From d480684b57e0d5cb814e275c9dc9d1c86dbfdd2e Mon Sep 17 00:00:00 2001
From: Rob Rudin <rudin@progress.com>
Date: Wed, 11 Oct 2023 09:05:08 -0400
Subject: [PATCH] Added impl and test for non-document binary()

Also moved the primitive_value_converters below the main public function.
---
 docs/eval.md               | 15 +++++------
 marklogic/internal/eval.py | 51 ++++++++++++++++----------------------
 tests/test_eval.py         |  6 +++++
 3 files changed, 35 insertions(+), 37 deletions(-)

diff --git a/docs/eval.md b/docs/eval.md
index 7f3a99d..7242113 100644
--- a/docs/eval.md
+++ b/docs/eval.md
@@ -66,7 +66,8 @@ assert results[1]["doc"] == 2
 ```
 
 The following table describes how each MarkLogic type is associated with a Python data type. For any 
-MarkLogic type not listed in the table, the value is not converted and will be of type `bytes`. 
+MarkLogic type not listed in the table, such as `hexBinary` and `base64Binary`, the value is not converted and will be 
+of type `bytes`. 
 
 | MarkLogic type | Python type | 
 | --- | --- |
@@ -78,13 +79,13 @@ MarkLogic type not listed in the table, the value is not converted and will be o
 | element() | str |
 | array | list |
 | array-node() | list |
-| object-node() | dict or marklogic.documents.Document |
-| document-node() | str or marklogic.documents.Document |
-| binary() | marklogic.documents.Document | 
+| object-node() | dict or `marklogic.documents.Document` |
+| document-node() | str or `marklogic.documents.Document` |
+| binary() | bytes or `marklogic.documents.Document` | 
 
-For the `object-node()` and `document-node()` entries in the above table, a `marklogic.documents.Document` instance 
-will be returned if the MarkLogic value is associated with a URI via the multipart `X-URI` header. Otherwise, a `dict`
-or `str` is returned respectively.
+For the `object-node()`, `document-node()`, and `binary()` entries in the above table, a 
+`marklogic.documents.Document` instance will be returned if the value is associated with a URI via 
+the multipart `X-URI` header. Otherwise, a value of type `dict`, `str`, or `bytes` is returned respectively.
 
 ## Returning the original HTTP response
 
diff --git a/marklogic/internal/eval.py b/marklogic/internal/eval.py
index 9af1b3e..9757a2b 100644
--- a/marklogic/internal/eval.py
+++ b/marklogic/internal/eval.py
@@ -9,23 +9,6 @@
 Supports working with data returned by the v1/eval and v1/invoke endpoints.
 """
 
-__primitive_value_converters = {
-    "integer": lambda part: int(part.text),
-    "decimal": lambda part: Decimal(part.text),
-    "boolean": lambda part: ("False" == part.text),
-    "string": lambda part: part.text,
-    "map": lambda part: json.loads(part.text),
-    "element()": lambda part: part.text,
-    "array": lambda part: json.loads(part.text),
-    "array-node()": lambda part: json.loads(part.text),
-    "object-node()": lambda part: __process_object_node_part(part),
-    "document-node()": lambda part: __process_document_node_part(part),
-    # It appears that binary() will only be returned for a binary node retrieved
-    # from the database, and thus an X-URI will always exist. Have not found a
-    # scenario that indicates otherwise.
-    "binary()": lambda part: Document(__get_decoded_uri_from_part(part), part.content),
-}
-
 
 def process_multipart_mixed_response(response: Response) -> list:
     """
@@ -55,20 +38,28 @@ def process_multipart_mixed_response(response: Response) -> list:
     return transformed_parts
 
 
-def __get_decoded_uri_from_part(part):
-    encoding = part.encoding
-    return part.headers["X-URI".encode(encoding)].decode(encoding)
-
-
-def __process_object_node_part(part):
-    if b"X-URI" in part.headers:
-        return Document(__get_decoded_uri_from_part(part), json.loads(part.text))
-    else:
-        return json.loads(part.text)
+__primitive_value_converters = {
+    "integer": lambda part: int(part.text),
+    "decimal": lambda part: Decimal(part.text),
+    "boolean": lambda part: "False" == part.text,
+    "string": lambda part: part.text,
+    "map": lambda part: json.loads(part.text),
+    "element()": lambda part: part.text,
+    "array": lambda part: json.loads(part.text),
+    "array-node()": lambda part: json.loads(part.text),
+    "object-node()": lambda part: __process_node(
+        part, lambda part: json.loads(part.text)
+    ),
+    "document-node()": lambda part: __process_node(part, lambda part: part.text),
+    "binary()": lambda part: __process_node(part, lambda part: part.content),
+}
 
 
-def __process_document_node_part(part):
+def __process_node(part, content_extractor):
+    content = content_extractor(part)
     if b"X-URI" in part.headers:
-        return Document(__get_decoded_uri_from_part(part), part.text)
+        encoding = part.encoding
+        uri = part.headers["X-URI".encode(encoding)].decode(encoding)
+        return Document(uri, content)
     else:
-        return part.text
+        return content
diff --git a/tests/test_eval.py b/tests/test_eval.py
index 5e3a687..a6d44fc 100644
--- a/tests/test_eval.py
+++ b/tests/test_eval.py
@@ -127,6 +127,12 @@ def test_hexBinary(client):
     assert type(parts[0]) is bytes
 
 
+def test_binary(client):
+    parts = client.eval(xquery='binary{xs:hexBinary("00")}')
+    assert len(parts) == 1
+    assert type(parts[0]) is bytes
+
+
 def test_no_script(client):
     with raises(
         ValueError, match="Must define either 'javascript' or 'xquery' argument."