package http import ( "bufio" "bytes" "context" "crypto/tls" "errors" "fmt" "io" "mime" "mime/multipart" "net/textproto" "net/url" urlpkg "net/url" "strconv" "strings" "sync" ) func badStringError(what, val string) error { return fmt.Errorf("%s %q", what, val) } type Request struct { // Method specifies the HTTP method (GET, POST, PUT, etc.). // For client requests, an empty string means GET. // // Go's HTTP client does not support sending a request with // the CONNECT method. See the documentation on Transport for // details. Method string // URL specifies either the URI being requested (for server // requests) or the URL to access (for client requests). // // For server requests, the URL is parsed from the URI // supplied on the Request-Line as stored in RequestURI. For // most requests, fields other than Path and RawQuery will be // empty. (See RFC 7230, Section 5.3) // // For client requests, the URL's Host specifies the server to // connect to, while the Request's Host field optionally // specifies the Host header value to send in the HTTP // request. URL *url.URL // The protocol version for incoming server requests. // // For client requests, these fields are ignored. The HTTP // client code always uses either HTTP/1.1 or HTTP/2. // See the docs on Transport for details. Proto string // "HTTP/1.0" ProtoMajor int // 1 ProtoMinor int // 0 // Header contains the request header fields either received // by the server or to be sent by the client. // // If a server received a request with header lines, // // Host: example.com // accept-encoding: gzip, deflate // Accept-Language: en-us // fOO: Bar // foo: two // // then // // Header = map[string][]string{ // "Accept-Encoding": {"gzip, deflate"}, // "Accept-Language": {"en-us"}, // "Foo": {"Bar", "two"}, // } // // For incoming requests, the Host header is promoted to the // Request.Host field and removed from the Header map. // // HTTP defines that header names are case-insensitive. The // request parser implements this by using CanonicalHeaderKey, // making the first character and any characters following a // hyphen uppercase and the rest lowercase. // // For client requests, certain headers such as Content-Length // and Connection are automatically written when needed and // values in Header may be ignored. See the documentation // for the Request.Write method. Header Header // Body is the request's body. // // For client requests, a nil body means the request has no // body, such as a GET request. The HTTP Client's Transport // is responsible for calling the Close method. // // For server requests, the Request Body is always non-nil // but will return EOF immediately when no body is present. // The Server will close the request body. The ServeHTTP // Handler does not need to. // // Body must allow Read to be called concurrently with Close. // In particular, calling Close should unblock a Read waiting // for input. Body io.ReadCloser // GetBody defines an optional func to return a new copy of // Body. It is used for client requests when a redirect requires // reading the body more than once. Use of GetBody still // requires setting Body. // // For server requests, it is unused. GetBody func() (io.ReadCloser, error) // ContentLength records the length of the associated content. // The value -1 indicates that the length is unknown. // Values >= 0 indicate that the given number of bytes may // be read from Body. // // For client requests, a value of 0 with a non-nil Body is // also treated as unknown. ContentLength int64 // TransferEncoding lists the transfer encodings from outermost to // innermost. An empty list denotes the "identity" encoding. // TransferEncoding can usually be ignored; chunked encoding is // automatically added and removed as necessary when sending and // receiving requests. TransferEncoding []string // Close indicates whether to close the connection after // replying to this request (for servers) or after sending this // request and reading its response (for clients). // // For server requests, the HTTP server handles this automatically // and this field is not needed by Handlers. // // For client requests, setting this field prevents re-use of // TCP connections between requests to the same hosts, as if // Transport.DisableKeepAlives were set. Close bool // For server requests, Host specifies the host on which the // URL is sought. For HTTP/1 (per RFC 7230, section 5.4), this // is either the value of the "Host" header or the host name // given in the URL itself. For HTTP/2, it is the value of the // ":authority" pseudo-header field. // It may be of the form "host:port". For international domain // names, Host may be in Punycode or Unicode form. Use // golang.org/x/net/idna to convert it to either format if // needed. // To prevent DNS rebinding attacks, server Handlers should // validate that the Host header has a value for which the // Handler considers itself authoritative. The included // ServeMux supports patterns registered to particular host // names and thus protects its registered Handlers. // // For client requests, Host optionally overrides the Host // header to send. If empty, the Request.Write method uses // the value of URL.Host. Host may contain an international // domain name. Host string // Form contains the parsed form data, including both the URL // field's query parameters and the PATCH, POST, or PUT form data. // This field is only available after ParseForm is called. // The HTTP client ignores Form and uses Body instead. Form url.Values // PostForm contains the parsed form data from PATCH, POST // or PUT body parameters. // // This field is only available after ParseForm is called. // The HTTP client ignores PostForm and uses Body instead. PostForm url.Values // MultipartForm is the parsed multipart form, including file uploads. // This field is only available after ParseMultipartForm is called. // The HTTP client ignores MultipartForm and uses Body instead. MultipartForm *multipart.Form // Trailer specifies additional headers that are sent after the request // body. // // For server requests, the Trailer map initially contains only the // trailer keys, with nil values. (The client declares which trailers it // will later send.) While the handler is reading from Body, it must // not reference Trailer. After reading from Body returns EOF, Trailer // can be read again and will contain non-nil values, if they were sent // by the client. // // For client requests, Trailer must be initialized to a map containing // the trailer keys to later send. The values may be nil or their final // values. The ContentLength must be 0 or -1, to send a chunked request. // After the HTTP request is sent the map values can be updated while // the request body is read. Once the body returns EOF, the caller must // not mutate Trailer. // // Few HTTP clients, servers, or proxies support HTTP trailers. Trailer Header // RemoteAddr allows HTTP servers and other software to record // the network address that sent the request, usually for // logging. This field is not filled in by ReadRequest and // has no defined format. The HTTP server in this package // sets RemoteAddr to an "IP:port" address before invoking a // handler. // This field is ignored by the HTTP client. RemoteAddr string // RequestURI is the unmodified request-target of the // Request-Line (RFC 7230, Section 3.1.1) as sent by the client // to a server. Usually the URL field should be used instead. // It is an error to set this field in an HTTP client request. RequestURI string // TLS allows HTTP servers and other software to record // information about the TLS connection on which the request // was received. This field is not filled in by ReadRequest. // The HTTP server in this package sets the field for // TLS-enabled connections before invoking a handler; // otherwise it leaves the field nil. // This field is ignored by the HTTP client. TLS *tls.ConnectionState // Cancel is an optional channel whose closure indicates that the client // request should be regarded as canceled. Not all implementations of // RoundTripper may support Cancel. // // For server requests, this field is not applicable. // // Deprecated: Set the Request's context with NewRequestWithContext // instead. If a Request's Cancel field and context are both // set, it is undefined whether Cancel is respected. Cancel <-chan struct{} // Response is the redirect response which caused this request // to be created. This field is only populated during client // redirects. Response *Response // ctx is either the client or server context. It should only // be modified via copying the whole Request using WithContext. // It is unexported to prevent people from using Context wrong // and mutating the contexts held by callers of the same request. ctx context.Context } // ProtoAtLeast reports whether the HTTP protocol used // in the request is at least major.minor. func (r *Request) ProtoAtLeast(major, minor int) bool { return r.ProtoMajor > major || r.ProtoMajor == major && r.ProtoMinor >= minor } // UserAgent returns the client's User-Agent, if sent in the request. func (r *Request) UserAgent() string { return r.Header.Get("User-Agent") } // Cookies parses and returns the HTTP cookies sent with the request. func (r *Request) Cookies() []*Cookie { return readCookies(r.Header, "") } // ErrNoCookie is returned by Request's Cookie method when a cookie is not found. var ErrNoCookie = errors.New("http: named cookie not present") // Cookie returns the named cookie provided in the request or // ErrNoCookie if not found. // If multiple cookies match the given name, only one cookie will // be returned. func (r *Request) Cookie(name string) (*Cookie, error) { for _, c := range readCookies(r.Header, name) { return c, nil } return nil, ErrNoCookie } // AddCookie adds a cookie to the request. Per RFC 6265 section 5.4, // AddCookie does not attach more than one Cookie header field. That // means all cookies, if any, are written into the same line, // separated by semicolon. // AddCookie only sanitizes c's name and value, and does not sanitize // a Cookie header already present in the request. func (r *Request) AddCookie(c *Cookie) { s := fmt.Sprintf("%s=%s", sanitizeCookieName(c.Name), sanitizeCookieValue(c.Value)) if c := r.Header.Get("Cookie"); c != "" { r.Header.Set("Cookie", c+"; "+s) } else { r.Header.Set("Cookie", s) } } // Referer returns the referring URL, if sent in the request. // // Referer is misspelled as in the request itself, a mistake from the // earliest days of HTTP. This value can also be fetched from the // Header map as Header["Referer"]; the benefit of making it available // as a method is that the compiler can diagnose programs that use the // alternate (correct English) spelling req.Referrer() but cannot // diagnose programs that use Header["Referrer"]. func (r *Request) Referer() string { return r.Header.Get("Referer") } // isH2Upgrade reports whether r represents the http2 "client preface" // magic string. func (r *Request) isH2Upgrade() bool { return r.Method == "PRI" && len(r.Header) == 0 && r.URL.Path == "*" && r.Proto == "HTTP/2.0" } // ParseHTTPVersion parses an HTTP version string. // "HTTP/1.0" returns (1, 0, true). func ParseHTTPVersion(vers string) (major, minor int, ok bool) { const Big = 1000000 // arbitrary upper bound switch vers { case "HTTP/1.1": return 1, 1, true case "HTTP/1.0": return 1, 0, true } if !strings.HasPrefix(vers, "HTTP/") { return 0, 0, false } dot := strings.Index(vers, ".") if dot < 0 { return 0, 0, false } major, err := strconv.Atoi(vers[5:dot]) if err != nil || major < 0 || major > Big { return 0, 0, false } minor, err = strconv.Atoi(vers[dot+1:]) if err != nil || minor < 0 || minor > Big { return 0, 0, false } return major, minor, true } func validMethod(method string) bool { /* Method = "OPTIONS" ; Section 9.2 | "GET" ; Section 9.3 | "HEAD" ; Section 9.4 | "POST" ; Section 9.5 | "PUT" ; Section 9.6 | "DELETE" ; Section 9.7 | "TRACE" ; Section 9.8 | "CONNECT" ; Section 9.9 | extension-method extension-method = token token = 1* */ return len(method) > 0 && strings.IndexFunc(method, isNotToken) == -1 } // NewRequest wraps NewRequestWithContext using the background context. func NewRequest(method, url string, body io.Reader) (*Request, error) { return NewRequestWithContext(context.Background(), method, url, body) } // NewRequestWithContext returns a new Request given a method, URL, and // optional body. // // If the provided body is also an io.Closer, the returned // Request.Body is set to body and will be closed by the Client // methods Do, Post, and PostForm, and Transport.RoundTrip. // // NewRequestWithContext returns a Request suitable for use with // Client.Do or Transport.RoundTrip. To create a request for use with // testing a Server Handler, either use the NewRequest function in the // net/http/httptest package, use ReadRequest, or manually update the // Request fields. For an outgoing client request, the context // controls the entire lifetime of a request and its response: // obtaining a connection, sending the request, and reading the // response headers and body. See the Request type's documentation for // the difference between inbound and outbound request fields. // // If body is of type *bytes.Buffer, *bytes.Reader, or // *strings.Reader, the returned request's ContentLength is set to its // exact value (instead of -1), GetBody is populated (so 307 and 308 // redirects can replay the body), and Body is set to NoBody if the // ContentLength is 0. func NewRequestWithContext(ctx context.Context, method, url string, body io.Reader) (*Request, error) { if method == "" { // We document that "" means "GET" for Request.Method, and people have // relied on that from NewRequest, so keep that working. // We still enforce validMethod for non-empty methods. method = "GET" } if !validMethod(method) { return nil, fmt.Errorf("net/http: invalid method %q", method) } if ctx == nil { return nil, errors.New("net/http: nil Context") } u, err := urlpkg.Parse(url) if err != nil { return nil, err } rc, ok := body.(io.ReadCloser) if !ok && body != nil { rc = io.NopCloser(body) } // The host's colon:port should be normalized. See Issue 14836. u.Host = removeEmptyPort(u.Host) req := &Request{ ctx: ctx, Method: method, URL: u, Proto: "HTTP/1.1", ProtoMajor: 1, ProtoMinor: 1, Header: make(Header), Body: rc, Host: u.Host, } if body != nil { switch v := body.(type) { case *bytes.Buffer: req.ContentLength = int64(v.Len()) buf := v.Bytes() req.GetBody = func() (io.ReadCloser, error) { r := bytes.NewReader(buf) return io.NopCloser(r), nil } case *bytes.Reader: req.ContentLength = int64(v.Len()) snapshot := *v req.GetBody = func() (io.ReadCloser, error) { r := snapshot return io.NopCloser(&r), nil } case *strings.Reader: req.ContentLength = int64(v.Len()) snapshot := *v req.GetBody = func() (io.ReadCloser, error) { r := snapshot return io.NopCloser(&r), nil } default: // This is where we'd set it to -1 (at least // if body != NoBody) to mean unknown, but // that broke people during the Go 1.8 testing // period. People depend on it being 0 I // guess. Maybe retry later. See Issue 18117. } // For client requests, Request.ContentLength of 0 // means either actually 0, or unknown. The only way // to explicitly say that the ContentLength is zero is // to set the Body to nil. But turns out too much code // depends on NewRequest returning a non-nil Body, // so we use a well-known ReadCloser variable instead // and have the http package also treat that sentinel // variable to mean explicitly zero. if req.GetBody != nil && req.ContentLength == 0 { req.Body = NoBody req.GetBody = func() (io.ReadCloser, error) { return NoBody, nil } } } return req, nil } // parseRequestLine parses "GET /foo HTTP/1.1" into its three parts. func parseRequestLine(line string) (method, requestURI, proto string, ok bool) { s1 := strings.Index(line, " ") s2 := strings.Index(line[s1+1:], " ") if s1 < 0 || s2 < 0 { return } s2 += s1 + 1 return line[:s1], line[s1+1 : s2], line[s2+1:], true } var textprotoReaderPool sync.Pool func newTextprotoReader(br *bufio.Reader) *textproto.Reader { if v := textprotoReaderPool.Get(); v != nil { tr := v.(*textproto.Reader) tr.R = br return tr } return textproto.NewReader(br) } func putTextprotoReader(r *textproto.Reader) { r.R = nil textprotoReaderPool.Put(r) } // ReadRequest reads and parses an incoming request from b. // // ReadRequest is a low-level function and should only be used for // specialized applications; most code should use the Server to read // requests and handle them via the Handler interface. ReadRequest // only supports HTTP/1.x requests. For HTTP/2, use golang.org/x/net/http2. func ReadRequest(b *bufio.Reader) (*Request, error) { return readRequest(b, deleteHostHeader) } // Constants for readRequest's deleteHostHeader parameter. const ( deleteHostHeader = true keepHostHeader = false ) func readRequest(b *bufio.Reader, deleteHostHeader bool) (req *Request, err error) { tp := newTextprotoReader(b) req = new(Request) // First line: GET /index.html HTTP/1.0 var s string if s, err = tp.ReadLine(); err != nil { return nil, err } defer func() { putTextprotoReader(tp) if err == io.EOF { err = io.ErrUnexpectedEOF } }() var ok bool req.Method, req.RequestURI, req.Proto, ok = parseRequestLine(s) if !ok { return nil, badStringError("malformed HTTP request", s) } if !validMethod(req.Method) { return nil, badStringError("invalid method", req.Method) } rawurl := req.RequestURI if req.ProtoMajor, req.ProtoMinor, ok = ParseHTTPVersion(req.Proto); !ok { return nil, badStringError("malformed HTTP version", req.Proto) } // CONNECT requests are used two different ways, and neither uses a full URL: // The standard use is to tunnel HTTPS through an HTTP proxy. // It looks like "CONNECT www.google.com:443 HTTP/1.1", and the parameter is // just the authority section of a URL. This information should go in req.URL.Host. // // The net/rpc package also uses CONNECT, but there the parameter is a path // that starts with a slash. It can be parsed with the regular URL parser, // and the path will end up in req.URL.Path, where it needs to be in order for // RPC to work. justAuthority := req.Method == "CONNECT" && !strings.HasPrefix(rawurl, "/") if justAuthority { rawurl = "http://" + rawurl } if req.URL, err = url.ParseRequestURI(rawurl); err != nil { return nil, err } if justAuthority { // Strip the bogus "http://" back off. req.URL.Scheme = "" } // Subsequent lines: Key: value. mimeHeader, err := tp.ReadMIMEHeader() if err != nil { return nil, err } req.Header = Header(mimeHeader) // RFC 7230, section 5.3: Must treat // GET /index.html HTTP/1.1 // Host: www.google.com // and // GET http://www.google.com/index.html HTTP/1.1 // Host: doesntmatter // the same. In the second case, any Host line is ignored. req.Host = req.URL.Host if req.Host == "" { req.Host = req.Header.get("Host") } if deleteHostHeader { delete(req.Header, "Host") } fixPragmaCacheControl(req.Header) req.Close = shouldClose(req.ProtoMajor, req.ProtoMinor, req.Header, false) err = readTransfer(req, b) if err != nil { return nil, err } if req.isH2Upgrade() { // Because it's neither chunked, nor declared: req.ContentLength = -1 // We want to give handlers a chance to hijack the // connection, but we need to prevent the Server from // dealing with the connection further if it's not // hijacked. Set Close to ensure that: req.Close = true } return req, nil } // MaxBytesReader is similar to io.LimitReader but is intended for // limiting the size of incoming request bodies. In contrast to // io.LimitReader, MaxBytesReader's result is a ReadCloser, returns a // non-EOF error for a Read beyond the limit, and closes the // underlying reader when its Close method is called. // // MaxBytesReader prevents clients from accidentally or maliciously // sending a large request and wasting server resources. func MaxBytesReader(w ResponseWriter, r io.ReadCloser, n int64) io.ReadCloser { return &maxBytesReader{w: w, r: r, n: n} } type maxBytesReader struct { w ResponseWriter r io.ReadCloser // underlying reader n int64 // max bytes remaining err error // sticky error } func (l *maxBytesReader) Read(p []byte) (n int, err error) { if l.err != nil { return 0, l.err } if len(p) == 0 { return 0, nil } // If they asked for a 32KB byte read but only 5 bytes are // remaining, no need to read 32KB. 6 bytes will answer the // question of the whether we hit the limit or go past it. if int64(len(p)) > l.n+1 { p = p[:l.n+1] } n, err = l.r.Read(p) if int64(n) <= l.n { l.n -= int64(n) l.err = err return n, err } n = int(l.n) l.n = 0 // The server code and client code both use // maxBytesReader. This "requestTooLarge" check is // only used by the server code. To prevent binaries // which only using the HTTP Client code (such as // cmd/go) from also linking in the HTTP server, don't // use a static type assertion to the server // "*response" type. Check this interface instead: type requestTooLarger interface { requestTooLarge() } if res, ok := l.w.(requestTooLarger); ok { res.requestTooLarge() } l.err = errors.New("http: request body too large") return n, l.err } func (l *maxBytesReader) Close() error { return l.r.Close() } func copyValues(dst, src url.Values) { for k, vs := range src { dst[k] = append(dst[k], vs...) } } func parsePostForm(r *Request) (vs url.Values, err error) { if r.Body == nil { err = errors.New("missing form body") return } ct := r.Header.Get("Content-Type") // RFC 7231, section 3.1.1.5 - empty type // MAY be treated as application/octet-stream if ct == "" { ct = "application/octet-stream" } ct, _, err = mime.ParseMediaType(ct) switch { case ct == "application/x-www-form-urlencoded": var reader io.Reader = r.Body maxFormSize := int64(1<<63 - 1) if _, ok := r.Body.(*maxBytesReader); !ok { maxFormSize = int64(10 << 20) // 10 MB is a lot of text. reader = io.LimitReader(r.Body, maxFormSize+1) } b, e := io.ReadAll(reader) if e != nil { if err == nil { err = e } break } if int64(len(b)) > maxFormSize { err = errors.New("http: POST too large") return } vs, e = url.ParseQuery(string(b)) if err == nil { err = e } case ct == "multipart/form-data": // handled by ParseMultipartForm (which is calling us, or should be) // TODO(bradfitz): there are too many possible // orders to call too many functions here. // Clean this up and write more tests. // request_test.go contains the start of this, // in TestParseMultipartFormOrder and others. } return } // ParseForm populates r.Form and r.PostForm. // // For all requests, ParseForm parses the raw query from the URL and updates // r.Form. // // For POST, PUT, and PATCH requests, it also reads the request body, parses it // as a form and puts the results into both r.PostForm and r.Form. Request body // parameters take precedence over URL query string values in r.Form. // // If the request Body's size has not already been limited by MaxBytesReader, // the size is capped at 10MB. // // For other HTTP methods, or when the Content-Type is not // application/x-www-form-urlencoded, the request Body is not read, and // r.PostForm is initialized to a non-nil, empty value. // // ParseMultipartForm calls ParseForm automatically. // ParseForm is idempotent. func (r *Request) ParseForm() error { var err error if r.PostForm == nil { if r.Method == "POST" || r.Method == "PUT" || r.Method == "PATCH" { r.PostForm, err = parsePostForm(r) } if r.PostForm == nil { r.PostForm = make(url.Values) } } if r.Form == nil { if len(r.PostForm) > 0 { r.Form = make(url.Values) copyValues(r.Form, r.PostForm) } var newValues url.Values if r.URL != nil { var e error newValues, e = url.ParseQuery(r.URL.RawQuery) if err == nil { err = e } } if newValues == nil { newValues = make(url.Values) } if r.Form == nil { r.Form = newValues } else { copyValues(r.Form, newValues) } } return err }