Refactoring: make Grammar an abstract class

parsley-examples/pom.xml

@@ -26,6 +26,12 @@
   </properties>
 
   <dependencies>
+    <dependency>
+      <groupId>com.albertoventurini.parsley</groupId>
+      <artifactId>parsley-grammar</artifactId>
+      <version>0.1.0-SNAPSHOT</version>
+    </dependency>
+
     <dependency>
       <groupId>org.junit.jupiter</groupId>
       <artifactId>junit-jupiter</artifactId>
@@ -37,10 +43,7 @@
       <artifactId>junit-jupiter-engine</artifactId>
       <scope>test</scope>
     </dependency>
-    <dependency>
+
-      <groupId>com.albertoventurini.parsley</groupId>
-      <artifactId>parsley-grammar</artifactId>
-    </dependency>
   </dependencies>
 
   <build>

parsley-examples/src/main/java/com/albertoventurini/parsley/examples/graphml/GrammarGraphMLParser.java

@@ -2,81 +2,17 @@ package com.albertoventurini.parsley.examples.graphml;
 
 import com.albertoventurini.parsley.grammar.Grammar;
 import com.albertoventurini.parsley.grammar.ParseTree;
-import com.albertoventurini.parsley.grammar.rules.Rule;
 
 import java.io.IOException;
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.util.List;
 import java.util.Map;
-import java.util.function.BiFunction;
-import java.util.function.Function;
 import java.util.stream.Collectors;
 
-import static com.albertoventurini.parsley.grammar.Grammar.*;
-
 public class GrammarGraphMLParser implements GraphMLParser {
 
-    private final Grammar grammar;
+    private final Grammar grammar = new GraphMLGrammar();
-
-    public GrammarGraphMLParser() {
-
-        final Rule comment = sequence(string("<!--"), until("-->")).as("comment");
-        final Rule comments = zeroOrMore(comment).as("comments");
-
-        final Rule xmlHeader = string("<?xml version='1.0' ?>").as("header");
-
-        final Rule attribute = sequence(
-                takeWhile(c -> c != '=' && c != '>'),
-                character('='),
-                character('\''),
-                takeWhile(c -> c != '\''),
-                character('\'')).as("attribute");
-
-        final Function<String, Rule> tagFunc = (s) -> sequence(
-                character('<'),
-                string(s).as("tagName"),
-                zeroOrMore(attribute).as("attributes"),
-                character('>')).as("tag:" + s);
-
-        final Function<String, Rule> closingTagFunc = (s) -> sequence(
-                string("</"),
-                string(s),
-                character('>')).as("closingTag:" + s);
-
-        final BiFunction<String, Rule, Rule> elementFunc = (tagName, content) -> sequence(
-                tagFunc.apply(tagName).as("tag:" + tagName),
-                content.as("content"),
-                closingTagFunc.apply(tagName).as("closingTag:" + tagName));
-
-        final Rule data = elementFunc.apply("data", takeWhile(c -> c != '<')).as("dataElem");
-
-        final Rule node = elementFunc.apply("node", zeroOrMore(data)).as("nodeElem");
-
-        final Rule edge = elementFunc.apply("edge", zeroOrMore(data)).as("edgeElem");
-
-        final Rule graph = sequence(
-                tagFunc.apply("graph"),
-                oneOrMore(node).as("nodes"),
-                oneOrMore(edge).as("edges"),
-                closingTagFunc.apply("graph")).as("graphElem");
-
-        final Rule key = sequence(tagFunc.apply("key"), closingTagFunc.apply("key"))
-                .as("keyElem");
-
-        final Rule graphml = sequence(
-                tagFunc.apply("graphml"),
-                oneOrMore(key).as("keys"),
-                graph,
-                closingTagFunc.apply("graphml")).as("graphmlElem");
-
-        final Rule graphmlFile = sequence(
-                xmlHeader,
-                comments.discard(),
-                graphml).as("graphmlFile");
-
-        grammar = new Grammar(graphmlFile, null);
-    }
 
     @Override
     public GraphMLParseResult parse(final String filePath) {

parsley-examples/src/main/java/com/albertoventurini/parsley/examples/graphml/GraphMLGrammar.java

@@ -0,0 +1,76 @@
+package com.albertoventurini.parsley.examples.graphml;
+
+import com.albertoventurini.parsley.grammar.Grammar;
+import com.albertoventurini.parsley.grammar.rules.Rule;
+
+import java.util.function.BiFunction;
+import java.util.function.Function;
+
+import static com.albertoventurini.parsley.grammar.rules.Rules.*;
+
+public class GraphMLGrammar extends Grammar {
+
+    private final Rule comment = sequence(string("<!--"), until("-->")).as("comment");
+    private final Rule comments = zeroOrMore(comment).setComment(true).as("comments");
+
+    private final Rule xmlHeader = string("<?xml version='1.0' ?>").as("header");
+
+    private final Rule attribute = sequence(
+            takeWhile(c -> c != '=' && c != '>'),
+            character('='),
+            character('\''),
+            takeWhile(c -> c != '\''),
+            character('\'')).as("attribute");
+
+    private final Function<String, Rule> tagFunc = (s) -> sequence(
+            character('<'),
+            string(s).as("tagName"),
+            zeroOrMore(attribute).as("attributes"),
+            character('>')).as("tag:" + s);
+
+    private final Function<String, Rule> closingTagFunc = (s) -> sequence(
+            string("</"),
+            string(s),
+            character('>')).as("closingTag:" + s);
+
+    private final BiFunction<String, Rule, Rule> elementFunc = (tagName, content) -> sequence(
+            tagFunc.apply(tagName).as("tag:" + tagName),
+            content.as("content"),
+            closingTagFunc.apply(tagName).as("closingTag:" + tagName));
+
+    private final Rule data = elementFunc.apply("data", takeWhile(c -> c != '<')).as("dataElem");
+
+    private final Rule node = elementFunc.apply("node", zeroOrMore(data)).as("nodeElem");
+
+    private final Rule edge = elementFunc.apply("edge", zeroOrMore(data)).as("edgeElem");
+
+    private final Rule graph = sequence(
+            tagFunc.apply("graph"),
+            oneOrMore(node).as("nodes"),
+            oneOrMore(edge).as("edges"),
+            closingTagFunc.apply("graph")).as("graphElem");
+
+    private final Rule key = sequence(tagFunc.apply("key"), closingTagFunc.apply("key"))
+            .as("keyElem");
+
+    private final Rule graphml = sequence(
+            tagFunc.apply("graphml"),
+            oneOrMore(key).as("keys"),
+            graph,
+            closingTagFunc.apply("graphml")).as("graphmlElem");
+
+    private final Rule graphmlFile = sequence(
+            xmlHeader,
+            comments.discard(),
+            graphml).as("graphmlFile");
+
+    @Override
+    protected Rule startRule() {
+        return graphmlFile;
+    }
+
+    @Override
+    protected Rule commentRule() {
+        return comments;
+    }
+}

parsley-examples/src/main/java/com/albertoventurini/parsley/examples/markdown/MarkdownGrammar.java

@@ -0,0 +1,35 @@
+package com.albertoventurini.parsley.examples.markdown;
+
+import com.albertoventurini.parsley.grammar.Grammar;
+import com.albertoventurini.parsley.grammar.rules.Rule;
+
+import static com.albertoventurini.parsley.grammar.rules.Rules.*;
+
+public class MarkdownGrammar extends Grammar {
+
+    private final Rule h1 = sequence(
+            character('#'),
+            takeWhile(c -> c != '\n')
+    );
+
+    private final Rule paragraph = sequence(
+            character('\n'),
+            takeWhile(c -> c != '\n')
+    );
+
+    private final Rule element = oneOf(h1, paragraph);
+
+    private final Rule elements = sequence(element);
+
+    private final Rule document = zeroOrMore(elements);
+
+    @Override
+    public Rule startRule() {
+        return document;
+    }
+
+    @Override
+    protected Rule commentRule() {
+        return null;
+    }
+}

parsley-examples/src/main/java/com/albertoventurini/parsley/examples/markdown/MarkdownParseResult.java

@@ -0,0 +1,4 @@
+package com.albertoventurini.parsley.examples.markdown;
+
+public class MarkdownParseResult {
+}

parsley-examples/src/main/java/com/albertoventurini/parsley/examples/markdown/MarkdownParser.java

@@ -0,0 +1,5 @@
+package com.albertoventurini.parsley.examples.markdown;
+
+public interface MarkdownParser {
+    MarkdownParseResult parse(String filePath);
+}

parsley-examples/src/test/java/com/albertoventurini/parsley/examples/graphml/GraphMLGrammarTest.java

@@ -1,6 +1,7 @@
 package com.albertoventurini.parsley.examples.graphml;
 
 import com.albertoventurini.parsley.grammar.Grammar;
+import com.albertoventurini.parsley.grammar.GrammarFactory;
 import com.albertoventurini.parsley.grammar.rules.Rule;
 import org.junit.jupiter.api.Test;
 
@@ -9,7 +10,7 @@ import java.nio.file.Path;
 import java.util.function.BiFunction;
 import java.util.function.Function;
 
-import static com.albertoventurini.parsley.grammar.Grammar.*;
+import static com.albertoventurini.parsley.grammar.rules.Rules.*;
 import static org.junit.jupiter.api.Assertions.assertTrue;
 
 public class GraphMLGrammarTest {
@@ -69,7 +70,7 @@ public class GraphMLGrammarTest {
 
         final Rule graphmlFile = sequence(xmlHeader, graphml).as("graphmlFile");
 
-        grammar = new Grammar(graphmlFile, comments);
+        grammar = GrammarFactory.newGrammar(graphmlFile, comments);
     }
 
     @Test

parsley-examples/src/test/java/com/albertoventurini/parsley/examples/graphml/MarkdownGrammarTest.java

@@ -0,0 +1,13 @@
+package com.albertoventurini.parsley.examples.graphml;
+
+import com.albertoventurini.parsley.examples.markdown.MarkdownGrammar;
+import org.junit.jupiter.api.Test;
+
+public class MarkdownGrammarTest {
+
+    @Test
+    public void markdownGrammar_withH1AndParagraph_shouldParse() {
+        final MarkdownGrammar grammar = new MarkdownGrammar();
+    }
+
+}

parsley-examples/src/test/resources/markdown/markdown1.md

@@ -0,0 +1,155 @@
+# An h1 header
+
+Paragraphs are separated by a blank line.
+
+2nd paragraph. *Italic*, **bold**, and `monospace`. Itemized lists
+look like:
+
+* this one
+* that one
+* the other one
+
+Note that --- not considering the asterisk --- the actual text
+content starts at 4-columns in.
+
+> Block quotes are
+> written like so.
+>
+> They can span multiple paragraphs,
+> if you like.
+
+Use 3 dashes for an em-dash. Use 2 dashes for ranges (ex., "it's all
+in chapters 12--14"). Three dots ... will be converted to an ellipsis.
+Unicode is supported. ☺
+
+
+
+# An h2 header
+
+Here's a numbered list:
+
+1. first item
+2. second item
+3. third item
+
+Note again how the actual text starts at 4 columns in (4 characters
+from the left side). Here's a code sample:
+
+    # Let me re-iterate ...
+    for i in 1 .. 10 { do-something(i) }
+
+As you probably guessed, indented 4 spaces. By the way, instead of
+indenting the block, you can use delimited blocks, if you like:
+
+~~~
+define foobar() {
+    print "Welcome to flavor country!";
+}
+~~~
+
+(which makes copying & pasting easier). You can optionally mark the
+delimited block for Pandoc to syntax highlight it:
+
+~~~python
+import time
+# Quick, count to ten!
+for i in range(10):
+    # (but not *too* quick)
+    time.sleep(0.5)
+    print i
+~~~
+
+
+
+### An h3 header
+
+Now a nested list:
+
+1. First, get these ingredients:
+
+    * carrots
+    * celery
+    * lentils
+
+2. Boil some water.
+
+3. Dump everything in the pot and follow
+   this algorithm:
+
+       find wooden spoon
+       uncover pot
+       stir
+       cover pot
+       balance wooden spoon precariously on pot handle
+       wait 10 minutes
+       goto first step (or shut off burner when done)
+
+   Do not bump wooden spoon or it will fall.
+
+Notice again how text always lines up on 4-space indents (including
+that last line which continues item 3 above).
+
+Here's a link to [a website](http://foo.bar), to a [local
+doc](local-doc.html), and to a [section heading in the current
+doc](#an-h2-header). Here's a footnote [^1].
+
+[^1]: Footnote text goes here.
+
+Tables can look like this:
+
+size  material      color
+----  ------------  ------------
+9     leather       brown
+10    hemp canvas   natural
+11    glass         transparent
+
+Table: Shoes, their sizes, and what they're made of
+
+(The above is the caption for the table.) Pandoc also supports
+multi-line tables:
+
+--------  -----------------------
+keyword   text
+--------  -----------------------
+red       Sunsets, apples, and
+other red or reddish
+things.
+
+green     Leaves, grass, frogs
+and other things it's
+not easy being.
+--------  -----------------------
+
+A horizontal rule follows.
+
+***
+
+Here's a definition list:
+
+apples
+: Good for making applesauce.
+oranges
+: Citrus!
+tomatoes
+: There's no "e" in tomatoe.
+
+Again, text is indented 4 spaces. (Put a blank line between each
+term/definition pair to spread things out more.)
+
+Here's a "line block":
+
+| Line one
+|   Line too
+| Line tree
+
+and images can be specified like so:
+
+![example image](example-image.jpg "An exemplary image")
+
+Inline math equations go in like so: $\omega = d\phi / dt$. Display
+math should get its own line and be put in in double-dollarsigns:
+
+$$I = \int \rho R^{2} dV$$
+
+And note that you can backslash-escape any punctuation characters
+which you wish to be displayed literally, ex.: \`foo\`, \*bar\*, etc.

parsley-grammar/src/main/java/com/albertoventurini/parsley/grammar/Grammar.java

@@ -1,89 +1,18 @@
 package com.albertoventurini.parsley.grammar;
 
-import com.albertoventurini.parsley.grammar.rules.AnyCharacter;
-import com.albertoventurini.parsley.grammar.rules.MatchCharacter;
-import com.albertoventurini.parsley.grammar.rules.MatchString;
-import com.albertoventurini.parsley.grammar.rules.OneOf;
-import com.albertoventurini.parsley.grammar.rules.OneOrMore;
 import com.albertoventurini.parsley.grammar.rules.Rule;
-import com.albertoventurini.parsley.grammar.rules.Sequence;
-import com.albertoventurini.parsley.grammar.rules.TakeWhileCharacter;
-import com.albertoventurini.parsley.grammar.rules.UntilString;
-import com.albertoventurini.parsley.grammar.rules.Wrapper;
-import com.albertoventurini.parsley.grammar.rules.ZeroOrMore;
-import com.albertoventurini.parsley.grammar.rules.ZeroOrOne;
 
 import java.util.Optional;
-import java.util.function.Predicate;
 
-public class Grammar {
+public abstract class Grammar {
 
-    private final Rule startRule;
+    protected abstract Rule startRule();
 
-    private final Rule commentRule;
+    protected abstract Rule commentRule();
-
-    public Grammar(
-            final Rule startRule,
-            final Rule commentRule) {
-        this.startRule = startRule;
-        this.commentRule = commentRule;
-
-        // TODO: better than this
-        if (commentRule != null) {
-            commentRule.setComment(true);
-        }
-    }
 
     public Optional<ParseTree> parse(final String text) {
-        final var ctx = new GrammarContext(text, commentRule);
+        final var ctx = new GrammarContext(text, commentRule());
-        return startRule.apply(ctx);
+        return startRule().apply(ctx);
     }
 
-    public static MatchCharacter character(final char c) {
-        return new MatchCharacter(c);
-    }
-
-    public static AnyCharacter anyChar() {
-        return new AnyCharacter();
-    }
-
-    public static MatchString string(final String s) {
-        return new MatchString(s);
-    }
-
-    public static TakeWhileCharacter token() {
-        return new TakeWhileCharacter();
-    }
-
-    public static TakeWhileCharacter takeWhile(final Predicate<Character> characterPredicate) {
-        return new TakeWhileCharacter(characterPredicate);
-    }
-
-    public static UntilString until(final String s) {
-        return new UntilString(s);
-    }
-
-    public static Sequence sequence(final Rule... rules) {
-        return new Sequence(rules);
-    }
-
-    public static OneOf oneOf(final Rule... rules) {
-        return new OneOf(rules);
-    }
-
-    public static ZeroOrMore zeroOrMore(final Rule childRule) {
-        return new ZeroOrMore(childRule);
-    }
-
-    public static ZeroOrOne zeroOrOne(final Rule childRule) {
-        return new ZeroOrOne(childRule);
-    }
-
-    public static OneOrMore oneOrMore(final Rule childRule) {
-        return new OneOrMore(childRule);
-    }
-
-    public static Wrapper wrapper() {
-        return new Wrapper();
-    }
 }

parsley-grammar/src/main/java/com/albertoventurini/parsley/grammar/GrammarFactory.java

@@ -0,0 +1,27 @@
+package com.albertoventurini.parsley.grammar;
+
+import com.albertoventurini.parsley.grammar.rules.Rule;
+
+public class GrammarFactory {
+
+    public static Grammar newGrammar(final Rule startRule, final Rule commentRule) {
+        // TODO: better than this
+
+        if (commentRule != null) {
+            commentRule.setComment(true);
+        }
+
+        return new Grammar() {
+
+            @Override
+            protected Rule startRule() {
+                return startRule;
+            }
+
+            @Override
+            protected Rule commentRule() {
+                return commentRule;
+            }
+        };
+    }
+}

parsley-grammar/src/main/java/com/albertoventurini/parsley/grammar/ParseContext.java

@@ -2,7 +2,7 @@ package com.albertoventurini.parsley.grammar;
 
 import java.util.Arrays;
 
-public class ParseContext {
+class ParseContext {
     private final char[] charArr;
     private int cursor;
 

parsley-grammar/src/main/java/com/albertoventurini/parsley/grammar/ParseTree.java

@@ -4,7 +4,7 @@ import java.util.Collections;
 import java.util.List;
 import java.util.Optional;
 
-public class ParseTree {
+public abstract class ParseTree {
 
     private final String text;
 

parsley-grammar/src/main/java/com/albertoventurini/parsley/grammar/rules/MatchCharacter.java

@@ -10,7 +10,6 @@ public final class MatchCharacter extends Rule {
 
     public MatchCharacter(final char c) {
         this.c = c;
-
         discard = true;
     }
 

parsley-grammar/src/main/java/com/albertoventurini/parsley/grammar/rules/Rule.java

@@ -42,7 +42,8 @@ public abstract class Rule {
 
     public abstract Optional<ParseTree> tryApply(final GrammarContext ctx);
 
-    public void setComment(final boolean comment) {
+    public Rule setComment(final boolean comment) {
         isComment = comment;
+        return this;
     }
 }

parsley-grammar/src/main/java/com/albertoventurini/parsley/grammar/rules/Rules.java

@@ -0,0 +1,54 @@
+package com.albertoventurini.parsley.grammar.rules;
+
+import java.util.function.Predicate;
+
+public class Rules {
+
+    public static MatchCharacter character(final char c) {
+        return new MatchCharacter(c);
+    }
+
+    public static AnyCharacter anyChar() {
+        return new AnyCharacter();
+    }
+
+    public static MatchString string(final String s) {
+        return new MatchString(s);
+    }
+
+    public static TakeWhileCharacter token() {
+        return new TakeWhileCharacter();
+    }
+
+    public static TakeWhileCharacter takeWhile(final Predicate<Character> characterPredicate) {
+        return new TakeWhileCharacter(characterPredicate);
+    }
+
+    public static UntilString until(final String s) {
+        return new UntilString(s);
+    }
+
+    public static Sequence sequence(final Rule... rules) {
+        return new Sequence(rules);
+    }
+
+    public static OneOf oneOf(final Rule... rules) {
+        return new OneOf(rules);
+    }
+
+    public static ZeroOrMore zeroOrMore(final Rule childRule) {
+        return new ZeroOrMore(childRule);
+    }
+
+    public static ZeroOrOne zeroOrOne(final Rule childRule) {
+        return new ZeroOrOne(childRule);
+    }
+
+    public static OneOrMore oneOrMore(final Rule childRule) {
+        return new OneOrMore(childRule);
+    }
+
+    public static Wrapper wrapper() {
+        return new Wrapper();
+    }
+}

parsley-grammar/src/main/java/com/albertoventurini/parsley/grammar/rules/Sequence.java

@@ -20,7 +20,7 @@ public final class Sequence extends Rule {
         final int start = ctx.getCursor();
         final List<ParseTree> children = new ArrayList<>(rules.length);
 
-        for (final com.albertoventurini.parsley.grammar.rules.Rule rule : rules) {
+        for (final Rule rule : rules) {
             if (!ctx.hasNext()) {
                 ctx.setCursor(start);
                 return Optional.empty();

parsley-grammar/src/test/java/com/albertoventurini/parsley/grammar/GrammarTest.java

@@ -5,13 +5,7 @@ import org.junit.jupiter.api.Test;
 
 import java.util.function.Function;
 
-import static com.albertoventurini.parsley.grammar.Grammar.character;
+import static com.albertoventurini.parsley.grammar.rules.Rules.*;
-import static com.albertoventurini.parsley.grammar.Grammar.oneOf;
-import static com.albertoventurini.parsley.grammar.Grammar.sequence;
-import static com.albertoventurini.parsley.grammar.Grammar.string;
-import static com.albertoventurini.parsley.grammar.Grammar.takeWhile;
-import static com.albertoventurini.parsley.grammar.Grammar.token;
-import static com.albertoventurini.parsley.grammar.Grammar.zeroOrMore;
 import static org.junit.jupiter.api.Assertions.assertEquals;
 import static org.junit.jupiter.api.Assertions.assertTrue;
 
@@ -24,7 +18,7 @@ public class GrammarTest {
                 takeWhile(Character::isLetterOrDigit),
                 oneOf(string("/>"), character('>')));
 
-        final Grammar grammar = new Grammar(tag, null);
+        final Grammar grammar = GrammarFactory.newGrammar(tag, null);
 
         final var parseTree1 = grammar.parse("<tag1>");
 
@@ -49,7 +43,7 @@ public class GrammarTest {
                 zeroOrMore(attribute),
                 oneOf(string("/>"), character('>')));
 
-        final Grammar grammar = new Grammar(tag, null);
+        final Grammar grammar = GrammarFactory.newGrammar(tag, null);
 
         assertTrue(grammar.parse("<tag1>").isPresent());
 
@@ -111,7 +105,7 @@ public class GrammarTest {
                 zeroOrMore(attribute),
                 oneOf(string("/>"), character('>')));
 
-        final Grammar grammar = new Grammar(tag, null);
+        final Grammar grammar = GrammarFactory.newGrammar(tag, null);
 
         assertTrue(grammar.parse("<graphml xmlns='http://graphml.graphdrawing.org/xmlns'>").isPresent());
     }
@@ -140,7 +134,7 @@ public class GrammarTest {
                 tagFunc.apply("key"),
                 closingTagFunc.apply("key"));
 
-        final Grammar grammar = new Grammar(key, null);
+        final Grammar grammar = GrammarFactory.newGrammar(key, null);
 
         assertTrue(grammar.parse("<key id='type'    for='node' attr.name='type'    attr.type='string'></key>").isPresent());
     }