Esempio n. 1
0
def mark_spaces(NTags):
    Str=''
    WPs=myModule.flatten_list(NTags)

    LstWP=('','')
    # and this is WC level
    for (Cntr,NTag) in enumerate(NTags):
#        if Debug: sys.stdout.write('Up to WC'+str(Cntr+1))
        # this part is to determine whether the space between two wcs is optional or not
        # so, the first one is ignored, 
        if Cntr==0:
            Space=''
        # and from the second one, the top tag of it and the last tag of the previous one are compared
        else:
            if optional_space_p(LstWP,NTag[0]):
                Space=' '+ZWNJ
            else:
                Space=' '
               
        # and this is the intra-WC part
        WCStr=mark_intrawc(NTag)
        # then mark the space plus the WC accordingly
        Str=Str+Space+WCStr
#        if Debug and Cntr==len(NTags)-1:
#                sys.stdout.write('Marked: '); print([Str])
        # the last one of the current tag is stored as the 'previous' tag
        LstWP=NTag[-1]
    return (Str,WPs)
Esempio n. 2
0
def normalisation_ok_p(WC_WPs,NWPs):
    OrgStr=''.join([ WC_WP[0] for WC_WP in WC_WPs ])
    NewStr=''.join([ WP[0] for WP in myModule.flatten_list(NWPs) ])
    if OrgStr==NewStr:
        Bool=True
    else:
        Bool=False
    return Bool