From 6dc1846fbe0b3939a089964bc2b8867db57f4d9d Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:25:01 -0500
Subject: [PATCH 01/15] [lh]inting

---
 chord_drs/backend.py  |  2 +-
 chord_drs/commands.py |  4 ++--
 chord_drs/models.py   |  3 +--
 chord_drs/routes.py   | 37 ++++++++++++++++++++-----------------
 4 files changed, 24 insertions(+), 22 deletions(-)

diff --git a/chord_drs/backend.py b/chord_drs/backend.py
index 22efb9c..ef12287 100644
--- a/chord_drs/backend.py
+++ b/chord_drs/backend.py
@@ -23,5 +23,5 @@ def get_backend() -> Optional[Backend]:
     return g.backend
 
 
-def close_backend(_e=None):
+def close_backend(_e=None) -> None:
     g.pop("backend", None)
diff --git a/chord_drs/commands.py b/chord_drs/commands.py
index 5dd3c9b..5c9e411 100644
--- a/chord_drs/commands.py
+++ b/chord_drs/commands.py
@@ -33,7 +33,7 @@ def create_drs_bundle(location: str, parent: Optional[DrsBundle] = None) -> DrsB
     return bundle
 
 
-def create_drs_object(location: str, parent: Optional[DrsBundle] = None):
+def create_drs_object(location: str, parent: Optional[DrsBundle] = None) -> None:
     drs_object = DrsObject(location=location)
 
     if parent:
@@ -47,7 +47,7 @@ def create_drs_object(location: str, parent: Optional[DrsBundle] = None):
 @click.command("ingest")
 @click.argument("source")
 @with_appcontext
-def ingest(source: str):
+def ingest(source: str) -> None:
     """
     When provided with a file or a directory, this command will add these
     to our list of objects, to be served by the application.
diff --git a/chord_drs/models.py b/chord_drs/models.py
index 62a4ef5..11cd1df 100644
--- a/chord_drs/models.py
+++ b/chord_drs/models.py
@@ -9,7 +9,6 @@
 
 from chord_drs.backend import get_backend
 from chord_drs.backends.minio import MinioBackend
-from chord_drs.constants import SERVICE_NAME
 from chord_drs.db import db
 from chord_drs.utils import drs_file_checksum
 
@@ -77,7 +76,7 @@ def __init__(self, *args, **kwargs):
         try:
             current_location = backend.save(location, new_filename)
         except Exception as e:
-            current_app.logger.error(f"[{SERVICE_NAME}] Encountered exception during DRS object creation: {e}")
+            current_app.logger.error(f"Encountered exception during DRS object creation: {e}")
             # TODO: implement more specific exception handling
             raise Exception("Well if the file is not saved... we can't do squat")
 
diff --git a/chord_drs/routes.py b/chord_drs/routes.py
index 9225ad7..b415f8d 100644
--- a/chord_drs/routes.py
+++ b/chord_drs/routes.py
@@ -94,7 +94,7 @@ def build_object_json(drs_object: DrsObject, inside_container: bool = False) ->
     default_access_method = {
         "access_url": {
             "url": url_for("drs_service.object_download", object_id=drs_object.id, _external=True)
-            # No headers means that auth will have to be obtained via some
+            # No headers --> auth will have to be obtained via some
             # out-of-band method, or the object's contents are public. This
             # will depend on how the service is deployed.
         },
@@ -187,8 +187,8 @@ def service_info():
 @drs_service.route("/objects/<string:object_id>", methods=["GET"])
 @drs_service.route("/ga4gh/drs/v1/objects/<string:object_id>", methods=["GET"])
 def object_info(object_id: str):
-    drs_bundle = DrsBundle.query.filter_by(id=object_id).first()
-    drs_object = None
+    drs_bundle: Optional[DrsBundle] = DrsBundle.query.filter_by(id=object_id).first()
+    drs_object: Optional[DrsObject] = None
 
     if not drs_bundle:  # Only try hitting the database for an object if no bundle was found
         drs_object = DrsObject.query.filter_by(id=object_id).first()
@@ -196,21 +196,21 @@ def object_info(object_id: str):
         if not drs_object:
             return flask_errors.flask_not_found_error("No object found for this ID")
 
-    # Are we inside the bento singularity container? if so, provide local accessmethod
-    inside_container = request.headers.get("X-CHORD-Internal", "0") == "1"
-
     # Log X-CHORD-Internal header
-    current_app.logger.info(
-        f"[{SERVICE_NAME}] object_info X-CHORD-Internal: {request.headers.get('X-CHORD-Internal', 'not set')}"
-    )
+    current_app.logger.info(f"object_info X-CHORD-Internal: {request.headers.get('X-CHORD-Internal', 'not set')}")
+
+    # Are we inside the bento singularity container? if so, provide local access method
+    inside_container = request.headers.get("X-CHORD-Internal", "0") == "1"
 
     # The requester can specify object internal path to be added to the response
     use_internal_path = strtobool(request.args.get("internal_path", ""))
 
+    include_internal_path = inside_container or use_internal_path
+
     if drs_bundle:
-        response = build_bundle_json(drs_bundle, inside_container=(inside_container or use_internal_path))
+        response = build_bundle_json(drs_bundle, inside_container=include_internal_path)
     else:
-        response = build_object_json(drs_object, inside_container=(inside_container or use_internal_path))
+        response = build_object_json(drs_object, inside_container=include_internal_path)
 
     return jsonify(response)
 
@@ -237,6 +237,8 @@ def object_search():
 
 @drs_service.route("/objects/<string:object_id>/download", methods=["GET"])
 def object_download(object_id):
+    logger = current_app.logger
+
     try:
         drs_object = DrsObject.query.filter_by(id=object_id).one()
     except NoResultFound:
@@ -256,23 +258,23 @@ def object_download(object_id):
                 download_name=drs_object.name,
             )
 
-        current_app.logger.debug(f"Found Range header: {range_header}")
+        logger.debug(f"Found Range header: {range_header}")
 
         rh_split = range_header.split("=")
         if len(rh_split) != 2 or rh_split[0] != "bytes":
             err = f"Malformatted range header: expected bytes=X-Y or bytes=X-, got {range_header}"
-            current_app.logger.error(err)
+            logger.error(err)
             return flask_errors.flask_bad_request_error(err)
 
         byte_range = rh_split[1].strip().split("-")
-        current_app.logger.debug(f"Retrieving byte range {byte_range}")
+        logger.debug(f"Retrieving byte range {byte_range}")
 
         start = int(byte_range[0])
         end = int(byte_range[1]) if byte_range[1] else None
 
         if end is not None and end < start:
             err = f"Invalid range header: end cannot be less than start (start={start}, end={end})"
-            current_app.logger.error(err)
+            logger.error(err)
             return flask_errors.flask_bad_request_error(err)
 
         def generate_bytes():
@@ -282,7 +284,7 @@ def generate_bytes():
 
                 # Then, read in either CHUNK_SIZE byte segments or however many bytes are left to send, whichever is
                 # left. This avoids filling memory with the contents of large files.
-                byte_offset = start
+                byte_offset: int = start
                 while True:
                     # Add a 1 to the amount to read if it's below chunk size, because the last coordinate is inclusive.
                     data = fh2.read(min(CHUNK_SIZE, (end + 1 - byte_offset) if end is not None else CHUNK_SIZE))
@@ -319,6 +321,7 @@ def generate_bytes():
 
 @drs_service.route("/private/ingest", methods=["POST"])
 def object_ingest():
+    logger = current_app.logger
     data = request.json or {}
 
     obj_path: str = data.get("path")
@@ -342,7 +345,7 @@ def object_ingest():
             db.session.add(drs_object)
             db.session.commit()
         except Exception as e:  # TODO: More specific handling
-            current_app.logger.error(f"[{SERVICE_NAME}] Encountered exception during ingest: {e}")
+            logger.error(f"Encountered exception during ingest: {e}")
             return flask_errors.flask_bad_request_error("Error while creating the object")
 
     response = build_object_json(drs_object)

From fbcf186441a15c43bf83c0339472de8de65abe1d Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:25:24 -0500
Subject: [PATCH 02/15] chore!: default deduplication to True instead of False

---
 chord_drs/routes.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/chord_drs/routes.py b/chord_drs/routes.py
index b415f8d..222a55c 100644
--- a/chord_drs/routes.py
+++ b/chord_drs/routes.py
@@ -329,14 +329,15 @@ def object_ingest():
     if not obj_path or not isinstance(obj_path, str):
         return flask_errors.flask_bad_request_error("Missing or invalid path parameter in JSON request")
 
-    # TODO: Should this always be the case?
-    deduplicate: bool = data.get("deduplicate", False)
-
     drs_object: Optional[DrsObject] = None
+    deduplicate: bool = data.get("deduplicate", True)  # Change for v0.9: default to True
+
     if deduplicate:
         # Get checksum of original file, and query database for objects that match
         checksum = drs_file_checksum(obj_path)
         drs_object = DrsObject.query.filter_by(checksum=checksum).first()
+        if drs_object:
+            logger.info(f"Found duplicate DRS object via checksum (will deduplicate): {drs_object}")
 
     if not drs_object:
         try:

From 3c47fea879f470d103ac45d99b646515a807f758 Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:25:48 -0500
Subject: [PATCH 03/15] feat: git commit in bento service-info

---
 chord_drs/routes.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/chord_drs/routes.py b/chord_drs/routes.py
index 222a55c..8df8057 100644
--- a/chord_drs/routes.py
+++ b/chord_drs/routes.py
@@ -176,6 +176,8 @@ def service_info():
             res_branch_str = res_branch.decode().strip()
             info["git_branch"] = res_branch_str
             info["bento"]["gitBranch"] = res_branch_str
+        if res_commit := subprocess.check_output(["git", "rev-parse", "HEAD"]):
+            info["bento"]["gitCommit"] = res_commit.decode().strip()
 
     except Exception as e:
         except_name = type(e).__name__

From ca87184be64bd511117079e29eee81690c963710 Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:25:55 -0500
Subject: [PATCH 04/15] chore: additional logging

---
 chord_drs/routes.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/chord_drs/routes.py b/chord_drs/routes.py
index 8df8057..2852637 100644
--- a/chord_drs/routes.py
+++ b/chord_drs/routes.py
@@ -329,6 +329,7 @@ def object_ingest():
     obj_path: str = data.get("path")
 
     if not obj_path or not isinstance(obj_path, str):
+        logger.error(f"Missing or invalid path parameter in JSON request: {obj_path}")
         return flask_errors.flask_bad_request_error("Missing or invalid path parameter in JSON request")
 
     drs_object: Optional[DrsObject] = None
@@ -344,9 +345,9 @@ def object_ingest():
     if not drs_object:
         try:
             drs_object = DrsObject(location=obj_path)
-
             db.session.add(drs_object)
             db.session.commit()
+            logger.info(f"Added DRS object: {drs_object}")
         except Exception as e:  # TODO: More specific handling
             logger.error(f"Encountered exception during ingest: {e}")
             return flask_errors.flask_bad_request_error("Error while creating the object")

From 8ae8d41c368750a4e1ad37ab267842775898a683 Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:26:01 -0500
Subject: [PATCH 05/15] chore: bump version to 0.9.0

---
 chord_drs/package.cfg | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/chord_drs/package.cfg b/chord_drs/package.cfg
index e35a06b..f59d4ab 100644
--- a/chord_drs/package.cfg
+++ b/chord_drs/package.cfg
@@ -1,5 +1,5 @@
 [package]
 name = chord_drs
-version = 0.8.0
+version = 0.9.0
 authors = Simon Chénard, David Lougheed
 author_emails = simon.chenard2@mcgill.ca, david.lougheed@mail.mcgill.ca

From f213ca8e8ad2e9bdfb19b34042fbca33a291302e Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:31:51 -0500
Subject: [PATCH 06/15] chore: update test deps

---
 requirements.txt | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index bbc1f6b..8cce86b 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -66,16 +66,17 @@ pytz==2022.7.1
 PyYAML==5.4.1
 redis==3.5.3
 requests==2.28.2
-responses==0.13.4
+responses==0.22.0
 s3transfer==0.5.0
 six==1.16.0
 SQLAlchemy==1.4.46
 toml==0.10.2
 tomli==2.0.1
-tox==4.3.5
+tox==4.4.4
+types-toml==0.10.8.3
 urllib3==1.26.14
-virtualenv==20.17.1
+virtualenv==20.18.0
 Werkzeug==2.2.2
 xmltodict==0.12.0
 yarl==1.8.2
-zipp==3.11.0
+zipp==3.12.1

From cb266c299832c8b7fb426697ec63dc720737fd8c Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:32:04 -0500
Subject: [PATCH 07/15] fix: handle file not found when checking checksum for
 dedup

---
 chord_drs/routes.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/chord_drs/routes.py b/chord_drs/routes.py
index 2852637..a9fe5e2 100644
--- a/chord_drs/routes.py
+++ b/chord_drs/routes.py
@@ -337,7 +337,14 @@ def object_ingest():
 
     if deduplicate:
         # Get checksum of original file, and query database for objects that match
-        checksum = drs_file_checksum(obj_path)
+
+        try:
+            checksum = drs_file_checksum(obj_path)
+        except FileNotFoundError:
+            err = f"File not found at path {obj_path}"
+            logger.error(err)
+            return flask_errors.flask_bad_request_error(err)
+
         drs_object = DrsObject.query.filter_by(checksum=checksum).first()
         if drs_object:
             logger.info(f"Found duplicate DRS object via checksum (will deduplicate): {drs_object}")

From 438b3cfc1512f4140115c4238082c6574860be41 Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:32:11 -0500
Subject: [PATCH 08/15] fix: tests

---
 tests/test_routes.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tests/test_routes.py b/tests/test_routes.py
index 4fe9820..0684d68 100644
--- a/tests/test_routes.py
+++ b/tests/test_routes.py
@@ -213,11 +213,11 @@ def test_object_ingest(client):
 
 def test_object_ingest_x2(client):
     data_1 = _ingest_one(client)
-    data_2 = _ingest_one(client)
-    assert data_1["id"] != data_2["id"]
+    data_2 = _ingest_one(client, data_1["id"])
+    assert json.dumps(data_1, sort_keys=True) == json.dumps(data_2, sort_keys=True)  # deduplicate is True by default
 
 
-def test_object_ingest_deduplicate(client):
+def test_object_ingest_no_deduplicate(client):
     data_1 = _ingest_one(client)
-    data_2 = _ingest_one(client, data_1["id"], {"deduplicate": True})
-    assert json.dumps(data_1, sort_keys=True) == json.dumps(data_2, sort_keys=True)
+    data_2 = _ingest_one(client, params={"deduplicate": False})
+    assert json.dumps(data_1, sort_keys=True) != json.dumps(data_2, sort_keys=True)

From ef72c9f39840218413fa62b36c72e951d49a586f Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:52:03 -0500
Subject: [PATCH 09/15] fix: range header error handling test: range header
 error states

---
 chord_drs/routes.py  | 14 +++++++++-----
 tests/test_routes.py | 12 ++++++++++++
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/chord_drs/routes.py b/chord_drs/routes.py
index a9fe5e2..15001b6 100644
--- a/chord_drs/routes.py
+++ b/chord_drs/routes.py
@@ -261,18 +261,22 @@ def object_download(object_id):
             )
 
         logger.debug(f"Found Range header: {range_header}")
+        range_err = f"Malformatted range header: expected bytes=X-Y or bytes=X-, got {range_header}"
 
         rh_split = range_header.split("=")
         if len(rh_split) != 2 or rh_split[0] != "bytes":
-            err = f"Malformatted range header: expected bytes=X-Y or bytes=X-, got {range_header}"
-            logger.error(err)
-            return flask_errors.flask_bad_request_error(err)
+            logger.error(range_err)
+            return flask_errors.flask_bad_request_error(range_err)
 
         byte_range = rh_split[1].strip().split("-")
         logger.debug(f"Retrieving byte range {byte_range}")
 
-        start = int(byte_range[0])
-        end = int(byte_range[1]) if byte_range[1] else None
+        try:
+            start = int(byte_range[0])
+            end = int(byte_range[1]) if byte_range[1] else None
+        except (IndexError, ValueError):
+            logger.error(range_err)
+            return flask_errors.flask_bad_request_error(range_err)
 
         if end is not None and end < start:
             err = f"Invalid range header: end cannot be less than start (start={start}, end={end})"
diff --git a/tests/test_routes.py b/tests/test_routes.py
index 0684d68..f087518 100644
--- a/tests/test_routes.py
+++ b/tests/test_routes.py
@@ -84,6 +84,7 @@ def _test_object_and_download(client, obj, test_range=False):
         assert len(body) == 1900
 
         # Size is 2455, so these'll run off the end and return the whole thing after 100
+
         res = client.get(data["access_methods"][0]["access_url"]["url"], headers=(("Range", "bytes=100-19999"),))
         assert res.status_code == 206
         body = res.get_data(as_text=False)
@@ -98,6 +99,17 @@ def _test_object_and_download(client, obj, test_range=False):
         body = res.get_data(as_text=False)
         assert len(body) == 2455
 
+        # Test range error state
+
+        res = client.get(data["access_methods"][0]["access_url"]["url"], headers=(("Range", "bytes"),))
+        assert res.status_code == 400
+
+        res = client.get(data["access_methods"][0]["access_url"]["url"], headers=(("Range", "bytes="),))
+        assert res.status_code == 400
+
+        res = client.get(data["access_methods"][0]["access_url"]["url"], headers=(("Range", "bites=0-4"),))
+        assert res.status_code == 400
+
 
 def test_object_and_download_minio(client_minio, drs_object_minio):
     _test_object_and_download(client_minio, drs_object_minio)

From f7beee21704cde4af5cad38ec6e55d508592bf07 Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:53:07 -0500
Subject: [PATCH 10/15] test: reversed byte range

---
 tests/test_routes.py | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tests/test_routes.py b/tests/test_routes.py
index f087518..b5e0c23 100644
--- a/tests/test_routes.py
+++ b/tests/test_routes.py
@@ -101,15 +101,22 @@ def _test_object_and_download(client, obj, test_range=False):
 
         # Test range error state
 
+        # - no range, no equals
         res = client.get(data["access_methods"][0]["access_url"]["url"], headers=(("Range", "bytes"),))
         assert res.status_code == 400
 
+        # - no range, with equals
         res = client.get(data["access_methods"][0]["access_url"]["url"], headers=(("Range", "bytes="),))
         assert res.status_code == 400
 
+        # - typo for bytes
         res = client.get(data["access_methods"][0]["access_url"]["url"], headers=(("Range", "bites=0-4"),))
         assert res.status_code == 400
 
+        # - reversed interval
+        res = client.get(data["access_methods"][0]["access_url"]["url"], headers=(("Range", "bytes=4-0"),))
+        assert res.status_code == 400
+
 
 def test_object_and_download_minio(client_minio, drs_object_minio):
     _test_object_and_download(client_minio, drs_object_minio)

From 411dcdf6d354cf219e59551a2cd3517ef1f2334e Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 14:59:39 -0500
Subject: [PATCH 11/15] test file checksum directly + increase chunk size for
 checksumming

---
 chord_drs/utils.py     |  4 +++-
 tests/conftest.py      |  1 +
 tests/empty_file.txt   |  0
 tests/test_checksum.py | 10 ++++++++++
 4 files changed, 14 insertions(+), 1 deletion(-)
 create mode 100644 tests/empty_file.txt
 create mode 100644 tests/test_checksum.py

diff --git a/chord_drs/utils.py b/chord_drs/utils.py
index ebeb62f..5b40e40 100644
--- a/chord_drs/utils.py
+++ b/chord_drs/utils.py
@@ -3,12 +3,14 @@
 
 __all__ = ["drs_file_checksum"]
 
+CHUNK_SIZE = 16 * 1024
+
 
 def drs_file_checksum(path: str) -> str:
     hash_obj = sha256()
 
     with open(path, "rb") as f:
-        for chunk in iter(lambda: f.read(4096), b""):
+        while chunk := f.read(CHUNK_SIZE):
             hash_obj.update(chunk)
 
     return hash_obj.hexdigest()
diff --git a/tests/conftest.py b/tests/conftest.py
index 729bd51..5733cf0 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -19,6 +19,7 @@
 NON_EXISTENT_DUMMY_FILE = os.path.join(BASEDIR, "potato")
 DUMMY_FILE = os.path.join(BASEDIR, "tests", "dummy_file.txt")
 DUMMY_DIRECTORY = os.path.join(APP_DIR, "migrations")
+EMPTY_FILE = os.path.join(BASEDIR, "tests", "empty_file.txt")
 
 
 @pytest.fixture
diff --git a/tests/empty_file.txt b/tests/empty_file.txt
new file mode 100644
index 0000000..e69de29
diff --git a/tests/test_checksum.py b/tests/test_checksum.py
new file mode 100644
index 0000000..42dddd6
--- /dev/null
+++ b/tests/test_checksum.py
@@ -0,0 +1,10 @@
+from .conftest import DUMMY_FILE, EMPTY_FILE
+from chord_drs.utils import drs_file_checksum
+
+
+def test_sha256_checksum():
+    # see https://crypto.stackexchange.com/questions/26133/sha-256-hash-of-null-input
+    assert drs_file_checksum(EMPTY_FILE) == "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
+
+    # file with content
+    assert drs_file_checksum(DUMMY_FILE) == "ca5170c51e4d4e68d4c39832489ea9ad8e275c9f46e0c195c86aaf61ee2ce3d8"

From 801b9e376b12fc05065623bbebc8f8baeb6e5dda Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Tue, 7 Feb 2023 15:10:37 -0500
Subject: [PATCH 12/15] docs: document deduplicate: false option for ingest

---
 README.md | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index a4c1693..ad9943e 100644
--- a/README.md
+++ b/README.md
@@ -6,11 +6,12 @@
 
 A proof of concept based on [GA4GH's DRS specifications](https://ga4gh.github.io/data-repository-service-schemas/preview/release/drs-1.0.0/docs/).
 This flask application offers an interface to query files in such 
-a fashion: "drs://some-domain/some-ID".
+a fashion: `drs://some-domain/some-ID`.
 
 For storing the files, two methods are currently supported : in the current filesystem
 or inside a MinIO instance (which is a s3-like software).
 
+
 ## TODO / Future considerations
 
  - Ingesting is either through the command line or by the endpoint of the same name
@@ -19,6 +20,7 @@ or inside a MinIO instance (which is a s3-like software).
  - Consider how to be aware of http vs https depending on the deployment setup
  (in singularity, docker, as is).
 
+
 ## Configuration
 
 At the root of this project there is a sample dotenv file (.env-sample). These can be
@@ -29,6 +31,7 @@ provide the missing values.
 cp .env-sample .env
 ```
 
+
 ## Running in Development
 
 Development dependencies are described in `requirements.txt` and can be
@@ -57,6 +60,7 @@ The Flask development server can be run with the following command:
 FLASK_DEBUG=True flask run
 ```
 
+
 ## Running Tests
 
 To run all tests and calculate coverage, run the following command:
@@ -69,6 +73,7 @@ Tox is configured to run both pytest and flake8, you may want to uncomment
 the second line of tox.ini (envlist = ...) so as to run these commands
 for multiple versions of Python.
 
+
 ## Deploying
 
 In production, the service should be deployed using a WSGI service like
@@ -78,6 +83,7 @@ With uWSGI you should point to chord_drs.app:application, the wsgi.py file
 at the root of the project is there to simplify executing the commands (such
 as "ingest")
 
+
 ## API
 
 ##### GET a single object
@@ -86,6 +92,8 @@ as "ingest")
 
 `/ga4gh/drs/v1/objects/<string:object_id>`
 
+Returns a standard GA4GH record for the object.
+
 ##### GET search
 
 `/search`
@@ -105,9 +113,20 @@ partial match `/search?fuzzy_name=1001`
 
 e.g. POST body
 
-```bash
+```json
 {
-     "path": "examples/P-1001.hc.g.vcf.gz"
+  "path": "examples/P-1001.hc.g.vcf.gz"
+}
+```
+
+This will automatically deduplicate with existing DRS objects if the file matches.
+
+To ingest and force-create a duplicate record, provide the `deduplicate` parameter, set to `false`:
+
+```json
+{
+  "path": "examples/P-1001.hc.g.vcf.gz",
+  "deduplicate": false
 }
 ```
 
@@ -115,3 +134,5 @@ e.g. POST body
 ##### GET service info
 
 `/service-info`
+
+Returns a GA4GH+Bento-formatted service info response.

From 988e8b0bf8c62940d227f748fdca3b2a5be331cb Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Thu, 9 Feb 2023 12:39:24 -0500
Subject: [PATCH 13/15] chore: set gitconfig for dev docker image

---
 entrypoint.dev.bash | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/entrypoint.dev.bash b/entrypoint.dev.bash
index 48d06fd..896439e 100644
--- a/entrypoint.dev.bash
+++ b/entrypoint.dev.bash
@@ -1,5 +1,8 @@
 #!/bin/bash
 
+# Set .gitconfig for development
+/set_gitconfig.bash
+
 export FLASK_ENV=development
 export FLASK_APP=chord_drs.app:application
 

From 8dd45b125c0b7ea065564079b679ac7fa2aed217 Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Thu, 9 Feb 2023 12:39:40 -0500
Subject: [PATCH 14/15] ci: bump bba to 0.10.1

---
 .github/workflows/build.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index bff85b4..a5be06a 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -23,7 +23,7 @@ jobs:
         uses: actions/checkout@v3
 
       - name: Run Bento build action
-        uses: bento-platform/bento_build_action@v0.9.3
+        uses: bento-platform/bento_build_action@v0.10.1
         with:
           registry: ghcr.io
           registry-username: ${{ github.actor }}

From ccc0a4ce82eb0c2a32ed049b43a692d5eb5ba349 Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Thu, 9 Feb 2023 12:40:08 -0500
Subject: [PATCH 15/15] chore: update docker base image ver

---
 Dockerfile     | 2 +-
 dev.Dockerfile | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 45ed903..5d9a701 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,4 +1,4 @@
-FROM ghcr.io/bento-platform/bento_base_image:python-debian-2022.12.06
+FROM ghcr.io/bento-platform/bento_base_image:python-debian-2023.02.09
 
 # TODO: change USER
 USER root
diff --git a/dev.Dockerfile b/dev.Dockerfile
index d27e5a3..dfa16bf 100644
--- a/dev.Dockerfile
+++ b/dev.Dockerfile
@@ -1,4 +1,4 @@
-FROM ghcr.io/bento-platform/bento_base_image:python-debian-2022.12.06
+FROM ghcr.io/bento-platform/bento_base_image:python-debian-2023.02.09
 
 # TODO: change USER
 USER root