diff options
Diffstat (limited to 'src/net/http/request.go')
| -rw-r--r-- | src/net/http/request.go | 1554 |
1 files changed, 1554 insertions, 0 deletions
diff --git a/src/net/http/request.go b/src/net/http/request.go new file mode 100644 index 0000000..99fdebc --- /dev/null +++ b/src/net/http/request.go @@ -0,0 +1,1554 @@ +// 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. + +// HTTP Request reading and parsing. + +package http + +import ( + "bufio" + "bytes" + "context" + "crypto/tls" + "encoding/base64" + "errors" + "fmt" + "io" + "mime" + "mime/multipart" + "net/http/httptrace" + "net/http/internal/ascii" + "net/textproto" + "net/url" + urlpkg "net/url" + "strconv" + "strings" + "sync" + + "golang.org/x/net/http/httpguts" + "golang.org/x/net/idna" +) + +const ( + defaultMaxMemory = 32 << 20 // 32 MB +) + +// ErrMissingFile is returned by FormFile when the provided file field name +// is either not present in the request or not a file field. +var ErrMissingFile = errors.New("http: no such file") + +// ProtocolError represents an HTTP protocol error. +// +// Deprecated: Not all errors in the http package related to protocol errors +// are of type ProtocolError. +type ProtocolError struct { + ErrorString string +} + +func (pe *ProtocolError) Error() string { return pe.ErrorString } + +// Is lets http.ErrNotSupported match errors.ErrUnsupported. +func (pe *ProtocolError) Is(err error) bool { + return pe == ErrNotSupported && err == errors.ErrUnsupported +} + +var ( + // ErrNotSupported indicates that a feature is not supported. + // + // It is returned by ResponseController methods to indicate that + // the handler does not support the method, and by the Push method + // of Pusher implementations to indicate that HTTP/2 Push support + // is not available. + ErrNotSupported = &ProtocolError{"feature not supported"} + + // Deprecated: ErrUnexpectedTrailer is no longer returned by + // anything in the net/http package. Callers should not + // compare errors against this variable. + ErrUnexpectedTrailer = &ProtocolError{"trailer header without chunked transfer encoding"} + + // ErrMissingBoundary is returned by Request.MultipartReader when the + // request's Content-Type does not include a "boundary" parameter. + ErrMissingBoundary = &ProtocolError{"no multipart boundary param in Content-Type"} + + // ErrNotMultipart is returned by Request.MultipartReader when the + // request's Content-Type is not multipart/form-data. + ErrNotMultipart = &ProtocolError{"request Content-Type isn't multipart/form-data"} + + // Deprecated: ErrHeaderTooLong is no longer returned by + // anything in the net/http package. Callers should not + // compare errors against this variable. + ErrHeaderTooLong = &ProtocolError{"header too long"} + + // Deprecated: ErrShortBody is no longer returned by + // anything in the net/http package. Callers should not + // compare errors against this variable. + ErrShortBody = &ProtocolError{"entity body too short"} + + // Deprecated: ErrMissingContentLength is no longer returned by + // anything in the net/http package. Callers should not + // compare errors against this variable. + ErrMissingContentLength = &ProtocolError{"missing ContentLength in HEAD response"} +) + +func badStringError(what, val string) error { return fmt.Errorf("%s %q", what, val) } + +// Headers that Request.Write handles itself and should be skipped. +var reqWriteExcludeHeader = map[string]bool{ + "Host": true, // not in Header map anyway + "User-Agent": true, + "Content-Length": true, + "Transfer-Encoding": true, + "Trailer": true, +} + +// A Request represents an HTTP request received by a server +// or to be sent by a client. +// +// The field semantics differ slightly between client and server +// usage. In addition to the notes on the fields below, see the +// documentation for [Request.Write] and [RoundTripper]. +type Request struct { + // Method specifies the HTTP method (GET, POST, PUT, etc.). + // For client requests, an empty string means GET. + 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 Clone or 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 + + // The following fields are for requests matched by ServeMux. + pat *pattern // the pattern that matched + matches []string // values for the matching wildcards in pat + otherValues map[string]string // for calls to SetPathValue that don't match a wildcard +} + +// Context returns the request's context. To change the context, use +// [Request.Clone] or [Request.WithContext]. +// +// The returned context is always non-nil; it defaults to the +// background context. +// +// For outgoing client requests, the context controls cancellation. +// +// For incoming server requests, the context is canceled when the +// client's connection closes, the request is canceled (with HTTP/2), +// or when the ServeHTTP method returns. +func (r *Request) Context() context.Context { + if r.ctx != nil { + return r.ctx + } + return context.Background() +} + +// WithContext returns a shallow copy of r with its context changed +// to ctx. The provided ctx must be non-nil. +// +// For 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. +// +// To create a new request with a context, use [NewRequestWithContext]. +// To make a deep copy of a request with a new context, use [Request.Clone]. +func (r *Request) WithContext(ctx context.Context) *Request { + if ctx == nil { + panic("nil context") + } + r2 := new(Request) + *r2 = *r + r2.ctx = ctx + return r2 +} + +// Clone returns a deep copy of r with its context changed to ctx. +// The provided ctx must be non-nil. +// +// 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. +func (r *Request) Clone(ctx context.Context) *Request { + if ctx == nil { + panic("nil context") + } + r2 := new(Request) + *r2 = *r + r2.ctx = ctx + r2.URL = cloneURL(r.URL) + if r.Header != nil { + r2.Header = r.Header.Clone() + } + if r.Trailer != nil { + r2.Trailer = r.Trailer.Clone() + } + if s := r.TransferEncoding; s != nil { + s2 := make([]string, len(s)) + copy(s2, s) + r2.TransferEncoding = s2 + } + r2.Form = cloneURLValues(r.Form) + r2.PostForm = cloneURLValues(r.PostForm) + r2.MultipartForm = cloneMultipartForm(r.MultipartForm) + + // Copy matches and otherValues. See issue 61410. + if s := r.matches; s != nil { + s2 := make([]string, len(s)) + copy(s2, s) + r2.matches = s2 + } + if s := r.otherValues; s != nil { + s2 := make(map[string]string, len(s)) + for k, v := range s { + s2[k] = v + } + r2.otherValues = s2 + } + return r2 +} + +// 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) { + if name == "" { + return nil, ErrNoCookie + } + 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") +} + +// multipartByReader is a sentinel value. +// Its presence in Request.MultipartForm indicates that parsing of the request +// body has been handed off to a MultipartReader instead of ParseMultipartForm. +var multipartByReader = &multipart.Form{ + Value: make(map[string][]string), + File: make(map[string][]*multipart.FileHeader), +} + +// MultipartReader returns a MIME multipart reader if this is a +// multipart/form-data or a multipart/mixed POST request, else returns nil and an error. +// Use this function instead of [Request.ParseMultipartForm] to +// process the request body as a stream. +func (r *Request) MultipartReader() (*multipart.Reader, error) { + if r.MultipartForm == multipartByReader { + return nil, errors.New("http: MultipartReader called twice") + } + if r.MultipartForm != nil { + return nil, errors.New("http: multipart handled by ParseMultipartForm") + } + r.MultipartForm = multipartByReader + return r.multipartReader(true) +} + +func (r *Request) multipartReader(allowMixed bool) (*multipart.Reader, error) { + v := r.Header.Get("Content-Type") + if v == "" { + return nil, ErrNotMultipart + } + if r.Body == nil { + return nil, errors.New("missing form body") + } + d, params, err := mime.ParseMediaType(v) + if err != nil || !(d == "multipart/form-data" || allowMixed && d == "multipart/mixed") { + return nil, ErrNotMultipart + } + boundary, ok := params["boundary"] + if !ok { + return nil, ErrMissingBoundary + } + return multipart.NewReader(r.Body, boundary), nil +} + +// 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" +} + +// Return value if nonempty, def otherwise. +func valueOrDefault(value, def string) string { + if value != "" { + return value + } + return def +} + +// NOTE: This is not intended to reflect the actual Go version being used. +// It was changed at the time of Go 1.1 release because the former User-Agent +// had ended up blocked by some intrusion detection systems. +// See https://codereview.appspot.com/7532043. +const defaultUserAgent = "Go-http-client/1.1" + +// Write writes an HTTP/1.1 request, which is the header and body, in wire format. +// This method consults the following fields of the request: +// +// Host +// URL +// Method (defaults to "GET") +// Header +// ContentLength +// TransferEncoding +// Body +// +// If Body is present, Content-Length is <= 0 and [Request.TransferEncoding] +// hasn't been set to "identity", Write adds "Transfer-Encoding: +// chunked" to the header. Body is closed after it is sent. +func (r *Request) Write(w io.Writer) error { + return r.write(w, false, nil, nil) +} + +// WriteProxy is like [Request.Write] but writes the request in the form +// expected by an HTTP proxy. In particular, [Request.WriteProxy] writes the +// initial Request-URI line of the request with an absolute URI, per +// section 5.3 of RFC 7230, including the scheme and host. +// In either case, WriteProxy also writes a Host header, using +// either r.Host or r.URL.Host. +func (r *Request) WriteProxy(w io.Writer) error { + return r.write(w, true, nil, nil) +} + +// errMissingHost is returned by Write when there is no Host or URL present in +// the Request. +var errMissingHost = errors.New("http: Request.Write on Request with no Host or URL set") + +// extraHeaders may be nil +// waitForContinue may be nil +// always closes body +func (r *Request) write(w io.Writer, usingProxy bool, extraHeaders Header, waitForContinue func() bool) (err error) { + trace := httptrace.ContextClientTrace(r.Context()) + if trace != nil && trace.WroteRequest != nil { + defer func() { + trace.WroteRequest(httptrace.WroteRequestInfo{ + Err: err, + }) + }() + } + closed := false + defer func() { + if closed { + return + } + if closeErr := r.closeBody(); closeErr != nil && err == nil { + err = closeErr + } + }() + + // Find the target host. Prefer the Host: header, but if that + // is not given, use the host from the request URL. + // + // Clean the host, in case it arrives with unexpected stuff in it. + host := r.Host + if host == "" { + if r.URL == nil { + return errMissingHost + } + host = r.URL.Host + } + host, err = httpguts.PunycodeHostPort(host) + if err != nil { + return err + } + // Validate that the Host header is a valid header in general, + // but don't validate the host itself. This is sufficient to avoid + // header or request smuggling via the Host field. + // The server can (and will, if it's a net/http server) reject + // the request if it doesn't consider the host valid. + if !httpguts.ValidHostHeader(host) { + // Historically, we would truncate the Host header after '/' or ' '. + // Some users have relied on this truncation to convert a network + // address such as Unix domain socket path into a valid, ignored + // Host header (see https://go.dev/issue/61431). + // + // We don't preserve the truncation, because sending an altered + // header field opens a smuggling vector. Instead, zero out the + // Host header entirely if it isn't valid. (An empty Host is valid; + // see RFC 9112 Section 3.2.) + // + // Return an error if we're sending to a proxy, since the proxy + // probably can't do anything useful with an empty Host header. + if !usingProxy { + host = "" + } else { + return errors.New("http: invalid Host header") + } + } + + // According to RFC 6874, an HTTP client, proxy, or other + // intermediary must remove any IPv6 zone identifier attached + // to an outgoing URI. + host = removeZone(host) + + ruri := r.URL.RequestURI() + if usingProxy && r.URL.Scheme != "" && r.URL.Opaque == "" { + ruri = r.URL.Scheme + "://" + host + ruri + } else if r.Method == "CONNECT" && r.URL.Path == "" { + // CONNECT requests normally give just the host and port, not a full URL. + ruri = host + if r.URL.Opaque != "" { + ruri = r.URL.Opaque + } + } + if stringContainsCTLByte(ruri) { + return errors.New("net/http: can't write control character in Request.URL") + } + // TODO: validate r.Method too? At least it's less likely to + // come from an attacker (more likely to be a constant in + // code). + + // Wrap the writer in a bufio Writer if it's not already buffered. + // Don't always call NewWriter, as that forces a bytes.Buffer + // and other small bufio Writers to have a minimum 4k buffer + // size. + var bw *bufio.Writer + if _, ok := w.(io.ByteWriter); !ok { + bw = bufio.NewWriter(w) + w = bw + } + + _, err = fmt.Fprintf(w, "%s %s HTTP/1.1\r\n", valueOrDefault(r.Method, "GET"), ruri) + if err != nil { + return err + } + + // Header lines + _, err = fmt.Fprintf(w, "Host: %s\r\n", host) + if err != nil { + return err + } + if trace != nil && trace.WroteHeaderField != nil { + trace.WroteHeaderField("Host", []string{host}) + } + + // Use the defaultUserAgent unless the Header contains one, which + // may be blank to not send the header. + userAgent := defaultUserAgent + if r.Header.has("User-Agent") { + userAgent = r.Header.Get("User-Agent") + } + if userAgent != "" { + userAgent = headerNewlineToSpace.Replace(userAgent) + userAgent = textproto.TrimString(userAgent) + _, err = fmt.Fprintf(w, "User-Agent: %s\r\n", userAgent) + if err != nil { + return err + } + if trace != nil && trace.WroteHeaderField != nil { + trace.WroteHeaderField("User-Agent", []string{userAgent}) + } + } + + // Process Body,ContentLength,Close,Trailer + tw, err := newTransferWriter(r) + if err != nil { + return err + } + err = tw.writeHeader(w, trace) + if err != nil { + return err + } + + err = r.Header.writeSubset(w, reqWriteExcludeHeader, trace) + if err != nil { + return err + } + + if extraHeaders != nil { + err = extraHeaders.write(w, trace) + if err != nil { + return err + } + } + + _, err = io.WriteString(w, "\r\n") + if err != nil { + return err + } + + if trace != nil && trace.WroteHeaders != nil { + trace.WroteHeaders() + } + + // Flush and wait for 100-continue if expected. + if waitForContinue != nil { + if bw, ok := w.(*bufio.Writer); ok { + err = bw.Flush() + if err != nil { + return err + } + } + if trace != nil && trace.Wait100Continue != nil { + trace.Wait100Continue() + } + if !waitForContinue() { + closed = true + r.closeBody() + return nil + } + } + + if bw, ok := w.(*bufio.Writer); ok && tw.FlushHeaders { + if err := bw.Flush(); err != nil { + return err + } + } + + // Write body and trailer + closed = true + err = tw.writeBody(w) + if err != nil { + if tw.bodyReadError == err { + err = requestBodyReadError{err} + } + return err + } + + if bw != nil { + return bw.Flush() + } + return nil +} + +// requestBodyReadError wraps an error from (*Request).write to indicate +// that the error came from a Read call on the Request.Body. +// This error type should not escape the net/http package to users. +type requestBodyReadError struct{ error } + +func idnaASCII(v string) (string, error) { + // TODO: Consider removing this check after verifying performance is okay. + // Right now punycode verification, length checks, context checks, and the + // permissible character tests are all omitted. It also prevents the ToASCII + // call from salvaging an invalid IDN, when possible. As a result it may be + // possible to have two IDNs that appear identical to the user where the + // ASCII-only version causes an error downstream whereas the non-ASCII + // version does not. + // Note that for correct ASCII IDNs ToASCII will only do considerably more + // work, but it will not cause an allocation. + if ascii.Is(v) { + return v, nil + } + return idna.Lookup.ToASCII(v) +} + +// removeZone removes IPv6 zone identifier from host. +// E.g., "[fe80::1%en0]:8080" to "[fe80::1]:8080" +func removeZone(host string) string { + if !strings.HasPrefix(host, "[") { + return host + } + i := strings.LastIndex(host, "]") + if i < 0 { + return host + } + j := strings.LastIndex(host[:i], "%") + if j < 0 { + return host + } + return host[:j] + host[i:] +} + +// ParseHTTPVersion parses an HTTP version string according to RFC 7230, section 2.6. +// "HTTP/1.0" returns (1, 0, true). Note that strings without +// a minor version, such as "HTTP/2", are not valid. +func ParseHTTPVersion(vers string) (major, minor int, ok bool) { + 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 + } + if len(vers) != len("HTTP/X.Y") { + return 0, 0, false + } + if vers[6] != '.' { + return 0, 0, false + } + maj, err := strconv.ParseUint(vers[5:6], 10, 0) + if err != nil { + return 0, 0, false + } + min, err := strconv.ParseUint(vers[7:8], 10, 0) + if err != nil { + return 0, 0, false + } + return int(maj), int(min), 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*<any CHAR except CTLs or separators> + */ + return len(method) > 0 && strings.IndexFunc(method, isNotToken) == -1 +} + +// NewRequest wraps [NewRequestWithContext] using [context.Background]. +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 (possibly +// asynchronously) 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 +} + +// BasicAuth returns the username and password provided in the request's +// Authorization header, if the request uses HTTP Basic Authentication. +// See RFC 2617, Section 2. +func (r *Request) BasicAuth() (username, password string, ok bool) { + auth := r.Header.Get("Authorization") + if auth == "" { + return "", "", false + } + return parseBasicAuth(auth) +} + +// parseBasicAuth parses an HTTP Basic Authentication string. +// "Basic QWxhZGRpbjpvcGVuIHNlc2FtZQ==" returns ("Aladdin", "open sesame", true). +func parseBasicAuth(auth string) (username, password string, ok bool) { + const prefix = "Basic " + // Case insensitive prefix match. See Issue 22736. + if len(auth) < len(prefix) || !ascii.EqualFold(auth[:len(prefix)], prefix) { + return "", "", false + } + c, err := base64.StdEncoding.DecodeString(auth[len(prefix):]) + if err != nil { + return "", "", false + } + cs := string(c) + username, password, ok = strings.Cut(cs, ":") + if !ok { + return "", "", false + } + return username, password, true +} + +// SetBasicAuth sets the request's Authorization header to use HTTP +// Basic Authentication with the provided username and password. +// +// With HTTP Basic Authentication the provided username and password +// are not encrypted. It should generally only be used in an HTTPS +// request. +// +// The username may not contain a colon. Some protocols may impose +// additional requirements on pre-escaping the username and +// password. For instance, when used with OAuth2, both arguments must +// be URL encoded first with [url.QueryEscape]. +func (r *Request) SetBasicAuth(username, password string) { + r.Header.Set("Authorization", "Basic "+basicAuth(username, password)) +} + +// parseRequestLine parses "GET /foo HTTP/1.1" into its three parts. +func parseRequestLine(line string) (method, requestURI, proto string, ok bool) { + method, rest, ok1 := strings.Cut(line, " ") + requestURI, proto, ok2 := strings.Cut(rest, " ") + if !ok1 || !ok2 { + return "", "", "", false + } + return method, requestURI, proto, 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) { + req, err := readRequest(b) + if err != nil { + return nil, err + } + + delete(req.Header, "Host") + return req, err +} + +func readRequest(b *bufio.Reader) (req *Request, err error) { + tp := newTextprotoReader(b) + defer putTextprotoReader(tp) + + 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() { + 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) + if len(req.Header["Host"]) > 1 { + return nil, fmt.Errorf("too many Host headers") + } + + // 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") + } + + 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-nil error of type [*MaxBytesError] 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. If possible, +// it tells the [ResponseWriter] to close the connection after the limit +// has been reached. +func MaxBytesReader(w ResponseWriter, r io.ReadCloser, n int64) io.ReadCloser { + if n < 0 { // Treat negative limits as equivalent to 0. + n = 0 + } + return &maxBytesReader{w: w, r: r, i: n, n: n} +} + +// MaxBytesError is returned by [MaxBytesReader] when its read limit is exceeded. +type MaxBytesError struct { + Limit int64 +} + +func (e *MaxBytesError) Error() string { + // Due to Hyrum's law, this text cannot be changed. + return "http: request body too large" +} + +type maxBytesReader struct { + w ResponseWriter + r io.ReadCloser // underlying reader + i int64 // max bytes initially, for MaxBytesError + 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. + // 0 < len(p) < 2^63 + if int64(len(p))-1 > l.n { + 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 = &MaxBytesError{l.i} + 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. +// +// [Request.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 +} + +// ParseMultipartForm parses a request body as multipart/form-data. +// The whole request body is parsed and up to a total of maxMemory bytes of +// its file parts are stored in memory, with the remainder stored on +// disk in temporary files. +// ParseMultipartForm calls [Request.ParseForm] if necessary. +// If ParseForm returns an error, ParseMultipartForm returns it but also +// continues parsing the request body. +// After one call to ParseMultipartForm, subsequent calls have no effect. +func (r *Request) ParseMultipartForm(maxMemory int64) error { + if r.MultipartForm == multipartByReader { + return errors.New("http: multipart handled by MultipartReader") + } + var parseFormErr error + if r.Form == nil { + // Let errors in ParseForm fall through, and just + // return it at the end. + parseFormErr = r.ParseForm() + } + if r.MultipartForm != nil { + return nil + } + + mr, err := r.multipartReader(false) + if err != nil { + return err + } + + f, err := mr.ReadForm(maxMemory) + if err != nil { + return err + } + + if r.PostForm == nil { + r.PostForm = make(url.Values) + } + for k, v := range f.Value { + r.Form[k] = append(r.Form[k], v...) + // r.PostForm should also be populated. See Issue 9305. + r.PostForm[k] = append(r.PostForm[k], v...) + } + + r.MultipartForm = f + + return parseFormErr +} + +// FormValue returns the first value for the named component of the query. +// The precedence order: +// 1. application/x-www-form-urlencoded form body (POST, PUT, PATCH only) +// 2. query parameters (always) +// 3. multipart/form-data form body (always) +// +// FormValue calls [Request.ParseMultipartForm] and [Request.ParseForm] +// if necessary and ignores any errors returned by these functions. +// If key is not present, FormValue returns the empty string. +// To access multiple values of the same key, call ParseForm and +// then inspect [Request.Form] directly. +func (r *Request) FormValue(key string) string { + if r.Form == nil { + r.ParseMultipartForm(defaultMaxMemory) + } + if vs := r.Form[key]; len(vs) > 0 { + return vs[0] + } + return "" +} + +// PostFormValue returns the first value for the named component of the POST, +// PUT, or PATCH request body. URL query parameters are ignored. +// PostFormValue calls [Request.ParseMultipartForm] and [Request.ParseForm] if necessary and ignores +// any errors returned by these functions. +// If key is not present, PostFormValue returns the empty string. +func (r *Request) PostFormValue(key string) string { + if r.PostForm == nil { + r.ParseMultipartForm(defaultMaxMemory) + } + if vs := r.PostForm[key]; len(vs) > 0 { + return vs[0] + } + return "" +} + +// FormFile returns the first file for the provided form key. +// FormFile calls [Request.ParseMultipartForm] and [Request.ParseForm] if necessary. +func (r *Request) FormFile(key string) (multipart.File, *multipart.FileHeader, error) { + if r.MultipartForm == multipartByReader { + return nil, nil, errors.New("http: multipart handled by MultipartReader") + } + if r.MultipartForm == nil { + err := r.ParseMultipartForm(defaultMaxMemory) + if err != nil { + return nil, nil, err + } + } + if r.MultipartForm != nil && r.MultipartForm.File != nil { + if fhs := r.MultipartForm.File[key]; len(fhs) > 0 { + f, err := fhs[0].Open() + return f, fhs[0], err + } + } + return nil, nil, ErrMissingFile +} + +// PathValue returns the value for the named path wildcard in the [ServeMux] pattern +// that matched the request. +// It returns the empty string if the request was not matched against a pattern +// or there is no such wildcard in the pattern. +func (r *Request) PathValue(name string) string { + if i := r.patIndex(name); i >= 0 { + return r.matches[i] + } + return r.otherValues[name] +} + +// SetPathValue sets name to value, so that subsequent calls to r.PathValue(name) +// return value. +func (r *Request) SetPathValue(name, value string) { + if i := r.patIndex(name); i >= 0 { + r.matches[i] = value + } else { + if r.otherValues == nil { + r.otherValues = map[string]string{} + } + r.otherValues[name] = value + } +} + +// patIndex returns the index of name in the list of named wildcards of the +// request's pattern, or -1 if there is no such name. +func (r *Request) patIndex(name string) int { + // The linear search seems expensive compared to a map, but just creating the map + // takes a lot of time, and most patterns will just have a couple of wildcards. + if r.pat == nil { + return -1 + } + i := 0 + for _, seg := range r.pat.segments { + if seg.wild && seg.s != "" { + if name == seg.s { + return i + } + i++ + } + } + return -1 +} + +func (r *Request) expectsContinue() bool { + return hasToken(r.Header.get("Expect"), "100-continue") +} + +func (r *Request) wantsHttp10KeepAlive() bool { + if r.ProtoMajor != 1 || r.ProtoMinor != 0 { + return false + } + return hasToken(r.Header.get("Connection"), "keep-alive") +} + +func (r *Request) wantsClose() bool { + if r.Close { + return true + } + return hasToken(r.Header.get("Connection"), "close") +} + +func (r *Request) closeBody() error { + if r.Body == nil { + return nil + } + return r.Body.Close() +} + +func (r *Request) isReplayable() bool { + if r.Body == nil || r.Body == NoBody || r.GetBody != nil { + switch valueOrDefault(r.Method, "GET") { + case "GET", "HEAD", "OPTIONS", "TRACE": + return true + } + // The Idempotency-Key, while non-standard, is widely used to + // mean a POST or other request is idempotent. See + // https://golang.org/issue/19943#issuecomment-421092421 + if r.Header.has("Idempotency-Key") || r.Header.has("X-Idempotency-Key") { + return true + } + } + return false +} + +// outgoingLength reports the Content-Length of this outgoing (Client) request. +// It maps 0 into -1 (unknown) when the Body is non-nil. +func (r *Request) outgoingLength() int64 { + if r.Body == nil || r.Body == NoBody { + return 0 + } + if r.ContentLength != 0 { + return r.ContentLength + } + return -1 +} + +// requestMethodUsuallyLacksBody reports whether the given request +// method is one that typically does not involve a request body. +// This is used by the Transport (via +// transferWriter.shouldSendChunkedRequestBody) to determine whether +// we try to test-read a byte from a non-nil Request.Body when +// Request.outgoingLength() returns -1. See the comments in +// shouldSendChunkedRequestBody. +func requestMethodUsuallyLacksBody(method string) bool { + switch method { + case "GET", "HEAD", "DELETE", "OPTIONS", "PROPFIND", "SEARCH": + return true + } + return false +} + +// requiresHTTP1 reports whether this request requires being sent on +// an HTTP/1 connection. +func (r *Request) requiresHTTP1() bool { + return hasToken(r.Header.Get("Connection"), "upgrade") && + ascii.EqualFold(r.Header.Get("Upgrade"), "websocket") +} |