rework indecies, will continue

utils/tree_utils.py

@@ -30,8 +30,10 @@ def node_str_idx(node):
     returns the character index of start and end of a node
     """
     whole_text = get_root(node).text.decode()
-    start_idx = line_chr2char(whole_text, node.start_point[0], node.start_point[1])
-    end_idx = line_chr2char(whole_text, node.end_point[0], node.end_point[1])
+    # start_idx = line_chr2char(whole_text, node.start_point[0], node.start_point[1])
+    # end_idx = line_chr2char(whole_text, node.end_point[0], node.end_point[1])
+    start_idx = node.start_byte #actual numbers?
+    end_idx = node.end_byte
     return start_idx, end_idx
 
 def give_tree(func_node):
@@ -68,16 +70,18 @@ def get_docstrings(func_node):
                     return docstring
     return docstring
 
-def full_func_head(func_node):
+def full_func_head(func_node) -> str:
     """
     returns function head including docstrings before any real body code
     """
     cursor = func_node.child_by_field_name("body").walk()
     cursor.goto_first_child()
     while cursor.node.type == "comment" or cursor.node.type == "{":
+        last_char = cursor.node.end_byte
         cursor.goto_next_sibling()
     end = cursor.node.start_point
-    return "\n".join(func_node.text.decode().split("\n")[:(end[0]-func_node.start_point[0])])
+    # return "\n".join(func_node.text.decode().split("\n")[:(end[0]-func_node.start_point[0])])[:-(last_char)-1]
+    return func_node.text.decode()[:(last_char - func_node.start_byte)]
 
 def grab_before_comments(func_node):
     """
@@ -93,7 +97,7 @@ def grab_before_comments(func_node):
             last_comment_line = node.start_point[0]
         elif node == func_node:
             return precomment
-    return precomment
+    return precomment 
 
 def has_docstrings(func_node):
     """
@@ -104,11 +108,15 @@ def has_docstrings(func_node):
 
 def line_chr2char(text, line_idx, chr_idx):
     """
+    ## just use strat_byte and end_byte instead!
     returns the character index at the given line and character index.
     """
     lines = text.split("\n")
     char_idx = 0
     for i in range(line_idx):
-        char_idx += len(lines[i]) + 1
+        try:
+            char_idx += len(lines[i]) + 1
+        except IndexError as e:
+            raise IndexError(f"{i=} of {line_idx=} does not exist in {text=}") from e
     char_idx += chr_idx
     return char_idx