Enhanced dependency parsing

combo/utils/graph.py

@@ -85,3 +85,30 @@ def _dfs(graph, start, end):
             if next_state in path:
                 continue
             fringe.append((next_state, path + [next_state]))
+
+
+def restore_collapse_edges(tree_tokens):
+    empty_tokens = []
+    for token in tree_tokens:
+        deps = token["deps"].split("|")
+        for i, d in enumerate(deps):
+            if ">" in d:
+                # {head}:{empty_node_relation}>{current_node_relation}
+                # should map to
+                # For new, empty node:
+                # {head}:{empty_node_relation}
+                # For current node:
+                # {new_empty_node_id}:{current_node_relation}
+                # TODO consider where to put new_empty_node_id (currently at the end)
+                head, relation = d.split(':', 1)
+                ehead = f"{len(tree_tokens)}.{len(empty_tokens) + 1}"
+                empty_node_relation, current_node_relation = relation.split(">", 1)
+                deps[i] = f"{ehead}:{current_node_relation}"
+                empty_tokens.append(
+                    {
+                        "id": ehead,
+                        "deps": f"{head}:{empty_node_relation}"
+                    }
+                )
+        token["deps"] = "|".join(deps)
+    return empty_tokens