Update snowball

Update to snowball tag v2.0.0.  Major changes are new stemmers for
Basque, Catalan, and Hindi.

Discussion: https://www.postgresql.org/message-id/flat/a8eeabd6-2be1-43fe-401e-a97594c38478%402ndquadrant.com

Author: petere

src/backend/snowball/Makefile

@@ -23,6 +23,8 @@ OBJS = \
 	utilities.o
 
 OBJS += \
+	stem_ISO_8859_1_basque.o \
+	stem_ISO_8859_1_catalan.o \
 	stem_ISO_8859_1_danish.o \
 	stem_ISO_8859_1_dutch.o \
 	stem_ISO_8859_1_english.o \
@@ -41,13 +43,16 @@ OBJS += \
 	stem_ISO_8859_2_romanian.o \
 	stem_KOI8_R_russian.o \
 	stem_UTF_8_arabic.o \
+	stem_UTF_8_basque.o \
+	stem_UTF_8_catalan.o \
 	stem_UTF_8_danish.o \
 	stem_UTF_8_dutch.o \
 	stem_UTF_8_english.o \
 	stem_UTF_8_finnish.o \
 	stem_UTF_8_french.o \
 	stem_UTF_8_german.o \
 	stem_UTF_8_greek.o \
+	stem_UTF_8_hindi.o \
 	stem_UTF_8_hungarian.o \
 	stem_UTF_8_indonesian.o \
 	stem_UTF_8_irish.o \
@@ -70,13 +75,16 @@ OBJS += \
 # must come after creation of that language
 LANGUAGES=  \
 	arabic		arabic		\
+	basque		basque		\
+	catalan		catalan		\
 	danish		danish		\
 	dutch		dutch		\
 	english		english		\
 	finnish		finnish		\
 	french		french		\
 	german		german		\
 	greek		greek		\
+	hindi		english		\
 	hungarian	hungarian	\
 	indonesian	indonesian	\
 	irish		irish		\

src/backend/snowball/README

@@ -7,7 +7,7 @@ This module uses the word stemming code developed by the Snowball project,
 http://snowballstem.org (formerly http://snowball.tartarus.org)
 which is released by them under a BSD-style license.
 
-The Snowball project is not currently making formal releases; it's best
+The Snowball project does not often make formal releases; it's best
 to pull from their git repository
 
 git clone https://github.com/snowballstem/snowball.git
@@ -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
-4456b82c26c02493e8807a66f30593a98c5d2888
-of 2019-06-24.
+c70ed64f9d41c1032fba4e962b054f8e9d489a74 (tag v2.0.0)
+of 2019-10-02.
 
 To update the PostgreSQL sources from a new Snowball version:
 
@@ -44,6 +44,9 @@ do
     sed 's|\.\./runtime/header\.h|header.h|' $f >libstemmer/`basename $f`
 done
 
+Do not copy stemmers that are listed in libstemmer/modules.txt as
+nonstandard, such as "german2" or "lovins".
+
 2. Copy the *.c files in snowball/runtime/ to
 src/backend/snowball/libstemmer, and edit them to remove direct inclusions
 of system headers such as <stdio.h> --- they should only include "header.h".

src/backend/snowball/dict_snowball.c

@@ -26,6 +26,8 @@
 
 /* Now we can include the original Snowball header.h */
 #include "snowball/libstemmer/header.h"
+#include "snowball/libstemmer/stem_ISO_8859_1_basque.h"
+#include "snowball/libstemmer/stem_ISO_8859_1_catalan.h"
 #include "snowball/libstemmer/stem_ISO_8859_1_danish.h"
 #include "snowball/libstemmer/stem_ISO_8859_1_dutch.h"
 #include "snowball/libstemmer/stem_ISO_8859_1_english.h"
@@ -44,13 +46,16 @@
 #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_basque.h"
+#include "snowball/libstemmer/stem_UTF_8_catalan.h"
 #include "snowball/libstemmer/stem_UTF_8_danish.h"
 #include "snowball/libstemmer/stem_UTF_8_dutch.h"
 #include "snowball/libstemmer/stem_UTF_8_english.h"
 #include "snowball/libstemmer/stem_UTF_8_finnish.h"
 #include "snowball/libstemmer/stem_UTF_8_french.h"
 #include "snowball/libstemmer/stem_UTF_8_german.h"
 #include "snowball/libstemmer/stem_UTF_8_greek.h"
+#include "snowball/libstemmer/stem_UTF_8_hindi.h"
 #include "snowball/libstemmer/stem_UTF_8_hungarian.h"
 #include "snowball/libstemmer/stem_UTF_8_indonesian.h"
 #include "snowball/libstemmer/stem_UTF_8_irish.h"
@@ -92,6 +97,8 @@ static const stemmer_module stemmer_modules[] =
 	/*
 	 * Stemmers list from Snowball distribution
 	 */
+	STEMMER_MODULE(basque, PG_LATIN1, ISO_8859_1),
+	STEMMER_MODULE(catalan, PG_LATIN1, ISO_8859_1),
 	STEMMER_MODULE(danish, PG_LATIN1, ISO_8859_1),
 	STEMMER_MODULE(dutch, PG_LATIN1, ISO_8859_1),
 	STEMMER_MODULE(english, PG_LATIN1, ISO_8859_1),
@@ -110,13 +117,16 @@ 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(basque, PG_UTF8, UTF_8),
+	STEMMER_MODULE(catalan, PG_UTF8, UTF_8),
 	STEMMER_MODULE(danish, PG_UTF8, UTF_8),
 	STEMMER_MODULE(dutch, PG_UTF8, UTF_8),
 	STEMMER_MODULE(english, PG_UTF8, UTF_8),
 	STEMMER_MODULE(finnish, PG_UTF8, UTF_8),
 	STEMMER_MODULE(french, PG_UTF8, UTF_8),
 	STEMMER_MODULE(german, PG_UTF8, UTF_8),
 	STEMMER_MODULE(greek, PG_UTF8, UTF_8),
+	STEMMER_MODULE(hindi, PG_UTF8, UTF_8),
 	STEMMER_MODULE(hungarian, PG_UTF8, UTF_8),
 	STEMMER_MODULE(indonesian, PG_UTF8, UTF_8),
 	STEMMER_MODULE(irish, PG_UTF8, UTF_8),

src/backend/snowball/libstemmer/api.c

@@ -61,4 +61,3 @@ extern int SN_set_current(struct SN_env * z, int size, const symbol * s)
     z->c = 0;
     return err;
 }
-