Subversion Repositories eFlore/Applications.cel

Rev

Rev 995 | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed

Rev 995 Rev 1318
Line 8... Line 8...
8 
 
 8 
 
9 
 /* Adapation par David Delon Decembre 2010 : gestion sous espece
 9 
 /* Adapation par David Delon Decembre 2010 : gestion sous espece
Line -... Line 10...
- 
 
 10 
 */
- 
 
 11 
 
- 
 
 12 
 
- 
 
 13 
/**
- 
 
 14 
 * Class NameParser
- 
 
 15 
 * Used to convert a string to a standarized format.
10 
 */
 16 
 */
11 
 
 17 
class NameParser {
12 
 
 18 
 
13 
	/**
 19 
	/**
14 
	 * Class NameParser
 - 
 
15 
	 * Used to convert a string to a standarized format.
 - 
 
16 
	 */
 - 
 
17 
	class NameParser {
 - 
 
18 
 
 - 
 
19 
		/**
 - 
 
20 
		 * Whether to debug or nor
 20 
	 * Whether to debug or nor
Line 21... Line 21...
21 
		 * @var bool|integer
 21 
	 * @var bool|integer
22 
		 */
 22 
	 */
23 
		public $debug_flag;
 23 
	public $debug_flag;
24 
 
 24 
 
25 
 
 - 
 
26 
 
 - 
 
27 
		/**
 - 
 
28 
		 * Constructor
- 
 
29 
		 */
 - 
 
30 
		public function __construct( ) {
 - 
 
31 
		}
 - 
 
32 
 
 - 
 
33 
		/**
 - 
 
34 
		 * Sets value to the method property
 25 
 
Line -... Line 26...
- 
 
 26 
 
- 
 
 27 
	/**
- 
 
 28 
	 * Constructor
- 
 
 29 
	 */
- 
 
 30 
	public function __construct( ) {
- 
 
 31 
	}
- 
 
 32 
 
- 
 
 33 
	/**
Line 35... Line 34...
35 
		 * @param mixed $name class property name
 34 
	 * Sets value to the method property
36 
		 * @param mixed $value class property value
 35 
	 * @param mixed $name class property name
37 
		 */
 36 
	 * @param mixed $value class property value
38 
		public function set($name,$value) {
 37 
	 */
39 
			$this->$name = $value;
 38 
	public function set($name,$value) {
40 
		}
 39 
		$this->$name = $value;
41 
 
 40 
	}
- 
 
 41 
 
- 
 
 42 
	/**
- 
 
 43 
	 * Reduce Spaces
Line 42... Line -...
42 
 
 - 
 
43 
		/**
 - 
 
44 
		 * Reduce Spaces
 - 
 
45 
		 * This will reduce the string to only allow once space between characters
 44 
	 * This will reduce the string to only allow once space between characters
46 
		 * @param string $str : string to reduce space
 45 
	 * @param string $str : string to reduce space
Line -... Line 46...
- 
 
 46 
	 * @return string : string with only once space between characters
- 
 
 47 
	 */
- 
 
 48 
	private function reduce_spaces( $str ) {
- 
 
 49
- 
 
 50 
		$str = preg_replace("/ {2,}/", ' ', $str );
- 
 
 51 
		$str = trim( $str );
- 
 
 52
- 
 
 53 
		return( $str );
- 
 
 54 
	}
- 
 
 55 
 
- 
 
 56 
	/**
- 
 
 57 
	 * Function: parse_auth
- 
 
 58 
	 * Purpose: Produce a parsed version of authority of a taxon name
- 
 
 59 
	 * @author Tony Rees (Tony.Rees@csiro.au)
- 
 
 60 
	 * Date created: March 2008
- 
 
 61 
	 * Inputs: authority string as str
- 
 
 62 
	 * Remarks:
- 
 
 63 
	 *  (1) Performs authority expension of known abbreviated authornames using
- 
 
 64 
	 *   table "auth_abbrev_test1" (must be available and populated with relevant content)
- 
 
 65 
	 *  (2) Recognises "and", "et", "&" as equivalents (special case for "et al.") - all parsed to ampersand
Line 47... Line -...
47 
		 * @return string : string with only once space between characters
 - 
 
48 
		 */
 - 
 
49 
		private function reduce_spaces( $str ) {
 - 
 
50
- 
 
51 
			$str = preg_replace("/ {2,}/", ' ', $str );
 - 
 
52 
			$str = trim( $str );
 - 
 
53
- 
 
54 
			return( $str );
 - 
 
55 
		}
 - 
 
56 
 
 - 
 
57 
 
 - 
 
58 
		/**
 - 
 
59 
		 * Function: parse_auth
 - 
 
60 
		 * Purpose: Produce a parsed version of authority of a taxon name
 - 
 
61 
		 * @author Tony Rees (Tony.Rees@csiro.au)
 - 
 
62 
		 * Date created: March 2008
 - 
 
63 
		 * Inputs: authority string as str
 - 
 
64 
		 * Remarks:
 - 
 
65 
		 *  (1) Performs authority expension of known abbreviated authornames using
 - 
 
66 
		 *   table "auth_abbrev_test1" (must be available and populated with relevant content)
 - 
 
67 
		 *  (2) Recognises "and", "et", "&" as equivalents (special case for "et al.") - all parsed to ampersand
 - 
 
68 
		 *  (3) Recognises (e.g.) "Smith 1980" and "Smith, 1980" as equivalents - comma is removed in these cases
 66 
	 *  (3) Recognises (e.g.) "Smith 1980" and "Smith, 1980" as equivalents - comma is removed in these cases
69 
		 *  (4) Recognises (e.g.) "F. J. R. Taylor, 1980" and "F.J.R. Taylor, 1980" as equivalents -
 67 
	 *  (4) Recognises (e.g.) "F. J. R. Taylor, 1980" and "F.J.R. Taylor, 1980" as equivalents -
Line 70... Line 68...
70 
		 *      extra space after full stops is ignored in these cases
 68 
	 *      extra space after full stops is ignored in these cases
71 
		 *  (5) Returns uppercase string, diacritical marks intact
 69 
	 *  (5) Returns uppercase string, diacritical marks intact
72 
		 *
 70 
	 *
73 
		 * @param string $str : authority string
 71 
	 * @param string $str : authority string
Line 74... Line 72...
74 
		 * @param integer $upcase : convert to uppercase if $upcase = 1
 72 
	 * @param integer $upcase : convert to uppercase if $upcase = 1
75 
		 * @return string : parsed author string
 73 
	 * @return string : parsed author string
76 
		 */
 74 
	 */
77 
		public function parse_auth( $str, $upcase=1 ) {
 75 
	public function parse_auth( $str, $upcase=1 ) {
Line 78... Line 76...
78 
 
 76 
 
79 
			$this->debug['parse_auth'][] = "1";
 77 
		$this->debug['parse_auth'][] = "1";
80 
			$temp = $str = trim($str);
 78 
		$temp = $str = trim($str);
81
79
82 
  		if ( ($str == NULL) || ($str == '') ) {
 80 
  		if ( ($str == NULL) || ($str == '') ) {
83 
				$this->debug['parse_auth'][] = "1a";
 81 
				$this->debug['parse_auth'][] = "1a";
84 
		    return '';
 82 
		    return '';
85 
			}
 83 
		}
86 
 
 84 
 
87 
			if ( ( $temp == null ) || ( $temp == '') ) {
 85 
		if ( ( $temp == null ) || ( $temp == '') ) {
88 
				$this->debug['parse_auth'][] = "2a";
 86 
			$this->debug['parse_auth'][] = "2a";
89 
				return('');
 87 
			return('');
Line 90... Line 88...
90 
			} else {
 88 
		} else {
91 
 
 89 
 
Line 92... Line 90...
92 
				$this->debug['parse_auth'][] = "2b";
 90 
			$this->debug['parse_auth'][] = "2b";
Line 93... Line 91...
93
91
94 
				// add space after full stops, except at end (NB, will also add spece before some close brackets)
 - 
 
95 
				$temp = rtrim( str_replace('.', '. ', $temp) );
 - 
 
96 
				$this->debug['parse_auth'][] = "4 (temp:$temp)";
 - 
 
97
- 
 
98 
				//normalise "et", "and" to ampersand (et al. is a special case)
 - 
 
99 
//				if ( $temp like '% et al%' ) {
 - 
 
100 
				if ( preg_match('/ et al/', $temp) ) {
 - 
 
Line 101... Line -...
101 
					$temp = str_replace(' et al','zzzzz', $temp);
 - 
 
102 
					$this->debug['parse_auth'][] = "4a (temp:$temp)";
 92 
			// add space after full stops, except at end (NB, will also add spece before some close brackets)
103 
				}
 - 
 
104
- 
 
105 
				$temp = str_replace(' et ',' & ', $temp );
 - 
 
106 
				$temp = str_replace(' and ',' & ', $temp );
 - 
 
107 
 
 93 
			$temp = rtrim( str_replace('.', '. ', $temp) );
108 
				$temp = str_replace('zzzzz',' et al', $temp);
 94 
			$this->debug['parse_auth'][] = "4 (temp:$temp)";
109 
 
 95
110 
				$this->debug['parse_auth'][] = "5 (temp:$temp)";
 96 
			//normalise "et", "and" to ampersand (et al. is a special case)
111
97 
			// if ( $temp like '% et al%' ) {
112 
				//remove commas before dates (only)
 98 
			if ( preg_match('/ et al/', $temp) ) {
113 
				//	like '%, 17%'
 99 
				$temp = str_replace(' et al','zzzzz', $temp);
114 
				if ( preg_match('/, 17/', $temp) ) {
 100 
				$this->debug['parse_auth'][] = "4a (temp:$temp)";
115 
					$temp = str_replace(', 17',' 17', $temp);
 101 
			}
116 
					$this->debug['parse_auth'][] = "5a (temp:$temp)";
 102
117 
				}
 103 
			$temp = str_replace(' et ',' & ', $temp );
Line -... Line 104...
- 
 
 104 
			$temp = str_replace(' and ',' & ', $temp );
- 
 
 105 
 
- 
 
 106 
			$temp = str_replace('zzzzz',' et al', $temp);
118
107 
 
- 
 
 108 
			$this->debug['parse_auth'][] = "5 (temp:$temp)";
- 
 
 109
- 
 
 110 
			//remove commas before dates (only)
- 
 
 111 
			//	like '%, 17%'
119 
				//	like '%, 18%'
 112 
			if ( preg_match('/, 17/', $temp) ) {
- 
 
 113 
				$temp = str_replace(', 17',' 17', $temp);
- 
 
 114 
				$this->debug['parse_auth'][] = "5a (temp:$temp)";
Line -... Line 115...
- 
 
 115 
			}
- 
 
 116
- 
 
 117 
			//	like '%, 18%'
120 
				if ( preg_match('/, 18/', $temp) ) {
 118 
			if ( preg_match('/, 18/', $temp) ) {
121 
					$temp = str_replace(', 18',' 18', $temp);
 119 
				$temp = str_replace(', 18',' 18', $temp);
Line 122... Line 120...
122 
					$this->debug['parse_auth'][] = "5b (temp:$temp)";
 120 
				$this->debug['parse_auth'][] = "5b (temp:$temp)";
123 
				}
 121 
			}
124
122
125 
				//	like '%, 19%'
 123 
			//	like '%, 19%'
126 
				if ( preg_match('/, 19/', $temp) ) {
 124 
			if ( preg_match('/, 19/', $temp) ) {
127 
					$temp = str_replace(', 19',' 19', $temp);
 - 
 
- 
 
 125 
				$temp = str_replace(', 19',' 19', $temp);
128 
					$this->debug['parse_auth'][] = "5c (temp:$temp)";
 126 
				$this->debug['parse_auth'][] = "5c (temp:$temp)";
129 
				}
 127 
			}
130
128
131 
				//	like '%, 20%'
 129 
			//	like '%, 20%'
132 
				if ( preg_match('/, 20/', $temp) ) {
 130 
			if ( preg_match('/, 20/', $temp) ) {
133 
					$temp = str_replace(', 20',' 20', $temp);
 - 
 
134 
					$this->debug['parse_auth'][] = "5d (temp:$temp)";
 - 
 
135 
				}
 - 
 
136
- 
 
137 
				// reduce multiple internal spaces to single space
 - 
 
138 
				$temp = $this->reduce_spaces( $temp );
 131 
				$temp = str_replace(', 20',' 20', $temp);
139
- 
 
140 
				//	like '% -%'
 - 
 
141 
				$temp = str_replace(' -', '-', $temp);
 - 
 
142 
 
 - 
 
143 
				$this->debug['parse_auth'][] = "6 (temp:$temp)";
 - 
 
Line 144... Line -...
144
- 
 
145 
				foreach( explode(' ', $temp) as $this_word ) {
 - 
 
146
- 
 
147 
					$this->debug['parse_auth'][] = "7 (this_word:$this_word)";
 - 
 
148
- 
 
149 
					//	like '(%'
 132 
				$this->debug['parse_auth'][] = "5d (temp:$temp)";
150 
					if ( preg_match('/^\(/', $this_word) ) {
 133 
			}
151 
						$elapsed_chars .= '(';
 - 
 
152 
						$this_word = substr( $this_word, 1 );
 - 
 
153 
						$this->debug['parse_auth'][] = "7a (this_word:$this_word) (elapsed_chars:$elapsed_chars)";
 - 
 
154 
					}
 - 
 
155 
 
 - 
 
156 
					// Add back the word to the final translation
 - 
 
157 
					$elapsed_chars .= $this_word . ' ';
 - 
 
158 
					$this->debug['parse_auth'][] = "7c (this_word:$this_word) (elapsed_chars:$elapsed_chars)";
 - 
 
159 
				}
 - 
 
160
- 
 
161 
				$elapsed_chars = $this->reduce_spaces( str_replace(' )', ')', $elapsed_chars) );
 - 
 
162
- 
 
163 
				return trim( $elapsed_chars ) ;
 - 
 
164 
			}
 - 
 
165 
 
 - 
 
166 
		}
 - 
 
167
- 
 
168 
		/**
 - 
 
169 
		 * Function: parse
 - 
 
170 
		 * Purpose: Produces parsed version of an input string (scientific name components)
 - 
 
171 
		 * @author Tony Rees (Tony.Rees@csiro.au)
 - 
 
172 
		 * Date created: June 2007-November 2008
 134
173 
		 * Inputs: input string as str (this version presumes genus, genus+species, or
 - 
 
174 
		 * genus+species+authority)
 135 
			// reduce multiple internal spaces to single space
175 
		 * Outputs: parsed version of input string, for match purposes
 - 
 
176 
		 * Remarks:
 - 
 
177 
		 *    (1) Removes known text elements e.g.
 136 
			$temp = $this->reduce_spaces( $temp );
178 
		 *      'aff.', 'cf.', 'subsp.', subgenera if enclosed in brackets, etc. as desired
 137
Line 179... Line 138...
179 
		 *    (2) Removes accented and non A-Z characters other than full stops
138 
			//	like '% -%'
- 
 
 139 
			$temp = str_replace(' -', '-', $temp);
Line -... Line 140...
- 
 
 140 
 
- 
 
 141 
			$this->debug['parse_auth'][] = "6 (temp:$temp)";
- 
 
 142
- 
 
 143 
			foreach( explode(' ', $temp) as $this_word ) {
- 
 
 144
- 
 
 145 
				//$this->debug['parse_auth'][] = "7 (this_word:$this_word)";
- 
 
 146 
				$elapsed_chars = '';
- 
 
 147 
				//	like '(%'
- 
 
 148 
				if ( preg_match('/^\(/', $this_word) ) {
- 
 
 149 
					$elapsed_chars .= '(';
- 
 
 150 
					$this_word = substr( $this_word, 1 );
- 
 
 151 
					//$this->debug['parse_auth'][] = "7a (this_word:$this_word) (elapsed_chars:$elapsed_chars)";
- 
 
 152 
				}
- 
 
 153 
 
- 
 
 154 
				// Add back the word to the final translation
- 
 
 155 
				$elapsed_chars .= $this_word . ' ';
- 
 
 156 
				//$this->debug['parse_auth'][] = "7c (this_word:$this_word) (elapsed_chars:$elapsed_chars)";
- 
 
 157 
			}
- 
 
 158
- 
 
 159 
			$elapsed_chars = $this->reduce_spaces( str_replace(' )', ')', $elapsed_chars) );
- 
 
 160
- 
 
 161 
			return trim( $elapsed_chars ) ;
- 
 
 162 
		}
- 
 
 163 
 
- 
 
 164 
	}
- 
 
 165
- 
 
 166 
	/**
- 
 
 167 
	 * Function: parse
- 
 
 168 
	 * Purpose: Produces parsed version of an input string (scientific name components)
- 
 
 169 
	 * @author Tony Rees (Tony.Rees@csiro.au)
- 
 
 170 
	 * Date created: June 2007-November 2008
- 
 
 171 
	 * Inputs: input string as str (this version presumes genus, genus+species, or
- 
 
 172 
	 * genus+species+authority)
- 
 
 173 
	 * Outputs: parsed version of input string, for match purposes
- 
 
 174 
	 * Remarks:
- 
 
 175 
	 *    (1) Removes known text elements e.g.
- 
 
 176 
	 *      'aff.', 'cf.', 'subsp.', subgenera if enclosed in brackets, etc. as desired
Line 180... Line 177...
180 
		 *       (in scientific name portions)
 177 
	 *    (2) Removes accented and non A-Z characters other than full stops
181 
		 *    (3) Returns uppercase scientific name (genus + species only)
178 
	 *       (in scientific name portions)
182 
		 *       plus unaltered (presumed) authority
 179 
	 *    (3) Returns uppercase scientific name (genus + species only)
183 
		 *     examples;
 180 
	 *       plus unaltered (presumed) authority
184 
		 *       Anabaena cf. flos-aquae Ralfs ex Born. et Flah. => ANABAENA FLOSAQUAE Ralfs
181 
	 *     examples;
185 
		 *       ex Born. et Flah.
 182 
	 *       Anabaena cf. flos-aquae Ralfs ex Born. et Flah. => ANABAENA FLOSAQUAE Ralfs
186 
		 *       Abisara lemÈe-pauli => ABISARA LEMEEPAULI
 183 
	 *       ex Born. et Flah.
187 
		 *       Fuc/us Vesiculos2us => FUCUS VESICULOSUS
 184 
	 *       Abisara lemÈe-pauli => ABISARA LEMEEPAULI
Line 188... Line 185...
188 
		 *       Buffo ignicolor LacÈpËde, 1788 => BUFFO IGNICOLOR LacÈpËde, 1788
 185 
	 *       Fuc/us Vesiculos2us => FUCUS VESICULOSUS
Line 189... Line 186...
189 
		 *       Barbatia (Mesocibota) bistrigata (Dunker, 1866) => BARBATIA BISTRIGATA (Dunker, 1866)
 186 
	 *       Buffo ignicolor LacÈpËde, 1788 => BUFFO IGNICOLOR LacÈpËde, 1788
190 
		 *    (4) Thus version does not handle genus+author, or genus+species+infraspecies
 187 
	 *       Barbatia (Mesocibota) bistrigata (Dunker, 1866) => BARBATIA BISTRIGATA (Dunker, 1866)
191 
		 *       (second" good" term is presumed to be species epithet, anything after is
188 
	 *    (4) Thus version does not handle genus+author, or genus+species+infraspecies
192 
		 *       considered to be start of the authority), however could be adapted further as required
 189 
	 *       (second" good" term is presumed to be species epithet, anything after is
193 
         *         and actually it was done in this version for Tela Botanica
 190 
	 *       considered to be start of the authority), however could be adapted further as required
194 
		 *    (5) There is a separate function "parse_auth" for normalizing authorities when required
 191 
     *         and actually it was done in this version for Tela Botanica
195 
		 *      (e.g. for authority comparisons)
 192 
	 *    (5) There is a separate function "parse_auth" for normalizing authorities when required
196 
		 *
 193 
	 *      (e.g. for authority comparisons)
Line 197... Line 194...
197 
		 * @param string $str : input string ( genus, genus+species, or genus+species+authority )
 194 
	 *
198 
		 * @return string : parsed string
 195 
	 * @param string $str : input string ( genus, genus+species, or genus+species+authority )
199 
		 */
 196 
	 * @return string : parsed string
- 
 
 197 
	 */
- 
 
 198 
	public function parse( $str = NULL ) {
- 
 
 199
- 
 
 200 
		unset($this->debug['parse']);
- 
 
 201 
 
- 
 
 202 
		$temp = '';
- 
 
 203 
		$first_str_part = NULL;
- 
 
 204 
		$second_str_part = NULL;
- 
 
 205 
		$temp_genus = '';
- 
 
 206 
		$temp_species = '';
- 
 
 207 
		$temp_genus_species = '';
- 
 
 208 
		$temp_authority = '';
- 
 
 209 
		$temp_infra = '';
- 
 
 210
- 
 
 211 
		//$this->debug['parse'][] = "1";
- 
 
 212 
 
- 
 
 213 
		if ( ($str == NULL) || ( trim($str) == '') ) {
- 
 
 214 
			//$this->debug[] = "N1a<br>";
- 
 
 215 
			return '';
- 
 
 216 
		} else {
- 
 
 217 
			//	trim any leading, trailing spaces or line feeds
- 
 
 218 
			$temp = trim( $str );
- 
 
 219 
			//$this->debug['parse'][] = "1b";
- 
 
 220 
		}
- 
 
 221 
 
- 
 
 222 
		if ( $temp == NULL || $temp == '') {
- 
 
 223 
			//$this->debug['parse'][] = "2a";
- 
 
 224 
			return '';
- 
 
 225 
		} else {
- 
 
 226 
			//$this->debug['parse'][] = "2b";
- 
 
 227 
 
- 
 
 228 
			// replace any HTML ampersands
- 
 
 229 
			$set = array('%', '&', 'amp;%', 'AMP;%');
- 
 
 230 
			$temp = str_replace( $set, '&', $temp );
- 
 
 231 
 
- 
 
 232 
			//$this->debug['parse'][] = "2b1 (temp:$temp)";
- 
 
 233 
 
- 
 
 234 
			// remove any content in angle brackets (e.g. html tags - <i>, </i>, etc.)
- 
 
 235 
			$html_pattern = "(\<(/?[^\>]+)\>)";
- 
 
 236 
			//? This should not just handle html tags but all <*>
- 
 
 237 
			$temp = preg_replace( $html_pattern, '', $temp);
- 
 
 238 
			//$this->debug['parse'][] = "2b2 (temp:$temp)";
- 
 
 239 
 
- 
 
 240 
			// if second term (only) is in round brackets, presume it is a subgenus or a comment and remove it
- 
 
 241 
			// examples: Barbatia (Mesocibota) bistrigata (Dunker, 1866) => Barbatia bistrigata (Dunker, 1866)
- 
 
 242 
			// Barbatia (?) bistrigata (Dunker, 1866) => Barbatia bistrigata (Dunker, 1866)
- 
 
 243 
			// (obviously this will not suit genus + author alone, where first part of authorname is in brackets,
- 
 
 244 
			// however this is very rare?? and in any case we are not supporting genus+authority in this version)
- 
 
 245 
			//if ( $temp like '% (%)%'
- 
 
 246 
			$temp = preg_replace( "/ \(\w*\W*\)/", '', $temp, 1 );
- 
 
 247 
			//? Not sure if this will catch if
- 
 
 248 
			//$this->debug['parse'][] = "2b3 (temp:$temp)";
- 
 
 249 
 
- 
 
 250 
			// if second term (only) is in square brackets, presume it is a comment and remove it
- 
 
 251 
			// example: Aphis [?] ficus Theobald, [1918] => Aphis ficus Theobald, [1918]
200 
		public function parse( $str = NULL ) {
 252 
			//if ( $temp like '% [%]%'
201
- 
 
202 
			unset($this->debug['parse']);
 - 
 
203 
 
 - 
 
204 
 
 - 
 
205 
			$temp = '';
 - 
 
206 
			$first_str_part = NULL;
 - 
 
207 
			$second_str_part = NULL;
 - 
 
208 
			$temp_genus = '';
 - 
 
209 
			$temp_species = '';
 - 
 
210 
			$temp_genus_species = '';
 - 
 
211 
			$temp_authority = '';
 - 
 
212 
			$temp_infra = '';
 - 
 
213
- 
 
214 
			$this->debug['parse'][] = "1";
 - 
 
215 
 
 - 
 
216 
			if ( ($str == NULL) || ( trim($str) == '') ) {
 - 
 
217 
				$this->debug[] = "N1a<br>";
 - 
 
218 
				return '';
 - 
 
219 
			} else {
 - 
 
220 
				//	trim any leading, trailing spaces or line feeds
 - 
 
221 
				$temp = trim( $str );
 - 
 
222 
				$this->debug['parse'][] = "1b";
 - 
 
223 
			}
 - 
 
224 
 
 - 
 
225 
			if ( $temp == NULL || $temp == '') {
 - 
 
226 
				$this->debug['parse'][] = "2a";
 - 
 
227 
				return '';
 - 
 
228 
			} else {
 - 
 
229 
				$this->debug['parse'][] = "2b";
 - 
 
230 
 
 - 
 
231 
				// replace any HTML ampersands
 - 
 
232 
				$set = array('%', '&', 'amp;%', 'AMP;%');
 - 
 
233 
				$temp = str_replace( $set, '&', $temp );
 - 
 
234 
 
 - 
 
235 
				$this->debug['parse'][] = "2b1 (temp:$temp)";
 - 
 
236 
 
 - 
 
237 
				// remove any content in angle brackets (e.g. html tags - <i>, </i>, etc.)
 - 
 
238 
				$html_pattern = "(\<(/?[^\>]+)\>)";
 - 
 
239 
//? This should not just handle html tags but all <*>
- 
 
240 
				$temp = preg_replace( $html_pattern, '', $temp);
 - 
 
241 
				$this->debug['parse'][] = "2b2 (temp:$temp)";
 - 
 
242 
 
 - 
 
243 
				// if second term (only) is in round brackets, presume it is a subgenus or a comment and remove it
 - 
 
244 
				// examples: Barbatia (Mesocibota) bistrigata (Dunker, 1866) => Barbatia bistrigata (Dunker, 1866)
 - 
 
245 
				// Barbatia (?) bistrigata (Dunker, 1866) => Barbatia bistrigata (Dunker, 1866)
 - 
 
246 
				// (obviously this will not suit genus + author alone, where first part of authorname is in brackets,
 - 
 
247 
				// however this is very rare?? and in any case we are not supporting genus+authority in this version)
 - 
 
248 
//if ( $temp like '% (%)%'
 - 
 
249 
				$temp = preg_replace( "/ \(\w*\W*\)/", '', $temp, 1 );
 - 
 
250 
//? Not sure if this will catch if
- 
 
251 
				$this->debug['parse'][] = "2b3 (temp:$temp)";
 - 
 
252 
 
 - 
 
253 
				// if second term (only) is in square brackets, presume it is a comment and remove it
 - 
 
254 
				// example: Aphis [?] ficus Theobald, [1918] => Aphis ficus Theobald, [1918]
- 
 
255 
//if ( $temp like '% [%]%'
 - 
 
256 
				$temp = preg_replace( "/ \[\w*\W*\]/", '', $temp, 1 );
 253 
			$temp = preg_replace( "/ \[\w*\W*\]/", '', $temp, 1 );
257 
//? Not sure if this will catch if
254 
			//? Not sure if this will catch if
258 
				$this->debug['parse'][] = "2b4 (temp:$temp)";
 255 
			//$this->debug['parse'][] = "2b4 (temp:$temp)";
Line 259... Line 256...
259 
 
 256 
 
Line 260... Line 257...
260 
				// drop indicators of questionable id's - presume all are lowercase for now (could extend as needed)
 257 
			// drop indicators of questionable id's - presume all are lowercase for now (could extend as needed)
261 
				$temp = preg_replace( "/ cf /", " ", $temp );
 258 
			$temp = preg_replace( "/ cf /", " ", $temp );
262 
				$temp = preg_replace( "/ cf\. /", " ", $temp );
 259 
			$temp = preg_replace( "/ cf\. /", " ", $temp );
263 
				$temp = preg_replace( "/ near /", " ", $temp );
 260 
			$temp = preg_replace( "/ near /", " ", $temp );
264 
				$temp = preg_replace( "/ aff\. /", " ", $temp );
 261 
			$temp = preg_replace( "/ aff\. /", " ", $temp );
265 
				$temp = preg_replace( "/ sp\. /", " ", $temp );
 262 
			$temp = preg_replace( "/ sp\. /", " ", $temp );
266 
				$temp = preg_replace( "/ spp\. /", " ", $temp );
 263 
			$temp = preg_replace( "/ spp\. /", " ", $temp );
267 
				$temp = preg_replace( "/ spp /", " ", $temp );
 264 
			$temp = preg_replace( "/ spp /", " ", $temp );
268 
 
 265 
 
269 
				$this->debug['parse'][] = "2b5 (temp:$temp)";
 266 
			//$this->debug['parse'][] = "2b5 (temp:$temp)";
Line 270... Line 267...
270 
 
 267 
 
Line 271... Line 268...
271 
				// eliminate or close up any stray spaces introduced by the above
 268 
			// eliminate or close up any stray spaces introduced by the above
272 
				$temp = $this->reduce_spaces( $temp );
 269 
			$temp = $this->reduce_spaces( $temp );
273 
 
 270 
 
274 
				$this->debug['parse'][] = "2b6 (temp:$temp)";
 271 
			//$this->debug['parse'][] = "2b6 (temp:$temp)";
275 
 
 272 
 
- 
 
 273 
			// now presume first element is genus, second (if present) is species, remainder
- 
 
 274 
			//   (if present) is authority
276 
				// now presume first element is genus, second (if present) is species, remainder
 275 
			// look for genus name
277 
				//   (if present) is authority
 276 
			$ar = explode( " ", $temp, 2);
278 
				// look for genus name
 277 
			if ( count( $ar ) ) {
279 
				$ar = explode( " ", $temp, 2);
 278 
				$temp_genus = $ar[0];
280 
				if ( count( $ar ) ) {
 - 
 
281 
					$temp_genus = $ar[0];
 279 
				$temp = @$ar[1];
282 
					$temp = @$ar[1];
 280 
			} else {
283 
				} else {
 281 
				$temp_genus = $temp;
284 
					$temp_genus = $temp;
 282 
				$temp = '';
285 
					$temp = '';
 283 
			}
286 
				}
 284
287
285 
			//$this->debug['parse'][] = "2b7 (temp_genus:$temp_genus) (temp:$temp)";
288 
				$this->debug['parse'][] = "2b7 (temp_genus:$temp_genus) (temp:$temp)";
 286 
 
289 
 
 287 
			// look for species epithet and authority
290 
				// look for species epithet and authority
 288 
			$ar = explode( " ", $temp, 2);
291 
				$ar = explode( " ", $temp, 2);
 - 
 
292 
				if ( count( $ar ) ) {
 - 
 
293 
					$temp_species = $ar[0];
 289 
			if ( count( $ar ) ) {
- 
 
 290 
				$temp_species = $ar[0];
294 
					$temp_authority = @$ar[1];
 291 
				$temp_authority = @$ar[1];
295 
				} else {
 - 
 
296 
					$temp_species = $temp;
 - 
 
297 
					$temp_authority = '';
 - 
 
298 
				}
 - 
 
299 
               	// look for subspecies
 - 
 
300 
 
 - 
 
301 
                $infras =array('subsp.','var.');
 - 
 
302 
 
 - 
 
303 
                $temp_authority = preg_replace( "/ssp./", "subsp.", $temp_authority);
 - 
 
304 
                $temp_authority = preg_replace( "/ssp /", "subsp.", $temp_authority);
 - 
 
305 
                $temp_authority = preg_replace( "/subsp /", "subsp.", $temp_authority);
 - 
 
306 
                $temp_authority = preg_replace( "/var /", "var.", $temp_authority);
 - 
 
307 
 
 - 
 
308 
                foreach ($infras as $infra) {
 - 
 
309 
                    $pos = strpos($temp_authority, $infra);
 - 
 
310 
                    if ($pos === false) {
 - 
 
311 
                        continue;
 - 
 
312 
                    }
 - 
 
313 
                    else {
 - 
 
314 
                        $temp_infra=substr($temp_authority,$pos+strlen($infra));
 - 
 
315 
                        $temp_authority=substr($temp_authority,0,$pos);
 - 
 
316 
                        $temp_infra=trim($temp_infra);
 - 
 
317 
                        $temp_infra_type=$infra;
 - 
 
318 
                        // look for infra epithet and authority
 - 
 
319 
                        $ar = explode(" ", $temp_infra, 2);
 - 
 
320 
                        if ( count( $ar ) ) {
 - 
 
321 
                            $temp_infra = $ar[0];
 - 
 
322 
                            $temp_infra_authority = @$ar[1];
 - 
 
323 
                        }
 - 
 
324 
                        break; // on s'arrete au premier trouve
 - 
 
325 
                    }
 - 
 
326 
                }
 - 
 
327 
 
 - 
 
328 
				$this->debug['parse'][] = "2b8 (temp_genus:$temp_genus) (temp_species:$temp_species) (temp_authority:$temp_authority) (temp_infra:$temp_infra) (temp_infra_authority:$temp_infra_authority) (temp:$temp)";
 - 
 
329 
 
 - 
 
330 
 
 - 
 
331 
				// replace selected ligatures here (Genus names can contain Æ, OE ligature)
 292 
			} else {
332 
				$temp_genus = str_replace( 'Æ', 'AE', $temp_genus);
 - 
 
333 
				$temp_species = str_replace( 'Æ', 'AE', $temp_species);
 - 
 
Line 334... Line -...
334 
				$temp_infra = str_replace( 'Æ', 'AE', $temp_infra );
 - 
 
335
- 
 
336 
 
 - 
 
- 
 
 293 
				$temp_species = $temp;
Line -... Line 294...
- 
 
 294 
				$temp_authority = '';
- 
 
 295 
			}
- 
 
 296 
            // look for subspecies
- 
 
 297 
 
- 
 
 298 
            $infras =array('subsp.','var.');
- 
 
 299 
 
- 
 
 300 
            $temp_authority = preg_replace( "/ssp./", "subsp.", $temp_authority);
- 
 
 301 
            $temp_authority = preg_replace( "/ssp /", "subsp.", $temp_authority);
- 
 
 302 
            $temp_authority = preg_replace( "/subsp /", "subsp.", $temp_authority);
- 
 
 303 
            $temp_authority = preg_replace( "/var /", "var.", $temp_authority);
- 
 
 304 
 
- 
 
 305 
            $temp_infra_authority = '';
- 
 
 306 
            $temp_infra_type = '';
- 
 
 307 
            foreach ($infras as $infra) {
- 
 
 308 
            	$pos = strpos($temp_authority, $infra);
- 
 
 309 
                if ($pos === false) {
- 
 
 310 
                	continue;
- 
 
 311 
                } else {
- 
 
 312 
                	$temp_infra=substr($temp_authority,$pos+strlen($infra));
- 
 
 313 
                    $temp_authority=substr($temp_authority,0,$pos);
- 
 
 314 
                    $temp_infra=trim($temp_infra);
- 
 
 315 
                    $temp_infra_type=$infra;
- 
 
 316 
                    // look for infra epithet and authority
- 
 
 317 
                    $ar = explode(" ", $temp_infra, 2);
- 
 
 318 
                    if ( count( $ar ) ) {
- 
 
 319 
                    	$temp_infra = $ar[0];
- 
 
 320 
                        $temp_infra_authority = @$ar[1];
- 
 
 321 
                    }
- 
 
 322 
                    break; // on s'arrete au premier trouve
- 
 
 323 
                }
337 
				$this->debug['parse'][] = "2b9 (temp_genus:$temp_genus) (temp_species:$temp_species) (temp_authority:$temp_authority) (temp_infra:$temp_infra) (temp_infra_authority:$temp_infra_authority) (temp:$temp)";
 324 
			}
338 
 
 325