Add parse_ints config in json parser to support parsing int or float properly

.chloggen/json_parser_number_data_type.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: pkg/stanza
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add `use_number` config in json parser to support decode into int or float properly
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [33696]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: []

pkg/stanza/docs/operators/json_parser.md

@@ -4,16 +4,17 @@ The `json_parser` operator parses the string-type field selected by `parse_from`
 
 ### Configuration Fields
 
-| Field         | Default          | Description |
-| ---           | ---              | ---         |
-| `id`          | `json_parser`    | A unique identifier for the operator. |
-| `output`      | Next in pipeline | The connected operator(s) that will receive all outbound entries. |
-| `parse_from`  | `body`           | The [field](../types/field.md) from which the value will be parsed. |
-| `parse_to`    | `attributes`     | The [field](../types/field.md) to which the value will be parsed. |
-| `on_error`    | `send`           | The behavior of the operator if it encounters an error. See [on_error](../types/on_error.md). |
-| `if`          |                  | An [expression](../types/expression.md) that, when set, will be evaluated to determine whether this operator should be used for the given entry. This allows you to do easy conditional parsing without branching logic with routers. |
-| `timestamp`   | `nil`            | An optional [timestamp](../types/timestamp.md) block which will parse a timestamp field before passing the entry to the output operator. |
-| `severity`    | `nil`            | An optional [severity](../types/severity.md) block which will parse a severity field before passing the entry to the output operator. |
+| Field        | Default          | Description |
+| ---          | ---              | ---         |
+| `id`         | `json_parser`    | A unique identifier for the operator. |
+| `output`     | Next in pipeline | The connected operator(s) that will receive all outbound entries. |
+| `parse_from` | `body`           | The [field](../types/field.md) from which the value will be parsed. |
+| `parse_to`   | `attributes`     | The [field](../types/field.md) to which the value will be parsed. |
+| `on_error`   | `send`           | The behavior of the operator if it encounters an error. See [on_error](../types/on_error.md). |
+| `if`         |                  | An [expression](../types/expression.md) that, when set, will be evaluated to determine whether this operator should be used for the given entry. This allows you to do easy conditional parsing without branching logic with routers. |
+| `timestamp`  | `nil`            | An optional [timestamp](../types/timestamp.md) block which will parse a timestamp field before passing the entry to the output operator. |
+| `severity`   | `nil`            | An optional [severity](../types/severity.md) block which will parse a severity field before passing the entry to the output operator. |
+| `use_number` | `false`          | Numbers like `int` and `float` are parsed as `float64` by default, when `use_number` is enabled, numbers are parsed as `json.Number` and then converted to `int64` or `float64` based on the value. |
 
 ### Embedded Operations
 

pkg/stanza/operator/parser/json/config.go

@@ -32,6 +32,8 @@ func NewConfigWithID(operatorID string) *Config {
 // Config is the configuration of a JSON parser operator.
 type Config struct {
 	helper.ParserConfig `mapstructure:",squash"`
+
+	UseNumber bool `mapstructure:"use_number"`
 }
 
 // Build will build a JSON parser operator.
@@ -41,8 +43,22 @@ func (c Config) Build(set component.TelemetrySettings) (operator.Operator, error
 		return nil, err
 	}
 
+	// jsonConfig defaults to jsoniter.ConfigFastest for backward compatibility
+	var jsonConfig = jsoniter.Config{
+		EscapeHTML:                    false,
+		MarshalFloatWith6Digits:       true,
+		ObjectFieldMustBeSimpleString: true,
+	}
+
+	// override the default values with the values from the config
+	// when UseNumber is disabled, `int` and `float` will be parsed as `float64`.
+	// when it is enabled, they will be parsed as `json.Number`, later the parser
+	// will convert them to `int` or `float64` according to the field type.
+	jsonConfig.UseNumber = c.UseNumber
+
 	return &Parser{
 		ParserOperator: parserOperator,
-		json:           jsoniter.ConfigFastest,
+		json:           jsonConfig.Froze(),
+		useNumber:      c.UseNumber,
 	}, nil
 }

pkg/stanza/operator/parser/json/config_test.go

@@ -110,6 +110,14 @@ func TestConfig(t *testing.T) {
 					return p
 				}(),
 			},
+			{
+				Name: "use_number",
+				Expect: func() *Config {
+					p := NewConfig()
+					p.UseNumber = true
+					return p
+				}(),
+			},
 		},
 	}.Run(t)
 }

pkg/stanza/operator/parser/json/parser.go

@@ -5,6 +5,7 @@ package json // import "github.com/open-telemetry/opentelemetry-collector-contri
 
 import (
 	"context"
+	"encoding/json"
 	"fmt"
 
 	jsoniter "github.com/json-iterator/go"
@@ -16,7 +17,8 @@ import (
 // Parser is an operator that parses JSON.
 type Parser struct {
 	helper.ParserOperator
-	json jsoniter.API
+	json      jsoniter.API
+	useNumber bool
 }
 
 // Process will parse an entry for JSON.
@@ -36,5 +38,47 @@ func (p *Parser) parse(value any) (any, error) {
 	default:
 		return nil, fmt.Errorf("type %T cannot be parsed as JSON", value)
 	}
+
+	if p.useNumber {
+		p.convertNumbers(parsedValue)
+	}
 	return parsedValue, nil
 }
+
+func (p *Parser) convertNumbers(parsedValue map[string]any) {
+	for k, v := range parsedValue {
+		switch t := v.(type) {
+		case json.Number:
+			parsedValue[k] = p.convertNumber(t)
+		case map[string]any:
+			p.convertNumbers(t)
+		case []any:
+			p.convertNumbersArray(t)
+		}
+	}
+}
+
+func (p *Parser) convertNumbersArray(arr []any) {
+	for i, v := range arr {
+		switch t := v.(type) {
+		case json.Number:
+			arr[i] = p.convertNumber(t)
+		case map[string]any:
+			p.convertNumbers(t)
+		case []any:
+			p.convertNumbersArray(t)
+		}
+	}
+}
+
+func (p *Parser) convertNumber(value json.Number) any {
+	i64, err := value.Int64()
+	if err == nil {
+		return i64
+	}
+	f64, err := value.Float64()
+	if err == nil {
+		return f64
+	}
+	return value.String()
+}

pkg/stanza/operator/parser/json/parser_test.go

@@ -139,6 +139,116 @@ func TestParser(t *testing.T) {
 				ScopeName: "logger",
 			},
 		},
+		{
+			"use_number_disabled",
+			func(_ *Config) {},
+			&entry.Entry{
+				Body: `{"int":1,"float":1.0}`,
+			},
+			&entry.Entry{
+				Attributes: map[string]any{
+					"int":   float64(1),
+					"float": float64(1),
+				},
+				Body: `{"int":1,"float":1.0}`,
+			},
+		},
+		{
+			"use_number_simple",
+			func(p *Config) {
+				p.UseNumber = true
+			},
+			&entry.Entry{
+				Body: `{"int":1,"float":1.0}`,
+			},
+			&entry.Entry{
+				Attributes: map[string]any{
+					"int":   int64(1),
+					"float": float64(1),
+				},
+				Body: `{"int":1,"float":1.0}`,
+			},
+		},
+		{
+			"use_number_nested",
+			func(p *Config) {
+				p.UseNumber = true
+			},
+			&entry.Entry{
+				Body: `{"int":1,"float":1.0,"nested":{"int":2,"float":2.0}}`,
+			},
+			&entry.Entry{
+				Attributes: map[string]any{
+					"int":   int64(1),
+					"float": float64(1),
+					"nested": map[string]any{
+						"int":   int64(2),
+						"float": float64(2),
+					},
+				},
+				Body: `{"int":1,"float":1.0,"nested":{"int":2,"float":2.0}}`,
+			},
+		},
+		{
+			"use_number_arrays",
+			func(p *Config) {
+				p.UseNumber = true
+			},
+			&entry.Entry{
+				Body: `{"int":1,"float":1.0,"nested":{"int":2,"float":2.0},"array":[1,2]}`,
+			},
+			&entry.Entry{
+				Attributes: map[string]any{
+					"int":   int64(1),
+					"float": float64(1),
+					"nested": map[string]any{
+						"int":   int64(2),
+						"float": float64(2),
+					},
+					"array": []any{int64(1), int64(2)},
+				},
+				Body: `{"int":1,"float":1.0,"nested":{"int":2,"float":2.0},"array":[1,2]}`,
+			},
+		},
+		{
+			"use_number_mixed_arrays",
+			func(p *Config) {
+				p.UseNumber = true
+			},
+			&entry.Entry{
+				Body: `{"int":1,"float":1.0,"mixed_array":[1,1.5,2]}`,
+			},
+			&entry.Entry{
+				Attributes: map[string]any{
+					"int":         int64(1),
+					"float":       float64(1),
+					"mixed_array": []any{int64(1), float64(1.5), int64(2)},
+				},
+				Body: `{"int":1,"float":1.0,"mixed_array":[1,1.5,2]}`,
+			},
+		},
+		{
+			"use_number_nested_arrays",
+			func(p *Config) {
+				p.UseNumber = true
+			},
+			&entry.Entry{
+				Body: `{"int":1,"float":1.0,"nested":{"int":2,"float":2.0,"array":[1,2]},"array":[3,4]}`,
+			},
+			&entry.Entry{
+				Attributes: map[string]any{
+					"int":   int64(1),
+					"float": float64(1),
+					"nested": map[string]any{
+						"int":   int64(2),
+						"float": float64(2),
+						"array": []any{int64(1), int64(2)},
+					},
+					"array": []any{int64(3), int64(4)},
+				},
+				Body: `{"int":1,"float":1.0,"nested":{"int":2,"float":2.0,"array":[1,2]},"array":[3,4]}`,
+			},
+		},
 	}
 
 	for _, tc := range cases {

pkg/stanza/operator/parser/json/testdata/config.yaml

@@ -37,3 +37,6 @@ timestamp:
     parse_from: body.timestamp_field
     layout_type: strptime
     layout: '%Y-%m-%d'
+use_number:
+  type: json_parser
+  use_number: true