Data commit

Task/LZW-compression/AWK/lzw-compression-1.awk

@@ -0,0 +1,9 @@
+==comp
+TOBEORNOTTOBEORTOBEORNOT
+To be or not to be that is the question!
+"There is nothing permanent except change."   ---   Heraclitus  [540 -- 475 BCE]
+
+==decomp
+84,79,66,69,79,82,78,79,84,256,258,260,265,259,261,263
+84,111,32,98,101,32,111,114,32,110,111,116,32,116,257,259,268,104,97,267,105,115,272,260,113,117,101,115,116,105,111,110,33
+34,84,104,101,114,101,32,105,115,32,110,111,116,104,105,110,103,32,112,259,109,97,110,101,110,116,32,101,120,99,101,112,281,99,104,277,103,101,46,34,32,296,45,298,296,32,72,259,97,99,108,105,116,117,264,32,91,53,52,48,32,299,52,55,53,32,66,67,69,93

Task/LZW-compression/AWK/lzw-compression-2.awk

@@ -0,0 +1,73 @@
+# ported from Python
+BEGIN {
+   is_comp = 0
+   is_decomp = 0
+}
+
+{
+    if ($0 == "") next
+
+    if ($1 == "==comp") {
+        is_comp = 1
+        is_decomp = 0
+        print "\ncompressing..."
+        next
+    }
+
+    if ($1 == "==decomp") {
+        is_comp = 0
+        is_decomp = 1
+        print "\ndecompressing..."
+        next
+    }
+
+    if (is_comp) print compress($0)
+
+    if (is_decomp) print decompress($0)
+}
+
+function compress(str,     dict_size, i, dictionary, w, result, len, uncompressed, c, wc ) {
+    dict_size = 256
+    for (i = 0; i <= dict_size; i++) dictionary[chr(i)] = i
+
+    w = ""
+    result = ""
+    len = split(str, uncompressed, "")
+    for (i = 1; i <= len; i++) {
+        c = uncompressed[i]
+        wc = w c
+        if (wc in dictionary) w = wc
+        else {
+            result = result "," dictionary[w]
+            dictionary[wc] = dict_size++
+            w = c
+        }
+    }
+    if (length(w)) result = result "," dictionary[w]
+    return substr(result,2)
+    return "[" substr(result,2) "]"
+}
+
+function decompress(str) {
+    dict_size = 256
+    for (i = 0; i <= dict_size; i++) dictionary[i] = chr(i)
+
+    result = ""
+    len = split(str, compressed, ",")
+    w = chr(compressed[1])
+    result = result w
+    for (i = 2; i <= len; i++) {
+        k = compressed[i]
+        if (k in dictionary) entry = dictionary[k]
+        else if (k == dict_size) entry = w substr(w,1,1)
+        else { entry = "*" }
+        result = result entry
+        dictionary[dict_size++] = w substr(entry,1,1)
+        w = entry
+    }
+    return result
+}
+
+function chr(c) {
+    return sprintf("%c", c + 0)
+}