tedkulp/Sonarr
1
0
Fork 0
mirror of https://github.com/Sonarr/Sonarr.git synced 2026-04-20 21:54:58 -04:00
Code Issues Projects Releases Wiki Activity

Language parsing improvements and more languages

Browse Source 
Fixed: Parsing of multiple languages
New: Add Romanian, Latvian, Persian, Catalan, Croatian, Serbian, Bosnian, Estonian, Tamil, Indonesian, Macedonian, Slovenian languages
New: Handle some ISO 639-2/B language codes

Closes #5112
Closes #5440
Closes #5494
This commit is contained in:
Mark McDowall
2023-04-03 20:00:52 -07:00
parent f4130d96e5
commit 2020e074db
5 changed files with 237 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/NzbDrone.Core/Parser/LanguageParser.cs
+78 -60
View File
@@ -19,7 +19,7 @@ namespace NzbDrone.Core.Parser
new RegexReplace(@".*?[_. ](S\d{2}(?:E\d{2,4})*[_. ].*)", "$1", RegexOptions.Compiled | RegexOptions.IgnoreCase)
};
private static readonly Regex LanguageRegex = new Regex(@"(?:\W|_)(?<italian>\b(?:ita|italian)\b)|(?<german>german\b|videomann|ger[. ]dub)|(?<flemish>flemish)|(?<greek>greek)|(?<french>(?:\W|_)(?:FR|VF|VF2|VFF|VFQ|TRUEFRENCH)(?:\W|_))|(?<russian>\brus\b)|(?<hungarian>\b(?:HUNDUB|HUN)\b)|(?<hebrew>\bHebDub\b)|(?<polish>\b(?:PL\W?DUB|DUB\W?PL|LEK\W?PL|PL\W?LEK)\b)|(?<chinese>\[(?:CH[ST]|BIG5|GB)\]|简|繁|字幕)|(?<bulgarian>\bbgaudio\b)|(?<spanish>\b(?:español|castellano)\b)|(?<ukrainian>\b(?:ukr)\b)|(?<thai>\b(?:THAI)\b)",
private static readonly Regex LanguageRegex = new Regex(@"(?:\W|_)(?<english>\b(?:ing|eng)\b)|(?<italian>\b(?:ita|italian)\b)|(?<german>german\b|videomann|ger[. ]dub)|(?<flemish>flemish)|(?<greek>greek)|(?<french>(?:\W|_)(?:FR|VF|VF2|VFF|VFQ|TRUEFRENCH)(?:\W|_))|(?<russian>\brus\b)|(?<hungarian>\b(?:HUNDUB|HUN)\b)|(?<hebrew>\bHebDub\b)|(?<polish>\b(?:PL\W?DUB|DUB\W?PL|LEK\W?PL|PL\W?LEK)\b)|(?<chinese>\[(?:CH[ST]|BIG5|GB)\]|简|繁|字幕)|(?<bulgarian>\bbgaudio\b)|(?<spanish>\b(?:español|castellano|esp|spa(?!\(Latino\)))\b)|(?<ukrainian>\b(?:ukr)\b)|(?<thai>\b(?:THAI)\b)|(?<romainian>\b(?:RoDubbed|ROMANIAN)\b)|(?<catalan>[-,. ]cat[. ](?:DD|subs)|\b(?:catalan|catalán)\b)",
RegexOptions.IgnoreCase | RegexOptions.Compiled);
private static readonly Regex CaseSensitiveLanguageRegex = new Regex(@"(?:(?i)(?<!SUB[\W|_|^]))(?:(?<lithuanian>\bLT\b)|(?<czech>\bCZ\b)|(?<polish>\bPL\b)|(?<bulgarian>\bBG\b)|(?<slovak>\bSK\b))(?:(?i)(?![\W|_|^]SUB))",
@@ -278,81 +278,99 @@ namespace NzbDrone.Core.Parser
}
// Case insensitive
var match = LanguageRegex.Match(title);
var matches = LanguageRegex.Matches(title);
if (match.Groups["italian"].Captures.Cast<Capture>().Any())
foreach (Match match in matches)
{
languages.Add(Language.Italian);
}
if (match.Groups["english"].Success)
{
languages.Add(Language.English);
}
if (match.Groups["german"].Captures.Cast<Capture>().Any())
{
languages.Add(Language.German);
}
if (match.Groups["italian"].Captures.Cast<Capture>().Any())
{
languages.Add(Language.Italian);
}
if (match.Groups["flemish"].Captures.Cast<Capture>().Any())
{
languages.Add(Language.Flemish);
}
if (match.Groups["german"].Captures.Cast<Capture>().Any())
{
languages.Add(Language.German);
}
if (match.Groups["greek"].Captures.Cast<Capture>().Any())
{
languages.Add(Language.Greek);
}
if (match.Groups["flemish"].Captures.Cast<Capture>().Any())
{
languages.Add(Language.Flemish);
}
if (match.Groups["french"].Success)
{
languages.Add(Language.French);
}
if (match.Groups["greek"].Captures.Cast<Capture>().Any())
{
languages.Add(Language.Greek);
}
if (match.Groups["russian"].Success)
{
languages.Add(Language.Russian);
}
if (match.Groups["french"].Success)
{
languages.Add(Language.French);
}
if (match.Groups["dutch"].Success)
{
languages.Add(Language.Dutch);
}
if (match.Groups["russian"].Success)
{
languages.Add(Language.Russian);
}
if (match.Groups["hungarian"].Success)
{
languages.Add(Language.Hungarian);
}
if (match.Groups["dutch"].Success)
{
languages.Add(Language.Dutch);
}
if (match.Groups["hebrew"].Success)
{
languages.Add(Language.Hebrew);
}
if (match.Groups["hungarian"].Success)
{
languages.Add(Language.Hungarian);
}
if (match.Groups["polish"].Success)
{
languages.Add(Language.Polish);
}
if (match.Groups["hebrew"].Success)
{
languages.Add(Language.Hebrew);
}
if (match.Groups["chinese"].Success)
{
languages.Add(Language.Chinese);
}
if (match.Groups["polish"].Success)
{
languages.Add(Language.Polish);
}
if (match.Groups["bulgarian"].Success)
{
languages.Add(Language.Bulgarian);
}
if (match.Groups["chinese"].Success)
{
languages.Add(Language.Chinese);
}
if (match.Groups["ukrainian"].Success)
{
languages.Add(Language.Ukrainian);
}
if (match.Groups["bulgarian"].Success)
{
languages.Add(Language.Bulgarian);
}
if (match.Groups["spanish"].Success)
{
languages.Add(Language.Spanish);
}
if (match.Groups["ukrainian"].Success)
{
languages.Add(Language.Ukrainian);
}
if (match.Groups["thai"].Success)
{
languages.Add(Language.Thai);
if (match.Groups["spanish"].Success)
{
languages.Add(Language.Spanish);
}
if (match.Groups["thai"].Success)
{
languages.Add(Language.Thai);
}
if (match.Groups["romainian"].Success)
{
languages.Add(Language.Romanian);
}
if (match.Groups["catalan"].Success)
{
languages.Add(Language.Catalan);
}
}
return languages;