aboutsummaryrefslogtreecommitdiffstats
path: root/server/src/org/jsoup/examples/HtmlToPlainText.java
diff options
context:
space:
mode:
authorLeif Åstrand <leif@vaadin.com>2012-09-05 19:50:56 +0300
committerLeif Åstrand <leif@vaadin.com>2012-09-05 19:51:15 +0300
commit7d25670284b11c7c62ba25183f265227cb3dba83 (patch)
treec8e76eb70dd3cdd5cf59a99419635f2188b25c24 /server/src/org/jsoup/examples/HtmlToPlainText.java
parent1d0c96de9595c243d88471476d21e5f248be63f7 (diff)
downloadvaadin-framework-7d25670284b11c7c62ba25183f265227cb3dba83.tar.gz
vaadin-framework-7d25670284b11c7c62ba25183f265227cb3dba83.zip
Reformat project
Diffstat (limited to 'server/src/org/jsoup/examples/HtmlToPlainText.java')
-rw-r--r--server/src/org/jsoup/examples/HtmlToPlainText.java63
1 files changed, 41 insertions, 22 deletions
diff --git a/server/src/org/jsoup/examples/HtmlToPlainText.java b/server/src/org/jsoup/examples/HtmlToPlainText.java
index 8f563e9608..53e485be34 100644
--- a/server/src/org/jsoup/examples/HtmlToPlainText.java
+++ b/server/src/org/jsoup/examples/HtmlToPlainText.java
@@ -1,5 +1,7 @@
package org.jsoup.examples;
+import java.io.IOException;
+
import org.jsoup.Jsoup;
import org.jsoup.helper.StringUtil;
import org.jsoup.helper.Validate;
@@ -10,15 +12,15 @@ import org.jsoup.nodes.TextNode;
import org.jsoup.select.NodeTraversor;
import org.jsoup.select.NodeVisitor;
-import java.io.IOException;
-
/**
- * HTML to plain-text. This example program demonstrates the use of jsoup to convert HTML input to lightly-formatted
- * plain-text. That is divergent from the general goal of jsoup's .text() methods, which is to get clean data from a
- * scrape.
+ * HTML to plain-text. This example program demonstrates the use of jsoup to
+ * convert HTML input to lightly-formatted plain-text. That is divergent from
+ * the general goal of jsoup's .text() methods, which is to get clean data from
+ * a scrape.
* <p/>
- * Note that this is a fairly simplistic formatter -- for real world use you'll want to embrace and extend.
- *
+ * Note that this is a fairly simplistic formatter -- for real world use you'll
+ * want to embrace and extend.
+ *
* @author Jonathan Hedley, jonathan@hedley.net
*/
public class HtmlToPlainText {
@@ -36,13 +38,16 @@ public class HtmlToPlainText {
/**
* Format an Element to plain-text
- * @param element the root element to format
+ *
+ * @param element
+ * the root element to format
* @return formatted text
*/
public String getPlainText(Element element) {
FormattingVisitor formatter = new FormattingVisitor();
NodeTraversor traversor = new NodeTraversor(formatter);
- traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node
+ traversor.traverse(element); // walk the DOM, and call .head() and
+ // .tail() for each node
return formatter.toString();
}
@@ -51,44 +56,57 @@ public class HtmlToPlainText {
private class FormattingVisitor implements NodeVisitor {
private static final int maxWidth = 80;
private int width = 0;
- private StringBuilder accum = new StringBuilder(); // holds the accumulated text
+ private StringBuilder accum = new StringBuilder(); // holds the
+ // accumulated text
// hit when the node is first seen
+ @Override
public void head(Node node, int depth) {
String name = node.nodeName();
- if (node instanceof TextNode)
- append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
- else if (name.equals("li"))
+ if (node instanceof TextNode) {
+ append(((TextNode) node).text()); // TextNodes carry all
+ // user-readable text in the
+ // DOM.
+ } else if (name.equals("li")) {
append("\n * ");
+ }
}
// hit when all of the node's children (if any) have been visited
+ @Override
public void tail(Node node, int depth) {
String name = node.nodeName();
- if (name.equals("br"))
+ if (name.equals("br")) {
append("\n");
- else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5"))
+ } else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5")) {
append("\n\n");
- else if (name.equals("a"))
+ } else if (name.equals("a")) {
append(String.format(" <%s>", node.absUrl("href")));
+ }
}
// appends text to the string builder with a simple word wrap method
private void append(String text) {
- if (text.startsWith("\n"))
- width = 0; // reset counter if starts with a newline. only from formats above, not in natural text
- if (text.equals(" ") &&
- (accum.length() == 0 || StringUtil.in(accum.substring(accum.length() - 1), " ", "\n")))
+ if (text.startsWith("\n")) {
+ width = 0; // reset counter if starts with a newline. only from
+ // formats above, not in natural text
+ }
+ if (text.equals(" ")
+ && (accum.length() == 0 || StringUtil.in(
+ accum.substring(accum.length() - 1), " ", "\n"))) {
return; // don't accumulate long runs of empty spaces
+ }
if (text.length() + width > maxWidth) { // won't fit, needs to wrap
String words[] = text.split("\\s+");
for (int i = 0; i < words.length; i++) {
String word = words[i];
boolean last = i == words.length - 1;
- if (!last) // insert a space if not the last word
+ if (!last) {
word = word + " ";
- if (word.length() + width > maxWidth) { // wrap and reset counter
+ }
+ if (word.length() + width > maxWidth) { // wrap and reset
+ // counter
accum.append("\n").append(word);
width = word.length();
} else {
@@ -102,6 +120,7 @@ public class HtmlToPlainText {
}
}
+ @Override
public String toString() {
return accum.toString();
}