From 78d72d6ab33830d41bc1bc1daca3903d23c9a4a4 Mon Sep 17 00:00:00 2001
From: "helgeu@urholm.no" <helge@urholm.no>
Date: Mon, 4 Jun 2018 18:44:46 +0200
Subject: [PATCH 1/3] Went through:

https://raw.githubusercontent.com/ecrmnn/norwegian-stop-words/master/dist/stop-words.txt
https://raw.githubusercontent.com/crodas/TextRank/master/lib/TextRank/Stopword/norwegian-stopwords.txt
https://raw.githubusercontent.com/Alir3z4/stop-words/master/norwegian.txt
https://raw.githubusercontent.com/helgeu/machinelearning/master/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt
http://snowball.tartarus.org/algorithms/norwegian/stop.txt

to collect and correct the Norwegian stopwords.
---
 .../Text/StopWords/Norwegian_Bokmal.txt       | Bin 1392 -> 2000 bytes
 1 file changed, 0 insertions(+), 0 deletions(-)

diff --git a/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt b/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt
index 21ab890d7850dcdf127d5b8f5e9815cdcf010462..00fc30a26f1f1f1d6cf982efea1970ad82dbf202 100644
GIT binary patch
literal 2000
zcmZ9NTdvzM3`F%^po_dgUQS{=uoDA!!R{LJ)t1M@k=(*SG^EJkLzMF8_g8tucPc;2
zkMdQ9ax7Dorg8|}g-*M#T$gP<guQLCyTm7+LuCYYX$_io_*KMrC}Zf2r(h-8A$0F@
zuZ(MCA@*ZhG@01=py?|bc4(-+r_2FcXKy@L4`qX%EFHIt{wPjY=J=Z4wHza7EKb=~
z)q6@mR{03cl^gk5me_3`iq$mANf{}Ia+Ak7y7-8Gu>)?}Df*%_kbW+o+ShZ~so&?a
zrthcvg2)lhOSx^V^u#jzmd2ctOY&Tkm-V=v3|>g8OGq6DE8lDI4e|XiD~fkdk(Joo
zoon>nyi0g%mwsv<_PqsnTd&O8<i^1Xo5kJ46U+oQOEj(H>U0+!_Utk>+zfdj?a{w_
zdEc^vTX<=*?=|8*GEhzTTC<R6>k+oTiD05r3HML)A*Aa2u(;<LgO!_*S^CIBZvaSa
zLQEsvNW3G?4cSZ}^%AYl8RW_8b2?e=19E;{#Bh|cqVKxDW(I5Q$%pw_k_#T?4pM)I
z$kUb}MIFlb#x&#vvnty$Yi6Bu*OiXt86Q0uV^4LCyPN!sT>QE{w-a->pUK1>a)r}&
zMz8o)m*?>Ax9$=FX~+)n`q+lv>rI}sLRQ@Z5O-EJBJGj7fYzr0b~ba|`A={wHZ$1p
zJFx#Z=0Kh;@O#JLKF!-~aPDG5uTv#*>k$&SvvIHKu}0>~9SfbQY+)4QKgst_8nN@g
zh83@bUVBN(fPCE{UJsqRkSvUqJ@1P6^kVycmDFrFcT1W)y)?uYa+OHU)^oR%Uy+L$
Pz|N+<yi1&r^=tVHz^^c&

delta 131
zcmcb>|AA|Q9)B4FF9R1t5<@COIuNE#tk+~tVMv^KS9LNUqtIkMMv2Kmj0uxZG47kZ
zfk|re6(*g@0?ZMU%a}!&vl$X6?`IC3EXSfZIfg}tF>mr_7GuWD$?U9Kf#h9Q@yT3l
hT$3%>OeVLnsZ8F+mND6aU1D+;yV>L&>=G;>TLH=ZB{Tp4


From 109c3e6d1f1615bbbb761b2a1dd698df6665e1c0 Mon Sep 17 00:00:00 2001
From: "helgeu@urholm.no" <helge@urholm.no>
Date: Mon, 4 Jun 2018 19:05:46 +0200
Subject: [PATCH 2/3] 2 more words nynorsk

---
 .../Text/StopWords/Norwegian_Bokmal.txt       | Bin 2000 -> 1974 bytes
 1 file changed, 0 insertions(+), 0 deletions(-)

diff --git a/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt b/src/Microsoft.ML.Transforms/Text/StopWords/Norwegian_Bokmal.txt
index 00fc30a26f1f1f1d6cf982efea1970ad82dbf202..57c93978abd805f0b6abccb98b1cf207c05da63c 100644
GIT binary patch
delta 11
Scmcb>zm0!G0Q=-D_A~$+Km-;5

delta 31
lcmdnSe}R8P0K0H1LlHwN11|#?Lm7}RVkluqo$Se;3jlz_2Z#Uw


From fb1f0de199a69f088737879f084f79b4f82f0bd3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Helge=20Ren=C3=A9=20Urholm?= <helge@urholm.no>
Date: Thu, 14 Jun 2018 08:10:44 +0200
Subject: [PATCH 3/3] Reverted to using two files for stopwords, and made
 changes according to @TomFinley

---
 .../Microsoft.ML.Transforms.csproj                 |  1 +
 .../Text/StopWordsRemoverTransform.cs              | 14 +++++++++++---
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/src/Microsoft.ML.Transforms/Microsoft.ML.Transforms.csproj b/src/Microsoft.ML.Transforms/Microsoft.ML.Transforms.csproj
index 8aa272922c..4aebfb6b91 100644
--- a/src/Microsoft.ML.Transforms/Microsoft.ML.Transforms.csproj
+++ b/src/Microsoft.ML.Transforms/Microsoft.ML.Transforms.csproj
@@ -4,6 +4,7 @@
     <TargetFramework>netstandard2.0</TargetFramework>
     <IncludeInPackage>Microsoft.ML</IncludeInPackage>
     <DefineConstants>CORECLR</DefineConstants>
+    <BaseIntermediateOutputPath>..\..\bin\obj\AnyCPU.Debug\Microsoft.ML.Transforms</BaseIntermediateOutputPath>
   </PropertyGroup>
 
   <ItemGroup>
diff --git a/src/Microsoft.ML.Transforms/Text/StopWordsRemoverTransform.cs b/src/Microsoft.ML.Transforms/Text/StopWordsRemoverTransform.cs
index 96bf44b4c2..4ce69cf7db 100644
--- a/src/Microsoft.ML.Transforms/Text/StopWordsRemoverTransform.cs
+++ b/src/Microsoft.ML.Transforms/Text/StopWordsRemoverTransform.cs
@@ -90,7 +90,10 @@ public enum Language
             Polish = 12,
             Czech = 13,
             Arabic = 14,
-            Japanese = 15
+            Japanese = 15,
+
+            [HideEnumValue]
+            Norwegian_Bokmal_v1 = 256
         }
 
         public sealed class Column : OneToOneColumn
@@ -198,6 +201,11 @@ public ColInfoEx(ModelLoadContext ctx, ISchema input)
                 // int: the id of languages column name
                 Lang = (Language)ctx.Reader.ReadInt32();
                 Contracts.CheckDecode(Enum.IsDefined(typeof(Language), Lang));
+                if(Lang == Language.Norwegian_Bokmal 
+                   && ctx.Header.ModelVerWritten == 0x00010001)
+                {
+                    Lang = Language.Norwegian_Bokmal_v1;
+                }
                 _langsColName = ctx.LoadStringOrNull();
                 if (_langsColName != null)
                 {
@@ -229,8 +237,8 @@ private static VersionInfo GetVersionInfo()
         {
             return new VersionInfo(
                 modelSignature: "STOPWRDR",
-                verWrittenCur: 0x00010001, // Initial
-                verReadableCur: 0x00010001,
+                verWrittenCur: 0x00010002, // Initial
+                verReadableCur: 0x00010002,
                 verWeCanReadBack: 0x00010001,
                 loaderSignature: LoaderSignature);
         }