Add Source ID from ComicInfo.xml to Metadata

darkseid/comicinfo.py

@@ -19,14 +19,15 @@
     Basic,
     Credit,
     ImageMetadata,
+    InfoSources,
     Links,
     Metadata,
     Notes,
     Publisher,
     Role,
     Series,
 )
-from darkseid.utils import list_to_string, xlate
+from darkseid.utils import get_issue_id_from_note, list_to_string, xlate
 
 
 class ComicInfo:
@@ -368,6 +369,10 @@ def get_age_rating(age_text: str) -> AgeRatings | None:
         md.alternate_count = xlate(get("AlternateCount"), True)
         md.comments = xlate(get("Summary"))
         md.notes = get_note(xlate(get("Notes")))
+        if md.notes is not None and md.notes.comic_rack is not None:
+            src = get_issue_id_from_note(md.notes.comic_rack)
+            if src is not None:
+                md.info_source = [InfoSources(src["source"], src["id"], True)]
         # Cover Year
         tmp_year = xlate(get("Year"), True)
         tmp_month = xlate(get("Month"), True)

darkseid/metroninfo.py

@@ -284,8 +284,10 @@ def _assign_series(root: ET.Element, series: Series) -> None:
         create_sub_element = ET.SubElement
 
         create_sub_element(series_node, "Name").text = series.name
-        create_sub_element(series_node, "SortName").text = series.sort_name
-        create_sub_element(series_node, "Volume").text = str(series.volume)
+        if series.sort_name is not None:
+            create_sub_element(series_node, "SortName").text = series.sort_name
+        if series.volume is not None:
+            create_sub_element(series_node, "Volume").text = str(series.volume)
         create_sub_element(series_node, "Format").text = (
             series.format if series.format in MetronInfo.mix_series_format else "Single Issue"
         )

darkseid/utils.py

@@ -3,10 +3,54 @@
 # Copyright 2019 Brian Pepple
 
 import itertools
+import re
 from collections import defaultdict
+from enum import Enum
 from pathlib import Path
 
 
+# TODO: Change to StrEnum when Python-3.10 support dropped
+class DataSources(str, Enum):
+    COMIC_VINE = "Comic Vine"
+    METRON = "Metron"
+    GCD = "Grand Comics Database"
+
+
+def get_issue_id_from_note(note_txt: str) -> dict[str, str] | None:
+    """
+    Extracts the issue ID from a given note text based on specific keywords and formats.
+    This function identifies the source of the issue ID and returns it along with the ID itself.
+
+    Args:
+        note_txt (str): The text from which to extract the issue ID.
+
+    Returns:
+        dict[str, str] | None: A dictionary containing the source and the issue ID if found,
+        otherwise None.
+    """
+
+    if not note_txt:
+        return None
+
+    note_lower = note_txt.lower()
+    source_map = {
+        "comic vine": DataSources.COMIC_VINE,
+        "metron": DataSources.METRON,
+        "grand comics database": DataSources.GCD,
+    }
+
+    if "comictagger" in note_lower:
+        if match := re.search(r"(issue id (\d+))|(cvdb(\d+))", note_lower):
+            for website, src_enum in source_map.items():
+                if website in note_lower:
+                    return {"source": src_enum, "id": match[2] or match[4]}
+    elif "metrontagger" in note_lower:  # NOQA: SIM102
+        if match := re.search(r"issue_id:(\d+)", note_lower):
+            return {"source": DataSources.METRON, "id": match[1]}
+
+    return None
+
+
 def cast_id_as_str(id_: str | int) -> str:
     """Convert an ID to a string.
 

tests/test_utils.py

@@ -3,6 +3,62 @@
 import pytest
 
 from darkseid import utils
+from darkseid.utils import DataSources, get_issue_id_from_note
+
+
+@pytest.mark.parametrize(
+    ("note_txt", "expected"),
+    [
+        # Happy path tests
+        (
+            "Tagged with ComicTagger 1.6.0b3.dev0 using info from Comic Vine on 2024-11-26 10:44:04. [Issue ID 806681]",
+            {"source": DataSources.COMIC_VINE, "id": "806681"},
+        ),
+        (
+            "Tagged with the ninjas.walk.alone fork of ComicTagger 1.3.5 using info from Comic Vine on "
+            "2023-05-09 22:26:42.  [CVDB806681]",
+            {"source": DataSources.COMIC_VINE, "id": "806681"},
+        ),
+        (
+            "Tagged with ComicTagger 1.6.0b3.dev0 using info from Grand Comics Database on "
+            "2024-11-26 10:44:04. [Issue ID 806681]",
+            {"source": DataSources.GCD, "id": "806681"},
+        ),
+        (
+            "Tagged with MetronTagger-2.3.0 using info from Metron on 2024-06-22 20:32:47. [issue_id:48013]",
+            {"source": DataSources.METRON, "id": "48013"},
+        ),
+        # Edge cases
+        ("", None),
+        ("ComicTagger issue id 0000 Comic Vine", {"source": DataSources.COMIC_VINE, "id": "0000"}),
+        ("ComicTagger issue id 1234", None),
+        ("MetronTagger issue_id:", None),
+        # Error cases
+        ("Random text with no issue id", None),
+        ("ComicTagger issue id abc Comic Vine", None),
+        ("MetronTagger issue_id:abc", None),
+    ],
+    ids=[
+        "comic_vine_issue_id",
+        "comic_vine_cvdb",
+        "gcd_issue_id",
+        "metrontagger_issue_id",
+        "zero_issue_id",
+        "empty_note",
+        "missing_source",
+        "missing_id_after_colon",
+        "no_issue_id",
+        "non_numeric_issue_id",
+        "non_numeric_metron_id",
+    ],
+)
+def test_get_issue_id_from_note(note_txt, expected):
+    # Act
+    result = get_issue_id_from_note(note_txt)
+
+    # Assert
+    assert result == expected
+
 
 test_articles = [
     pytest.param("The Champions & Inhumans", "Test string with '&'", "Champions Inhumans"),