Merge pull request #52 from HEPData/submission-linking

Changes for related data update.

.gitignore

@@ -60,3 +60,6 @@ target/
 
 # Downloaded schemas
 hepdata_validator/schemas_remote/
+
+# venv
+venv/

README.rst

@@ -323,7 +323,7 @@ download them. However, in principle, for testing purposes, note that the same m
 
 .. code:: python
 
-    schema_path = 'https://hepdata.net/submission/schemas/1.1.0/'
+    schema_path = 'https://hepdata.net/submission/schemas/1.1.1/'
     schema_name = 'data_schema.json'
 
 and passing a HEPData YAML data file as the ``file_path`` argument of the ``validate`` method.

hepdata_validator/__init__.py

@@ -48,7 +48,7 @@
 
 __all__ = ('__version__', )
 
-VALID_SCHEMA_VERSIONS = ['1.1.0', '1.0.1', '1.0.0', '0.1.0']
+VALID_SCHEMA_VERSIONS = ['1.1.1', '1.1.0', '1.0.1', '1.0.0', '0.1.0']
 LATEST_SCHEMA_VERSION = VALID_SCHEMA_VERSIONS[0]
 
 RAW_SCHEMAS_URL = 'https://raw.githubusercontent.com/HEPData/hepdata-validator/' \

hepdata_validator/schemas/1.1.1/additional_info_schema.json

@@ -0,0 +1,63 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://hepdata.net/submission/schemas/1.1.1/additional_info_schema.json",
+  "title": "Additional information",
+  "description": "Optional information concerning a whole submission rather than individual data tables",
+  "type": "object",
+  "properties": {
+    "record_ids": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "type": { "type": [ "string" ] },
+          "id": { "type": [ "string", "number" ] }
+        },
+        "required": [ "type", "id" ],
+        "additionalProperties": false
+      }
+    },
+    "preprintyear": {
+      "type": "string",
+      "title": "Preprint Year",
+      "description": "Indicates the year when the submission preprint was first available.",
+      "name": "preprintyear"
+    },
+    "publicationyear": {
+      "type": "string",
+      "title": "Publication Year",
+      "description": "Indicates the year when the submission publication was available.",
+      "name": "publicationyear"
+    },
+    "dateupdated": {
+      "type": "string",
+      "title": "Date Updated",
+      "description": "Indicates when the submission was last updated.",
+      "name": "dateupdated"
+    },
+    "modifications": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "action": { "type": "string" },
+          "who": { "type": "string" }
+        },
+        "required": [ "action", "who" ]
+      }
+    },
+    "additional_resources": {
+      "$ref": "additional_resources_schema.json"
+    },
+    "comment": {
+      "type": "string",
+      "description": "Information that applies to all data tables."
+    },
+    "related_to_hepdata_records" : {
+      "type" : "array",
+      "uniqueItems": true,
+      "items" : {"type" : "integer", "minimum": 1}
+    }
+  },
+  "additionalProperties": true
+}

hepdata_validator/schemas/1.1.1/additional_resources_schema.json

@@ -0,0 +1,26 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://hepdata.net/submission/schemas/1.1.1/additional_resources_schema.json",
+  "title": "Additional resources",
+  "type": "array",
+  "items": {
+    "type": "object",
+    "properties": {
+      "location": { "type": "string", "maxLength": 256 },
+      "description": { "type": "string" },
+      "type": { "type": "string", "maxLength": 64 },
+      "license": {
+        "type": "object",
+        "properties": {
+          "name": { "type": "string", "maxLength": 256 },
+          "url": { "type": "string", "maxLength": 256 },
+          "description": { "type": "string" }
+        },
+        "required": [ "name", "url" ],
+        "additionalProperties": false
+      }
+    },
+    "required": [ "location", "description" ],
+    "additionalProperties": false
+  }
+}

hepdata_validator/schemas/1.1.1/data_schema.json

@@ -0,0 +1,121 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://hepdata.net/submission/schemas/1.1.1/data_schema.json",
+  "title": "Data table",
+  "description": "A HEPData table comprising independent_variables and dependent_variables",
+  "type": "object",
+  "properties": {
+    "independent_variables": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "header": {
+            "type": "object",
+            "properties": {
+              "name": { "type": "string" },
+              "units": { "type": "string" }
+            },
+            "required": [ "name" ],
+            "additionalProperties": false
+          },
+          "values": {
+            "type": "array",
+            "items": {
+              "oneOf": [
+                {
+                  "type": "object",
+                  "properties": {
+                    "value": { "type": [ "string", "number" ] }
+                  },
+                  "required": ["value"],
+                  "additionalProperties": false
+                },
+                {
+                  "type": "object",
+                  "properties": {
+                    "value": { "type": "number" },
+                    "low": { "type": "number" },
+                    "high": { "type": "number" }
+                  },
+                  "required": ["low", "high"],
+                  "additionalProperties": false
+                }
+              ]
+            }
+          }
+        },
+        "required": [ "header", "values" ],
+        "additionalProperties": false
+      }
+    },
+    "dependent_variables": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "header": {
+            "type": "object",
+            "properties": {
+              "name": { "type": "string" },
+              "units": { "type": "string" }
+            },
+            "required": [ "name" ],
+            "additionalProperties": false
+          },
+          "qualifiers": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "name": { "type": "string" },
+                "value": { "type": [ "string", "number" ] },
+                "units": { "type": "string" }
+              },
+              "required": [ "name", "value" ],
+              "additionalProperties": false
+            }
+          },
+          "values": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "value": {
+                  "type": [ "string", "number" ]
+                },
+                "errors": {
+                  "type": "array",
+                  "items": {
+                    "type": "object",
+                    "properties": {
+                      "symerror": { "type": [ "number", "string" ] },
+                      "asymerror": {
+                        "type": "object",
+                        "properties": {
+                          "minus": { "type": [ "number", "string" ] },
+                          "plus": { "type": [ "number", "string" ] }
+                        },
+                        "required": [ "minus", "plus" ],
+                        "additionalProperties": false
+                      },
+                      "label": { "type": "string" }
+                    },
+                    "oneOf": [{"required": [ "symerror" ]}, {"required": [ "asymerror" ]}],
+                    "additionalProperties": false
+                  }
+                }
+              },
+              "required": [ "value" ],
+              "additionalProperties": false
+            }
+          }
+        },
+        "required": [ "header", "values" ],
+        "additionalProperties": false
+      }
+    }
+  },
+  "required": [ "independent_variables", "dependent_variables" ],
+  "additionalProperties": false
+}

hepdata_validator/schemas/1.1.1/submission_schema.json

@@ -0,0 +1,56 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://hepdata.net/submission/schemas/1.1.1/submission_schema.json",
+  "title": "Submission table",
+  "description": "Metadata for a HEPData table apart from independent_variables and dependent_variables",
+  "type": "object",
+  "properties": {
+    "name": { "type": "string", "maxLength": 64 },
+    "location": { "type": "string", "maxLength": 256 },
+    "description": { "type": "string"},
+    "keywords": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "name": { "type": "string", "maxLength": 128, "enum": ["cmenergies", "observables", "reactions", "phrases"] },
+          "values": {
+            "type": "array",
+            "items": { "type": [ "string", "number" ], "maxLength": 128 }
+          }
+        },
+        "required": [ "name", "values" ],
+        "additionalProperties": false
+      }
+    },
+    "data_file": { "type": "string" },
+    "data_schema": {
+      "type": "string",
+      "description": "Remote location of the JSON schema for the data_file"
+    },
+    "data_license": {
+      "type": "object",
+      "properties": {
+        "name": { "type": "string", "maxLength": 256 },
+        "url": { "type": "string", "maxLength": 256 },
+        "description": { "type": "string" }
+      },
+      "required": [ "name", "url" ],
+      "additionalProperties": false
+    },
+    "additional_resources": {
+      "$ref": "additional_resources_schema.json"
+    },
+    "table_doi": {
+      "type": "string",
+      "description": "Present if a user downloads YAML from an existing HEPData record"
+    },
+    "related_to_table_dois" : {
+      "type" : "array",
+      "uniqueItems": true,
+      "items" : {"type" : "string",  "maxLength" : 128, "pattern" : "^10\\.17182\/hepdata\\.\\d+\\.v\\d+\/t\\d+$" }
+    }
+  },
+  "required": ["name", "description", "keywords", "data_file"],
+  "additionalProperties": false
+}

hepdata_validator/schemas/additional_info_schema.json

@@ -1 +1 @@
-1.1.0/additional_info_schema.json
+1.1.1/additional_info_schema.json

hepdata_validator/schemas/additional_resources_schema.json

@@ -1 +1 @@
-1.1.0/additional_resources_schema.json
+1.1.1/additional_resources_schema.json

hepdata_validator/schemas/data_schema.json

@@ -1 +1 @@
-1.1.0/data_schema.json
+1.1.1/data_schema.json

hepdata_validator/schemas/submission_schema.json

@@ -1 +1 @@
-1.1.0/submission_schema.json
+1.1.1/submission_schema.json

hepdata_validator/version.py

@@ -27,4 +27,4 @@
 
 from __future__ import absolute_import, print_function
 
-__version__ = "0.3.3"
+__version__ = "0.3.4"

testsuite/test_data/TestHEPSubmission/submission.yaml

@@ -25,11 +25,16 @@ comment: | # preserve newlines
   - No events with a jet for which ptJet > 25 GeV and |etaJet| < 4.5
   - No events with a third lepton for which ptLepton > 10 GeV
   - min(DeltaR(l,l)) > 0.3
+  
+related_to_hepdata_records:
+  - 1
 
 ---
 # Start a new YAML document to indicate a new data table.
 # This is Table 1.
 name: "Table 1"
+related_to_table_dois: 
+ - "10.17182/hepdata.1.v1/t1"
 location: Data from Page 17 of preprint
 description: The measured fiducial cross sections.  The first systematic uncertainty is the combined systematic uncertainty excluding luminosity, the second is the luminosity
 keywords: # used for searching, possibly multiple values for each keyword

testsuite/test_data/TestRelatedSubmissions/data1.yaml

@@ -0,0 +1,7 @@
+independent_variables: []
+dependent_variables:
+- header: {name: TestData1, units: NA}
+  qualifiers:
+  - {name: TestData1, value: 0}
+  values:
+  - value: 0

testsuite/test_data/TestRelatedSubmissions/invalid_submission_doi.yaml

@@ -0,0 +1,16 @@
+---
+comment: "Test Text"
+---
+name: "Table 1"
+description: Words
+keywords: 
+- {name: reactions, values: []}
+data_file: data1.yaml
+related_to_table_dois:
+- 1
+- "10.17182/hepdata.1"
+- "10.17182/hepdata.1.v1"
+- "10.17182/hepdata.1.v1/"
+- "10.17182/hepdata.1.v1/a2"
+- "10.17182/hepdata.1.v1/t1"
+- "10.17182/hepdata.1.v1/t1"

testsuite/test_data/TestRelatedSubmissions/invalid_submission_recid.yaml

@@ -0,0 +1,9 @@
+---
+comment: "Test Text"
+related_to_hepdata_records: ["a", b, 0, 1, 1]
+---
+name: "Table 1"
+description: Words
+keywords: 
+- {name: reactions, values: []}
+data_file: data1.yaml

testsuite/test_data/TestRelatedSubmissions/valid_submission_related.yaml

@@ -0,0 +1,12 @@
+description: "Test Data"
+comment: Test
+related_to_hepdata_records:
+- 1
+---
+name: "Table 1"
+description: Words
+keywords:
+- {name: cmenergies, values: [0]}
+data_file: data1.yaml
+related_to_table_dois:
+- "10.17182/hepdata.1.v1/t1"

testsuite/test_data_validator.py

@@ -23,7 +23,7 @@ def validator_v0():
 
 @pytest.fixture(scope="module")
 def validator_v1():
-    return DataFileValidator(schema_version='1.1.0')
+    return DataFileValidator()
 
 
 ####################################################