hare

commit cb7c2f4a4b3113561efd1e673400ee186aac1183
parent 2e40a9474e3e1c588ea0ba392c1c698dccf295f3
Author: Max Schillinger <max@mxsr.de>
Date:   Thu, 18 Jul 2024 20:47:14 +0200

regex: allow $ at end of every whole-expression alternation

Signed-off-by: Max Schillinger <max@mxsr.de>

Diffstat:
M
regex/+test.ha
 | 
7
+++++++
M
regex/regex.ha
 | 
18
+++++++++++++-----

2 files changed, 20 insertions(+), 5 deletions(-)
diff --git a/regex/+test.ha b/regex/+test.ha
@@ -582,10 +582,17 @@ fn run_rawreplace_case(
 		(`ab|cd`, "bcd", matchres::MATCH, 1, 3),
 		(`^ab|cd`, "bcd", matchres::MATCH, 1, 3),
 		(`^ab|cd`, "zab", matchres::NOMATCH, 0, 0),
+		(`ab$|cd`, "ab", matchres::MATCH, 0, 2),
+		(`ab$|cd`, "abc", matchres::NOMATCH, 0, 0),
+		(`ab|cd$`, "cde", matchres::NOMATCH, 0, 0),
 		// multiple alternation
 		(`a|b|c|d|e`, "e", matchres::MATCH, 0, -1),
 		(`a|b|c|d|e`, "xe", matchres::MATCH, 1, -1),
 		(`(a|b|c|d|e)f`, "ef", matchres::MATCH, 0, -1),
+		(`a|b$|c$|d$|e`, "cd", matchres::MATCH, 1, -1),
+		(`a|b$|c$|d$|e`, "ax", matchres::MATCH, 0, 1),
+		(`a|b$|c$|d$|e`, "cx", matchres::NOMATCH, 0, 0),
+		(`a|b$|c$|d$|e`, "ex", matchres::MATCH, 0, 1),
 		// TODO: nested capture groups
 		(`((a))`, "abc", matchres::ERROR, 0, -1),
 		// (`((a))`, "abc", matchres::MATCH, 0, -1),
diff --git a/regex/regex.ha b/regex/regex.ha
@@ -222,7 +222,6 @@ export fn compile(expr: str) (regex | error) = {
 	let charsets: []charset = [];
 	let iter = strings::iter(expr);
 	let r_idx = 0z;
-	let anchored = false;
 	let jump_idxs: []size = [];
 	let in_bracket = false;
 	let skip_charclass_rest = false;
@@ -272,10 +271,17 @@ export fn compile(expr: str) (regex | error) = {
 				return `Anchor '^' not at start`: error;
 			};
 		case '$' =>
-			if (r_idx != len(expr) - 1) {
-				return `Anchor '$' not at end`: error;
+			if (n_groupstarts > 0) {
+				return `Anchor '$' in capture groups is unsupported`: error;
 			};
-			anchored = true;
+			const peek1 = strings::next(&iter);
+			if (peek1 is rune) {
+				if (peek1 as rune != '|') {
+					return `Anchor '$' not at end of whole pattern or alternation`: error;
+				};
+				strings::prev(&iter);
+			};
+			append(insts, true: inst_match);
 		case '[' =>
 			in_bracket = true;
 		case ']' =>
@@ -412,7 +418,9 @@ export fn compile(expr: str) (regex | error) = {
 	};
 	jump_idxs = [];
 
-	append(insts, anchored: inst_match);
+	if (len(insts) == 0 || !(insts[len(insts) - 1] is inst_match)) {
+		append(insts, false: inst_match);
+	};
 
 	return regex {
 		insts = insts,