Thursday, May 06 2004

~/lib/xsl/jpegrdf/prepare.sh

#!/bin/sh

# currently requires the saxon:distinct()
# function- I gather the xsltsl libraries
# define similar hooks but I haven't tested
# them yet

# I know this isn't how you're supposed to
# load java thingies : me.the.java.way.can.Bite()

EXEC_SAXON='javavm -jar /usr/local/share/java/classes/saxon.jar'

# XSL_EXPAND inherits : 

# /home/asc/lib/xsl/rdf/expand-resources.xsl
# base class/framework for expanding resources

# /home/asc/lib/xsl/rdf/expand-wordnet.xsl
# the rdf wordnet output is especially verbose
# so we perform some additional hoop-jumping

# /home/asc/lib/xsl/rdf/expand-asc-knows.xsl
# glue to expand x-urn:aaronstraupcope:* resources

XSL_PRUNE='/home/asc/lib/xsl/jpegrdf/prune-exif.xsl'
XSL_EXPAND='/home/asc/lib/xsl/jpegrdf/expand-resources.xsl'

# dump.rdf is the output created by 
# jpegrdf -s ~/photos/*/*/*/*.jpg

PHOTOS='/home/asc/photos'
DUMP=${PHOTOS}/dump.rdf
FINAL=${PHOTOS}/final.rdf

# see below

TMP1=${PHOTOS}/tmp1.rdf
TMP2=${PHOTOS}/tmp2.rdf
TMP3=${PHOTOS}/tmp3.rdf

# first remove all the exif properties
# except dateTime; further munge dateTime
# into a resource

${EXEC_SAXON} ${DUMP} ${XSL_PRUNE} > ${TMP1}

# do a first pass and try to expand
# all the foreign resources in the
# document - at a minimum this will
# expand x-urn:asc:knows:where# / vcard
# locality resources. think :

# <rdf:Description rdf:about = "some-picture.jpg">
#  <dc:coverage rdf:resource = "x-urn:asc:knows:where#montreal" />
# </rdf:Description>

# <rdf:Description rdf:about = "x-urn:asc:knows:where#montreal">
#  <rdf:type rdf:resource = "http://www.w3.org/2001/vcard-rdf/3.0#Locality" />
#  <dc:title>Montréal</dc:title>
#  <vcard:Region rdf:resource = "x-urn:asc:knows:where#qc" />
# </rdf:Description>

# <!-- and so on -->

${EXEC_SAXON} ${TMP1} ${XSL_EXPAND} > ${TMP2}

# this is a pretty clunky approach but
# it works as a proof of concept: do another
# two passes over the output in order to
# expand vcard locality/region and then
# region/country resources.

# a better way to do this would be to create
# separate stylesheets to expand only regions
# or countries since there may be other second
# or third level resources that you don't care
# about expanding.

# at a minimum there are hooks to prevent the
# same resource from being expanded twice in 
# the output document

${EXEC_SAXON} ${TMP2} ${XSL_EXPAND} > ${TMP3}
${EXEC_SAXON} ${TMP3} ${XSL_EXPAND} > ${FINAL}

# clean up

rm ${TMP1}
rm ${TMP2}
rm ${TMP3}
     

meta