From 34d72e3acf4f61f88264068ba78b28a006d2b7af Mon Sep 17 00:00:00 2001
From: David Rosson <david@rosson.com.au>
Date: Sat, 31 Dec 2016 20:23:51 -0800
Subject: [PATCH] Add tokenizer with language-specific RegExp matchers

---
 .../tokenizers/orthography_matchers.js        | 33 +++++++++++++++++++
 lib/natural/tokenizers/regexp_tokenizer.js    | 18 ++++++++++
 2 files changed, 51 insertions(+)
 create mode 100644 lib/natural/tokenizers/orthography_matchers.js

diff --git a/lib/natural/tokenizers/orthography_matchers.js b/lib/natural/tokenizers/orthography_matchers.js
new file mode 100644
index 000000000..50ae062d2
--- /dev/null
+++ b/lib/natural/tokenizers/orthography_matchers.js
@@ -0,0 +1,33 @@
+/*
+Copyright (c) 2011, Chris Umbel
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+*/
+
+
+/***
+ * RegExp definitions for tokenizing text in a specific language based
+ * on its alphabet. Each language is keyed by the two-letter code per
+ * ISO 639-1, and defines a RegExp that excludes alphabetic characters.
+ */
+var matchers = {
+  fi: /[^A-Za-zÅåÄäÖö]/
+};
+
+module.exports = matchers;
diff --git a/lib/natural/tokenizers/regexp_tokenizer.js b/lib/natural/tokenizers/regexp_tokenizer.js
index ae9ddac2a..12109d379 100644
--- a/lib/natural/tokenizers/regexp_tokenizer.js
+++ b/lib/natural/tokenizers/regexp_tokenizer.js
@@ -53,6 +53,24 @@ RegexpTokenizer.prototype.tokenize = function(s) {
 
 exports.RegexpTokenizer = RegexpTokenizer;
 
+var orthographyMatchers = require('./orthography_matchers');
+
+/***
+ * A tokenizer that accepts an alphabet definition.
+ * @param {string} options.language ISO 639-1 for the language, e.g. 'en'
+ */
+var OrthographyTokenizer = function(options) {
+    var pattern = orthographyMatchers[options.language];
+    if (!pattern) {
+        WordTokenizer.call(this, options);
+    } else {
+        this._pattern = pattern;
+        RegexpTokenizer.call(this, options);
+    }
+};
+
+exports.OrthographyTokenizer = OrthographyTokenizer;
+
 /***
  * A tokenizer that divides a text into sequences of alphabetic and
  * non-alphabetic characters.  E.g.: