GoDoxy/socket-proxy/pkg/reverseproxy/reverse_proxy.go

// Copyright 2011 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// License URL: https://cs.opensource.google/go/go/+/master:LICENSE

// HTTP reverse proxy handler

package reverseproxy

import (
	"context"
	"errors"
	"fmt"
	"io"
	"log"
	"net"
	"net/http"
	"net/http/httptrace"
	"net/textproto"
	"net/url"
	"strings"
	"sync"
	"time"

	"github.com/yusing/go-proxy/internal/utils"
	"golang.org/x/net/http/httpguts"
)

// A ProxyRequest contains a request to be rewritten by a [ReverseProxy].
type ProxyRequest struct {
	// In is the request received by the proxy.
	// The Rewrite function must not modify In.
	In *http.Request

	// Out is the request which will be sent by the proxy.
	// The Rewrite function may modify or replace this request.
	// Hop-by-hop headers are removed from this request
	// before Rewrite is called.
	Out *http.Request
}

// SetURL routes the outbound request to the scheme, host, and base path
// provided in target. If the target's path is "/base" and the incoming
// request was for "/dir", the target request will be for "/base/dir".
//
// SetURL rewrites the outbound Host header to match the target's host.
// To preserve the inbound request's Host header (the default behavior
// of [NewSingleHostReverseProxy]):
//
//	rewriteFunc := func(r *httputil.ProxyRequest) {
//		r.SetURL(url)
//		r.Out.Host = r.In.Host
//	}
func (r *ProxyRequest) SetURL(target *url.URL) {
	rewriteRequestURL(r.Out, target)
	r.Out.Host = ""
}

// SetXForwarded sets the X-Forwarded-For, X-Forwarded-Host, and
// X-Forwarded-Proto headers of the outbound request.
//
//   - The X-Forwarded-For header is set to the client IP address.
//   - The X-Forwarded-Host header is set to the host name requested
//     by the client.
//   - The X-Forwarded-Proto header is set to "http" or "https", depending
//     on whether the inbound request was made on a TLS-enabled connection.
//
// If the outbound request contains an existing X-Forwarded-For header,
// SetXForwarded appends the client IP address to it. To append to the
// inbound request's X-Forwarded-For header (the default behavior of
// [ReverseProxy] when using a Director function), copy the header
// from the inbound request before calling SetXForwarded:
//
//	rewriteFunc := func(r *httputil.ProxyRequest) {
//		r.Out.Header["X-Forwarded-For"] = r.In.Header["X-Forwarded-For"]
//		r.SetXForwarded()
//	}
func (r *ProxyRequest) SetXForwarded() {
	clientIP, _, err := net.SplitHostPort(r.In.RemoteAddr)
	if err == nil {
		prior := r.Out.Header["X-Forwarded-For"]
		if len(prior) > 0 {
			clientIP = strings.Join(prior, ", ") + ", " + clientIP
		}
		r.Out.Header.Set("X-Forwarded-For", clientIP)
	} else {
		r.Out.Header.Del("X-Forwarded-For")
	}
	r.Out.Header.Set("X-Forwarded-Host", r.In.Host)
	if r.In.TLS == nil {
		r.Out.Header.Set("X-Forwarded-Proto", "http")
	} else {
		r.Out.Header.Set("X-Forwarded-Proto", "https")
	}
}

// ReverseProxy is an HTTP Handler that takes an incoming request and
// sends it to another server, proxying the response back to the
// client.
//
// 1xx responses are forwarded to the client if the underlying
// transport supports ClientTrace.Got1xxResponse.
type ReverseProxy struct {
	// Director is a function which modifies
	// the request into a new request to be sent
	// using Transport. Its response is then copied
	// back to the original client unmodified.
	// Director must not access the provided Request
	// after returning.
	//
	// By default, the X-Forwarded-For header is set to the
	// value of the client IP address. If an X-Forwarded-For
	// header already exists, the client IP is appended to the
	// existing values. As a special case, if the header
	// exists in the Request.Header map but has a nil value
	// (such as when set by the Director func), the X-Forwarded-For
	// header is not modified.
	//
	// To prevent IP spoofing, be sure to delete any pre-existing
	// X-Forwarded-For header coming from the client or
	// an untrusted proxy.
	//
	// Hop-by-hop headers are removed from the request after
	// Director returns, which can remove headers added by
	// Director. Use a Rewrite function instead to ensure
	// modifications to the request are preserved.
	//
	// Unparsable query parameters are removed from the outbound
	// request if Request.Form is set after Director returns.
	//
	// At most one of Rewrite or Director may be set.
	Director func(*http.Request)

	// The transport used to perform proxy requests.
	// If nil, http.DefaultTransport is used.
	Transport http.RoundTripper

	// FlushInterval specifies the flush interval
	// to flush to the client while copying the
	// response body.
	// If zero, no periodic flushing is done.
	// A negative value means to flush immediately
	// after each write to the client.
	// The FlushInterval is ignored when ReverseProxy
	// recognizes a response as a streaming response, or
	// if its ContentLength is -1; for such responses, writes
	// are flushed to the client immediately.
	FlushInterval time.Duration

	// ErrorLog specifies an optional logger for errors
	// that occur when attempting to proxy the request.
	// If nil, logging is done via the log package's standard logger.
	ErrorLog *log.Logger

	// BufferPool optionally specifies a buffer pool to
	// get byte slices for use by io.CopyBuffer when
	// copying HTTP response bodies.
	BufferPool BufferPool

	// ModifyResponse is an optional function that modifies the
	// Response from the backend. It is called if the backend
	// returns a response at all, with any HTTP status code.
	// If the backend is unreachable, the optional ErrorHandler is
	// called without any call to ModifyResponse.
	//
	// If ModifyResponse returns an error, ErrorHandler is called
	// with its error value. If ErrorHandler is nil, its default
	// implementation is used.
	ModifyResponse func(*http.Response) error

	// ErrorHandler is an optional function that handles errors
	// reaching the backend or errors from ModifyResponse.
	//
	// If nil, the default is to log the provided error and return
	// a 502 Status Bad Gateway response.
	ErrorHandler func(http.ResponseWriter, *http.Request, error)
}

// A BufferPool is an interface for getting and returning temporary
// byte slices for use by [io.CopyBuffer].
type BufferPool interface {
	Get() []byte
	Put([]byte)
}

func singleJoiningSlash(a, b string) string {
	aslash := strings.HasSuffix(a, "/")
	bslash := strings.HasPrefix(b, "/")
	switch {
	case aslash && bslash:
		return a + b[1:]
	case !aslash && !bslash:
		return a + "/" + b
	}
	return a + b
}

func joinURLPath(a, b *url.URL) (path, rawpath string) {
	if a.RawPath == "" && b.RawPath == "" {
		return singleJoiningSlash(a.Path, b.Path), ""
	}
	// Same as singleJoiningSlash, but uses EscapedPath to determine
	// whether a slash should be added
	apath := a.EscapedPath()
	bpath := b.EscapedPath()

	aslash := strings.HasSuffix(apath, "/")
	bslash := strings.HasPrefix(bpath, "/")

	switch {
	case aslash && bslash:
		return a.Path + b.Path[1:], apath + bpath[1:]
	case !aslash && !bslash:
		return a.Path + "/" + b.Path, apath + "/" + bpath
	}
	return a.Path + b.Path, apath + bpath
}

// NewSingleHostReverseProxy returns a new [ReverseProxy] that routes
// URLs to the scheme, host, and base path provided in target. If the
// target's path is "/base" and the incoming request was for "/dir",
// the target request will be for /base/dir.
//
// NewSingleHostReverseProxy does not rewrite the Host header.
//
// To customize the ReverseProxy behavior beyond what
// NewSingleHostReverseProxy provides, use ReverseProxy directly
// with a Rewrite function. The ProxyRequest SetURL method
// may be used to route the outbound request. (Note that SetURL,
// unlike NewSingleHostReverseProxy, rewrites the Host header
// of the outbound request by default.)
//
//	proxy := &ReverseProxy{
//		Rewrite: func(r *ProxyRequest) {
//			r.SetURL(target)
//			r.Out.Host = r.In.Host // if desired
//		},
//	}
func NewSingleHostReverseProxy(target *url.URL) *ReverseProxy {
	director := func(req *http.Request) {
		rewriteRequestURL(req, target)
	}
	return &ReverseProxy{Director: director}
}

func rewriteRequestURL(req *http.Request, target *url.URL) {
	targetQuery := target.RawQuery
	req.URL.Scheme = target.Scheme
	req.URL.Host = target.Host
	req.URL.Path, req.URL.RawPath = joinURLPath(target, req.URL)
	if targetQuery == "" || req.URL.RawQuery == "" {
		req.URL.RawQuery = targetQuery + req.URL.RawQuery
	} else {
		req.URL.RawQuery = targetQuery + "&" + req.URL.RawQuery
	}
}

func copyHeader(dst, src http.Header) {
	for k, vv := range src {
		for _, v := range vv {
			dst.Add(k, v)
		}
	}
}

// Hop-by-hop headers. These are removed when sent to the backend.
// As of RFC 7230, hop-by-hop headers are required to appear in the
// Connection header field. These are the headers defined by the
// obsoleted RFC 2616 (section 13.5.1) and are used for backward
// compatibility.
var hopHeaders = []string{
	"Connection",
	"Proxy-Connection", // non-standard but still sent by libcurl and rejected by e.g. google
	"Keep-Alive",
	"Proxy-Authenticate",
	"Proxy-Authorization",
	"Te",      // canonicalized version of "TE"
	"Trailer", // not Trailers per URL above; https://www.rfc-editor.org/errata_search.php?eid=4522
	"Transfer-Encoding",
	"Upgrade",
}

func (p *ReverseProxy) defaultErrorHandler(rw http.ResponseWriter, req *http.Request, err error) {
	p.logf("http: proxy error: %v", err)
	rw.WriteHeader(http.StatusBadGateway)
}

func (p *ReverseProxy) getErrorHandler() func(http.ResponseWriter, *http.Request, error) {
	if p.ErrorHandler != nil {
		return p.ErrorHandler
	}
	return p.defaultErrorHandler
}

// modifyResponse conditionally runs the optional ModifyResponse hook
// and reports whether the request should proceed.
func (p *ReverseProxy) modifyResponse(rw http.ResponseWriter, res *http.Response, req *http.Request) bool {
	if p.ModifyResponse == nil {
		return true
	}
	if err := p.ModifyResponse(res); err != nil {
		res.Body.Close()
		p.getErrorHandler()(rw, req, err)
		return false
	}
	return true
}

func (p *ReverseProxy) ServeHTTP(rw http.ResponseWriter, req *http.Request) {
	transport := p.Transport
	ctx := req.Context()

	outreq := req.Clone(ctx)
	if req.ContentLength == 0 {
		outreq.Body = nil // Issue 16036: nil Body for http.Transport retries
	}
	if outreq.Body != nil {
		// Reading from the request body after returning from a handler is not
		// allowed, and the RoundTrip goroutine that reads the Body can outlive
		// this handler. This can lead to a crash if the handler panics (see
		// Issue 46866). Although calling Close doesn't guarantee there isn't
		// any Read in flight after the handle returns, in practice it's safe to
		// read after closing it.
		defer outreq.Body.Close()
	}
	if outreq.Header == nil {
		outreq.Header = make(http.Header) // Issue 33142: historical behavior was to always allocate
	}

	p.Director(outreq)
	if outreq.Form != nil {
		outreq.URL.RawQuery = cleanQueryParams(outreq.URL.RawQuery)
	}
	outreq.Close = false

	reqUpType := upgradeType(outreq.Header)
	if !IsPrint(reqUpType) {
		p.getErrorHandler()(rw, req, fmt.Errorf("client tried to switch to invalid protocol %q", reqUpType))
		return
	}
	removeHopByHopHeaders(outreq.Header)

	// Issue 21096: tell backend applications that care about trailer support
	// that we support trailers. (We do, but we don't go out of our way to
	// advertise that unless the incoming client request thought it was worth
	// mentioning.) Note that we look at req.Header, not outreq.Header, since
	// the latter has passed through removeHopByHopHeaders.
	if httpguts.HeaderValuesContainsToken(req.Header["Te"], "trailers") {
		outreq.Header.Set("Te", "trailers")
	}

	if _, ok := outreq.Header["User-Agent"]; !ok {
		// If the outbound request doesn't have a User-Agent header set,
		// don't send the default Go HTTP client User-Agent.
		outreq.Header.Set("User-Agent", "")
	}

	var (
		roundTripMutex sync.Mutex
		roundTripDone  bool
	)
	trace := &httptrace.ClientTrace{
		Got1xxResponse: func(code int, header textproto.MIMEHeader) error {
			roundTripMutex.Lock()
			defer roundTripMutex.Unlock()
			if roundTripDone {
				// If RoundTrip has returned, don't try to further modify
				// the ResponseWriter's header map.
				return nil
			}
			h := rw.Header()
			copyHeader(h, http.Header(header))
			rw.WriteHeader(code)

			// Clear headers, it's not automatically done by ResponseWriter.WriteHeader() for 1xx responses
			clear(h)
			return nil
		},
	}
	outreq = outreq.WithContext(httptrace.WithClientTrace(outreq.Context(), trace))

	res, err := transport.RoundTrip(outreq)
	roundTripMutex.Lock()
	roundTripDone = true
	roundTripMutex.Unlock()
	if err != nil {
		p.getErrorHandler()(rw, outreq, err)
		return
	}

	// Deal with 101 Switching Protocols responses: (WebSocket, h2c, etc)
	if res.StatusCode == http.StatusSwitchingProtocols {
		if !p.modifyResponse(rw, res, outreq) {
			return
		}
		p.handleUpgradeResponse(rw, outreq, res)
		return
	}

	removeHopByHopHeaders(res.Header)

	if !p.modifyResponse(rw, res, outreq) {
		return
	}

	copyHeader(rw.Header(), res.Header)

	// The "Trailer" header isn't included in the Transport's response,
	// at least for *http.Transport. Build it up from Trailer.
	announcedTrailers := len(res.Trailer)
	if announcedTrailers > 0 {
		trailerKeys := make([]string, 0, len(res.Trailer))
		for k := range res.Trailer {
			trailerKeys = append(trailerKeys, k)
		}
		rw.Header().Add("Trailer", strings.Join(trailerKeys, ", "))
	}

	rw.WriteHeader(res.StatusCode)

	err = utils.CopyCloseWithContext(ctx, rw, res.Body)
	if err != nil {
		if !errors.Is(err, context.Canceled) {
			p.getErrorHandler()(rw, req, err)
		}
		return
	}

	if len(res.Trailer) > 0 {
		// Force chunking if we saw a response trailer.
		// This prevents net/http from calculating the length for short
		// bodies and adding a Content-Length.
		http.NewResponseController(rw).Flush()
	}

	if len(res.Trailer) == announcedTrailers {
		copyHeader(rw.Header(), res.Trailer)
		return
	}

	for k, vv := range res.Trailer {
		k = http.TrailerPrefix + k
		for _, v := range vv {
			rw.Header().Add(k, v)
		}
	}
}

// removeHopByHopHeaders removes hop-by-hop headers.
func removeHopByHopHeaders(h http.Header) {
	// RFC 7230, section 6.1: Remove headers listed in the "Connection" header.
	for _, f := range h["Connection"] {
		for sf := range strings.SplitSeq(f, ",") {
			if sf = textproto.TrimString(sf); sf != "" {
				h.Del(sf)
			}
		}
	}
	// RFC 2616, section 13.5.1: Remove a set of known hop-by-hop headers.
	// This behavior is superseded by the RFC 7230 Connection header, but
	// preserve it for backwards compatibility.
	for _, f := range hopHeaders {
		h.Del(f)
	}
}

func (p *ReverseProxy) logf(format string, args ...any) {
	if p.ErrorLog != nil {
		p.ErrorLog.Printf(format, args...)
	} else {
		log.Printf(format, args...)
	}
}

func upgradeType(h http.Header) string {
	if !httpguts.HeaderValuesContainsToken(h["Connection"], "Upgrade") {
		return ""
	}
	return h.Get("Upgrade")
}

func (p *ReverseProxy) handleUpgradeResponse(rw http.ResponseWriter, req *http.Request, res *http.Response) {
	reqUpType := upgradeType(req.Header)
	resUpType := upgradeType(res.Header)
	if !IsPrint(resUpType) { // We know reqUpType is ASCII, it's checked by the caller.
		p.getErrorHandler()(rw, req, fmt.Errorf("backend tried to switch to invalid protocol %q", resUpType))
		return
	}
	if !strings.EqualFold(reqUpType, resUpType) {
		p.getErrorHandler()(rw, req, fmt.Errorf("backend tried to switch protocol %q when %q was requested", resUpType, reqUpType))
		return
	}

	backConn, ok := res.Body.(io.ReadWriteCloser)
	if !ok {
		p.getErrorHandler()(rw, req, fmt.Errorf("internal error: 101 switching protocols response with non-writable body"))
		return
	}

	rc := http.NewResponseController(rw)
	conn, brw, hijackErr := rc.Hijack()
	if errors.Is(hijackErr, http.ErrNotSupported) {
		p.getErrorHandler()(rw, req, fmt.Errorf("can't switch protocols using non-Hijacker ResponseWriter type %T", rw))
		return
	}

	backConnCloseCh := make(chan bool)
	go func() {
		// Ensure that the cancellation of a request closes the backend.
		// See issue https://golang.org/issue/35559.
		select {
		case <-req.Context().Done():
		case <-backConnCloseCh:
		}
		backConn.Close()
	}()
	defer close(backConnCloseCh)

	if hijackErr != nil {
		p.getErrorHandler()(rw, req, fmt.Errorf("Hijack failed on protocol switch: %v", hijackErr))
		return
	}
	defer conn.Close()

	copyHeader(rw.Header(), res.Header)

	res.Header = rw.Header()
	res.Body = nil // so res.Write only writes the headers; we have res.Body in backConn above
	if err := res.Write(brw); err != nil {
		p.getErrorHandler()(rw, req, fmt.Errorf("response write: %v", err))
		return
	}
	if err := brw.Flush(); err != nil {
		p.getErrorHandler()(rw, req, fmt.Errorf("response flush: %v", err))
		return
	}
	errc := make(chan error, 1)
	spc := switchProtocolCopier{user: conn, backend: backConn}
	go spc.copyToBackend(errc)
	go spc.copyFromBackend(errc)
	<-errc
}

// switchProtocolCopier exists so goroutines proxying data back and
// forth have nice names in stacks.
type switchProtocolCopier struct {
	user, backend io.ReadWriter
}

func (c switchProtocolCopier) copyFromBackend(errc chan<- error) {
	_, err := io.Copy(c.user, c.backend)
	errc <- err
}

func (c switchProtocolCopier) copyToBackend(errc chan<- error) {
	_, err := io.Copy(c.backend, c.user)
	errc <- err
}

func cleanQueryParams(s string) string {
	reencode := func(s string) string {
		v, _ := url.ParseQuery(s)
		return v.Encode()
	}
	for i := 0; i < len(s); {
		switch s[i] {
		case ';':
			return reencode(s)
		case '%':
			if i+2 >= len(s) || !ishex(s[i+1]) || !ishex(s[i+2]) {
				return reencode(s)
			}
			i += 3
		default:
			i++
		}
	}
	return s
}

func ishex(c byte) bool {
	switch {
	case '0' <= c && c <= '9':
		return true
	case 'a' <= c && c <= 'f':
		return true
	case 'A' <= c && c <= 'F':
		return true
	}
	return false
}

func IsPrint(s string) bool {
	for _, r := range s {
		if r < ' ' || r > '~' {
			return false
		}
	}
	return true
}