paperstack-cli 0.4.1__tar.gz → 0.4.2__tar.gz

{paperstack_cli-0.4.1 → paperstack_cli-0.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: paperstack-cli
-Version: 0.4.1
+Version: 0.4.2
 Summary: Review, inspect, and retrieve research sources from one CLI
 Project-URL: Repository, https://github.com/MilkClouds/paperstack
 Project-URL: Issues, https://github.com/MilkClouds/paperstack/issues

{paperstack_cli-0.4.1 → paperstack_cli-0.4.2}/src/paperstack/content/arxiv_pdf.py

@@ -16,6 +16,8 @@ import urllib.error
 import urllib.request
 from pathlib import Path
 
+from ..tls import arxiv_context
+
 _CACHE_ROOT = Path(os.environ.get("XDG_CACHE_HOME", Path.home() / ".cache"))
 CACHE_DIR = Path(os.environ.get("PAPERSTACK_PAPERS_DIR", _CACHE_ROOT / "paperstack" / "papers"))
 CONVERTER = "pdf-inspector"
@@ -27,7 +29,7 @@ def _fetch(url: str, timeout: int = 60) -> bytes | None:
     req = urllib.request.Request(url, headers={"User-Agent": "paperstack/1.0 (+arxiv pdf fetch)"})
     for attempt in range(3):
         try:
-            with urllib.request.urlopen(req, timeout=timeout) as resp:
+            with urllib.request.urlopen(req, timeout=timeout, context=arxiv_context()) as resp:
                 return resp.read()
         except urllib.error.HTTPError as e:
             if e.code == 429:

{paperstack_cli-0.4.1 → paperstack_cli-0.4.2}/src/paperstack/content/arxiv_source.py

@@ -22,6 +22,8 @@ import urllib.request
 import zlib
 from pathlib import Path
 
+from ..tls import arxiv_context
+
 _CACHE_ROOT = Path(os.environ.get("XDG_CACHE_HOME", Path.home() / ".cache"))
 CACHE_DIR = Path(os.environ.get("PAPERSTACK_PAPERS_DIR", _CACHE_ROOT / "paperstack" / "papers"))
 
@@ -43,7 +45,7 @@ def _fetch_bytes(url: str, timeout: int = 60) -> bytes | None:
     )
     for attempt in range(3):
         try:
-            with urllib.request.urlopen(req, timeout=timeout) as resp:
+            with urllib.request.urlopen(req, timeout=timeout, context=arxiv_context()) as resp:
                 return resp.read()
         except urllib.error.HTTPError as e:
             if e.code == 429:

{paperstack_cli-0.4.1 → paperstack_cli-0.4.2}/src/paperstack/metadata.py

@@ -20,6 +20,7 @@ from pathlib import Path
 from filelock import FileLock
 
 from . import credentials
+from .tls import arxiv_context
 
 ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", "arxiv": "http://arxiv.org/schemas/atom"}
 SOURCES = ("semantic_scholar", "dblp", "crossref", "openreview", "acl_anthology", "arxiv")
@@ -123,6 +124,7 @@ def request(
         **(headers or {}),
     }
     req = urllib.request.Request(url, headers=request_headers, data=data)
+    open_options = {"context": arxiv_context()} if "arxiv.org" in host else {}
     with _request_slot(request_key) as shared_timestamp:
         for attempt in range(3):
             elapsed = min(
@@ -132,7 +134,7 @@ def request(
             if elapsed < interval:
                 time.sleep(interval - elapsed)
             try:
-                with urllib.request.urlopen(req, timeout=30) as response:
+                with urllib.request.urlopen(req, timeout=30, **open_options) as response:
                     _last_request[request_key] = time.monotonic()
                     _mark_request(shared_timestamp)
                     return response.read()

paperstack_cli-0.4.2/src/paperstack/tls.py

@@ -0,0 +1,15 @@
+"""TLS settings for hosts that reject some client handshakes."""
+
+from __future__ import annotations
+
+import functools
+import ssl
+
+
+@functools.cache
+def arxiv_context() -> ssl.SSLContext:
+    # arXiv's Fastly edge answers uncached requests with 406 when the TLS 1.3
+    # ClientHello offers the X25519MLKEM768 hybrid key share (OpenSSL >= 3.5 default).
+    context = ssl.create_default_context()
+    context.set_ecdh_curve("X25519")
+    return context