Compare commits

..

2 Commits

Author SHA1 Message Date
Claude b7ffaf15eb Move regression tests to public Unmarshal API with full error string assertions
Remove the unstable package test and consolidate all test cases into
TestDecodeError_PositionAfterComment, which exercises toml.Unmarshal
and validates the complete human-readable error output including
context lines and tilde markers.

https://claude.ai/code/session_01EXYfFXc3DDGpQ27sWdXTKq
2026-04-12 11:59:46 +00:00
Claude 0248fc4c8c Fix incorrect error positions for non-suffix subslices in unstable.Parser.Range (#1047)
The unsafe removal (#1021) replaced danger.SubsliceOffset (pointer
arithmetic) with len(p.data)-len(b), which only works for suffix
slices. Parser.Range is called with arbitrary interior subslices
(e.g. ParserError.Highlight), so the offset was wrong whenever the
error occurred after previously scanned content like comments.

Fix by using reflect.ValueOf().Pointer() to recover the actual data
pointer, matching the approach already used in errors.go.

https://claude.ai/code/session_01EXYfFXc3DDGpQ27sWdXTKq
2026-04-12 11:52:16 +00:00
3 changed files with 75 additions and 82 deletions
+67 -32
View File
@@ -202,38 +202,6 @@ 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
@@ -333,6 +301,73 @@ OtherMissing = 1
assert.Equal(t, 2, len(strictErr.Unwrap())) assert.Equal(t, 2, len(strictErr.Unwrap()))
} }
func TestDecodeError_PositionAfterComment(t *testing.T) {
// Regression test for https://github.com/pelletier/go-toml/issues/1047
// Error positions must be correct when the error occurs after comments or
// other content that was already scanned past.
examples := []struct {
desc string
doc string
expectedRow int
expectedCol int
expectedStr string
}{
{
desc: "invalid key after comment",
doc: "# comment\n= \"value\"",
expectedRow: 2,
expectedCol: 1,
expectedStr: "1| # comment\n2| = \"value\"\n | ~ invalid character at start of key: =",
},
{
desc: "invalid key after two comments",
doc: "# one\n# two\n= \"value\"",
expectedRow: 3,
expectedCol: 1,
expectedStr: "1| # one\n2| # two\n3| = \"value\"\n | ~ invalid character at start of key: =",
},
{
desc: "invalid key after key-value pair",
doc: "a = 1\n= 2",
expectedRow: 2,
expectedCol: 1,
expectedStr: "1| a = 1\n2| = 2\n | ~ invalid character at start of key: =",
},
{
desc: "invalid key after blank line",
doc: "a = 1\n\n= 2",
expectedRow: 3,
expectedCol: 1,
expectedStr: "1| a = 1\n2|\n3| = 2\n | ~ invalid character at start of key: =",
},
}
for _, e := range examples {
t.Run(e.desc, func(t *testing.T) {
var v interface{}
err := Unmarshal([]byte(e.doc), &v)
if err == nil {
t.Fatal("expected an error")
}
var derr *DecodeError
if !errors.As(err, &derr) {
t.Fatalf("error not a *DecodeError: %T: %v", err, err)
}
row, col := derr.Position()
if row != e.expectedRow {
t.Errorf("row: got %d, want %d (error: %s)", row, e.expectedRow, derr.String())
}
if col != e.expectedCol {
t.Errorf("col: got %d, want %d (error: %s)", col, e.expectedCol, derr.String())
}
assert.Equal(t, e.expectedStr, derr.String())
})
}
}
func ExampleDecodeError() { func ExampleDecodeError() {
doc := `name = 123__456` doc := `name = 123__456`
+8 -14
View File
@@ -70,8 +70,8 @@ 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(subsliceOffset(p.data, b)), //nolint:gosec // TOML documents are small Offset: uint32(p.subsliceOffset(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
} }
} }
@@ -83,21 +83,15 @@ 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 data. // subsliceOffset returns the byte offset of subslice b within p.data.
// b must share the same backing array as data (any subslice of data). // b must be a subslice of p.data (sharing the same backing array).
func subsliceOffset(data, b []byte) int { func (p *Parser) subsliceOffset(b []byte) int {
if len(b) == 0 { if len(b) == 0 {
return 0 return 0
} }
dataPtr := reflect.ValueOf(p.data).Pointer()
dataPtr := reflect.ValueOf(data).Pointer() subPtr := reflect.ValueOf(b).Pointer()
bPtr := reflect.ValueOf(b).Pointer() return int(subPtr - dataPtr)
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
@@ -1,36 +0,0 @@
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)
}
}