Make ORCID regex more permissive (#500)

CHANGELOG.md

@@ -5,6 +5,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+### Fixed
+  - [500](https://github.com/thoth-pub/thoth/issues/500) - Update ORCID regex
 
 ## [[0.11.2]](https://github.com/thoth-pub/thoth/releases/tag/v0.11.2) - 2023-06-19
 ### Changed

thoth-api/migrations/0.11.3/down.sql

@@ -0,0 +1,6 @@
+-- Reinstate earlier version of ORCID validation
+
+ALTER TABLE contributor
+    DROP CONSTRAINT contributor_orcid_check,
+    ADD CONSTRAINT contributor_orcid_check
+    CHECK (orcid ~ '^https:\/\/orcid\.org\/0000-000(1-[5-9]|2-[0-9]|3-[0-4])\d{3}-\d{3}[\dX]$');

thoth-api/migrations/0.11.3/up.sql

@@ -0,0 +1,7 @@
+-- Make ORCID validation more permissive as the docs don't specify a strict pattern
+-- Should be kept in line with Orcid::FromStr, although regex syntax differs slightly
+
+ALTER TABLE contributor
+    DROP CONSTRAINT contributor_orcid_check,
+    ADD CONSTRAINT contributor_orcid_check
+    CHECK (orcid ~ '^https:\/\/orcid\.org\/\d{4}-\d{4}-\d{4}-\d{3}[\dX]$');

thoth-api/src/graphql/model.rs

@@ -2349,7 +2349,7 @@ impl Work {
     }
 
     #[graphql(
-        description = "Indicates that the work contains a bibliogrpahy or other similar information"
+        description = "Indicates that the work contains a bibliography or other similar information"
     )]
     pub fn bibliography_note(&self) -> Option<&String> {
         self.bibliography_note.as_ref()

thoth-api/src/model/mod.rs

@@ -66,7 +66,7 @@ pub struct Isbn(String);
     feature = "backend",
     derive(DieselNewType, juniper::GraphQLScalarValue),
     graphql(
-        description = r#"ORCID (Open Researcher and Contributor ID) identifier. Expressed as `^https:\/\/orcid\.org\/0000-000(1-[5-9]|2-[0-9]|3-[0-4])\d{3}-\d{3}[\dX]$`"#
+        description = r#"ORCID (Open Researcher and Contributor ID) identifier. Expressed as `^https:\/\/orcid\.org\/\d{4}-\d{4}-\d{4}-\d{3}[\dX]$`"#
     )
 )]
 #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq)]
@@ -193,10 +193,10 @@ impl FromStr for Orcid {
             // (?:) = non-capturing group
             // i    = case-insensitive flag
             // $    = end of string
-            // Matches strings of format "[[http[s]://][www.]orcid.org/]0000-000X-XXXX-XXXX"
+            // Matches strings of format "[[http[s]://][www.]orcid.org/]XXXX-XXXX-XXXX-XXXX"
             // and captures the 16-digit identifier segment
             // Corresponds to database constraints although regex syntax differs slightly
-            r#"^(?i:(?:https?://)?(?:www\.)?orcid\.org/)?(0000-000(?:1-[5-9]|2-[0-9]|3-[0-4])\d{3}-\d{3}[\dX]$)"#).unwrap();
+            r#"^(?i:(?:https?://)?(?:www\.)?orcid\.org/)?(\d{4}-\d{4}-\d{4}-\d{3}[\dX]$)"#).unwrap();
         }
         if input.is_empty() {
             Err(ThothError::OrcidEmptyError)
@@ -776,6 +776,7 @@ fn test_orcid_fromstr() {
     assert!(Orcid::from_str("//orcid.org/0000-0002-1234-5678").is_err());
     assert!(Orcid::from_str("https://orcid-org/0000-0002-1234-5678").is_err());
     assert!(Orcid::from_str("0000-0002-1234-5678https://orcid.org/").is_err());
+    assert!(Orcid::from_str("0009-0002-1234-567X").is_ok());
 }
 
 #[test]

thoth-client/assets/schema.json

@@ -12250,7 +12250,7 @@
             {
               "args": [],
               "deprecationReason": null,
-              "description": null,
+              "description": "A general-purpose field used to include information that does not have a specific designated field",
               "isDeprecated": false,
               "name": "generalNote",
               "type": {
@@ -12262,7 +12262,7 @@
             {
               "args": [],
               "deprecationReason": null,
-              "description": null,
+              "description": "Indicates that the work contains a bibliography or other similar information",
               "isDeprecated": false,
               "name": "bibliographyNote",
               "type": {
@@ -22164,7 +22164,7 @@
           "possibleTypes": null
         },
         {
-          "description": "ORCID (Open Researcher and Contributor ID) identifier. Expressed as `^https:\\/\\/orcid\\.org\\/0000-000(1-[5-9]|2-[0-9]|3-[0-4])\\d{3}-\\d{3}[\\dX]$`",
+          "description": "ORCID (Open Researcher and Contributor ID) identifier. Expressed as `^https:\\/\\/orcid\\.org\\/\\d{4}-\\d{4}-\\d{4}-\\d{3}[\\dX]$`",
           "enumValues": null,
           "fields": null,
           "inputFields": null,