.
* For example, matching the above expression to
*
* http://www.ics.uci.edu/pub/ietf/uri/#Related
*
* results in the following subexpression matches:
*
* $1 = http:
* $2 = http
* $3 = //www.ics.uci.edu
* $4 = www.ics.uci.edu
* $5 = /pub/ietf/uri/
* $6 =
* $7 =
* $8 = #Related
* $9 = Related
*
* where indicates that the component is not present, as is the
* case for the query component in the above example. Therefore, we can
* determine the value of the five components as
*
* scheme = $2
* authority = $4
* path = $5
* query = $7
* fragment = $9
*
*
* The regular expression has been modified slightly to expose the
* userInfo, domain, and port separately from the authority.
* The modified version yields
*
* $1 = http scheme
* $2 = userInfo -\
* $3 = www.ics.uci.edu domain | authority
* $4 = port -/
* $5 = /pub/ietf/uri/ path
* $6 = query without ?
* $7 = Related fragment without #
*
* @type {!RegExp}
* @internal
*/
var _splitRe = RegExpWrapper.create(
'^' +
'(?:' +
'([^:/?#.]+)' + // scheme - ignore special characters
// used by other URL parts such as :,
// ?, /, #, and .
':)?' +
'(?://' +
'(?:([^/?#]*)@)?' + // userInfo
'([\\w\\d\\-\\u0100-\\uffff.%]*)' + // domain - restrict to letters,
// digits, dashes, dots, percent
// escapes, and unicode characters.
'(?::([0-9]+))?' + // port
')?' +
'([^?#]+)?' + // path
'(?:\\?([^#]*))?' + // query
'(?:#(.*))?' + // fragment
'$');
/**
* The index of each URI component in the return value of goog.uri.utils.split.
* @enum {number}
*/
enum _ComponentIndex {
Scheme = 1,
UserInfo,
Domain,
Port,
Path,
QueryData,
Fragment
}
/**
* Splits a URI into its component parts.
*
* Each component can be accessed via the component indices; for example:
*
* goog.uri.utils.split(someStr)[goog.uri.utils.CompontentIndex.QUERY_DATA];
*
*
* @param uri The URI string to examine.
* @return Each component still URI-encoded.
* Each component that is present will contain the encoded value, whereas
* components that are not present will be undefined or empty, depending
* on the browser's regular expression implementation. Never null, since
* arbitrary strings may still look like path names.
*/
function _split(uri: string): Array {
return RegExpWrapper.firstMatch(_splitRe, uri);
}
/**
* Removes dot segments in given path component, as described in
* RFC 3986, section 5.2.4.
*
* @param path A non-empty path component.
* @return Path component with removed dot segments.
*/
function _removeDotSegments(path: string): string {
if (path == '/') return '/';
var leadingSlash = path[0] == '/' ? '/' : '';
var trailingSlash = path[path.length - 1] === '/' ? '/' : '';
var segments = path.split('/');
var out: string[] = [];
var up = 0;
for (var pos = 0; pos < segments.length; pos++) {
var segment = segments[pos];
switch (segment) {
case '':
case '.':
break;
case '..':
if (out.length > 0) {
out.pop();
} else {
up++;
}
break;
default:
out.push(segment);
}
}
if (leadingSlash == '') {
while (up-- > 0) {
out.unshift('..');
}
if (out.length === 0) out.push('.');
}
return leadingSlash + out.join('/') + trailingSlash;
}
/**
* Takes an array of the parts from split and canonicalizes the path part
* and then joins all the parts.
*/
function _joinAndCanonicalizePath(parts: any[]): string {
var path = parts[_ComponentIndex.Path];
path = isBlank(path) ? '' : _removeDotSegments(path);
parts[_ComponentIndex.Path] = path;
return _buildFromEncodedParts(
parts[_ComponentIndex.Scheme], parts[_ComponentIndex.UserInfo], parts[_ComponentIndex.Domain],
parts[_ComponentIndex.Port], path, parts[_ComponentIndex.QueryData],
parts[_ComponentIndex.Fragment]);
}
/**
* Resolves a URL.
* @param base The URL acting as the base URL.
* @param to The URL to resolve.
*/
function _resolveUrl(base: string, url: string): string {
var parts = _split(encodeURI(url));
var baseParts = _split(base);
if (isPresent(parts[_ComponentIndex.Scheme])) {
return _joinAndCanonicalizePath(parts);
} else {
parts[_ComponentIndex.Scheme] = baseParts[_ComponentIndex.Scheme];
}
for (var i = _ComponentIndex.Scheme; i <= _ComponentIndex.Port; i++) {
if (isBlank(parts[i])) {
parts[i] = baseParts[i];
}
}
if (parts[_ComponentIndex.Path][0] == '/') {
return _joinAndCanonicalizePath(parts);
}
var path = baseParts[_ComponentIndex.Path];
if (isBlank(path)) path = '/';
var index = path.lastIndexOf('/');
path = path.substring(0, index + 1) + parts[_ComponentIndex.Path];
parts[_ComponentIndex.Path] = path;
return _joinAndCanonicalizePath(parts);
}