gecko-dev/webtools/tinderbox/scrape.pl

98 lines
2.4 KiB
Perl
Raw Normal View History

2001-11-02 05:22:00 +00:00
#! /usr/bonsaitools/bin/perl
# -*- Mode: perl; indent-tabs-mode: nil -*-
#
# The contents of this file are subject to the Mozilla Public License
# Version 1.1 (the "License"); you may not use this file except in
# compliance with the License. You may obtain a copy of the License at
# http://www.mozilla.org/MPL/
#
# Software distributed under the License is distributed on an "AS IS"
# basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
# License for the specific language governing rights and limitations
# under the License.
#
# The Original Code is Tinderbox
#
# The Initial Developer of the Original Code is Netscape Communications
# Corporation. Portions created by Netscape are Copyright (C) 1999
# Netscape Communications Corporation. All Rights Reserved.
#
# Contributor(s): Chris McAfee <mcafee@netscape.com>
#
# scrape.pl - Process log-scraped data into scrape.dat
# Write data to $tree/scrape.dat in the following format,
#
# <logfilename>|blurb1|blurb2|blurb3 ...
#
sub usage {
warn "./scrape.pl <tree> <logfile>";
}
use FileHandle;
# This is for gunzip (Should add a configure script to handle this).
$ENV{PATH} .= ":/usr/local/bin";
unless ($#ARGV == 1) {
&usage;
die "Error: Wrong number of arguments\n";
}
($tree, $logfile) = @ARGV;
die "Error: No tree named $tree" unless -r "$tree/treedata.pl";
require "$tree/treedata.pl";
# Seach the build log for the scrape data
#
2001-11-02 09:37:35 +00:00
$fh = new FileHandle "gunzip -c $tree/$logfile |"
2001-11-02 05:22:00 +00:00
or die "Unable to open $tree/$logfile\n";
@scrape_data = find_scrape_data($fh);
2001-11-02 09:37:35 +00:00
2001-11-02 05:22:00 +00:00
$fh->close;
die "No scrape data found in log.\n" unless @scrape_data;
# Save the scrape data to 'scrape.dat'
#
open SCRAPE, ">>$tree/scrape.dat" or die "Unable to open $tree/scrape.dat";
print SCRAPE "$logfile|".join('|', @scrape_data)."\n";
close SCRAPE;
2001-11-02 09:37:35 +00:00
#print "scrape_data = ";
#my $i;
#foreach $i (@scrape_data) {
# print "$i ";
#}
#print "\n";
2001-11-02 05:22:00 +00:00
# end of main
#============================================================
sub find_scrape_data {
my ($fh) = $_[0];
local $_;
2001-11-02 09:37:35 +00:00
my @rv;
my @line;
2001-11-02 05:22:00 +00:00
while (<$fh>) {
if (/TinderboxPrint:/) {
2001-11-02 05:22:00 +00:00
# Line format:
# TinderboxPrint:<general html>
# Strip off the TinderboxPrint: part of the line
2001-11-02 05:22:00 +00:00
chomp;
s/.*TinderboxPrint://;
2002-12-27 10:21:19 +00:00
# No longer use ; to create separate lines.
#@line = split(';', $_);
2002-12-27 10:21:19 +00:00
$line[0] = $_;
push(@rv, @line);
2001-11-02 05:22:00 +00:00
}
}
2001-11-02 09:37:35 +00:00
return @rv;
2001-11-02 05:22:00 +00:00
}