8000 Java style fix by tushuhei · Pull Request #132 · google/budoux · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Java style fix #132

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Mar 17, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 29 additions & 13 deletions java/src/main/java/com/google/budoux/HTMLProcessor.java
Original file line number Diff line number Diff line change
Expand Up @@ -17,12 +17,17 @@
package com.google.budoux;

import com.google.gson.Gson;
import com.google.gson.JsonIOException;
import com.google.gson.JsonSyntaxException;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.nio.charset.StandardCharsets;
import java.util.Arrays;
import java.util.HashSet;
import java.util.List;
import java.util.Locale;
import java.util.Set;
import java.util.stream.Collectors;
import org.jsoup.Jsoup;
Expand All @@ -37,45 +42,56 @@ final class HTMLProcessor {
private static final Set<String> skipNodes;
private static final String STYLE = "word-break: keep-all; overflow-wrap: break-word;";

private HTMLProcessor() {}

static {
Gson gson = new Gson();
InputStream inputStream = HTMLProcessor.class.getResourceAsStream("/skip_nodes.json");
Reader reader = new InputStreamReader(inputStream);
String[] skipNodesStrings = gson.fromJson(reader, String[].class);
skipNodes = new HashSet<>(Arrays.asList(skipNodesStrings));
try (Reader reader = new InputStreamReader(inputStream, StandardCharsets.UTF_8)) {
String[] skipNodesStrings = gson.fromJson(reader, String[].class);
skipNodes = new HashSet<>(Arrays.asList(skipNodesStrings));
} catch (JsonSyntaxException | JsonIOException | IOException e) {
throw new RuntimeException(e);
}
}

private static class PhraseResolvingNodeVisitor implements NodeVisitor {
private static final char SEP = '\uFFFF';
private final String phrasesJoined;
private final StringBuilder output = new StringBuilder();
private Integer scanIndex = 0;
private StringBuffer output = new StringBuffer();
private boolean toSkip = false;

PhraseResolvingNodeVisitor(List<String> phrases) {
this.phrasesJoined = String.join(Character.toString(SEP), phrases);
}

public StringBuffer getOutput() {
public StringBuilder getOutput() {
return output;
}

@Override
public void head(Node node, int depth) {
if (node.nodeName() == "body") return;
if (node.nodeName().equals("body")) {
return;
}
if (node instanceof Element) {
String attributesEncoded =
node.attributes().asList().stream()
.map(attribute -> " " + attribute.toString())
.map(attribute -> " " + attribute)
.collect(Collectors.joining(""));
output.append(String.format("<%s%s>", node.nodeName(), attributesEncoded));
if (skipNodes.contains(node.nodeName().toUpperCase())) toSkip = true;
if (skipNodes.contains(node.nodeName().toUpperCase(Locale.ENGLISH))) {
toSkip = true;
}
} else if (node instanceof TextNode) {
String data = ((TextNode) node).getWholeText();
for (int i = 0; i < data.length(); i++) {
char c = data.charAt(i);
if (c != phrasesJoined.charAt(scanIndex)) {
if (!toSkip) output.append("<wbr>");
if (!toSkip) {
output.append("<wbr>");
}
scanIndex++;
}
scanIndex++;
Expand All @@ -86,8 +102,9 @@ public void head(Node node, int depth) {

@Override
public void tail(Node node, int depth) {
if (node.nodeName() == "body") return;
if (node instanceof TextNode) return;
if (node.nodeName().equals("body") || node instanceof TextNode) {
return;
}
output.append(String.format("</%s>", node.nodeName()));
}
}
Expand All @@ -103,8 +120,7 @@ public static String resolve(List<String> phrases, String html) {
Document doc = Jsoup.parseBodyFragment(html);
PhraseResolvingNodeVisitor nodeVisitor = new PhraseResolvingNodeVisitor(phrases);
doc.body().traverse(nodeVisitor);
String result = String.format("<span style=\"%s\">%s</span>", STYLE, nodeVisitor.getOutput());
return result;
return String.format("<span style=\"%s\">%s</span>", STYLE, nodeVisitor.getOutput());
}

/**
Expand Down
52 changes: 35 additions & 17 deletions java/src/main/java/com/google/budoux/Parser.java
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
import java.io.InputStre 10000 amReader;
import java.io.Reader;
import java.lang.reflect.Type;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
Expand Down Expand Up @@ -93,14 +94,12 @@ public static Parser loadByFileName(String modelFileName) {
Gson gson = new Gson();
Type type = new TypeToken<Map<String, Map<String, Integer>>>() {}.getType();
InputStream inputStream = Parser.class.getResourceAsStream(modelFileName);
try (Reader reader = new InputStreamReader(inputStream, "UTF-8")) {
try (Reader reader = new InputStreamReader(inputStream, StandardCharsets.UTF_8)) {
Map<String, Map<String, Integer>> model = gson.fromJson(reader, type);
Parser parser = new Parser(model);
return parser;
return new Parser(model);
} catch (JsonIOException | JsonSyntaxException | IOException e) {
e.printStackTrace();
throw new RuntimeException(e);
}
return null;
}

/**
Expand All @@ -123,7 +122,9 @@ private int getScore(String featureKey, String sequence) {
* @return a list of phrases.
*/
public List<String> parse(String sentence) {
if (sentence.equals("")) return new ArrayList<>();
if (sentence.isEmpty()) {
return new ArrayList<>();
}
List<String> result = new ArrayList<>();
result.add(String.valueOf(sentence.charAt(0)));
int totalScore =
Expand All @@ -132,25 +133,42 @@ public List<String> parse(String sentence) {
.sum();
for (int i = 1; i < sentence.length(); i++) {
int score = -totalScore;
if (i - 2 > 0) score += 2 * this.getScore("UW1", sentence.substring(i - 3, i - 2));
if (i - 1 > 0) score += 2 * this.getScore("UW2", sentence.substring(i - 2, i - 1));
if (i - 2 > 0) {
score += 2 * this.getScore("UW1", sentence.substring(i - 3, i - 2));
}
if (i - 1 > 0) {
score += 2 * this.getScore("UW2", sentence.substring(i - 2, i - 1));
}
score += 2 * this.getScore("UW3", sentence.substring(i - 1, i));
score += 2 * this.getScore("UW4", sentence.substring(i, i + 1));
if (i + 1 < sentence.length())
if (i + 1 < sentence.length()) {
score += 2 * this.getScore("UW5", sentence.substring(i + 1, i + 2));
if (i + 2 < sentence.length())
}
if (i + 2 < sentence.length()) {
score += 2 * this.getScore("UW6", sentence.substring(i + 2, i + 3));
if (i > 1) score += 2 * this.getScore("BW1", sentence.substring(i - 2, i));
}
if (i > 1) {
score += 2 * this.getScore("BW1", sentence.substring(i - 2, i));
}
score += 2 * this.getScore("BW2", sentence.substring(i - 1, i + 1));
if (i + 1 < sentence.length())
if (i + 1 < sentence.length()) {
score += 2 * this.getScore("BW3", sentence.substring(i, i + 2));
if (i - 2 > 0) score += 2 * this.getScore("TW1", sentence.substring(i - 3, i));
if (i - 1 > 0) score += 2 * this.getScore("TW2", sentence.substring(i - 2, i + 1));
if (i + 1 < sentence.length())
}
if (i - 2 > 0) {
score += 2 * this.getScore("TW1", sentence.substring(i - 3, i));
}
if (i - 1 > 0) {
score += 2 * this.getScore("TW2", sentence.substring(i - 2, i + 1));
}
if (i + 1 < sentence.length()) {
score += 2 * this.getScore("TW3", sentence.substring(i - 1, i + 2));
if (i + 2 < sentence.length())
}
if (i + 2 < sentence.length()) {
score += 2 * this.getScore("TW4", sentence.substring(i, i + 3));
if (score > 0) result.add("");
}
if (score > 0) {
result.add("");
}
result.set(result.size() - 1, result.get(result.size() - 1) + sentence.charAt(i));
}
return result;
Expand Down
0