chore: import upstream snapshot with attribution

scripts/sql-test-helpers/create-pgvector-schema.sql

@@ -0,0 +1,43 @@
+CREATE EXTENSION vector;
+
+CREATE TABLE elements (
+    id UUID PRIMARY KEY,
+    element_id VARCHAR,
+    text TEXT,
+    embeddings vector(384),
+    type VARCHAR,
+    system VARCHAR,
+    layout_width DECIMAL,
+    layout_height DECIMAL,
+    points TEXT,
+    url TEXT,
+    version VARCHAR,
+    date_created TIMESTAMPTZ,
+    date_modified TIMESTAMPTZ,
+    date_processed TIMESTAMPTZ,
+    permissions_data TEXT,
+    record_locator TEXT,
+    category_depth INTEGER,
+    parent_id VARCHAR,
+    attached_filename VARCHAR,
+    filetype VARCHAR,
+    last_modified TIMESTAMPTZ,
+    file_directory VARCHAR,
+    filename VARCHAR,
+    languages VARCHAR [],
+    page_number VARCHAR,
+    links TEXT,
+    page_name VARCHAR,
+    link_urls VARCHAR [],
+    link_texts VARCHAR [],
+    sent_from VARCHAR [],
+    sent_to VARCHAR [],
+    subject VARCHAR,
+    section VARCHAR,
+    header_footer_type VARCHAR,
+    emphasized_text_contents VARCHAR [],
+    emphasized_text_tags VARCHAR [],
+    text_as_html TEXT,
+    detection_class_prob DECIMAL
+);
+

scripts/sql-test-helpers/create-sql-instance.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+
+set -e
+
+SCRIPT_DIR=$(dirname "$(realpath "$0")")
+DATABASE_NAME=$1
+DATABASE_FILE_PATH=$2
+
+# Create the SQL instance
+if [[ "$DATABASE_NAME" != "sqlite" ]]; then
+  docker compose version
+  docker compose -f "$SCRIPT_DIR"/docker-compose-"$DATABASE_NAME".yaml up --wait
+  docker compose -f "$SCRIPT_DIR"/docker-compose-"$DATABASE_NAME".yaml ps
+else
+  touch "$DATABASE_FILE_PATH"
+
+  python "$SCRIPT_DIR"/create-sqlite-schema.py "$DATABASE_FILE_PATH"
+fi
+
+echo "$DATABASE_NAME instance is live."

scripts/sql-test-helpers/create-sqlite-schema.py

@@ -0,0 +1,14 @@
+import sqlite3
+import sys
+from pathlib import Path
+
+if __name__ == "__main__":
+    connection = sqlite3.connect(database=sys.argv[1])
+
+    query = None
+    script_path = (Path(__file__).parent / Path("create-sqlite-schema.sql")).resolve()
+    with open(script_path) as f:
+        query = f.read()
+    cursor = connection.cursor()
+    cursor.executescript(query)
+    connection.close()

scripts/sql-test-helpers/create-sqlite-schema.sql

@@ -0,0 +1,40 @@
+CREATE TABLE elements (
+    id TEXT PRIMARY KEY,
+    element_id TEXT,
+    text TEXT,
+    embeddings TEXT,
+    type TEXT,
+    system TEXT,
+    layout_width REAL,
+    layout_height REAL,
+    points TEXT,
+    url TEXT,
+    version TEXT,
+    date_created TEXT,
+    date_modified TEXT,
+    date_processed TEXT,
+    permissions_data TEXT,
+    record_locator TEXT,
+    category_depth INTEGER,
+    parent_id TEXT,
+    attached_filename TEXT,
+    filetype TEXT,
+    last_modified TEXT,
+    file_directory TEXT,
+    filename TEXT,
+    languages TEXT,
+    page_number TEXT,
+    links TEXT,
+    page_name TEXT,
+    link_urls TEXT,
+    link_texts TEXT,
+    sent_from TEXT,
+    sent_to TEXT,
+    subject TEXT,
+    section TEXT,
+    header_footer_type TEXT,
+    emphasized_text_contents TEXT,
+    emphasized_text_tags TEXT,
+    text_as_html TEXT,
+    detection_class_prob DECIMAL
+);

scripts/sql-test-helpers/docker-compose-pgvector.yaml

@@ -0,0 +1,13 @@
+services:
+  pgvector:
+    image: ankane/pgvector
+    restart: always
+    container_name: pgvector_dest
+    ports:
+     - 5433:5432
+    environment:
+      POSTGRES_DB: elements
+      POSTGRES_USER: unstructured
+      POSTGRES_PASSWORD: test
+    volumes:
+      - ./create-pgvector-schema.sql:/docker-entrypoint-initdb.d/init.sql