xref: /OpenGrok/opengrok-indexer/src/main/jflex/analysis/clojure/ClojureSymbolTokenizer.lex (revision d219b4cea555a12b602d2d5518daa22134ad4879)
1 /*
2  * CDDL HEADER START
3  *
4  * The contents of this file are subject to the terms of the
5  * Common Development and Distribution License (the "License").
6  * You may not use this file except in compliance with the License.
7  *
8  * See LICENSE.txt included in this distribution for the specific
9  * language governing permissions and limitations under the License.
10  *
11  * When distributing Covered Code, include this CDDL HEADER in each
12  * file and include the License file at LICENSE.txt.
13  * If applicable, add the following below this CDDL HEADER, with the
14  * fields enclosed by brackets "[]" replaced with your own identifying
15  * information: Portions Copyright [yyyy] [name of copyright owner]
16  *
17  * CDDL HEADER END
18  */
19 
20 /*
21  * Copyright (c) 2015, 2021, Oracle and/or its affiliates. All rights reserved.
22  * Portions Copyright (c) 2017, Chris Fraire <cfraire@me.com>.
23  */
24 
25 /*
26  * Gets Clojure symbols - ignores comments, strings, keywords
27  */
28 
29 package org.opengrok.indexer.analysis.clojure;
30 
31 import org.opengrok.indexer.analysis.JFlexSymbolMatcher;
32 %%
33 %public
34 %class ClojureSymbolTokenizer
35 %extends JFlexSymbolMatcher
36 %unicode
37 %int
38 %include ../CommonLexer.lexh
39 %char
40 
41 %{
42     private int nestedComment;
43 
44     @Override
reset()45     public void reset() {
46         super.reset();
47         nestedComment = 0;
48     }
49 %}
50 
51 %state STRING COMMENT SCOMMENT
52 
53 %include ../Common.lexh
54 %include Clojure.lexh
55 %%
56 
57 <YYINITIAL> {
58 {Identifier} {
59     String id = yytext();
60               if (!Consts.kwd.contains(id)) {
61                         onSymbolMatched(id, yychar);
62                         return yystate();
63               }
64  }
65 
66  {Number}    {}
67 
68  \"     { yybegin(STRING); }
69 ";"     { yybegin(SCOMMENT); }
70 }
71 
72 <STRING> {
73  \"     { yybegin(YYINITIAL); }
74  \\[\"\\]    {}
75 }
76 
77 <YYINITIAL, COMMENT> {
78  "#|"   { if (nestedComment++ == 0) { yybegin(COMMENT); } }
79 }
80 
81 <COMMENT> {
82 "|#"    { if (--nestedComment == 0) { yybegin(YYINITIAL); } }
83 }
84 
85 <SCOMMENT> {
86 {EOL}   { yybegin(YYINITIAL);}
87 }
88 
89 <YYINITIAL, STRING, COMMENT, SCOMMENT> {
90 {WhspChar}+    {}
91 [^]    {}
92 }
93