Experimenting with the ORCID public data file: counting the number of different locales, and plotting the result

orcidlocales.R

############################################################################
#
# Plotting the locale value from the ORCID Public Data File 
# https://orcid.org/content/orcid-public-data-file
#
# Tuija Sonkkila 12.11.2013
#
############################################################################

library(ggplot2)
library(scales)

orcids <- read.table(file = "orcidlocalesAll.csv",
                     header = FALSE,
                     col.names = c("locale"),
                     colClasses = c("character"),
                     stringsAsFactors = FALSE)

orc <- within(orcids,
              locale <- factor(locale,
                               levels = names(sort(table(locale),
                                                   decreasing = TRUE))))

png("orcidlocales.png", width = 1024, height = 768, res = 72)

ggplot(orc, aes(x = locale, fill = locale) ) +  
  geom_bar() + 
  scale_fill_brewer(palette = "Set2") + 
  scale_y_continuous(labels = comma, 
                     breaks = c(1000, 10000, 100000, 200000, 300000))

dev.off()

# https://www.dropbox.com/s/hq3wfhayb1nd8wi/orcidlocales.png

orcidlocales.xsl

<?xml version="1.0"?>
<xsl:stylesheet 
    xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema"
    xmlns:o="http://www.orcid.org/ns/orcid"
    version="2.0">

<! -- 

     Pulling out the locale value from the ORCID Public Data File 
     https://orcid.org/content/orcid-public-data-file

     Run with: java -jar ~/saxon9he.jar -it:main -xsl:orcidlocales.xsl -o:orcidlocales.csv
-->

 <xsl:output method="text" indent="yes"/>

 <xsl:template match="/" name="main">
   <!-- 
       In theory like this below, in one shot, but in practice I split the XML files to 8 directories (50000 files each), 
       run this XSL against each of them in return and finally, cat all output files together into orcidlocalesAll.csv
   -->
   <xsl:apply-templates select="collection('/l/xml?select=*.xml')/o:orcid-message/o:orcid-profile/o:orcid-preferences"/>
 </xsl:template>

 <xsl:template match="o:orcid-preferences">
   <xsl:value-of select="o:locale"/><xsl:text>
</xsl:text>
 </xsl:template>

</xsl:stylesheet>