Merge pull request #132 from E-ARK-Software/fix/CSIP1

Validating package name  - CSIP1

Author: carlwilson

eark_validator/ipxml/resources/schematron/V2.0.4/CSIP/mets_metsRootElement_rules.xml

@@ -7,7 +7,7 @@
         <assert test="mets:mets">CSIP1000;ERROR;The mets root element is mandatory.</assert>
       </rule>
       <rule context="/mets:mets">
-        <assert test="@OBJID != ''">CSIP1;ERROR;The mets/@OBJID attribute is mandatory, its value is a string identifier for the METS document. For the package METS document, this should be the name/ID of the package, i.e. the name of the package root folder. For a representation level METS document this value records the name/ID of the representation, i.e. the name of the top-level representation folder.</assert>
+        <assert test="@OBJID_test">CSIP1;ERROR;The mets/@OBJID attribute is mandatory, its value is a string identifier for the METS document. For the package METS document, this should be the name/ID of the package, i.e. the name of the package root folder. For a representation level METS document this value records the name/ID of the representation, i.e. the name of the top-level representation folder.</assert>
         <assert test="(@TYPE_vocabulary_test) and (@TYPE != 'Other' or (@TYPE = 'Other' and @csip:OTHERTYPE != ''))">CSIP2;ERROR;The mets/@TYPE attibute MUST be used to declare the category of the content held in the package, e.g. book, journal, stereograph, video, etc.. Legal values are defined in a fixed vocabulary.</assert>
         <assert test="(@TYPE = 'Other' and @csip:OTHERTYPE) or @TYPE != 'Other'">CSIP3;WARN;When the `mets/@TYPE` attribute has the value "Other" the `mets/@csip:OTHERTYPE` attribute MUST be used to declare the content category of the package/representation. The value can either be "Other" or any other string that are not present in the vocabulary used in the `mets/@TYPE` attribute.</assert>
         <assert test="(@csip:CONTENTINFORMATIONTYPE_vocabulary_test) and (@csip:CONTENTINFORMATIONTYPE != 'OTHER' or (@csip:CONTENTINFORMATIONTYPE = 'OTHER' and @csip:OTHERCONTENTINFORMATIONTYPE != ''))">CSIP4;ERROR;Used to declare the Content Information Type Specification used when creating the package. Legal values are defined in a fixed vocabulary. The attribute is mandatory for representation level METS documents.</assert>

eark_validator/ipxml/resources/schematron/V2.1.0/CSIP/mets_metsRootElement_rules.xml

@@ -7,7 +7,7 @@
         <assert test="mets:mets">CSIP1000;ERROR;The mets root element is mandatory.</assert>
       </rule>
       <rule context="/mets:mets">
-        <assert test="@OBJID != ''">CSIP1;ERROR;The mets/@OBJID attribute is mandatory, its value is a string identifier for the METS document. For the package METS document, this should be the name/ID of the package, i.e. the name of the package root folder. For a representation level METS document this value records the name/ID of the representation, i.e. the name of the top-level representation folder.</assert>
+        <assert test="@OBJID_test">CSIP1;ERROR;The mets/@OBJID attribute is mandatory, its value is a string identifier for the METS document. For the package METS document, this should be the name/ID of the package, i.e. the name of the package root folder. For a representation level METS document this value records the name/ID of the representation, i.e. the name of the top-level representation folder.</assert>
         <assert test="(@TYPE_vocabulary_test) and (@TYPE != 'Other' or (@TYPE = 'Other' and @csip:OTHERTYPE != ''))">CSIP2;ERROR;The `mets/@TYPE` attribute MUST be used to declare the category of the content held in the package, e.g. "Datasets", "Websites", "Mixes" , "Other", etc.. Legal values are defined in a fixed vocabulary. When the content category used falls outside of the defined vocabulary the `mets/@TYPE` value must be set to "Other" and the specific value declared in `mets/@csip:OTHERTYPE`. The vocabulary will develop under the curation of the DILCIS Board as additional content information type specifications are produced.</assert>
         <assert test="(@TYPE = 'Other' and @csip:OTHERTYPE) or @TYPE != 'Other'">CSIP3;WARN;When the `mets/@TYPE` attribute has the value "Other" the `mets/@csip:OTHERTYPE` attribute MUST be used to declare the content category of the package/representation. The value can either be "Other" or any other string that are not present in the vocabulary used in the `mets/@TYPE` attribute.</assert>
         <assert test="(@csip:CONTENTINFORMATIONTYPE_vocabulary_test) and (@csip:CONTENTINFORMATIONTYPE != 'OTHER' or (@csip:CONTENTINFORMATIONTYPE = 'OTHER' and @csip:OTHERCONTENTINFORMATIONTYPE != ''))">CSIP4;ERROR;Used to declare the Content Information Type Specification used when creating the package. Legal values are defined in a fixed vocabulary. The attribute is mandatory for representation level METS documents.</assert>

eark_validator/ipxml/schematron.py

@@ -51,11 +51,13 @@ class SchematronTests():
 
     tests = {}
 
-    def __init__(self):
+    def __init__(self, to_validate: Optional[Path]):
         for attribute, vocabulary_uri in self.__vocabulary_definitions.items():
-            self.tests[attribute + '_vocabulary_test'] = self.__create_vocabulary_test(attribute, vocabulary_uri)
+            self.tests[attribute + '_vocabulary_test'] = self._create_vocabulary_test(attribute, vocabulary_uri)
 
-    def __create_vocabulary_test(self, attribute: str, vocabulary_uri: str) -> str:
+        self.tests['@OBJID_test'] = self._create_OBJID_test(to_validate)
+
+    def _create_vocabulary_test(self, attribute: str, vocabulary_uri: str) -> str:
         vocabulary_tests = []
         for line_bytes in urlopen(vocabulary_uri):
             line = line_bytes.decode('utf-8')
@@ -70,17 +72,21 @@ def __create_vocabulary_test(self, attribute: str, vocabulary_uri: str) -> str:
 
         return ' or '.join(vocabulary_tests)
 
-schematron_tests = SchematronTests()
+    def _create_OBJID_test(self, to_validate: Optional[Path]):
+        if to_validate:
+            return f"(@OBJID = '{to_validate.stem}')"
+        return "(@OBJID != '')"
 
 class SchematronRuleset():
     """Encapsulates a set of Schematron rules loaded from a file."""
-    def __init__(self, sch_path: str=None):
+    def __init__(self, sch_path: str=None, to_validate: Path=None):
         if not os.path.exists(sch_path):
             raise FileNotFoundError(NO_PATH.format(sch_path))
         if not os.path.isfile(sch_path):
             raise ValueError(NOT_FILE.format(sch_path))
         self._path = sch_path
 
+        schematron_tests = SchematronTests(to_validate)
         try:
             with open(sch_path) as schematron_file:
                 schematron_data = schematron_file.read()

eark_validator/packages.py

@@ -102,13 +102,13 @@ def validate(cls, version: SpecificationVersion, to_validate: Path) -> Validatio
                 'metadata': metadata
                 })
 
-        csip_profile = SC.ValidationProfile(SpecificationType.CSIP, version)
+        csip_profile = SC.ValidationProfile(SpecificationType.CSIP, version, to_validate)
         csip_profile.validate(to_validate.joinpath(METS))
         results = csip_profile.get_all_results()
 
         package: InformationPackage = InformationPackages.from_path(to_validate)
         if package.details.oaispackagetype in ['SIP', 'DIP']:
-            profile = SC.ValidationProfile(SpecificationType.from_string(package.details.oaispackagetype), version)
+            profile = SC.ValidationProfile(SpecificationType.from_string(package.details.oaispackagetype), version, to_validate)
             profile.validate(to_validate.joinpath(METS))
             results.extend(profile.get_all_results())
 

eark_validator/rules.py

@@ -33,10 +33,11 @@
 from eark_validator.specifications.specification import EarkSpecification, Specification, SpecificationType, SpecificationVersion
 from eark_validator.const import NO_PATH, NOT_FILE
 from eark_validator.model import Severity
+from pathlib import Path
 
 class ValidationProfile():
     """ A complete set of Schematron rule sets that comprise a complete validation profile."""
-    def __init__(self, type: SpecificationType, version: SpecificationVersion):
+    def __init__(self, type: SpecificationType, version: SpecificationVersion, to_validate: Path = None):
         specification: Specification = EarkSpecification(type, version).specification
 
         self._rulesets: Dict[str, SchematronRuleset] = {}
@@ -46,7 +47,7 @@ def __init__(self, type: SpecificationType, version: SpecificationVersion):
         self.results: Dict[str, List[Result]] = {}
         self.messages: List[str] = []
         for section in specification.sections:
-            self.rulesets[section] = SchematronRuleset(get_schematron_path(version, specification.id, section))
+            self.rulesets[section] = SchematronRuleset(get_schematron_path(version, specification.id, section), to_validate)
 
     @property
     def specification(self) -> Specification: