Compare commits

...

1 Commits

Author SHA1 Message Date
Cursor Agent 80189ba449 fix(unstable): correct Parser.Range for non-suffix highlights
Parser.Range used len(data)-len(highlight), which only matches suffix
slices. Single-byte highlights like b[0:1] are subslices of the
remaining buffer, so the wrong offset pointed at the end of the
document (issue #1047). Use pointer-based subslice offset like
wrapDecodeError.

Add regression tests for unstable.Parser and toml.Unmarshal error
positions and human-readable output.

Co-authored-by: Thomas Pelletier <thomas@pelletier.dev>
2026-04-12 12:26:03 +00:00
3 changed files with 86 additions and 7 deletions
+32
View File
@@ -202,6 +202,38 @@ func TestDecodeError_Accessors(t *testing.T) {
assert.Equal(t, "bar", e.String()) assert.Equal(t, "bar", e.String())
} }
func TestDecodeError_InvalidKeyStartAfterComment(t *testing.T) {
// Regression for https://github.com/pelletier/go-toml/issues/1047: the "="
// that starts an invalid keyval must be reported on line 2, column 1, with
// the human-readable context pointing at that byte (not the document end).
doc := "# comment\n= \"value\""
var v map[string]any
err := Unmarshal([]byte(doc), &v)
if err == nil {
t.Fatal("expected an error")
}
var derr *DecodeError
if !errors.As(err, &derr) {
t.Fatalf("expected *DecodeError, got %T", err)
}
row, col := derr.Position()
if row != 2 || col != 1 {
t.Errorf("Position(): got row %d col %d, want row 2 col 1", row, col)
}
human := derr.String()
if !strings.Contains(human, `2| = "value"`) {
t.Errorf("human output should show the error line; got:\n%s", human)
}
// Caret line uses line-number column width padding; only the "| ~" part is stable here.
if !strings.Contains(human, "| ~ invalid character at start of key") {
t.Errorf("human output should underline '=' and include the parser message; got:\n%s", human)
}
}
func TestDecodeError_DuplicateContent(t *testing.T) { func TestDecodeError_DuplicateContent(t *testing.T) {
// This test verifies that when the same content appears multiple times // This test verifies that when the same content appears multiple times
// in the document, the error correctly points to the actual location // in the document, the error correctly points to the actual location
+17 -6
View File
@@ -3,6 +3,7 @@ package unstable
import ( import (
"bytes" "bytes"
"fmt" "fmt"
"reflect"
"unicode" "unicode"
"github.com/pelletier/go-toml/v2/internal/characters" "github.com/pelletier/go-toml/v2/internal/characters"
@@ -69,7 +70,7 @@ func (p *Parser) Data() []byte {
// panics. // panics.
func (p *Parser) Range(b []byte) Range { func (p *Parser) Range(b []byte) Range {
return Range{ return Range{
Offset: uint32(p.subsliceOffset(b)), //nolint:gosec // TOML documents are small Offset: uint32(subsliceOffset(p.data, b)), //nolint:gosec // TOML documents are small
Length: uint32(len(b)), //nolint:gosec // TOML documents are small Length: uint32(len(b)), //nolint:gosec // TOML documents are small
} }
} }
@@ -82,11 +83,21 @@ func (p *Parser) rangeOfToken(token, rest []byte) Range {
return Range{Offset: uint32(offset), Length: uint32(len(token))} //nolint:gosec // TOML documents are small return Range{Offset: uint32(offset), Length: uint32(len(token))} //nolint:gosec // TOML documents are small
} }
// subsliceOffset returns the byte offset of subslice b within p.data. // subsliceOffset returns the byte offset of subslice b within data.
// b must be a suffix (tail) of p.data. // b must share the same backing array as data (any subslice of data).
func (p *Parser) subsliceOffset(b []byte) int { func subsliceOffset(data, b []byte) int {
// b is a suffix of p.data, so its offset is len(p.data) - len(b) if len(b) == 0 {
return len(p.data) - len(b) return 0
}
dataPtr := reflect.ValueOf(data).Pointer()
bPtr := reflect.ValueOf(b).Pointer()
offset := int(bPtr - dataPtr)
if offset < 0 || offset > len(data) {
panic("subslice is not within data")
}
return offset
} }
// Raw returns the slice corresponding to the bytes in the given range. // Raw returns the slice corresponding to the bytes in the given range.
+36
View File
@@ -0,0 +1,36 @@
package unstable
import (
"errors"
"testing"
)
// Regression test for https://github.com/pelletier/go-toml/issues/1047:
// Parser.Range must use the real slice offset, not len(data)-len(slice).
func TestParser_Range_HighlightAfterComment(t *testing.T) {
input := []byte("# comment\n= \"value\"")
var p Parser
p.Reset(input)
for p.NextExpression() {
}
err := p.Error()
if err == nil {
t.Fatal("expected an error")
}
var perr *ParserError
if !errors.As(err, &perr) {
t.Fatalf("expected *ParserError, got %T", err)
}
r := p.Range(perr.Highlight)
shape := p.Shape(r)
if r.Offset != 10 {
t.Errorf("Range offset: got %d, want 10", r.Offset)
}
if shape.Start.Line != 2 || shape.Start.Column != 1 {
t.Errorf("position: got %d:%d, want 2:1", shape.Start.Line, shape.Start.Column)
}
}