From 7dece304d305f46ed2cbed4b6acac2e7bf0f60b9 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Wed, 11 Mar 2026 20:48:26 +0100
Subject: [PATCH 01/11] WIP: Local Works somewhat

---
 docs.bzl                                      |  17 +-
 scripts_bazel/generate_sourcelinks_cli.py     |  51 ++++-
 scripts_bazel/merge_sourcelinks.py            |  70 ++++++-
 .../score_source_code_linker/__init__.py      | 184 +++++++++---------
 .../score_source_code_linker/metadata.py      |  23 +++
 .../module_source_links.py                    | 137 +++++++++++++
 .../need_source_links.py                      |  51 +++++
 .../score_source_code_linker/needlinks.py     | 114 +++++++++--
 src/helper_lib/additional_functions.py        |  25 +++
 9 files changed, 555 insertions(+), 117 deletions(-)
 create mode 100644 src/extensions/score_source_code_linker/metadata.py
 create mode 100644 src/extensions/score_source_code_linker/module_source_links.py

diff --git a/docs.bzl b/docs.bzl
index 8f728f123..4f1ec3131 100644
--- a/docs.bzl
+++ b/docs.bzl
@@ -69,7 +69,7 @@ def _rewrite_needs_json_to_sourcelinks(labels):
             out.append(s)
     return out
 
-def _merge_sourcelinks(name, sourcelinks):
+def _merge_sourcelinks(name, sourcelinks, known_good = None):
     """Merge multiple sourcelinks JSON files into a single file.
 
     Args:
@@ -77,15 +77,22 @@ def _merge_sourcelinks(name, sourcelinks):
         sourcelinks: List of sourcelinks JSON file targets
     """
 
+    extra_srcs = []
+    known_good_arg = ""
+    if known_good != None:
+        extra_srcs = [known_good]
+        known_good_arg = "--known_good $(location %s)" % known_good
+
     native.genrule(
         name = name,
-        srcs = sourcelinks,
+        srcs = sourcelinks + extra_srcs,
         outs = [name + ".json"],
         cmd = """
         $(location @score_docs_as_code//scripts_bazel:merge_sourcelinks) \
             --output $@ \
+            {known_good_arg} \
             $(SRCS)
-        """,
+        """.format(known_good_arg = known_good_arg),
         tools = ["@score_docs_as_code//scripts_bazel:merge_sourcelinks"],
     )
 
@@ -120,7 +127,7 @@ def _missing_requirements(deps):
         fail(msg)
     fail("This case should be unreachable?!")
 
-def docs(source_dir = "docs", data = [], deps = [], scan_code = []):
+def docs(source_dir = "docs", data = [], deps = [], scan_code = [], known_good = None):
     """Creates all targets related to documentation.
 
     By using this function, you'll get any and all updates for documentation targets in one place.
@@ -175,7 +182,7 @@ def docs(source_dir = "docs", data = [], deps = [], scan_code = []):
 
     data_with_docs_sources = _rewrite_needs_json_to_docs_sources(data)
     additional_combo_sourcelinks = _rewrite_needs_json_to_sourcelinks(data)
-    _merge_sourcelinks(name = "merged_sourcelinks", sourcelinks = [":sourcelinks_json"] + additional_combo_sourcelinks)
+    _merge_sourcelinks(name = "merged_sourcelinks", sourcelinks = [":sourcelinks_json"] + additional_combo_sourcelinks, known_good = known_good)
 
     py_binary(
         name = "docs",
diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 4291b97c5..27a0e4508 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -26,24 +26,51 @@
     _extract_references_from_file,  # pyright: ignore[reportPrivateUsage] TODO: move it out of the extension and into this script
 )
 from src.extensions.score_source_code_linker.needlinks import (
-    store_source_code_links_json,
+    store_source_code_links_with_metadata_json,
 )
+from src.extensions.score_source_code_linker.metadata import MetaData
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
 
+def parse_module_name_from_path(path: Path) -> str:
+    """
+    Parse out the Module-Name from the filename gotten
+    /home/user/.cache/bazel/aksj37981712/external/score_docs_as_code+/src/tests/testfile.py
+    => score_docs_as_code
+    """
+
+    # COMBO BUILD
+    # If external is in the filepath that gets parsed =>
+    # file is in an external module => combo build
+    # e.g. .../external/score_docs_as_code+/src/helper_lib/__init__.py
+
+    # PATH if we are in local repository
+    # PosixPath('src/helper_lib/test_helper_lib.py')
+    # Path if we are in combo build and externally
+    # PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
+    print("======== THIs IS PATH we PARSIGN FOr MODULE NAME")
+    print(path)
+    if str(path).startswith("external/"):
+        module_raw = str(path).removeprefix("external/")
+        filepath_split = str(module_raw).split("/", maxsplit=1)
+        module_name = str(filepath_split[0].removesuffix("+"))
+        return module_name
+    return "local_module"
+
+
 def main():
     parser = argparse.ArgumentParser(
         description="Generate source code links JSON from source files"
     )
-    parser.add_argument(
+    _ = parser.add_argument(
         "--output",
         required=True,
         type=Path,
         help="Output JSON file path",
     )
-    parser.add_argument(
+    _ = parser.add_argument(
         "files",
         nargs="*",
         type=Path,
@@ -53,15 +80,29 @@ def main():
     args = parser.parse_args()
 
     all_need_references = []
+    metadata: MetaData = {
+        "module_name": "",
+        "hash": "",
+        "url": "",
+    }
+    metadata_set = False
     for file_path in args.files:
+        if "known_good.json" not in str(file_path) and not metadata_set:
+            metadata["module_name"] = parse_module_name_from_path(file_path)
+            print("================")
+            print(metadata)
+            print("===============")
+            print("METADATA SET")
+            metadata_set = True
         abs_file_path = file_path.resolve()
         assert abs_file_path.exists(), abs_file_path
         references = _extract_references_from_file(
             abs_file_path.parent, Path(abs_file_path.name)
         )
         all_need_references.extend(references)
-
-    store_source_code_links_json(args.output, all_need_references)
+    store_source_code_links_with_metadata_json(
+        file=args.output, metadata=metadata, needlist=all_need_references
+    )
     logger.info(
         f"Found {len(all_need_references)} need references in {len(args.files)} files"
     )
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index f194e19ca..034d45db5 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -20,22 +20,71 @@
 import logging
 import sys
 from pathlib import Path
+from typing import Any
+
+# from src.extensions.score_source_code_linker.need_source_links import (
+#     store_source_code_links_combined_json,
+# )
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
+# [
+# PosixPath('bazel-out/k8-fastbuild/bin/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_persistency+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_orchestrator+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_kyron+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_baselibs+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_baselibs_rust+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_logging+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_platform+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_process+/sourcelinks_json.json'),
+# PosixPath('bazel-out/k8-fastbuild/bin/external/score_docs_as_code+/sourcelinks_json.json')
+# ]
+
+
+"""
+if bazel-out/k8-fastbuild/bin/external/ in file_path => module is external 
+otherwise it's local 
+if local => module_name & hash == empty
+if external => parse thing for module_name => look up known_good json for hash & url
+"""
+
+
+def parse_info_from_known_good(
+    known_good_json: Path, module_name: str
+) -> tuple[str, str]:
+    print("===THIS IS MODULE NAME WE LOOK FOR===========")
+    print(module_name)
+    with open(known_good_json, "r") as f:
+        kg_json = json.load(f)
+    for category in kg_json["modules"].values():
+        print("===THIS IS CATEGORY=========")
+        print(category)
+        if module_name in category:
+            print("===THIS IS MODULE NAME INSIDe CATEGORY===========")
+            print(module_name)
+            m = category[module_name]
+            return (m["hash"], m["repo"].removesuffix(".git"))
+    raise KeyError(f"Module {module_name!r} not found in known_good_json.")
+
 
 def main():
     parser = argparse.ArgumentParser(
         description="Merge multiple sourcelinks JSON files into one"
     )
-    parser.add_argument(
+    _ = parser.add_argument(
         "--output",
         required=True,
         type=Path,
         help="Output merged JSON file path",
     )
-    parser.add_argument(
+    _ = parser.add_argument(
+        "--known_good",
+        default=None,
+        help="Optional path to a 'known good' JSON file (provided by Bazel).",
+    )
+    _ = parser.add_argument(
         "files",
         nargs="*",
         type=Path,
@@ -43,13 +92,26 @@ def main():
     )
 
     args = parser.parse_args()
+    all_files = [x for x in args.files if "known_good.json" not in str(x)]
 
     merged = []
-    for json_file in args.files:
+    for json_file in all_files:
         with open(json_file) as f:
             data = json.load(f)
+            metadata = data[0]
+            if metadata["module_name"] and metadata["module_name"] != "local_module":
+                hash, repo = parse_info_from_known_good(
+                    known_good_json=args.known_good, module_name=metadata["module_name"]
+                )
+                metadata["hash"] = hash
+                metadata["url"] = repo
+            # In the case that 'metadata[module_name]' is empty
+            # hash & url are already existing and empty inside of 'metadata'
+            # Therefore all 3 keys will be written to needlinks in each branch
+            for d in data[1:]:
+                d.update(metadata)
             assert isinstance(data, list), repr(data)
-            merged.extend(data)
+            merged.extend(data[1:])
 
     with open(args.output, "w") as f:
         json.dump(merged, f, indent=2, ensure_ascii=False)
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index cf9843dc5..7e0ff0252 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -21,7 +21,6 @@
 # This whole directory implements the above mentioned tool requirements
 
 import os
-from collections import defaultdict
 from copy import deepcopy
 from pathlib import Path
 from typing import cast
@@ -40,10 +39,19 @@
     SourceCodeLinks,
     load_source_code_links_combined_json,
     store_source_code_links_combined_json,
+    group_by_need,
 )
+
+from src.extensions.score_source_code_linker.module_source_links import (
+    group_needs_by_module,
+    store_module_source_links_json,
+    load_module_source_links_json,
+)
+
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     load_source_code_links_json,
+    load_source_code_links_with_metadata_json,
 )
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
@@ -71,53 +79,6 @@
 #          ╰──────────────────────────────────────╯
 
 
-def group_by_need(
-    source_code_links: list[NeedLink],
-    test_case_links: list[DataForTestLink] | None = None,
-) -> list[SourceCodeLinks]:
-    """
-    Groups the given need links and test case links by their need ID.
-    Returns a nested dictionary structure with 'CodeLink' and 'TestLink' categories.
-    Example output:
-
-
-      {
-        "need": "<need_id>",
-        "links": {
-          "CodeLinks": [NeedLink, NeedLink, ...],
-          "TestLinks": [testlink, testlink, ...]
-        }
-      }
-    """
-    # TODO: I wonder if there is a more efficent way to do this
-    grouped_by_need: dict[str, NeedSourceLinks] = defaultdict(
-        lambda: NeedSourceLinks(TestLinks=[], CodeLinks=[])
-    )
-
-    # Group source code links
-    for needlink in source_code_links:
-        grouped_by_need[needlink.need].CodeLinks.append(needlink)
-
-    # Group test case links
-    if test_case_links is not None:
-        for testlink in test_case_links:
-            grouped_by_need[testlink.need].TestLinks.append(testlink)
-
-    # Build final list of SourceCodeLinks
-    result: list[SourceCodeLinks] = [
-        SourceCodeLinks(
-            need=need,
-            links=NeedSourceLinks(
-                CodeLinks=need_links.CodeLinks,
-                TestLinks=need_links.TestLinks,
-            ),
-        )
-        for need, need_links in grouped_by_need.items()
-    ]
-
-    return result
-
-
 def get_cache_filename(build_dir: Path, filename: str) -> Path:
     """
     Returns the path to the cache file for the source code linker.
@@ -142,14 +103,19 @@ def build_and_save_combined_file(outdir: Path):
     else:
         source_code_links_json = Path(source_code_links_json)
 
-    source_code_links = load_source_code_links_json(source_code_links_json)
+    # This isn't pretty will think of a better solution later, for now this should work
+    try:
+        source_code_links = load_source_code_links_json(source_code_links_json)
+    except AssertionError:
+        source_code_links = load_source_code_links_with_metadata_json(
+            source_code_links_json
+        )
     test_code_links = load_test_xml_parsed_json(
         get_cache_filename(outdir, "score_xml_parser_cache.json")
     )
-
+    scl_list = group_by_need(source_code_links, test_code_links)
     store_source_code_links_combined_json(
-        outdir / "score_scl_grouped_cache.json",
-        group_by_need(source_code_links, test_code_links),
+        outdir / "score_scl_grouped_cache.json", scl_list
     )
 
 
@@ -254,10 +220,10 @@ def setup_test_code_linker(app: Sphinx, env: BuildEnvironment):
 
 
 def register_combined_linker(app: Sphinx):
-    # Registering the combined linker to Sphinx
+    # Registering the final combine linker to Sphinx
     # priority is set to make sure it is called in the right order.
-    # Needs to be called after xml parsing & codelink
-    app.connect("env-updated", setup_combined_linker, priority=507)
+    # Needs to be called after xml parsing & codelink & combined_linker
+    app.connect("env-updated", setup_combined_linker, priority=510)
 
 
 def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
@@ -272,6 +238,37 @@ def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
         build_and_save_combined_file(app.outdir)
 
 
+def register_module_linker(app: Sphinx):
+    # Registering the combined linker to Sphinx
+    # priority is set to make sure it is called in the right order.
+    # Needs to be called after xml parsing & codelink
+    app.connect("env-updated", setup_module_linker, priority=520)
+
+
+def build_and_save_module_scl_file(outdir: Path):
+    scl_links = load_source_code_links_combined_json(
+        get_cache_filename(outdir, "score_scl_grouped_cache.json")
+    )
+    mcl_links = group_needs_by_module(scl_links)
+    store_module_source_links_json(
+        outdir / "score_module_grouped_scl_cache.json", mcl_links
+    )
+
+
+def setup_module_linker(app: Sphinx, _: BuildEnvironment):
+    grouped_cache = get_cache_filename(
+        app.outdir, "score_module_grouped_scl_cache.json"
+    )
+    gruped_cache_exists = grouped_cache.exists()
+    # TODO this cache should be done via Bazel
+    if not gruped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
+        LOGGER.debug(
+            "Did not find combined json 'score_module_grouped_scl_cache.json' "
+            "in _build. Generating new one"
+        )
+        build_and_save_module_scl_file(app.outdir)
+
+
 def setup_once(app: Sphinx):
     # might be the only way to solve this?
     if "skip_rescanning_via_source_code_linker" in app.config:
@@ -295,9 +292,10 @@ def setup_once(app: Sphinx):
     setup_source_code_linker(app, ws_root)
     register_test_code_linker(app)
     register_combined_linker(app)
+    register_module_linker(app)
 
-    # Priorty=510 to ensure it's called after the test code linker & combined connection
-    app.connect("env-updated", inject_links_into_needs, priority=510)
+    # Priorty=515 to ensure it's called after the test code linker & combined connection
+    app.connect("env-updated", inject_links_into_needs, priority=525)
 
 
 def setup(app: Sphinx) -> dict[str, str | bool]:
@@ -352,42 +350,46 @@ def inject_links_into_needs(app: Sphinx, env: BuildEnvironment) -> None:
                     f"?? Need {id} already has testlink: {need.get('testlink')}"
                 )
 
-    source_code_links_by_need = load_source_code_links_combined_json(
-        get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
+    scl_by_module = load_module_source_links_json(
+        get_cache_filename(app.outdir, "score_module_grouped_scl_cache.json")
     )
+    # source_code_links_by_need = load_source_code_links_combined_json(
+    #     get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
+    # )
+    for module_grouped_needs in scl_by_module:
+        for source_code_links in module_grouped_needs.needs:
+            need = find_need(needs_copy, source_code_links.need)
+            if need is None:
+                # TODO: print github annotations as in https://github.com/eclipse-score/bazel_registry/blob/7423b9996a45dd0a9ec868e06a970330ee71cf4f/tools/verify_semver_compatibility_level.py#L126-L129
+                for n in source_code_links.links.CodeLinks:
+                    LOGGER.warning(
+                        f"{n.file}:{n.line}: Could not find {source_code_links.need} "
+                        "in documentation [CODE LINK]",
+                        type="score_source_code_linker",
+                    )
+                for n in source_code_links.links.TestLinks:
+                    LOGGER.warning(
+                        f"{n.file}:{n.line}: Could not find {source_code_links.need} "
+                        "in documentation [TEST LINK]",
+                        type="score_source_code_linker",
+                    )
+                continue
+
+            need_as_dict = cast(dict[str, object], need)
+            metadata = module_grouped_needs.module_name
+            need_as_dict["source_code_link"] = ", ".join(
+                f"{get_github_link(metadata, n)}<>{n.file}:{n.line}"
+                for n in source_code_links.links.CodeLinks
+            )
+            need_as_dict["testlink"] = ", ".join(
+                f"{get_github_link(metadata, n)}<>{n.name}"
+                for n in source_code_links.links.TestLinks
+            )
 
-    for source_code_links in source_code_links_by_need:
-        need = find_need(needs_copy, source_code_links.need)
-        if need is None:
-            # TODO: print github annotations as in https://github.com/eclipse-score/bazel_registry/blob/7423b9996a45dd0a9ec868e06a970330ee71cf4f/tools/verify_semver_compatibility_level.py#L126-L129
-            for n in source_code_links.links.CodeLinks:
-                LOGGER.warning(
-                    f"{n.file}:{n.line}: Could not find {source_code_links.need} "
-                    "in documentation [CODE LINK]",
-                    type="score_source_code_linker",
-                )
-            for n in source_code_links.links.TestLinks:
-                LOGGER.warning(
-                    f"{n.file}:{n.line}: Could not find {source_code_links.need} "
-                    "in documentation [TEST LINK]",
-                    type="score_source_code_linker",
-                )
-            continue
-
-        need_as_dict = cast(dict[str, object], need)
-
-        need_as_dict["source_code_link"] = ", ".join(
-            f"{get_github_link(n)}<>{n.file}:{n.line}"
-            for n in source_code_links.links.CodeLinks
-        )
-        need_as_dict["testlink"] = ", ".join(
-            f"{get_github_link(n)}<>{n.name}" for n in source_code_links.links.TestLinks
-        )
-
-        # NOTE: Removing & adding the need is important to make sure
-        # the needs gets 're-evaluated'.
-        Needs_Data.remove_need(need["id"])
-        Needs_Data.add_need(need)
+            # NOTE: Removing & adding the need is important to make sure
+            # the needs gets 're-evaluated'.
+            Needs_Data.remove_need(need["id"])
+            Needs_Data.add_need(need)
 
 
 #          ╭──────────────────────────────────────╮
diff --git a/src/extensions/score_source_code_linker/metadata.py b/src/extensions/score_source_code_linker/metadata.py
new file mode 100644
index 000000000..03acc537a
--- /dev/null
+++ b/src/extensions/score_source_code_linker/metadata.py
@@ -0,0 +1,23 @@
+# *******************************************************************************
+# Copyright (c) 2026 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+
+from typing import TypedDict, TypeGuard
+
+class MetaData(TypedDict):
+    module_name: str
+    hash: str
+    url: str
+
+def is_metadata(x: object) -> TypeGuard[MetaData]:
+    # Make this as strict/loose as you want; at minimum, it must be a dict.
+    return isinstance(x, dict) and {"module_name", "hash", "url"} <= x.keys()
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
new file mode 100644
index 000000000..3957733f0
--- /dev/null
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -0,0 +1,137 @@
+# *******************************************************************************
+# Copyright (c) 2025 Contributors to the Eclipse Foundation
+#
+# See the NOTICE file(s) distributed with this work for additional
+# information regarding copyright ownership.
+#
+# This program and the accompanying materials are made available under the
+# terms of the Apache License Version 2.0 which is available at
+# https://www.apache.org/licenses/LICENSE-2.0
+#
+# SPDX-License-Identifier: Apache-2.0
+# *******************************************************************************
+
+
+from dataclasses import dataclass, asdict, field
+import json
+from typing import Any
+from pathlib import Path
+
+
+from src.extensions.score_source_code_linker.need_source_links import (
+    NeedSourceLinks,
+    SourceCodeLinks,
+    SourceCodeLinks_JSON_Decoder,
+)
+from src.extensions.score_source_code_linker.needlinks import NeedLink
+from src.extensions.score_source_code_linker.testlink import DataForTestLink
+
+
+@dataclass
+class moduleInfo:
+    name: str
+    hash: str
+    url: str
+
+
+@dataclass
+class ModuleSourceLinks:
+    module_name: moduleInfo
+    needs: list[SourceCodeLinks] = field(default_factory=list)
+
+
+class ModuleSourceLinks_JSON_Encoder(json.JSONEncoder):
+    def default(self, o: object):
+        if isinstance(o, Path):
+            return str(o)
+        # We do not want to save the metadata inside the codelink
+        # (hash, module_name, url)
+        if isinstance(o, NeedLink):
+            return o.to_dict_without_metadata()
+        if isinstance(
+            o, ModuleSourceLinks | SourceCodeLinks | DataForTestLink | NeedSourceLinks
+        ):
+            return asdict(o)
+        return super().default(o)
+
+
+def ModuleSourceLinks_JSON_Decoder(
+    d: dict[str, Any],
+) -> ModuleSourceLinks | dict[str, Any]:
+    if "module_name" in d and "needs" in d:
+        module_name = d["module_name"]
+        needs = d["needs"]
+        return ModuleSourceLinks(
+            module_name=moduleInfo(
+                name=module_name.get("module_name"),
+                hash=module_name.get("hash"),
+                url=module_name.get("url"),
+            ),
+            # We know this can only be list[SourceCodeLinks] and nothing else
+            # Therefore => we ignore the type error here
+            needs=[SourceCodeLinks_JSON_Decoder(need) for need in needs] # type: ignore
+        )
+    return d
+
+
+def store_module_source_links_json(
+    file: Path, source_code_links: list[ModuleSourceLinks]
+):
+    # After `rm -rf _build` or on clean builds the directory does not exist, so we need
+    # to create it
+    file.parent.mkdir(exist_ok=True)
+    with open(file, "w") as f:
+        json.dump(
+            source_code_links,
+            f,
+            cls=ModuleSourceLinks_JSON_Encoder,
+            indent=2,
+            ensure_ascii=False,
+        )
+
+
+def load_module_source_links_json(file: Path) -> list[ModuleSourceLinks]:
+    links: list[ModuleSourceLinks] = json.loads(
+        file.read_text(encoding="utf-8"),
+        object_hook=ModuleSourceLinks_JSON_Decoder,
+    )
+    assert isinstance(links, list), (
+        "The combined source code linker links should be "
+        "a list of SourceCodeLinks objects."
+    )
+    assert all(isinstance(link, ModuleSourceLinks) for link in links), (
+        "All items in combined_source_code_linker_cache should be "
+        "SourceCodeLinks objects."
+    )
+    return links
+
+
+def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLinks]:
+    module_groups: dict[str, ModuleSourceLinks] = {}
+
+    for source_link in links:
+        if not source_link.links.CodeLinks:
+            continue
+
+        first_link = source_link.links.CodeLinks[0]
+        module_key = first_link.module_name
+
+        if module_key not in module_groups:
+            module_groups[module_key] = ModuleSourceLinks(
+                module_name=moduleInfo(name=module_key, hash=first_link.hash, url=first_link.url)
+            )
+
+        module_groups[module_key].needs.append(source_link)  # Much clearer!
+
+    return [
+        ModuleSourceLinks(module_name=group.module_name, needs=group.needs)
+        for group in module_groups.values()
+    ]
+
+
+# # Pouplate Metadata
+# # Since all metadata inside the Codelinks is the same
+# # we can just arbitrarily grab the first one
+# module_name=need_links.CodeLinks[0].module_name,
+# hash=need_links.CodeLinks[0].hash,
+# url=need_links.CodeLinks[0].url,
diff --git a/src/extensions/score_source_code_linker/need_source_links.py b/src/extensions/score_source_code_linker/need_source_links.py
index 6c738da8e..2deb4c5e8 100644
--- a/src/extensions/score_source_code_linker/need_source_links.py
+++ b/src/extensions/score_source_code_linker/need_source_links.py
@@ -21,6 +21,7 @@
 
 import json
 from dataclasses import asdict, dataclass, field
+from collections import defaultdict
 from pathlib import Path
 from typing import Any
 
@@ -108,3 +109,53 @@ def load_source_code_links_combined_json(file: Path) -> list[SourceCodeLinks]:
         "SourceCodeLinks objects."
     )
     return links
+
+
+def group_by_need(
+    source_code_links: list[NeedLink],
+    test_case_links: list[DataForTestLink] | None = None,
+) -> list[SourceCodeLinks]:
+    """
+    Groups the given need links and test case links by their need ID.
+    Returns a nested dictionary structure with 'CodeLink' and 'TestLink' categories.
+    Example output:
+
+
+      {
+        "need": "<need_id>",
+        "module_name": <module_name>,
+        "hash": <git hash>,
+        "url": <github base url>,
+        "links": {
+          "CodeLinks": [NeedLink, NeedLink, ...],
+          "TestLinks": [testlink, testlink, ...]
+        }
+      }
+    """
+    # TODO: I wonder if there is a more efficent way to do this
+    grouped_by_need: dict[str, NeedSourceLinks] = defaultdict(
+        lambda: NeedSourceLinks(TestLinks=[], CodeLinks=[])
+    )
+
+    # Group source code links
+    for needlink in source_code_links:
+        grouped_by_need[needlink.need].CodeLinks.append(needlink)
+
+    # Group test case links
+    if test_case_links is not None:
+        for testlink in test_case_links:
+            grouped_by_need[testlink.need].TestLinks.append(testlink)
+
+    # Build final list of SourceCodeLinks
+    result: list[SourceCodeLinks] = [
+        SourceCodeLinks(
+            need=need,
+            links=NeedSourceLinks(
+                CodeLinks=need_links.CodeLinks,
+                TestLinks=need_links.TestLinks,
+            ),
+        )
+        for need, need_links in grouped_by_need.items()
+    ]
+
+    return result
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index 348147292..a727025bd 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -16,10 +16,11 @@
 import os
 from dataclasses import asdict, dataclass
 from pathlib import Path
-from typing import Any
+from typing import Any, TypeGuard
+from src.extensions.score_source_code_linker.metadata import MetaData, is_metadata
 
 
-@dataclass(frozen=True, order=True)
+@dataclass(order=True)
 class NeedLink:
     """Represents a single template string finding in a file."""
 
@@ -28,6 +29,19 @@ class NeedLink:
     tag: str
     need: str
     full_line: str
+    module_name: str = ""
+    hash: str = ""
+    url: str = ""
+
+    def to_dict_full(self) -> dict[str, str | Path]:
+        return asdict(self)
+
+    def to_dict_without_metadata(self) -> dict[str, str | Path]:
+        d = asdict(self)
+        d.pop("module_name", None)
+        d.pop("hash", None)
+        d.pop("url", None)
+        return d
 
 
 def DefaultNeedLink() -> NeedLink:
@@ -41,6 +55,8 @@ def DefaultNeedLink() -> NeedLink:
         tag="",
         need="",
         full_line="",
+        # Module_name, hash, url are defaulted to ""
+        # therefore not needed to be listed
     )
 
 
@@ -61,26 +77,99 @@ def needlink_decoder(d: dict[str, Any]) -> NeedLink | dict[str, Any]:
             tag=d["tag"],
             need=d["need"],
             full_line=d["full_line"],
+            module_name=d.get("module_name", ""),
+            hash=d.get("hash", ""),
+            url=d.get("url", ""),
         )
     # It's something else, pass it on to other decoders
     return d
 
 
-def store_source_code_links_json(file: Path, needlist: list[NeedLink]):
-    # After `rm -rf _build` or on clean builds the directory does not exist,
-    # so we need to create it
+def store_source_code_links_with_metadata_json(
+    file: Path, metadata: MetaData, needlist: list[NeedLink]
+) -> None:
+    """
+    Writes a JSON array:
+      [ meta_dict, needlink1, needlink2, ... ]
+
+    meta_dict must include:
+      module_name, hash, url
+    """
+    payload: list[object] = [metadata, *needlist]
+
     file.parent.mkdir(exist_ok=True)
-    with open(file, "w") as f:
-        json.dump(
-            needlist,
-            f,
-            cls=NeedLinkEncoder,  # use your custom encoder
-            indent=2,
-            ensure_ascii=False,
+    with open(file, "w", encoding="utf-8") as f:
+        json.dump(payload, f, cls=NeedLinkEncoder, indent=2, ensure_ascii=False)
+
+
+def store_source_code_links_json(file: Path, needlist: list[NeedLink]) -> None:
+    """
+    Writes a JSON array:
+      [ meta_dict, needlink1, needlink2, ... ]
+
+    meta_dict must include:
+      module_name, hash, url
+    """
+
+    file.parent.mkdir(exist_ok=True)
+    with open(file, "w", encoding="utf-8") as f:
+        json.dump(needlist, f, cls=NeedLinkEncoder, indent=2, ensure_ascii=False)
+
+
+def _is_needlink_list(xs: list[object]) -> TypeGuard[list[NeedLink]]:
+    return all(isinstance(link, NeedLink) for link in xs)
+
+
+def load_source_code_links_with_metadata_json(file: Path) -> list[NeedLink]:
+    """
+    Expects the JSON array where first is a meta_dict:
+      [ meta_dict, needlink1, needlink2, ... ]
+    Returns:
+      [NeedLink, NeedLink, ...]
+
+    This normally should be the one called 'locally' => :docs target
+    """
+    if not file.is_absolute():
+        ws_root = os.environ.get("BUILD_WORKSPACE_DIRECTORY")
+        if ws_root:
+            file = Path(ws_root) / file
+
+    data: list[object] = json.loads(
+        file.read_text(encoding="utf-8"),
+        object_hook=needlink_decoder,
+    )
+    links: list[object] = []
+    if not is_metadata(data[0]):
+        raise TypeError(
+            "If you do not have a 'metadata' dict as the first one in the json "
+            "you might wanted to call the load without metadata named: "
+            "'load_source_code_links_json'"
         )
+    metadata: MetaData = data[0]
+    links = data[1:]
+    if not _is_needlink_list(links):
+        raise TypeError(
+            "In local build context all items after"
+            f"metadata must decode to NeedLink objects. File: {file}"
+        )
+    for d in links:
+        d.module_name = metadata["module_name"]
+        d.hash = metadata["hash"]
+        d.url = metadata["url"]
+    return links
 
 
 def load_source_code_links_json(file: Path) -> list[NeedLink]:
+    """
+    Expects the JSON array with needlinks
+    *that already have extra info in them* (module_name, hash, url):
+      [ needlink1, needlink2, ... ]
+    Returns:
+      [NeedLink, NeedLink, ...]
+
+    This normally should be the one called in combo builds
+    => :docs_combo_experimental target
+    """
     if not file.is_absolute():
         # use env variable set by Bazel
         ws_root = os.environ.get("BUILD_WORKSPACE_DIRECTORY")
@@ -98,3 +187,4 @@ def load_source_code_links_json(file: Path) -> list[NeedLink]:
         "All items in source_code_links should be NeedLink objects."
     )
     return links
+
diff --git a/src/helper_lib/additional_functions.py b/src/helper_lib/additional_functions.py
index 5b1ce6d98..872d66af2 100644
--- a/src/helper_lib/additional_functions.py
+++ b/src/helper_lib/additional_functions.py
@@ -14,6 +14,7 @@
 
 # Import types that depend on score_source_code_linker
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink, NeedLink
+from src.extensions.score_source_code_linker.module_source_links import moduleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
     DataOfTestCase,
@@ -26,6 +27,19 @@
 
 
 def get_github_link(
+    metadata: moduleInfo,
+    link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
+) -> str:
+    if link is None:
+        link = DefaultNeedLink()
+    if not metadata.hash:
+        # Local path (//:docs)
+        return get_github_link_from_git(link)
+    # Ref-Integration path (//:docs_combo..)
+    return get_github_link_from_json(metadata, link)
+
+
+def get_github_link_from_git(
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
 ) -> str:
     if link is None:
@@ -36,3 +50,14 @@ def get_github_link(
     base_url = get_github_base_url()
     current_hash = get_current_git_hash(passed_git_root)
     return f"{base_url}/blob/{current_hash}/{link.file}#L{link.line}"
+
+
+def get_github_link_from_json(
+    metadata: moduleInfo,
+    link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
+):
+    if link is None:
+        link = DefaultNeedLink()
+    base_url = metadata.url
+    current_hash = metadata.hash
+    return f"{base_url}/blob/{current_hash}/{link.file}#L{link.line}"

From ebdb40faa3b0a400e46bb76952fd3ec766c0bad8 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Wed, 11 Mar 2026 21:55:42 +0100
Subject: [PATCH 02/11] WIP: seems to work in ref & local

---
 scripts_bazel/generate_sourcelinks_cli.py     | 13 ++++++++-----
 .../generate_source_code_links_json.py        | 19 +++++++++++--------
 2 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 27a0e4508..2f26784ff 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -89,15 +89,18 @@ def main():
     for file_path in args.files:
         if "known_good.json" not in str(file_path) and not metadata_set:
             metadata["module_name"] = parse_module_name_from_path(file_path)
-            print("================")
-            print(metadata)
-            print("===============")
-            print("METADATA SET")
+            # print("================")
+            # print(metadata)
+            # print("===============")
+            # print("METADATA SET")
             metadata_set = True
         abs_file_path = file_path.resolve()
         assert abs_file_path.exists(), abs_file_path
+        # print("THIS Is ABS FILEPATH: ", file_path)
+        # print("THIS IS ABS FILEPATH NAME: ", abs_file_path.name)
+        # print("THIS Is ABS FILEPATH PARENT: ", abs_file_path.parent)
         references = _extract_references_from_file(
-            abs_file_path.parent, Path(abs_file_path.name)
+            abs_file_path.parent, Path(abs_file_path.name), file_path
         )
         all_need_references.extend(references)
     store_source_code_links_with_metadata_json(
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index abedc2db4..1c240e0ef 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -19,6 +19,8 @@
 
 import os
 from pathlib import Path
+from sphinx_needs.logging import get_logger
+LOGGER = get_logger(__name__)
 
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
@@ -43,21 +45,21 @@ def _extract_references_from_line(line: str):
                 yield tag, req.strip()
 
 
-def _extract_references_from_file(root: Path, file_path: Path) -> list[NeedLink]:
+def _extract_references_from_file(root: Path, file_path_name: Path, file_path: Path) -> list[NeedLink]:
     """Scan a single file for template strings and return findings."""
     assert root.is_absolute(), "Root path must be absolute"
-    assert not file_path.is_absolute(), "File path must be relative to the root"
+    assert not file_path_name.is_absolute(), "File path must be relative to the root"
     # assert file_path.is_relative_to(root), (
     #     f"File path ({file_path}) must be relative to the root ({root})"
     # )
-    assert (root / file_path).exists(), (
-        f"File {file_path} does not exist in root {root}."
+    assert (root / file_path_name).exists(), (
+        f"File {file_path_name} does not exist in root {root}."
     )
 
     findings: list[NeedLink] = []
 
     try:
-        with open(root / file_path, encoding="utf-8", errors="ignore") as f:
+        with open(root / file_path_name, encoding="utf-8", errors="ignore") as f:
             for line_num, line in enumerate(f, 1):
                 for tag, req in _extract_references_from_line(line):
                     findings.append(
@@ -69,8 +71,9 @@ def _extract_references_from_file(root: Path, file_path: Path) -> list[NeedLink]
                             full_line=line.strip(),
                         )
                     )
-    except (UnicodeDecodeError, PermissionError, OSError):
+    except (UnicodeDecodeError, PermissionError, OSError) as e:
         # Skip files that can't be read as text
+        LOGGER.debug(f"Error reading file to parse for linked needs: \n{e}")
         pass
 
     return findings
@@ -121,8 +124,8 @@ def find_all_need_references(search_path: Path) -> list[NeedLink]:
         all_need_references.extend(references)
 
     elapsed_time = os.times().elapsed - start_time
-    print(
-        f"DEBUG: Found {len(all_need_references)} need references "
+    LOGGER.debug(
+        f"Found {len(all_need_references)} need references "
         f"in {elapsed_time:.2f} seconds"
     )
 

From 7f9f8bb12fdc8280b4b87da4bdba73b23b2f67f2 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:23:22 +0100
Subject: [PATCH 03/11] Remove metadata file

---
 scripts_bazel/generate_sourcelinks_cli.py     |  2 +-
 .../score_source_code_linker/metadata.py      | 23 -------------------
 .../score_source_code_linker/needlinks.py     | 14 ++++++++---
 3 files changed, 12 insertions(+), 27 deletions(-)
 delete mode 100644 src/extensions/score_source_code_linker/metadata.py

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 2f26784ff..6d9336e23 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -27,8 +27,8 @@
 )
 from src.extensions.score_source_code_linker.needlinks import (
     store_source_code_links_with_metadata_json,
+    MetaData,
 )
-from src.extensions.score_source_code_linker.metadata import MetaData
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
diff --git a/src/extensions/score_source_code_linker/metadata.py b/src/extensions/score_source_code_linker/metadata.py
deleted file mode 100644
index 03acc537a..000000000
--- a/src/extensions/score_source_code_linker/metadata.py
+++ /dev/null
@@ -1,23 +0,0 @@
-# *******************************************************************************
-# Copyright (c) 2026 Contributors to the Eclipse Foundation
-#
-# See the NOTICE file(s) distributed with this work for additional
-# information regarding copyright ownership.
-#
-# This program and the accompanying materials are made available under the
-# terms of the Apache License Version 2.0 which is available at
-# https://www.apache.org/licenses/LICENSE-2.0
-#
-# SPDX-License-Identifier: Apache-2.0
-# *******************************************************************************
-
-from typing import TypedDict, TypeGuard
-
-class MetaData(TypedDict):
-    module_name: str
-    hash: str
-    url: str
-
-def is_metadata(x: object) -> TypeGuard[MetaData]:
-    # Make this as strict/loose as you want; at minimum, it must be a dict.
-    return isinstance(x, dict) and {"module_name", "hash", "url"} <= x.keys()
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index a727025bd..abcdd0dbb 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -16,8 +16,17 @@
 import os
 from dataclasses import asdict, dataclass
 from pathlib import Path
-from typing import Any, TypeGuard
-from src.extensions.score_source_code_linker.metadata import MetaData, is_metadata
+from typing import Any, TypeGuard, TypedDict
+
+
+class MetaData(TypedDict):
+    module_name: str
+    hash: str
+    url: str
+
+def is_metadata(x: object) -> TypeGuard[MetaData]:
+    # Make this as strict/loose as you want; at minimum, it must be a dict.
+    return isinstance(x, dict) and {"module_name", "hash", "url"} <= x.keys()
 
 
 @dataclass(order=True)
@@ -187,4 +196,3 @@ def load_source_code_links_json(file: Path) -> list[NeedLink]:
         "All items in source_code_links should be NeedLink objects."
     )
     return links
-

From 403b9e97f5fe8730655ace40bd97ca196304cd0f Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:24:21 +0100
Subject: [PATCH 04/11] Formatting & Linting

---
 scripts_bazel/merge_sourcelinks.py               |  7 +++----
 .../score_source_code_linker/__init__.py         | 16 +++++++---------
 .../generate_source_code_links_json.py           |  2 ++
 .../module_source_links.py                       | 13 ++++++-------
 .../need_source_links.py                         |  2 +-
 src/helper_lib/additional_functions.py           |  3 ++-
 6 files changed, 21 insertions(+), 22 deletions(-)

diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 034d45db5..aa5ece761 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -20,7 +20,6 @@
 import logging
 import sys
 from pathlib import Path
-from typing import Any
 
 # from src.extensions.score_source_code_linker.need_source_links import (
 #     store_source_code_links_combined_json,
@@ -44,8 +43,8 @@
 
 
 """
-if bazel-out/k8-fastbuild/bin/external/ in file_path => module is external 
-otherwise it's local 
+if bazel-out/k8-fastbuild/bin/external/ in file_path => module is external
+otherwise it's local
 if local => module_name & hash == empty
 if external => parse thing for module_name => look up known_good json for hash & url
 """
@@ -56,7 +55,7 @@ def parse_info_from_known_good(
 ) -> tuple[str, str]:
     print("===THIS IS MODULE NAME WE LOOK FOR===========")
     print(module_name)
-    with open(known_good_json, "r") as f:
+    with open(known_good_json) as f:
         kg_json = json.load(f)
     for category in kg_json["modules"].values():
         print("===THIS IS CATEGORY=========")
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index 7e0ff0252..d82994dd0 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -34,20 +34,18 @@
 from src.extensions.score_source_code_linker.generate_source_code_links_json import (
     generate_source_code_links_json,
 )
+from src.extensions.score_source_code_linker.module_source_links import (
+    group_needs_by_module,
+    load_module_source_links_json,
+    store_module_source_links_json,
+)
 from src.extensions.score_source_code_linker.need_source_links import (
     NeedSourceLinks,
     SourceCodeLinks,
+    group_by_need,
     load_source_code_links_combined_json,
     store_source_code_links_combined_json,
-    group_by_need,
 )
-
-from src.extensions.score_source_code_linker.module_source_links import (
-    group_needs_by_module,
-    store_module_source_links_json,
-    load_module_source_links_json,
-)
-
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     load_source_code_links_json,
@@ -376,7 +374,7 @@ def inject_links_into_needs(app: Sphinx, env: BuildEnvironment) -> None:
                 continue
 
             need_as_dict = cast(dict[str, object], need)
-            metadata = module_grouped_needs.module_name
+            metadata = module_grouped_needs.module
             need_as_dict["source_code_link"] = ", ".join(
                 f"{get_github_link(metadata, n)}<>{n.file}:{n.line}"
                 for n in source_code_links.links.CodeLinks
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index 1c240e0ef..ce6839b80 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -19,7 +19,9 @@
 
 import os
 from pathlib import Path
+
 from sphinx_needs.logging import get_logger
+
 LOGGER = get_logger(__name__)
 
 from src.extensions.score_source_code_linker.needlinks import (
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 3957733f0..fe757b947 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -12,11 +12,10 @@
 # *******************************************************************************
 
 
-from dataclasses import dataclass, asdict, field
 import json
-from typing import Any
+from dataclasses import asdict, dataclass, field
 from pathlib import Path
-
+from typing import Any
 
 from src.extensions.score_source_code_linker.need_source_links import (
     NeedSourceLinks,
@@ -36,7 +35,7 @@ class moduleInfo:
 
 @dataclass
 class ModuleSourceLinks:
-    module_name: moduleInfo
+    module: moduleInfo
     needs: list[SourceCodeLinks] = field(default_factory=list)
 
 
@@ -62,7 +61,7 @@ def ModuleSourceLinks_JSON_Decoder(
         module_name = d["module_name"]
         needs = d["needs"]
         return ModuleSourceLinks(
-            module_name=moduleInfo(
+            module=moduleInfo(
                 name=module_name.get("module_name"),
                 hash=module_name.get("hash"),
                 url=module_name.get("url"),
@@ -118,13 +117,13 @@ def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLink
 
         if module_key not in module_groups:
             module_groups[module_key] = ModuleSourceLinks(
-                module_name=moduleInfo(name=module_key, hash=first_link.hash, url=first_link.url)
+                module=moduleInfo(name=module_key, hash=first_link.hash, url=first_link.url)
             )
 
         module_groups[module_key].needs.append(source_link)  # Much clearer!
 
     return [
-        ModuleSourceLinks(module_name=group.module_name, needs=group.needs)
+        ModuleSourceLinks(module=group.module, needs=group.needs)
         for group in module_groups.values()
     ]
 
diff --git a/src/extensions/score_source_code_linker/need_source_links.py b/src/extensions/score_source_code_linker/need_source_links.py
index 2deb4c5e8..1823ba4b4 100644
--- a/src/extensions/score_source_code_linker/need_source_links.py
+++ b/src/extensions/score_source_code_linker/need_source_links.py
@@ -20,8 +20,8 @@
 # req-Id: tool_req__docs_dd_link_source_code_link
 
 import json
-from dataclasses import asdict, dataclass, field
 from collections import defaultdict
+from dataclasses import asdict, dataclass, field
 from pathlib import Path
 from typing import Any
 
diff --git a/src/helper_lib/additional_functions.py b/src/helper_lib/additional_functions.py
index 872d66af2..049a14548 100644
--- a/src/helper_lib/additional_functions.py
+++ b/src/helper_lib/additional_functions.py
@@ -12,9 +12,10 @@
 # *******************************************************************************
 from pathlib import Path
 
+from src.extensions.score_source_code_linker.module_source_links import moduleInfo
+
 # Import types that depend on score_source_code_linker
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink, NeedLink
-from src.extensions.score_source_code_linker.module_source_links import moduleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
     DataOfTestCase,

From bb73a0f97ea399d96d0f2f010cf750185cc657d4 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:26:11 +0100
Subject: [PATCH 05/11] Known_good required in merge script

---
 scripts_bazel/merge_sourcelinks.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index aa5ece761..43785ea91 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -80,7 +80,7 @@ def main():
     )
     _ = parser.add_argument(
         "--known_good",
-        default=None,
+        required=True,
         help="Optional path to a 'known good' JSON file (provided by Bazel).",
     )
     _ = parser.add_argument(

From 703cc71dbe3a11f8e687c16a3722e72836fb0fac Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:30:37 +0100
Subject: [PATCH 06/11] Remove debug print statements

---
 scripts_bazel/generate_sourcelinks_cli.py | 17 +++--------------
 scripts_bazel/merge_sourcelinks.py        |  8 +-------
 2 files changed, 4 insertions(+), 21 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 6d9336e23..8b1c4bfd5 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -44,15 +44,11 @@ def parse_module_name_from_path(path: Path) -> str:
     # COMBO BUILD
     # If external is in the filepath that gets parsed =>
     # file is in an external module => combo build
-    # e.g. .../external/score_docs_as_code+/src/helper_lib/__init__.py
+    # Example Path:
+    #   PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
 
-    # PATH if we are in local repository
-    # PosixPath('src/helper_lib/test_helper_lib.py')
-    # Path if we are in combo build and externally
-    # PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
-    print("======== THIs IS PATH we PARSIGN FOr MODULE NAME")
-    print(path)
     if str(path).startswith("external/"):
+        # This allows for files / folders etc. to have `external` in their name too.
         module_raw = str(path).removeprefix("external/")
         filepath_split = str(module_raw).split("/", maxsplit=1)
         module_name = str(filepath_split[0].removesuffix("+"))
@@ -89,16 +85,9 @@ def main():
     for file_path in args.files:
         if "known_good.json" not in str(file_path) and not metadata_set:
             metadata["module_name"] = parse_module_name_from_path(file_path)
-            # print("================")
-            # print(metadata)
-            # print("===============")
-            # print("METADATA SET")
             metadata_set = True
         abs_file_path = file_path.resolve()
         assert abs_file_path.exists(), abs_file_path
-        # print("THIS Is ABS FILEPATH: ", file_path)
-        # print("THIS IS ABS FILEPATH NAME: ", abs_file_path.name)
-        # print("THIS Is ABS FILEPATH PARENT: ", abs_file_path.parent)
         references = _extract_references_from_file(
             abs_file_path.parent, Path(abs_file_path.name), file_path
         )
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 43785ea91..b956b0bda 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -53,16 +53,10 @@
 def parse_info_from_known_good(
     known_good_json: Path, module_name: str
 ) -> tuple[str, str]:
-    print("===THIS IS MODULE NAME WE LOOK FOR===========")
-    print(module_name)
     with open(known_good_json) as f:
         kg_json = json.load(f)
     for category in kg_json["modules"].values():
-        print("===THIS IS CATEGORY=========")
-        print(category)
         if module_name in category:
-            print("===THIS IS MODULE NAME INSIDe CATEGORY===========")
-            print(module_name)
             m = category[module_name]
             return (m["hash"], m["repo"].removesuffix(".git"))
     raise KeyError(f"Module {module_name!r} not found in known_good_json.")
@@ -104,7 +98,7 @@ def main():
                 )
                 metadata["hash"] = hash
                 metadata["url"] = repo
-            # In the case that 'metadata[module_name]' is empty
+            # In the case that 'metadata[module_name]' is 'local_module' or empty (somehow)
             # hash & url are already existing and empty inside of 'metadata'
             # Therefore all 3 keys will be written to needlinks in each branch
             for d in data[1:]:

From 59f760283c45304bb84e10ca586868b713ad1458 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 13:40:57 +0100
Subject: [PATCH 07/11] Copilot Findings

---
 .../score_source_code_linker/__init__.py           |  4 ++--
 .../module_source_links.py                         | 14 ++++++++------
 .../score_source_code_linker/needlinks.py          |  9 +++------
 src/helper_lib/additional_functions.py             |  6 +++---
 4 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index d82994dd0..6a409b917 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -226,9 +226,9 @@ def register_combined_linker(app: Sphinx):
 
 def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
     grouped_cache = get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
-    gruped_cache_exists = grouped_cache.exists()
+    grouped_cache_exists = grouped_cache.exists()
     # TODO this cache should be done via Bazel
-    if not gruped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
+    if not grouped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
         LOGGER.debug(
             "Did not find combined json 'score_scl_grouped_cache.json' in _build."
             "Generating new one"
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index fe757b947..9197b75ff 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -27,7 +27,7 @@
 
 
 @dataclass
-class moduleInfo:
+class ModuleInfo:
     name: str
     hash: str
     url: str
@@ -35,7 +35,7 @@ class moduleInfo:
 
 @dataclass
 class ModuleSourceLinks:
-    module: moduleInfo
+    module: ModuleInfo
     needs: list[SourceCodeLinks] = field(default_factory=list)
 
 
@@ -48,7 +48,7 @@ def default(self, o: object):
         if isinstance(o, NeedLink):
             return o.to_dict_without_metadata()
         if isinstance(
-            o, ModuleSourceLinks | SourceCodeLinks | DataForTestLink | NeedSourceLinks
+            o, (ModuleSourceLinks, SourceCodeLinks, DataForTestLink, NeedSourceLinks)
         ):
             return asdict(o)
         return super().default(o)
@@ -61,14 +61,14 @@ def ModuleSourceLinks_JSON_Decoder(
         module_name = d["module_name"]
         needs = d["needs"]
         return ModuleSourceLinks(
-            module=moduleInfo(
+            module=ModuleInfo(
                 name=module_name.get("module_name"),
                 hash=module_name.get("hash"),
                 url=module_name.get("url"),
             ),
             # We know this can only be list[SourceCodeLinks] and nothing else
             # Therefore => we ignore the type error here
-            needs=[SourceCodeLinks_JSON_Decoder(need) for need in needs] # type: ignore
+            needs=[SourceCodeLinks_JSON_Decoder(need) for need in needs],  # type: ignore
         )
     return d
 
@@ -117,7 +117,9 @@ def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLink
 
         if module_key not in module_groups:
             module_groups[module_key] = ModuleSourceLinks(
-                module=moduleInfo(name=module_key, hash=first_link.hash, url=first_link.url)
+                module=ModuleInfo(
+                    name=module_key, hash=first_link.hash, url=first_link.url
+                )
             )
 
         module_groups[module_key].needs.append(source_link)  # Much clearer!
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index abcdd0dbb..324e54114 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -42,10 +42,10 @@ class NeedLink:
     hash: str = ""
     url: str = ""
 
-    def to_dict_full(self) -> dict[str, str | Path]:
+    def to_dict_full(self) -> dict[str, str | Path | int]:
         return asdict(self)
 
-    def to_dict_without_metadata(self) -> dict[str, str | Path]:
+    def to_dict_without_metadata(self) -> dict[str, str | Path | int]:
         d = asdict(self)
         d.pop("module_name", None)
         d.pop("hash", None)
@@ -114,10 +114,7 @@ def store_source_code_links_with_metadata_json(
 def store_source_code_links_json(file: Path, needlist: list[NeedLink]) -> None:
     """
     Writes a JSON array:
-      [ meta_dict, needlink1, needlink2, ... ]
-
-    meta_dict must include:
-      module_name, hash, url
+      [ needlink1, needlink2, ... ]
     """
 
     file.parent.mkdir(exist_ok=True)
diff --git a/src/helper_lib/additional_functions.py b/src/helper_lib/additional_functions.py
index 049a14548..21b4d6fd2 100644
--- a/src/helper_lib/additional_functions.py
+++ b/src/helper_lib/additional_functions.py
@@ -12,7 +12,7 @@
 # *******************************************************************************
 from pathlib import Path
 
-from src.extensions.score_source_code_linker.module_source_links import moduleInfo
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 
 # Import types that depend on score_source_code_linker
 from src.extensions.score_source_code_linker.needlinks import DefaultNeedLink, NeedLink
@@ -28,7 +28,7 @@
 
 
 def get_github_link(
-    metadata: moduleInfo,
+    metadata: ModuleInfo,
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
 ) -> str:
     if link is None:
@@ -54,7 +54,7 @@ def get_github_link_from_git(
 
 
 def get_github_link_from_json(
-    metadata: moduleInfo,
+    metadata: ModuleInfo,
     link: NeedLink | DataForTestLink | DataOfTestCase | None = None,
 ):
     if link is None:

From 715544154c9f9b69b3b0ad2848bdb69ac589e315 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 14:06:22 +0100
Subject: [PATCH 08/11] Formatting & Linting

---
 scripts_bazel/generate_sourcelinks_cli.py          |  5 ++---
 scripts_bazel/merge_sourcelinks.py                 | 14 +-------------
 .../score_source_code_linker/__init__.py           | 12 ++++--------
 .../generate_source_code_links_json.py             |  8 +++++---
 .../module_source_links.py                         |  2 +-
 .../score_source_code_linker/needlinks.py          |  2 +-
 6 files changed, 14 insertions(+), 29 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index 8b1c4bfd5..ba54b5d23 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -26,8 +26,8 @@
     _extract_references_from_file,  # pyright: ignore[reportPrivateUsage] TODO: move it out of the extension and into this script
 )
 from src.extensions.score_source_code_linker.needlinks import (
-    store_source_code_links_with_metadata_json,
     MetaData,
+    store_source_code_links_with_metadata_json,
 )
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
@@ -51,8 +51,7 @@ def parse_module_name_from_path(path: Path) -> str:
         # This allows for files / folders etc. to have `external` in their name too.
         module_raw = str(path).removeprefix("external/")
         filepath_split = str(module_raw).split("/", maxsplit=1)
-        module_name = str(filepath_split[0].removesuffix("+"))
-        return module_name
+        return str(filepath_split[0].removesuffix("+"))
     return "local_module"
 
 
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index b956b0bda..626b48c56 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -28,18 +28,6 @@
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
-# [
-# PosixPath('bazel-out/k8-fastbuild/bin/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_persistency+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_orchestrator+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_kyron+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_baselibs+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_baselibs_rust+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_logging+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_platform+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_process+/sourcelinks_json.json'),
-# PosixPath('bazel-out/k8-fastbuild/bin/external/score_docs_as_code+/sourcelinks_json.json')
-# ]
 
 
 """
@@ -98,7 +86,7 @@ def main():
                 )
                 metadata["hash"] = hash
                 metadata["url"] = repo
-            # In the case that 'metadata[module_name]' is 'local_module' or empty (somehow)
+            # In the case that 'metadata[module_name]' is 'local_module'
             # hash & url are already existing and empty inside of 'metadata'
             # Therefore all 3 keys will be written to needlinks in each branch
             for d in data[1:]:
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index 6a409b917..a84ddfb42 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -40,19 +40,15 @@
     store_module_source_links_json,
 )
 from src.extensions.score_source_code_linker.need_source_links import (
-    NeedSourceLinks,
-    SourceCodeLinks,
     group_by_need,
     load_source_code_links_combined_json,
     store_source_code_links_combined_json,
 )
 from src.extensions.score_source_code_linker.needlinks import (
-    NeedLink,
     load_source_code_links_json,
     load_source_code_links_with_metadata_json,
 )
 from src.extensions.score_source_code_linker.testlink import (
-    DataForTestLink,
     load_data_of_test_case_json,
     load_test_xml_parsed_json,
 )
@@ -228,7 +224,10 @@ def setup_combined_linker(app: Sphinx, _: BuildEnvironment):
     grouped_cache = get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
     grouped_cache_exists = grouped_cache.exists()
     # TODO this cache should be done via Bazel
-    if not grouped_cache_exists or not app.config.skip_rescanning_via_source_code_linker:
+    if (
+        not grouped_cache_exists
+        or not app.config.skip_rescanning_via_source_code_linker
+    ):
         LOGGER.debug(
             "Did not find combined json 'score_scl_grouped_cache.json' in _build."
             "Generating new one"
@@ -351,9 +350,6 @@ def inject_links_into_needs(app: Sphinx, env: BuildEnvironment) -> None:
     scl_by_module = load_module_source_links_json(
         get_cache_filename(app.outdir, "score_module_grouped_scl_cache.json")
     )
-    # source_code_links_by_need = load_source_code_links_combined_json(
-    #     get_cache_filename(app.outdir, "score_scl_grouped_cache.json")
-    # )
     for module_grouped_needs in scl_by_module:
         for source_code_links in module_grouped_needs.needs:
             need = find_need(needs_copy, source_code_links.need)
diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index ce6839b80..33ef6af37 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -22,13 +22,13 @@
 
 from sphinx_needs.logging import get_logger
 
-LOGGER = get_logger(__name__)
-
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     store_source_code_links_json,
 )
 
+LOGGER = get_logger(__name__)
+
 TAGS = [
     "# " + "req-traceability:",
     "# " + "req-Id:",
@@ -47,7 +47,9 @@ def _extract_references_from_line(line: str):
                 yield tag, req.strip()
 
 
-def _extract_references_from_file(root: Path, file_path_name: Path, file_path: Path) -> list[NeedLink]:
+def _extract_references_from_file(
+    root: Path, file_path_name: Path, file_path: Path
+) -> list[NeedLink]:
     """Scan a single file for template strings and return findings."""
     assert root.is_absolute(), "Root path must be absolute"
     assert not file_path_name.is_absolute(), "File path must be relative to the root"
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 9197b75ff..887d4b667 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -48,7 +48,7 @@ def default(self, o: object):
         if isinstance(o, NeedLink):
             return o.to_dict_without_metadata()
         if isinstance(
-            o, (ModuleSourceLinks, SourceCodeLinks, DataForTestLink, NeedSourceLinks)
+            o, ModuleSourceLinks | SourceCodeLinks | DataForTestLink | NeedSourceLinks
         ):
             return asdict(o)
         return super().default(o)
diff --git a/src/extensions/score_source_code_linker/needlinks.py b/src/extensions/score_source_code_linker/needlinks.py
index 324e54114..8bc8f9439 100644
--- a/src/extensions/score_source_code_linker/needlinks.py
+++ b/src/extensions/score_source_code_linker/needlinks.py
@@ -16,7 +16,7 @@
 import os
 from dataclasses import asdict, dataclass
 from pathlib import Path
-from typing import Any, TypeGuard, TypedDict
+from typing import Any, TypedDict, TypeGuard
 
 
 class MetaData(TypedDict):

From 2355aa3a4e12ad9984e94349216d35cc516d32ce Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Thu, 12 Mar 2026 14:11:28 +0100
Subject: [PATCH 09/11] Basepyright linting

---
 .../score_source_code_linker/generate_source_code_links_json.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/extensions/score_source_code_linker/generate_source_code_links_json.py b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
index 33ef6af37..7b39b7228 100644
--- a/src/extensions/score_source_code_linker/generate_source_code_links_json.py
+++ b/src/extensions/score_source_code_linker/generate_source_code_links_json.py
@@ -124,7 +124,7 @@ def find_all_need_references(search_path: Path) -> list[NeedLink]:
 
     # Use os.walk to have better control over directory traversal
     for file in iterate_files_recursively(search_path):
-        references = _extract_references_from_file(search_path, file)
+        references = _extract_references_from_file(search_path,Path(file.name), file)
         all_need_references.extend(references)
 
     elapsed_time = os.times().elapsed - start_time

From bb475e882c3ec915bf58d4b59b6e60d5405b7c3b Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Fri, 13 Mar 2026 16:51:28 +0100
Subject: [PATCH 10/11] WIP: Testlinks endlink still wrong

---
 scripts_bazel/BUILD                           |  1 +
 scripts_bazel/generate_sourcelinks_cli.py     | 23 +-------
 scripts_bazel/merge_sourcelinks.py            | 22 +++-----
 src/extensions/score_source_code_linker/BUILD |  1 +
 .../score_source_code_linker/__init__.py      |  2 +-
 .../score_source_code_linker/helpers.py}      | 36 ++++++++++++
 .../module_source_links.py                    | 42 ++++++++------
 .../score_source_code_linker/testlink.py      | 34 +++++++++++
 .../tests/test_codelink.py                    |  2 +-
 .../test_source_code_link_integration.py      |  3 +-
 .../score_source_code_linker/xml_parser.py    | 56 ++++++++++++++++---
 src/helper_lib/BUILD                          |  3 +-
 src/helper_lib/__init__.py                    |  2 +-
 13 files changed, 160 insertions(+), 67 deletions(-)
 rename src/{helper_lib/additional_functions.py => extensions/score_source_code_linker/helpers.py} (60%)

diff --git a/scripts_bazel/BUILD b/scripts_bazel/BUILD
index 81c9212f1..befe51730 100644
--- a/scripts_bazel/BUILD
+++ b/scripts_bazel/BUILD
@@ -33,6 +33,7 @@ py_binary(
 py_binary(
     name = "merge_sourcelinks",
     srcs = ["merge_sourcelinks.py"],
+    deps= [ "//src/extensions/score_source_code_linker"],
     main = "merge_sourcelinks.py",
     visibility = ["//visibility:public"],
 )
diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index ba54b5d23..e1feb8e0b 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -25,36 +25,17 @@
 from src.extensions.score_source_code_linker.generate_source_code_links_json import (
     _extract_references_from_file,  # pyright: ignore[reportPrivateUsage] TODO: move it out of the extension and into this script
 )
+from src.extensions.score_source_code_linker.helpers import parse_module_name_from_path
 from src.extensions.score_source_code_linker.needlinks import (
     MetaData,
     store_source_code_links_with_metadata_json,
 )
 
+
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
 
-def parse_module_name_from_path(path: Path) -> str:
-    """
-    Parse out the Module-Name from the filename gotten
-    /home/user/.cache/bazel/aksj37981712/external/score_docs_as_code+/src/tests/testfile.py
-    => score_docs_as_code
-    """
-
-    # COMBO BUILD
-    # If external is in the filepath that gets parsed =>
-    # file is in an external module => combo build
-    # Example Path:
-    #   PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
-
-    if str(path).startswith("external/"):
-        # This allows for files / folders etc. to have `external` in their name too.
-        module_raw = str(path).removeprefix("external/")
-        filepath_split = str(module_raw).split("/", maxsplit=1)
-        return str(filepath_split[0].removesuffix("+"))
-    return "local_module"
-
-
 def main():
     parser = argparse.ArgumentParser(
         description="Generate source code links JSON from source files"
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index 626b48c56..afb2cc198 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -21,9 +21,7 @@
 import sys
 from pathlib import Path
 
-# from src.extensions.score_source_code_linker.need_source_links import (
-#     store_source_code_links_combined_json,
-# )
+from src.extensions.score_source_code_linker.helpers import parse_info_from_known_good
 
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
@@ -38,17 +36,10 @@
 """
 
 
-def parse_info_from_known_good(
-    known_good_json: Path, module_name: str
-) -> tuple[str, str]:
-    with open(known_good_json) as f:
-        kg_json = json.load(f)
-    for category in kg_json["modules"].values():
-        if module_name in category:
-            m = category[module_name]
-            return (m["hash"], m["repo"].removesuffix(".git"))
-    raise KeyError(f"Module {module_name!r} not found in known_good_json.")
 
+def add_needid_to_metaneed_mapping(mapping: dict[str, dict[str, str]], metadata: dict[str, str], needid: str):
+    mapping
+    pass
 
 def main():
     parser = argparse.ArgumentParser(
@@ -76,6 +67,7 @@ def main():
     all_files = [x for x in args.files if "known_good.json" not in str(x)]
 
     merged = []
+    needs_metadata_mapping = {}
     for json_file in all_files:
         with open(json_file) as f:
             data = json.load(f)
@@ -89,11 +81,11 @@ def main():
             # In the case that 'metadata[module_name]' is 'local_module'
             # hash & url are already existing and empty inside of 'metadata'
             # Therefore all 3 keys will be written to needlinks in each branch
+
             for d in data[1:]:
                 d.update(metadata)
             assert isinstance(data, list), repr(data)
-            merged.extend(data[1:])
-
+            merged.extend(data[1:]) 
     with open(args.output, "w") as f:
         json.dump(merged, f, indent=2, ensure_ascii=False)
 
diff --git a/src/extensions/score_source_code_linker/BUILD b/src/extensions/score_source_code_linker/BUILD
index e3c289c66..55d471374 100644
--- a/src/extensions/score_source_code_linker/BUILD
+++ b/src/extensions/score_source_code_linker/BUILD
@@ -54,6 +54,7 @@ py_library(
         "needlinks.py",
         "testlink.py",
         "xml_parser.py",
+        "helpers.py",
     ],
     imports = ["."],
     visibility = ["//visibility:public"],
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index a84ddfb42..c687e2e3e 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -60,7 +60,7 @@
     find_git_root,
     find_ws_root,
 )
-from src.helper_lib.additional_functions import get_github_link
+from src.extensions.score_source_code_linker.helpers import get_github_link
 
 LOGGER = get_logger(__name__)
 # Uncomment this to enable more verbose logging
diff --git a/src/helper_lib/additional_functions.py b/src/extensions/score_source_code_linker/helpers.py
similarity index 60%
rename from src/helper_lib/additional_functions.py
rename to src/extensions/score_source_code_linker/helpers.py
index 21b4d6fd2..5544e2696 100644
--- a/src/helper_lib/additional_functions.py
+++ b/src/extensions/score_source_code_linker/helpers.py
@@ -10,6 +10,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 # *******************************************************************************
+import json
 from pathlib import Path
 
 from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
@@ -62,3 +63,38 @@ def get_github_link_from_json(
     base_url = metadata.url
     current_hash = metadata.hash
     return f"{base_url}/blob/{current_hash}/{link.file}#L{link.line}"
+
+
+def parse_module_name_from_path(path: Path) -> str:
+    """
+    Parse out the Module-Name from the filename gotten
+    /home/user/.cache/bazel/aksj37981712/external/score_docs_as_code+/src/tests/testfile.py
+    => score_docs_as_code
+    """
+
+    # COMBO BUILD
+    # If external is in the filepath that gets parsed =>
+    # file is in an external module => combo build
+    # Example Path:
+    #   PosixPath('external/score_docs_as_code+/src/helper_lib/test_helper_lib.py'
+
+    if str(path).startswith("external/"):
+        # This allows for files / folders etc. to have `external` in their name too.
+        module_raw = str(path).removeprefix("external/")
+        filepath_split = str(module_raw).split("/", maxsplit=1)
+        return str(filepath_split[0].removesuffix("+"))
+    # We return this when we are in a local build `//:docs` the rest of DaC knows
+    # What to do then if it encounters this module_name
+    return "local_module"
+
+
+def parse_info_from_known_good(
+    known_good_json: Path, module_name: str
+) -> tuple[str, str]:
+    with open(known_good_json) as f:
+        kg_json = json.load(f)
+    for category in kg_json["modules"].values():
+        if module_name in category:
+            m = category[module_name]
+            return (m["hash"], m["repo"].removesuffix(".git"))
+    raise KeyError(f"Module {module_name!r} not found in known_good_json.")
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 887d4b667..97dc27a68 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -15,6 +15,7 @@
 import json
 from dataclasses import asdict, dataclass, field
 from pathlib import Path
+from re import M
 from typing import Any
 
 from src.extensions.score_source_code_linker.need_source_links import (
@@ -43,13 +44,12 @@ class ModuleSourceLinks_JSON_Encoder(json.JSONEncoder):
     def default(self, o: object):
         if isinstance(o, Path):
             return str(o)
-        # We do not want to save the metadata inside the codelink
+        # We do not want to save the metadata inside the codelink or testlink
+        # As we save this already in a structure above it
         # (hash, module_name, url)
-        if isinstance(o, NeedLink):
+        if isinstance(o, NeedLink | DataForTestLink):
             return o.to_dict_without_metadata()
-        if isinstance(
-            o, ModuleSourceLinks | SourceCodeLinks | DataForTestLink | NeedSourceLinks
-        ):
+        if isinstance(o, ModuleSourceLinks | SourceCodeLinks | NeedSourceLinks):
             return asdict(o)
         return super().default(o)
 
@@ -57,14 +57,14 @@ def default(self, o: object):
 def ModuleSourceLinks_JSON_Decoder(
     d: dict[str, Any],
 ) -> ModuleSourceLinks | dict[str, Any]:
-    if "module_name" in d and "needs" in d:
-        module_name = d["module_name"]
+    if "module" in d and "needs" in d:
+        module = d["module"]
         needs = d["needs"]
         return ModuleSourceLinks(
             module=ModuleInfo(
-                name=module_name.get("module_name"),
-                hash=module_name.get("hash"),
-                url=module_name.get("url"),
+                name=module.get("module_name"),
+                hash=module.get("hash"),
+                url=module.get("url"),
             ),
             # We know this can only be list[SourceCodeLinks] and nothing else
             # Therefore => we ignore the type error here
@@ -95,12 +95,16 @@ def load_module_source_links_json(file: Path) -> list[ModuleSourceLinks]:
         object_hook=ModuleSourceLinks_JSON_Decoder,
     )
     assert isinstance(links, list), (
-        "The combined source code linker links should be "
-        "a list of SourceCodeLinks objects."
+        "The ModuleSourceLink json should be aa list of ModuleSourceLink objects."
     )
+    print("=====================")
+    print("=== TESTING LINKS IN ModuleSourceLink === ")
+    for link in links:
+        if not isinstance(link, ModuleSourceLinks):
+            print(f"Link not module_sourcelink: {link}")
+    print("=====================")
     assert all(isinstance(link, ModuleSourceLinks) for link in links), (
-        "All items in combined_source_code_linker_cache should be "
-        "SourceCodeLinks objects."
+        "All items in module source link cache should be ModuleSourceLink objects."
     )
     return links
 
@@ -109,10 +113,14 @@ def group_needs_by_module(links: list[SourceCodeLinks]) -> list[ModuleSourceLink
     module_groups: dict[str, ModuleSourceLinks] = {}
 
     for source_link in links:
-        if not source_link.links.CodeLinks:
+        # Check if we can take moduleInfo from code or testlinks
+        if source_link.links.CodeLinks:
+            first_link = source_link.links.CodeLinks[0]
+        elif source_link.links.TestLinks:
+            first_link = source_link.links.TestLinks[0]
+        else:
+            # This should not happen?
             continue
-
-        first_link = source_link.links.CodeLinks[0]
         module_key = first_link.module_name
 
         if module_key not in module_groups:
diff --git a/src/extensions/score_source_code_linker/testlink.py b/src/extensions/score_source_code_linker/testlink.py
index ee83c7f95..f001cc203 100644
--- a/src/extensions/score_source_code_linker/testlink.py
+++ b/src/extensions/score_source_code_linker/testlink.py
@@ -30,6 +30,7 @@
 
 from sphinx_needs import logging
 
+
 LOGGER = logging.get_logger(__name__)
 
 
@@ -42,6 +43,19 @@ class DataForTestLink:
     verify_type: str
     result: str
     result_text: str = ""
+    module_name: str = ""
+    hash: str = ""
+    url: str = ""
+
+    def to_dict_full(self) -> dict[str, str | Path | int]:
+        return asdict(self)
+
+    def to_dict_without_metadata(self) -> dict[str, str | Path | int]:
+        d = asdict(self)
+        d.pop("module_name", None)
+        d.pop("hash", None)
+        d.pop("url", None)
+        return d
 
 
 class DataForTestLink_JSON_Encoder(json.JSONEncoder):
@@ -60,6 +74,9 @@ def DataForTestLink_JSON_Decoder(d: dict[str, Any]) -> DataForTestLink | dict[st
         "line",
         "need",
         "verify_type",
+        "module_name",
+        "hash",
+        "url",
         "result",
         "result_text",
     } <= d.keys():
@@ -68,6 +85,9 @@ def DataForTestLink_JSON_Decoder(d: dict[str, Any]) -> DataForTestLink | dict[st
             file=Path(d["file"]),
             line=d["line"],
             need=d["need"],
+            module_name=d.get("module_name", ""),
+            hash=d.get("hash", ""),
+            url=d.get("url", ""),
             verify_type=d["verify_type"],
             result=d["result"],
             result_text=d["result_text"],
@@ -83,6 +103,9 @@ class DataOfTestCase:
     file: str | None = None
     line: str | None = None
     result: str | None = None  # passed | falied | skipped | disabled
+    module_name: str | None = None
+    hash: str | None = None
+    url: str | None = None
     # Intentionally not snakecase to make dict parsing simple
     TestType: str | None = None
     DerivationTechnique: str | None = None
@@ -98,6 +121,9 @@ def from_dict(cls, data: dict[str, Any]):  # type-ignore
             file=data.get("file"),
             line=data.get("line"),
             result=data.get("result"),
+            module_name=data.get("module_name"),
+            hash=data.get("hash"),
+            url=data.get("url"),
             TestType=data.get("TestType"),
             DerivationTechnique=data.get("DerivationTechnique"),
             result_text=data.get("result_text"),
@@ -158,6 +184,8 @@ def is_valid(self) -> bool:
         #         and self.TestType is not None
         #         and self.DerivationTechnique is not None
         # ):
+        # Hash & URL are explictily allowed to be empty but not none.
+        # module_name has to be always filled or something went wrong
         fields = [
             x
             for x in self.__dataclass_fields__
@@ -199,6 +227,9 @@ def parse_attributes(verify_field: str | None, verify_type: str):
             assert self.file is not None
             assert self.line is not None
             assert self.result is not None
+            assert self.module_name is not None
+            assert self.hash is not None
+            assert self.url is not None
             assert self.result_text is not None
             assert self.TestType is not None
             assert self.DerivationTechnique is not None
@@ -212,6 +243,9 @@ def parse_attributes(verify_field: str | None, verify_type: str):
                     verify_type=verify_type,
                     result=self.result,
                     result_text=self.result_text,
+                    module_name=self.module_name,
+                    hash=self.hash,
+                    url=self.url,
                 )
 
         return list(
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 29ddc7235..9615c0058 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -43,7 +43,7 @@
 from src.helper_lib import (
     get_current_git_hash,
 )
-from src.helper_lib.additional_functions import get_github_link
+from src.extensions.score_source_code_linker.helpers import get_github_link
 
 """
 #          ────────────────ATTENTION───────────────
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index 60bb98f80..01bb7ff58 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -37,7 +37,8 @@
     SourceCodeLinks_TEST_JSON_Decoder,
 )
 from src.helper_lib import find_ws_root, get_github_base_url
-from src.helper_lib.additional_functions import get_github_link
+
+from src.extensions.score_source_code_linker.helpers import  get_github_link
 
 
 @pytest.fixture()
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index 8432e1fc3..6facb983b 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -33,18 +33,41 @@
 from sphinx_needs import logging
 from sphinx_needs.api import add_external_need
 
+from src.extensions.score_source_code_linker.needlinks import (
+    MetaData,
+)
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataOfTestCase,
     store_data_of_test_case_json,
     store_test_xml_parsed_json,
 )
 from src.helper_lib import find_ws_root
-from src.helper_lib.additional_functions import get_github_link
+from src.extensions.score_source_code_linker.helpers import (
+    get_github_link,
+    parse_info_from_known_good,
+    parse_module_name_from_path,
+)
 
 logger = logging.get_logger(__name__)
 logger.setLevel("DEBUG")
 
 
+def get_metadata_from_test_path(filepath: Path) -> MetaData:
+    known_good_json = os.environ.get("KNOWN_GOOD_JSON")
+    module_name = parse_module_name_from_path(filepath)
+    md: MetaData = {
+        "module_name": module_name,
+        "hash": "",
+        "url": "",
+    }
+    if module_name != "local_module" and known_good_json:
+        md["hash"], md["url"] = parse_info_from_known_good(
+            Path(known_good_json), module_name
+        )
+    return md
+
+
 def parse_testcase_result(testcase: ET.Element) -> tuple[str, str]:
     """
     Returns 'result' and 'result_text' found in the 'message'
@@ -101,7 +124,7 @@ def read_test_xml_file(file: Path) -> tuple[list[DataOfTestCase], list[str], lis
     missing_prop_tests: list[str] = []
     tree = ET.parse(file)
     root = tree.getroot()
-
+    md = get_metadata_from_test_path(file)
     for testsuite in root.findall("testsuite"):
         for testcase in testsuite.findall("testcase"):
             case_properties = {}
@@ -161,6 +184,7 @@ def read_test_xml_file(file: Path) -> tuple[list[DataOfTestCase], list[str], lis
             # If the is_valid method would return 'False' anyway.
             # I just can't think of it right now, leaving this for future me
             case_properties = parse_properties(case_properties, properties_element)
+            case_properties.update(md)
             test_case = DataOfTestCase.from_dict(case_properties)
             if not test_case.is_valid():
                 missing_prop_tests.append(testname)
@@ -169,6 +193,7 @@ def read_test_xml_file(file: Path) -> tuple[list[DataOfTestCase], list[str], lis
     return test_case_needs, non_prop_tests, missing_prop_tests
 
 
+# /home/maximilianp/score_personal/reference_integration/bazel-testlogs/external/score_docs_as_code+/src/helper_lib/helper_lib_tests/test.xml
 def find_xml_files(dir: Path) -> list[Path]:
     """
     Recursively search all test.xml files inside 'bazel-testlogs'
@@ -183,18 +208,21 @@ def find_xml_files(dir: Path) -> list[Path]:
     for root, _, files in os.walk(dir):
         if test_file_name in files:
             xml_paths.append(Path(os.path.join(root, test_file_name)))
+    print("=========================================")
+    print(xml_paths[0])
+    print("=========================================")
     return xml_paths
 
 
-def find_test_folder(base_path: Path | None = None) -> Path | None:
+def find_test_folder(base_path: Path | None = None) -> tuple[Path | None, Path | None]:
     ws_root = base_path if base_path is not None else find_ws_root()
     assert ws_root is not None
     if os.path.isdir(ws_root / "tests-report"):
-        return ws_root / "tests-report"
+        return ws_root, ws_root / "tests-report"
     if os.path.isdir(ws_root / "bazel-testlogs"):
-        return ws_root / "bazel-testlogs"
+        return ws_root, ws_root / "bazel-testlogs"
     logger.info("could not find tests-report or bazel-testlogs to parse testcases")
-    return None
+    return ws_root, None
 
 
 def run_xml_parser(app: Sphinx, env: BuildEnvironment):
@@ -203,11 +231,19 @@ def run_xml_parser(app: Sphinx, env: BuildEnvironment):
     building testcase needs.
     It gets called from the source_code_linker __init__
     """
-    testlogs_dir = find_test_folder()
+    root_path, testlogs_dir = find_test_folder()
     # early return
     if testlogs_dir is None:
         return
     xml_file_paths = find_xml_files(testlogs_dir)
+    # scl_with_metadata = load_source_code_links_with_metadata_json(
+    #     app.outdir / "score_source_links_metadata.json"
+    # )[0]
+    # metadata: MetaData = {
+    #     "module_name": scl_with_metadata.module_name,
+    #     "hash": scl_with_metadata.hash,
+    #     "url": scl_with_metadata.url,
+    # }
     test_case_needs = build_test_needs_from_files(app, env, xml_file_paths)
     # Saving the test case needs for cache
     store_data_of_test_case_json(
@@ -262,6 +298,10 @@ def construct_and_add_need(app: Sphinx, tn: DataOfTestCase):
     # and either 'Fully' or 'PartiallyVerifies' should not be None here
     assert tn.file is not None
     assert tn.name is not None
+    assert tn.module_name is not None
+    assert tn.hash is not None
+    assert tn.url is not None
+    metadata = ModuleInfo(name=tn.module_name, hash=tn.hash, url=tn.url)
     # IDK if this is ideal or not
     with contextlib.suppress(BaseException):
         _ = add_external_need(
@@ -271,7 +311,7 @@ def construct_and_add_need(app: Sphinx, tn: DataOfTestCase):
             tags="TEST",
             id=f"testcase__{tn.name}_{short_hash(tn.file + tn.name).upper()}",
             name=tn.name,
-            external_url=get_github_link(tn),
+            external_url=get_github_link(metadata, tn),
             fully_verifies=tn.FullyVerifies if tn.FullyVerifies is not None else "",
             partially_verifies=tn.PartiallyVerifies
             if tn.PartiallyVerifies is not None
diff --git a/src/helper_lib/BUILD b/src/helper_lib/BUILD
index 748a2a730..ad6316363 100644
--- a/src/helper_lib/BUILD
+++ b/src/helper_lib/BUILD
@@ -27,8 +27,7 @@ py_library(
     visibility = ["//visibility:public"],
     deps = [
         "@rules_python//python/runfiles",
-        "@score_docs_as_code//src/extensions/score_source_code_linker:source_code_linker_helpers",
-    ],
+    ] + all_requirements,
 )
 
 score_py_pytest(
diff --git a/src/helper_lib/__init__.py b/src/helper_lib/__init__.py
index 5699e478d..a72fffb0b 100644
--- a/src/helper_lib/__init__.py
+++ b/src/helper_lib/__init__.py
@@ -17,7 +17,7 @@
 from pathlib import Path
 from typing import Any
 
-from runfiles import Runfiles
+from python.runfiles import Runfiles
 from sphinx.config import Config
 from sphinx_needs.logging import get_logger
 

From 996a51e2da92535bcd0f300c84f907b910b22395 Mon Sep 17 00:00:00 2001
From: MaximilianSoerenPollak <maximilian.pollak@qorix.com>
Date: Fri, 13 Mar 2026 16:52:42 +0100
Subject: [PATCH 11/11] Formatting

---
 scripts_bazel/generate_sourcelinks_cli.py            |  1 -
 scripts_bazel/merge_sourcelinks.py                   |  2 +-
 src/extensions/score_source_code_linker/__init__.py  |  2 +-
 .../score_source_code_linker/module_source_links.py  |  1 -
 src/extensions/score_source_code_linker/testlink.py  |  1 -
 .../score_source_code_linker/tests/test_codelink.py  |  2 +-
 .../tests/test_source_code_link_integration.py       |  3 +--
 .../score_source_code_linker/xml_parser.py           | 12 ++++++------
 8 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/scripts_bazel/generate_sourcelinks_cli.py b/scripts_bazel/generate_sourcelinks_cli.py
index e1feb8e0b..6f09ef075 100644
--- a/scripts_bazel/generate_sourcelinks_cli.py
+++ b/scripts_bazel/generate_sourcelinks_cli.py
@@ -31,7 +31,6 @@
     store_source_code_links_with_metadata_json,
 )
 
-
 logging.basicConfig(level=logging.INFO, format="%(message)s")
 logger = logging.getLogger(__name__)
 
diff --git a/scripts_bazel/merge_sourcelinks.py b/scripts_bazel/merge_sourcelinks.py
index afb2cc198..932d91380 100644
--- a/scripts_bazel/merge_sourcelinks.py
+++ b/scripts_bazel/merge_sourcelinks.py
@@ -85,7 +85,7 @@ def main():
             for d in data[1:]:
                 d.update(metadata)
             assert isinstance(data, list), repr(data)
-            merged.extend(data[1:]) 
+            merged.extend(data[1:])
     with open(args.output, "w") as f:
         json.dump(merged, f, indent=2, ensure_ascii=False)
 
diff --git a/src/extensions/score_source_code_linker/__init__.py b/src/extensions/score_source_code_linker/__init__.py
index c687e2e3e..d80754036 100644
--- a/src/extensions/score_source_code_linker/__init__.py
+++ b/src/extensions/score_source_code_linker/__init__.py
@@ -34,6 +34,7 @@
 from src.extensions.score_source_code_linker.generate_source_code_links_json import (
     generate_source_code_links_json,
 )
+from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.module_source_links import (
     group_needs_by_module,
     load_module_source_links_json,
@@ -60,7 +61,6 @@
     find_git_root,
     find_ws_root,
 )
-from src.extensions.score_source_code_linker.helpers import get_github_link
 
 LOGGER = get_logger(__name__)
 # Uncomment this to enable more verbose logging
diff --git a/src/extensions/score_source_code_linker/module_source_links.py b/src/extensions/score_source_code_linker/module_source_links.py
index 97dc27a68..b77450eb8 100644
--- a/src/extensions/score_source_code_linker/module_source_links.py
+++ b/src/extensions/score_source_code_linker/module_source_links.py
@@ -15,7 +15,6 @@
 import json
 from dataclasses import asdict, dataclass, field
 from pathlib import Path
-from re import M
 from typing import Any
 
 from src.extensions.score_source_code_linker.need_source_links import (
diff --git a/src/extensions/score_source_code_linker/testlink.py b/src/extensions/score_source_code_linker/testlink.py
index f001cc203..bd7139271 100644
--- a/src/extensions/score_source_code_linker/testlink.py
+++ b/src/extensions/score_source_code_linker/testlink.py
@@ -30,7 +30,6 @@
 
 from sphinx_needs import logging
 
-
 LOGGER = logging.get_logger(__name__)
 
 
diff --git a/src/extensions/score_source_code_linker/tests/test_codelink.py b/src/extensions/score_source_code_linker/tests/test_codelink.py
index 9615c0058..9d3fa78f5 100644
--- a/src/extensions/score_source_code_linker/tests/test_codelink.py
+++ b/src/extensions/score_source_code_linker/tests/test_codelink.py
@@ -35,6 +35,7 @@
     get_cache_filename,
     group_by_need,
 )
+from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.needlinks import (
     NeedLink,
     load_source_code_links_json,
@@ -43,7 +44,6 @@
 from src.helper_lib import (
     get_current_git_hash,
 )
-from src.extensions.score_source_code_linker.helpers import get_github_link
 
 """
 #          ────────────────ATTENTION───────────────
diff --git a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
index 01bb7ff58..b4e65279d 100644
--- a/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
+++ b/src/extensions/score_source_code_linker/tests/test_source_code_link_integration.py
@@ -25,6 +25,7 @@
 from sphinx.testing.util import SphinxTestApp
 from sphinx_needs.data import SphinxNeedsData
 
+from src.extensions.score_source_code_linker.helpers import get_github_link
 from src.extensions.score_source_code_linker.needlinks import NeedLink
 from src.extensions.score_source_code_linker.testlink import (
     DataForTestLink,
@@ -38,8 +39,6 @@
 )
 from src.helper_lib import find_ws_root, get_github_base_url
 
-from src.extensions.score_source_code_linker.helpers import  get_github_link
-
 
 @pytest.fixture()
 def sphinx_base_dir(tmp_path_factory: TempPathFactory) -> Path:
diff --git a/src/extensions/score_source_code_linker/xml_parser.py b/src/extensions/score_source_code_linker/xml_parser.py
index 6facb983b..123ebd5d8 100644
--- a/src/extensions/score_source_code_linker/xml_parser.py
+++ b/src/extensions/score_source_code_linker/xml_parser.py
@@ -33,21 +33,21 @@
 from sphinx_needs import logging
 from sphinx_needs.api import add_external_need
 
+from src.extensions.score_source_code_linker.helpers import (
+    get_github_link,
+    parse_info_from_known_good,
+    parse_module_name_from_path,
+)
+from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 from src.extensions.score_source_code_linker.needlinks import (
     MetaData,
 )
-from src.extensions.score_source_code_linker.module_source_links import ModuleInfo
 from src.extensions.score_source_code_linker.testlink import (
     DataOfTestCase,
     store_data_of_test_case_json,
     store_test_xml_parsed_json,
 )
 from src.helper_lib import find_ws_root
-from src.extensions.score_source_code_linker.helpers import (
-    get_github_link,
-    parse_info_from_known_good,
-    parse_module_name_from_path,
-)
 
 logger = logging.get_logger(__name__)
 logger.setLevel("DEBUG")