1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
|
// 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.
// Author: kenton@google.com (Kenton Varda)
// Based on original Protocol Buffers design by
// Sanjay Ghemawat, Jeff Dean, and others.
#include <algorithm>
#include <limits>
#include <vector>
#include <sstream>
#include <compiler/csharp/csharp_helpers.h>
#include <compiler/csharp/csharp_names.h>
#include <descriptor.pb.h>
#include <io/printer.h>
#include <wire_format.h>
#include <stubs/strutil.h>
#include <compiler/csharp/csharp_field_base.h>
#include <compiler/csharp/csharp_enum_field.h>
#include <compiler/csharp/csharp_map_field.h>
#include <compiler/csharp/csharp_message_field.h>
#include <compiler/csharp/csharp_options.h>
#include <compiler/csharp/csharp_primitive_field.h>
#include <compiler/csharp/csharp_repeated_enum_field.h>
#include <compiler/csharp/csharp_repeated_message_field.h>
#include <compiler/csharp/csharp_repeated_primitive_field.h>
#include <compiler/csharp/csharp_wrapper_field.h>
namespace google {
namespace protobuf {
namespace compiler {
namespace csharp {
CSharpType GetCSharpType(FieldDescriptor::Type type) {
switch (type) {
case FieldDescriptor::TYPE_INT32:
return CSHARPTYPE_INT32;
case FieldDescriptor::TYPE_INT64:
return CSHARPTYPE_INT64;
case FieldDescriptor::TYPE_UINT32:
return CSHARPTYPE_UINT32;
case FieldDescriptor::TYPE_UINT64:
return CSHARPTYPE_UINT32;
case FieldDescriptor::TYPE_SINT32:
return CSHARPTYPE_INT32;
case FieldDescriptor::TYPE_SINT64:
return CSHARPTYPE_INT64;
case FieldDescriptor::TYPE_FIXED32:
return CSHARPTYPE_UINT32;
case FieldDescriptor::TYPE_FIXED64:
return CSHARPTYPE_UINT64;
case FieldDescriptor::TYPE_SFIXED32:
return CSHARPTYPE_INT32;
case FieldDescriptor::TYPE_SFIXED64:
return CSHARPTYPE_INT64;
case FieldDescriptor::TYPE_FLOAT:
return CSHARPTYPE_FLOAT;
case FieldDescriptor::TYPE_DOUBLE:
return CSHARPTYPE_DOUBLE;
case FieldDescriptor::TYPE_BOOL:
return CSHARPTYPE_BOOL;
case FieldDescriptor::TYPE_ENUM:
return CSHARPTYPE_ENUM;
case FieldDescriptor::TYPE_STRING:
return CSHARPTYPE_STRING;
case FieldDescriptor::TYPE_BYTES:
return CSHARPTYPE_BYTESTRING;
case FieldDescriptor::TYPE_GROUP:
return CSHARPTYPE_MESSAGE;
case FieldDescriptor::TYPE_MESSAGE:
return CSHARPTYPE_MESSAGE;
// No default because we want the compiler to complain if any new
// types are added.
}
GOOGLE_LOG(FATAL)<< "Can't get here.";
return (CSharpType) -1;
}
std::string StripDotProto(const std::string& proto_file) {
int lastindex = proto_file.find_last_of(".");
return proto_file.substr(0, lastindex);
}
std::string GetFileNamespace(const FileDescriptor* descriptor) {
if (descriptor->options().has_csharp_namespace()) {
return descriptor->options().csharp_namespace();
}
return UnderscoresToCamelCase(descriptor->package(), true, true);
}
// Returns the Pascal-cased last part of the proto file. For example,
// input of "google/protobuf/foo_bar.proto" would result in "FooBar".
std::string GetFileNameBase(const FileDescriptor* descriptor) {
std::string proto_file = descriptor->name();
int lastslash = proto_file.find_last_of("/");
std::string base = proto_file.substr(lastslash + 1);
return UnderscoresToPascalCase(StripDotProto(base));
}
std::string GetReflectionClassUnqualifiedName(const FileDescriptor* descriptor) {
// TODO: Detect collisions with existing messages,
// and append an underscore if necessary.
return GetFileNameBase(descriptor) + "Reflection";
}
std::string GetExtensionClassUnqualifiedName(const FileDescriptor* descriptor) {
// TODO: Detect collisions with existing messages,
// and append an underscore if necessary.
return GetFileNameBase(descriptor) + "Extensions";
}
// TODO(jtattermusch): can we reuse a utility function?
std::string UnderscoresToCamelCase(const std::string& input,
bool cap_next_letter,
bool preserve_period) {
std::string result;
// Note: I distrust ctype.h due to locales.
for (int i = 0; i < input.size(); i++) {
if ('a' <= input[i] && input[i] <= 'z') {
if (cap_next_letter) {
result += input[i] + ('A' - 'a');
} else {
result += input[i];
}
cap_next_letter = false;
} else if ('A' <= input[i] && input[i] <= 'Z') {
if (i == 0 && !cap_next_letter) {
// Force first letter to lower-case unless explicitly told to
// capitalize it.
result += input[i] + ('a' - 'A');
} else {
// Capital letters after the first are left as-is.
result += input[i];
}
cap_next_letter = false;
} else if ('0' <= input[i] && input[i] <= '9') {
result += input[i];
cap_next_letter = true;
} else {
cap_next_letter = true;
if (input[i] == '.' && preserve_period) {
result += '.';
}
}
}
// Add a trailing "_" if the name should be altered.
if (input.size() > 0 && input[input.size() - 1] == '#') {
result += '_';
}
return result;
}
std::string UnderscoresToPascalCase(const std::string& input) {
return UnderscoresToCamelCase(input, true);
}
// Convert a string which is expected to be SHOUTY_CASE (but may not be *precisely* shouty)
// into a PascalCase string. Precise rules implemented:
// Previous input character Current character Case
// Any Non-alphanumeric Skipped
// None - first char of input Alphanumeric Upper
// Non-letter (e.g. _ or 1) Alphanumeric Upper
// Numeric Alphanumeric Upper
// Lower letter Alphanumeric Same as current
// Upper letter Alphanumeric Lower
std::string ShoutyToPascalCase(const std::string& input) {
std::string result;
// Simple way of implementing "always start with upper"
char previous = '_';
for (int i = 0; i < input.size(); i++) {
char current = input[i];
if (!ascii_isalnum(current)) {
previous = current;
continue;
}
if (!ascii_isalnum(previous)) {
result += ascii_toupper(current);
} else if (ascii_isdigit(previous)) {
result += ascii_toupper(current);
} else if (ascii_islower(previous)) {
result += current;
} else {
result += ascii_tolower(current);
}
previous = current;
}
return result;
}
// Attempt to remove a prefix from a value, ignoring casing and skipping underscores.
// (foo, foo_bar) => bar - underscore after prefix is skipped
// (FOO, foo_bar) => bar - casing is ignored
// (foo_bar, foobarbaz) => baz - underscore in prefix is ignored
// (foobar, foo_barbaz) => baz - underscore in value is ignored
// (foo, bar) => bar - prefix isn't matched; return original value
std::string TryRemovePrefix(const std::string& prefix, const std::string& value) {
// First normalize to a lower-case no-underscores prefix to match against
std::string prefix_to_match = "";
for (size_t i = 0; i < prefix.size(); i++) {
if (prefix[i] != '_') {
prefix_to_match += ascii_tolower(prefix[i]);
}
}
// This keeps track of how much of value we've consumed
size_t prefix_index, value_index;
for (prefix_index = 0, value_index = 0;
prefix_index < prefix_to_match.size() && value_index < value.size();
value_index++) {
// Skip over underscores in the value
if (value[value_index] == '_') {
continue;
}
if (ascii_tolower(value[value_index]) != prefix_to_match[prefix_index++]) {
// Failed to match the prefix - bail out early.
return value;
}
}
// If we didn't finish looking through the prefix, we can't strip it.
if (prefix_index < prefix_to_match.size()) {
return value;
}
// Step over any underscores after the prefix
while (value_index < value.size() && value[value_index] == '_') {
value_index++;
}
// If there's nothing left (e.g. it was a prefix with only underscores afterwards), don't strip.
if (value_index == value.size()) {
return value;
}
return value.substr(value_index);
}
// Format the enum value name in a pleasant way for C#:
// - Strip the enum name as a prefix if possible
// - Convert to PascalCase.
// For example, an enum called Color with a value of COLOR_BLUE should
// result in an enum value in C# called just Blue
std::string GetEnumValueName(const std::string& enum_name, const std::string& enum_value_name) {
std::string stripped = TryRemovePrefix(enum_name, enum_value_name);
std::string result = ShoutyToPascalCase(stripped);
// Just in case we have an enum name of FOO and a value of FOO_2... make sure the returned
// string is a valid identifier.
if (ascii_isdigit(result[0])) {
result = "_" + result;
}
return result;
}
uint GetGroupEndTag(const Descriptor* descriptor) {
const Descriptor* containing_type = descriptor->containing_type();
if (containing_type != NULL) {
const FieldDescriptor* field;
for (int i = 0; i < containing_type->field_count(); i++) {
field = containing_type->field(i);
if (field->type() == FieldDescriptor::Type::TYPE_GROUP &&
field->message_type() == descriptor) {
return internal::WireFormatLite::MakeTag(
field->number(), internal::WireFormatLite::WIRETYPE_END_GROUP);
}
}
for (int i = 0; i < containing_type->extension_count(); i++) {
field = containing_type->extension(i);
if (field->type() == FieldDescriptor::Type::TYPE_GROUP &&
field->message_type() == descriptor) {
return internal::WireFormatLite::MakeTag(
field->number(), internal::WireFormatLite::WIRETYPE_END_GROUP);
}
}
} else {
const FileDescriptor* containing_file = descriptor->file();
if (containing_file != NULL) {
const FieldDescriptor* field;
for (int i = 0; i < containing_file->extension_count(); i++) {
field = containing_file->extension(i);
if (field->type() == FieldDescriptor::Type::TYPE_GROUP &&
field->message_type() == descriptor) {
return internal::WireFormatLite::MakeTag(
field->number(), internal::WireFormatLite::WIRETYPE_END_GROUP);
}
}
}
}
return 0;
}
std::string ToCSharpName(const std::string& name, const FileDescriptor* file) {
std::string result = GetFileNamespace(file);
if (!result.empty()) {
result += '.';
}
std::string classname;
if (file->package().empty()) {
classname = name;
} else {
// Strip the proto package from full_name since we've replaced it with
// the C# namespace.
classname = name.substr(file->package().size() + 1);
}
result += StringReplace(classname, ".", ".Types.", true);
return "global::" + result;
}
std::string GetReflectionClassName(const FileDescriptor* descriptor) {
std::string result = GetFileNamespace(descriptor);
if (!result.empty()) {
result += '.';
}
result += GetReflectionClassUnqualifiedName(descriptor);
return "global::" + result;
}
std::string GetFullExtensionName(const FieldDescriptor* descriptor) {
if (descriptor->extension_scope()) {
return GetClassName(descriptor->extension_scope()) + ".Extensions." + GetPropertyName(descriptor);
}
else {
return GetExtensionClassUnqualifiedName(descriptor->file()) + "." + GetPropertyName(descriptor);
}
}
std::string GetClassName(const Descriptor* descriptor) {
return ToCSharpName(descriptor->full_name(), descriptor->file());
}
std::string GetClassName(const EnumDescriptor* descriptor) {
return ToCSharpName(descriptor->full_name(), descriptor->file());
}
// Groups are hacky: The name of the field is just the lower-cased name
// of the group type. In C#, though, we would like to retain the original
// capitalization of the type name.
std::string GetFieldName(const FieldDescriptor* descriptor) {
if (descriptor->type() == FieldDescriptor::TYPE_GROUP) {
return descriptor->message_type()->name();
} else {
return descriptor->name();
}
}
std::string GetFieldConstantName(const FieldDescriptor* field) {
return GetPropertyName(field) + "FieldNumber";
}
std::string GetPropertyName(const FieldDescriptor* descriptor) {
// TODO(jtattermusch): consider introducing csharp_property_name field option
std::string property_name = UnderscoresToPascalCase(GetFieldName(descriptor));
// Avoid either our own type name or reserved names. Note that not all names
// are reserved - a field called to_string, write_to etc would still cause a problem.
// There are various ways of ending up with naming collisions, but we try to avoid obvious
// ones.
if (property_name == descriptor->containing_type()->name()
|| property_name == "Types"
|| property_name == "Descriptor") {
property_name += "_";
}
return property_name;
}
std::string GetOutputFile(const FileDescriptor* descriptor,
const std::string file_extension,
const bool generate_directories,
const std::string base_namespace,
std::string* error) {
std::string relative_filename = GetFileNameBase(descriptor) + file_extension;
if (!generate_directories) {
return relative_filename;
}
std::string ns = GetFileNamespace(descriptor);
std::string namespace_suffix = ns;
if (!base_namespace.empty()) {
// Check that the base_namespace is either equal to or a leading part of
// the file namespace. This isn't just a simple prefix; "Foo.B" shouldn't
// be regarded as a prefix of "Foo.Bar". The simplest option is to add "."
// to both.
std::string extended_ns = ns + ".";
if (extended_ns.find(base_namespace + ".") != 0) {
*error = "Namespace " + ns + " is not a prefix namespace of base namespace " + base_namespace;
return ""; // This will be ignored, because we've set an error.
}
namespace_suffix = ns.substr(base_namespace.length());
if (namespace_suffix.find(".") == 0) {
namespace_suffix = namespace_suffix.substr(1);
}
}
std::string namespace_dir = StringReplace(namespace_suffix, ".", "/", true);
if (!namespace_dir.empty()) {
namespace_dir += "/";
}
return namespace_dir + relative_filename;
}
// TODO: c&p from Java protoc plugin
// For encodings with fixed sizes, returns that size in bytes. Otherwise
// returns -1.
int GetFixedSize(FieldDescriptor::Type type) {
switch (type) {
case FieldDescriptor::TYPE_INT32 : return -1;
case FieldDescriptor::TYPE_INT64 : return -1;
case FieldDescriptor::TYPE_UINT32 : return -1;
case FieldDescriptor::TYPE_UINT64 : return -1;
case FieldDescriptor::TYPE_SINT32 : return -1;
case FieldDescriptor::TYPE_SINT64 : return -1;
case FieldDescriptor::TYPE_FIXED32 : return internal::WireFormatLite::kFixed32Size;
case FieldDescriptor::TYPE_FIXED64 : return internal::WireFormatLite::kFixed64Size;
case FieldDescriptor::TYPE_SFIXED32: return internal::WireFormatLite::kSFixed32Size;
case FieldDescriptor::TYPE_SFIXED64: return internal::WireFormatLite::kSFixed64Size;
case FieldDescriptor::TYPE_FLOAT : return internal::WireFormatLite::kFloatSize;
case FieldDescriptor::TYPE_DOUBLE : return internal::WireFormatLite::kDoubleSize;
case FieldDescriptor::TYPE_BOOL : return internal::WireFormatLite::kBoolSize;
case FieldDescriptor::TYPE_ENUM : return -1;
case FieldDescriptor::TYPE_STRING : return -1;
case FieldDescriptor::TYPE_BYTES : return -1;
case FieldDescriptor::TYPE_GROUP : return -1;
case FieldDescriptor::TYPE_MESSAGE : return -1;
// No default because we want the compiler to complain if any new
// types are added.
}
GOOGLE_LOG(FATAL) << "Can't get here.";
return -1;
}
static const char base64_chars[] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
std::string StringToBase64(const std::string& input) {
std::string result;
size_t remaining = input.size();
const unsigned char *src = (const unsigned char*) input.c_str();
while (remaining > 2) {
result += base64_chars[src[0] >> 2];
result += base64_chars[((src[0] & 0x3) << 4) | (src[1] >> 4)];
result += base64_chars[((src[1] & 0xf) << 2) | (src[2] >> 6)];
result += base64_chars[src[2] & 0x3f];
remaining -= 3;
src += 3;
}
switch (remaining) {
case 2:
result += base64_chars[src[0] >> 2];
result += base64_chars[((src[0] & 0x3) << 4) | (src[1] >> 4)];
result += base64_chars[(src[1] & 0xf) << 2];
result += '=';
src += 2;
break;
case 1:
result += base64_chars[src[0] >> 2];
result += base64_chars[((src[0] & 0x3) << 4)];
result += '=';
result += '=';
src += 1;
break;
}
return result;
}
std::string FileDescriptorToBase64(const FileDescriptor* descriptor) {
std::string fdp_bytes;
FileDescriptorProto fdp;
descriptor->CopyTo(&fdp);
fdp.SerializeToString(&fdp_bytes);
return StringToBase64(fdp_bytes);
}
FieldGeneratorBase* CreateFieldGenerator(const FieldDescriptor* descriptor,
int presenceIndex,
const Options* options) {
switch (descriptor->type()) {
case FieldDescriptor::TYPE_GROUP:
case FieldDescriptor::TYPE_MESSAGE:
if (descriptor->is_repeated()) {
if (descriptor->is_map()) {
return new MapFieldGenerator(descriptor, presenceIndex, options);
} else {
return new RepeatedMessageFieldGenerator(descriptor, presenceIndex, options);
}
} else {
if (IsWrapperType(descriptor)) {
if (descriptor->real_containing_oneof()) {
return new WrapperOneofFieldGenerator(descriptor, presenceIndex, options);
} else {
return new WrapperFieldGenerator(descriptor, presenceIndex, options);
}
} else {
if (descriptor->real_containing_oneof()) {
return new MessageOneofFieldGenerator(descriptor, presenceIndex, options);
} else {
return new MessageFieldGenerator(descriptor, presenceIndex, options);
}
}
}
case FieldDescriptor::TYPE_ENUM:
if (descriptor->is_repeated()) {
return new RepeatedEnumFieldGenerator(descriptor, presenceIndex, options);
} else {
if (descriptor->real_containing_oneof()) {
return new EnumOneofFieldGenerator(descriptor, presenceIndex, options);
} else {
return new EnumFieldGenerator(descriptor, presenceIndex, options);
}
}
default:
if (descriptor->is_repeated()) {
return new RepeatedPrimitiveFieldGenerator(descriptor, presenceIndex, options);
} else {
if (descriptor->real_containing_oneof()) {
return new PrimitiveOneofFieldGenerator(descriptor, presenceIndex, options);
} else {
return new PrimitiveFieldGenerator(descriptor, presenceIndex, options);
}
}
}
}
bool IsNullable(const FieldDescriptor* descriptor) {
if (descriptor->is_repeated()) {
return true;
}
switch (descriptor->type()) {
case FieldDescriptor::TYPE_ENUM:
case FieldDescriptor::TYPE_DOUBLE:
case FieldDescriptor::TYPE_FLOAT:
case FieldDescriptor::TYPE_INT64:
case FieldDescriptor::TYPE_UINT64:
case FieldDescriptor::TYPE_INT32:
case FieldDescriptor::TYPE_FIXED64:
case FieldDescriptor::TYPE_FIXED32:
case FieldDescriptor::TYPE_BOOL:
case FieldDescriptor::TYPE_UINT32:
case FieldDescriptor::TYPE_SFIXED32:
case FieldDescriptor::TYPE_SFIXED64:
case FieldDescriptor::TYPE_SINT32:
case FieldDescriptor::TYPE_SINT64:
return false;
case FieldDescriptor::TYPE_MESSAGE:
case FieldDescriptor::TYPE_GROUP:
case FieldDescriptor::TYPE_STRING:
case FieldDescriptor::TYPE_BYTES:
return true;
default:
GOOGLE_LOG(FATAL) << "Unknown field type.";
return true;
}
}
} // namespace csharp
} // namespace compiler
} // namespace protobuf
} // namespace google
|