parselogs.awk

function isNoHomepageSearch(input) {
  return input !~ /bIsWorldwide/
}

function getIp(input) {
	return $3
}

function isGetRequest(input) {
	return input ~ /^"GET/
}

function getPathId(input) {
	match(input, /iPathId=([0-9])+/, pathId)
	
	if (length(pathId) > 0) {
		return pathId[0]
	}
}
function getPathList(input) {
	match(input, /aPathList=([0-9,])+/, pathList)
	
	if (length(pathList) > 0) {
		return pathList[0]
	}
}

function join(array, start, end, sep, result, i) {
	if (sep == "")
		sep = " "
	else if (sep == SUBSEP) # magic value
		sep = ""
	
	result = array[start]
	for (i = start + 1; i <= end; i++)
		result = result sep array[i]
	return result
}

BEGIN {
	pathListPart[0] = ""
	pathPart[0] = ""
	use_pathlist = 0
}
{
	if (isNoHomepageSearch($7) && isGetRequest($6)) {
		
		rawPathId = getPathId($7)
		
		if (use_pathlist == 1)
			rawPathList = getPathList($7)

		if (rawPathId != "") {
			match(rawPathId, /([0-9]+)/, pathPart)
		}

		if (use_pathlist == 1 && rawPathList != "") {
			match(rawPathList, /([0-9,]+)/, pathListPart)
		}

		if (length(pathPart) > 0 && (use_pathlist == 1 && length(pathListPart) > 0))
			final = pathPart[0] "," pathListPart[0]
		else if (use_pathlist == 1 && length(pathListPart) > 0)
			final = pathListPart[0]
		else
			final = pathPart[0]
		
		print $3 ";" final
	}
}