Girish Kumar | e48ec8a | 2020-08-18 12:28:51 +0000 | [diff] [blame] | 1 | // Copyright (c) 2017 Uber Technologies, Inc. |
| 2 | // |
| 3 | // Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | // you may not use this file except in compliance with the License. |
| 5 | // You may obtain a copy of the License at |
| 6 | // |
| 7 | // http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | // |
| 9 | // Unless required by applicable law or agreed to in writing, software |
| 10 | // distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | // See the License for the specific language governing permissions and |
| 13 | // limitations under the License. |
| 14 | |
| 15 | package rpcmetrics |
| 16 | |
| 17 | // NameNormalizer is used to convert the endpoint names to strings |
| 18 | // that can be safely used as tags in the metrics. |
| 19 | type NameNormalizer interface { |
| 20 | Normalize(name string) string |
| 21 | } |
| 22 | |
| 23 | // DefaultNameNormalizer converts endpoint names so that they contain only characters |
| 24 | // from the safe charset [a-zA-Z0-9-./_]. All other characters are replaced with '-'. |
| 25 | var DefaultNameNormalizer = &SimpleNameNormalizer{ |
| 26 | SafeSets: []SafeCharacterSet{ |
| 27 | &Range{From: 'a', To: 'z'}, |
| 28 | &Range{From: 'A', To: 'Z'}, |
| 29 | &Range{From: '0', To: '9'}, |
| 30 | &Char{'-'}, |
| 31 | &Char{'_'}, |
| 32 | &Char{'/'}, |
| 33 | &Char{'.'}, |
| 34 | }, |
| 35 | Replacement: '-', |
| 36 | } |
| 37 | |
| 38 | // SimpleNameNormalizer uses a set of safe character sets. |
| 39 | type SimpleNameNormalizer struct { |
| 40 | SafeSets []SafeCharacterSet |
| 41 | Replacement byte |
| 42 | } |
| 43 | |
| 44 | // SafeCharacterSet determines if the given character is "safe" |
| 45 | type SafeCharacterSet interface { |
| 46 | IsSafe(c byte) bool |
| 47 | } |
| 48 | |
| 49 | // Range implements SafeCharacterSet |
| 50 | type Range struct { |
| 51 | From, To byte |
| 52 | } |
| 53 | |
| 54 | // IsSafe implements SafeCharacterSet |
| 55 | func (r *Range) IsSafe(c byte) bool { |
| 56 | return c >= r.From && c <= r.To |
| 57 | } |
| 58 | |
| 59 | // Char implements SafeCharacterSet |
| 60 | type Char struct { |
| 61 | Val byte |
| 62 | } |
| 63 | |
| 64 | // IsSafe implements SafeCharacterSet |
| 65 | func (ch *Char) IsSafe(c byte) bool { |
| 66 | return c == ch.Val |
| 67 | } |
| 68 | |
| 69 | // Normalize checks each character in the string against SafeSets, |
| 70 | // and if it's not safe substitutes it with Replacement. |
| 71 | func (n *SimpleNameNormalizer) Normalize(name string) string { |
| 72 | var retMe []byte |
| 73 | nameBytes := []byte(name) |
| 74 | for i, b := range nameBytes { |
| 75 | if n.safeByte(b) { |
| 76 | if retMe != nil { |
| 77 | retMe[i] = b |
| 78 | } |
| 79 | } else { |
| 80 | if retMe == nil { |
| 81 | retMe = make([]byte, len(nameBytes)) |
| 82 | copy(retMe[0:i], nameBytes[0:i]) |
| 83 | } |
| 84 | retMe[i] = n.Replacement |
| 85 | } |
| 86 | } |
| 87 | if retMe == nil { |
| 88 | return name |
| 89 | } |
| 90 | return string(retMe) |
| 91 | } |
| 92 | |
| 93 | // safeByte checks if b against all safe charsets. |
| 94 | func (n *SimpleNameNormalizer) safeByte(b byte) bool { |
| 95 | for i := range n.SafeSets { |
| 96 | if n.SafeSets[i].IsSafe(b) { |
| 97 | return true |
| 98 | } |
| 99 | } |
| 100 | return false |
| 101 | } |