# Create an index of plants from Tucson Mountains plant list found at:
#  http://eebweb.arizona.edu/herb/TUCSONS/tucsons.html 
# Example input:
#  <p><a name="A"></a><b>Acanthaceae Acanthus Family</b> </p>
#  <p><b><i>*Justicia californica</i></b> (Benth.) D. Gibson. [Beloperone
#  californica Benth.]. Chuparosa. <br>
#  Local subshrub; common along north slope of Safford Peak; 790 &amp; 885
#  m (2600 &amp; 2900 feet); flowers red &amp; orange, March &amp; April (November).
#  </p>
# Example output:
#  Janusia gracilis Gray. Desert vine. Widespread woody vine f=Malpighiaceae Malpighia 
#  Justicia californica f=Acanthaceae Acanthus 
#  Kallstroemia californica (Wats.) Vail. Little summer poppy, f=Zygophyllaceae Caltrop 
# Example invocation:
#  awk -f tucsonsplantsindex.awk tucsons*.html | sort > tucsonsplantsindex.txt
# Courtesy of: jendon
# Handy awk intro: http://www-106.ibm.com/developerworks/library/l-awk1.html

BEGIN                         {FS=">"}
/<p><a name=.*Family/         {
                              family = $5
                              sub("</b","",family)
                              sub("Family","",family)
                              next
                              }
/<p><b>.*Family<\/b>.*<\/p>/  { 
                              family = $3
                              sub("</b","",family)
                              sub("Family","",family)
                              next
                              }
/<b>.*Family<\/b>/            { 
                              family = $2
                              sub("</b","",family)
                              sub("Family","",family)
                              next
                              }
/<p><b><i>.*<\/i><\/b>/       {
                              plant = $4
                              sub("</i","",plant)
                              sub("*","",plant)
                              sub("+","",plant)
                              print plant " f=" family 
                              next
                              }
/<li>/                        {
                              plant = $2
                              sub("*","",plant)
                              sub("+","",plant)
                              print plant " f=" family 
                              next
                              }
END                           {}