#!/usr/bin/env python
# Import MS Project XML File

# Copyright 2006 by Brian C. Christensen

#    This file is part of GanttPV.
#
#    GanttPV is free software; you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation; either version 2 of the License, or
#    (at your option) any later version.
#
#    GanttPV is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.
#
#    You should have received a copy of the GNU General Public License
#    along with GanttPV; if not, write to the Free Software
#    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

# 060529 - started work on this script
# 060601 - successful import of task, dependency, resoure, & assignment data from xml file
# 060602 - keeps task hierarchy
# 060603 - uses the first MS Project calendar for the normal workweek
#           added task and assignment effort (when not equal defaults)
# 060604 - update to logic that eliminates redundant assignment and task effort hours values

debug = 1

import re
from xml.dom.minidom import parse, parseString
# from xml import xpath

def getText(nodelist):
    rc = ""
    for node in nodelist:
        if node.nodeType == node.TEXT_NODE:
            rc = rc + node.data
    return rc

def Import(path):

    xref = {}  # covert between MS Project IDs and GanttPV IDs
    parents = {} # get ID of MS Project parent task

    def GetID(UID, table):
        '''UID is from MS Project
        table is the GanttPV table name
        returns GanttPV UI of record
        '''
        key = (UID, table)
        if not key in xref:
            change = { 'Table': table }
            id = Data.Update(change)['ID']
            xref[key] = id
        return xref[key]
    
    dom1 = parse(path) # parse an XML file by name

    # datasource = open('c:\\temp\\mydata.xml')
    # dom2 = parse(datasource)   # parse an open file

    # dom3 = parseString('<myxml>Some data<empty/> some more data</myxml>')

    # one at top level
    n = dom1.getElementsByTagName("Name")
    if n:
        name = getText(n[0].childNodes)[:-4]
        print "Name: %s" % name
    else:
        name = None

    s = dom1.getElementsByTagName("StartDate")
    if s:
        d = getText(s[0].childNodes)
        startdate, pstarttime = d.split("T")
        print "Start Date is: %s" % startdate
    else:
        startdate = None

    change = { 'Table': 'Project', 'Name': name, 'StartDate': startdate,
               'Imported': 'MS Project'}
    projectid = Data.Update(change)['ID']

    # load in calendar #1
    workweek = [0] * 7  # count hours per day from calendary
    dowx = [0, 6, 0, 1, 2, 3, 4, 5]  # convert MS Project day to GanttPV day
    c = dom1.getElementsByTagName("Calendars")
    if c:
        callist = c[0].getElementsByTagName("Calendar")
    else:
        callist = []

    for cal in callist:

        uid = cal.getElementsByTagName("UID")
        if uid:  # if any names found
            tuid = getText(uid[0].childNodes)
            print "Calendar UID: %s" % uid
            if tuid != '1': continue  # only look at first calendar?
        else:
            continue  # must always be present

        d = cal.getElementsByTagName("WeekDays")
        if d:
            daylist = d[0].getElementsByTagName("WeekDay")
        else:
            daylist = []

        for day in daylist:

            daytype = day.getElementsByTagName("DayType")
            if daytype:  # if any names found
                daytype = int(getText(daytype[0].childNodes))
                print "Day Type: %d" % daytype
            else:
                daytype = 0

            w = day.getElementsByTagName("WorkingTimes")
            if w:
                worklist = w[0].getElementsByTagName("WorkingTime")
            else:
                worklist = []

            for work in worklist:

                fromtime = work.getElementsByTagName("FromTime")
                if fromtime:  # if found
                    fromtime = getText(fromtime[0].childNodes)
                else:
                    fromtime = None

                totime = work.getElementsByTagName("ToTime")
                if totime:  # if found
                    totime = getText(totime[0].childNodes)
                else:
                    totime = None

                if fromtime and totime:
                    hours = int(totime[:2]) - int(fromtime[:2])
                    print "hours added for %d = %d" % (daytype-1, hours)
                    workweek[dowx[daytype]] += hours

    # hopefully this will never be zeros
    change = {'Table': 'OtherData', 'ID': 1, 'WeekHours': workweek}
    Data.Update(change)
    
    # load in each of the tasks
    t = dom1.getElementsByTagName("Tasks")
    if t:
        tasklist = t[0].getElementsByTagName("Task")
    else:
        tasklist = []

    for task in tasklist:

        uid = task.getElementsByTagName("UID")
        if uid:  # if any names found
            tuid = getText(uid[0].childNodes)
            print "UID: %s" % uid
            if tuid == '0': continue  # appears to be a dummy task
        else:
            continue  # must always be present

        onum = task.getElementsByTagName("OutlineNumber")
        if onum:  # if any names found
            onum = getText(onum[0].childNodes)
        else:
            onum = None

        # ignore tasks w/ outline level < 1
        # if level > 1 then parent has outline number w/ last part removed
        olev = task.getElementsByTagName("OutlineLevel")
        if olev:  # if any names found
            olev = getText(olev[0].childNodes)
        else:
            olev = None

        name = task.getElementsByTagName("Name")
        if name:  # if any names found
            tname = getText(name[0].childNodes)
            print "Name: %s" % tname
        else:
            tname = ""

        # Duration, DurationFormat, Work
        # PercentComplete, PercentWorkComplete
        duration = task.getElementsByTagName("Duration")
        if duration:  # if any names found
            d = getText(duration[0].childNodes)
            m = re.match(r"PT(\d*)H", d)  # ignore minutes and seconds
            hours = int(m.group(1))
            print "Raw Duration: %s" % d
            print "Duration: %d" % hours
        else:
            hours = None

        # Work -> effort
        # This should be ommitted if it matches "everyone full time"
        work = task.getElementsByTagName("Work")
        if work:  # if any names found
            w = getText(work[0].childNodes)
            m = re.match(r"PT(\d*)H", w)  # ignore minutes and seconds
            effort = int(m.group(1))
            print "Raw work: %s" % w
            print "Effort: %d" % effort
        else:
            effort = None

        cstart = task.getElementsByTagName("ConstraintDate")
        if cstart:  # if any names found
            d = getText(cstart[0].childNodes)
            tstart = d.split("T")[0]
            print "Constraint Date: %s" % tstart
        else:
            tstart = None

        # 'Start' is the equivalent of 'CalculatedStartDate'
#        start = task.getElementsByTagName("Start")
#        if start:  # if any names found
#            d = getText(start[0].childNodes)
#            print "Start Date: %s" % d.split("T")[0]

        tid = GetID(tuid, 'Task')

        parents[onum] = tid  # build xref
        if olev and int(olev) > 1:
            ponum = onum[:onum.rfind('.')]
            print "onum %s -> parent onum %s" % (onum, ponum)
            parentid = parents.get(ponum)
        else:
            parentid = None
            
        change = {'Table': 'Task', 'ID': tid, 'ProjectID': projectid,
                  'TaskID': parentid,
                  'Name': tname,
                  'DurationHours': hours,
                  'EffortHours': effort,
                  'StartDate': tstart}
        Data.Update(change)

        # PredecessorLink
        plist = task.getElementsByTagName("PredecessorLink")
        for pred in plist:
            ## PredecessorUID. Type, LagFormat
            
            uid = pred.getElementsByTagName("PredecessorUID")
            if uid:  # if any names found
                puid = getText(uid[0].childNodes)
                print "PredecessorUID: %s" % puid
            else:
                continue

            predid = GetID(puid, 'Task')
            change = {'Table': 'Dependency',
                      'TaskID': tid, 'PrerequisiteID': predid}
            Data.Update(change)

    # resources
    r = dom1.getElementsByTagName("Resources")
    if r:
        reslist = r[0].getElementsByTagName("Resource")
    else:
        reslist = []

    for res in reslist:

        uid = res.getElementsByTagName("UID")
        if uid:  # if any names found
            ruid = getText(uid[0].childNodes)
            print "UID: %s" % ruid
            if ruid == '0': continue  # ms project has an extra resource record
        else:
            continue

        name = res.getElementsByTagName("Name")
        if name:  # if any names found
            rname = getText(name[0].childNodes)
            print "Name: %s" % rname
        else:
            rname = None

        rid = GetID(ruid, 'Resource')
        change = {'Table': 'Resource', 'ID': rid, 'ProjectID': projectid,
                  'Name': rname}
        Data.Update(change)

    # assignments
    a = dom1.getElementsByTagName("Assignments")
    if a:
        aslist = a[0].getElementsByTagName("Assignment")
    else:
        aslist = []

    for as in aslist:

        uid = as.getElementsByTagName("UID")
        if uid:  # if any names found
            auid = getText(uid[0].childNodes)
            print "UID: %s" % auid
        else:
            continue

        if auid == '0':
            continue

        tuid = as.getElementsByTagName("TaskUID")
        if tuid:  # if any names found
            tuid = getText(tuid[0].childNodes)
            print "TaskUID: %s" % tuid
        else:
            continue

        ruid = as.getElementsByTagName("ResourceUID")
        if ruid:  # if any names found
            ruid = getText(ruid[0].childNodes)
            print "ResourceUID: %s" % ruid
        else:
            continue
        
        # if resource uid is < 0 it means no resource is assigned
        if ruid[0] == '-':
            continue

        # Work -> effort
        # This should be ommitted if it matches "everyone full time"
        work = as.getElementsByTagName("Work")
        if work:  # if any names found
            w = getText(work[0].childNodes)
            m = re.match(r"PT(\d*)H", w)  # ignore minutes and seconds
            effort = int(m.group(1))
            print "Raw work: %s" % w
            print "Effort: %d" % effort
        else:
            effort = None

        tid = GetID(tuid, 'Task')
        rid = GetID(ruid, 'Resource')

        # if assignment effort = task duration then omit it here???

        change = {'Table': 'Assignment', 'ProjectID': projectid,
                  'TaskID': tid,
                  'ResourceID': rid,
                  'EffortHours': effort}
        Data.Update(change)

    # clear redundant task and assignment effort value
    dt = Data.Database['Task']
    da = Data.Database['Assignment']
    tasks = Data.SearchByColumn(dt, {'ProjectID': projectid})
    for kt, vt in tasks.iteritems():
        assignments = Data.SearchByColumn(da, {'TaskID': kt})
        dhours = vt.get('DurationHours') or 0
        ehours = vt.get('EffortHours') or 0
        if dhours * len(assignments) == ehours:  # all full time people
            change = { 'Table': 'Task', 'ID': kt, 'EffortHours': None }
            Data.Update(change)
            ehours = 0
        for ka, va in assignments.iteritems():
            ahours = va.get('EffortHours') or 0
            if ((ehours == 0 and ahours == dhours)
                or (ehours and ahours == int(ehours / len(assignments)))):
                change = { 'Table': 'Assignment', 'ID': ka, 'EffortHours': None }
                Data.Update(change)
                
    Data.SetUndo("Import MS Project XML File")

    # mandatory - to make sure memory used by dom1 is released
    dom1.unlink()

def DoImport():

    wildcardx = "XML (*.xml)|*.xml|" "All files (*.*)|*.*"
    dlg = wx.FileDialog(
        self, message="Open MS Project XML File ...", 
        defaultFile="", wildcard=wildcardx,
        style = wx.OPEN
        )

    dlg.SetFilterIndex(0)
    if dlg.ShowModal() == wx.ID_OK:
        path = dlg.GetPath()
        Import(path)

    dlg.Destroy()

DoImport()