| all D 0.474 | |
| out P 0.698 | |
| of P 0.970 | |
| wood ^ 0.633 | |
| facts N 0.906 | |
| u O 0.997 | |
| can V 1.000 | |
| build V 1.000 | |
| a D 0.998 |
| all D 0.323 | |
| out P 0.578 | |
| of P 0.955 | |
| wood ^ 0.584 | |
| facts N 0.912 | |
| u O 0.998 | |
| can V 0.999 | |
| build V 1.000 | |
| a D 0.998 |
| http://opinionator.blogs.nytimes.com/2012/08/08/hear-all-ye-people-hearken-o-earth/ | |
| http://news.ycombinator.com/item?id=4362277 | |
| http://news.ycombinator.com/item?id=4365086 |
| 2009-01 19 | |
| 2009-02 20 | |
| 2009-03 48 | |
| 2009-04 100 | |
| 2009-05 275 | |
| 2009-06 292 | |
| 2009-07 494 | |
| 2009-08 259 | |
| 2009-09 207 | |
| 2009-10 65 |
| { | |
| "contributors": null, | |
| "coordinates": null, | |
| "created_at": "Tue Jul 03 00:35:49 +0000 2012", | |
| "entities": { | |
| "hashtags": [], | |
| "urls": [], | |
| "user_mentions": [] | |
| }, | |
| "favorited": false, |
| 2009-06-01 4507 1 [470275] | |
| 2009-06-08 4507 1 [422879] | |
| 2009-06-22 4507 1 [257976] | |
| 2009-07-06 4507 1 [69444] | |
| 2009-07-13 4507 4 [16042,237457,457813,61273] | |
| 2009-07-20 4507 6 [422879,358078,82438,34891,47316,97749] | |
| 2009-07-27 4507 2 [423154,477645] | |
| 2009-08-10 4507 6 [356596,316917,99418,247707,230452,3538] | |
| 2009-08-17 4507 7 [82438,263332,23135,35494,94656,122471,272590] | |
| 2009-08-24 4507 7 [157430,338463,426119,157430,405565,309448,338463] |
| # handle the wikipedia dump format | |
| module WikiDump | |
| def self.yield_page_strings(stream) | |
| buf = "" | |
| stream.each do |line| | |
| if line =~ /^\s* <page> \s*$/x | |
| buf = "" |
| #!/usr/bin/env ruby | |
| # | |
| # Data structures and proccessing of documents to be indexed, e.g. wikipedia | |
| # pages. ok, everything is wikipedia-specific. :-) | |
| # | |
| # This file can be executed for various sorts of testing (see bottom) | |
| require File.dirname(__FILE__)+'/common' |
| #!/usr/bin/env python | |
| """ | |
| Convert STDIN to UTF-8 | |
| based on character encoding detection | |
| """ | |
| import sys, json, itertools | |
| from chardet.universaldetector import UniversalDetector | |
| detector = UniversalDetector() |
by Brendan O'Connor (http://brenocon.com)
I got all of ocropus to compile on Mac OSX 10.6, though I haven't tested it much yet. This is the current version inside the ocropus hg repository, so approximately version 0.5, with iulib perhaps 0.4ish.
See ocroinst.osx -- the first file in "everything_besides_iulib.diff" -- for line-by-line instructions; the script may even just run. We're assuming Homebrew and pip (see the comments).