From 2e4b6574832b7478d29d37842818da09a2cb71da Mon Sep 17 00:00:00 2001
From: pubpub-zz <4083478+pubpub-zz@users.noreply.github.com>
Date: Sat, 25 Feb 2023 06:21:45 +0100
Subject: [PATCH] ROB: Decode encoded values in get_fields (#1636)

Fixes #424
---
 pypdf/generic/_data_structures.py |  7 +++++++
 tests/test_workflows.py           | 12 ++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/pypdf/generic/_data_structures.py b/pypdf/generic/_data_structures.py
index bb2e028d2..5fc736d82 100644
--- a/pypdf/generic/_data_structures.py
+++ b/pypdf/generic/_data_structures.py
@@ -1162,6 +1162,13 @@ def __init__(self, data: DictionaryObject) -> None:
                 self[NameObject(attr)] = data[attr]
             except KeyError:
                 pass
+        if isinstance(self.get("/V"), EncodedStreamObject):
+            d = cast(EncodedStreamObject, self[NameObject("/V")]).get_data()
+            if isinstance(d, bytes):
+                d = d.decode()
+            elif d is None:
+                d = ""
+            self[NameObject("/V")] = TextStringObject(d)
 
     # TABLE 8.69 Entries common to all field dictionaries
     @property
diff --git a/tests/test_workflows.py b/tests/test_workflows.py
index 74406125b..73d9c9597 100644
--- a/tests/test_workflows.py
+++ b/tests/test_workflows.py
@@ -942,3 +942,15 @@ def test_extra_test_iss1541():
     with pytest.raises(PdfReadError) as exc:
         reader.pages[0].extract_text()
     assert exc.value.args[0] == "Unexpected end of stream"
+
+
+@pytest.mark.external
+def test_fields_returning_stream():
+    """
+    problem reported in #424
+    """
+    url = "https://github.com/mstamy2/PyPDF2/files/1948267/Simple.form.pdf"
+    name = "tst_iss424.pdf"
+    data = BytesIO(get_pdf_from_url(url, name=name))
+    reader = PdfReader(data, strict=False)
+    assert "BtchIssQATit_time" in reader.get_form_text_fields()["TimeStampData"]