From 43946ca0c9e19f904b7f763b9dc590d8095e6472 Mon Sep 17 00:00:00 2001
From: EuAndreh <eu@euandre.org>
Date: Tue, 15 Jul 2025 20:43:57 -0300
Subject: Support tokenizing `^` and `$` anchors

* src/paca.mjs
  (ANCHOR_FNS): Add simple handlers for ^ and $ anchors, that only look
    for the position of the character in the pattern as validation
    during tokenization.
  (isAnchor): Add simple boolean function to identify anchor characters.
  (tokenizeRegexStep): Include check if character `isAnchor()`, and call
    the appropriate `ANCHOR_FNS[char]` when true.
* tests/paca.mjs
  (test_ANCHOR_FNS): Add test with 4 cases - 2 for success and 2 for
    errors for ^ and $.
  (test_isAnchor): Add obligatory simple test cases.
  (test_tokenizeRegexStep): Include test case for tokenizing patterns
    with character class.
---
 src/paca.mjs | 49 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

(limited to 'src/paca.mjs')

diff --git a/src/paca.mjs b/src/paca.mjs
index ae14538..42c2f88 100644
--- a/src/paca.mjs
+++ b/src/paca.mjs
@@ -15,7 +15,7 @@ const ConcatStep = {
 	CLASS:     "class",
 };
 
-const nonConcatOperators = new Set(["*", "+", "?", "|", ")"]);
+const nonConcatOperators = new Set(["*", "+", "?", "|", ")", "$"]);
 
 const shouldConcat = (char, next) =>
 	next !== undefined &&
@@ -272,6 +272,44 @@ const TRANSITION_FNS = {
 	}),
 };
 
+const ANCHOR_FNS = {
+	"^": ({ out, state, context }, _char, index, _next) =>
+		index !== 0
+			? reduced({
+				out,
+				state,
+				context,
+				error: new SyntaxError(
+					"^ not at the start of the expression",
+				),
+			})
+			: {
+				out: out.concat({ operator: "caret" }),
+				state,
+				context,
+			},
+	"$": ({ out, state, context }, _char, _index, next) =>
+		next !== undefined
+			? reduced({
+				out,
+				state,
+				context,
+				error: new SyntaxError(
+					"$ not at the end of the expression",
+				),
+			})
+			: {
+				out: out.concat({ operator: "dollar" }),
+				state,
+				context,
+			},
+};
+
+const anchors = new Set(Object.keys(ANCHOR_FNS));
+
+const isAnchor = char =>
+	anchors.has(char);
+
 const stateTransitionOperators = new Set(Object.keys(TRANSITION_FNS));
 
 const isOperator = char =>
@@ -298,6 +336,15 @@ const tokenizeRegexStep = chars => ({ out, state, context }, char, index) => {
 		);
 	}
 
+	if (isAnchor(char)) {
+		return ANCHOR_FNS[char](
+			{ out, state, context },
+			char,
+			index,
+			next,
+		);
+	}
+
 	const op = isOperator(char) ? { operator: char } : char;
 	return {
 		out: out.concat(
-- 
cgit v1.2.3