--- /dev/null
+branches:
+ only:
+ - refactor
\ No newline at end of file
+++ /dev/null
-<?php
-
-/**
- * Description of CharacterEntities
- *
- * @author Sander
- */
-class CharacterEntities {
- public static function convert($str){
- //Assume the encoding is UTF-8 -> output is UTF-8
- return $str;
- //return utf8_encode($str);
- //Convert to CP1252
- list($from, $to) = CharacterEntities::generateTables();
- return str_replace($from, $to, $str);
- }
-
- private static function generateTables(){
- $from = array();
- $to = array();
-
- for($i = 0; $i < 256; $i++){
- $from[$i] = $to[$i] = chr($i);
- }
-
- $from[0x80] = "€";
- $from[0x82] = "‚";
- $from[0x83] = "ƒ";
- $from[0x84] = "„";
- $from[0x85] = "…";
- $from[0x86] = "†";
- $from[0x87] = "‡";
- $from[0x88] = "ˆ";
- $from[0x89] = "‰";
- $from[0x8A] = "Š";
- $from[0x8B] = "‹";
- $from[0x8C] = "Œ";
- $from[0x8E] = "Ž";
-
- $from[0x91] = "‘";
- $from[0x92] = "’";
- $from[0x93] = "“";
- $from[0x94] = "”";
- $from[0x95] = "•";
- $from[0x96] = "–";
- $from[0x97] = "—";
- $from[0x98] = "˜";
- $from[0x99] = "™";
- $from[0x9A] = "š";
- $from[0x9B] = "›";
- $from[0x9C] = "œ";
- $from[0x9E] = "ž";
- $from[0x9F] = "Ÿ";
-
- $from[0xA1] = "¡";
- $from[0xA2] = "¢";
- $from[0xA3] = "£";
- $from[0xA4] = "¤";
- $from[0xA5] = "¥";
- $from[0xA6] = "¦";
- $from[0xA7] = "§";
- $from[0xA8] = "¨";
- $from[0xA9] = "©";
- $from[0xAA] = "ª";
- $from[0xAB] = "«";
- $from[0xAC] = "¬";
- $from[0xAE] = "®";
- $from[0xAF] = "¯";
-
- $from[0xB0] = "°";
- $from[0xB1] = "±";
- $from[0xB2] = "²";
- $from[0xB3] = "³";
- $from[0xB4] = "´";
- $from[0xB5] = "µ";
- $from[0xB6] = "¶";
- $from[0xB7] = "·";
- $from[0xB8] = "¸";
- $from[0xB9] = "¹";
- $from[0xBA] = "º";
- $from[0xBB] = "»";
- $from[0xBC] = "¼";
- $from[0xBD] = "½";
- $from[0xBE] = "¾";
- $from[0xBF] = "¿";
-
- $from[0xC0] = "À";
- $from[0xC1] = "Á";
- $from[0xC2] = "Â";
- $from[0xC3] = "Ã";
- $from[0xC4] = "Ä";
- $from[0xC5] = "Å";
- $from[0xC6] = "Æ";
- $from[0xC7] = "Ç";
- $from[0xC8] = "È";
- $from[0xC9] = "É";
- $from[0xCA] = "Ê";
- $from[0xCB] = "Ë";
- $from[0xCC] = "Ì";
- $from[0xCD] = "Í";
- $from[0xCE] = "Î";
- $from[0xCF] = "Ï";
-
- $from[0xD0] = "Ð";
- $from[0xD1] = "Ñ";
- $from[0xD2] = "Ò";
- $from[0xD3] = "Ó";
- $from[0xD4] = "Ô";
- $from[0xD5] = "Õ";
- $from[0xD6] = "Ö";
- $from[0xD7] = "×";
- $from[0xD8] = "Ø";
- $from[0xD9] = "Ù";
- $from[0xDA] = "Ú";
- $from[0xDB] = "Û";
- $from[0xDC] = "Ü";
- $from[0xDD] = "Ý";
- $from[0xDE] = "Þ";
- $from[0xDF] = "ß";
-
- $from[0xE0] = "à";
- $from[0xE1] = "á";
- $from[0xE2] = "â";
- $from[0xE3] = "ã";
- $from[0xE4] = "ä";
- $from[0xE5] = "å";
- $from[0xE6] = "æ";
- $from[0xE7] = "ç";
- $from[0xE8] = "è";
- $from[0xE9] = "é";
- $from[0xEA] = "ê";
- $from[0xEB] = "ë";
- $from[0xEC] = "ì";
- $from[0xED] = "í";
- $from[0xEE] = "î";
- $from[0xEF] = "ï";
-
- $from[0xF0] = "ð";
- $from[0xF1] = "ñ";
- $from[0xF2] = "ò";
- $from[0xF3] = "ó";
- $from[0xF4] = "ô";
- $from[0xF5] = "õ";
- $from[0xF6] = "ö";
- $from[0xF7] = "÷";
- $from[0xF8] = "ø";
- $from[0xF9] = "ù";
- $from[0xFA] = "ú";
- $from[0xFB] = "û";
- $from[0xFC] = "ü";
- $from[0xFD] = "ý";
- $from[0xFE] = "þ";
- $from[0xFF] = "ÿ";
-
-
- return array($from, $to);
- }
- /*
- 00 = U+0000 : NULL
-01 = U+0001 : START OF HEADING
-02 = U+0002 : START OF TEXT
-03 = U+0003 : END OF TEXT
-04 = U+0004 : END OF TRANSMISSION
-05 = U+0005 : ENQUIRY
-06 = U+0006 : ACKNOWLEDGE
-07 = U+0007 : BELL
-08 = U+0008 : BACKSPACE
-09 = U+0009 : HORIZONTAL TABULATION
-0A = U+000A : LINE FEED
-0B = U+000B : VERTICAL TABULATION
-0C = U+000C : FORM FEED
-0D = U+000D : CARRIAGE RETURN
-0E = U+000E : SHIFT OUT
-0F = U+000F : SHIFT IN
-10 = U+0010 : DATA LINK ESCAPE
-11 = U+0011 : DEVICE CONTROL ONE
-12 = U+0012 : DEVICE CONTROL TWO
-13 = U+0013 : DEVICE CONTROL THREE
-14 = U+0014 : DEVICE CONTROL FOUR
-15 = U+0015 : NEGATIVE ACKNOWLEDGE
-16 = U+0016 : SYNCHRONOUS IDLE
-17 = U+0017 : END OF TRANSMISSION BLOCK
-18 = U+0018 : CANCEL
-19 = U+0019 : END OF MEDIUM
-1A = U+001A : SUBSTITUTE
-1B = U+001B : ESCAPE
-1C = U+001C : FILE SEPARATOR
-1D = U+001D : GROUP SEPARATOR
-1E = U+001E : RECORD SEPARATOR
-1F = U+001F : UNIT SEPARATOR
-20 = U+0020 : SPACE
-21 = U+0021 : EXCLAMATION MARK
-22 = U+0022 : QUOTATION MARK
-23 = U+0023 : NUMBER SIGN
-24 = U+0024 : DOLLAR SIGN
-25 = U+0025 : PERCENT SIGN
-26 = U+0026 : AMPERSAND
-27 = U+0027 : APOSTROPHE
-28 = U+0028 : LEFT PARENTHESIS
-29 = U+0029 : RIGHT PARENTHESIS
-2A = U+002A : ASTERISK
-2B = U+002B : PLUS SIGN
-2C = U+002C : COMMA
-2D = U+002D : HYPHEN-MINUS
-2E = U+002E : FULL STOP
-2F = U+002F : SOLIDUS
-30 = U+0030 : DIGIT ZERO
-31 = U+0031 : DIGIT ONE
-32 = U+0032 : DIGIT TWO
-33 = U+0033 : DIGIT THREE
-34 = U+0034 : DIGIT FOUR
-35 = U+0035 : DIGIT FIVE
-36 = U+0036 : DIGIT SIX
-37 = U+0037 : DIGIT SEVEN
-38 = U+0038 : DIGIT EIGHT
-39 = U+0039 : DIGIT NINE
-3A = U+003A : COLON
-3B = U+003B : SEMICOLON
-3C = U+003C : LESS-THAN SIGN
-3D = U+003D : EQUALS SIGN
-3E = U+003E : GREATER-THAN SIGN
-3F = U+003F : QUESTION MARK
-40 = U+0040 : COMMERCIAL AT
-41 = U+0041 : LATIN CAPITAL LETTER A
-42 = U+0042 : LATIN CAPITAL LETTER B
-43 = U+0043 : LATIN CAPITAL LETTER C
-44 = U+0044 : LATIN CAPITAL LETTER D
-45 = U+0045 : LATIN CAPITAL LETTER E
-46 = U+0046 : LATIN CAPITAL LETTER F
-47 = U+0047 : LATIN CAPITAL LETTER G
-48 = U+0048 : LATIN CAPITAL LETTER H
-49 = U+0049 : LATIN CAPITAL LETTER I
-4A = U+004A : LATIN CAPITAL LETTER J
-4B = U+004B : LATIN CAPITAL LETTER K
-4C = U+004C : LATIN CAPITAL LETTER L
-4D = U+004D : LATIN CAPITAL LETTER M
-4E = U+004E : LATIN CAPITAL LETTER N
-4F = U+004F : LATIN CAPITAL LETTER O
-50 = U+0050 : LATIN CAPITAL LETTER P
-51 = U+0051 : LATIN CAPITAL LETTER Q
-52 = U+0052 : LATIN CAPITAL LETTER R
-53 = U+0053 : LATIN CAPITAL LETTER S
-54 = U+0054 : LATIN CAPITAL LETTER T
-55 = U+0055 : LATIN CAPITAL LETTER U
-56 = U+0056 : LATIN CAPITAL LETTER V
-57 = U+0057 : LATIN CAPITAL LETTER W
-58 = U+0058 : LATIN CAPITAL LETTER X
-59 = U+0059 : LATIN CAPITAL LETTER Y
-5A = U+005A : LATIN CAPITAL LETTER Z
-5B = U+005B : LEFT SQUARE BRACKET
-5C = U+005C : REVERSE SOLIDUS
-5D = U+005D : RIGHT SQUARE BRACKET
-5E = U+005E : CIRCUMFLEX ACCENT
-5F = U+005F : LOW LINE
-60 = U+0060 : GRAVE ACCENT
-61 = U+0061 : LATIN SMALL LETTER A
-62 = U+0062 : LATIN SMALL LETTER B
-63 = U+0063 : LATIN SMALL LETTER C
-64 = U+0064 : LATIN SMALL LETTER D
-65 = U+0065 : LATIN SMALL LETTER E
-66 = U+0066 : LATIN SMALL LETTER F
-67 = U+0067 : LATIN SMALL LETTER G
-68 = U+0068 : LATIN SMALL LETTER H
-69 = U+0069 : LATIN SMALL LETTER I
-6A = U+006A : LATIN SMALL LETTER J
-6B = U+006B : LATIN SMALL LETTER K
-6C = U+006C : LATIN SMALL LETTER L
-6D = U+006D : LATIN SMALL LETTER M
-6E = U+006E : LATIN SMALL LETTER N
-6F = U+006F : LATIN SMALL LETTER O
-70 = U+0070 : LATIN SMALL LETTER P
-71 = U+0071 : LATIN SMALL LETTER Q
-72 = U+0072 : LATIN SMALL LETTER R
-73 = U+0073 : LATIN SMALL LETTER S
-74 = U+0074 : LATIN SMALL LETTER T
-75 = U+0075 : LATIN SMALL LETTER U
-76 = U+0076 : LATIN SMALL LETTER V
-77 = U+0077 : LATIN SMALL LETTER W
-78 = U+0078 : LATIN SMALL LETTER X
-79 = U+0079 : LATIN SMALL LETTER Y
-7A = U+007A : LATIN SMALL LETTER Z
-7B = U+007B : LEFT CURLY BRACKET
-7C = U+007C : VERTICAL LINE
-7D = U+007D : RIGHT CURLY BRACKET
-7E = U+007E : TILDE
-7F = U+007F : DELETE
-80 = U+20AC : EURO SIGN
-82 = U+201A : SINGLE LOW-9 QUOTATION MARK
-83 = U+0192 : LATIN SMALL LETTER F WITH HOOK
-84 = U+201E : DOUBLE LOW-9 QUOTATION MARK
-85 = U+2026 : HORIZONTAL ELLIPSIS
-86 = U+2020 : DAGGER
-87 = U+2021 : DOUBLE DAGGER
-88 = U+02C6 : MODIFIER LETTER CIRCUMFLEX ACCENT
-89 = U+2030 : PER MILLE SIGN
-8A = U+0160 : LATIN CAPITAL LETTER S WITH CARON
-8B = U+2039 : SINGLE LEFT-POINTING ANGLE QUOTATION MARK
-8C = U+0152 : LATIN CAPITAL LIGATURE OE
-8E = U+017D : LATIN CAPITAL LETTER Z WITH CARON
-91 = U+2018 : LEFT SINGLE QUOTATION MARK
-92 = U+2019 : RIGHT SINGLE QUOTATION MARK
-93 = U+201C : LEFT DOUBLE QUOTATION MARK
-94 = U+201D : RIGHT DOUBLE QUOTATION MARK
-95 = U+2022 : BULLET
-96 = U+2013 : EN DASH
-97 = U+2014 : EM DASH
-98 = U+02DC : SMALL TILDE
-99 = U+2122 : TRADE MARK SIGN
-9A = U+0161 : LATIN SMALL LETTER S WITH CARON
-9B = U+203A : SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
-9C = U+0153 : LATIN SMALL LIGATURE OE
-9E = U+017E : LATIN SMALL LETTER Z WITH CARON
-9F = U+0178 : LATIN CAPITAL LETTER Y WITH DIAERESIS
-A0 = U+00A0 : NO-BREAK SPACE
-A1 = U+00A1 : INVERTED EXCLAMATION MARK
-A2 = U+00A2 : CENT SIGN
-A3 = U+00A3 : POUND SIGN
-A4 = U+00A4 : CURRENCY SIGN
-A5 = U+00A5 : YEN SIGN
-A6 = U+00A6 : BROKEN BAR
-A7 = U+00A7 : SECTION SIGN
-A8 = U+00A8 : DIAERESIS
-A9 = U+00A9 : COPYRIGHT SIGN
-AA = U+00AA : FEMININE ORDINAL INDICATOR
-AB = U+00AB : LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
-AC = U+00AC : NOT SIGN
-AD = U+00AD : SOFT HYPHEN
-AE = U+00AE : REGISTERED SIGN
-AF = U+00AF : MACRON
-B0 = U+00B0 : DEGREE SIGN
-B1 = U+00B1 : PLUS-MINUS SIGN
-B2 = U+00B2 : SUPERSCRIPT TWO
-B3 = U+00B3 : SUPERSCRIPT THREE
-B4 = U+00B4 : ACUTE ACCENT
-B5 = U+00B5 : MICRO SIGN
-B6 = U+00B6 : PILCROW SIGN
-B7 = U+00B7 : MIDDLE DOT
-B8 = U+00B8 : CEDILLA
-B9 = U+00B9 : SUPERSCRIPT ONE
-BA = U+00BA : MASCULINE ORDINAL INDICATOR
-BB = U+00BB : RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
-BC = U+00BC : VULGAR FRACTION ONE QUARTER
-BD = U+00BD : VULGAR FRACTION ONE HALF
-BE = U+00BE : VULGAR FRACTION THREE QUARTERS
-BF = U+00BF : INVERTED QUESTION MARK
-C0 = U+00C0 : LATIN CAPITAL LETTER A WITH GRAVE
-C1 = U+00C1 : LATIN CAPITAL LETTER A WITH ACUTE
-C2 = U+00C2 : LATIN CAPITAL LETTER A WITH CIRCUMFLEX
-C3 = U+00C3 : LATIN CAPITAL LETTER A WITH TILDE
-C4 = U+00C4 : LATIN CAPITAL LETTER A WITH DIAERESIS
-C5 = U+00C5 : LATIN CAPITAL LETTER A WITH RING ABOVE
-C6 = U+00C6 : LATIN CAPITAL LETTER AE
-C7 = U+00C7 : LATIN CAPITAL LETTER C WITH CEDILLA
-C8 = U+00C8 : LATIN CAPITAL LETTER E WITH GRAVE
-C9 = U+00C9 : LATIN CAPITAL LETTER E WITH ACUTE
-CA = U+00CA : LATIN CAPITAL LETTER E WITH CIRCUMFLEX
-CB = U+00CB : LATIN CAPITAL LETTER E WITH DIAERESIS
-CC = U+00CC : LATIN CAPITAL LETTER I WITH GRAVE
-CD = U+00CD : LATIN CAPITAL LETTER I WITH ACUTE
-CE = U+00CE : LATIN CAPITAL LETTER I WITH CIRCUMFLEX
-CF = U+00CF : LATIN CAPITAL LETTER I WITH DIAERESIS
-D0 = U+00D0 : LATIN CAPITAL LETTER ETH
-D1 = U+00D1 : LATIN CAPITAL LETTER N WITH TILDE
-D2 = U+00D2 : LATIN CAPITAL LETTER O WITH GRAVE
-D3 = U+00D3 : LATIN CAPITAL LETTER O WITH ACUTE
-D4 = U+00D4 : LATIN CAPITAL LETTER O WITH CIRCUMFLEX
-D5 = U+00D5 : LATIN CAPITAL LETTER O WITH TILDE
-D6 = U+00D6 : LATIN CAPITAL LETTER O WITH DIAERESIS
-D7 = U+00D7 : MULTIPLICATION SIGN
-D8 = U+00D8 : LATIN CAPITAL LETTER O WITH STROKE
-D9 = U+00D9 : LATIN CAPITAL LETTER U WITH GRAVE
-DA = U+00DA : LATIN CAPITAL LETTER U WITH ACUTE
-DB = U+00DB : LATIN CAPITAL LETTER U WITH CIRCUMFLEX
-DC = U+00DC : LATIN CAPITAL LETTER U WITH DIAERESIS
-DD = U+00DD : LATIN CAPITAL LETTER Y WITH ACUTE
-DE = U+00DE : LATIN CAPITAL LETTER THORN
-DF = U+00DF : LATIN SMALL LETTER SHARP S
-E0 = U+00E0 : LATIN SMALL LETTER A WITH GRAVE
-E1 = U+00E1 : LATIN SMALL LETTER A WITH ACUTE
-E2 = U+00E2 : LATIN SMALL LETTER A WITH CIRCUMFLEX
-E3 = U+00E3 : LATIN SMALL LETTER A WITH TILDE
-E4 = U+00E4 : LATIN SMALL LETTER A WITH DIAERESIS
-E5 = U+00E5 : LATIN SMALL LETTER A WITH RING ABOVE
-E6 = U+00E6 : LATIN SMALL LETTER AE
-E7 = U+00E7 : LATIN SMALL LETTER C WITH CEDILLA
-E8 = U+00E8 : LATIN SMALL LETTER E WITH GRAVE
-E9 = U+00E9 : LATIN SMALL LETTER E WITH ACUTE
-EA = U+00EA : LATIN SMALL LETTER E WITH CIRCUMFLEX
-EB = U+00EB : LATIN SMALL LETTER E WITH DIAERESIS
-EC = U+00EC : LATIN SMALL LETTER I WITH GRAVE
-ED = U+00ED : LATIN SMALL LETTER I WITH ACUTE
-EE = U+00EE : LATIN SMALL LETTER I WITH CIRCUMFLEX
-EF = U+00EF : LATIN SMALL LETTER I WITH DIAERESIS
-F0 = U+00F0 : LATIN SMALL LETTER ETH
-F1 = U+00F1 : LATIN SMALL LETTER N WITH TILDE
-F2 = U+00F2 : LATIN SMALL LETTER O WITH GRAVE
-F3 = U+00F3 : LATIN SMALL LETTER O WITH ACUTE
-F4 = U+00F4 : LATIN SMALL LETTER O WITH CIRCUMFLEX
-F5 = U+00F5 : LATIN SMALL LETTER O WITH TILDE
-F6 = U+00F6 : LATIN SMALL LETTER O WITH DIAERESIS
-F7 = U+00F7 : DIVISION SIGN
-F8 = U+00F8 : LATIN SMALL LETTER O WITH STROKE
-F9 = U+00F9 : LATIN SMALL LETTER U WITH GRAVE
-FA = U+00FA : LATIN SMALL LETTER U WITH ACUTE
-FB = U+00FB : LATIN SMALL LETTER U WITH CIRCUMFLEX
-FC = U+00FC : LATIN SMALL LETTER U WITH DIAERESIS
-FD = U+00FD : LATIN SMALL LETTER Y WITH ACUTE
-FE = U+00FE : LATIN SMALL LETTER THORN
-FF = U+00FF : LATIN SMALL LETTER Y WITH DIAERESIS
- *
- */
-}
-?>
+++ /dev/null
-<?php
-
-abstract class ContentProvider{
- /**
- * Get the text data to be integrated in the MOBI file
- * @return string
- */
- public abstract function getTextData();
- /**
- * Get the images (an array containing the jpeg data). Array entry 0 will
- * correspond to image record 0.
- * @return array
- */
- public abstract function getImages();
- /**
- * Get the metadata in the form of a hashtable (for example, title or author).
- * @return array
- */
- public abstract function getMetaData();
-}
-
-?>
+++ /dev/null
-<?php
-//Reference: http://wiki.mobileread.com/wiki/MOBI
-
-class EXTHHelper{
- static function typeToText($type){
- $types = self::$types;
- if(isset($types[$type])){
- return $types[$type];
- }
- return $type;
- }
- static function textToType($text){
- $text = strtolower($text);
- if(isset(self::$flippedTypes[$text])){
- return self::$flippedTypes[$text];
- }
- return false;
- }
-
- static function convert($n, $size){
- $mask = 0xFF;
- $out = "";
- for($i = 0; $i < $size; $i++){
- $out = chr(($n & $mask) >> (8*$i)).$out;
- $mask = $mask << 8;
- }
- return $out;
- }
-
- static function getRightRepresentation($type, $value){
- if($type >= 100 && $type < 200){
- return $value;
- }else{
- return self::toHex($value);
- }
- }
-
- static function toHex($value){
- $out = "";
- for($i = 0, $len = strlen($value); $i < $len; $i++){
- if($i > 0) $out .= " ";
- $hex = dechex(ord($value[$i]));
- if(strlen($hex) < 2) $hex = "0".$hex;
- $out .= $hex;
- }
- return $out;
- }
-
-
- static private $types = array(
- 1 => "drm server id",
- 2 => "drm commerce id",
- 3 => "drm ebookbase book id",
- 100 => "author",
- 101 => "publisher",
- 102 => "imprint",
- 103 => "description",
- 104 => "isbn",
- 105 => "subject",
- 106 => "publishingdate",
- 107 => "review",
- 108 => "contributor",
- 109 => "rights",
- 110 => "subjectcode",
- 111 => "type",
- 112 => "source",
- 113 => "asin",
- 114 => "versionnumber",
- 115 => "sample",
- 116 => "startreading",
- 118 => "retail price",
- 119 => "retail price currency",
- 201 => "coveroffset",
- 202 => "thumboffset",
- 203 => "hasfakecover",
- 204 => "Creator Software",
- 205 => "Creator Major Version",
- 206 => "Creator Minor Version",
- 207 => "Creator Build Number",
- 208 => "watermark",
- 209 => "tamper proof keys",
- 300 => "fontsignature",
- 401 => "clippinglimit",
- 402 => "publisherlimit",
- 403 => "403",
- 404 => "ttsflag",
- 501 => "cdetype",
- 502 => "lastupdatetime",
- 503 => "updatedtitle"
- );
- static private $flippedTypes = array(
- "drm server id" => 1,
- "drm commerce id" => 2,
- "drm ebookbase book id" => 3,
- "author" => 100,
- "publisher" => 101,
- "imprint" => 102,
- "description" => 103,
- "isbn" => 104,
- "subject" => 105,
- "publishingdate" => 106,
- "review" => 107,
- "contributor" => 108,
- "rights" => 109,
- "subjectcode" => 110,
- "type" => 111,
- "source" => 112,
- "asin" => 113,
- "versionnumber" => 114,
- "sample" => 115,
- "startreading" => 116,
- "retail price" => 118,
- "retail price currency" => 119,
- "coveroffset" => 201,
- "thumboffset" => 202,
- "hasfakecover" => 203,
- "Creator Software" => 204,
- "Creator Major Version" => 205,
- "Creator Minor Version" => 206,
- "Creator Build Number" => 207,
- "watermark" => 208,
- "tamper proof keys" => 209,
- "fontsignature" => 300,
- "clippinglimit" => 401,
- "publisherlimit" => 402,
- "403" => 403,
- "ttsflag" => 404,
- "cdetype" => 501,
- "lastupdatetime" => 502,
- "updatedtitle" => 503
- );
-}
\ No newline at end of file
+++ /dev/null
-<?php
-
-/**
- * Description of FileByte
- *
- * @author Sander
- */
-class FileByte extends FileObject {
- private $data;
-
- /**
- * Make a short to be stored in a file
- * @param short $n
- */
- public function __construct($n = 0){
- parent::__construct(1);
- $this->set($n);
- }
-
- public function get(){
- return $this->data;
- }
-
- public function set($value){
- $this->data = intval($value) & 0xFF;
- }
-
- public function serialize() {
- return $this->byteToString($this->data);
- }
-
- public function unserialize($data) {
- __construct($this->toInt($data));
- }
-
-
- public function __toString(){
- return "FileByte: {".$this->byteAsString($this->data)."}";
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of FileDate
- *
- * @author Sander
- */
-class FileDate extends FileObject {
- private $data;
-
- /**
- * Make an integer to be stored in a file
- * @param int $n
- */
- public function __construct($n = 0){
- parent::__construct(4);
- $this->set($n);
- }
-
- public function get(){
- return $this->data;
- }
-
- public function set($value){
- $this->data = intval($value);
- }
-
- public function serialize() {
- return $this->intToString($this->data);
- }
-
- public function unserialize($data) {
- __construct($this->toInt($data));
- }
-
- public function __toString(){
- return "FileDate: {".(date("r", $this->data-94694400))."}";
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of FileElement
- *
- * @author Sander
- */
-class FileElement {
- /**
- * @var FileObject
- */
- public $elements;
-
- /**
- * Make a record to be stored in a file
- * @param Record $record
- */
- public function __construct($elements = array()){
- $this->elements = $elements;
- }
-
- public function getByteLength(){
- return $this->getLength();
- }
-
- public function getLength(){
- $total = 0;
- foreach($this->elements as $val){
- $total += $val->getByteLength();
- }
- return $total;
- }
-
- public function offsetToEntry($name){
- $pos = 0;
- foreach($this->elements as $key=>$value){
- if($name == $key){
- break;
- }
- $pos += $value->getByteLength();
- }
- return $pos;
- }
-
- public function exists($key){
- return isset($this->elements[$key]);
- }
- /**
- * @param string $key
- * @return FileObject
- */
- public function get($key){
- return $this->elements[$key];
- }
-
- /**
- * @param string $key
- * @param FileObject $value
- */
- public function set($key, $value){
- $this->elements[$key] = $value;
- }
-
- public function add($key, $value){
- $this->elements[$key] = $value;
- }
-
- public function serialize() {
- $result = "";
- foreach($this->elements as $val){
- $result .= $val->serialize();
- }
- return $result;
- }
-
- public function unserialize($data) {
- //TODO: If reading is needed -> way more complex
- }
-
- public function __toString(){
- $output = "FileElement (".$this->getByteLength()." bytes): {\n";
- foreach($this->elements as $key=>$value){
- $output .= "\t".$key.": ".$value."\n";
- }
- $output .= "}";
- return $output;
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of FileInt
- *
- * @author Sander
- */
-class FileInt extends FileObject {
- private $data;
-
- /**
- * Make an integer to be stored in a file
- * @param int $n
- */
- public function __construct($n = 0){
- parent::__construct(4);
- $this->set($n);
- }
-
- public function get(){
- return $this->data;
- }
-
- public function set($value){
- $this->data = intval($value);
- }
-
- public function serialize() {
- return $this->intToString($this->data);
- }
-
- public function unserialize($data) {
- __construct($this->toInt($data));
- }
-
- public function __toString(){
- return "FileInt: {".$this->intAsString($this->data)."}";
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of FileObject
- *
- * @author Sander
- */
-abstract class FileObject {
- private $byteLength = -1;
-
- public function __construct($byteLength = -1){
- $this->byteLength = $byteLength;
- }
-
- public function getByteLength(){
- if($this->byteLength >= 0){
- return $this->byteLength;
- }
- return $this->getLength();
- }
-
- public function getLength(){
- throw new Exception("Sub-class needs to implement this if it doesn't have a fixed length");
- }
-
- /**
- * Convert a string to byte format (maximum 4 bytes)
- * @param string $string Input string
- * @return int Output integer
- */
- public function toInt($string){
- $out = 0;
- for($i = 0, $len = min(4, strlen($string)); $i < $len; $i++){
- $out = $out | (ord($string[$i]) << (($len-$i-1)*8));
- }
- return $out;
- }
-
- /**
- * Convert a byte (stored in an integer) to a string
- * @param byte $int
- * @return string
- */
- public function byteToString($int){
- return $this->toString($int, 1);
- }
-
- /**
- * Convert a byte (stored in an integer) to a string
- * @param byte $int
- * @return string
- */
- public function byteAsString($int){
- return $this->asString($int, 1);
- }
-
- /**
- * Convert a short (stored in an integer) to a string
- * @param short $int
- * @return string
- */
- public function shortToString($int){
- return $this->toString($int, 2);
- }
-
- /**
- * Convert a short (stored in an integer) to a string
- * @param short $int
- * @return string
- */
- public function shortAsString($int){
- return $this->asString($int, 2);
- }
-
- /**
- * Convert a tri-byte (stored in an integer) to a string
- * @param tri-byte $int
- * @return string
- */
- public function triToString($int){
- return $this->toString($int, 3);
- }
-
- /**
- * Convert a tri-byte (stored in an integer) to a string
- * @param tri-byte $int
- * @return string
- */
- public function triAsString($int){
- return $this->asString($int, 3);
- }
-
- /**
- * Convert an integer to a string
- * @param int $int
- * @return string
- */
- public function intToString($int){
- return $this->toString($int, 4);
- }
-
- /**
- * Convert an integer to a string
- * @param int $int
- * @return string
- */
- public function intAsString($int){
- return $this->asString($int, 4);
- }
-
- /**
- * Convert a number of n bytes to a string
- * @param int $int Number that should be converted
- * @param int $size Number of bytes to convert
- * @return string Output string
- */
- private function toString($int, $size){
- $out = "";
- for($i = 0; $i < $size; $i++){
- $out = chr($int & 0xFF).$out;
- $int = $int >> 8;
- }
- return $out;
- }
-
- /**
- * Convert a number of n bytes to a string
- * @param int $int Number that should be converted
- * @param int $size Number of bytes to convert
- * @return string Output string
- */
- private function asString($int, $size){
- $out = "";
- for($i = 0; $i < $size; $i++){
- if($i > 0) $out = " ".$out;
- $byte = dechex($int & 0xFF);
- if(strlen($byte) == 1) $byte = "0".$byte;
- $out = $byte.$out;
- $int = $int >> 8;
- }
- return $out;
- }
-
- /**
- * Get the value
- * @return mixed Value to get
- */
- abstract public function get();
-
- /**
- * Set the value
- * @return mixed Value to set
- */
- abstract public function set($value);
-
- /**
- * Serialize the object
- * @return string String representation
- */
- abstract public function serialize();
-
- /**
- * Unserialize the object
- * @param string $data String representation
- */
- abstract public function unserialize($data);
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of FileRecord
- *
- * @author Sander
- */
-class FileRecord extends FileObject {
- /**
- * @var Record
- */
- private $record;
-
- /**
- * Make a record to be stored in a file
- * @param Record $record
- */
- public function __construct($record){
- $this->record = $record;
- }
-
- public function getByteLength(){
- return $this->getLength();
- }
-
- public function getLength(){
- return $this->record->getLength();
- }
-
- public function get(){
- return $this->record;
- }
-
- public function set($record){
- $this->record = $record;
- }
-
- public function serialize() {
- return $this->record->serialize();
- }
-
- public function unserialize($data) {
- __construct($this->record->unserialize($data));
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of FileShort
- *
- * @author Sander
- */
-class FileShort extends FileObject {
- private $data;
-
- /**
- * Make a short to be stored in a file
- * @param short $n
- */
- public function __construct($n = 0){
- parent::__construct(2);
- $this->set($n);
- }
-
- public function get(){
- return $this->data;
- }
-
- public function set($value){
- $this->data = intval($value) & 0xFFFF;
- }
-
- public function serialize() {
- return $this->shortToString($this->data);
- }
-
- public function unserialize($data) {
- __construct($this->toInt($data));
- }
-
-
- public function __toString(){
- return "FileShort: {".$this->shortAsString($this->data)."}";
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of FileString
- *
- * @author Sander
- */
-class FileString extends FileObject {
- private $forcedLength;
- private $data;
-
- /**
- * Make a string to be stored in a file
- * @param string|int $first Optional, if it is a string, it will be the contents,
- * if it is a number, it will set the forced length.
- * @param int $second Optional, will set the forced length. Can only be used when the
- * first argument is contents.
- */
- public function __construct($first = null, $second = null){
- $this->forcedLength = -1;
- $this->data = "";
-
- if($second != null){
- $this->data = $first;
- $this->forcedLength = $second;
- }else if($first != null){
- if(is_string($first)){
- $this->data = $first;
- }else{
- $this->forcedLength = $first;
- }
- }
- }
-
- public function getByteLength(){
- return $this->getLength();
- }
-
- public function getLength(){
- if($this->forcedLength >= 0){
- return $this->forcedLength;
- }
- return strlen($this->data);
- }
-
- public function get(){
- return $this->data;
- }
-
- public function set($value){
- $this->data = $value;
- }
-
- public function serialize() {
- $output = $this->data;
- $curLength = strlen($output);
-
- if($this->forcedLength >= 0){
- if($this->forcedLength > $curLength){
- return str_pad($output, $this->forcedLength, "\0", STR_PAD_RIGHT);
- }elseif($this->forcedLength == $curLength){
- return $output;
- }else{
- return substr($output, 0, $this->forcedLength);
- }
- }
- return $output;
- }
-
- public function unserialize($data) {
- __construct($data);
- }
-
- public function __toString(){
- $out = "FileString";
- if($this->forcedLength >= 0){
- $out .= " ".$this->forcedLength;
- }
- $out .= ": {\"".str_replace(array(" ", "\0"), " ", $this->serialize())."\"}";
- return $out;
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of FileTri
- *
- * @author Sander
- */
-class FileTri extends FileObject {
- private $data;
-
- /**
- * Make a tri-byte to be stored in a file
- * @param tri-byte $n
- */
- public function __construct($n = 0){
- parent::__construct(3);
- $this->set($n);
- }
-
- public function get(){
- return $this->data;
- }
-
- public function set($value){
- $this->data = intval($value) & 0xFFFFFF;
- }
-
- public function serialize() {
- return $this->triToString($this->data);
- }
-
- public function unserialize($data) {
- __construct($this->toInt($data));
- }
-
-
- public function __toString(){
- return "FileTri: {".$this->triAsString($this->data)."}";
- }
-}
-?>
+++ /dev/null
-<?php
-class Http{
- private static $cache = false;
-
- public static function Request($url){
- $url_parts = parse_url($url);
- $url_parts["port"] = isset($url_parts["port"]) ? $url_parts["port"] : 80;
- $url_parts["path"] = isset($url_parts["path"]) ? $url_parts["path"] : "/";
-
- return self::FullRequest("GET", $url_parts["host"], $url_parts["port"], $url_parts["path"]);
- }
-
- public static function FullRequest(
- $verb = 'GET', /* HTTP Request Method (GET and POST supported) */
- $ip, /* Target IP/Hostname */
- $port = 80, /* Target TCP port */
- $uri = '/', /* Target URI */
- $getdata = array(), /* HTTP GET Data ie. array('var1' => 'val1', 'var2' => 'val2') */
- $postdata = array(), /* HTTP POST Data ie. array('var1' => 'val1', 'var2' => 'val2') */
- $cookie = array(), /* HTTP Cookie Data ie. array('var1' => 'val1', 'var2' => 'val2') */
- $custom_headers = array(), /* Custom HTTP headers ie. array('Referer: http://localhost/ */
- $timeout = 1000, /* Socket timeout in milliseconds */
- $req_hdr = false, /* Include HTTP request headers */
- $res_hdr = false, /* Include HTTP response headers */
- $depth = 4 /* Depth of the iteration left (to avoid redirection loops) */
- )
- {
- if(self::$cache){
- $cacheFile = "cache/".$ip."/".str_replace("/", "...", $uri);
-
- if(is_file($cacheFile)){
- $data = file_get_contents($cacheFile);
-
- return self::resolveTruncated($data);
- }
- }
- $ret = '';
- $verb = strtoupper($verb);
- $cookie_str = '';
- $getdata_str = count($getdata) ? '?' : '';
- $postdata_str = '';
-
- foreach ($getdata as $k => $v)
- $getdata_str .= urlencode($k) .'='. urlencode($v);
-
- foreach ($postdata as $k => $v)
- $postdata_str .= urlencode($k) .'='. urlencode($v) .'&';
-
- foreach ($cookie as $k => $v)
- $cookie_str .= urlencode($k) .'='. urlencode($v) .'; ';
-
- $crlf = "\r\n";
- $req = $verb .' '. $uri . $getdata_str .' HTTP/1.1' . $crlf;
- $req .= 'Host: '. $ip . $crlf;
- $req .= 'User-Agent: Mozilla/5.0 Firefox/3.6.12' . $crlf;
- $req .= 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' . $crlf;
- $req .= 'Accept-Language: en-us,en;q=0.5' . $crlf;
- $req .= 'Accept-Encoding: deflate' . $crlf;
- $req .= 'Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7' . $crlf;
-
-
- foreach ($custom_headers as $k => $v)
- $req .= $k .': '. $v . $crlf;
-
- if (!empty($cookie_str))
- $req .= 'Cookie: '. substr($cookie_str, 0, -2) . $crlf;
-
- if ($verb == 'POST' && !empty($postdata_str))
- {
- $postdata_str = substr($postdata_str, 0, -1);
- $req .= 'Content-Type: application/x-www-form-urlencoded' . $crlf;
- $req .= 'Content-Length: '. strlen($postdata_str) . $crlf . $crlf;
- $req .= $postdata_str;
- }
- else $req .= $crlf;
-
- if ($req_hdr)
- $ret .= $req;
-
- if (($fp = @fsockopen($ip, $port, $errno, $errstr)) == false)
- return "Error $errno: $errstr\n";
-
- stream_set_timeout($fp, 0, $timeout * 1000);
-
- fputs($fp, $req);
- $ret .= stream_get_contents($fp);
- fclose($fp);
-
- $headerSplit = strpos($ret, "\r\n\r\n");
- $header = substr($ret, 0, $headerSplit);
-
- $redirectURL = self::CheckForRedirect($header);
-
- if($redirectURL !== false){
- if($depth > 0){
- $url_parts = parse_url($redirectURL);
- $url_parts["port"] = isset($url_parts["port"]) ? $url_parts["port"] : 80;
- $url_parts["path"] = isset($url_parts["path"]) ? $url_parts["path"] : "/";
-
- return self::FullRequest($verb, $url_parts["host"], $url_parts["port"], $url_parts["path"], $getdata, $postdata, $cookie, $custom_headers, $timeout, $req_hdr, $res_hdr, $depth-1);
- }else{
- return "Redirect loop, stopping...";
- }
- }
-
- $truncated = false;
- $headerLines = explode("\r\n", $header);
- foreach($headerLines as $line){
- list($name, $value) = explode(":", $line);
- $name = trim($name);
- $value = trim($value);
-
- if(strtolower($name) == "transfer-encoding" && strtolower($value) == "chunked"){ //TODO: Put right values!
- $truncated = true;
- }
- }
-
- if (!$res_hdr)
- $ret = substr($ret, $headerSplit + 4);
-
- if($truncated){
- $ret = self::resolveTruncated($ret);
- }
- if(self::$cache){
- if(!is_dir("cache")){
- mkdir("cache");
- }
- if(!is_dir("cache/".$ip)){
- mkdir("cache/".$ip);
- }
- if(!is_file("cache/".$ip."/".str_replace("/", "...", $uri))){
- $h = fopen("cache/".$ip."/".str_replace("/", "...", $uri), "w");
- fwrite($h, $ret);
- fclose($h);
- }
- }
-
- return $ret;
- }
-
- private static function resolveTruncated($data){
- $pos = 0;
- $end = strlen($data);
- $out = "";
-
- while($pos < $end){
- $endVal = strpos($data, "\r\n", $pos);
- $value = hexdec(substr($data, $pos, $endVal-$pos));
- $out .= substr($data, $endVal+2, $value);
- $pos = $endVal+2+$value;
- }
-
- return $out;
- }
-
- private static function CheckForRedirect($header){
- $firstLine = substr($header, 0, strpos($header, "\r\n"));
- list($httpVersion, $statusCode, $message) = explode(" ", $firstLine);
-
- if(substr($statusCode, 0, 1) == "3"){
- $part = substr($header, strpos(strtolower($header), "location: ")+strlen("location: "));
- $location = trim(substr($part, 0, strpos($part, "\r\n")));
-
- if(strlen($location) > 0){
- return $location;
- }
- }
- return false;
- }
-}
-?>
\ No newline at end of file
+++ /dev/null
-<?php
-
-class ImageHandler {
- /**
- * Download an image
- * @param string $url Url to the image
- * @return false|string False if failed, else the data of the image (converted to grayscale jpeg)
- */
- public static function DownloadImage($url){
- $data = Http::Request($url);
- $imgFile = @imagecreatefromstring($data);
-
- if($imgFile !== false){
- $result = self::CreateImage($imgFile);
- imagedestroy($imgFile);
- return $result;
- }
- return false;
- }
- /**
- * Create an image
- * @param resource $img Create an image created with createimagetruecolor
- * @return false|string False if failed, else the data of the image (converted to grayscale jpeg)
- */
- public static function CreateImage($img){
- try{
- imagefilter($img, IMG_FILTER_GRAYSCALE);
-
- ob_start();
- imagejpeg($img);
- $image = ob_get_contents();
- ob_end_clean();
-
- return $image;
- }catch(Exception $e){
- return false;
- }
- }
-}
-?>
+++ /dev/null
-<?php
-require_once(dirname(__FILE__)."/../readability/Readability.php");
-require_once(dirname(__FILE__).'/CharacterEntities.php');
-require_once(dirname(__FILE__).'/constants.php');
-require_once(dirname(__FILE__).'/ContentProvider.php');
-require_once(dirname(__FILE__).'/MultipleFileHandler.php');
-require_once(dirname(__FILE__)."/downloaders/FanFictionNet.php");
-require_once(dirname(__FILE__).'/EXTHHelper.php');
-require_once(dirname(__FILE__).'/FileObject.php');
-require_once(dirname(__FILE__).'/FileByte.php');
-require_once(dirname(__FILE__).'/FileDate.php');
-require_once(dirname(__FILE__).'/FileElement.php');
-require_once(dirname(__FILE__).'/FileInt.php');
-require_once(dirname(__FILE__).'/FileRecord.php');
-require_once(dirname(__FILE__).'/FileShort.php');
-require_once(dirname(__FILE__).'/FileString.php');
-require_once(dirname(__FILE__).'/FileTri.php');
-require_once(dirname(__FILE__).'/Http.php');
-require_once(dirname(__FILE__).'/http_build_url.php');
-require_once(dirname(__FILE__).'/ImageHandler.php');
-require_once(dirname(__FILE__).'/MOBIFile.php');
-require_once(dirname(__FILE__).'/OnlineArticle.php');
-require_once(dirname(__FILE__).'/PalmRecord.php');
-require_once(dirname(__FILE__).'/Prc.php');
-require_once(dirname(__FILE__).'/PreprocessedArticle.php');
-require_once(dirname(__FILE__).'/RecognizeURL.php');
-require_once(dirname(__FILE__).'/Record.php');
-require_once(dirname(__FILE__).'/RecordFactory.php');
-require_once(dirname(__FILE__).'/Settings.php');
-
-/**
- * Description of MOBI.
- *
- * Usage:
- * include("MOBIClass/MOBI.php");
- *
- * $mobi = new MOBI();
- *
- * //Then use one of the following ways to prepare information (it should be in the form of valid html)
- * $mobi->setInternetSource($url); //Load URL, the result will be cleaned using a Readability port
- * $mobi->setFileSource($file); //Load a local file without any extra changes
- * $mobi->setData($data); //Load data
- *
- * //If you want, you can set some optional settings (see Settings.php for all recognized settings)
- * $options = array(
- * "title"=>"Insert title here",
- * "author"=>"Author"
- * );
- * $mobi->setOptions($options);
- *
- * //Then there are two ways to output it:
- * $mobi->save($file); //Save the file locally
- * $mobi->download($name); //Let the client download the file, make sure the page
- * //that calls it doesn't output anything, otherwise it might
- * //conflict with the download. $name contains the file name,
- * //usually something like "title.mobi" (where the title should
- * //be cleaned so as not to contain illegal characters).
- *
- *
- * @author Sander Kromwijk
- */
-class MOBI {
- private $source = false;
- private $images = array();
- private $optional = array();
- private $imgCounter = 0;
- private $debug = false;
- private $prc = false;
-
- public function __construct(){
-
- }
-
- public function getTitle(){
- if(isset($this->optional["title"])){
- return $this->optional["title"];
- }
- return false;
- }
-
- /**
- * Set a content provider as source
- * @param ContentProvider $content Content Provider to use
- */
- public function setContentProvider($content){
- $this->setOptions($content->getMetaData());
- $this->setImages($content->getImages());
- $this->setData($content->getTextData());
- }
-
- /**
- * Set a local file as source
- * @param string $file Path to the file
- */
- public function setFileSource($file){
- $this->setData(file_get_contents($file));
- }
-
- /**
- * Set the data to use
- * @param string $data Data to put in the file
- */
- public function setData($data){
- //$data = utf8_encode($data);
- $data = CharacterEntities::convert($data);
- //$data = utf8_decode($data);
- //$this->source = iconv('UTF-8', 'ISO-8859-1//TRANSLIT', $data);
- $this->source = $data;
- $this->prc = false;
- }
-
- /**
- * Set the images to use
- * @param array $data Data to put in the file
- */
- public function setImages($data){
- $this->images = $data;
- $this->prc = false;
- }
-
- /**
- * Set options, usually for things like titles, authors, etc...
- * @param array $options Options to set
- */
- public function setOptions($options){
- $this->optional = $options;
- $this->prc = false;
- }
-
- /**
- * Prepare the prc file
- * @return Prc The file that can be used to be saved/downloaded
- */
- private function preparePRC(){
- if($this->source === false){
- throw new Exception("No data set");
- }
- if($this->prc !== false) return $this->prc;
-
- $data = $this->source;
- $len = strlen($data);
-
- $settings = new Settings($this->optional);
- $rec = new RecordFactory($settings);
- $dataRecords = $rec->createRecords($data);
- $nRecords = sizeof($dataRecords);
- $mobiHeader = new PalmRecord($settings, $dataRecords, $nRecords, $len, sizeof($this->images));
- array_unshift($dataRecords, $mobiHeader);
- $dataRecords = array_merge($dataRecords, $this->images);
- $dataRecords[] = $rec->createFLISRecord();
- $dataRecords[] = $rec->createFCISRecord($len);
- $dataRecords[] = $rec->createEOFRecord();
- $this->prc = new Prc($settings, $dataRecords);
- return $this->prc;
- }
-
- /**
- * Save the file locally
- * @param string $filename Path to save the file
- */
- public function save($filename){
- $prc = $this->preparePRC();
- $prc->save($filename);
- }
-
- /**
- * Let the client download the file. Warning! No data should be
- * outputted before or after.
- * @param string $name Name used for download, usually "title.mobi"
- */
- public function download($name){
- $prc = $this->preparePRC();
- $data = $prc->serialize();
- $length = strlen($data);
-
- if($this->debug) return; //In debug mode, don't start the download
-
- header("Content-Type: application/x-mobipocket-ebook");
- header("Content-Disposition: attachment; filename=\"".$name."\"");
- header("Content-Transfer-Encoding: binary");
- header("Accept-Ranges: bytes");
- header("Cache-control: private");
- header('Pragma: private');
- header("Expires: Mon, 26 Jul 1997 05:00:00 GMT");
- header("Content-Length: ".$length);
-
- echo $data;
- //Finished!
- }
-
-}
-?>
+++ /dev/null
-<?php
-/**
- * This is the way MOBI files should be created if you want all features (TOC, images).
- *
- * File modified by Dawson for use in eBook Creator
- * Added pagebreaks and a setting to remove table of contents.
- */
-
-class MOBIFile extends ContentProvider {
- const PARAGRAPH = 0;
- const H2 = 1;
- const H3 = 2;
- const IMAGE = 3;
- const PAGEBREAK = 4;
-
- private $settings = array("title" => "Unknown Title", "toc" => true);
- private $parts = array();
- private $images = array();
-
- /**
- * Get the text data (the "html" code)
- */
- public function getTextData(){
- $prefix = "<html><head><guide><reference title='CONTENT' type='toc' filepos=0000000000 /></guide></head><body>";
-
- $title = "<h1>".$this->settings["title"]."</h1>";
-
- list($text, $entries) = $this->generateText();
-
- if($this->settings["toc"]) {
- $toc = $this->generateTOC($entries); //Generate TOC to get the right length
- $toc = $this->generateTOC($entries, strlen($prefix)+strlen($toc)+strlen($title)); //Generate the real TOC
- }
-
- $suffix = "</body></html>";
-
- return $prefix.$toc.$title.$text.$suffix;
- }
-
- /**
- * Generate the body's text and the chapter entries
- * @return array($string, $entries) $string is the html data, $entries
- * contains the level, the title and the position of the titles.
- */
- public function generateText(){
- $str = "";
- $entries = array();
-
- for($i = 0; $i < sizeof($this->parts); $i++){
- list($type, $data) = $this->parts[$i];
- $id = "title_".$i;
- switch($type){
- case self::PARAGRAPH:
- $str .= "<p>".$data."</p>";
- break;
- case self::PAGEBREAK:
- $str .= '<mbp:pagebreak/>';
- break;
- case self::H2:
- $entries[] = array("level" => 2, "position" => strlen($str), "title" => $data, "id" => $id);
- $str .= "<h2 id='" . $id . "'>".$data."</h2>";
- break;
- case self::H3:
- $entries[] = array("level" => 3, "position" => strlen($str), "title" => $data, "id" => $id);
- $str .= "<h3 id='" . $id . "'>".$data."</h3>";
- break;
- case self::IMAGE:
- $str .= "<img recindex=".str_pad($data+1, 10, "0", STR_PAD_LEFT)." />";
- break;
- }
- }
- return array($str, $entries);
- }
-
- /**
- * Generate a TOC
- * @param $entries The entries array generated by generateText
- * @param $base The zero position
- */
- public function generateTOC($entries, $base = 0){
- $toc = "<h2>Contents</h2>";
- $toc .= "<blockquote><table summary='Table of Contents'><col/><tbody>";
- for($i = 0, $len = sizeof($entries); $i < $len; $i++){
- $entry = $entries[$i];
- $pos = str_pad($entry["position"]+$base, 10, "0", STR_PAD_LEFT);
- $toc .= "<tr><td><a href='#".$entry["id"]."' filepos='".$pos."'>".$entry["title"]."</a></td></tr>";
- }
- return $toc."</tbody></b></table></blockquote><mbp:pagebreak/>";
- }
-
- /**
- * Get the file records of the images
- */
- public function getImages(){
- return $this->images;
- }
-
- /**
- * Get the metadata
- */
- public function getMetaData(){
- return $this->settings;
- }
-
- /**
- * Change the file's settings. For example set("author", "John Doe") or set("title", "The adventures of John Doe").
- * @param $key Key of the setting to insert.
- */
- public function set($key, $value){
- $this->settings[$key] = $value;
- }
-
- /**
- * Get the file's settings.
- */
- public function get($key){
- return $this->settings[$key];
- }
-
- /**
- * Append a paragraph of text to the file.
- * @param string $text The text to insert.
- */
- public function appendParagraph($text){
- $this->parts[] = array(self::PARAGRAPH, $text);
- }
-
- /**
- * Append a chapter title (H2)
- * @param string $title The title to insert.
- */
- public function appendChapterTitle($title){
- $this->parts[] = array(self::H2, $title);
- }
-
- /**
- * Append a section title (H3)
- * @param string $title The title to insert.
- */
- public function appendSectionTitle($title){
- $this->parts[] = array(self::H3, $title);
- }
-
- public function appendPageBreak() {
- $this->parts[] = array(self::PAGEBREAK, null);
- }
-
- /**
- * Append an image.
- * @param resource $img An image file (for example, created by `imagecreate`)
- */
- public function appendImage($img){
- $imgIndex = sizeof($this->images);
- $this->images[] = new FileRecord(new Record(ImageHandler::CreateImage($img)));
- $this->parts[] = array(self::IMAGE, $imgIndex);
- }
-}
\ No newline at end of file
+++ /dev/null
-<?php
-
-/**
- * Description of MultipleFileHandler
- *
- * @author Sander
- */
-abstract class MultipleFileHandler extends ContentProvider {
- /**
- * @var array
- */
- private $files = array();
- /**
- * @var array
- */
- private $images = array();
- /**
- * @var array
- */
- private $metadata = array();
-
- private $toc = array();
-
- /**
- * Add a page to the file
- * @param string $contents Contents of the chapter/page
- * @param string $title Optional, title of the chapter/page. Will automatically add a h2
- * before the contents
- */
- public function addPage($contents, $title = ""){
- if($title != ""){
- //TODO: Add in TOC (and add a way of generating it
- $contents = "<h2>".$title."</h2>".$contents."<mbp:pagebreak>";
- }
- $pos = 0;
-
- if(sizeof($this->toc) > 0){
- $lastToc = $this->toc[sizeof($this->toc)-1];
- $lastFile = $this->files[sizeof($this->files)-1];
- $pos = $lastToc["pos"] + strlen($lastFile) + 1;
- }
-
- $this->files[] = $contents;
- $this->toc[] = array("title"=>$title, "pos"=>$pos);
- }
-
- /**
- * Add an image to the file
- * @param string $imageContents Data string containing the binary data of the image
- * @return int The reference of the image
- */
- public function addImage($imageContents){
- $this->images[] = $imageContents;
- return sizeof($this->images)-1;
- }
-
- /**
- * Add an image to the file
- * @param string $url Url to the image
- * @return int The reference of the image, false if the image couldn't be downloaded
- */
- public function addImageFromUrl($url){
- $image = ImageHandler::DownloadImage($url);
-
- if($image === false) return false;
- return $this->addImage($image);
- }
-
- /**
- * Set the metadata
- * @param string $key Key
- * @param string $value Value
- */
- public function setMetadata($key, $value){
- $this->metadata[$key] = $value;
- }
-
- /**
- * Get the text data to be integrated in the MOBI file
- * @return string
- */
- public function getTextData(){
- $data = implode("\n", $this->files);
- $begin = "<html><head><guide><reference title='CONTENT' type='toc' filepos=0000000000 /></guide></head><body>";
- $beforeTOC = $begin.$data;
-
- $tocPos = strlen($beforeTOC);
-
- $toc = $this->generateTOC(strlen($begin));
-
- $customBegin = "<html><head><guide><reference title='CONTENT' type='toc' filepos=".$this->forceLength($tocPos, 10)." /></guide></head><body>";
- $data = $customBegin.$data.$toc."</body></html>";
- return $data;
- }
-
- public function forceLength($n, $l){
- $str = $n."";
- $cur = strlen($str);
- while($cur < $l){
- $str = "0".$str;
- $cur++;
- }
- return $str;
- }
-
- public function generateTOC($base = 0){
- $toc = "<h2>Contents</h2>";
- $toc .= "<blockquote><table summary='Table of Contents'><b><col/><col/><tbody>";
- for($i = 0, $len = sizeof($this->toc); $i < $len; $i++){
- $entry = $this->toc[$i];
- $position = $entry["pos"]+$base;
- $toc .= "<tr><td>".($i+1).".</td><td><a filepos=".$position.">".$entry["title"]."</a></td></tr>";
- }
- $toc .= "</tbody></b></table></blockquote>";
-
- return $toc;
- }
- /**
- * Get the images (an array containing the jpeg data). Array entry 0 will
- * correspond to image record 0.
- * @return array
- */
- public function getImages(){
- return $this->images;
- }
-
- /**
- * Get the metadata in the form of a hashtable (for example, title or author).
- * @return array
- */
- public function getMetaData(){
- return $this->metadata;
- }
-
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of OnlineArticle
- *
- * @author Sander
- */
-class OnlineArticle extends ContentProvider {
- private $text;
- private $images;
- private $metadata = array();
- private $imgCounter = 0;
-
- public function __construct($url) {
- if (!preg_match('!^https?://!i', $url)) $url = 'http://'.$url;
-
- $data = Http::Request($url);
- //$enc = mb_detect_encoding($str, "UTF-8,ISO-8859-1,ASCII");
- $html = mb_convert_encoding($data, "UTF-8", "UTF-8,ISO-8859-1,ASCII");
- //$html = utf8_encode($html);
- $r = new Readability($html, $url);
- $r->init();
- if(!isset($this->metadata["title"])){
- $this->metadata["title"] = CharacterEntities::convert(strip_tags($r->getTitle()->innerHTML));
- }
- if(!isset($this->metadata["author"])){
- $parts = parse_url($url);
- $this->metadata["author"] = $parts["host"];
- }
-
- $article = $r->getContent()->innerHTML;
- if(substr($article, 0, 5) == "<body"){
- $article = "<html><head><meta http-equiv='Content-Type' content='text/html; charset=UTF-8'/></head>".$article."</html>";
- }else{
- $article = "<html><head><meta http-equiv='Content-Type' content='text/html; charset=UTF-8'/></head><body>".$article."</body></html>";
- }
- $doc = new DOMDocument();
- @$doc->loadHTML($article) or die($article);
- $doc->normalizeDocument();
-
- $this->images = $this->handleImages($doc, $url);
- $this->text = $doc->saveHTML();
- }
-
- /**
- * Get the text data to be integrated in the MOBI file
- * @return string
- */
- public function getTextData(){
- return $this->text;
- }
- /**
- * Get the images (an array containing the jpeg data). Array entry 0 will
- * correspond to image record 0.
- * @return array
- */
- public function getImages(){
- return $this->images;
- }
- /**
- * Get the metadata in the form of a hashtable (for example, title or author).
- * @return array
- */
- public function getMetaData(){
- return $this->metadata;
- }
- /**
- *
- * @param DOMElement $dom
- * @return array
- */
- private function handleImages($dom, $url){
- $images = array();
-
- $parts = parse_url($url);
-
- $savedImages = array();
-
- $imgElements = $dom->getElementsByTagName('img');
- foreach($imgElements as $img) {
- $src = $img->getAttribute("src");
-
- $is_root = false;
- if(substr($src, 0, 1) == "/"){
- $is_root = true;
- }
-
- $parsed = parse_url($src);
-
- if(!isset($parsed["host"])){
- if($is_root){
- $src = http_build_url($url, $parsed, HTTP_URL_REPLACE);
- }else{
- $src = http_build_url($url, $parsed, HTTP_URL_JOIN_PATH);
- }
- }
- $img->setAttribute("src", "");
- if(isset($savedImages[$src])){
- $img->setAttribute("recindex", $savedImages[$src]);
- }else{
- $image = ImageHandler::DownloadImage($src);
-
- if($image !== false){
- $images[$this->imgCounter] = new FileRecord(new Record($image));
-
- $img->setAttribute("recindex", $this->imgCounter);
- $savedImages[$src] = $this->imgCounter;
- $this->imgCounter++;
- }
- }
- }
-
- return $images;
- }
-}
-?>
+++ /dev/null
-<?php
-/**
- * A Record of a PDB file
- *
- * @author Sander
- */
-class PalmRecord extends FileObject {
- /**
- * @var FileElement
- */
- private $elements;
-
- public function __construct($settings, $records, $textRecords, $textLength, $images){
- $this->elements = new FileElement(array(
- "compression"=>new FileShort(),
- "unused"=>new FileShort(),
- "textLength"=>new FileInt(),
- "recordCount"=>new FileShort(),
- "recordSize"=>new FileShort(),
- "encryptionType"=>new FileShort(),
- "unused2"=>new FileShort(),
- //MOBI Header
- "mobiIdentifier"=>new FileString("MOBI", 4),
- "mobiHeaderLength"=>new FileInt(),
- "mobiType"=>new FileInt(),
- "textEncoding"=>new FileInt(),
- "uniqueID"=>new FileInt(),
- "fileVersion"=>new FileInt(),
- "reserved"=>new FileString(40),
- "firstNonBookIndex"=>new FileInt(),
- "fullNameOffset"=>new FileInt(),
- "fullNameLength"=>new FileInt(),
- "locale"=>new FileInt(),
- "inputLanguage"=>new FileInt(),
- "outputLanguage"=>new FileInt(),
- "minimumVersion"=>new FileInt(),
- "firstImageIndex"=>new FileInt(),
- "huffmanRecordOffset"=>new FileInt(),
- "huffmanRecordCount"=>new FileInt(),
- "unused3"=>new FileString(8),
- "exthFlags"=>new FileInt(0x40),
- "unknown"=>new FileString(32),
- "drmOffset"=>new FileInt(0xFFFFFFFF),
- "drmCount"=>new FileShort(0xFFFFFFFF),
- "drmSize"=>new FileShort(),
- "drmFlags"=>new FileInt(),
- "mobiFiller"=>new FileString(72),
- //EXTH Header
- "exthIdentifier"=>new FileString("EXTH", 4),
- "exthHeaderLength"=>new FileInt(),
- "exthRecordCount"=>new FileInt(),
- "exthRecords"=>new FileElement(),
- "exthPadding"=>new FileString(),
- //"fullNamePadding"=>new FileString(100),
- "fullName"=>new FileString()
- ));
-
- //Set values from the info block
- foreach($settings->values as $name => $val){
- //echo $name.", ";
- if($this->elements->exists($name)){
- $this->elements->get($name)->set($settings->get($name));
- }
- }
-
- $els = $settings->values;
-
- $exthElems = new FileElement();
- $i = 0;
- $l = 0;
- foreach($els as $name=>$val){
- $type = EXTHHelper::textToType($name);
- if($type !== false){
- $type = new FileInt($type);
- $length = new FileInt(8+strlen($val));
- $data = new FileString($val);
- $l += 8+strlen($val);
- $exthElems->add("type".$i, $type);
- $exthElems->add("length".$i, $length);
- $exthElems->add("data".$i, $data);
- $i++;
- }
- }
-
- if($images > 0){
- $this->elements->get("firstImageIndex")->set($textRecords+1);
- }
- $this->elements->get("firstNonBookIndex")->set($textRecords+2+$images);
- $this->elements->get("reserved")->set(str_pad("", 40, chr(255), STR_PAD_RIGHT));
- $this->elements->get("exthRecordCount")->set($i);
- $this->elements->set("exthRecords", $exthElems);
- $pad = $l%4;
- $pad = (4-$pad)%4;
- $this->elements->get("exthPadding")->set(str_pad("", $pad, "\0", STR_PAD_RIGHT));
- $this->elements->get("exthHeaderLength")->set(12+$l+$pad);
-
-
- $this->elements->get("recordCount")->set($textRecords);
-
- $this->elements->get("fullNameOffset")->set($this->elements->offsetToEntry("fullName"));
- $this->elements->get("fullNameLength")->set(strlen($settings->get("title")));
- $this->elements->get("fullName")->set($settings->get("title"));
- $this->elements->get("textLength")->set($textLength);
- }
-
- public function getByteLength(){
- return $this->getLength();
- }
-
- public function getLength(){
- return $this->elements->getByteLength();
- }
-
- public function get(){
- return $this;
- }
-
- public function set($elements){
- throw new Exception("Unallowed set");
- }
-
- public function serialize() {
- return $this->elements->serialize();
- }
-
- public function unserialize($data) {
- $this->elements->unserialize($data);
- }
-
- public function __toString(){
- $output = "PalmDoc Record (".$this->getByteLength()." bytes):\n";
- $output .= $this->elements;
- return $output;
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of Prc
- *
- * @author Sander
- */
-class Prc extends FileElement {
- public function __construct($settings, $records){
- parent::__construct(array(
- "title"=>new FileString(32),
- "attributes"=>new FileShort(),
- "version"=>new FileShort(),
- "creationTime"=>new FileDate(),
- "modificationTime"=>new FileDate(),
- "backupTime"=>new FileDate(),
- "modificationNumber"=>new FileInt(),
- "appInfoID"=>new FileInt(),
- "sortInfoID"=>new FileInt(),
- "prcType"=>new FileString(4),
- "creator"=>new FileString(4),
- "uniqueIDSeed"=>new FileInt(),
- "nextRecordListID"=>new FileInt(),
- "numberRecords"=>new FileShort(),
- "recordList"=>new FileElement(),
- "filler"=>new FileShort(),
- "records"=>new FileElement()
- ));
-
- //Set values from the info block
- foreach($this->elements as $name => $val){
- if($settings->exists($name)){
- $this->get($name)->set($settings->get($name));
- }
- }
-
- $this->get("numberRecords")->set(sizeof($records));
-
- $i = 0;
- foreach($records as $record){
- $offset = new FileInt();
- $attr = new FileByte();
- $uniqueID = new FileTri($i);
-
- $this->elements["recordList"]->add("Rec".$i, new FileElement(array(
- "offset"=>$offset,
- "attribute"=>$attr,
- "uniqueID"=>$uniqueID
- )));
-
- $this->elements["records"]->add("Rec".$i, $record);
- $i++;
- }
-
- $this->updateOffsets($records);
- }
-
- public function getByteLength(){
- throw new Exception("Test");
- }
-
- public function updateOffsets($records){
- $base = $this->offsetToEntry("records");
-
- $i = 0;
-
- foreach($records as $record){
- $el = $this->elements["recordList"]->get("Rec".$i);
-
- $local = $this->elements["records"]->offsetToEntry("Rec".$i);
-
- $el->get("offset")->set($base+$local);
-
- $i++;
- }
- }
-
- public function save($file){
- $handle = fopen($file, "w");
- fwrite($handle, $this->serialize());
- fclose($handle);
- }
-
- public function output(){
- echo $this->serialize();
- }
-
- public function __toString(){
- $output = "Prc (".$this->getByteLength()." bytes): {\n";
- foreach($this->elements as $key=>$value){
- $output .= "\t".$key.": ".$value."\n";
- }
- $output .= "}";
- return $output;
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of OnlineArticle
- *
- * @author Sander
- */
-class PreprocessedArticle extends ContentProvider {
- private $text;
- private $images;
- private $metadata = array();
- private $imgCounter = 0;
-
- public function __construct($textData, $imageLinks, $metadata) {
- $this->text = $textData;
- $this->metadata = $metadata;
-
- $this->images = $this->downloadImages($imageLinks);
- }
-
- /**
- * Create a Preprocessed article from a json string
- * @param string $json JSON data. Should be of the following format:
- * {"text": "TEXT", "images: ["imageURL1", "imageURL2"], "metadata": {"key": "value"}}
- *
- * Note: Any image tags should have the recindex attribute set to the appropriate index (the
- * same index as the image in the array)
- * @return PreprocessedArticle The generated preprocessed array
- */
- static public function CreateFromJson($json){
- $data = json_decode($json);
- return new PreprocessedArticle($data["text"], $data["images"], $data["metadata"]);
- }
-
- /**
- * Get the text data to be integrated in the MOBI file
- * @return string
- */
- public function getTextData(){
- return $this->text;
- }
- /**
- * Get the images (an array containing the jpeg data). Array entry 0 will
- * correspond to image record 0.
- * @return array
- */
- public function getImages(){
- return $this->images;
- }
- /**
- * Get the metadata in the form of a hashtable (for example, title or author).
- * @return array
- */
- public function getMetaData(){
- return $this->metadata;
- }
- /**
- *
- * @param DOMElement $dom
- * @return array
- */
- private function downloadImages($links){
- $images = array();
- foreach($links as $link) {
- $imgFile = @imagecreatefromstring(Http::Request($link));
-
- if($imgFile === false){
- $imgFile = @imagecreate(1, 1);
- $black = @imagecolorallocate($imgFile, 255, 255, 255);
- }
- if($imgFile !== false){
- @imagefilter($imgFile, IMG_FILTER_GRAYSCALE);
-
- ob_start();
- @imagejpeg($imgFile);
- $image = ob_get_contents();
- ob_end_clean();
-
- $images[$this->imgCounter] = new FileRecord(new Record($image));
- imagedestroy($imgFile);
-
- $this->imgCounter++;
- }
- }
-
- return $images;
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of RecognizeURL
- *
- * @author Sander
- */
-class RecognizeURL {
- public static function GetContentHandler($url){
- if(FanFictionNet::Matches($url)){
- return new FanFictionNet($url);
- }
- return null;
- }
-}
-?>
+++ /dev/null
-<?php
-/**
- * A Record of a PDB file
- *
- * @author Sander
- */
-class Record extends FileObject {
- /**
- * Data in the record
- * @var string
- */
- private $data;
- /**
- * Length of the record
- * @var int
- */
- private $length;
-
- /**
- * Create a record
- * @param string $data Data contained in the record
- * @param int $length Length of the record (if set to -1,
- * the length of $data will be taken)
- */
- public function __construct($data = "", $length = -1){
- $this->data = $data;
- if($length >= 0){
- $this->length = $length;
- }else{
- $this->length = strlen($data);
- }
- }
-
- public function compress($compression_method){
- switch($compression_method){
- case NO_COMPRESSION:
- //Finished!
- break;
- case PALMDOC_COMPRESSION:
- throw new Exception("Not implemented yet");
- break;
- case HUFF:
- throw new Exception("Not implemented yet");
- break;
- default:
- throw new Exception("Invalid argument");
- }
- }
-
- public function getByteLength(){
- return $this->getLength();
- }
-
- /**
- * Get the length of the record
- * @return int Length of the data
- */
- public function getLength(){
- return $this->length;
- }
-
- /**
- * Get the data contained in the record
- * @return string Data contained in the record
- */
- public function get(){
- return $this->data;
- }
-
- /**
- * Set the data contained in the record
- * @param string $value Data contained in the record
- */
- public function set($value){
- $this->data = $value;
- }
-
- public function serialize(){
- return $this->data;
- }
- public function unserialize($data){
- __construct($data);
- }
-
- public function __toString() {
- $toShow = $this->data;
- if(strlen($this->data) > 103){
- $toShow = substr($this->data, 0, 100)."...";
- }
- $out = "Record: {\n";
- $out .= "\t".htmlspecialchars($toShow)."\n";
- $out .= "}";
- return $out;
- }
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Helper class to help with creating records from a
- * long data stream
- *
- * @author Sander
- */
-class RecordFactory {
- /**
- * Settings for the record factory
- * @var Settings
- */
- private $settings;
-
- /**
- * Create the helper class
- * @param Settings $settings The Settings to be used for the records
- */
- public function __construct($settings){
- $this->settings = $settings;
- }
-
- /**
- * Create records from a data string
- * @param string $data
- * @return array(Record)
- */
- public function createRecords($data){
- $records = array();
- $size = $this->settings->get("recordSize");
- $compression = $this->settings->get("compression");
-
- $dataEntries = mb_str_split($data, $size);
-
- for($i = 0, $len = sizeof($dataEntries); $i < $len; $i++){
- $records[$i] = new Record($dataEntries[$i]);
- $records[$i]->compress($compression);
- }
-
- return $records;
- }
-
- public function createEOFRecord(){
- return new Record(0xe98e0d0a);
- }
-
- public function createFCISRecord($textLength){
- $r = "FCIS";
- $r .= $this->asString(20, 4);
- $r .= $this->asString(16, 4);
- $r .= $this->asString(1, 4);
- $r .= $this->asString(0, 4);
- $r .= $this->asString($textLength, 4);
- $r .= $this->asString(0, 4);
- $r .= $this->asString(32, 4);
- $r .= $this->asString(8, 4);
- $r .= $this->asString(1, 2);
- $r .= $this->asString(1, 2);
- $r .= $this->asString(0, 4);
- return new Record($r);
- }
-
- public function createFLISRecord(){
- $r = "FLIS";
- $r .= $this->asString(8, 4);
- $r .= $this->asString(65, 2);
- $r .= $this->asString(0, 2);
- $r .= $this->asString(0, 4);
- $r .= $this->asString(-1, 4);
- $r .= $this->asString(1, 2);
- $r .= $this->asString(3, 2);
- $r .= $this->asString(3, 4);
- $r .= $this->asString(1, 4);
- $r .= $this->asString(-1, 4);
- return new Record($r);
- }
-
- private function asString($int, $size){
- $out = "";
- for($i = 0; $i < $size; $i++){
- if($i > 0) $out = " ".$out;
- $byte = dechex($int & 0xFF);
- if(strlen($byte) == 1) $byte = "0".$byte;
- $out = $byte.$out;
- $int = $int >> 8;
- }
- return $out;
- }
-
- public function __toString() {
- $out = "Record Factory: {\n";
- $out .= "\tRecord Size: ".$this->settings->get("recordSize")."\n";
- $out .= "\tCompression: ".$this->settings->get("compression")."\n";
- $out .= "}";
- return $out;
- }
-}
-function mb_str_split($string, $split_length = 1){
- mb_internal_encoding('UTF-8');
- mb_regex_encoding('UTF-8');
-
- $split_length = ($split_length <= 0) ? 1 : $split_length;
-
- $mb_strlen = mb_strlen($string, 'utf-8');
-
- $array = array();
-
- for($i = 0; $i < $mb_strlen; $i += $split_length){
- $array[] = mb_substr($string, $i, $split_length);
- }
-
- return $array;
-}
-?>
+++ /dev/null
-<?php
-
-/**
- * Description of Settings
- *
- * @author Sander
- */
-class Settings {
- /**
- * Values of the settings
- * @var array
- */
- public $values;
-
- /**
- * Construct a Settings object with the default settings. If necessary,
- * those settings can be extended with additional settings
- * @param array $additionalSettings Additional settings to add (should
- * be added with a key/value pair format.
- */
- public function __construct($additionalSettings = array()) {
- // Most values shouldn't be changed (the result will be an invalid file)
- $this->values = array(
- "attributes"=>0,
- "version"=>0,
- "creationTime"=>time()+94694400,
- "modificationTime"=>time()+94694400,
- "backupTime"=>0,
- "modificationNumber"=>0,
- "appInfoID"=>0,
- "sortInfoID"=>0,
- "prcType"=>"BOOK",
- "creator"=>"MOBI",
- "uniqueIDSeed"=>rand(),
- "nextRecordListID"=>0,
- "recordAttributes"=>0,
- "compression"=>NO_COMPRESSION,
- "recordSize"=>RECORD_SIZE,
- "encryptionType"=>NO_ENCRYPTION,
- "mobiIdentifier"=>"MOBI",
- "mobiHeaderLength"=>0xe8,
- "mobiType"=>MOBIPOCKET_BOOK,
- "textEncoding"=>UTF8,
- "uniqueID"=>rand(),
- "fileVersion"=>6,
- "locale"=>0x09,
- "inputLanguage"=>0,
- "outputLanguage"=>0,
- "minimumVersion"=>6,
- "huffmanRecordOffset"=>0,
- "huffmanRecordCount"=>0,
- "exthFlags"=>0x40,
- "drmOffset"=>0xFFFFFFFF,
- "drmCount"=>0,
- "drmSize"=>0,
- "drmFlags"=>0,
- "extraDataFlags"=>0,
- "exthIdentifier"=>"EXTH",
- // These can be changed without any risk
- "title"=>"Unknown title",
- "author"=>"Unknown author",
- "subject"=>"Unknown subject"
- );
-
- foreach($additionalSettings as $key=>$value){
- $this->values[$key] = $value;
- }
- }
-
- /**
- * Get a value from the settings
- * @param string $key Key of the setting
- * @return mixed The value of the setting
- */
- public function get($key){
- return $this->values[$key];
- }
-
- /**
- * Checks if a value is set
- * @param string $key Key of the setting
- * @return bool True if the value exists
- */
- public function exists($key){
- return isset($this->values[$key]);
- }
-
- public function __toString() {
- $out = "Settings: {\n";
- foreach($this->values as $key=>$value){
- $out .= "\t".$key.": ".$value."\n";
- }
- $out .= "}";
- return $out;
- }
-}
-?>
+++ /dev/null
-<?php
-define("NO_COMPRESSION", 1);
-define("PALMDOC_COMPRESSION", 2);
-define("HUFF", 17480);
-define("RECORD_SIZE", 4096);
-
-define("NO_ENCRYPTION", 0);
-
-define("MOBIPOCKET_BOOK", 2);
-define("CP1252", 1252);
-define("UTF8", 65001);
\ No newline at end of file
+++ /dev/null
-<?php
-
-/**
- * Description of FanFictionNet
- *
- * @author Sander
- */
-class FanFictionNet extends MultipleFileHandler {
- private static $prefix = "http://www.fanfiction.net/s/";
- private $downloadedMetadata = false;
- private $id = 0;
- private $chapterCount = -1;
-
- public function __construct($url) {
- $ending = substr($url, strlen(self::$prefix));
- $this->id = intval(substr($ending, 0, strpos($ending, "/")));
-
- for($i = 1; $i <= max(1, $this->chapterCount); $i++){
- $this->addChapter($i);
- }
- }
-
- private function addChapter($n){
- $doc = new DOMDocument();
- $file = Http::Request(self::$prefix.$this->id."/".$n."/");
- @$doc->loadHTML($file) or die($file);
-
- if(!$this->downloadedMetadata){
- $this->loadMetadata($doc);
- $this->downloadedMetadata = true;
- }
- if($this->chapterCount < 0){
- $this->chapterCount = $this->getNumberChapters($doc);
-
- if($this->chapterCount > 4){
- die("Too many files to download, don't use php for this!");
- }
- }
-
- $textEl = $doc->getElementById("storytext");
- if($textEl == null) die("Error: ".$doc->saveHTML());
- $horizontalRulebars = $doc->getElementsByTagName('hr');
- /**
- * @var DOMNode
- */
- $hr;
- foreach($horizontalRulebars as $hr) {
- $hr->setAttribute("size", null);
- $hr->setAttribute("noshade", null);
- }
- $text = $this->innerHtml($textEl);
-
- $title = "";
- $selects = $doc->getElementsByTagName('select');
- foreach($selects as $select) {
- if($select->hasAttribute("name") && $select->getAttribute("name") == "chapter"){
- $options = $select->getElementsByTagName("option");
-
- $test = $n.". ";
- foreach($options as $option){
- $val = $option->nodeValue;
- if(substr($val, 0, strlen($test)) == $test){
- $title = substr($val, strlen($test));
- break;
- }
- }
- break;
- }
- }
- $this->addPage($text, $title);
- }
-
- private function getNumberChapters($doc){
- $selects = $doc->getElementsByTagName('select');
- foreach($selects as $select) {
- if($select->hasAttribute("name") && $select->getAttribute("name") == "chapter"){
- $options = $select->getElementsByTagName("option");
-
- $count = $options->length;
- return $count;
- }
- }
- }
-
- private function loadMetadata($doc){
- //Author
- $links = $doc->getElementsByTagName('a');
- foreach($links as $link) {
- if($link == null){
- var_dump($link);
- }
- if($link->hasAttribute("href") && substr($link->getAttribute("href"), 0, 3) == "/u/"){
- $this->setMetadata("author", $link->nodeValue);
- }
- }
- //Title
- /*
- $links = $doc->getElementsByTagName('link');
- foreach($links as $link) {
- if($link->hasAttribute("rel") && $link->getAttribute("rel") == "canonical"){
- $url = $link->getAttribute("href");
- $title = str_replace("_", " ", substr($url, strrpos($url, "/")+1));
- $this->setMetadata("title", $title);
- }
- }*/
-
- //TODO: Find a more reliable way to extract the title
- $title = $doc->getElementsByTagName("b")->item(0)->nodeValue;
- $this->setMetadata("title", $title);
- }
-
- private function innerHtml($node){
- $doc = new DOMDocument();
- foreach ($node->childNodes as $child)
- $doc->appendChild($doc->importNode($child, true));
-
- return $doc->saveHTML();
- }
-
- public static function Matches($url){
- //TODO: Implement with regex
- return strpos($url, self::$prefix) !== false;
- }
-}
-?>
+++ /dev/null
-<?php
-if(!is_callable("http_build_url")){
- define('HTTP_URL_REPLACE', 1); // Replace every part of the first URL when there's one of the second URL
- define('HTTP_URL_JOIN_PATH', 2); // Join relative paths
- define('HTTP_URL_JOIN_QUERY', 4); // Join query strings
- define('HTTP_URL_STRIP_USER', 8); // Strip any user authentication information
- define('HTTP_URL_STRIP_PASS', 16); // Strip any password authentication information
- define('HTTP_URL_STRIP_AUTH', 32); // Strip any authentication information
- define('HTTP_URL_STRIP_PORT', 64); // Strip explicit port numbers
- define('HTTP_URL_STRIP_PATH', 128); // Strip complete path
- define('HTTP_URL_STRIP_QUERY', 256); // Strip query string
- define('HTTP_URL_STRIP_FRAGMENT', 512); // Strip any fragments (#identifier)
- define('HTTP_URL_STRIP_ALL', 1024); // Strip anything but scheme and host
-
- // Build an URL
- // The parts of the second URL will be merged into the first according to the flags argument.
- //
- // @param mixed (Part(s) of) an URL in form of a string or associative array like parse_url() returns
- // @param mixed Same as the first argument
- // @param int A bitmask of binary or'ed HTTP_URL constants (Optional)HTTP_URL_REPLACE is the default
- // @param array If set, it will be filled with the parts of the composed url like parse_url() would return
- function http_build_url($url, $parts = array (), $flags = HTTP_URL_REPLACE, &$new_url = false) {
- $keys = array (
- 'user',
- 'pass',
- 'port',
- 'path',
- 'query',
- 'fragment'
- );
-
- // HTTP_URL_STRIP_ALL becomes all the HTTP_URL_STRIP_Xs
- if ($flags & HTTP_URL_STRIP_ALL) {
- $flags |= HTTP_URL_STRIP_USER;
- $flags |= HTTP_URL_STRIP_PASS;
- $flags |= HTTP_URL_STRIP_PORT;
- $flags |= HTTP_URL_STRIP_PATH;
- $flags |= HTTP_URL_STRIP_QUERY;
- $flags |= HTTP_URL_STRIP_FRAGMENT;
- }
- // HTTP_URL_STRIP_AUTH becomes HTTP_URL_STRIP_USER and HTTP_URL_STRIP_PASS
- else if ($flags & HTTP_URL_STRIP_AUTH) {
- $flags |= HTTP_URL_STRIP_USER;
- $flags |= HTTP_URL_STRIP_PASS;
- }
-
- // Parse the original URL
- $parse_url = parse_url($url);
-
- // Scheme and Host are always replaced
- if (isset($parts['scheme']))
- $parse_url['scheme'] = $parts['scheme'];
-
- if (isset($parts['host']))
- $parse_url['host'] = $parts['host'];
-
- // (If applicable) Replace the original URL with it's new parts
- if ($flags & HTTP_URL_REPLACE) {
- foreach ($keys as $key) {
- if (isset($parts[$key]))
- $parse_url[$key] = $parts[$key];
- }
- } else {
- // Join the original URL path with the new path
- if (isset($parts['path']) && ($flags & HTTP_URL_JOIN_PATH)) {
- if (isset($parse_url['path']))
- $parse_url['path'] = rtrim(str_replace(basename($parse_url['path']), '', $parse_url['path']), '/') . '/' . ltrim($parts['path'], '/');
- else
- $parse_url['path'] = $parts['path'];
- }
-
- // Join the original query string with the new query string
- if (isset($parts['query']) && ($flags & HTTP_URL_JOIN_QUERY)) {
- if (isset($parse_url['query']))
- $parse_url['query'] .= '&' . $parts['query'];
- else
- $parse_url['query'] = $parts['query'];
- }
- }
-
- // Strips all the applicable sections of the URL
- // Note: Scheme and Host are never stripped
- foreach ($keys as $key) {
- if ($flags & (int)constant('HTTP_URL_STRIP_' . strtoupper($key)))
- unset($parse_url[$key]);
- }
-
- $new_url = $parse_url;
-
- return ((isset($parse_url['scheme'])) ? $parse_url['scheme'] . '://' : '') . ((isset($parse_url['user'])) ? $parse_url['user'] . ((isset($parse_url['pass'])) ? ':' . $parse_url['pass'] : '') . '@' : '')
- . ((isset($parse_url['host'])) ? $parse_url['host'] : '') . ((isset($parse_url['port'])) ? ':' . $parse_url['port'] : '') . ((isset($parse_url['path'])) ? $parse_url['path'] : '')
- . ((isset($parse_url['query'])) ? '?' . $parse_url['query'] : '') . ((isset($parse_url['fragment'])) ? '#' . $parse_url['fragment'] : '');
- }
-}
+++ /dev/null
-<?php\r
-/**\r
-* JavaScript-like HTML DOM Element\r
-*\r
-* This class extends PHP's DOMElement to allow\r
-* users to get and set the innerHTML property of\r
-* HTML elements in the same way it's done in \r
-* JavaScript.\r
-*\r
-* Example usage:\r
-* @code\r
-* require_once 'JSLikeHTMLElement.php';\r
-* header('Content-Type: text/plain');\r
-* $doc = new DOMDocument();\r
-* $doc->registerNodeClass('DOMElement', 'JSLikeHTMLElement');\r
-* $doc->loadHTML('<div><p>Para 1</p><p>Para 2</p></div>');\r
-* $elem = $doc->getElementsByTagName('div')->item(0);\r
-* \r
-* // print innerHTML\r
-* echo $elem->innerHTML; // prints '<p>Para 1</p><p>Para 2</p>'\r
-* echo "\n\n";\r
-* \r
-* // set innerHTML\r
-* $elem->innerHTML = '<a href="http://fivefilters.org">FiveFilters.org</a>';\r
-* echo $elem->innerHTML; // prints '<a href="http://fivefilters.org">FiveFilters.org</a>'\r
-* echo "\n\n";\r
-* \r
-* // print document (with our changes)\r
-* echo $doc->saveXML();\r
-* @endcode\r
-*\r
-* @author Keyvan Minoukadeh - http://www.keyvan.net - keyvan@keyvan.net\r
-* @see http://fivefilters.org (the project this was written for)\r
-*/\r
-class JSLikeHTMLElement extends DOMElement\r
-{\r
- /**\r
- * Used for setting innerHTML like it's done in JavaScript:\r
- * @code\r
- * $div->innerHTML = '<h2>Chapter 2</h2><p>The story begins...</p>';\r
- * @endcode\r
- */\r
- public function __set($name, $value) {\r
- if ($name == 'innerHTML') {\r
- // first, empty the element\r
- for ($x=$this->childNodes->length-1; $x>=0; $x--) {\r
- $this->removeChild($this->childNodes->item($x));\r
- }\r
- // $value holds our new inner HTML\r
- if ($value != '') {\r
- $f = $this->ownerDocument->createDocumentFragment();\r
- // appendXML() expects well-formed markup (XHTML)\r
- $result = @$f->appendXML($value); // @ to suppress PHP warnings\r
- if ($result) {\r
- if ($f->hasChildNodes()) $this->appendChild($f);\r
- } else {\r
- // $value is probably ill-formed\r
- $f = new DOMDocument();\r
- $value = mb_convert_encoding($value, 'HTML-ENTITIES', 'UTF-8');\r
- // Using <htmlfragment> will generate a warning, but so will bad HTML\r
- // (and by this point, bad HTML is what we've got).\r
- // We use it (and suppress the warning) because an HTML fragment will \r
- // be wrapped around <html><body> tags which we don't really want to keep.\r
- // Note: despite the warning, if loadHTML succeeds it will return true.\r
- $result = @$f->loadHTML('<htmlfragment>'.$value.'</htmlfragment>');\r
- if ($result) {\r
- $import = $f->getElementsByTagName('htmlfragment')->item(0);\r
- foreach ($import->childNodes as $child) {\r
- $importedNode = $this->ownerDocument->importNode($child, true);\r
- $this->appendChild($importedNode);\r
- }\r
- } else {\r
- // oh well, we tried, we really did. :(\r
- // this element is now empty\r
- }\r
- }\r
- }\r
- } else {\r
- $trace = debug_backtrace();\r
- trigger_error('Undefined property via __set(): '.$name.' in '.$trace[0]['file'].' on line '.$trace[0]['line'], E_USER_NOTICE);\r
- }\r
- }\r
-\r
- /**\r
- * Used for getting innerHTML like it's done in JavaScript:\r
- * @code\r
- * $string = $div->innerHTML;\r
- * @endcode\r
- */ \r
- public function __get($name)\r
- {\r
- if ($name == 'innerHTML') {\r
- $inner = '';\r
- foreach ($this->childNodes as $child) {\r
- $inner .= $this->ownerDocument->saveXML($child);\r
- }\r
- return $inner;\r
- }\r
-\r
- $trace = debug_backtrace();\r
- trigger_error('Undefined property via __get(): '.$name.' in '.$trace[0]['file'].' on line '.$trace[0]['line'], E_USER_NOTICE);\r
- return null;\r
- }\r
-\r
- public function __toString()\r
- {\r
- return '['.$this->tagName.']';\r
- }\r
-}\r
-?>
\ No newline at end of file
+++ /dev/null
-<?php
-/**
-* Arc90's Readability ported to PHP for FiveFilters.org
-* Based on readability.js version 1.7.1 (without multi-page support)
-* Updated to allow HTML5 parsing with html5lib
-* Updated with lightClean mode to preserve more images and youtube/vimeo/viddler embeds
-* ------------------------------------------------------
-* Original URL: http://lab.arc90.com/experiments/readability/js/readability.js
-* Arc90's project URL: http://lab.arc90.com/experiments/readability/
-* JS Source: http://code.google.com/p/arc90labs-readability
-* Ported by: Keyvan Minoukadeh, http://www.keyvan.net
-* More information: http://fivefilters.org/content-only/
-* License: Apache License, Version 2.0
-* Requires: PHP5
-* Date: 2012-09-19
-*
-* Differences between the PHP port and the original
-* ------------------------------------------------------
-* Arc90's Readability is designed to run in the browser. It works on the DOM
-* tree (the parsed HTML) after the page's CSS styles have been applied and
-* Javascript code executed. This PHP port does not run inside a browser.
-* We use PHP's ability to parse HTML to build our DOM tree, but we cannot
-* rely on CSS or Javascript support. As such, the results will not always
-* match Arc90's Readability. (For example, if a web page contains CSS style
-* rules or Javascript code which hide certain HTML elements from display,
-* Arc90's Readability will dismiss those from consideration but our PHP port,
-* unable to understand CSS or Javascript, will not know any better.)
-*
-* Another significant difference is that the aim of Arc90's Readability is
-* to re-present the main content block of a given web page so users can
-* read it more easily in their browsers. Correct identification, clean up,
-* and separation of the content block is only a part of this process.
-* This PHP port is only concerned with this part, it does not include code
-* that relates to presentation in the browser - Arc90 already do
-* that extremely well, and for PDF output there's FiveFilters.org's
-* PDF Newspaper: http://fivefilters.org/pdf-newspaper/.
-*
-* Finally, this class contains methods that might be useful for developers
-* working on HTML document fragments. So without deviating too much from
-* the original code (which I don't want to do because it makes debugging
-* and updating more difficult), I've tried to make it a little more
-* developer friendly. You should be able to use the methods here on
-* existing DOMElement objects without passing an entire HTML document to
-* be parsed.
-*/
-
-// This class allows us to do JavaScript like assignements to innerHTML
-require_once(dirname(__FILE__).'/JSLikeHTMLElement.php');
-libxml_use_internal_errors(true);
-
-// Alternative usage (for testing only!)
-// uncomment the lines below and call Readability.php in your browser
-// passing it the URL of the page you'd like content from, e.g.:
-// Readability.php?url=http://medialens.org/alerts/09/090615_the_guardian_climate.php
-
-/*
-if (!isset($_GET['url']) || $_GET['url'] == '') {
- die('Please pass a URL to the script. E.g. Readability.php?url=bla.com/story.html');
-}
-$url = $_GET['url'];
-if (!preg_match('!^https?://!i', $url)) $url = 'http://'.$url;
-$html = file_get_contents($url);
-$r = new Readability($html, $url);
-$r->init();
-echo $r->articleContent->innerHTML;
-*/
-
-class Readability
-{
- public $version = '1.7.1-without-multi-page';
- public $convertLinksToFootnotes = false;
- public $revertForcedParagraphElements = true;
- public $articleTitle;
- public $articleContent;
- public $dom;
- public $url = null; // optional - URL where HTML was retrieved
- public $debug = false;
- public $lightClean = true; // preserves more content (experimental) added 2012-09-19
- protected $body = null; //
- protected $bodyCache = null; // Cache the body HTML in case we need to re-use it later
- protected $flags = 7; // 1 | 2 | 4; // Start with all flags set.
- protected $success = false; // indicates whether we were able to extract or not
-
- /**
- * All of the regular expressions in use within readability.
- * Defined up here so we don't instantiate them repeatedly in loops.
- **/
- public $regexps = array(
- 'unlikelyCandidates' => '/combx|comment|community|disqus|extra|foot|header|menu|remark|rss|shoutbox|sidebar|sponsor|ad-break|agegate|pagination|pager|popup/i',
- 'okMaybeItsACandidate' => '/and|article|body|column|main|shadow/i',
- 'positive' => '/article|body|content|entry|hentry|main|page|attachment|pagination|post|text|blog|story/i',
- 'negative' => '/combx|comment|com-|contact|foot|footer|_nav|footnote|masthead|media|meta|outbrain|promo|related|scroll|shoutbox|sidebar|sponsor|shopping|tags|tool|widget/i',
- 'divToPElements' => '/<(a|blockquote|dl|div|img|ol|p|pre|table|ul)/i',
- 'replaceBrs' => '/(<br[^>]*>[ \n\r\t]*){2,}/i',
- 'replaceFonts' => '/<(\/?)font[^>]*>/i',
- // 'trimRe' => '/^\s+|\s+$/g', // PHP has trim()
- 'normalize' => '/\s{2,}/',
- 'killBreaks' => '/(<br\s*\/?>(\s| ?)*){1,}/',
- 'video' => '!//(player\.|www\.)?(youtube|vimeo|viddler)\.com!i',
- 'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i'
- );
-
- /* constants */
- const FLAG_STRIP_UNLIKELYS = 1;
- const FLAG_WEIGHT_CLASSES = 2;
- const FLAG_CLEAN_CONDITIONALLY = 4;
-
- /**
- * Create instance of Readability
- * @param string UTF-8 encoded string
- * @param string (optional) URL associated with HTML (used for footnotes)
- * @param string which parser to use for turning raw HTML into a DOMDocument (either 'libxml' or 'html5lib')
- */
- function __construct($html, $url=null, $parser='libxml')
- {
- $this->url = $url;
- /* Turn all double br's into p's */
- $html = preg_replace($this->regexps['replaceBrs'], '</p><p>', $html);
- $html = preg_replace($this->regexps['replaceFonts'], '<$1span>', $html);
- $html = mb_convert_encoding($html, 'HTML-ENTITIES', "UTF-8");
- if (trim($html) == '') $html = '<html></html>';
- if ($parser=='html5lib' && ($this->dom = HTML5_Parser::parse($html))) {
- // all good
- } else {
- $this->dom = new DOMDocument();
- $this->dom->preserveWhiteSpace = false;
- @$this->dom->loadHTML($html);
- }
- $this->dom->registerNodeClass('DOMElement', 'JSLikeHTMLElement');
- }
-
- /**
- * Get article title element
- * @return DOMElement
- */
- public function getTitle() {
- return $this->articleTitle;
- }
-
- /**
- * Get article content element
- * @return DOMElement
- */
- public function getContent() {
- return $this->articleContent;
- }
-
- /**
- * Runs readability.
- *
- * Workflow:
- * 1. Prep the document by removing script tags, css, etc.
- * 2. Build readability's DOM tree.
- * 3. Grab the article content from the current dom tree.
- * 4. Replace the current DOM tree with the new one.
- * 5. Read peacefully.
- *
- * @return boolean true if we found content, false otherwise
- **/
- public function init()
- {
- if (!isset($this->dom->documentElement)) return false;
- $this->removeScripts($this->dom);
- //die($this->getInnerHTML($this->dom->documentElement));
-
- // Assume successful outcome
- $this->success = true;
-
- $bodyElems = $this->dom->getElementsByTagName('body');
- if ($bodyElems->length > 0) {
- if ($this->bodyCache == null) {
- $this->bodyCache = $bodyElems->item(0)->innerHTML;
- }
- if ($this->body == null) {
- $this->body = $bodyElems->item(0);
- }
- }
-
- $this->prepDocument();
-
- //die($this->dom->documentElement->parentNode->nodeType);
- //$this->setInnerHTML($this->dom->documentElement, $this->getInnerHTML($this->dom->documentElement));
- //die($this->getInnerHTML($this->dom->documentElement));
-
- /* Build readability's DOM tree */
- $overlay = $this->dom->createElement('div');
- $innerDiv = $this->dom->createElement('div');
- $articleTitle = $this->getArticleTitle();
- $articleContent = $this->grabArticle();
-
- if (!$articleContent) {
- $this->success = false;
- $articleContent = $this->dom->createElement('div');
- $articleContent->setAttribute('id', 'readability-content');
- $articleContent->innerHTML = '<p>Sorry, Readability was unable to parse this page for content.</p>';
- }
-
- $overlay->setAttribute('id', 'readOverlay');
- $innerDiv->setAttribute('id', 'readInner');
-
- /* Glue the structure of our document together. */
- $innerDiv->appendChild($articleTitle);
- $innerDiv->appendChild($articleContent);
- $overlay->appendChild($innerDiv);
-
- /* Clear the old HTML, insert the new content. */
- $this->body->innerHTML = '';
- $this->body->appendChild($overlay);
- //document.body.insertBefore(overlay, document.body.firstChild);
- $this->body->removeAttribute('style');
-
- $this->postProcessContent($articleContent);
-
- // Set title and content instance variables
- $this->articleTitle = $articleTitle;
- $this->articleContent = $articleContent;
-
- return $this->success;
- }
-
- /**
- * Debug
- */
- protected function dbg($msg) {
- if ($this->debug) echo '* ',$msg, "\n";
- }
-
- /**
- * Run any post-process modifications to article content as necessary.
- *
- * @param DOMElement
- * @return void
- */
- public function postProcessContent($articleContent) {
- if ($this->convertLinksToFootnotes && !preg_match('/wikipedia\.org/', @$this->url)) {
- $this->addFootnotes($articleContent);
- }
- }
-
- /**
- * Get the article title as an H1.
- *
- * @return DOMElement
- */
- protected function getArticleTitle() {
- $curTitle = '';
- $origTitle = '';
-
- try {
- $curTitle = $origTitle = $this->getInnerText($this->dom->getElementsByTagName('title')->item(0));
- } catch(Exception $e) {}
-
- if (preg_match('/ [\|\-] /', $curTitle))
- {
- $curTitle = preg_replace('/(.*)[\|\-] .*/i', '$1', $origTitle);
-
- if (count(explode(' ', $curTitle)) < 3) {
- $curTitle = preg_replace('/[^\|\-]*[\|\-](.*)/i', '$1', $origTitle);
- }
- }
- else if (strpos($curTitle, ': ') !== false)
- {
- $curTitle = preg_replace('/.*:(.*)/i', '$1', $origTitle);
-
- if (count(explode(' ', $curTitle)) < 3) {
- $curTitle = preg_replace('/[^:]*[:](.*)/i','$1', $origTitle);
- }
- }
- else if(strlen($curTitle) > 150 || strlen($curTitle) < 15)
- {
- $hOnes = $this->dom->getElementsByTagName('h1');
- if($hOnes->length == 1)
- {
- $curTitle = $this->getInnerText($hOnes->item(0));
- }
- }
-
- $curTitle = trim($curTitle);
-
- if (count(explode(' ', $curTitle)) <= 4) {
- $curTitle = $origTitle;
- }
-
- $articleTitle = $this->dom->createElement('h1');
- $articleTitle->innerHTML = $curTitle;
-
- return $articleTitle;
- }
-
- /**
- * Prepare the HTML document for readability to scrape it.
- * This includes things like stripping javascript, CSS, and handling terrible markup.
- *
- * @return void
- **/
- protected function prepDocument() {
- /**
- * In some cases a body element can't be found (if the HTML is totally hosed for example)
- * so we create a new body node and append it to the document.
- */
- if ($this->body == null)
- {
- $this->body = $this->dom->createElement('body');
- $this->dom->documentElement->appendChild($this->body);
- }
- $this->body->setAttribute('id', 'readabilityBody');
-
- /* Remove all style tags in head */
- $styleTags = $this->dom->getElementsByTagName('style');
- for ($i = $styleTags->length-1; $i >= 0; $i--)
- {
- $styleTags->item($i)->parentNode->removeChild($styleTags->item($i));
- }
-
- /* Turn all double br's into p's */
- /* Note, this is pretty costly as far as processing goes. Maybe optimize later. */
- //document.body.innerHTML = document.body.innerHTML.replace(readability.regexps.replaceBrs, '</p><p>').replace(readability.regexps.replaceFonts, '<$1span>');
- // We do this in the constructor for PHP as that's when we have raw HTML - before parsing it into a DOM tree.
- // Manipulating innerHTML as it's done in JS is not possible in PHP.
- }
-
- /**
- * For easier reading, convert this document to have footnotes at the bottom rather than inline links.
- * @see http://www.roughtype.com/archives/2010/05/experiments_in.php
- *
- * @return void
- **/
- public function addFootnotes($articleContent) {
- $footnotesWrapper = $this->dom->createElement('div');
- $footnotesWrapper->setAttribute('id', 'readability-footnotes');
- $footnotesWrapper->innerHTML = '<h3>References</h3>';
-
- $articleFootnotes = $this->dom->createElement('ol');
- $articleFootnotes->setAttribute('id', 'readability-footnotes-list');
- $footnotesWrapper->appendChild($articleFootnotes);
-
- $articleLinks = $articleContent->getElementsByTagName('a');
-
- $linkCount = 0;
- for ($i = 0; $i < $articleLinks->length; $i++)
- {
- $articleLink = $articleLinks->item($i);
- $footnoteLink = $articleLink->cloneNode(true);
- $refLink = $this->dom->createElement('a');
- $footnote = $this->dom->createElement('li');
- $linkDomain = @parse_url($footnoteLink->getAttribute('href'), PHP_URL_HOST);
- if (!$linkDomain && isset($this->url)) $linkDomain = @parse_url($this->url, PHP_URL_HOST);
- //linkDomain = footnoteLink.host ? footnoteLink.host : document.location.host,
- $linkText = $this->getInnerText($articleLink);
-
- if ((strpos($articleLink->getAttribute('class'), 'readability-DoNotFootnote') !== false) || preg_match($this->regexps['skipFootnoteLink'], $linkText)) {
- continue;
- }
-
- $linkCount++;
-
- /** Add a superscript reference after the article link */
- $refLink->setAttribute('href', '#readabilityFootnoteLink-' . $linkCount);
- $refLink->innerHTML = '<small><sup>[' . $linkCount . ']</sup></small>';
- $refLink->setAttribute('class', 'readability-DoNotFootnote');
- $refLink->setAttribute('style', 'color: inherit;');
-
- //TODO: does this work or should we use DOMNode.isSameNode()?
- if ($articleLink->parentNode->lastChild == $articleLink) {
- $articleLink->parentNode->appendChild($refLink);
- } else {
- $articleLink->parentNode->insertBefore($refLink, $articleLink->nextSibling);
- }
-
- $articleLink->setAttribute('style', 'color: inherit; text-decoration: none;');
- $articleLink->setAttribute('name', 'readabilityLink-' . $linkCount);
-
- $footnote->innerHTML = '<small><sup><a href="#readabilityLink-' . $linkCount . '" title="Jump to Link in Article">^</a></sup></small> ';
-
- $footnoteLink->innerHTML = ($footnoteLink->getAttribute('title') != '' ? $footnoteLink->getAttribute('title') : $linkText);
- $footnoteLink->setAttribute('name', 'readabilityFootnoteLink-' . $linkCount);
-
- $footnote->appendChild($footnoteLink);
- if ($linkDomain) $footnote->innerHTML = $footnote->innerHTML . '<small> (' . $linkDomain . ')</small>';
-
- $articleFootnotes->appendChild($footnote);
- }
-
- if ($linkCount > 0) {
- $articleContent->appendChild($footnotesWrapper);
- }
- }
-
- /**
- * Reverts P elements with class 'readability-styled'
- * to text nodes - which is what they were before.
- *
- * @param DOMElement
- * @return void
- */
- function revertReadabilityStyledElements($articleContent) {
- $xpath = new DOMXPath($articleContent->ownerDocument);
- $elems = $xpath->query('.//p[@class="readability-styled"]', $articleContent);
- //$elems = $articleContent->getElementsByTagName('p');
- for ($i = $elems->length-1; $i >= 0; $i--) {
- $e = $elems->item($i);
- $e->parentNode->replaceChild($articleContent->ownerDocument->createTextNode($e->textContent), $e);
- //if ($e->hasAttribute('class') && $e->getAttribute('class') == 'readability-styled') {
- // $e->parentNode->replaceChild($this->dom->createTextNode($e->textContent), $e);
- //}
- }
- }
-
- /**
- * Prepare the article node for display. Clean out any inline styles,
- * iframes, forms, strip extraneous <p> tags, etc.
- *
- * @param DOMElement
- * @return void
- */
- function prepArticle($articleContent) {
- $this->cleanStyles($articleContent);
- $this->killBreaks($articleContent);
- if ($this->revertForcedParagraphElements) {
- $this->revertReadabilityStyledElements($articleContent);
- }
-
- /* Clean out junk from the article content */
- $this->cleanConditionally($articleContent, 'form');
- $this->clean($articleContent, 'object');
- $this->clean($articleContent, 'h1');
-
- /**
- * If there is only one h2, they are probably using it
- * as a header and not a subheader, so remove it since we already have a header.
- ***/
- if (!$this->lightClean && ($articleContent->getElementsByTagName('h2')->length == 1)) {
- $this->clean($articleContent, 'h2');
- }
- $this->clean($articleContent, 'iframe');
-
- $this->cleanHeaders($articleContent);
-
- /* Do these last as the previous stuff may have removed junk that will affect these */
- $this->cleanConditionally($articleContent, 'table');
- $this->cleanConditionally($articleContent, 'ul');
- $this->cleanConditionally($articleContent, 'div');
-
- /* Remove extra paragraphs */
- $articleParagraphs = $articleContent->getElementsByTagName('p');
- for ($i = $articleParagraphs->length-1; $i >= 0; $i--)
- {
- $imgCount = $articleParagraphs->item($i)->getElementsByTagName('img')->length;
- $embedCount = $articleParagraphs->item($i)->getElementsByTagName('embed')->length;
- $objectCount = $articleParagraphs->item($i)->getElementsByTagName('object')->length;
- $iframeCount = $articleParagraphs->item($i)->getElementsByTagName('iframe')->length;
-
- if ($imgCount === 0 && $embedCount === 0 && $objectCount === 0 && $iframeCount === 0 && $this->getInnerText($articleParagraphs->item($i), false) == '')
- {
- $articleParagraphs->item($i)->parentNode->removeChild($articleParagraphs->item($i));
- }
- }
-
- try {
- $articleContent->innerHTML = preg_replace('/<br[^>]*>\s*<p/i', '<p', $articleContent->innerHTML);
- //articleContent.innerHTML = articleContent.innerHTML.replace(/<br[^>]*>\s*<p/gi, '<p');
- }
- catch (Exception $e) {
- $this->dbg("Cleaning innerHTML of breaks failed. This is an IE strict-block-elements bug. Ignoring.: " . $e);
- }
- }
-
- /**
- * Initialize a node with the readability object. Also checks the
- * className/id for special names to add to its score.
- *
- * @param Element
- * @return void
- **/
- protected function initializeNode($node) {
- $readability = $this->dom->createAttribute('readability');
- $readability->value = 0; // this is our contentScore
- $node->setAttributeNode($readability);
-
- switch (strtoupper($node->tagName)) { // unsure if strtoupper is needed, but using it just in case
- case 'DIV':
- $readability->value += 5;
- break;
-
- case 'PRE':
- case 'TD':
- case 'BLOCKQUOTE':
- $readability->value += 3;
- break;
-
- case 'ADDRESS':
- case 'OL':
- case 'UL':
- case 'DL':
- case 'DD':
- case 'DT':
- case 'LI':
- case 'FORM':
- $readability->value -= 3;
- break;
-
- case 'H1':
- case 'H2':
- case 'H3':
- case 'H4':
- case 'H5':
- case 'H6':
- case 'TH':
- $readability->value -= 5;
- break;
- }
- $readability->value += $this->getClassWeight($node);
- }
-
- /***
- * grabArticle - Using a variety of metrics (content score, classname, element types), find the content that is
- * most likely to be the stuff a user wants to read. Then return it wrapped up in a div.
- *
- * @return DOMElement
- **/
- protected function grabArticle($page=null) {
- $stripUnlikelyCandidates = $this->flagIsActive(self::FLAG_STRIP_UNLIKELYS);
- if (!$page) $page = $this->dom;
- $allElements = $page->getElementsByTagName('*');
- /**
- * First, node prepping. Trash nodes that look cruddy (like ones with the class name "comment", etc), and turn divs
- * into P tags where they have been used inappropriately (as in, where they contain no other block level elements.)
- *
- * Note: Assignment from index for performance. See http://www.peachpit.com/articles/article.aspx?p=31567&seqNum=5
- * TODO: Shouldn't this be a reverse traversal?
- **/
- $node = null;
- $nodesToScore = array();
- for ($nodeIndex = 0; ($node = $allElements->item($nodeIndex)); $nodeIndex++) {
- //for ($nodeIndex=$targetList->length-1; $nodeIndex >= 0; $nodeIndex--) {
- //$node = $targetList->item($nodeIndex);
- $tagName = strtoupper($node->tagName);
- /* Remove unlikely candidates */
- if ($stripUnlikelyCandidates) {
- $unlikelyMatchString = $node->getAttribute('class') . $node->getAttribute('id');
- if (
- preg_match($this->regexps['unlikelyCandidates'], $unlikelyMatchString) &&
- !preg_match($this->regexps['okMaybeItsACandidate'], $unlikelyMatchString) &&
- $tagName != 'BODY'
- )
- {
- $this->dbg('Removing unlikely candidate - ' . $unlikelyMatchString);
- //$nodesToRemove[] = $node;
- $node->parentNode->removeChild($node);
- $nodeIndex--;
- continue;
- }
- }
-
- if ($tagName == 'P' || $tagName == 'TD' || $tagName == 'PRE') {
- $nodesToScore[] = $node;
- }
-
- /* Turn all divs that don't have children block level elements into p's */
- if ($tagName == 'DIV') {
- if (!preg_match($this->regexps['divToPElements'], $node->innerHTML)) {
- //$this->dbg('Altering div to p');
- $newNode = $this->dom->createElement('p');
- try {
- $newNode->innerHTML = $node->innerHTML;
- //$nodesToReplace[] = array('new'=>$newNode, 'old'=>$node);
- $node->parentNode->replaceChild($newNode, $node);
- $nodeIndex--;
- $nodesToScore[] = $node; // or $newNode?
- }
- catch(Exception $e) {
- $this->dbg('Could not alter div to p, reverting back to div.: ' . $e);
- }
- }
- else
- {
- /* EXPERIMENTAL */
- // TODO: change these p elements back to text nodes after processing
- for ($i = 0, $il = $node->childNodes->length; $i < $il; $i++) {
- $childNode = $node->childNodes->item($i);
- if ($childNode->nodeType == 3) { // XML_TEXT_NODE
- //$this->dbg('replacing text node with a p tag with the same content.');
- $p = $this->dom->createElement('p');
- $p->innerHTML = $childNode->nodeValue;
- $p->setAttribute('style', 'display: inline;');
- $p->setAttribute('class', 'readability-styled');
- $childNode->parentNode->replaceChild($p, $childNode);
- }
- }
- }
- }
- }
-
- /**
- * Loop through all paragraphs, and assign a score to them based on how content-y they look.
- * Then add their score to their parent node.
- *
- * A score is determined by things like number of commas, class names, etc. Maybe eventually link density.
- **/
- $candidates = array();
- for ($pt=0; $pt < count($nodesToScore); $pt++) {
- $parentNode = $nodesToScore[$pt]->parentNode;
- // $grandParentNode = $parentNode ? $parentNode->parentNode : null;
- $grandParentNode = !$parentNode ? null : (($parentNode->parentNode instanceof DOMElement) ? $parentNode->parentNode : null);
- $innerText = $this->getInnerText($nodesToScore[$pt]);
-
- if (!$parentNode || !isset($parentNode->tagName)) {
- continue;
- }
-
- /* If this paragraph is less than 25 characters, don't even count it. */
- if(strlen($innerText) < 25) {
- continue;
- }
-
- /* Initialize readability data for the parent. */
- if (!$parentNode->hasAttribute('readability'))
- {
- $this->initializeNode($parentNode);
- $candidates[] = $parentNode;
- }
-
- /* Initialize readability data for the grandparent. */
- if ($grandParentNode && !$grandParentNode->hasAttribute('readability') && isset($grandParentNode->tagName))
- {
- $this->initializeNode($grandParentNode);
- $candidates[] = $grandParentNode;
- }
-
- $contentScore = 0;
-
- /* Add a point for the paragraph itself as a base. */
- $contentScore++;
-
- /* Add points for any commas within this paragraph */
- $contentScore += count(explode(',', $innerText));
-
- /* For every 100 characters in this paragraph, add another point. Up to 3 points. */
- $contentScore += min(floor(strlen($innerText) / 100), 3);
-
- /* Add the score to the parent. The grandparent gets half. */
- $parentNode->getAttributeNode('readability')->value += $contentScore;
-
- if ($grandParentNode) {
- $grandParentNode->getAttributeNode('readability')->value += $contentScore/2;
- }
- }
-
- /**
- * After we've calculated scores, loop through all of the possible candidate nodes we found
- * and find the one with the highest score.
- **/
- $topCandidate = null;
- for ($c=0, $cl=count($candidates); $c < $cl; $c++)
- {
- /**
- * Scale the final candidates score based on link density. Good content should have a
- * relatively small link density (5% or less) and be mostly unaffected by this operation.
- **/
- $readability = $candidates[$c]->getAttributeNode('readability');
- $readability->value = $readability->value * (1-$this->getLinkDensity($candidates[$c]));
-
- $this->dbg('Candidate: ' . $candidates[$c]->tagName . ' (' . $candidates[$c]->getAttribute('class') . ':' . $candidates[$c]->getAttribute('id') . ') with score ' . $readability->value);
-
- if (!$topCandidate || $readability->value > (int)$topCandidate->getAttribute('readability')) {
- $topCandidate = $candidates[$c];
- }
- }
-
- /**
- * If we still have no top candidate, just use the body as a last resort.
- * We also have to copy the body node so it is something we can modify.
- **/
- if ($topCandidate === null || strtoupper($topCandidate->tagName) == 'BODY')
- {
- $topCandidate = $this->dom->createElement('div');
- if ($page instanceof DOMDocument) {
- if (!isset($page->documentElement)) {
- // we don't have a body either? what a mess! :)
- } else {
- $topCandidate->innerHTML = $page->documentElement->innerHTML;
- $page->documentElement->innerHTML = '';
- $this->reinitBody();
- $page->documentElement->appendChild($topCandidate);
- }
- } else {
- $topCandidate->innerHTML = $page->innerHTML;
- $page->innerHTML = '';
- $page->appendChild($topCandidate);
- }
- $this->initializeNode($topCandidate);
- }
-
- /**
- * Now that we have the top candidate, look through its siblings for content that might also be related.
- * Things like preambles, content split by ads that we removed, etc.
- **/
- $articleContent = $this->dom->createElement('div');
- $articleContent->setAttribute('id', 'readability-content');
- $siblingScoreThreshold = max(10, ((int)$topCandidate->getAttribute('readability')) * 0.2);
- $siblingNodes = @$topCandidate->parentNode->childNodes;
- if (!isset($siblingNodes)) {
- $siblingNodes = new stdClass;
- $siblingNodes->length = 0;
- }
-
- for ($s=0, $sl=$siblingNodes->length; $s < $sl; $s++)
- {
- $siblingNode = $siblingNodes->item($s);
- $append = false;
-
- $this->dbg('Looking at sibling node: ' . $siblingNode->nodeName . (($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('readability')) ? (' with score ' . $siblingNode->getAttribute('readability')) : ''));
-
- //dbg('Sibling has score ' . ($siblingNode->readability ? siblingNode.readability.contentScore : 'Unknown'));
-
- if ($siblingNode === $topCandidate)
- // or if ($siblingNode->isSameNode($topCandidate))
- {
- $append = true;
- }
-
- $contentBonus = 0;
- /* Give a bonus if sibling nodes and top candidates have the example same classname */
- if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->getAttribute('class') == $topCandidate->getAttribute('class') && $topCandidate->getAttribute('class') != '') {
- $contentBonus += ((int)$topCandidate->getAttribute('readability')) * 0.2;
- }
-
- if ($siblingNode->nodeType === XML_ELEMENT_NODE && $siblingNode->hasAttribute('readability') && (((int)$siblingNode->getAttribute('readability')) + $contentBonus) >= $siblingScoreThreshold)
- {
- $append = true;
- }
-
- if (strtoupper($siblingNode->nodeName) == 'P') {
- $linkDensity = $this->getLinkDensity($siblingNode);
- $nodeContent = $this->getInnerText($siblingNode);
- $nodeLength = strlen($nodeContent);
-
- if ($nodeLength > 80 && $linkDensity < 0.25)
- {
- $append = true;
- }
- else if ($nodeLength < 80 && $linkDensity === 0 && preg_match('/\.( |$)/', $nodeContent))
- {
- $append = true;
- }
- }
-
- if ($append)
- {
- $this->dbg('Appending node: ' . $siblingNode->nodeName);
-
- $nodeToAppend = null;
- $sibNodeName = strtoupper($siblingNode->nodeName);
- if ($sibNodeName != 'DIV' && $sibNodeName != 'P') {
- /* We have a node that isn't a common block level element, like a form or td tag. Turn it into a div so it doesn't get filtered out later by accident. */
-
- $this->dbg('Altering siblingNode of ' . $sibNodeName . ' to div.');
- $nodeToAppend = $this->dom->createElement('div');
- try {
- $nodeToAppend->setAttribute('id', $siblingNode->getAttribute('id'));
- $nodeToAppend->innerHTML = $siblingNode->innerHTML;
- }
- catch(Exception $e)
- {
- $this->dbg('Could not alter siblingNode to div, reverting back to original.');
- $nodeToAppend = $siblingNode;
- $s--;
- $sl--;
- }
- } else {
- $nodeToAppend = $siblingNode;
- $s--;
- $sl--;
- }
-
- /* To ensure a node does not interfere with readability styles, remove its classnames */
- $nodeToAppend->removeAttribute('class');
-
- /* Append sibling and subtract from our list because it removes the node when you append to another node */
- $articleContent->appendChild($nodeToAppend);
- }
- }
-
- /**
- * So we have all of the content that we need. Now we clean it up for presentation.
- **/
- $this->prepArticle($articleContent);
-
- /**
- * Now that we've gone through the full algorithm, check to see if we got any meaningful content.
- * If we didn't, we may need to re-run grabArticle with different flags set. This gives us a higher
- * likelihood of finding the content, and the sieve approach gives us a higher likelihood of
- * finding the -right- content.
- **/
- if (strlen($this->getInnerText($articleContent, false)) < 250)
- {
- // TODO: find out why element disappears sometimes, e.g. for this URL http://www.businessinsider.com/6-hedge-fund-etfs-for-average-investors-2011-7
- // in the meantime, we check and create an empty element if it's not there.
- $this->reinitBody();
-
- if ($this->flagIsActive(self::FLAG_STRIP_UNLIKELYS)) {
- $this->removeFlag(self::FLAG_STRIP_UNLIKELYS);
- return $this->grabArticle($this->body);
- }
- else if ($this->flagIsActive(self::FLAG_WEIGHT_CLASSES)) {
- $this->removeFlag(self::FLAG_WEIGHT_CLASSES);
- return $this->grabArticle($this->body);
- }
- else if ($this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) {
- $this->removeFlag(self::FLAG_CLEAN_CONDITIONALLY);
- return $this->grabArticle($this->body);
- }
- else {
- return false;
- }
- }
- return $articleContent;
- }
-
- /**
- * Remove script tags from document
- *
- * @param DOMElement
- * @return void
- */
- public function removeScripts($doc) {
- $scripts = $doc->getElementsByTagName('script');
- for($i = $scripts->length-1; $i >= 0; $i--)
- {
- $scripts->item($i)->parentNode->removeChild($scripts->item($i));
- }
- }
-
- /**
- * Get the inner text of a node.
- * This also strips out any excess whitespace to be found.
- *
- * @param DOMElement $
- * @param boolean $normalizeSpaces (default: true)
- * @return string
- **/
- public function getInnerText($e, $normalizeSpaces=true) {
- $textContent = '';
-
- if (!isset($e->textContent) || $e->textContent == '') {
- return '';
- }
-
- $textContent = trim($e->textContent);
-
- if ($normalizeSpaces) {
- return preg_replace($this->regexps['normalize'], ' ', $textContent);
- } else {
- return $textContent;
- }
- }
-
- /**
- * Get the number of times a string $s appears in the node $e.
- *
- * @param DOMElement $e
- * @param string - what to count. Default is ","
- * @return number (integer)
- **/
- public function getCharCount($e, $s=',') {
- return substr_count($this->getInnerText($e), $s);
- }
-
- /**
- * Remove the style attribute on every $e and under.
- *
- * @param DOMElement $e
- * @return void
- */
- public function cleanStyles($e) {
- if (!is_object($e)) return;
- $elems = $e->getElementsByTagName('*');
- foreach ($elems as $elem) {
- $elem->removeAttribute('style');
- }
- }
-
- /**
- * Get the density of links as a percentage of the content
- * This is the amount of text that is inside a link divided by the total text in the node.
- *
- * @param DOMElement $e
- * @return number (float)
- */
- public function getLinkDensity($e) {
- $links = $e->getElementsByTagName('a');
- $textLength = strlen($this->getInnerText($e));
- $linkLength = 0;
- for ($i=0, $il=$links->length; $i < $il; $i++)
- {
- $linkLength += strlen($this->getInnerText($links->item($i)));
- }
- if ($textLength > 0) {
- return $linkLength / $textLength;
- } else {
- return 0;
- }
- }
-
- /**
- * Get an elements class/id weight. Uses regular expressions to tell if this
- * element looks good or bad.
- *
- * @param DOMElement $e
- * @return number (Integer)
- */
- public function getClassWeight($e) {
- if(!$this->flagIsActive(self::FLAG_WEIGHT_CLASSES)) {
- return 0;
- }
-
- $weight = 0;
-
- /* Look for a special classname */
- if ($e->hasAttribute('class') && $e->getAttribute('class') != '')
- {
- if (preg_match($this->regexps['negative'], $e->getAttribute('class'))) {
- $weight -= 25;
- }
- if (preg_match($this->regexps['positive'], $e->getAttribute('class'))) {
- $weight += 25;
- }
- }
-
- /* Look for a special ID */
- if ($e->hasAttribute('id') && $e->getAttribute('id') != '')
- {
- if (preg_match($this->regexps['negative'], $e->getAttribute('id'))) {
- $weight -= 25;
- }
- if (preg_match($this->regexps['positive'], $e->getAttribute('id'))) {
- $weight += 25;
- }
- }
- return $weight;
- }
-
- /**
- * Remove extraneous break tags from a node.
- *
- * @param DOMElement $node
- * @return void
- */
- public function killBreaks($node) {
- $html = $node->innerHTML;
- $html = preg_replace($this->regexps['killBreaks'], '<br />', $html);
- $node->innerHTML = $html;
- }
-
- /**
- * Clean a node of all elements of type "tag".
- * (Unless it's a youtube/vimeo video. People love movies.)
- *
- * Updated 2012-09-18 to preserve youtube/vimeo iframes
- *
- * @param DOMElement $e
- * @param string $tag
- * @return void
- */
- public function clean($e, $tag) {
- $targetList = $e->getElementsByTagName($tag);
- $isEmbed = ($tag == 'iframe' || $tag == 'object' || $tag == 'embed');
-
- for ($y=$targetList->length-1; $y >= 0; $y--) {
- /* Allow youtube and vimeo videos through as people usually want to see those. */
- if ($isEmbed) {
- $attributeValues = '';
- for ($i=0, $il=$targetList->item($y)->attributes->length; $i < $il; $i++) {
- $attributeValues .= $targetList->item($y)->attributes->item($i)->value . '|'; // DOMAttr? (TODO: test)
- }
-
- /* First, check the elements attributes to see if any of them contain youtube or vimeo */
- if (preg_match($this->regexps['video'], $attributeValues)) {
- continue;
- }
-
- /* Then check the elements inside this element for the same. */
- if (preg_match($this->regexps['video'], $targetList->item($y)->innerHTML)) {
- continue;
- }
- }
- $targetList->item($y)->parentNode->removeChild($targetList->item($y));
- }
- }
-
- /**
- * Clean an element of all tags of type "tag" if they look fishy.
- * "Fishy" is an algorithm based on content length, classnames,
- * link density, number of images & embeds, etc.
- *
- * @param DOMElement $e
- * @param string $tag
- * @return void
- */
- public function cleanConditionally($e, $tag) {
- if (!$this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) {
- return;
- }
-
- $tagsList = $e->getElementsByTagName($tag);
- $curTagsLength = $tagsList->length;
-
- /**
- * Gather counts for other typical elements embedded within.
- * Traverse backwards so we can remove nodes at the same time without effecting the traversal.
- *
- * TODO: Consider taking into account original contentScore here.
- */
- for ($i=$curTagsLength-1; $i >= 0; $i--) {
- $weight = $this->getClassWeight($tagsList->item($i));
- $contentScore = ($tagsList->item($i)->hasAttribute('readability')) ? (int)$tagsList->item($i)->getAttribute('readability') : 0;
-
- $this->dbg('Cleaning Conditionally ' . $tagsList->item($i)->tagName . ' (' . $tagsList->item($i)->getAttribute('class') . ':' . $tagsList->item($i)->getAttribute('id') . ')' . (($tagsList->item($i)->hasAttribute('readability')) ? (' with score ' . $tagsList->item($i)->getAttribute('readability')) : ''));
-
- if ($weight + $contentScore < 0) {
- $tagsList->item($i)->parentNode->removeChild($tagsList->item($i));
- }
- else if ( $this->getCharCount($tagsList->item($i), ',') < 10) {
- /**
- * If there are not very many commas, and the number of
- * non-paragraph elements is more than paragraphs or other ominous signs, remove the element.
- **/
- $p = $tagsList->item($i)->getElementsByTagName('p')->length;
- $img = $tagsList->item($i)->getElementsByTagName('img')->length;
- $li = $tagsList->item($i)->getElementsByTagName('li')->length-100;
- $input = $tagsList->item($i)->getElementsByTagName('input')->length;
- $a = $tagsList->item($i)->getElementsByTagName('a')->length;
-
- $embedCount = 0;
- $embeds = $tagsList->item($i)->getElementsByTagName('embed');
- for ($ei=0, $il=$embeds->length; $ei < $il; $ei++) {
- if (preg_match($this->regexps['video'], $embeds->item($ei)->getAttribute('src'))) {
- $embedCount++;
- }
- }
- $embeds = $tagsList->item($i)->getElementsByTagName('iframe');
- for ($ei=0, $il=$embeds->length; $ei < $il; $ei++) {
- if (preg_match($this->regexps['video'], $embeds->item($ei)->getAttribute('src'))) {
- $embedCount++;
- }
- }
-
- $linkDensity = $this->getLinkDensity($tagsList->item($i));
- $contentLength = strlen($this->getInnerText($tagsList->item($i)));
- $toRemove = false;
-
- if ($this->lightClean) {
- $this->dbg('Light clean...');
- if ( ($img > $p) && ($img > 4) ) {
- $this->dbg(' more than 4 images and more image elements than paragraph elements');
- $toRemove = true;
- } else if ($li > $p && $tag != 'ul' && $tag != 'ol') {
- $this->dbg(' too many <li> elements, and parent is not <ul> or <ol>');
- $toRemove = true;
- } else if ( $input > floor($p/3) ) {
- $this->dbg(' too many <input> elements');
- $toRemove = true;
- } else if ($contentLength < 10 && ($embedCount === 0 && ($img === 0 || $img > 2))) {
- $this->dbg(' content length less than 10 chars, 0 embeds and either 0 images or more than 2 images');
- $toRemove = true;
- } else if($weight < 25 && $linkDensity > 0.2) {
- $this->dbg(' weight smaller than 25 and link density above 0.2');
- $toRemove = true;
- } else if($a > 2 && ($weight >= 25 && $linkDensity > 0.5)) {
- $this->dbg(' more than 2 links and weight above 25 but link density greater than 0.5');
- $toRemove = true;
- } else if($embedCount > 3) {
- $this->dbg(' more than 3 embeds');
- $toRemove = true;
- }
- } else {
- $this->dbg('Standard clean...');
- if ( $img > $p ) {
- $this->dbg(' more image elements than paragraph elements');
- $toRemove = true;
- } else if ($li > $p && $tag != 'ul' && $tag != 'ol') {
- $this->dbg(' too many <li> elements, and parent is not <ul> or <ol>');
- $toRemove = true;
- } else if ( $input > floor($p/3) ) {
- $this->dbg(' too many <input> elements');
- $toRemove = true;
- } else if ($contentLength < 25 && ($img === 0 || $img > 2) ) {
- $this->dbg(' content length less than 25 chars and 0 images, or more than 2 images');
- $toRemove = true;
- } else if($weight < 25 && $linkDensity > 0.2) {
- $this->dbg(' weight smaller than 25 and link density above 0.2');
- $toRemove = true;
- } else if($weight >= 25 && $linkDensity > 0.5) {
- $this->dbg(' weight above 25 but link density greater than 0.5');
- $toRemove = true;
- } else if(($embedCount == 1 && $contentLength < 75) || $embedCount > 1) {
- $this->dbg(' 1 embed and content length smaller than 75 chars, or more than one embed');
- $toRemove = true;
- }
- }
-
- if ($toRemove) {
- //$this->dbg('Removing: '.$tagsList->item($i)->innerHTML);
- $tagsList->item($i)->parentNode->removeChild($tagsList->item($i));
- }
- }
- }
- }
-
- /**
- * Clean out spurious headers from an Element. Checks things like classnames and link density.
- *
- * @param DOMElement $e
- * @return void
- */
- public function cleanHeaders($e) {
- for ($headerIndex = 1; $headerIndex < 3; $headerIndex++) {
- $headers = $e->getElementsByTagName('h' . $headerIndex);
- for ($i=$headers->length-1; $i >=0; $i--) {
- if ($this->getClassWeight($headers->item($i)) < 0 || $this->getLinkDensity($headers->item($i)) > 0.33) {
- $headers->item($i)->parentNode->removeChild($headers->item($i));
- }
- }
- }
- }
-
- public function flagIsActive($flag) {
- return ($this->flags & $flag) > 0;
- }
-
- public function addFlag($flag) {
- $this->flags = $this->flags | $flag;
- }
-
- public function removeFlag($flag) {
- $this->flags = $this->flags & ~$flag;
- }
-
- /**\r
- * Will recreate previously deleted body property\r
- *\r
- * @return void\r
- */\r
- protected function reinitBody() {\r
- if (!isset($this->body->childNodes)) {\r
- $this->body = $this->dom->createElement('body');
- $this->body->innerHTML = $this->bodyCache;\r
- }\r
- }
-
-}
-?>