bson_ext 0.20

data/ext/cbson/encoding_helpers.c

@@ -0,0 +1,118 @@
+/*
+ * Copyright 2009-2010 10gen, Inc.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include "encoding_helpers.h"
+
+/*
+ * Portions Copyright 2001 Unicode, Inc.
+ *
+ * Disclaimer
+ *
+ * This source code is provided as is by Unicode, Inc. No claims are
+ * made as to fitness for any particular purpose. No warranties of any
+ * kind are expressed or implied. The recipient agrees to determine
+ * applicability of information provided. If this file has been
+ * purchased on magnetic or optical media from Unicode, Inc., the
+ * sole remedy for any claim will be exchange of defective media
+ * within 90 days of receipt.
+ *
+ * Limitations on Rights to Redistribute This Code
+ *
+ * Unicode, Inc. hereby grants the right to freely use the information
+ * supplied in this file in the creation of products supporting the
+ * Unicode Standard, and to make copies of this file in any form
+ * for internal or external distribution as long as this notice
+ * remains attached.
+ */
+
+/*
+ * Index into the table below with the first byte of a UTF-8 sequence to
+ * get the number of trailing bytes that are supposed to follow it.
+ */
+static const char trailingBytesForUTF8[256] = {
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
+};
+
+/* --------------------------------------------------------------------- */
+
+/*
+ * Utility routine to tell whether a sequence of bytes is legal UTF-8.
+ * This must be called with the length pre-determined by the first byte.
+ * The length can be set by:
+ *  length = trailingBytesForUTF8[*source]+1;
+ * and the sequence is illegal right away if there aren't that many bytes
+ * available.
+ * If presented with a length > 4, this returns 0.  The Unicode
+ * definition of UTF-8 goes up to 4-byte sequences.
+ */
+static unsigned char isLegalUTF8(const unsigned char* source, int length) {
+    unsigned char a;
+    const unsigned char* srcptr = source + length;
+    switch (length) {
+    default: return 0;
+        /* Everything else falls through when "true"... */
+    case 4: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return 0;
+    case 3: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return 0;
+    case 2: if ((a = (*--srcptr)) > 0xBF) return 0;
+        switch (*source) {
+            /* no fall-through in this inner switch */
+            case 0xE0: if (a < 0xA0) return 0; break;
+            case 0xF0: if (a < 0x90) return 0; break;
+            case 0xF4: if (a > 0x8F) return 0; break;
+            default:  if (a < 0x80) return 0;
+        }
+        case 1: if (*source >= 0x80 && *source < 0xC2) return 0;
+        if (*source > 0xF4) return 0;
+    }
+    return 1;
+}
+
+result_t check_string(const unsigned char* string, const int length,
+                      const char check_utf8, const char check_null) {
+    int position = 0;
+    /* By default we go character by character. Will be different for checking
+     * UTF-8 */
+    int sequence_length = 1;
+
+    if (!check_utf8 && !check_null) {
+        return VALID;
+    }
+
+    while (position < length) {
+        if (check_null && *(string + position) == 0) {
+            return HAS_NULL;
+        }
+        if (check_utf8) {
+            sequence_length = trailingBytesForUTF8[*(string + position)] + 1;
+            if ((position + sequence_length) > length) {
+                return NOT_UTF_8;
+            }
+            if (!isLegalUTF8(string + position, sequence_length)) {
+                return NOT_UTF_8;
+            }
+        }
+        position += sequence_length;
+    }
+
+    return VALID;
+}

data/ext/cbson/encoding_helpers.h

@@ -0,0 +1,29 @@
+/*
+ * Copyright 2009-2010 10gen, Inc.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#ifndef ENCODING_HELPERS_H
+#define ENCODING_HELPERS_H
+
+typedef enum {
+    VALID,
+    NOT_UTF_8,
+    HAS_NULL
+} result_t;
+
+result_t check_string(const unsigned char* string, const int length,
+                      const char check_utf8, const char check_null);
+
+#endif

data/ext/cbson/extconf.rb

@@ -0,0 +1,10 @@
+require 'mkmf'
+
+have_func("asprintf")
+
+have_header("ruby/st.h") || have_header("st.h")
+have_header("ruby/regex.h") || have_header("regex.h")
+have_header("ruby/encoding.h")
+
+dir_config('cbson')
+create_makefile('bson_ext/cbson')

data/ext/cbson/version.h

@@ -0,0 +1,17 @@
+/*
+ * Copyright 2009-2010 10gen, Inc.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#define VERSION "0.20"

data/ext/lib/bson_ext.rb

@@ -0,0 +1 @@
+puts "hello world"

metadata

@@ -0,0 +1,70 @@
+--- !ruby/object:Gem::Specification 
+name: bson_ext
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 20
+  version: "0.20"
+platform: ruby
+authors: 
+- Mike Dirolf
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-04-07 00:00:00 -04:00
+default_executable: 
+dependencies: []
+
+description: C extensions to accelerate the Ruby BSON serialization. For more information about BSON, see http://bsonspec.org.  For information about MongoDB, see http://www.mongodb.org.
+email: mongodb-dev@googlegroups.com
+executables: []
+
+extensions: 
+- ext/cbson/extconf.rb
+extra_rdoc_files: []
+
+files: 
+- Rakefile
+- bson_ext.gemspec
+- ext/cbson/extconf.rb
+- ext/lib/bson_ext.rb
+- ext/cbson/buffer.c
+- ext/cbson/cbson.c
+- ext/cbson/encoding_helpers.c
+- ext/cbson/buffer.h
+- ext/cbson/encoding_helpers.h
+- ext/cbson/version.h
+has_rdoc: false
+homepage: http://www.mongodb.org
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- ext
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.6
+signing_key: 
+specification_version: 3
+summary: C extensions for Ruby BSON.
+test_files: []
+