link_thumbnailer 3.3.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (95) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +19 -0
  3. data/.rspec +2 -0
  4. data/.ruby-version +1 -0
  5. data/.travis.yml +5 -0
  6. data/CHANGELOG.md +334 -0
  7. data/Gemfile +12 -0
  8. data/LICENSE.txt +22 -0
  9. data/README.md +210 -0
  10. data/Rakefile +9 -0
  11. data/lib/generators/link_thumbnailer/install_generator.rb +17 -0
  12. data/lib/generators/templates/initializer.rb +89 -0
  13. data/lib/link_thumbnailer.rb +38 -0
  14. data/lib/link_thumbnailer/configuration.rb +72 -0
  15. data/lib/link_thumbnailer/exceptions.rb +11 -0
  16. data/lib/link_thumbnailer/grader.rb +43 -0
  17. data/lib/link_thumbnailer/graders/base.rb +39 -0
  18. data/lib/link_thumbnailer/graders/html_attribute.rb +48 -0
  19. data/lib/link_thumbnailer/graders/length.rb +37 -0
  20. data/lib/link_thumbnailer/graders/link_density.rb +20 -0
  21. data/lib/link_thumbnailer/graders/position.rb +13 -0
  22. data/lib/link_thumbnailer/image_comparator.rb +26 -0
  23. data/lib/link_thumbnailer/image_comparators/base.rb +19 -0
  24. data/lib/link_thumbnailer/image_comparators/size.rb +13 -0
  25. data/lib/link_thumbnailer/image_parser.rb +62 -0
  26. data/lib/link_thumbnailer/image_validator.rb +32 -0
  27. data/lib/link_thumbnailer/model.rb +20 -0
  28. data/lib/link_thumbnailer/models/description.rb +37 -0
  29. data/lib/link_thumbnailer/models/favicon.rb +27 -0
  30. data/lib/link_thumbnailer/models/image.rb +56 -0
  31. data/lib/link_thumbnailer/models/title.rb +22 -0
  32. data/lib/link_thumbnailer/models/video.rb +44 -0
  33. data/lib/link_thumbnailer/models/website.rb +54 -0
  34. data/lib/link_thumbnailer/page.rb +43 -0
  35. data/lib/link_thumbnailer/parser.rb +15 -0
  36. data/lib/link_thumbnailer/processor.rb +128 -0
  37. data/lib/link_thumbnailer/railtie.rb +6 -0
  38. data/lib/link_thumbnailer/response.rb +39 -0
  39. data/lib/link_thumbnailer/scraper.rb +62 -0
  40. data/lib/link_thumbnailer/scrapers/base.rb +69 -0
  41. data/lib/link_thumbnailer/scrapers/default/base.rb +12 -0
  42. data/lib/link_thumbnailer/scrapers/default/description.rb +49 -0
  43. data/lib/link_thumbnailer/scrapers/default/favicon.rb +38 -0
  44. data/lib/link_thumbnailer/scrapers/default/images.rb +78 -0
  45. data/lib/link_thumbnailer/scrapers/default/title.rb +27 -0
  46. data/lib/link_thumbnailer/scrapers/default/videos.rb +18 -0
  47. data/lib/link_thumbnailer/scrapers/opengraph/base.rb +45 -0
  48. data/lib/link_thumbnailer/scrapers/opengraph/description.rb +12 -0
  49. data/lib/link_thumbnailer/scrapers/opengraph/favicon.rb +17 -0
  50. data/lib/link_thumbnailer/scrapers/opengraph/image.rb +107 -0
  51. data/lib/link_thumbnailer/scrapers/opengraph/images.rb +18 -0
  52. data/lib/link_thumbnailer/scrapers/opengraph/title.rb +12 -0
  53. data/lib/link_thumbnailer/scrapers/opengraph/video.rb +115 -0
  54. data/lib/link_thumbnailer/scrapers/opengraph/videos.rb +18 -0
  55. data/lib/link_thumbnailer/uri.rb +20 -0
  56. data/lib/link_thumbnailer/version.rb +5 -0
  57. data/lib/link_thumbnailer/video_parser.rb +47 -0
  58. data/link_thumbnailer.gemspec +29 -0
  59. data/spec/configuration_spec.rb +61 -0
  60. data/spec/fixture_spec.rb +114 -0
  61. data/spec/fixtures/bar.png +2907 -0
  62. data/spec/fixtures/default_from_body.html +13 -0
  63. data/spec/fixtures/default_from_meta.html +12 -0
  64. data/spec/fixtures/foo.png +0 -0
  65. data/spec/fixtures/google_shift_jis.html +6 -0
  66. data/spec/fixtures/google_utf8.html +6 -0
  67. data/spec/fixtures/og_not_valid_example.html +12 -0
  68. data/spec/fixtures/og_valid_example.html +18 -0
  69. data/spec/fixtures/og_valid_multi_image_example.html +13 -0
  70. data/spec/fixtures/og_valid_multi_video_example.html +13 -0
  71. data/spec/grader_spec.rb +27 -0
  72. data/spec/graders/base_spec.rb +14 -0
  73. data/spec/graders/html_attribute_spec.rb +50 -0
  74. data/spec/graders/length_spec.rb +93 -0
  75. data/spec/graders/link_density_spec.rb +52 -0
  76. data/spec/graders/position_spec.rb +49 -0
  77. data/spec/image_comparators/size_spec.rb +58 -0
  78. data/spec/image_validator_spec.rb +37 -0
  79. data/spec/model_spec.rb +27 -0
  80. data/spec/models/description_spec.rb +66 -0
  81. data/spec/models/favicon_spec.rb +12 -0
  82. data/spec/models/image_spec.rb +95 -0
  83. data/spec/models/title_spec.rb +26 -0
  84. data/spec/models/video_spec.rb +49 -0
  85. data/spec/models/website_spec.rb +51 -0
  86. data/spec/page_spec.rb +28 -0
  87. data/spec/processor_spec.rb +410 -0
  88. data/spec/response_spec.rb +62 -0
  89. data/spec/scraper_spec.rb +70 -0
  90. data/spec/scrapers/base_spec.rb +69 -0
  91. data/spec/scrapers/opengraph/base_spec.rb +96 -0
  92. data/spec/spec_helper.rb +11 -0
  93. data/spec/uri_spec.rb +44 -0
  94. data/spec/video_parser_spec.rb +148 -0
  95. metadata +271 -0
data/spec/fixtures/default_from_body.html ADDED
@@ -0,0 +1,13 @@
1
+ <html>
2
+ <head>
3
+ <title>Title from meta</title>
4
+ <link rel="shortcut icon" href="http://foo.com/foo.ico">
5
+ </head>
6
+ <body>
7
+
8
+ <p>Description from body</p>
9
+
10
+ <img src="http://foo.com/foo.png">
11
+
12
+ </body>
13
+ </html>
data/spec/fixtures/default_from_meta.html ADDED
@@ -0,0 +1,12 @@
1
+ <html>
2
+ <head>
3
+ <title>Title from meta</title>
4
+ <meta content="Description from meta" name="description">
5
+ <link rel="icon whatever" href="http://foo.com/foo.ico">
6
+ </head>
7
+ <body>
8
+
9
+ <p>Description from body</p>
10
+
11
+ </body>
12
+ </html>
data/spec/fixtures/foo.png ADDED
Binary file
data/spec/fixtures/google_shift_jis.html ADDED
@@ -0,0 +1,6 @@
1
+ <!doctype html><html itemscope="" itemtype="http://schema.org/WebPage" lang="ja"><head><meta content="���E���̂���������������邽�߂̃c�[����񋟂��Ă��܂��B���܂��܂Ȍ����@�\�����p���āA���T���̏������‚��Ă��������B" name="description"><meta content="noodp" name="robots"><meta content="text/html; charset=UTF-8" http-equiv="Content-Type"><meta content="/images/branding/googleg/1x/googleg_standard_color_128dp.png" itemprop="image"><title>Google</title><script>(function(){window.google={kEI:'716VWJL3JYq18QWo_qzoAg',kEXPI:'750722,1351903,1352241,1352381,3700253,3700347,4028875,4029815,4032677,4038012,4043492,4045839,4048347,4062666,4065787,4068816,4069773,4069838,4069840,4070138,4072773,4073405,4073726,4073959,4076096,4076931,4076999,4077777,4078438,4079081,4079105,4079894,4081038,4081485,4082194,4082201,4082298,4082619,4083044,4083476,4084343,4084673,4085336,4085412,4085683,4086011,4089003,4089144,4089183,4089427,4089538,4089913,4090414,4090547,4090549,4090598,4090657,4090806,4090893,4091966,4092028,4092182,4092218,4092474,4092478,4092598,4092864,4092867,4092875,4092897,4092934,4093073,4093948,4094169,4094250,4094769,4094987,4094997,4095554,4095771,4095907,4095998,8300096,8300272,8507380,8507419,8507861,8507940,8508624,8510023,10200083,13500022,13500024',authuser:0,kscs:'c9c918f0_24'};google.kHL='ja';})();(function(){google.lc=[];google.li=0;google.getEI=function(a){for(var b;a&&(!a.getAttribute||!(b=a.getAttribute("eid")));)a=a.parentNode;return b||google.kEI};google.getLEI=function(a){for(var b=null;a&&(!a.getAttribute||!(b=a.getAttribute("leid")));)a=a.parentNode;return b};google.https=function(){return"https:"==window.location.protocol};google.ml=function(){return null};google.wl=function(a,b){try{google.ml(Error(a),!1,b)}catch(c){}};google.time=function(){return(new Date).getTime()};google.log=function(a,b,c,d,g){a=google.logUrl(a,b,c,d,g);if(""!=a){b=new Image;var e=google.lc,f=google.li;e[f]=b;b.onerror=b.onload=b.onabort=function(){delete e[f]};window.google&&window.google.vel&&window.google.vel.lu&&window.google.vel.lu(a);b.src=a;google.li=f+1}};google.logUrl=function(a,b,c,d,g){var e="",f=google.ls||"";c||-1!=b.search("&ei=")||(e="&ei="+google.getEI(d),-1==b.search("&lei=")&&(d=google.getLEI(d))&&(e+="&lei="+d));a=c||"/"+(g||"gen_204")+"?atyp=i&ct="+a+"&cad="+b+e+f+"&zx="+google.time();/^http:/i.test(a)&&google.https()&&(google.ml(Error("a"),!1,{src:a,glmm:1}),a="");return a};google.y={};google.x=function(a,b){google.y[a.id]=[a,b];return!1};google.lq=[];google.load=function(a,b,c){google.lq.push([[a],b,c])};google.loadAll=function(a,b){google.lq.push([a,b])};}).call(this);var a=window.location,b=a.href.indexOf("#");if(0<=b){var c=a.href.substring(b+1);/(^|&)q=/.test(c)&&-1==c.indexOf("#")&&a.replace("/search?"+c.replace(/(^|&)fp=[^&]*/g,"")+"&cad=h")};</script><style>#gbar,#guser{font-size:13px;padding-top:1px !important;}#gbar{height:22px}#guser{padding-bottom:7px !important;text-align:right}.gbh,.gbd{border-top:1px solid #c9d7f1;font-size:1px}.gbh{height:0;position:absolute;top:24px;width:100%}@media all{.gb1{height:22px;margin-right:.5em;vertical-align:top}#gbar{float:left}}a.gb1,a.gb4{text-decoration:underline !important}a.gb1,a.gb4{color:#00c !important}.gbi .gb4{color:#dd8e27 !important}.gbf .gb4{color:#900 !important}
2
+ </style><style>body,td,a,p,.h{font-family:arial,sans-serif}body{margin:0;overflow-y:scroll}#gog{padding:3px 8px 0}td{line-height:.8em}.gac_m td{line-height:17px}form{margin-bottom:20px}.h{color:#36c}.q{color:#00c}.ts td{padding:0}.ts{border-collapse:collapse}em{font-weight:bold;font-style:normal}.lst{height:25px;width:496px}.gsfi,.lst{font:18px arial,sans-serif}.gsfs{font:17px arial,sans-serif}.ds{display:inline-box;display:inline-block;margin:3px 0 4px;margin-left:4px}input{font-family:inherit}a.gb1,a.gb2,a.gb3,a.gb4{color:#11c !important}body{background:#fff;color:black}a{color:#11c;text-decoration:none}a:hover,a:active{text-decoration:underline}.fl a{color:#36c}a:visited{color:#551a8b}a.gb1,a.gb4{text-decoration:underline}a.gb3:hover{text-decoration:none}#ghead a.gb2:hover{color:#fff !important}.sblc{padding-top:5px}.sblc a{display:block;margin:2px 0;margin-left:13px;font-size:11px}.lsbb{background:#eee;border:solid 1px;border-color:#ccc #999 #999 #ccc;height:30px}.lsbb{display:block}.ftl,#fll a{display:inline-block;margin:0 12px}.lsb{background:url(/images/nav_logo229.png) 0 -261px repeat-x;border:none;color:#000;cursor:pointer;height:30px;margin:0;outline:0;font:15px arial,sans-serif;vertical-align:top}.lsb:active{background:#ccc}.lst:focus{outline:none}</style><script></script><link href="/images/branding/product/ico/googleg_lodp.ico" rel="shortcut icon"></head><body bgcolor="#fff"><script>(function(){var src='/images/nav_logo229.png';var iesg=false;document.body.onload = function(){window.n && window.n();if (document.images){new Image().src=src;}
3
+ if (!iesg){document.f&&document.f.q.focus();document.gbqf&&document.gbqf.q.focus();}
4
+ }
5
+ })();</script><div id="mngb"> <div id=gbar><nobr><b class=gb1>����</b> <a class=gb1 href="https://www.google.co.jp/imghp?hl=ja&tab=wi">�摜</a> <a class=gb1 href="https://maps.google.co.jp/maps?hl=ja&tab=wl">�}�b�v</a> <a class=gb1 href="https://play.google.com/?hl=ja&tab=w8">Play</a> <a class=gb1 href="https://www.youtube.com/?gl=JP&tab=w1">YouTube</a> <a class=gb1 href="https://news.google.co.jp/nwshp?hl=ja&tab=wn">�j���[�X</a> <a class=gb1 href="https://mail.google.com/mail/?tab=wm">Gmail</a> <a class=gb1 href="https://drive.google.com/?tab=wo">�h���C�u</a> <a class=gb1 style="text-decoration:none" href="https://www.google.co.jp/intl/ja/options/"><u>�����ƌ���</u> &raquo;</a></nobr></div><div id=guser width=100%><nobr><span id=gbn class=gbi></span><span id=gbf class=gbf></span><span id=gbe></span><a href="http://www.google.co.jp/history/optout?hl=ja" class=gb4>�E�F�u����</a> | <a href="/preferences?hl=ja" class=gb4>�ݒ�</a> | <a target=_top id=gb_70 href="https://accounts.google.com/ServiceLogin?hl=ja&passive=true&continue=https://www.google.co.jp/" class=gb4>���O�C��</a></nobr></div><div class=gbh style=left:0></div><div class=gbh style=right:0></div> </div><center><br clear="all" id="lgpd"><div id="lga"><div style="padding:28px 0 3px"><div style="height:110px;width:276px;background:url(/images/branding/googlelogo/1x/googlelogo_white_background_color_272x92dp.png) no-repeat" title="Google" align="left" id="hplogo" onload="window.lol&&lol()"><div style="color:#777;font-size:16px;font-weight:bold;position:relative;top:70px;left:218px" nowrap="">���{</div></div></div><br></div><form action="/search" name="f"><table cellpadding="0" cellspacing="0"><tr valign="top"><td width="25%">&nbsp;</td><td align="center" nowrap=""><input name="ie" value="Shift_JIS" type="hidden"><input value="ja" name="hl" type="hidden"><input name="source" type="hidden" value="hp"><input name="biw" type="hidden"><input name="bih" type="hidden"><div class="ds" style="height:32px;margin:4px 0"><input style="color:#000;margin:0;padding:5px 8px 0 6px;vertical-align:top" autocomplete="off" class="lst" value="" title="Google ����" maxlength="2048" name="q" size="57"></div><br style="line-height:0"><span class="ds"><span class="lsbb"><input class="lsb" value="Google ����" name="btnG" type="submit"></span></span><span class="ds"><span class="lsbb"><input class="lsb" value="I'm Feeling Lucky" name="btnI" onclick="if(this.form.q.value)this.checked=1; else top.location='/doodles/'" type="submit"></span></span></td><td class="fl sblc" align="left" nowrap="" width="25%"><a href="/advanced_search?hl=ja&amp;authuser=0">�����I�v�V����</a><a href="/language_tools?hl=ja&amp;authuser=0">����c�[��</a></td></tr></table><input id="gbv" name="gbv" type="hidden" value="1"></form><div id="gac_scont"></div><div style="font-size:83%;min-height:3.5em"><br></div><span id="footer"><div style="font-size:10pt"><div style="margin:19px auto;text-align:center" id="fll"><a href="/intl/ja/ads/">�L���f��</a><a href="http://www.google.co.jp/intl/ja/services/">�r�W�l�X �\�����[�V����</a><a href="https://plus.google.com/115899767381375908215" rel="publisher">+Google</a><a href="/intl/ja/about.html">Google �ɂ‚���</a><a href="https://www.google.co.jp/setprefdomain?prefdom=US&amp;sig=__NSwOcr0nRFmauaxJWrHJmztdkTc%3D" id="fehl">Google.com</a></div></div><p style="color:#767676;font-size:8pt">&copy; 2017 - <a href="/intl/ja/policies/privacy/">�v���C�o�V�[</a> - <a href="/intl/ja/policies/terms/">�K��</a></p></span></center><script>(function(){window.google.cdo={height:0,width:0};(function(){var a=window.innerWidth,b=window.innerHeight;if(!a||!b)var c=window.document,d="CSS1Compat"==c.compatMode?c.documentElement:c.body,a=d.clientWidth,b=d.clientHeight;a&&b&&(a!=google.cdo.width||b!=google.cdo.height)&&google.log("","","/client_204?&atyp=i&biw="+a+"&bih="+b+"&ei="+google.kEI);}).call(this);})();</script><div id="xjsd"></div><div id="xjsi"><script>(function(){function c(b){window.setTimeout(function(){var a=document.createElement("script");a.src=b;document.getElementById("xjsd").appendChild(a)},0)}google.dljp=function(b,a){google.xjsu=b;c(a)};google.dlj=c;}).call(this);(function(){window.google.xjsrm=[];})();if(google.y)google.y.first=[];if(!google.xjs){window._=window._||{};window._._DumpException=function(e){throw e};if(google.timers&&google.timers.load.t){google.timers.load.t.xjsls=new Date().getTime();}google.dljp('/xjs/_/js/k\x3dxjs.hp.en_US.usfcb5N0rIw.O/m\x3dsb_he,d/rt\x3dj/d\x3d1/t\x3dzcms/rs\x3dACT90oH_6o1ZdJ1OdBerX9LppN-xEd11Eg','/xjs/_/js/k\x3dxjs.hp.en_US.usfcb5N0rIw.O/m\x3dsb_he,d/rt\x3dj/d\x3d1/t\x3dzcms/rs\x3dACT90oH_6o1ZdJ1OdBerX9LppN-xEd11Eg');google.xjs=1;}google.pmc={"sb_he":{"agen":true,"cgen":true,"client":"heirloom-hp","dh":true,"dhqt":true,"ds":"","fl":true,"host":"google.co.jp","isbh":28,"jam":0,"jsonp":true,"msgs":{"cibl":"�������N���A","dym":"����������:","lcky":"I\u0026#39;m Feeling Lucky","lml":"�ڍ�","oskt":"���̓c�[��","psrc":"���̌����L�[���[�h��\u003Ca href=\"/history\"\u003E�E�F�u����\u003C/a\u003E����폜����܂���","psrl":"�폜","sbit":"�摜�Ō���","srch":"Google ����"},"nds":true,"ovr":{},"pq":"","refpd":true,"refspre":true,"rfs":[],"scd":10,"sce":5,"stok":"WXDdTX_0YGr0J9JRNcHRvk23BlI"},"d":{}};google.y.first.push(function(){if(google.med){google.med('init');google.initHistory();google.med('history');}});if(google.j&&google.j.en&&google.j.xi){window.setTimeout(google.j.xi,0);}
6
+ </script></div></body></html>
data/spec/fixtures/google_utf8.html ADDED
@@ -0,0 +1,6 @@
1
+ <!doctype html><html itemscope="" itemtype="http://schema.org/WebPage" lang="ja"><head><meta content="世界中のあらゆる情報を検索するためのツールを提供しています。さまざまな検索機能を活用して、お探しの情報を見つけてください。" name="description"><meta content="noodp" name="robots"><meta content="text/html; charset=UTF-8" http-equiv="Content-Type"><meta content="/images/branding/googleg/1x/googleg_standard_color_128dp.png" itemprop="image"><title>Google</title><script>(function(){window.google={kEI:'716VWJL3JYq18QWo_qzoAg',kEXPI:'750722,1351903,1352241,1352381,3700253,3700347,4028875,4029815,4032677,4038012,4043492,4045839,4048347,4062666,4065787,4068816,4069773,4069838,4069840,4070138,4072773,4073405,4073726,4073959,4076096,4076931,4076999,4077777,4078438,4079081,4079105,4079894,4081038,4081485,4082194,4082201,4082298,4082619,4083044,4083476,4084343,4084673,4085336,4085412,4085683,4086011,4089003,4089144,4089183,4089427,4089538,4089913,4090414,4090547,4090549,4090598,4090657,4090806,4090893,4091966,4092028,4092182,4092218,4092474,4092478,4092598,4092864,4092867,4092875,4092897,4092934,4093073,4093948,4094169,4094250,4094769,4094987,4094997,4095554,4095771,4095907,4095998,8300096,8300272,8507380,8507419,8507861,8507940,8508624,8510023,10200083,13500022,13500024',authuser:0,kscs:'c9c918f0_24'};google.kHL='ja';})();(function(){google.lc=[];google.li=0;google.getEI=function(a){for(var b;a&&(!a.getAttribute||!(b=a.getAttribute("eid")));)a=a.parentNode;return b||google.kEI};google.getLEI=function(a){for(var b=null;a&&(!a.getAttribute||!(b=a.getAttribute("leid")));)a=a.parentNode;return b};google.https=function(){return"https:"==window.location.protocol};google.ml=function(){return null};google.wl=function(a,b){try{google.ml(Error(a),!1,b)}catch(c){}};google.time=function(){return(new Date).getTime()};google.log=function(a,b,c,d,g){a=google.logUrl(a,b,c,d,g);if(""!=a){b=new Image;var e=google.lc,f=google.li;e[f]=b;b.onerror=b.onload=b.onabort=function(){delete e[f]};window.google&&window.google.vel&&window.google.vel.lu&&window.google.vel.lu(a);b.src=a;google.li=f+1}};google.logUrl=function(a,b,c,d,g){var e="",f=google.ls||"";c||-1!=b.search("&ei=")||(e="&ei="+google.getEI(d),-1==b.search("&lei=")&&(d=google.getLEI(d))&&(e+="&lei="+d));a=c||"/"+(g||"gen_204")+"?atyp=i&ct="+a+"&cad="+b+e+f+"&zx="+google.time();/^http:/i.test(a)&&google.https()&&(google.ml(Error("a"),!1,{src:a,glmm:1}),a="");return a};google.y={};google.x=function(a,b){google.y[a.id]=[a,b];return!1};google.lq=[];google.load=function(a,b,c){google.lq.push([[a],b,c])};google.loadAll=function(a,b){google.lq.push([a,b])};}).call(this);var a=window.location,b=a.href.indexOf("#");if(0<=b){var c=a.href.substring(b+1);/(^|&)q=/.test(c)&&-1==c.indexOf("#")&&a.replace("/search?"+c.replace(/(^|&)fp=[^&]*/g,"")+"&cad=h")};</script><style>#gbar,#guser{font-size:13px;padding-top:1px !important;}#gbar{height:22px}#guser{padding-bottom:7px !important;text-align:right}.gbh,.gbd{border-top:1px solid #c9d7f1;font-size:1px}.gbh{height:0;position:absolute;top:24px;width:100%}@media all{.gb1{height:22px;margin-right:.5em;vertical-align:top}#gbar{float:left}}a.gb1,a.gb4{text-decoration:underline !important}a.gb1,a.gb4{color:#00c !important}.gbi .gb4{color:#dd8e27 !important}.gbf .gb4{color:#900 !important}
2
+ </style><style>body,td,a,p,.h{font-family:arial,sans-serif}body{margin:0;overflow-y:scroll}#gog{padding:3px 8px 0}td{line-height:.8em}.gac_m td{line-height:17px}form{margin-bottom:20px}.h{color:#36c}.q{color:#00c}.ts td{padding:0}.ts{border-collapse:collapse}em{font-weight:bold;font-style:normal}.lst{height:25px;width:496px}.gsfi,.lst{font:18px arial,sans-serif}.gsfs{font:17px arial,sans-serif}.ds{display:inline-box;display:inline-block;margin:3px 0 4px;margin-left:4px}input{font-family:inherit}a.gb1,a.gb2,a.gb3,a.gb4{color:#11c !important}body{background:#fff;color:black}a{color:#11c;text-decoration:none}a:hover,a:active{text-decoration:underline}.fl a{color:#36c}a:visited{color:#551a8b}a.gb1,a.gb4{text-decoration:underline}a.gb3:hover{text-decoration:none}#ghead a.gb2:hover{color:#fff !important}.sblc{padding-top:5px}.sblc a{display:block;margin:2px 0;margin-left:13px;font-size:11px}.lsbb{background:#eee;border:solid 1px;border-color:#ccc #999 #999 #ccc;height:30px}.lsbb{display:block}.ftl,#fll a{display:inline-block;margin:0 12px}.lsb{background:url(/images/nav_logo229.png) 0 -261px repeat-x;border:none;color:#000;cursor:pointer;height:30px;margin:0;outline:0;font:15px arial,sans-serif;vertical-align:top}.lsb:active{background:#ccc}.lst:focus{outline:none}</style><script></script><link href="/images/branding/product/ico/googleg_lodp.ico" rel="shortcut icon"></head><body bgcolor="#fff"><script>(function(){var src='/images/nav_logo229.png';var iesg=false;document.body.onload = function(){window.n && window.n();if (document.images){new Image().src=src;}
3
+ if (!iesg){document.f&&document.f.q.focus();document.gbqf&&document.gbqf.q.focus();}
4
+ }
5
+ })();</script><div id="mngb"> <div id=gbar><nobr><b class=gb1>検索</b> <a class=gb1 href="https://www.google.co.jp/imghp?hl=ja&tab=wi">画像</a> <a class=gb1 href="https://maps.google.co.jp/maps?hl=ja&tab=wl">マップ</a> <a class=gb1 href="https://play.google.com/?hl=ja&tab=w8">Play</a> <a class=gb1 href="https://www.youtube.com/?gl=JP&tab=w1">YouTube</a> <a class=gb1 href="https://news.google.co.jp/nwshp?hl=ja&tab=wn">ニュース</a> <a class=gb1 href="https://mail.google.com/mail/?tab=wm">Gmail</a> <a class=gb1 href="https://drive.google.com/?tab=wo">ドライブ</a> <a class=gb1 style="text-decoration:none" href="https://www.google.co.jp/intl/ja/options/"><u>もっと見る</u> &raquo;</a></nobr></div><div id=guser width=100%><nobr><span id=gbn class=gbi></span><span id=gbf class=gbf></span><span id=gbe></span><a href="http://www.google.co.jp/history/optout?hl=ja" class=gb4>ウェブ履歴</a> | <a href="/preferences?hl=ja" class=gb4>設定</a> | <a target=_top id=gb_70 href="https://accounts.google.com/ServiceLogin?hl=ja&passive=true&continue=https://www.google.co.jp/" class=gb4>ログイン</a></nobr></div><div class=gbh style=left:0></div><div class=gbh style=right:0></div> </div><center><br clear="all" id="lgpd"><div id="lga"><div style="padding:28px 0 3px"><div style="height:110px;width:276px;background:url(/images/branding/googlelogo/1x/googlelogo_white_background_color_272x92dp.png) no-repeat" title="Google" align="left" id="hplogo" onload="window.lol&&lol()"><div style="color:#777;font-size:16px;font-weight:bold;position:relative;top:70px;left:218px" nowrap="">日本</div></div></div><br></div><form action="/search" name="f"><table cellpadding="0" cellspacing="0"><tr valign="top"><td width="25%">&nbsp;</td><td align="center" nowrap=""><input name="ie" value="Shift_JIS" type="hidden"><input value="ja" name="hl" type="hidden"><input name="source" type="hidden" value="hp"><input name="biw" type="hidden"><input name="bih" type="hidden"><div class="ds" style="height:32px;margin:4px 0"><input style="color:#000;margin:0;padding:5px 8px 0 6px;vertical-align:top" autocomplete="off" class="lst" value="" title="Google 検索" maxlength="2048" name="q" size="57"></div><br style="line-height:0"><span class="ds"><span class="lsbb"><input class="lsb" value="Google 検索" name="btnG" type="submit"></span></span><span class="ds"><span class="lsbb"><input class="lsb" value="I'm Feeling Lucky" name="btnI" onclick="if(this.form.q.value)this.checked=1; else top.location='/doodles/'" type="submit"></span></span></td><td class="fl sblc" align="left" nowrap="" width="25%"><a href="/advanced_search?hl=ja&amp;authuser=0">検索オプション</a><a href="/language_tools?hl=ja&amp;authuser=0">言語ツール</a></td></tr></table><input id="gbv" name="gbv" type="hidden" value="1"></form><div id="gac_scont"></div><div style="font-size:83%;min-height:3.5em"><br></div><span id="footer"><div style="font-size:10pt"><div style="margin:19px auto;text-align:center" id="fll"><a href="/intl/ja/ads/">広告掲載</a><a href="http://www.google.co.jp/intl/ja/services/">ビジネス ソリューション</a><a href="https://plus.google.com/115899767381375908215" rel="publisher">+Google</a><a href="/intl/ja/about.html">Google について</a><a href="https://www.google.co.jp/setprefdomain?prefdom=US&amp;sig=__NSwOcr0nRFmauaxJWrHJmztdkTc%3D" id="fehl">Google.com</a></div></div><p style="color:#767676;font-size:8pt">&copy; 2017 - <a href="/intl/ja/policies/privacy/">プライバシー</a> - <a href="/intl/ja/policies/terms/">規約</a></p></span></center><script>(function(){window.google.cdo={height:0,width:0};(function(){var a=window.innerWidth,b=window.innerHeight;if(!a||!b)var c=window.document,d="CSS1Compat"==c.compatMode?c.documentElement:c.body,a=d.clientWidth,b=d.clientHeight;a&&b&&(a!=google.cdo.width||b!=google.cdo.height)&&google.log("","","/client_204?&atyp=i&biw="+a+"&bih="+b+"&ei="+google.kEI);}).call(this);})();</script><div id="xjsd"></div><div id="xjsi"><script>(function(){function c(b){window.setTimeout(function(){var a=document.createElement("script");a.src=b;document.getElementById("xjsd").appendChild(a)},0)}google.dljp=function(b,a){google.xjsu=b;c(a)};google.dlj=c;}).call(this);(function(){window.google.xjsrm=[];})();if(google.y)google.y.first=[];if(!google.xjs){window._=window._||{};window._._DumpException=function(e){throw e};if(google.timers&&google.timers.load.t){google.timers.load.t.xjsls=new Date().getTime();}google.dljp('/xjs/_/js/k\x3dxjs.hp.en_US.usfcb5N0rIw.O/m\x3dsb_he,d/rt\x3dj/d\x3d1/t\x3dzcms/rs\x3dACT90oH_6o1ZdJ1OdBerX9LppN-xEd11Eg','/xjs/_/js/k\x3dxjs.hp.en_US.usfcb5N0rIw.O/m\x3dsb_he,d/rt\x3dj/d\x3d1/t\x3dzcms/rs\x3dACT90oH_6o1ZdJ1OdBerX9LppN-xEd11Eg');google.xjs=1;}google.pmc={"sb_he":{"agen":true,"cgen":true,"client":"heirloom-hp","dh":true,"dhqt":true,"ds":"","fl":true,"host":"google.co.jp","isbh":28,"jam":0,"jsonp":true,"msgs":{"cibl":"検索をクリア","dym":"もしかして:","lcky":"I\u0026#39;m Feeling Lucky","lml":"詳細","oskt":"入力ツール","psrc":"この検索キーワードは\u003Ca href=\"/history\"\u003Eウェブ履歴\u003C/a\u003Eから削除されました","psrl":"削除","sbit":"画像で検索","srch":"Google 検索"},"nds":true,"ovr":{},"pq":"","refpd":true,"refspre":true,"rfs":[],"scd":10,"sce":5,"stok":"WXDdTX_0YGr0J9JRNcHRvk23BlI"},"d":{}};google.y.first.push(function(){if(google.med){google.med('init');google.initHistory();google.med('history');}});if(google.j&&google.j.en&&google.j.xi){window.setTimeout(google.j.xi,0);}
6
+ </script></div></body></html>
data/spec/fixtures/og_not_valid_example.html ADDED
@@ -0,0 +1,12 @@
1
+ <html xmlns:og="http://opengraphprotocol.org/schema/">
2
+ <head>
3
+ <meta charset="utf-8"/>
4
+ <meta name="og:type" content="website"/>
5
+ <meta name="og:site_name" content="foo.com">
6
+ <meta name="og:title" content="Title from og">
7
+ <meta name="og:description" content="Description from og">
8
+ <meta name="og:image" content="http://foo.com/foo.png">
9
+ <title>Title</title>
10
+ </head>
11
+
12
+ </html>
data/spec/fixtures/og_valid_example.html ADDED
@@ -0,0 +1,18 @@
1
+ <html xmlns:og="http://opengraphprotocol.org/schema/">
2
+ <head>
3
+ <meta charset="utf-8"/>
4
+ <meta property="og:type" content="website"/>
5
+ <meta property="og:site_name" content="foo.com">
6
+ <meta property="og:title" content="Title from og">
7
+ <meta property="og:description" content="Description from og">
8
+ <meta property="og:image" content="http://foo.com/foo.png">
9
+ <meta property="og:image:width" content="100">
10
+ <meta property="og:image:height" content="100">
11
+ <meta property="og:video" content="http://foo.com/foo.swf">
12
+ <meta property="og:video:width" content="100">
13
+ <meta property="og:video:height" content="100">
14
+ <link rel="icon" href="http://foo.com/foo.ico">
15
+ <title>Title</title>
16
+ </head>
17
+
18
+ </html>
data/spec/fixtures/og_valid_multi_image_example.html ADDED
@@ -0,0 +1,13 @@
1
+ <html xmlns:og="http://opengraphprotocol.org/schema/">
2
+ <head>
3
+ <meta charset="utf-8"/>
4
+ <meta property="og:type" content="website"/>
5
+ <meta property="og:site_name" content="foo.com">
6
+ <meta property="og:title" content="Title from og">
7
+ <meta property="og:description" content="Description from og">
8
+ <meta property="og:image" content="http://foo.com/foo.png">
9
+ <meta property="og:image:url" content="http://foo.com/bar.png">
10
+ <title>Title</title>
11
+ </head>
12
+
13
+ </html>
data/spec/fixtures/og_valid_multi_video_example.html ADDED
@@ -0,0 +1,13 @@
1
+ <html xmlns:og="http://opengraphprotocol.org/schema/">
2
+ <head>
3
+ <meta charset="utf-8"/>
4
+ <meta property="og:type" content="website"/>
5
+ <meta property="og:site_name" content="foo.com">
6
+ <meta property="og:title" content="Title from og">
7
+ <meta property="og:description" content="Description from og">
8
+ <meta property="og:video" content="http://foo.com/foo.swf">
9
+ <meta property="og:video:url" content="http://foo.com/bar.swf">
10
+ <title>Title</title>
11
+ </head>
12
+
13
+ </html>
data/spec/grader_spec.rb ADDED
@@ -0,0 +1,27 @@
1
+ # frozen_string_literal: true
2
+
3
+ require 'spec_helper'
4
+
5
+ describe LinkThumbnailer::Grader do
6
+
7
+ let(:description) { double('description') }
8
+ let(:instance) { described_class.new(description) }
9
+
10
+ describe '#call' do
11
+
12
+ let(:probability) { 0.5 }
13
+ let(:weight) { 2 }
14
+ let(:grader) { double('grader', call: probability, weight: weight) }
15
+ let(:lambda) { ->(_) { grader } }
16
+ let(:graders) { [lambda, lambda] }
17
+ let(:action) { instance.call }
18
+
19
+ before do
20
+ allow(instance).to receive(:graders).and_return(graders)
21
+ end
22
+
23
+ it { expect(action).to eq((0.5 * 0.5) ** weight) }
24
+
25
+ end
26
+
27
+ end
data/spec/graders/base_spec.rb ADDED
@@ -0,0 +1,14 @@
1
+ # frozen_string_literal: true
2
+
3
+ require 'spec_helper'
4
+
5
+ describe LinkThumbnailer::Graders::Base do
6
+
7
+ let(:description) { double('description', text: 'foo', node: node) }
8
+ let(:node) { double('node', text: 'foo') }
9
+ let(:instance) { described_class.new(description) }
10
+
11
+ it { expect(instance.send(:node)).to eq(description.node) }
12
+ it { expect(instance.send(:text)).to eq(description.text) }
13
+
14
+ end
data/spec/graders/html_attribute_spec.rb ADDED
@@ -0,0 +1,50 @@
1
+ # frozen_string_literal: true
2
+
3
+ require 'spec_helper'
4
+
5
+ describe LinkThumbnailer::Graders::HtmlAttribute do
6
+
7
+ let(:description) { double('description') }
8
+ let(:instance) { described_class.new(description, :class) }
9
+
10
+ describe '#call' do
11
+
12
+ let(:action) { instance.call }
13
+
14
+ context 'when current node does not match attribute' do
15
+
16
+ before do
17
+ allow(instance).to receive(:attribute?).and_return(false)
18
+ end
19
+
20
+ it { expect(action).to eq(1.0) }
21
+
22
+ end
23
+
24
+ context 'when current node has a negative attribute' do
25
+
26
+ before do
27
+ allow(instance).to receive(:attribute?).and_return(true)
28
+ allow(instance).to receive(:negative?).and_return(true)
29
+ allow(instance).to receive(:positive?).and_return(false)
30
+ end
31
+
32
+ it { expect(action).to eq(0.0) }
33
+
34
+ end
35
+
36
+ context 'when current node has a positive attribute' do
37
+
38
+ before do
39
+ allow(instance).to receive(:attribute?).and_return(true)
40
+ allow(instance).to receive(:negative?).and_return(false)
41
+ allow(instance).to receive(:positive?).and_return(true)
42
+ end
43
+
44
+ it { expect(action).to eq(1.0) }
45
+
46
+ end
47
+
48
+ end
49
+
50
+ end
data/spec/graders/length_spec.rb ADDED
@@ -0,0 +1,93 @@
1
+ # frozen_string_literal: true
2
+
3
+ require 'spec_helper'
4
+
5
+ describe LinkThumbnailer::Graders::Length do
6
+
7
+ let(:config) { double('config') }
8
+ let(:description) { double('description') }
9
+ let(:instance) { described_class.new(description) }
10
+
11
+ before do
12
+ allow(instance).to receive(:config).and_return(config)
13
+ end
14
+
15
+ describe '#call' do
16
+
17
+ let(:action) { instance.call }
18
+
19
+ context 'when text is too short' do
20
+
21
+ before do
22
+ allow(instance).to receive(:too_short?).and_return(true)
23
+ end
24
+
25
+ it { expect(action).to eq(0.0) }
26
+
27
+ end
28
+
29
+ context 'when text is not too short' do
30
+
31
+ before do
32
+ allow(instance).to receive(:too_short?).and_return(false)
33
+ allow(instance).to receive(:text).and_return(text)
34
+ end
35
+
36
+ context 'when text length is 120' do
37
+
38
+ let(:text) { 'f' * 120 }
39
+
40
+ it { expect(action).to eq(1.0) }
41
+
42
+ end
43
+
44
+ context 'when text length is 100' do
45
+
46
+ let(:text) { 'f' * 100 }
47
+
48
+ it { expect(action).to be < 1.0 }
49
+
50
+ end
51
+
52
+ context 'when text length is 60' do
53
+
54
+ let(:text) { 'f' * 60 }
55
+
56
+ it { expect(action).to be < 1.0 }
57
+
58
+ end
59
+
60
+ end
61
+
62
+ end
63
+
64
+ describe '#too_short?' do
65
+
66
+ let(:action) { instance.send(:too_short?) }
67
+ let(:config) { double }
68
+
69
+ before do
70
+ allow(instance).to receive(:config).and_return(config)
71
+ allow(config).to receive(:description_min_length).and_return(10)
72
+ allow(instance).to receive(:text).and_return(text)
73
+ end
74
+
75
+ context 'when true' do
76
+
77
+ let(:text) { 'f' * 9 }
78
+
79
+ it { expect(action).to be_truthy }
80
+
81
+ end
82
+
83
+ context 'when false' do
84
+
85
+ let(:text) { 'f' * 10 }
86
+
87
+ it { expect(action).to be_falsey }
88
+
89
+ end
90
+
91
+ end
92
+
93
+ end
data/spec/graders/link_density_spec.rb ADDED
@@ -0,0 +1,52 @@
1
+ # frozen_string_literal: true
2
+
3
+ require 'spec_helper'
4
+
5
+ describe LinkThumbnailer::Graders::LinkDensity do
6
+
7
+ let(:description) { double('description') }
8
+ let(:instance) { described_class.new(description) }
9
+
10
+ describe '#call' do
11
+
12
+ let(:action) { instance.call }
13
+
14
+ before do
15
+ allow(instance).to receive(:text).and_return(text)
16
+ allow(instance).to receive(:links).and_return(links)
17
+ end
18
+
19
+ context 'when text length is 0' do
20
+
21
+ let(:text) { '' }
22
+ let(:links) { [] }
23
+
24
+ it { expect(action).to eq(0.0) }
25
+
26
+ end
27
+
28
+ context 'when text length is > 0' do
29
+
30
+ let(:text) { 'foo' }
31
+
32
+ context 'and links is 0' do
33
+
34
+ let(:links) { [] }
35
+
36
+ it { expect(action).to eq(1.0) }
37
+
38
+ end
39
+
40
+ context 'and links is > 0' do
41
+
42
+ let(:links) { [1] }
43
+
44
+ it { expect(action).to be_within(0.001).of(0.666) }
45
+
46
+ end
47
+
48
+ end
49
+
50
+ end
51
+
52
+ end
data/spec/graders/position_spec.rb ADDED
@@ -0,0 +1,49 @@
1
+ # frozen_string_literal: true
2
+
3
+ require 'spec_helper'
4
+
5
+ describe LinkThumbnailer::Graders::Position do
6
+
7
+ let(:description) { double('description') }
8
+ let(:instance) { described_class.new(description) }
9
+
10
+ describe '#call' do
11
+
12
+ let(:action) { instance.call }
13
+
14
+ context 'when position is 0' do
15
+
16
+ before do
17
+ allow(description).to receive(:position).and_return(0)
18
+ allow(description).to receive(:candidates_number).and_return(1)
19
+ end
20
+
21
+ it { expect(action).to eq(1.0) }
22
+
23
+ end
24
+
25
+ context 'when position is 1 over 1 candidates' do
26
+
27
+ before do
28
+ allow(description).to receive(:position).and_return(1)
29
+ allow(description).to receive(:candidates_number).and_return(1)
30
+ end
31
+
32
+ it { expect(action).to eq(0.0) }
33
+
34
+ end
35
+
36
+ context 'when position is 1 over more than 1 candidates' do
37
+
38
+ before do
39
+ allow(description).to receive(:position).and_return(1)
40
+ allow(description).to receive(:candidates_number).and_return(2)
41
+ end
42
+
43
+ it { expect(action).to eq(0.5) }
44
+
45
+ end
46
+
47
+ end
48
+
49
+ end
data/spec/image_comparators/size_spec.rb ADDED
@@ -0,0 +1,58 @@
1
+ # frozen_string_literal: true
2
+
3
+ require 'spec_helper'
4
+
5
+ describe LinkThumbnailer::ImageComparators::Size do
6
+
7
+ let(:image) { double(size: [20, 20]) }
8
+ let(:instance) { described_class.new(image) }
9
+
10
+ describe '#call' do
11
+
12
+ let(:other) { double(size: other_size) }
13
+ let(:action) { instance.call(other) }
14
+
15
+ context 'when other has a better image' do
16
+
17
+ let(:other_size) { [10, 10] }
18
+
19
+ it { expect(action).to eq(-1) }
20
+
21
+ end
22
+
23
+ context 'when other has an identical image' do
24
+
25
+ let(:other_size) { [20, 20] }
26
+
27
+ it { expect(action).to eq(0) }
28
+
29
+ end
30
+
31
+ context 'when other has a weaker image' do
32
+
33
+ let(:other_size) { [30, 30] }
34
+
35
+ it { expect(action).to eq(1) }
36
+
37
+ end
38
+
39
+ context 'when other image size could not be computed' do
40
+
41
+ let(:other_size) { [] }
42
+
43
+ it { expect(action).to eq(-1) }
44
+
45
+ end
46
+
47
+ context 'when self image size could not be computed' do
48
+
49
+ let(:image) { double(size: []) }
50
+ let(:other_size) { [10, 10] }
51
+
52
+ it { expect(action).to eq(1) }
53
+
54
+ end
55
+
56
+ end
57
+
58
+ end