bson_ext 1.8.6 → 1.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c65812858113d36ab4eabd70baa49338ef93887b
-  data.tar.gz: bc9d5786498123d9f5d2e1d8142d0853935aec15
+  metadata.gz: f0154dfba09c2e43e8f5cb9d1889f0b08a41408f
+  data.tar.gz: e1b85f77e8ddb9faa027a218e32d87730ef08b9c
 SHA512:
-  metadata.gz: 07538e80ea4776323e77d1420ceee868d7b644ae1783dbfd4c810ed33a20390ff89b6df58e4ba695f197d376b70e77a1ec9d632eb65c7404e7058310fb543dac
-  data.tar.gz: b2955ad06298b40c67ca63c3665a07bcd4391ae4f11a7324148fe078f87e767313f164901826ad54c8f4a53898648a333153761971b5b93329016f987999eaa5
+  metadata.gz: 7872d36e308936e291f0b899b15501060731e21cc96ba6d0aeaf0495d3362167fa411ac6ba5635c2bd5b94b50b1ad041951d96cf858a0a10c7afc812bae502b3
+  data.tar.gz: c0558e9f81070a16c0a010a20e133fd18c60fa7feac74e3366f0f57d86303bab8fe887e6bddc532a05a923b59bbcfdfa6c8efc2b1d27e76b5286d9e95ce26d8a

data.tar.gz.sig

@@ -1 +1,4 @@
-`�����byv���򰢉��
+Wkԃw/'a�}��ag]:1��k���zC�nu�e�hR��~�
+j�֙X�&�Ӑx]��;�@ԛ�,/g��=
+qW{X�T�'
+X���v�����6"�'>�3�r(��>j���a�:�q�����&N���.�u�)ŜGǔ)Nv��ǵ��

data/VERSION

@@ -1 +1 @@
-1.8.6
+1.9.0

data/ext/cbson/bson_buffer.c

@@ -1,3 +1,19 @@
+/*
+ * Copyright (C) 2013 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 <stdlib.h>
 #include <string.h>
 

data/ext/cbson/bson_buffer.h

@@ -1,3 +1,19 @@
+/*
+ * Copyright (C) 2013 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 _BSON_BUFFER_H
 #define _BSON_BUFFER_H
 

data/ext/cbson/cbson.c

@@ -1,3 +1,19 @@
+/*
+ * Copyright (C) 2013 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.
+ */
+
 /*
  * This file contains C implementations of some of the functions needed by the
  * bson module. If possible, these implementations should be used to speed up
@@ -98,13 +114,14 @@ static int max_bson_size;
 #define STR_NEW(p,n) rb_str_new((p), (n))
 #endif
 
-static void write_utf8(bson_buffer_t buffer, VALUE string, char check_null) {
-    result_t status = check_string((unsigned char*)RSTRING_PTR(string), RSTRING_LEN(string),
-                                   1, check_null);
+static void write_utf8(bson_buffer_t buffer, VALUE string, int allow_null) {
+    result_t status = validate_utf8_encoding(
+        (const char*)RSTRING_PTR(string), RSTRING_LEN(string), allow_null);
+
     if (status == HAS_NULL) {
         bson_buffer_free(buffer);
         rb_raise(InvalidDocument, "Key names / regex patterns must not contain the NULL byte");
-    } else if (status == NOT_UTF_8) {
+    } else if (status == INVALID_UTF8) {
         bson_buffer_free(buffer);
         rb_raise(InvalidStringEncoding, "String not valid UTF-8");
     }
@@ -186,7 +203,7 @@ static VALUE pack_extra(bson_buffer_t buffer, VALUE check_keys) {
 
 static void write_name_and_type(bson_buffer_t buffer, VALUE name, char type) {
     SAFE_WRITE(buffer, &type, 1);
-    write_utf8(buffer, name, 1);
+    write_utf8(buffer, name, 0);
     SAFE_WRITE(buffer, &zero, 1);
 }
 
@@ -315,7 +332,7 @@ static int write_element(VALUE key, VALUE value, VALUE extra, int allow_id) {
             write_name_and_type(buffer, key, 0x02);
             length = RSTRING_LENINT(value) + 1;
             SAFE_WRITE(buffer, (char*)&length, 4);
-            write_utf8(buffer, value, 0);
+            write_utf8(buffer, value, 1);
             SAFE_WRITE(buffer, &zero, 1);
             break;
         }
@@ -447,7 +464,7 @@ static int write_element(VALUE key, VALUE value, VALUE extra, int allow_id) {
                 write_name_and_type(buffer, key, 0x02);
                 length = RSTRING_LENINT(str) + 1;
                 SAFE_WRITE(buffer, (char*)&length, 4);
-                write_utf8(buffer, str, 0);
+                write_utf8(buffer, str, 1);
                 SAFE_WRITE(buffer, &zero, 1);
                 break;
             }
@@ -488,7 +505,7 @@ static int write_element(VALUE key, VALUE value, VALUE extra, int allow_id) {
 
             write_name_and_type(buffer, key, 0x0B);
 
-            write_utf8(buffer, pattern, 1);
+            write_utf8(buffer, pattern, 0);
             SAFE_WRITE(buffer, &zero, 1);
 
             if (flags & IGNORECASE) {
@@ -541,6 +558,7 @@ static void write_doc(bson_buffer_t buffer, VALUE hash, VALUE check_keys, VALUE
     bson_buffer_position length_location = bson_buffer_save_space(buffer, 4);
     bson_buffer_position length;
     int allow_id;
+    int max_size;
     int (*write_function)(VALUE, VALUE, VALUE) = NULL;
     VALUE id_str = rb_str_new2("_id");
     VALUE id_sym = ID2SYM(rb_intern("_id"));
@@ -601,12 +619,12 @@ static void write_doc(bson_buffer_t buffer, VALUE hash, VALUE check_keys, VALUE
     length = bson_buffer_get_position(buffer) - start_position;
 
     // make sure that length doesn't exceed the max size (determined by server, defaults to 4mb)
-    if (length > bson_buffer_get_max_size(buffer)) {
-      bson_buffer_free(buffer);
-      rb_raise(InvalidDocument,
-          "Document too large: This BSON document is limited to %d bytes.",
-          bson_buffer_get_max_size(buffer));
-      return;
+    max_size = bson_buffer_get_max_size(buffer);
+    if (length > max_size) {
+        bson_buffer_free(buffer);
+        rb_raise(InvalidDocument,
+            "Document too large: This BSON document is limited to %d bytes.",
+            max_size);
     }
     SAFE_WRITE_AT_POS(buffer, length_location, (const char*)&length, 4);
 }
@@ -616,10 +634,10 @@ static VALUE method_serialize(VALUE self, VALUE doc, VALUE check_keys,
 
     VALUE result;
     bson_buffer_t buffer = bson_buffer_new();
-    bson_buffer_set_max_size(buffer, FIX2INT(max_size));
     if (buffer == NULL) {
         rb_raise(rb_eNoMemError, "failed to allocate memory in buffer.c");
     }
+    bson_buffer_set_max_size(buffer, FIX2INT(max_size));
 
     write_doc(buffer, doc, check_keys, move_id);
 

data/ext/cbson/encoding_helpers.c

@@ -1,102 +1,98 @@
-#include "encoding_helpers.h"
-
 /*
- * Portions Copyright 2001 Unicode, Inc.
+ * Copyright 2013 10gen Inc.
  *
- * Disclaimer
+ * 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
  *
- * 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.
+ *   http://www.apache.org/licenses/LICENSE-2.0
  *
- * 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.
+ * 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.
  */
 
-/*
- * 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
-};
 
-/* --------------------------------------------------------------------- */
+#include <string.h>
+#include "encoding_helpers.h"
 
-/*
- * 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;
+
+static void
+get_utf8_sequence (const char       *utf8,
+                   unsigned char    *seq_length,
+                   unsigned char    *first_mask)
+{
+   unsigned char c = *(const unsigned char *)utf8;
+   unsigned char m;
+   unsigned char n;
+
+   /*
+    * See the following[1] for a description of what the given multi-byte
+    * sequences will be based on the bits set of the first byte. We also need
+    * to mask the first byte based on that.  All subsequent bytes are masked
+    * against 0x3F.
+    *
+    * [1] http://www.joelonsoftware.com/articles/Unicode.html
+    */
+
+   if ((c & 0x80) == 0) {
+      n = 1;
+      m = 0x7F;
+   } else if ((c & 0xE0) == 0xC0) {
+      n = 2;
+      m = 0x1F;
+   } else if ((c & 0xF0) == 0xE0) {
+      n = 3;
+      m = 0x0F;
+   } else if ((c & 0xF8) == 0xF0) {
+      n = 4;
+      m = 0x07;
+   } else if ((c & 0xFC) == 0xF8) {
+      n = 5;
+      m = 0x03;
+   } else if ((c & 0xFE) == 0xFC) {
+      n = 6;
+      m = 0x01;
+   } else {
+      n = 0;
+      m = 0;
+   }
+
+   *seq_length = n;
+   *first_mask = m;
 }
 
-result_t check_string(const unsigned char* string, const long 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;
-    }
+result_t
+validate_utf8_encoding (const char  *utf8,
+                        size_t      utf8_len,
+                        int         allow_null)
+{
+   unsigned char first_mask;
+   unsigned char seq_length;
+   unsigned i;
+   unsigned j;
 
-    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;
+   for (i = 0; i < utf8_len; i += seq_length) {
+      get_utf8_sequence(&utf8[i], &seq_length, &first_mask);
+      if (!seq_length) {
+         return INVALID_UTF8;
+      }
+      for (j = i + 1; j < (i + seq_length); j++) {
+         if ((utf8[j] & 0xC0) != 0x80) {
+            return INVALID_UTF8;
+         }
+      }
+      if (!allow_null) {
+         for (j = 0; j < seq_length; j++) {
+            if (((i + j) > utf8_len) || !utf8[i + j]) {
+               return HAS_NULL;
             }
-        }
-        position += sequence_length;
-    }
+         }
+      }
+   }
 
-    return VALID;
+   return VALID_UTF8;
 }

data/ext/cbson/encoding_helpers.h

@@ -1,13 +1,50 @@
+/*
+ * Copyright 2013 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
 
+#include <unistd.h>
+
 typedef enum {
-    VALID,
-    NOT_UTF_8,
+    VALID_UTF8,
+    INVALID_UTF8,
     HAS_NULL
 } result_t;
 
-result_t check_string(const unsigned char* string, const long length,
-                      const char check_utf8, const char check_null);
+/**
+ * validate_utf8_encoding:
+ * @utf8: A UTF-8 encoded string.
+ * @utf8_len: The length of @utf8 in bytes.
+ * @allow_null: 1 If '\0' is allowed within @utf8, excluding trailing \0.
+ *
+ * Validates that @utf8 is a valid UTF-8 string.
+ *
+ * If @allow_null is 1, then '\0' is allowed within @utf8_len bytes of @utf8.
+ * Generally, this is bad practice since the main point of UTF-8 strings is
+ * that they can be used with strlen() and friends. However, some languages
+ * such as Python can send UTF-8 encoded strings with NUL's in them.
+ *
+ * Returns: enum indicating validity of @utf8.
+ */
+result_t
+validate_utf8_encoding (const char  *utf8,
+                        size_t      utf8_len,
+                        int         allow_null);
+
 
-#endif
+#endif /* ENCODING_HELPERS_H */

data/ext/cbson/version.h

@@ -1 +1,17 @@
-#define VERSION "1.8.6"
+/*
+ * Copyright (C) 2013 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 "1.9.0"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bson_ext
 version: !ruby/object:Gem::Version
-  version: 1.8.6
+  version: 1.9.0
 platform: ruby
 authors:
 - Tyler Brock
@@ -33,7 +33,7 @@ cert_chain:
   8v7zLF2XliYbfurYIwkcXs8yPn8ggApBIy9bX6VJxRs/l2+UvqzaHIFaFy/F8/GP
   RNTuXsVG5NDACo7Q
   -----END CERTIFICATE-----
-date: 2013-05-16 00:00:00.000000000 Z
+date: 2013-06-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bson
@@ -41,14 +41,14 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 1.8.6
+        version: 1.9.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 1.8.6
+        version: 1.9.0
 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