From c2c5ecf6af1ce169468ad0adf68a0b827df32efb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jan=20Bedna=C5=99=C3=ADk?= <jan.bednarik@gmail.com>
Date: Wed, 29 Nov 2017 23:00:48 +0100
Subject: [PATCH] Custom thesaurus of czech synonyms.
---
Dockerfile | 1 +
README.md | 10 +++++++++-
analysis/cs_CZ/synonym.txt | 8 ++++++++
3 files changed, 18 insertions(+), 1 deletion(-)
create mode 100644 analysis/cs_CZ/synonym.txt
diff --git a/Dockerfile b/Dockerfile
index 016a5e5..84f2356 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -4,3 +4,4 @@ RUN elasticsearch-plugin remove --purge x-pack
RUN elasticsearch-plugin install analysis-icu
ADD hunspell/ /usr/share/elasticsearch/config/hunspell/
+ADD analysis/ /usr/share/elasticsearch/config/analysis/
diff --git a/README.md b/README.md
index ac6a62e..063f786 100644
--- a/README.md
+++ b/README.md
@@ -30,7 +30,11 @@ Create Index with these settings:
'type': 'hunspell',
'locale': 'cs_CZ',
'dedup': True,
- }
+ },
+ 'czech_synonym': {
+ 'type': 'synonym',
+ 'synonyms_path': 'analysis/cs_CZ/synonym.txt',
+ },
},
'analyzer': {
'czech': {
@@ -38,6 +42,7 @@ Create Index with these settings:
'filter': [
'icu_folding',
'lowercase',
+ 'czech_synonym',
'czech_stop',
'czech_stemmer',
'cs_CZ',
@@ -51,6 +56,9 @@ Create Index with these settings:
You can use `'czech'` analyzer on text fields now.
+There is custom dictionary of synonyms included. You can adjust it for your
+needs or remove it from analyzer settings.
+
## Build
If you don't want to use pre-built container from
diff --git a/analysis/cs_CZ/synonym.txt b/analysis/cs_CZ/synonym.txt
new file mode 100644
index 0000000..a76a5e2
--- /dev/null
+++ b/analysis/cs_CZ/synonym.txt
@@ -0,0 +1,8 @@
+# Czech Synonyms in Solr format
+# =============================
+#
+# Write comma separated list of words without diacritic in lowercase.
+# One set of synonyms per line.
+
+kava, kafe
+tramvaj, salina
--
GitLab