in src/node-fallbacks/url.js [143:391]
Url.prototype.parse = function (url, parseQueryString, slashesDenoteHost) {
if (!util_isString(url)) {
throw new TypeError("Parameter 'url' must be a string, not " + typeof url);
}
// Copy chrome, IE, opera backslash-handling behavior.
// Back slashes before the query string get converted to forward slashes
// See: https://code.google.com/p/chromium/issues/detail?id=25916
var queryIndex = url.indexOf("?"),
splitter = queryIndex !== -1 && queryIndex < url.indexOf("#") ? "?" : "#",
uSplit = url.split(splitter),
slashRegex = /\\/g;
uSplit[0] = uSplit[0].replace(slashRegex, "/");
url = uSplit.join(splitter);
var rest = url;
// trim before proceeding.
// This is to support parse stuff like " http://foo.com \n"
rest = rest.trim();
if (!slashesDenoteHost && url.split("#").length === 1) {
// Try fast path regexp
var simplePath = simplePathPattern.exec(rest);
if (simplePath) {
this.path = rest;
this.href = rest;
this.pathname = simplePath[1];
if (simplePath[2]) {
this.search = simplePath[2];
if (parseQueryString) {
this.query = querystring.parse(this.search.substr(1));
} else {
this.query = this.search.substr(1);
}
} else if (parseQueryString) {
this.search = "";
this.query = {};
}
return this;
}
}
var proto = protocolPattern.exec(rest);
if (proto) {
proto = proto[0];
var lowerProto = proto.toLowerCase();
this.protocol = lowerProto;
rest = rest.substr(proto.length);
}
// figure out if it's got a host
// user@server is *always* interpreted as a hostname, and url
// resolution will treat //foo/bar as host=foo,path=bar because that's
// how the browser resolves relative URLs.
if (slashesDenoteHost || proto || rest.match(/^\/\/[^@\/]+@[^@\/]+/)) {
var slashes = rest.substr(0, 2) === "//";
if (slashes && !(proto && hostlessProtocol[proto])) {
rest = rest.substr(2);
this.slashes = true;
}
}
if (!hostlessProtocol[proto] && (slashes || (proto && !slashedProtocol[proto]))) {
// there's a hostname.
// the first instance of /, ?, ;, or # ends the host.
//
// If there is an @ in the hostname, then non-host chars *are* allowed
// to the left of the last @ sign, unless some host-ending character
// comes *before* the @-sign.
// URLs are obnoxious.
//
// ex:
// http://a@b@c/ => user:a@b host:c
// http://a@b?@c => user:a host:c path:/?@c
// v0.12 TODO(isaacs): This is not quite how Chrome does things.
// Review our test case against browsers more comprehensively.
// find the first instance of any hostEndingChars
var hostEnd = -1;
for (var i = 0; i < hostEndingChars.length; i++) {
var hec = rest.indexOf(hostEndingChars[i]);
if (hec !== -1 && (hostEnd === -1 || hec < hostEnd)) hostEnd = hec;
}
// at this point, either we have an explicit point where the
// auth portion cannot go past, or the last @ char is the decider.
var auth, atSign;
if (hostEnd === -1) {
// atSign can be anywhere.
atSign = rest.lastIndexOf("@");
} else {
// atSign must be in auth portion.
// http://a@b/c@d => host:b auth:a path:/c@d
atSign = rest.lastIndexOf("@", hostEnd);
}
// Now we have a portion which is definitely the auth.
// Pull that off.
if (atSign !== -1) {
auth = rest.slice(0, atSign);
rest = rest.slice(atSign + 1);
this.auth = decodeURIComponent(auth);
}
// the host is the remaining to the left of the first non-host char
hostEnd = -1;
for (var i = 0; i < nonHostChars.length; i++) {
var hec = rest.indexOf(nonHostChars[i]);
if (hec !== -1 && (hostEnd === -1 || hec < hostEnd)) hostEnd = hec;
}
// if we still have not hit it, then the entire thing is a host.
if (hostEnd === -1) hostEnd = rest.length;
this.host = rest.slice(0, hostEnd);
rest = rest.slice(hostEnd);
// pull out port.
this.parseHost();
// we've indicated that there is a hostname,
// so even if it's empty, it has to be present.
this.hostname = this.hostname || "";
// if hostname begins with [ and ends with ]
// assume that it's an IPv6 address.
var ipv6Hostname = this.hostname[0] === "[" && this.hostname[this.hostname.length - 1] === "]";
// validate a little.
if (!ipv6Hostname) {
var hostparts = this.hostname.split(/\./);
for (var i = 0, l = hostparts.length; i < l; i++) {
var part = hostparts[i];
if (!part) continue;
if (!part.match(hostnamePartPattern)) {
var newpart = "";
for (var j = 0, k = part.length; j < k; j++) {
if (part.charCodeAt(j) > 127) {
// we replace non-ASCII char with a temporary placeholder
// we need this to make sure size of hostname is not
// broken by replacing non-ASCII by nothing
newpart += "x";
} else {
newpart += part[j];
}
}
// we test again with ASCII char only
if (!newpart.match(hostnamePartPattern)) {
var validParts = hostparts.slice(0, i);
var notHost = hostparts.slice(i + 1);
var bit = part.match(hostnamePartStart);
if (bit) {
validParts.push(bit[1]);
notHost.unshift(bit[2]);
}
if (notHost.length) {
rest = "/" + notHost.join(".") + rest;
}
this.hostname = validParts.join(".");
break;
}
}
}
}
if (this.hostname.length > hostnameMaxLen) {
this.hostname = "";
} else {
// hostnames are always lower case.
this.hostname = this.hostname.toLowerCase();
}
if (!ipv6Hostname) {
// IDNA Support: Returns a punycoded representation of "domain".
// It only converts parts of the domain name that
// have non-ASCII characters, i.e. it doesn't matter if
// you call it with a domain that already is ASCII-only.
this.hostname = new URL(`https://${this.hostname}`).hostname;
}
var p = this.port ? ":" + this.port : "";
var h = this.hostname || "";
this.host = h + p;
this.href += this.host;
// strip [ and ] from the hostname
// the host field still retains them, though
if (ipv6Hostname) {
this.hostname = this.hostname.substr(1, this.hostname.length - 2);
if (rest[0] !== "/") {
rest = "/" + rest;
}
}
}
// now rest is set to the post-host stuff.
// chop off any delim chars.
if (!unsafeProtocol[lowerProto]) {
// First, make 100% sure that any "autoEscape" chars get
// escaped, even if encodeURIComponent doesn't think they
// need to be.
for (var i = 0, l = autoEscape.length; i < l; i++) {
var ae = autoEscape[i];
if (rest.indexOf(ae) === -1) continue;
var esc = encodeURIComponent(ae);
if (esc === ae) {
esc = escape(ae);
}
rest = rest.split(ae).join(esc);
}
}
// chop off from the tail first.
var hash = rest.indexOf("#");
if (hash !== -1) {
// got a fragment string.
this.hash = rest.substr(hash);
rest = rest.slice(0, hash);
}
var qm = rest.indexOf("?");
if (qm !== -1) {
this.search = rest.substr(qm);
this.query = rest.substr(qm + 1);
if (parseQueryString) {
this.query = querystring.parse(this.query);
}
rest = rest.slice(0, qm);
} else if (parseQueryString) {
// no query string, but parseQueryString still requested
this.search = "";
this.query = {};
}
if (rest) this.pathname = rest;
if (slashedProtocol[lowerProto] && this.hostname && !this.pathname) {
this.pathname = "/";
}
//to support http.request
if (this.pathname || this.search) {
var p = this.pathname || "";
var s = this.search || "";
this.path = p + s;
}
// finally, reconstruct the href based on what has been validated.
this.href = this.format();
return this;
};