Fixes extra whitespace on generated comments. (#1950)

Fixes extra whitespace on generated comments.

objectivec/GPBExtensionRegistry.h

@@ -77,7 +77,7 @@ NS_ASSUME_NONNULL_BEGIN
  * @param descriptor  The descriptor to look for a registered extension on.
  * @param fieldNumber The field number of the extension to look for.
  *
- * @return The registered  GPBExtensionDescripto or nil if none was found.
+ * @return The registered GPBExtensionDescriptor or nil if none was found.
  **/
 - (nullable GPBExtensionDescriptor *)extensionForDescriptor:(GPBDescriptor *)descriptor
                                                 fieldNumber:(NSInteger)fieldNumber;

objectivec/google/protobuf/Any.pbobjc.h

@@ -51,12 +51,12 @@ typedef GPB_ENUM(GPBAny_FieldNumber) {
 /**
  * `Any` contains an arbitrary serialized protocol buffer message along with a
  * URL that describes the type of the serialized message.
- * 
+ *
  * Protobuf library provides support to pack/unpack Any values in the form
  * of utility functions or additional generated methods of the Any type.
- * 
+ *
  * Example 1: Pack and unpack a message in C++.
- * 
+ *
  *     Foo foo = ...;
  *     Any any;
  *     any.PackFrom(foo);
@@ -64,18 +64,18 @@ typedef GPB_ENUM(GPBAny_FieldNumber) {
  *     if (any.UnpackTo(&foo)) {
  *       ...
  *     }
- * 
+ *
  * Example 2: Pack and unpack a message in Java.
- * 
+ *
  *     Foo foo = ...;
  *     Any any = Any.pack(foo);
  *     ...
  *     if (any.is(Foo.class)) {
  *       foo = any.unpack(Foo.class);
  *     }
- * 
+ *
  *  Example 3: Pack and unpack a message in Python.
- * 
+ *
  *     foo = Foo(...)
  *     any = Any()
  *     any.Pack(foo)
@@ -83,37 +83,37 @@ typedef GPB_ENUM(GPBAny_FieldNumber) {
  *     if any.Is(Foo.DESCRIPTOR):
  *       any.Unpack(foo)
  *       ...
- * 
+ *
  * The pack methods provided by protobuf library will by default use
  * 'type.googleapis.com/full.type.name' as the type URL and the unpack
  * methods only use the fully qualified type name after the last '/'
  * in the type URL, for example "foo.bar.com/x/y.z" will yield type
  * name "y.z".
- * 
- * 
+ *
+ *
  * JSON
  * ====
  * The JSON representation of an `Any` value uses the regular
  * representation of the deserialized, embedded message, with an
  * additional field `\@type` which contains the type URL. Example:
- * 
+ *
  *     package google.profile;
  *     message Person {
  *       string first_name = 1;
  *       string last_name = 2;
  *     }
- * 
+ *
  *     {
  *       "\@type": "type.googleapis.com/google.profile.Person",
  *       "firstName": <string>,
  *       "lastName": <string>
  *     }
- * 
+ *
  * If the embedded message type is well-known and has a custom JSON
  * representation, that representation will be embedded adding a field
  * `value` which holds the custom JSON in addition to the `\@type`
  * field. Example (for message [google.protobuf.Duration][]):
- * 
+ *
  *     {
  *       "\@type": "type.googleapis.com/google.protobuf.Duration",
  *       "value": "1.212s"
@@ -124,10 +124,10 @@ typedef GPB_ENUM(GPBAny_FieldNumber) {
 /**
  * A URL/resource name whose content describes the type of the
  * serialized protocol buffer message.
- * 
+ *
  * For URLs which use the scheme `http`, `https`, or no scheme, the
  * following restrictions and interpretations apply:
- * 
+ *
  * * If no scheme is provided, `https` is assumed.
  * * The last segment of the URL's path must represent the fully
  *   qualified name of the type (as in `path/google.protobuf.Duration`).
@@ -140,7 +140,7 @@ typedef GPB_ENUM(GPBAny_FieldNumber) {
  *   lookup. Therefore, binary compatibility needs to be preserved
  *   on changes to types. (Use versioned type names to manage
  *   breaking changes.)
- * 
+ *
  * Schemes other than `http`, `https` (or the empty scheme) might be
  * used with implementation specific semantics.
  **/

objectivec/google/protobuf/Api.pbobjc.h

@@ -88,14 +88,14 @@ typedef GPB_ENUM(GPBApi_FieldNumber) {
  * outlined below. If the field is not empty, the version in the
  * package name will be verified to be consistent with what is
  * provided here.
- * 
+ *
  * The versioning schema uses [semantic
  * versioning](http://semver.org) where the major version number
  * indicates a breaking change and the minor version an additive,
  * non-breaking change. Both version numbers are signals to users
  * what to expect from different versions, and should be carefully
  * chosen based on the product plan.
- * 
+ *
  * The major version is also reflected in the package name of the
  * API, which must end in `v<major-version>`, as in
  * `google.feature.v1`. For major versions 0 and 1, the suffix can
@@ -199,21 +199,21 @@ typedef GPB_ENUM(GPBMixin_FieldNumber) {
  * Declares an API to be included in this API. The including API must
  * redeclare all the methods from the included API, but documentation
  * and options are inherited as follows:
- * 
+ *
  * - If after comment and whitespace stripping, the documentation
  *   string of the redeclared method is empty, it will be inherited
  *   from the original method.
- * 
+ *
  * - Each annotation belonging to the service config (http,
  *   visibility) which is not set in the redeclared method will be
  *   inherited.
- * 
+ *
  * - If an http annotation is inherited, the path pattern will be
  *   modified as follows. Any version prefix will be replaced by the
  *   version of the including API plus the [root][] path if specified.
- * 
+ *
  * Example of a simple mixin:
- * 
+ *
  *     package google.acl.v1;
  *     service AccessControl {
  *       // Get the underlying ACL object.
@@ -221,30 +221,30 @@ typedef GPB_ENUM(GPBMixin_FieldNumber) {
  *         option (google.api.http).get = "/v1/{resource=**}:getAcl";
  *       }
  *     }
- * 
+ *
  *     package google.storage.v2;
  *     service Storage {
  *       rpc GetAcl(GetAclRequest) returns (Acl);
- * 
+ *
  *       // Get a data record.
  *       rpc GetData(GetDataRequest) returns (Data) {
  *         option (google.api.http).get = "/v2/{resource=**}";
  *       }
  *     }
- * 
+ *
  * Example of a mixin configuration:
- * 
+ *
  *     apis:
  *     - name: google.storage.v2.Storage
  *       mixins:
  *       - name: google.acl.v1.AccessControl
- * 
+ *
  * The mixin construct implies that all methods in `AccessControl` are
  * also declared with same name and request/response types in
  * `Storage`. A documentation generator or annotation processor will
  * see the effective `Storage.GetAcl` method after inherting
  * documentation and annotations as follows:
- * 
+ *
  *     service Storage {
  *       // Get the underlying ACL object.
  *       rpc GetAcl(GetAclRequest) returns (Acl) {
@@ -252,20 +252,20 @@ typedef GPB_ENUM(GPBMixin_FieldNumber) {
  *       }
  *       ...
  *     }
- * 
+ *
  * Note how the version in the path pattern changed from `v1` to `v2`.
- * 
+ *
  * If the `root` field in the mixin is specified, it should be a
  * relative path under which inherited HTTP paths are placed. Example:
- * 
+ *
  *     apis:
  *     - name: google.storage.v2.Storage
  *       mixins:
  *       - name: google.acl.v1.AccessControl
  *         root: acls
- * 
+ *
  * This implies the following inherited HTTP annotation:
- * 
+ *
  *     service Storage {
  *       // Get the underlying ACL object.
  *       rpc GetAcl(GetAclRequest) returns (Acl) {

objectivec/google/protobuf/Duration.pbobjc.h

@@ -55,16 +55,16 @@ typedef GPB_ENUM(GPBDuration_FieldNumber) {
  * or "month". It is related to Timestamp in that the difference between
  * two Timestamp values is a Duration and it can be added or subtracted
  * from a Timestamp. Range is approximately +-10,000 years.
- * 
+ *
  * Example 1: Compute Duration from two Timestamps in pseudo code.
- * 
+ *
  *     Timestamp start = ...;
  *     Timestamp end = ...;
  *     Duration duration = ...;
- * 
+ *
  *     duration.seconds = end.seconds - start.seconds;
  *     duration.nanos = end.nanos - start.nanos;
- * 
+ *
  *     if (duration.seconds < 0 && duration.nanos > 0) {
  *       duration.seconds += 1;
  *       duration.nanos -= 1000000000;
@@ -72,16 +72,16 @@ typedef GPB_ENUM(GPBDuration_FieldNumber) {
  *       duration.seconds -= 1;
  *       duration.nanos += 1000000000;
  *     }
- * 
+ *
  * Example 2: Compute Timestamp from Timestamp + Duration in pseudo code.
- * 
+ *
  *     Timestamp start = ...;
  *     Duration duration = ...;
  *     Timestamp end = ...;
- * 
+ *
  *     end.seconds = start.seconds + duration.seconds;
  *     end.nanos = start.nanos + duration.nanos;
- * 
+ *
  *     if (end.nanos < 0) {
  *       end.seconds -= 1;
  *       end.nanos += 1000000000;

objectivec/google/protobuf/Empty.pbobjc.h

@@ -47,11 +47,11 @@ NS_ASSUME_NONNULL_BEGIN
  * A generic empty message that you can re-use to avoid defining duplicated
  * empty messages in your APIs. A typical example is to use it as the request
  * or the response type of an API method. For instance:
- * 
+ *
  *     service Foo {
  *       rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);
  *     }
- * 
+ *
  * The JSON representation for `Empty` is empty JSON object `{}`.
  **/
 @interface GPBEmpty : GPBMessage

objectivec/google/protobuf/FieldMask.pbobjc.h

@@ -49,25 +49,25 @@ typedef GPB_ENUM(GPBFieldMask_FieldNumber) {
 
 /**
  * `FieldMask` represents a set of symbolic field paths, for example:
- * 
+ *
  *     paths: "f.a"
  *     paths: "f.b.d"
- * 
+ *
  * Here `f` represents a field in some root message, `a` and `b`
  * fields in the message found in `f`, and `d` a field found in the
  * message in `f.b`.
- * 
+ *
  * Field masks are used to specify a subset of fields that should be
  * returned by a get operation or modified by an update operation.
  * Field masks also have a custom JSON encoding (see below).
- * 
+ *
  * # Field Masks in Projections
- * 
+ *
  * When used in the context of a projection, a response message or
  * sub-message is filtered by the API to only contain those fields as
  * specified in the mask. For example, if the mask in the previous
  * example is applied to a response message as follows:
- * 
+ *
  *     f {
  *       a : 22
  *       b {
@@ -77,26 +77,26 @@ typedef GPB_ENUM(GPBFieldMask_FieldNumber) {
  *       y : 13
  *     }
  *     z: 8
- * 
+ *
  * The result will not contain specific values for fields x,y and z
  * (their value will be set to the default, and omitted in proto text
  * output):
- * 
- * 
+ *
+ *
  *     f {
  *       a : 22
  *       b {
  *         d : 1
  *       }
  *     }
- * 
+ *
  * A repeated field is not allowed except at the last position of a
  * field mask.
- * 
+ *
  * If a FieldMask object is not present in a get operation, the
  * operation applies to all fields (as if a FieldMask of all fields
  * had been specified).
- * 
+ *
  * Note that a field mask does not necessarily apply to the
  * top-level response message. In case of a REST get operation, the
  * field mask applies directly to the response, but in case of a REST
@@ -106,25 +106,25 @@ typedef GPB_ENUM(GPBFieldMask_FieldNumber) {
  * clearly documented together with its declaration in the API.  In
  * any case, the effect on the returned resource/resources is required
  * behavior for APIs.
- * 
+ *
  * # Field Masks in Update Operations
- * 
+ *
  * A field mask in update operations specifies which fields of the
  * targeted resource are going to be updated. The API is required
  * to only change the values of the fields as specified in the mask
  * and leave the others untouched. If a resource is passed in to
  * describe the updated values, the API ignores the values of all
  * fields not covered by the mask.
- * 
+ *
  * If a repeated field is specified for an update operation, the existing
  * repeated values in the target resource will be overwritten by the new values.
  * Note that a repeated field is only allowed in the last position of a field
  * mask.
- * 
+ *
  * If a sub-message is specified in the last position of the field mask for an
  * update operation, then the existing sub-message in the target resource is
  * overwritten. Given the target message:
- * 
+ *
  *     f {
  *       b {
  *         d : 1
@@ -132,34 +132,34 @@ typedef GPB_ENUM(GPBFieldMask_FieldNumber) {
  *       }
  *       c : 1
  *     }
- * 
+ *
  * And an update message:
- * 
+ *
  *     f {
  *       b {
  *         d : 10
  *       }
  *     }
- * 
+ *
  * then if the field mask is:
- * 
+ *
  *  paths: "f.b"
- * 
+ *
  * then the result will be:
- * 
+ *
  *     f {
  *       b {
  *         d : 10
  *       }
  *       c : 1
  *     }
- * 
+ *
  * However, if the update mask was:
- * 
+ *
  *  paths: "f.b.d"
- * 
+ *
  * then the result would be:
- * 
+ *
  *     f {
  *       b {
  *         d : 10
@@ -167,13 +167,13 @@ typedef GPB_ENUM(GPBFieldMask_FieldNumber) {
  *       }
  *       c : 1
  *     }
- * 
+ *
  * In order to reset a field's value to the default, the field must
  * be in the mask and set to the default value in the provided resource.
  * Hence, in order to reset all fields of a resource, provide a default
  * instance of the resource and set all fields in the mask, or do
  * not provide a mask as described below.
- * 
+ *
  * If a field mask is not present on update, the operation applies to
  * all fields (as if a field mask of all fields has been specified).
  * Note that in the presence of schema evolution, this may mean that
@@ -181,26 +181,26 @@ typedef GPB_ENUM(GPBFieldMask_FieldNumber) {
  * the request will be reset to their default. If this is unwanted
  * behavior, a specific service may require a client to always specify
  * a field mask, producing an error if not.
- * 
+ *
  * As with get operations, the location of the resource which
  * describes the updated values in the request message depends on the
  * operation kind. In any case, the effect of the field mask is
  * required to be honored by the API.
- * 
+ *
  * ## Considerations for HTTP REST
- * 
+ *
  * The HTTP kind of an update operation which uses a field mask must
  * be set to PATCH instead of PUT in order to satisfy HTTP semantics
  * (PUT must only be used for full updates).
- * 
+ *
  * # JSON Encoding of Field Masks
- * 
+ *
  * In JSON, a field mask is encoded as a single string where paths are
  * separated by a comma. Fields name in each path are converted
  * to/from lower-camel naming conventions.
- * 
+ *
  * As an example, consider the following message declarations:
- * 
+ *
  *     message Profile {
  *       User user = 1;
  *       Photo photo = 2;
@@ -209,44 +209,44 @@ typedef GPB_ENUM(GPBFieldMask_FieldNumber) {
  *       string display_name = 1;
  *       string address = 2;
  *     }
- * 
+ *
  * In proto a field mask for `Profile` may look as such:
- * 
+ *
  *     mask {
  *       paths: "user.display_name"
  *       paths: "photo"
  *     }
- * 
+ *
  * In JSON, the same mask is represented as below:
- * 
+ *
  *     {
  *       mask: "user.displayName,photo"
  *     }
- * 
+ *
  * # Field Masks and Oneof Fields
- * 
+ *
  * Field masks treat fields in oneofs just as regular fields. Consider the
  * following message:
- * 
+ *
  *     message SampleMessage {
  *       oneof test_oneof {
  *         string name = 4;
  *         SubMessage sub_message = 9;
  *       }
  *     }
- * 
+ *
  * The field mask can be:
- * 
+ *
  *     mask {
  *       paths: "name"
  *     }
- * 
+ *
  * Or:
- * 
+ *
  *     mask {
  *       paths: "sub_message"
  *     }
- * 
+ *
  * Note that oneof type names ("test_oneof" in this case) cannot be used in
  * paths.
  **/

objectivec/google/protobuf/Struct.pbobjc.h

@@ -35,7 +35,7 @@ NS_ASSUME_NONNULL_BEGIN
 /**
  * `NullValue` is a singleton enumeration to represent the null value for the
  * `Value` type union.
- * 
+ *
  *  The JSON representation for `NullValue` is JSON `null`.
  **/
 typedef GPB_ENUM(GPBNullValue) {
@@ -85,7 +85,7 @@ typedef GPB_ENUM(GPBStruct_FieldNumber) {
  * scripting languages like JS a struct is represented as an
  * object. The details of that representation are described together
  * with the proto support for the language.
- * 
+ *
  * The JSON representation for `Struct` is JSON object.
  **/
 @interface GPBStruct : GPBMessage
@@ -123,7 +123,7 @@ typedef GPB_ENUM(GPBValue_Kind_OneOfCase) {
  * null, a number, a string, a boolean, a recursive struct value, or a
  * list of values. A producer of value is expected to set one of that
  * variants, absence of any variant indicates an error.
- * 
+ *
  * The JSON representation for `Value` is JSON value.
  **/
 @interface GPBValue : GPBMessage
@@ -176,7 +176,7 @@ typedef GPB_ENUM(GPBListValue_FieldNumber) {
 
 /**
  * `ListValue` is a wrapper around a repeated field of values.
- * 
+ *
  * The JSON representation for `ListValue` is JSON array.
  **/
 @interface GPBListValue : GPBMessage

objectivec/google/protobuf/Timestamp.pbobjc.h

@@ -60,44 +60,44 @@ typedef GPB_ENUM(GPBTimestamp_FieldNumber) {
  * By restricting to that range, we ensure that we can convert to
  * and from  RFC 3339 date strings.
  * See [https://www.ietf.org/rfc/rfc3339.txt](https://www.ietf.org/rfc/rfc3339.txt).
- * 
+ *
  * Example 1: Compute Timestamp from POSIX `time()`.
- * 
+ *
  *     Timestamp timestamp;
  *     timestamp.set_seconds(time(NULL));
  *     timestamp.set_nanos(0);
- * 
+ *
  * Example 2: Compute Timestamp from POSIX `gettimeofday()`.
- * 
+ *
  *     struct timeval tv;
  *     gettimeofday(&tv, NULL);
- * 
+ *
  *     Timestamp timestamp;
  *     timestamp.set_seconds(tv.tv_sec);
  *     timestamp.set_nanos(tv.tv_usec * 1000);
- * 
+ *
  * Example 3: Compute Timestamp from Win32 `GetSystemTimeAsFileTime()`.
- * 
+ *
  *     FILETIME ft;
  *     GetSystemTimeAsFileTime(&ft);
  *     UINT64 ticks = (((UINT64)ft.dwHighDateTime) << 32) | ft.dwLowDateTime;
- * 
+ *
  *     // A Windows tick is 100 nanoseconds. Windows epoch 1601-01-01T00:00:00Z
  *     // is 11644473600 seconds before Unix epoch 1970-01-01T00:00:00Z.
  *     Timestamp timestamp;
  *     timestamp.set_seconds((INT64) ((ticks / 10000000) - 11644473600LL));
  *     timestamp.set_nanos((INT32) ((ticks % 10000000) * 100));
- * 
+ *
  * Example 4: Compute Timestamp from Java `System.currentTimeMillis()`.
- * 
+ *
  *     long millis = System.currentTimeMillis();
- * 
+ *
  *     Timestamp timestamp = Timestamp.newBuilder().setSeconds(millis / 1000)
  *         .setNanos((int) ((millis % 1000) * 1000000)).build();
- * 
- * 
+ *
+ *
  * Example 5: Compute Timestamp from current time in Python.
- * 
+ *
  *     now = time.time()
  *     seconds = int(now)
  *     nanos = int((now - seconds) * 10**9)

objectivec/google/protobuf/Wrappers.pbobjc.h

@@ -49,7 +49,7 @@ typedef GPB_ENUM(GPBDoubleValue_FieldNumber) {
 
 /**
  * Wrapper message for `double`.
- * 
+ *
  * The JSON representation for `DoubleValue` is JSON number.
  **/
 @interface GPBDoubleValue : GPBMessage
@@ -67,7 +67,7 @@ typedef GPB_ENUM(GPBFloatValue_FieldNumber) {
 
 /**
  * Wrapper message for `float`.
- * 
+ *
  * The JSON representation for `FloatValue` is JSON number.
  **/
 @interface GPBFloatValue : GPBMessage
@@ -85,7 +85,7 @@ typedef GPB_ENUM(GPBInt64Value_FieldNumber) {
 
 /**
  * Wrapper message for `int64`.
- * 
+ *
  * The JSON representation for `Int64Value` is JSON string.
  **/
 @interface GPBInt64Value : GPBMessage
@@ -103,7 +103,7 @@ typedef GPB_ENUM(GPBUInt64Value_FieldNumber) {
 
 /**
  * Wrapper message for `uint64`.
- * 
+ *
  * The JSON representation for `UInt64Value` is JSON string.
  **/
 @interface GPBUInt64Value : GPBMessage
@@ -121,7 +121,7 @@ typedef GPB_ENUM(GPBInt32Value_FieldNumber) {
 
 /**
  * Wrapper message for `int32`.
- * 
+ *
  * The JSON representation for `Int32Value` is JSON number.
  **/
 @interface GPBInt32Value : GPBMessage
@@ -139,7 +139,7 @@ typedef GPB_ENUM(GPBUInt32Value_FieldNumber) {
 
 /**
  * Wrapper message for `uint32`.
- * 
+ *
  * The JSON representation for `UInt32Value` is JSON number.
  **/
 @interface GPBUInt32Value : GPBMessage
@@ -157,7 +157,7 @@ typedef GPB_ENUM(GPBBoolValue_FieldNumber) {
 
 /**
  * Wrapper message for `bool`.
- * 
+ *
  * The JSON representation for `BoolValue` is JSON `true` and `false`.
  **/
 @interface GPBBoolValue : GPBMessage
@@ -175,7 +175,7 @@ typedef GPB_ENUM(GPBStringValue_FieldNumber) {
 
 /**
  * Wrapper message for `string`.
- * 
+ *
  * The JSON representation for `StringValue` is JSON string.
  **/
 @interface GPBStringValue : GPBMessage
@@ -193,7 +193,7 @@ typedef GPB_ENUM(GPBBytesValue_FieldNumber) {
 
 /**
  * Wrapper message for `bytes`.
- * 
+ *
  * The JSON representation for `BytesValue` is JSON string.
  **/
 @interface GPBBytesValue : GPBMessage

src/google/protobuf/compiler/objectivec/objectivec_helpers.cc

@@ -850,14 +850,17 @@ string BuildCommentsString(const SourceLocation& location,
   string final_comments;
   string epilogue;
 
+  bool add_leading_space = false;
+
   if (prefer_single_line && lines.size() == 1) {
     prefix = "/** ";
     suffix = " */\n";
   } else {
-    prefix = " * ";
+    prefix = "* ";
     suffix = "\n";
     final_comments += "/**\n";
     epilogue = " **/\n";
+    add_leading_space = true;
   }
 
   for (int i = 0; i < lines.size(); i++) {
@@ -868,7 +871,12 @@ string BuildCommentsString(const SourceLocation& location,
     // Decouple / from * to not have inline comments inside comments.
     line = StringReplace(line, "/*", "/\\*", true);
     line = StringReplace(line, "*/", "*\\/", true);
-    final_comments += prefix + line + suffix;
+    line = prefix + line;
+    StripWhitespace(&line);
+    // If not a one line, need to add the first space before *, as
+    // StripWhitespace would have removed it.
+    line = (add_leading_space ? " " : "") + line;
+    final_comments += line + suffix;
   }
   final_comments += epilogue;
   return final_comments;