X-Git-Url: https://git.pterodactylus.net/?a=blobdiff_plain;ds=sidebyside;f=src%2Fmain%2Fjava%2Fnet%2Fpterodactylus%2Frhynodge%2Ffilters%2FComicSiteFilter.java;h=19286a6c3b2d0990046f551dcb91d67e5eb7dc4b;hb=cf2f4441705f9a5941022fb0837d08c95a1d0633;hp=fb01349e683369e1e0524e88a703ba6cc05a3645;hpb=a4dfb17e4e1d00440a049cb1063e1b1509216739;p=rhynodge.git

diff --git a/src/main/java/net/pterodactylus/rhynodge/filters/ComicSiteFilter.java b/src/main/java/net/pterodactylus/rhynodge/filters/ComicSiteFilter.java
index fb01349..19286a6 100644
--- a/src/main/java/net/pterodactylus/rhynodge/filters/ComicSiteFilter.java
+++ b/src/main/java/net/pterodactylus/rhynodge/filters/ComicSiteFilter.java
@@ -17,17 +17,22 @@
 
 package net.pterodactylus.rhynodge.filters;
 
-import static com.google.common.base.Preconditions.*;
+import static com.google.common.base.Preconditions.checkArgument;
 
+import java.net.URI;
+import java.net.URISyntaxException;
 import java.util.List;
 
 import net.pterodactylus.rhynodge.Filter;
 import net.pterodactylus.rhynodge.State;
 import net.pterodactylus.rhynodge.states.ComicState;
 import net.pterodactylus.rhynodge.states.ComicState.Comic;
+import net.pterodactylus.rhynodge.states.ComicState.Strip;
+import net.pterodactylus.rhynodge.states.FailedState;
 import net.pterodactylus.rhynodge.states.HtmlState;
 
 import com.google.common.base.Optional;
+import org.jetbrains.annotations.NotNull;
 import org.jsoup.nodes.Document;
 
 /**
@@ -38,26 +43,39 @@ import org.jsoup.nodes.Document;
  */
 public abstract class ComicSiteFilter implements Filter {
 
+	@NotNull
 	@Override
-	public State filter(State state) {
+	public State filter(@NotNull State state) {
 		checkArgument(state instanceof HtmlState, "state must be an HTML state");
 
 		/* initialize states: */
 		HtmlState htmlState = (HtmlState) state;
-		ComicState comicState = new ComicState();
 
 		/* extract comics. */
 		Optional<String> title = extractTitle(htmlState.document());
 		List<String> imageUrls = extractImageUrls(htmlState.document());
+		List<String> imageComments = extractImageComments(htmlState.document());
 
 		/* store comic, if found, into state. */
-		if (title.isPresent() && !imageUrls.isEmpty()) {
-			Comic comic = new Comic(title.get());
-			for (String imageUrl : imageUrls) {
-				comic.addImageUrl(imageUrl);
+		if (!title.isPresent() || imageUrls.isEmpty()) {
+			return new FailedState();
+		}
+
+		ComicState comicState = new ComicState();
+		Comic comic = new Comic(title.get());
+		int imageCounter = 0;
+		for (String imageUrl : imageUrls) {
+			String imageComment = (imageCounter < imageComments.size()) ? imageComments.get(imageCounter) : "";
+			try {
+				URI stripUri = new URI(htmlState.uri()).resolve(imageUrl.replaceAll(" ", "%20"));
+				Strip strip = new Strip(stripUri.toString(), imageComment);
+				imageCounter++;
+				comic.add(strip);
+			} catch (URISyntaxException use1) {
+				throw new IllegalStateException(String.format("Could not resolve image URL “%s” against base URL “%s”.", imageUrl, htmlState.uri()), use1);
 			}
-			comicState.add(comic);
 		}
+		comicState.add(comic);
 
 		return comicState;
 	}
@@ -86,4 +104,16 @@ public abstract class ComicSiteFilter implements Filter {
 	 */
 	protected abstract List<String> extractImageUrls(Document document);
 
+	/**
+	 * Extracts the image comments from the given document. The elements of this
+	 * last and of the list returned by {@link #extractImageUrls(org.jsoup.nodes.Document)}
+	 * are paired up and added as {@link Strip}s. If the list returned by this
+	 * method has less elements, an empty string is used for the remaining images.
+	 *
+	 * @param document
+	 * 		The document to extract the image comments from
+	 * @return The extracted image comments
+	 */
+	protected abstract List<String> extractImageComments(Document document);
+
 }