Merged in feature/textextract (pull request #108)

Start adding Textract + UUID changes * base * startclient * ts * short * tests
2025-03-20 11:06:41 +00:00
parent 1587da9d11
commit 53ea7d34e6
196 changed files with 25972 additions and 1456 deletions
@@ -0,0 +1,145 @@
+erDiagram
+    clients ||--o{ clientCanSync : "has"
+    clients ||--o{ documents : "contains"
+    clients ||--o{ collectorVersions : "has"
+    clients ||--o{ collectorActiveVersions : "has current"
+    clients ||--o{ collectorMinCleanVersions : "has"
+    clients ||--o{ collectorMinTextVersions : "has"
+    clients ||--o{ collectorQueries : "maps to"
+
+    documents ||--o{ documentEntries : "has"
+    documents ||--o{ documentCleans : "has clean version"
+    documentCleans ||--o{ documentTextExtractions : "has text extraction"
+    documentTextExtractions ||--o{ results : "produces"
+
+    queries ||--o{ queryVersions : "has"
+    queries ||--o{ queryActiveVersions : "has current"
+    queries ||--o{ requiredQueries : "requires"
+    queries ||--o{ queryConfigs : "configured by"
+    queries ||--o{ collectorQueries : "used in"
+    queries ||--o{ results : "generates"
+
+    results ||--o{ resultDependencies : "depends on"
+
+    clients {
+        uuid id PK
+        TEXT name
+    }
+
+    clientCanSync {
+        uuid id PK
+        uuid clientId FK
+        boolean canSync
+    }
+
+    documents {
+        uuid id PK
+        uuid clientId FK
+        text hash
+    }
+
+    documentEntries {
+        uuid id PK
+        uuid documentId FK
+        text bucket
+        text key
+    }
+
+    documentCleans {
+        uuid id PK
+        uuid documentId FK
+        int version
+        text bucket
+        text key
+    }
+
+    documentTextExtractions {
+        uuid id PK
+        uuid cleanEntryId FK
+        int version
+        text bucket
+        text key
+    }
+
+    queries {
+        uuid id PK
+        queryType type
+    }
+
+    queryVersions {
+        uuid queryId FK
+        int id
+        timestamp addedAt
+    }
+
+    queryActiveVersions {
+        uuid id PK
+        uuid queryId FK
+        int versionId FK
+    }
+
+    requiredQueries {
+        uuid id PK
+        uuid queryId FK
+        uuid requiredQueryId FK
+        int addedVersion FK
+        int removedVersion FK
+    }
+
+    queryConfigs {
+        uuid id PK
+        uuid queryId FK
+        jsonb config
+        int addedVersion FK
+        int removedVersion FK
+    }
+
+    collectorVersions {
+        uuid clientId FK
+        int id
+        timestamp addedAt
+    }
+
+    collectorActiveVersions {
+        uuid id PK
+        uuid clientId FK
+        int versionId FK
+    }
+
+    collectorMinCleanVersions {
+        uuid id PK
+        uuid clientId FK
+        int versionId
+        int addedVersion FK
+        int removedVersion FK
+    }
+
+    collectorMinTextVersions {
+        uuid id PK
+        uuid clientId FK
+        int versionId
+        int addedVersion FK
+        int removedVersion FK
+    }
+
+    collectorQueries {
+        uuid id PK
+        uuid clientId FK
+        varchar name
+        uuid queryId FK
+        int addedVersion FK
+        int removedVersion FK
+    }
+
+    results {
+        uuid id PK
+        uuid textEntryId FK
+        uuid queryId FK
+        TEXT value
+        int queryVersion
+    }
+
+    resultDependencies {
+        uuid resultId FK
+        uuid requiredResultId FK
+    }