Browse Source

updated pear LangDetect to version 1.0.0

pull/3678/head
Tobias Diekershoff 4 years ago
parent
commit
c86840c4b9
  1. 157
      library/langdet/README.rst
  2. 174
      library/langdet/Text/LanguageDetect.php
  3. 24
      library/langdet/Text/LanguageDetect/Exception.php
  4. 3
      library/langdet/Text/LanguageDetect/ISO639.php
  5. 189
      library/langdet/Text/LanguageDetect/Parser.php
  6. 7
      library/langdet/data/build-unicode_blocks.php
  7. 2
      library/langdet/data/unicode_blocks.dat
  8. 874
      library/langdet/data/unicode_blocks.php
  9. 18
      library/langdet/docs/confidence.php
  10. 15
      library/langdet/docs/errorhandling.php
  11. 2
      library/langdet/docs/example_clui.php
  12. 2
      library/langdet/docs/example_web.php
  13. 14
      library/langdet/docs/iso.php
  14. 11
      library/langdet/docs/languages.php
  15. 10
      library/langdet/docs/simple.php
  16. 42
      library/langdet/tests/PrivProxy.php
  17. 117
      library/langdet/tests/Text_LanguageDetectTest.php

157
library/langdet/README.rst

@ -0,0 +1,157 @@
*******************
Text_LanguageDetect
*******************
PHP library to identify human languages from text samples.
Returns confidence scores for each.
Installation
============
PEAR
----
::
$ pear install Text_LanguageDetect
Composer
--------
::
$ composer require pear/text_languagedetect
Usage
=====
Also see the examples in the ``docs/`` directory and
the `official documentation`__.
__ http://pear.php.net/package/Text_LanguageDetect/docs
Language detection
------------------
Simple language detection::
<?php
require_once 'Text/LanguageDetect.php';
$text = 'Was wäre, wenn ich Ihnen das jetzt sagen würde?';
$ld = new Text_LanguageDetect();
$language = $ld->detectSimple($text);
echo $language;
//output: german
Show the three most probable languages with their confidence score::
<?php
require_once 'Text/LanguageDetect.php';
$text = 'Was wäre, wenn ich Ihnen das jetzt sagen würde?';
$ld = new Text_LanguageDetect();
//3 most probable languages
$results = $ld->detect($text, 3);
foreach ($results as $language => $confidence) {
echo $language . ': ' . number_format($confidence, 2) . "\n";
}
//output:
//german: 0.35
//dutch: 0.25
//swedish: 0.20
?>
Language code
-------------
Instead of returning the full language name, ISO 639-2 two and three
letter codes can be returned::
<?php
require_once 'Text/LanguageDetect.php';
$ld = new Text_LanguageDetect();
//will output the ISO 639-1 two-letter language code
// "de"
$ld->setNameMode(2);
echo $ld->detectSimple('Das ist ein kleiner Text') . "\n";
//will output the ISO 639-2 three-letter language code
// "deu"
$ld->setNameMode(3);
echo $ld->detectSimple('Das ist ein kleiner Text') . "\n";
?>
Supported languages
===================
- albanian
- arabic
- azeri
- bengali
- bulgarian
- cebuano
- croatian
- czech
- danish
- dutch
- english
- estonian
- farsi
- finnish
- french
- german
- hausa
- hawaiian
- hindi
- hungarian
- icelandic
- indonesian
- italian
- kazakh
- kyrgyz
- latin
- latvian
- lithuanian
- macedonian
- mongolian
- nepali
- norwegian
- pashto
- pidgin
- polish
- portuguese
- romanian
- russian
- serbian
- slovak
- slovene
- somali
- spanish
- swahili
- swedish
- tagalog
- turkish
- ukrainian
- urdu
- uzbek
- vietnamese
- welsh
Links
=====
Homepage
http://pear.php.net/package/Text_LanguageDetect
Bug tracker
http://pear.php.net/bugs/search.php?cmd=display&package_name[]=Text_LanguageDetect
Documentation
http://pear.php.net/package/Text_LanguageDetect/docs
Unit test status
https://travis-ci.org/pear/Text_LanguageDetect
.. image:: https://travis-ci.org/pear/Text_LanguageDetect.svg?branch=master
:target: https://travis-ci.org/pear/Text_LanguageDetect

174
library/langdet/Text/LanguageDetect.php

@ -1,13 +1,6 @@
<?php
/**
* Detects the language of a given piece of text.
*
* Attempts to detect the language of a sample of text by correlating ranked
* 3-gram frequencies to a table of 3-gram frequencies of known languages.
*
* Implements a version of a technique originally proposed by Cavnar & Trenkle
* (1994): "N-Gram-Based Text Categorization"
* Part of Text_LanguageDetect
*
* PHP version 5
*
@ -15,20 +8,24 @@
* @package Text_LanguageDetect
* @author Nicholas Pisarro <infinityminusnine+pear@gmail.com>
* @copyright 2005-2006 Nicholas Pisarro
* @license http://www.debian.org/misc/bsd.license BSD
* @version SVN: $Id: LanguageDetect.php 322353 2012-01-16 08:41:43Z cweiske $
* @license BSD http://www.opensource.org/licenses/bsd-license.php
* @link http://pear.php.net/package/Text_LanguageDetect/
* @link http://langdetect.blogspot.com/
*/
require_once 'library/langdet/Text/LanguageDetect/Exception.php';
require_once 'library/langdet/Text/LanguageDetect/Parser.php';
require_once 'library/langdet/Text/LanguageDetect/ISO639.php';
require_once 'Text/LanguageDetect/Exception.php';
require_once 'Text/LanguageDetect/Parser.php';
require_once 'Text/LanguageDetect/ISO639.php';
/**
* Language detection class
* Detects the language of a given piece of text.
*
* Attempts to detect the language of a sample of text by correlating ranked
* 3-gram frequencies to a table of 3-gram frequencies of known languages.
*
* Implements a version of a technique originally proposed by Cavnar & Trenkle
* (1994): "N-Gram-Based Text Categorization"
*
* Requires the langauge model database (lang.dat) that should have
* Requires the language model database (lang.dat) that should have
* accompanied this class definition in order to be instantiated.
*
* Example usage:
@ -60,10 +57,9 @@ require_once 'library/langdet/Text/LanguageDetect/ISO639.php';
* @package Text_LanguageDetect
* @author Nicholas Pisarro <infinityminusnine+pear@gmail.com>
* @copyright 2005 Nicholas Pisarro
* @license http://www.debian.org/misc/bsd.license BSD
* @license BSD http://www.opensource.org/licenses/bsd-license.php
* @version Release: @package_version@
* @link http://pear.php.net/package/Text_LanguageDetect/
* @todo allow users to generate their own language models
*/
class Text_LanguageDetect
{
@ -73,10 +69,9 @@ class Text_LanguageDetect
* If this value starts with a slash (/) or a dot (.) the value of
* $this->_data_dir will be ignored
*
* @var string
* @access private
* @var string
*/
var $_db_filename = 'lang.dat';
protected $_db_filename = 'lang.dat';
/**
* The filename that stores the unicode block definitions
@ -85,83 +80,74 @@ class Text_LanguageDetect
* $this->_data_dir will be ignored
*
* @var string
* @access private
*/
var $_unicode_db_filename = 'unicode_blocks.dat';
protected $_unicode_db_filename = 'unicode_blocks.dat';
/**
* The data directory
*
* Should be set by PEAR installer
*
* @var string
* @access private
* @var string
*/
var $_data_dir = '@data_dir@';
protected $_data_dir = '@data_dir@';
/**
* The trigram data for comparison
*
* Will be loaded on start from $this->_db_filename
*
* @var array
* @access private
* @var array
*/
var $_lang_db = array();
protected $_lang_db = array();
/**
* stores the map of the trigram data to unicode characters
* Stores the map of the trigram data to unicode characters
*
* @access private
* @var array
*/
var $_unicode_map;
protected $_unicode_map;
/**
* The size of the trigram data arrays
*
* @var int
* @access private
* @var int
*/
var $_threshold = 300;
protected $_threshold = 300;
/**
* the maximum possible score.
* The maximum possible score.
*
* needed for score normalization. Different depending on the
* Needed for score normalization. Different depending on the
* perl compatibility setting
*
* @access private
* @var int
* @see setPerlCompatible()
* @var int
* @see setPerlCompatible()
*/
var $_max_score = 0;
protected $_max_score = 0;
/**
* Whether or not to simulate perl's Language::Guess exactly
*
* @access private
* @var bool
* @see setPerlCompatible()
* @var bool
* @see setPerlCompatible()
*/
var $_perl_compatible = false;
protected $_perl_compatible = false;
/**
* Whether to use the unicode block detection to speed up processing
*
* @access private
* @var bool
*/
var $_use_unicode_narrowing = true;
protected $_use_unicode_narrowing = true;
/**
* stores the result of the clustering operation
* Stores the result of the clustering operation
*
* @access private
* @var array
* @see clusterLanguages()
* @var array
* @see clusterLanguages()
*/
var $_clusters;
protected $_clusters;
/**
* Which type of "language names" are accepted and returned:
@ -170,7 +156,7 @@ class Text_LanguageDetect
* 2 - 2-letter ISO 639-1 code ("en")
* 3 - 3-letter ISO 639-2 code ("eng")
*/
var $_name_mode = 0;
protected $_name_mode = 0;
/**
* Constructor
@ -178,7 +164,7 @@ class Text_LanguageDetect
* Will attempt to load the language database. If it fails, you will get
* an exception.
*/
function __construct()
public function __construct()
{
$data = $this->_readdb($this->_db_filename);
$this->_checkTrigram($data['trigram']);
@ -200,9 +186,8 @@ class Text_LanguageDetect
* @param string $fname File name to load
*
* @return string expected path to the language model database
* @access private
*/
function _get_data_loc($fname)
protected function _get_data_loc($fname)
{
if ($fname{0} == '/' || $fname{0} == '.') {
// if filename starts with a slash, assume it's an absolute pathname
@ -229,9 +214,8 @@ class Text_LanguageDetect
*
* @return array the language model data
* @throws Text_LanguageDetect_Exception
* @access private
*/
function _readdb($fname)
protected function _readdb($fname)
{
// finds the correct data dir
$fname = $this->_get_data_loc($fname);
@ -259,9 +243,8 @@ class Text_LanguageDetect
* @param array $trigram Trigram data from database
*
* @return void
* @access private
*/
function _checkTrigram($trigram)
protected function _checkTrigram($trigram)
{
if (!is_array($trigram)) {
if (ini_get('magic_quotes_runtime')) {
@ -353,11 +336,10 @@ class Text_LanguageDetect
/**
* Returns the number of languages that this object can detect
*
* @access public
* @return int the number of languages
* @throws Text_LanguageDetect_Exception
* @throws Text_LanguageDetect_Exception
*/
function getLanguageCount()
public function getLanguageCount()
{
return count($this->_lang_db);
}
@ -395,11 +377,10 @@ class Text_LanguageDetect
/**
* Returns the list of detectable languages
*
* @access public
* @return array the names of the languages known to this object
* @throws Text_LanguageDetect_Exception
* @return array the names of the languages known to this object<<<<<<<
* @throws Text_LanguageDetect_Exception
*/
function getLanguages()
public function getLanguages()
{
return $this->_convertToNameMode(
array_keys($this->_lang_db)
@ -437,7 +418,7 @@ class Text_LanguageDetect
*
* @return void
*/
function setNameMode($name_mode)
public function setNameMode($name_mode)
{
$this->_name_mode = $name_mode;
}
@ -467,10 +448,9 @@ class Text_LanguageDetect
* @param string $text text to convert
*
* @return array array of trigram frequencies
* @access private
* @deprecated Superceded by the Text_LanguageDetect_Parser class
*/
function _trigram($text)
protected function _trigram($text)
{
$s = new Text_LanguageDetect_Parser($text);
$s->prepareTrigram();
@ -488,9 +468,8 @@ class Text_LanguageDetect
* @param array $arr array of trigram
*
* @return array ranks of trigrams
* @access protected
*/
function _arr_rank($arr)
protected function _arr_rank($arr)
{
// sorts alphabetically first as a standard way of breaking rank ties
@ -518,12 +497,11 @@ class Text_LanguageDetect
/**
* Sorts an array by value breaking ties alphabetically
*
* @param array &$arr the array to sort
* @param array $arr the array to sort
*
* @return void
* @access private
*/
function _bub_sort(&$arr)
protected function _bub_sort(&$arr)
{
// should do the same as this perl statement:
// sort { $trigrams{$b} == $trigrams{$a}
@ -561,9 +539,8 @@ class Text_LanguageDetect
*
* @return int 1 if $a is greater, -1 if not
* @see _bub_sort()
* @access private
*/
function _sort_func($a, $b)
protected function _sort_func($a, $b)
{
// each is actually a key/value pair, so that it can compare using both
list($a_key, $a_value) = $a;
@ -601,9 +578,8 @@ class Text_LanguageDetect
*
* @return int the sum of the differences between the ranks of
* the two trigram sets
* @access private
*/
function _distance($arr1, $arr2)
protected function _distance($arr1, $arr2)
{
$sumdist = 0;
@ -634,9 +610,8 @@ class Text_LanguageDetect
*
* @return float the normalized score
* @see _distance()
* @access private
*/
function _normalize_score($score, $base_count = null)
protected function _normalize_score($score, $base_count = null)
{
if ($base_count === null) {
$base_count = $this->_threshold;
@ -712,7 +687,7 @@ class Text_LanguageDetect
$sample_obj->setPadStart(!$this->_perl_compatible);
$sample_obj->analyze();
$trigram_freqs =& $sample_obj->getTrigramRanks();
$trigram_freqs = $sample_obj->getTrigramRanks();
$trigram_count = count($trigram_freqs);
if ($trigram_count == 0) {
@ -723,7 +698,7 @@ class Text_LanguageDetect
// use unicode block detection to narrow down the possibilities
if ($this->_use_unicode_narrowing) {
$blocks =& $sample_obj->getUnicodeBlocks();
$blocks = $sample_obj->getUnicodeBlocks();
if (is_array($blocks)) {
$present_blocks = array_keys($blocks);
@ -975,9 +950,8 @@ class Text_LanguageDetect
*
* @return mixed Block name, -1 if it failed
* @see unicodeBlockName()
* @access protected
*/
function _unicode_block_name($unicode, $blocks, $block_count = -1)
protected function _unicode_block_name($unicode, $blocks, $block_count = -1)
{
// for a reference, see
// http://www.unicode.org/Public/UNIDATA/Blocks.txt
@ -1028,9 +1002,8 @@ class Text_LanguageDetect
*
* @return array the database of unicode block definitions
* @throws Text_LanguageDetect_Exception
* @access protected
*/
function _read_unicode_block_db()
protected function _read_unicode_block_db()
{
// since the unicode definitions are always going to be the same,
// might as well share the memory for the db with all other instances
@ -1149,14 +1122,13 @@ class Text_LanguageDetect
* Uses a nearest neighbor technique to generate the maximum possible
* number of dendograms from the similarity data.
*
* @access public
* @return array language cluster data
* @throws Text_LanguageDetect_Exception
* @see languageSimilarity()
* @deprecated this function will eventually be removed and placed into
* @return array language cluster data
* @throws Text_LanguageDetect_Exception
* @see languageSimilarity()
* @deprecated this function will eventually be removed and placed into
* the model generation class
*/
function clusterLanguages()
public function clusterLanguages()
{
// todo: set the maximum number of clusters
// return cached result, if any
@ -1465,7 +1437,7 @@ class Text_LanguageDetect
}
/**
* ut8-safe strlen()
* UTF8-safe strlen()
*
* Returns the numbers of characters (not bytes) in a utf8 string
*
@ -1489,10 +1461,9 @@ class Text_LanguageDetect
* @param string $char a utf8 (possibly multi-byte) char
*
* @return int unicode value
* @access protected
* @link http://en.wikipedia.org/wiki/UTF-8
*/
function _utf8char2unicode($char)
protected function _utf8char2unicode($char)
{
// strlen() here will actually get the binary length of a single char
switch (strlen($char)) {
@ -1529,20 +1500,19 @@ class Text_LanguageDetect
}
/**
* utf8-safe fast character iterator
* UTF8-safe fast character iterator
*
* Will get the next character starting from $counter, which will then be
* incremented. If a multi-byte char the bytes will be concatenated and
* $counter will be incremeted by the number of bytes in the char.
*
* @param string $str the string being iterated over
* @param int &$counter the iterator, will increment by reference
* @param int $counter the iterator, will increment by reference
* @param bool $special_convert whether to do special conversions
*
* @return char the next (possibly multi-byte) char from $counter
* @access private
*/
static function _next_char($str, &$counter, $special_convert = false)
protected static function _next_char($str, &$counter, $special_convert = false)
{
$char = $str{$counter++};
$ord = ord($char);
@ -1634,7 +1604,7 @@ class Text_LanguageDetect
*
* @return string|array Language name
*/
function _convertFromNameMode($lang, $convertKey = false)
protected function _convertFromNameMode($lang, $convertKey = false)
{
if ($this->_name_mode == 0) {
return $lang;
@ -1674,7 +1644,7 @@ class Text_LanguageDetect
*
* @return string|array Language name
*/
function _convertToNameMode($lang, $convertKey = false)
protected function _convertToNameMode($lang, $convertKey = false)
{
if ($this->_name_mode == 0) {
return $lang;

24
library/langdet/Text/LanguageDetect/Exception.php

@ -1,4 +1,28 @@
<?php
/**
* Part of Text_LanguageDetect
*
* PHP version 5
*
* @category Text
* @package Text_LanguageDetect
* @author Nicholas Pisarro <infinityminusnine+pear@gmail.com>
* @license BSD http://www.opensource.org/licenses/bsd-license.php
* @link http://pear.php.net/package/Text_LanguageDetect/
*/
/**
* Part of the PEAR language detection package
*
* PHP version 5
*
* @category Text
* @package Text_LanguageDetect
* @author Nicholas Pisarro <infinityminusnine+pear@gmail.com>
* @license BSD http://www.opensource.org/licenses/bsd-license.php
* @link http://pear.php.net/package/Text_LanguageDetect/
* @link http://langdetect.blogspot.com/
*/
class Text_LanguageDetect_Exception extends Exception
{
/**

3
library/langdet/Text/LanguageDetect/ISO639.php

@ -9,7 +9,6 @@
* @author Christian Weiske <cweiske@php.net>
* @copyright 2011 Christian Weiske <cweiske@php.net>
* @license http://www.debian.org/misc/bsd.license BSD
* @version SVN: $Id$
* @link http://pear.php.net/package/Text_LanguageDetect/
*/
@ -23,7 +22,7 @@
* @package Text_LanguageDetect
* @author Christian Weiske <cweiske@php.net>
* @copyright 2011 Christian Weiske <cweiske@php.net>
* @license http://www.debian.org/misc/bsd.license BSD
* @license BSD http://www.opensource.org/licenses/bsd-license.php
* @link http://www.loc.gov/standards/iso639-2/php/code_list.php
*/
class Text_LanguageDetect_ISO639

189
library/langdet/Text/LanguageDetect/Parser.php

@ -1,16 +1,15 @@
<?php
/**
* This class represents a text sample to be parsed.
* Part of Text_LanguageDetect
*
* PHP version 5
*
* @category Text
* @package Text_LanguageDetect
* @author Nicholas Pisarro
* @copyright 2006
* @license BSD
* @version CVS: $Id: Parser.php 322327 2012-01-15 17:55:59Z cweiske $
* @link http://pear.php.net/package/Text_LanguageDetect/
* @link http://langdetect.blogspot.com/
* @category Text
* @package Text_LanguageDetect
* @author Nicholas Pisarro <infinityminusnine+pear@gmail.com>
* @copyright 2006 Nicholas Pisarro
* @license BSD http://www.opensource.org/licenses/bsd-license.php
* @link http://pear.php.net/package/Text_LanguageDetect/
*/
/**
@ -20,99 +19,106 @@
* class. After a new profile has been built, the data can be retrieved using
* the accessor functions.
*
* This class is intended to be used by the Text_LanguageDetect class, not
* This class is intended to be used by the Text_LanguageDetect class, not
* end-users.
*
* @category Text
* @package Text_LanguageDetect
* @author Nicholas Pisarro
* @copyright 2006
* @license BSD
* @version release: 0.3.0
* @category Text
* @package Text_LanguageDetect
* @author Nicholas Pisarro <infinityminusnine+pear@gmail.com>
* @copyright 2006 Nicholas Pisarro
* @license BSD http://www.opensource.org/licenses/bsd-license.php
* @version Release: @package_version@
* @link http://pear.php.net/package/Text_LanguageDetect/
*/
class Text_LanguageDetect_Parser extends Text_LanguageDetect
{
/**
* the piece of text being parsed
* The piece of text being parsed
*
* @access private
* @var string
* @var string
*/
var $_string;
protected $_string;
/**
* stores the trigram frequencies of the sample
* Stores the trigram frequencies of the sample
*
* @access private
* @var string
* @var string
*/
var $_trigrams = array();
protected $_trigrams = array();
/**
* stores the trigram ranks of the sample
* Stores the trigram ranks of the sample
*
* @access private
* @var array
* @var array
*/
var $_trigram_ranks = array();
protected $_trigram_ranks = array();
/**
* stores the unicode blocks of the sample
* Stores the unicode blocks of the sample
*
* @access private
* @var array
* @var array
*/
var $_unicode_blocks = array();
protected $_unicode_blocks = array();
/**
* Whether the parser should compile the unicode ranges
*
* @access private
* @var bool
*
* @var bool
*/
var $_compile_unicode = false;
protected $_compile_unicode = false;
/**
* Whether the parser should compile trigrams
*
* @access private
* @var bool
* @var bool
*/
var $_compile_trigram = false;
protected $_compile_trigram = false;
/**
* Whether the trigram parser should pad the beginning of the string
*
* @access private
* @var bool
* @var bool
*/
var $_trigram_pad_start = false;
protected $_trigram_pad_start = false;
/**
* Whether the unicode parser should skip non-alphabetical ascii chars
*
* @access private
* @var bool
* @var bool
*/
var $_unicode_skip_symbols = true;
protected $_unicode_skip_symbols = true;
/**
* Constructor
*
* @access private
* @param string $string string to be parsed
* @param string $string string to be parsed
*/
function Text_LanguageDetect_Parser($string) {
public function __construct($string)
{
$this->_string = $string;
}
/**
* PHP 4 constructor for backwards compatibility.
*
* @param string $string string to be parsed
*
* @return void
*/
public function Text_LanguageDetect_Parser($string)
{
self::__construct($string);
}
/**
* Returns true if a string is suitable for parsing
*
* @param string $str input string to test
* @return bool true if acceptable, false if not
* @param string $str input string to test
*
* @return bool true if acceptable, false if not
*/
public static function validateString($str) {
public static function validateString($str)
{
if (!empty($str) && strlen($str) > 3 && preg_match('/\S/', $str)) {
return true;
} else {
@ -121,34 +127,37 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
}
/**
* turn on/off trigram counting
* Turn on/off trigram counting
*
* @access public
* @param bool $bool true for on, false for off
* @param bool $bool true for on, false for off
*
* @return void
*/
function prepareTrigram($bool = true)
public function prepareTrigram($bool = true)
{
$this->_compile_trigram = $bool;
}
/**
* turn on/off unicode block counting
* Turn on/off unicode block counting
*
* @param bool $bool true for on, false for off
*
* @access public
* @param bool $bool true for on, false for off
* @return void
*/
function prepareUnicode($bool = true)
public function prepareUnicode($bool = true)
{
$this->_compile_unicode = $bool;
}
/**
* turn on/off padding the beginning of the sample string
* Turn on/off padding the beginning of the sample string
*
* @param bool $bool true for on, false for off
*
* @access public
* @param bool $bool true for on, false for off
* @return void
*/
function setPadStart($bool = true)
public function setPadStart($bool = true)
{
$this->_trigram_pad_start = $bool;
}
@ -156,10 +165,11 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
/**
* Should the unicode block counter skip non-alphabetical ascii chars?
*
* @access public
* @param bool $bool true for on, false for off
* @param bool $bool true for on, false for off
*
* @return void
*/
function setUnicodeSkipSymbols($bool = true)
public function setUnicodeSkipSymbols($bool = true)
{
$this->_unicode_skip_symbols = $bool;
}
@ -167,10 +177,9 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
/**
* Returns the trigram ranks for the text sample
*
* @access public
* @return array trigram ranks in the text sample
* @return array Trigram ranks in the text sample
*/
function &getTrigramRanks()
public function getTrigramRanks()
{
return $this->_trigram_ranks;
}
@ -178,39 +187,37 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
/**
* Return the trigram freqency table
*
* only used in testing to make sure the parser is working
* Only used in testing to make sure the parser is working
*
* @access public
* @return array trigram freqencies in the text sample
* @return array Trigram freqencies in the text sample
*/
function &getTrigramFreqs()
public function getTrigramFreqs()
{
return $this->_trigram;
}
/**
* returns the array of unicode blocks
* Returns the array of unicode blocks
*
* @access public
* @return array unicode blocks in the text sample
* @return array Unicode blocks in the text sample
*/
function &getUnicodeBlocks()
public function getUnicodeBlocks()
{
return $this->_unicode_blocks;
}
/**
* Executes the parsing operation
*
* Be sure to call the set*() functions to set options and the
*
* Be sure to call the set*() functions to set options and the
* prepare*() functions first to tell it what kind of data to compute
*
* Afterwards the get*() functions can be used to access the compiled
* information.
*
* @access public
* @return void
*/
function analyze()
public function analyze()
{
$len = strlen($this->_string);
$byte_counter = 0;
@ -258,9 +265,9 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
if ($this->_compile_trigram) {
if (!($b == ' ' && ($a == ' ' || $char == ' '))) {
if (!isset($this->_trigram[$a . $b . $char])) {
$this->_trigram[$a . $b . $char] = 1;
$this->_trigram[$a . $b . $char] = 1;
} else {
$this->_trigram[$a . $b . $char]++;
$this->_trigram[$a . $b . $char]++;
}
}
@ -271,10 +278,11 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
// unicode block detection
if ($this->_compile_unicode) {
if ($this->_unicode_skip_symbols
&& strlen($char) == 1
&& ($char < 'A' || $char > 'z'
|| ($char > 'Z' && $char < 'a'))
&& $char != "'") { // does not skip the apostrophe
&& strlen($char) == 1
&& ($char < 'A' || $char > 'z'
|| ($char > 'Z' && $char < 'a'))
&& $char != "'"
) { // does not skip the apostrophe
// since it's included in the language
// models
@ -297,7 +305,8 @@ class Text_LanguageDetect_Parser extends Text_LanguageDetect
if ($this->_compile_unicode) {
foreach ($unicode_chars as $utf8_char => $count) {
$search_result = $this->_unicode_block_name(
$this->_utf8char2unicode($utf8_char), $blocks, $block_count);
$this->_utf8char2unicode($utf8_char), $blocks, $block_count
);
if ($search_result != -1) {
$block_name = $search_result[2];

7
library/langdet/data/build-unicode_blocks.php

@ -0,0 +1,7 @@
<?php
/**
* Generate the serialized unicode_blocks.dat file shipped with the package
*/
$unicode_blocks = include __DIR__ . '/unicode_blocks.php';
file_put_contents(__DIR__ . '/unicode_blocks.dat', serialize($unicode_blocks));
?>

2
library/langdet/data/unicode_blocks.dat
File diff suppressed because it is too large
View File

874
library/langdet/data/unicode_blocks.php

@ -0,0 +1,874 @@
<?php
return array (
0 =>
array (
0 => 0x0000,
1 => 0x007F,
2 => 'Basic Latin',
),
1 =>
array (
0 => 0x0080,
1 => 0x00FF,
2 => 'Latin-1 Supplement',
),
2 =>
array (
0 => 0x0100,
1 => 0x017F,
2 => 'Latin Extended-A',
),
3 =>
array (
0 => 0x0180,
1 => 0x024F,
2 => 'Latin Extended-B',
),
4 =>
array (
0 => 0x0250,
1 => 0x02AF,
2 => 'IPA Extensions',
),
5 =>
array (
0 => 0x02B0,
1 => 0x02FF,
2 => 'Spacing Modifier Letters',
),
6 =>
array (
0 => 0x0300,
1 => 0x036F,
2 => 'Combining Diacritical Marks',
),
7 =>
array (
0 => 0x0370,
1 => 0x03FF,
2 => 'Greek and Coptic',
),
8 =>
array (
0 => 0x0400,
1 => 0x04FF,
2 => 'Cyrillic',
),
9 =>
array (
0 => 0x0500,
1 => 0x052F,
2 => 'Cyrillic Supplement',
),
10 =>
array (
0 => 0x0530,
1 => 0x058F,
2 => 'Armenian',
),
11 =>
array (
0 => 0x0590,
1 => 0x05FF,
2 => 'Hebrew',
),
12 =>
array (
0 => 0x0600,
1 => 0x06FF,
2 => 'Arabic',
),
13 =>
array (
0 => 0x0700,
1 => 0x074F,
2 => 'Syriac',
),
14 =>
array (
0 => 0x0750,
1 => 0x077F,
2 => 'Arabic Supplement',
),
15 =>
array (
0 => 0x0780,
1 => 0x07BF,
2 => 'Thaana',
),
16 =>
array (
0 => 0x0900,
1 => 0x097F,
2 => 'Devanagari',
),
17 =>
array (
0 => 0x0980,
1 => 0x09FF,
2 => 'Bengali',
),
18 =>
array (
0 => 0x0A00,
1 => 0x0A7F,
2 => 'Gurmukhi',
),
19 =>
array (
0 => 0x0A80,
1 => 0x0AFF,
2 => 'Gujarati',
),
20 =>
array (
0 => 0x0B00,
1 => 0x0B7F,
2 => 'Oriya',
),
21 =>
array (
0 => 0x0B80,
1 => 0x0BFF,
2 => 'Tamil',
),
22 =>
array (
0 => 0x0C00,
1 => 0x0C7F,
2 => 'Telugu',
),
23 =>
array (
0 => 0x0C80,
1 => 0x0CFF,
2 => 'Kannada',
),
24 =>
array (
0 => 0x0D00,
1 => 0x0D7F,
2 => 'Malayalam',
),
25 =>
array (
0 => 0x0D80,
1 => 0x0DFF,
2 => 'Sinhala',
),
26 =>
array (
0 => 0x0E00,
1 => 0x0E7F,
2 => 'Thai',
),
27 =>
array (
0 => 0x0E80,
1 => 0x0EFF,
2 => 'Lao',
),
28 =>
array (
0 => 0x0F00,
1 => 0x0FFF,
2 => 'Tibetan',
),
29 =>
array (
0 => 0x1000,
1 => 0x109F,
2 => 'Myanmar',
),
30 =>
array (
0 => 0x10A0,
1 => 0x10FF,
2 => 'Georgian',
),
31 =>
array (
0 => 0x1100,
1 => 0x11FF,
2 => 'Hangul Jamo',
),
32 =>
array (
0 => 0x1200,
1 => 0x137F,
2 => 'Ethiopic',
),
33 =>
array (
0 => 0x1380,
1 => 0x139F,
2 => 'Ethiopic Supplement',
),
34 =>
array (
0 => 0x13A0,
1 => 0x13FF,
2 => 'Cherokee',
),
35 =>
array (
0 => 0x1400,
1 => 0x167F,
2 => 'Unified Canadian Aboriginal Syllabics',
),
36 =>
array (
0 => 0x1680,
1 => 0x169F,
2 => 'Ogham',
),
37 =>
array (
0 => 0x16A0,
1 => 0x16FF,
2 => 'Runic',
),
38 =>
array (
0 => 0x1700,
1 => 0x171F,
2 => 'Tagalog',
),
39 =>
array (
0 => 0x1720,
1 => 0x173F,
2 => 'Hanunoo',
),
40 =>
array (
0 => 0x1740,
1 => 0x175F,
2 => 'Buhid',
),
41 =>
array (
0 => 0x1760,
1 => 0x177F,
2 => 'Tagbanwa',
),
42 =>
array (
0 => 0x1780,
1 => 0x17FF,
2 => 'Khmer',
),
43 =>
array (
0 => 0x1800,
1 => 0x18AF,
2 => 'Mongolian',
),
44 =>
array (
0 => 0x1900,
1 => 0x194F,
2 => 'Limbu',
),
45 =>
array (
0 => 0x1950,
1 => 0x197F,
2 => 'Tai Le',
),
46 =>
array (
0 => 0x1980,
1 => 0x19DF,
2 => 'New Tai Lue',
),
47 =>
array (
0 => 0x19E0,
1 => 0x19FF,
2 => 'Khmer Symbols',
),
48 =>
array (
0 => 0x1A00,
1 => 0x1A1F,
2 => 'Buginese',
),
49 =>
array (
0 => 0x1D00,
1 => 0x1D7F,
2 => 'Phonetic Extensions',
),
50 =>
array (
0 => 0x1D80,
1 => 0x1DBF,
2 => 'Phonetic Extensions Supplement',
),
51 =>
array (
0 => 0x1DC0,
1 => 0x1DFF,
2 => 'Combining Diacritical Marks Supplement',
),
52 =>
array (
0 => 0x1E00,
1 => 0x1EFF,
2 => 'Latin Extended Additional',
),
53 =>
array (
0 => 0x1F00,
1 => 0x1FFF,
2 => 'Greek Extended',
),
54 =>
array (
0 => 0x2000,
1 => 0x206F,
2 => 'General Punctuation',
),
55 =>
array (
0 => 0x2070,
1 => 0x209F,
2 => 'Superscripts and Subscripts',
),
56 =>
array (
0 => 0x20A0,
1 => 0x20CF,
2 => 'Currency Symbols',
),
57 =>
array (
0 => 0x20D0,
1 => 0x20FF,
2 => 'Combining Diacritical Marks for Symbols',
),
58 =>
array (
0 => 0x2100,
1 => 0x214F,
2 => 'Letterlike Symbols',
),
59 =>
array (
0 => 0x2150,
1 => 0x218F,
2 => 'Number Forms',
),
60 =>
array (
0 => 0x2190,
1 => 0x21FF,
2 => 'Arrows',
),
61 =>
array (
0 => 0x2200,
1 => 0x22FF,
2 => 'Mathematical Operators',
),
62 =>
array (
0 => 0x2300,
1 => 0x23FF,
2 => 'Miscellaneous Technical',
),
63 =>
array (
0 => 0x2400,
1 => 0x243F,
2 => 'Control Pictures',
),
64 =>
array (
0 => 0x2440,
1 => 0x245F,
2 => 'Optical Character Recognition',
),
65 =>
array (
0 => 0x2460,
1 => 0x24FF,
2 => 'Enclosed Alphanumerics',
),
66 =>
array (
0 => 0x2500,
1 => 0x257F,
2 => 'Box Drawing',
),
67 =>
array (
0 => 0x2580,
1 => 0x259F,
2 => 'Block Elements',
),
68 =>
array (
0 => 0x25A0,
1 => 0x25FF,
2 => 'Geometric Shapes',
),
69 =>
array (
0 => 0x2600,
1 => 0x26FF,
2 => 'Miscellaneous Symbols',
),
70 =>
array (
0 => 0x2700,
1 => 0x27BF,
2 => 'Dingbats',
),
71 =>
array (
0 => 0x27C0,
1 => 0x27EF,
2 => 'Miscellaneous Mathematical Symbols-A',
),
72 =>
array (
0 => 0x27F0,
1 => 0x27FF,
2 => 'Supplemental Arrows-A',
),
73 =>
array (
0 => 0x2800,
1 => 0x28FF,
2 => 'Braille Patterns',
),
74 =>
array (
0 => 0x2900,
1 => 0x297F,
2 => 'Supplemental Arrows-B',
),
75 =>
array (
0 => 0x2980,
1 => 0x29FF,
2 => 'Miscellaneous Mathematical Symbols-B',
),
76 =>
array (
0 => 0x2A00,
1 => 0x2AFF,
2 => 'Supplemental Mathematical Operators',
),
77 =>
array (
0 => 0x2B00,
1 => 0x2BFF,
2 => 'Miscellaneous Symbols and Arrows',
),
78 =>
array (
0 => 0x2C00,
1 => 0x2C5F,
2 => 'Glagolitic',
),
79 =>
array (
0 => 0x2C80,
1 => 0x2CFF,
2 => 'Coptic',
),
80 =>
array (
0 => 0x2D00,
1 => 0x2D2F,
2 => 'Georgian Supplement',
),
81 =>
array (
0 => 0x2D30,
1 => 0x2D7F,
2 => 'Tifinagh',
),
82 =>
array (
0 => 0x2D80,
1 => 0x2DDF,
2 => 'Ethiopic Extended',
),
83 =>
array (
0 => 0x2E00,
1 => 0x2E7F,
2 => 'Supplemental Punctuation',
),
84 =>
array (
0 => 0x2E80,
1 => 0x2EFF,
2 => 'CJK Radicals Supplement',
),
85 =>
array (
0 => 0x2F00,
1 => 0x2FDF,
2 => 'Kangxi Radicals',
),
86 =>
array (
0 => 0x2FF0,
1 => 0x2FFF,
2 => 'Ideographic Description Characters',
),
87 =>
array (
0 => 0x3000,
1 => 0x303F,
2 => 'CJK Symbols and Punctuation',
),
88 =>
array (
0 => 0x3040,
1 => 0x309F,
2 => 'Hiragana',
),
89 =>
array (
0 => 0x30A0,
1 => 0x30FF,
2 => 'Katakana',