mbirth / cops

transliteration.php

Indentation +80 added lines, -80 removed lines

@@ -26,56 +26,56 @@ 
  *   Transliterated text.
  */
 function _transliteration_process($string, $unknown = '?', $source_langcode = NULL) {
-  // ASCII is always valid NFC! If we're only ever given plain ASCII, we can
-  // avoid the overhead of initializing the decomposition tables by skipping
-  // out early.
-  if (!preg_match('/[\x80-\xff]/', $string)) {
+    // ASCII is always valid NFC! If we're only ever given plain ASCII, we can
+    // avoid the overhead of initializing the decomposition tables by skipping
+    // out early.
+    if (!preg_match('/[\x80-\xff]/', $string)) {
     return $string;
-  }
+    }
 
-  static $tail_bytes;
+    static $tail_bytes;
 
-  if (!isset($tail_bytes)) {
+    if (!isset($tail_bytes)) {
     // Each UTF-8 head byte is followed by a certain number of tail bytes.
     $tail_bytes = array();
     for ($n = 0; $n < 256; $n++) {
-      if ($n < 0xc0) {
+        if ($n < 0xc0) {
         $remaining = 0;
-      }
-      elseif ($n < 0xe0) {
+        }
+        elseif ($n < 0xe0) {
         $remaining = 1;
-      }
-      elseif ($n < 0xf0) {
+        }
+        elseif ($n < 0xf0) {
         $remaining = 2;
-      }
-      elseif ($n < 0xf8) {
+        }
+        elseif ($n < 0xf8) {
         $remaining = 3;
-      }
-      elseif ($n < 0xfc) {
+        }
+        elseif ($n < 0xfc) {
         $remaining = 4;
-      }
-      elseif ($n < 0xfe) {
+        }
+        elseif ($n < 0xfe) {
         $remaining = 5;
-      }
-      else {
+        }
+        else {
         $remaining = 0;
-      }
-      $tail_bytes[chr($n)] = $remaining;
+        }
+        $tail_bytes[chr($n)] = $remaining;
+    }
     }
-  }
 
-  // Chop the text into pure-ASCII and non-ASCII areas; large ASCII parts can
-  // be handled much more quickly. Don't chop up Unicode areas for punctuation,
-  // though, that wastes energy.
-  preg_match_all('/[\x00-\x7f]+|[\x80-\xff][\x00-\x40\x5b-\x5f\x7b-\xff]*/', $string, $matches);
+    // Chop the text into pure-ASCII and non-ASCII areas; large ASCII parts can
+    // be handled much more quickly. Don't chop up Unicode areas for punctuation,
+    // though, that wastes energy.
+    preg_match_all('/[\x00-\x7f]+|[\x80-\xff][\x00-\x40\x5b-\x5f\x7b-\xff]*/', $string, $matches);
 
-  $result = '';
-  foreach ($matches[0] as $str) {
+    $result = '';
+    foreach ($matches[0] as $str) {
     if ($str[0] < "\x80") {
-      // ASCII chunk: guaranteed to be valid UTF-8 and in normal form C, so
-      // skip over it.
-      $result .= $str;
-      continue;
+        // ASCII chunk: guaranteed to be valid UTF-8 and in normal form C, so
+        // skip over it.
+        $result .= $str;
+        continue;
     }
 
     // We'll have to examine the chunk byte by byte to ensure that it consists
@@ -91,72 +91,72 @@ 
     $len = $chunk + 1;
 
     for ($i = -1; --$len; ) {
-      $c = $str[++$i];
-      if ($remaining = $tail_bytes[$c]) {
+        $c = $str[++$i];
+        if ($remaining = $tail_bytes[$c]) {
         // UTF-8 head byte!
         $sequence = $head = $c;
         do {
-          // Look for the defined number of tail bytes...
-          if (--$len && ($c = $str[++$i]) >= "\x80" && $c < "\xc0") {
+            // Look for the defined number of tail bytes...
+            if (--$len && ($c = $str[++$i]) >= "\x80" && $c < "\xc0") {
             // Legal tail bytes are nice.
             $sequence .= $c;
-          }
-          else {
+            }
+            else {
             if ($len == 0) {
-              // Premature end of string! Drop a replacement character into
-              // output to represent the invalid UTF-8 sequence.
-              $result .= $unknown;
-              break 2;
+                // Premature end of string! Drop a replacement character into
+                // output to represent the invalid UTF-8 sequence.
+                $result .= $unknown;
+                break 2;
             }
             else {
-              // Illegal tail byte; abandon the sequence.
-              $result .= $unknown;
-              // Back up and reprocess this byte; it may itself be a legal
-              // ASCII or UTF-8 sequence head.
-              --$i;
-              ++$len;
-              continue 2;
+                // Illegal tail byte; abandon the sequence.
+                $result .= $unknown;
+                // Back up and reprocess this byte; it may itself be a legal
+                // ASCII or UTF-8 sequence head.
+                --$i;
+                ++$len;
+                continue 2;
+            }
             }
-          }
         } while (--$remaining);
 
         $n = ord($head);
         if ($n <= 0xdf) {
-          $ord = ($n - 192) * 64 + (ord($sequence[1]) - 128);
+            $ord = ($n - 192) * 64 + (ord($sequence[1]) - 128);
         }
         elseif ($n <= 0xef) {
-          $ord = ($n - 224) * 4096 + (ord($sequence[1]) - 128) * 64 + (ord($sequence[2]) - 128);
+            $ord = ($n - 224) * 4096 + (ord($sequence[1]) - 128) * 64 + (ord($sequence[2]) - 128);
         }
         elseif ($n <= 0xf7) {
-          $ord = ($n - 240) * 262144 + (ord($sequence[1]) - 128) * 4096 + (ord($sequence[2]) - 128) * 64 + (ord($sequence[3]) - 128);
+            $ord = ($n - 240) * 262144 + (ord($sequence[1]) - 128) * 4096 + (ord($sequence[2]) - 128) * 64 + (ord($sequence[3]) - 128);
         }
         elseif ($n <= 0xfb) {
-          $ord = ($n - 248) * 16777216 + (ord($sequence[1]) - 128) * 262144 + (ord($sequence[2]) - 128) * 4096 + (ord($sequence[3]) - 128) * 64 + (ord($sequence[4]) - 128);
+            $ord = ($n - 248) * 16777216 + (ord($sequence[1]) - 128) * 262144 + (ord($sequence[2]) - 128) * 4096 + (ord($sequence[3]) - 128) * 64 + (ord($sequence[4]) - 128);
         }
         elseif ($n <= 0xfd) {
-          $ord = ($n - 252) * 1073741824 + (ord($sequence[1]) - 128) * 16777216 + (ord($sequence[2]) - 128) * 262144 + (ord($sequence[3]) - 128) * 4096 + (ord($sequence[4]) - 128) * 64 + (ord($sequence[5]) - 128);
+            $ord = ($n - 252) * 1073741824 + (ord($sequence[1]) - 128) * 16777216 + (ord($sequence[2]) - 128) * 262144 + (ord($sequence[3]) - 128) * 4096 + (ord($sequence[4]) - 128) * 64 + (ord($sequence[5]) - 128);
         } else {
-          $ord = $n;
+            $ord = $n;
         }
         $result .= _transliteration_replace($ord, $unknown, $source_langcode);
         $head = '';
-      } elseif ($c < "\x80") {
+        } elseif ($c < "\x80") {
         // ASCII byte.
         $result .= $c;
         $head = '';
-      } elseif ($c < "\xc0") {
+        } elseif ($c < "\xc0") {
         // Illegal tail bytes.
         if ($head == '') {
-          $result .= $unknown;
+            $result .= $unknown;
         }
-      } else {
+        } else {
         // Miscellaneous freaks.
         $result .= $unknown;
         $head = '';
-      }
+        }
     }
-  }
-  return $result;
+    }
+    return $result;
 }
 
 /**
@@ -175,38 +175,38 @@ 
  *   ASCII replacement character.
  */
 function _transliteration_replace($ord, $unknown = '?', $langcode = NULL) {
-  static $map = array();
+    static $map = array();
 
-  //GL: set language later
-  /*
+    //GL: set language later
+    /*
   if (!isset($langcode)) {
     global $language;
     $langcode = $language->language;
   }
   */
 
-  $bank = $ord >> 8;
+    $bank = $ord >> 8;
 
-  if (!isset($map[$bank][$langcode])) {
+    if (!isset($map[$bank][$langcode])) {
     $file = './resources/transliteration-data/' . sprintf('x%02x', $bank) . '.php';  
     if (file_exists($file)) {
-      $base = array();
-      $variant = array();
-      include $file;
-      if ($langcode != 'en' && isset($variant[$langcode])) {
+        $base = array();
+        $variant = array();
+        include $file;
+        if ($langcode != 'en' && isset($variant[$langcode])) {
         // Merge in language specific mappings.
         $map[$bank][$langcode] = $variant[$langcode] + $base;
-      }
-      else {
+        }
+        else {
         $map[$bank][$langcode] = $base;
-      }
+        }
     }
     else {
-      $map[$bank][$langcode] = array();
+        $map[$bank][$langcode] = array();
+    }
     }
-  }
 
-  $ord = $ord & 255;
+    $ord = $ord & 255;
 
-  return isset($map[$bank][$langcode][$ord]) ? $map[$bank][$langcode][$ord] : $unknown;
+    return isset($map[$bank][$langcode][$ord]) ? $map[$bank][$langcode][$ord] : $unknown;
 }

Braces +18 added lines, -30 removed lines

@@ -25,7 +25,8 @@ 
  * @return
  *   Transliterated text.
  */
-function _transliteration_process($string, $unknown = '?', $source_langcode = NULL) {
+function _transliteration_process($string, $unknown = '?', $source_langcode = NULL)
+{
   // ASCII is always valid NFC! If we're only ever given plain ASCII, we can
   // avoid the overhead of initializing the decomposition tables by skipping
   // out early.
@@ -41,23 +42,17 @@ 
     for ($n = 0; $n < 256; $n++) {
       if ($n < 0xc0) {
         $remaining = 0;
-      }
-      elseif ($n < 0xe0) {
+      } elseif ($n < 0xe0) {
         $remaining = 1;
-      }
-      elseif ($n < 0xf0) {
+      } elseif ($n < 0xf0) {
         $remaining = 2;
-      }
-      elseif ($n < 0xf8) {
+      } elseif ($n < 0xf8) {
         $remaining = 3;
-      }
-      elseif ($n < 0xfc) {
+      } elseif ($n < 0xfc) {
         $remaining = 4;
-      }
-      elseif ($n < 0xfe) {
+      } elseif ($n < 0xfe) {
         $remaining = 5;
-      }
-      else {
+      } else {
         $remaining = 0;
       }
       $tail_bytes[chr($n)] = $remaining;
@@ -100,15 +95,13 @@ 
           if (--$len && ($c = $str[++$i]) >= "\x80" && $c < "\xc0") {
             // Legal tail bytes are nice.
             $sequence .= $c;
-          }
-          else {
+          } else {
             if ($len == 0) {
               // Premature end of string! Drop a replacement character into
               // output to represent the invalid UTF-8 sequence.
               $result .= $unknown;
               break 2;
-            }
-            else {
+            } else {
               // Illegal tail byte; abandon the sequence.
               $result .= $unknown;
               // Back up and reprocess this byte; it may itself be a legal
@@ -123,17 +116,13 @@ 
         $n = ord($head);
         if ($n <= 0xdf) {
           $ord = ($n - 192) * 64 + (ord($sequence[1]) - 128);
-        }
-        elseif ($n <= 0xef) {
+        } elseif ($n <= 0xef) {
           $ord = ($n - 224) * 4096 + (ord($sequence[1]) - 128) * 64 + (ord($sequence[2]) - 128);
-        }
-        elseif ($n <= 0xf7) {
+        } elseif ($n <= 0xf7) {
           $ord = ($n - 240) * 262144 + (ord($sequence[1]) - 128) * 4096 + (ord($sequence[2]) - 128) * 64 + (ord($sequence[3]) - 128);
-        }
-        elseif ($n <= 0xfb) {
+        } elseif ($n <= 0xfb) {
           $ord = ($n - 248) * 16777216 + (ord($sequence[1]) - 128) * 262144 + (ord($sequence[2]) - 128) * 4096 + (ord($sequence[3]) - 128) * 64 + (ord($sequence[4]) - 128);
-        }
-        elseif ($n <= 0xfd) {
+        } elseif ($n <= 0xfd) {
           $ord = ($n - 252) * 1073741824 + (ord($sequence[1]) - 128) * 16777216 + (ord($sequence[2]) - 128) * 262144 + (ord($sequence[3]) - 128) * 4096 + (ord($sequence[4]) - 128) * 64 + (ord($sequence[5]) - 128);
         } else {
           $ord = $n;
@@ -174,7 +163,8 @@ 
  * @return
  *   ASCII replacement character.
  */
-function _transliteration_replace($ord, $unknown = '?', $langcode = NULL) {
+function _transliteration_replace($ord, $unknown = '?', $langcode = NULL)
+{
   static $map = array();
 
   //GL: set language later
@@ -196,12 +186,10 @@ 
       if ($langcode != 'en' && isset($variant[$langcode])) {
         // Merge in language specific mappings.
         $map[$bank][$langcode] = $variant[$langcode] + $base;
-      }
-      else {
+      } else {
         $map[$bank][$langcode] = $base;
       }
-    }
-    else {
+    } else {
       $map[$bank][$langcode] = array();
     }
   }