Merged in feature/postprocessing (pull request #114)

Feature/postprocessing

* tests

* passtest

* fixshorttests

* mosttests

* improvingbasedockerfile

* testspeeds

* testing

* host

* canparallel

* clean

* passfullsuite

* singlepagemax

* test

* findfeatures

* findstables

* tbls

* tablestoo

* tablestoo

* lateraltests

* tableloc

* cleanup

* inlinetable

* childids

* cleanup

* tests

internal/database/queries/text.sql

@@ -6,24 +6,18 @@ SELECT EXISTS(
 -- name: GetDocumentTextExtractionByHash :one
 SELECT id FROM currentTextEntries WHERE cleanId = @cleanEntryId and hash = @hash;
 
--- name: AddDocumentTextTrigger :one
-INSERT INTO documentTextTriggerExtractions
-    (cleanId, version, createdAt, part) VALUES
-    ($1, $2, $3, $4)
-    returning id;
-
 -- name: GetTextractOutputCurrentPart :one
 WITH client as (
     select id from clients where id = @clientId
 ),
 parts as (
-    SELECT triggers.part
+    SELECT extract.part
         FROM client as c
         JOIN documents as docs on docs.clientId = c.id
         JOIN documentCleans as clean on docs.id = clean.documentId
-        JOIN documentTextTriggerExtractions as triggers
-            on triggers.cleanId = clean.id
-        WHERE date(triggers.createdAt) = date(@queryDate)
+        JOIN documentTextExtractions as extract
+            on extract.cleanId = clean.id
+        WHERE date(extract.createdAt) = date(@queryDate)
 ),
 max_part as (
     SELECT COALESCE(max(part), 0) as max_part_num FROM parts
@@ -40,17 +34,12 @@ WITH client as (
     select id from clients where id = @clientId
 ),
 parts as (
-    SELECT extractions.part
+    SELECT extract.part
         FROM client as c
         JOIN documents as docs on docs.clientId = c.id
         JOIN documentCleans as clean on docs.id = clean.documentId
-        JOIN documentTextTriggerExtractions as triggers
-            on triggers.cleanId = clean.id
-        JOIN documentTextExtractionEntries as textEntries
-            on textEntries.triggerId = triggers.id
-        JOIN documentTextExtractions as extractions
-            on extractions.id = textEntries.textId
-        WHERE date(extractions.createdAt) = date(@queryDate)
+        JOIN documentTextExtractions extract ON extract.cleanId = clean.id
+        WHERE date(extract.createdAt) = date(@queryDate)
 ),
 max_part as (
     SELECT COALESCE(max(part), 0) as max_part_num FROM parts
@@ -62,30 +51,18 @@ FROM parts p
 RIGHT JOIN max_part mp ON p.part = mp.max_part_num
 GROUP BY p.part;
 
--- name: AddDocumentTextTriggerJobId :exec
-UPDATE documentTextTriggerExtractions
-    SET textractJobId = @textractJobId
-    WHERE id = @id;
-
--- name: GetDocumentTextTrigger :one
-SELECT dt.id, dt.cleanId, dt.version, dt.textractJobId, dc.documentId
-    from documentTextTriggerExtractions as dt
-    join documentCleans as dc on dt.cleanId = dc.id
-    where dt.id = @triggerId;
-
 -- name: AddDocumentText :one
 INSERT INTO documentTextExtractions
-    (bucket, key, hash, createdAt, part)
-    VALUES ($1, $2, $3, $4, $5)
+    (cleanId, bucket, key, hash, createdAt, part)
+    VALUES ($1, $2, $3, $4, $5, $6)
     returning id;
 
 -- name: AddDocumentTextEntry :exec
 INSERT INTO documentTextExtractionEntries
-    (textId, triggerId, version)
-    VALUES ($1, $2, $3);
+    (textId, version)
+    VALUES ($1, $2);
 
 -- name: GetTextEntryByDocId :one
-SELECT id, documentId, bucket, key, hash, cleanId,
-    triggerId, textractJobId, triggerVersion, extractionVersion
+SELECT id, documentId, bucket, key, hash, cleanId, extractionVersion
     FROM currentTextEntries
     WHERE documentId = @documentId;