google-protobuf 3.21.0 → 4.28.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c45dfcce28e802c96cf4b4179161ae0c36f724a54d5a2535830e1f3def8addd4
-  data.tar.gz: e93796377de0d6aacea3094077cfc2e715d7f8566356933319456ef59cf9f718
+  metadata.gz: 531c1d4e78630f992244bac8fac8176297a60073b58bd92d344083f478f8dcb5
+  data.tar.gz: de1b062231118253de9063e495ce188907760bf536a368a426d0ab1cf59ea5bb
 SHA512:
-  metadata.gz: 97934da6ce205d16d9de579349a4bcf80431582ce1cc39a32d6a8ca5273b850f96afec25bda3dd903c9361d54cad01a2bf53d4af908fd21d39926239de35bcc7
-  data.tar.gz: d78bb7e9b1ba2dd1d14fd8dbf9b76fe4313500fcb380a57de1e79d50767c00313bbbabdf335f37cf734e88b8a3adafa8528cc3507fee9a6532954ac2aacb45cb
+  metadata.gz: ec022839412e0210fa1cd44b34d96defb2c83a0ca7c1b84bc62f00526f2af64d70abbfda7c405b0a8eaa718ab366a80bbbd7ee3a072144a539282adc7fb24059
+  data.tar.gz: 87463961cb841e762147dcdbd648557cd0a5228e122a717f6429220d485a2dea1fe32f3f1efbcb71504e2b2ad1a191810adcf4327c93bcb047bb6fb244a7748b

data/ext/google/protobuf_c/Rakefile

@@ -0,0 +1,3 @@
+import '../../../lib/google/tasks/ffi.rake'
+
+task default: ['ffi-protobuf:default']

data/ext/google/protobuf_c/convert.c

@@ -1,32 +1,9 @@
 // Protocol Buffers - Google's data interchange format
 // Copyright 2008 Google Inc.  All rights reserved.
-// https://developers.google.com/protocol-buffers/
 //
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are
-// met:
-//
-//     * Redistributions of source code must retain the above copyright
-// notice, this list of conditions and the following disclaimer.
-//     * Redistributions in binary form must reproduce the above
-// copyright notice, this list of conditions and the following disclaimer
-// in the documentation and/or other materials provided with the
-// distribution.
-//     * Neither the name of Google Inc. nor the names of its
-// contributors may be used to endorse or promote products derived from
-// this software without specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file or at
+// https://developers.google.com/open-source/licenses/bsd
 
 // -----------------------------------------------------------------------------
 // Ruby <-> upb data conversion functions.
@@ -41,6 +18,7 @@
 
 #include "message.h"
 #include "protobuf.h"
+#include "shared_convert.h"
 
 static upb_StringView Convert_StringData(VALUE str, upb_Arena* arena) {
   upb_StringView ret;
@@ -111,8 +89,7 @@ static int32_t Convert_ToEnum(VALUE value, const char* name,
     case T_SYMBOL: {
       const upb_EnumValueDef* ev =
           upb_EnumDef_FindValueByName(e, rb_id2name(SYM2ID(value)));
-      if (!ev)
-        goto unknownval;
+      if (!ev) goto unknownval;
       val = upb_EnumValueDef_Number(ev);
       break;
     }
@@ -127,6 +104,41 @@ unknownval:
   rb_raise(rb_eRangeError, "Unknown symbol value for enum field '%s'.", name);
 }
 
+VALUE Convert_CheckStringUtf8(VALUE str) {
+  VALUE utf8 = rb_enc_from_encoding(rb_utf8_encoding());
+
+  if (rb_obj_encoding(str) == utf8) {
+    // Note: Just because a string is marked as having UTF-8 encoding does
+    // not mean that it is *valid* UTF-8.  We have to check separately
+    // whether it is valid.
+    if (rb_enc_str_coderange(str) == ENC_CODERANGE_BROKEN) {
+      // TODO: For now
+      // we only warn for this case.  We will remove the warning and throw an
+      // exception below in the 30.x release
+
+      rb_warn(
+          "String is invalid UTF-8. This will be an error in a future "
+          "version.");
+      // VALUE exc = rb_const_get_at(
+      //     rb_cEncoding, rb_intern("InvalidByteSequenceError"));
+      // rb_raise(exc, "String is invalid UTF-8");
+    }
+  } else {
+    // Note: this will not duplicate underlying string data unless
+    // necessary.
+    //
+    // This will throw an exception if the conversion cannot be performed:
+    // - Encoding::UndefinedConversionError if certain characters cannot be
+    //   converted to UTF-8.
+    // - Encoding::InvalidByteSequenceError if certain characters were invalid
+    //   in the source encoding.
+    str = rb_str_encode(str, utf8, 0, Qnil);
+    PBRUBY_ASSERT(rb_enc_str_coderange(str) != ENC_CODERANGE_BROKEN);
+  }
+
+  return str;
+}
+
 upb_MessageValue Convert_RubyToUpb(VALUE value, const char* name,
                                    TypeInfo type_info, upb_Arena* arena) {
   upb_MessageValue ret;
@@ -160,29 +172,18 @@ upb_MessageValue Convert_RubyToUpb(VALUE value, const char* name,
       }
       break;
     }
-    case kUpb_CType_String: {
-      VALUE utf8 = rb_enc_from_encoding(rb_utf8_encoding());
+    case kUpb_CType_String:
       if (rb_obj_class(value) == rb_cSymbol) {
         value = rb_funcall(value, rb_intern("to_s"), 0);
-      } else if (rb_obj_class(value) != rb_cString) {
+      } else if (!rb_obj_is_kind_of(value, rb_cString)) {
         rb_raise(cTypeError,
                  "Invalid argument for string field '%s' (given %s).", name,
                  rb_class2name(CLASS_OF(value)));
       }
 
-      if (rb_obj_encoding(value) != utf8) {
-        // Note: this will not duplicate underlying string data unless
-        // necessary.
-        value = rb_str_encode(value, utf8, 0, Qnil);
-
-        if (rb_enc_str_coderange(value) == ENC_CODERANGE_BROKEN) {
-          rb_raise(rb_eEncodingError, "String is invalid UTF-8");
-        }
-      }
-
+      value = Convert_CheckStringUtf8(value);
       ret.str_val = Convert_StringData(value, arena);
       break;
-    }
     case kUpb_CType_Bytes: {
       VALUE bytes = rb_enc_from_encoding(rb_ascii8bit_encoding());
       if (rb_obj_class(value) != rb_cString) {
@@ -194,7 +195,7 @@ upb_MessageValue Convert_RubyToUpb(VALUE value, const char* name,
       if (rb_obj_encoding(value) != bytes) {
         // Note: this will not duplicate underlying string data unless
         // necessary.
-        // TODO(haberman): is this really necessary to get raw bytes?
+        // TODO: is this really necessary to get raw bytes?
         value = rb_str_encode(value, bytes, 0, Qnil);
       }
 
@@ -227,11 +228,13 @@ upb_MessageValue Convert_RubyToUpb(VALUE value, const char* name,
           ret.uint64_val = NUM2ULL(value);
           break;
         default:
-          break;
+          rb_raise(cTypeError, "Convert_RubyToUpb(): Unexpected type %d",
+                   (int)type_info.type);
       }
       break;
     default:
-      break;
+      rb_raise(cTypeError,
+                "Convert_RubyToUpb(): Unexpected type %d", (int)type_info.type);
   }
 
   return ret;
@@ -255,7 +258,7 @@ VALUE Convert_UpbToRuby(upb_MessageValue upb_val, TypeInfo type_info,
     case kUpb_CType_UInt64:
       return ULL2NUM(upb_val.int64_val);
     case kUpb_CType_Enum: {
-      const upb_EnumValueDef *ev = upb_EnumDef_FindValueByNumber(
+      const upb_EnumValueDef* ev = upb_EnumDef_FindValueByNumber(
           type_info.def.enumdef, upb_val.int32_val);
       if (ev) {
         return ID2SYM(rb_intern(upb_EnumValueDef_Name(ev)));
@@ -312,50 +315,28 @@ upb_MessageValue Msgval_DeepCopy(upb_MessageValue msgval, TypeInfo type_info,
 
 bool Msgval_IsEqual(upb_MessageValue val1, upb_MessageValue val2,
                     TypeInfo type_info) {
-  switch (type_info.type) {
-    case kUpb_CType_Bool:
-      return memcmp(&val1, &val2, 1) == 0;
-    case kUpb_CType_Float:
-    case kUpb_CType_Int32:
-    case kUpb_CType_UInt32:
-    case kUpb_CType_Enum:
-      return memcmp(&val1, &val2, 4) == 0;
-    case kUpb_CType_Double:
-    case kUpb_CType_Int64:
-    case kUpb_CType_UInt64:
-      return memcmp(&val1, &val2, 8) == 0;
-    case kUpb_CType_String:
-    case kUpb_CType_Bytes:
-      return val1.str_val.size == val2.str_val.size &&
-             memcmp(val1.str_val.data, val2.str_val.data, val1.str_val.size) ==
-                 0;
-    case kUpb_CType_Message:
-      return Message_Equal(val1.msg_val, val2.msg_val, type_info.def.msgdef);
-    default:
-      rb_raise(rb_eRuntimeError, "Internal error, unexpected type");
+  upb_Status status;
+  upb_Status_Clear(&status);
+  bool return_value = shared_Msgval_IsEqual(val1, val2, type_info.type,
+                                            type_info.def.msgdef, &status);
+  if (upb_Status_IsOk(&status)) {
+    return return_value;
+  } else {
+    rb_raise(rb_eRuntimeError, "Msgval_IsEqual(): %s",
+             upb_Status_ErrorMessage(&status));
   }
 }
 
 uint64_t Msgval_GetHash(upb_MessageValue val, TypeInfo type_info,
                         uint64_t seed) {
-  switch (type_info.type) {
-    case kUpb_CType_Bool:
-      return _upb_Hash(&val, 1, seed);
-    case kUpb_CType_Float:
-    case kUpb_CType_Int32:
-    case kUpb_CType_UInt32:
-    case kUpb_CType_Enum:
-      return _upb_Hash(&val, 4, seed);
-    case kUpb_CType_Double:
-    case kUpb_CType_Int64:
-    case kUpb_CType_UInt64:
-      return _upb_Hash(&val, 8, seed);
-    case kUpb_CType_String:
-    case kUpb_CType_Bytes:
-      return _upb_Hash(val.str_val.data, val.str_val.size, seed);
-    case kUpb_CType_Message:
-      return Message_Hash(val.msg_val, type_info.def.msgdef, seed);
-    default:
-      rb_raise(rb_eRuntimeError, "Internal error, unexpected type");
+  upb_Status status;
+  upb_Status_Clear(&status);
+  uint64_t return_value = shared_Msgval_GetHash(
+      val, type_info.type, type_info.def.msgdef, seed, &status);
+  if (upb_Status_IsOk(&status)) {
+    return return_value;
+  } else {
+    rb_raise(rb_eRuntimeError, "Msgval_GetHash(): %s",
+             upb_Status_ErrorMessage(&status));
   }
 }

data/ext/google/protobuf_c/convert.h

@@ -1,38 +1,13 @@
 // Protocol Buffers - Google's data interchange format
 // Copyright 2008 Google Inc.  All rights reserved.
-// https://developers.google.com/protocol-buffers/
 //
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are
-// met:
-//
-//     * Redistributions of source code must retain the above copyright
-// notice, this list of conditions and the following disclaimer.
-//     * Redistributions in binary form must reproduce the above
-// copyright notice, this list of conditions and the following disclaimer
-// in the documentation and/or other materials provided with the
-// distribution.
-//     * Neither the name of Google Inc. nor the names of its
-// contributors may be used to endorse or promote products derived from
-// this software without specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file or at
+// https://developers.google.com/open-source/licenses/bsd
 
 #ifndef RUBY_PROTOBUF_CONVERT_H_
 #define RUBY_PROTOBUF_CONVERT_H_
 
-#include <ruby/ruby.h>
-
 #include "protobuf.h"
 #include "ruby-upb.h"