moparisthebest
/
filebot
mirror of https://github.com/mitb-archive/filebot
1
0
Fork 0
Code Issues Releases Wiki Activity

* use XZ Utils for packing online database files

This commit is contained in:
Reinhard Pointner 2013-08-10 07:56:11 +00:00
parent c0498185d1
commit 09d2dc24af
7 changed files with 118 additions and 153 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
BuildData.groovy
View File

@ -1,3 +1,4 @@
import org.tukaani.xz.*
// ------------------------------------------------------------------------- //
@ -37,14 +38,13 @@ println "Reviews: " + reviews.size()
// ------------------------------------------------------------------------- //
def series_out = new File("website/data/series.list.gz")
def movies_out = new File("website/data/movies.txt.gz")
def thetvdb_out = new File("website/data/thetvdb.txt.gz")
def anidb_out = new File("website/data/anidb.txt.gz")
def movies_out = new File("website/data/movies.txt")
def thetvdb_out = new File("website/data/thetvdb.txt")
def anidb_out = new File("website/data/anidb.txt")
def gz(file, lines) {
file.withOutputStream{ out ->
new java.util.zip.GZIPOutputStream(out).withWriter('UTF-8'){ writer ->
def pack(file, lines) {
new File(file.parentFile, file.name + '.xz').withOutputStream{ out ->
new XZOutputStream(out, new LZMA2Options(LZMA2Options.PRESET_DEFAULT)).withWriter('UTF-8'){ writer ->
lines.each{ writer.append(it).append('\n') }
}
}
@ -80,7 +80,7 @@ def movieSorter = new TreeMap(String.CASE_INSENSITIVE_ORDER)
movies.each{ movieSorter.put([it[1], it[2], it[0]].join('\t'), it) }
movies = movieSorter.values().collect{ it.join('\t') }
gz(movies_out, movies)
pack(movies_out, movies)
println "Movie Count: " + movies.size()
// sanity check
@ -146,7 +146,7 @@ thetvdb_index = thetvdb_index.sort(new Comparator() {
// join and sort
def thetvdb_txt = thetvdb_index.findResults{ [it[0].pad(6), it[1].trim()].join('\t') }
gz(thetvdb_out, thetvdb_txt)
pack(thetvdb_out, thetvdb_txt)
println "TheTVDB Index: " + thetvdb_txt.size()
// sanity check
@ -160,8 +160,8 @@ def anidb = new net.sourceforge.filebot.web.AnidbClient(null, 0).getAnimeTitles(
def anidb_index = anidb.findResults{ [it.getAnimeId(), it.getPrimaryTitle(), it.getEnglishTitle()] }
// join and sort
def anidb_txt = anidb_index.findResults{ [it[0].pad(5), it[1] ?: '', it[2] ?: ''].join('\t').replaceAll(/['`´‘’ʻ]+/, /'/) }.sort().unique()
gz(anidb_out, anidb_txt)
def anidb_txt = anidb_index.findResults{ [it[0].pad(5), it[1] ?: '', it[2] == null || it[2].equals(it[1]) ? '' : it[2]]*.replaceAll(/\s+/, ' ')*.trim().join('\t').replaceAll(/['`´‘’ʻ]+/, /'/) }.sort().unique()
pack(anidb_out, anidb_txt)
println "AniDB Index: " + anidb_txt.size()
// sanity check

5
build.xml
View File

@ -108,6 +108,10 @@
<zipfileset src="${dir.lib}/args4j.jar">
<include name="org/kohsuke/args4j/**" />
</zipfileset>
<zipfileset src="${dir.lib}/xz.jar">
<include name="org/tukaani/xz/**" />
</zipfileset>
<zipfileset src="${dir.lib}/ehcache.jar">
<include name="net/sf/ehcache/**" />
@ -632,6 +636,7 @@
<target name="upload-data-frs" depends="login">
<scp todir="${sf.user}:${sf.password}@${deploy.data.frs}" trust="yes" verbose="true" sftp="true">
<fileset dir="${dir.website}/data">
<include name="*.xz" />
<include name="*.gz" />
</fileset>
</scp>

7
installer/webstart/filebot.jnlp
View File

@ -27,13 +27,13 @@
<property name="application.warmup" value="false" />
<property name="unixfs" value="false" />
<property name="useNativeShell" value="false" />
<property name="useExtendedFileAttributes" value="false" />
<property name="useExtendedFileAttributes" value="true" />
<property name="java.net.useSystemProxies" value="true" />
<property name="sun.net.client.defaultConnectTimeout" value="10000" />
<property name="sun.net.client.defaultReadTimeout" value="60000" />
<java version="1.6+" />
<java version="1.7+" />
<property name="jnlp.packEnabled" value="true" />
<jar href="filebot.jar" download="eager" main="true" />
@ -50,11 +50,12 @@
<jar href="slf4j-jdk.jar" download="eager" />
<jar href="jgat-custom.jar" download="eager" />
<jar href="xmlrpc.jar" download="eager" />
<jar href="sublight-ws.jar" download="eager" />
<jar href="xz.jar" download="eager" />
<jar href="json-simple.jar" download="lazy" />
<jar href="json-io.jar" download="lazy" />
<jar href="junrar-custom.jar" download="lazy" />
<jar href="jacksum.jar" download="lazy" />
<jar href="jsoup.jar" download="lazy" />
<jar href="nekohtml.jar" download="lazy" part="scraper" />
<jar href="xercesImpl.jar" download="lazy" part="scraper" />
<jar href="mediainfo.jar" download="lazy" part="native" />

BIN
lib/xz.jar Normal file
View File

Binary file not shown.

226
source/net/sourceforge/filebot/media/ReleaseInfo.java
View File

@ -1,13 +1,13 @@
package net.sourceforge.filebot.media;
import static java.util.Arrays.*;
import static java.util.Collections.*;
import static java.util.ResourceBundle.*;
import static java.util.regex.Pattern.*;
import static net.sourceforge.filebot.similarity.Normalization.*;
import static net.sourceforge.tuned.StringUtilities.*;
import static java.util.Arrays.asList;
import static java.util.Collections.unmodifiableMap;
import static java.util.ResourceBundle.getBundle;
import static java.util.regex.Pattern.CASE_INSENSITIVE;
import static java.util.regex.Pattern.UNICODE_CASE;
import static java.util.regex.Pattern.compile;
import static net.sourceforge.filebot.similarity.Normalization.normalizePunctuation;
import static net.sourceforge.tuned.StringUtilities.join;
import java.io.File;
import java.io.FileFilter;
@ -31,7 +31,6 @@ import java.util.Set;
import java.util.TreeMap;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.zip.GZIPInputStream;
import net.sourceforge.filebot.web.AnidbSearchResult;
import net.sourceforge.filebot.web.CachedResource;
@ -39,57 +38,55 @@ import net.sourceforge.filebot.web.Movie;
import net.sourceforge.filebot.web.TheTVDBSearchResult;
import net.sourceforge.tuned.ByteBufferInputStream;
import org.tukaani.xz.XZInputStream;
public class ReleaseInfo {
public String getVideoSource(String... strings) {
// check parent and itself for group names
return matchLast(getVideoSourcePattern(), getBundle(getClass().getName()).getString("pattern.video.source").split("[|]"), strings);
}
public String getReleaseGroup(String... strings) throws IOException {
// check file and folder for release group names
String[] groups = releaseGroupResource.get();
// try case-sensitive match
String match = matchLast(getReleaseGroupPattern(true), groups, strings);
// try case-insensitive match as fallback
if (match == null) {
match = matchLast(getReleaseGroupPattern(false), groups, strings);
}
return match;
}
public Locale getLanguageSuffix(String name) {
// match locale identifier and lookup Locale object
Map<String, Locale> languages = getLanguageMap(Locale.ENGLISH, Locale.getDefault());
String lang = matchLast(getLanguageSuffixPattern(languages.keySet(), false), null, name);
if (lang == null)
return null;
return languages.get(lang);
}
protected String matchLast(Pattern pattern, String[] standardValues, CharSequence... sequence) {
String lastMatch = null;
// match last occurrence
for (CharSequence name : sequence) {
if (name == null)
continue;
Matcher matcher = pattern.matcher(name);
while (matcher.find()) {
lastMatch = matcher.group();
}
}
// prefer standard value over matched value
if (lastMatch != null && standardValues != null) {
for (String standard : standardValues) {
@ -98,24 +95,23 @@ public class ReleaseInfo {
}
}
}
return lastMatch;
}
// cached patterns
private final Map<Boolean, Pattern[]> stopwords = new HashMap<Boolean, Pattern[]>(2);
private final Map<Boolean, Pattern[]> blacklist = new HashMap<Boolean, Pattern[]>(2);
public List<String> cleanRelease(Collection<String> items, boolean strict) throws IOException {
Pattern[] stopwords;
Pattern[] blacklist;
// initialize cached patterns
synchronized (this.stopwords) {
stopwords = this.stopwords.get(strict);
blacklist = this.blacklist.get(strict);
if (stopwords == null || blacklist == null) {
Set<String> languages = getLanguageMap(Locale.ENGLISH, Locale.getDefault()).keySet();
Pattern clutterBracket = getClutterBracketPattern(strict);
@ -126,39 +122,37 @@ public class ReleaseInfo {
Pattern videoFormat = getVideoFormatPattern();
Pattern resolution = getResolutionPattern();
Pattern queryBlacklist = getBlacklistPattern();
stopwords = new Pattern[] { languageTag, videoSource, videoFormat, resolution, languageSuffix };
blacklist = new Pattern[] { queryBlacklist, languageTag, clutterBracket, releaseGroup, videoSource, videoFormat, resolution, languageSuffix };
// cache compiled patterns for common usage
this.stopwords.put(strict, stopwords);
this.blacklist.put(strict, blacklist);
}
}
List<String> output = new ArrayList<String>(items.size());
for (String it : items) {
it = strict ? clean(it, stopwords) : substringBefore(it, stopwords);
it = normalizePunctuation(clean(it, blacklist));
// ignore empty values
if (it.length() > 0) {
output.add(it);
}
}
return output;
}
public String clean(String item, Pattern... blacklisted) {
for (Pattern it : blacklisted) {
item = it.matcher(item).replaceAll("");
}
return item;
}
public String substringBefore(String item, Pattern... stopwords) {
for (Pattern it : stopwords) {
Matcher matcher = it.matcher(item);
@ -171,80 +165,67 @@ public class ReleaseInfo {
}
return item;
}
public Pattern getLanguageTagPattern(Collection<String> languages) {
// [en]
return compile("(?<=[-\\[{(])(" + join(quoteAll(languages), "|") + ")(?=\\p{Punct})", CASE_INSENSITIVE | UNICODE_CASE);
}
public Pattern getLanguageSuffixPattern(Collection<String> languages, boolean strict) {
// .en.srt
return compile("(?<=[.])(" + join(quoteAll(languages), "|") + ")(?=[._ ]*$)", (strict ? 0 : CASE_INSENSITIVE) | UNICODE_CASE);
}
public Pattern getResolutionPattern() {
// match screen resolutions 640x480, 1280x720, etc
return compile("(?<!\\p{Alnum})(\\d{4}|[6-9]\\d{2})x(\\d{4}|[4-9]\\d{2})(?!\\p{Alnum})");
}
public Pattern getVideoFormatPattern() {
// pattern matching any video source name
String pattern = getBundle(getClass().getName()).getString("pattern.video.format");
return compile("(?<!\\p{Alnum})(" + pattern + ")(?!\\p{Alnum})", CASE_INSENSITIVE);
}
public Pattern getVideoSourcePattern() {
// pattern matching any video source name
String pattern = getBundle(getClass().getName()).getString("pattern.video.source");
return compile("(?<!\\p{Alnum})(" + pattern + ")(?!\\p{Alnum})", CASE_INSENSITIVE);
}
public Pattern getClutterBracketPattern(boolean strict) {
// match patterns like [Action, Drama] or {ENG-XViD-MP3-DVDRiP} etc
String contentFilter = strict ? "[\\p{Space}\\p{Punct}&&[^\\[\\]]]" : "\\p{Alpha}";
return compile("(?:\\[([^\\[\\]]+?" + contentFilter + "[^\\[\\]]+?)\\])|(?:\\{([^\\{\\}]+?" + contentFilter + "[^\\{\\}]+?)\\})|(?:\\(([^\\(\\)]+?" + contentFilter + "[^\\(\\)]+?)\\))");
}
public Pattern getReleaseGroupPattern(boolean strict) throws IOException {
// pattern matching any release group name enclosed in separators
return compile("(?<!\\p{Alnum})(" + join(releaseGroupResource.get(), "|") + ")(?!\\p{Alnum})", strict ? 0 : CASE_INSENSITIVE | UNICODE_CASE);
}
public Pattern getBlacklistPattern() throws IOException {
// pattern matching any release group name enclosed in separators
return compile("(?<!\\p{Alnum})(" + join(queryBlacklistResource.get(), "|") + ")(?!\\p{Alnum})", CASE_INSENSITIVE | UNICODE_CASE);
}
public Pattern getExcludePattern() throws IOException {
// pattern matching any release group name enclosed in separators
return compile(join(excludeBlacklistResource.get(), "|"), CASE_INSENSITIVE | UNICODE_CASE);
}
public Movie[] getMovieList() throws IOException {
return movieListResource.get();
}
public TheTVDBSearchResult[] getTheTVDBIndex() throws IOException {
return tvdbIndexResource.get();
}
public AnidbSearchResult[] getAnidbIndex() throws IOException {
return anidbIndexResource.get();
}
public Map<Pattern, String> getSeriesDirectMappings() throws IOException {
Map<Pattern, String> mappings = new LinkedHashMap<Pattern, String>();
for (String line : seriesDirectMappingsResource.get()) {
@ -255,17 +236,15 @@ public class ReleaseInfo {
}
return mappings;
}
public FileFilter getDiskFolderFilter() {
return new FolderEntryFilter(compile(getBundle(getClass().getName()).getString("pattern.diskfolder.entry")));
}
public FileFilter getClutterFileFilter() throws IOException {
return new ClutterFileFilter(getExcludePattern(), 262144000); // only files smaller than 250 MB may be considered clutter
}
// fetch release group names online and try to update the data every other day
protected final CachedResource<String[]> releaseGroupResource = new PatternResource(getBundle(getClass().getName()).getString("url.release-groups"));
protected final CachedResource<String[]> queryBlacklistResource = new PatternResource(getBundle(getClass().getName()).getString("url.query-blacklist"));
@ -274,33 +253,29 @@ public class ReleaseInfo {
protected final CachedResource<String[]> seriesDirectMappingsResource = new PatternResource(getBundle(getClass().getName()).getString("url.series-mappings"));
protected final CachedResource<TheTVDBSearchResult[]> tvdbIndexResource = new TheTVDBIndexResource(getBundle(getClass().getName()).getString("url.thetvdb-index"));
protected final CachedResource<AnidbSearchResult[]> anidbIndexResource = new AnidbIndexResource(getBundle(getClass().getName()).getString("url.anidb-index"));
protected static class PatternResource extends CachedResource<String[]> {
public PatternResource(String resource) {
super(resource, String[].class, 24 * 60 * 60 * 1000); // 24h update interval
}
@Override
public String[] process(ByteBuffer data) {
return compile("\\n").split(Charset.forName("UTF-8").decode(data));
}
}
protected static class MovieResource extends CachedResource<Movie[]> {
public MovieResource(String resource) {
super(resource, Movie[].class, 7 * 24 * 60 * 60 * 1000); // check for updates once a week
}
@Override
public Movie[] process(ByteBuffer data) throws IOException {
Scanner scanner = new Scanner(new GZIPInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
Scanner scanner = new Scanner(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
List<Movie> movies = new ArrayList<Movie>();
while (scanner.hasNext()) {
int imdbid = scanner.nextInt();
@ -308,74 +283,63 @@ public class ReleaseInfo {
int year = scanner.nextInt();
movies.add(new Movie(name, year, imdbid, -1));
}
return movies.toArray(new Movie[0]);
}
}
protected static class TheTVDBIndexResource extends CachedResource<TheTVDBSearchResult[]> {
public TheTVDBIndexResource(String resource) {
super(resource, TheTVDBSearchResult[].class, 7 * 24 * 60 * 60 * 1000); // check for updates once a week
}
@Override
public TheTVDBSearchResult[] process(ByteBuffer data) throws IOException {
Scanner scanner = new Scanner(new GZIPInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
Scanner scanner = new Scanner(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
List<TheTVDBSearchResult> tvshows = new ArrayList<TheTVDBSearchResult>();
while (scanner.hasNext() && scanner.hasNextInt()) {
int id = scanner.nextInt();
String name = scanner.next().trim();
tvshows.add(new TheTVDBSearchResult(name, id));
}
return tvshows.toArray(new TheTVDBSearchResult[0]);
}
}
protected static class AnidbIndexResource extends CachedResource<AnidbSearchResult[]> {
public AnidbIndexResource(String resource) {
super(resource, AnidbSearchResult[].class, 7 * 24 * 60 * 60 * 1000); // check for updates once a week
}
@Override
public AnidbSearchResult[] process(ByteBuffer data) throws IOException {
Scanner scanner = new Scanner(new GZIPInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
Scanner scanner = new Scanner(new XZInputStream(new ByteBufferInputStream(data)), "UTF-8").useDelimiter("\t|\n");
List<AnidbSearchResult> anime = new ArrayList<AnidbSearchResult>();
while (scanner.hasNext() && scanner.hasNextInt()) {
int aid = scanner.nextInt();
String primaryTitle = scanner.next().trim();
String englishTitle = scanner.next().trim();
if (englishTitle.isEmpty() || englishTitle.equals(primaryTitle)) {
anime.add(new AnidbSearchResult(aid, primaryTitle, null));
} else {
anime.add(new AnidbSearchResult(aid, primaryTitle, englishTitle));
}
anime.add(new AnidbSearchResult(aid, primaryTitle, englishTitle.isEmpty() ? null : englishTitle));
}
return anime.toArray(new AnidbSearchResult[0]);
}
}
protected static class FolderEntryFilter implements FileFilter {
private final Pattern entryPattern;
public FolderEntryFilter(Pattern entryPattern) {
this.entryPattern = entryPattern;
}
@Override
public boolean accept(File dir) {
if (dir.isDirectory()) {
@ -388,43 +352,36 @@ public class ReleaseInfo {
return false;
}
}
public static class FileFolderNameFilter implements FileFilter {
private final Pattern namePattern;
public FileFolderNameFilter(Pattern namePattern) {
this.namePattern = namePattern;
}
@Override
public boolean accept(File file) {
return (namePattern.matcher(file.getName()).find() || (file.isFile() && namePattern.matcher(file.getParentFile().getName()).find()));
}
}
public static class ClutterFileFilter extends FileFolderNameFilter {
private long maxFileSize;
public ClutterFileFilter(Pattern namePattern, long maxFileSize) {
super(namePattern);
this.maxFileSize = maxFileSize;
}
@Override
public boolean accept(File file) {
return super.accept(file) && file.isFile() && file.length() < maxFileSize;
}
}
private Collection<String> quoteAll(Collection<String> strings) {
List<String> patterns = new ArrayList<String>(strings.size());
for (String it : strings) {
@ -432,23 +389,22 @@ public class ReleaseInfo {
}
return patterns;
}
private Map<String, Locale> getLanguageMap(Locale... supportedDisplayLocale) {
// use maximum strength collator by default
Collator collator = Collator.getInstance(Locale.ROOT);
collator.setDecomposition(Collator.FULL_DECOMPOSITION);
collator.setStrength(Collator.PRIMARY);
@SuppressWarnings("unchecked")
Comparator<String> order = (Comparator) collator;
Map<String, Locale> languageMap = languageMap = new TreeMap<String, Locale>(order);
for (String code : Locale.getISOLanguages()) {
Locale locale = new Locale(code);
languageMap.put(locale.getLanguage(), locale);
languageMap.put(locale.getISO3Language(), locale);
// map display language names for given locales
for (Locale language : new HashSet<Locale>(asList(supportedDisplayLocale))) {
// make sure language name is properly normalized so accents and whatever don't break the regex pattern syntax
@ -456,13 +412,13 @@ public class ReleaseInfo {
languageMap.put(languageName.toLowerCase(), locale);
}
}
// remove illegal tokens
languageMap.remove("");
languageMap.remove("II");
languageMap.remove("III");
languageMap.remove("hi"); // hi => hearing-impaired subtitles, NOT hindi language
Map<String, Locale> result = unmodifiableMap(languageMap);
return result;
}

6
source/net/sourceforge/filebot/media/ReleaseInfo.properties
View File

@ -17,13 +17,13 @@ url.exclude-blacklist: http://filebot.net/data/exclude-blacklist.txt
url.series-mappings: http://filebot.net/data/series-mappings.txt
# list of all movies (id, name, year)
url.movie-list: http://filebot.net/data/movies.txt.gz
url.movie-list: http://filebot.net/data/movies.txt.xz
# TheTVDB index
url.thetvdb-index: http://filebot.net/data/thetvdb.txt.gz
url.thetvdb-index: http://filebot.net/data/thetvdb.txt.xz
# AniDB index
url.anidb-index: http://filebot.net/data/anidb.txt.gz
url.anidb-index: http://filebot.net/data/anidb.txt.xz
# disk folder matcher
pattern.diskfolder.entry: BDMV|HVDVD_TS|VIDEO_TS|AUDIO_TS|VCD|movie.nfo

5
website/data/.htaccess
View File

@ -1,6 +1,9 @@
options +indexes
redirect 301 /data/movies.txt.xz http://sourceforge.net/projects/filebot/files/data/movies.txt.xz/download
redirect 301 /data/thetvdb.txt.xz http://sourceforge.net/projects/filebot/files/data/thetvdb.txt.xz/download
redirect 301 /data/anidb.txt.xz http://sourceforge.net/projects/filebot/files/data/anidb.txt.xz/download
redirect 301 /data/movies.txt.gz http://sourceforge.net/projects/filebot/files/data/movies.txt.gz/download
redirect 301 /data/series.list.gz http://sourceforge.net/projects/filebot/files/data/series.list.gz/download
redirect 301 /data/thetvdb.txt.gz http://sourceforge.net/projects/filebot/files/data/thetvdb.txt.gz/download
redirect 301 /data/anidb.txt.gz http://sourceforge.net/projects/filebot/files/data/anidb.txt.gz/download