Merge pull request #1901 from idodeclare/feature/sh_tests

Feature/sh tests

Author: tarzanek

opengrok-indexer/pom.xml

@@ -144,6 +144,13 @@ Portions Copyright (c) 2017, Chris Fraire <[email protected]>.
                     <exclude>*.java</exclude>
                 </excludes>
             </testResource>
+            <testResource>
+                <targetPath>org/opensolaris/opengrok/analysis/sh/</targetPath>
+                <directory>../test/org/opensolaris/opengrok/analysis/sh/</directory>
+                <excludes>
+                    <exclude>*.java</exclude>
+                </excludes>
+            </testResource>
         </testResources>
 
         <plugins>

src/org/opensolaris/opengrok/analysis/JFlexXref.java

@@ -420,6 +420,15 @@ public void disjointSpan(String className) throws IOException {
         disjointSpanClassName = className;
     }
 
+    /**
+     * Gets the argument from the last call to
+     * {@link #disjointSpan(java.lang.String)}.
+     * @return a defined value or null
+     */
+    public String getDisjointSpanClassName() {
+        return disjointSpanClassName;
+    }
+
     /**
      * Write xref to the specified {@code Writer}.
      *

src/org/opensolaris/opengrok/analysis/sh/Consts.java

@@ -20,6 +20,7 @@
 /*
  * Copyright 2005 Sun Microsystems, Inc.  All rights reserved.
  * Use is subject to license terms.
+ * Portions Copyright (c) 2017, Chris Fraire <[email protected]>.
  */
 
 package org.opensolaris.opengrok.analysis.sh;
@@ -144,5 +145,6 @@ public class Consts{
         shkwd.add( "void" );
         shkwd.add( "unsigned" );
         shkwd.add( "nameref" );
+        shkwd.add( "in" );
     }
 }

src/org/opensolaris/opengrok/analysis/sh/Sh.lexh

@@ -0,0 +1,37 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * See LICENSE.txt included in this distribution for the specific
+ * language governing permissions and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at LICENSE.txt.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2005, 2017, Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2017, Chris Fraire <[email protected]>.
+ */
+
+Identifier = [a-zA-Z_] [a-zA-Z0-9_]*
+
+Number = \$? [0-9]+\.[0-9]+| [0-9][0-9]* | [0][xX] [0-9a-fA-F]+
+
+/*
+ * Rather than enumerate letters, just treat all hyphen- or plus- with a
+ * single-char as a unary op. "req_lookahead" because an assertion is needed
+ * that it is followed by non-word or end-of-line.
+ */
+Unary_op_req_lookahead = [\-\+]{Unary_op_char}
+Unary_op_char = [A-Za-z]
+
+Binary_op = [\-]("ef"|"nt"|"ot"|"eq"|"ge"|"gt"|"le"|"lt"|"ne"){WhspChar}

src/org/opensolaris/opengrok/analysis/sh/ShSymbolTokenizer.lex

@@ -23,8 +23,7 @@
  */
 
 package org.opensolaris.opengrok.analysis.sh;
-import java.io.IOException;
-import java.io.Reader;
+
 import org.opensolaris.opengrok.analysis.JFlexTokenizer;
 %%
 %public
@@ -38,48 +37,65 @@ super(in);
 %include CommonTokenizer.lexh
 %char
 
-Identifier = [a-zA-Z_] [a-zA-Z0-9_]*
-
 %state STRING COMMENT SCOMMENT QSTRING
 
+%include Common.lexh
+%include Sh.lexh
 %%
 
 <YYINITIAL> {
-{Identifier} {String id = yytext();
+{Identifier}    {
+    String id = yytext();
                 if(!Consts.shkwd.contains(id)){
                         setAttribs(id, yychar, yychar + yylength());
                         return yystate(); }
               }
+ {Number}    {}
  \"     { yybegin(STRING); }
  \'     { yybegin(QSTRING); }
  "#"    { yybegin(SCOMMENT); }
+
+ {Unary_op_req_lookahead} / \W    {
+    // noop
+ }
+ {Unary_op_req_lookahead} $    {
+    // noop
+ }
+ {WhiteSpace} {Unary_op_char} / ")"    {
+    // noop
+ }
+ {Binary_op}    {
+    // noop
+ }
 }
 
 <STRING> {
-"$" {Identifier} {
+"$" {Identifier}    {
     setAttribs(yytext().substring(1), yychar + 1, yychar + yylength());
     return yystate();
-}
+ }
 
-"${" {Identifier} "}" {
+"${" {Identifier} "}"    {
     int startOffset = 2;            // trim away the "${" prefix
     int endOffset = yylength() - 1; // trim away the "}" suffix
     setAttribs(yytext().substring(startOffset, endOffset),
                yychar + startOffset,
                yychar + endOffset);
     return yystate();
-}
+ }
 
  \"     { yybegin(YYINITIAL); }
-\\\\ | \\\"     {}
+ \\[\"\$\`\\]    {}
 }
 
 <QSTRING> {
+ \\[\']    {}
  \'     { yybegin(YYINITIAL); }
 }
 
 <SCOMMENT> {
-\n      { yybegin(YYINITIAL);}
+{WhiteSpace}    {}
+{EOL}      { yybegin(YYINITIAL);}
 }
 
 <YYINITIAL, STRING, SCOMMENT, QSTRING> {