PHP utf8_deaccent函数代码示例

 public function renderXml()
 {
     $nameSuffix = str_replace(' ', '-', utf8_romanize(utf8_deaccent(ucfirst($this->_params['name']))));
     XenForo_Application::autoload('Zend_Debug');
     $this->setDownloadFileName('BBM_BbCode_' . $nameSuffix . '.xml');
     return $this->_params['xml']->saveXml();
 }

 function add()
 {
     $a = $this->get_macros();
     $macros = $_REQUEST['macro'];
     $words = $_REQUEST['word'];
     foreach ($macros as $key => $value) {
         if (isset($value) && trim($value)) {
             if (isset($words[$key]) && trim($words[$key])) {
                 $value = utf8_deaccent($value);
                 $a[$value] = htmlspecialchars($words[$key], ENT_NOQUOTES, 'UTF-8');
             }
         }
     }
     io_saveFile(MACROS_FILE, serialize($a));
     return $a;
 }

function cleanID($raw_id)
{
    $sepchar = "_";
    $sepcharpat = '#\\' . $sepchar . '+#';
    $id = trim((string) $raw_id);
    $id = utf8_strtolower($id);
    //alternative namespace seperator
    $id = strtr($id, ';', ':');
    $id = strtr($id, '/', $sepchar);
    $id = utf8_romanize($id);
    $id = utf8_deaccent($id, -1);
    //remove specials
    $id = utf8_stripspecials($id, $sepchar, '\\*');
    $id = utf8_strip($id);
    $id = preg_replace($sepcharpat, $sepchar, $id);
    $id = preg_replace('#:+#', ':', $id);
    $id = preg_replace('#:[:\\._\\-]+#', ':', $id);
    return $id;
}

/**
 * Encodes an email address header
 *
 * Unicode characters will be deaccented and encoded
 * quoted_printable for headers.
 * Addresses may not contain Non-ASCII data!
 *
 * Example:
 *   mail_encode_address("föö <foo@bar.com>, me@somewhere.com","TBcc");
 *
 * @param string  $string Multiple adresses separated by commas
 * @param string  $header Name of the header (To,Bcc,Cc,...)
 * @param boolean $names  Allow named Recipients?
 */
function mail_encode_address($string, $header = '', $names = true)
{
    $headers = '';
    $parts = split(',', $string);
    foreach ($parts as $part) {
        $part = trim($part);
        // parse address
        if (preg_match('#(.*?)<(.*?)>#', $part, $matches)) {
            $text = trim($matches[1]);
            $addr = $matches[2];
        } else {
            $addr = $part;
        }
        // skip empty ones
        if (empty($addr)) {
            continue;
        }
        // FIXME: is there a way to encode the localpart of a emailaddress?
        if (!utf8_isASCII($addr)) {
            msg(htmlspecialchars("E-Mail address <{$addr}> is not ASCII"), -1);
            continue;
        }
        if (!mail_isvalid($addr)) {
            msg(htmlspecialchars("E-Mail address <{$addr}> is not valid"), -1);
            continue;
        }
        // text was given
        if (!empty($text) && $names) {
            // add address quotes
            $addr = "<{$addr}>";
            if (defined('MAILHEADER_ASCIIONLY')) {
                $text = utf8_deaccent($text);
                $text = utf8_strip($text);
            }
            if (!utf8_isASCII($text)) {
                $text = '=?UTF-8?Q?' . mail_quotedprintable_encode($text, 0) . '?=';
            }
        } else {
            $text = '';
        }
        // add to header comma seperated and in new line to avoid too long headers
        if ($headers != '') {
            $headers .= ',' . MAILHEADER_EOL . ' ';
        }
        $headers .= $text . ' ' . $addr;
    }
    if (empty($headers)) {
        return null;
    }
    //if headername was given add it and close correctly
    if ($header) {
        $headers = $header . ': ' . $headers . MAILHEADER_EOL;
    }
    return $headers;
}

<?php

if (!empty($_GET['anywhere']) && $_GET['searchtype'] == 'metadata') {
    $anywhere_array = array($_GET['anywhere']);
    if ($_GET['anywhere_separator'] == 'AND' || $_GET['anywhere_separator'] == 'OR') {
        $anywhere_array = explode(' ', $_GET['anywhere']);
    }
    while ($anywhere = each($anywhere_array)) {
        $like_query_esc = str_replace("\\", "\\\\", $anywhere[1]);
        $like_query_esc = str_replace("%", "\\%", $like_query_esc);
        $like_query_esc = str_replace("_", "\\_", $like_query_esc);
        $like_query_esc = str_replace("<*>", "%", $like_query_esc);
        $like_query_esc = str_replace("<?>", "_", $like_query_esc);
        $author_like_query = $dbHandle->quote("%L:\"{$like_query_esc}%");
        $like_query = $dbHandle->quote("%{$like_query_esc}%");
        $translation = utf8_deaccent($like_query_esc);
        if ($translation != $like_query_esc) {
            $author_like_query_translated = $dbHandle->quote("%L:\"{$translation}%");
            $like_query_translated = $dbHandle->quote("%{$translation}%");
            $like_sql = "authors LIKE {$author_like_query} ESCAPE '\\' OR" . " editor LIKE {$author_like_query} ESCAPE '\\' OR" . " journal LIKE {$like_query} ESCAPE '\\' OR" . " secondary_title LIKE {$like_query} ESCAPE '\\' OR" . " tertiary_title LIKE {$like_query} ESCAPE '\\' OR" . " affiliation LIKE {$like_query} ESCAPE '\\' OR" . " title LIKE {$like_query} ESCAPE '\\' OR" . " abstract LIKE {$like_query} ESCAPE '\\' OR" . " year LIKE {$like_query} ESCAPE '\\' OR" . " id=" . intval($anywhere[1]) . " OR" . " keywords LIKE {$like_query} ESCAPE '\\' OR" . " authors_ascii LIKE {$author_like_query_translated} ESCAPE '\\' OR" . " title_ascii LIKE {$like_query_translated} ESCAPE '\\' OR" . " abstract_ascii LIKE {$like_query_translated} ESCAPE '\\'";
        } else {
            $like_sql = "authors_ascii LIKE {$author_like_query} ESCAPE '\\' OR" . " editor LIKE {$author_like_query} ESCAPE '\\' OR" . " journal LIKE {$like_query} ESCAPE '\\' OR" . " secondary_title LIKE {$like_query} ESCAPE '\\' OR" . " tertiary_title LIKE {$like_query} ESCAPE '\\' OR" . " affiliation LIKE {$like_query} ESCAPE '\\' OR" . " title_ascii LIKE {$like_query} ESCAPE '\\' OR" . " abstract_ascii LIKE {$like_query} ESCAPE '\\' OR" . " year LIKE {$like_query} ESCAPE '\\' OR" . " id=" . intval($anywhere[1]) . " OR" . " keywords LIKE {$like_query} ESCAPE '\\'";
        }
        $anywhere_regexp[] = '(' . $like_sql . ')';
    }
    if ($_GET['anywhere_separator'] == 'AND') {
        $search_string = join(' AND ', $anywhere_regexp);
    }
    if ($_GET['anywhere_separator'] == 'OR') {
        $search_string = join(' OR ', $anywhere_regexp);
    }

 /**
  * Verification callback to check that a username is valid
  *
  * @param string Username
  *
  * @return bool
  */
 protected function _verifyUsername(&$username)
 {
     if ($this->isUpdate() && $username === $this->getExisting('username')) {
         return true;
         // unchanged, always pass
     }
     // standardize white space in names
     $username = preg_replace('/\\s+/u', ' ', $username);
     try {
         // if this matches, then \v isn't known (appears to be PCRE < 7.2) so don't strip
         if (!preg_match('/\\v/', 'v')) {
             $newName = preg_replace('/\\v+/u', ' ', $username);
             if (is_string($newName)) {
                 $username = $newName;
             }
         }
     } catch (Exception $e) {
     }
     $username = trim($username);
     $usernameLength = utf8_strlen($username);
     $minLength = $this->getOption(self::OPTION_USERNAME_LENGTH_MIN);
     $maxLength = $this->getOption(self::OPTION_USERNAME_LENGTH_MAX);
     if (!$this->getOption(self::OPTION_ADMIN_EDIT)) {
         if ($minLength > 0 && $usernameLength < $minLength) {
             $this->error(new XenForo_Phrase('please_enter_name_that_is_at_least_x_characters_long', array('count' => $minLength)), 'username');
             return false;
         }
         if ($maxLength > 0 && $usernameLength > $maxLength) {
             $this->error(new XenForo_Phrase('please_enter_name_that_is_at_most_x_characters_long', array('count' => $maxLength)), 'username');
             return false;
         }
         $disallowedNames = $this->getOption(self::OPTION_USERNAME_DISALLOWED_NAMES);
         if ($disallowedNames) {
             foreach ($disallowedNames as $name) {
                 $name = trim($name);
                 if ($name === '') {
                     continue;
                 }
                 if (stripos($username, $name) !== false) {
                     $this->error(new XenForo_Phrase('please_enter_another_name_disallowed_words'), 'username');
                     return false;
                 }
             }
         }
         $matchRegex = $this->getOption(self::OPTION_USERNAME_REGEX);
         if ($matchRegex) {
             $matchRegex = str_replace('#', '\\#', $matchRegex);
             // escape delim only
             if (!preg_match('#' . $matchRegex . '#i', $username)) {
                 $this->error(new XenForo_Phrase('please_enter_another_name_required_format'), 'username');
                 return false;
             }
         }
         $censoredUserName = XenForo_Helper_String::censorString($username);
         if ($censoredUserName !== $username) {
             $this->error(new XenForo_Phrase('please_enter_name_that_does_not_contain_any_censored_words'), 'username');
             return false;
         }
     }
     // ignore check if unicode properties aren't compiled
     try {
         if (@preg_match("/\\p{C}/u", $username)) {
             $this->error(new XenForo_Phrase('please_enter_name_without_using_control_characters'), 'username');
             return false;
         }
     } catch (Exception $e) {
     }
     if (strpos($username, ',') !== false) {
         $this->error(new XenForo_Phrase('please_enter_name_that_does_not_contain_comma'), 'username');
         return false;
     }
     if (XenForo_Helper_Email::isEmailValid($username)) {
         $this->error(new XenForo_Phrase('please_enter_name_that_does_not_resemble_an_email_address'), 'username');
         return false;
     }
     $existingUser = $this->_getUserModel()->getUserByName($username);
     if ($existingUser && $existingUser['user_id'] != $this->get('user_id')) {
         $this->error(new XenForo_Phrase('usernames_must_be_unique'), 'username');
         return false;
     }
     // compare against romanized name to help reduce confusable issues
     $romanized = utf8_deaccent(utf8_romanize($username));
     if ($romanized != $username) {
         $existingUser = $this->_getUserModel()->getUserByName($romanized);
         if ($existingUser && $existingUser['user_id'] != $this->get('user_id')) {
             $this->error(new XenForo_Phrase('usernames_must_be_unique'), 'username');
             return false;
         }
     }
     return true;
 }

/**
 * Remove unwanted chars from ID
 *
 * Cleans a given ID to only use allowed characters. Accented characters are
 * converted to unaccented ones
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 * @param  string  $raw_id    The pageid to clean
 * @param  boolean $ascii     Force ASCII
 * @param  boolean $media     Allow leading or trailing _ for media files
 */
function cleanID($raw_id, $ascii = false, $media = false)
{
    global $conf;
    static $sepcharpat = null;
    global $cache_cleanid;
    $cache =& $cache_cleanid;
    // check if it's already in the memory cache
    if (isset($cache[(string) $raw_id])) {
        return $cache[(string) $raw_id];
    }
    $sepchar = $conf['sepchar'];
    if ($sepcharpat == null) {
        // build string only once to save clock cycles
        $sepcharpat = '#\\' . $sepchar . '+#';
    }
    $id = trim((string) $raw_id);
    $id = utf8_strtolower($id);
    //alternative namespace seperator
    $id = strtr($id, ';', ':');
    if ($conf['useslash']) {
        $id = strtr($id, '/', ':');
    } else {
        $id = strtr($id, '/', $sepchar);
    }
    if ($conf['deaccent'] == 2 || $ascii) {
        $id = utf8_romanize($id);
    }
    if ($conf['deaccent'] || $ascii) {
        $id = utf8_deaccent($id, -1);
    }
    //remove specials
    $id = utf8_stripspecials($id, $sepchar, '\\*');
    if ($ascii) {
        $id = utf8_strip($id);
    }
    //clean up
    $id = preg_replace($sepcharpat, $sepchar, $id);
    $id = preg_replace('#:+#', ':', $id);
    $id = $media ? trim($id, ':.-') : trim($id, ':._-');
    $id = preg_replace('#:[:\\._\\-]+#', ':', $id);
    $cache[(string) $raw_id] = $id;
    return $id;
}

 /**
  * Cleanup and encode the headers array
  */
 protected function cleanHeaders()
 {
     global $conf;
     // clean up addresses
     if (empty($this->headers['From'])) {
         $this->from($conf['mailfrom']);
     }
     $addrs = array('To', 'From', 'Cc', 'Bcc', 'Reply-To', 'Sender');
     foreach ($addrs as $addr) {
         if (isset($this->headers[$addr])) {
             $this->headers[$addr] = $this->cleanAddress($this->headers[$addr]);
         }
     }
     if (isset($this->headers['Subject'])) {
         // add prefix to subject
         if (empty($conf['mailprefix'])) {
             if (utf8_strlen($conf['title']) < 20) {
                 $prefix = '[' . $conf['title'] . ']';
             } else {
                 $prefix = '[' . utf8_substr($conf['title'], 0, 20) . '...]';
             }
         } else {
             $prefix = '[' . $conf['mailprefix'] . ']';
         }
         $len = strlen($prefix);
         if (substr($this->headers['Subject'], 0, $len) != $prefix) {
             $this->headers['Subject'] = $prefix . ' ' . $this->headers['Subject'];
         }
         // encode subject
         if (defined('MAILHEADER_ASCIIONLY')) {
             $this->headers['Subject'] = utf8_deaccent($this->headers['Subject']);
             $this->headers['Subject'] = utf8_strip($this->headers['Subject']);
         }
         if (!utf8_isASCII($this->headers['Subject'])) {
             $this->headers['Subject'] = '=?UTF-8?B?' . base64_encode($this->headers['Subject']) . '?=';
         }
     }
 }

 protected function _getUrlVersionOfTag($tag)
 {
     $db = $this->_getDb();
     $urlVersion = preg_replace('/[^a-zA-Z0-9_ -]/', '', utf8_romanize(utf8_deaccent($tag)));
     $urlVersion = preg_replace('/[ -]+/', '-', $urlVersion);
     if (!strlen($urlVersion)) {
         $urlVersion = 1 + intval($db->fetchOne("\r\n\t\t\t\tSELECT MAX(tag_id)\r\n\t\t\t\tFROM xf_tag\r\n\t\t\t"));
     } else {
         $existing = $db->fetchRow("\r\n\t\t\t\tSELECT *\r\n\t\t\t\tFROM xf_tag\r\n\t\t\t\tWHERE tag_url = ?\r\n\t\t\t\t\tOR (tag_url LIKE ? AND tag_url REGEXP ?)\r\n\t\t\t\tORDER BY tag_id DESC\r\n\t\t\t\tLIMIT 1\r\n\t\t\t", array($urlVersion, "{$urlVersion}-%", "^{$urlVersion}-[0-9]+\$"));
         if ($existing) {
             $counter = 1;
             if ($existing['tag_url'] != $urlVersion && preg_match('/-(\\d+)$/', $existing['tag_url'], $match)) {
                 $counter = $match[1];
             }
             $testExists = true;
             while ($testExists) {
                 $counter++;
                 $testExists = $db->fetchOne("\r\n\t\t\t\t\t\tSELECT tag_id\r\n\t\t\t\t\t\tFROM xf_tag\r\n\t\t\t\t\t\tWHERE tag_url = ?\r\n\t\t\t\t\t", "{$urlVersion}-{$counter}");
             }
             $urlVersion .= "-{$counter}";
         }
     }
     return $urlVersion;
 }

 $stmt->bindParam(':authors_ascii', $authors_ascii, PDO::PARAM_STR);
 $stmt->bindParam(':title_ascii', $title_ascii, PDO::PARAM_STR);
 $stmt->bindParam(':abstract_ascii', $abstract_ascii, PDO::PARAM_STR);
 $stmt->bindParam(':added_by', $userID, PDO::PARAM_INT);
 $dbHandle->exec("BEGIN IMMEDIATE TRANSACTION");
 $stmt->execute();
 $stmt = null;
 $id = $dbHandle->lastInsertId();
 $new_file = str_pad($id, 5, "0", STR_PAD_LEFT) . '.pdf';
 // Save citation key.
 $stmt6 = $dbHandle->prepare("UPDATE library SET bibtex=:bibtex WHERE id=:id");
 $stmt6->bindParam(':bibtex', $bibtex, PDO::PARAM_STR);
 $stmt6->bindParam(':id', $id, PDO::PARAM_INT);
 $bibtex_author = 'unknown';
 if (!empty($last_name[0])) {
     $bibtex_author = utf8_deaccent($last_name[0]);
 }
 empty($year) ? $bibtex_year = '0000' : ($bibtex_year = substr($year, 0, 4));
 $bibtex = $bibtex_author . '-' . $bibtex_year . '-ID' . $id;
 $insert = $stmt6->execute();
 $insert = null;
 if (isset($_GET['shelf']) && !empty($userID)) {
     $user_query = $dbHandle->quote($userID);
     $file_query = $dbHandle->quote($id);
     $dbHandle->exec("INSERT OR IGNORE INTO shelves (userID,fileID) VALUES ({$user_query},{$file_query})");
 }
 if (isset($_GET['project']) && !empty($_GET['projectID'])) {
     $dbHandle->exec("INSERT OR IGNORE INTO projectsfiles (projectID,fileID) VALUES (" . intval($_GET['projectID']) . "," . intval($id) . ")");
 }
 ####### record new category into categories, if not exists #########
 if (!empty($_GET['category2'])) {

 print "<br><u>External IDs:</u> " . htmlspecialchars(implode(", ", $uids));
 print '<br><u>DOI:</u> <span id="file-doi">' . htmlspecialchars($paper['doi']) . '</span>';
 if (!empty($paper['bibtex'])) {
     print '<br><u>BibTex:</u> <input type="text" class="bibtex" value="' . htmlspecialchars($paper['bibtex']) . '" style="outline:none;width:200px" readonly>';
 } else {
     $bibtex_author = substr($paper['authors'], 3);
     $bibtex_author = substr($bibtex_author, 0, strpos($bibtex_author, '"'));
     if (empty($bibtex_author)) {
         $bibtex_author = 'unknown';
     }
     $bibtex_year = '0000';
     $bibtex_year_array = explode('-', $paper['year']);
     if (!empty($bibtex_year_array[0])) {
         $bibtex_year = $bibtex_year_array[0];
     }
     $bibtex_key = utf8_deaccent($bibtex_author) . '-' . $bibtex_year . '-ID' . $paper['id'];
     print '<br><u>BibTex:</u> <input type="text" class="bibtex" value="' . $bibtex_key . '" style="outline:none;width:200px" readonly>';
 }
 $editor_string = '';
 if (!empty($paper['editor'])) {
     $array = explode(';', $paper['editor']);
     $array = array_filter($array);
     if (!empty($array)) {
         foreach ($array as $editor) {
             $array2 = explode(',', $editor);
             $last = trim($array2[0]);
             $last = substr($array2[0], 3, -1);
             $first = trim($array2[1]);
             $first = substr($array2[1], 3, -1);
             $new_editor[] = $last . ', ' . $first;
         }

 /**
  * Gets version of a title that is valid in a URL. Invalid elements are stripped
  * or replaced with '-'. It may not be possible to reverse a URL'd title to the
  * original title.
  *
  * @param string $title
  * @param boolean $romanize If true, non-latin strings are romanized
  *
  * @return string
  */
 public static function getTitleForUrl($title, $romanize = false)
 {
     $title = strval($title);
     $lookup = $title . ($romanize ? '|r' : '');
     if (isset(self::$_titleCache[$lookup])) {
         return self::$_titleCache[$lookup];
     }
     if ($romanize) {
         $title = utf8_romanize(utf8_deaccent($title));
     }
     $aPattern = array("a" => "á|à|ạ|ả|ã|ă|ắ|ằ|ặ|ẳ|ẵ|â|ấ|ầ|ậ|ẩ|ẫ|Á|À|Ạ|Ả|Ã|Ă|Ắ|Ằ|Ặ|Ẳ|Ẵ|Â|Ấ|Ầ|Ậ|Ẩ|Ẫ", "o" => "ó|ò|ọ|ỏ|õ|ô|ố|ồ|ộ|ổ|ỗ|ơ|ớ|ờ|ợ|ở|ỡ|Ó|Ò|Ọ|Ỏ|Õ|Ô|Ố|Ồ|Ộ|Ổ|Ỗ|Ơ|Ớ|Ờ|Ợ|Ở|Ỡ", "e" => "é|è|ẹ|ẻ|ẽ|ê|ế|ề|ệ|ể|ễ|É|È|Ẹ|Ẻ|Ẽ|Ê|Ế|Ề|Ệ|Ể|Ễ", "u" => "ú|ù|ụ|ủ|ũ|ư|ứ|ừ|ự|ử|ữ|Ú|Ù|Ụ|Ủ|Ũ|Ư|Ứ|Ừ|Ự|Ử|Ữ", "i" => "í|ì|ị|ỉ|ĩ|Í|Ì|Ị|Ỉ|Ĩ", "y" => "ý|ỳ|ỵ|ỷ|ỹ|Ý|Ỳ|Ỵ|Ỷ|Ỹ", "d" => "đ|Đ");
     while (list($key, $value) = each($aPattern)) {
         $title = @ereg_replace($value, $key, $title);
     }
     $title = strtr($title, '`!"$%^&*()-+={}[]<>;:@#~,./?|' . "\r\n\t\\", '                             ' . '    ');
     $title = strtr($title, array('"' => '', "'" => ''));
     if ($romanize) {
         $title = preg_replace('/[^a-zA-Z0-9_ -]/', '', $title);
     }
     $title = preg_replace('/[ ]+/', '-', trim($title));
     $title = strtr($title, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz');
     self::$_titleCache[$lookup] = $title;
     return $title;
 }

 function utf8_deaccent($string, $case = 0)
 {
     return utf8_deaccent($string, $case);
 }

 public function renderXml()
 {
     $title = str_replace(' ', '-', utf8_romanize(utf8_deaccent($this->_params['style']['title'])));
     $this->setDownloadFileName('style-' . $title . '.xml');
     return $this->_params['xml']->saveXml();
 }

         }
     }
     reset($add_item);
 }
 if (isset($add_item['id'])) {
     $id_author = substr($item['authors'], 3);
     $id_author = substr($id_author, 0, strpos($id_author, '"'));
     if (empty($id_author)) {
         $id_author = 'unknown';
     }
     $id_year_array = explode('-', $item['year']);
     $id_year = '0000';
     if (!empty($id_year_array[0])) {
         $id_year = $id_year_array[0];
     }
     $add_item['id'] = utf8_deaccent($id_author) . '-' . $id_year . '-ID' . $item['id'];
     if ($_GET['format'] == 'BibTex' && !empty($item['bibtex'])) {
         $add_item['id'] = $item['bibtex'];
     }
     $add_item['id'] = str_replace(' ', '', $add_item['id']);
 }
 if ($_GET['format'] == 'list') {
     $new_authors = array();
     $array = explode(';', $item['authors']);
     $array = array_filter($array);
     if (!empty($array)) {
         foreach ($array as $author) {
             $array2 = explode(',', $author);
             $last = trim($array2[0]);
             $last = substr($array2[0], 3, -1);
             $first = trim($array2[1]);