Refactoring: make Grammar an abstract class
This commit is contained in:
parent
c9c1454f90
commit
301eaaf98d
18 changed files with 395 additions and 163 deletions
|
|
@ -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;
|
||||
|
||||
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);
|
||||
}
|
||||
private final Grammar grammar = new GraphMLGrammar();
|
||||
|
||||
@Override
|
||||
public GraphMLParseResult parse(final String filePath) {
|
||||
|
|
|
|||
|
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
package com.albertoventurini.parsley.examples.markdown;
|
||||
|
||||
public class MarkdownParseResult {
|
||||
}
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
package com.albertoventurini.parsley.examples.markdown;
|
||||
|
||||
public interface MarkdownParser {
|
||||
MarkdownParseResult parse(String filePath);
|
||||
}
|
||||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -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();
|
||||
}
|
||||
|
||||
}
|
||||
155
parsley-examples/src/test/resources/markdown/markdown1.md
Normal file
155
parsley-examples/src/test/resources/markdown/markdown1.md
Normal file
|
|
@ -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:
|
||||
|
||||
|
||||
|
||||
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.
|
||||
Loading…
Add table
Add a link
Reference in a new issue