Last active
March 4, 2024 09:15
-
-
Save paniq/ff7c84972a3fa9a862cc1ab12f92b035 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using import struct enum print itertools | |
enum Token plain | |
None | |
Word | |
Open | |
Close | |
@@ finite-state-machine | |
struct Tokenizer | |
state = Token.None | |
x0 = 0:usize | |
x1 = 0:usize | |
inline insert (self send ch) | |
x2 := self.x1 + 1 | |
newstate group? := switch ch | |
pass c" " | |
pass c"\t" | |
pass c"\n" | |
pass c"\r" | |
pass c"\x00" | |
do | |
pass Token.None true | |
case c"(" | |
pass Token.Open false | |
case c")" | |
pass Token.Close false | |
default | |
pass Token.Word true | |
if ((newstate == self.state) and group?) | |
self.x1 = x2 | |
else | |
send self.x0 self.x1 self.state | |
self.state = newstate | |
self.x0 = self.x1 | |
self.x1 = x2 | |
# Output: | |
Token.None "" | |
Token.Word the | |
Token.None " " | |
Token.Word quick | |
Token.Open "(" | |
Token.Word brown | |
Token.None " " | |
Token.Open "(" | |
Token.Word fox | |
Token.None " " | |
Token.Close ")" | |
Token.Close ")" | |
Token.None " " | |
Token.Word jumped | |
Token.None " " | |
Token.Word over | |
Token.None " " | |
Token.Word the | |
Token.None 2314:i16 | |
Token.Word lazy | |
Token.None 0x9:u8 | |
Token.Word dog | |
# input must explicitly insert a zero as terminator | |
S := "the quick(brown (fox )) jumped over the\n\tlazy\tdog\x00" | |
->> S | |
Tokenizer | |
map | |
inline (x0 x1 state) | |
print2 state | |
/prettydata | |
& (S @ x0) | |
x1 - x0 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment