issue #187: add parameter to exclude issue types

pkiraly · Nov 6, 2022 · 40be8e8 · 40be8e8
1 parent 26276f1
commit 40be8e8
Show file tree

Hide file tree

Showing 2 changed files with 42 additions and 21 deletions.
diff --git a/README.md b/README.md
@@ -281,7 +281,6 @@ The `./metadata-qa.sh` script has the following options:
 
 ## Detailed instructions
 
-
 We will use the same jar file in every command, so we save its path into a variable.
 
 ```bash
@@ -415,7 +414,29 @@ options:
   will be segmented, which should be handled after the process.
 * `-t`, `--collectAllErrors`: collect all errors (useful only for validating small number of records). Default is 
   turned off.
-
+* `-i`, `--ignorableIssueTypes`: comma separated list of issue types not to collect. The valid values are:
+  * `undetectableType`: undetectable type
+  * `invalidLinkage`: invalid linkage
+  * `ambiguousLinkage`: ambiguous linkage
+  * `obsoleteControlPosition`: obsolete code
+  * `controlValueContainsInvalidCode`: invalid code
+  * `hasInvalidValue`: invalid value
+  * `missingSubfield`: missing reference subfield (880$6)
+  * `nonrepeatableField`: repetition of non-repeatable field
+  * `undefinedField`: undefined field
+  * `obsoleteIndicator`: obsolete value
+  * `nonEmptyIndicator`: non-empty indicator
+  * `hasInvalidValue`: invalid value
+  * `undefinedSubfield`: undefined subfield
+  * `invalidLength`: invalid length
+  * `invalidReference`: invalid classification reference
+  * `patternMismatch`: content does not match any patterns
+  * `nonrepeatableSubfield`: repetition of non-repeatable subfield
+  * `invalidISBN`: invalid ISBN
+  * `invalidISSN`: invalid ISSN
+  * `unparsableContent`: content is not well-formatted
+  * `nullCode`: null subfield code
+  * `hasInvalidValue`: invalid value
 
 Outputs:
 * `issue-by-category.csv`: the counts of issues by categories

diff --git a/src/main/java/de/gwdg/metadataqa/marc/model/validation/ValidationErrorType.java b/src/main/java/de/gwdg/metadataqa/marc/model/validation/ValidationErrorType.java
@@ -4,35 +4,35 @@ public enum ValidationErrorType {
 
   // record
   RECORD_UNDETECTABLE_TYPE(1, "undetectableType", "undetectable type", ValidationErrorCategory.RECORD),
-  RECORD_INVALID_LINKAGE(2, "invalidLinkage", "invalid linkage",  ValidationErrorCategory.RECORD),
-  RECORD_AMBIGUOUS_LINKAGE(3, "ambiguousLinkage", "ambiguous linkage",  ValidationErrorCategory.RECORD),
+  RECORD_INVALID_LINKAGE(2, "invalidLinkage", "invalid linkage", ValidationErrorCategory.RECORD),
+  RECORD_AMBIGUOUS_LINKAGE(3, "ambiguousLinkage", "ambiguous linkage", ValidationErrorCategory.RECORD),
 
   // control subfield
   CONTROL_POSITION_OBSOLETE_CODE(4, "obsoleteControlPosition", "obsolete code", ValidationErrorCategory.CONTROLFIELD),
-  CONTROL_POSITION_INVALID_CODE(5, "controlValueContainsInvalidCode", "invalid code",  ValidationErrorCategory.CONTROLFIELD),
-  CONTROL_POSITION_INVALID_VALUE(6, "hasInvalidValue", "invalid value",  ValidationErrorCategory.CONTROLFIELD),
+  CONTROL_POSITION_INVALID_CODE(5, "controlValueContainsInvalidCode", "invalid code", ValidationErrorCategory.CONTROLFIELD),
+  CONTROL_POSITION_INVALID_VALUE(6, "hasInvalidValue", "invalid value", ValidationErrorCategory.CONTROLFIELD),
 
   // field
-  FIELD_MISSING_REFERENCE_SUBFIELD(7, "missingSubfield", "missing reference subfield (880$6)",  ValidationErrorCategory.DATAFIELD),
-  FIELD_NONREPEATABLE(8, "nonrepeatableField", "repetition of non-repeatable field",  ValidationErrorCategory.DATAFIELD),
-  FIELD_UNDEFINED(9, "undefinedField", "undefined field",  ValidationErrorCategory.DATAFIELD),
+  FIELD_MISSING_REFERENCE_SUBFIELD(7, "missingSubfield", "missing reference subfield (880$6)", ValidationErrorCategory.DATAFIELD),
+  FIELD_NONREPEATABLE(8, "nonrepeatableField", "repetition of non-repeatable field", ValidationErrorCategory.DATAFIELD),
+  FIELD_UNDEFINED(9, "undefinedField", "undefined field", ValidationErrorCategory.DATAFIELD),
 
   // indicator
-  INDICATOR_OBSOLETE(10, "obsoleteIndicator", "obsolete value",  ValidationErrorCategory.INDICATOR),
-  INDICATOR_NON_EMPTY(11, "nonEmptyIndicator", "non-empty indicator",  ValidationErrorCategory.INDICATOR),
-  INDICATOR_INVALID_VALUE(12, "hasInvalidValue", "invalid value",  ValidationErrorCategory.INDICATOR),
+  INDICATOR_OBSOLETE(10, "obsoleteIndicator", "obsolete value", ValidationErrorCategory.INDICATOR),
+  INDICATOR_NON_EMPTY(11, "nonEmptyIndicator", "non-empty indicator", ValidationErrorCategory.INDICATOR),
+  INDICATOR_INVALID_VALUE(12, "hasInvalidValue", "invalid value", ValidationErrorCategory.INDICATOR),
 
   // subfield
   SUBFIELD_UNDEFINED(13, "undefinedSubfield", "undefined subfield", ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_INVALID_LENGTH(14, "invalidLength", "invalid length",  ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_INVALID_CLASSIFICATION_REFERENCE(15, "invalidReference", "invalid classification reference",  ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_PATTERN_MISMATCH(16, "patternMismatch", "content does not match any patterns",  ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_NONREPEATABLE(17, "nonrepeatableSubfield", "repetition of non-repeatable subfield",  ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_ISBN(18, "invalidISBN", "invalid ISBN",  ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_ISSN(19, "invalidISSN", "invalid ISSN",  ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_UNPARSABLE_CONTENT(20, "unparsableContent", "content is not well-formatted",  ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_NULL_CODE(21, "nullCode", "null subfield code",  ValidationErrorCategory.SUBFIELD),
-  SUBFIELD_INVALID_VALUE(22, "hasInvalidValue", "invalid value",  ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_INVALID_LENGTH(14, "invalidLength", "invalid length", ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_INVALID_CLASSIFICATION_REFERENCE(15, "invalidReference", "invalid classification reference", ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_PATTERN_MISMATCH(16, "patternMismatch", "content does not match any patterns", ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_NONREPEATABLE(17, "nonrepeatableSubfield", "repetition of non-repeatable subfield", ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_ISBN(18, "invalidISBN", "invalid ISBN", ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_ISSN(19, "invalidISSN", "invalid ISSN", ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_UNPARSABLE_CONTENT(20, "unparsableContent", "content is not well-formatted", ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_NULL_CODE(21, "nullCode", "null subfield code", ValidationErrorCategory.SUBFIELD),
+  SUBFIELD_INVALID_VALUE(22, "hasInvalidValue", "invalid value", ValidationErrorCategory.SUBFIELD),
   ;
 
   private final int id;