From 7a602f2365e9a4de32d31904e4da05bbc6d51ede Mon Sep 17 00:00:00 2001
From: Tessa Walsh <tessa@bitarchivist.net>
Date: Mon, 28 Oct 2024 15:10:11 -0400
Subject: [PATCH] Replace deprecated cgi module with multipart

---
 cdxj_indexer/postquery.py | 22 ++++++++++++----------
 setup.py                  |  1 +
 2 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/cdxj_indexer/postquery.py b/cdxj_indexer/postquery.py
index aafb110..8e35719 100644
--- a/cdxj_indexer/postquery.py
+++ b/cdxj_indexer/postquery.py
@@ -1,14 +1,16 @@
-from warcio.utils import to_native_str
+import base64
+import json
+import sys
 
 from urllib.parse import unquote_plus, urlencode
 from io import BytesIO
 
+from multipart import parse_options_header, MultipartParser
+from warcio.utils import to_native_str
+
 from cdxj_indexer.amf import amf_parse
 
-import base64
-import cgi
-import json
-import sys
+
 
 MAX_QUERY_LENGTH = 4096
 
@@ -101,17 +103,17 @@ def handle_binary(query_data):
 
         args = dict(fp=BytesIO(query_data), environ=env, keep_blank_values=True)
 
-        args["encoding"] = "utf-8"
-
         try:
-            data = cgi.FieldStorage(**args)
+            _, params = parse_options_header(mime)
+            boundary = params["boundary"]
+            parser = MultipartParser(stream, boundary, charset="utf8")
         except ValueError:
             # Content-Type multipart/form-data may lack "boundary" info
             query = handle_binary(query_data)
         else:
             values = []
-            for item in data.list:
-                values.append((item.name, item.value))
+            for part in parser:
+                values.append((part.name, part.value))
 
             query = urlencode(values, True)
 
diff --git a/setup.py b/setup.py
index 9679105..0220633 100755
--- a/setup.py
+++ b/setup.py
@@ -51,6 +51,7 @@ def run_tests(self):
         # temp fix for requests
         "idna<3.0",
         "py3amf",
+        "multipart",
     ],
     zip_safe=True,
     entry_points="""