Created
January 1, 2013 16:49
-
-
Save carsonmcdonald/4428542 to your computer and use it in GitHub Desktop.
CouchDB map function used to count #code2012 entires.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
map: function (doc) | |
{ | |
if(doc.text.indexOf("RT ") != -1 || doc.text.indexOf("RT:") != -1 || | |
doc.text.indexOf("rt ") != -1 || doc.text.indexOf("rt:") != -1) | |
{ | |
return; | |
} | |
function pre_replacements(obj) | |
{ | |
return obj.toLowerCase() | |
.replace('objective c','objective-c').replace('objc','objective-c') | |
.replace('obj-c','objective-c').replace('objectivec','objective-c') | |
.replace(' js','javascript').replace('asm','assembler') | |
.replace('assembly','assembler').replace('common lisp','lisp') | |
.replace('x86 assembly','assembler').replace('x86asm','assembler') | |
.replace(' script','sh').replace('nodejs', 'node.js') | |
.replace('csharp','c#').replace('mysql','sql') | |
.replace('visual basic','vb').replace('x86 assembler','assembler') | |
.replace('arm asm','assembler').replace('arm assembly','assembler') | |
.replace('x86 asm','assembler').replace('as3','actionscript') | |
.replace('css3','css').replace('html5','html') | |
.replace('emacs','elisp').replace('turbo pascal', 'pascal') | |
.replace('small talk','smalltalk').replace('javascripton','javascript') | |
.replace('c++11','c++'); | |
} | |
function post_replacements(obj) | |
{ | |
return obj.toLowerCase() | |
.replace('"' , '').replace('&' , '').replace('<' , '') | |
.replace('>' , '').replace('(' , '').replace(')' , '') | |
.replace(/^-$/ , '').replace('..' , '').replace(':' , '') | |
.replace(/^--$/, '').replace(/\.$/, '').replace(/^#/, '') | |
.replace(/^js$/, 'javascript').replace('perlease','perl') | |
.replace(/^go$/, 'golang').replace(/^node$/, 'node.js') | |
.replace(/^bat$/, 'batch').replace(/^x86$/, 'assembler') | |
.replace(/^arm$/, 'assembler').replace(/^pl$/,'perl') | |
.replace(/^sh$/, 'shell').replace(/^coffescript$/, 'coffeescript'); | |
} | |
function contains(a, obj) | |
{ | |
var i = a.length; | |
while (i--) | |
{ | |
if (a[i] === obj.toLowerCase()) | |
{ | |
return true; | |
} | |
} | |
return false; | |
} | |
skip_terms = [ | |
'#code2012', 'code2012', 'data', 'pure', 'and', 'the', 'year', 'you', 'program', 'programming', | |
'it', '2012', '2013', '#code2013', 'code2013', 'this', 'that', "that's", 'tools', "i'm", "it's", | |
'i', 'of', 'older', 'twitter.com', 'treat', 'toyed', 'top', 'old', 'not', "i've", 'languages', | |
'language', 'need', 'have', 'hope', 'hey', 'my', 'in', 'for', 'src', 'must', 'a', 'an', | |
'around', 'as', 'at', 'be', 'been', 'bit', 'bit.ly', 'but', 'can', 'coding', 'developers', 'did', | |
'doubts', 'focused', 'gist.git', 'http', 'just', 'know', 'last', 'learning', 'look', 'lot', 'lots', | |
'mention', 'mentioned', 'mostly', 'nothing', 'order', 'really', 'rt', 'sometimes', 'statuses', | |
'terribly', 'used', 'weird', 'what', 'whoever', 'with', 'wow', 'wrong', 'to', 'code', 'more', | |
'www.ioncannon.net', 'little', 'is', '&', 'was', 'processing', 'projects', 'project', 'wrote', | |
'forgot', 'count', 'on', 'oh', 'time', 'some', 'me', 'too', 'all', 'also', 'think', 'past', '', | |
'my', 'satisfy', 'mining', 'gods:', 'the', '@deadprogram', 'using', 't.co', 'about', 'next', 'so', | |
'or', 'list', 'much', 'year?', 'tweet', 'do', 'no', 'by', 'work', 'tiny', 'course', 'very', 'from', | |
'his', 'then', 'mainly', 'now', 'will', 'others', 'here', '2', '3', 'various', 'amount', 'one', | |
'should', 'write', '+', 'few', 'stats', 'y', 'de', 'good', 'yes', 'are', 'how', 'fun', 'than', | |
'other', 'cc', 'add', 'should', 'only', 'use', 'first', 'new', 'touch', 'if', 'any', 'like', "you've", | |
'most', 'maybe', 'production', 'maybe', 'learned', '6502', 'out', 'even', 'trying', 'into', 'does', | |
'stuff', 'same', 'started', 'que', 'el', 'probably', 'played', 'play', 'please', 'coded', 'remember', | |
'would', 'still', "don't", 'feel', 'had', 'many', 'has', 'hoping', 'something', 'up', 'ok', ';', | |
'“@deadprogram', 'enough', 'read', 'hopefully', 'home', 'quite', 'en', 'there', 'people', 'lines', | |
'written', 'count?', 'bits', '=', '?', "didn't", 'over', 'thanks', 'want', 'plus', 'pretty', '-', | |
'well', 'et', 'langs', 'were', '@humancoders', 'through', 'tweets', 'end', 'learn', 'common', | |
'guess', '5', 'real', 'see', 'writing', 'descending', 'looking', 'standard', '@marcocantu', | |
'interesting', 'friends', 'encouraging', 'things', 'programmed', 'code2012"', 'ones', 'those', | |
'results', 'least' | |
]; | |
var langs = []; | |
var st = pre_replacements(doc.text).split(/,|\s|\//g); | |
for(var i=0; i<st.length; i++) | |
{ | |
var cs = post_replacements(st[i]); | |
if(!contains(skip_terms, cs) && !contains(langs, cs)) | |
{ | |
langs.push(cs); | |
} | |
} | |
emit(doc._id, { created: doc.created_at, text: doc.text, languages: langs }); | |
} | |
}, | |
function (err, res) | |
{ | |
if (err) console.log(err); | |
var langs = {}; | |
res.forEach(function(val, index, arr) | |
{ | |
index.languages.forEach(function(valb, indexb, arrb) | |
{ | |
if(!langs[valb]) | |
{ | |
langs[valb] = 0; | |
} | |
langs[valb]++; | |
}); | |
}); | |
var out = []; | |
for(var lang in langs) | |
{ | |
if(langs[lang] > 8) | |
out.push({language: lang, value: langs[lang]}); | |
} | |
console.log(JSON.stringify(out)); | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment