mirror of
https://github.com/booklore-app/booklore.git
synced 2025-12-23 14:20:48 -05:00
Fix: correctly assign main title and subtitle from <dc:title> elements (#1626)
This commit is contained in:
Aditya Chandel
@@ -18,10 +18,14 @@ import org.w3c.dom.NodeList;
|
||||
import javax.xml.XMLConstants;
|
||||
import javax.xml.parsers.DocumentBuilder;
|
||||
import javax.xml.parsers.DocumentBuilderFactory;
|
||||
import java.io.*;
|
||||
import java.io.File;
|
||||
import java.io.FileInputStream;
|
||||
import java.io.InputStream;
|
||||
import java.time.LocalDate;
|
||||
import java.time.OffsetDateTime;
|
||||
import java.util.HashMap;
|
||||
import java.util.HashSet;
|
||||
import java.util.Map;
|
||||
import java.util.Set;
|
||||
|
||||
@Slf4j
|
||||
@@ -55,6 +59,7 @@ public class EpubMetadataExtractor implements FileMetadataExtractor {
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
public BookMetadata extractMetadata(File epubFile) {
|
||||
try (ZipFile zip = new ZipFile(epubFile)) {
|
||||
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
|
||||
@@ -89,6 +94,10 @@ public class EpubMetadataExtractor implements FileMetadataExtractor {
|
||||
boolean seriesIndexFound = false;
|
||||
|
||||
NodeList children = metadata.getChildNodes();
|
||||
|
||||
Map<String, String> titlesById = new HashMap<>();
|
||||
Map<String, String> titleTypeById = new HashMap<>();
|
||||
|
||||
for (int i = 0; i < children.getLength(); i++) {
|
||||
if (!(children.item(i) instanceof Element el)) continue;
|
||||
|
||||
@@ -96,51 +105,29 @@ public class EpubMetadataExtractor implements FileMetadataExtractor {
|
||||
String text = el.getTextContent().trim();
|
||||
|
||||
switch (tag) {
|
||||
case "title" -> builderMeta.title(text);
|
||||
case "description" -> builderMeta.description(text);
|
||||
case "publisher" -> builderMeta.publisher(text);
|
||||
case "language" -> builderMeta.language(text);
|
||||
case "creator" -> authors.add(text);
|
||||
case "subject" -> categories.add(text);
|
||||
case "identifier" -> {
|
||||
String scheme = el.getAttributeNS("http://www.idpf.org/2007/opf", "scheme").toUpperCase();
|
||||
String value = text.toLowerCase().startsWith("isbn:") ? text.substring(5) : text;
|
||||
|
||||
if (!scheme.isEmpty()) {
|
||||
switch (scheme) {
|
||||
case "ISBN" -> {
|
||||
if (value.length() == 13) builderMeta.isbn13(value);
|
||||
else if (value.length() == 10) builderMeta.isbn10(value);
|
||||
}
|
||||
case "GOODREADS" -> builderMeta.goodreadsId(value);
|
||||
case "COMICVINE" -> builderMeta.comicvineId(value);
|
||||
case "GOOGLE" -> builderMeta.googleId(value);
|
||||
case "AMAZON" -> builderMeta.asin(value);
|
||||
case "HARDCOVER" -> builderMeta.hardcoverId(value);
|
||||
}
|
||||
case "title" -> {
|
||||
String id = el.getAttribute("id");
|
||||
if (StringUtils.isNotBlank(id)) {
|
||||
titlesById.put(id, text);
|
||||
} else {
|
||||
if (text.toLowerCase().startsWith("isbn:")) {
|
||||
if (value.length() == 13) builderMeta.isbn13(value);
|
||||
else if (value.length() == 10) builderMeta.isbn10(value);
|
||||
}
|
||||
builderMeta.title(text);
|
||||
}
|
||||
}
|
||||
case "date" -> {
|
||||
LocalDate parsed = parseDate(text);
|
||||
if (parsed != null) builderMeta.publishedDate(parsed);
|
||||
}
|
||||
case "meta" -> {
|
||||
String name = el.getAttribute("name").trim().toLowerCase();
|
||||
String prop = el.getAttribute("property").trim().toLowerCase();
|
||||
String prop = el.getAttribute("property").trim();
|
||||
String name = el.getAttribute("name").trim();
|
||||
String refines = el.getAttribute("refines").trim();
|
||||
String content = el.hasAttribute("content") ? el.getAttribute("content").trim() : text;
|
||||
if (StringUtils.isBlank(content)) continue;
|
||||
|
||||
if (!seriesFound && ("booklore:series".equals(prop) || "calibre:series".equals(name) || "calibre:series".equals(prop) || "belongs-to-collection".equals(prop))) {
|
||||
if ("title-type".equals(prop) && StringUtils.isNotBlank(refines)) {
|
||||
titleTypeById.put(refines.substring(1), content.toLowerCase());
|
||||
}
|
||||
|
||||
if (!seriesFound && ("booklore:series".equals(prop) || "calibre:series".equals(name) || "belongs-to-collection".equals(prop))) {
|
||||
builderMeta.seriesName(content);
|
||||
seriesFound = true;
|
||||
}
|
||||
|
||||
if (!seriesIndexFound && ("booklore:series_index".equals(prop) || "calibre:series_index".equals(name) || "calibre:series_index".equals(prop) || "group-position".equals(prop))) {
|
||||
if (!seriesIndexFound && ("booklore:series_index".equals(prop) || "calibre:series_index".equals(name) || "group-position".equals(prop))) {
|
||||
try {
|
||||
builderMeta.seriesNumber(Float.parseFloat(content));
|
||||
seriesIndexFound = true;
|
||||
@@ -180,14 +167,52 @@ public class EpubMetadataExtractor implements FileMetadataExtractor {
|
||||
case "booklore:page_count" -> safeParseInt(content, builderMeta::pageCount);
|
||||
}
|
||||
}
|
||||
case "creator" -> authors.add(text);
|
||||
case "subject" -> categories.add(text);
|
||||
case "publisher" -> builderMeta.publisher(text);
|
||||
case "language" -> builderMeta.language(text);
|
||||
case "identifier" -> {
|
||||
String scheme = el.getAttributeNS("http://www.idpf.org/2007/opf", "scheme").toUpperCase();
|
||||
String value = text.toLowerCase().startsWith("isbn:") ? text.substring(5) : text;
|
||||
|
||||
if (!scheme.isEmpty()) {
|
||||
switch (scheme) {
|
||||
case "ISBN" -> {
|
||||
if (value.length() == 13) builderMeta.isbn13(value);
|
||||
else if (value.length() == 10) builderMeta.isbn10(value);
|
||||
}
|
||||
case "GOODREADS" -> builderMeta.goodreadsId(value);
|
||||
case "COMICVINE" -> builderMeta.comicvineId(value);
|
||||
case "GOOGLE" -> builderMeta.googleId(value);
|
||||
case "AMAZON" -> builderMeta.asin(value);
|
||||
case "HARDCOVER" -> builderMeta.hardcoverId(value);
|
||||
}
|
||||
} else {
|
||||
if (text.toLowerCase().startsWith("isbn:")) {
|
||||
if (value.length() == 13) builderMeta.isbn13(value);
|
||||
else if (value.length() == 10) builderMeta.isbn10(value);
|
||||
}
|
||||
}
|
||||
}
|
||||
case "date" -> {
|
||||
LocalDate parsed = parseDate(text);
|
||||
if (parsed != null) builderMeta.publishedDate(parsed);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for (Map.Entry<String, String> entry : titlesById.entrySet()) {
|
||||
String id = entry.getKey();
|
||||
String value = entry.getValue();
|
||||
String type = titleTypeById.getOrDefault(id, "main");
|
||||
if ("main".equals(type)) builderMeta.title(value);
|
||||
else if ("subtitle".equals(type)) builderMeta.subtitle(value);
|
||||
}
|
||||
|
||||
if (builderMeta.build().getPublishedDate() == null) {
|
||||
for (int i = 0; i < children.getLength(); i++) {
|
||||
if (!(children.item(i) instanceof Element el)) continue;
|
||||
if (!"meta".equals(el.getLocalName())) continue;
|
||||
|
||||
String prop = el.getAttribute("property").trim().toLowerCase();
|
||||
String content = el.hasAttribute("content") ? el.getAttribute("content").trim() : el.getTextContent().trim();
|
||||
if ("dcterms:modified".equals(prop)) {
|
||||
@@ -204,7 +229,7 @@ public class EpubMetadataExtractor implements FileMetadataExtractor {
|
||||
builderMeta.categories(categories);
|
||||
|
||||
BookMetadata extractedMetadata = builderMeta.build();
|
||||
// Fallback to filename if no title found in EPUB metadata
|
||||
|
||||
if (StringUtils.isBlank(extractedMetadata.getTitle())) {
|
||||
builderMeta.title(FilenameUtils.getBaseName(epubFile.getName()));
|
||||
extractedMetadata = builderMeta.build();
|
||||
@@ -220,7 +245,6 @@ public class EpubMetadataExtractor implements FileMetadataExtractor {
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
private void safeParseInt(String value, java.util.function.IntConsumer setter) {
|
||||
try {
|
||||
setter.accept(Integer.parseInt(value));
|
||||
@@ -256,4 +280,4 @@ public class EpubMetadataExtractor implements FileMetadataExtractor {
|
||||
log.warn("Failed to parse date from string: {}", value);
|
||||
return null;
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user