AZEN-SGG/Kavita
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Parser optimization part1 (#1531)

Browse source 
* Optimize CleanTitle

* Optimize MangaEditionRegex

* Optimize special regexes

* Refactor manga|comic special parsing into simple tests

* Word bind the special regexps. Support additional "special" use cases.

* Updates to address PR comments

* CleanTitle benchmarking

* Use a smaller Comics Data set for benchmarking
This commit is contained in:
tjarls 2022-09-18 19:26:17 +01:00 • committed by GitHub
parent 0403f938b0
commit 28c868b46c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 269 additions and 203 deletions
Download patch file Download diff file Expand all files Collapse all files

52
API.Tests/Parser/ParserTest.cs
View file

@ -64,6 +64,10 @@ public class ParserTests
[InlineData("[Suihei Kiki]_Kasumi_Otoko_no_Ko_[Taruby]_v1.1", false, "Kasumi Otoko no Ko v1.1")]
[InlineData("Batman - Detective Comics - Rebirth Deluxe Edition Book 04 (2019) (digital) (Son of Ultron-Empire)", true, "Batman - Detective Comics - Rebirth Deluxe Edition")]
[InlineData("Something - Full Color Edition", false, "Something - Full Color Edition")]
[InlineData("Witchblade 089 (2005) (Bittertek-DCP) (Top Cow (Image Comics))", true, "Witchblade 089")]
[InlineData("(C99) Kami-sama Hiroimashita. (SSSS.GRIDMAN)", false, "Kami-sama Hiroimashita.")]
[InlineData("Dr. Ramune - Mysterious Disease Specialist v01 (2020) (Digital) (danke-Empire)", false, "Dr. Ramune - Mysterious Disease Specialist v01")]
[InlineData("Magic Knight Rayearth {Omnibus Edition}", false, "Magic Knight Rayearth {}")]
public void CleanTitleTest(string input, bool isComic, string expected)
{
Assert.Equal(expected, CleanTitle(input, isComic));
@ -236,4 +240,52 @@ public class ParserTests
{
Assert.Equal(expected, NormalizePath(inputPath));
}
[Theory]
[InlineData("The quick brown fox jumps over the lazy dog")]
[InlineData("(The quick brown fox jumps over the lazy dog)")]
[InlineData("()The quick brown fox jumps over the lazy dog")]
[InlineData("The ()quick brown fox jumps over the lazy dog")]
[InlineData("The (quick (brown)) fox jumps over the lazy dog")]
[InlineData("The (quick (brown) fox jumps over the lazy dog)")]
public void BalancedParenTestMatches(string input)
{
Assert.Matches($@"^{BalancedParen}$", input);
}
[Theory]
[InlineData("(The quick brown fox jumps over the lazy dog")]
[InlineData("The quick brown fox jumps over the lazy dog)")]
[InlineData("The )(quick brown fox jumps over the lazy dog")]
[InlineData("The quick (brown)) fox jumps over the lazy dog")]
[InlineData("The quick (brown) fox jumps over the lazy dog)")]
[InlineData("(The ))(quick (brown) fox jumps over the lazy dog")]
public void BalancedParenTestDoesNotMatch(string input)
{
Assert.DoesNotMatch($@"^{BalancedParen}$", input);
}
[Theory]
[InlineData("The quick brown fox jumps over the lazy dog")]
[InlineData("[The quick brown fox jumps over the lazy dog]")]
[InlineData("[]The quick brown fox jumps over the lazy dog")]
[InlineData("The []quick brown fox jumps over the lazy dog")]
[InlineData("The [quick [brown]] fox jumps over the lazy dog")]
[InlineData("The [quick [brown] fox jumps over the lazy dog]")]
public void BalancedBrackTestMatches(string input)
{
Assert.Matches($@"^{BalancedBrack}$", input);
}
[Theory]
[InlineData("[The quick brown fox jumps over the lazy dog")]
[InlineData("The quick brown fox jumps over the lazy dog]")]
[InlineData("The ][quick brown fox jumps over the lazy dog")]
[InlineData("The quick [brown]] fox jumps over the lazy dog")]
[InlineData("The quick [brown] fox jumps over the lazy dog]")]
[InlineData("[The ]][quick [brown] fox jumps over the lazy dog")]
public void BalancedBrackTestDoesNotMatch(string input)
{
Assert.DoesNotMatch($@"^{BalancedBrack}$", input);
}
}