Accepting request 1189727 from devel:languages:python

- Add CVE-2024-39705.patch upstream patch to fix unsafe pickle usage.
  (CVE-2024-39705, gh#nltk/nltk#3266, bsc#1227174).
- Drop CVE-2024-39705-disable-download.patch as it's not needed
  anymore.

OBS-URL: https://build.opensuse.org/request/show/1189727
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/python-nltk?expand=0&rev=17

CVE-2024-39705-disable-download.patch

@@ -1,104 +0,0 @@
----
- nltk/app/chartparser_app.py    |   13 +++++++++++++
- nltk/corpus/reader/util.py     |    2 ++
- nltk/data.py                   |    2 ++
- nltk/parse/transitionparser.py |    2 ++
- nltk/tbl/demo.py               |    4 +++-
- 5 files changed, 22 insertions(+), 1 deletion(-)
-
---- a/nltk/app/chartparser_app.py
-+++ b/nltk/app/chartparser_app.py
-@@ -800,6 +800,10 @@ class ChartComparer:
-             showerror("Error Saving Chart", f"Unable to open file: {filename!r}\n{e}")
- 
-     def load_chart_dialog(self, *args):
-+        showerror("Security Error",
-+                  "Due to gh#nltk/nltk#3266, deserializing from " +
-+                  "a pickle is forbidden.")
-+        return
-         filename = askopenfilename(
-             filetypes=self.CHART_FILE_TYPES, defaultextension=".pickle"
-         )
-@@ -811,6 +815,8 @@ class ChartComparer:
-             showerror("Error Loading Chart", f"Unable to open file: {filename!r}\n{e}")
- 
-     def load_chart(self, filename):
-+        raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                           "a pickle is forbidden.")
-         with open(filename, "rb") as infile:
-             chart = pickle.load(infile)
-         name = os.path.basename(filename)
-@@ -2268,6 +2274,10 @@ class ChartParserApp:
-         if not filename:
-             return
-         try:
-+            showerror("Security Error",
-+                      "Due to gh#nltk/nltk#3266, deserializing from " +
-+                      "a pickle is forbidden.")
-+            return
-             with open(filename, "rb") as infile:
-                 chart = pickle.load(infile)
-             self._chart = chart
-@@ -2306,6 +2316,9 @@ class ChartParserApp:
-             return
-         try:
-             if filename.endswith(".pickle"):
-+                showerror("Due to gh#nltk/nltk#3266, deserializing from " +
-+                          "a pickle is forbidden.")
-+                return
-                 with open(filename, "rb") as infile:
-                     grammar = pickle.load(infile)
-             else:
---- a/nltk/corpus/reader/util.py
-+++ b/nltk/corpus/reader/util.py
-@@ -521,6 +521,8 @@ class PickleCorpusView(StreamBackedCorpu
- 
-     def read_block(self, stream):
-         result = []
-+        raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                           "a pickle is forbidden.")
-         for i in range(self.BLOCK_SIZE):
-             try:
-                 result.append(pickle.load(stream))
---- a/nltk/data.py
-+++ b/nltk/data.py
-@@ -752,6 +752,8 @@ def load(
-     if format == "raw":
-         resource_val = opened_resource.read()
-     elif format == "pickle":
-+        raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                           "a pickle is forbidden.")
-         resource_val = pickle.load(opened_resource)
-     elif format == "json":
-         import json
---- a/nltk/parse/transitionparser.py
-+++ b/nltk/parse/transitionparser.py
-@@ -553,6 +553,8 @@ class TransitionParser(ParserI):
-         """
-         result = []
-         # First load the model
-+        raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                           "a pickle is forbidden.")
-         model = pickle.load(open(modelFile, "rb"))
-         operation = Transition(self._algorithm)
- 
---- a/nltk/tbl/demo.py
-+++ b/nltk/tbl/demo.py
-@@ -253,6 +253,8 @@ def postag(
-                 )
-             )
-         with open(cache_baseline_tagger) as print_rules:
-+            raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                               "a pickle is forbidden.")
-             baseline_tagger = pickle.load(print_rules)
-             print(f"Reloaded pickled tagger from {cache_baseline_tagger}")
-     else:
-@@ -327,7 +329,7 @@ def postag(
-         with open(serialize_output) as print_rules:
-             brill_tagger_reloaded = pickle.load(print_rules)
-         print(f"Reloaded pickled tagger from {serialize_output}")
--        taggedtest_reloaded = brill_tagger.tag_sents(testing_data)
-+        taggedtest_reloaded = brill_tagger_reloaded.tag_sents(testing_data)
-         if taggedtest == taggedtest_reloaded:
-             print("Reloaded tagger tried on test set, results identical")
-         else:

CVE-2024-39705.patch

@@ -0,0 +1,38 @@
+From a12d0a6a8cdba58d5e4e5f92ac62bb80fc26c624 Mon Sep 17 00:00:00 2001
+From: Eric Kafe <kafe.eric@gmail.com>
+Date: Tue, 23 Jul 2024 09:09:09 +0200
+Subject: [PATCH] Prevent data.load from unpickling classes or functions
+
+---
+ nltk/data.py | 11 ++++++++++-
+ 1 file changed, 10 insertions(+), 1 deletion(-)
+
+diff --git a/nltk/data.py b/nltk/data.py
+index cc9229b0a2..fb242721c5 100644
+--- a/nltk/data.py
++++ b/nltk/data.py
+@@ -658,6 +658,15 @@ def retrieve(resource_url, filename=None, verbose=True):
+ }
+ 
+ 
++def restricted_pickle_load(string):
++    """
++    Prevents any class or function from loading.
++    """
++    from nltk.app.wordnet_app import RestrictedUnpickler
++
++    return RestrictedUnpickler(BytesIO(string)).load()
++
++
+ def load(
+     resource_url,
+     format="auto",
+@@ -751,7 +760,7 @@ def load(
+     if format == "raw":
+         resource_val = opened_resource.read()
+     elif format == "pickle":
+-        resource_val = pickle.load(opened_resource)
++        resource_val = restricted_pickle_load(opened_resource.read())
+     elif format == "json":
+         import json
+ 

python-nltk.changes

@@ -1,3 +1,11 @@
+-------------------------------------------------------------------
+Fri Jul 26 07:14:33 UTC 2024 - Daniel Garcia <daniel.garcia@suse.com>
+
+- Add CVE-2024-39705.patch upstream patch to fix unsafe pickle usage.
+  (CVE-2024-39705, gh#nltk/nltk#3266, bsc#1227174).
+- Drop CVE-2024-39705-disable-download.patch as it's not needed
+  anymore.
+
 -------------------------------------------------------------------
 Mon Jul  1 21:02:45 UTC 2024 - Matej Cepl <mcepl@cepl.eu>
 

python-nltk.spec

@@ -63,9 +63,8 @@ Source99:       python-nltk.rpmlintrc
 Patch0:         skip-networked-test.patch
 # PATCH-FIX-UPSTREAM nltk-pr3207-py312.patch gh#nltk/nltk#3207
 Patch1:         nltk-pr3207-py312.patch
-# PATCH-FIX-UPSTREAM CVE-2024-39705-disable-download.patch bsc#1227174 mcepl@suse.com
+# PATCH-FIX-UPSTREAM CVE-2024-39705.patch bsc#1227174 gh#nltk/nltk#3290
-# this patch makes things totally awesome
+Patch2:         CVE-2024-39705.patch
-Patch2:         CVE-2024-39705-disable-download.patch
 BuildRequires:  %{python_module base >= 3.7}
 BuildRequires:  %{python_module pip}
 BuildRequires:  %{python_module setuptools}