You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
261 lines
8.2 KiB
261 lines
8.2 KiB
'use strict'; |
|
|
|
const charCodeDefinitions = require('./char-code-definitions.cjs'); |
|
|
|
function getCharCode(source, offset) { |
|
return offset < source.length ? source.charCodeAt(offset) : 0; |
|
} |
|
|
|
function getNewlineLength(source, offset, code) { |
|
if (code === 13 /* \r */ && getCharCode(source, offset + 1) === 10 /* \n */) { |
|
return 2; |
|
} |
|
|
|
return 1; |
|
} |
|
|
|
function cmpChar(testStr, offset, referenceCode) { |
|
let code = testStr.charCodeAt(offset); |
|
|
|
// code.toLowerCase() for A..Z |
|
if (charCodeDefinitions.isUppercaseLetter(code)) { |
|
code = code | 32; |
|
} |
|
|
|
return code === referenceCode; |
|
} |
|
|
|
function cmpStr(testStr, start, end, referenceStr) { |
|
if (end - start !== referenceStr.length) { |
|
return false; |
|
} |
|
|
|
if (start < 0 || end > testStr.length) { |
|
return false; |
|
} |
|
|
|
for (let i = start; i < end; i++) { |
|
const referenceCode = referenceStr.charCodeAt(i - start); |
|
let testCode = testStr.charCodeAt(i); |
|
|
|
// testCode.toLowerCase() for A..Z |
|
if (charCodeDefinitions.isUppercaseLetter(testCode)) { |
|
testCode = testCode | 32; |
|
} |
|
|
|
if (testCode !== referenceCode) { |
|
return false; |
|
} |
|
} |
|
|
|
return true; |
|
} |
|
|
|
function findWhiteSpaceStart(source, offset) { |
|
for (; offset >= 0; offset--) { |
|
if (!charCodeDefinitions.isWhiteSpace(source.charCodeAt(offset))) { |
|
break; |
|
} |
|
} |
|
|
|
return offset + 1; |
|
} |
|
|
|
function findWhiteSpaceEnd(source, offset) { |
|
for (; offset < source.length; offset++) { |
|
if (!charCodeDefinitions.isWhiteSpace(source.charCodeAt(offset))) { |
|
break; |
|
} |
|
} |
|
|
|
return offset; |
|
} |
|
|
|
function findDecimalNumberEnd(source, offset) { |
|
for (; offset < source.length; offset++) { |
|
if (!charCodeDefinitions.isDigit(source.charCodeAt(offset))) { |
|
break; |
|
} |
|
} |
|
|
|
return offset; |
|
} |
|
|
|
// § 4.3.7. Consume an escaped code point |
|
function consumeEscaped(source, offset) { |
|
// It assumes that the U+005C REVERSE SOLIDUS (\) has already been consumed and |
|
// that the next input code point has already been verified to be part of a valid escape. |
|
offset += 2; |
|
|
|
// hex digit |
|
if (charCodeDefinitions.isHexDigit(getCharCode(source, offset - 1))) { |
|
// Consume as many hex digits as possible, but no more than 5. |
|
// Note that this means 1-6 hex digits have been consumed in total. |
|
for (const maxOffset = Math.min(source.length, offset + 5); offset < maxOffset; offset++) { |
|
if (!charCodeDefinitions.isHexDigit(getCharCode(source, offset))) { |
|
break; |
|
} |
|
} |
|
|
|
// If the next input code point is whitespace, consume it as well. |
|
const code = getCharCode(source, offset); |
|
if (charCodeDefinitions.isWhiteSpace(code)) { |
|
offset += getNewlineLength(source, offset, code); |
|
} |
|
} |
|
|
|
return offset; |
|
} |
|
|
|
// §4.3.11. Consume a name |
|
// Note: This algorithm does not do the verification of the first few code points that are necessary |
|
// to ensure the returned code points would constitute an <ident-token>. If that is the intended use, |
|
// ensure that the stream starts with an identifier before calling this algorithm. |
|
function consumeName(source, offset) { |
|
// Let result initially be an empty string. |
|
// Repeatedly consume the next input code point from the stream: |
|
for (; offset < source.length; offset++) { |
|
const code = source.charCodeAt(offset); |
|
|
|
// name code point |
|
if (charCodeDefinitions.isName(code)) { |
|
// Append the code point to result. |
|
continue; |
|
} |
|
|
|
// the stream starts with a valid escape |
|
if (charCodeDefinitions.isValidEscape(code, getCharCode(source, offset + 1))) { |
|
// Consume an escaped code point. Append the returned code point to result. |
|
offset = consumeEscaped(source, offset) - 1; |
|
continue; |
|
} |
|
|
|
// anything else |
|
// Reconsume the current input code point. Return result. |
|
break; |
|
} |
|
|
|
return offset; |
|
} |
|
|
|
// §4.3.12. Consume a number |
|
function consumeNumber(source, offset) { |
|
let code = source.charCodeAt(offset); |
|
|
|
// 2. If the next input code point is U+002B PLUS SIGN (+) or U+002D HYPHEN-MINUS (-), |
|
// consume it and append it to repr. |
|
if (code === 0x002B || code === 0x002D) { |
|
code = source.charCodeAt(offset += 1); |
|
} |
|
|
|
// 3. While the next input code point is a digit, consume it and append it to repr. |
|
if (charCodeDefinitions.isDigit(code)) { |
|
offset = findDecimalNumberEnd(source, offset + 1); |
|
code = source.charCodeAt(offset); |
|
} |
|
|
|
// 4. If the next 2 input code points are U+002E FULL STOP (.) followed by a digit, then: |
|
if (code === 0x002E && charCodeDefinitions.isDigit(source.charCodeAt(offset + 1))) { |
|
// 4.1 Consume them. |
|
// 4.2 Append them to repr. |
|
offset += 2; |
|
|
|
// 4.3 Set type to "number". |
|
// TODO |
|
|
|
// 4.4 While the next input code point is a digit, consume it and append it to repr. |
|
|
|
offset = findDecimalNumberEnd(source, offset); |
|
} |
|
|
|
// 5. If the next 2 or 3 input code points are U+0045 LATIN CAPITAL LETTER E (E) |
|
// or U+0065 LATIN SMALL LETTER E (e), ... , followed by a digit, then: |
|
if (cmpChar(source, offset, 101 /* e */)) { |
|
let sign = 0; |
|
code = source.charCodeAt(offset + 1); |
|
|
|
// ... optionally followed by U+002D HYPHEN-MINUS (-) or U+002B PLUS SIGN (+) ... |
|
if (code === 0x002D || code === 0x002B) { |
|
sign = 1; |
|
code = source.charCodeAt(offset + 2); |
|
} |
|
|
|
// ... followed by a digit |
|
if (charCodeDefinitions.isDigit(code)) { |
|
// 5.1 Consume them. |
|
// 5.2 Append them to repr. |
|
|
|
// 5.3 Set type to "number". |
|
// TODO |
|
|
|
// 5.4 While the next input code point is a digit, consume it and append it to repr. |
|
offset = findDecimalNumberEnd(source, offset + 1 + sign + 1); |
|
} |
|
} |
|
|
|
return offset; |
|
} |
|
|
|
// § 4.3.14. Consume the remnants of a bad url |
|
// ... its sole use is to consume enough of the input stream to reach a recovery point |
|
// where normal tokenizing can resume. |
|
function consumeBadUrlRemnants(source, offset) { |
|
// Repeatedly consume the next input code point from the stream: |
|
for (; offset < source.length; offset++) { |
|
const code = source.charCodeAt(offset); |
|
|
|
// U+0029 RIGHT PARENTHESIS ()) |
|
// EOF |
|
if (code === 0x0029) { |
|
// Return. |
|
offset++; |
|
break; |
|
} |
|
|
|
if (charCodeDefinitions.isValidEscape(code, getCharCode(source, offset + 1))) { |
|
// Consume an escaped code point. |
|
// Note: This allows an escaped right parenthesis ("\)") to be encountered |
|
// without ending the <bad-url-token>. This is otherwise identical to |
|
// the "anything else" clause. |
|
offset = consumeEscaped(source, offset); |
|
} |
|
} |
|
|
|
return offset; |
|
} |
|
|
|
// § 4.3.7. Consume an escaped code point |
|
// Note: This algorithm assumes that escaped is valid without leading U+005C REVERSE SOLIDUS (\) |
|
function decodeEscaped(escaped) { |
|
// Single char escaped that's not a hex digit |
|
if (escaped.length === 1 && !charCodeDefinitions.isHexDigit(escaped.charCodeAt(0))) { |
|
return escaped[0]; |
|
} |
|
|
|
// Interpret the hex digits as a hexadecimal number. |
|
let code = parseInt(escaped, 16); |
|
|
|
if ( |
|
(code === 0) || // If this number is zero, |
|
(code >= 0xD800 && code <= 0xDFFF) || // or is for a surrogate, |
|
(code > 0x10FFFF) // or is greater than the maximum allowed code point |
|
) { |
|
// ... return U+FFFD REPLACEMENT CHARACTER |
|
code = 0xFFFD; |
|
} |
|
|
|
// Otherwise, return the code point with that value. |
|
return String.fromCodePoint(code); |
|
} |
|
|
|
exports.cmpChar = cmpChar; |
|
exports.cmpStr = cmpStr; |
|
exports.consumeBadUrlRemnants = consumeBadUrlRemnants; |
|
exports.consumeEscaped = consumeEscaped; |
|
exports.consumeName = consumeName; |
|
exports.consumeNumber = consumeNumber; |
|
exports.decodeEscaped = decodeEscaped; |
|
exports.findDecimalNumberEnd = findDecimalNumberEnd; |
|
exports.findWhiteSpaceEnd = findWhiteSpaceEnd; |
|
exports.findWhiteSpaceStart = findWhiteSpaceStart; |
|
exports.getNewlineLength = getNewlineLength;
|
|
|