remove .eml parser from tika

src/paperless_mail/migrations/0011_alter_mailrule_action.py

@@ -1,27 +0,0 @@
-# Generated by Django 4.0.4 on 2022-04-19 18:13
-
-from django.db import migrations, models
-
-
-class Migration(migrations.Migration):
-
-    dependencies = [
-        ("paperless_mail", "0010_mailrule_consumption_scope"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="mailrule",
-            name="action",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Delete"),
-                    (2, "Move to specified folder"),
-                    (3, "Mark as read, don't process read mails"),
-                    (4, "Flag the mail, don't process flagged mails"),
-                ],
-                default=3,
-                verbose_name="action",
-            ),
-        ),
-    ]

src/paperless_mail/migrations/0015_mailrule_consumption_scope.py

@@ -1,4 +1,4 @@
-# Generated by Django 4.0.4 on 2022-04-14 22:36
+# Generated by Django 4.0.4 on 2022-05-03 15:58
 
 from django.db import migrations, models
 
@@ -6,7 +6,7 @@ from django.db import migrations, models
 class Migration(migrations.Migration):
 
     dependencies = [
-        ("paperless_mail", "0009_alter_mailrule_action_alter_mailrule_folder"),
+        ("paperless_mail", "0014_alter_mailrule_action"),
     ]
 
     operations = [

src/paperless_mail/migrations/0015_merge_20220429_2356.py

@@ -1,13 +0,0 @@
-# Generated by Django 4.0.4 on 2022-04-29 21:56
-
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-
-    dependencies = [
-        ("paperless_mail", "0011_alter_mailrule_action"),
-        ("paperless_mail", "0014_alter_mailrule_action"),
-    ]
-
-    operations = []

src/paperless_mail/parsers.py

@@ -10,6 +10,7 @@ from documents.parsers import DocumentParser
 from documents.parsers import make_thumbnail_from_pdf
 from documents.parsers import ParseError
 from imap_tools import MailMessage
+from tika import parser
 
 
 class MailDocumentParser(DocumentParser):
@@ -117,6 +118,36 @@ class MailDocumentParser(DocumentParser):
         self.date = mail.date
         self.archive_path = self.generate_pdf(document_path)
 
+    def tika_parse(self, document_path):
+
+        self.log("info", f"Sending {document_path} to Tika server")
+        tika_server = settings.PAPERLESS_TIKA_ENDPOINT
+
+        try:
+            parsed = parser.from_file(document_path, tika_server)
+        except Exception as err:
+            raise ParseError(
+                f"Could not parse {document_path} with tika server at "
+                f"{tika_server}: {err}",
+            )
+
+        subject = parsed["metadata"].get("dc:subject", "<no subject>")
+        content = parsed["content"].strip()
+
+        if content.startswith(subject):
+            content = content[len(subject) :].strip()
+
+        content = re.sub(" +", " ", content)
+        content = re.sub("\n+", "\n", content)
+
+        text = (
+            f"{content}\n\n"
+            f"From: {parsed['metadata'].get('Message-From', '')}\n"
+            f"To: {parsed['metadata'].get('Message-To', '')}\n"
+            f"CC: {parsed['metadata'].get('Message-CC', '')}"
+        )
+        return text
+
     def generate_pdf(self, document_path):
         def clean_html(text: str):
             if isinstance(text, list):