parent
1ce9243f72
commit
3a9463a0ef
@ -0,0 +1,67 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta http-equiv="X-UA-Compatible" content="IE=edge">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Test</title>
|
||||
</head>
|
||||
<body>
|
||||
<div class="content">
|
||||
<h1>Illegal Music Site</h1>
|
||||
<form id="addSongForm">
|
||||
<label for="Title">Title</label>
|
||||
<input type="text" id="Title" name="Title" placeholder="Title" />
|
||||
<label for="Artist">Artist</label>
|
||||
<input type="text" id="Artist" name="Artist" placeholder="Artist" />
|
||||
<label for="File">Mp3 File</label>
|
||||
<input type="file" id="File" name="File"/>
|
||||
<button id="formSubmit">Submit</button>
|
||||
</form>
|
||||
<div>
|
||||
{{@each(it.songs) => s, i}}
|
||||
<div class="song">
|
||||
<p>{{s.Title}} - {{s.Artist}}</p>
|
||||
<audio controls>
|
||||
<source src="{{s.File}}" type="audio/mpeg">
|
||||
</audio>
|
||||
</div>
|
||||
{{/each}}
|
||||
</div>
|
||||
</div>
|
||||
<script>
|
||||
document.getElementById("formSubmit").addEventListener("click", formSubmit)
|
||||
async function formSubmit(e) {
|
||||
e.preventDefault()
|
||||
let file = document.getElementById("File").files[0]
|
||||
let title = document.getElementById("Title").value
|
||||
let artist = document.getElementById("Artist").value
|
||||
|
||||
let data = new FormData()
|
||||
data.append('File', file)
|
||||
data.append('Title', title)
|
||||
data.append('Artist', artist)
|
||||
|
||||
let resp = await fetch("/add", {
|
||||
method: 'POST',
|
||||
body: data
|
||||
}).then((r) => {
|
||||
console.log(r)
|
||||
}
|
||||
)
|
||||
}
|
||||
</script>
|
||||
</body>
|
||||
<style>
|
||||
body {
|
||||
font-family: Verdana, Geneva, Tahoma, sans-serif;
|
||||
}
|
||||
h1 {
|
||||
text-align: center;
|
||||
font-family: 'Franklin Gothic Medium', 'Arial Narrow', Arial, sans-serif;
|
||||
}
|
||||
.content {
|
||||
width: 60%;
|
||||
}
|
||||
</style>
|
||||
</html>
|
||||
@ -0,0 +1,5 @@
|
||||
'use strict';
|
||||
|
||||
module.exports = {
|
||||
extends: '@mscdex/eslint-config',
|
||||
};
|
||||
@ -0,0 +1,24 @@
|
||||
name: CI
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [ master ]
|
||||
|
||||
jobs:
|
||||
tests-linux:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
node-version: [10.16.0, 10.x, 12.x, 14.x, 16.x]
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Use Node.js ${{ matrix.node-version }}
|
||||
uses: actions/setup-node@v1
|
||||
with:
|
||||
node-version: ${{ matrix.node-version }}
|
||||
- name: Install module
|
||||
run: npm install
|
||||
- name: Run tests
|
||||
run: npm test
|
||||
@ -0,0 +1,23 @@
|
||||
name: lint
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [ master ]
|
||||
|
||||
env:
|
||||
NODE_VERSION: 16.x
|
||||
|
||||
jobs:
|
||||
lint-js:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Use Node.js ${{ env.NODE_VERSION }}
|
||||
uses: actions/setup-node@v1
|
||||
with:
|
||||
node-version: ${{ env.NODE_VERSION }}
|
||||
- name: Install ESLint + ESLint configs/plugins
|
||||
run: npm install --only=dev
|
||||
- name: Lint files
|
||||
run: npm run lint
|
||||
@ -0,0 +1,19 @@
|
||||
Copyright Brian White. All rights reserved.
|
||||
|
||||
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.
|
||||
@ -0,0 +1,191 @@
|
||||
# Description
|
||||
|
||||
A node.js module for parsing incoming HTML form data.
|
||||
|
||||
Changes (breaking or otherwise) in v1.0.0 can be found [here](https://github.com/mscdex/busboy/issues/266).
|
||||
|
||||
# Requirements
|
||||
|
||||
* [node.js](http://nodejs.org/) -- v10.16.0 or newer
|
||||
|
||||
|
||||
# Install
|
||||
|
||||
npm install busboy
|
||||
|
||||
|
||||
# Examples
|
||||
|
||||
* Parsing (multipart) with default options:
|
||||
|
||||
```js
|
||||
const http = require('http');
|
||||
|
||||
const busboy = require('busboy');
|
||||
|
||||
http.createServer((req, res) => {
|
||||
if (req.method === 'POST') {
|
||||
console.log('POST request');
|
||||
const bb = busboy({ headers: req.headers });
|
||||
bb.on('file', (name, file, info) => {
|
||||
const { filename, encoding, mimeType } = info;
|
||||
console.log(
|
||||
`File [${name}]: filename: %j, encoding: %j, mimeType: %j`,
|
||||
filename,
|
||||
encoding,
|
||||
mimeType
|
||||
);
|
||||
file.on('data', (data) => {
|
||||
console.log(`File [${name}] got ${data.length} bytes`);
|
||||
}).on('close', () => {
|
||||
console.log(`File [${name}] done`);
|
||||
});
|
||||
});
|
||||
bb.on('field', (name, val, info) => {
|
||||
console.log(`Field [${name}]: value: %j`, val);
|
||||
});
|
||||
bb.on('close', () => {
|
||||
console.log('Done parsing form!');
|
||||
res.writeHead(303, { Connection: 'close', Location: '/' });
|
||||
res.end();
|
||||
});
|
||||
req.pipe(bb);
|
||||
} else if (req.method === 'GET') {
|
||||
res.writeHead(200, { Connection: 'close' });
|
||||
res.end(`
|
||||
<html>
|
||||
<head></head>
|
||||
<body>
|
||||
<form method="POST" enctype="multipart/form-data">
|
||||
<input type="file" name="filefield"><br />
|
||||
<input type="text" name="textfield"><br />
|
||||
<input type="submit">
|
||||
</form>
|
||||
</body>
|
||||
</html>
|
||||
`);
|
||||
}
|
||||
}).listen(8000, () => {
|
||||
console.log('Listening for requests');
|
||||
});
|
||||
|
||||
// Example output:
|
||||
//
|
||||
// Listening for requests
|
||||
// < ... form submitted ... >
|
||||
// POST request
|
||||
// File [filefield]: filename: "logo.jpg", encoding: "binary", mime: "image/jpeg"
|
||||
// File [filefield] got 11912 bytes
|
||||
// Field [textfield]: value: "testing! :-)"
|
||||
// File [filefield] done
|
||||
// Done parsing form!
|
||||
```
|
||||
|
||||
* Save all incoming files to disk:
|
||||
|
||||
```js
|
||||
const { randomFillSync } = require('crypto');
|
||||
const fs = require('fs');
|
||||
const http = require('http');
|
||||
const os = require('os');
|
||||
const path = require('path');
|
||||
|
||||
const busboy = require('busboy');
|
||||
|
||||
const random = (() => {
|
||||
const buf = Buffer.alloc(16);
|
||||
return () => randomFillSync(buf).toString('hex');
|
||||
})();
|
||||
|
||||
http.createServer((req, res) => {
|
||||
if (req.method === 'POST') {
|
||||
const bb = busboy({ headers: req.headers });
|
||||
bb.on('file', (name, file, info) => {
|
||||
const saveTo = path.join(os.tmpdir(), `busboy-upload-${random()}`);
|
||||
file.pipe(fs.createWriteStream(saveTo));
|
||||
});
|
||||
bb.on('close', () => {
|
||||
res.writeHead(200, { 'Connection': 'close' });
|
||||
res.end(`That's all folks!`);
|
||||
});
|
||||
req.pipe(bb);
|
||||
return;
|
||||
}
|
||||
res.writeHead(404);
|
||||
res.end();
|
||||
}).listen(8000, () => {
|
||||
console.log('Listening for requests');
|
||||
});
|
||||
```
|
||||
|
||||
|
||||
# API
|
||||
|
||||
## Exports
|
||||
|
||||
`busboy` exports a single function:
|
||||
|
||||
**( _function_ )**(< _object_ >config) - Creates and returns a new _Writable_ form parser stream.
|
||||
|
||||
* Valid `config` properties:
|
||||
|
||||
* **headers** - _object_ - These are the HTTP headers of the incoming request, which are used by individual parsers.
|
||||
|
||||
* **highWaterMark** - _integer_ - highWaterMark to use for the parser stream. **Default:** node's _stream.Writable_ default.
|
||||
|
||||
* **fileHwm** - _integer_ - highWaterMark to use for individual file streams. **Default:** node's _stream.Readable_ default.
|
||||
|
||||
* **defCharset** - _string_ - Default character set to use when one isn't defined. **Default:** `'utf8'`.
|
||||
|
||||
* **defParamCharset** - _string_ - For multipart forms, the default character set to use for values of part header parameters (e.g. filename) that are not extended parameters (that contain an explicit charset). **Default:** `'latin1'`.
|
||||
|
||||
* **preservePath** - _boolean_ - If paths in filenames from file parts in a `'multipart/form-data'` request shall be preserved. **Default:** `false`.
|
||||
|
||||
* **limits** - _object_ - Various limits on incoming data. Valid properties are:
|
||||
|
||||
* **fieldNameSize** - _integer_ - Max field name size (in bytes). **Default:** `100`.
|
||||
|
||||
* **fieldSize** - _integer_ - Max field value size (in bytes). **Default:** `1048576` (1MB).
|
||||
|
||||
* **fields** - _integer_ - Max number of non-file fields. **Default:** `Infinity`.
|
||||
|
||||
* **fileSize** - _integer_ - For multipart forms, the max file size (in bytes). **Default:** `Infinity`.
|
||||
|
||||
* **files** - _integer_ - For multipart forms, the max number of file fields. **Default:** `Infinity`.
|
||||
|
||||
* **parts** - _integer_ - For multipart forms, the max number of parts (fields + files). **Default:** `Infinity`.
|
||||
|
||||
* **headerPairs** - _integer_ - For multipart forms, the max number of header key-value pairs to parse. **Default:** `2000` (same as node's http module).
|
||||
|
||||
This function can throw exceptions if there is something wrong with the values in `config`. For example, if the Content-Type in `headers` is missing entirely, is not a supported type, or is missing the boundary for `'multipart/form-data'` requests.
|
||||
|
||||
## (Special) Parser stream events
|
||||
|
||||
* **file**(< _string_ >name, < _Readable_ >stream, < _object_ >info) - Emitted for each new file found. `name` contains the form field name. `stream` is a _Readable_ stream containing the file's data. No transformations/conversions (e.g. base64 to raw binary) are done on the file's data. `info` contains the following properties:
|
||||
|
||||
* `filename` - _string_ - If supplied, this contains the file's filename. **WARNING:** You should almost _never_ use this value as-is (especially if you are using `preservePath: true` in your `config`) as it could contain malicious input. You are better off generating your own (safe) filenames, or at the very least using a hash of the filename.
|
||||
|
||||
* `encoding` - _string_ - The file's `'Content-Transfer-Encoding'` value.
|
||||
|
||||
* `mimeType` - _string_ - The file's `'Content-Type'` value.
|
||||
|
||||
**Note:** If you listen for this event, you should always consume the `stream` whether you care about its contents or not (you can simply do `stream.resume();` if you want to discard/skip the contents), otherwise the `'finish'`/`'close'` event will never fire on the busboy parser stream.
|
||||
However, if you aren't accepting files, you can either simply not listen for the `'file'` event at all or set `limits.files` to `0`, and any/all files will be automatically skipped (these skipped files will still count towards any configured `limits.files` and `limits.parts` limits though).
|
||||
|
||||
**Note:** If a configured `limits.fileSize` limit was reached for a file, `stream` will both have a boolean property `truncated` set to `true` (best checked at the end of the stream) and emit a `'limit'` event to notify you when this happens.
|
||||
|
||||
* **field**(< _string_ >name, < _string_ >value, < _object_ >info) - Emitted for each new non-file field found. `name` contains the form field name. `value` contains the string value of the field. `info` contains the following properties:
|
||||
|
||||
* `nameTruncated` - _boolean_ - Whether `name` was truncated or not (due to a configured `limits.fieldNameSize` limit)
|
||||
|
||||
* `valueTruncated` - _boolean_ - Whether `value` was truncated or not (due to a configured `limits.fieldSize` limit)
|
||||
|
||||
* `encoding` - _string_ - The field's `'Content-Transfer-Encoding'` value.
|
||||
|
||||
* `mimeType` - _string_ - The field's `'Content-Type'` value.
|
||||
|
||||
* **partsLimit**() - Emitted when the configured `limits.parts` limit has been reached. No more `'file'` or `'field'` events will be emitted.
|
||||
|
||||
* **filesLimit**() - Emitted when the configured `limits.files` limit has been reached. No more `'file'` events will be emitted.
|
||||
|
||||
* **fieldsLimit**() - Emitted when the configured `limits.fields` limit has been reached. No more `'field'` events will be emitted.
|
||||
@ -0,0 +1,149 @@
|
||||
'use strict';
|
||||
|
||||
function createMultipartBuffers(boundary, sizes) {
|
||||
const bufs = [];
|
||||
for (let i = 0; i < sizes.length; ++i) {
|
||||
const mb = sizes[i] * 1024 * 1024;
|
||||
bufs.push(Buffer.from([
|
||||
`--${boundary}`,
|
||||
`content-disposition: form-data; name="field${i + 1}"`,
|
||||
'',
|
||||
'0'.repeat(mb),
|
||||
'',
|
||||
].join('\r\n')));
|
||||
}
|
||||
bufs.push(Buffer.from([
|
||||
`--${boundary}--`,
|
||||
'',
|
||||
].join('\r\n')));
|
||||
return bufs;
|
||||
}
|
||||
|
||||
const boundary = '-----------------------------168072824752491622650073';
|
||||
const buffers = createMultipartBuffers(boundary, [
|
||||
10,
|
||||
10,
|
||||
10,
|
||||
20,
|
||||
50,
|
||||
]);
|
||||
const calls = {
|
||||
partBegin: 0,
|
||||
headerField: 0,
|
||||
headerValue: 0,
|
||||
headerEnd: 0,
|
||||
headersEnd: 0,
|
||||
partData: 0,
|
||||
partEnd: 0,
|
||||
end: 0,
|
||||
};
|
||||
|
||||
const moduleName = process.argv[2];
|
||||
switch (moduleName) {
|
||||
case 'busboy': {
|
||||
const busboy = require('busboy');
|
||||
|
||||
const parser = busboy({
|
||||
limits: {
|
||||
fieldSizeLimit: Infinity,
|
||||
},
|
||||
headers: {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
},
|
||||
});
|
||||
parser.on('field', (name, val, info) => {
|
||||
++calls.partBegin;
|
||||
++calls.partData;
|
||||
++calls.partEnd;
|
||||
}).on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
console.time(moduleName);
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
break;
|
||||
}
|
||||
|
||||
case 'formidable': {
|
||||
const { MultipartParser } = require('formidable');
|
||||
|
||||
const parser = new MultipartParser();
|
||||
parser.initWithBoundary(boundary);
|
||||
parser.on('data', ({ name }) => {
|
||||
++calls[name];
|
||||
if (name === 'end')
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
console.time(moduleName);
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
case 'multiparty': {
|
||||
const { Readable } = require('stream');
|
||||
|
||||
const { Form } = require('multiparty');
|
||||
|
||||
const form = new Form({
|
||||
maxFieldsSize: Infinity,
|
||||
maxFields: Infinity,
|
||||
maxFilesSize: Infinity,
|
||||
autoFields: false,
|
||||
autoFiles: false,
|
||||
});
|
||||
|
||||
const req = new Readable({ read: () => {} });
|
||||
req.headers = {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
};
|
||||
|
||||
function hijack(name, fn) {
|
||||
const oldFn = form[name];
|
||||
form[name] = function() {
|
||||
fn();
|
||||
return oldFn.apply(this, arguments);
|
||||
};
|
||||
}
|
||||
|
||||
hijack('onParseHeaderField', () => {
|
||||
++calls.headerField;
|
||||
});
|
||||
hijack('onParseHeaderValue', () => {
|
||||
++calls.headerValue;
|
||||
});
|
||||
hijack('onParsePartBegin', () => {
|
||||
++calls.partBegin;
|
||||
});
|
||||
hijack('onParsePartData', () => {
|
||||
++calls.partData;
|
||||
});
|
||||
hijack('onParsePartEnd', () => {
|
||||
++calls.partEnd;
|
||||
});
|
||||
|
||||
form.on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
}).on('part', (p) => p.resume());
|
||||
|
||||
console.time(moduleName);
|
||||
form.parse(req);
|
||||
for (const buf of buffers)
|
||||
req.push(buf);
|
||||
req.push(null);
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
if (moduleName === undefined)
|
||||
console.error('Missing parser module name');
|
||||
else
|
||||
console.error(`Invalid parser module name: ${moduleName}`);
|
||||
process.exit(1);
|
||||
}
|
||||
@ -0,0 +1,143 @@
|
||||
'use strict';
|
||||
|
||||
function createMultipartBuffers(boundary, sizes) {
|
||||
const bufs = [];
|
||||
for (let i = 0; i < sizes.length; ++i) {
|
||||
const mb = sizes[i] * 1024 * 1024;
|
||||
bufs.push(Buffer.from([
|
||||
`--${boundary}`,
|
||||
`content-disposition: form-data; name="field${i + 1}"`,
|
||||
'',
|
||||
'0'.repeat(mb),
|
||||
'',
|
||||
].join('\r\n')));
|
||||
}
|
||||
bufs.push(Buffer.from([
|
||||
`--${boundary}--`,
|
||||
'',
|
||||
].join('\r\n')));
|
||||
return bufs;
|
||||
}
|
||||
|
||||
const boundary = '-----------------------------168072824752491622650073';
|
||||
const buffers = createMultipartBuffers(boundary, (new Array(100)).fill(1));
|
||||
const calls = {
|
||||
partBegin: 0,
|
||||
headerField: 0,
|
||||
headerValue: 0,
|
||||
headerEnd: 0,
|
||||
headersEnd: 0,
|
||||
partData: 0,
|
||||
partEnd: 0,
|
||||
end: 0,
|
||||
};
|
||||
|
||||
const moduleName = process.argv[2];
|
||||
switch (moduleName) {
|
||||
case 'busboy': {
|
||||
const busboy = require('busboy');
|
||||
|
||||
const parser = busboy({
|
||||
limits: {
|
||||
fieldSizeLimit: Infinity,
|
||||
},
|
||||
headers: {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
},
|
||||
});
|
||||
parser.on('field', (name, val, info) => {
|
||||
++calls.partBegin;
|
||||
++calls.partData;
|
||||
++calls.partEnd;
|
||||
}).on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
console.time(moduleName);
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
break;
|
||||
}
|
||||
|
||||
case 'formidable': {
|
||||
const { MultipartParser } = require('formidable');
|
||||
|
||||
const parser = new MultipartParser();
|
||||
parser.initWithBoundary(boundary);
|
||||
parser.on('data', ({ name }) => {
|
||||
++calls[name];
|
||||
if (name === 'end')
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
console.time(moduleName);
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
case 'multiparty': {
|
||||
const { Readable } = require('stream');
|
||||
|
||||
const { Form } = require('multiparty');
|
||||
|
||||
const form = new Form({
|
||||
maxFieldsSize: Infinity,
|
||||
maxFields: Infinity,
|
||||
maxFilesSize: Infinity,
|
||||
autoFields: false,
|
||||
autoFiles: false,
|
||||
});
|
||||
|
||||
const req = new Readable({ read: () => {} });
|
||||
req.headers = {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
};
|
||||
|
||||
function hijack(name, fn) {
|
||||
const oldFn = form[name];
|
||||
form[name] = function() {
|
||||
fn();
|
||||
return oldFn.apply(this, arguments);
|
||||
};
|
||||
}
|
||||
|
||||
hijack('onParseHeaderField', () => {
|
||||
++calls.headerField;
|
||||
});
|
||||
hijack('onParseHeaderValue', () => {
|
||||
++calls.headerValue;
|
||||
});
|
||||
hijack('onParsePartBegin', () => {
|
||||
++calls.partBegin;
|
||||
});
|
||||
hijack('onParsePartData', () => {
|
||||
++calls.partData;
|
||||
});
|
||||
hijack('onParsePartEnd', () => {
|
||||
++calls.partEnd;
|
||||
});
|
||||
|
||||
form.on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
}).on('part', (p) => p.resume());
|
||||
|
||||
console.time(moduleName);
|
||||
form.parse(req);
|
||||
for (const buf of buffers)
|
||||
req.push(buf);
|
||||
req.push(null);
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
if (moduleName === undefined)
|
||||
console.error('Missing parser module name');
|
||||
else
|
||||
console.error(`Invalid parser module name: ${moduleName}`);
|
||||
process.exit(1);
|
||||
}
|
||||
@ -0,0 +1,154 @@
|
||||
'use strict';
|
||||
|
||||
function createMultipartBuffers(boundary, sizes) {
|
||||
const bufs = [];
|
||||
for (let i = 0; i < sizes.length; ++i) {
|
||||
const mb = sizes[i] * 1024 * 1024;
|
||||
bufs.push(Buffer.from([
|
||||
`--${boundary}`,
|
||||
`content-disposition: form-data; name="file${i + 1}"; `
|
||||
+ `filename="random${i + 1}.bin"`,
|
||||
'content-type: application/octet-stream',
|
||||
'',
|
||||
'0'.repeat(mb),
|
||||
'',
|
||||
].join('\r\n')));
|
||||
}
|
||||
bufs.push(Buffer.from([
|
||||
`--${boundary}--`,
|
||||
'',
|
||||
].join('\r\n')));
|
||||
return bufs;
|
||||
}
|
||||
|
||||
const boundary = '-----------------------------168072824752491622650073';
|
||||
const buffers = createMultipartBuffers(boundary, [
|
||||
10,
|
||||
10,
|
||||
10,
|
||||
20,
|
||||
50,
|
||||
]);
|
||||
const calls = {
|
||||
partBegin: 0,
|
||||
headerField: 0,
|
||||
headerValue: 0,
|
||||
headerEnd: 0,
|
||||
headersEnd: 0,
|
||||
partData: 0,
|
||||
partEnd: 0,
|
||||
end: 0,
|
||||
};
|
||||
|
||||
const moduleName = process.argv[2];
|
||||
switch (moduleName) {
|
||||
case 'busboy': {
|
||||
const busboy = require('busboy');
|
||||
|
||||
const parser = busboy({
|
||||
limits: {
|
||||
fieldSizeLimit: Infinity,
|
||||
},
|
||||
headers: {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
},
|
||||
});
|
||||
parser.on('file', (name, stream, info) => {
|
||||
++calls.partBegin;
|
||||
stream.on('data', (chunk) => {
|
||||
++calls.partData;
|
||||
}).on('end', () => {
|
||||
++calls.partEnd;
|
||||
});
|
||||
}).on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
console.time(moduleName);
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
break;
|
||||
}
|
||||
|
||||
case 'formidable': {
|
||||
const { MultipartParser } = require('formidable');
|
||||
|
||||
const parser = new MultipartParser();
|
||||
parser.initWithBoundary(boundary);
|
||||
parser.on('data', ({ name }) => {
|
||||
++calls[name];
|
||||
if (name === 'end')
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
console.time(moduleName);
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
case 'multiparty': {
|
||||
const { Readable } = require('stream');
|
||||
|
||||
const { Form } = require('multiparty');
|
||||
|
||||
const form = new Form({
|
||||
maxFieldsSize: Infinity,
|
||||
maxFields: Infinity,
|
||||
maxFilesSize: Infinity,
|
||||
autoFields: false,
|
||||
autoFiles: false,
|
||||
});
|
||||
|
||||
const req = new Readable({ read: () => {} });
|
||||
req.headers = {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
};
|
||||
|
||||
function hijack(name, fn) {
|
||||
const oldFn = form[name];
|
||||
form[name] = function() {
|
||||
fn();
|
||||
return oldFn.apply(this, arguments);
|
||||
};
|
||||
}
|
||||
|
||||
hijack('onParseHeaderField', () => {
|
||||
++calls.headerField;
|
||||
});
|
||||
hijack('onParseHeaderValue', () => {
|
||||
++calls.headerValue;
|
||||
});
|
||||
hijack('onParsePartBegin', () => {
|
||||
++calls.partBegin;
|
||||
});
|
||||
hijack('onParsePartData', () => {
|
||||
++calls.partData;
|
||||
});
|
||||
hijack('onParsePartEnd', () => {
|
||||
++calls.partEnd;
|
||||
});
|
||||
|
||||
form.on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
}).on('part', (p) => p.resume());
|
||||
|
||||
console.time(moduleName);
|
||||
form.parse(req);
|
||||
for (const buf of buffers)
|
||||
req.push(buf);
|
||||
req.push(null);
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
if (moduleName === undefined)
|
||||
console.error('Missing parser module name');
|
||||
else
|
||||
console.error(`Invalid parser module name: ${moduleName}`);
|
||||
process.exit(1);
|
||||
}
|
||||
@ -0,0 +1,148 @@
|
||||
'use strict';
|
||||
|
||||
function createMultipartBuffers(boundary, sizes) {
|
||||
const bufs = [];
|
||||
for (let i = 0; i < sizes.length; ++i) {
|
||||
const mb = sizes[i] * 1024 * 1024;
|
||||
bufs.push(Buffer.from([
|
||||
`--${boundary}`,
|
||||
`content-disposition: form-data; name="file${i + 1}"; `
|
||||
+ `filename="random${i + 1}.bin"`,
|
||||
'content-type: application/octet-stream',
|
||||
'',
|
||||
'0'.repeat(mb),
|
||||
'',
|
||||
].join('\r\n')));
|
||||
}
|
||||
bufs.push(Buffer.from([
|
||||
`--${boundary}--`,
|
||||
'',
|
||||
].join('\r\n')));
|
||||
return bufs;
|
||||
}
|
||||
|
||||
const boundary = '-----------------------------168072824752491622650073';
|
||||
const buffers = createMultipartBuffers(boundary, (new Array(100)).fill(1));
|
||||
const calls = {
|
||||
partBegin: 0,
|
||||
headerField: 0,
|
||||
headerValue: 0,
|
||||
headerEnd: 0,
|
||||
headersEnd: 0,
|
||||
partData: 0,
|
||||
partEnd: 0,
|
||||
end: 0,
|
||||
};
|
||||
|
||||
const moduleName = process.argv[2];
|
||||
switch (moduleName) {
|
||||
case 'busboy': {
|
||||
const busboy = require('busboy');
|
||||
|
||||
const parser = busboy({
|
||||
limits: {
|
||||
fieldSizeLimit: Infinity,
|
||||
},
|
||||
headers: {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
},
|
||||
});
|
||||
parser.on('file', (name, stream, info) => {
|
||||
++calls.partBegin;
|
||||
stream.on('data', (chunk) => {
|
||||
++calls.partData;
|
||||
}).on('end', () => {
|
||||
++calls.partEnd;
|
||||
});
|
||||
}).on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
console.time(moduleName);
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
break;
|
||||
}
|
||||
|
||||
case 'formidable': {
|
||||
const { MultipartParser } = require('formidable');
|
||||
|
||||
const parser = new MultipartParser();
|
||||
parser.initWithBoundary(boundary);
|
||||
parser.on('data', ({ name }) => {
|
||||
++calls[name];
|
||||
if (name === 'end')
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
console.time(moduleName);
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
case 'multiparty': {
|
||||
const { Readable } = require('stream');
|
||||
|
||||
const { Form } = require('multiparty');
|
||||
|
||||
const form = new Form({
|
||||
maxFieldsSize: Infinity,
|
||||
maxFields: Infinity,
|
||||
maxFilesSize: Infinity,
|
||||
autoFields: false,
|
||||
autoFiles: false,
|
||||
});
|
||||
|
||||
const req = new Readable({ read: () => {} });
|
||||
req.headers = {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
};
|
||||
|
||||
function hijack(name, fn) {
|
||||
const oldFn = form[name];
|
||||
form[name] = function() {
|
||||
fn();
|
||||
return oldFn.apply(this, arguments);
|
||||
};
|
||||
}
|
||||
|
||||
hijack('onParseHeaderField', () => {
|
||||
++calls.headerField;
|
||||
});
|
||||
hijack('onParseHeaderValue', () => {
|
||||
++calls.headerValue;
|
||||
});
|
||||
hijack('onParsePartBegin', () => {
|
||||
++calls.partBegin;
|
||||
});
|
||||
hijack('onParsePartData', () => {
|
||||
++calls.partData;
|
||||
});
|
||||
hijack('onParsePartEnd', () => {
|
||||
++calls.partEnd;
|
||||
});
|
||||
|
||||
form.on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
}).on('part', (p) => p.resume());
|
||||
|
||||
console.time(moduleName);
|
||||
form.parse(req);
|
||||
for (const buf of buffers)
|
||||
req.push(buf);
|
||||
req.push(null);
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
if (moduleName === undefined)
|
||||
console.error('Missing parser module name');
|
||||
else
|
||||
console.error(`Invalid parser module name: ${moduleName}`);
|
||||
process.exit(1);
|
||||
}
|
||||
@ -0,0 +1,101 @@
|
||||
'use strict';
|
||||
|
||||
const buffers = [
|
||||
Buffer.from(
|
||||
(new Array(100)).fill('').map((_, i) => `key${i}=value${i}`).join('&')
|
||||
),
|
||||
];
|
||||
const calls = {
|
||||
field: 0,
|
||||
end: 0,
|
||||
};
|
||||
|
||||
let n = 3e3;
|
||||
|
||||
const moduleName = process.argv[2];
|
||||
switch (moduleName) {
|
||||
case 'busboy': {
|
||||
const busboy = require('busboy');
|
||||
|
||||
console.time(moduleName);
|
||||
(function next() {
|
||||
const parser = busboy({
|
||||
limits: {
|
||||
fieldSizeLimit: Infinity,
|
||||
},
|
||||
headers: {
|
||||
'content-type': 'application/x-www-form-urlencoded; charset=utf-8',
|
||||
},
|
||||
});
|
||||
parser.on('field', (name, val, info) => {
|
||||
++calls.field;
|
||||
}).on('close', () => {
|
||||
++calls.end;
|
||||
if (--n === 0)
|
||||
console.timeEnd(moduleName);
|
||||
else
|
||||
process.nextTick(next);
|
||||
});
|
||||
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
parser.end();
|
||||
})();
|
||||
break;
|
||||
}
|
||||
|
||||
case 'formidable': {
|
||||
const QuerystringParser =
|
||||
require('formidable/src/parsers/Querystring.js');
|
||||
|
||||
console.time(moduleName);
|
||||
(function next() {
|
||||
const parser = new QuerystringParser();
|
||||
parser.on('data', (obj) => {
|
||||
++calls.field;
|
||||
}).on('end', () => {
|
||||
++calls.end;
|
||||
if (--n === 0)
|
||||
console.timeEnd(moduleName);
|
||||
else
|
||||
process.nextTick(next);
|
||||
});
|
||||
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
parser.end();
|
||||
})();
|
||||
break;
|
||||
}
|
||||
|
||||
case 'formidable-streaming': {
|
||||
const QuerystringParser =
|
||||
require('formidable/src/parsers/StreamingQuerystring.js');
|
||||
|
||||
console.time(moduleName);
|
||||
(function next() {
|
||||
const parser = new QuerystringParser();
|
||||
parser.on('data', (obj) => {
|
||||
++calls.field;
|
||||
}).on('end', () => {
|
||||
++calls.end;
|
||||
if (--n === 0)
|
||||
console.timeEnd(moduleName);
|
||||
else
|
||||
process.nextTick(next);
|
||||
});
|
||||
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
parser.end();
|
||||
})();
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
if (moduleName === undefined)
|
||||
console.error('Missing parser module name');
|
||||
else
|
||||
console.error(`Invalid parser module name: ${moduleName}`);
|
||||
process.exit(1);
|
||||
}
|
||||
@ -0,0 +1,84 @@
|
||||
'use strict';
|
||||
|
||||
const buffers = [
|
||||
Buffer.from(
|
||||
(new Array(900)).fill('').map((_, i) => `key${i}=value${i}`).join('&')
|
||||
),
|
||||
];
|
||||
const calls = {
|
||||
field: 0,
|
||||
end: 0,
|
||||
};
|
||||
|
||||
const moduleName = process.argv[2];
|
||||
switch (moduleName) {
|
||||
case 'busboy': {
|
||||
const busboy = require('busboy');
|
||||
|
||||
console.time(moduleName);
|
||||
const parser = busboy({
|
||||
limits: {
|
||||
fieldSizeLimit: Infinity,
|
||||
},
|
||||
headers: {
|
||||
'content-type': 'application/x-www-form-urlencoded; charset=utf-8',
|
||||
},
|
||||
});
|
||||
parser.on('field', (name, val, info) => {
|
||||
++calls.field;
|
||||
}).on('close', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
parser.end();
|
||||
break;
|
||||
}
|
||||
|
||||
case 'formidable': {
|
||||
const QuerystringParser =
|
||||
require('formidable/src/parsers/Querystring.js');
|
||||
|
||||
console.time(moduleName);
|
||||
const parser = new QuerystringParser();
|
||||
parser.on('data', (obj) => {
|
||||
++calls.field;
|
||||
}).on('end', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
parser.end();
|
||||
break;
|
||||
}
|
||||
|
||||
case 'formidable-streaming': {
|
||||
const QuerystringParser =
|
||||
require('formidable/src/parsers/StreamingQuerystring.js');
|
||||
|
||||
console.time(moduleName);
|
||||
const parser = new QuerystringParser();
|
||||
parser.on('data', (obj) => {
|
||||
++calls.field;
|
||||
}).on('end', () => {
|
||||
++calls.end;
|
||||
console.timeEnd(moduleName);
|
||||
});
|
||||
|
||||
for (const buf of buffers)
|
||||
parser.write(buf);
|
||||
parser.end();
|
||||
break;
|
||||
}
|
||||
|
||||
default:
|
||||
if (moduleName === undefined)
|
||||
console.error('Missing parser module name');
|
||||
else
|
||||
console.error(`Invalid parser module name: ${moduleName}`);
|
||||
process.exit(1);
|
||||
}
|
||||
@ -0,0 +1,57 @@
|
||||
'use strict';
|
||||
|
||||
const { parseContentType } = require('./utils.js');
|
||||
|
||||
function getInstance(cfg) {
|
||||
const headers = cfg.headers;
|
||||
const conType = parseContentType(headers['content-type']);
|
||||
if (!conType)
|
||||
throw new Error('Malformed content type');
|
||||
|
||||
for (const type of TYPES) {
|
||||
const matched = type.detect(conType);
|
||||
if (!matched)
|
||||
continue;
|
||||
|
||||
const instanceCfg = {
|
||||
limits: cfg.limits,
|
||||
headers,
|
||||
conType,
|
||||
highWaterMark: undefined,
|
||||
fileHwm: undefined,
|
||||
defCharset: undefined,
|
||||
defParamCharset: undefined,
|
||||
preservePath: false,
|
||||
};
|
||||
if (cfg.highWaterMark)
|
||||
instanceCfg.highWaterMark = cfg.highWaterMark;
|
||||
if (cfg.fileHwm)
|
||||
instanceCfg.fileHwm = cfg.fileHwm;
|
||||
instanceCfg.defCharset = cfg.defCharset;
|
||||
instanceCfg.defParamCharset = cfg.defParamCharset;
|
||||
instanceCfg.preservePath = cfg.preservePath;
|
||||
return new type(instanceCfg);
|
||||
}
|
||||
|
||||
throw new Error(`Unsupported content type: ${headers['content-type']}`);
|
||||
}
|
||||
|
||||
// Note: types are explicitly listed here for easier bundling
|
||||
// See: https://github.com/mscdex/busboy/issues/121
|
||||
const TYPES = [
|
||||
require('./types/multipart'),
|
||||
require('./types/urlencoded'),
|
||||
].filter(function(typemod) { return typeof typemod.detect === 'function'; });
|
||||
|
||||
module.exports = (cfg) => {
|
||||
if (typeof cfg !== 'object' || cfg === null)
|
||||
cfg = {};
|
||||
|
||||
if (typeof cfg.headers !== 'object'
|
||||
|| cfg.headers === null
|
||||
|| typeof cfg.headers['content-type'] !== 'string') {
|
||||
throw new Error('Missing Content-Type');
|
||||
}
|
||||
|
||||
return getInstance(cfg);
|
||||
};
|
||||
@ -0,0 +1,653 @@
|
||||
'use strict';
|
||||
|
||||
const { Readable, Writable } = require('stream');
|
||||
|
||||
const StreamSearch = require('streamsearch');
|
||||
|
||||
const {
|
||||
basename,
|
||||
convertToUTF8,
|
||||
getDecoder,
|
||||
parseContentType,
|
||||
parseDisposition,
|
||||
} = require('../utils.js');
|
||||
|
||||
const BUF_CRLF = Buffer.from('\r\n');
|
||||
const BUF_CR = Buffer.from('\r');
|
||||
const BUF_DASH = Buffer.from('-');
|
||||
|
||||
function noop() {}
|
||||
|
||||
const MAX_HEADER_PAIRS = 2000; // From node
|
||||
const MAX_HEADER_SIZE = 16 * 1024; // From node (its default value)
|
||||
|
||||
const HPARSER_NAME = 0;
|
||||
const HPARSER_PRE_OWS = 1;
|
||||
const HPARSER_VALUE = 2;
|
||||
class HeaderParser {
|
||||
constructor(cb) {
|
||||
this.header = Object.create(null);
|
||||
this.pairCount = 0;
|
||||
this.byteCount = 0;
|
||||
this.state = HPARSER_NAME;
|
||||
this.name = '';
|
||||
this.value = '';
|
||||
this.crlf = 0;
|
||||
this.cb = cb;
|
||||
}
|
||||
|
||||
reset() {
|
||||
this.header = Object.create(null);
|
||||
this.pairCount = 0;
|
||||
this.byteCount = 0;
|
||||
this.state = HPARSER_NAME;
|
||||
this.name = '';
|
||||
this.value = '';
|
||||
this.crlf = 0;
|
||||
}
|
||||
|
||||
push(chunk, pos, end) {
|
||||
let start = pos;
|
||||
while (pos < end) {
|
||||
switch (this.state) {
|
||||
case HPARSER_NAME: {
|
||||
let done = false;
|
||||
for (; pos < end; ++pos) {
|
||||
if (this.byteCount === MAX_HEADER_SIZE)
|
||||
return -1;
|
||||
++this.byteCount;
|
||||
const code = chunk[pos];
|
||||
if (TOKEN[code] !== 1) {
|
||||
if (code !== 58/* ':' */)
|
||||
return -1;
|
||||
this.name += chunk.latin1Slice(start, pos);
|
||||
if (this.name.length === 0)
|
||||
return -1;
|
||||
++pos;
|
||||
done = true;
|
||||
this.state = HPARSER_PRE_OWS;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (!done) {
|
||||
this.name += chunk.latin1Slice(start, pos);
|
||||
break;
|
||||
}
|
||||
// FALLTHROUGH
|
||||
}
|
||||
case HPARSER_PRE_OWS: {
|
||||
// Skip optional whitespace
|
||||
let done = false;
|
||||
for (; pos < end; ++pos) {
|
||||
if (this.byteCount === MAX_HEADER_SIZE)
|
||||
return -1;
|
||||
++this.byteCount;
|
||||
const code = chunk[pos];
|
||||
if (code !== 32/* ' ' */ && code !== 9/* '\t' */) {
|
||||
start = pos;
|
||||
done = true;
|
||||
this.state = HPARSER_VALUE;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (!done)
|
||||
break;
|
||||
// FALLTHROUGH
|
||||
}
|
||||
case HPARSER_VALUE:
|
||||
switch (this.crlf) {
|
||||
case 0: // Nothing yet
|
||||
for (; pos < end; ++pos) {
|
||||
if (this.byteCount === MAX_HEADER_SIZE)
|
||||
return -1;
|
||||
++this.byteCount;
|
||||
const code = chunk[pos];
|
||||
if (FIELD_VCHAR[code] !== 1) {
|
||||
if (code !== 13/* '\r' */)
|
||||
return -1;
|
||||
++this.crlf;
|
||||
break;
|
||||
}
|
||||
}
|
||||
this.value += chunk.latin1Slice(start, pos++);
|
||||
break;
|
||||
case 1: // Received CR
|
||||
if (this.byteCount === MAX_HEADER_SIZE)
|
||||
return -1;
|
||||
++this.byteCount;
|
||||
if (chunk[pos++] !== 10/* '\n' */)
|
||||
return -1;
|
||||
++this.crlf;
|
||||
break;
|
||||
case 2: { // Received CR LF
|
||||
if (this.byteCount === MAX_HEADER_SIZE)
|
||||
return -1;
|
||||
++this.byteCount;
|
||||
const code = chunk[pos];
|
||||
if (code === 32/* ' ' */ || code === 9/* '\t' */) {
|
||||
// Folded value
|
||||
start = pos;
|
||||
this.crlf = 0;
|
||||
} else {
|
||||
if (++this.pairCount < MAX_HEADER_PAIRS) {
|
||||
this.name = this.name.toLowerCase();
|
||||
if (this.header[this.name] === undefined)
|
||||
this.header[this.name] = [this.value];
|
||||
else
|
||||
this.header[this.name].push(this.value);
|
||||
}
|
||||
if (code === 13/* '\r' */) {
|
||||
++this.crlf;
|
||||
++pos;
|
||||
} else {
|
||||
// Assume start of next header field name
|
||||
start = pos;
|
||||
this.crlf = 0;
|
||||
this.state = HPARSER_NAME;
|
||||
this.name = '';
|
||||
this.value = '';
|
||||
}
|
||||
}
|
||||
break;
|
||||
}
|
||||
case 3: { // Received CR LF CR
|
||||
if (this.byteCount === MAX_HEADER_SIZE)
|
||||
return -1;
|
||||
++this.byteCount;
|
||||
if (chunk[pos++] !== 10/* '\n' */)
|
||||
return -1;
|
||||
// End of header
|
||||
const header = this.header;
|
||||
this.reset();
|
||||
this.cb(header);
|
||||
return pos;
|
||||
}
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return pos;
|
||||
}
|
||||
}
|
||||
|
||||
class FileStream extends Readable {
|
||||
constructor(opts, owner) {
|
||||
super(opts);
|
||||
this.truncated = false;
|
||||
this._readcb = null;
|
||||
this.once('end', () => {
|
||||
// We need to make sure that we call any outstanding _writecb() that is
|
||||
// associated with this file so that processing of the rest of the form
|
||||
// can continue. This may not happen if the file stream ends right after
|
||||
// backpressure kicks in, so we force it here.
|
||||
this._read();
|
||||
if (--owner._fileEndsLeft === 0 && owner._finalcb) {
|
||||
const cb = owner._finalcb;
|
||||
owner._finalcb = null;
|
||||
// Make sure other 'end' event handlers get a chance to be executed
|
||||
// before busboy's 'finish' event is emitted
|
||||
process.nextTick(cb);
|
||||
}
|
||||
});
|
||||
}
|
||||
_read(n) {
|
||||
const cb = this._readcb;
|
||||
if (cb) {
|
||||
this._readcb = null;
|
||||
cb();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const ignoreData = {
|
||||
push: (chunk, pos) => {},
|
||||
destroy: () => {},
|
||||
};
|
||||
|
||||
function callAndUnsetCb(self, err) {
|
||||
const cb = self._writecb;
|
||||
self._writecb = null;
|
||||
if (err)
|
||||
self.destroy(err);
|
||||
else if (cb)
|
||||
cb();
|
||||
}
|
||||
|
||||
function nullDecoder(val, hint) {
|
||||
return val;
|
||||
}
|
||||
|
||||
class Multipart extends Writable {
|
||||
constructor(cfg) {
|
||||
const streamOpts = {
|
||||
autoDestroy: true,
|
||||
emitClose: true,
|
||||
highWaterMark: (typeof cfg.highWaterMark === 'number'
|
||||
? cfg.highWaterMark
|
||||
: undefined),
|
||||
};
|
||||
super(streamOpts);
|
||||
|
||||
if (!cfg.conType.params || typeof cfg.conType.params.boundary !== 'string')
|
||||
throw new Error('Multipart: Boundary not found');
|
||||
|
||||
const boundary = cfg.conType.params.boundary;
|
||||
const paramDecoder = (typeof cfg.defParamCharset === 'string'
|
||||
&& cfg.defParamCharset
|
||||
? getDecoder(cfg.defParamCharset)
|
||||
: nullDecoder);
|
||||
const defCharset = (cfg.defCharset || 'utf8');
|
||||
const preservePath = cfg.preservePath;
|
||||
const fileOpts = {
|
||||
autoDestroy: true,
|
||||
emitClose: true,
|
||||
highWaterMark: (typeof cfg.fileHwm === 'number'
|
||||
? cfg.fileHwm
|
||||
: undefined),
|
||||
};
|
||||
|
||||
const limits = cfg.limits;
|
||||
const fieldSizeLimit = (limits && typeof limits.fieldSize === 'number'
|
||||
? limits.fieldSize
|
||||
: 1 * 1024 * 1024);
|
||||
const fileSizeLimit = (limits && typeof limits.fileSize === 'number'
|
||||
? limits.fileSize
|
||||
: Infinity);
|
||||
const filesLimit = (limits && typeof limits.files === 'number'
|
||||
? limits.files
|
||||
: Infinity);
|
||||
const fieldsLimit = (limits && typeof limits.fields === 'number'
|
||||
? limits.fields
|
||||
: Infinity);
|
||||
const partsLimit = (limits && typeof limits.parts === 'number'
|
||||
? limits.parts
|
||||
: Infinity);
|
||||
|
||||
let parts = -1; // Account for initial boundary
|
||||
let fields = 0;
|
||||
let files = 0;
|
||||
let skipPart = false;
|
||||
|
||||
this._fileEndsLeft = 0;
|
||||
this._fileStream = undefined;
|
||||
this._complete = false;
|
||||
let fileSize = 0;
|
||||
|
||||
let field;
|
||||
let fieldSize = 0;
|
||||
let partCharset;
|
||||
let partEncoding;
|
||||
let partType;
|
||||
let partName;
|
||||
let partTruncated = false;
|
||||
|
||||
let hitFilesLimit = false;
|
||||
let hitFieldsLimit = false;
|
||||
|
||||
this._hparser = null;
|
||||
const hparser = new HeaderParser((header) => {
|
||||
this._hparser = null;
|
||||
skipPart = false;
|
||||
|
||||
partType = 'text/plain';
|
||||
partCharset = defCharset;
|
||||
partEncoding = '7bit';
|
||||
partName = undefined;
|
||||
partTruncated = false;
|
||||
|
||||
let filename;
|
||||
if (!header['content-disposition']) {
|
||||
skipPart = true;
|
||||
return;
|
||||
}
|
||||
|
||||
const disp = parseDisposition(header['content-disposition'][0],
|
||||
paramDecoder);
|
||||
if (!disp || disp.type !== 'form-data') {
|
||||
skipPart = true;
|
||||
return;
|
||||
}
|
||||
|
||||
if (disp.params) {
|
||||
if (disp.params.name)
|
||||
partName = disp.params.name;
|
||||
|
||||
if (disp.params['filename*'])
|
||||
filename = disp.params['filename*'];
|
||||
else if (disp.params.filename)
|
||||
filename = disp.params.filename;
|
||||
|
||||
if (filename !== undefined && !preservePath)
|
||||
filename = basename(filename);
|
||||
}
|
||||
|
||||
if (header['content-type']) {
|
||||
const conType = parseContentType(header['content-type'][0]);
|
||||
if (conType) {
|
||||
partType = `${conType.type}/${conType.subtype}`;
|
||||
if (conType.params && typeof conType.params.charset === 'string')
|
||||
partCharset = conType.params.charset.toLowerCase();
|
||||
}
|
||||
}
|
||||
|
||||
if (header['content-transfer-encoding'])
|
||||
partEncoding = header['content-transfer-encoding'][0].toLowerCase();
|
||||
|
||||
if (partType === 'application/octet-stream' || filename !== undefined) {
|
||||
// File
|
||||
|
||||
if (files === filesLimit) {
|
||||
if (!hitFilesLimit) {
|
||||
hitFilesLimit = true;
|
||||
this.emit('filesLimit');
|
||||
}
|
||||
skipPart = true;
|
||||
return;
|
||||
}
|
||||
++files;
|
||||
|
||||
if (this.listenerCount('file') === 0) {
|
||||
skipPart = true;
|
||||
return;
|
||||
}
|
||||
|
||||
fileSize = 0;
|
||||
this._fileStream = new FileStream(fileOpts, this);
|
||||
++this._fileEndsLeft;
|
||||
this.emit(
|
||||
'file',
|
||||
partName,
|
||||
this._fileStream,
|
||||
{ filename,
|
||||
encoding: partEncoding,
|
||||
mimeType: partType }
|
||||
);
|
||||
} else {
|
||||
// Non-file
|
||||
|
||||
if (fields === fieldsLimit) {
|
||||
if (!hitFieldsLimit) {
|
||||
hitFieldsLimit = true;
|
||||
this.emit('fieldsLimit');
|
||||
}
|
||||
skipPart = true;
|
||||
return;
|
||||
}
|
||||
++fields;
|
||||
|
||||
if (this.listenerCount('field') === 0) {
|
||||
skipPart = true;
|
||||
return;
|
||||
}
|
||||
|
||||
field = [];
|
||||
fieldSize = 0;
|
||||
}
|
||||
});
|
||||
|
||||
let matchPostBoundary = 0;
|
||||
const ssCb = (isMatch, data, start, end, isDataSafe) => {
|
||||
retrydata:
|
||||
while (data) {
|
||||
if (this._hparser !== null) {
|
||||
const ret = this._hparser.push(data, start, end);
|
||||
if (ret === -1) {
|
||||
this._hparser = null;
|
||||
hparser.reset();
|
||||
this.emit('error', new Error('Malformed part header'));
|
||||
break;
|
||||
}
|
||||
start = ret;
|
||||
}
|
||||
|
||||
if (start === end)
|
||||
break;
|
||||
|
||||
if (matchPostBoundary !== 0) {
|
||||
if (matchPostBoundary === 1) {
|
||||
switch (data[start]) {
|
||||
case 45: // '-'
|
||||
// Try matching '--' after boundary
|
||||
matchPostBoundary = 2;
|
||||
++start;
|
||||
break;
|
||||
case 13: // '\r'
|
||||
// Try matching CR LF before header
|
||||
matchPostBoundary = 3;
|
||||
++start;
|
||||
break;
|
||||
default:
|
||||
matchPostBoundary = 0;
|
||||
}
|
||||
if (start === end)
|
||||
return;
|
||||
}
|
||||
|
||||
if (matchPostBoundary === 2) {
|
||||
matchPostBoundary = 0;
|
||||
if (data[start] === 45/* '-' */) {
|
||||
// End of multipart data
|
||||
this._complete = true;
|
||||
this._bparser = ignoreData;
|
||||
return;
|
||||
}
|
||||
// We saw something other than '-', so put the dash we consumed
|
||||
// "back"
|
||||
const writecb = this._writecb;
|
||||
this._writecb = noop;
|
||||
ssCb(false, BUF_DASH, 0, 1, false);
|
||||
this._writecb = writecb;
|
||||
} else if (matchPostBoundary === 3) {
|
||||
matchPostBoundary = 0;
|
||||
if (data[start] === 10/* '\n' */) {
|
||||
++start;
|
||||
if (parts >= partsLimit)
|
||||
break;
|
||||
// Prepare the header parser
|
||||
this._hparser = hparser;
|
||||
if (start === end)
|
||||
break;
|
||||
// Process the remaining data as a header
|
||||
continue retrydata;
|
||||
} else {
|
||||
// We saw something other than LF, so put the CR we consumed
|
||||
// "back"
|
||||
const writecb = this._writecb;
|
||||
this._writecb = noop;
|
||||
ssCb(false, BUF_CR, 0, 1, false);
|
||||
this._writecb = writecb;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (!skipPart) {
|
||||
if (this._fileStream) {
|
||||
let chunk;
|
||||
const actualLen = Math.min(end - start, fileSizeLimit - fileSize);
|
||||
if (!isDataSafe) {
|
||||
chunk = Buffer.allocUnsafe(actualLen);
|
||||
data.copy(chunk, 0, start, start + actualLen);
|
||||
} else {
|
||||
chunk = data.slice(start, start + actualLen);
|
||||
}
|
||||
|
||||
fileSize += chunk.length;
|
||||
if (fileSize === fileSizeLimit) {
|
||||
if (chunk.length > 0)
|
||||
this._fileStream.push(chunk);
|
||||
this._fileStream.emit('limit');
|
||||
this._fileStream.truncated = true;
|
||||
skipPart = true;
|
||||
} else if (!this._fileStream.push(chunk)) {
|
||||
if (this._writecb)
|
||||
this._fileStream._readcb = this._writecb;
|
||||
this._writecb = null;
|
||||
}
|
||||
} else if (field !== undefined) {
|
||||
let chunk;
|
||||
const actualLen = Math.min(
|
||||
end - start,
|
||||
fieldSizeLimit - fieldSize
|
||||
);
|
||||
if (!isDataSafe) {
|
||||
chunk = Buffer.allocUnsafe(actualLen);
|
||||
data.copy(chunk, 0, start, start + actualLen);
|
||||
} else {
|
||||
chunk = data.slice(start, start + actualLen);
|
||||
}
|
||||
|
||||
fieldSize += actualLen;
|
||||
field.push(chunk);
|
||||
if (fieldSize === fieldSizeLimit) {
|
||||
skipPart = true;
|
||||
partTruncated = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
if (isMatch) {
|
||||
matchPostBoundary = 1;
|
||||
|
||||
if (this._fileStream) {
|
||||
// End the active file stream if the previous part was a file
|
||||
this._fileStream.push(null);
|
||||
this._fileStream = null;
|
||||
} else if (field !== undefined) {
|
||||
let data;
|
||||
switch (field.length) {
|
||||
case 0:
|
||||
data = '';
|
||||
break;
|
||||
case 1:
|
||||
data = convertToUTF8(field[0], partCharset, 0);
|
||||
break;
|
||||
default:
|
||||
data = convertToUTF8(
|
||||
Buffer.concat(field, fieldSize),
|
||||
partCharset,
|
||||
0
|
||||
);
|
||||
}
|
||||
field = undefined;
|
||||
fieldSize = 0;
|
||||
this.emit(
|
||||
'field',
|
||||
partName,
|
||||
data,
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: partTruncated,
|
||||
encoding: partEncoding,
|
||||
mimeType: partType }
|
||||
);
|
||||
}
|
||||
|
||||
if (++parts === partsLimit)
|
||||
this.emit('partsLimit');
|
||||
}
|
||||
};
|
||||
this._bparser = new StreamSearch(`\r\n--${boundary}`, ssCb);
|
||||
|
||||
this._writecb = null;
|
||||
this._finalcb = null;
|
||||
|
||||
// Just in case there is no preamble
|
||||
this.write(BUF_CRLF);
|
||||
}
|
||||
|
||||
static detect(conType) {
|
||||
return (conType.type === 'multipart' && conType.subtype === 'form-data');
|
||||
}
|
||||
|
||||
_write(chunk, enc, cb) {
|
||||
this._writecb = cb;
|
||||
this._bparser.push(chunk, 0);
|
||||
if (this._writecb)
|
||||
callAndUnsetCb(this);
|
||||
}
|
||||
|
||||
_destroy(err, cb) {
|
||||
this._hparser = null;
|
||||
this._bparser = ignoreData;
|
||||
if (!err)
|
||||
err = checkEndState(this);
|
||||
const fileStream = this._fileStream;
|
||||
if (fileStream) {
|
||||
this._fileStream = null;
|
||||
fileStream.destroy(err);
|
||||
}
|
||||
cb(err);
|
||||
}
|
||||
|
||||
_final(cb) {
|
||||
this._bparser.destroy();
|
||||
if (!this._complete)
|
||||
return cb(new Error('Unexpected end of form'));
|
||||
if (this._fileEndsLeft)
|
||||
this._finalcb = finalcb.bind(null, this, cb);
|
||||
else
|
||||
finalcb(this, cb);
|
||||
}
|
||||
}
|
||||
|
||||
function finalcb(self, cb, err) {
|
||||
if (err)
|
||||
return cb(err);
|
||||
err = checkEndState(self);
|
||||
cb(err);
|
||||
}
|
||||
|
||||
function checkEndState(self) {
|
||||
if (self._hparser)
|
||||
return new Error('Malformed part header');
|
||||
const fileStream = self._fileStream;
|
||||
if (fileStream) {
|
||||
self._fileStream = null;
|
||||
fileStream.destroy(new Error('Unexpected end of file'));
|
||||
}
|
||||
if (!self._complete)
|
||||
return new Error('Unexpected end of form');
|
||||
}
|
||||
|
||||
const TOKEN = [
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,
|
||||
0, 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, 0, 0, 0, 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, 0, 1, 0, 1, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
];
|
||||
|
||||
const FIELD_VCHAR = [
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
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, 0,
|
||||
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,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
];
|
||||
|
||||
module.exports = Multipart;
|
||||
@ -0,0 +1,350 @@
|
||||
'use strict';
|
||||
|
||||
const { Writable } = require('stream');
|
||||
|
||||
const { getDecoder } = require('../utils.js');
|
||||
|
||||
class URLEncoded extends Writable {
|
||||
constructor(cfg) {
|
||||
const streamOpts = {
|
||||
autoDestroy: true,
|
||||
emitClose: true,
|
||||
highWaterMark: (typeof cfg.highWaterMark === 'number'
|
||||
? cfg.highWaterMark
|
||||
: undefined),
|
||||
};
|
||||
super(streamOpts);
|
||||
|
||||
let charset = (cfg.defCharset || 'utf8');
|
||||
if (cfg.conType.params && typeof cfg.conType.params.charset === 'string')
|
||||
charset = cfg.conType.params.charset;
|
||||
|
||||
this.charset = charset;
|
||||
|
||||
const limits = cfg.limits;
|
||||
this.fieldSizeLimit = (limits && typeof limits.fieldSize === 'number'
|
||||
? limits.fieldSize
|
||||
: 1 * 1024 * 1024);
|
||||
this.fieldsLimit = (limits && typeof limits.fields === 'number'
|
||||
? limits.fields
|
||||
: Infinity);
|
||||
this.fieldNameSizeLimit = (
|
||||
limits && typeof limits.fieldNameSize === 'number'
|
||||
? limits.fieldNameSize
|
||||
: 100
|
||||
);
|
||||
|
||||
this._inKey = true;
|
||||
this._keyTrunc = false;
|
||||
this._valTrunc = false;
|
||||
this._bytesKey = 0;
|
||||
this._bytesVal = 0;
|
||||
this._fields = 0;
|
||||
this._key = '';
|
||||
this._val = '';
|
||||
this._byte = -2;
|
||||
this._lastPos = 0;
|
||||
this._encode = 0;
|
||||
this._decoder = getDecoder(charset);
|
||||
}
|
||||
|
||||
static detect(conType) {
|
||||
return (conType.type === 'application'
|
||||
&& conType.subtype === 'x-www-form-urlencoded');
|
||||
}
|
||||
|
||||
_write(chunk, enc, cb) {
|
||||
if (this._fields >= this.fieldsLimit)
|
||||
return cb();
|
||||
|
||||
let i = 0;
|
||||
const len = chunk.length;
|
||||
this._lastPos = 0;
|
||||
|
||||
// Check if we last ended mid-percent-encoded byte
|
||||
if (this._byte !== -2) {
|
||||
i = readPctEnc(this, chunk, i, len);
|
||||
if (i === -1)
|
||||
return cb(new Error('Malformed urlencoded form'));
|
||||
if (i >= len)
|
||||
return cb();
|
||||
if (this._inKey)
|
||||
++this._bytesKey;
|
||||
else
|
||||
++this._bytesVal;
|
||||
}
|
||||
|
||||
main:
|
||||
while (i < len) {
|
||||
if (this._inKey) {
|
||||
// Parsing key
|
||||
|
||||
i = skipKeyBytes(this, chunk, i, len);
|
||||
|
||||
while (i < len) {
|
||||
switch (chunk[i]) {
|
||||
case 61: // '='
|
||||
if (this._lastPos < i)
|
||||
this._key += chunk.latin1Slice(this._lastPos, i);
|
||||
this._lastPos = ++i;
|
||||
this._key = this._decoder(this._key, this._encode);
|
||||
this._encode = 0;
|
||||
this._inKey = false;
|
||||
continue main;
|
||||
case 38: // '&'
|
||||
if (this._lastPos < i)
|
||||
this._key += chunk.latin1Slice(this._lastPos, i);
|
||||
this._lastPos = ++i;
|
||||
this._key = this._decoder(this._key, this._encode);
|
||||
this._encode = 0;
|
||||
if (this._bytesKey > 0) {
|
||||
this.emit(
|
||||
'field',
|
||||
this._key,
|
||||
'',
|
||||
{ nameTruncated: this._keyTrunc,
|
||||
valueTruncated: false,
|
||||
encoding: this.charset,
|
||||
mimeType: 'text/plain' }
|
||||
);
|
||||
}
|
||||
this._key = '';
|
||||
this._val = '';
|
||||
this._keyTrunc = false;
|
||||
this._valTrunc = false;
|
||||
this._bytesKey = 0;
|
||||
this._bytesVal = 0;
|
||||
if (++this._fields >= this.fieldsLimit) {
|
||||
this.emit('fieldsLimit');
|
||||
return cb();
|
||||
}
|
||||
continue;
|
||||
case 43: // '+'
|
||||
if (this._lastPos < i)
|
||||
this._key += chunk.latin1Slice(this._lastPos, i);
|
||||
this._key += ' ';
|
||||
this._lastPos = i + 1;
|
||||
break;
|
||||
case 37: // '%'
|
||||
if (this._encode === 0)
|
||||
this._encode = 1;
|
||||
if (this._lastPos < i)
|
||||
this._key += chunk.latin1Slice(this._lastPos, i);
|
||||
this._lastPos = i + 1;
|
||||
this._byte = -1;
|
||||
i = readPctEnc(this, chunk, i + 1, len);
|
||||
if (i === -1)
|
||||
return cb(new Error('Malformed urlencoded form'));
|
||||
if (i >= len)
|
||||
return cb();
|
||||
++this._bytesKey;
|
||||
i = skipKeyBytes(this, chunk, i, len);
|
||||
continue;
|
||||
}
|
||||
++i;
|
||||
++this._bytesKey;
|
||||
i = skipKeyBytes(this, chunk, i, len);
|
||||
}
|
||||
if (this._lastPos < i)
|
||||
this._key += chunk.latin1Slice(this._lastPos, i);
|
||||
} else {
|
||||
// Parsing value
|
||||
|
||||
i = skipValBytes(this, chunk, i, len);
|
||||
|
||||
while (i < len) {
|
||||
switch (chunk[i]) {
|
||||
case 38: // '&'
|
||||
if (this._lastPos < i)
|
||||
this._val += chunk.latin1Slice(this._lastPos, i);
|
||||
this._lastPos = ++i;
|
||||
this._inKey = true;
|
||||
this._val = this._decoder(this._val, this._encode);
|
||||
this._encode = 0;
|
||||
if (this._bytesKey > 0 || this._bytesVal > 0) {
|
||||
this.emit(
|
||||
'field',
|
||||
this._key,
|
||||
this._val,
|
||||
{ nameTruncated: this._keyTrunc,
|
||||
valueTruncated: this._valTrunc,
|
||||
encoding: this.charset,
|
||||
mimeType: 'text/plain' }
|
||||
);
|
||||
}
|
||||
this._key = '';
|
||||
this._val = '';
|
||||
this._keyTrunc = false;
|
||||
this._valTrunc = false;
|
||||
this._bytesKey = 0;
|
||||
this._bytesVal = 0;
|
||||
if (++this._fields >= this.fieldsLimit) {
|
||||
this.emit('fieldsLimit');
|
||||
return cb();
|
||||
}
|
||||
continue main;
|
||||
case 43: // '+'
|
||||
if (this._lastPos < i)
|
||||
this._val += chunk.latin1Slice(this._lastPos, i);
|
||||
this._val += ' ';
|
||||
this._lastPos = i + 1;
|
||||
break;
|
||||
case 37: // '%'
|
||||
if (this._encode === 0)
|
||||
this._encode = 1;
|
||||
if (this._lastPos < i)
|
||||
this._val += chunk.latin1Slice(this._lastPos, i);
|
||||
this._lastPos = i + 1;
|
||||
this._byte = -1;
|
||||
i = readPctEnc(this, chunk, i + 1, len);
|
||||
if (i === -1)
|
||||
return cb(new Error('Malformed urlencoded form'));
|
||||
if (i >= len)
|
||||
return cb();
|
||||
++this._bytesVal;
|
||||
i = skipValBytes(this, chunk, i, len);
|
||||
continue;
|
||||
}
|
||||
++i;
|
||||
++this._bytesVal;
|
||||
i = skipValBytes(this, chunk, i, len);
|
||||
}
|
||||
if (this._lastPos < i)
|
||||
this._val += chunk.latin1Slice(this._lastPos, i);
|
||||
}
|
||||
}
|
||||
|
||||
cb();
|
||||
}
|
||||
|
||||
_final(cb) {
|
||||
if (this._byte !== -2)
|
||||
return cb(new Error('Malformed urlencoded form'));
|
||||
if (!this._inKey || this._bytesKey > 0 || this._bytesVal > 0) {
|
||||
if (this._inKey)
|
||||
this._key = this._decoder(this._key, this._encode);
|
||||
else
|
||||
this._val = this._decoder(this._val, this._encode);
|
||||
this.emit(
|
||||
'field',
|
||||
this._key,
|
||||
this._val,
|
||||
{ nameTruncated: this._keyTrunc,
|
||||
valueTruncated: this._valTrunc,
|
||||
encoding: this.charset,
|
||||
mimeType: 'text/plain' }
|
||||
);
|
||||
}
|
||||
cb();
|
||||
}
|
||||
}
|
||||
|
||||
function readPctEnc(self, chunk, pos, len) {
|
||||
if (pos >= len)
|
||||
return len;
|
||||
|
||||
if (self._byte === -1) {
|
||||
// We saw a '%' but no hex characters yet
|
||||
const hexUpper = HEX_VALUES[chunk[pos++]];
|
||||
if (hexUpper === -1)
|
||||
return -1;
|
||||
|
||||
if (hexUpper >= 8)
|
||||
self._encode = 2; // Indicate high bits detected
|
||||
|
||||
if (pos < len) {
|
||||
// Both hex characters are in this chunk
|
||||
const hexLower = HEX_VALUES[chunk[pos++]];
|
||||
if (hexLower === -1)
|
||||
return -1;
|
||||
|
||||
if (self._inKey)
|
||||
self._key += String.fromCharCode((hexUpper << 4) + hexLower);
|
||||
else
|
||||
self._val += String.fromCharCode((hexUpper << 4) + hexLower);
|
||||
|
||||
self._byte = -2;
|
||||
self._lastPos = pos;
|
||||
} else {
|
||||
// Only one hex character was available in this chunk
|
||||
self._byte = hexUpper;
|
||||
}
|
||||
} else {
|
||||
// We saw only one hex character so far
|
||||
const hexLower = HEX_VALUES[chunk[pos++]];
|
||||
if (hexLower === -1)
|
||||
return -1;
|
||||
|
||||
if (self._inKey)
|
||||
self._key += String.fromCharCode((self._byte << 4) + hexLower);
|
||||
else
|
||||
self._val += String.fromCharCode((self._byte << 4) + hexLower);
|
||||
|
||||
self._byte = -2;
|
||||
self._lastPos = pos;
|
||||
}
|
||||
|
||||
return pos;
|
||||
}
|
||||
|
||||
function skipKeyBytes(self, chunk, pos, len) {
|
||||
// Skip bytes if we've truncated
|
||||
if (self._bytesKey > self.fieldNameSizeLimit) {
|
||||
if (!self._keyTrunc) {
|
||||
if (self._lastPos < pos)
|
||||
self._key += chunk.latin1Slice(self._lastPos, pos - 1);
|
||||
}
|
||||
self._keyTrunc = true;
|
||||
for (; pos < len; ++pos) {
|
||||
const code = chunk[pos];
|
||||
if (code === 61/* '=' */ || code === 38/* '&' */)
|
||||
break;
|
||||
++self._bytesKey;
|
||||
}
|
||||
self._lastPos = pos;
|
||||
}
|
||||
|
||||
return pos;
|
||||
}
|
||||
|
||||
function skipValBytes(self, chunk, pos, len) {
|
||||
// Skip bytes if we've truncated
|
||||
if (self._bytesVal > self.fieldSizeLimit) {
|
||||
if (!self._valTrunc) {
|
||||
if (self._lastPos < pos)
|
||||
self._val += chunk.latin1Slice(self._lastPos, pos - 1);
|
||||
}
|
||||
self._valTrunc = true;
|
||||
for (; pos < len; ++pos) {
|
||||
if (chunk[pos] === 38/* '&' */)
|
||||
break;
|
||||
++self._bytesVal;
|
||||
}
|
||||
self._lastPos = pos;
|
||||
}
|
||||
|
||||
return pos;
|
||||
}
|
||||
|
||||
/* eslint-disable no-multi-spaces */
|
||||
const HEX_VALUES = [
|
||||
-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,
|
||||
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -1, -1, -1, -1,
|
||||
-1, 10, 11, 12, 13, 14, 15, -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, 10, 11, 12, 13, 14, 15, -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, -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,
|
||||
];
|
||||
/* eslint-enable no-multi-spaces */
|
||||
|
||||
module.exports = URLEncoded;
|
||||
@ -0,0 +1,596 @@
|
||||
'use strict';
|
||||
|
||||
function parseContentType(str) {
|
||||
if (str.length === 0)
|
||||
return;
|
||||
|
||||
const params = Object.create(null);
|
||||
let i = 0;
|
||||
|
||||
// Parse type
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (TOKEN[code] !== 1) {
|
||||
if (code !== 47/* '/' */ || i === 0)
|
||||
return;
|
||||
break;
|
||||
}
|
||||
}
|
||||
// Check for type without subtype
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
const type = str.slice(0, i).toLowerCase();
|
||||
|
||||
// Parse subtype
|
||||
const subtypeStart = ++i;
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (TOKEN[code] !== 1) {
|
||||
// Make sure we have a subtype
|
||||
if (i === subtypeStart)
|
||||
return;
|
||||
|
||||
if (parseContentTypeParams(str, i, params) === undefined)
|
||||
return;
|
||||
break;
|
||||
}
|
||||
}
|
||||
// Make sure we have a subtype
|
||||
if (i === subtypeStart)
|
||||
return;
|
||||
|
||||
const subtype = str.slice(subtypeStart, i).toLowerCase();
|
||||
|
||||
return { type, subtype, params };
|
||||
}
|
||||
|
||||
function parseContentTypeParams(str, i, params) {
|
||||
while (i < str.length) {
|
||||
// Consume whitespace
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (code !== 32/* ' ' */ && code !== 9/* '\t' */)
|
||||
break;
|
||||
}
|
||||
|
||||
// Ended on whitespace
|
||||
if (i === str.length)
|
||||
break;
|
||||
|
||||
// Check for malformed parameter
|
||||
if (str.charCodeAt(i++) !== 59/* ';' */)
|
||||
return;
|
||||
|
||||
// Consume whitespace
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (code !== 32/* ' ' */ && code !== 9/* '\t' */)
|
||||
break;
|
||||
}
|
||||
|
||||
// Ended on whitespace (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
let name;
|
||||
const nameStart = i;
|
||||
// Parse parameter name
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (TOKEN[code] !== 1) {
|
||||
if (code !== 61/* '=' */)
|
||||
return;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// No value (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
name = str.slice(nameStart, i);
|
||||
++i; // Skip over '='
|
||||
|
||||
// No value (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
let value = '';
|
||||
let valueStart;
|
||||
if (str.charCodeAt(i) === 34/* '"' */) {
|
||||
valueStart = ++i;
|
||||
let escaping = false;
|
||||
// Parse quoted value
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (code === 92/* '\\' */) {
|
||||
if (escaping) {
|
||||
valueStart = i;
|
||||
escaping = false;
|
||||
} else {
|
||||
value += str.slice(valueStart, i);
|
||||
escaping = true;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
if (code === 34/* '"' */) {
|
||||
if (escaping) {
|
||||
valueStart = i;
|
||||
escaping = false;
|
||||
continue;
|
||||
}
|
||||
value += str.slice(valueStart, i);
|
||||
break;
|
||||
}
|
||||
if (escaping) {
|
||||
valueStart = i - 1;
|
||||
escaping = false;
|
||||
}
|
||||
// Invalid unescaped quoted character (malformed)
|
||||
if (QDTEXT[code] !== 1)
|
||||
return;
|
||||
}
|
||||
|
||||
// No end quote (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
++i; // Skip over double quote
|
||||
} else {
|
||||
valueStart = i;
|
||||
// Parse unquoted value
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (TOKEN[code] !== 1) {
|
||||
// No value (malformed)
|
||||
if (i === valueStart)
|
||||
return;
|
||||
break;
|
||||
}
|
||||
}
|
||||
value = str.slice(valueStart, i);
|
||||
}
|
||||
|
||||
name = name.toLowerCase();
|
||||
if (params[name] === undefined)
|
||||
params[name] = value;
|
||||
}
|
||||
|
||||
return params;
|
||||
}
|
||||
|
||||
function parseDisposition(str, defDecoder) {
|
||||
if (str.length === 0)
|
||||
return;
|
||||
|
||||
const params = Object.create(null);
|
||||
let i = 0;
|
||||
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (TOKEN[code] !== 1) {
|
||||
if (parseDispositionParams(str, i, params, defDecoder) === undefined)
|
||||
return;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
const type = str.slice(0, i).toLowerCase();
|
||||
|
||||
return { type, params };
|
||||
}
|
||||
|
||||
function parseDispositionParams(str, i, params, defDecoder) {
|
||||
while (i < str.length) {
|
||||
// Consume whitespace
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (code !== 32/* ' ' */ && code !== 9/* '\t' */)
|
||||
break;
|
||||
}
|
||||
|
||||
// Ended on whitespace
|
||||
if (i === str.length)
|
||||
break;
|
||||
|
||||
// Check for malformed parameter
|
||||
if (str.charCodeAt(i++) !== 59/* ';' */)
|
||||
return;
|
||||
|
||||
// Consume whitespace
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (code !== 32/* ' ' */ && code !== 9/* '\t' */)
|
||||
break;
|
||||
}
|
||||
|
||||
// Ended on whitespace (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
let name;
|
||||
const nameStart = i;
|
||||
// Parse parameter name
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (TOKEN[code] !== 1) {
|
||||
if (code === 61/* '=' */)
|
||||
break;
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
// No value (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
let value = '';
|
||||
let valueStart;
|
||||
let charset;
|
||||
//~ let lang;
|
||||
name = str.slice(nameStart, i);
|
||||
if (name.charCodeAt(name.length - 1) === 42/* '*' */) {
|
||||
// Extended value
|
||||
|
||||
const charsetStart = ++i;
|
||||
// Parse charset name
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (CHARSET[code] !== 1) {
|
||||
if (code !== 39/* '\'' */)
|
||||
return;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Incomplete charset (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
charset = str.slice(charsetStart, i);
|
||||
++i; // Skip over the '\''
|
||||
|
||||
//~ const langStart = ++i;
|
||||
// Parse language name
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (code === 39/* '\'' */)
|
||||
break;
|
||||
}
|
||||
|
||||
// Incomplete language (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
//~ lang = str.slice(langStart, i);
|
||||
++i; // Skip over the '\''
|
||||
|
||||
// No value (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
valueStart = i;
|
||||
|
||||
let encode = 0;
|
||||
// Parse value
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (EXTENDED_VALUE[code] !== 1) {
|
||||
if (code === 37/* '%' */) {
|
||||
let hexUpper;
|
||||
let hexLower;
|
||||
if (i + 2 < str.length
|
||||
&& (hexUpper = HEX_VALUES[str.charCodeAt(i + 1)]) !== -1
|
||||
&& (hexLower = HEX_VALUES[str.charCodeAt(i + 2)]) !== -1) {
|
||||
const byteVal = (hexUpper << 4) + hexLower;
|
||||
value += str.slice(valueStart, i);
|
||||
value += String.fromCharCode(byteVal);
|
||||
i += 2;
|
||||
valueStart = i + 1;
|
||||
if (byteVal >= 128)
|
||||
encode = 2;
|
||||
else if (encode === 0)
|
||||
encode = 1;
|
||||
continue;
|
||||
}
|
||||
// '%' disallowed in non-percent encoded contexts (malformed)
|
||||
return;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
value += str.slice(valueStart, i);
|
||||
value = convertToUTF8(value, charset, encode);
|
||||
if (value === undefined)
|
||||
return;
|
||||
} else {
|
||||
// Non-extended value
|
||||
|
||||
++i; // Skip over '='
|
||||
|
||||
// No value (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
if (str.charCodeAt(i) === 34/* '"' */) {
|
||||
valueStart = ++i;
|
||||
let escaping = false;
|
||||
// Parse quoted value
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (code === 92/* '\\' */) {
|
||||
if (escaping) {
|
||||
valueStart = i;
|
||||
escaping = false;
|
||||
} else {
|
||||
value += str.slice(valueStart, i);
|
||||
escaping = true;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
if (code === 34/* '"' */) {
|
||||
if (escaping) {
|
||||
valueStart = i;
|
||||
escaping = false;
|
||||
continue;
|
||||
}
|
||||
value += str.slice(valueStart, i);
|
||||
break;
|
||||
}
|
||||
if (escaping) {
|
||||
valueStart = i - 1;
|
||||
escaping = false;
|
||||
}
|
||||
// Invalid unescaped quoted character (malformed)
|
||||
if (QDTEXT[code] !== 1)
|
||||
return;
|
||||
}
|
||||
|
||||
// No end quote (malformed)
|
||||
if (i === str.length)
|
||||
return;
|
||||
|
||||
++i; // Skip over double quote
|
||||
} else {
|
||||
valueStart = i;
|
||||
// Parse unquoted value
|
||||
for (; i < str.length; ++i) {
|
||||
const code = str.charCodeAt(i);
|
||||
if (TOKEN[code] !== 1) {
|
||||
// No value (malformed)
|
||||
if (i === valueStart)
|
||||
return;
|
||||
break;
|
||||
}
|
||||
}
|
||||
value = str.slice(valueStart, i);
|
||||
}
|
||||
|
||||
value = defDecoder(value, 2);
|
||||
if (value === undefined)
|
||||
return;
|
||||
}
|
||||
|
||||
name = name.toLowerCase();
|
||||
if (params[name] === undefined)
|
||||
params[name] = value;
|
||||
}
|
||||
|
||||
return params;
|
||||
}
|
||||
|
||||
function getDecoder(charset) {
|
||||
let lc;
|
||||
while (true) {
|
||||
switch (charset) {
|
||||
case 'utf-8':
|
||||
case 'utf8':
|
||||
return decoders.utf8;
|
||||
case 'latin1':
|
||||
case 'ascii': // TODO: Make these a separate, strict decoder?
|
||||
case 'us-ascii':
|
||||
case 'iso-8859-1':
|
||||
case 'iso8859-1':
|
||||
case 'iso88591':
|
||||
case 'iso_8859-1':
|
||||
case 'windows-1252':
|
||||
case 'iso_8859-1:1987':
|
||||
case 'cp1252':
|
||||
case 'x-cp1252':
|
||||
return decoders.latin1;
|
||||
case 'utf16le':
|
||||
case 'utf-16le':
|
||||
case 'ucs2':
|
||||
case 'ucs-2':
|
||||
return decoders.utf16le;
|
||||
case 'base64':
|
||||
return decoders.base64;
|
||||
default:
|
||||
if (lc === undefined) {
|
||||
lc = true;
|
||||
charset = charset.toLowerCase();
|
||||
continue;
|
||||
}
|
||||
return decoders.other.bind(charset);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const decoders = {
|
||||
utf8: (data, hint) => {
|
||||
if (data.length === 0)
|
||||
return '';
|
||||
if (typeof data === 'string') {
|
||||
// If `data` never had any percent-encoded bytes or never had any that
|
||||
// were outside of the ASCII range, then we can safely just return the
|
||||
// input since UTF-8 is ASCII compatible
|
||||
if (hint < 2)
|
||||
return data;
|
||||
|
||||
data = Buffer.from(data, 'latin1');
|
||||
}
|
||||
return data.utf8Slice(0, data.length);
|
||||
},
|
||||
|
||||
latin1: (data, hint) => {
|
||||
if (data.length === 0)
|
||||
return '';
|
||||
if (typeof data === 'string')
|
||||
return data;
|
||||
return data.latin1Slice(0, data.length);
|
||||
},
|
||||
|
||||
utf16le: (data, hint) => {
|
||||
if (data.length === 0)
|
||||
return '';
|
||||
if (typeof data === 'string')
|
||||
data = Buffer.from(data, 'latin1');
|
||||
return data.ucs2Slice(0, data.length);
|
||||
},
|
||||
|
||||
base64: (data, hint) => {
|
||||
if (data.length === 0)
|
||||
return '';
|
||||
if (typeof data === 'string')
|
||||
data = Buffer.from(data, 'latin1');
|
||||
return data.base64Slice(0, data.length);
|
||||
},
|
||||
|
||||
other: (data, hint) => {
|
||||
if (data.length === 0)
|
||||
return '';
|
||||
if (typeof data === 'string')
|
||||
data = Buffer.from(data, 'latin1');
|
||||
try {
|
||||
const decoder = new TextDecoder(this);
|
||||
return decoder.decode(data);
|
||||
} catch {}
|
||||
},
|
||||
};
|
||||
|
||||
function convertToUTF8(data, charset, hint) {
|
||||
const decode = getDecoder(charset);
|
||||
if (decode)
|
||||
return decode(data, hint);
|
||||
}
|
||||
|
||||
function basename(path) {
|
||||
if (typeof path !== 'string')
|
||||
return '';
|
||||
for (let i = path.length - 1; i >= 0; --i) {
|
||||
switch (path.charCodeAt(i)) {
|
||||
case 0x2F: // '/'
|
||||
case 0x5C: // '\'
|
||||
path = path.slice(i + 1);
|
||||
return (path === '..' || path === '.' ? '' : path);
|
||||
}
|
||||
}
|
||||
return (path === '..' || path === '.' ? '' : path);
|
||||
}
|
||||
|
||||
const TOKEN = [
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,
|
||||
0, 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, 0, 0, 0, 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, 0, 1, 0, 1, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
];
|
||||
|
||||
const QDTEXT = [
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
1, 1, 0, 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, 0, 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, 0,
|
||||
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,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
];
|
||||
|
||||
const CHARSET = [
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,
|
||||
0, 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, 0, 0, 0, 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, 0, 1, 1, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
];
|
||||
|
||||
const EXTENDED_VALUE = [
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0,
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0,
|
||||
0, 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, 0, 0, 0, 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, 0, 1, 0, 1, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
];
|
||||
|
||||
/* eslint-disable no-multi-spaces */
|
||||
const HEX_VALUES = [
|
||||
-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,
|
||||
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -1, -1, -1, -1,
|
||||
-1, 10, 11, 12, 13, 14, 15, -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, 10, 11, 12, 13, 14, 15, -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, -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,
|
||||
];
|
||||
/* eslint-enable no-multi-spaces */
|
||||
|
||||
module.exports = {
|
||||
basename,
|
||||
convertToUTF8,
|
||||
getDecoder,
|
||||
parseContentType,
|
||||
parseDisposition,
|
||||
};
|
||||
@ -0,0 +1,22 @@
|
||||
{ "name": "busboy",
|
||||
"version": "1.6.0",
|
||||
"author": "Brian White <mscdex@mscdex.net>",
|
||||
"description": "A streaming parser for HTML form data for node.js",
|
||||
"main": "./lib/index.js",
|
||||
"dependencies": {
|
||||
"streamsearch": "^1.1.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@mscdex/eslint-config": "^1.1.0",
|
||||
"eslint": "^7.32.0"
|
||||
},
|
||||
"scripts": {
|
||||
"test": "node test/test.js",
|
||||
"lint": "eslint --cache --report-unused-disable-directives --ext=.js .eslintrc.js lib test bench",
|
||||
"lint:fix": "npm run lint -- --fix"
|
||||
},
|
||||
"engines": { "node": ">=10.16.0" },
|
||||
"keywords": [ "uploads", "forms", "multipart", "form-data" ],
|
||||
"licenses": [ { "type": "MIT", "url": "http://github.com/mscdex/busboy/raw/master/LICENSE" } ],
|
||||
"repository": { "type": "git", "url": "http://github.com/mscdex/busboy.git" }
|
||||
}
|
||||
@ -0,0 +1,109 @@
|
||||
'use strict';
|
||||
|
||||
const assert = require('assert');
|
||||
const { inspect } = require('util');
|
||||
|
||||
const mustCallChecks = [];
|
||||
|
||||
function noop() {}
|
||||
|
||||
function runCallChecks(exitCode) {
|
||||
if (exitCode !== 0) return;
|
||||
|
||||
const failed = mustCallChecks.filter((context) => {
|
||||
if ('minimum' in context) {
|
||||
context.messageSegment = `at least ${context.minimum}`;
|
||||
return context.actual < context.minimum;
|
||||
}
|
||||
context.messageSegment = `exactly ${context.exact}`;
|
||||
return context.actual !== context.exact;
|
||||
});
|
||||
|
||||
failed.forEach((context) => {
|
||||
console.error('Mismatched %s function calls. Expected %s, actual %d.',
|
||||
context.name,
|
||||
context.messageSegment,
|
||||
context.actual);
|
||||
console.error(context.stack.split('\n').slice(2).join('\n'));
|
||||
});
|
||||
|
||||
if (failed.length)
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
function mustCall(fn, exact) {
|
||||
return _mustCallInner(fn, exact, 'exact');
|
||||
}
|
||||
|
||||
function mustCallAtLeast(fn, minimum) {
|
||||
return _mustCallInner(fn, minimum, 'minimum');
|
||||
}
|
||||
|
||||
function _mustCallInner(fn, criteria = 1, field) {
|
||||
if (process._exiting)
|
||||
throw new Error('Cannot use common.mustCall*() in process exit handler');
|
||||
|
||||
if (typeof fn === 'number') {
|
||||
criteria = fn;
|
||||
fn = noop;
|
||||
} else if (fn === undefined) {
|
||||
fn = noop;
|
||||
}
|
||||
|
||||
if (typeof criteria !== 'number')
|
||||
throw new TypeError(`Invalid ${field} value: ${criteria}`);
|
||||
|
||||
const context = {
|
||||
[field]: criteria,
|
||||
actual: 0,
|
||||
stack: inspect(new Error()),
|
||||
name: fn.name || '<anonymous>'
|
||||
};
|
||||
|
||||
// Add the exit listener only once to avoid listener leak warnings
|
||||
if (mustCallChecks.length === 0)
|
||||
process.on('exit', runCallChecks);
|
||||
|
||||
mustCallChecks.push(context);
|
||||
|
||||
function wrapped(...args) {
|
||||
++context.actual;
|
||||
return fn.call(this, ...args);
|
||||
}
|
||||
// TODO: remove origFn?
|
||||
wrapped.origFn = fn;
|
||||
|
||||
return wrapped;
|
||||
}
|
||||
|
||||
function getCallSite(top) {
|
||||
const originalStackFormatter = Error.prepareStackTrace;
|
||||
Error.prepareStackTrace = (err, stack) =>
|
||||
`${stack[0].getFileName()}:${stack[0].getLineNumber()}`;
|
||||
const err = new Error();
|
||||
Error.captureStackTrace(err, top);
|
||||
// With the V8 Error API, the stack is not formatted until it is accessed
|
||||
// eslint-disable-next-line no-unused-expressions
|
||||
err.stack;
|
||||
Error.prepareStackTrace = originalStackFormatter;
|
||||
return err.stack;
|
||||
}
|
||||
|
||||
function mustNotCall(msg) {
|
||||
const callSite = getCallSite(mustNotCall);
|
||||
return function mustNotCall(...args) {
|
||||
args = args.map(inspect).join(', ');
|
||||
const argsInfo = (args.length > 0
|
||||
? `\ncalled with arguments: ${args}`
|
||||
: '');
|
||||
assert.fail(
|
||||
`${msg || 'function should not have been called'} at ${callSite}`
|
||||
+ argsInfo);
|
||||
};
|
||||
}
|
||||
|
||||
module.exports = {
|
||||
mustCall,
|
||||
mustCallAtLeast,
|
||||
mustNotCall,
|
||||
};
|
||||
@ -0,0 +1,94 @@
|
||||
'use strict';
|
||||
|
||||
const assert = require('assert');
|
||||
const { inspect } = require('util');
|
||||
|
||||
const { mustCall } = require(`${__dirname}/common.js`);
|
||||
|
||||
const busboy = require('..');
|
||||
|
||||
const input = Buffer.from([
|
||||
'-----------------------------paZqsnEHRufoShdX6fh0lUhXBP4k',
|
||||
'Content-Disposition: form-data; '
|
||||
+ 'name="upload_file_0"; filename="テスト.dat"',
|
||||
'Content-Type: application/octet-stream',
|
||||
'',
|
||||
'A'.repeat(1023),
|
||||
'-----------------------------paZqsnEHRufoShdX6fh0lUhXBP4k--'
|
||||
].join('\r\n'));
|
||||
const boundary = '---------------------------paZqsnEHRufoShdX6fh0lUhXBP4k';
|
||||
const expected = [
|
||||
{ type: 'file',
|
||||
name: 'upload_file_0',
|
||||
data: Buffer.from('A'.repeat(1023)),
|
||||
info: {
|
||||
filename: 'テスト.dat',
|
||||
encoding: '7bit',
|
||||
mimeType: 'application/octet-stream',
|
||||
},
|
||||
limited: false,
|
||||
},
|
||||
];
|
||||
const bb = busboy({
|
||||
defParamCharset: 'utf8',
|
||||
headers: {
|
||||
'content-type': `multipart/form-data; boundary=${boundary}`,
|
||||
}
|
||||
});
|
||||
const results = [];
|
||||
|
||||
bb.on('field', (name, val, info) => {
|
||||
results.push({ type: 'field', name, val, info });
|
||||
});
|
||||
|
||||
bb.on('file', (name, stream, info) => {
|
||||
const data = [];
|
||||
let nb = 0;
|
||||
const file = {
|
||||
type: 'file',
|
||||
name,
|
||||
data: null,
|
||||
info,
|
||||
limited: false,
|
||||
};
|
||||
results.push(file);
|
||||
stream.on('data', (d) => {
|
||||
data.push(d);
|
||||
nb += d.length;
|
||||
}).on('limit', () => {
|
||||
file.limited = true;
|
||||
}).on('close', () => {
|
||||
file.data = Buffer.concat(data, nb);
|
||||
assert.strictEqual(stream.truncated, file.limited);
|
||||
}).once('error', (err) => {
|
||||
file.err = err.message;
|
||||
});
|
||||
});
|
||||
|
||||
bb.on('error', (err) => {
|
||||
results.push({ error: err.message });
|
||||
});
|
||||
|
||||
bb.on('partsLimit', () => {
|
||||
results.push('partsLimit');
|
||||
});
|
||||
|
||||
bb.on('filesLimit', () => {
|
||||
results.push('filesLimit');
|
||||
});
|
||||
|
||||
bb.on('fieldsLimit', () => {
|
||||
results.push('fieldsLimit');
|
||||
});
|
||||
|
||||
bb.on('close', mustCall(() => {
|
||||
assert.deepStrictEqual(
|
||||
results,
|
||||
expected,
|
||||
'Results mismatch.\n'
|
||||
+ `Parsed: ${inspect(results)}\n`
|
||||
+ `Expected: ${inspect(expected)}`
|
||||
);
|
||||
}));
|
||||
|
||||
bb.end(input);
|
||||
@ -0,0 +1,102 @@
|
||||
'use strict';
|
||||
|
||||
const assert = require('assert');
|
||||
const { randomFillSync } = require('crypto');
|
||||
const { inspect } = require('util');
|
||||
|
||||
const busboy = require('..');
|
||||
|
||||
const { mustCall } = require('./common.js');
|
||||
|
||||
const BOUNDARY = 'u2KxIV5yF1y+xUspOQCCZopaVgeV6Jxihv35XQJmuTx8X3sh';
|
||||
|
||||
function formDataSection(key, value) {
|
||||
return Buffer.from(
|
||||
`\r\n--${BOUNDARY}`
|
||||
+ `\r\nContent-Disposition: form-data; name="${key}"`
|
||||
+ `\r\n\r\n${value}`
|
||||
);
|
||||
}
|
||||
|
||||
function formDataFile(key, filename, contentType) {
|
||||
const buf = Buffer.allocUnsafe(100000);
|
||||
return Buffer.concat([
|
||||
Buffer.from(`\r\n--${BOUNDARY}\r\n`),
|
||||
Buffer.from(`Content-Disposition: form-data; name="${key}"`
|
||||
+ `; filename="${filename}"\r\n`),
|
||||
Buffer.from(`Content-Type: ${contentType}\r\n\r\n`),
|
||||
randomFillSync(buf)
|
||||
]);
|
||||
}
|
||||
|
||||
const reqChunks = [
|
||||
Buffer.concat([
|
||||
formDataFile('file', 'file.bin', 'application/octet-stream'),
|
||||
formDataSection('foo', 'foo value'),
|
||||
]),
|
||||
formDataSection('bar', 'bar value'),
|
||||
Buffer.from(`\r\n--${BOUNDARY}--\r\n`)
|
||||
];
|
||||
const bb = busboy({
|
||||
headers: {
|
||||
'content-type': `multipart/form-data; boundary=${BOUNDARY}`
|
||||
}
|
||||
});
|
||||
const expected = [
|
||||
{ type: 'file',
|
||||
name: 'file',
|
||||
info: {
|
||||
filename: 'file.bin',
|
||||
encoding: '7bit',
|
||||
mimeType: 'application/octet-stream',
|
||||
},
|
||||
},
|
||||
{ type: 'field',
|
||||
name: 'foo',
|
||||
val: 'foo value',
|
||||
info: {
|
||||
nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: '7bit',
|
||||
mimeType: 'text/plain',
|
||||
},
|
||||
},
|
||||
{ type: 'field',
|
||||
name: 'bar',
|
||||
val: 'bar value',
|
||||
info: {
|
||||
nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: '7bit',
|
||||
mimeType: 'text/plain',
|
||||
},
|
||||
},
|
||||
];
|
||||
const results = [];
|
||||
|
||||
bb.on('field', (name, val, info) => {
|
||||
results.push({ type: 'field', name, val, info });
|
||||
});
|
||||
|
||||
bb.on('file', (name, stream, info) => {
|
||||
results.push({ type: 'file', name, info });
|
||||
// Simulate a pipe where the destination is pausing (perhaps due to waiting
|
||||
// for file system write to finish)
|
||||
setTimeout(() => {
|
||||
stream.resume();
|
||||
}, 10);
|
||||
});
|
||||
|
||||
bb.on('close', mustCall(() => {
|
||||
assert.deepStrictEqual(
|
||||
results,
|
||||
expected,
|
||||
'Results mismatch.\n'
|
||||
+ `Parsed: ${inspect(results)}\n`
|
||||
+ `Expected: ${inspect(expected)}`
|
||||
);
|
||||
}));
|
||||
|
||||
for (const chunk of reqChunks)
|
||||
bb.write(chunk);
|
||||
bb.end();
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,488 @@
|
||||
'use strict';
|
||||
|
||||
const assert = require('assert');
|
||||
const { transcode } = require('buffer');
|
||||
const { inspect } = require('util');
|
||||
|
||||
const busboy = require('..');
|
||||
|
||||
const active = new Map();
|
||||
|
||||
const tests = [
|
||||
{ source: ['foo'],
|
||||
expected: [
|
||||
['foo',
|
||||
'',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Unassigned value'
|
||||
},
|
||||
{ source: ['foo=bar'],
|
||||
expected: [
|
||||
['foo',
|
||||
'bar',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Assigned value'
|
||||
},
|
||||
{ source: ['foo&bar=baz'],
|
||||
expected: [
|
||||
['foo',
|
||||
'',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['bar',
|
||||
'baz',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Unassigned and assigned value'
|
||||
},
|
||||
{ source: ['foo=bar&baz'],
|
||||
expected: [
|
||||
['foo',
|
||||
'bar',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['baz',
|
||||
'',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Assigned and unassigned value'
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [
|
||||
['foo',
|
||||
'bar',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['baz',
|
||||
'bla',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Two assigned values'
|
||||
},
|
||||
{ source: ['foo&bar'],
|
||||
expected: [
|
||||
['foo',
|
||||
'',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['bar',
|
||||
'',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Two unassigned values'
|
||||
},
|
||||
{ source: ['foo&bar&'],
|
||||
expected: [
|
||||
['foo',
|
||||
'',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['bar',
|
||||
'',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Two unassigned values and ampersand'
|
||||
},
|
||||
{ source: ['foo+1=bar+baz%2Bquux'],
|
||||
expected: [
|
||||
['foo 1',
|
||||
'bar baz+quux',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Assigned key and value with (plus) space'
|
||||
},
|
||||
{ source: ['foo=bar%20baz%21'],
|
||||
expected: [
|
||||
['foo',
|
||||
'bar baz!',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Assigned value with encoded bytes'
|
||||
},
|
||||
{ source: ['foo%20bar=baz%20bla%21'],
|
||||
expected: [
|
||||
['foo bar',
|
||||
'baz bla!',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Assigned value with encoded bytes #2'
|
||||
},
|
||||
{ source: ['foo=bar%20baz%21&num=1000'],
|
||||
expected: [
|
||||
['foo',
|
||||
'bar baz!',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['num',
|
||||
'1000',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Two assigned values, one with encoded bytes'
|
||||
},
|
||||
{ source: [
|
||||
Array.from(transcode(Buffer.from('foo'), 'utf8', 'utf16le')).map(
|
||||
(n) => `%${n.toString(16).padStart(2, '0')}`
|
||||
).join(''),
|
||||
'=',
|
||||
Array.from(transcode(Buffer.from('😀!'), 'utf8', 'utf16le')).map(
|
||||
(n) => `%${n.toString(16).padStart(2, '0')}`
|
||||
).join(''),
|
||||
],
|
||||
expected: [
|
||||
['foo',
|
||||
'😀!',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'UTF-16LE',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
charset: 'UTF-16LE',
|
||||
what: 'Encoded value with multi-byte charset'
|
||||
},
|
||||
{ source: [
|
||||
'foo=<',
|
||||
Array.from(transcode(Buffer.from('©:^þ'), 'utf8', 'latin1')).map(
|
||||
(n) => `%${n.toString(16).padStart(2, '0')}`
|
||||
).join(''),
|
||||
],
|
||||
expected: [
|
||||
['foo',
|
||||
'<©:^þ',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'ISO-8859-1',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
charset: 'ISO-8859-1',
|
||||
what: 'Encoded value with single-byte, ASCII-compatible, non-UTF8 charset'
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [],
|
||||
what: 'Limits: zero fields',
|
||||
limits: { fields: 0 }
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [
|
||||
['foo',
|
||||
'bar',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Limits: one field',
|
||||
limits: { fields: 1 }
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [
|
||||
['foo',
|
||||
'bar',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['baz',
|
||||
'bla',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Limits: field part lengths match limits',
|
||||
limits: { fieldNameSize: 3, fieldSize: 3 }
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [
|
||||
['fo',
|
||||
'bar',
|
||||
{ nameTruncated: true,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['ba',
|
||||
'bla',
|
||||
{ nameTruncated: true,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Limits: truncated field name',
|
||||
limits: { fieldNameSize: 2 }
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [
|
||||
['foo',
|
||||
'ba',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: true,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['baz',
|
||||
'bl',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: true,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Limits: truncated field value',
|
||||
limits: { fieldSize: 2 }
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [
|
||||
['fo',
|
||||
'ba',
|
||||
{ nameTruncated: true,
|
||||
valueTruncated: true,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['ba',
|
||||
'bl',
|
||||
{ nameTruncated: true,
|
||||
valueTruncated: true,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Limits: truncated field name and value',
|
||||
limits: { fieldNameSize: 2, fieldSize: 2 }
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [
|
||||
['fo',
|
||||
'',
|
||||
{ nameTruncated: true,
|
||||
valueTruncated: true,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['ba',
|
||||
'',
|
||||
{ nameTruncated: true,
|
||||
valueTruncated: true,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Limits: truncated field name and zero value limit',
|
||||
limits: { fieldNameSize: 2, fieldSize: 0 }
|
||||
},
|
||||
{ source: ['foo=bar&baz=bla'],
|
||||
expected: [
|
||||
['',
|
||||
'',
|
||||
{ nameTruncated: true,
|
||||
valueTruncated: true,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
['',
|
||||
'',
|
||||
{ nameTruncated: true,
|
||||
valueTruncated: true,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Limits: truncated zero field name and zero value limit',
|
||||
limits: { fieldNameSize: 0, fieldSize: 0 }
|
||||
},
|
||||
{ source: ['&'],
|
||||
expected: [],
|
||||
what: 'Ampersand'
|
||||
},
|
||||
{ source: ['&&&&&'],
|
||||
expected: [],
|
||||
what: 'Many ampersands'
|
||||
},
|
||||
{ source: ['='],
|
||||
expected: [
|
||||
['',
|
||||
'',
|
||||
{ nameTruncated: false,
|
||||
valueTruncated: false,
|
||||
encoding: 'utf-8',
|
||||
mimeType: 'text/plain' },
|
||||
],
|
||||
],
|
||||
what: 'Assigned value, empty name and value'
|
||||
},
|
||||
{ source: [''],
|
||||
expected: [],
|
||||
what: 'Nothing'
|
||||
},
|
||||
];
|
||||
|
||||
for (const test of tests) {
|
||||
active.set(test, 1);
|
||||
|
||||
const { what } = test;
|
||||
const charset = test.charset || 'utf-8';
|
||||
const bb = busboy({
|
||||
limits: test.limits,
|
||||
headers: {
|
||||
'content-type': `application/x-www-form-urlencoded; charset=${charset}`,
|
||||
},
|
||||
});
|
||||
const results = [];
|
||||
|
||||
bb.on('field', (key, val, info) => {
|
||||
results.push([key, val, info]);
|
||||
});
|
||||
|
||||
bb.on('file', () => {
|
||||
throw new Error(`[${what}] Unexpected file`);
|
||||
});
|
||||
|
||||
bb.on('close', () => {
|
||||
active.delete(test);
|
||||
|
||||
assert.deepStrictEqual(
|
||||
results,
|
||||
test.expected,
|
||||
`[${what}] Results mismatch.\n`
|
||||
+ `Parsed: ${inspect(results)}\n`
|
||||
+ `Expected: ${inspect(test.expected)}`
|
||||
);
|
||||
});
|
||||
|
||||
for (const src of test.source) {
|
||||
const buf = (typeof src === 'string' ? Buffer.from(src, 'utf8') : src);
|
||||
bb.write(buf);
|
||||
}
|
||||
bb.end();
|
||||
}
|
||||
|
||||
// Byte-by-byte versions
|
||||
for (let test of tests) {
|
||||
test = { ...test };
|
||||
test.what += ' (byte-by-byte)';
|
||||
active.set(test, 1);
|
||||
|
||||
const { what } = test;
|
||||
const charset = test.charset || 'utf-8';
|
||||
const bb = busboy({
|
||||
limits: test.limits,
|
||||
headers: {
|
||||
'content-type': `application/x-www-form-urlencoded; charset="${charset}"`,
|
||||
},
|
||||
});
|
||||
const results = [];
|
||||
|
||||
bb.on('field', (key, val, info) => {
|
||||
results.push([key, val, info]);
|
||||
});
|
||||
|
||||
bb.on('file', () => {
|
||||
throw new Error(`[${what}] Unexpected file`);
|
||||
});
|
||||
|
||||
bb.on('close', () => {
|
||||
active.delete(test);
|
||||
|
||||
assert.deepStrictEqual(
|
||||
results,
|
||||
test.expected,
|
||||
`[${what}] Results mismatch.\n`
|
||||
+ `Parsed: ${inspect(results)}\n`
|
||||
+ `Expected: ${inspect(test.expected)}`
|
||||
);
|
||||
});
|
||||
|
||||
for (const src of test.source) {
|
||||
const buf = (typeof src === 'string' ? Buffer.from(src, 'utf8') : src);
|
||||
for (let i = 0; i < buf.length; ++i)
|
||||
bb.write(buf.slice(i, i + 1));
|
||||
}
|
||||
bb.end();
|
||||
}
|
||||
|
||||
{
|
||||
let exception = false;
|
||||
process.once('uncaughtException', (ex) => {
|
||||
exception = true;
|
||||
throw ex;
|
||||
});
|
||||
process.on('exit', () => {
|
||||
if (exception || active.size === 0)
|
||||
return;
|
||||
process.exitCode = 1;
|
||||
console.error('==========================');
|
||||
console.error(`${active.size} test(s) did not finish:`);
|
||||
console.error('==========================');
|
||||
console.error(Array.from(active.keys()).map((v) => v.what).join('\n'));
|
||||
});
|
||||
}
|
||||
@ -0,0 +1,20 @@
|
||||
'use strict';
|
||||
|
||||
const { spawnSync } = require('child_process');
|
||||
const { readdirSync } = require('fs');
|
||||
const { join } = require('path');
|
||||
|
||||
const files = readdirSync(__dirname).sort();
|
||||
for (const filename of files) {
|
||||
if (filename.startsWith('test-')) {
|
||||
const path = join(__dirname, filename);
|
||||
console.log(`> Running ${filename} ...`);
|
||||
const result = spawnSync(`${process.argv0} ${path}`, {
|
||||
shell: true,
|
||||
stdio: 'inherit',
|
||||
windowsHide: true
|
||||
});
|
||||
if (result.status !== 0)
|
||||
process.exitCode = 1;
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,5 @@
|
||||
'use strict';
|
||||
|
||||
module.exports = {
|
||||
extends: '@mscdex/eslint-config',
|
||||
};
|
||||
@ -0,0 +1,24 @@
|
||||
name: CI
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [ master ]
|
||||
|
||||
jobs:
|
||||
tests-linux:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
node-version: [10.x, 12.x, 14.x, 16.x]
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Use Node.js ${{ matrix.node-version }}
|
||||
uses: actions/setup-node@v1
|
||||
with:
|
||||
node-version: ${{ matrix.node-version }}
|
||||
- name: Install module
|
||||
run: npm install
|
||||
- name: Run tests
|
||||
run: npm test
|
||||
@ -0,0 +1,23 @@
|
||||
name: lint
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [ master ]
|
||||
|
||||
env:
|
||||
NODE_VERSION: 16.x
|
||||
|
||||
jobs:
|
||||
lint-js:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Use Node.js ${{ env.NODE_VERSION }}
|
||||
uses: actions/setup-node@v1
|
||||
with:
|
||||
node-version: ${{ env.NODE_VERSION }}
|
||||
- name: Install ESLint + ESLint configs/plugins
|
||||
run: npm install --only=dev
|
||||
- name: Lint files
|
||||
run: npm run lint
|
||||
@ -0,0 +1,19 @@
|
||||
Copyright Brian White. All rights reserved.
|
||||
|
||||
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.
|
||||
@ -0,0 +1,95 @@
|
||||
Description
|
||||
===========
|
||||
|
||||
streamsearch is a module for [node.js](http://nodejs.org/) that allows searching a stream using the Boyer-Moore-Horspool algorithm.
|
||||
|
||||
This module is based heavily on the Streaming Boyer-Moore-Horspool C++ implementation by Hongli Lai [here](https://github.com/FooBarWidget/boyer-moore-horspool).
|
||||
|
||||
|
||||
Requirements
|
||||
============
|
||||
|
||||
* [node.js](http://nodejs.org/) -- v10.0.0 or newer
|
||||
|
||||
|
||||
Installation
|
||||
============
|
||||
|
||||
npm install streamsearch
|
||||
|
||||
Example
|
||||
=======
|
||||
|
||||
```js
|
||||
const { inspect } = require('util');
|
||||
|
||||
const StreamSearch = require('streamsearch');
|
||||
|
||||
const needle = Buffer.from('\r\n');
|
||||
const ss = new StreamSearch(needle, (isMatch, data, start, end) => {
|
||||
if (data)
|
||||
console.log('data: ' + inspect(data.toString('latin1', start, end)));
|
||||
if (isMatch)
|
||||
console.log('match!');
|
||||
});
|
||||
|
||||
const chunks = [
|
||||
'foo',
|
||||
' bar',
|
||||
'\r',
|
||||
'\n',
|
||||
'baz, hello\r',
|
||||
'\n world.',
|
||||
'\r\n Node.JS rules!!\r\n\r\n',
|
||||
];
|
||||
for (const chunk of chunks)
|
||||
ss.push(Buffer.from(chunk));
|
||||
|
||||
// output:
|
||||
//
|
||||
// data: 'foo'
|
||||
// data: ' bar'
|
||||
// match!
|
||||
// data: 'baz, hello'
|
||||
// match!
|
||||
// data: ' world.'
|
||||
// match!
|
||||
// data: ' Node.JS rules!!'
|
||||
// match!
|
||||
// data: ''
|
||||
// match!
|
||||
```
|
||||
|
||||
|
||||
API
|
||||
===
|
||||
|
||||
Properties
|
||||
----------
|
||||
|
||||
* **maxMatches** - < _integer_ > - The maximum number of matches. Defaults to `Infinity`.
|
||||
|
||||
* **matches** - < _integer_ > - The current match count.
|
||||
|
||||
|
||||
Functions
|
||||
---------
|
||||
|
||||
* **(constructor)**(< _mixed_ >needle, < _function_ >callback) - Creates and returns a new instance for searching for a _Buffer_ or _string_ `needle`. `callback` is called any time there is non-matching data and/or there is a needle match. `callback` will be called with the following arguments:
|
||||
|
||||
1. `isMatch` - _boolean_ - Indicates whether a match has been found
|
||||
|
||||
2. `data` - _mixed_ - If set, this contains data that did not match the needle.
|
||||
|
||||
3. `start` - _integer_ - The index in `data` where the non-matching data begins (inclusive).
|
||||
|
||||
4. `end` - _integer_ - The index in `data` where the non-matching data ends (exclusive).
|
||||
|
||||
5. `isSafeData` - _boolean_ - Indicates if it is safe to store a reference to `data` (e.g. as-is or via `data.slice()`) or not, as in some cases `data` may point to a Buffer whose contents change over time.
|
||||
|
||||
* **destroy**() - _(void)_ - Emits any last remaining unmatched data that may still be buffered and then resets internal state.
|
||||
|
||||
* **push**(< _Buffer_ >chunk) - _integer_ - Processes `chunk`, searching for a match. The return value is the last processed index in `chunk` + 1.
|
||||
|
||||
* **reset**() - _(void)_ - Resets internal state. Useful for when you wish to start searching a new/different stream for example.
|
||||
|
||||
@ -0,0 +1,267 @@
|
||||
'use strict';
|
||||
/*
|
||||
Based heavily on the Streaming Boyer-Moore-Horspool C++ implementation
|
||||
by Hongli Lai at: https://github.com/FooBarWidget/boyer-moore-horspool
|
||||
*/
|
||||
function memcmp(buf1, pos1, buf2, pos2, num) {
|
||||
for (let i = 0; i < num; ++i) {
|
||||
if (buf1[pos1 + i] !== buf2[pos2 + i])
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
class SBMH {
|
||||
constructor(needle, cb) {
|
||||
if (typeof cb !== 'function')
|
||||
throw new Error('Missing match callback');
|
||||
|
||||
if (typeof needle === 'string')
|
||||
needle = Buffer.from(needle);
|
||||
else if (!Buffer.isBuffer(needle))
|
||||
throw new Error(`Expected Buffer for needle, got ${typeof needle}`);
|
||||
|
||||
const needleLen = needle.length;
|
||||
|
||||
this.maxMatches = Infinity;
|
||||
this.matches = 0;
|
||||
|
||||
this._cb = cb;
|
||||
this._lookbehindSize = 0;
|
||||
this._needle = needle;
|
||||
this._bufPos = 0;
|
||||
|
||||
this._lookbehind = Buffer.allocUnsafe(needleLen);
|
||||
|
||||
// Initialize occurrence table.
|
||||
this._occ = [
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen, needleLen, needleLen,
|
||||
needleLen, needleLen, needleLen, needleLen
|
||||
];
|
||||
|
||||
// Populate occurrence table with analysis of the needle, ignoring the last
|
||||
// letter.
|
||||
if (needleLen > 1) {
|
||||
for (let i = 0; i < needleLen - 1; ++i)
|
||||
this._occ[needle[i]] = needleLen - 1 - i;
|
||||
}
|
||||
}
|
||||
|
||||
reset() {
|
||||
this.matches = 0;
|
||||
this._lookbehindSize = 0;
|
||||
this._bufPos = 0;
|
||||
}
|
||||
|
||||
push(chunk, pos) {
|
||||
let result;
|
||||
if (!Buffer.isBuffer(chunk))
|
||||
chunk = Buffer.from(chunk, 'latin1');
|
||||
const chunkLen = chunk.length;
|
||||
this._bufPos = pos || 0;
|
||||
while (result !== chunkLen && this.matches < this.maxMatches)
|
||||
result = feed(this, chunk);
|
||||
return result;
|
||||
}
|
||||
|
||||
destroy() {
|
||||
const lbSize = this._lookbehindSize;
|
||||
if (lbSize)
|
||||
this._cb(false, this._lookbehind, 0, lbSize, false);
|
||||
this.reset();
|
||||
}
|
||||
}
|
||||
|
||||
function feed(self, data) {
|
||||
const len = data.length;
|
||||
const needle = self._needle;
|
||||
const needleLen = needle.length;
|
||||
|
||||
// Positive: points to a position in `data`
|
||||
// pos == 3 points to data[3]
|
||||
// Negative: points to a position in the lookbehind buffer
|
||||
// pos == -2 points to lookbehind[lookbehindSize - 2]
|
||||
let pos = -self._lookbehindSize;
|
||||
const lastNeedleCharPos = needleLen - 1;
|
||||
const lastNeedleChar = needle[lastNeedleCharPos];
|
||||
const end = len - needleLen;
|
||||
const occ = self._occ;
|
||||
const lookbehind = self._lookbehind;
|
||||
|
||||
if (pos < 0) {
|
||||
// Lookbehind buffer is not empty. Perform Boyer-Moore-Horspool
|
||||
// search with character lookup code that considers both the
|
||||
// lookbehind buffer and the current round's haystack data.
|
||||
//
|
||||
// Loop until
|
||||
// there is a match.
|
||||
// or until
|
||||
// we've moved past the position that requires the
|
||||
// lookbehind buffer. In this case we switch to the
|
||||
// optimized loop.
|
||||
// or until
|
||||
// the character to look at lies outside the haystack.
|
||||
while (pos < 0 && pos <= end) {
|
||||
const nextPos = pos + lastNeedleCharPos;
|
||||
const ch = (nextPos < 0
|
||||
? lookbehind[self._lookbehindSize + nextPos]
|
||||
: data[nextPos]);
|
||||
|
||||
if (ch === lastNeedleChar
|
||||
&& matchNeedle(self, data, pos, lastNeedleCharPos)) {
|
||||
self._lookbehindSize = 0;
|
||||
++self.matches;
|
||||
if (pos > -self._lookbehindSize)
|
||||
self._cb(true, lookbehind, 0, self._lookbehindSize + pos, false);
|
||||
else
|
||||
self._cb(true, undefined, 0, 0, true);
|
||||
|
||||
return (self._bufPos = pos + needleLen);
|
||||
}
|
||||
|
||||
pos += occ[ch];
|
||||
}
|
||||
|
||||
// No match.
|
||||
|
||||
// There's too few data for Boyer-Moore-Horspool to run,
|
||||
// so let's use a different algorithm to skip as much as
|
||||
// we can.
|
||||
// Forward pos until
|
||||
// the trailing part of lookbehind + data
|
||||
// looks like the beginning of the needle
|
||||
// or until
|
||||
// pos == 0
|
||||
while (pos < 0 && !matchNeedle(self, data, pos, len - pos))
|
||||
++pos;
|
||||
|
||||
if (pos < 0) {
|
||||
// Cut off part of the lookbehind buffer that has
|
||||
// been processed and append the entire haystack
|
||||
// into it.
|
||||
const bytesToCutOff = self._lookbehindSize + pos;
|
||||
|
||||
if (bytesToCutOff > 0) {
|
||||
// The cut off data is guaranteed not to contain the needle.
|
||||
self._cb(false, lookbehind, 0, bytesToCutOff, false);
|
||||
}
|
||||
|
||||
self._lookbehindSize -= bytesToCutOff;
|
||||
lookbehind.copy(lookbehind, 0, bytesToCutOff, self._lookbehindSize);
|
||||
lookbehind.set(data, self._lookbehindSize);
|
||||
self._lookbehindSize += len;
|
||||
|
||||
self._bufPos = len;
|
||||
return len;
|
||||
}
|
||||
|
||||
// Discard lookbehind buffer.
|
||||
self._cb(false, lookbehind, 0, self._lookbehindSize, false);
|
||||
self._lookbehindSize = 0;
|
||||
}
|
||||
|
||||
pos += self._bufPos;
|
||||
|
||||
const firstNeedleChar = needle[0];
|
||||
|
||||
// Lookbehind buffer is now empty. Perform Boyer-Moore-Horspool
|
||||
// search with optimized character lookup code that only considers
|
||||
// the current round's haystack data.
|
||||
while (pos <= end) {
|
||||
const ch = data[pos + lastNeedleCharPos];
|
||||
|
||||
if (ch === lastNeedleChar
|
||||
&& data[pos] === firstNeedleChar
|
||||
&& memcmp(needle, 0, data, pos, lastNeedleCharPos)) {
|
||||
++self.matches;
|
||||
if (pos > 0)
|
||||
self._cb(true, data, self._bufPos, pos, true);
|
||||
else
|
||||
self._cb(true, undefined, 0, 0, true);
|
||||
|
||||
return (self._bufPos = pos + needleLen);
|
||||
}
|
||||
|
||||
pos += occ[ch];
|
||||
}
|
||||
|
||||
// There was no match. If there's trailing haystack data that we cannot
|
||||
// match yet using the Boyer-Moore-Horspool algorithm (because the trailing
|
||||
// data is less than the needle size) then match using a modified
|
||||
// algorithm that starts matching from the beginning instead of the end.
|
||||
// Whatever trailing data is left after running this algorithm is added to
|
||||
// the lookbehind buffer.
|
||||
while (pos < len) {
|
||||
if (data[pos] !== firstNeedleChar
|
||||
|| !memcmp(data, pos, needle, 0, len - pos)) {
|
||||
++pos;
|
||||
continue;
|
||||
}
|
||||
data.copy(lookbehind, 0, pos, len);
|
||||
self._lookbehindSize = len - pos;
|
||||
break;
|
||||
}
|
||||
|
||||
// Everything until `pos` is guaranteed not to contain needle data.
|
||||
if (pos > 0)
|
||||
self._cb(false, data, self._bufPos, pos < len ? pos : len, true);
|
||||
|
||||
self._bufPos = len;
|
||||
return len;
|
||||
}
|
||||
|
||||
function matchNeedle(self, data, pos, len) {
|
||||
const lb = self._lookbehind;
|
||||
const lbSize = self._lookbehindSize;
|
||||
const needle = self._needle;
|
||||
|
||||
for (let i = 0; i < len; ++i, ++pos) {
|
||||
const ch = (pos < 0 ? lb[lbSize + pos] : data[pos]);
|
||||
if (ch !== needle[i])
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
module.exports = SBMH;
|
||||
@ -0,0 +1,34 @@
|
||||
{
|
||||
"name": "streamsearch",
|
||||
"version": "1.1.0",
|
||||
"author": "Brian White <mscdex@mscdex.net>",
|
||||
"description": "Streaming Boyer-Moore-Horspool searching for node.js",
|
||||
"main": "./lib/sbmh.js",
|
||||
"engines": {
|
||||
"node": ">=10.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@mscdex/eslint-config": "^1.1.0",
|
||||
"eslint": "^7.32.0"
|
||||
},
|
||||
"scripts": {
|
||||
"test": "node test/test.js",
|
||||
"lint": "eslint --cache --report-unused-disable-directives --ext=.js .eslintrc.js lib test",
|
||||
"lint:fix": "npm run lint -- --fix"
|
||||
},
|
||||
"keywords": [
|
||||
"stream",
|
||||
"horspool",
|
||||
"boyer-moore-horspool",
|
||||
"boyer-moore",
|
||||
"search"
|
||||
],
|
||||
"licenses": [{
|
||||
"type": "MIT",
|
||||
"url": "http://github.com/mscdex/streamsearch/raw/master/LICENSE"
|
||||
}],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "http://github.com/mscdex/streamsearch.git"
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,70 @@
|
||||
'use strict';
|
||||
|
||||
const assert = require('assert');
|
||||
|
||||
const StreamSearch = require('../lib/sbmh.js');
|
||||
|
||||
[
|
||||
{
|
||||
needle: '\r\n',
|
||||
chunks: [
|
||||
'foo',
|
||||
' bar',
|
||||
'\r',
|
||||
'\n',
|
||||
'baz, hello\r',
|
||||
'\n world.',
|
||||
'\r\n Node.JS rules!!\r\n\r\n',
|
||||
],
|
||||
expect: [
|
||||
[false, 'foo'],
|
||||
[false, ' bar'],
|
||||
[ true, null],
|
||||
[false, 'baz, hello'],
|
||||
[ true, null],
|
||||
[false, ' world.'],
|
||||
[ true, null],
|
||||
[ true, ' Node.JS rules!!'],
|
||||
[ true, ''],
|
||||
],
|
||||
},
|
||||
{
|
||||
needle: '---foobarbaz',
|
||||
chunks: [
|
||||
'---foobarbaz',
|
||||
'asdf',
|
||||
'\r\n',
|
||||
'---foobarba',
|
||||
'---foobar',
|
||||
'ba',
|
||||
'\r\n---foobarbaz--\r\n',
|
||||
],
|
||||
expect: [
|
||||
[ true, null],
|
||||
[false, 'asdf'],
|
||||
[false, '\r\n'],
|
||||
[false, '---foobarba'],
|
||||
[false, '---foobarba'],
|
||||
[ true, '\r\n'],
|
||||
[false, '--\r\n'],
|
||||
],
|
||||
},
|
||||
].forEach((test, i) => {
|
||||
console.log(`Running test #${i + 1}`);
|
||||
const { needle, chunks, expect } = test;
|
||||
|
||||
const results = [];
|
||||
const ss = new StreamSearch(Buffer.from(needle),
|
||||
(isMatch, data, start, end) => {
|
||||
if (data)
|
||||
data = data.toString('latin1', start, end);
|
||||
else
|
||||
data = null;
|
||||
results.push([isMatch, data]);
|
||||
});
|
||||
|
||||
for (const chunk of chunks)
|
||||
ss.push(Buffer.from(chunk));
|
||||
|
||||
assert.deepStrictEqual(results, expect);
|
||||
});
|
||||
Loading…
Reference in new issue