internal/vfs/serving/serving.go

// Copyright 2009 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.

package serving

import (
	"context"
	"errors"
	"io"
	"net/http"
	"net/textproto"
	"strings"
	"time"

	"gitlab.com/gitlab-org/gitlab-pages/internal/errortracking"
	"gitlab.com/gitlab-org/gitlab-pages/internal/feature"
	"gitlab.com/gitlab-org/gitlab-pages/internal/httperrors"
	"gitlab.com/gitlab-org/gitlab-pages/internal/logging"
	"gitlab.com/gitlab-org/gitlab-pages/internal/logging/slowlogs"
	"gitlab.com/gitlab-org/gitlab-pages/internal/vfs"
)

var errUnknownContentType = errors.New("serving: unknown content type")

// ServeCompressedFile is a modified version of https://github.com/golang/go/blob/go1.16.10/src/net/http/fs.go#L192
func ServeCompressedFile(w http.ResponseWriter, req *http.Request, modtime time.Time, content vfs.File) {
	serveContent(w, req, modtime, content)
}

// serveContent is a modified version of https://github.com/golang/go/blob/go1.16.10/src/net/http/fs.go#L221
// this function relies on the assumption that a Content-Type header is set
func serveContent(w http.ResponseWriter, r *http.Request, modtime time.Time, content vfs.File) {
	defer slowlogs.Recorder(r.Context(), "serving.serveContent")()

	setLastModified(w, modtime)
	done := checkPreconditions(w, r, modtime)
	if done {
		return
	}

	code := http.StatusOK

	_, haveType := w.Header()["Content-Type"]
	if !haveType {
		// this shouldn't happen

		errortracking.CaptureErrWithReqAndStackTrace(errUnknownContentType, r)
		logging.LogRequest(r).WithError(errUnknownContentType).Error("could not serve content")
		httperrors.Serve500(w)

		return
	}

	if r.Method == http.MethodHead {
		w.WriteHeader(code)
		return
	}

	handleContentCopy(w, r, content)
}

func handleContentCopy(w http.ResponseWriter, r *http.Request, content vfs.File) {
	defer slowlogs.Recorder(r.Context(), "serving.handleContentCopy")()
	if _, err := io.Copy(w, content); err != nil {
		if errors.Is(err, &vfs.ReadError{}) {
			if errors.Is(err, context.DeadlineExceeded) || errors.Is(err, context.Canceled) {
				return
			}
			logging.LogRequest(r).WithField("handle_read_errors", feature.HandleReadErrors.Enabled()).WithError(err).Error("error reading content")
			if feature.HandleReadErrors.Enabled() {
				errortracking.CaptureErrWithReqAndStackTrace(err, r)
				logging.LogRequest(r).WithError(err).Error("error reading content")
				httperrors.Serve500(w)
			}
		}
	}
}

// scanETag determines if a syntactically valid ETag is present at s. If so,
// the ETag and remaining text after consuming ETag is returned. Otherwise,
// it returns "", "".
func scanETag(s string) (etag string, remain string) {
	s = textproto.TrimString(s)
	start := 0
	if strings.HasPrefix(s, "W/") {
		start = 2
	}
	if len(s[start:]) < 2 || s[start] != '"' {
		return "", ""
	}
	// ETag is either W/"text" or "text".
	// See RFC 7232 2.3.
	for i := start + 1; i < len(s); i++ {
		c := s[i]
		switch {
		// Character values allowed in ETags.
		case c == 0x21 || c >= 0x23 && c <= 0x7E || c >= 0x80:
		case c == '"':
			return s[:i+1], s[i+1:]
		default:
			return "", ""
		}
	}
	return "", ""
}

// etagStrongMatch reports whether a and b match using strong ETag comparison.
// Assumes a and b are valid ETags.
func etagStrongMatch(a, b string) bool {
	return a == b && a != "" && a[0] == '"'
}

// etagWeakMatch reports whether a and b match using weak ETag comparison.
// Assumes a and b are valid ETags.
func etagWeakMatch(a, b string) bool {
	return strings.TrimPrefix(a, "W/") == strings.TrimPrefix(b, "W/")
}

// condResult is the result of an HTTP request precondition check.
// See https://tools.ietf.org/html/rfc7232 section 3.
type condResult int

const (
	condNone condResult = iota
	condTrue
	condFalse
)

func checkIfMatch(w http.ResponseWriter, r *http.Request) condResult {
	im := r.Header.Get("If-Match")
	if im == "" {
		return condNone
	}
	for {
		im = textproto.TrimString(im)
		if len(im) == 0 {
			break
		}
		if im[0] == ',' {
			im = im[1:]
			continue
		}
		if im[0] == '*' {
			return condTrue
		}
		etag, remain := scanETag(im)
		if etag == "" {
			break
		}
		if etagStrongMatch(etag, w.Header().Get("Etag")) {
			return condTrue
		}
		im = remain
	}

	return condFalse
}

func checkIfUnmodifiedSince(r *http.Request, modtime time.Time) condResult {
	ius := r.Header.Get("If-Unmodified-Since")
	if ius == "" || isZeroTime(modtime) {
		return condNone
	}
	t, err := http.ParseTime(ius)
	if err != nil {
		return condNone
	}

	// The Last-Modified header truncates sub-second precision so
	// the modtime needs to be truncated too.
	modtime = modtime.Truncate(time.Second)
	if modtime.Before(t) || modtime.Equal(t) {
		return condTrue
	}
	return condFalse
}

func checkIfNoneMatch(w http.ResponseWriter, r *http.Request) condResult {
	inm := r.Header.Get("If-None-Match")
	if inm == "" {
		return condNone
	}
	buf := inm
	for {
		buf = textproto.TrimString(buf)
		if len(buf) == 0 {
			break
		}
		if buf[0] == ',' {
			buf = buf[1:]
			continue
		}
		if buf[0] == '*' {
			return condFalse
		}
		etag, remain := scanETag(buf)
		if etag == "" {
			break
		}
		if etagWeakMatch(etag, w.Header().Get("Etag")) {
			return condFalse
		}
		buf = remain
	}
	return condTrue
}

func checkIfModifiedSince(r *http.Request, modtime time.Time) condResult {
	if r.Method != http.MethodGet && r.Method != http.MethodHead {
		return condNone
	}
	ims := r.Header.Get("If-Modified-Since")
	if ims == "" || isZeroTime(modtime) {
		return condNone
	}
	t, err := http.ParseTime(ims)
	if err != nil {
		return condNone
	}
	// The Last-Modified header truncates sub-second precision so
	// the modtime needs to be truncated too.
	modtime = modtime.Truncate(time.Second)
	if modtime.Before(t) || modtime.Equal(t) {
		return condFalse
	}
	return condTrue
}

var unixEpochTime = time.Unix(0, 0)

// isZeroTime reports whether t is obviously unspecified (either zero or Unix()=0).
func isZeroTime(t time.Time) bool {
	return t.IsZero() || t.Equal(unixEpochTime)
}

func setLastModified(w http.ResponseWriter, modtime time.Time) {
	if !isZeroTime(modtime) {
		w.Header().Set("Last-Modified", modtime.UTC().Format(http.TimeFormat))
	}
}

func writeNotModified(w http.ResponseWriter) {
	// RFC 7232 section 4.1:
	// a sender SHOULD NOT generate representation metadata other than the
	// above listed fields unless said metadata exists for the purpose of
	// guiding cache updates (e.g., Last-Modified might be useful if the
	// response does not have an ETag field).
	h := w.Header()
	delete(h, "Content-Type")
	delete(h, "Content-Length")
	if h.Get("Etag") != "" {
		delete(h, "Last-Modified")
	}
	w.WriteHeader(http.StatusNotModified)
}

// checkPreconditions evaluates request preconditions and reports whether a precondition
// resulted in sending StatusNotModified or StatusPreconditionFailed.
func checkPreconditions(w http.ResponseWriter, r *http.Request, modtime time.Time) (done bool) {
	defer slowlogs.Recorder(r.Context(), "serving.checkPreconditions")()
	// This function carefully follows RFC 7232 section 6.
	ch := checkIfMatch(w, r)
	if ch == condNone {
		ch = checkIfUnmodifiedSince(r, modtime)
	}
	if ch == condFalse {
		w.WriteHeader(http.StatusPreconditionFailed)
		return true
	}
	switch checkIfNoneMatch(w, r) {
	case condFalse:
		if r.Method == http.MethodGet || r.Method == http.MethodHead {
			writeNotModified(w)
			return true
		}
		w.WriteHeader(http.StatusPreconditionFailed)
		return true
	case condNone:
		if checkIfModifiedSince(r, modtime) == condFalse {
			writeNotModified(w)
			return true
		}
	}

	return false
}