Optimizing dot files by removing redundant information

Uncategorized
10

Thanks @steveroush , that is great start. I knew my dormant AWK skills are there for something.

I’m attaching a refined version of your script. It handles \N as labels for nodes and also keeps edge labels.

/* vim: set ft=awk:
 *
 * Generate copy of input graph, replacing names with labels
 * NOTE: DOES NOT COPY SUBGRAPHS!
 * NOTE: ugly if you use record OR html nodes
*/

BEGIN {
  int id = 0;
  int cnt[];
  string names[string];

  string mapn (string inname, string lbl)
  {
     string s;

     s = names[inname];

     /* print("// mapn returning: >", s, "< with inname >", inname, "< and lbl >", lbl, "<"); */

     if(!strcmp(lbl,""))
     {
       print("// Error:: node ", inname, " has no label");
       s = inname;
     }
     else
     {
       if(!strcmp(lbl,"\\N"))
       {
         lbl = inname;
       }
     }

     if(cnt[lbl] > 0)
     {
       print("// Error:: duplicate label >", lbl, "<");
       s = inname;
     }
     else
     {
       if(!strcmp(s, ""))
       {
         s = lbl;
         cnt[lbl] = 1;
       }
     }

     names[inname] = s;

     return s;
  }

  string getmapn (string inname)
  {
     string s;

     s = names[inname];
     if (s == "") {
       print("// Error:: Edge had mapping problem with: ", inname);
     }

     return s;
  }
}

BEG_G {
  graph_t g;
  node_t aNode;

  g = copy (NULL, $G);
  for (aNode = fstnode($G);aNode;aNode = nxtnode(aNode)){
    node (g, mapn(aNode.name, aNode.label));
  }
}

E {
  edge_t e = edge (node (g, getmapn($.tail.name)), node (g, getmapn($.head.name)), "");
  e.label = $.label;
}

END_G {
  write (g);
}

My test input

digraph g {
        n0      [label=A];
        n1      [label=B];
        C       [label="\N"];
        n0 -> n1 [label = "Yes"];
        n1 -> C [label = "No"];
}