heiglandreas /
Org_Heigl_Hyphenator
| @@ 72-96 (lines=25) @@ | ||
| 69 | * |
|
| 70 | * @return \Org\Heigl\Hyphenator\Tokenizer\TokenRegistry |
|
| 71 | */ |
|
| 72 | public function run($input) |
|
| 73 | { |
|
| 74 | if ($input instanceof TokenRegistry) { |
|
| 75 | // Tokenize a TokenRegistry |
|
| 76 | $f = clone($input); |
|
| 77 | foreach ($input as $token) { |
|
| 78 | if (! $token instanceof WordToken) { |
|
| 79 | continue; |
|
| 80 | } |
|
| 81 | $newTokens = $this->tokenize($token->get()); |
|
| 82 | $f->replace($token, $newTokens); |
|
| 83 | } |
|
| 84 | ||
| 85 | return $f ; |
|
| 86 | } |
|
| 87 | ||
| 88 | // Tokenize a simple string. |
|
| 89 | $array = $this->tokenize($input); |
|
| 90 | $registry = new TokenRegistry(); |
|
| 91 | foreach ($array as $item) { |
|
| 92 | $registry->add($item); |
|
| 93 | } |
|
| 94 | ||
| 95 | return $registry; |
|
| 96 | } |
|
| 97 | ||
| 98 | /** |
|
| 99 | * Split the given string into tokens using whitespace. |
|
| @@ 109-136 (lines=28) @@ | ||
| 106 | * |
|
| 107 | * @return \Org\Heigl\Hyphenator\Tokenizer\TokenRegistry |
|
| 108 | */ |
|
| 109 | public function run($input) |
|
| 110 | { |
|
| 111 | if ($input instanceof TokenRegistry) { |
|
| 112 | // Tokenize a TokenRegistry |
|
| 113 | $f = clone($input); |
|
| 114 | foreach ($input as $token) { |
|
| 115 | if (! $token instanceof WordToken) { |
|
| 116 | continue; |
|
| 117 | } |
|
| 118 | $newTokens = $this->_tokenize($token->get()); |
|
| 119 | if ($newTokens == array($token)) { |
|
| 120 | continue; |
|
| 121 | } |
|
| 122 | $f->replace($token, $newTokens); |
|
| 123 | } |
|
| 124 | ||
| 125 | return $f ; |
|
| 126 | } |
|
| 127 | ||
| 128 | // Tokenize a simple string. |
|
| 129 | $array = $this->_tokenize($input); |
|
| 130 | $registry = new TokenRegistry(); |
|
| 131 | foreach ($array as $item) { |
|
| 132 | $registry->add($item); |
|
| 133 | } |
|
| 134 | ||
| 135 | return $registry; |
|
| 136 | } |
|
| 137 | ||
| 138 | /** |
|
| 139 | * Split the given string into tokens using whitespace. |
|
| @@ 68-94 (lines=27) @@ | ||
| 65 | * |
|
| 66 | * @return \Org\Heigl\Hyphenator\Tokenizer\TokenRegistry |
|
| 67 | */ |
|
| 68 | public function run($input) |
|
| 69 | { |
|
| 70 | if ($input instanceof TokenRegistry) { |
|
| 71 | // Tokenize a TokenRegistry |
|
| 72 | foreach ($input as $token) { |
|
| 73 | if (! $token instanceof WordToken) { |
|
| 74 | continue; |
|
| 75 | } |
|
| 76 | $newTokens = $this->_tokenize($token->get()); |
|
| 77 | if ($newTokens == array($token)) { |
|
| 78 | continue; |
|
| 79 | } |
|
| 80 | $input->replace($token, $newTokens); |
|
| 81 | } |
|
| 82 | ||
| 83 | return $input ; |
|
| 84 | } |
|
| 85 | ||
| 86 | // Tokenize a simple string. |
|
| 87 | $array = $this->_tokenize($input); |
|
| 88 | $registry = new TokenRegistry(); |
|
| 89 | foreach ($array as $item) { |
|
| 90 | $registry->add($item); |
|
| 91 | } |
|
| 92 | ||
| 93 | return $registry; |
|
| 94 | } |
|
| 95 | ||
| 96 | /** |
|
| 97 | * Split the given string into tokens using whitespace. |
|
