You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@groovy.apache.org by pa...@apache.org on 2019/09/27 10:28:59 UTC
[groovy] branch GROOVY_3_0_X updated: groovysh: prepare
RelaxedParser for switch to antlr4
This is an automated email from the ASF dual-hosted git repository.
paulk pushed a commit to branch GROOVY_3_0_X
in repository https://gitbox.apache.org/repos/asf/groovy.git
The following commit(s) were added to refs/heads/GROOVY_3_0_X by this push:
new 49840d8 groovysh: prepare RelaxedParser for switch to antlr4
49840d8 is described below
commit 49840d8daf8ee9fdd889c0ef4eec230bf26a44d7
Author: Paul King <pa...@asert.com.au>
AuthorDate: Fri Sep 27 20:19:23 2019 +1000
groovysh: prepare RelaxedParser for switch to antlr4
---
.../org/apache/groovy/groovysh/Groovysh.groovy | 3 +-
.../org/apache/groovy/groovysh/Parser.groovy | 83 +++------------------
.../apache/groovy/groovysh/RelaxedParser.groovy | 84 ++++++++++++++++++++++
.../groovy/groovysh/antlr4/RelaxedParser.groovy | 73 +++++++++++++++++++
4 files changed, 167 insertions(+), 76 deletions(-)
diff --git a/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/Groovysh.groovy b/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/Groovysh.groovy
index 5a73b5b..7e3a95c 100644
--- a/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/Groovysh.groovy
+++ b/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/Groovysh.groovy
@@ -18,7 +18,6 @@
*/
package org.apache.groovy.groovysh
-import antlr.TokenStreamException
import groovy.transform.CompileStatic
import jline.Terminal
import jline.WindowsTerminal
@@ -376,7 +375,7 @@ try {$COLLECTED_BOUND_VARS_MAP_VARNAME[\"$varname\"] = $varname;
try {
while (lexer.nextToken().getType() != CurlyCountingGroovyLexer.EOF) {
}
- } catch (TokenStreamException e) {
+ } catch (Exception ignore) { // TokenStreamException for antlr2
// pass
}
curlyLevel = lexer.getParenLevel()
diff --git a/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/Parser.groovy b/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/Parser.groovy
index 44ce5ac..b793d60 100644
--- a/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/Parser.groovy
+++ b/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/Parser.groovy
@@ -18,15 +18,9 @@
*/
package org.apache.groovy.groovysh
-import antlr.RecognitionException
-import antlr.TokenStreamException
-import antlr.collections.AST
-import org.codehaus.groovy.antlr.SourceBuffer
-import org.codehaus.groovy.antlr.UnicodeEscapingReader
-import org.codehaus.groovy.antlr.parser.GroovyLexer
-import org.codehaus.groovy.antlr.parser.GroovyRecognizer
+import org.codehaus.groovy.antlr.AntlrParserPluginFactory
import org.codehaus.groovy.control.CompilationFailedException
-import org.codehaus.groovy.control.ParserPluginFactory
+import org.codehaus.groovy.control.CompilerConfiguration
import org.codehaus.groovy.control.SourceUnit
import org.codehaus.groovy.tools.shell.util.Logger
import org.codehaus.groovy.tools.shell.util.Preferences
@@ -40,8 +34,7 @@ interface Parsing {
/**
* Provides a facade over the parser to recognize valid Groovy syntax.
*/
-class Parser
-{
+class Parser {
static final String NEWLINE = System.getProperty('line.separator')
private static final Logger log = Logger.create(Parser)
@@ -55,7 +48,8 @@ class Parser
switch (flavor) {
case Preferences.PARSER_RELAXED:
- delegate = new RelaxedParser()
+ boolean oldParserEnabled = CompilerConfiguration.DEFAULT.getPluginFactory() instanceof AntlrParserPluginFactory;
+ delegate = oldParserEnabled ? new RelaxedParser() : new org.apache.groovy.groovysh.antlr4.RelaxedParser()
break
case Preferences.PARSER_RIGID:
@@ -74,68 +68,11 @@ class Parser
}
}
-/**
- * A relaxed parser, which tends to allow more, but won't really catch valid syntax errors.
- */
-final class RelaxedParser implements Parsing
-{
- private final Logger log = Logger.create(this.class)
-
- private SourceBuffer sourceBuffer
-
- private String[] tokenNames
-
- @Override
- ParseStatus parse(final Collection<String> buffer) {
- assert buffer
-
- sourceBuffer = new SourceBuffer()
-
- def source = buffer.join(Parser.NEWLINE)
-
- log.debug("Parsing: $source")
-
- try {
- doParse(new UnicodeEscapingReader(new StringReader(source), sourceBuffer))
-
- log.debug('Parse complete')
-
- return new ParseStatus(ParseCode.COMPLETE)
- }
- catch (e) {
- switch (e.getClass()) {
- case TokenStreamException:
- case RecognitionException:
- log.debug("Parse incomplete: $e (${e.getClass().name})")
-
- return new ParseStatus(ParseCode.INCOMPLETE)
-
- default:
- log.debug("Parse error: $e (${e.getClass().name})")
-
- return new ParseStatus(e)
- }
- }
- }
-
- protected AST doParse(final UnicodeEscapingReader reader) throws Exception {
- GroovyLexer lexer = new GroovyLexer(reader)
- reader.setLexer(lexer)
-
- def parser = GroovyRecognizer.make(lexer)
- parser.setSourceBuffer(sourceBuffer)
- tokenNames = parser.tokenNames
-
- parser.compilationUnit()
- return parser.AST
- }
-}
/**
* A more rigid parser which catches more syntax errors, but also tends to barf on stuff that is really valid from time to time.
*/
-final class RigidParser implements Parsing
-{
+final class RigidParser implements Parsing {
private static final Pattern ANNOTATION_PATTERN = Pattern.compile('^@[a-zA-Z_][a-zA-Z_0-9]*(.*)$')
static final String SCRIPT_FILENAME = 'groovysh_parse'
@@ -217,7 +154,7 @@ final class RigidParser implements Parsing
int parens = 0
int brackets = 0
for (ch in source) {
- switch(ch) {
+ switch (ch) {
case '[': ++brackets; break;
case ']': --brackets; break;
case '(': ++parens; break;
@@ -237,8 +174,7 @@ final class RigidParser implements Parsing
/**
* Container for the parse code.
*/
-final class ParseCode
-{
+final class ParseCode {
static final ParseCode COMPLETE = new ParseCode(0)
static final ParseCode INCOMPLETE = new ParseCode(1)
@@ -260,8 +196,7 @@ final class ParseCode
/**
* Container for parse status details.
*/
-final class ParseStatus
-{
+final class ParseStatus {
final ParseCode code
final Throwable cause
diff --git a/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/RelaxedParser.groovy b/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/RelaxedParser.groovy
new file mode 100644
index 0000000..21389f9
--- /dev/null
+++ b/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/RelaxedParser.groovy
@@ -0,0 +1,84 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.groovy.groovysh
+
+import antlr.RecognitionException
+import antlr.TokenStreamException
+import antlr.collections.AST
+import org.apache.groovy.parser.antlr4.GroovyLangLexer
+import org.codehaus.groovy.antlr.SourceBuffer
+import org.codehaus.groovy.antlr.UnicodeEscapingReader
+import org.codehaus.groovy.antlr.parser.GroovyRecognizer
+import org.codehaus.groovy.tools.shell.util.Logger
+
+/**
+ * A relaxed parser, which tends to allow more, but won't really catch valid syntax errors.
+ */
+final class RelaxedParser implements Parsing {
+ private final Logger log = Logger.create(this.class)
+
+ private SourceBuffer sourceBuffer
+
+ private String[] tokenNames
+
+ @Override
+ ParseStatus parse(final Collection<String> buffer) {
+ assert buffer
+
+ sourceBuffer = new SourceBuffer()
+
+ def source = buffer.join(Parser.NEWLINE)
+
+ log.debug("Parsing: $source")
+
+ try {
+ doParse(new UnicodeEscapingReader(new StringReader(source), sourceBuffer))
+
+ log.debug('Parse complete')
+
+ return new ParseStatus(ParseCode.COMPLETE)
+ }
+ catch (e) {
+ switch (e.getClass()) {
+ case TokenStreamException:
+ case RecognitionException:
+ log.debug("Parse incomplete: $e (${e.getClass().name})")
+
+ return new ParseStatus(ParseCode.INCOMPLETE)
+
+ default:
+ log.debug("Parse error: $e (${e.getClass().name})")
+
+ return new ParseStatus(e)
+ }
+ }
+ }
+
+ protected AST doParse(final UnicodeEscapingReader reader) throws Exception {
+ GroovyLangLexer lexer = new GroovyLangLexer(reader)
+ reader.setLexer(lexer)
+
+ def parser = GroovyRecognizer.make(lexer)
+ parser.setSourceBuffer(sourceBuffer)
+ tokenNames = parser.tokenNames
+
+ parser.compilationUnit()
+ return parser.AST
+ }
+}
\ No newline at end of file
diff --git a/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/antlr4/RelaxedParser.groovy b/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/antlr4/RelaxedParser.groovy
new file mode 100644
index 0000000..6102eea
--- /dev/null
+++ b/subprojects/groovy-groovysh/src/main/groovy/org/apache/groovy/groovysh/antlr4/RelaxedParser.groovy
@@ -0,0 +1,73 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.groovy.groovysh.antlr4
+
+import org.antlr.v4.runtime.CharStream
+import org.antlr.v4.runtime.CharStreams
+import org.antlr.v4.runtime.CommonTokenStream
+import org.antlr.v4.runtime.ConsoleErrorListener
+import org.apache.groovy.groovysh.ParseCode
+import org.apache.groovy.groovysh.ParseStatus
+import org.apache.groovy.groovysh.Parser
+import org.apache.groovy.groovysh.Parsing
+import org.apache.groovy.parser.antlr4.GroovyLangLexer
+import org.codehaus.groovy.tools.shell.util.Logger
+
+/**
+ * A relaxed parser, which tends to allow more, but won't really catch valid syntax errors.
+ */
+final class RelaxedParser implements Parsing {
+ private final Logger log = Logger.create(this.class)
+
+ @Override
+ ParseStatus parse(final Collection<String> buffer) {
+ assert buffer
+ def source = buffer.join(Parser.NEWLINE)
+
+ log.debug("Parsing: $source")
+
+ try {
+ CharStream charStream = CharStreams.fromReader(new StringReader(source))
+ GroovyLangLexer lexer = new GroovyLangLexer(charStream)
+ lexer.removeErrorListener(ConsoleErrorListener.INSTANCE)
+ def tokenStream = new CommonTokenStream(lexer)
+ tokenStream.fill()
+
+ log.debug('Parse complete')
+
+ return new ParseStatus(ParseCode.COMPLETE)
+ }
+ catch (e) {
+ log.debug(e)
+ switch (e.getClass()) {
+ // TODO determine appropriate antlr4 exceptions or detect EOF earlier at end of stream
+// case TokenStreamException:
+// case RecognitionException:
+// log.debug("Parse incomplete: $e (${e.getClass().name})")
+//
+// return new ParseStatus(ParseCode.INCOMPLETE)
+
+ default:
+ log.debug("Parse error: $e (${e.getClass().name})")
+
+ return new ParseStatus(e)
+ }
+ }
+ }
+}
\ No newline at end of file