Receive images in WhatsApp batches

[onechat] / telegram_api.go

package main

import (
        "bytes"
        "context"
        "encoding/json"
        "errors"
        "fmt"
        "io"
        "net/http"
        "net/url"
        "path"
        "strings"
        "time"
)

const (
        // telegramPollSeconds is how long one getUpdates call waits for an
        // update.
        telegramPollSeconds = 50

        // telegramPollSlack is how much longer than telegramPollSeconds a
        // getUpdates call can take before the bot gives it up.
        telegramPollSlack = 20 * time.Second

        // telegramPollTimeout is how long one getUpdates call can take.
        telegramPollTimeout = telegramPollSeconds*time.Second + telegramPollSlack

        // telegramSendTimeout is how long a sendMessage, sendRichMessage, or
        // sendChatAction call can take. A connection that stops without a
        // close, such as after a network change, then fails the call, and the
        // sender tries again, instead of a wait until TCP gives up. The client
        // has no timeout of its own, because the long poll of getUpdates needs
        // a longer limit.
        telegramSendTimeout = 30 * time.Second

        // telegramAnswerBytes is the most bytes of one answer of the Bot API.
        telegramAnswerBytes = 16 << 20
)

// newTelegramAPI returns the client of the Bot API at base with token.
func newTelegramAPI(base, token string) *TelegramAPI {
        return &TelegramAPI{
                base:        base,
                token:       token,
                http:        &http.Client{},
                sendTimeout: telegramSendTimeout,
        }
}

// telegramRetryable tells if a later try of a failed Bot API call can work:
// after a network error, HTTP 429, or a server error. It returns the wait that
// the Bot API asks for, or 0.
func telegramRetryable(err error) (bool, time.Duration) {
        var network *TelegramNetworkError

        if errors.As(err, &network) {
                return true, 0
        }

        var answer *TelegramError

        if errors.As(err, &answer) {
                return answer.Status == http.StatusTooManyRequests || answer.Status >= 500, answer.RetryAfter
        }

        return false, 0
}

// telegramRejected tells if the Bot API refused a call with ok false and HTTP
// 400 or 404. Then the call did nothing: 400 refuses the request, and 404 tells
// that the method is not there. An error page with no Bot API answer does not
// tell this, so it is not a refusal.
func telegramRejected(err error) bool {
        var answer *TelegramError

        return errors.As(err, &answer) && answer.Refused && (answer.Status == http.StatusBadRequest || answer.Status == http.StatusNotFound)
}

// TelegramAPI calls the Telegram Bot API. The bot token is a part of each URL,
// so no error of TelegramAPI holds a URL, a net/http error, or the token. Its
// sendTimeout field limits each sendMessage, sendRichMessage, and
// sendChatAction call.
type TelegramAPI struct {
        base        string
        token       string
        http        *http.Client
        sendTimeout time.Duration
}

// GetUpdates waits for the updates from offset on, up to telegramPollSeconds,
// and returns them. Telegram forgets each update before offset. Only new
// messages are asked for.
func (b *TelegramAPI) GetUpdates(ctx context.Context, offset int64) ([]TelegramUpdate, error) {
        var updates []TelegramUpdate

        err := b.call(ctx, telegramPollTimeout, "getUpdates", map[string]any{
                "offset":          offset,
                "timeout":         telegramPollSeconds,
                "allowed_updates": []string{"message"},
        }, &updates)

        return updates, err
}

// GetImage downloads a file through the authenticated file endpoint. Errors
// never include its token or URL, and the body is limited before storage.
func (b *TelegramAPI) GetImage(ctx context.Context, id string) (data []byte, err error) {
        var file struct {
                Path string `json:"file_path"`
                Size int64  `json:"file_size"`
        }

        err = b.call(ctx, b.sendTimeout, "getFile", map[string]any{"file_id": id}, &file)
        if err != nil {
                return nil, fmt.Errorf("get image file: %w", err)
        }

        if file.Size > imageMaxBytes {
                return nil, errImageSize
        }

        if file.Path == "" || path.Clean(file.Path) != file.Path || strings.HasPrefix(file.Path, "/") || strings.HasPrefix(file.Path, "../") || strings.ContainsAny(file.Path, "?%#\\") {
                return nil, errors.New("invalid image file path")
        }

        ctx, cancel := context.WithTimeout(ctx, b.sendTimeout)
        defer cancel()

        request, err := http.NewRequestWithContext(ctx, http.MethodGet, b.base+"/file/bot"+b.token+"/"+file.Path, nil)
        if err != nil {
                return nil, fmt.Errorf("make image request: %s", b.redact(err))
        }

        response, err := b.http.Do(request)
        if err != nil {
                return nil, b.networkError("image download failed", err, b.sendTimeout)
        }

        defer func() {
                closeErr := response.Body.Close()
                if closeErr != nil {
                        err = errors.Join(err, b.networkError("close image download", closeErr, b.sendTimeout))
                }
        }()

        if response.StatusCode != http.StatusOK {
                return nil, &TelegramError{
                        Status:      response.StatusCode,
                        Description: http.StatusText(response.StatusCode),
                }
        }

        data, err = io.ReadAll(io.LimitReader(response.Body, imageMaxBytes+1))
        if err != nil {
                return nil, b.networkError("image cut off", err, b.sendTimeout)
        }

        if len(data) > imageMaxBytes {
                return nil, errImageSize
        }

        return data, nil
}

// SendMessage sends text to chat with the format of entities, with no parse
// mode, so the text needs no escaping. With no entities, the text is plain. A
// call that takes longer than telegramSendTimeout fails with a
// TelegramNetworkError.
func (b *TelegramAPI) SendMessage(ctx context.Context, chat int64, text string, entities []TelegramEntity) error {
        params := map[string]any{
                "chat_id": chat,
                "text":    text,
        }

        if len(entities) > 0 {
                params["entities"] = entities
        }

        return b.call(ctx, b.sendTimeout, "sendMessage", params, nil)
}

// SendRichMessage sends markdown to chat as a rich message, which Telegram
// renders itself, tables included. A call that takes longer than
// telegramSendTimeout fails with a TelegramNetworkError.
func (b *TelegramAPI) SendRichMessage(ctx context.Context, chat int64, markdown string) error {
        return b.call(ctx, b.sendTimeout, "sendRichMessage", map[string]any{
                "chat_id": chat,
                "rich_message": map[string]any{
                        "markdown": markdown,
                },
        }, nil)
}

// SendTyping shows the typing action in chat for about five seconds. A call
// that takes longer than telegramSendTimeout fails with a TelegramNetworkError.
func (b *TelegramAPI) SendTyping(ctx context.Context, chat int64) error {
        return b.call(ctx, b.sendTimeout, "sendChatAction", map[string]any{
                "chat_id": chat,
                "action":  "typing",
        }, nil)
}

// call sends one call of method with the JSON params and decodes its result
// into result, when result is not nil. The call can take up to timeout. Its
// errors tell the cause in plain words, with no method name, so that a log line
// can say first what the call was for.
func (b *TelegramAPI) call(ctx context.Context, timeout time.Duration, method string, params, result any) error {
        ctx, cancel := context.WithTimeout(ctx, timeout)
        defer cancel()

        body, err := json.Marshal(params)
        if err != nil {
                return fmt.Errorf("%s: encode request: %w", method, err)
        }

        request, err := http.NewRequestWithContext(ctx, http.MethodPost, b.base+"/bot"+b.token+"/"+method, bytes.NewReader(body))
        if err != nil {
                return fmt.Errorf("%s: make request: %s", method, b.redact(err))
        }

        request.Header.Set("Content-Type", "application/json")

        response, err := b.http.Do(request)
        if err != nil {
                return b.networkError("no answer", err, timeout)
        }

        data, err := io.ReadAll(io.LimitReader(response.Body, telegramAnswerBytes))
        err = errors.Join(err, response.Body.Close())
        if err != nil {
                return b.networkError("answer cut off", err, timeout)
        }

        var answer TelegramAnswer

        err = json.Unmarshal(data, &answer)
        if err != nil && response.StatusCode != http.StatusOK {
                return &TelegramError{
                        Status:      response.StatusCode,
                        Description: http.StatusText(response.StatusCode),
                }
        }

        if err != nil {
                return b.networkError("invalid JSON", err, timeout)
        }

        if !answer.OK {
                return &TelegramError{
                        Status:      response.StatusCode,
                        Description: b.redact(errors.New(answer.Description)),
                        RetryAfter:  time.Duration(answer.Parameters.RetryAfter) * time.Second,
                        Refused:     true,
                }
        }

        if result == nil {
                return nil
        }

        err = json.Unmarshal(answer.Result, result)
        if err != nil {
                return b.networkError("invalid result", err, timeout)
        }

        return nil
}

// networkError returns the TelegramNetworkError of err, which happened at the
// step that what names. When the call used all of its time timeout, the cause
// is "no answer in TIMEOUT", because the Go text of a deadline does not tell
// how long the wait was.
func (b *TelegramAPI) networkError(what string, err error, timeout time.Duration) error {
        if errors.Is(err, context.DeadlineExceeded) {
                return &TelegramNetworkError{
                        Cause: "no answer in " + timeout.String(),
                }
        }

        return &TelegramNetworkError{
                Cause: what + ": " + b.redact(err),
        }
}

// redact returns the text of err without a URL and without the token. A
// *url.Error holds the URL of the call, which holds the token, so only its
// cause is kept.
func (b *TelegramAPI) redact(err error) string {
        var urlError *url.Error

        if errors.As(err, &urlError) {
                err = urlError.Err
        }

        return strings.ReplaceAll(err.Error(), b.token, "TOKEN")
}

// TelegramNetworkError tells that a Bot API call got no valid answer, such as
// after a network error. A later call can work. Cause tells why in plain words,
// with no URL and no token.
type TelegramNetworkError struct {
        Cause string
}

func (e *TelegramNetworkError) Error() string {
        return e.Cause
}

// TelegramError is an answer of the Bot API that tells of a failure. Its text
// gives the HTTP status and the description, such as "502 Bad Gateway".
// RetryAfter is the wait that the Bot API asks for after HTTP 429. Refused
// tells that the answer is a Bot API answer with ok false, not a page of a
// proxy or of a server error.
type TelegramError struct {
        Status      int
        Description string
        RetryAfter  time.Duration
        Refused     bool
}

func (e *TelegramError) Error() string {
        return fmt.Sprintf("%d %s", e.Status, e.Description)
}

// TelegramUpdate is one update of getUpdates. Message is nil for the kinds of
// updates that are not a new message.
type TelegramUpdate struct {
        UpdateID int64            `json:"update_id"`
        Message  *TelegramMessage `json:"message"`
}

// TelegramEntity is a message entity of sendMessage: a part of the text with a
// format, such as bold or a link. Offset and Length count UTF-16 code units.
// URL is the target of a text_link, and Language the language of a pre.
type TelegramEntity struct {
        Type     string `json:"type"`
        Offset   int    `json:"offset"`
        Length   int    `json:"length"`
        URL      string `json:"url,omitempty"`
        Language string `json:"language,omitempty"`
}

// TelegramAnswer is the envelope of each answer of the Bot API.
type TelegramAnswer struct {
        OK          bool            `json:"ok"`
        Result      json.RawMessage `json:"result"`
        ErrorCode   int             `json:"error_code"`
        Description string          `json:"description"`
        Parameters  struct {
                RetryAfter int `json:"retry_after"`
        } `json:"parameters"`
}

// TelegramMessage holds the text, caption, and image sizes of a bot message.
type TelegramMessage struct {
        Chat     TelegramChat      `json:"chat"`
        From     *TelegramUser     `json:"from"`
        Text     string            `json:"text"`
        Caption  string            `json:"caption"`
        Photo    []TelegramPhoto   `json:"photo"`
        Document *TelegramDocument `json:"document"`
}

// TelegramPhoto is one supplied size of a photo.
type TelegramPhoto struct {
        FileID   string `json:"file_id"`
        Width    int    `json:"width"`
        Height   int    `json:"height"`
        FileSize int64  `json:"file_size"`
}

// TelegramDocument is a file sent without photo compression.
type TelegramDocument struct {
        FileID   string `json:"file_id"`
        MimeType string `json:"mime_type"`
        FileSize int64  `json:"file_size"`
}

// TelegramChat is the chat of a message. Type is private for a chat with one
// user.
type TelegramChat struct {
        ID   int64  `json:"id"`
        Type string `json:"type"`
}

// TelegramUser is the sender of a message.
type TelegramUser struct {
        ID int64 `json:"id"`
}