✨ Add path pattern exclusion as option to read_gfa_line and propaga…

…tion
dubssieg · Jan 19, 2024 · fc6aa63 · fc6aa63
1 parent c31bed0
commit fc6aa63
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 7 deletions.
diff --git a/pgGraphs/gfaparser.py b/pgGraphs/gfaparser.py
@@ -179,7 +179,7 @@ def supplementary_datas(datas: list, length_condition: int) -> dict:
         return mapping
 
     @staticmethod
-    def read_gfa_line(datas: list[str], load_sequence_in_memory: bool = True) -> tuple[str, GFALine, dict]:
+    def read_gfa_line(datas: list[str], load_sequence_in_memory: bool = True, exclude_end_path_pattern: str = "") -> tuple[str, GFALine, dict]:
         """Calls methods to parse a GFA line,
         accordingly to it's fields described in the GFAspec github.
 
@@ -203,7 +203,8 @@ def read_gfa_line(datas: list[str], load_sequence_in_memory: bool = True) -> tup
                 line_datas["orientation"] = f"{datas[2]}/{datas[4]}"
                 return ((line_datas['start'], line_datas['end']), line_type, {**line_datas, **GFAParser.supplementary_datas(datas, 5)})
             case GFALine.WALK:
-                line_datas["id"] = datas[3]
+                line_datas["id"] = (datas[3].upper(), datas[3].upper()[
+                                    :-len(exclude_end_path_pattern)])[datas[3].upper().endswith(exclude_end_path_pattern)]
                 line_datas["origin"] = int(datas[2])
                 line_datas["start_offset"] = datas[4]
                 line_datas["stop_offset"] = datas[5]
@@ -216,7 +217,8 @@ def read_gfa_line(datas: list[str], load_sequence_in_memory: bool = True) -> tup
                 ]
                 return (datas[1], line_type, {**line_datas, **GFAParser.supplementary_datas(datas, 7)})
             case GFALine.PATH:
-                line_datas["id"] = datas[1]
+                line_datas["id"] = (datas[1].upper(), datas[1].upper()[
+                                    :-len(exclude_end_path_pattern)])[datas[1].upper().endswith(exclude_end_path_pattern)]
                 line_datas["origin"] = None
                 line_datas["start_offset"] = None
                 line_datas["stop_offset"] = None

diff --git a/pgGraphs/graph.py b/pgGraphs/graph.py
@@ -21,7 +21,8 @@ def __init__(
         self,
         gfa_file: str | None = None,
         with_sequence: bool = True,
-        low_memory: bool = False
+        low_memory: bool = False,
+        end_pattern_exclusion: str = ""
     ) -> None:
         """Constructor for GFA Graph object.
 
@@ -53,8 +54,9 @@ def __init__(
                         )
 
                     name, line_type, datas = GFAParser.read_gfa_line(
-                        [__.strip() for __ in gfa_line.split('\t')],
-                        with_sequence and not low_memory
+                        datas=[__.strip() for __ in gfa_line.split('\t')],
+                        load_sequence_in_memory=with_sequence and not low_memory,
+                        exclude_end_path_pattern=end_pattern_exclusion,
                     )
                     match line_type:
                         case GFALine.SEGMENT:

diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@
 
     [project]
     name = "gfagraphs"
-    version = "0.2.19"
+    version = "0.2.20"
     authors = [
     { name="Siegfried Dubois", email="siegfried.dubois@inria.fr" },
     ]