Feat: Add pdf layout switch for email

src/documents/consumer.py

@@ -47,6 +47,7 @@ from documents.templating.workflows import parse_w_workflow_placeholders
 from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
+from paperless_mail.parsers import MailDocumentParser
 
 
 class WorkflowTriggerPlugin(
@@ -474,7 +475,18 @@ class ConsumerPlugin(
                 ConsumerStatusShortMessage.PARSING_DOCUMENT,
             )
             self.log.debug(f"Parsing {self.filename}...")
-            document_parser.parse(self.working_copy, mime_type, self.filename)
+            if (
+                isinstance(document_parser, MailDocumentParser)
+                and self.input_doc.mailrule_id
+            ):
+                document_parser.parse(
+                    self.working_copy,
+                    mime_type,
+                    self.filename,
+                    self.input_doc.mailrule_id,
+                )
+            else:
+                document_parser.parse(self.working_copy, mime_type, self.filename)
 
             self.log.debug(f"Generating thumbnail for {self.filename}...")
             self._send_progress(

src/paperless_mail/migrations/0029_mailrule_pdf_layout.py

@@ -0,0 +1,27 @@
+# Generated by Django 5.1.3 on 2024-11-24 12:39
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("paperless_mail", "0028_alter_mailaccount_password_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="mailrule",
+            name="pdf_layout",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Text, then HTML"),
+                    (2, "HTML, then text"),
+                    (3, "HTML only"),
+                    (4, "Text only"),
+                ],
+                default=1,
+                verbose_name="pdf layout",
+            ),
+        ),
+    ]

src/paperless_mail/models.py

@@ -115,6 +115,12 @@ class MailRule(document_models.ModelWithOwner):
         ATTACHMENTS_ONLY = 1, _("Only process attachments.")
         EVERYTHING = 2, _("Process all files, including 'inline' attachments.")
 
+    class PdfLayout(models.IntegerChoices):
+        TEXT_HTML = 1, _("Text, then HTML")
+        HTML_TEXT = 2, _("HTML, then text")
+        HTML_ONLY = 3, _("HTML only")
+        TEXT_ONLY = 4, _("Text only")
+
     class MailAction(models.IntegerChoices):
         DELETE = 1, _("Delete")
         MOVE = 2, _("Move to specified folder")
@@ -230,6 +236,12 @@ class MailRule(document_models.ModelWithOwner):
         default=ConsumptionScope.ATTACHMENTS_ONLY,
     )
 
+    pdf_layout = models.PositiveIntegerField(
+        _("pdf layout"),
+        choices=PdfLayout.choices,
+        default=PdfLayout.TEXT_HTML,
+    )
+
     action = models.PositiveIntegerField(
         _("action"),
         choices=MailAction.choices,

src/paperless_mail/parsers.py

@@ -22,6 +22,7 @@ from documents.parsers import DocumentParser
 from documents.parsers import ParseError
 from documents.parsers import make_thumbnail_from_pdf
 from paperless.models import OutputTypeChoices
+from paperless_mail.models import MailRule
 
 
 class MailDocumentParser(DocumentParser):
@@ -121,7 +122,13 @@ class MailDocumentParser(DocumentParser):
         result.sort(key=lambda item: (item["prefix"], item["key"]))
         return result
 
-    def parse(self, document_path: Path, mime_type: str, file_name=None):
+    def parse(
+        self,
+        document_path: Path,
+        mime_type: str,
+        file_name=None,
+        mailrule: int | None = None,
+    ):
         """
         Parses the given .eml into formatted text, based on the decoded email.
 
@@ -180,7 +187,11 @@ class MailDocumentParser(DocumentParser):
             self.date = mail.date
 
         self.log.debug("Creating a PDF from the email")
-        self.archive_path = self.generate_pdf(mail)
+        if mailrule:
+            rule = MailRule.objects.get(pk=mailrule)
+            self.archive_path = self.generate_pdf(mail, rule.pdf_layout)
+        else:
+            self.archive_path = self.generate_pdf(mail)
 
     @staticmethod
     def parse_file_to_message(filepath: Path) -> MailMessage:
@@ -217,7 +228,11 @@ class MailDocumentParser(DocumentParser):
                 f"{settings.TIKA_ENDPOINT}: {err}",
             ) from err
 
-    def generate_pdf(self, mail_message: MailMessage) -> Path:
+    def generate_pdf(
+        self,
+        mail_message: MailMessage,
+        pdf_layout: MailRule.PdfLayout = MailRule.PdfLayout.TEXT_HTML,
+    ) -> Path:
         archive_path = Path(self.tempdir) / "merged.pdf"
 
         mail_pdf_file = self.generate_pdf_from_mail(mail_message)
@@ -246,7 +261,17 @@ class MailDocumentParser(DocumentParser):
                 if pdf_a_format is not None:
                     route.pdf_format(pdf_a_format)
 
-                route.merge([mail_pdf_file, pdf_of_html_content])
+                match pdf_layout:
+                    case MailRule.PdfLayout.TEXT_HTML:
+                        route.merge([mail_pdf_file, pdf_of_html_content])
+                    case MailRule.PdfLayout.HTML_TEXT:
+                        route.merge([pdf_of_html_content, mail_pdf_file])
+                    case MailRule.PdfLayout.HTML_ONLY:
+                        route.merge([pdf_of_html_content])
+                    case MailRule.PdfLayout.TEXT_ONLY:
+                        route.merge([mail_pdf_file])
+                    case _:
+                        route.merge([mail_pdf_file, pdf_of_html_content])
 
                 try:
                     response = route.run()

src/paperless_mail/serialisers.py

@@ -96,6 +96,7 @@ class MailRuleSerializer(OwnedObjectSerializer):
             "order",
             "attachment_type",
             "consumption_scope",
+            "pdf_layout",
             "owner",
             "user_can_change",
             "permissions",