#!/usr/skunk/bin/gawk -f
#!/usr/bin/awk -f
# @(#) postings.awk 1.0 94/03/09
# 93/01/24 john h. dubois iii (john@armory.com)
# 93/07/02 Added help, fixed Total.
# 94/03/09 Use gawk so - options can be given
BEGIN {
    Usage = "Usage: postings [-h] article-file ..."
    if (ARGC < 2) {
	print Usage
	print "Use -h for help."
	exit(1)
    }
    if (ARGV[1] ~ "^[-+]h$") {
	print \
"postings: report number of postings to groups.\n"\
Usage "\n"\
"article-file is a file that postings are saved to, in mailbox format."
	exit(0)
    }
    GoodFile = Total = 0
    for (FileNum = 1; FileNum < ARGC; FileNum++) {
	InFile = ARGV[FileNum]
	while ((ret = (getline < InFile)) == 1) {
	    if ($1 == "\001\001\001\001") {
		InHeader = 1
	    }
	    else if ($0 == "")
		InHeader = 0
	    else if (InHeader && $1 == "Newsgroups:") {
		Total++
		split($2,Groups,",")
		for (i = 1; i in Groups; i++)
		    GroupCt[Groups[i]]++
	    }
	}
	close(InFile)
	if (ret)
	    printf "Error reading file %s.\n",InFile
	else
	    GoodFile = 1
    }
    if (!GoodFile)
	exit(1)
    NGroup = qsort_arb_ind(GroupCt,k)
    for (i = 1; i <= NGroup; i++) {
	group = k[i]
	printf "%3d %s\n",GroupCt[group],group
    }
    printf "%3d Total\n",Total
}

# Arr is an array of values with arbitrary indices.
# Array k is returned with numeric indices 1..n.
# The values in k are the indices of array arr, 
# ordered so that if array arr is stepped through
# in the order arr[k[1]] .. arr[k[n]], it will be stepped
# through in order of the values of its elements.
# The return value is the number of elements in the array (n).
function qsort_arb_ind(arr,k,  ArrInd,end) {
    end = 0
    for (ArrInd in arr)
	k[++end] = ArrInd;
    qsortseg(arr,k,1,end);
    return end
}

function qsortseg(arr,k,start,end,  left,right,sepval,tmp,tmpe,tmps) {
    # handle two-element case explicitely for a tiny speedup
    if ((end - start) == 1) {
	if (arr[tmps = k[start]] > arr[tmpe = k[end]]) {
	    k[start] = tmpe
	    k[end] = tmps
	}
	return
    }
    left = start;
    right = end;
    sepval = arr[k[int((left + right) / 2)]]
    # Make every element <= sepval be to the left of every element > sepval
    while (left < right) {
	while (arr[k[left]] < sepval)
	    left++
	while (arr[k[right]] > sepval)
	    right--
	if (left < right) {
	    tmp = k[left]
	    k[left++] = k[right]
	    k[right--] = tmp 
	}
    }
    if (left == right)
	if (arr[k[left]] < sepval)
	    left++
	else
	    right--
    if (start < right)
	qsortseg(arr,k,start,right)
    if (left < end)
	qsortseg(arr,k,left,end)
}