ListDiffNew::diffLists() - Code Metrics - Inspection of "New Feature: Table Diffing" - caxy/php-htmldiff - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#31)

by Josh

created 2016-02-23 22:08 UTC

ListDiffNew::diffLists() F

↳ Parent: ListDiffNew

Complexity

Conditions	27
Paths	528

Size

Total Lines	121
Code Lines	72

Duplication

Lines	5
Ratio	4.13 %

Code Coverage

Tests	76
CRAP Score	27.8657

Importance

Changes	2
Bugs	2	Features	0

Metric	Value
c	2
b	2
f	0
dl	5
loc	121
ccs	76
cts	85
cp	0.8941
rs	2.7195
cc	27
eloc	72
nc	528
nop	2
crap	27.8657

How to fix Long Method Complexity

<?php

namespace Caxy\HtmlDiff;

use Caxy\HtmlDiff\ListDiff\DiffList;
use Caxy\HtmlDiff\ListDiff\DiffListItem;

class ListDiffNew extends AbstractDiff
{
    protected static $listTypes = array('ul', 'ol', 'dl');

    public function build()
    {
        $this->splitInputsToWords();

        return $this->diffLists(
            $this->buildDiffList($this->oldWords),
            $this->buildDiffList($this->newWords)
        );
    }

    protected function diffLists(DiffList $oldList, DiffList $newList)
    {
        $oldMatchData = array();
        $newMatchData = array();
        $oldListIndices = array();
        $newListIndices = array();
        $oldListItems = array();
        $newListItems = array();

        foreach ($oldList->getListItems() as $oldIndex => $oldListItem) {
            if ($oldListItem instanceof DiffListItem) {
                $oldListItems[$oldIndex] = $oldListItem;

                $oldListIndices[] = $oldIndex;
                $oldMatchData[$oldIndex] = array();

                // Get match percentages
                foreach ($newList->getListItems() as $newIndex => $newListItem) {
                    if ($newListItem instanceof DiffListItem) {
                        if (!in_array($newListItem, $newListItems)) {
                            $newListItems[$newIndex] = $newListItem;
                        }
                        if (!in_array($newIndex, $newListIndices)) {
                            $newListIndices[] = $newIndex;
                        }
                        if (!array_key_exists($newIndex, $newMatchData)) {
                            $newMatchData[$newIndex] = array();
                        }

                        $oldText = implode('', $oldListItem->getText());
                        $newText = implode('', $newListItem->getText());

                        // similar_text
                        $percentage = null;
                        similar_text($oldText, $newText, $percentage);

                        $oldMatchData[$oldIndex][$newIndex] = $percentage;
                        $newMatchData[$newIndex][$oldIndex] = $percentage;
                    }
                }
            }
        }

        $currentIndexInOld = 0;
        $currentIndexInNew = 0;
        $oldCount = count($oldListIndices);
        $newCount = count($newListIndices);
        $difference = max($oldCount, $newCount) - min($oldCount, $newCount);

        $diffOutput = '';

        foreach ($newList->getListItems() as $newIndex => $newListItem) {
            if ($newListItem instanceof DiffListItem) {
                $operation = null;
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}

                $oldListIndex = array_key_exists($currentIndexInOld, $oldListIndices) ? $oldListIndices[$currentIndexInOld] : null;

                $class = 'normal';
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}

                if (null !== $oldListIndex && array_key_exists($oldListIndex, $oldMatchData)) {
                    // Check percentage matches of upcoming list items in old.
                    $matchPercentage = $oldMatchData[$oldListIndex][$newIndex];

                    // does the old list item match better?
                    $otherMatchBetter = false;
                    foreach ($oldMatchData[$oldListIndex] as $index => $percentage) {

                        if ($index > $newIndex && $percentage > $matchPercentage) {
                            $otherMatchBetter = $index;
                        }
                    }

                    if (false !== $otherMatchBetter && $newCount > $oldCount && $difference > 0) {
                        $diffOutput .= sprintf('%s', $newListItem->getHtml('normal new', 'ins'));
                        $currentIndexInNew++;
                        $difference--;

                        continue;
                    }

                    $nextOldListIndex = array_key_exists($currentIndexInOld + 1, $oldListIndices) ? $oldListIndices[$currentIndexInOld + 1] : null;


                    $replacement = false;

                    if ($nextOldListIndex !== null && $oldMatchData[$nextOldListIndex][$newIndex] > $matchPercentage && $oldMatchData[$nextOldListIndex][$newIndex] > $this->matchThreshold) {

                        // Following list item in old is better match, use that.
                        $diffOutput .= sprintf('%s', $oldListItems[$oldListIndex]->getHtml('removed', 'del'));

                        $currentIndexInOld++;
                        $oldListIndex = $nextOldListIndex;
                        $matchPercentage = $oldMatchData[$oldListIndex];
                        $replacement = true;
                    }

                    if ($matchPercentage > $this->matchThreshold || $currentIndexInNew === $currentIndexInOld) {
                        // Diff the two lists.
                        $htmlDiff = new HtmlDiff($oldListItems[$oldListIndex]->getInnerHtml(), $newListItem->getInnerHtml(), $this->encoding, $this->specialCaseTags, $this->groupDiffs);

                        $diffContent = $htmlDiff->build();

                        $diffOutput .= sprintf('%s%s%s', $newListItem->getStartTagWithDiffClass($replacement ? 'replacement' : 'normal'), $diffContent, $newListItem->getEndTag());


                    } else {
                        $diffOutput .= sprintf('%s', $oldListItems[$oldListIndex]->getHtml('removed', 'del'));
                        $diffOutput .= sprintf('%s', $newListItem->getHtml('replacement', 'ins'));
                    }
                    $currentIndexInOld++;
                } else {
                    $diffOutput .= sprintf('%s', $newListItem->getHtml('normal new', 'ins'));
                }

                $currentIndexInNew++;
            }
        }

        // Output any additional list items
        while (array_key_exists($currentIndexInOld, $oldListIndices)) {
            $oldListIndex = $oldListIndices[$currentIndexInOld];
            $diffOutput .= sprintf('%s', $oldListItems[$oldListIndex]->getHtml('removed', 'del'));
            $currentIndexInOld++;
        }

        return sprintf('%s%s%s', $newList->getStartTagWithDiffClass(), $diffOutput, $newList->getEndTag());
    }

    protected function buildDiffList($words)
    {
        $listType = null;
        $listStartTag = null;
        $listEndTag = null;
        $attributes = array();
        $openLists = 0;
        $openListItems = 0;
        $list = array();
        $currentListItem = null;
        $listItemType = null;
        $listItemStart = null;
        $listItemEnd = null;
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}

        foreach ($words as $i => $word) {
            if ($this->isOpeningListTag($word, $listType)) {
                if ($openLists > 0) {
                    if ($openListItems > 0) {
                        $currentListItem[] = $word;
                    } else {
                        $list[] = $word;
                    }
                } else {
                    $listType = substr($word, 1, 2);
                    $listStartTag = $word;
                }

                $openLists++;
            } elseif ($this->isClosingListTag($word, $listType)) {
                if ($openLists > 1) {
                    if ($openListItems > 0) {
                        $currentListItem[] = $word;
                    } else {
                        $list[] = $word;
                    }
                } else {
                    $listEndTag = $word;
                }

                $openLists--;
            } elseif ($this->isOpeningListItemTag($word, $listItemType)) {
                if ($openListItems === 0) {
                    // New top-level list item
                    $currentListItem = array();
                    $listItemType = substr($word, 1, 2);
                    $listItemStart = $word;
                } else {
                    $currentListItem[] = $word;
                }

                $openListItems++;
            } elseif ($this->isClosingListItemTag($word, $listItemType)) {
                if ($openListItems === 1) {
                    $listItemEnd = $word;
                    $listItem = new DiffListItem($currentListItem, array(), $listItemStart, $listItemEnd);
                    $list[] = $listItem;
                    $currentListItem = null;
                } else {
                    $currentListItem[] = $word;
                }

                $openListItems--;
            } else {
                if ($openListItems > 0) {
                    $currentListItem[] = $word;
                } else {
                    $list[] = $word;
                }
            }
        }

        $diffList = new DiffList($listType, $listStartTag, $listEndTag, $list, $attributes);

        return $diffList;
    }

    protected function isOpeningListTag($word, $type = null)
    {
        $filter = $type !== null ? array('<' . $type) : array('<ul', '<ol', '<dl');
        return in_array(substr($word, 0, 3), $filter);
    }

    protected function isClosingListTag($word, $type = null)
    {
        $filter = $type !== null ? array('</' . $type) : array('</ul', '</ol', '</dl');

        return in_array(substr($word, 0, 4), $filter);
    }

    protected function isOpeningListItemTag($word, $type = null)
    {
        $filter = $type !== null ? array('<' . $type) : array('<li', '<dd', '<dt');

        return in_array(substr($word, 0, 3), $filter);
    }

    protected function isClosingListItemTag($word, $type = null)
    {
        $filter = $type !== null ? array('</' . $type) : array('</li', '</dd', '</dt');

        return in_array(substr($word, 0, 4), $filter);
    }
}


1			<?php
2
3			namespace Caxy\HtmlDiff;
4
5			use Caxy\HtmlDiff\ListDiff\DiffList;
6			use Caxy\HtmlDiff\ListDiff\DiffListItem;
7
8			class ListDiffNew extends AbstractDiff
9			{
10			protected static $listTypes = array('ul', 'ol', 'dl');
11
12	4		public function build()
13			{
14	4		$this->splitInputsToWords();
15
16	4		return $this->diffLists(
17	4		$this->buildDiffList($this->oldWords),
18	4		$this->buildDiffList($this->newWords)
19	4		);
20			}
21
22	4		protected function diffLists(DiffList $oldList, DiffList $newList)
23			{
24	4		$oldMatchData = array();
25	4		$newMatchData = array();
26	4		$oldListIndices = array();
27	4		$newListIndices = array();
28	4		$oldListItems = array();
29	4		$newListItems = array();
30
31	4		foreach ($oldList->getListItems() as $oldIndex => $oldListItem) {
32	4		if ($oldListItem instanceof DiffListItem) {
33	4		$oldListItems[$oldIndex] = $oldListItem;
34
35	4		$oldListIndices[] = $oldIndex;
36	4		$oldMatchData[$oldIndex] = array();
37
38			// Get match percentages
39	4		foreach ($newList->getListItems() as $newIndex => $newListItem) {
40	4		if ($newListItem instanceof DiffListItem) {
41	4		if (!in_array($newListItem, $newListItems)) {
42	4		$newListItems[$newIndex] = $newListItem;
43	4		}
44	4		if (!in_array($newIndex, $newListIndices)) {
45	4		$newListIndices[] = $newIndex;
46	4		}
47	4		if (!array_key_exists($newIndex, $newMatchData)) {
48	4		$newMatchData[$newIndex] = array();
49	4		}
50
51	4		$oldText = implode('', $oldListItem->getText());
52	4		$newText = implode('', $newListItem->getText());
53
54			// similar_text
55	4		$percentage = null;
56	4		similar_text($oldText, $newText, $percentage);
57
58	4		$oldMatchData[$oldIndex][$newIndex] = $percentage;
59	4		$newMatchData[$newIndex][$oldIndex] = $percentage;
60	4		}
61	4		}
62	4		}
63	4		}
64
65	4		$currentIndexInOld = 0;
66	4		$currentIndexInNew = 0;
67	4		$oldCount = count($oldListIndices);
68	4		$newCount = count($newListIndices);
69	4		$difference = max($oldCount, $newCount) - min($oldCount, $newCount);
70
71	4		$diffOutput = '';
72
73	4		foreach ($newList->getListItems() as $newIndex => $newListItem) {
74	4		if ($newListItem instanceof DiffListItem) {
75	4		$operation = null;
			0 ignored issues – show Unused Code introduced 2016-01-12 15:21 UTC by Report Bug Copy Issue Report `$operation` 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...
76
77	4		$oldListIndex = array_key_exists($currentIndexInOld, $oldListIndices) ? $oldListIndices[$currentIndexInOld] : null;
			0 ignored issues – show Coding Style introduced 2016-02-09 16:38 UTC by Report Bug Copy Issue Report This line exceeds maximum limit of 120 characters; contains 131 characters Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line. Loading history...
78	4		$class = 'normal';
			0 ignored issues – show Unused Code introduced 2016-01-12 15:21 UTC by Report Bug Copy Issue Report `$class` 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...
79
80	4		if (null !== $oldListIndex && array_key_exists($oldListIndex, $oldMatchData)) {
81			// Check percentage matches of upcoming list items in old.
82	4		$matchPercentage = $oldMatchData[$oldListIndex][$newIndex];
83
84			// does the old list item match better?
85	4		$otherMatchBetter = false;
86	4	View Code Duplication	foreach ($oldMatchData[$oldListIndex] as $index => $percentage) {
			0 ignored issues – show Duplication introduced 2016-02-23 20:32 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
87	4		if ($index > $newIndex && $percentage > $matchPercentage) {
88	2		$otherMatchBetter = $index;
89	2		}
90	4		}
91
92	4		if (false !== $otherMatchBetter && $newCount > $oldCount && $difference > 0) {
93	1		$diffOutput .= sprintf('%s', $newListItem->getHtml('normal new', 'ins'));
94	1		$currentIndexInNew++;
95	1		$difference--;
96
97	1		continue;
98			}
99
100	4		$nextOldListIndex = array_key_exists($currentIndexInOld + 1, $oldListIndices) ? $oldListIndices[$currentIndexInOld + 1] : null;
			0 ignored issues – show Coding Style introduced 2016-02-09 16:38 UTC by Report Bug Copy Issue Report This line exceeds maximum limit of 120 characters; contains 147 characters Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line. Loading history...
101
102	4		$replacement = false;
103
104	4		if ($nextOldListIndex !== null && $oldMatchData[$nextOldListIndex][$newIndex] > $matchPercentage && $oldMatchData[$nextOldListIndex][$newIndex] > $this->matchThreshold) {
			0 ignored issues – show Coding Style introduced 2016-02-09 16:38 UTC by Report Bug Copy Issue Report This line exceeds maximum limit of 120 characters; contains 190 characters Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line. Loading history...
105			// Following list item in old is better match, use that.
106			$diffOutput .= sprintf('%s', $oldListItems[$oldListIndex]->getHtml('removed', 'del'));
107
108			$currentIndexInOld++;
109			$oldListIndex = $nextOldListIndex;
110			$matchPercentage = $oldMatchData[$oldListIndex];
111			$replacement = true;
112			}
113
114	4		if ($matchPercentage > $this->matchThreshold \|\| $currentIndexInNew === $currentIndexInOld) {
115			// Diff the two lists.
116	4		$htmlDiff = new HtmlDiff($oldListItems[$oldListIndex]->getInnerHtml(), $newListItem->getInnerHtml(), $this->encoding, $this->specialCaseTags, $this->groupDiffs);
			0 ignored issues – show Coding Style introduced 2016-02-09 16:38 UTC by Report Bug Copy Issue Report This line exceeds maximum limit of 120 characters; contains 185 characters Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line. Loading history...
117	4		$diffContent = $htmlDiff->build();
118
119	4		$diffOutput .= sprintf('%s%s%s', $newListItem->getStartTagWithDiffClass($replacement ? 'replacement' : 'normal'), $diffContent, $newListItem->getEndTag());
			0 ignored issues – show Coding Style introduced 2016-02-09 16:38 UTC by Report Bug Copy Issue Report This line exceeds maximum limit of 120 characters; contains 179 characters Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line. Loading history...
120
121	4		} else {
122			$diffOutput .= sprintf('%s', $oldListItems[$oldListIndex]->getHtml('removed', 'del'));
123			$diffOutput .= sprintf('%s', $newListItem->getHtml('replacement', 'ins'));
124			}
125	4		$currentIndexInOld++;
126	4		} else {
127			$diffOutput .= sprintf('%s', $newListItem->getHtml('normal new', 'ins'));
128			}
129
130	4		$currentIndexInNew++;
131	4		}
132	4		}
133
134			// Output any additional list items
135	4		while (array_key_exists($currentIndexInOld, $oldListIndices)) {
136	2		$oldListIndex = $oldListIndices[$currentIndexInOld];
137	2		$diffOutput .= sprintf('%s', $oldListItems[$oldListIndex]->getHtml('removed', 'del'));
138	2		$currentIndexInOld++;
139	2		}
140
141	4		return sprintf('%s%s%s', $newList->getStartTagWithDiffClass(), $diffOutput, $newList->getEndTag());
142			}
143
144	4		protected function buildDiffList($words)
145			{
146	4		$listType = null;
147	4		$listStartTag = null;
148	4		$listEndTag = null;
149	4		$attributes = array();
150	4		$openLists = 0;
151	4		$openListItems = 0;
152	4		$list = array();
153	4		$currentListItem = null;
154	4		$listItemType = null;
155	4		$listItemStart = null;
156	4		$listItemEnd = null;
			0 ignored issues – show Unused Code introduced 2016-01-12 15:21 UTC by Report Bug Copy Issue Report `$listItemEnd` 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 `$higher` is always overwritten for every possible time line. Loading history...
157
158	4		foreach ($words as $i => $word) {
159	4		if ($this->isOpeningListTag($word, $listType)) {
160	4		if ($openLists > 0) {
161	1		if ($openListItems > 0) {
162	1		$currentListItem[] = $word;
163	1		} else {
164			$list[] = $word;
165			}
166	1		} else {
167	4		$listType = substr($word, 1, 2);
168	4		$listStartTag = $word;
169			}
170
171	4		$openLists++;
172	4		} elseif ($this->isClosingListTag($word, $listType)) {
173	4		if ($openLists > 1) {
174	1		if ($openListItems > 0) {
175	1		$currentListItem[] = $word;
176	1		} else {
177			$list[] = $word;
178			}
179	1		} else {
180	4		$listEndTag = $word;
181			}
182
183	4		$openLists--;
184	4		} elseif ($this->isOpeningListItemTag($word, $listItemType)) {
185	4		if ($openListItems === 0) {
186			// New top-level list item
187	4		$currentListItem = array();
188	4		$listItemType = substr($word, 1, 2);
189	4		$listItemStart = $word;
190	4		} else {
191	1		$currentListItem[] = $word;
192			}
193
194	4		$openListItems++;
195	4		} elseif ($this->isClosingListItemTag($word, $listItemType)) {
196	4		if ($openListItems === 1) {
197	4		$listItemEnd = $word;
198	4		$listItem = new DiffListItem($currentListItem, array(), $listItemStart, $listItemEnd);
199	4		$list[] = $listItem;
200	4		$currentListItem = null;
201	4		} else {
202	1		$currentListItem[] = $word;
203			}
204
205	4		$openListItems--;
206	4		} else {
207	4		if ($openListItems > 0) {
208	4		$currentListItem[] = $word;
209	4		} else {
210	4		$list[] = $word;
211			}
212			}
213	4		}
214
215	4		$diffList = new DiffList($listType, $listStartTag, $listEndTag, $list, $attributes);
216
217	4		return $diffList;
218			}
219
220	4		protected function isOpeningListTag($word, $type = null)
221			{
222	4		$filter = $type !== null ? array('<' . $type) : array('<ul', '<ol', '<dl');
223	4		return in_array(substr($word, 0, 3), $filter);
224			}
225
226	4		protected function isClosingListTag($word, $type = null)
227			{
228	4		$filter = $type !== null ? array('</' . $type) : array('</ul', '</ol', '</dl');
229
230	4		return in_array(substr($word, 0, 4), $filter);
231			}
232
233	4		protected function isOpeningListItemTag($word, $type = null)
234			{
235	4		$filter = $type !== null ? array('<' . $type) : array('<li', '<dd', '<dt');
236
237	4		return in_array(substr($word, 0, 3), $filter);
238			}
239
240	4		protected function isClosingListItemTag($word, $type = null)
241			{
242	4		$filter = $type !== null ? array('</' . $type) : array('</li', '</dd', '</dt');
243
244	4		return in_array(substr($word, 0, 4), $filter);
245			}
246			}
247

caxy / php-htmldiff

Pull Request — master (#31)

ListDiffNew::diffLists() F

Complexity

Size

Duplication

Code Coverage

Importance

How to fix Long Method Complexity

Long Method

Duplication Side-by-Side

Filter issues like