This file is indexed.

/usr/share/php/arc/serializers/ARC2_NTriplesSerializer.php is in libarc-php 2.2.4-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
<?php
/**
 * ARC2 N-Triples Serializer
 *
 * @author Benjamin Nowack
 * @license <http://arc.semsol.org/license>
 * @homepage <http://arc.semsol.org/>
 * @package ARC2
*/

ARC2::inc('RDFSerializer');

class ARC2_NTriplesSerializer extends ARC2_RDFSerializer {

  function __construct($a, &$caller) {
    parent::__construct($a, $caller);
  }
  
  function __init() {
    parent::__init();
    $this->esc_chars = array();
    $this->raw = 0;
  }

  /*  */
  
  function getTerm($v, $term = '') {
    // type detection
    if (!is_array($v) || empty($v['type'])) {
      // bnode
      if (preg_match('/^\_\:/', $v)) {
        return $this->getTerm(array('value' => $v, 'type' => 'bnode'));
      }
      // uri
      if (preg_match('/^[a-z0-9]+\:[^\s\"]*$/is' . ($this->has_pcre_unicode ? 'u' : ''), $v)) {
        return $this->getTerm(array('value' => $v, 'type' => 'uri'));
      }
      // fallback for non-unicode environments: subjects and predicates can't be literals.
      if (in_array($term, array('s', 'p'))) {
        return $this->getTerm(array('value' => $v, 'type' => 'uri'));
      }
      // assume literal
      return $this->getTerm(array('type' => 'literal', 'value' => $v));
    }
    if ($v['type'] == 'bnode') {
      return $v['value'];
    }
    elseif ($v['type'] == 'uri') {
      return '<' . $this->escape($v['value']) . '>';
    }
    // something went wrong
    elseif ($v['type'] != 'literal') {
      return $this->getTerm($v['value']);
    }
    /* literal */
    $quot = '"';
    if ($this->raw && preg_match('/\"/', $v['value'])) {
      $quot = "'";
      if (preg_match('/\'/', $v['value'])) {
        $quot = '"""';
        if (preg_match('/\"\"\"/', $v['value']) || preg_match('/\"$/', $v['value']) || preg_match('/^\"/', $v['value'])) {
          $quot = "'''";
          $v['value'] = preg_replace("/'$/", "' ", $v['value']);
          $v['value'] = preg_replace("/^'/", " '", $v['value']);
          $v['value'] = str_replace("'''", '\\\'\\\'\\\'', $v['value']);
        }
      }
    }
    if ($this->raw && (strlen($quot) == 1) && preg_match('/[\x0d\x0a]/', $v['value'])) {
      $quot = $quot . $quot . $quot;
    }
    $suffix = isset($v['lang']) && $v['lang'] ? '@' . $v['lang'] : '';
    $suffix = isset($v['datatype']) && $v['datatype'] ? '^^' . $this->getTerm($v['datatype']) : $suffix;
    //return $quot . "object" . utf8_encode($v['value']) . $quot . $suffix;
    return $quot . $this->escape($v['value']) . $quot . $suffix;
  }
  
  function getSerializedIndex($index, $raw = 0) {
    $this->raw = $raw;
    $r = '';
    $nl = "\n";
    foreach ($index as $s => $ps) {
      $s = $this->getTerm($s, 's');
      foreach ($ps as $p => $os) {
        $p = $this->getTerm($p, 'p');
        if (!is_array($os)) {/* single literal o */
          $os = array(array('value' => $os, 'type' => 'literal'));
        }
        foreach ($os as $o) {
          $o = $this->getTerm($o, 'o‚');
          $r .= $r ? $nl : '';
          $r .= $s . ' ' . $p . ' ' . $o . ' .';
        }
      }
    }
    return $r . $nl;
  }
  
  /*  */

  function escape($v) {
    $r = '';
	// decode, if possible
    $v = (strpos(utf8_decode(str_replace('?', '', $v)), '?') === false) ? utf8_decode($v) : $v;
	if ($this->raw) return $v;// no further escaping wanted
	// escape tabs and linefeeds
	$v = str_replace(array("\t", "\r", "\n"), array('\t', '\r', '\n'), $v);
	// escape non-ascii-chars
	$v = preg_replace_callback('/([^a-zA-Z0-9 \!\#\$\%\&\(\)\*\+\,\-\.\/\:\;\=\?\@\^\_\{\|\}]+)/', array($this, 'escapeChars'), $v);
	return $v;
  }
  
  function escapeChars($matches) {
	$v = $matches[1];
	$r = '';
	// loop through mb chars
	if (function_exists('mb_strlen')) {
		for ($i = 0, $i_max = mb_strlen($v, 'UTF-8'); $i < $i_max; $i++) {
		  $c = mb_substr($v, $i, 1, 'UTF-8');
		  if (!isset($this->esc_chars[$c])) {
			$this->esc_chars[$c] = $this->getEscapedChar($c, $this->getCharNo($c, 1));
		  }
		  $r .= $this->esc_chars[$c];
		}
	}
	// fall back to built-in JSON functionality, if available
	else if (function_exists('json_encode')) {
		$r = json_encode($v);
		if ($r == 'null') $r = json_encode (utf8_encode($v));
		// remove boundary quotes
		if (substr($r, 0, 1) == '"') $r = substr($r, 1);
		if (substr($r, -1) == '"') $r = substr($r, 0, -1);
		// uppercase hex chars
		$r = preg_replace('/(\\\u)([0-9a-f]{4})/e', "'\\1' . strtoupper('\\2')", $r);
		$r = preg_replace('/(\\\U)([0-9a-f]{8})/e', "'\\1' . strtoupper('\\2')", $r);
	}
	// escape byte-wise (may be wrong for mb chars and newer php versions)
	else {
		for ($i = 0, $i_max = strlen($v); $i < $i_max; $i++) {
		  $c = $v[$i];
		  if (!isset($this->esc_chars[$c])) {
			$this->esc_chars[$c] = $this->getEscapedChar($c, $this->getCharNo($c));
		  }
		  $r .= $this->esc_chars[$c];
		}
	}
	return $r;
  }
  
  /*  */
  
  function getCharNo($c, $is_encoded = false) {
    $c_utf = $is_encoded ? $c : utf8_encode($c);
    $bl = strlen($c_utf);/* binary length */
    $r = 0;
    switch ($bl) {
      case 1:/* 0####### (0-127) */
        $r = ord($c_utf);
        break;
      case 2:/* 110##### 10###### = 192+x 128+x */
        $r = ((ord($c_utf[0]) - 192) * 64) + (ord($c_utf[1]) - 128);
        break;
      case 3:/* 1110#### 10###### 10###### = 224+x 128+x 128+x */
        $r = ((ord($c_utf[0]) - 224) * 4096) + ((ord($c_utf[1]) - 128) * 64) + (ord($c_utf[2]) - 128);
        break;
      case 4:/* 1111#### 10###### 10###### 10###### = 240+x 128+x 128+x 128+x */
        $r = ((ord($c_utf[0]) - 240) * 262144) + ((ord($c_utf[1]) - 128) * 4096) + ((ord($c_utf[2]) - 128) * 64) + (ord($c_utf[3]) - 128);
        break;
    }
    return $r;
  }

  function getEscapedChar($c, $no) {/*see http://www.w3.org/TR/rdf-testcases/#ntrip_strings */
    if ($no < 9)        return "\\u" . sprintf('%04X', $no);  /* #x0-#x8 (0-8) */
    if ($no == 9)       return '\t';                          /* #x9 (9) */
    if ($no == 10)      return '\n';                          /* #xA (10) */
    if ($no < 13)       return "\\u" . sprintf('%04X', $no);  /* #xB-#xC (11-12) */
    if ($no == 13)      return '\r';                          /* #xD (13) */
    if ($no < 32)       return "\\u" . sprintf('%04X', $no);  /* #xE-#x1F (14-31) */
    if ($no < 34)       return $c;                            /* #x20-#x21 (32-33) */
    if ($no == 34)      return '\"';                          /* #x22 (34) */
    if ($no < 92)       return $c;                            /* #x23-#x5B (35-91) */
    if ($no == 92)      return '\\';                          /* #x5C (92) */
    if ($no < 127)      return $c;                            /* #x5D-#x7E (93-126) */
    if ($no < 65536)    return "\\u" . sprintf('%04X', $no);  /* #x7F-#xFFFF (128-65535) */
    if ($no < 1114112)  return "\\U" . sprintf('%08X', $no);  /* #x10000-#x10FFFF (65536-1114111) */
    return '';                                                /* not defined => ignore */
  }
  
  /*  */
 
}