Fix bug and possible panic when decoding nested structs

ianlopshire · Feb 8, 2024 · 549210b · 549210b
1 parent 45d0d87
commit 549210b
Show file tree

Hide file tree

Showing 2 changed files with 97 additions and 12 deletions.
diff --git a/decode.go b/decode.go
@@ -196,7 +196,7 @@ func (d *Decoder) readLine(v reflect.Value) (err error, ok bool) {
 	return valueSetter(v, rawValue), true
 }
 
-func rawValueFromLine(value rawValue, startPos, endPos int, format format) rawValue {
+func rawValueFromLine(value rawValue, startPos, endPos int, format format) (rawValue, error) {
 	var trimFunc func(string) string
 
 	switch format.alignment {
@@ -218,7 +218,7 @@ func rawValueFromLine(value rawValue, startPos, endPos int, format format) rawVa
 
 	if value.codepointIndices != nil {
 		if len(value.codepointIndices) == 0 || startPos > len(value.codepointIndices) {
-			return rawValue{data: ""}
+			return rawValue{data: ""}, nil
 		}
 		var relevantIndices []int
 		var lineData string
@@ -229,20 +229,30 @@ func rawValueFromLine(value rawValue, startPos, endPos int, format format) rawVa
 			relevantIndices = value.codepointIndices[startPos-1 : endPos]
 			lineData = value.data[relevantIndices[0]:value.codepointIndices[endPos]]
 		}
+
+		trimmed := trimFunc(lineData)
+
+		// If the value was trimmed or didn't start at the first codepoint, the indices
+		// will be incorrect. Create a new rawValue to get the correct indices.
+		if len(trimmed) != len(lineData) || len(relevantIndices) == 0 {
+			return newRawValue(trimmed, true)
+		}
+
 		return rawValue{
-			data:             trimFunc(lineData),
+			data:             lineData,
 			codepointIndices: relevantIndices,
-		}
+		}, nil
+
 	} else {
 		if len(value.data) == 0 || startPos > len(value.data) {
-			return rawValue{data: ""}
+			return rawValue{data: ""}, nil
 		}
 		if endPos > len(value.data) {
 			endPos = len(value.data)
 		}
 		return rawValue{
 			data: trimFunc(value.data[startPos-1 : endPos]),
-		}
+		}, nil
 	}
 }
 
@@ -288,9 +298,12 @@ func structSetter(t reflect.Type) valueSetter {
 			if !fieldSpec.ok {
 				continue
 			}
-			rawValue := rawValueFromLine(raw, fieldSpec.startPos, fieldSpec.endPos, fieldSpec.format)
-			err := fieldSpec.setter(v.Field(i), rawValue)
+
+			rawValue, err := rawValueFromLine(raw, fieldSpec.startPos, fieldSpec.endPos, fieldSpec.format)
 			if err != nil {
+				return err
+			}
+			if err := fieldSpec.setter(v.Field(i), rawValue); err != nil {
 				sf := t.Field(i)
 				return &UnmarshalTypeError{raw.data, sf.Type, t.Name(), sf.Name, err}
 			}

diff --git a/decode_test.go b/decode_test.go
@@ -40,10 +40,10 @@ func ExampleUnmarshal() {
 	fmt.Printf("%+v\n", people[2])
 	fmt.Printf("%+v\n", people[3])
 	// Output:
-	//{ID:1 FirstName:Ian LastName:Lopshire Grade:99.5 Age:20 Alive:false Github:false}
-	//{ID:2 FirstName:John LastName:Doe Grade:89.5 Age:21 Alive:true Github:true}
-	//{ID:3 FirstName:Jane LastName:Doe Grade:79.5 Age:22 Alive:false Github:false}
-	//{ID:4 FirstName:Ann LastName:Carraway Grade:79.59 Age:23 Alive:false Github:true}
+	// {ID:1 FirstName:Ian LastName:Lopshire Grade:99.5 Age:20 Alive:false Github:false}
+	// {ID:2 FirstName:John LastName:Doe Grade:89.5 Age:21 Alive:true Github:true}
+	// {ID:3 FirstName:Jane LastName:Doe Grade:79.5 Age:22 Alive:false Github:false}
+	// {ID:4 FirstName:Ann LastName:Carraway Grade:79.59 Age:23 Alive:false Github:true}
 }
 
 func TestUnmarshal(t *testing.T) {
@@ -539,3 +539,75 @@ func TestLineSeparator(t *testing.T) {
 		})
 	}
 }
+
+func TestDecode_Nested(t *testing.T) {
+	type Nested struct {
+		First  string `fixed:"1,3"`
+		Second string `fixed:"4,6"`
+	}
+
+	type Test struct {
+		Nested Nested `fixed:"1,6,none"`
+	}
+
+	for _, tt := range []struct {
+		name string
+		raw  []byte
+
+		expected Test
+	}{
+		{
+			name: "ascii no trimming needed",
+			raw:  []byte("123ABC\n"),
+			expected: Test{
+				Nested: Nested{
+					First:  "123",
+					Second: "ABC",
+				},
+			},
+		},
+		{
+			name: "ascii with trimmed values",
+			raw:  []byte(" 12BC\n"),
+			expected: Test{
+				Nested: Nested{
+					First:  "12",
+					Second: "BC",
+				},
+			},
+		},
+		{
+			name: "Multi-byte no trimming needed",
+			raw:  []byte("12☃☃BC\n"),
+			expected: Test{
+				Nested: Nested{
+					First:  "12☃",
+					Second: "☃BC",
+				},
+			},
+		},
+		{
+			name: "Multi-byte with trimmed values",
+			raw:  []byte(" ☃2B☃\n"),
+			expected: Test{
+				Nested: Nested{
+					First:  "☃2",
+					Second: "B☃",
+				},
+			},
+		},
+	} {
+		t.Run(tt.name, func(t *testing.T) {
+			d := NewDecoder(bytes.NewReader(tt.raw))
+			d.SetUseCodepointIndices(true)
+			var s Test
+			err := d.Decode(&s)
+			if err != nil {
+				t.Errorf("Unexpected err: %v", err)
+			}
+			if !reflect.DeepEqual(tt.expected, s) {
+				t.Errorf("Decode(%v) want %v, have %v", tt.raw, tt.expected, s)
+			}
+		})
+	}
+}