Add hash for test data (unicode-org#252)

* Adding ICU4C running collation tests - first try * Cache ICU4C binaries in GH and locally, only if they don't exist * Install JSON-C dependency if not installed at beginning of CI or e2e script * Fix bash if condition syntax * Hash code for tests and updating schema * Adding hex hash to all tests data * updating hexhash generation for tests * Add common hash function for JavaScript * Clean up some unneeded warning/error messges * Revise white space * Update testgen/generators/generate_test_hash.js Co-authored-by: Shane F. Carr <[email protected]> --------- Co-authored-by: Elango Cheran <[email protected]> Co-authored-by: Shane F. Carr <[email protected]>
sven-oly · Jul 15, 2024 · b08229f · b08229f
1 parent 7567db8
commit b08229f
Show file tree

Hide file tree

Showing 19 changed files with 329 additions and 45 deletions.
diff --git a/schema/check_generated_data.py b/schema/check_generated_data.py
@@ -74,15 +74,18 @@ def main(args):
     # Create .json
     summary_json = {
         'validation_type': 'Generated test data files',
-        'description': 'Results of validating generated test data agains schema',
+        'description': 'Results of validating generated test data against schema',
         'when_processed': datetime.now().strftime('%Y-%m-%d T%H%M%S.%f'),
         'validations': {
             'failed': failed_validations,
             'passed': passed_validations
         }
     }
 
-    summary_data = json.dumps(summary_json)
+    try:
+        summary_data = json.dumps(summary_json)
+    except BaseException as error:
+        logging.error('json.dumps Summary data problem: %s, ')
 
     try:
         output_filename = os.path.join(test_data_path, 'test_data_validation_summary.json')

diff --git a/schema/collation_short/test_schema.json b/schema/collation_short/test_schema.json
@@ -29,6 +29,10 @@
             "description": "A numeric ID, unique for the set of tests",
             "type": "string"
           },
+          "hexhash": {
+            "description": "A hexadecimal hash code for the test without the label",
+            "type": "string"
+          },
           "s1": {
             "description": "First string for comparison",
             "type": "string"

diff --git a/schema/datetime_fmt/test_schema.json b/schema/datetime_fmt/test_schema.json
@@ -20,6 +20,10 @@
            "description": "A numeric ID, unique for the set of tests",
            "type": "string"
          },
+          "hexhash": {
+            "description": "A hexadecimal hash code for the test without the label",
+            "type": "string"
+          },
          "locale": {
            "description": "language tag for formatting the output",
            "type": "string"

diff --git a/schema/language_names/result_schema.json → schema/lang_names/result_schema.json b/schema/language_names/result_schema.json → schema/lang_names/result_schema.json
diff --git a/schema/language_names/test_schema.json → schema/lang_names/test_schema.json b/schema/language_names/test_schema.json → schema/lang_names/test_schema.json
@@ -41,6 +41,10 @@
            "description": "A numeric ID, unique for the set of tests",
            "type": "string"
          },
+          "hexhash": {
+            "description": "A hexadecimal hash code for the test without the label",
+            "type": "string"
+          },
          "language_label": {
            "description": "locale tag of the source language ",
            "type": "string"

diff --git a/schema/language_names/verify_schema.json → schema/lang_names/verify_schema.json b/schema/language_names/verify_schema.json → schema/lang_names/verify_schema.json
diff --git a/schema/likely_subtags/test_schema.json b/schema/likely_subtags/test_schema.json
@@ -75,6 +75,10 @@
            "description": "A numeric ID, unique for the set of tests",
            "type": "string"
          },
+          "hexhash": {
+            "description": "A hexadecimal hash code for the test without the label",
+            "type": "string"
+          },
          "locale": {
            "description": "locale tag source ",
            "type": "string"

diff --git a/schema/list_fmt/test_schema.json b/schema/list_fmt/test_schema.json
@@ -74,6 +74,10 @@
            "description": "A numeric ID, unique for the set of tests",
            "type": "string"
          },
+          "hexhash": {
+            "description": "A hexadecimal hash code for the test without the label",
+            "type": "string"
+          },
          "locale": {
            "description": "locale tag source ",
            "type": "string"

diff --git a/schema/message_fmt2/test_schema.json b/schema/message_fmt2/test_schema.json
@@ -27,6 +27,10 @@
           "type": "string",
           "description": "Identifier for the test."
         },
+        "hexhash": {
+          "description": "A hexadecimal hash code for the test without the label",
+          "type": "string"
+        },
         "test_description": {
           "type": "string",
           "description": "Information about the test."

diff --git a/schema/number_format/test_schema.json b/schema/number_format/test_schema.json
@@ -42,6 +42,10 @@
            "description": "A numeric ID, unique for the set of tests",
            "type": "string"
          },
+         "hexhash": {
+           "description": "A hexadecimal hash code for the test without the label",
+           "type": "string"
+         },
          "locale": {
            "description": "language tag for formatting the output",
            "type": "string"

diff --git a/schema/rdt_fmt/test_schema.json b/schema/rdt_fmt/test_schema.json
@@ -0,0 +1,118 @@
+{"$schema": "https://json-schema.org/draft/2020-12/schema",
+ "$id": "https://github.com/unicode/conformance/_test_schema.json'",
+ "title": "ICU Conformance test data description",
+ "description": "This documents the format of relative date time format test data for execution",
+ "type": "object",
+ "properties": {
+   "additionalProperties": false,
+   "test_type": {
+     "description": "The name of the test",
+     "type": "string",
+     "enum": ["rdt_fmt"]
+   },
+   "Test scenario": {
+     "type": "string",
+     "description":" Obsolete tag to be removed and replaced with test Type"
+   },
+   "source_file": {
+     "description": "origin of conformance data",
+     "type": "string"
+   },
+   "source_version": {
+     "description": "version of conformance data",
+     "type": "string"
+   },
+   "test_ environmment": {
+     "test_language":  {
+       "description": "Programming language of execution",
+       "type": "string"
+     },
+     "executor": {
+       "description": "path to the executor for this output",
+       "type": "string"
+     },
+     "test_type": {
+       "description": "the kind of tests run",
+       "type": "string"
+     },
+     "date_time": {
+       "description": "timestamp of output",
+       "type": "string"
+     },
+     "input_file": {
+       "description": "path to test data",
+       "type": "string"
+     },
+     "icu_version": {
+       "description": "ICU data version used in testing",
+       "type": "string"
+     },
+     "cldr_version": {
+       "description": "CLDR version used in testing",
+       "type": "string"
+     },
+     "test_count": {
+       "description": "Number of tests run",
+       "type": "integer"
+     }
+   },
+   "error_info": {
+     "description": "count of detected errors",
+     "type": "integer"
+   },
+   "platform": {
+     "description": "the executor's platorm",
+     "type": "integer"
+   },
+   "tests": {
+     "description": "list of N tests for relative date time format testing",
+     "type": "array",
+     "items": {
+       "additionalProperties": false,
+       "type": "object",
+       "properties": {
+         "label": {
+           "description": "A numeric ID, unique for the set of tests",
+           "type": "string"
+         },
+          "hexhash": {
+            "description": "A hexadecimal hash code for the test without the label",
+            "type": "string"
+          },
+         "unit": {
+           "description": "time interval, e.g., year, month, day, hour, etc. ",
+           "type": "string"
+         },
+         "unit": {
+           "count": "how may of the units in past or future",
+           "type": "string"
+         },
+         "options": {
+           "type": "string",
+           "description": "Optional parameters for the output",
+           "type": "object",
+           "properties": {
+             "style": {
+               "type": "string",
+               "description": "size of formated output, e.g., long"
+             },
+             "numberingSystem": {
+               "type": "string",
+               "description": "4 letter script code of numbering system"
+             }
+           }
+
+         }
+       }
+     },
+     "required": [
+       "label",
+       "locale",
+       "count",
+       "unit"
+     ]
+   }
+ },
+ "required": ["test_type"]
+}
+
diff --git a/schema/schema_files.py b/schema/schema_files.py
@@ -2,21 +2,26 @@
 
 ALL_TEST_TYPES = ['collation_short',
                   'datetime_fmt',
+                  'lang_names',
+                  'likely_subtags',
+                  'lang_names',
                   'list_fmt',
                   'message_fmt2',
                   'number_format',
-                  'language_names',
-                  'likely_subtags'
+                  'plural_rules',
+                  'rdt_fmt'
                   ]
 
 TEST_FILE_TO_TEST_TYPE_MAP = {
     'collation_test': 'collation_short',
     'datetime_fmt_test_file': 'datetime_fmt',
-    'lang_name_test_file': 'language_names',
+    'lang_names_test_file': 'lang_names',
     'likely_subtags_test': 'likely_subtags',
+    'list_fmt_test_file': 'list_fmt',
     'message_fmt2_test_file': 'message_fmt2',
     'num_fmt_test_file': 'number_fmt',
-    'list_fmt_test_file': 'list_fmt'
+    'plural_rules_test_file': 'plural_rules',
+    'rdt_fmt_test_file': 'rdt'
 }
 
 SCHEMA_FILE_MAP = {
@@ -83,32 +88,17 @@
         }
     },
 
-    "language_names": {
-        "test_data": {
-            "schema_file": "language_names/test_schema.json",
-            'prod_file': 'lang_name_test_file.json'
-        },
-        "verify_data": {
-            "schema_file": "language_names/verify_schema.json",
-            'prod_file': 'pass.json'
-        },
-        "result_data": {
-            "schema_file": "language_names/result_schema.json",
-            "prod_file": "lang_name_test_file.json"
-        }
-    },
-
     "lang_names": {
         "test_data": {
-            "schema_file": "language_names/test_schema.json",
+            "schema_file": "lang_names/test_schema.json",
             'prod_file': 'lang_name_test_file.json'
         },
         "verify_data": {
-            "schema_file": "language_names/verify_schema.json",
+            "schema_file": "lang_names/verify_schema.json",
             'prod_file': 'pass.json'
         },
         "result_data": {
-            "schema_file": "language_names/result_schema.json",
+            "schema_file": "lang_names/result_schema.json",
             "prod_file": "lang_name_test_file.json"
         }
     },
@@ -139,8 +129,20 @@
             "schema_file": "list_fmt/result_schema.json",
             "prod_file": "list_fmt_test.json"
         }
-
-    # Additional tests
+    },
+    "plural_rules" : {
+        "test_data": {
+            "schema_file": "plural_rules/test_schema.json",
+            'prod_file': 'plural_rules.json'
+        },
+        "verify_data": {
+            "schema_file": "plural_rules/verify_schema.json",
+            'prod_file': 'plural_rules.json'
+        },
+        "result_data": {
+            "schema_file": "plural_rules/result_schema.json",
+            "prod_file": "plural_rules.json"
+        }
     },
     "message_fmt2": {
         "test_data": {
@@ -155,5 +157,21 @@
             "schema_file": "message_fmt2/result_schema.json",
             'prod_file': 'message_fmt2_result.json'
         }
-    }
+    },
+    "rdt_fmt": {
+        "test_data": {
+            "schema_file": "rdt_fmt/test_schema.json",
+            'prod_file': 'rdt_fmt.json'
+        },
+        "verify_data": {
+            "schema_file": "rdt_fmt/verify_schema.json",
+            'prod_file': 'rdt_fmt.json'
+        },
+        "result_data": {
+            "schema_file": "plural_rules/result_schema.json",
+            "prod_file": "rdt_fmt.json"
+        }
+    },
+    # Additional tests
+
 }
diff --git a/schema/schema_validator.py b/schema/schema_validator.py
@@ -133,7 +133,9 @@ def validate_test_data_with_schema(self):
                 file_path_pair = self.get_schema_data_info(icu_version, test_type)
                 if file_path_pair:
                     schema_test_info.append(file_path_pair)
-
+                else:
+                    # logging.info('No data test file  %s for %s, %s', file_path_pair, test_type, icu_version)
+                    pass
         results = self.parallel_check_test_data_schema(schema_test_info)
 
         for result_data in results:
@@ -176,6 +178,7 @@ def get_schema_data_info(self, icu_version, test_type):
                 'test_result_file': test_file_name
             }
         else:
+            # logging.warning('## get_schema_data_info. No file at test_file_name: %s', test_file_name);
             return None
 
     def check_test_data_against_schema(self, schema_info):