Added barebone to have a splitter

Scripts/DataCleaning/path_splitter_tree.py

@@ -0,0 +1,141 @@
+import argparse
+import csv
+import sys
+from typing import Self
+
+class ProgramArgs:
+
+    def __init__(
+        self,
+        file: str,
+        treshold: int
+    ):
+        self.file = file
+        self.treshold = treshold
+
+
+class Node:
+
+    def __init__(
+        self,
+        name: str,
+        quantity: int = 0,
+    ):
+        self.name = name
+        self.quantity = quantity
+        self.children : dict[str, Node] = {}
+
+
+    @property
+    def is_leaf(self):
+        return len(self.children) == 0
+
+
+    def append_child(self, child : list[str]):
+
+        print(child)
+        KEY = child[0]
+
+        if not self.children.get(KEY):
+            self.children[KEY] = Node(KEY, 0)
+
+        CHILD = self.children[KEY]
+        CHILD.quantity += 1
+
+        if len(child) == 1:
+            return
+
+        new_children = child[1:]
+
+        CHILD.append_child(new_children[1:])
+
+
+    def __str__(self):
+        return f"{self.name}: {self.quantity}"
+
+
+
+
+
+
+def get_args(args: list[str]) -> ProgramArgs:
+
+    PARSER = argparse.ArgumentParser()
+    PARSER.add_argument("--input-file", "-i", required=True, type=str)
+    PARSER.add_argument("--treshold", "-t", type=int, default=1)
+    parsed_args, _ = PARSER.parse_known_args(args)
+
+    print(parsed_args.input_file)
+
+    return ProgramArgs(
+        parsed_args.input_file,
+        parsed_args.treshold
+    ) # type ignore
+
+
+def tree_like(file: str):
+
+    INDENTATION = "\t"
+
+    properties : dict[str, Node] = {}
+
+    properties["pure"] = Node("pure", 0)
+    properties["URI"] = Node("uri", 0)
+
+    FILE = open(file, "r", encoding="utf-8")
+
+    for row in FILE:
+
+        sections = row.split("/")
+
+        print(sections)
+
+        if len(sections) < 2:
+            properties["pure"].append_child(sections)
+            continue
+
+        properties["URI"].append_child(
+            sections
+        )
+
+
+
+    FILE.close()
+
+    stack : list[(Node, int)] = []
+
+    for _, item in properties.items():
+        stack.append((item, 0))
+
+    while len(stack) > 0:
+
+        LAST_ITEM = stack.pop()
+
+        NODE : Node = LAST_ITEM[0]
+        DEPTH : int = LAST_ITEM[1]
+
+        INDENT : str = INDENTATION * DEPTH
+
+        if NODE.quantity < ARGS.treshold:
+            continue
+
+        print(f"{INDENT}{NODE}")
+
+        if NODE.is_leaf:
+            continue
+
+        CHILDREN = []
+
+        for _, child in NODE.children.items():
+            CHILDREN.append(
+                (child, DEPTH + 1)
+            )
+
+        stack.extend(
+            CHILDREN
+        )
+
+
+if __name__ == "__main__":
+    ARGS = get_args(sys.argv)
+    tree_like(ARGS.file)