeToChar str = | ||
| let | ||
| length = String.length str | ||
| code = String.foldl addHex 0 str | ||
|
There was a problem hiding this comment. let's check for the length, that's great, but let's use Hex.fromString for the actual "is this a hex string" and "what int value does it represent" functionality |
||
| in | ||
| if length < 4 || length > 6 then | ||
| P.problem InvalidUnicodeCodePoint | ||
| else if 0 <= code && code <= 0x10FFFF then | ||
| P.succeed (Char.fromCode code) | ||
| else | ||
| P.problem InvalidUnicodeCodePoint | ||
|
|
||
|
|
||
| addHex : Char -> Int -> Int | ||
| addHex char total = | ||
|
There was a problem hiding this comment. let's use Hex.fromString instead of this. Also, it is buggy wrt. characters outside the hex range I think. |
||
| let | ||
| code = Char.toCode char | ||
| in | ||
| if 0x30 <= code && code <= 0x39 then | ||
| 16 * total + (code - 0x30) | ||
| else if 0x41 <= code && code <= 0x46 then | ||
| 16 * total + (10 + code - 0x41) | ||
| else | ||
| 16 * total + (10 + code - 0x61) | ||
|
|
||
|
|
||
| {-| TODO escapes | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Next time please don't bother shifting the numbers, life's too short for that :)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Phew 👍