Set text replacement type to char instead of string

iamgio · Sep 11, 2024 · 5cfcd6d · 5cfcd6d
1 parent 4b94640
commit 5cfcd6d
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 20 deletions.
diff --git a/core/src/main/kotlin/eu/iamgio/quarkdown/ast/quarkdown/inline/TextSymbol.kt b/core/src/main/kotlin/eu/iamgio/quarkdown/ast/quarkdown/inline/TextSymbol.kt
@@ -6,9 +6,15 @@ import eu.iamgio.quarkdown.visitor.node.NodeVisitor
 /**
  * A text-based symbol, such as `©`, `…`, `≥`.
  * This is usually the result of a combination of multiple characters (e.g. `(C)` -> `©`).
- * @param text processed symbol (e.g. `©`)
+ * @param symbol processed symbol (e.g. `©`)
  * @see eu.iamgio.quarkdown.lexer.patterns.TextSymbolReplacement
  */
-data class TextSymbol(override val text: String) : PlainTextNode {
+data class TextSymbol(val symbol: Char) : PlainTextNode {
+    /**
+     * @return [symbol] as a string
+     */
+    override val text: String
+        get() = symbol.toString()
+
     override fun <T> accept(visitor: NodeVisitor<T>): T = visitor.visit(this)
 }
diff --git a/core/src/main/kotlin/eu/iamgio/quarkdown/lexer/patterns/TextSymbolReplacement.kt b/core/src/main/kotlin/eu/iamgio/quarkdown/lexer/patterns/TextSymbolReplacement.kt
@@ -5,104 +5,106 @@ import eu.iamgio.quarkdown.lexer.tokens.TextSymbolToken
 
 /**
  * Patterns for sequences of characters that correspond to text symbols.
+ * @param result symbol that the sequence is replaced with
+ * @param regex regex pattern that matches the sequence to be replaced
  */
-enum class TextSymbolReplacement(val result: String, val regex: Regex) {
+enum class TextSymbolReplacement(val result: Char, val regex: Regex) {
     /**
      * `(C)` -> `©`
      */
-    COPYRIGHT("©", "\\(C\\)".toRegex()),
+    COPYRIGHT('©', "\\(C\\)".toRegex()),
 
     /**
      * `(R)` -> `®`
      */
-    REGISTERED("®", "\\(R\\)".toRegex()),
+    REGISTERED('®', "\\(R\\)".toRegex()),
 
     /**
      * `(TM)` -> `™`
      */
-    TRADEMARK("™", "\\(TM\\)".toRegex()),
+    TRADEMARK('™', "\\(TM\\)".toRegex()),
 
     /**
      * `-` -> `—`
      *
      * It must be surrounded by a word character and a space on both sides.
      */
-    EM_DASH("—", "(?<=\\w\\s)-(?=\\s\\w)".toRegex()),
+    EM_DASH('—', "(?<=\\w\\s)-(?=\\s\\w)".toRegex()),
 
     /**
      * `...` -> `…`
      *
      * Must be either at the beginning or end of a word, not in-between.
      */
-    ELLIPSIS("…", "(\\.\\.\\.(?=\\s|\$))|((?<=\\s|^)\\.\\.\\.)".toRegex()),
+    ELLIPSIS('…', "(\\.\\.\\.(?=\\s|\$))|((?<=\\s|^)\\.\\.\\.)".toRegex()),
 
     /**
      * `->` -> `→`
      */
-    SINGLE_RIGHT_ARROW("→", "->".toRegex()),
+    SINGLE_RIGHT_ARROW('→', "->".toRegex()),
 
     /**
      * `<-` -> `←`
      */
-    SINGLE_LEFT_ARROW("←", "<-".toRegex()),
+    SINGLE_LEFT_ARROW('←', "<-".toRegex()),
 
     /**
      * `=>` -> `⇒`
      */
-    DOUBLE_RIGHT_ARROW("⇒", "=>".toRegex()),
+    DOUBLE_RIGHT_ARROW('⇒', "=>".toRegex()),
 
     /**
      * `<==` -> `⇐`
      */
-    DOUBLE_LEFT_ARROW("⇐", "<==".toRegex()),
+    DOUBLE_LEFT_ARROW('⇐', "<==".toRegex()),
 
     /**
      * `>=` -> `≥`
      */
-    GREATER_EQUAL("≥", ">=".toRegex()),
+    GREATER_EQUAL('≥', ">=".toRegex()),
 
     /**
      * `<=` -> `≤`
      */
-    LESS_EQUAL("≤", "<=".toRegex()),
+    LESS_EQUAL('≤', "<=".toRegex()),
 
     /**
      * `!=` -> `≠`
      */
-    NOT_EQUAL("≠", "!=".toRegex()),
+    NOT_EQUAL('≠', "!=".toRegex()),
 
     /**
      * `+-` -> `±`
      */
-    PLUS_MINUS("±", "\\+-".toRegex()),
+    PLUS_MINUS('±', "\\+-".toRegex()),
 
     /**
      * `'` -> `‘`
      *
      * Must not be preceded by a word and must be followed by a word character.
      */
-    TYPOGRAPHIC_LEFT_APOSTROPHE("‘", "(?<=\\s|^)'(?=\\w)".toRegex()),
+    TYPOGRAPHIC_LEFT_APOSTROPHE('‘', "(?<=\\s|^)'(?=\\w)".toRegex()),
 
     /**
      * `'` -> `’`
      *
      * Must not be preceded by a whitespace.
      */
-    TYPOGRAPHIC_RIGHT_APOSTROPHE("’", "(?<!\\s)'".toRegex()),
+    TYPOGRAPHIC_RIGHT_APOSTROPHE('’', "(?<!\\s)'".toRegex()),
 
     /**
      * `"` -> `“`
      *
      * Must not be preceded by a word character and must be followed by a word character.
      */
-    TYPOGRAPHIC_LEFT_QUOTATION_MARK("“", "(?<!\\w)\"(?=\\w)".toRegex()),
+    TYPOGRAPHIC_LEFT_QUOTATION_MARK('“', "(?<!\\w)\"(?=\\w)".toRegex()),
 
     /**
      * `"` -> `”`
      *
      * Must not be preceded by a whitespace and not followed by a word character.
      */
-    TYPOGRAPHIC_RIGHT_QUOTATION_MARK("”", "(?<!\\s)\"(?!\\w)".toRegex()),
+    TYPOGRAPHIC_RIGHT_QUOTATION_MARK('”', "(?<!\\s)\"(?!\\w)".toRegex()),
     ;
 
     /**