From adb150d1fb801c032d62be69cb03ac60c158ecb9 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Mon, 6 Apr 2026 08:45:00 +0000
Subject: [PATCH] S2-S4: tighten lexer condition, fix doc header, add Unicode
 example

Agent-Logs-Url: https://github.com/mikefarah/yq/sessions/ec06083e-e20a-45d2-bf7e-4e1fa7be1073

Co-authored-by: mikefarah <1151925+mikefarah@users.noreply.github.com>
---
 pkg/yqlib/doc/operators/headers/slice-array.md |  2 +-
 pkg/yqlib/doc/operators/slice-array.md         | 18 +++++++++++++++++-
 pkg/yqlib/lexer.go                             |  7 ++++++-
 3 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/pkg/yqlib/doc/operators/headers/slice-array.md b/pkg/yqlib/doc/operators/headers/slice-array.md
index 0113a585..448c38ea 100644
--- a/pkg/yqlib/doc/operators/headers/slice-array.md
+++ b/pkg/yqlib/doc/operators/headers/slice-array.md
@@ -1,4 +1,4 @@
-# Slice/Splice Array or String
+# Slice Array or String
 
 The slice operator works on both arrays and strings. Like the `jq` equivalent, `.[10:15]` will return a subarray (or substring) of length 5, starting from index 10 inclusive, up to index 15 exclusive. Negative numbers count backwards from the end of the array or string.
 
diff --git a/pkg/yqlib/doc/operators/slice-array.md b/pkg/yqlib/doc/operators/slice-array.md
index aee24811..a7920406 100644
--- a/pkg/yqlib/doc/operators/slice-array.md
+++ b/pkg/yqlib/doc/operators/slice-array.md
@@ -1,4 +1,4 @@
-# Slice/Splice Array or String
+# Slice Array or String
 
 The slice operator works on both arrays and strings. Like the `jq` equivalent, `.[10:15]` will return a subarray (or substring) of length 5, starting from index 10 inclusive, up to index 15 exclusive. Negative numbers count backwards from the end of the array or string.
 
@@ -165,3 +165,19 @@ will output
 ralia
 ```
 
+## Slicing strings - Unicode
+Indices are rune-based, so multibyte characters are handled correctly
+
+Given a sample.yml file of:
+```yaml
+greeting: héllo
+```
+then
+```bash
+yq '.greeting[1:3]' sample.yml
+```
+will output
+```yaml
+él
+```
+
diff --git a/pkg/yqlib/lexer.go b/pkg/yqlib/lexer.go
index 25ef12ac..12e63e37 100644
--- a/pkg/yqlib/lexer.go
+++ b/pkg/yqlib/lexer.go
@@ -127,10 +127,15 @@ func handleToken(tokens []*token, index int, postProcessedTokens []*token) (toke
 	if tokenIsOpType(currentToken, createMapOpType) {
 		log.Debugf("tokenIsOpType: createMapOpType")
 		// check the previous token is '[', means we are slice, but dont have a first number
-		if index > 0 && (tokens[index-1].TokenType == traverseArrayCollect || tokens[index-1].TokenType == openCollect) {
+		if index > 0 && tokens[index-1].TokenType == traverseArrayCollect {
 			log.Debugf("previous token is : traverseArrayOpType")
 			// need to put the number 0 before this token, as that is implied
 			postProcessedTokens = append(postProcessedTokens, &token{TokenType: operationToken, Operation: createValueOperation(0, "0")})
+		} else if index >= 2 && tokens[index-1].TokenType == openCollect &&
+			(tokens[index-2].TokenType == operationToken || tokens[index-2].TokenType == closeCollect || tokens[index-2].TokenType == closeCollectObject) {
+			log.Debugf("previous token is : openCollect following a traversal, implying 0 start")
+			// need to put the number 0 before this token, as that is implied
+			postProcessedTokens = append(postProcessedTokens, &token{TokenType: operationToken, Operation: createValueOperation(0, "0")})
 		}
 	}