#####################################################################
# SCRIPT: SS_WebToText.txt
#
# This script reads web page files .html and writes corresponding plain text
# versions into files .txt in the same directory. It does this for
# all .html pages within a specified directory. The plain text versions
# of web pages, thus created, can then be used for spell-checking, review by
# legal department, inclusion into legal documents, inclusion into
# requirements/specifications documents, keeping the page lengths within limits, or other
# purposes. The script can handle a large number (including thousands)
# of web pages.
#
# Download this script into directory C:/Scripts to a file named sS_WebToText.txt
#
# Let's say you have all your web pages in a directory C:/myproject.
# In that case, invoke biterScripting Interactive and type the following
# on the command line.
#
#    script "C:/Scripts/SS_WebToText.txt" dir("C:/myproject") files("*.html")
#
# The above needs to be entered exactly as shown here. The script will execute
# and create respective .txt files. For example, if the web page is
# C:/myproject/disclaimer/newcustomers.html, the corresponding text version
# will be in file C:/myproject/disclaimer/newcustomers.txt .
#
# If the number of web pages is really large, or if the web page contents are
# huge, the script, depending on the speed of your computer, may take some time
# to complete execution. The script will execute in the background, so you can
# continue to use your computer for other purposes while the script is running.
#
# The script does not change the original (input) web pages.
#
# If you don't have biterscripting, you can download it from biterScripting.com .
#
#####################################################################

var str files	# patterns for file names
var str dir	# dir where entire project is

# Collect a list of files
var str fileList
find -rn $files $dir > $fileList

# We will collect the text version into the following variable
var str text_version

# Process files one by one
while ( $fileList <> "")
do

  # Get the next file
  var str file
  lex "1" $fileList > $file

  # Use script SS_WebPageToText to convert the contents of this file into plain text.
  script SS_WebPageToText.txt page($file) > $text_version

  # Get the file name without the ending .html, etc.
  stex "[^.^l" $file > null

  # Add .txt extension to file name.
  set $file = $file + ".txt"

  # Write the modified content to the .txt file.
  echo $text_version > { echo $file }

  done # end of do after while ( $fileList <> "")

# All text version are now available in corresponding .txt files in the respective directories.