mittens 0.2.0 → 0.3.0

data/vendor/snowball/README.rst

@@ -24,7 +24,7 @@ What is Stemming?
 
 Stemming maps different forms of the same word to a common "stem" - for
 example, the English stemmer maps *connection*, *connections*, *connective*,
-*connected*, and *connecting* to *connect*.  So a searching for *connected*
+*connected*, and *connecting* to *connect*.  So a search for *connected*
 would also find documents which only have the other forms.
 
 This stem form is often a word itself, but this is not always the case as this
@@ -35,3 +35,52 @@ stem), and over-stemming is more problematic than under-stemming so we tend not
 to stem in cases that are hard to resolve.  If you want to always reduce words
 to a root form and/or get a root form which is itself a word then Snowball's
 stemming algorithms likely aren't the right answer.
+
+Building Snowball
+=================
+
+GNU make is required to build Snowball.
+
+The build system is currently structured as two separate stages for many of the
+target languages.
+
+The first stage builds the Snowball compiler and runs it to create target
+language code (and it can also run tests on each stemmer).  The expectation is
+that you then create a "distribution" tarballs of this code with ``make dist``
+(or to create one for a specific target language, e.g.  ``make
+dist_libstemmer_c`` for C).  These tarballs are created in the ``dist/``
+subdirectory.
+
+To actually build the libstemmer library you then unpack and build the
+distribution tarball, e.g. for C::
+
+    tar xf dist/libstemmer_c-3.0.0.tar.gz
+    cd libstemmer_c-3.0.0
+    make
+
+Cross-compiling
+---------------
+
+If cross-compiling starting from the git repo, the Snowball compiler needs to
+be built with a native compiler then libstemmer with the cross-compiler.  For
+example::
+
+    make CC=cc dist_libstemmer_c
+    tar xf dist/libstemmer_c-3.0.0.tar.gz
+    cd libstemmer_c-3.0.0
+    make CC=riscv64-unknown-linux-gnu-gcc
+
+If you are cross-compiling to or from Microsoft Windows, you'll need to also
+work around an assumption in libstemmer's ``Makefile`` which sets ``EXEEXT``
+based on the OS you are building on::
+
+    ifeq ($(OS),Windows_NT)
+    EXEEXT=.exe
+    endif
+
+For example, if cross-compiling from Linux to Microsoft Windows, use something
+like this for the libstemmer build::
+
+    make CC=x86_64-w64-mingw32-gcc EXEEXT=.exe
+
+When going the other way, you'll need to use ``EXEEXT=``.

data/vendor/snowball/ada/src/stemmer.adb

@@ -38,6 +38,7 @@ package body Stemmer with SPARK_Mode is
                         Result   : out Boolean) is
    begin
       Context.P (1 .. Word'Length) := Word;
+      Context.Len := Word'Length;
       Context.C := 0;
       Context.L := Word'Length;
       Context.Lb := 0;
@@ -46,7 +47,7 @@ package body Stemmer with SPARK_Mode is
 
    function Get_Result (Context : in Context_Type'Class) return String is
    begin
-      return Context.P (1 .. Context.L);
+      return Context.P (1 .. Context.Len);
    end Get_Result;
 
    function Eq_S (Context : in Context_Type'Class;
@@ -73,17 +74,12 @@ package body Stemmer with SPARK_Mode is
       return S'Length;
    end Eq_S_Backward;
 
-   function Length (Context : in Context_Type'Class) return Natural is
-   begin
-      return Context.L - Context.Lb;
-   end Length;
-
    function Length_Utf8 (Context : in Context_Type'Class) return Natural is
       Count : Natural := 0;
       Pos   : Positive := 1;
       Val   : Byte;
    begin
-      while Pos <= Context.L loop
+      while Pos <= Context.Len loop
          Val := Character'Pos (Context.P (Pos));
          Pos := Pos + 1;
          if Val >= 16#C0# or Val < 16#80# then
@@ -93,6 +89,21 @@ package body Stemmer with SPARK_Mode is
       return Count;
    end Length_Utf8;
 
+   function Length_Utf8 (S : in String) return Natural is
+      Count : Natural := 0;
+      Pos   : Positive := 1;
+      Val   : Byte;
+   begin
+      while Pos <= S'Length loop
+         Val := Character'Pos (S (Pos));
+         Pos := Pos + 1;
+         if Val >= 16#C0# or Val < 16#80# then
+            Count := Count + 1;
+         end if;
+      end loop;
+      return Count;
+   end Length_Utf8;
+
    function Check_Among (Context : in Context_Type'Class;
                          Pos     : in Char_Index;
                          Shift   : in Natural;
@@ -464,7 +475,7 @@ package body Stemmer with SPARK_Mode is
       Ch    : Utf8_Type;
       Count : Natural;
    begin
-      if Context.C = 0 then
+      if Context.C <= Context.Lb then
          Result := -1;
          return;
       end if;
@@ -532,7 +543,7 @@ package body Stemmer with SPARK_Mode is
       Ch    : Utf8_Type;
       Count : Natural;
    begin
-      if Context.C = 0 then
+      if Context.C <= Context.Lb then
          Result := -1;
          return;
       end if;
@@ -566,16 +577,17 @@ package body Stemmer with SPARK_Mode is
    begin
       Adjustment := S'Length - (C_Ket - C_Bra);
       if Adjustment > 0 then
-         Context.P (C_Bra + S'Length + 1 .. Context.Lb + Adjustment + 1)
-           := Context.P (C_Ket + 1 .. Context.Lb + 1);
+         Context.P (C_Bra + S'Length + 1 .. Context.Len + Adjustment + 1)
+           := Context.P (C_Ket + 1 .. Context.Len + 1);
       end if;
       if S'Length > 0 then
          Context.P (C_Bra + 1 .. C_Bra + S'Length) := S;
       end if;
       if Adjustment < 0 then
-         Context.P (C_Bra + S'Length + 1 .. Context.L + Adjustment + 1)
-           := Context.P (C_Ket + 1 .. Context.L + 1);
+         Context.P (C_Bra + S'Length + 1 .. Context.Len + Adjustment + 1)
+           := Context.P (C_Ket + 1 .. Context.Len + 1);
       end if;
+      Context.Len := Context.Len + Adjustment;
       Context.L := Context.L + Adjustment;
       if Context.C >= C_Ket then
          Context.C := Context.C + Adjustment;

data/vendor/snowball/ada/src/stemmer.ads

@@ -138,10 +138,10 @@ private
                                 Value   : out Utf8_Type;
                                 Count   : out Natural);
 
-   function Length (Context : in Context_Type'Class) return Natural;
-
    function Length_Utf8 (Context : in Context_Type'Class) return Natural;
 
+   function Length_Utf8 (S : in String) return Natural;
+
    function Check_Among (Context : in Context_Type'Class;
                          Pos     : in Char_Index;
                          Shift   : in Natural;
@@ -181,19 +181,17 @@ private
                       S          : in String;
                       Adjustment : out Integer) with
      Global => null,
-     Pre => C_Bra >= Context.Lb and C_Ket >= C_Bra and C_Ket <= Context.L;
+     Pre => C_Ket >= C_Bra;
 
    procedure Slice_Del (Context : in out Context_Type'Class) with
      Global => null,
-     Pre => Context.Bra >= Context.Lb and Context.Ket >= Context.Bra
-     and Context.Ket <= Context.L;
+     Pre => Context.Ket >= Context.Bra;
 
    procedure Slice_From (Context : in out Context_Type'Class;
                          Text    : in String) with
      Global => null,
-     Pre => Context.Bra >= Context.Lb and Context.Ket >= Context.Bra
-     and Context.Ket <= Context.L
-     and Context.L - Context.Lb + Text'Length + Context.Ket - Context.Bra < Context.P'Length;
+     Pre => Context.Ket >= Context.Bra
+     and Context.Len - (Context.Ket - Context.Bra) + Text'Length < Context.P'Length;
 
    function Slice_To (Context : in Context_Type'Class) return String;
 
@@ -202,13 +200,15 @@ private
                      C_Ket   : in Char_Index;
                      S       : in String) with
      Global => null,
-     Pre => C_Bra >= Context.Lb and C_Ket >= C_Bra and C_Ket <= Context.L;
+     Pre => C_Ket >= C_Bra
+     and Context.Len - (C_Ket - C_Bra) + S'Length < Context.P'Length;
 
    --  The context indexes follow the C paradigm: they start at 0 for the first character.
    --  This is necessary because several algorithms rely on this when they compare the
    --  cursor position ('C') or setup some markers from the cursor.
    type Context_Type is abstract tagged record
       C   : Char_Index := 0;
+      Len : Char_Index := 0;
       L   : Char_Index := 0;
       Lb  : Char_Index := 0;
       Bra : Char_Index := 0;

data/vendor/snowball/ada/stemmer_config.gpr

@@ -12,7 +12,7 @@ abstract project Stemmer_Config is
 
    package Builder is
        case Mode is
-          when "debug" => 
+          when "debug" =>
              for Default_Switches ("Ada") use ("-g", "-j" & Processors);
           when others =>
              for Default_Switches ("Ada") use ("-g", "-O3", "-j" & Processors);
@@ -50,7 +50,7 @@ abstract project Stemmer_Config is
          when "debug" =>
             for Default_Switches ("Ada") use ("-E");
 
-	 when others =>
+         when others =>
             for Default_Switches ("Ada") use ("-E");
 
       end case;
@@ -69,13 +69,13 @@ abstract project Stemmer_Config is
 
          when "coverage" =>
             for Default_Switches ("ada") use ("-fprofile-arcs");
-	 
-	 when others =>
-	    null;
+
+         when others =>
+            null;
       end case;
 
-   end linker;        
- 
+   end linker;
+
    package Ide is
       for VCS_Kind use "git";
    end Ide;

data/vendor/snowball/algorithms/basque.sbl

@@ -59,13 +59,8 @@ backwardmode (
             ( RV delete )
             'garri' 'garria' 'tza'
             (R2 delete)
-            'atseden'
-            (<- 'atseden')
-            'arabera'
-            (<- 'arabera')
-            'baditu'
-            (<- 'baditu')
-
+            'atseden' 'arabera' 'baditu'
+            ( )
         )
     )
 
@@ -111,14 +106,8 @@ backwardmode (
             (<- 'tra')
             'minutuko'
             (<- 'minutu')
-            'zehar'
-            (<- 'zehar')
-            'geldi'
-            (<- 'geldi')
-            'igaro'
-            (<- 'igaro')
-            'aurka'
-            (<- 'aurka')
+            'zehar' 'geldi' 'igaro' 'aurka'
+            ( )
         )
     )
 
@@ -143,7 +132,3 @@ define stem as (
     )
 
 )
-
-/*
-    Note 1: additions of 21 Jul 2010
-*/

data/vendor/snowball/algorithms/catalan.sbl

@@ -19,7 +19,7 @@ stringescapes {}
 
 stringdef a'   '{U+00E1}'  // a-acute
 stringdef a`   '{U+00E0}'  // a-grave
-stringdef c,   '{U+00E7}'  // c-cedilla
+stringdef cc   '{U+00E7}'  // c-cedilla
 stringdef e'   '{U+00E9}'  // e-acute
 stringdef e`   '{U+00E8}'  // e-grave
 stringdef i'   '{U+00ED}'  // i-acute
@@ -90,7 +90,7 @@ backwardmode (
             'i{o'}' 'itat' 'itats' 'itzar' 'iva' 'ives' 'ivisme' 'ius'
             'fer' 'ment' 'amen' 'ament' 'aments' 'ments' 'ot' 'sfera' 'al' 'als' 'era' 'ana' 'iste'
             'aire' 'eria' 'esa' 'eses' 'esos' 'or' '{i'}cia' '{i'}cies' 'icis' 'ici' '{i'}ci' '{i'}cis'
-            '{a`}ria' '{a`}ries' 'alla' 'ci{o'}' 'cions' 'n{c,}a' 'nces' '{o'}' 'dor' 'all'
+            '{a`}ria' '{a`}ries' 'alla' 'ci{o'}' 'cions' 'n{cc}a' 'nces' '{o'}' 'dor' 'all'
             'il' '{i'}stic' 'enc' 'enca' '{i'}s' 'issa' 'issos' '{i'}ssem' '{i'}ssiu' 'issem' 'isseu' '{i'}sseu'
             '{o'}s' 'osa'  'dora' 'dores' 'dors' 'adura' 'ble' 'bles' '{i'}vol' '{i'}vola' 'd{i'}s' 'egar' 'ejar' 'ificar'
             'itar' 'ables' 'adors' 'idores' 'idors'
@@ -193,10 +193,3 @@ define stem as (
     )
     do cleaning
 )
-
-/*
-     First works 2010/07/19
-     First Grammatical Reviews: https://ca.wikipedia.org/wiki/Gram%C3%A0tica_del_catal%C3%A0
-     Suffix list: https://ca.wikipedia.org/wiki/Llista_de_sufixos
-     Irregular Verbs: https://ca.wikipedia.org/wiki/Flexi%C3%B3_verbal_del_catal%C3%A0
-*/

data/vendor/snowball/algorithms/danish.sbl

@@ -33,7 +33,7 @@ define mark_regions as (
     $p1 = limit
 
     test ( hop 3 setmark x )
-    goto v gopast non-v  setmark p1
+    gopast v  gopast non-v  setmark p1
     try ( $p1 < x  $p1 = x )
 )