Breaking: Remove the positional arguments from the pre/post consume scripts. Environment has been preferred for quite some time now

docs/migration-v3.md

@@ -241,3 +241,66 @@ For example:
   }
 }
 ```
+
+## Consume Script Positional Arguments Removed
+
+Pre- and post-consumption scripts no longer receive positional arguments. All information is
+now passed exclusively via environment variables, which have been available since earlier versions.
+
+### Pre-consumption script
+
+Previously, the original file path was passed as `$1`. It is now only available as
+`DOCUMENT_SOURCE_PATH`.
+
+**Before:**
+
+```bash
+#!/usr/bin/env bash
+# $1 was the original file path
+process_document "$1"
+```
+
+**After:**
+
+```bash
+#!/usr/bin/env bash
+process_document "${DOCUMENT_SOURCE_PATH}"
+```
+
+### Post-consumption script
+
+Previously, document metadata was passed as positional arguments `$1` through `$8`:
+
+| Argument | Environment Variable Equivalent |
+| -------- | ------------------------------- |
+| `$1`     | `DOCUMENT_ID`                   |
+| `$2`     | `DOCUMENT_FILE_NAME`            |
+| `$3`     | `DOCUMENT_SOURCE_PATH`          |
+| `$4`     | `DOCUMENT_THUMBNAIL_PATH`       |
+| `$5`     | `DOCUMENT_DOWNLOAD_URL`         |
+| `$6`     | `DOCUMENT_THUMBNAIL_URL`        |
+| `$7`     | `DOCUMENT_CORRESPONDENT`        |
+| `$8`     | `DOCUMENT_TAGS`                 |
+
+**Before:**
+
+```bash
+#!/usr/bin/env bash
+DOCUMENT_ID=$1
+CORRESPONDENT=$7
+TAGS=$8
+```
+
+**After:**
+
+```bash
+#!/usr/bin/env bash
+# Use environment variables directly
+echo "Document ${DOCUMENT_ID} from ${DOCUMENT_CORRESPONDENT} tagged: ${DOCUMENT_TAGS}"
+```
+
+### Action Required
+
+Update any pre- or post-consumption scripts that read `$1`, `$2`, etc. to use the
+corresponding environment variables instead. Environment variables have been the preferred
+option since v1.8.0.

src/documents/consumer.py

@@ -313,7 +313,6 @@ class ConsumerPlugin(
             run_subprocess(
                 [
                     settings.PRE_CONSUME_SCRIPT,
-                    original_file_path,
                 ],
                 script_env,
                 self.log,
@@ -383,14 +382,6 @@ class ConsumerPlugin(
             run_subprocess(
                 [
                     settings.POST_CONSUME_SCRIPT,
-                    str(document.pk),
-                    document.get_public_filename(),
-                    os.path.normpath(document.source_path),
-                    os.path.normpath(document.thumbnail_path),
-                    reverse("document-download", kwargs={"pk": document.pk}),
-                    reverse("document-thumb", kwargs={"pk": document.pk}),
-                    str(document.correspondent),
-                    str(",".join(document.tags.all().values_list("name", flat=True))),
                 ],
                 script_env,
                 self.log,

src/documents/sanity_checker.py

@@ -182,9 +182,8 @@ def _check_thumbnail(
     present_files: set[Path],
 ) -> None:
     """Verify the thumbnail exists and is readable."""
-    # doc.thumbnail_path already returns a resolved Path; no need to re-resolve.
-    thumbnail_path: Final[Path] = doc.thumbnail_path
-    if not thumbnail_path.is_file():
+    thumbnail_path: Final[Path] = Path(doc.thumbnail_path).resolve()
+    if not thumbnail_path.exists() or not thumbnail_path.is_file():
         messages.error(doc.pk, "Thumbnail of document does not exist.")
         return
 
@@ -201,9 +200,8 @@ def _check_original(
     present_files: set[Path],
 ) -> None:
     """Verify the original file exists, is readable, and has matching checksum."""
-    # doc.source_path already returns a resolved Path; no need to re-resolve.
-    source_path: Final[Path] = doc.source_path
-    if not source_path.is_file():
+    source_path: Final[Path] = Path(doc.source_path).resolve()
+    if not source_path.exists() or not source_path.is_file():
         messages.error(doc.pk, "Original of document does not exist.")
         return
 
@@ -239,9 +237,8 @@ def _check_archive(
     elif doc.has_archive_version:
         if TYPE_CHECKING:
             assert isinstance(doc.archive_path, Path)
-        # doc.archive_path already returns a resolved Path; no need to re-resolve.
-        archive_path: Final[Path] = doc.archive_path  # type: ignore[assignment]
-        if not archive_path.is_file():
+        archive_path: Final[Path] = Path(doc.archive_path).resolve()
+        if not archive_path.exists() or not archive_path.is_file():
             messages.error(doc.pk, "Archived version of document does not exist.")
             return
 
@@ -317,15 +314,7 @@ def check_sanity(
     messages = SanityCheckMessages()
     present_files = _build_present_files()
 
-    documents = Document.global_objects.only(
-        "pk",
-        "filename",
-        "mime_type",
-        "checksum",
-        "archive_checksum",
-        "archive_filename",
-        "content",
-    ).iterator(chunk_size=500)
+    documents = Document.global_objects.all()
     for doc in iter_wrapper(documents):
         _check_document(doc, messages, present_files)
 

src/documents/tests/test_consumer.py

@@ -1328,7 +1328,7 @@ class PreConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
                     environment = args[1]
 
                     self.assertEqual(command[0], script.name)
-                    self.assertEqual(command[1], str(self.test_file))
+                    self.assertEqual(len(command), 1)
 
                     subset = {
                         "DOCUMENT_SOURCE_PATH": str(c.input_doc.original_file),
@@ -1478,11 +1478,7 @@ class PostConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
                 environment = args[1]
 
                 self.assertEqual(command[0], script.name)
-                self.assertEqual(command[1], str(doc.pk))
-                self.assertEqual(command[5], f"/api/documents/{doc.pk}/download/")
-                self.assertEqual(command[6], f"/api/documents/{doc.pk}/thumb/")
-                self.assertEqual(command[7], "my_bank")
-                self.assertCountEqual(command[8].split(","), ["a", "b"])
+                self.assertEqual(len(command), 1)
 
                 subset = {
                     "DOCUMENT_ID": str(doc.pk),