Shell Programming and Scripting

$ cat xmlt.awk

BEGIN {
        DEP=4;  # How many tags out to keep data
        POS=0   # Position in tag stack
        RS="<"; # Input record separator
        FS="[ \n\t\t>/]";       # Input field separator

        # Hardcode the first two things in the output order
        ORDER[++O]="XN:MECONTEXT:ID";
        ORDER["XN:MECONTEXT:ID"]=O

        ORDER[++O]="XN:VSDATACONTAINER:ID";
        ORDER["XN:VSDATACONTAINER:ID"]=O
}

# This function is checked on whether a property should be added to
# the list of what to print.
function catchthis(PROPNAME, PROPVAL) {

        # Catch all CDATA elements inside XN:VSDATACONTAINER tags
        if(TSS ~ /XN:VSDATACONTAINER/) return(PROPNAME ~ /DATA/);

        return((TSS ~ /XN:VSDATACONTAINER/) && (PROPNAME ~ /CDATA/));
}

# Always this finicky case when RS isn't \n
(NR==1) && (length($0) == 0) { next }

# Skip XML comments
/^!--/ {
        while(!(I=index($0, "-->"))) if(getline <= 0) exit;
        # Strip out comment
        $0="--XMLCOMMENT-- />"substr($0,I+3);
}

# Ignore XML specification junk
/^\?/ || /^\!/ { next }

# These should be special variables for match() but aren't.
# String before match
function rbefore(STR)   { return(substr(STR, N, RSTART-1)); }
# First char of match
function rmid(STR)      { return(substr(STR, RSTART, 1)); }
# Entire match
function rall(STR)      { return(substr(STR, RSTART, RLENGTH)); }
# String after match
function rafter(STR)    { return(substr(STR, RSTART+RLENGTH)); }

# Turns Q SUBSEP R into A[PFIX":"Q]=R
function aquote(OUT, A, PFIX, TA) {
        if(OUT)
        {
                if(PFIX) PFIX=PFIX":"
                split(OUT, TA, SUBSEP);
                A[toupper(PFIX) toupper(TA[1])]=TA[2];
        }

        return("");
}

# Intended to be less stupid about quoted text in XML/HTML.
# Splits a='b' c='d' e='f' into A[PFIX":"a]=b, A[PFIX":"c]=d, etc.
function qsplit(STR, A, PFIX, X, OUT) {
        while(STR && match(STR, /([ \n\t]+)|[\x27\x22=]/))
        {
                OUT = OUT rbefore(STR);

                RMID=rmid(STR);
                if((RMID == "'") || (RMID == "\""))     # Quote characters
                {
                        if(!Q)          Q=RMID;         # Begin quote section
                        else if(Q == RMID)      Q="";   # End quote section
                        else                    OUT = OUT RMID; # Quoted quote
                } else if(RMID == "=") {
                        if(Q)   OUT=OUT RMID; else OUT=OUT SUBSEP;
                } else if((RMID=="\r")||(RMID=="\n")||(RMID=="\t")||(RMID==" ")) {
                        if(Q)   OUT = OUT rall(STR); # Literal quoted whitespace
                        else    OUT = aquote(OUT, A, PFIX); # Unquoted WS, next block
                }
                STR=rafter(STR); # Strip off the text we've processed already.
        }

        aquote(OUT STR, A, PFIX); # Process any text we haven't already.
}

# Call before increment
function addprop(AIN,X,S) {
        for(X in AIN)
        {
                if(!(X in ORDER))
                if(catchthis(X, AIN[X]))
                {
                        ORDER[++O]=X
                        ORDER[X]=O
                }

                PROP[X]=AIN[X]
                KEEP[X]=(POS+2)-DEP
        }
}

# Call before decrement
function delprop(TA, N, M,X) {
        for(X in KEEP)
        if(KEEP[X] > POS)
        {
                delete PROP[X];
                delete KEEP[X];
        }
}

# Non-close tag
!/^\// {

        TAG=$1;                         sub(/^[^ \r\n\t>\/]*/, "");
        match($0, /\/?>/);
        TDATA=rbefore($0);              CDATA=rafter($0);

        # Flatten and strip whitespace
        gsub(/[ \r\n\t]+/, " ", CDATA);
        gsub(/^[ \r\n\t]+/, "", CDATA); gsub(/[ \r\n\t]+$/, "", CDATA);

        for(X in TA) delete TA[X];
        qsplit(TDATA, TA, TAG);
        if(length(CDATA))
                TA[toupper(TAG)":""CDATA"]=CDATA

        addprop(TA);

        if(RLENGTH != 2) # Found > instead of self-closing />
        {
                TS[++POS]=toupper(TAG);
                TSS=TSS"/"toupper(TAG);
        }



#       for(X in A) printf("%s[%s]=%s\n", TAG, X, A[X]);
}

# Close tags
/^\// {

        for(TPOS=POS; (TPOS>0) && (toupper($2) != TS[TPOS]); TPOS--);

        if(toupper($2) == "XN:VSDATACONTAINER")
        {
                OUT=""
                PFIX=""
                for(N=1; N<=O; N++)
                {
                        if(!PROP[ORDER[N]]) PROP[ORDER[N]]="!"ORDER[N]
                        OUT=OUT PFIX PROP[ORDER[N]];
                        PFIX=OFS
                }
                print OUT;
        }

        if(TPOS <= 0) print "Went under for "$2" pos="POS
        else
        {
                TPOS--;
                while(TPOS < POS)
                {
                        delprop();
                        sub(/\/[^\/]*$/, "", TSS); POS--;
                }
        }
}

$ awk -f xmlt.awk OFS="\t" Enodeb_MO_Export_10_47.xml
CCL01736        1       vsDataENodeBFunction    EricssonSpecificAttributes.13.25CCL01736        SubNetwork=ONRM_ROOT_MO_R,MeContext=CCL01736,ManagedElement=1,vsDataTransportNetwork=1,vsDataSctp=1     0       32      1       0       310    410      3       30      1440    30      true    SubNetwork=ONRM_ROOT_MO_R,MeContext=CCL01736,ManagedElement=1,vsDataIpSystem=1,vsDataIpAccessHostEt=1   false  1true    true    1       -2000000000     -2000000000     -2000000000     -2000000000     100     true    0       false