Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Translit improvements #52

Merged
merged 9 commits into from
Jun 16, 2024
8 changes: 8 additions & 0 deletions Osmalyzer/Analyzers/Helpers/BoundaryHelper.cs
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,14 @@ public static OsmPolygon GetRigaPolygon(OsmMasterData osmData)
return _rigaPolygon;
}

[Pure]
public static OsmPolygon GetDaugavpilsPolygon(OsmMasterData osmData)
{
if (_rigaPolygon == null)
_rigaPolygon = GetAdminRelationPolygon(osmData, "6", "Daugavpils");

return _rigaPolygon;
}

[Pure]
private static OsmPolygon GetAdminRelationPolygon(OsmMasterData osmData, string level, string name)
Expand Down
6 changes: 5 additions & 1 deletion Osmalyzer/Analyzers/Helpers/FuzzyAddressMatcher.cs
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ namespace Osmalyzer;

public static class FuzzyAddressMatcher
{
// TODO: rewrite to use tsv file from data
private static readonly string[] _suffixes =
{
"iela",
Expand All @@ -18,7 +19,10 @@ public static class FuzzyAddressMatcher
"apvedceļš",
"laukums",
"prospekts",
"pārvads"
"pārvads",
"līnija",
"šķērslīnija",
"krastmala",
};
// Note: ImproperTranslationAnalyzer is doing Russian translations, so add value there if adding here

Expand Down
450 changes: 268 additions & 182 deletions Osmalyzer/Analyzers/Misc Analyzers/ImproperTranslationAnalyzer.cs

Large diffs are not rendered by default.

14 changes: 14 additions & 0 deletions Osmalyzer/Misc/Transliterator.cs
Original file line number Diff line number Diff line change
Expand Up @@ -82,10 +82,24 @@ public static string TransliterateFromLvToRu(string name)
translit += newC;
}

// Post processing
translit = translit.Replace("ьйо","ё");
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🤣


return translit;
}


[Pure]
public static string TransliterateFromLvToEn(string name)
{
string translit = name;
translit = Regex.Replace(translit, @"(?<!1)1\.\s*$", @"1st");
translit = Regex.Replace(translit, @"(?<!1)2\.\s*$", @"2nd");
translit = Regex.Replace(translit, @"(?<!1)3\.\s*$", @"3rd");
translit = Regex.Replace(translit, @"(\d)\.\s*$", @"$1th");
return translit;
}

private static string ReplaceWithPreserveCase(string str, string find, string replace)
{
string lowerFind = find.ToLower();
Expand Down
16 changes: 8 additions & 8 deletions Osmalyzer/Runner.cs
Original file line number Diff line number Diff line change
Expand Up @@ -65,16 +65,16 @@ public static void Run()
// new WikidataSynchronicityAnalyzer(), -- disabled
// new BarrierConnectionAnalyzer(),
// new BottleDepositPointsAnalyzer(),
new VenipakParcelLockerAnalyzer(),
new OmnivaParcelLockerAnalyzer(),
new ItellaParcelLockerAnalyzer(),
new DPDParcelLockerAnalyzer(),
new UnknownParcelLockerAnalyzer(),
new LatviaPostLockerAnalyzer(),
// new VenipakParcelLockerAnalyzer(),
// new OmnivaParcelLockerAnalyzer(),
// new ItellaParcelLockerAnalyzer(),
// new DPDParcelLockerAnalyzer(),
// new UnknownParcelLockerAnalyzer(),
// new LatviaPostLockerAnalyzer(),
// new LatviaPostMailBoxAnalyzer(),
// new ImproperTranslationAnalyzer(),
new ImproperTranslationAnalyzer(),
// new LidlShopAnalyzer(),
new UnisendParcelLockerAnalyzer(),
// new UnisendParcelLockerAnalyzer(),
// new SpellingAnalyzer()
};
#endif
Expand Down
6 changes: 5 additions & 1 deletion data/street name qualifiers.tsv
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,8 @@ aleja аллея alley
apvedceļš окружная дорога bypass
laukums площадь square
prospekts проспект avenue
pārvads переезд crossing
pārvads переезд crossing
līnija линия line
šķērslīnija поперечная линия cross line
krastmala набережная waterfront
stacija станция station
5 changes: 4 additions & 1 deletion data/street name suffixes.tsv
Original file line number Diff line number Diff line change
Expand Up @@ -13,4 +13,7 @@ aleja
līnija
šoseja
aplis
celiņš
celiņš
līnija
šķērslīnija
krastmala