Skip to content

Fix comment parsing #195

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.

Sign up for GitHub

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

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Fix comment parsing #195

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4406761
Update HNCommentsParser.java
kyleivey Jun 2, 2024
ed9f2a1
Update HNCommentsParser.java
kyleivey Jun 2, 2024
091e4fa
Update HNCommentsParser.java
kyleivey Jun 2, 2024
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
38 changes: 16 additions & 22 deletions app/src/main/java/com/manuelmaly/hn/parser/HNCommentsParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
import org.jsoup.select.Elements;

import java.util.ArrayList;
import java.util.Set;

public class HNCommentsParser extends BaseHTMLParser<HNPostComments> {

Expand Down Expand Up @@ -42,21 +43,12 @@ public HNPostComments parseDocument(Element doc) throws Exception {
if (mainRowElement == null)
continue;

// The not portion of this query is meant to remove the reply link
// from the text. As far as I can tell that is the only place
// where size=1 is used. If that turns out to not be the case then
// searching for u tags is also a pretty decent option - @jmaltz
Element mainCommentDiv = mainRowElement.select("div.comment > span").first();
Element mainCommentDiv = mainRowElement.select("div.commtext").first();
if (mainCommentDiv == null)
continue;

mainCommentDiv.select("div.reply").remove();

// Parse the class attribute to get the comment color
int commentColor = Color.rgb(0, 0, 0);
if (mainCommentDiv.attributes().hasKey("class")) {
commentColor = getCommentColor(mainCommentDiv.attributes().get("class"));
}
int commentColor = getCommentColor(mainCommentDiv.classNames());

// In order to eliminate whitespace at the end of multi-line comments,
// <p> tags are replaced with double <br/> tags.
Expand Down Expand Up @@ -123,27 +115,29 @@ private String getVoteUrl(Element voteElement) {
return null;
}

private int getCommentColor(String className) {
if ("c5a".equals(className)) {
private int getCommentColor(Set<String> classNames) {
if (classNames.contains("c00")) {
return Color.BLACK;
} else if (classNames.contains("c5a")) {
return Color.rgb(0x5A, 0x5A, 0x5A);
} else if ("c73".equals(className)) {
} else if (classNames.contains("c73")) {
return Color.rgb(0x73, 0x73, 0x73);
} else if ("c82".equals(className)) {
} else if (classNames.contains("c82")) {
return Color.rgb(0x82, 0x82, 0x82);
} else if ("c88".equals(className)) {
} else if (classNames.contains("c88")) {
return Color.rgb(0x88, 0x88, 0x88);
} else if ("c9c".equals(className)) {
} else if (classNames.contains("c9c")) {
return Color.rgb(0x9C, 0x9C, 0x9C);
} else if ("cae".equals(className)) {
} else if (classNames.contains("cae")) {
return Color.rgb(0xAE, 0xAE, 0xAE);
} else if ("cbe".equals(className)) {
} else if (classNames.contains("cbe")) {
return Color.rgb(0xBE, 0xBE, 0xBE);
} else if ("cce".equals(className)) {
} else if (classNames.contains("cce")) {
return Color.rgb(0xCE, 0xCE, 0xCE);
} else if ("cdd".equals(className)) {
} else if (classNames.contains("cdd")) {
return Color.rgb(0xDD, 0xDD, 0xDD);
} else {
return Color.rgb(0, 0, 0);
return Color.BLACK;
}
}
}