feat: support for nested groups and quantifiers

Demali-876 · Nov 3, 2024 · f4200ae · f4200ae
2 parents fdb77ad + af79c13
commit f4200ae
Show file tree

Hide file tree

Showing 2 changed files with 39 additions and 38 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,19 @@
+# [0.1.0](https://github.com/Demali-876/motoko_regex_engine/compare/v0.0.0...v0.1.0) (2024-10-29)
+
+
+### Bug Fixes
+
+* setup semantic release workflow ([823d429](https://github.com/Demali-876/motoko_regex_engine/commit/823d429f549ccde9812db741c5d22126282c9c29))
+* setup semantic release workflow ([a7addf2](https://github.com/Demali-876/motoko_regex_engine/commit/a7addf26dd204370a4afe77208b0ec5913163d40))
+* setup semantic release workflow ([8dffe34](https://github.com/Demali-876/motoko_regex_engine/commit/8dffe34f9726fe79baa14b6f5a20f96570ba5f91))
+
+
+### Features
+
+* add semantic release configuration ([9cbf0ab](https://github.com/Demali-876/motoko_regex_engine/commit/9cbf0abe8f6a944019bb36c504ebe90a319e0953))
+* **engine:** change log automation ([bf83e73](https://github.com/Demali-876/motoko_regex_engine/commit/bf83e73b54c7b46c1810e6ace3a1e2997f6a3aa3))
+* **parser:** add nested quantifier support ([f8055a6](https://github.com/Demali-876/motoko_regex_engine/commit/f8055a6f5a90cfb3bc56a28ba6a3f6f03826b34e))
+
 # [0.0.0] Unreleased - 10-03-2024
 
 ## 🚀 New Features

diff --git a/src/motoko_regex/Lexer.mo b/src/motoko_regex/Lexer.mo
@@ -4,27 +4,30 @@ import Array "mo:base/Array";
 import Int "mo:base/Int";
 import Result "mo:base/Result";
 import Buffer "mo:base/Buffer";
-import Debug "mo:base/Debug";
 import Types "Types";
 import Extensions "Extensions";
 import Cursor "Cursor";
 
 module {
   type Token = Types.Token;
-  type LexerError = Types.RegexError;
+  public type LexerError = Types.RegexError;
   type CharacterClass = Types.CharacterClass;
   public class Lexer(input: Text) {
     let cursor = Cursor.Cursor(input);
     let tokenBuffer = Buffer.Buffer<Token>(16);
 
-    public func tokenize(): [Token] {
+    public func tokenize(): Result.Result<[Token], LexerError> {
       while (cursor.hasNext()) {
         switch (nextToken()) {
-          case (#ok(token)) { tokenBuffer.add(token) };
-          case (#err(error)) { Debug.trap(Extensions.errorToText(error)) };
+          case (#ok(token)) {
+            tokenBuffer.add(token);
+          };
+          case (#err(error)) {
+            return #err(error);
+          };
         };
       };
-      Buffer.toArray(tokenBuffer)
+      #ok(Buffer.toArray(tokenBuffer))
     };
 
     private func nextToken(): Result.Result<Token, LexerError> {
@@ -44,7 +47,7 @@ module {
                 case (#err(error)) { return #err(error) };
               };
             };
-            case '[' { 
+            case '[' {
               switch (tokenizeCharacterClass()) {
                 case (#ok(token)) {
                   let quantifiedToken = checkAndApplyQuantifier(token);
@@ -234,7 +237,7 @@ module {
         };
       };
 
-      if (not cursor.hasNext() or cursor.current() != ']') {
+      if (not cursor.hasNext() and cursor.current() != ']') {
       return #err(#GenericError("Unclosed character class at position " # Nat.toText(cursor.getPos())));
       };
 
@@ -328,42 +331,24 @@ module {
 
     private func tokenizeSubExpression(): Result.Result<Buffer.Buffer<Token>, LexerError> {
     var subTokens = Buffer.Buffer<Token>(16);
-    var depth = 1;
+
+    while (cursor.hasNext()) {
+        if (cursor.current() == ')') {
+            return #ok(subTokens);
+        };
 
-    while (cursor.hasNext() and depth > 0) {
-        switch (cursor.current()) {
-            case '(' {
-                switch (tokenizeGroup()) {
-                    case (#ok(token)) {
-                        subTokens.add(token);
-                    };
-                    case (#err(error)) { return #err(error) };
-                };
-            };
-            case ')' {
-                depth -= 1;
-                if (depth == 0) {
-                    return #ok(subTokens);
-                } else {
-                    return #ok(subTokens);
-                };
+        switch (nextToken()) {
+            case (#ok(token)) { 
+                subTokens.add(token);
             };
-            case _ {
-                switch (nextToken()) {
-                    case (#ok(token)) { subTokens.add(token) };
-                    case (#err(error)) { return #err(error) };
-                };
+            case (#err(error)) { 
+                return #err(error);
             };
         };
     };
 
-    if (depth > 0) {
-        return #err(#GenericError("Unclosed group at position " # Nat.toText(cursor.getPos())));
-    };
-
-    #ok(subTokens)
-    };
-
+    #err(#GenericError("Unclosed group at position " # Nat.toText(cursor.getPos())))
+};
     private func tokenizeEscapedChar(): Result.Result<Token, LexerError> {
       cursor.inc();
       switch (cursor.current()) {