internal/strs: unify string manipulation functionality
Create a new internal/strs package that unifies common functionality:
* Since protobuf itself pseudo-specifies at least 4 different camel-case
and snake-case conversion functions, we define all variants in one place.
* We move the internal/filedesc.nameBuilder function to this package.
We simplify its implementation to not depend on a strings.Builder fork
under the hood since the semantics we desire is simpler than what
strings.Builder provides.
* We use strs.Builder in reflect/protodesc in its construction of all
the full names. This is perfect use case of strs.Builder since all
full names within a file descriptor share the same lifetime.
* Add an UnsafeString and UnsafeBytes cast function that will be useful
in the near future for optimizing encoding/prototext and encoding/protojson.
Change-Id: I2cf07cbaf6f72e5f9fd6ae3d37b0d46f6af2ad59
Reviewed-on: https://go-review.googlesource.com/c/protobuf/+/185198
Reviewed-by: Damien Neil <dneil@google.com>
diff --git a/internal/strs/strings.go b/internal/strs/strings.go
new file mode 100644
index 0000000..295bd29
--- /dev/null
+++ b/internal/strs/strings.go
@@ -0,0 +1,111 @@
+// Copyright 2019 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// Package strs provides string manipulation functionality specific to protobuf.
+package strs
+
+import (
+ "strings"
+ "unicode"
+)
+
+// JSONCamelCase converts a snake_case identifier to a camelCase identifier,
+// according to the protobuf JSON specification.
+func JSONCamelCase(s string) string {
+ var b []byte
+ var wasUnderscore bool
+ for i := 0; i < len(s); i++ { // proto identifiers are always ASCII
+ c := s[i]
+ if c != '_' {
+ isLower := 'a' <= c && c <= 'z'
+ if wasUnderscore && isLower {
+ c -= 'a' - 'A' // convert to uppercase
+ }
+ b = append(b, c)
+ }
+ wasUnderscore = c == '_'
+ }
+ return string(b)
+}
+
+// JSONSnakeCase converts a camelCase identifier to a snake_case identifier,
+// according to the protobuf JSON specification.
+func JSONSnakeCase(s string) string {
+ var b []byte
+ for i := 0; i < len(s); i++ { // proto identifiers are always ASCII
+ c := s[i]
+ isUpper := 'A' <= c && c <= 'Z'
+ if isUpper {
+ b = append(b, '_')
+ c += 'a' - 'A' // convert to lowercase
+ }
+ b = append(b, c)
+ }
+ return string(b)
+}
+
+// MapEntryName derives the name of the map entry message given the field name.
+// See protoc v3.8.0: src/google/protobuf/descriptor.cc:254-276,6057
+func MapEntryName(s string) string {
+ var b []byte
+ upperNext := true
+ for _, c := range s {
+ switch {
+ case c == '_':
+ upperNext = true
+ case upperNext:
+ b = append(b, byte(unicode.ToUpper(c)))
+ upperNext = false
+ default:
+ b = append(b, byte(c))
+ }
+ }
+ b = append(b, "Entry"...)
+ return string(b)
+}
+
+// EnumValueName derives the camel-cased enum value name.
+// See protoc v3.8.0: src/google/protobuf/descriptor.cc:297-313
+func EnumValueName(s string) string {
+ var b []byte
+ upperNext := true
+ for _, c := range s {
+ switch {
+ case c == '_':
+ upperNext = true
+ case upperNext:
+ b = append(b, byte(unicode.ToUpper(c)))
+ upperNext = false
+ default:
+ b = append(b, byte(unicode.ToLower(c)))
+ upperNext = false
+ }
+ }
+ return string(b)
+}
+
+// TrimEnumPrefix trims the enum name prefix from an enum value name,
+// where the prefix is all lowercase without underscores.
+// See protoc v3.8.0: src/google/protobuf/descriptor.cc:330-375
+func TrimEnumPrefix(s, prefix string) string {
+ s0 := s // original input
+ for len(s) > 0 && len(prefix) > 0 {
+ if s[0] == '_' {
+ s = s[1:]
+ continue
+ }
+ if unicode.ToLower(rune(s[0])) != rune(prefix[0]) {
+ return s0 // no prefix match
+ }
+ s, prefix = s[1:], prefix[1:]
+ }
+ if len(prefix) > 0 {
+ return s0 // no prefix match
+ }
+ s = strings.TrimLeft(s, "_")
+ if len(s) == 0 {
+ return s0 // avoid returning empty string
+ }
+ return s
+}