smalot /
pdfparser
| Conditions | 1 |
| Paths | 1 |
| Total Lines | 140 |
| Code Lines | 138 |
| Lines | 0 |
| Ratio | 0 % |
| Changes | 1 | ||
| Bugs | 0 | Features | 0 |
Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.
For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.
Commonly applied refactorings include:
If many parameters/temporary variables are present:
| 1 | <?php |
||
| 43 | public static function convertPDFDoc2UTF8(string $content): string |
||
| 44 | { |
||
| 45 | return strtr($content, array( |
||
| 46 | "\x18" => "\u{02d8}", // breve |
||
| 47 | "\x19" => "\u{02c7}", // caron |
||
| 48 | "\x1a" => "\u{02c6}", // circumflex |
||
| 49 | "\x1b" => "\u{02d9}", // dotaccent |
||
| 50 | "\x1c" => "\u{02dd}", // hungarumlaut |
||
| 51 | "\x1d" => "\u{02db}", // ogonek |
||
| 52 | "\x1e" => "\u{02de}", // ring |
||
| 53 | "\x1f" => "\u{02dc}", // tilde |
||
| 54 | "\x7f" => '', |
||
| 55 | "\x80" => "\u{2022}", // bullet |
||
| 56 | "\x81" => "\u{2020}", // dagger |
||
| 57 | "\x82" => "\u{2021}", // daggerdbl |
||
| 58 | "\x83" => "\u{2026}", // ellipsis |
||
| 59 | "\x84" => "\u{2014}", // emdash |
||
| 60 | "\x85" => "\u{2013}", // endash |
||
| 61 | "\x86" => "\u{0192}", // florin |
||
| 62 | "\x87" => "\u{2044}", // fraction |
||
| 63 | "\x88" => "\u{2039}", // guilsinglleft |
||
| 64 | "\x89" => "\u{203a}", // guilsinglright |
||
| 65 | "\x8a" => "\u{2212}", // minus |
||
| 66 | "\x8b" => "\u{2030}", // perthousand |
||
| 67 | "\x8c" => "\u{201e}", // quotedblbase |
||
| 68 | "\x8d" => "\u{201c}", // quotedblleft |
||
| 69 | "\x8e" => "\u{201d}", // quotedblright |
||
| 70 | "\x8f" => "\u{2018}", // quoteleft |
||
| 71 | "\x90" => "\u{2019}", // quoteright |
||
| 72 | "\x91" => "\u{201a}", // quotesinglbase |
||
| 73 | "\x92" => "\u{2122}", // trademark |
||
| 74 | "\x93" => "\u{fb01}", // fi |
||
| 75 | "\x94" => "\u{fb02}", // fl |
||
| 76 | "\x95" => "\u{0141}", // Lslash |
||
| 77 | "\x96" => "\u{0152}", // OE |
||
| 78 | "\x97" => "\u{0160}", // Scaron |
||
| 79 | "\x98" => "\u{0178}", // Ydieresis |
||
| 80 | "\x99" => "\u{017d}", // Zcaron |
||
| 81 | "\x9a" => "\u{0131}", // dotlessi |
||
| 82 | "\x9b" => "\u{0142}", // lslash |
||
| 83 | "\x9c" => "\u{0153}", // oe |
||
| 84 | "\x9d" => "\u{0161}", // scaron |
||
| 85 | "\x9e" => "\u{017e}", // zcaron |
||
| 86 | "\x9f" => '', |
||
| 87 | "\xa0" => "\u{20ac}", // Euro |
||
| 88 | "\xa1" => "\u{00a1}", // exclamdown |
||
| 89 | "\xa2" => "\u{00a2}", // cent |
||
| 90 | "\xa3" => "\u{00a3}", // sterling |
||
| 91 | "\xa4" => "\u{00a4}", // currency |
||
| 92 | "\xa5" => "\u{00a5}", // yen |
||
| 93 | "\xa6" => "\u{00a6}", // brokenbar |
||
| 94 | "\xa7" => "\u{00a7}", // section |
||
| 95 | "\xa8" => "\u{00a8}", // dieresis |
||
| 96 | "\xa9" => "\u{00a9}", // copyright |
||
| 97 | "\xaa" => "\u{00aa}", // ordfeminine |
||
| 98 | "\xab" => "\u{00ab}", // guillemotleft |
||
| 99 | "\xac" => "\u{00ac}", // logicalnot |
||
| 100 | "\xad" => '', |
||
| 101 | "\xae" => "\u{00ae}", // registered |
||
| 102 | "\xaf" => "\u{00af}", // macron |
||
| 103 | "\xb0" => "\u{00b0}", // degree |
||
| 104 | "\xb1" => "\u{00b1}", // plusminus |
||
| 105 | "\xb2" => "\u{00b2}", // twosuperior |
||
| 106 | "\xb3" => "\u{00b3}", // threesuperior |
||
| 107 | "\xb4" => "\u{00b4}", // acute |
||
| 108 | "\xb5" => "\u{00b5}", // mu |
||
| 109 | "\xb6" => "\u{00b6}", // paragraph |
||
| 110 | "\xb7" => "\u{00b7}", // periodcentered |
||
| 111 | "\xb8" => "\u{00b8}", // cedilla |
||
| 112 | "\xb9" => "\u{00b9}", // onesuperior |
||
| 113 | "\xba" => "\u{00ba}", // ordmasculine |
||
| 114 | "\xbb" => "\u{00bb}", // guillemotright |
||
| 115 | "\xbc" => "\u{00bc}", // onequarter |
||
| 116 | "\xbd" => "\u{00bd}", // onehalf |
||
| 117 | "\xbe" => "\u{00be}", // threequarters |
||
| 118 | "\xbf" => "\u{00bf}", // questiondown |
||
| 119 | "\xc0" => "\u{00c0}", // Agrave |
||
| 120 | "\xc1" => "\u{00c1}", // Aacute |
||
| 121 | "\xc2" => "\u{00c2}", // Acircumflex |
||
| 122 | "\xc3" => "\u{00c3}", // Atilde |
||
| 123 | "\xc4" => "\u{00c4}", // Adieresis |
||
| 124 | "\xc5" => "\u{00c5}", // Aring |
||
| 125 | "\xc6" => "\u{00c6}", // AE |
||
| 126 | "\xc7" => "\u{00c7}", // Ccedill |
||
| 127 | "\xc8" => "\u{00c8}", // Egrave |
||
| 128 | "\xc9" => "\u{00c9}", // Eacute |
||
| 129 | "\xca" => "\u{00ca}", // Ecircumflex |
||
| 130 | "\xcb" => "\u{00cb}", // Edieresis |
||
| 131 | "\xcc" => "\u{00cc}", // Igrave |
||
| 132 | "\xcd" => "\u{00cd}", // Iacute |
||
| 133 | "\xce" => "\u{00ce}", // Icircumflex |
||
| 134 | "\xcf" => "\u{00cf}", // Idieresis |
||
| 135 | "\xd0" => "\u{00d0}", // Eth |
||
| 136 | "\xd1" => "\u{00d1}", // Ntilde |
||
| 137 | "\xd2" => "\u{00d2}", // Ograve |
||
| 138 | "\xd3" => "\u{00d3}", // Oacute |
||
| 139 | "\xd4" => "\u{00d4}", // Ocircumflex |
||
| 140 | "\xd5" => "\u{00d5}", // Otilde |
||
| 141 | "\xd6" => "\u{00d6}", // Odieresis |
||
| 142 | "\xd7" => "\u{00d7}", // multiply |
||
| 143 | "\xd8" => "\u{00d8}", // Oslash |
||
| 144 | "\xd9" => "\u{00d9}", // Ugrave |
||
| 145 | "\xda" => "\u{00da}", // Uacute |
||
| 146 | "\xdb" => "\u{00db}", // Ucircumflex |
||
| 147 | "\xdc" => "\u{00dc}", // Udieresis |
||
| 148 | "\xdd" => "\u{00dd}", // Yacute |
||
| 149 | "\xde" => "\u{00de}", // Thorn |
||
| 150 | "\xdf" => "\u{00df}", // germandbls |
||
| 151 | "\xe0" => "\u{00e0}", // agrave |
||
| 152 | "\xe1" => "\u{00e1}", // aacute |
||
| 153 | "\xe2" => "\u{00e2}", // acircumflex |
||
| 154 | "\xe3" => "\u{00e3}", // atilde |
||
| 155 | "\xe4" => "\u{00e4}", // adieresis |
||
| 156 | "\xe5" => "\u{00e5}", // aring |
||
| 157 | "\xe6" => "\u{00e6}", // ae |
||
| 158 | "\xe7" => "\u{00e7}", // ccedilla |
||
| 159 | "\xe8" => "\u{00e8}", // egrave |
||
| 160 | "\xe9" => "\u{00e9}", // eacute |
||
| 161 | "\xea" => "\u{00ea}", // ecircumflex |
||
| 162 | "\xeb" => "\u{00eb}", // edieresis |
||
| 163 | "\xec" => "\u{00ec}", // igrave |
||
| 164 | "\xed" => "\u{00ed}", // iacute |
||
| 165 | "\xee" => "\u{00ee}", // icircumflex |
||
| 166 | "\xef" => "\u{00ef}", // idieresis |
||
| 167 | "\xf0" => "\u{00f0}", // eth |
||
| 168 | "\xf1" => "\u{00f1}", // ntilde |
||
| 169 | "\xf2" => "\u{00f2}", // ograve |
||
| 170 | "\xf3" => "\u{00f3}", // oacute |
||
| 171 | "\xf4" => "\u{00f4}", // ocircumflex |
||
| 172 | "\xf5" => "\u{00f5}", // otilde |
||
| 173 | "\xf6" => "\u{00f6}", // odieresis |
||
| 174 | "\xf7" => "\u{00f7}", // divide |
||
| 175 | "\xf8" => "\u{00f8}", // oslash |
||
| 176 | "\xf9" => "\u{00f9}", // ugrave |
||
| 177 | "\xfa" => "\u{00fa}", // uacute |
||
| 178 | "\xfb" => "\u{00fb}", // ucircumflex |
||
| 179 | "\xfc" => "\u{00fc}", // udieresis |
||
| 180 | "\xfd" => "\u{00fd}", // yacute |
||
| 181 | "\xfe" => "\u{00fe}", // thorn |
||
| 182 | "\xff" => "\u{00ff}" // ydieresis |
||
| 183 | )); |
||
| 186 |
