Remove unneeded Juxt token
#208
Conversation
neuroevolutus
had a problem deploying
to
scrapscript-pr-208
GitHub Actions
Failure
scrapscript.py
Outdated
| @@ -394,8 +388,6 @@ def parse(tokens: typing.List[Token], p: float = 0) -> "Object": | |||
| # we can match variants in MatchFunction | |||
| # It needs to be higher than the precedence of the && operator so that | |||
| # we can use #true() and #false() in boolean expressions | |||
| # It needs to be higher than the precedence of juxtaposition so that | |||
There was a problem hiding this comment.
Please leave this comment; still applies
There was a problem hiding this comment.
Oh, I see. Thanks for pointing that out. I've restored this hunk.
|
Thanks for the fix! Please add back the comment or I'll do it in a couple of days. Then we merge! If you would like to work on anything else, please let me know |
|
I saw that #84 was about utilizing Pratt parsing, but it seems like you've already implemented a pretty neat Pratt parser for the language. Are there any other parts of the parsing code that could use some help? A couple of things I was thinking about:
|
neuroevolutus
had a problem deploying
to
scrapscript-pr-208
GitHub Actions
Failure
84 is mostly about deciding if we want to have the lexer be a generator and have the parser pull from it. But I also dropped a Pratt parsing resource because our parser is a big ball of hacks and I wonder if it's possible to make it more regular-looking.
That is a good question. I think it feels too low in the precedence list but didn't have any actual notion of what that means or why it's wrong. Added in 33a6c8f but not explained well. |
|
Thank you for the PR! |
I started reading through the parsing code and noticed that this token was being unused. Let me know if you'd like me to make any further changes!