Update snowball

Update to snowball tag v2.1.0.  Major changes are new stemmers for
Armenian, Serbian, and Yiddish.

Author: petere

doc/src/sgml/textsearch.sgml

@@ -3837,6 +3837,7 @@ Parser: "pg_catalog.default"
    Schema   |      Name       |                        Description
 ------------+-----------------+-----------------------------------------------------------
  pg_catalog | arabic_stem     | snowball stemmer for arabic language
+ pg_catalog | armenian_stem   | snowball stemmer for armenian language
  pg_catalog | basque_stem     | snowball stemmer for basque language
  pg_catalog | catalan_stem    | snowball stemmer for catalan language
  pg_catalog | danish_stem     | snowball stemmer for danish language
@@ -3857,11 +3858,13 @@ Parser: "pg_catalog.default"
  pg_catalog | portuguese_stem | snowball stemmer for portuguese language
  pg_catalog | romanian_stem   | snowball stemmer for romanian language
  pg_catalog | russian_stem    | snowball stemmer for russian language
+ pg_catalog | serbian_stem    | snowball stemmer for serbian language
  pg_catalog | simple          | simple dictionary: just lower case and check for stopword
  pg_catalog | spanish_stem    | snowball stemmer for spanish language
  pg_catalog | swedish_stem    | snowball stemmer for swedish language
  pg_catalog | tamil_stem      | snowball stemmer for tamil language
  pg_catalog | turkish_stem    | snowball stemmer for turkish language
+ pg_catalog | yiddish_stem    | snowball stemmer for yiddish language
 </screen>
      </para>
     </listitem>

src/backend/snowball/Makefile

@@ -43,6 +43,7 @@ OBJS += \
 	stem_ISO_8859_2_romanian.o \
 	stem_KOI8_R_russian.o \
 	stem_UTF_8_arabic.o \
+	stem_UTF_8_armenian.o \
 	stem_UTF_8_basque.o \
 	stem_UTF_8_catalan.o \
 	stem_UTF_8_danish.o \
@@ -64,17 +65,20 @@ OBJS += \
 	stem_UTF_8_portuguese.o \
 	stem_UTF_8_romanian.o \
 	stem_UTF_8_russian.o \
+	stem_UTF_8_serbian.o \
 	stem_UTF_8_spanish.o \
 	stem_UTF_8_swedish.o \
 	stem_UTF_8_tamil.o \
-	stem_UTF_8_turkish.o
+	stem_UTF_8_turkish.o \
+	stem_UTF_8_yiddish.o
 
 # first column is language name and also name of dictionary for not-all-ASCII
 # words, second is name of dictionary for all-ASCII words
 # Note order dependency: use of some other language as ASCII dictionary
 # must come after creation of that language
 LANGUAGES=  \
 	arabic		arabic		\
+	armenian	armenian	\
 	basque		basque		\
 	catalan		catalan		\
 	danish		danish		\
@@ -95,10 +99,12 @@ LANGUAGES=  \
 	portuguese	portuguese	\
 	romanian	romanian	\
 	russian		english		\
+	serbian		serbian		\
 	spanish		spanish		\
 	swedish		swedish		\
 	tamil		tamil		\
-	turkish		turkish
+	turkish		turkish		\
+	yiddish		yiddish
 
 
 SQLSCRIPT= snowball_create.sql

src/backend/snowball/README

@@ -29,8 +29,8 @@ We choose to include the derived files in the PostgreSQL distribution
 because most installations will not have the Snowball compiler available.
 
 We are currently synced with the Snowball git commit
-c70ed64f9d41c1032fba4e962b054f8e9d489a74 (tag v2.0.0)
-of 2019-10-02.
+4764395431c8f2a0b4fe18b816ab1fc966a45837 (tag v2.1.0)
+of 2021-01-21.
 
 To update the PostgreSQL sources from a new Snowball version:
 
@@ -59,7 +59,8 @@ do not require any changes.
 
 4. Check whether any stemmer modules have been added or removed.  If so, edit
 the OBJS list in Makefile, the list of #include's in dict_snowball.c, and the
-stemmer_modules[] table in dict_snowball.c.  You might also need to change
+stemmer_modules[] table in dict_snowball.c, as well as the list in the
+documentation in textsearch.sgml.  You might also need to change
 the LANGUAGES list in Makefile and tsearch_config_languages in initdb.c.
 
 5. The various stopword files in stopwords/ must be downloaded

src/backend/snowball/dict_snowball.c

@@ -46,6 +46,7 @@
 #include "snowball/libstemmer/stem_ISO_8859_2_romanian.h"
 #include "snowball/libstemmer/stem_KOI8_R_russian.h"
 #include "snowball/libstemmer/stem_UTF_8_arabic.h"
+#include "snowball/libstemmer/stem_UTF_8_armenian.h"
 #include "snowball/libstemmer/stem_UTF_8_basque.h"
 #include "snowball/libstemmer/stem_UTF_8_catalan.h"
 #include "snowball/libstemmer/stem_UTF_8_danish.h"
@@ -67,10 +68,12 @@
 #include "snowball/libstemmer/stem_UTF_8_portuguese.h"
 #include "snowball/libstemmer/stem_UTF_8_romanian.h"
 #include "snowball/libstemmer/stem_UTF_8_russian.h"
+#include "snowball/libstemmer/stem_UTF_8_serbian.h"
 #include "snowball/libstemmer/stem_UTF_8_spanish.h"
 #include "snowball/libstemmer/stem_UTF_8_swedish.h"
 #include "snowball/libstemmer/stem_UTF_8_tamil.h"
 #include "snowball/libstemmer/stem_UTF_8_turkish.h"
+#include "snowball/libstemmer/stem_UTF_8_yiddish.h"
 
 PG_MODULE_MAGIC;
 
@@ -117,6 +120,7 @@ static const stemmer_module stemmer_modules[] =
 	STEMMER_MODULE(romanian, PG_LATIN2, ISO_8859_2),
 	STEMMER_MODULE(russian, PG_KOI8R, KOI8_R),
 	STEMMER_MODULE(arabic, PG_UTF8, UTF_8),
+	STEMMER_MODULE(armenian, PG_UTF8, UTF_8),
 	STEMMER_MODULE(basque, PG_UTF8, UTF_8),
 	STEMMER_MODULE(catalan, PG_UTF8, UTF_8),
 	STEMMER_MODULE(danish, PG_UTF8, UTF_8),
@@ -138,10 +142,12 @@ static const stemmer_module stemmer_modules[] =
 	STEMMER_MODULE(portuguese, PG_UTF8, UTF_8),
 	STEMMER_MODULE(romanian, PG_UTF8, UTF_8),
 	STEMMER_MODULE(russian, PG_UTF8, UTF_8),
+	STEMMER_MODULE(serbian, PG_UTF8, UTF_8),
 	STEMMER_MODULE(spanish, PG_UTF8, UTF_8),
 	STEMMER_MODULE(swedish, PG_UTF8, UTF_8),
 	STEMMER_MODULE(tamil, PG_UTF8, UTF_8),
 	STEMMER_MODULE(turkish, PG_UTF8, UTF_8),
+	STEMMER_MODULE(yiddish, PG_UTF8, UTF_8),
 
 	/*
 	 * Stemmer with PG_SQL_ASCII encoding should be valid for any server

src/backend/snowball/libstemmer/api.c

@@ -1,6 +1,6 @@
 #include "header.h"
 
-extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size)
+extern struct SN_env * SN_create_env(int S_size, int I_size)
 {
     struct SN_env * z = (struct SN_env *) calloc(1, sizeof(struct SN_env));
     if (z == NULL) return NULL;
@@ -25,12 +25,6 @@ extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size)
         if (z->I == NULL) goto error;
     }
 
-    if (B_size)
-    {
-        z->B = (unsigned char *) calloc(B_size, sizeof(unsigned char));
-        if (z->B == NULL) goto error;
-    }
-
     return z;
 error:
     SN_close_env(z, S_size);
@@ -50,7 +44,6 @@ extern void SN_close_env(struct SN_env * z, int S_size)
         free(z->S);
     }
     free(z->I);
-    free(z->B);
     if (z->p) lose_s(z->p);
     free(z);
 }