#!/usr/bin/env python
# -*- Mode: python -*-

#    Copyright (C) 2001 Artifex Software Inc.
#
# This software is provided AS-IS with no warranty, either express or
# implied.
#
# This software is distributed under license and may not be copied,
# modified or distributed except as expressly authorized under the terms
# of the license contained in the file LICENSE in this distribution.
#
# For more information about licensing, please refer to
# http://www.ghostscript.com/licensing/. For information on
# commercial licensing, go to http://www.artifex.com/licensing/ or
# contact Artifex Software, Inc., 101 Lucas Valley Road #110,
# San Rafael, CA  94903, U.S.A., +1(415)492-9861.

# $Id: testdiff,v 1.2.2.2 2004/05/12 04:06:00 giles Exp $

#
# testdiff <start date> [<end date>]
#
# this script provides the difference between two sets of regression results.
# if end date is omitted, the current date will be used.
#
# dates should be specified as YYYYMMDD

import sys
import re
import time
import anydbm
import gsconf

def usage():
    print "testdiff <start date> [<end date>]"
    print
    print "dates should be specified in YYYYMMDD format. if the end date"
    print "is omitted, the current date will be used."
    print
    sys.exit(1)

def sort_list(a, b):
    if a[0] < b[0]:
        return 1
    elif a[0] > b[0]:
        return -1

    if a[1] < b[1]:
        return 1
    elif a[1] > b[1]:
        return -1

    if a[2] < b[2]:
        return 1
    elif a[2] > b[2]:
        return -1

    if a[3] < b[3]:
        return 1
    elif a[3] > b[3]:
        return -1

    if a[4] < b[4]:
        return 1
    elif a[4] > b[4]:
        return -1

    return 0
                    

normal_re = re.compile("^(.*?)\.(p[bgpk]mraw)\.(\d+)\.(\d+)$")
pdfwrite_re = re.compile("^(.*?)\.(ps|pdf)\.pdf\.(p[bgpk]mraw)\.(\d+)\.(\d+)$")

start_date = ''
end_date = ''

# process arguments

if len(sys.argv) == 2:
    start_date = sys.argv[1]
elif len(sys.argv) == 3:
    start_date = sys.argv[1]
    end_date = sys.argv[2]
else:
    usage()

if not end_date:
    end_date = time.strftime("%Y%m%d", time.localtime(time.time()))

# check if databases for both dates exist

start_dbname = gsconf.dailydir + start_date + '.db'
start_db = None
end_dbname = gsconf.dailydir + end_date + '.db'
end_db = None
baseline_db = None

try:
    start_db = anydbm.open(start_dbname, 'r')
    end_db = anydbm.open(end_dbname, 'r')
    baseline_db = anydbm.open(gsconf.testdatadb, 'r')
except:
    pass

if not start_db:
    print "Test results for %s were not found." % (start_date,)
    sys.exit(1)
if not end_db:
    print "Test results for %s were not found." % (end_date,)
    sys.exit(1)
if not baseline_db:
    print "Baseline database could not be opened."
    sys.exit(1)
    
# now find the differences, ignoring updated baselines

keys = []
diffs = []

# get a list of all keys
for k in start_db.keys():
    if k not in keys:
        keys.append(k)
for k in end_db.keys():
    if k not in keys:
        keys.append(k)

for k in keys:
    if k not in start_db.keys():
        if k in baseline_db.keys() and end_db[k] != baseline_db[k]:
            diffs.append(k)
    elif k not in end_db.keys():
        diffs.append(k)
    elif start_db[k] != end_db[k] and (k not in baseline_db.keys() or
                                       end_db[k] != baseline_db[k]):
        diffs.append(k)

list = []

for d in diffs:
    type = ''
    filename = ''
    device = ''
    dpi = 0
    banded = 0
    
    m = pdfwrite_re.search(d)
    if m:
        type = 'pdfwrite'
        filename = m.group(1) + "." + m.group(2)
        device = m.group(3)
        dpi = int(m.group(4))
        banded = int(m.group(5))
    else:
        m = normal_re.search(d)
        if m:
            type = 'normal'
            filename = m.group(1)
            device = m.group(2)
            dpi = int(m.group(3))
            banded = int(m.group(4))

    if not type:
        print "WARNING: Got a key that didn't match expressions!"
        continue

    bandstr = "noband"
    if banded:
        bandstr = "banded"

    list.append((type, filename, device, dpi, bandstr))

    
list.sort()
for l in list:
    print "%s %s (%s/%d/%s)" % (l[0], l[1], l[2], l[3], l[4])
