Issue #23248: Update ssl error codes from latest OpenSSL git master.

Misc/NEWS

@@ -203,6 +203,8 @@ Core and Builtins
 Library
 -------
 
+- Issue #23248: Update ssl error codes from latest OpenSSL git master.
+
 - Issue #23266: Much faster implementation of ipaddress.collapse_addresses()
   when there are many non-consecutive addresses.
 

Tools/ssl/make_ssl_data.py

@@ -5,8 +5,7 @@ This script should be called *manually* when we want to upgrade SSLError
 `library` and `reason` mnemnonics to a more recent OpenSSL version.
 
 It takes two arguments:
-- the path to the OpenSSL include files' directory
-  (e.g. openssl-1.0.1-beta3/include/openssl/)
+- the path to the OpenSSL source tree (e.g. git checkout)
 - the path to the C file to be generated
   (probably Modules/_ssl_data.h)
 """
@@ -15,9 +14,10 @@ import datetime
 import os
 import re
 import sys
+import _ssl
 
 
-def parse_error_codes(h_file, prefix):
+def parse_error_codes(h_file, prefix, libcode):
     pat = re.compile(r"#define\W+(%s([\w]+))\W+(\d+)\b" % re.escape(prefix))
     codes = []
     with open(h_file, "r", encoding="latin1") as f:
@@ -26,7 +26,8 @@ def parse_error_codes(h_file, prefix):
             if match:
                 code, name, num = match.groups()
                 num = int(num)
-                codes.append((code, name, num))
+                # e.g. ("SSL_R_BAD_DATA", ("ERR_LIB_SSL", "BAD_DATA", 390))
+                codes.append((code, (libcode, name, num)))
     return codes
 
 if __name__ == "__main__":
@@ -34,12 +35,32 @@ if __name__ == "__main__":
     outfile = sys.argv[2]
     use_stdout = outfile == '-'
     f = sys.stdout if use_stdout else open(outfile, "w")
-    error_libraries = (
-        # (library code, mnemonic, error prefix, header file)
-        ('ERR_LIB_PEM', 'PEM', 'PEM_R_', 'pem.h'),
-        ('ERR_LIB_SSL', 'SSL', 'SSL_R_', 'ssl.h'),
-        ('ERR_LIB_X509', 'X509', 'X509_R_', 'x509.h'),
-        )
+    error_libraries = {
+        # mnemonic -> (library code, error prefix, header file)
+        'PEM': ('ERR_LIB_PEM', 'PEM_R_', 'crypto/pem/pem.h'),
+        'SSL': ('ERR_LIB_SSL', 'SSL_R_', 'ssl/ssl.h'),
+        'X509': ('ERR_LIB_X509', 'X509_R_', 'crypto/x509/x509.h'),
+        }
+
+    # Read codes from libraries
+    new_codes = []
+    for libcode, prefix, h_file in sorted(error_libraries.values()):
+        new_codes += parse_error_codes(os.path.join(openssl_inc, h_file),
+                                       prefix, libcode)
+    new_code_nums = set((libcode, num)
+                        for (code, (libcode, name, num)) in new_codes)
+
+    # Merge with existing codes (in case some old codes disappeared).
+    codes = {}
+    for errname, (libnum, errnum) in _ssl.err_names_to_codes.items():
+        lib = error_libraries[_ssl.lib_codes_to_names[libnum]]
+        libcode = lib[0]              # e.g. ERR_LIB_PEM
+        errcode = lib[1] + errname    # e.g. SSL_R_BAD_SSL_SESSION_ID_LENGTH
+        # Only keep it if the numeric codes weren't reused
+        if (libcode, errnum) not in new_code_nums:
+            codes[errcode] = libcode, errname, errnum
+    codes.update(dict(new_codes))
+
     def w(l):
         f.write(l + "\n")
     w("/* File generated by Tools/ssl/make_ssl_data.py */")
@@ -47,21 +68,19 @@ if __name__ == "__main__":
     w("")
 
     w("static struct py_ssl_library_code library_codes[] = {")
-    for libcode, mnemo, _, _ in error_libraries:
+    for mnemo, (libcode, _, _) in sorted(error_libraries.items()):
         w('    {"%s", %s},' % (mnemo, libcode))
     w('    { NULL }')
     w('};')
     w("")
 
     w("static struct py_ssl_error_code error_codes[] = {")
-    for libcode, _, prefix, h_file in error_libraries:
-        codes = parse_error_codes(os.path.join(openssl_inc, h_file), prefix)
-        for code, name, num in sorted(codes):
-            w('  #ifdef %s' % (code))
-            w('    {"%s", %s, %s},' % (name, libcode, code))
-            w('  #else')
-            w('    {"%s", %s, %d},' % (name, libcode, num))
-            w('  #endif')
+    for errcode, (libcode, name, num) in sorted(codes.items()):
+        w('  #ifdef %s' % (errcode))
+        w('    {"%s", %s, %s},' % (name, libcode, errcode))
+        w('  #else')
+        w('    {"%s", %s, %d},' % (name, libcode, num))
+        w('  #endif')
     w('    { NULL }')
     w('};')
     if not use_stdout: