fix: regex recognizer anchoring

igordejanovic · Jan 4, 2024 · 2de5537 · 2de5537
1 parent 4383f5e
commit 2de5537
Show file tree

Hide file tree

Showing 8 changed files with 22 additions and 19 deletions.
diff --git a/docs/src/tutorials/calculator/calculator1/src/calculator.rs b/docs/src/tutorials/calculator/calculator1/src/calculator.rs
@@ -295,13 +295,13 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
     TokenRecognizer(
         TokenKind::Operand,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\d+(\\.\\d+)?")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\d+(\\.\\d+)?", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(
         TokenKind::Operator,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\+|-|\\*|/")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\+|-|\\*|/", ")")).unwrap() }),
         ),
     ),
 ];

diff --git a/docs/src/tutorials/calculator/calculator2/src/calculator.rs b/docs/src/tutorials/calculator/calculator2/src/calculator.rs
@@ -421,7 +421,7 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
     TokenRecognizer(
         TokenKind::Number,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\d+(\\.\\d+)?")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\d+(\\.\\d+)?", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(TokenKind::Plus, Recognizer::StrMatch("+")),

diff --git a/docs/src/tutorials/calculator/calculator3/src/calculator.rs b/docs/src/tutorials/calculator/calculator3/src/calculator.rs
@@ -421,7 +421,7 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
     TokenRecognizer(
         TokenKind::Number,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\d+(\\.\\d+)?")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\d+(\\.\\d+)?", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(TokenKind::Plus, Recognizer::StrMatch("+")),

diff --git a/docs/src/tutorials/calculator/calculator4/src/calculator.rs b/docs/src/tutorials/calculator/calculator4/src/calculator.rs
@@ -421,7 +421,7 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
     TokenRecognizer(
         TokenKind::Number,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\d+(\\.\\d+)?")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\d+(\\.\\d+)?", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(TokenKind::Plus, Recognizer::StrMatch("+")),

diff --git a/docs/src/tutorials/calculator/calculator5/src/calculator.rs b/docs/src/tutorials/calculator/calculator5/src/calculator.rs
@@ -421,7 +421,7 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
     TokenRecognizer(
         TokenKind::Number,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\d+(\\.\\d+)?")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\d+(\\.\\d+)?", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(TokenKind::Plus, Recognizer::StrMatch("+")),

diff --git a/rustemo-compiler/src/generator/base.rs b/rustemo-compiler/src/generator/base.rs
@@ -618,7 +618,7 @@ impl<'g, 's> PartGenerator<'g, 's> for BasePartGenerator {
                                 let r = r.as_ref();
                                 parse_quote! {
                                     TokenRecognizer(TokenKind::#token_kind, Recognizer::RegexMatch(Lazy::new(|| {
-                                        Regex::new(concat!("^", #r)).unwrap()
+                                        Regex::new(concat!("^(", #r, ")")).unwrap()
                                     })))
                                 }
                             },

diff --git a/rustemo-compiler/src/lang/rustemo.rs b/rustemo-compiler/src/lang/rustemo.rs
@@ -16900,35 +16900,37 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
         TokenKind::Name,
         Recognizer::RegexMatch(
             Lazy::new(|| {
-                Regex::new(concat!("^", "[a-zA-Z_][a-zA-Z0-9_\\.]*")).unwrap()
+                Regex::new(concat!("^(", "[a-zA-Z_][a-zA-Z0-9_\\.]*", ")")).unwrap()
             }),
         ),
     ),
     TokenRecognizer(
         TokenKind::RegexTerm,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "/(\\\\.|[^/\\\\])*/")).unwrap() }),
+            Lazy::new(|| {
+                Regex::new(concat!("^(", "/(\\\\.|[^/\\\\])*/", ")")).unwrap()
+            }),
         ),
     ),
     TokenRecognizer(
         TokenKind::IntConst,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\d+")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\d+", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(
         TokenKind::FloatConst,
         Recognizer::RegexMatch(
             Lazy::new(|| {
-                Regex::new(concat!("^", "[+-]?[0-9]+[.][0-9]*([e][+-]?[0-9]+)?"))
+                Regex::new(concat!("^(", "[+-]?[0-9]+[.][0-9]*([e][+-]?[0-9]+)?", ")"))
                     .unwrap()
             }),
         ),
     ),
     TokenRecognizer(
         TokenKind::BoolConst,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "true|false")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "true|false", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(
@@ -16937,8 +16939,9 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
             Lazy::new(|| {
                 Regex::new(
                         concat!(
-                            "^",
-                            "(?s)(^'[^'\\\\]*(?:\\\\.[^'\\\\]*)*')|(^\"[^\"\\\\]*(?:\\\\.[^\"\\\\]*)*\")"
+                            "^(",
+                            "(?s)(^'[^'\\\\]*(?:\\\\.[^'\\\\]*)*')|(^\"[^\"\\\\]*(?:\\\\.[^\"\\\\]*)*\")",
+                            ")"
                         ),
                     )
                     .unwrap()
@@ -16948,26 +16951,26 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
     TokenRecognizer(
         TokenKind::Annotation,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "@[a-zA-Z0-9_]+")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "@[a-zA-Z0-9_]+", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(
         TokenKind::WS,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\s+")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\s+", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(
         TokenKind::CommentLine,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "//.*")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "//.*", ")")).unwrap() }),
         ),
     ),
     TokenRecognizer(
         TokenKind::NotComment,
         Recognizer::RegexMatch(
             Lazy::new(|| {
-                Regex::new(concat!("^", "((\\*[^/])|[^\\s*/]|/[^\\*])+")).unwrap()
+                Regex::new(concat!("^(", "((\\*[^/])|[^\\s*/]|/[^\\*])+", ")")).unwrap()
             }),
         ),
     ),

diff --git a/tests/src/output_dir/output_dir.rs b/tests/src/output_dir/output_dir.rs
@@ -319,7 +319,7 @@ pub(crate) static RECOGNIZERS: [TokenRecognizer; TERMINAL_COUNT] = [
     TokenRecognizer(
         TokenKind::Num,
         Recognizer::RegexMatch(
-            Lazy::new(|| { Regex::new(concat!("^", "\\d+")).unwrap() }),
+            Lazy::new(|| { Regex::new(concat!("^(", "\\d+", ")")).unwrap() }),
         ),
     ),
 ];