✨ adding self method 'sequence_offsets'

gfagraphs/gfagraphs.py

@@ -1,5 +1,6 @@
 "Tools to represent GFA format"
-from os import path, stat
+from os import stat
+from os.path import exists
 from enum import Enum
 from re import sub, match
 from typing import Callable
@@ -24,7 +25,7 @@ def get_gfa_subtype(gfa_file_path: str | list[str]) -> str | list[str]:
         gfa_file_path = [gfa_file_path]
     for gfa_file in gfa_file_path:
         # Checking if path exists
-        if not path.exists(gfa_file):
+        if not exists(gfa_file):
             raise OSError(
                 "Specified file does not exists. Please check provided path."
             )
@@ -466,7 +467,7 @@ def __init__(self, gfa_file: str | None = None, gfa_type: str = 'unknown', with_
         if gfa_file:
             # We try to load file from disk
             # Checking if path exists
-            if not path.exists(gfa_file):
+            if not exists(gfa_file):
                 raise OSError(
                     "Specified file does not exists. Please check provided path."
                 )

pgGraphs/graph.py

@@ -337,3 +337,35 @@ def merge_segments(
             # We go backwards to dodge index collisions
             for pos in positions:
                 path['path'][pos:pos-len(segs)+1] = [merge_name]
+
+############### POsitionnal tag ###############
+
+    def sequence_offsets(self) -> None:
+        """
+            Calculates the offsets within each path for each node
+            Here, we aim to extend the current GFA tag format by adding tags
+            that do respect the GFA naming convention.
+            A JSON string, PO (Path Offset) positions, relative to paths.
+            Hence, PO:J:{'w1':[(334,335,'+')],'w2':[(245,247,'-')]} tells that the walk/path w1
+            contains the sequence starting at position 334 and ending at position 335,
+            and the walk/path w2 contains the sequence starting at the offset 245 (ending 247),
+            and that the sequences are reversed one to each other.
+            Note that any non-referenced walk in this field means that the node
+            is not inside the given walk.
+        """
+        for walk_name, walk_datas in self.paths.items():
+            start_offset: int = int(
+                walk_datas['start_offset']) if 'start_offset' in walk_datas.keys() else 0
+            for node, vect in walk_datas["path"]:
+                if 'PO' not in self.segments[node]:
+                    self.segments[node]['PO']: dict[str,
+                                                    list[tuple[int, int, Orientation]]] = dict()
+                if walk_name in self.segments[node]['PO']:
+                    # We already encountered the node in this path
+                    self.segments[node]['PO'][walk_name].append(
+                        (start_offset, start_offset+self.segments[node]['length'], vect.value))
+                else:
+                    # First time we encounter this node for this path
+                    self.segments[node]['PO'][walk_name] = [
+                        (start_offset, start_offset+self.segments[node]['length'], vect.value)]
+                start_offset += self.segments[node]['length']

pyproject.toml

@@ -4,7 +4,7 @@
 
     [project]
     name = "gfagraphs"
-    version = "0.2.0"
+    version = "0.2.2"
     authors = [
     { name="Siegfried Dubois", email="siegfried.dubois@inria.fr" },
     ]

setup.py

@@ -12,8 +12,8 @@
 LICENCE: str = "LICENCE"
 DESCRIPTION: str = "Library to parse, edit and handle in memory GFA graphs"
 REQUIRED_PYTHON: tuple = (3, 10)
-OVERRIDE_VN: bool = False
-VN: str = "0.2.0"
+OVERRIDE_VN: bool = True
+VN: str = "0.2.2"
 URL: str = "https://github.com/Tharos-ux/gfagraphs"
 REQUIREMENTS: list[str] = ['networkx', 'tharos-pytools']