13168072550

Committed 05 Feb 2025 10:52PM UTC coverage: 99.406%. Remained the same

Build # 13168072550

Build Type

push

github

Committed by

xemlock

Commit Message

Adjust tests for HTMLPurifier 4.18.0

Support for conditional comments was removed in HTMLPurifier 4.18.0,
see: https://github.com/ezyang/htmlpurifier/commit/4828fdf.

Run Details

1507 of 1516 relevant lines covered (99.41%)

3215.37 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

93.88

/library/HTMLPurifier/ChildDef/HTML5/Table.php

<?php

/**
 * HTML5 compliant definition for table contents.
 *
 * Content model: In this order: optionally a caption element, followed by zero or more
 * colgroup elements, followed optionally by a thead element, followed by either zero
 * or more tbody elements or one or more tr elements, followed optionally by a tfoot
 * element.
 *
 * @see https://html.spec.whatwg.org/multipage/tables.html#the-table-element
 */
class HTMLPurifier_ChildDef_HTML5_Table extends HTMLPurifier_ChildDef
{
    /**
     * @type bool
     */
    public $allow_empty = false;

    /**
     * @type string
     */
    public $type = 'table';

    /**
     * @type array
     */
    public $elements = array(
        'tr' => true,
        'tbody' => true,
        'thead' => true,
        'tfoot' => true,
        'caption' => true,
        'colgroup' => true,
        'col' => true,
    );

    /**
     * @param array $children
     * @param HTMLPurifier_Config $config
     * @param HTMLPurifier_Context $context
     * @return array
     */
    public function validateChildren($children, $config, $context)
    {
        if (empty($children)) {
            // Table children are optional
            return $children;
        }

        // At most one of each of these elements is allowed in a table
        $caption = array();
        $thead = array();
        $tfoot = array();

        // and as many of these as you want
        $cols = array(); // <col>, <colgroup> and following whitespace nodes
        $content = array(); // <tr> and <tbody>

        // Whitespace accumulators
        $initial_ws = array();
        $after_caption_ws = array();
        $after_thead_ws = array();
        $after_tfoot_ws = array();

        // Essentially, we have two modes: thead/tfoot/tbody mode, and tr mode.
        // If we encounter a thead, tfoot or tbody, we are placed in the former
        // mode, and we *must* wrap any stray tr segments with a tbody. But if
        // we don't run into any of them, just having tr tags is OK.
        $tbody_mode = false;

        $ws_accum =& $initial_ws;

        foreach ($children as $node) {
            if ($node instanceof HTMLPurifier_Node_Comment) {
                $ws_accum[] = $node;
                continue;
            }

            switch ($node->name) {
                case 'tbody':
                    $tbody_mode = true;
                    // no break

                case 'tr':
                    $content[] = $node;
                    $ws_accum =& $content;
                    break;

                case 'caption':
                    // there can only be one caption!
                    if (count($caption)) {
                        break;
                    }
                    $caption[] = $node;
                    $ws_accum =& $after_caption_ws;
                    break;

                case 'thead':
                    $tbody_mode = true;
                    if (empty($thead)) {
                        $thead[] = $node;
                        $ws_accum =& $after_thead_ws;
                    } else {
                        // Oops, there's a second one! What should we do? Current behavior
                        // is to mutate the first and last entries into <tbody> tags, and
                        // then put into content, same as in HTMLPurifier_ChildDef_Table.
                        $node->name = 'tbody';
                        $content[] = $node;
                        $ws_accum =& $content;
                    }
                    break;

                case 'tfoot':
                    $tbody_mode = true;
                    if (empty($tfoot)) {
                        $tfoot[] = $node;
                        $ws_accum =& $after_tfoot_ws;
                    } else {
                        $node->name = 'tbody';
                        $content[] = $node;
                        $ws_accum =& $content;
                    }
                    break;

                case 'colgroup':
                case 'col':
                    $cols[] = $node;
                    $ws_accum =& $cols;
                    break;

                case '#PCDATA':
                    // How is whitespace handled? We treat is as sticky to the *end* of
                    // the previous element. So all the nonsense we have worked on is to
                    // keep things together.
                    if (!empty($node->is_whitespace)) {
                        $ws_accum[] = $node;
                    }
                    break;
            }
        }

        $ret = array_merge(
            $initial_ws,
            $caption,
            $after_caption_ws,
            $cols,
            $thead,
            $after_thead_ws,
            $tfoot,
            $after_tfoot_ws
        );

        if ($tbody_mode) {
            // At least one of thead/tbody/tfoot children is present, we have to
            // shuffle any <tr> children into <tbody>
            $current_tr_tbody = null;

            foreach ($content as $node) {
                switch ($node->name) {
                    case 'tbody':
                        $current_tr_tbody = null;
                        $ret[] = $node;
                        break;

                    case 'tr':
                        if ($current_tr_tbody === null) {
                            $current_tr_tbody = new HTMLPurifier_Node_Element('tbody');
                            $ret[] = $current_tr_tbody;
                        }
                        $current_tr_tbody->children[] = $node;
                        break;

                    case '#PCDATA':
                        // The only text nodes present here are whitespace
                        if ($current_tr_tbody === null) {
                            $ret[] = $node;
                        } else {
                            $current_tr_tbody->children[] = $node;
                        }
                        break;
                }
            }
        } else {
            $ret = array_merge($ret, $content);
        }

        return $ret;
    }
}

1	<?php
2
3	/**
4	* HTML5 compliant definition for table contents.
5	*
6	* Content model: In this order: optionally a caption element, followed by zero or more
7	* colgroup elements, followed optionally by a thead element, followed by either zero
8	* or more tbody elements or one or more tr elements, followed optionally by a tfoot
9	* element.
10	*
11	* @see https://html.spec.whatwg.org/multipage/tables.html#the-table-element
12	*/
13	class HTMLPurifier_ChildDef_HTML5_Table extends HTMLPurifier_ChildDef
14	{
15	/**
16	* @type bool
17	*/
18	public $allow_empty = false;
19
20	/**
21	* @type string
22	*/
23	public $type = 'table';
24
25	/**
26	* @type array
27	*/
28	public $elements = array(
29	'tr' => true,
30	'tbody' => true,
31	'thead' => true,
32	'tfoot' => true,
33	'caption' => true,
34	'colgroup' => true,
35	'col' => true,
36	);
37
38	/**
39	* @param array $children
40	* @param HTMLPurifier_Config $config
41	* @param HTMLPurifier_Context $context
42	* @return array
43	*/
44	public function validateChildren($children, $config, $context)
45	{
46	if (empty($children)) {	280✔
47	// Table children are optional
48	return $children;	20✔
49	}
50
51	// At most one of each of these elements is allowed in a table
52	$caption = array();	260✔
53	$thead = array();	260✔
54	$tfoot = array();	260✔
55
56	// and as many of these as you want
57	$cols = array(); // <col>, <colgroup> and following whitespace nodes	260✔
58	$content = array(); // <tr> and <tbody>	260✔
59
60	// Whitespace accumulators
61	$initial_ws = array();	260✔
62	$after_caption_ws = array();	260✔
63	$after_thead_ws = array();	260✔
64	$after_tfoot_ws = array();	260✔
65
66	// Essentially, we have two modes: thead/tfoot/tbody mode, and tr mode.
67	// If we encounter a thead, tfoot or tbody, we are placed in the former
68	// mode, and we must wrap any stray tr segments with a tbody. But if
69	// we don't run into any of them, just having tr tags is OK.
70	$tbody_mode = false;	260✔
71
72	$ws_accum =& $initial_ws;	260✔
73
74	foreach ($children as $node) {	260✔
75	if ($node instanceof HTMLPurifier_Node_Comment) {	260✔
76	$ws_accum[] = $node;	×
77	continue;	×
78	}
79
80	switch ($node->name) {	260✔
81	case 'tbody':	260✔
82	$tbody_mode = true;	90✔
83	// no break
84
85	case 'tr':	244✔
86	$content[] = $node;	160✔
87	$ws_accum =& $content;	160✔
88	break;	160✔
89
90	case 'caption':	180✔
91	// there can only be one caption!
92	if (count($caption)) {	110✔
93	break;	10✔
94	}
95	$caption[] = $node;	110✔
96	$ws_accum =& $after_caption_ws;	110✔
97	break;	110✔
98
99	case 'thead':	100✔
100	$tbody_mode = true;	60✔
101	if (empty($thead)) {	60✔
102	$thead[] = $node;	60✔
103	$ws_accum =& $after_thead_ws;	60✔
104	} else {	12✔
105	// Oops, there's a second one! What should we do? Current behavior
106	// is to mutate the first and last entries into <tbody> tags, and
107	// then put into content, same as in HTMLPurifier_ChildDef_Table.
108	$node->name = 'tbody';	×
109	$content[] = $node;	×
110	$ws_accum =& $content;	×
111	}
112	break;	60✔
113
114	case 'tfoot':	60✔
115	$tbody_mode = true;	40✔
116	if (empty($tfoot)) {	40✔
117	$tfoot[] = $node;	40✔
118	$ws_accum =& $after_tfoot_ws;	40✔
119	} else {	8✔
120	$node->name = 'tbody';	10✔
121	$content[] = $node;	10✔
122	$ws_accum =& $content;	10✔
123	}
124	break;	40✔
125
126	case 'colgroup':	50✔
127	case 'col':	50✔
128	$cols[] = $node;	20✔
129	$ws_accum =& $cols;	20✔
130	break;	20✔
131
132	case '#PCDATA':	30✔
133	// How is whitespace handled? We treat is as sticky to the end of
134	// the previous element. So all the nonsense we have worked on is to
135	// keep things together.
136	if (!empty($node->is_whitespace)) {	30✔
137	$ws_accum[] = $node;	20✔
138	}	4✔
139	break;	76✔
140	}	52✔
141	}	52✔
142
143	$ret = array_merge(	260✔
144	$initial_ws,	260✔
145	$caption,	260✔
146	$after_caption_ws,	260✔
147	$cols,	260✔
148	$thead,	260✔
149	$after_thead_ws,	260✔
150	$tfoot,	260✔
151	$after_tfoot_ws	208✔
152	);	182✔
153
154	if ($tbody_mode) {	260✔
155	// At least one of thead/tbody/tfoot children is present, we have to
156	// shuffle any <tr> children into <tbody>
157	$current_tr_tbody = null;	120✔
158
159	foreach ($content as $node) {	120✔
160	switch ($node->name) {	100✔
161	case 'tbody':	100✔
162	$current_tr_tbody = null;	90✔
163	$ret[] = $node;	90✔
164	break;	90✔
165
166	case 'tr':	40✔
167	if ($current_tr_tbody === null) {	30✔
168	$current_tr_tbody = new HTMLPurifier_Node_Element('tbody');	30✔
169	$ret[] = $current_tr_tbody;	30✔
170	}	6✔
171	$current_tr_tbody->children[] = $node;	30✔
172	break;	30✔
173
174	case '#PCDATA':	10✔
175	// The only text nodes present here are whitespace
176	if ($current_tr_tbody === null) {	10✔
177	$ret[] = $node;	10✔
178	} else {	2✔
179	$current_tr_tbody->children[] = $node;	×
180	}
181	break;	32✔
182	}	20✔
183	}	24✔
184	} else {	24✔
185	$ret = array_merge($ret, $content);	150✔
186	}
187
188	return $ret;	260✔
189	}
190	}

xemlock / htmlpurifier-html5 / 13168072550

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous