PHPSQLLexer::balanceMultilineComments() - Code Metrics - thecodingmachine/magic-query - Measure and Improve Code Quality continuously with Scrutinizer

PHPSQLLexer::balanceMultilineComments() C
last analyzed 2016-08-17 10:37 UTC

↳ Parent: PHPSQLLexer

Complexity

Conditions	11
Paths	11

Size

Total Lines	39
Code Lines	25

Duplication

Lines	9
Ratio	23.08 %

Importance

Changes	2
Bugs	0	Features	0

Metric	Value
c	2
b	0
f	0
dl	9
loc	39
rs	5.2653
cc	11
eloc	25
nc	11
nop	1

How to fix Complexity

<?php

/**
 * lexer.php.
 *
 * This file contains the lexer, which splits the SQL statement just before parsing.
 *
 * Copyright (c) 2010-2012, Justin Swanhart
 * with contributions by André Rothe <[email protected], [email protected]>
 *
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without modification,
 * are permitted provided that the following conditions are met:
 *
 *   * Redistributions of source code must retain the above copyright notice,
 *     this list of conditions and the following disclaimer.
 *   * Redistributions in binary form must reproduce the above copyright notice,
 *     this list of conditions and the following disclaimer in the documentation
 *     and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT
 * SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
 * TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
 * DAMAGE.
 */
namespace SQLParser;

/**
 * This class splits the SQL string into little parts, which the parser can
 * use to build the result array.
 *
 * @author arothe
 */
class PHPSQLLexer extends PHPSQLParserUtils
{
    private $splitters;

    public function __construct()
    {
        $this->splitters = new LexerSplitter();
    }

    public function split($sql)
    {
        if (!is_string($sql)) {
            throw new InvalidParameterException($sql);
        }

        $tokens = array();
        $token = '';

        $splitLen = $this->splitters->getMaxLengthOfSplitter();
        $found = false;
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}
        $len = strlen($sql);
        $pos = 0;

        while ($pos < $len) {
            for ($i = $splitLen; $i > 0; --$i) {
                $substr = substr($sql, $pos, $i);
                if ($this->splitters->isSplitter($substr)) {
                    if ($token !== '') {
                        $tokens[] = $token;
                    }

                    $tokens[] = $substr;
                    $pos += $i;
                    $token = '';

                    continue 2;
                }
            }

            $token .= $sql[$pos];
            ++$pos;
        }

        if ($token !== '') {
            $tokens[] = $token;
        }

        $tokens = $this->concatEscapeSequences($tokens);
        $tokens = $this->balanceBackticks($tokens);
        $tokens = $this->concatColReferences($tokens);
        $tokens = $this->balanceParenthesis($tokens);
        $tokens = $this->balanceMultilineComments($tokens);
        $tokens = $this->concatInlineComments($tokens);
        $tokens = $this->concatUserDefinedVariables($tokens);

        return $tokens;
    }

    private function concatUserDefinedVariables($tokens)
    {
        $i = 0;
        $cnt = count($tokens);
        $userdef = false;

        while ($i < $cnt) {
            if (!isset($tokens[$i])) {
                ++$i;
                continue;
            }

            $token = $tokens[$i];

            if ($userdef !== false) {

                $tokens[$userdef] .= $token;
                unset($tokens[$i]);
                if ($token !== '@') {
                    $userdef = false;
                }
            }

            if ($userdef === false && $token === '@') {
                $userdef = $i;
            }

            ++$i;
        }

        return array_values($tokens);
    }

    private function concatInlineComments($tokens)
    {
        $i = 0;
        $cnt = count($tokens);
        $comment = false;

        while ($i < $cnt) {
            if (!isset($tokens[$i])) {
                ++$i;
                continue;
            }

            $token = $tokens[$i];

            if ($comment !== false) {

                if ($token === "\n" || $token === "\r\n") {
                    $comment = false;
                } else {
                    unset($tokens[$i]);
                    $tokens[$comment] .= $token;
                }
            }

            if (($comment === false) && ($token === '-')) {

                if (isset($tokens[$i + 1]) && $tokens[$i + 1] === '-') {
                    $comment = $i;
                    $tokens[$i] = '--';
                    ++$i;
                    unset($tokens[$i]);
                    continue;
                }
            }

            ++$i;
        }

        return array_values($tokens);
    }

    private function balanceMultilineComments($tokens)
    {
        $i = 0;
        $cnt = count($tokens);
        $comment = false;

        while ($i < $cnt) {
            if (!isset($tokens[$i])) {
                ++$i;
                continue;
            }

            $token = $tokens[$i];

            if ($comment !== false) {
                unset($tokens[$i]);
                $tokens[$comment] .= $token;
                if ($token === '*' && isset($tokens[$i + 1]) && $tokens[$i + 1] === '/') {
                    unset($tokens[$i + 1]);
                    $tokens[$comment] .= '/';
                    $comment = false;
                }
            }

            if (($comment === false) && ($token === '/')) {

                if (isset($tokens[$i + 1]) && $tokens[$i + 1] === '*') {
                    $comment = $i;
                    $tokens[$i] = '/*';
                    ++$i;
                    unset($tokens[$i]);
                    continue;
                }
            }

            ++$i;
        }

        return array_values($tokens);
    }

    private function isBacktick($token)
    {
        return ($token === "'" || $token === '"' || $token === '`');
    }

    private function balanceBackticks($tokens)
    {
        $i = 0;
        $cnt = count($tokens);
        while ($i < $cnt) {
            if (!isset($tokens[$i])) {
                ++$i;
                continue;
            }

            $token = $tokens[$i];

            if ($this->isBacktick($token)) {
                $tokens = $this->balanceCharacter($tokens, $i, $token);
            }

            ++$i;
        }

        return $tokens;
    }

    # backticks are not balanced within one token, so we have
    # to re-combine some tokens
    private function balanceCharacter($tokens, $idx, $char)
    {
        $token_count = count($tokens);
        $i = $idx + 1;
        while ($i < $token_count) {
            if (!isset($tokens[$i])) {
                ++$i;
                continue;
            }

            $token = $tokens[$i];
            $tokens[$idx] .= $token;
            unset($tokens[$i]);

            if ($token === $char) {
                break;
            }

            ++$i;
        }

        return array_values($tokens);
    }

    /*
     * does the token ends with dot?
     * concat it with the next token
     *
     * does the token starts with a dot?
     * concat it with the previous token
     */
    private function concatColReferences($tokens)
    {
        $cnt = count($tokens);
        $i = 0;
        while ($i < $cnt) {
            if (!isset($tokens[$i])) {
                ++$i;
                continue;
            }

            if ($tokens[$i][0] === '.') {

                // concat the previous tokens, till the token has been changed
                $k = $i - 1;
                $len = strlen($tokens[$i]);
                while (($k >= 0) && ($len == strlen($tokens[$i]))) {
                    if (!isset($tokens[$k])) { # FIXME: this can be wrong if we have schema . table . column
                        --$k;
                        continue;
                    }
                    $tokens[$i] = $tokens[$k].$tokens[$i];
                    unset($tokens[$k]);
                    --$k;
                }
            }

            if ($this->endsWith($tokens[$i], '.')) {

                // concat the next tokens, till the token has been changed
                $k = $i + 1;
                $len = strlen($tokens[$i]);
                while (($k < $cnt) && ($len == strlen($tokens[$i]))) {
                    if (!isset($tokens[$k])) {
                        ++$k;
                        continue;
                    }
                    $tokens[$i] .= $tokens[$k];
                    unset($tokens[$k]);
                    ++$k;
                }
            }

            ++$i;
        }

        return array_values($tokens);
    }

    private function concatEscapeSequences($tokens)
    {
        $tokenCount = count($tokens);
        $i = 0;
        while ($i < $tokenCount) {
            if ($this->endsWith($tokens[$i], '\\')) {
                ++$i;
                if (isset($tokens[$i])) {
                    $tokens[$i - 1] .= $tokens[$i];
                    unset($tokens[$i]);
                }
            }
            ++$i;
        }

        return array_values($tokens);
    }

    private function balanceParenthesis($tokens)
    {
        $token_count = count($tokens);
        $i = 0;
        while ($i < $token_count) {
            if ($tokens[$i] !== '(') {
                ++$i;
                continue;
            }
            $count = 1;
            for ($n = $i + 1; $n < $token_count; ++$n) {
                $token = $tokens[$n];
                if ($token === '(') {
                    ++$count;
                }
                if ($token === ')') {
                    --$count;
                }
                $tokens[$i] .= $token;
                unset($tokens[$n]);
                if ($count === 0) {
                    ++$n;
                    break;
                }
            }
            $i = $n;
        }

        return array_values($tokens);
    }
}


1		<?php
2
3		/**
4		* lexer.php.
5		*
6		* This file contains the lexer, which splits the SQL statement just before parsing.
7		*
8		* Copyright (c) 2010-2012, Justin Swanhart
9		* with contributions by André Rothe <[email protected], [email protected]>
10		*
11		* All rights reserved.
12		*
13		* Redistribution and use in source and binary forms, with or without modification,
14		* are permitted provided that the following conditions are met:
15		*
16		* * Redistributions of source code must retain the above copyright notice,
17		* this list of conditions and the following disclaimer.
18		* * Redistributions in binary form must reproduce the above copyright notice,
19		* this list of conditions and the following disclaimer in the documentation
20		* and/or other materials provided with the distribution.
21		*
22		* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
23		* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
24		* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT
25		* SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
26		* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
27		* TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
28		* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
29		* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
30		* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
31		* DAMAGE.
32		*/
33		namespace SQLParser;
34
35		/**
36		* This class splits the SQL string into little parts, which the parser can
37		* use to build the result array.
38		*
39		* @author arothe
40		*/
41		class PHPSQLLexer extends PHPSQLParserUtils
42		{
43		private $splitters;
44
45		public function __construct()
46		{
47		$this->splitters = new LexerSplitter();
48		}
49
50		public function split($sql)
51		{
52		if (!is_string($sql)) {
53		throw new InvalidParameterException($sql);
54		}
55
56		$tokens = array();
57		$token = '';
58
59		$splitLen = $this->splitters->getMaxLengthOfSplitter();
60		$found = false;
		0 ignored issues – show Unused Code introduced 2015-12-08 18:20 UTC by Report Bug Copy Issue Report `$found` is not used, you could remove the assignment. This check looks for variable assignements that are either overwritten by other assignments or where the variable is not used subsequently. $myVar = 'Value'; $higher = false; if (rand(1, 6) > 3) { $higher = true; } else { $higher = false; } Both the `$myVar` assignment in line 1 and the `$higher` assignment in line 2 are dead. The first because `$myVar` is never used and the second because `$higher` is always overwritten for every possible time line. Loading history...
61		$len = strlen($sql);
62		$pos = 0;
63
64		while ($pos < $len) {
65		for ($i = $splitLen; $i > 0; --$i) {
66		$substr = substr($sql, $pos, $i);
67		if ($this->splitters->isSplitter($substr)) {
68		if ($token !== '') {
69		$tokens[] = $token;
70		}
71
72		$tokens[] = $substr;
73		$pos += $i;
74		$token = '';
75
76		continue 2;
77		}
78		}
79
80		$token .= $sql[$pos];
81		++$pos;
82		}
83
84		if ($token !== '') {
85		$tokens[] = $token;
86		}
87
88		$tokens = $this->concatEscapeSequences($tokens);
89		$tokens = $this->balanceBackticks($tokens);
90		$tokens = $this->concatColReferences($tokens);
91		$tokens = $this->balanceParenthesis($tokens);
92		$tokens = $this->balanceMultilineComments($tokens);
93		$tokens = $this->concatInlineComments($tokens);
94		$tokens = $this->concatUserDefinedVariables($tokens);
95
96		return $tokens;
97		}
98
99		private function concatUserDefinedVariables($tokens)
100		{
101		$i = 0;
102		$cnt = count($tokens);
103		$userdef = false;
104
105		while ($i < $cnt) {
106		if (!isset($tokens[$i])) {
107		++$i;
108		continue;
109		}
110
111		$token = $tokens[$i];
112
113	View Code Duplication	if ($userdef !== false) {
		0 ignored issues – show Duplication introduced 2015-12-08 18:20 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
114		$tokens[$userdef] .= $token;
115		unset($tokens[$i]);
116		if ($token !== '@') {
117		$userdef = false;
118		}
119		}
120
121		if ($userdef === false && $token === '@') {
122		$userdef = $i;
123		}
124
125		++$i;
126		}
127
128		return array_values($tokens);
129		}
130
131		private function concatInlineComments($tokens)
132		{
133		$i = 0;
134		$cnt = count($tokens);
135		$comment = false;
136
137		while ($i < $cnt) {
138		if (!isset($tokens[$i])) {
139		++$i;
140		continue;
141		}
142
143		$token = $tokens[$i];
144
145	View Code Duplication	if ($comment !== false) {
		0 ignored issues – show Duplication introduced 2015-12-08 18:20 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
146		if ($token === "\n" \|\| $token === "\r\n") {
147		$comment = false;
148		} else {
149		unset($tokens[$i]);
150		$tokens[$comment] .= $token;
151		}
152		}
153
154	View Code Duplication	if (($comment === false) && ($token === '-')) {
		0 ignored issues – show Duplication introduced 2015-12-08 18:20 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
155		if (isset($tokens[$i + 1]) && $tokens[$i + 1] === '-') {
156		$comment = $i;
157		$tokens[$i] = '--';
158		++$i;
159		unset($tokens[$i]);
160		continue;
161		}
162		}
163
164		++$i;
165		}
166
167		return array_values($tokens);
168		}
169
170		private function balanceMultilineComments($tokens)
171		{
172		$i = 0;
173		$cnt = count($tokens);
174		$comment = false;
175
176		while ($i < $cnt) {
177		if (!isset($tokens[$i])) {
178		++$i;
179		continue;
180		}
181
182		$token = $tokens[$i];
183
184		if ($comment !== false) {
185		unset($tokens[$i]);
186		$tokens[$comment] .= $token;
187		if ($token === '*' && isset($tokens[$i + 1]) && $tokens[$i + 1] === '/') {
188		unset($tokens[$i + 1]);
189		$tokens[$comment] .= '/';
190		$comment = false;
191		}
192		}
193
194	View Code Duplication	if (($comment === false) && ($token === '/')) {
		0 ignored issues – show Duplication introduced 2015-12-08 18:20 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
195		if (isset($tokens[$i + 1]) && $tokens[$i + 1] === '*') {
196		$comment = $i;
197		$tokens[$i] = '/*';
198		++$i;
199		unset($tokens[$i]);
200		continue;
201		}
202		}
203
204		++$i;
205		}
206
207		return array_values($tokens);
208		}
209
210		private function isBacktick($token)
211		{
212		return ($token === "'" \|\| $token === '"' \|\| $token === '`');
213		}
214
215		private function balanceBackticks($tokens)
216		{
217		$i = 0;
218		$cnt = count($tokens);
219		while ($i < $cnt) {
220		if (!isset($tokens[$i])) {
221		++$i;
222		continue;
223		}
224
225		$token = $tokens[$i];
226
227		if ($this->isBacktick($token)) {
228		$tokens = $this->balanceCharacter($tokens, $i, $token);
229		}
230
231		++$i;
232		}
233
234		return $tokens;
235		}
236
237		# backticks are not balanced within one token, so we have
238		# to re-combine some tokens
239		private function balanceCharacter($tokens, $idx, $char)
240		{
241		$token_count = count($tokens);
242		$i = $idx + 1;
243		while ($i < $token_count) {
244		if (!isset($tokens[$i])) {
245		++$i;
246		continue;
247		}
248
249		$token = $tokens[$i];
250		$tokens[$idx] .= $token;
251		unset($tokens[$i]);
252
253		if ($token === $char) {
254		break;
255		}
256
257		++$i;
258		}
259
260		return array_values($tokens);
261		}
262
263		/*
264		* does the token ends with dot?
265		* concat it with the next token
266		*
267		* does the token starts with a dot?
268		* concat it with the previous token
269		*/
270		private function concatColReferences($tokens)
271		{
272		$cnt = count($tokens);
273		$i = 0;
274		while ($i < $cnt) {
275		if (!isset($tokens[$i])) {
276		++$i;
277		continue;
278		}
279
280		if ($tokens[$i][0] === '.') {
281
282		// concat the previous tokens, till the token has been changed
283		$k = $i - 1;
284		$len = strlen($tokens[$i]);
285		while (($k >= 0) && ($len == strlen($tokens[$i]))) {
286		if (!isset($tokens[$k])) { # FIXME: this can be wrong if we have schema . table . column
287		--$k;
288		continue;
289		}
290		$tokens[$i] = $tokens[$k].$tokens[$i];
291		unset($tokens[$k]);
292		--$k;
293		}
294		}
295
296		if ($this->endsWith($tokens[$i], '.')) {
297
298		// concat the next tokens, till the token has been changed
299		$k = $i + 1;
300		$len = strlen($tokens[$i]);
301		while (($k < $cnt) && ($len == strlen($tokens[$i]))) {
302		if (!isset($tokens[$k])) {
303		++$k;
304		continue;
305		}
306		$tokens[$i] .= $tokens[$k];
307		unset($tokens[$k]);
308		++$k;
309		}
310		}
311
312		++$i;
313		}
314
315		return array_values($tokens);
316		}
317
318		private function concatEscapeSequences($tokens)
319		{
320		$tokenCount = count($tokens);
321		$i = 0;
322		while ($i < $tokenCount) {
323		if ($this->endsWith($tokens[$i], '\\')) {
324		++$i;
325		if (isset($tokens[$i])) {
326		$tokens[$i - 1] .= $tokens[$i];
327		unset($tokens[$i]);
328		}
329		}
330		++$i;
331		}
332
333		return array_values($tokens);
334		}
335
336		private function balanceParenthesis($tokens)
337		{
338		$token_count = count($tokens);
339		$i = 0;
340		while ($i < $token_count) {
341		if ($tokens[$i] !== '(') {
342		++$i;
343		continue;
344		}
345		$count = 1;
346		for ($n = $i + 1; $n < $token_count; ++$n) {
347		$token = $tokens[$n];
348		if ($token === '(') {
349		++$count;
350		}
351		if ($token === ')') {
352		--$count;
353		}
354		$tokens[$i] .= $token;
355		unset($tokens[$n]);
356		if ($count === 0) {
357		++$n;
358		break;
359		}
360		}
361		$i = $n;
362		}
363
364		return array_values($tokens);
365		}
366		}
367

thecodingmachine / magic-query

PHPSQLLexer::balanceMultilineComments() C last analyzed 2016-08-17 10:37 UTC

Complexity

Size

Duplication

Importance

How to fix Complexity

Long Method

Duplication Side-by-Side

Filter issues like

PHPSQLLexer::balanceMultilineComments() C
last analyzed 2016-08-17 10:37 UTC