node/lib/querystring.js

455 строки
14 KiB
JavaScript

// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.
// Query String Utilities
'use strict';
const { Buffer } = require('buffer');
const { ERR_INVALID_URI } = require('internal/errors').codes;
const {
hexTable,
isHexTable
} = require('internal/querystring');
const QueryString = module.exports = {
unescapeBuffer,
// `unescape()` is a JS global, so we need to use a different local name
unescape: qsUnescape,
// `escape()` is a JS global, so we need to use a different local name
escape: qsEscape,
stringify,
encode: stringify,
parse,
decode: parse
};
const unhexTable = [
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 0 - 15
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 16 - 31
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 32 - 47
+0, +1, +2, +3, +4, +5, +6, +7, +8, +9, -1, -1, -1, -1, -1, -1, // 48 - 63
-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 64 - 79
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 80 - 95
-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 96 - 111
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 112 - 127
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, // 128 ...
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 // ... 255
];
// a safe fast alternative to decodeURIComponent
function unescapeBuffer(s, decodeSpaces) {
var out = Buffer.allocUnsafe(s.length);
var index = 0;
var outIndex = 0;
var currentChar;
var nextChar;
var hexHigh;
var hexLow;
var maxLength = s.length - 2;
// Flag to know if some hex chars have been decoded
var hasHex = false;
while (index < s.length) {
currentChar = s.charCodeAt(index);
if (currentChar === 43 /* '+' */ && decodeSpaces) {
out[outIndex++] = 32; // ' '
index++;
continue;
}
if (currentChar === 37 /* '%' */ && index < maxLength) {
currentChar = s.charCodeAt(++index);
hexHigh = unhexTable[currentChar];
if (!(hexHigh >= 0)) {
out[outIndex++] = 37; // '%'
} else {
nextChar = s.charCodeAt(++index);
hexLow = unhexTable[nextChar];
if (!(hexLow >= 0)) {
out[outIndex++] = 37; // '%'
out[outIndex++] = currentChar;
currentChar = nextChar;
} else {
hasHex = true;
currentChar = hexHigh * 16 + hexLow;
}
}
}
out[outIndex++] = currentChar;
index++;
}
return hasHex ? out.slice(0, outIndex) : out;
}
function qsUnescape(s, decodeSpaces) {
try {
return decodeURIComponent(s);
} catch (e) {
return QueryString.unescapeBuffer(s, decodeSpaces).toString();
}
}
// These characters do not need escaping when generating query strings:
// ! - . _ ~
// ' ( ) *
// digits
// alpha (uppercase)
// alpha (lowercase)
const noEscape = [
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0 - 15
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 16 - 31
0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, // 32 - 47
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, // 48 - 63
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 64 - 79
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, // 80 - 95
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 96 - 111
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0 // 112 - 127
];
// QueryString.escape() replaces encodeURIComponent()
// http://www.ecma-international.org/ecma-262/5.1/#sec-15.1.3.4
function qsEscape(str) {
if (typeof str !== 'string') {
if (typeof str === 'object')
str = String(str);
else
str += '';
}
var out = '';
var lastPos = 0;
for (var i = 0; i < str.length; ++i) {
var c = str.charCodeAt(i);
// ASCII
if (c < 0x80) {
if (noEscape[c] === 1)
continue;
if (lastPos < i)
out += str.slice(lastPos, i);
lastPos = i + 1;
out += hexTable[c];
continue;
}
if (lastPos < i)
out += str.slice(lastPos, i);
// Multi-byte characters ...
if (c < 0x800) {
lastPos = i + 1;
out += hexTable[0xC0 | (c >> 6)] + hexTable[0x80 | (c & 0x3F)];
continue;
}
if (c < 0xD800 || c >= 0xE000) {
lastPos = i + 1;
out += hexTable[0xE0 | (c >> 12)] +
hexTable[0x80 | ((c >> 6) & 0x3F)] +
hexTable[0x80 | (c & 0x3F)];
continue;
}
// Surrogate pair
++i;
if (i >= str.length)
throw new ERR_INVALID_URI();
var c2 = str.charCodeAt(i) & 0x3FF;
lastPos = i + 1;
c = 0x10000 + (((c & 0x3FF) << 10) | c2);
out += hexTable[0xF0 | (c >> 18)] +
hexTable[0x80 | ((c >> 12) & 0x3F)] +
hexTable[0x80 | ((c >> 6) & 0x3F)] +
hexTable[0x80 | (c & 0x3F)];
}
if (lastPos === 0)
return str;
if (lastPos < str.length)
return out + str.slice(lastPos);
return out;
}
function stringifyPrimitive(v) {
if (typeof v === 'string')
return v;
if (typeof v === 'number' && isFinite(v))
return '' + v;
if (typeof v === 'boolean')
return v ? 'true' : 'false';
return '';
}
function stringify(obj, sep, eq, options) {
sep = sep || '&';
eq = eq || '=';
var encode = QueryString.escape;
if (options && typeof options.encodeURIComponent === 'function') {
encode = options.encodeURIComponent;
}
if (obj !== null && typeof obj === 'object') {
var keys = Object.keys(obj);
var len = keys.length;
var flast = len - 1;
var fields = '';
for (var i = 0; i < len; ++i) {
var k = keys[i];
var v = obj[k];
var ks = encode(stringifyPrimitive(k)) + eq;
if (Array.isArray(v)) {
var vlen = v.length;
var vlast = vlen - 1;
for (var j = 0; j < vlen; ++j) {
fields += ks + encode(stringifyPrimitive(v[j]));
if (j < vlast)
fields += sep;
}
if (vlen && i < flast)
fields += sep;
} else {
fields += ks + encode(stringifyPrimitive(v));
if (i < flast)
fields += sep;
}
}
return fields;
}
return '';
}
function charCodes(str) {
if (str.length === 0) return [];
if (str.length === 1) return [str.charCodeAt(0)];
const ret = [];
for (var i = 0; i < str.length; ++i)
ret[ret.length] = str.charCodeAt(i);
return ret;
}
const defSepCodes = [38]; // &
const defEqCodes = [61]; // =
// Parse a key/val string.
function parse(qs, sep, eq, options) {
const obj = Object.create(null);
if (typeof qs !== 'string' || qs.length === 0) {
return obj;
}
var sepCodes = (!sep ? defSepCodes : charCodes(sep + ''));
var eqCodes = (!eq ? defEqCodes : charCodes(eq + ''));
const sepLen = sepCodes.length;
const eqLen = eqCodes.length;
var pairs = 1000;
if (options && typeof options.maxKeys === 'number') {
// -1 is used in place of a value like Infinity for meaning
// "unlimited pairs" because of additional checks V8 (at least as of v5.4)
// has to do when using variables that contain values like Infinity. Since
// `pairs` is always decremented and checked explicitly for 0, -1 works
// effectively the same as Infinity, while providing a significant
// performance boost.
pairs = (options.maxKeys > 0 ? options.maxKeys : -1);
}
var decode = QueryString.unescape;
if (options && typeof options.decodeURIComponent === 'function') {
decode = options.decodeURIComponent;
}
const customDecode = (decode !== qsUnescape);
var lastPos = 0;
var sepIdx = 0;
var eqIdx = 0;
var key = '';
var value = '';
var keyEncoded = customDecode;
var valEncoded = customDecode;
const plusChar = (customDecode ? '%20' : ' ');
var encodeCheck = 0;
for (var i = 0; i < qs.length; ++i) {
const code = qs.charCodeAt(i);
// Try matching key/value pair separator (e.g. '&')
if (code === sepCodes[sepIdx]) {
if (++sepIdx === sepLen) {
// Key/value pair separator match!
const end = i - sepIdx + 1;
if (eqIdx < eqLen) {
// We didn't find the (entire) key/value separator
if (lastPos < end) {
// Treat the substring as part of the key instead of the value
key += qs.slice(lastPos, end);
} else if (key.length === 0) {
// We saw an empty substring between separators
if (--pairs === 0)
return obj;
lastPos = i + 1;
sepIdx = eqIdx = 0;
continue;
}
} else if (lastPos < end) {
value += qs.slice(lastPos, end);
}
if (key.length > 0 && keyEncoded)
key = decodeStr(key, decode);
if (value.length > 0 && valEncoded)
value = decodeStr(value, decode);
if (obj[key] === undefined) {
obj[key] = value;
} else {
const curValue = obj[key];
// A simple Array-specific property check is enough here to
// distinguish from a string value and is faster and still safe
// since we are generating all of the values being assigned.
if (curValue.pop)
curValue[curValue.length] = value;
else
obj[key] = [curValue, value];
}
if (--pairs === 0)
return obj;
keyEncoded = valEncoded = customDecode;
key = value = '';
encodeCheck = 0;
lastPos = i + 1;
sepIdx = eqIdx = 0;
}
} else {
sepIdx = 0;
// Try matching key/value separator (e.g. '=') if we haven't already
if (eqIdx < eqLen) {
if (code === eqCodes[eqIdx]) {
if (++eqIdx === eqLen) {
// Key/value separator match!
const end = i - eqIdx + 1;
if (lastPos < end)
key += qs.slice(lastPos, end);
encodeCheck = 0;
lastPos = i + 1;
}
continue;
} else {
eqIdx = 0;
if (!keyEncoded) {
// Try to match an (valid) encoded byte once to minimize unnecessary
// calls to string decoding functions
if (code === 37/* % */) {
encodeCheck = 1;
continue;
} else if (encodeCheck > 0) {
// eslint-disable-next-line no-extra-boolean-cast
if (!!isHexTable[code]) {
if (++encodeCheck === 3)
keyEncoded = true;
continue;
} else {
encodeCheck = 0;
}
}
}
}
if (code === 43/* + */) {
if (lastPos < i)
key += qs.slice(lastPos, i);
key += plusChar;
lastPos = i + 1;
continue;
}
}
if (code === 43/* + */) {
if (lastPos < i)
value += qs.slice(lastPos, i);
value += plusChar;
lastPos = i + 1;
} else if (!valEncoded) {
// Try to match an (valid) encoded byte (once) to minimize unnecessary
// calls to string decoding functions
if (code === 37/* % */) {
encodeCheck = 1;
} else if (encodeCheck > 0) {
// eslint-disable-next-line no-extra-boolean-cast
if (!!isHexTable[code]) {
if (++encodeCheck === 3)
valEncoded = true;
} else {
encodeCheck = 0;
}
}
}
}
}
// Deal with any leftover key or value data
if (lastPos < qs.length) {
if (eqIdx < eqLen)
key += qs.slice(lastPos);
else if (sepIdx < sepLen)
value += qs.slice(lastPos);
} else if (eqIdx === 0 && key.length === 0) {
// We ended on an empty substring
return obj;
}
if (key.length > 0 && keyEncoded)
key = decodeStr(key, decode);
if (value.length > 0 && valEncoded)
value = decodeStr(value, decode);
if (obj[key] === undefined) {
obj[key] = value;
} else {
const curValue = obj[key];
// A simple Array-specific property check is enough here to
// distinguish from a string value and is faster and still safe since
// we are generating all of the values being assigned.
if (curValue.pop)
curValue[curValue.length] = value;
else
obj[key] = [curValue, value];
}
return obj;
}
// v8 does not optimize functions with try-catch blocks, so we isolate them here
// to minimize the damage (Note: no longer true as of V8 5.4 -- but still will
// not be inlined).
function decodeStr(s, decoder) {
try {
return decoder(s);
} catch (e) {
return QueryString.unescape(s, true);
}
}