From 264629cfa52b86030046fb33caaca64acbb4149d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?V=C3=A1clav=20Slav=C3=ADk?= Date: Sun, 24 Feb 2019 18:00:04 +0100 Subject: [PATCH] Fixed: Mis-classification of releases as being Czech (#3378) After the changes from PR #2948, the regex was too eager to match any substring contain "SK", such as in "MASK". Fix by requiring word separation around it, as was already the case with the "CZ" token. --- src/NzbDrone.Core.Test/ParserTests/LanguageParserFixture.cs | 1 + src/NzbDrone.Core/Parser/LanguageParser.cs | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/src/NzbDrone.Core.Test/ParserTests/LanguageParserFixture.cs b/src/NzbDrone.Core.Test/ParserTests/LanguageParserFixture.cs index ab5e0a79d..831a18137 100644 --- a/src/NzbDrone.Core.Test/ParserTests/LanguageParserFixture.cs +++ b/src/NzbDrone.Core.Test/ParserTests/LanguageParserFixture.cs @@ -49,6 +49,7 @@ namespace NzbDrone.Core.Test.ParserTests [TestCase("The Danish Girl 2015", Language.English)] [TestCase("Nocturnal Animals (2016) MULTi VFQ English [1080p] BluRay x264-PopHD", Language.English, Language.French)] [TestCase("Wonder.Woman.2017.720p.BluRay.DD5.1.x264-TayTO.CZ-FTU", Language.Czech)] + [TestCase("Fantastic.Beasts.The.Crimes.Of.Grindelwald.2018.2160p.WEBRip.x265.10bit.HDR.DD5.1-GASMASK", Language.English)] public void should_parse_language(string postTitle, params Language[] languages) { var movieInfo = Parser.Parser.ParseMovieTitle(postTitle, true); diff --git a/src/NzbDrone.Core/Parser/LanguageParser.cs b/src/NzbDrone.Core/Parser/LanguageParser.cs index 8c621c625..b863de208 100644 --- a/src/NzbDrone.Core/Parser/LanguageParser.cs +++ b/src/NzbDrone.Core/Parser/LanguageParser.cs @@ -13,7 +13,7 @@ namespace NzbDrone.Core.Parser { private static readonly Logger Logger = NzbDroneLogger.GetLogger(typeof(LanguageParser)); - private static readonly Regex LanguageRegex = new Regex(@"(?:\W|_)(?\b(?:ita|italian)\b)|(?german\b|videomann)|(?flemish)|(?greek)|(?(?:\W|_)(?:FR|VOSTFR|VO|VFF|VFQ|VF2|TRUEFRENCH)(?:\W|_))|(?\brus\b)|(?nl\W?subs?)|(?\b(?:HUNDUB|HUN)\b)|(?\bHebDub\b)|(?\bCZ|SK\b)", + private static readonly Regex LanguageRegex = new Regex(@"(?:\W|_)(?\b(?:ita|italian)\b)|(?german\b|videomann)|(?flemish)|(?greek)|(?(?:\W|_)(?:FR|VOSTFR|VO|VFF|VFQ|VF2|TRUEFRENCH)(?:\W|_))|(?\brus\b)|(?nl\W?subs?)|(?\b(?:HUNDUB|HUN)\b)|(?\bHebDub\b)|(?\b(?:CZ|SK)\b)", RegexOptions.IgnoreCase | RegexOptions.Compiled); private static readonly Regex SubtitleLanguageRegex = new Regex(".+?[-_. ](?[a-z]{2,3})$", RegexOptions.Compiled | RegexOptions.IgnoreCase);