Fixed bug for parsing and added CLI functionalities

Scripts/DataCleaning/path_splitter_tree.py

@@ -3,14 +3,12 @@ import csv
 import sys
 from typing import Self
 
+
 class ProgramArgs:
 
-    def __init__(
-        self,
-        file: str,
-        treshold: int
-    ):
+    def __init__(self, file: str, output: str, treshold: int):
         self.file = file
+        self.output = output
         self.treshold = treshold
 
 
@@ -23,61 +21,63 @@ class Node:
     ):
         self.name = name
         self.quantity = quantity
-        self.children : dict[str, Node] = {}
-
+        self.children: dict[str, Node] = {}
 
     @property
     def is_leaf(self):
         return len(self.children) == 0
 
+    def append_child(self, child: list[str]):
 
-    def append_child(self, child : list[str]):
-
-        print(child)
+        # print(child)
         KEY = child[0]
 
         if not self.children.get(KEY):
             self.children[KEY] = Node(KEY, 0)
 
         CHILD = self.children[KEY]
-        CHILD.quantity += 1
+        self.quantity += 1
 
         if len(child) == 1:
             return
 
         new_children = child[1:]
 
-        CHILD.append_child(new_children[1:])
-
+        CHILD.append_child(new_children)
 
     def __str__(self):
-        return f"{self.name}: {self.quantity}"
-
-
-
-
+        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("--output-file", "-o", 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)
+    # print(parsed_args.input_file)
+
+    return ProgramArgs(parsed_args.input_file,parsed_args.output_file, parsed_args.treshold)  # type ignore
+
+
+def get_debug_args() -> ProgramArgs:
+
+    FILE = "./Assets/Dataset/Tmp/reverse-rel.txt"
+    TRESHOLD = 1
 
     return ProgramArgs(
-        parsed_args.input_file,
-        parsed_args.treshold
-    ) # type ignore
+        FILE,
+        TRESHOLD
+    )
 
 
-def tree_like(file: str):
+def tree_like(file: str, out: str):
 
-    INDENTATION = "\t"
+    INDENTATION = "    "
 
-    properties : dict[str, Node] = {}
+    properties: dict[str, Node] = {}
 
     properties["pure"] = Node("pure", 0)
     properties["URI"] = Node("uri", 0)
@@ -87,39 +87,38 @@ def tree_like(file: str):
     for row in FILE:
 
         sections = row.split("/")
+        sections = list(filter(lambda item: item != "", sections))
 
-        print(sections)
+        # print(sections)
 
-        if len(sections) < 2:
+        if sections[0] != "http:" and sections[0] != "https:":
             properties["pure"].append_child(sections)
             continue
 
-        properties["URI"].append_child(
-            sections
-        )
-
-
+        properties["URI"].append_child(sections)
 
     FILE.close()
 
-    stack : list[(Node, int)] = []
+    stack: list[tuple[Node, int]] = []
 
     for _, item in properties.items():
         stack.append((item, 0))
 
+    OUT = open(out, mode="w", encoding="utf-8")
+
     while len(stack) > 0:
 
         LAST_ITEM = stack.pop()
 
-        NODE : Node = LAST_ITEM[0]
-        DEPTH : int = LAST_ITEM[1]
+        NODE: Node = LAST_ITEM[0]
+        DEPTH: int = LAST_ITEM[1]
 
-        INDENT : str = INDENTATION * DEPTH
+        INDENT: str = INDENTATION * DEPTH
 
         if NODE.quantity < ARGS.treshold:
             continue
 
-        print(f"{INDENT}{NODE}")
+        OUT.write(f"{INDENT}- {NODE}\n")
 
         if NODE.is_leaf:
             continue
@@ -127,15 +126,14 @@ def tree_like(file: str):
         CHILDREN = []
 
         for _, child in NODE.children.items():
-            CHILDREN.append(
-                (child, DEPTH + 1)
-            )
+            CHILDREN.append((child, DEPTH + 1))
 
-        stack.extend(
-            CHILDREN
-        )
+        stack.extend(CHILDREN)
+
+    OUT.close()
 
 
 if __name__ == "__main__":
     ARGS = get_args(sys.argv)
-    tree_like(ARGS.file)
+    # ARGS = get_debug_args()
+    tree_like(ARGS.file, ARGS.output)