fix: fixed regex for string value in json examples

maciejhirsz · Jan 20, 2025 · ddc6ba0 · ddc6ba0
1 parent 5e5046c
commit ddc6ba0
Show file tree

Hide file tree

Showing 4 changed files with 6 additions and 5 deletions.
diff --git a/book/src/examples/json.md b/book/src/examples/json.md
@@ -19,7 +19,8 @@ Knowing that, we can construct a lexer with `Logos` that will identify all those
 ```admonish note
 The hardest part is to define valid regexes for `Number` and `String` variants.
 The present solution was inspired by
-[this stackoverflow thread](https://stackoverflow.com/questions/32155133/regex-to-match-a-json-string).
+[this stackoverflow thread](https://stackoverflow.com/questions/32155133/regex-to-match-a-json-string)
+and checked against [the JSON specification](https://www.json.org/json-en.html).
 ```
 
 Once we have our tokens, we must parse them into actual JSON values. We will proceed be creating 3 functions:

diff --git a/book/src/examples/json_borrowed.md b/book/src/examples/json_borrowed.md
@@ -13,9 +13,9 @@ is straightforward:
 - enum Token {
 + enum Token<'source> {
 @ 62,63c58,59
--     #[regex(r#""([^"\\]|\\["\\bnfrt]|u[a-fA-F0-9]{4})*""#, |lex| lex.slice().to_owned())]
+-     #[regex(r#""([^"\\\x00-\x1F]|\\(["\\bnfrt/]|u[a-fA-F0-9]{4}))*""#, |lex| lex.slice().to_owned())]
 -     String(String),
-+     #[regex(r#""([^"\\]|\\["\\bnfrt]|u[a-fA-F0-9]{4})*""#, |lex| lex.slice())]
++     #[regex(r#""([^"\\\x00-\x1F]|\\(["\\bnfrt/]|u[a-fA-F0-9]{4}))*""#, |lex| lex.slice())]
 +     String(&'source str),
 @ 70c66
 - enum Value {

diff --git a/examples/json.rs b/examples/json.rs
@@ -59,7 +59,7 @@ enum Token {
     #[regex(r"-?(?:0|[1-9]\d*)(?:\.\d+)?(?:[eE][+-]?\d+)?", |lex| lex.slice().parse::<f64>().unwrap())]
     Number(f64),
 
-    #[regex(r#""([^"\\]|\\["\\bnfrt]|u[a-fA-F0-9]{4})*""#, |lex| lex.slice().to_owned())]
+    #[regex(r#""([^"\\\x00-\x1F]|\\(["\\bnfrt/]|u[a-fA-F0-9]{4}))*""#, |lex| lex.slice().to_owned())]
     String(String),
 }
 /* ANCHOR_END: tokens */

diff --git a/examples/json_borrowed.rs b/examples/json_borrowed.rs
@@ -55,7 +55,7 @@ enum Token<'source> {
     #[regex(r"-?(?:0|[1-9]\d*)(?:\.\d+)?(?:[eE][+-]?\d+)?", |lex| lex.slice().parse::<f64>().unwrap())]
     Number(f64),
 
-    #[regex(r#""([^"\\]|\\["\\bnfrt]|u[a-fA-F0-9]{4})*""#, |lex| lex.slice())]
+    #[regex(r#""([^"\\\x00-\x1F]|\\(["\\bnfrt/]|u[a-fA-F0-9]{4}))*""#, |lex| lex.slice())]
     String(&'source str),
 }
 /* ANCHOR_END: tokens */