Use EXIF data of image to prefill image description

During attachment upload Pleroma returns a "description" field. Pleroma-fe has an MR to use that to pre-fill the image description field, <https://git.pleroma.social/pleroma/pleroma-fe/-/merge_requests/1399>

* This MR allows Pleroma to read the EXIF data during upload and return the description to the FE
    * If a description is already present (e.g. because a previous module added it), it will use that
    * Otherwise it will read from the EXIF data. First it will check -ImageDescription, if that's empty, it will check -iptc:Caption-Abstract
    * If no description is found, it will simply return nil, just like before
* When people set up a new instance, they will be asked if they want to read metadata and this module will be activated if so

This was taken from an MR i did on Pleroma and isn't finished yet.

5 files changed, 112 insertions, 1 deletions

diff --git a/test/fixtures/portrait_of_owls_caption-abstract_tmp.jpg b/test/fixtures/portrait_of_owls_caption-abstract_tmp.jpg
new file mode 100644
index 000000000..f5fe63999
--- /dev/null
+++ b/test/fixtures/portrait_of_owls_caption-abstract_tmp.jpg
diff --git a/test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract_tmp.jpg b/test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract_tmp.jpg
new file mode 100644
index 000000000..0b8b85754
--- /dev/null
+++ b/test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract_tmp.jpg
diff --git a/test/fixtures/portrait_of_owls_no_description_tmp.jpg b/test/fixtures/portrait_of_owls_no_description_tmp.jpg
new file mode 100644
index 000000000..d63d40af8
--- /dev/null
+++ b/test/fixtures/portrait_of_owls_no_description_tmp.jpg
diff --git a/test/mix/tasks/pleroma/instance_test.exs b/test/mix/tasks/pleroma/instance_test.exs
index 249689ec6..e72aab701 100644
--- a/test/mix/tasks/pleroma/instance_test.exs
+++ b/test/mix/tasks/pleroma/instance_test.exs
@@ -69,6 +69,8 @@ defmodule Mix.Tasks.Pleroma.InstanceTest do
         "./test/../test/instance/static/",
         "--strip-uploads",
         "y",
+        "--read-uploads-data",
+        "y",
         "--dedupe-uploads",
         "n",
         "--anonymize-uploads",
@@ -91,7 +93,10 @@ defmodule Mix.Tasks.Pleroma.InstanceTest do
     assert generated_config =~ "password: \"dbpass\""
     assert generated_config =~ "configurable_from_database: true"
     assert generated_config =~ "http: [ip: {127, 0, 0, 1}, port: 4000]"
-    assert generated_config =~ "filters: [Pleroma.Upload.Filter.Exiftool]"
+
+    assert generated_config =~
+             "filters: [Pleroma.Upload.Filter.Exiftool, Pleroma.Upload.Filter.ExiftoolReadData]"
+
     assert File.read!(tmp_path() <> "setup.psql") == generated_setup_psql()
     assert File.exists?(Path.expand("./test/instance/static/robots.txt"))
   end
diff --git a/test/pleroma/upload/filter/exiftool_read_data_test.exs b/test/pleroma/upload/filter/exiftool_read_data_test.exs
new file mode 100644
index 000000000..0861d293a
--- /dev/null
+++ b/test/pleroma/upload/filter/exiftool_read_data_test.exs
@@ -0,0 +1,106 @@
+# Pleroma: A lightweight social networking server
+# Copyright © 2017-2021 Pleroma Authors <https://pleroma.social/>
+# SPDX-License-Identifier: AGPL-3.0-only
+
+defmodule Pleroma.Upload.Filter.ExiftoolReadDataTest do
+  use Pleroma.DataCase, async: true
+  alias Pleroma.Upload.Filter
+
+  @uploads %Pleroma.Upload{
+    name: "portrait_of_owls_imagedescription_and_caption-abstract.jpg",
+    content_type: "image/jpeg",
+    path:
+      Path.absname("test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract.jpg"),
+    tempfile:
+      Path.absname("test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract_tmp.jpg"),
+    description: nil
+  }
+
+  test "keeps description when not empty" do
+    uploads = %Pleroma.Upload{
+      name: "portrait_of_owls_imagedescription_and_caption-abstract.jpg",
+      content_type: "image/jpeg",
+      path:
+        Path.absname("test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract.jpg"),
+      tempfile:
+        Path.absname(
+          "test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract_tmp.jpg"
+        ),
+      description: "Eight different owls"
+    }
+
+    assert Filter.ExiftoolReadData.filter(uploads) ==
+             {:ok, :noop}
+  end
+
+  test "otherwise returns ImageDescription when present" do
+    uploads_after = %Pleroma.Upload{
+      name: "portrait_of_owls_imagedescription_and_caption-abstract.jpg",
+      content_type: "image/jpeg",
+      path:
+        Path.absname("test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract.jpg"),
+      tempfile:
+        Path.absname(
+          "test/fixtures/portrait_of_owls_imagedescription_and_caption-abstract_tmp.jpg"
+        ),
+      description: "Pictures of eight different owls"
+    }
+
+    assert Filter.ExiftoolReadData.filter(@uploads) ==
+             {:ok, :filtered, uploads_after}
+  end
+
+  test "otherwise returns iptc:Caption-Abstract when present" do
+    upload = %Pleroma.Upload{
+      name: "portrait_of_owls_caption-abstract.jpg",
+      content_type: "image/jpeg",
+      path: Path.absname("test/fixtures/portrait_of_owls_caption-abstract.jpg"),
+      tempfile: Path.absname("test/fixtures/portrait_of_owls_caption-abstract_tmp.jpg"),
+      description: nil
+    }
+
+    upload_after = %Pleroma.Upload{
+      name: "portrait_of_owls_caption-abstract.jpg",
+      content_type: "image/jpeg",
+      path: Path.absname("test/fixtures/portrait_of_owls_caption-abstract.jpg"),
+      tempfile: Path.absname("test/fixtures/portrait_of_owls_caption-abstract_tmp.jpg"),
+      description: "Pictures of eight different owls - iptc"
+    }
+
+    assert Filter.ExiftoolReadData.filter(upload) ==
+             {:ok, :filtered, upload_after}
+  end
+
+  test "otherwise returns nil" do
+    uploads = %Pleroma.Upload{
+      name: "portrait_of_owls_no_description-abstract.jpg",
+      content_type: "image/jpeg",
+      path: Path.absname("test/fixtures/portrait_of_owls_no_description.jpg"),
+      tempfile: Path.absname("test/fixtures/portrait_of_owls_no_description_tmp.jpg"),
+      description: nil
+    }
+
+    assert Filter.ExiftoolReadData.filter(uploads) ==
+             {:ok, :filtered, uploads}
+  end
+
+  test "Return nil when image description from EXIF data exceeds the maximum length" do
+    clear_config([:instance, :description_limit], 5)
+
+    assert Filter.ExiftoolReadData.filter(@uploads) ==
+             {:ok, :filtered, @uploads}
+  end
+
+  test "Return nil when image description from EXIF data can't be read" do
+    uploads = %Pleroma.Upload{
+      name: "non-existant.jpg",
+      content_type: "image/jpeg",
+      path: Path.absname("test/fixtures/non-existant.jpg"),
+      tempfile: Path.absname("test/fixtures/non-existant_tmp.jpg"),
+      description: nil
+    }
+
+    assert Filter.ExiftoolReadData.filter(uploads) ==
+             {:ok, :filtered, uploads}
+  end
+end