EmailLexer::moveNext() - Code Metrics - Inspection of "Bug #321" - egulias/EmailValidator - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — 3.x (#323)

by Eduardo Gulias

created 2022-05-28 22:00 UTC

EmailLexer::moveNext() A

↳ Parent: EmailLexer

Complexity

Conditions	5
Paths	8

Size

Total Lines	19
Code Lines	9

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	10
CRAP Score	5

Importance

Changes

Metric	Value
cc	5
eloc	9
nc	8
nop	0
dl	0
loc	19
ccs	10
cts	10
cp	1
crap	5
rs	9.6111
c	0
b	0
f	0

<?php

namespace Egulias\EmailValidator;

use Doctrine\Common\Lexer\AbstractLexer;

class EmailLexer extends AbstractLexer
{
    //ASCII values
    const S_EMPTY            = null;
    const C_NUL              = 0;
    const S_HTAB             = 9;
    const S_LF               = 10;
    const S_CR               = 13;
    const S_SP               = 32;
    const EXCLAMATION        = 33;
    const S_DQUOTE           = 34;
    const NUMBER_SIGN        = 35;
    const DOLLAR             = 36;
    const PERCENTAGE         = 37;
    const AMPERSAND          = 38;
    const S_SQUOTE           = 39;
    const S_OPENPARENTHESIS  = 40;
    const S_CLOSEPARENTHESIS = 41;
    const ASTERISK           = 42;
    const S_PLUS             = 43;
    const S_COMMA            = 44;
    const S_HYPHEN           = 45;
    const S_DOT              = 46;
    const S_SLASH            = 47;
    const S_COLON            = 58;
    const S_SEMICOLON        = 59;
    const S_LOWERTHAN        = 60;
    const S_EQUAL            = 61;
    const S_GREATERTHAN      = 62;
    const QUESTIONMARK       = 63;
    const S_AT               = 64;
    const S_OPENBRACKET      = 91;
    const S_BACKSLASH        = 92;
    const S_CLOSEBRACKET     = 93;
    const CARET              = 94;
    const S_UNDERSCORE       = 95;
    const S_BACKTICK         = 96;
    const S_OPENCURLYBRACES  = 123;
    const S_PIPE             = 124;
    const S_CLOSECURLYBRACES = 125;
    const S_TILDE            = 126;
    const C_DEL              = 127;
    const INVERT_QUESTIONMARK= 168;
    const INVERT_EXCLAMATION = 173;
    const GENERIC            = 300;
    const S_IPV6TAG          = 301;
    const INVALID            = 302;
    const CRLF               = 1310;
    const S_DOUBLECOLON      = 5858;
    const ASCII_INVALID_FROM = 127;
    const ASCII_INVALID_TO   = 199;

    /**
     * US-ASCII visible characters not valid for atext (@link http://tools.ietf.org/html/rfc5322#section-3.2.3)
     *
     * @var array
     */
    protected $charValue = [
        '{'    => self::S_OPENCURLYBRACES,
        '}'    => self::S_CLOSECURLYBRACES,
        '('    => self::S_OPENPARENTHESIS,
        ')'    => self::S_CLOSEPARENTHESIS,
        '<'    => self::S_LOWERTHAN,
        '>'    => self::S_GREATERTHAN,
        '['    => self::S_OPENBRACKET,
        ']'    => self::S_CLOSEBRACKET,
        ':'    => self::S_COLON,
        ';'    => self::S_SEMICOLON,
        '@'    => self::S_AT,
        '\\'   => self::S_BACKSLASH,
        '/'    => self::S_SLASH,
        ','    => self::S_COMMA,
        '.'    => self::S_DOT,
        "'"    => self::S_SQUOTE,
        "`"    => self::S_BACKTICK,
        '"'    => self::S_DQUOTE,
        '-'    => self::S_HYPHEN,
        '::'   => self::S_DOUBLECOLON,
        ' '    => self::S_SP,
        "\t"   => self::S_HTAB,
        "\r"   => self::S_CR,
        "\n"   => self::S_LF,
        "\r\n" => self::CRLF,
        'IPv6' => self::S_IPV6TAG,
        ''     => self::S_EMPTY,
        '\0'   => self::C_NUL,
        '*'    => self::ASTERISK,
        '!'    => self::EXCLAMATION,
        '&'    => self::AMPERSAND,
        '^'    => self::CARET,
        '$'    => self::DOLLAR,
        '%'    => self::PERCENTAGE,
        '~'    => self::S_TILDE,
        '|'    => self::S_PIPE,
        '_'    => self::S_UNDERSCORE,
        '='    => self::S_EQUAL,
        '+'    => self::S_PLUS,
        '¿'    => self::INVERT_QUESTIONMARK,
        '?'    => self::QUESTIONMARK,
        '#'    => self::NUMBER_SIGN,
        '¡'    => self::INVERT_EXCLAMATION,
    ];

    const INVALID_CHARS_REGEX = "/[^\p{S}\p{C}\p{Cc}]+/iu";

    const VALID_UTF8_REGEX = '/\p{Cc}+/u';

    const CATCHABLE_PATTERNS = [
        '[a-zA-Z]+[46]?', //ASCII and domain literal
        '[^\x00-\x7F]',  //UTF-8
        '[0-9]+',
        '\r\n',
        '::',
        '\s+?',
        '.',
    ];

    const NON_CATCHABLE_PATTERNS = [
        '[\xA0-\xff]+',
    ];

    const MODIFIERS = 'iu';

    /** @var bool */
    protected $hasInvalidTokens = false;

    /**
     * @var array
     *
     * @psalm-var array{value:string, type:null|int, position:int}|array<empty, empty>
     */
    protected $previous = [];

    /**
     * The last matched/seen token.
     *
     * @var array
     *
     * @psalm-suppress NonInvariantDocblockPropertyType
     * @psalm-var array{value:string, type:null|int, position:int}
     * @psalm-suppress NonInvariantDocblockPropertyType
     */
    public $token;

    /**
     * The next token in the input.
     *
     * @var array{position: int, type: int|null|string, value: int|string}|null
     */
    public $lookahead;

    /** @psalm-var array{value:'', type:null, position:0} */
    private static $nullToken = [
        'value' => '',
        'type' => null,
        'position' => 0,
    ];

    /** @var string */
    private $accumulator = '';

    /** @var bool */
    private $hasToRecord = false;

    public function __construct()
    {
        $this->previous = $this->token = self::$nullToken;
        $this->lookahead = null;
    }

    public function reset() : void
    {
        $this->hasInvalidTokens = false;
        parent::reset();
        $this->previous = $this->token = self::$nullToken;
    }

    /**
     * @param int $type
     * @throws \UnexpectedValueException
     * @return boolean
     *
     * @psalm-suppress InvalidScalarArgument
     */
    public function find($type) : bool
    {
        $search = clone $this;
        $search->skipUntil($type);

        if (!$search->lookahead) {
            throw new \UnexpectedValueException($type . ' not found');
        }
        return true;
    }

    /**
     * moveNext
     *
     * @return boolean
     */
    public function moveNext() : bool
    {
        if ($this->hasToRecord && $this->previous === self::$nullToken) {
            $this->accumulator .= $this->token['value'];
        }

        $this->previous = $this->token;
        
        if($this->lookahead === null) {
            $this->lookahead = self::$nullToken;
        }

        $hasNext = parent::moveNext();

        if ($this->hasToRecord) {
            $this->accumulator .= $this->token['value'];
        }

        return $hasNext;
    }

    /**
     * Retrieve token type. Also processes the token value if necessary.
     *
     * @param string $value
     * @throws \InvalidArgumentException
     * @return integer
     */
    protected function getType(&$value)
    {
        $encoded = $value;

        if (mb_detect_encoding($value, 'auto', true) !== 'UTF-8') {
            $encoded = utf8_encode($value);
        }

        if ($this->isValid($encoded)) {
            return $this->charValue[$encoded];
        }

        if ($this->isNullType($encoded)) {
            return self::C_NUL;
        }

        if ($this->isInvalidChar($encoded)) {
            $this->hasInvalidTokens = true;
            return self::INVALID;
        }


        return  self::GENERIC;
    }

    protected function isValid(string $value) : bool
    {
        return isset($this->charValue[$value]);
    }

    protected function isNullType(string $value) : bool
    {
        return $value === "\0";
    }

    protected function isInvalidChar(string $value) : bool
    {
        return !preg_match(self::INVALID_CHARS_REGEX, $value);
    }

    protected function isUTF8Invalid(string $value) : bool
    {
        return preg_match(self::VALID_UTF8_REGEX, $value) !== false;
    }

    public function hasInvalidTokens() : bool
    {
        return $this->hasInvalidTokens;
    }

    /**
     * getPrevious
     *
     * @return array
     */
    public function getPrevious() : array
    {
        return $this->previous;
    }

    /**
     * Lexical catchable patterns.
     *
     * @return string[]
     */
    protected function getCatchablePatterns() : array
    {
        return self::CATCHABLE_PATTERNS;
    }

    /**
     * Lexical non-catchable patterns.
     *
     * @return string[]
     */
    protected function getNonCatchablePatterns() : array
    {
        return self::NON_CATCHABLE_PATTERNS;
    }

    protected function getModifiers() : string
    {
        return self::MODIFIERS;
    }

    public function getAccumulatedValues() : string
    {
        return $this->accumulator;
    }

    public function startRecording() : void
    {
        $this->hasToRecord = true;
    }

    public function stopRecording() : void
    {
        $this->hasToRecord = false;
    }

    public function clearRecorded() : void
    {
        $this->accumulator = '';
    }
}


1		<?php
2
3		namespace Egulias\EmailValidator;
4
5		use Doctrine\Common\Lexer\AbstractLexer;
6
7		class EmailLexer extends AbstractLexer
8		{
9		//ASCII values
10		const S_EMPTY = null;
11		const C_NUL = 0;
12		const S_HTAB = 9;
13		const S_LF = 10;
14		const S_CR = 13;
15		const S_SP = 32;
16		const EXCLAMATION = 33;
17		const S_DQUOTE = 34;
18		const NUMBER_SIGN = 35;
19		const DOLLAR = 36;
20		const PERCENTAGE = 37;
21		const AMPERSAND = 38;
22		const S_SQUOTE = 39;
23		const S_OPENPARENTHESIS = 40;
24		const S_CLOSEPARENTHESIS = 41;
25		const ASTERISK = 42;
26		const S_PLUS = 43;
27		const S_COMMA = 44;
28		const S_HYPHEN = 45;
29		const S_DOT = 46;
30		const S_SLASH = 47;
31		const S_COLON = 58;
32		const S_SEMICOLON = 59;
33		const S_LOWERTHAN = 60;
34		const S_EQUAL = 61;
35		const S_GREATERTHAN = 62;
36		const QUESTIONMARK = 63;
37		const S_AT = 64;
38		const S_OPENBRACKET = 91;
39		const S_BACKSLASH = 92;
40		const S_CLOSEBRACKET = 93;
41		const CARET = 94;
42		const S_UNDERSCORE = 95;
43		const S_BACKTICK = 96;
44		const S_OPENCURLYBRACES = 123;
45		const S_PIPE = 124;
46		const S_CLOSECURLYBRACES = 125;
47		const S_TILDE = 126;
48		const C_DEL = 127;
49		const INVERT_QUESTIONMARK= 168;
50		const INVERT_EXCLAMATION = 173;
51		const GENERIC = 300;
52		const S_IPV6TAG = 301;
53		const INVALID = 302;
54		const CRLF = 1310;
55		const S_DOUBLECOLON = 5858;
56		const ASCII_INVALID_FROM = 127;
57		const ASCII_INVALID_TO = 199;
58
59		/**
60		* US-ASCII visible characters not valid for atext (@link http://tools.ietf.org/html/rfc5322#section-3.2.3)
61		*
62		* @var array
63		*/
64		protected $charValue = [
65		'{' => self::S_OPENCURLYBRACES,
66		'}' => self::S_CLOSECURLYBRACES,
67		'(' => self::S_OPENPARENTHESIS,
68		')' => self::S_CLOSEPARENTHESIS,
69		'<' => self::S_LOWERTHAN,
70		'>' => self::S_GREATERTHAN,
71		'[' => self::S_OPENBRACKET,
72		']' => self::S_CLOSEBRACKET,
73		':' => self::S_COLON,
74		';' => self::S_SEMICOLON,
75		'@' => self::S_AT,
76		'\\' => self::S_BACKSLASH,
77		'/' => self::S_SLASH,
78		',' => self::S_COMMA,
79		'.' => self::S_DOT,
80		"'" => self::S_SQUOTE,
81		"`" => self::S_BACKTICK,
82		'"' => self::S_DQUOTE,
83		'-' => self::S_HYPHEN,
84		'::' => self::S_DOUBLECOLON,
85		' ' => self::S_SP,
86		"\t" => self::S_HTAB,
87		"\r" => self::S_CR,
88		"\n" => self::S_LF,
89		"\r\n" => self::CRLF,
90		'IPv6' => self::S_IPV6TAG,
91		'' => self::S_EMPTY,
92		'\0' => self::C_NUL,
93		'*' => self::ASTERISK,
94		'!' => self::EXCLAMATION,
95		'&' => self::AMPERSAND,
96		'^' => self::CARET,
97		'$' => self::DOLLAR,
98		'%' => self::PERCENTAGE,
99		'~' => self::S_TILDE,
100		'\|' => self::S_PIPE,
101		'_' => self::S_UNDERSCORE,
102		'=' => self::S_EQUAL,
103		'+' => self::S_PLUS,
104		'¿' => self::INVERT_QUESTIONMARK,
105		'?' => self::QUESTIONMARK,
106		'#' => self::NUMBER_SIGN,
107		'¡' => self::INVERT_EXCLAMATION,
108		];
109
110		const INVALID_CHARS_REGEX = "/[^\p{S}\p{C}\p{Cc}]+/iu";
111
112		const VALID_UTF8_REGEX = '/\p{Cc}+/u';
113
114		const CATCHABLE_PATTERNS = [
115		'[a-zA-Z]+[46]?', //ASCII and domain literal
116		'[^\x00-\x7F]', //UTF-8
117		'[0-9]+',
118		'\r\n',
119		'::',
120		'\s+?',
121		'.',
122		];
123
124		const NON_CATCHABLE_PATTERNS = [
125		'[\xA0-\xff]+',
126		];
127
128		const MODIFIERS = 'iu';
129
130		/** @var bool */
131		protected $hasInvalidTokens = false;
132
133		/**
134		* @var array
135		*
136		* @psalm-var array{value:string, type:null\|int, position:int}\|array<empty, empty>
137		*/
138		protected $previous = [];
139
140		/**
141		* The last matched/seen token.
142		*
143		* @var array
144		*
145		* @psalm-suppress NonInvariantDocblockPropertyType
146		* @psalm-var array{value:string, type:null\|int, position:int}
147		* @psalm-suppress NonInvariantDocblockPropertyType
148		*/
149		public $token;
150
151		/**
152		* The next token in the input.
153		*
154		* @var array{position: int, type: int\|null\|string, value: int\|string}\|null
155		*/
156		public $lookahead;
157
158		/** @psalm-var array{value:'', type:null, position:0} */
159		private static $nullToken = [
160		'value' => '',
161		'type' => null,
162		'position' => 0,
163		];
164
165		/** @var string */
166		private $accumulator = '';
167
168		/** @var bool */
169		private $hasToRecord = false;
170
171	340	public function __construct()
172		{
173	340	$this->previous = $this->token = self::$nullToken;
174	340	$this->lookahead = null;
175		}
176
177	308	public function reset() : void
178		{
179	308	$this->hasInvalidTokens = false;
180	308	parent::reset();
181	308	$this->previous = $this->token = self::$nullToken;
182		}
183
184		/**
185		* @param int $type
186		* @throws \UnexpectedValueException
187		* @return boolean
188		*
189		* @psalm-suppress InvalidScalarArgument
190		*/
191	54	public function find($type) : bool
192		{
193	54	$search = clone $this;
194	54	$search->skipUntil($type);
195
196	54	if (!$search->lookahead) {
197	6	throw new \UnexpectedValueException($type . ' not found');
198		}
199	48	return true;
200		}
201
202		/**
203		* moveNext
204		*
205		* @return boolean
206		*/
207	297	public function moveNext() : bool
208		{
209	297	if ($this->hasToRecord && $this->previous === self::$nullToken) {
210	179	$this->accumulator .= $this->token['value'];
211		}
212
213	297	$this->previous = $this->token;
214
215	297	if($this->lookahead === null) {
216	297	$this->lookahead = self::$nullToken;
217		}
218
219	297	$hasNext = parent::moveNext();
220
221	297	if ($this->hasToRecord) {
222	179	$this->accumulator .= $this->token['value'];
223		}
224
225	297	return $hasNext;
226		}
227
228		/**
229		* Retrieve token type. Also processes the token value if necessary.
230		*
231		* @param string $value
232		* @throws \InvalidArgumentException
233		* @return integer
234		*/
235	300	protected function getType(&$value)
236		{
237	300	$encoded = $value;
238
239	300	if (mb_detect_encoding($value, 'auto', true) !== 'UTF-8') {
240	237	$encoded = utf8_encode($value);
241		}
242
243	300	if ($this->isValid($encoded)) {
244	229	return $this->charValue[$encoded];
245		}
246
247	262	if ($this->isNullType($encoded)) {
248	2	return self::C_NUL;
249		}
250
251	261	if ($this->isInvalidChar($encoded)) {
252	66	$this->hasInvalidTokens = true;
253	66	return self::INVALID;
254		}
255
256
257	199	return self::GENERIC;
258		}
259
260	300	protected function isValid(string $value) : bool
261		{
262	300	return isset($this->charValue[$value]);
263		}
264
265	262	protected function isNullType(string $value) : bool
266		{
267	262	return $value === "\0";
268		}
269
270	261	protected function isInvalidChar(string $value) : bool
271		{
272	261	return !preg_match(self::INVALID_CHARS_REGEX, $value);
273		}
274
275		protected function isUTF8Invalid(string $value) : bool
276		{
277		return preg_match(self::VALID_UTF8_REGEX, $value) !== false;
278		}
279
280	191	public function hasInvalidTokens() : bool
281		{
282	191	return $this->hasInvalidTokens;
283		}
284
285		/**
286		* getPrevious
287		*
288		* @return array
289		*/
290	178	public function getPrevious() : array
291		{
292	178	return $this->previous;
293		}
294
295		/**
296		* Lexical catchable patterns.
297		*
298		* @return string[]
299		*/
300	301	protected function getCatchablePatterns() : array
301		{
302	301	return self::CATCHABLE_PATTERNS;
303		}
304
305		/**
306		* Lexical non-catchable patterns.
307		*
308		* @return string[]
309		*/
310	301	protected function getNonCatchablePatterns() : array
311		{
312	301	return self::NON_CATCHABLE_PATTERNS;
313		}
314
315	301	protected function getModifiers() : string
316		{
317	301	return self::MODIFIERS;
318		}
319
320	151	public function getAccumulatedValues() : string
321		{
322	151	return $this->accumulator;
323		}
324
325	188	public function startRecording() : void
326		{
327	188	$this->hasToRecord = true;
328		}
329
330	148	public function stopRecording() : void
331		{
332	148	$this->hasToRecord = false;
333		}
334
335	149	public function clearRecorded() : void
336		{
337	149	$this->accumulator = '';
338		}
339		}
340

egulias / EmailValidator

Pull Request — 3.x (#323)

EmailLexer::moveNext() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like