# updateFooterDates.pl
#
# Process a list of HTML files, checking their internal last
# updated META tag (NAME="date"). If the value of the date in
# the page footer is earlier, change it to the META date.
#
# Assumption: the META tag will precede the page footer. This
# is a safe assumption, since the META tag should be in the
# section and the footer should be in the .
# Note that the footer date pattern is very specific. See
# code for details.
#
# The date tag must have this format:
#
#
#
# The date in the META tag must be in ISO format, e.g. 2001-11-26
# is 26 November, 2001.
#
# The "last updated" line in the footer must have this format:
#
# Last updated dd month year
#
# e.g.,
Last updated 26 November 2001
. The date on
# this line can be either 1 or 2 digits.
#
# Input: a list of files to process.
#
# Mark L. Irons
# 18 July 2000
#
#--------------------------------------------------------------------
# Array of months
#
@months = ('January','February','March','April','May','June',
'July','August','September','October','November','December');
#
#--------------------------------------------------------------------
#
# Patterns to match.
#
# METADatePattern looks like ''
#
$METADatePattern = '';
#
# footerDatePattern looks like '
Last updated 17 July 2000
'
#
$footerDatePattern = '^(
Last updated )(\d\d? [A-Z][a-z]+ \d\d\d\d)(
)$';
#
#--------------------------------------------------------------------
# Loop over files, processing each.
#
while (<>) {
$filename = $_;
if (!open(HTMLFILE,$filename)) {
chop $filename;
warn "Can't open $filename, skipping: $!\n";
next;
}
$modifiedFlag = 0; # haven't changed file
$modifiedFile = ""; # text of modified file
$readableDate = "";
while () {
if (/$METADatePattern/) { # check for META date tag
$year = $1;
$month = $2;
$day = $3;
if (substr($day,0,1) eq "0") {
$day = substr($day,1,1);
}
$month = $months[$month-1];
$readableDate = "$day $month $year";
}
elsif (/$footerDatePattern/) {
if (($readableDate ne "") && ($2 ne $readableDate)) {
$_ = $1.$readableDate.$3."\n";
$modifiedFlag = 1;
}
}
$modifiedFile .= $_;
} # processing single file
close(HTMLFILE); # close the input file
if ($modifiedFlag) {
if (open(HTMLFILE,"> ".$filename)) {
print HTMLFILE $modifiedFile; # write the modified contents
close HTMLFILE; # and close it of course
print "Updated dates in $filename"; # print names of modified files
}
}
} # all files