ParsedText::decode() - Code Metrics - Inspection of "WiP" - s9e/TextFormatter - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Branch — wip/litedown (e88c6d)

by Josh

created 2017-10-22 21:43 UTC

ParsedText::decode() B

↳ Parent: ParsedText

Complexity

Conditions	4
Paths	4

Size

Total Lines	23
Code Lines	12

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	17
CRAP Score	4

Importance

Changes

Metric	Value
dl	0
loc	23
ccs	17
cts	17
cp	1
rs	8.7972
c	0
b	0
f	0
cc	4
eloc	12
nc	4
nop	1
crap	4

<?php

/**
* @package   s9e\TextFormatter
* @copyright Copyright (c) 2010-2017 The s9e Authors
* @license   http://www.opensource.org/licenses/mit-license.php The MIT License
*/
namespace s9e\TextFormatter\Plugins\Litedown\Parser;

class ParsedText
{
	/**
	* @var bool Whether to decode HTML entities when decoding text
	*/
	public $decodeHtmlEntities = false;

	/**
	* @var bool Whether text contains escape characters
	*/
	protected $hasEscapedChars = false;

	/**
	* @var bool Whether text contains link references
	*/
	public $hasReferences = false;

	/**
	* @var array Array of [label => link info]
	*/
	public $linkReferences = [];

	/**
	* @var string Text being parsed
	*/
	protected $text;

	/**
	* @param string $text Original text
	*/
	public function __construct($text)
	{
		if (strpos($text, '\\') !== false && preg_match('/\\\\[!"\'()*[\\\\\\]^_`~]/', $text))
		{
			$this->hasEscapedChars = true;

			// Encode escaped literals that have a special meaning otherwise, so that we don't have
			// to take them into account in regexps
			$text = strtr(
				$text,
				[
					'\\!' => "\x1B0", '\\"' => "\x1B1", "\\'" => "\x1B2", '\\('  => "\x1B3",
					'\\)' => "\x1B4", '\\*' => "\x1B5", '\\[' => "\x1B6", '\\\\' => "\x1B7",
					'\\]' => "\x1B8", '\\^' => "\x1B9", '\\_' => "\x1BA", '\\`'  => "\x1BB",
					'\\~' => "\x1BC"
				]
			);
		}

		// We append a couple of lines and a non-whitespace character at the end of the text in
		// order to trigger the closure of all open blocks such as quotes and lists
		$this->text = $text . "\n\n\x17";
	}

	/**
	* @return string
	*/
	public function __toString()
	{
		return $this->text;
	}

	/**
	* Return the character at given position
	*
	* @param  integer $pos
	* @return string
	*/
	public function charAt($pos)
	{
		return $this->text[$pos];
	}

	/**
	* Decode a chunk of encoded text to be used as an attribute value
	*
	* Decodes escaped literals and removes slashes and 0x1A characters
	*
	* @param  string $str Encoded text
	* @return string      Decoded text
	*/
	public function decode($str)
	{
		if ($this->decodeHtmlEntities && strpos($str, '&') !== false)
		{
			$str = html_entity_decode($str, ENT_QUOTES, 'UTF-8');
		}
		$str = str_replace("\x1A", '', $str);

		if ($this->hasEscapedChars)
		{
			$str = strtr(
				$str,
				[
					"\x1B0" => '!', "\x1B1" => '"', "\x1B2" => "'", "\x1B3" => '(',
					"\x1B4" => ')', "\x1B5" => '*', "\x1B6" => '[', "\x1B7" => '\\',
					"\x1B8" => ']', "\x1B9" => '^', "\x1BA" => '_', "\x1BB" => '`',
					"\x1BC" => '~'
				]
			);
		}

		return $str;
	}

	/**
	* Find the first occurence of given substring starting at given position
	*
	* @param  string       $str
	* @param  integer      $pos
	* @return bool|integer
	*/
	public function indexOf($str, $pos = 0)
	{
		return strpos($this->text, $str, $pos);
	}

	/**
	* Test whether given position is preceded by whitespace
	*
	* @param  integer $pos
	* @return bool
	*/
	public function isAfterWhitespace($pos)
	{
		return ($pos > 0 && $this->isWhitespace($this->text[$pos - 1]));
	}

	/**
	* Test whether given character is alphanumeric
	*
	* @param  string $chr
	* @return bool
	*/
	public function isAlnum($chr)
	{
		return (strpos(' abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789', $chr) > 0);
	}

	/**
	* Test whether given position is followed by whitespace
	*
	* @param  integer $pos
	* @return bool
	*/
	public function isBeforeWhitespace($pos)
	{
		return $this->isWhitespace($this->text[$pos + 1]);
	}

	/**
	* Test whether a length of text is surrounded by alphanumeric characters
	*
	* @param  integer $pos Start of the text
	* @param  integer $len Length of the text
	* @return bool
	*/
	public function isSurroundedByAlnum($pos, $len)
	{
		return ($pos > 0 && $this->isAlnum($this->text[$pos - 1]) && $this->isAlnum($this->text[$pos + $len]));
	}

	/**
	* Test whether given character is an ASCII whitespace character
	*
	* NOTE: newlines are normalized to LF before parsing so we don't have to check for CR
	*
	* @param  string $chr
	* @return bool
	*/
	public function isWhitespace($chr)
	{
		return (strpos(" \n\t", $chr) !== false);
	}

	/**
	* Mark the boundary of a block in the original text
	*
	* @param  integer $pos
	* @return void
	*/
	public function markBoundary($pos)
	{
		$this->text[$pos] = "\x17";
	}

	/**
	* Overwrite part of the text with substitution characters ^Z (0x1A)
	*
	* @param  integer $pos Start of the range
	* @param  integer $len Length of text to overwrite
	* @return void
	*/
	public function overwrite($pos, $len)
	{
		if ($len > 0)
		{
			$this->text = substr($this->text, 0, $pos) . str_repeat("\x1A", $len) . substr($this->text, $pos + $len);
		}
	}
}

1		<?php
2
3		/**
4		* @package s9e\TextFormatter
5		* @copyright Copyright (c) 2010-2017 The s9e Authors
6		* @license http://www.opensource.org/licenses/mit-license.php The MIT License
7		*/
8		namespace s9e\TextFormatter\Plugins\Litedown\Parser;
9
10		class ParsedText
11		{
12		/**
13		* @var bool Whether to decode HTML entities when decoding text
14		*/
15		public $decodeHtmlEntities = false;
16
17		/**
18		* @var bool Whether text contains escape characters
19		*/
20		protected $hasEscapedChars = false;
21
22		/**
23		* @var bool Whether text contains link references
24		*/
25		public $hasReferences = false;
26
27		/**
28		* @var array Array of [label => link info]
29		*/
30		public $linkReferences = [];
31
32		/**
33		* @var string Text being parsed
34		*/
35		protected $text;
36
37		/**
38		* @param string $text Original text
39		*/
40	263	public function __construct($text)
41		{
42	263	if (strpos($text, '\\') !== false && preg_match('/\\\\[!"\'()*[\\\\\\]^_`~]/', $text))
43	263	{
44	15	$this->hasEscapedChars = true;
45
46		// Encode escaped literals that have a special meaning otherwise, so that we don't have
47		// to take them into account in regexps
48	15	$text = strtr(
49	15	$text,
50		[
51	15	'\\!' => "\x1B0", '\\"' => "\x1B1", "\\'" => "\x1B2", '\\(' => "\x1B3",
52	15	'\\)' => "\x1B4", '\\*' => "\x1B5", '\\[' => "\x1B6", '\\\\' => "\x1B7",
53	15	'\\]' => "\x1B8", '\\^' => "\x1B9", '\\_' => "\x1BA", '\\`' => "\x1BB",
54		'\\~' => "\x1BC"
55	15	]
56	15	);
57	15	}
58
59		// We append a couple of lines and a non-whitespace character at the end of the text in
60		// order to trigger the closure of all open blocks such as quotes and lists
61	263	$this->text = $text . "\n\n\x17";
62	263	}
63
64		/**
65		* @return string
66		*/
67	263	public function __toString()
68		{
69	263	return $this->text;
70		}
71
72		/**
73		* Return the character at given position
74		*
75		* @param integer $pos
76		* @return string
77		*/
78	130	public function charAt($pos)
79		{
80	130	return $this->text[$pos];
81		}
82
83		/**
84		* Decode a chunk of encoded text to be used as an attribute value
85		*
86		* Decodes escaped literals and removes slashes and 0x1A characters
87		*
88		* @param string $str Encoded text
89		* @return string Decoded text
90		*/
91	69	public function decode($str)
92		{
93	69	if ($this->decodeHtmlEntities && strpos($str, '&') !== false)
94	69	{
95	1	$str = html_entity_decode($str, ENT_QUOTES, 'UTF-8');
96	1	}
97	69	$str = str_replace("\x1A", '', $str);
98
99	69	if ($this->hasEscapedChars)
100	69	{
101	7	$str = strtr(
102	7	$str,
103		[
104	7	"\x1B0" => '!', "\x1B1" => '"', "\x1B2" => "'", "\x1B3" => '(',
105	7	"\x1B4" => ')', "\x1B5" => '*', "\x1B6" => '[', "\x1B7" => '\\',
106	7	"\x1B8" => ']', "\x1B9" => '^', "\x1BA" => '_', "\x1BB" => '`',
107		"\x1BC" => '~'
108	7	]
109	7	);
110	7	}
111
112	69	return $str;
113		}
114
115		/**
116		* Find the first occurence of given substring starting at given position
117		*
118		* @param string $str
119		* @param integer $pos
120		* @return bool\|integer
121		*/
122	263	public function indexOf($str, $pos = 0)
123		{
124	263	return strpos($this->text, $str, $pos);
125		}
126
127		/**
128		* Test whether given position is preceded by whitespace
129		*
130		* @param integer $pos
131		* @return bool
132		*/
133	59	public function isAfterWhitespace($pos)
134		{
135	59	return ($pos > 0 && $this->isWhitespace($this->text[$pos - 1]));
136		}
137
138		/**
139		* Test whether given character is alphanumeric
140		*
141		* @param string $chr
142		* @return bool
143		*/
144	8	public function isAlnum($chr)
145		{
146	8	return (strpos(' abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789', $chr) > 0);
147		}
148
149		/**
150		* Test whether given position is followed by whitespace
151		*
152		* @param integer $pos
153		* @return bool
154		*/
155	59	public function isBeforeWhitespace($pos)
156		{
157	59	return $this->isWhitespace($this->text[$pos + 1]);
158		}
159
160		/**
161		* Test whether a length of text is surrounded by alphanumeric characters
162		*
163		* @param integer $pos Start of the text
164		* @param integer $len Length of the text
165		* @return bool
166		*/
167	8	public function isSurroundedByAlnum($pos, $len)
168		{
169	8	return ($pos > 0 && $this->isAlnum($this->text[$pos - 1]) && $this->isAlnum($this->text[$pos + $len]));
170		}
171
172		/**
173		* Test whether given character is an ASCII whitespace character
174		*
175		* NOTE: newlines are normalized to LF before parsing so we don't have to check for CR
176		*
177		* @param string $chr
178		* @return bool
179		*/
180	59	public function isWhitespace($chr)
181		{
182	59	return (strpos(" \n\t", $chr) !== false);
183		}
184
185		/**
186		* Mark the boundary of a block in the original text
187		*
188		* @param integer $pos
189		* @return void
190		*/
191	263	public function markBoundary($pos)
192		{
193	263	$this->text[$pos] = "\x17";
194	263	}
195
196		/**
197		* Overwrite part of the text with substitution characters ^Z (0x1A)
198		*
199		* @param integer $pos Start of the range
200		* @param integer $len Length of text to overwrite
201		* @return void
202		*/
203	169	public function overwrite($pos, $len)
204		{
205	169	if ($len > 0)
206	169	{
207	169	$this->text = substr($this->text, 0, $pos) . str_repeat("\x1A", $len) . substr($this->text, $pos + $len);
208	169	}
209		}
210		}

s9e / TextFormatter

Branch — wip/litedown (e88c6d)

ParsedText::decode() B

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like