1 // Copyright (C) 2017 The Android Open Source Project 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 syntax = "proto2"; 16 option optimize_for = LITE_RUNTIME; 17 18 package libtextclassifier; 19 20 // Represents a codepoint range [start, end) with its role for tokenization. 21 message TokenizationCodepointRange { 22 optional int32 start = 1; 23 optional int32 end = 2; 24 25 // Role of the codepoints in the range. 26 enum Role { 27 // Concatenates the codepoint to the current run of codepoints. 28 DEFAULT_ROLE = 0; 29 30 // Splits a run of codepoints before the current codepoint. 31 SPLIT_BEFORE = 0x1; 32 33 // Splits a run of codepoints after the current codepoint. 34 SPLIT_AFTER = 0x2; 35 36 // Discards the codepoint. 37 DISCARD_CODEPOINT = 0x4; 38 39 // Common values: 40 // Splits on the characters and discards them. Good e.g. for the space 41 // character. 42 WHITESPACE_SEPARATOR = 0x7; 43 // Each codepoint will be a separate token. Good e.g. for Chinese 44 // characters. 45 TOKEN_SEPARATOR = 0x3; 46 } 47 optional Role role = 3; 48 } 49