Made CleanStringParser go through regexps only once

This commit is contained in:
sushilicious 2021-08-04 23:25:54 -07:00
parent 7fdef4b82b
commit b2a10609af
2 changed files with 9 additions and 28 deletions

View File

@ -139,9 +139,9 @@ namespace Emby.Naming.Common
{
@"^\s*(?<cleaned>.+?)[ _\,\.\(\)\[\]\-](3d|sbs|tab|hsbs|htab|mvc|HDR|HDC|UHD|UltraHD|4k|ac3|dts|custom|dc|divx|divx5|dsr|dsrip|dutch|dvd|dvdrip|dvdscr|dvdscreener|screener|dvdivx|cam|fragment|fs|hdtv|hdrip|hdtvrip|internal|limited|multisubs|ntsc|ogg|ogm|pal|pdtv|proper|repack|rerip|retail|cd[1-9]|r3|r5|bd5|bd|se|svcd|swedish|german|read.nfo|nfofix|unrated|ws|telesync|ts|telecine|tc|brrip|bdrip|480p|480i|576p|576i|720p|720i|1080p|1080i|2160p|hrhd|hrhdtv|hddvd|bluray|blu-ray|x264|x265|h264|h265|xvid|xvidvd|xxx|www.www|AAC|DTS|\[.*\])([ _\,\.\(\)\[\]\-]|$)",
@"^(?<cleaned>.+?)(\[.*\])",
@"^\s*(?<cleaned>.+?)\WE\d+(-|~)E?\d+(\W|$)",
@"^\s*(?<cleaned>.+?)\WE[0-9]+(-|~)E?[0-9]+(\W|$)",
@"^\s*\[[^\]]+\](?!\.\w+$)\s*(?<cleaned>.+)",
@"^\s*(?<cleaned>.+?)\s+-\s+\d+\s*$"
@"^\s*(?<cleaned>.+?)\s+-\s+[0-9]+\s*$"
};
SubtitleFileExtensions = new[]

View File

@ -25,37 +25,18 @@ namespace Emby.Naming.Video
return false;
}
// Iteratively remove extra cruft until we're left with the string
// we want.
newName = ReadOnlySpan<char>.Empty;
const int maxTries = 100; // This is just a precautionary
// measure. Should not be neccesary.
var loopCounter = 0;
for (; loopCounter < maxTries; loopCounter++)
{
// Iteratively apply the regexps to clean the string.
bool cleaned = false;
var len = expressions.Count;
for (int i = 0; i < len; i++)
for (int i = 0; i < expressions.Count; i++)
{
if (TryClean(name, expressions[i], out newName))
{
cleaned = true;
name = newName.ToString();
break;
}
}
if (!cleaned)
{
break;
}
}
if (loopCounter > 0)
{
newName = name.AsSpan();
}
newName = cleaned ? name.AsSpan() : ReadOnlySpan<char>.Empty;
return newName != ReadOnlySpan<char>.Empty;
}