| /** | |
| * Split DDMMSS or DD coordinate pair string into an array | |
| * | |
| * @param string $point A string purported to be a coordinate | |
| * @return array(latitude, longitude) in DD | |
| */ | |
| function make_coordinates($point) | |
| { | |
| $loc = preg_replace(array('/[\p{Z}\s]/u', '/[^\d\s,;.\-NSEWO°ºdms\'"]/i'), array(' ', ''), $point); | |
| if (preg_match('/[NSEWO]/', $loc) != 0) { |
| <html> | |
| <head> | |
| <style type="text/css"> | |
| #map{width:600px;height:400px;} | |
| #freehand { | |
| margin-left:-5px; | |
| margin-top:5px; | |
| } | |
| #freehand .button{ | |
| direction: ltr; |
| <?php | |
| //MapServer version 7.0.4 | |
| $map = ms_newMapObjFromString("MAP END"); | |
| $map->set("units", MS_DD); | |
| $map->setProjection("proj=longlat,ellps=WGS84,datum=WGS84,no_defs", true); | |
| $map->setExtent(-180, -90, 180, 90); | |
| $map->setSize(100,100); | |
| $map->setProjection("proj=robin,lon_0=0,x_0=0,y_0=0,ellps=WGS84,datum=WGS84,units=m,over,no_defs", true); |
| require 'parallel' | |
| require 'rtesseract' | |
| require 'mini_magick' | |
| source = "/MyDirectory/my.pdf" | |
| doc = {} | |
| pdf = MiniMagick::Image.open(source) | |
| Parallel.map(pdf.pages.each_with_index, in_threads: 8) do |page, idx| | |
| tmpfile = Tempfile.new(['', '.tif']) | |
| MiniMagick::Tool::Convert.new do |convert| |
| species | latitude | longitude | |
|---|---|---|---|
| Pardosa moesta | 45.755 | -110.12 | |
| Pardosa fuscula | 47.9 | -112 | |
| Pardosa moesta | 55.6 | -101 | |
| Pardosa xerampelina | 48.9 | -103.55 | |
| Pardosa xerampelina | 43.02 | -105.9 | |
| Trochosa terricola | 45.5 | -103.8 | |
| Trochosa terricola | 46 | -100 | |
| Trochosa terricola | 47.7 | -110.9 | |
| Pardosa moesta | 48 | -109 |
| 910 | |
| 1984 | |
| DZRJ | |
| - | |
| () | |
| (UB 19881) | |
| (UB 19882) | |
| (UFG 13985) | |
| (UFG 13986) | |
| * |
| NULL,"0000-0002-7101-9767","Roderic","Page" | |
| NULL,"0000-0001-9008-0611","Stylianos","Chatzimanolis" | |
| NULL,"0000-0002-6752-9721","Tod","Robbins" | |
| NULL,"0000-0002-7053-8557","Paul","Sokoloff" | |
| NULL,"0000-0001-7618-5230","David Peter","Shorthouse" | |
| NULL,"0000-0003-1366-145X","Timothy","Dickinson" | |
| NULL,"0000-0003-0768-1286","Richard","Pyle" | |
| NULL,"0000-0002-4124-2175","Peter","Hovenkamp" | |
| NULL,"0000-0001-6065-0812","Frank-Thorsten","Krell" | |
| NULL,"0000-0002-1314-755X","Neal","Evenhuis" |
This is a quick test of a modified version of the Bloodhound spark script to check it runs on the GBIF Cloudera cluster (CDH 5.16.2).
From the gateway, grab the file from HDFS (skip HTTP for speed), unzip (15-20 mins) and upload to HDFS:
hdfs dfs -getmerge /occurrence-download/prod-downloads/0002504-181003121212138.zip /mnt/auto/misc/bloodhound/data.zip
unzip /mnt/auto/misc/bloodhound/data.zip -d /mnt/auto/misc/bloodhound/data
hdfs dfs -rm /tmp/verbatim.txt
hdfs dfs -rm /tmp/occurrence.txt
| {:user_id=>11771, :name=>"Cyrus Pringle", :orphaned=>716}, | |
| {:user_id=>14743, :name=>"Gerdt Guenther Hatschbach", :orphaned=>594}, | |
| {:user_id=>191, :name=>"Volker Framenau", :orphaned=>586}, | |
| {:user_id=>35074, :name=>"Martti Rautanen", :orphaned=>454}, | |
| {:user_id=>10182, :name=>"Georg August Zenker", :orphaned=>381}, | |
| {:user_id=>12169, :name=>"Paul Sintenis", :orphaned=>349}, | |
| {:user_id=>9829, :name=>"Joseph Friedrich Nicolaus Bornmüller", :orphaned=>302}, | |
| {:user_id=>10487, :name=>"José Arechavaleta", :orphaned=>250}, | |
| {:user_id=>11937, :name=>"Theodor Kotschy", :orphaned=>233}, | |
| {:user_id=>11853, :name=>"Ynes Mexia", :orphaned=>150}, |
| GBIF URL,recordedBy,eventDate,year,country,countryCode,GBIF Dataset | |
| https://gbif.org/occurrence/2433942,"Mrs. C. Pease, Miss E. Butler",,1903,Jamaica,JM,https://gbif.org/dataset/40d2de00-0c6e-11dd-84d2-b8a03c50a862 | |
| https://gbif.org/occurrence/29404620,U.Mizushima (Mrs.),1954-09-06T01:00Z,1954,,JP,https://gbif.org/dataset/8346c3a8-f762-11e1-a439-00145eb45e9a | |
| https://gbif.org/occurrence/29408002,U.Mizushima (Mrs.),1954-09-19T01:00Z,1954,,JP,https://gbif.org/dataset/8346c3a8-f762-11e1-a439-00145eb45e9a | |
| https://gbif.org/occurrence/29426346,U.Mizushima (Mrs.),1952-08-01T01:00Z,1952,,JP,https://gbif.org/dataset/8346c3a8-f762-11e1-a439-00145eb45e9a | |
| https://gbif.org/occurrence/29429161,U.Mizushima (Mrs.),1954-09-29T01:00Z,1954,,JP,https://gbif.org/dataset/8346c3a8-f762-11e1-a439-00145eb45e9a | |
| https://gbif.org/occurrence/29451087,U.Mizushima (Mrs.),1955-03-04T01:00Z,1955,,JP,https://gbif.org/dataset/8346c3a8-f762-11e1-a439-00145eb45e9a | |
| https://gbif.org/occurrence/29451907,Mrs. Fay A. Mac Fadden,1926-08-16T01:00Z,1926,, |