MensBeam
/
HTML-Parser
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Browse Source

Replace Content-Type parser with proper version

ns
J. King 4 years ago
parent
596a58eff1
commit
ad0a8ae27a
3 changed files with 84 additions and 69 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 5
      composer.json
  2. 90
      composer.lock
  3. 58
      lib/Charset.php

5
composer.json
View File

@ -3,9 +3,10 @@
"description": "Parses HTML5 text into a php DOMDocument",
"type": "library",
"require": {
"php": "^7.0",
"php": "^7.1",
"ext-dom": "*",
"mensbeam/intl": "*"
"mensbeam/intl": "*",
"mensbeam/mimesniff": "^0.2.0"
},
"suggest": {
"ext-ctype": "Improved performance"

90
composer.lock
View File

@ -4,16 +4,22 @@
"Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
"This file is @generated automatically"
],
"content-hash": "037fcc961f6e8f68b15379be21f45854",
"content-hash": "96a5c225aba74182ddfac27fa5cee1e8",
"packages": [
{
"name": "mensbeam/intl",
"version": "0.7.0",
"source": {
"type": "git",
"url": "https://code.mensbeam.com/MensBeam/intl",
"url": "https://github.com/mensbeam/intl.git",
"reference": "c4a2ae17142a1846c841c5b5b9246e67d56c568e"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/mensbeam/intl/zipball/c4a2ae17142a1846c841c5b5b9246e67d56c568e",
"reference": "c4a2ae17142a1846c841c5b5b9246e67d56c568e",
"shasum": ""
},
"require": {
"php": "^7.0"
},
@ -50,36 +56,80 @@
"utf8"
],
"time": "2019-12-21T01:56:59+00:00"
},
{
"name": "mensbeam/mimesniff",
"version": "0.2.0",
"source": {
"type": "git",
"url": "https://github.com/mensbeam/mime.git",
"reference": "d3f6c031687d532c1bb32e3eb362da4a948d4750"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/mensbeam/mime/zipball/d3f6c031687d532c1bb32e3eb362da4a948d4750",
"reference": "d3f6c031687d532c1bb32e3eb362da4a948d4750",
"shasum": ""
},
"require": {
"php": "^7.1"
},
"require-dev": {
"bamarni/composer-bin-plugin": "^1.3",
"ext-intl": "*"
},
"type": "library",
"autoload": {
"psr-4": {
"MensBeam\\Mime\\": "lib/"
}
},
"notification-url": "https://packagist.org/downloads/",
"license": [
"MIT"
],
"authors": [
{
"name": "J. King",
"email": "jking@jkingweb.ca",
"homepage": "https://jkingweb.ca/"
}
],
"description": "An implementation of the WHATWG MIME Sniffing specification",
"keywords": [
"WHATWG",
"mime",
"mimesniff"
],
"time": "2020-04-19T16:07:41+00:00"
}
],
"packages-dev": [
{
"name": "bamarni/composer-bin-plugin",
"version": "v1.3.0",
"version": "1.4.1",
"source": {
"type": "git",
"url": "https://github.com/bamarni/composer-bin-plugin.git",
"reference": "67f9d314dc7ecf7245b8637906e151ccc62b8d24"
"reference": "9329fb0fbe29e0e1b2db8f4639a193e4f5406225"
},
"dist": {
"type": "zip",
"url": "https://api.github.com/repos/bamarni/composer-bin-plugin/zipball/67f9d314dc7ecf7245b8637906e151ccc62b8d24",
"reference": "67f9d314dc7ecf7245b8637906e151ccc62b8d24",
"url": "https://api.github.com/repos/bamarni/composer-bin-plugin/zipball/9329fb0fbe29e0e1b2db8f4639a193e4f5406225",
"reference": "9329fb0fbe29e0e1b2db8f4639a193e4f5406225",
"shasum": ""
},
"require": {
"composer-plugin-api": "^1.0"
"composer-plugin-api": "^1.0 || ^2.0",
"php": "^5.5.9 || ^7.0 || ^8.0"
},
"require-dev": {
"composer/composer": "dev-master",
"composer/composer": "^1.0 || ^2.0",
"symfony/console": "^2.5 || ^3.0 || ^4.0"
},
"type": "composer-plugin",
"extra": {
"class": "Bamarni\\Composer\\Bin\\Plugin",
"branch-alias": {
"dev-master": "1.1-dev"
}
"class": "Bamarni\\Composer\\Bin\\Plugin"
},
"autoload": {
"psr-4": {
@ -90,7 +140,16 @@
"license": [
"MIT"
],
"time": "2019-03-17T12:38:04+00:00"
"description": "No conflicts for your bin dependencies",
"keywords": [
"composer",
"conflict",
"dependency",
"executable",
"isolation",
"tool"
],
"time": "2020-05-03T08:27:20+00:00"
}
],
"aliases": [],
@ -99,8 +158,9 @@
"prefer-stable": false,
"prefer-lowest": false,
"platform": {
"php": "^7.0",
"php": "^7.1",
"ext-dom": "*"
},
"platform-dev": []
"platform-dev": [],
"plugin-api-version": "1.1.0"
}

58
lib/Charset.php
View File

@ -3,6 +3,7 @@ declare(strict_types=1);
namespace dW\HTML5;
use MensBeam\Intl\Encoding;
use MensBeam\Mime\MimeType;
abstract class Charset {
/** Finds a Unicode byte order mark by a byte stream
@ -37,58 +38,11 @@ abstract class Charset {
* @param string $contentType The value of a Content-Type header-field
*/
public static function fromTransport(string $contentType): ?string {
// Try to sniff out a charset from a Content-Type header-field.
// This does cut some corners, but should be sufficient for practical use
$s = preg_replace("/\s+/", " ", strtolower($contentType));
$pos = 0;
$end = strlen($s);
// skip the type
while ($pos < $end && @$s[$pos++] !== "/");
// skip the subtype
while ($pos < $end && @$s[$pos++] !== ";");
// check parameters in sequence
while ($pos < $end) {
// skip any leading whitespace
if (@$s[$pos] === " ") {
$pos++;
}
// collect characters for the parameter name
$param = "";
while ($pos < $end && @$s[$pos] !== "=") {
$param .= @$s[$pos++];
}
// skip the equals sign
$pos++;
if ($s[$pos] === '"') {
// Value is a quoted-string
$pos++;
$value = "";
while (!in_array($c = @$s[$pos++], ['"', ""])) {
if ($c === "\\") {
$value .= @$s[$pos++];
} else {
$value .= $c;
}
}
// only interpret the value if a closing quotation mark was seen
if ($c !== '"') {
$value = "";
}
} else {
// Value is a bare token
$value = "";
while (!in_array($c = @$s[$pos++], [';', " ", ""])) {
$value .= $c;
}
}
// if the parameter was the character set, interpret its value and return
if ($param === "charset") {
$encoding = Encoding::matchLabel($value);
if ($encoding) {
return $encoding['name'];
} else {
return null;
}
$type = MimeType::parseBytes($contentType);
if ($type && isset($type->params['charset'])) {
$encoding = Encoding::matchLabel($type->params['charset']);
if ($encoding) {
return $encoding['name'];
}
}
return null;

Write Preview
Loading…
Cancel
Save