Home | History | Annotate | Download | only in lexer
      1 /*
      2  * Copyright (C) 2017 The Android Open Source Project
      3  *
      4  * Licensed under the Apache License, Version 2.0 (the "License");
      5  * you may not use this file except in compliance with the License.
      6  * You may obtain a copy of the License at
      7  *
      8  *      http://www.apache.org/licenses/LICENSE-2.0
      9  *
     10  * Unless required by applicable law or agreed to in writing, software
     11  * distributed under the License is distributed on an "AS IS" BASIS,
     12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     13  * See the License for the specific language governing permissions and
     14  * limitations under the License.
     15  */
     16 
     17 package lexer
     18 
     19 import java.util.*
     20 
     21 object DocLexer : ILexer {
     22 
     23     /**
     24      * @param str The string should already be padded from the file lexer.
     25      */
     26     override fun tokenize(str: String): List<Token> {
     27         val tokens = mutableListOf<Token>()
     28         var token: String
     29 
     30         //remove docblock comment indention - must go before others
     31         val formattedStr = str.lines()
     32                 //remove docblock comment indent prefix (must go before others) ...
     33                 .map { it.replace(Regex("^\\s*\\*[^/]"), "") } //indented prefix except doc_end
     34                 .map { it.replace(Regex("^\\s*\\*$"), "") }    //prefix empty lines remain
     35                 //replace empty lines with something the scanner can pick out ...
     36                 .map { it.replace(Regex("$\\s*^"), TokenGrammar.EMPTY_LINE.value) }
     37                 .joinToString("\n")
     38 
     39         Scanner(formattedStr).use { scanner ->
     40             while (scanner.hasNext()) {
     41                 token = scanner.next()
     42 
     43                 when (token) {
     44                     TokenGrammar.EMPTY_LINE.value -> tokens.add(TokenGrammar.newToken("", TokenGrammar.EMPTY_LINE))
     45 
     46                     //if part of annotation, add following tag as well
     47                     TokenGrammar.AT.value -> {
     48                         tokens.add(TokenGrammar.newToken(token)) //'@'
     49                         //determine if part of annotation
     50                         for (annotation in TokenGrammar.docAnnotations()) {
     51                             if (scanner.hasNext(annotation.value)) {
     52                                 tokens.add(TokenGrammar.newToken(scanner.next()))
     53                             }
     54                         }
     55                     }
     56 
     57                     //default to DocWord
     58                     else -> {
     59                         val id = TokenGrammar.getFromValueOrDefault(token)
     60                         val category = if (id == TokenGrammar.WORD) TokenCategory.DocWord else id.category
     61                         tokens.add(TokenGrammar.newToken(token, category))
     62                         //TODO: Perhaps make all docblock words a DocWord
     63                         //tokens.add(TokenGrammar.newToken(token, TokenCategory.DocWord))
     64                     }
     65                 }
     66             }
     67         }
     68         return tokens.toList()
     69     }
     70 }