Merged in feature/support-more-types (pull request #219)

support new types for import

* tests pass

* missing file

* bug fixes

docs/ai.generated/04-data-architecture.md

@@ -1049,7 +1049,7 @@ CREATE TABLE documentEntries (
 - Multiple entries possible per document for version tracking
 
 #### Document Cleans (`documentCleans`)
-PDF validation and format processing records.
+Document validation and format processing records.
 
 ```sql
 CREATE TYPE cleanFailType AS ENUM (
@@ -1061,10 +1061,27 @@ CREATE TYPE cleanFailType AS ENUM (
     'small_dimensions',
     'large_dimensions',
     'small_dpi',
-    'large_dpi'
+    'large_dpi',
+    'password_protected',
+    'contains_macros',
+    'empty_content',
+    'binary_content',
+    'unsupported_encoding',
+    'contains_attachments'
 );
 
-CREATE TYPE cleanMimeType AS ENUM ('application/pdf');
+CREATE TYPE cleanMimeType AS ENUM (
+    'application/pdf',
+    'image/tiff',
+    'image/jpeg',
+    'image/png',
+    'image/bmp',
+    'application/docx',
+    'application/xlsx',
+    'application/pptx',
+    'text/plain',
+    'message/rfc822'
+);
 
 CREATE TABLE documentCleans (
     id uuid PRIMARY KEY DEFAULT uuid_generate_v7(),
@@ -1091,6 +1108,33 @@ CREATE TABLE documentCleans (
 - Cannot have both success and failure indicators
 - Tracks specific failure reasons for troubleshooting
 
+**Supported MIME Types**:
+- `application/pdf` -- PDF documents
+- `image/tiff` -- TIFF images (multi-frame supported)
+- `image/jpeg` -- JPEG images
+- `image/png` -- PNG images
+- `image/bmp` -- BMP images
+- `application/docx` -- Word documents
+- `application/xlsx` -- Excel spreadsheets
+- `application/pptx` -- PowerPoint presentations
+- `text/plain` -- Plain text files
+- `message/rfc822` -- Email messages (EML)
+
+**Failure Reasons**:
+- `invalid_mimetype` -- Unrecognized or unsupported content type
+- `invalid_read` -- Could not read document content
+- `invalid_read_pages` -- Could not read individual pages
+- `zero_page_count` -- Document has no pages/sheets/slides
+- `large_file` -- File exceeds size limit (500MB for images/Office, 100MB for text/email)
+- `small_dimensions` / `large_dimensions` -- Image dimensions outside acceptable range
+- `small_dpi` / `large_dpi` -- Image resolution outside acceptable range (min 72 DPI)
+- `password_protected` -- Document is encrypted or password-protected (DOCX, XLSX, PPTX, OLE2)
+- `contains_macros` -- Document contains VBA macros (DOCX, XLSX, PPTX)
+- `empty_content` -- Document has no meaningful content (blank images, empty text)
+- `binary_content` -- Text file contains binary data (null bytes)
+- `unsupported_encoding` -- Text file uses an unsupported character encoding
+- `contains_attachments` -- Email contains MIME attachments (only plain text emails accepted)
+
 #### Document Clean Entries (`documentCleanEntries`)
 Version tracking for clean operations.