feat(genapi): derive discriminators and decode RichText alternates

The generator gated all union decoder emission behind knownDiscriminators, a
hand-curated map of 13 entries. Any sealed union absent from that map received
no decoder, so decoding must fail. Bot API v10 added RichBlock and RichText,
which were absent. Roughly 8.6 percent of Telegram updates failed with HTTP 400.

The generator now derives discriminators from the specification instead of a
fixed list. A gate check fails the build when a union resolves no discriminator.
Eleven unions gain decoders that never had one: BotCommandScope, InputMedia,
InputPaidMedia, InputPollMedia, InputPollOptionMedia, InputProfilePhoto,
InputRichBlock, InputStoryContent, PassportElementError, RichBlock and RichText.

RichText can also appear as a bare string or an array of RichText. The scraper
now extracts these alternate shapes into the intermediate representation. The
emitter adds RichTextPlain and RichTextSequence. The decoder dispatches on the
first JSON byte before it reads any discriminator.

Unions without alternates must regenerate byte for byte. The golden test proves
this.

Claude-Session: https://claude.ai/code/session_01Fu2wXqGUrfVBi5aLafKk8U
This commit is contained in:
2026-09-15 10:59:48 +01:00
parent fa84f08b25
commit d666cda3b1
16 changed files with 4449 additions and 695 deletions
+65 -6
View File
@@ -7,14 +7,16 @@
package api
import (
"bytes"
"github.com/goccy/go-json"
"fmt"
"io"
)
var _ = io.Discard // keep import even if no fields use io
var _ = json.Marshal // keep import for UnmarshalXxx helpers
var _ = fmt.Errorf // keep import for UnmarshalXxx helpers
var _ = io.Discard // keep import even if no fields use io
var _ = json.Marshal // keep import for UnmarshalXxx helpers
var _ = fmt.Errorf // keep import for UnmarshalXxx helpers
var _ = bytes.TrimLeft // keep import for shape-dispatching UnmarshalXxx helpers (unions with alternates)
{{range .Types}}
{{- $td := . -}}
@@ -22,6 +24,7 @@ var _ = fmt.Errorf // keep import for UnmarshalXxx helpers
// {{.Name}} is a union type. The following concrete variants implement
// it:
{{range .OneOf}}// - {{.}}
{{end}}{{range unionAlternates .}}// - {{.Name}} ({{if .IsString}}bare JSON string{{else}}JSON array of {{$td.Name}}{{end}})
{{end}}//
{{docComment .Doc -}}
type {{.Name}} interface{ is{{.Name}}() }
@@ -30,11 +33,67 @@ type {{.Name}} interface{ is{{.Name}}() }
// is{{$td.Name}} is the marker method that makes {{.}} implement {{$td.Name}}.
func (*{{.}}) is{{$td.Name}}() {}
{{end}}
{{range unionAlternates .}}
// {{.Name}} implements {{$td.Name}} for the {{if .IsString}}bare JSON string{{else}}JSON array of {{$td.Name}}{{end}} wire
// shape Telegram documents for this union, alongside its object variants.
type {{.Name}} struct {
{{if .IsString}} Text string
{{else}} Items []{{$td.Name}}
{{end}}}
// is{{$td.Name}} is the marker method that makes {{.Name}} implement {{$td.Name}}.
func (*{{.Name}}) is{{$td.Name}}() {}
{{if .IsString}}// MarshalJSON encodes {{.Name}} back to its bare JSON string wire shape.
func (v *{{.Name}}) MarshalJSON() ([]byte, error) {
return json.Marshal(v.Text)
}
{{else}}// MarshalJSON encodes {{.Name}} back to its bare JSON array wire shape.
func (v *{{.Name}}) MarshalJSON() ([]byte, error) {
return json.Marshal(v.Items)
}
{{end}}
{{end}}
{{if hasDiscriminator .Name}}
// Unmarshal{{.Name}} decodes a {{.Name}} from JSON by inspecting the
{{$alts := unionAlternates .}}{{if $alts}}// Unmarshal{{.Name}} decodes a {{.Name}} from JSON. Telegram documents
// this type as either a bare JSON string, a JSON array of {{.Name}}, or
// an object dispatched by its "{{discriminatorField .Name}}" field;
// leading whitespace is trimmed and the first remaining byte selects
// the shape.
{{else}}// Unmarshal{{.Name}} decodes a {{.Name}} from JSON by inspecting the
// "{{discriminatorField .Name}}" field and dispatching to the correct concrete type.
func Unmarshal{{.Name}}(data []byte) ({{.Name}}, error) {
var probe struct {
{{end}}func Unmarshal{{.Name}}(data []byte) ({{.Name}}, error) {
{{if $alts}} trimmed := bytes.TrimLeft(data, " \t\r\n")
if len(trimmed) == 0 {
return nil, fmt.Errorf("{{.Name}}: empty JSON value")
}
switch trimmed[0] {
{{range $alts}}{{if .IsString}} case '"':
var s string
if err := json.Unmarshal(data, &s); err != nil {
return nil, fmt.Errorf("{{$td.Name}}: decoding string: %w", err)
}
return &{{.Name}}{Text: s}, nil
{{else}} case '[':
var raws []json.RawMessage
if err := json.Unmarshal(data, &raws); err != nil {
return nil, fmt.Errorf("{{$td.Name}}: decoding array: %w", err)
}
items := make([]{{$td.Name}}, 0, len(raws))
for i, r := range raws {
v, err := Unmarshal{{$td.Name}}(r)
if err != nil {
return nil, fmt.Errorf("{{$td.Name}}: decoding array[%d]: %w", i, err)
}
items = append(items, v)
}
return &{{.Name}}{Items: items}, nil
{{end}}{{end}} case '{':
// fall through to the discriminator switch below.
default:
return nil, fmt.Errorf("{{.Name}}: unrecognised JSON value starting with %q", trimmed[0])
}
{{end}} var probe struct {
V string `json:"{{discriminatorField .Name}}"`
}
if err := json.Unmarshal(data, &probe); err != nil {