From 47e27a8e29d11337f03bcf16b500052eafca0d3e Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Tue, 9 Jan 2024 14:31:14 +0000
Subject: [PATCH 01/24] Add optional licence argument to
 add_additional_resource

Adds support for adding an optional licence to the add_additional_resource function in additional resource objects
---
 hepdata_lib/__init__.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index f9cd4ae5..0be3357b 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -55,7 +55,7 @@ def __init__(self):
         self.files_to_copy = []
         self.additional_resources = []
 
-    def add_additional_resource(self, description, location, copy_file=False, file_type=None):
+    def add_additional_resource(self, description, location, copy_file=False, file_type=None, licence=None):
         """
         Add any kind of additional resource.
         If copy_file is set to False, the location and description will be added as-is.
@@ -80,6 +80,9 @@ def add_additional_resource(self, description, location, copy_file=False, file_t
 
         :param file_type: Type of the resource file.  Currently, only "HistFactory" has any effect.
         :type file_type: string
+
+        :param licence: Licence information for the resource
+        :type licence: string
         """
 
         resource = {}
@@ -94,6 +97,9 @@ def add_additional_resource(self, description, location, copy_file=False, file_t
 
         if file_type:
             resource["type"] = file_type
+        
+        if licence:
+            resource["licence"] = licence
 
         self.additional_resources.append(resource)
 
@@ -306,6 +312,7 @@ def __init__(self, name):
         self.location = "Example location"
         self.keywords = {}
         self.image_files = set()
+        self.licence = {}
 
     @property
     def name(self):

From 14ccd11fd60608066604a5cd214cd64712cf1587 Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Tue, 9 Jan 2024 14:32:06 +0000
Subject: [PATCH 02/24] Add licence function to Table class

Adds a function to add licence information to the Table class
---
 hepdata_lib/__init__.py | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index 0be3357b..7496d236 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -369,7 +369,35 @@ def add_related_doi(self, doi):
             self.related_tables.append(to_string)
         else:
             raise ValueError(f"DOI does not match the correct pattern: {pattern}.")
+    
+    def add_data_licence(self, name, url, description=None):
+        """
+        Verify and store the given licence data.
+
+        :param name: The licence name
+        :type name: string
+        :param url:
+        :type url: string
+        :param description:
+        :type description: string
+        """
+        licence_data = {}
+
+        if name:
+            licence_data["name"] = name
+        else:
+            raise ValueError("You must insert a value for the licence's name.")
+        
+        if url:
+            licence_data["url"] = url
+        else:
+            raise ValueError("You must insert a value for the licence's url.")
+        
+        if description:
+            licence_data["description"] = description
 
+        self.licence = licence_data
+        
     def write_output(self, outdir):
         """
         Write the table files into the output directory.

From de8661acca69176bfa856efea609bb817ff20e71 Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Tue, 9 Jan 2024 14:32:39 +0000
Subject: [PATCH 03/24] Add test for Table data licence function

Adds a test for the new add_data_licence function in the Table class
---
 tests/test_submission.py | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/tests/test_submission.py b/tests/test_submission.py
index f86b05be..a19a34e1 100644
--- a/tests/test_submission.py
+++ b/tests/test_submission.py
@@ -156,7 +156,7 @@ def test_nested_files_to_copy(self):
 
     def test_add_related_doi(self):
         """Test insertion and retrieval of recid values in the Table object"""
-        # Possibly unneccessary boundary testing
+        # Possibly unnecessary boundary testing
         test_data = [
             {"doi": "10.17182/hepdata.1.v1/t1", "error": False},
             {"doi": "10.17182/hepdata.1", "error": ValueError},
@@ -190,3 +190,22 @@ def test_add_related_recid(self):
                 sub.add_related_recid(test["recid"])
                 assert int(test["recid"]) == sub.related_records[-1]
         assert len(sub.related_records) == 2
+
+    def test_add_data_licence(self):
+        """Test addition of data licence entries to the table class"""
+        test_data = [
+            {"expected_err": None, "licence": ["name", "url", "desc"]},  # Valid, full
+            {"expected_err": None, "licence": ["name", "url", None]},  # Valid, no desc
+            {"expected_err": ValueError, "licence": ["name", None, "desc"]},  # Error, no url
+            {"expected_err": ValueError, "licence": [None, "url", "desc"]}  # Error, no name
+        ]
+        tab = Table("Table")  # Test table class
+        for test in test_data:
+            # Check if an error is expected here or not
+            if test["expected_err"]:
+                self.assertRaises(test["expected_err"], tab.add_data_licence, *test["licence"])
+            else:
+                # Check data exists and is correct
+                tab.add_data_licence(*test["licence"])
+                assert tab.licence["name"] == test["licence"][0]
+                assert tab.licence["url"] == test["licence"][1]

From 04464bf3881276b5c25ebd9bd52839ee0f96ef64 Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Wed, 10 Jan 2024 10:22:08 +0000
Subject: [PATCH 04/24] Fix incorrect type AdditionalResource docs

Fixed incorrect docstring type added to the AdditionalResourceMixin object
---
 hepdata_lib/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index 7496d236..5d443db4 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -82,7 +82,7 @@ def add_additional_resource(self, description, location, copy_file=False, file_t
         :type file_type: string
 
         :param licence: Licence information for the resource
-        :type licence: string
+        :type licence: dict
         """
 
         resource = {}

From ea1335f8eb8a0a324f3bcecb17924df3afa00adf Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Wed, 10 Jan 2024 10:25:31 +0000
Subject: [PATCH 05/24] Update add_additional_resource test

Completes and updates the test_add_additional_resource test.
---
 tests/test_table.py | 39 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 34 insertions(+), 5 deletions(-)

diff --git a/tests/test_table.py b/tests/test_table.py
index 6989c7c7..aa5610a7 100644
--- a/tests/test_table.py
+++ b/tests/test_table.py
@@ -169,14 +169,43 @@ def test_write_images_multiple_executions(self):
         self.assertTrue(modified_time_main < os.path.getmtime(expected_main_file))
         self.assertTrue(modified_time_thumbnail < os.path.getmtime(expected_thumbnail_file))
 
-
-
-
-
     def test_add_additional_resource(self): # pylint: disable=no-self-use
         """Test the add_additional_resource function."""
         test_table = Table("Some Table")
-        test_table.add_additional_resource("some link","www.cern.ch")
+        test_data = [
+            {
+                "description": "SomeLink",
+                "location": "www.cern.ch",
+                "type": None,
+                "licence": None
+            },
+            {
+                "description": "SomeLink",
+                "location": "www.cern.ch",
+                "type": "HistFactory",
+                "licence": {"name": "LicenceName", "url": "www.cern.ch", "description": "LicenceDesc"}
+            }
+        ]
+
+        for test in test_data:
+            test_table.add_additional_resource(
+                test["description"],
+                test["location"],
+                file_type=test["type"],
+                licence=test["licence"]
+            )
+
+            # Check resource and mandatory arguments
+            resource = test_table.additional_resources[-1]
+            assert resource["description"] == test["description"]
+            assert resource["location"] == test["location"]
+
+            # Check optional arguments type and licence
+            if test["type"]:
+                assert resource["type"] == test["type"]
+
+            if test["licence"]:
+                assert resource["licence"] == test["licence"]
 
     def test_copy_files(self):
         """Test the copy_files function."""

From 1383a3c816bdf5762f2940297e5a2045c74f4bfd Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Wed, 10 Jan 2024 11:16:40 +0000
Subject: [PATCH 06/24] Complete test_copy_files

Completes implementation of incomplete test_copy_files function
---
 tests/test_table.py | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/tests/test_table.py b/tests/test_table.py
index aa5610a7..56ae49ef 100644
--- a/tests/test_table.py
+++ b/tests/test_table.py
@@ -4,7 +4,7 @@
 import shutil
 from unittest import TestCase
 
-from hepdata_lib import Table, Variable, Uncertainty
+from hepdata_lib import Table, Variable, Uncertainty, helpers
 from .test_utilities import tmp_directory_name
 
 class TestTable(TestCase):
@@ -194,9 +194,10 @@ def test_add_additional_resource(self): # pylint: disable=no-self-use
                 file_type=test["type"],
                 licence=test["licence"]
             )
+            resource = test_table.additional_resources[-1]
 
             # Check resource and mandatory arguments
-            resource = test_table.additional_resources[-1]
+            assert resource
             assert resource["description"] == test["description"]
             assert resource["location"] == test["location"]
 
@@ -214,6 +215,23 @@ def test_copy_files(self):
         testdir = tmp_directory_name()
         self.addCleanup(shutil.rmtree, testdir)
         os.makedirs(testdir)
+        test_table.add_additional_resource("a plot", some_pdf, copy_file=True)
 
-        test_table.add_additional_resource("a plot",some_pdf, copy_file=True)
-        test_table.copy_files(testdir)
+        # Check that the file has been created
+        assert helpers.check_file_existence(some_pdf)
+
+        # Explicitly test for lack of an error
+        try:
+            # No boundaries
+            helpers.check_file_size(some_pdf)
+            # Between boundaries
+            helpers.check_file_size(some_pdf, upper_limit=1, lower_limit=0.001)
+        except Exception as e:
+            self.fail(f"check_file_size() raised an Exception: {e}.")
+
+        # Check that both boundaries function correctly
+        with self.assertRaises(RuntimeError):
+            helpers.check_file_size(some_pdf, upper_limit=0.001)
+
+        with self.assertRaises(RuntimeError):
+            helpers.check_file_size(some_pdf, lower_limit=1)

From b83359c2e100989fc742a9e8bf687503fcfc9c28 Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Fri, 12 Jan 2024 13:04:05 +0000
Subject: [PATCH 07/24] Add validation check to additional resource licence add

Adds validation of licence additions to the add_additional_resource function for AdditionalResource objects.
---
 hepdata_lib/__init__.py | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index 5d443db4..8b3bb21f 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -97,9 +97,23 @@ def add_additional_resource(self, description, location, copy_file=False, file_t
 
         if file_type:
             resource["type"] = file_type
-        
+
+        # Confirm that licence does not contain extra keys, and has the mandatory name and description values
         if licence:
-            resource["licence"] = licence
+            # Get the licence dict keys as a set
+            licence_keys = set(licence.keys())
+
+            # Create sets for both possibilities
+            mandatory_keys = {"name", "description"}
+            all_keys = mandatory_keys.union(["url"])
+
+            # If licence matches either of the correct values
+            if licence_keys == mandatory_keys or licence_keys == all_keys:
+                resource["licence"] = licence
+            else:
+                raise ValueError("Incorrect licence format: \
+                                 Licence must be a dictionary containing a \
+                                 name, description and optional URL value.")
 
         self.additional_resources.append(resource)
 

From 63f820d42ca49a3b3158a85cc330540153657ecd Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Fri, 12 Jan 2024 13:15:49 +0000
Subject: [PATCH 08/24] Update error in TestTable

Updates error check in TestTable.test_copy_files
---
 tests/test_table.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/test_table.py b/tests/test_table.py
index 56ae49ef..6f613c88 100644
--- a/tests/test_table.py
+++ b/tests/test_table.py
@@ -226,8 +226,8 @@ def test_copy_files(self):
             helpers.check_file_size(some_pdf)
             # Between boundaries
             helpers.check_file_size(some_pdf, upper_limit=1, lower_limit=0.001)
-        except Exception as e:
-            self.fail(f"check_file_size() raised an Exception: {e}.")
+        except RuntimeError:
+            self.fail("Table.check_file_size raised an unexpected RuntimeError.")
 
         # Check that both boundaries function correctly
         with self.assertRaises(RuntimeError):

From efedcaf48726c91e639ae2f38c949085d5a19150 Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Fri, 12 Jan 2024 13:18:18 +0000
Subject: [PATCH 09/24] Add additional resource licence check test

Adds a test to check licence validation in TestTable.add_additional_resource.
---
 tests/test_table.py | 64 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/tests/test_table.py b/tests/test_table.py
index 6f613c88..09144e7a 100644
--- a/tests/test_table.py
+++ b/tests/test_table.py
@@ -208,6 +208,70 @@ def test_add_additional_resource(self): # pylint: disable=no-self-use
             if test["licence"]:
                 assert resource["licence"] == test["licence"]
 
+    def test_add_additional_resource_licence_check(self):
+        """ Test the licence value check in Table.add_additional_resource """
+        # First two pass, last two fail
+        licence_data = [
+            {
+                "error": None,
+                "licence_data": {
+                    "name": "Name",
+                    "description": "Desc"
+                }
+            },
+            {
+                "error": None,
+                "licence_data": {
+                    "name": "Name",
+                    "description": "Desc",
+                    "url": "URL"
+                }
+            },
+            {
+                "error": ValueError,
+                "licence_data": {
+                    "name": "Name",
+                    "description": "Desc",
+                    "shouldnotbehere": "shouldnotbehere"
+                }
+            },
+            {
+                "error": ValueError,
+                "licence_data": {
+                    "name": "Name",
+                    "description": "Desc",
+                    "url": "URL",
+                    "toomany": "toomany"
+                }
+            }]
+
+        # Create test table and get the test pdf
+        test_table = Table("Some Table")
+        some_pdf = "%s/minimal.pdf" % os.path.dirname(__file__)
+
+        # Set default description, location and type arguments for a table object
+        resource_args = ["Description", some_pdf, "Type"]
+
+        for data in licence_data:
+            # If error is expected, we check for the error
+            # Otherwise, just add and check length later
+            if data["error"]:
+                with self.assertRaises(ValueError):
+                    test_table.add_additional_resource(
+                        *resource_args,
+                        licence=data["licence_data"]
+                    )
+            else:
+                # Check for lack of failure
+                try:
+                    test_table.add_additional_resource(
+                        *resource_args,
+                        licence=data["licence_data"]
+                    )
+                except ValueError:
+                    self.fail("Table.add_additional_resource raised an unexpected ValueError.")
+
+
     def test_copy_files(self):
         """Test the copy_files function."""
         test_table = Table("Some Table")

From d8807847ddf818ca900cb04fcc2bb2002dece13f Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Wed, 24 Jan 2024 15:52:42 +0000
Subject: [PATCH 10/24] Update usage documentation to include licences

Updates the usage documentation in USAGE.rst to include adding licences to additional resource and table objects.
---
 docs/usage.rst | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/docs/usage.rst b/docs/usage.rst
index 8d450e32..23466285 100644
--- a/docs/usage.rst
+++ b/docs/usage.rst
@@ -124,11 +124,14 @@ Additional resources, hosted either externally or locally, can be linked with th
     sub.add_additional_resource("Web page with auxiliary material", "https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PAPERS/STDM-2012-02/")
     sub.add_additional_resource("Some file", "root_file.root", copy_file=True)
     sub.add_additional_resource("Archive of full likelihoods in the HistFactory JSON format", "Likelihoods.tar.gz", copy_file=True, file_type="HistFactory")
+    sub.add_additional_resource("Some file", "root_file.root", licence={"name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "description": "This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator."})
 
 The first argument is a ``description`` and the second is the ``location`` of the external link or local resource file.
 The optional argument ``copy_file=True`` (default value of ``False``) will copy a local file into the output directory.
 The optional argument ``file_type="HistFactory"`` (default value of ``None``) can be used to identify statistical models provided in the HistFactory JSON
 format rather than relying on certain trigger words in the ``description`` (see `pyhf section of submission documentation`_).
+The optional argument ``licence`` can be used to define a data licence for an additional resource.
+The ``licence`` is in the form of a dictionary with mandatory string ``name`` and ``url`` values, and an optional ``description``.
 
 The ``add_link`` function can alternatively be used to add a link to an external resource:
 
@@ -316,6 +319,17 @@ The documentation for this feature can be found here: `Linking tables`_.
 
 .. _`Linking tables`: https://hepdata-submission.readthedocs.io/en/latest/bidirectional.html#linking-tables
 
+Adding a Data Licence
+^^^^^^^^^^^^^^^^^^^^^
+
+You can add data licence information to a table using the ``add_data_licence`` function of the Table class.
+This function takes mandatory ``name`` and ``url`` string arguments, as well as an optional ``description``.
+
+::
+
+    table.add_data_licence("CC BY 4.0", "https://creativecommons.org/licences/by/4.0/")
+    table.add_data_licence("CC BY 4.0", "https://creativecommons.org/licences/by/4.0/", "This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator.")
+
 Uncertainties
 +++++++++++++
 

From 919a5ca59f5f863ab4b49c2592e3ae01e25c5956 Mon Sep 17 00:00:00 2001
From: Graeme Watt <Graeme.Watt@durham.ac.uk>
Date: Wed, 14 Feb 2024 17:44:39 +0000
Subject: [PATCH 11/24] Some fixes and cleaning up for pylint

* Use spelling "license" rather than "licence" consistently.
* Rename argument "license" as "resource_license" to avoid pylint issue.
* Rename Table "license" as "data_license" and write to YAML.
* Check that "resource_license" is a dict and correct mandatory keys.
---
 docs/usage.rst           | 14 ++++----
 hepdata_lib/__init__.py  | 74 +++++++++++++++++++++++-----------------
 tests/test_submission.py | 20 +++++------
 tests/test_table.py      | 43 +++++++++++------------
 4 files changed, 81 insertions(+), 70 deletions(-)

diff --git a/docs/usage.rst b/docs/usage.rst
index 23466285..3ffb3292 100644
--- a/docs/usage.rst
+++ b/docs/usage.rst
@@ -123,15 +123,15 @@ Additional resources, hosted either externally or locally, can be linked with th
 
     sub.add_additional_resource("Web page with auxiliary material", "https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PAPERS/STDM-2012-02/")
     sub.add_additional_resource("Some file", "root_file.root", copy_file=True)
+    sub.add_additional_resource("Some file", "root_file.root", copy_file=True, resource_license={"name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "description": "This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator."})
     sub.add_additional_resource("Archive of full likelihoods in the HistFactory JSON format", "Likelihoods.tar.gz", copy_file=True, file_type="HistFactory")
-    sub.add_additional_resource("Some file", "root_file.root", licence={"name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "description": "This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator."})
 
 The first argument is a ``description`` and the second is the ``location`` of the external link or local resource file.
 The optional argument ``copy_file=True`` (default value of ``False``) will copy a local file into the output directory.
+The optional argument ``resource_license`` can be used to define a data license for an additional resource.
+The ``resource_license`` is in the form of a dictionary with mandatory string ``name`` and ``url`` values, and an optional ``description``.
 The optional argument ``file_type="HistFactory"`` (default value of ``None``) can be used to identify statistical models provided in the HistFactory JSON
 format rather than relying on certain trigger words in the ``description`` (see `pyhf section of submission documentation`_).
-The optional argument ``licence`` can be used to define a data licence for an additional resource.
-The ``licence`` is in the form of a dictionary with mandatory string ``name`` and ``url`` values, and an optional ``description``.
 
 The ``add_link`` function can alternatively be used to add a link to an external resource:
 
@@ -319,16 +319,16 @@ The documentation for this feature can be found here: `Linking tables`_.
 
 .. _`Linking tables`: https://hepdata-submission.readthedocs.io/en/latest/bidirectional.html#linking-tables
 
-Adding a Data Licence
+Adding a data license
 ^^^^^^^^^^^^^^^^^^^^^
 
-You can add data licence information to a table using the ``add_data_licence`` function of the Table class.
+You can add data license information to a table using the ``add_data_license`` function of the Table class.
 This function takes mandatory ``name`` and ``url`` string arguments, as well as an optional ``description``.
 
 ::
 
-    table.add_data_licence("CC BY 4.0", "https://creativecommons.org/licences/by/4.0/")
-    table.add_data_licence("CC BY 4.0", "https://creativecommons.org/licences/by/4.0/", "This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator.")
+    table.add_data_license("CC BY 4.0", "https://creativecommons.org/licenses/by/4.0/")
+    table.add_data_license("CC BY 4.0", "https://creativecommons.org/licenses/by/4.0/", "This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator.")
 
 Uncertainties
 +++++++++++++
diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index 8b3bb21f..1e26482a 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -55,7 +55,8 @@ def __init__(self):
         self.files_to_copy = []
         self.additional_resources = []
 
-    def add_additional_resource(self, description, location, copy_file=False, file_type=None, licence=None):
+    def add_additional_resource(self, description, location, copy_file=False, file_type=None,
+                                resource_license=None):
         """
         Add any kind of additional resource.
         If copy_file is set to False, the location and description will be added as-is.
@@ -81,10 +82,12 @@ def add_additional_resource(self, description, location, copy_file=False, file_t
         :param file_type: Type of the resource file.  Currently, only "HistFactory" has any effect.
         :type file_type: string
 
-        :param licence: Licence information for the resource
-        :type licence: dict
+        :param resource_license: License information comprising name, url and optional description.
+        :type resource_license: dict
         """
 
+        #pylint: disable=too-many-arguments
+
         resource = {}
         resource["description"] = description
         if copy_file:
@@ -98,22 +101,27 @@ def add_additional_resource(self, description, location, copy_file=False, file_t
         if file_type:
             resource["type"] = file_type
 
-        # Confirm that licence does not contain extra keys, and has the mandatory name and description values
-        if licence:
-            # Get the licence dict keys as a set
-            licence_keys = set(licence.keys())
+        # Confirm that license does not contain extra keys,
+        # and has the mandatory name and description values
+        if resource_license:
+
+            if isinstance(resource_license) != dict:
+                raise ValueError("resource_license must be a dictionary.")
+
+            # Get the license dict keys as a set
+            license_keys = set(resource_license.keys())
 
             # Create sets for both possibilities
-            mandatory_keys = {"name", "description"}
-            all_keys = mandatory_keys.union(["url"])
+            mandatory_keys = {"name", "url"}
+            all_keys = mandatory_keys.union(["description"])
 
-            # If licence matches either of the correct values
-            if licence_keys == mandatory_keys or licence_keys == all_keys:
-                resource["licence"] = licence
+            # If license matches either of the correct values
+            if license_keys in (mandatory_keys, all_keys):
+                resource["license"] = resource_license
             else:
-                raise ValueError("Incorrect licence format: \
-                                 Licence must be a dictionary containing a \
-                                 name, description and optional URL value.")
+                raise ValueError("Incorrect resource_license format: "
+                                 "resource_license must be a dictionary containing a "
+                                 "name, url and optional description.")
 
         self.additional_resources.append(resource)
 
@@ -326,7 +334,7 @@ def __init__(self, name):
         self.location = "Example location"
         self.keywords = {}
         self.image_files = set()
-        self.licence = {}
+        self.data_license = {}
 
     @property
     def name(self):
@@ -383,35 +391,35 @@ def add_related_doi(self, doi):
             self.related_tables.append(to_string)
         else:
             raise ValueError(f"DOI does not match the correct pattern: {pattern}.")
-    
-    def add_data_licence(self, name, url, description=None):
+
+    def add_data_license(self, name, url, description=None):
         """
-        Verify and store the given licence data.
+        Verify and store the given license data.
 
-        :param name: The licence name
+        :param name: The license name
         :type name: string
-        :param url:
+        :param url: The license URL
         :type url: string
-        :param description:
+        :param description: The (optional) license description
         :type description: string
         """
-        licence_data = {}
+        license_data = {}
 
         if name:
-            licence_data["name"] = name
+            license_data["name"] = name
         else:
-            raise ValueError("You must insert a value for the licence's name.")
-        
+            raise ValueError("You must insert a value for the license's name.")
+
         if url:
-            licence_data["url"] = url
+            license_data["url"] = url
         else:
-            raise ValueError("You must insert a value for the licence's url.")
-        
+            raise ValueError("You must insert a value for the license's url.")
+
         if description:
-            licence_data["description"] = description
+            license_data["description"] = description
+
+        self.data_license = license_data
 
-        self.licence = licence_data
-        
     def write_output(self, outdir):
         """
         Write the table files into the output directory.
@@ -523,6 +531,8 @@ def write_yaml(self, outdir="."):
             submission["keywords"] = []
             if self.additional_resources:
                 submission["additional_resources"] = self.additional_resources
+            if self.data_license:
+                submission["data_license"] = self.data_license
 
             for name, values in list(self.keywords.items()):
                 submission["keywords"].append({"name": name, "values": values})
diff --git a/tests/test_submission.py b/tests/test_submission.py
index a19a34e1..77730dba 100644
--- a/tests/test_submission.py
+++ b/tests/test_submission.py
@@ -191,21 +191,21 @@ def test_add_related_recid(self):
                 assert int(test["recid"]) == sub.related_records[-1]
         assert len(sub.related_records) == 2
 
-    def test_add_data_licence(self):
-        """Test addition of data licence entries to the table class"""
+    def test_add_data_license(self):
+        """Test addition of data license entries to the Table class"""
         test_data = [
-            {"expected_err": None, "licence": ["name", "url", "desc"]},  # Valid, full
-            {"expected_err": None, "licence": ["name", "url", None]},  # Valid, no desc
-            {"expected_err": ValueError, "licence": ["name", None, "desc"]},  # Error, no url
-            {"expected_err": ValueError, "licence": [None, "url", "desc"]}  # Error, no name
+            {"expected_err": None, "data_license": ["name", "url", "desc"]},  # Valid, full
+            {"expected_err": None, "data_license": ["name", "url", None]},  # Valid, no desc
+            {"expected_err": ValueError, "data_license": ["name", None, "desc"]},  # Error, no url
+            {"expected_err": ValueError, "data_license": [None, "url", "desc"]}  # Error, no name
         ]
         tab = Table("Table")  # Test table class
         for test in test_data:
             # Check if an error is expected here or not
             if test["expected_err"]:
-                self.assertRaises(test["expected_err"], tab.add_data_licence, *test["licence"])
+                self.assertRaises(test["expected_err"], tab.add_data_license, *test["data_license"])
             else:
                 # Check data exists and is correct
-                tab.add_data_licence(*test["licence"])
-                assert tab.licence["name"] == test["licence"][0]
-                assert tab.licence["url"] == test["licence"][1]
+                tab.add_data_license(*test["data_license"])
+                assert tab.data_license["name"] == test["data_license"][0]
+                assert tab.data_license["url"] == test["data_license"][1]
diff --git a/tests/test_table.py b/tests/test_table.py
index 09144e7a..bedf6c6f 100644
--- a/tests/test_table.py
+++ b/tests/test_table.py
@@ -177,13 +177,14 @@ def test_add_additional_resource(self): # pylint: disable=no-self-use
                 "description": "SomeLink",
                 "location": "www.cern.ch",
                 "type": None,
-                "licence": None
+                "license": None
             },
             {
                 "description": "SomeLink",
                 "location": "www.cern.ch",
                 "type": "HistFactory",
-                "licence": {"name": "LicenceName", "url": "www.cern.ch", "description": "LicenceDesc"}
+                "license": {"name": "licenseName", "url": "www.cern.ch",
+                            "description": "licenseDesc"}
             }
         ]
 
@@ -192,7 +193,7 @@ def test_add_additional_resource(self): # pylint: disable=no-self-use
                 test["description"],
                 test["location"],
                 file_type=test["type"],
-                licence=test["licence"]
+                resource_license=test["license"]
             )
             resource = test_table.additional_resources[-1]
 
@@ -201,46 +202,46 @@ def test_add_additional_resource(self): # pylint: disable=no-self-use
             assert resource["description"] == test["description"]
             assert resource["location"] == test["location"]
 
-            # Check optional arguments type and licence
+            # Check optional arguments type and license
             if test["type"]:
                 assert resource["type"] == test["type"]
 
-            if test["licence"]:
-                assert resource["licence"] == test["licence"]
+            if test["license"]:
+                assert resource["license"] == test["license"]
 
-    def test_add_additional_resource_licence_check(self):
-        """ Test the licence value check in Table.add_additional_resource """
+    def test_add_additional_resource_license_check(self):
+        """ Test the license value check in Table.add_additional_resource """
         # First two pass, last two fail
-        licence_data = [
+        license_data = [
             {
                 "error": None,
-                "licence_data": {
+                "license_data": {
                     "name": "Name",
-                    "description": "Desc"
+                    "url": "URL"
                 }
             },
             {
                 "error": None,
-                "licence_data": {
+                "license_data": {
                     "name": "Name",
-                    "description": "Desc",
-                    "url": "URL"
+                    "url": "URL",
+                    "description": "Desc"
                 }
             },
             {
                 "error": ValueError,
-                "licence_data": {
+                "license_data": {
                     "name": "Name",
-                    "description": "Desc",
+                    "url": "URL",
                     "shouldnotbehere": "shouldnotbehere"
                 }
             },
             {
                 "error": ValueError,
-                "licence_data": {
+                "license_data": {
                     "name": "Name",
-                    "description": "Desc",
                     "url": "URL",
+                    "description": "Desc",
                     "toomany": "toomany"
                 }
             }]
@@ -252,21 +253,21 @@ def test_add_additional_resource_licence_check(self):
         # Set default description, location and type arguments for a table object
         resource_args = ["Description", some_pdf, "Type"]
 
-        for data in licence_data:
+        for data in license_data:
             # If error is expected, we check for the error
             # Otherwise, just add and check length later
             if data["error"]:
                 with self.assertRaises(ValueError):
                     test_table.add_additional_resource(
                         *resource_args,
-                        licence=data["licence_data"]
+                        resource_license=data["license_data"]
                     )
             else:
                 # Check for lack of failure
                 try:
                     test_table.add_additional_resource(
                         *resource_args,
-                        licence=data["licence_data"]
+                        resource_license=data["license_data"]
                     )
                 except ValueError:
                     self.fail("Table.add_additional_resource raised an unexpected ValueError.")

From 2cf90464ec5a05e122504019d37b444da6890e51 Mon Sep 17 00:00:00 2001
From: Graeme Watt <Graeme.Watt@durham.ac.uk>
Date: Wed, 14 Feb 2024 17:49:32 +0000
Subject: [PATCH 12/24] Remove get_license() from Submission class

* Not supported by JSON schema or HEPData web application.
---
 hepdata_lib/__init__.py | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index 1e26482a..06c2c6c3 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -562,17 +562,6 @@ def __init__(self):
             "Created with hepdata_lib " + __version__,
             "https://doi.org/10.5281/zenodo.1217998")
 
-    @staticmethod
-    def get_license():
-        """Return the default license."""
-        data_license = {}
-        data_license["name"] = "cc-by-4.0"
-        data_license["url"] = "https://creativecommons.org/licenses/by/4.0/"
-        data_license[
-            "description"] = "The content can be shared and adapted but you must\
-             give appropriate credit and cannot restrict access to others."
-        return data_license
-
     def add_table(self, table):
         """Append table to tables list.
 
@@ -667,7 +656,6 @@ def create_files(self, outdir=".", validate=True, remove_old=False):
 
         # Write general info about submission
         submission = {}
-        submission["data_license"] = self.get_license()
         submission["comment"] = self.comment
         submission["related_to_hepdata_records"] = self.related_records
 

From 7211f55d0a4050503b73c660d53253b5f9221118 Mon Sep 17 00:00:00 2001
From: Graeme Watt <Graeme.Watt@durham.ac.uk>
Date: Thu, 15 Feb 2024 16:15:31 +0000
Subject: [PATCH 13/24] examples: show how to add license information

* Modify "Getting_started.ipynb" to add license information.
* Also print out submission.yaml and YAML data file at end of notebook.
---
 examples/Getting_started.ipynb | 193 +++++++++++++++++++++++++++++++--
 1 file changed, 184 insertions(+), 9 deletions(-)

diff --git a/examples/Getting_started.ipynb b/examples/Getting_started.ipynb
index e940c44c..2a636653 100644
--- a/examples/Getting_started.ipynb
+++ b/examples/Getting_started.ipynb
@@ -35,7 +35,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Welcome to JupyROOT 6.28/06\n"
+      "Welcome to JupyROOT 6.26/06\n"
      ]
     }
    ],
@@ -271,25 +271,50 @@
     "If you want, the original data file can be attached to the table as an additional resource file."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The default license for HEPData records is [CC0](https://creativecommons.org/publicdomain/zero/1.0/legalcode) (see [Terms of Use](https://www.hepdata.net/terms)), but it is possible to specify a different license for both additional resource files and data tables."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
-    "table.add_additional_resource(\"Original data file\", \"example_inputs/effacc_signal.txt\", copy_file=True)"
+    "license = {\"name\": \"CC BY 4.0\", \"url\": \"https://creativecommons.org/licenses/by/4.0/\", \"description\": \"This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator.\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "table.add_additional_resource(\"Original data file\", \"example_inputs/effacc_signal.txt\", copy_file=True, resource_license=license)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "table.add_data_license(license[\"name\"], license[\"url\"])"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This is all that's needed for the table/figure. We still need it to the submission:"
+    "This is all that's needed for the table/figure. We still need to add it to the submission:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -305,7 +330,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -322,7 +347,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -339,7 +364,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -363,7 +388,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -378,6 +403,156 @@
    "source": [
     "!ls example_output"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "---\n",
+      "additional_resources:\n",
+      "- description: Created with hepdata_lib 0.14.0\n",
+      "  location: https://doi.org/10.5281/zenodo.1217998\n",
+      "- description: Webpage with all figures and tables\n",
+      "  location: https://cms-results.web.cern.ch/cms-results/public-results/publications/B2G-16-029/\n",
+      "- description: arXiv\n",
+      "  location: http://arxiv.org/abs/arXiv:1802.09407\n",
+      "- description: Original abstract file\n",
+      "  location: abstract.txt\n",
+      "comment: A search for a new heavy particle decaying to a pair of vector bosons (WW\n",
+      "  or WZ) is presented using data from the CMS detector corresponding to an integrated\n",
+      "  luminosity of $35.9~\\mathrm{fb}^{-1}$ collected in proton-proton collisions at a\n",
+      "  centre-of-mass energy of 13~TeV in 2016. One of the bosons is required to be a W\n",
+      "  boson decaying to $e\\nu$ or $mu\\nu$, while the other boson is required to be reconstructed\n",
+      "  as a single massive jet with substructure compatible with that of a highly-energetic\n",
+      "  quark pair from a W or Z boson decay. The search is performed in the resonance mass\n",
+      "  range between 1.0 and 4.5~TeV.  The largest deviation from the background-only hypothesis\n",
+      "  is observed for a mass near 1.4~TeV and corresponds to a local significance of 2.5\n",
+      "  standard deviations. The result is interpreted as an upper bound on the resonance\n",
+      "  production cross section. Comparing the excluded cross section values and the expectations\n",
+      "  from theoretical calculations in the bulk graviton and heavy vector triplet models,\n",
+      "  spin-2 WW resonances with mass smaller than 1.07~TeV and spin-1 WZ resonances lighter\n",
+      "  than 3.05~TeV, respectively, are excluded at 95\\% confidence level.\n",
+      "record_ids:\n",
+      "- id: 1657397\n",
+      "  type: inspire\n",
+      "---\n",
+      "additional_resources:\n",
+      "- description: Original data file\n",
+      "  license:\n",
+      "    description: This license enables reusers to distribute, remix, adapt, and build\n",
+      "      upon the material in any medium or format, so long as attribution is given to\n",
+      "      the creator.\n",
+      "    name: CC BY 4.0\n",
+      "    url: https://creativecommons.org/licenses/by/4.0/\n",
+      "  location: effacc_signal.txt\n",
+      "- description: Image file\n",
+      "  location: signalEffVsMass.png\n",
+      "- description: Thumbnail image file\n",
+      "  location: thumb_signalEffVsMass.png\n",
+      "data_file: additional_figure_1.yaml\n",
+      "data_license:\n",
+      "  name: CC BY 4.0\n",
+      "  url: https://creativecommons.org/licenses/by/4.0/\n",
+      "description: Signal selection efficiency times acceptance as a function of resonance\n",
+      "  mass for a spin-2 bulk graviton decaying to WW and a spin-1 W' decaying to WZ.\n",
+      "keywords:\n",
+      "- name: observables\n",
+      "  values:\n",
+      "  - ACC\n",
+      "  - EFF\n",
+      "- name: reactions\n",
+      "  values:\n",
+      "  - P P --> GRAVITON --> W+ W-\n",
+      "  - P P --> WPRIME --> W+/W- Z0\n",
+      "- name: cmenergies\n",
+      "  values:\n",
+      "  - 13000\n",
+      "location: Data from additional Figure 1\n",
+      "name: Additional Figure 1\n"
+     ]
+    }
+   ],
+   "source": [
+    "!cat example_output/submission.yaml"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "dependent_variables:\n",
+      "- header:\n",
+      "    name: Efficiency times acceptance\n",
+      "  qualifiers:\n",
+      "  - name: Efficiency times acceptance\n",
+      "    value: Bulk graviton --> WW\n",
+      "  - name: SQRT(S)\n",
+      "    units: TeV\n",
+      "    value: 13\n",
+      "  values:\n",
+      "  - value: 0.4651\n",
+      "  - value: 0.50336\n",
+      "  - value: 0.5126\n",
+      "  - value: 0.52474\n",
+      "  - value: 0.531\n",
+      "  - value: 0.5391\n",
+      "  - value: 0.54943\n",
+      "  - value: 0.55378\n",
+      "  - value: 0.56216\n",
+      "  - value: 0.56454\n",
+      "  - value: 0.56682\n",
+      "- header:\n",
+      "    name: Efficiency times acceptance\n",
+      "  qualifiers:\n",
+      "  - name: Efficiency times acceptance\n",
+      "    value: Wprime --> WZ\n",
+      "  - name: SQRT(S)\n",
+      "    units: TeV\n",
+      "    value: 13\n",
+      "  values:\n",
+      "  - value: 0.45136\n",
+      "  - value: 0.5109\n",
+      "  - value: 0.54016\n",
+      "  - value: 0.5513\n",
+      "  - value: 0.56724\n",
+      "  - value: 0.5728\n",
+      "  - value: 0.5856\n",
+      "  - value: 0.58952\n",
+      "  - value: 0.60324\n",
+      "  - value: .nan\n",
+      "  - value: 0.59978\n",
+      "independent_variables:\n",
+      "- header:\n",
+      "    name: Resonance mass\n",
+      "    units: GeV\n",
+      "  values:\n",
+      "  - value: 1000.0\n",
+      "  - value: 1200.0\n",
+      "  - value: 1400.0\n",
+      "  - value: 1600.0\n",
+      "  - value: 1800.0\n",
+      "  - value: 2000.0\n",
+      "  - value: 2500.0\n",
+      "  - value: 3000.0\n",
+      "  - value: 3500.0\n",
+      "  - value: 4000.0\n",
+      "  - value: 4500.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "!cat example_output/additional_figure_1.yaml"
+   ]
   }
  ],
  "metadata": {
@@ -396,7 +571,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

From 3918d70ec7ce565c082823efb52c26c2838fb89f Mon Sep 17 00:00:00 2001
From: Graeme Watt <Graeme.Watt@durham.ac.uk>
Date: Thu, 15 Feb 2024 16:21:53 +0000
Subject: [PATCH 14/24] tests: fix isinstance, add test, suppress keys

* Fix incorrect use of isinstance added in 919a5ca59f5f863ab4b49c2592e3ae01e25c5956.
* Add a test for resource_license not a dictionary to increase coverage.
* Suppress empty "related_records" and "related_to_table_dois" keys.
---
 hepdata_lib/__init__.py | 8 +++++---
 tests/test_table.py     | 8 ++++++--
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index 06c2c6c3..29765cb1 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -105,7 +105,7 @@ def add_additional_resource(self, description, location, copy_file=False, file_t
         # and has the mandatory name and description values
         if resource_license:
 
-            if isinstance(resource_license) != dict:
+            if not isinstance(resource_license, dict):
                 raise ValueError("resource_license must be a dictionary.")
 
             # Get the license dict keys as a set
@@ -526,7 +526,8 @@ def write_yaml(self, outdir="."):
             submission["name"] = self.name
             submission["description"] = self.description
             submission["location"] = self.location
-            submission["related_to_table_dois"] = self.related_tables
+            if self.related_tables:
+                submission["related_to_table_dois"] = self.related_tables
             submission["data_file"] = f'{shortname}.yaml'
             submission["keywords"] = []
             if self.additional_resources:
@@ -657,7 +658,8 @@ def create_files(self, outdir=".", validate=True, remove_old=False):
         # Write general info about submission
         submission = {}
         submission["comment"] = self.comment
-        submission["related_to_hepdata_records"] = self.related_records
+        if self.related_records:
+            submission["related_to_hepdata_records"] = self.related_records
 
         if self.additional_resources:
             submission["additional_resources"] = self.additional_resources
diff --git a/tests/test_table.py b/tests/test_table.py
index bedf6c6f..03f63555 100644
--- a/tests/test_table.py
+++ b/tests/test_table.py
@@ -244,14 +244,18 @@ def test_add_additional_resource_license_check(self):
                     "description": "Desc",
                     "toomany": "toomany"
                 }
+            },
+            {
+                "error": ValueError,
+                "license_data": "a string not a dictionary"
             }]
 
         # Create test table and get the test pdf
         test_table = Table("Some Table")
         some_pdf = "%s/minimal.pdf" % os.path.dirname(__file__)
 
-        # Set default description, location and type arguments for a table object
-        resource_args = ["Description", some_pdf, "Type"]
+        # Set default description, location, copy_file and file_type arguments for a resource file
+        resource_args = ["Description", some_pdf, True, "Type"]
 
         for data in license_data:
             # If error is expected, we check for the error

From d84bef6221d9a37d66906370bd8488b967a81d5b Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Mon, 25 Mar 2024 08:25:11 +0000
Subject: [PATCH 15/24] Update test data

Updates test data in TestTable.test_write_yaml to test missed lines.
---
 tests/test_table.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tests/test_table.py b/tests/test_table.py
index 03f63555..38079d2e 100644
--- a/tests/test_table.py
+++ b/tests/test_table.py
@@ -61,6 +61,12 @@ def test_write_yaml(self):
         test_table = Table("Some Table")
         test_variable = Variable("Some Variable")
         test_table.add_variable(test_variable)
+        test_table.add_related_doi("10.17182/hepdata.1.v1/t1")
+        test_table.add_data_license(
+            name="data_license",
+            url="test_url"
+        )
+        test_table.keywords = {"name": "keywords", "values": "1"}
         testdir = tmp_directory_name()
         self.addCleanup(shutil.rmtree, testdir)
         try:

From 14f65e3896c25d188e1614676db793cfecea54a1 Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Tue, 16 Apr 2024 15:25:03 +0100
Subject: [PATCH 16/24] Update test for coverage

Updates test_create_files function in test_submission.py to cover missing lines
---
 tests/test_submission.py | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/tests/test_submission.py b/tests/test_submission.py
index f7fe367c..ed30b5a9 100644
--- a/tests/test_submission.py
+++ b/tests/test_submission.py
@@ -71,11 +71,26 @@ def test_additional_resource_size(self):
     def test_create_files(self):
         """Test create_files() for Submission."""
 
+        # Set test directory/file pat
         testdir = tmp_directory_name()
+        testpath = "./testfile.txt"
+
+        # Create test file and set cleanup
+        f = open(testpath, "a")
+        f.close()
+        self.addCleanup(os.remove, testpath)
+
+        # Create submission and set values for testing
         test_submission = Submission()
         test_submission.add_record_id(1657397, "inspire")
-        tab = Table("test")
-        test_submission.add_table(tab)
+        test_submission.add_related_recid(111)
+        test_submission.add_additional_resource("Some description", testpath,
+                                                copy_file=True, file_type="HistFactory")
+        # Create table and set test values
+        test_table = Table("test")
+        test_table.add_related_doi("10.17182/hepdata.1.v1/t1")
+        test_submission.add_table(test_table)
+
         test_submission.create_files(testdir)
 
         self.doCleanups()

From edcf9162a3e7576825703d7c5a44afe1962d1e42 Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Tue, 16 Apr 2024 15:26:00 +0100
Subject: [PATCH 17/24] Pylint fixes

Fixed some issues output by pylint in the actions output
---
 tests/test_table.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/test_table.py b/tests/test_table.py
index 67e32382..1fa434f9 100644
--- a/tests/test_table.py
+++ b/tests/test_table.py
@@ -179,7 +179,7 @@ def test_write_images_multiple_executions(self):
         self.assertTrue(modified_time_main < os.path.getmtime(expected_main_file))
         self.assertTrue(modified_time_thumbnail < os.path.getmtime(expected_thumbnail_file))
 
-    def test_add_additional_resource(self): # pylint: disable=no-self-use
+    def test_add_additional_resource(self):
         """Test the add_additional_resource function."""
         test_table = Table("Some Table")
         test_data = [
@@ -262,7 +262,7 @@ def test_add_additional_resource_license_check(self):
 
         # Create test table and get the test pdf
         test_table = Table("Some Table")
-        some_pdf = "%s/minimal.pdf" % os.path.dirname(__file__)
+        some_pdf = f"{os.path.dirname(__file__)}/minimal.pdf"
 
         # Set default description, location, copy_file and file_type arguments for a resource file
         resource_args = ["Description", some_pdf, True, "Type"]

From c579a96fccd62ba5386af0197beb0289d06c708a Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Tue, 16 Apr 2024 15:26:27 +0100
Subject: [PATCH 18/24] Update usage.rst

Updates usage documentation to note default licence
---
 docs/usage.rst | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/docs/usage.rst b/docs/usage.rst
index 48a23ba5..48147fac 100644
--- a/docs/usage.rst
+++ b/docs/usage.rst
@@ -133,6 +133,11 @@ The ``resource_license`` is in the form of a dictionary with mandatory string ``
 The optional argument ``file_type="HistFactory"`` (default value of ``None``) can be used to identify statistical models provided in the HistFactory JSON
 format rather than relying on certain trigger words in the ``description`` (see `pyhf section of submission documentation`_).
 
+**Please note:** The default license applied to records uploaded to HEPData is `CC0`_. You do not
+need to specify a license by default.
+
+.. _`CC0`: https://creativecommons.org/public-domain/cc0/
+
 The ``add_link`` function can alternatively be used to add a link to an external resource:
 
 ::
@@ -329,6 +334,11 @@ Adding a data license
 You can add data license information to a table using the ``add_data_license`` function of the Table class.
 This function takes mandatory ``name`` and ``url`` string arguments, as well as an optional ``description``.
 
+**Please note:** The default license applied to records uploaded to HEPData is `CC0`_. You do not
+need to specify a license by default.
+
+.. _`CC0`: https://creativecommons.org/public-domain/cc0/
+
 ::
 
     table.add_data_license("CC BY 4.0", "https://creativecommons.org/licenses/by/4.0/")

From 60bcbe05e3c6ae1bb6bc7b1837387d4e30cfdd50 Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Wed, 17 Apr 2024 12:54:55 +0100
Subject: [PATCH 19/24] Pylint fix

Fixes pylint error around use of open() for files
---
 tests/test_submission.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tests/test_submission.py b/tests/test_submission.py
index ed30b5a9..6bee2c01 100644
--- a/tests/test_submission.py
+++ b/tests/test_submission.py
@@ -75,9 +75,9 @@ def test_create_files(self):
         testdir = tmp_directory_name()
         testpath = "./testfile.txt"
 
-        # Create test file and set cleanup
-        f = open(testpath, "a")
-        f.close()
+        with open(testpath, "a", encoding="utf-8") as f:
+            f.close()
+
         self.addCleanup(os.remove, testpath)
 
         # Create submission and set values for testing

From 1968670ffbab9b15f164298a383d0ddc029fc9ae Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Wed, 17 Apr 2024 15:16:58 +0100
Subject: [PATCH 20/24] Update usage documentation

Updates the documentation for usage in usage.rst to improve licence notice clarity. Now mentions that a licence does not need to be specified if it is CC0.
---
 docs/usage.rst | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/docs/usage.rst b/docs/usage.rst
index 48147fac..c6d2e7d5 100644
--- a/docs/usage.rst
+++ b/docs/usage.rst
@@ -133,8 +133,8 @@ The ``resource_license`` is in the form of a dictionary with mandatory string ``
 The optional argument ``file_type="HistFactory"`` (default value of ``None``) can be used to identify statistical models provided in the HistFactory JSON
 format rather than relying on certain trigger words in the ``description`` (see `pyhf section of submission documentation`_).
 
-**Please note:** The default license applied to records uploaded to HEPData is `CC0`_. You do not
-need to specify a license by default.
+**Please note:** The default license applied to all data uploaded to HEPData is `CC0`_. You do not
+need to specify a license for a resource file unless it differs from `CC0`_.
 
 .. _`CC0`: https://creativecommons.org/public-domain/cc0/
 
@@ -334,8 +334,8 @@ Adding a data license
 You can add data license information to a table using the ``add_data_license`` function of the Table class.
 This function takes mandatory ``name`` and ``url`` string arguments, as well as an optional ``description``.
 
-**Please note:** The default license applied to records uploaded to HEPData is `CC0`_. You do not
-need to specify a license by default.
+**Please note:** The default license applied to all data uploaded to HEPData is `CC0`_. You do not
+need to specify a license for a data table unless it differs from `CC0`_.
 
 .. _`CC0`: https://creativecommons.org/public-domain/cc0/
 

From e4d7e7e3968762a9f1b98b5961212d34c19dcaaa Mon Sep 17 00:00:00 2001
From: Jordan <21129425+ItIsJordan@users.noreply.github.com>
Date: Wed, 17 Apr 2024 15:23:36 +0100
Subject: [PATCH 21/24] Remove duplicate ref in usage.rst

Removes duplicate reference for `CC0` URL in usage.rst.
---
 docs/usage.rst | 2 --
 1 file changed, 2 deletions(-)

diff --git a/docs/usage.rst b/docs/usage.rst
index c6d2e7d5..410f0002 100644
--- a/docs/usage.rst
+++ b/docs/usage.rst
@@ -337,8 +337,6 @@ This function takes mandatory ``name`` and ``url`` string arguments, as well as
 **Please note:** The default license applied to all data uploaded to HEPData is `CC0`_. You do not
 need to specify a license for a data table unless it differs from `CC0`_.
 
-.. _`CC0`: https://creativecommons.org/public-domain/cc0/
-
 ::
 
     table.add_data_license("CC BY 4.0", "https://creativecommons.org/licenses/by/4.0/")

From 3742535fa647befa2f3fcda21f254998eede777b Mon Sep 17 00:00:00 2001
From: Graeme Watt <Graeme.Watt@durham.ac.uk>
Date: Thu, 18 Apr 2024 12:02:46 +0100
Subject: [PATCH 22/24] Remove license addition from Getting_started.ipynb

* A license will usually not be needed, so remove for clarity.
---
 examples/Getting_started.ipynb | 58 +++++++---------------------------
 1 file changed, 12 insertions(+), 46 deletions(-)

diff --git a/examples/Getting_started.ipynb b/examples/Getting_started.ipynb
index 0934890a..1b323b1d 100644
--- a/examples/Getting_started.ipynb
+++ b/examples/Getting_started.ipynb
@@ -27,8 +27,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Welcome to JupyROOT 6.26/06\n",
-      "hepdata_lib version 0.14.1\n"
+      "Welcome to JupyROOT 6.30/04\n",
+      "hepdata_lib version 0.15.0\n"
      ]
     }
    ],
@@ -265,38 +265,13 @@
     "If you want, the original data file can be attached to the table as an additional resource file."
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The default license for HEPData records is [CC0](https://creativecommons.org/publicdomain/zero/1.0/legalcode) (see [Terms of Use](https://www.hepdata.net/terms)), but it is possible to specify a different license for both additional resource files and data tables."
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
-    "license = {\"name\": \"CC BY 4.0\", \"url\": \"https://creativecommons.org/licenses/by/4.0/\", \"description\": \"This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator.\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "table.add_additional_resource(\"Original data file\", \"example_inputs/effacc_signal.txt\", copy_file=True, resource_license=license)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "table.add_data_license(license[\"name\"], license[\"url\"])"
+    "table.add_additional_resource(\"Original data file\", \"example_inputs/effacc_signal.txt\", copy_file=True)"
    ]
   },
   {
@@ -308,7 +283,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -324,7 +299,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -341,7 +316,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -358,7 +333,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -382,7 +357,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -400,7 +375,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -409,7 +384,7 @@
      "text": [
       "---\n",
       "additional_resources:\n",
-      "- description: Created with hepdata_lib 0.14.0\n",
+      "- description: Created with hepdata_lib 0.15.0\n",
       "  location: https://doi.org/10.5281/zenodo.1217998\n",
       "- description: Webpage with all figures and tables\n",
       "  location: https://cms-results.web.cern.ch/cms-results/public-results/publications/B2G-16-029/\n",
@@ -437,21 +412,12 @@
       "---\n",
       "additional_resources:\n",
       "- description: Original data file\n",
-      "  license:\n",
-      "    description: This license enables reusers to distribute, remix, adapt, and build\n",
-      "      upon the material in any medium or format, so long as attribution is given to\n",
-      "      the creator.\n",
-      "    name: CC BY 4.0\n",
-      "    url: https://creativecommons.org/licenses/by/4.0/\n",
       "  location: effacc_signal.txt\n",
       "- description: Image file\n",
       "  location: signalEffVsMass.png\n",
       "- description: Thumbnail image file\n",
       "  location: thumb_signalEffVsMass.png\n",
       "data_file: additional_figure_1.yaml\n",
-      "data_license:\n",
-      "  name: CC BY 4.0\n",
-      "  url: https://creativecommons.org/licenses/by/4.0/\n",
       "description: Signal selection efficiency times acceptance as a function of resonance\n",
       "  mass for a spin-2 bulk graviton decaying to WW and a spin-1 W' decaying to WZ.\n",
       "keywords:\n",
@@ -477,7 +443,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -565,7 +531,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,

From d87017d9bf1eaefb6d728c7d1743b55291cad2d5 Mon Sep 17 00:00:00 2001
From: Graeme Watt <Graeme.Watt@durham.ac.uk>
Date: Thu, 18 Apr 2024 12:04:14 +0100
Subject: [PATCH 23/24] Revert "Remove get_license() from Submission class"

This reverts commit 2cf90464ec5a05e122504019d37b444da6890e51.
---
 hepdata_lib/__init__.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index 3bcc6b01..7e565d0e 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -565,6 +565,17 @@ def __init__(self):
             "Created with hepdata_lib " + __version__,
             "https://doi.org/10.5281/zenodo.1217998")
 
+    @staticmethod
+    def get_license():
+        """Return the default license."""
+        data_license = {}
+        data_license["name"] = "cc-by-4.0"
+        data_license["url"] = "https://creativecommons.org/licenses/by/4.0/"
+        data_license[
+            "description"] = "The content can be shared and adapted but you must\
+             give appropriate credit and cannot restrict access to others."
+        return data_license
+
     def add_table(self, table):
         """Append table to tables list.
 
@@ -659,6 +670,7 @@ def create_files(self, outdir=".", validate=True, remove_old=False):
 
         # Write general info about submission
         submission = {}
+        submission["data_license"] = self.get_license()
         submission["comment"] = self.comment
         if self.related_records:
             submission["related_to_hepdata_records"] = self.related_records

From 2ce00358975563b445005a924106bbbe73b55374 Mon Sep 17 00:00:00 2001
From: Graeme Watt <Graeme.Watt@durham.ac.uk>
Date: Thu, 18 Apr 2024 13:04:32 +0100
Subject: [PATCH 24/24] Change default license from "CC BY 4.0" to "CC0"

* Written in the first document of the submission.yaml file, although
  it is not supported by the JSON schema or the HEPData web application.
---
 examples/Getting_started.ipynb |  5 +++++
 hepdata_lib/__init__.py        | 10 +++++-----
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/examples/Getting_started.ipynb b/examples/Getting_started.ipynb
index 1b323b1d..767d57f1 100644
--- a/examples/Getting_started.ipynb
+++ b/examples/Getting_started.ipynb
@@ -406,6 +406,11 @@
       "  from theoretical calculations in the bulk graviton and heavy vector triplet models,\n",
       "  spin-2 WW resonances with mass smaller than 1.07~TeV and spin-1 WZ resonances lighter\n",
       "  than 3.05~TeV, respectively, are excluded at 95\\% confidence level.\n",
+      "data_license:\n",
+      "  description: CC0 enables reusers to distribute, remix, adapt, and build upon the\n",
+      "    material in any medium or format, with no conditions.\n",
+      "  name: CC0\n",
+      "  url: https://creativecommons.org/publicdomain/zero/1.0/\n",
       "record_ids:\n",
       "- id: 1657397\n",
       "  type: inspire\n",
diff --git a/hepdata_lib/__init__.py b/hepdata_lib/__init__.py
index 7e565d0e..e919b5f7 100644
--- a/hepdata_lib/__init__.py
+++ b/hepdata_lib/__init__.py
@@ -569,11 +569,11 @@ def __init__(self):
     def get_license():
         """Return the default license."""
         data_license = {}
-        data_license["name"] = "cc-by-4.0"
-        data_license["url"] = "https://creativecommons.org/licenses/by/4.0/"
-        data_license[
-            "description"] = "The content can be shared and adapted but you must\
-             give appropriate credit and cannot restrict access to others."
+        data_license["name"] = "CC0"
+        data_license["url"] = "https://creativecommons.org/publicdomain/zero/1.0/"
+        data_license["description"] = (
+            "CC0 enables reusers to distribute, remix, adapt, and build upon the material "
+            "in any medium or format, with no conditions.")
         return data_license
 
     def add_table(self, table):