goog.string.string.js Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of google-closure-library
Show all versions of google-closure-library
The Google Closure Library is a collection of JavaScript code
designed for use with the Google Closure JavaScript Compiler.
This non-official distribution was prepared by the ClojureScript
team at http://clojure.org/
// Copyright 2006 The Closure Library Authors. All Rights Reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS-IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
/**
* @fileoverview Utilities for string manipulation.
* @author [email protected] (Erik Arvidsson)
*/
/**
* Namespace for string utilities
*/
goog.provide('goog.string');
goog.provide('goog.string.Unicode');
/**
* @define {boolean} Enables HTML escaping of lowercase letter "e" which helps
* with detection of double-escaping as this letter is frequently used.
*/
goog.define('goog.string.DETECT_DOUBLE_ESCAPING', false);
/**
* @define {boolean} Whether to force non-dom html unescaping.
*/
goog.define('goog.string.FORCE_NON_DOM_HTML_UNESCAPING', false);
/**
* Common Unicode string characters.
* @enum {string}
*/
goog.string.Unicode = {
NBSP: '\xa0'
};
/**
* Fast prefix-checker.
* @param {string} str The string to check.
* @param {string} prefix A string to look for at the start of {@code str}.
* @return {boolean} True if {@code str} begins with {@code prefix}.
*/
goog.string.startsWith = function(str, prefix) {
return str.lastIndexOf(prefix, 0) == 0;
};
/**
* Fast suffix-checker.
* @param {string} str The string to check.
* @param {string} suffix A string to look for at the end of {@code str}.
* @return {boolean} True if {@code str} ends with {@code suffix}.
*/
goog.string.endsWith = function(str, suffix) {
var l = str.length - suffix.length;
return l >= 0 && str.indexOf(suffix, l) == l;
};
/**
* Case-insensitive prefix-checker.
* @param {string} str The string to check.
* @param {string} prefix A string to look for at the end of {@code str}.
* @return {boolean} True if {@code str} begins with {@code prefix} (ignoring
* case).
*/
goog.string.caseInsensitiveStartsWith = function(str, prefix) {
return goog.string.caseInsensitiveCompare(
prefix, str.substr(0, prefix.length)) == 0;
};
/**
* Case-insensitive suffix-checker.
* @param {string} str The string to check.
* @param {string} suffix A string to look for at the end of {@code str}.
* @return {boolean} True if {@code str} ends with {@code suffix} (ignoring
* case).
*/
goog.string.caseInsensitiveEndsWith = function(str, suffix) {
return goog.string.caseInsensitiveCompare(
suffix, str.substr(str.length - suffix.length, suffix.length)) ==
0;
};
/**
* Case-insensitive equality checker.
* @param {string} str1 First string to check.
* @param {string} str2 Second string to check.
* @return {boolean} True if {@code str1} and {@code str2} are the same string,
* ignoring case.
*/
goog.string.caseInsensitiveEquals = function(str1, str2) {
return str1.toLowerCase() == str2.toLowerCase();
};
/**
* Does simple python-style string substitution.
* subs("foo%s hot%s", "bar", "dog") becomes "foobar hotdog".
* @param {string} str The string containing the pattern.
* @param {...*} var_args The items to substitute into the pattern.
* @return {string} A copy of {@code str} in which each occurrence of
* {@code %s} has been replaced an argument from {@code var_args}.
*/
goog.string.subs = function(str, var_args) {
var splitParts = str.split('%s');
var returnString = '';
var subsArguments = Array.prototype.slice.call(arguments, 1);
while (subsArguments.length &&
// Replace up to the last split part. We are inserting in the
// positions between split parts.
splitParts.length > 1) {
returnString += splitParts.shift() + subsArguments.shift();
}
return returnString + splitParts.join('%s'); // Join unused '%s'
};
/**
* Converts multiple whitespace chars (spaces, non-breaking-spaces, new lines
* and tabs) to a single space, and strips leading and trailing whitespace.
* @param {string} str Input string.
* @return {string} A copy of {@code str} with collapsed whitespace.
*/
goog.string.collapseWhitespace = function(str) {
// Since IE doesn't include non-breaking-space (0xa0) in their \s character
// class (as required by section 7.2 of the ECMAScript spec), we explicitly
// include it in the regexp to enforce consistent cross-browser behavior.
return str.replace(/[\s\xa0]+/g, ' ').replace(/^\s+|\s+$/g, '');
};
/**
* Checks if a string is empty or contains only whitespaces.
* @param {string} str The string to check.
* @return {boolean} Whether {@code str} is empty or whitespace only.
*/
goog.string.isEmptyOrWhitespace = function(str) {
// testing length == 0 first is actually slower in all browsers (about the
// same in Opera).
// Since IE doesn't include non-breaking-space (0xa0) in their \s character
// class (as required by section 7.2 of the ECMAScript spec), we explicitly
// include it in the regexp to enforce consistent cross-browser behavior.
return /^[\s\xa0]*$/.test(str);
};
/**
* Checks if a string is empty.
* @param {string} str The string to check.
* @return {boolean} Whether {@code str} is empty.
*/
goog.string.isEmptyString = function(str) {
return str.length == 0;
};
/**
* Checks if a string is empty or contains only whitespaces.
*
* TODO(user): Deprecate this when clients have been switched over to
* goog.string.isEmptyOrWhitespace.
*
* @param {string} str The string to check.
* @return {boolean} Whether {@code str} is empty or whitespace only.
*/
goog.string.isEmpty = goog.string.isEmptyOrWhitespace;
/**
* Checks if a string is null, undefined, empty or contains only whitespaces.
* @param {*} str The string to check.
* @return {boolean} Whether {@code str} is null, undefined, empty, or
* whitespace only.
* @deprecated Use goog.string.isEmptyOrWhitespace(goog.string.makeSafe(str))
* instead.
*/
goog.string.isEmptyOrWhitespaceSafe = function(str) {
return goog.string.isEmptyOrWhitespace(goog.string.makeSafe(str));
};
/**
* Checks if a string is null, undefined, empty or contains only whitespaces.
*
* TODO(user): Deprecate this when clients have been switched over to
* goog.string.isEmptyOrWhitespaceSafe.
*
* @param {*} str The string to check.
* @return {boolean} Whether {@code str} is null, undefined, empty, or
* whitespace only.
*/
goog.string.isEmptySafe = goog.string.isEmptyOrWhitespaceSafe;
/**
* Checks if a string is all breaking whitespace.
* @param {string} str The string to check.
* @return {boolean} Whether the string is all breaking whitespace.
*/
goog.string.isBreakingWhitespace = function(str) {
return !/[^\t\n\r ]/.test(str);
};
/**
* Checks if a string contains all letters.
* @param {string} str string to check.
* @return {boolean} True if {@code str} consists entirely of letters.
*/
goog.string.isAlpha = function(str) {
return !/[^a-zA-Z]/.test(str);
};
/**
* Checks if a string contains only numbers.
* @param {*} str string to check. If not a string, it will be
* casted to one.
* @return {boolean} True if {@code str} is numeric.
*/
goog.string.isNumeric = function(str) {
return !/[^0-9]/.test(str);
};
/**
* Checks if a string contains only numbers or letters.
* @param {string} str string to check.
* @return {boolean} True if {@code str} is alphanumeric.
*/
goog.string.isAlphaNumeric = function(str) {
return !/[^a-zA-Z0-9]/.test(str);
};
/**
* Checks if a character is a space character.
* @param {string} ch Character to check.
* @return {boolean} True if {@code ch} is a space.
*/
goog.string.isSpace = function(ch) {
return ch == ' ';
};
/**
* Checks if a character is a valid unicode character.
* @param {string} ch Character to check.
* @return {boolean} True if {@code ch} is a valid unicode character.
*/
goog.string.isUnicodeChar = function(ch) {
return ch.length == 1 && ch >= ' ' && ch <= '~' ||
ch >= '\u0080' && ch <= '\uFFFD';
};
/**
* Takes a string and replaces newlines with a space. Multiple lines are
* replaced with a single space.
* @param {string} str The string from which to strip newlines.
* @return {string} A copy of {@code str} stripped of newlines.
*/
goog.string.stripNewlines = function(str) {
return str.replace(/(\r\n|\r|\n)+/g, ' ');
};
/**
* Replaces Windows and Mac new lines with unix style: \r or \r\n with \n.
* @param {string} str The string to in which to canonicalize newlines.
* @return {string} {@code str} A copy of {@code} with canonicalized newlines.
*/
goog.string.canonicalizeNewlines = function(str) {
return str.replace(/(\r\n|\r|\n)/g, '\n');
};
/**
* Normalizes whitespace in a string, replacing all whitespace chars with
* a space.
* @param {string} str The string in which to normalize whitespace.
* @return {string} A copy of {@code str} with all whitespace normalized.
*/
goog.string.normalizeWhitespace = function(str) {
return str.replace(/\xa0|\s/g, ' ');
};
/**
* Normalizes spaces in a string, replacing all consecutive spaces and tabs
* with a single space. Replaces non-breaking space with a space.
* @param {string} str The string in which to normalize spaces.
* @return {string} A copy of {@code str} with all consecutive spaces and tabs
* replaced with a single space.
*/
goog.string.normalizeSpaces = function(str) {
return str.replace(/\xa0|[ \t]+/g, ' ');
};
/**
* Removes the breaking spaces from the left and right of the string and
* collapses the sequences of breaking spaces in the middle into single spaces.
* The original and the result strings render the same way in HTML.
* @param {string} str A string in which to collapse spaces.
* @return {string} Copy of the string with normalized breaking spaces.
*/
goog.string.collapseBreakingSpaces = function(str) {
return str.replace(/[\t\r\n ]+/g, ' ')
.replace(/^[\t\r\n ]+|[\t\r\n ]+$/g, '');
};
/**
* Trims white spaces to the left and right of a string.
* @param {string} str The string to trim.
* @return {string} A trimmed copy of {@code str}.
*/
goog.string.trim =
(goog.TRUSTED_SITE && String.prototype.trim) ? function(str) {
return str.trim();
} : function(str) {
// Since IE doesn't include non-breaking-space (0xa0) in their \s
// character class (as required by section 7.2 of the ECMAScript spec),
// we explicitly include it in the regexp to enforce consistent
// cross-browser behavior.
return str.replace(/^[\s\xa0]+|[\s\xa0]+$/g, '');
};
/**
* Trims whitespaces at the left end of a string.
* @param {string} str The string to left trim.
* @return {string} A trimmed copy of {@code str}.
*/
goog.string.trimLeft = function(str) {
// Since IE doesn't include non-breaking-space (0xa0) in their \s character
// class (as required by section 7.2 of the ECMAScript spec), we explicitly
// include it in the regexp to enforce consistent cross-browser behavior.
return str.replace(/^[\s\xa0]+/, '');
};
/**
* Trims whitespaces at the right end of a string.
* @param {string} str The string to right trim.
* @return {string} A trimmed copy of {@code str}.
*/
goog.string.trimRight = function(str) {
// Since IE doesn't include non-breaking-space (0xa0) in their \s character
// class (as required by section 7.2 of the ECMAScript spec), we explicitly
// include it in the regexp to enforce consistent cross-browser behavior.
return str.replace(/[\s\xa0]+$/, '');
};
/**
* A string comparator that ignores case.
* -1 = str1 less than str2
* 0 = str1 equals str2
* 1 = str1 greater than str2
*
* @param {string} str1 The string to compare.
* @param {string} str2 The string to compare {@code str1} to.
* @return {number} The comparator result, as described above.
*/
goog.string.caseInsensitiveCompare = function(str1, str2) {
var test1 = String(str1).toLowerCase();
var test2 = String(str2).toLowerCase();
if (test1 < test2) {
return -1;
} else if (test1 == test2) {
return 0;
} else {
return 1;
}
};
/**
* Compares two strings interpreting their numeric substrings as numbers.
*
* @param {string} str1 First string.
* @param {string} str2 Second string.
* @param {!RegExp} tokenizerRegExp Splits a string into substrings of
* non-negative integers, non-numeric characters and optionally fractional
* numbers starting with a decimal point.
* @return {number} Negative if str1 < str2, 0 is str1 == str2, positive if
* str1 > str2.
* @private
*/
goog.string.numberAwareCompare_ = function(str1, str2, tokenizerRegExp) {
if (str1 == str2) {
return 0;
}
if (!str1) {
return -1;
}
if (!str2) {
return 1;
}
// Using match to split the entire string ahead of time turns out to be faster
// for most inputs than using RegExp.exec or iterating over each character.
var tokens1 = str1.toLowerCase().match(tokenizerRegExp);
var tokens2 = str2.toLowerCase().match(tokenizerRegExp);
var count = Math.min(tokens1.length, tokens2.length);
for (var i = 0; i < count; i++) {
var a = tokens1[i];
var b = tokens2[i];
// Compare pairs of tokens, returning if one token sorts before the other.
if (a != b) {
// Only if both tokens are integers is a special comparison required.
// Decimal numbers are sorted as strings (e.g., '.09' < '.1').
var num1 = parseInt(a, 10);
if (!isNaN(num1)) {
var num2 = parseInt(b, 10);
if (!isNaN(num2) && num1 - num2) {
return num1 - num2;
}
}
return a < b ? -1 : 1;
}
}
// If one string is a substring of the other, the shorter string sorts first.
if (tokens1.length != tokens2.length) {
return tokens1.length - tokens2.length;
}
// The two strings must be equivalent except for case (perfect equality is
// tested at the head of the function.) Revert to default ASCII string
// comparison to stabilize the sort.
return str1 < str2 ? -1 : 1;
};
/**
* String comparison function that handles non-negative integer numbers in a
* way humans might expect. Using this function, the string 'File 2.jpg' sorts
* before 'File 10.jpg', and 'Version 1.9' before 'Version 1.10'. The comparison
* is mostly case-insensitive, though strings that are identical except for case
* are sorted with the upper-case strings before lower-case.
*
* This comparison function is up to 50x slower than either the default or the
* case-insensitive compare. It should not be used in time-critical code, but
* should be fast enough to sort several hundred short strings (like filenames)
* with a reasonable delay.
*
* @param {string} str1 The string to compare in a numerically sensitive way.
* @param {string} str2 The string to compare {@code str1} to.
* @return {number} less than 0 if str1 < str2, 0 if str1 == str2, greater than
* 0 if str1 > str2.
*/
goog.string.intAwareCompare = function(str1, str2) {
return goog.string.numberAwareCompare_(str1, str2, /\d+|\D+/g);
};
/**
* String comparison function that handles non-negative integer and fractional
* numbers in a way humans might expect. Using this function, the string
* 'File 2.jpg' sorts before 'File 10.jpg', and '3.14' before '3.2'. Equivalent
* to {@link goog.string.intAwareCompare} apart from the way how it interprets
* dots.
*
* @param {string} str1 The string to compare in a numerically sensitive way.
* @param {string} str2 The string to compare {@code str1} to.
* @return {number} less than 0 if str1 < str2, 0 if str1 == str2, greater than
* 0 if str1 > str2.
*/
goog.string.floatAwareCompare = function(str1, str2) {
return goog.string.numberAwareCompare_(str1, str2, /\d+|\.\d+|\D+/g);
};
/**
* Alias for {@link goog.string.floatAwareCompare}.
*
* @param {string} str1
* @param {string} str2
* @return {number}
*/
goog.string.numerateCompare = goog.string.floatAwareCompare;
/**
* URL-encodes a string
* @param {*} str The string to url-encode.
* @return {string} An encoded copy of {@code str} that is safe for urls.
* Note that '#', ':', and other characters used to delimit portions
* of URLs *will* be encoded.
*/
goog.string.urlEncode = function(str) {
return encodeURIComponent(String(str));
};
/**
* URL-decodes the string. We need to specially handle '+'s because
* the javascript library doesn't convert them to spaces.
* @param {string} str The string to url decode.
* @return {string} The decoded {@code str}.
*/
goog.string.urlDecode = function(str) {
return decodeURIComponent(str.replace(/\+/g, ' '));
};
/**
* Converts \n to
s or
s.
* @param {string} str The string in which to convert newlines.
* @param {boolean=} opt_xml Whether to use XML compatible tags.
* @return {string} A copy of {@code str} with converted newlines.
*/
goog.string.newLineToBr = function(str, opt_xml) {
return str.replace(/(\r\n|\r|\n)/g, opt_xml ? '
' : '
');
};
/**
* Escapes double quote '"' and single quote '\'' characters in addition to
* '&', '<', and '>' so that a string can be included in an HTML tag attribute
* value within double or single quotes.
*
* It should be noted that > doesn't need to be escaped for the HTML or XML to
* be valid, but it has been decided to escape it for consistency with other
* implementations.
*
* With goog.string.DETECT_DOUBLE_ESCAPING, this function escapes also the
* lowercase letter "e".
*
* NOTE(user):
* HtmlEscape is often called during the generation of large blocks of HTML.
* Using statics for the regular expressions and strings is an optimization
* that can more than half the amount of time IE spends in this function for
* large apps, since strings and regexes both contribute to GC allocations.
*
* Testing for the presence of a character before escaping increases the number
* of function calls, but actually provides a speed increase for the average
* case -- since the average case often doesn't require the escaping of all 4
* characters and indexOf() is much cheaper than replace().
* The worst case does suffer slightly from the additional calls, therefore the
* opt_isLikelyToContainHtmlChars option has been included for situations
* where all 4 HTML entities are very likely to be present and need escaping.
*
* Some benchmarks (times tended to fluctuate +-0.05ms):
* FireFox IE6
* (no chars / average (mix of cases) / all 4 chars)
* no checks 0.13 / 0.22 / 0.22 0.23 / 0.53 / 0.80
* indexOf 0.08 / 0.17 / 0.26 0.22 / 0.54 / 0.84
* indexOf + re test 0.07 / 0.17 / 0.28 0.19 / 0.50 / 0.85
*
* An additional advantage of checking if replace actually needs to be called
* is a reduction in the number of object allocations, so as the size of the
* application grows the difference between the various methods would increase.
*
* @param {string} str string to be escaped.
* @param {boolean=} opt_isLikelyToContainHtmlChars Don't perform a check to see
* if the character needs replacing - use this option if you expect each of
* the characters to appear often. Leave false if you expect few html
* characters to occur in your strings, such as if you are escaping HTML.
* @return {string} An escaped copy of {@code str}.
*/
goog.string.htmlEscape = function(str, opt_isLikelyToContainHtmlChars) {
if (opt_isLikelyToContainHtmlChars) {
str = str.replace(goog.string.AMP_RE_, '&')
.replace(goog.string.LT_RE_, '<')
.replace(goog.string.GT_RE_, '>')
.replace(goog.string.QUOT_RE_, '"')
.replace(goog.string.SINGLE_QUOTE_RE_, ''')
.replace(goog.string.NULL_RE_, '�');
if (goog.string.DETECT_DOUBLE_ESCAPING) {
str = str.replace(goog.string.E_RE_, 'e');
}
return str;
} else {
// quick test helps in the case when there are no chars to replace, in
// worst case this makes barely a difference to the time taken
if (!goog.string.ALL_RE_.test(str)) return str;
// str.indexOf is faster than regex.test in this case
if (str.indexOf('&') != -1) {
str = str.replace(goog.string.AMP_RE_, '&');
}
if (str.indexOf('<') != -1) {
str = str.replace(goog.string.LT_RE_, '<');
}
if (str.indexOf('>') != -1) {
str = str.replace(goog.string.GT_RE_, '>');
}
if (str.indexOf('"') != -1) {
str = str.replace(goog.string.QUOT_RE_, '"');
}
if (str.indexOf('\'') != -1) {
str = str.replace(goog.string.SINGLE_QUOTE_RE_, ''');
}
if (str.indexOf('\x00') != -1) {
str = str.replace(goog.string.NULL_RE_, '�');
}
if (goog.string.DETECT_DOUBLE_ESCAPING && str.indexOf('e') != -1) {
str = str.replace(goog.string.E_RE_, 'e');
}
return str;
}
};
/**
* Regular expression that matches an ampersand, for use in escaping.
* @const {!RegExp}
* @private
*/
goog.string.AMP_RE_ = /&/g;
/**
* Regular expression that matches a less than sign, for use in escaping.
* @const {!RegExp}
* @private
*/
goog.string.LT_RE_ = //g;
/**
* Regular expression that matches a double quote, for use in escaping.
* @const {!RegExp}
* @private
*/
goog.string.QUOT_RE_ = /"/g;
/**
* Regular expression that matches a single quote, for use in escaping.
* @const {!RegExp}
* @private
*/
goog.string.SINGLE_QUOTE_RE_ = /'/g;
/**
* Regular expression that matches null character, for use in escaping.
* @const {!RegExp}
* @private
*/
goog.string.NULL_RE_ = /\x00/g;
/**
* Regular expression that matches a lowercase letter "e", for use in escaping.
* @const {!RegExp}
* @private
*/
goog.string.E_RE_ = /e/g;
/**
* Regular expression that matches any character that needs to be escaped.
* @const {!RegExp}
* @private
*/
goog.string.ALL_RE_ =
(goog.string.DETECT_DOUBLE_ESCAPING ? /[\x00&<>"'e]/ : /[\x00&<>"']/);
/**
* Unescapes an HTML string.
*
* @param {string} str The string to unescape.
* @return {string} An unescaped copy of {@code str}.
*/
goog.string.unescapeEntities = function(str) {
if (goog.string.contains(str, '&')) {
// We are careful not to use a DOM if we do not have one or we explicitly
// requested non-DOM html unescaping.
if (!goog.string.FORCE_NON_DOM_HTML_UNESCAPING &&
'document' in goog.global) {
return goog.string.unescapeEntitiesUsingDom_(str);
} else {
// Fall back on pure XML entities
return goog.string.unescapePureXmlEntities_(str);
}
}
return str;
};
/**
* Unescapes a HTML string using the provided document.
*
* @param {string} str The string to unescape.
* @param {!Document} document A document to use in escaping the string.
* @return {string} An unescaped copy of {@code str}.
*/
goog.string.unescapeEntitiesWithDocument = function(str, document) {
if (goog.string.contains(str, '&')) {
return goog.string.unescapeEntitiesUsingDom_(str, document);
}
return str;
};
/**
* Unescapes an HTML string using a DOM to resolve non-XML, non-numeric
* entities. This function is XSS-safe and whitespace-preserving.
* @private
* @param {string} str The string to unescape.
* @param {Document=} opt_document An optional document to use for creating
* elements. If this is not specified then the default window.document
* will be used.
* @return {string} The unescaped {@code str} string.
*/
goog.string.unescapeEntitiesUsingDom_ = function(str, opt_document) {
/** @type {!Object} */
var seen = {'&': '&', '<': '<', '>': '>', '"': '"'};
var div;
if (opt_document) {
div = opt_document.createElement('div');
} else {
div = goog.global.document.createElement('div');
}
// Match as many valid entity characters as possible. If the actual entity
// happens to be shorter, it will still work as innerHTML will return the
// trailing characters unchanged. Since the entity characters do not include
// open angle bracket, there is no chance of XSS from the innerHTML use.
// Since no whitespace is passed to innerHTML, whitespace is preserved.
return str.replace(goog.string.HTML_ENTITY_PATTERN_, function(s, entity) {
// Check for cached entity.
var value = seen[s];
if (value) {
return value;
}
// Check for numeric entity.
if (entity.charAt(0) == '#') {
// Prefix with 0 so that hex entities (e.g. ) parse as hex numbers.
var n = Number('0' + entity.substr(1));
if (!isNaN(n)) {
value = String.fromCharCode(n);
}
}
// Fall back to innerHTML otherwise.
if (!value) {
// Append a non-entity character to avoid a bug in Webkit that parses
// an invalid entity at the end of innerHTML text as the empty string.
div.innerHTML = s + ' ';
// Then remove the trailing character from the result.
value = div.firstChild.nodeValue.slice(0, -1);
}
// Cache and return.
return seen[s] = value;
});
};
/**
* Unescapes XML entities.
* @private
* @param {string} str The string to unescape.
* @return {string} An unescaped copy of {@code str}.
*/
goog.string.unescapePureXmlEntities_ = function(str) {
return str.replace(/&([^;]+);/g, function(s, entity) {
switch (entity) {
case 'amp':
return '&';
case 'lt':
return '<';
case 'gt':
return '>';
case 'quot':
return '"';
default:
if (entity.charAt(0) == '#') {
// Prefix with 0 so that hex entities (e.g. ) parse as hex.
var n = Number('0' + entity.substr(1));
if (!isNaN(n)) {
return String.fromCharCode(n);
}
}
// For invalid entities we just return the entity
return s;
}
});
};
/**
* Regular expression that matches an HTML entity.
* See also HTML5: Tokenization / Tokenizing character references.
* @private
* @type {!RegExp}
*/
goog.string.HTML_ENTITY_PATTERN_ = /&([^;\s<&]+);?/g;
/**
* Do escaping of whitespace to preserve spatial formatting. We use character
* entity #160 to make it safer for xml.
* @param {string} str The string in which to escape whitespace.
* @param {boolean=} opt_xml Whether to use XML compatible tags.
* @return {string} An escaped copy of {@code str}.
*/
goog.string.whitespaceEscape = function(str, opt_xml) {
// This doesn't use goog.string.preserveSpaces for backwards compatibility.
return goog.string.newLineToBr(str.replace(/ /g, ' '), opt_xml);
};
/**
* Preserve spaces that would be otherwise collapsed in HTML by replacing them
* with non-breaking space Unicode characters.
* @param {string} str The string in which to preserve whitespace.
* @return {string} A copy of {@code str} with preserved whitespace.
*/
goog.string.preserveSpaces = function(str) {
return str.replace(/(^|[\n ]) /g, '$1' + goog.string.Unicode.NBSP);
};
/**
* Strip quote characters around a string. The second argument is a string of
* characters to treat as quotes. This can be a single character or a string of
* multiple character and in that case each of those are treated as possible
* quote characters. For example:
*
*
* goog.string.stripQuotes('"abc"', '"`') --> 'abc'
* goog.string.stripQuotes('`abc`', '"`') --> 'abc'
*
*
* @param {string} str The string to strip.
* @param {string} quoteChars The quote characters to strip.
* @return {string} A copy of {@code str} without the quotes.
*/
goog.string.stripQuotes = function(str, quoteChars) {
var length = quoteChars.length;
for (var i = 0; i < length; i++) {
var quoteChar = length == 1 ? quoteChars : quoteChars.charAt(i);
if (str.charAt(0) == quoteChar && str.charAt(str.length - 1) == quoteChar) {
return str.substring(1, str.length - 1);
}
}
return str;
};
/**
* Truncates a string to a certain length and adds '...' if necessary. The
* length also accounts for the ellipsis, so a maximum length of 10 and a string
* 'Hello World!' produces 'Hello W...'.
* @param {string} str The string to truncate.
* @param {number} chars Max number of characters.
* @param {boolean=} opt_protectEscapedCharacters Whether to protect escaped
* characters from being cut off in the middle.
* @return {string} The truncated {@code str} string.
*/
goog.string.truncate = function(str, chars, opt_protectEscapedCharacters) {
if (opt_protectEscapedCharacters) {
str = goog.string.unescapeEntities(str);
}
if (str.length > chars) {
str = str.substring(0, chars - 3) + '...';
}
if (opt_protectEscapedCharacters) {
str = goog.string.htmlEscape(str);
}
return str;
};
/**
* Truncate a string in the middle, adding "..." if necessary,
* and favoring the beginning of the string.
* @param {string} str The string to truncate the middle of.
* @param {number} chars Max number of characters.
* @param {boolean=} opt_protectEscapedCharacters Whether to protect escaped
* characters from being cutoff in the middle.
* @param {number=} opt_trailingChars Optional number of trailing characters to
* leave at the end of the string, instead of truncating as close to the
* middle as possible.
* @return {string} A truncated copy of {@code str}.
*/
goog.string.truncateMiddle = function(
str, chars, opt_protectEscapedCharacters, opt_trailingChars) {
if (opt_protectEscapedCharacters) {
str = goog.string.unescapeEntities(str);
}
if (opt_trailingChars && str.length > chars) {
if (opt_trailingChars > chars) {
opt_trailingChars = chars;
}
var endPoint = str.length - opt_trailingChars;
var startPoint = chars - opt_trailingChars;
str = str.substring(0, startPoint) + '...' + str.substring(endPoint);
} else if (str.length > chars) {
// Favor the beginning of the string:
var half = Math.floor(chars / 2);
var endPos = str.length - half;
half += chars % 2;
str = str.substring(0, half) + '...' + str.substring(endPos);
}
if (opt_protectEscapedCharacters) {
str = goog.string.htmlEscape(str);
}
return str;
};
/**
* Special chars that need to be escaped for goog.string.quote.
* @private {!Object}
*/
goog.string.specialEscapeChars_ = {
'\0': '\\0',
'\b': '\\b',
'\f': '\\f',
'\n': '\\n',
'\r': '\\r',
'\t': '\\t',
'\x0B': '\\x0B', // '\v' is not supported in JScript
'"': '\\"',
'\\': '\\\\',
// To support the use case of embedding quoted strings inside of script
// tags, we have to make sure HTML comments and opening/closing script tags do
// not appear in the resulting string. The specific strings that must be
// escaped are documented at:
// http://www.w3.org/TR/html51/semantics.html#restrictions-for-contents-of-script-elements
'<': '\x3c'
};
/**
* Character mappings used internally for goog.string.escapeChar.
* @private {!Object}
*/
goog.string.jsEscapeCache_ = {
'\'': '\\\''
};
/**
* Encloses a string in double quotes and escapes characters so that the
* string is a valid JS string. The resulting string is safe to embed in
* `