From e8b0e13efcb232b6aaed61bd302bdb65ecbd98f1 Mon Sep 17 00:00:00 2001
From: Jamie Willis <j.willis19@imperial.ac.uk>
Date: Sun, 25 Jun 2023 00:27:04 +0100
Subject: [PATCH] Exposed `codePoint` combinator

---
 .../src/main/scala/parsley/character.scala      | 17 ++++++++---------
 .../src/test/scala/parsley/CharTests.scala      |  8 ++++----
 .../parsley/token/symbol/OriginalSymbol.scala   |  4 ++--
 3 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/parsley/shared/src/main/scala/parsley/character.scala b/parsley/shared/src/main/scala/parsley/character.scala
index aaaed4081..bbea8ce18 100644
--- a/parsley/shared/src/main/scala/parsley/character.scala
+++ b/parsley/shared/src/main/scala/parsley/character.scala
@@ -78,7 +78,6 @@ import parsley.internal.deepembedding.singletons
   *     [[https://www.unicode.org/Public/13.0.0/ucd/extracted/DerivedGeneralCategory.txt Unicode Character Database]]''.
   */
 object character {
-    // TODO: in @note: or [[charUtf16 `charUtf16`]]
     /** This combinator tries to parse a single specific character `c` from the input.
       *
       * Attempts to read the given character `c` from the input stream at the current
@@ -97,7 +96,7 @@ object character {
       *
       * @param c the character to parse
       * @return a parser that tries to read a single `c`, or fails.
-      * @note this combinator can only handle 16-bit characters: for larger codepoints, consider using [[string `string`]].
+      * @note this combinator can only handle 16-bit characters: for larger codepoints, consider using [[string `string`]] or [[codePoint `codePoint`]].
       * @group core
       */
     def char(c: Char): Parsley[Char] = char(c, NotConfigured)
@@ -107,25 +106,25 @@ object character {
     /** This combinator tries to parse a single specific codepoint `c` from the input.
       *
       * Like [[char `char`]], except it may consume two characters from the input,
-      * in the case where the codepoint is greater than `0xffff`. This is parsed ''atomically''
+      * in the case where the code-point is greater than `0xffff`. This is parsed ''atomically''
       * so that no input is consumed if the first half of the codepoint is parsed and the second
       * is not.
       *
       * @example {{{
-      * scala> import parsley.character.charUtf16
-      * scala> char(0x1F643).parse("")
+      * scala> import parsley.character.codePoint
+      * scala> codePoint(0x1F643).parse("")
       * val res0 = Failure(..)
-      * scala> char(0x1F643).parse("🙂")
+      * scala> codePoint(0x1F643).parse("🙂")
       * val res1 = Success(0x1F643)
-      * scala> char(0x1F643).parse("b🙂")
+      * scala> codePoint(0x1F643).parse("b🙂")
       * val res2 = Failure(..)
       * }}}
       *
-      * @param c the codepoint to parse
+      * @param c the code-point to parse
       * @return
       * @group core
       */
-    private [parsley] def charUtf16(c: Int): Parsley[Int] = { //TODO: release along with the utf combinators
+    def codePoint(c: Int): Parsley[Int] = {
         if (Character.isBmpCodePoint(c)) char(c.toChar) #> c
         else new Parsley(new singletons.SupplementaryCharTok(c, NotConfigured))
     }
diff --git a/parsley/shared/src/test/scala/parsley/CharTests.scala b/parsley/shared/src/test/scala/parsley/CharTests.scala
index 4bb3af767..becb6f32c 100644
--- a/parsley/shared/src/test/scala/parsley/CharTests.scala
+++ b/parsley/shared/src/test/scala/parsley/CharTests.scala
@@ -119,15 +119,15 @@ class CharTests extends ParsleyTest {
     }
 
     "charUtf16" should "handle BMP characters" in {
-        cases(charUtf16('a'))("a" -> Some('a'))
-        cases(charUtf16('λ'))("λ" -> Some('λ'))
+        cases(codePoint('a'))("a" -> Some('a'))
+        cases(codePoint('λ'))("λ" -> Some('λ'))
     }
 
     it should "handle multi-character codepoints" in {
-        cases(charUtf16(0x1F642))("🙂" -> Some(0x1F642))
+        cases(codePoint(0x1F642))("🙂" -> Some(0x1F642))
     }
 
     it should "handle multi-character codepoints atomically on fail" in {
-        cases(charUtf16(0x1F642) <|> charUtf16(0x1F643))("🙃" -> Some(0x1F643))
+        cases(codePoint(0x1F642) <|> codePoint(0x1F643))("🙃" -> Some(0x1F643))
     }
 }
diff --git a/parsley/shared/src/test/scala/parsley/token/symbol/OriginalSymbol.scala b/parsley/shared/src/test/scala/parsley/token/symbol/OriginalSymbol.scala
index a92340732..8abe88939 100644
--- a/parsley/shared/src/test/scala/parsley/token/symbol/OriginalSymbol.scala
+++ b/parsley/shared/src/test/scala/parsley/token/symbol/OriginalSymbol.scala
@@ -4,7 +4,7 @@
 package parsley.token.symbol
 
 import parsley.Parsley, Parsley.{attempt, notFollowedBy, unit}
-import parsley.character.{char, charUtf16, string, strings}
+import parsley.character.{char, codePoint, string, strings}
 import parsley.errors.combinator.{ErrorMethods, empty, amend}
 import parsley.token.descriptions.{NameDesc, SymbolDesc}
 import parsley.token.errors.ErrorConfig
@@ -22,7 +22,7 @@ private [token] class OriginalSymbol(nameDesc: NameDesc, symbolDesc: SymbolDesc,
     override def apply(name: Char): Parsley[Unit] = char(name).void
 
     private lazy val identLetter = nameDesc.identifierLetter.toNative
-    private def caseChar(c: Int) = if (Character.isLetter(c)) charUtf16(Character.toLowerCase(c)) <|> charUtf16(Character.toUpperCase(c)) else charUtf16(c)
+    private def caseChar(c: Int) = if (Character.isLetter(c)) codePoint(Character.toLowerCase(c)) <|> codePoint(Character.toUpperCase(c)) else codePoint(c)
     private def caseString(name: String): Parsley[Unit] = {
         if (symbolDesc.caseSensitive) string(name).void
         else {