PyThaiNLP · wannaphong · Apr 11, 2019 · Apr 8, 2019 · Apr 8, 2019 · Apr 8, 2019
diff --git a/README-pypi.md b/README-pypi.md
@@ -1,6 +1,6 @@
 ![PyThaiNLP Logo](https://avatars0.githubusercontent.com/u/32934255?s=200&v=4)
 
-# PyThaiNLP 2.0
+# PyThaiNLP 2.0.2
 
 [![Codacy Badge](https://api.codacy.com/project/badge/Grade/cb946260c87a4cc5905ca608704406f7)](https://www.codacy.com/app/pythainlp/pythainlp_2?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=PyThaiNLP/pythainlp&amp;utm_campaign=Badge_Grade)[![pypi](https://img.shields.io/pypi/v/pythainlp.svg)](https://pypi.python.org/pypi/pythainlp)
 [![Build Status](https://travis-ci.org/PyThaiNLP/pythainlp.svg?branch=develop)](https://travis-ci.org/PyThaiNLP/pythainlp)
@@ -12,9 +12,9 @@ PyThaiNLP is a Python library for natural language processing (NLP) of Thai lang
 
 PyThaiNLP includes Thai word tokenizers, transliterators, soundex converters, part-of-speech taggers, and spell checkers.
 
-📖 For details on upgrading from PyThaiNLP 1.7 to PyThaiNLP 2.0, see [From PyThaiNLP 1.7 to PyThaiNLP 2.0](https://thainlp.org/pythainlp/docs/2.0/notes/pythainlp-1_7-2_0.html)
+📖 [Upgrading from PyThaiNLP 1.7 to 2.0](https://thainlp.org/pythainlp/docs/2.0/notes/pythainlp-1_7-2_0.html)
 
-📖 For ThaiNER user after upgrading from PyThaiNLP 1.7 to PyThaiNLP 2.0, see [Upgrade ThaiNER from PyThaiNLP 1.7 to PyThaiNLP 2.0](https://github.com/PyThaiNLP/pythainlp/wiki/Upgrade-ThaiNER-from-PyThaiNLP-1.7-to-PyThaiNLP-2.0)
+📖 [Upgrade ThaiNER from PyThaiNLP 1.7 to 2.0](https://github.com/PyThaiNLP/pythainlp/wiki/Upgrade-ThaiNER-from-PyThaiNLP-1.7-to-PyThaiNLP-2.0)
 
 📫 follow us on Facebook [Pythainlp](https://www.facebook.com/pythainlp/)
 

diff --git a/README.md b/README.md
@@ -15,10 +15,10 @@ Thai Natural Language Processing in Python.
 PyThaiNLP is a Python package for text processing and linguistic analysis, similar to `nltk` but with focus on Thai language.
 
 - [Current PyThaiNLP stable release is 2.0](https://github.com/PyThaiNLP/pythainlp/tree/master)
-- PyThaiNLP 2.0 will support only Python 3.6+. Some functions may work with older version of Python 3, but it is not well-tested and will not be supported. See [PyThaiNLP 2.0 change log](https://github.com/PyThaiNLP/pythainlp/issues/118).
-- Python 2 users can use PyThaiNLP 1.6, our latest released that tested with Python 2.7.
+- PyThaiNLP 2.0 supports Python 3.6+. Some functions may work with older version of Python 3, but it is not well-tested and will not be supported. See [PyThaiNLP 2.0 change log](https://github.com/PyThaiNLP/pythainlp/issues/118).
+- Python 2.7+ users can use PyThaiNLP 1.6.
 
-**This is a document for development branch (post 1.7.x). Things will break. For a stable branch document, see [master](https://github.com/PyThaiNLP/pythainlp/tree/master).**
+**This is a document for development branch (post 2.0). Things will break. For a stable branch document, see [master](https://github.com/PyThaiNLP/pythainlp/tree/master).**
 
 📫 follow us on Facebook [PyThaiNLP](https://www.facebook.com/pythainlp/)
 
@@ -102,13 +102,10 @@ PyThaiNLP เป็นไลบารีภาษาไพทอนเพื่
 
 > เพราะโลกขับเคลื่อนต่อไปด้วยการแบ่งปัน
 
-รองรับ Python 3.6 ขึ้นไป
+- PyThaiNLP 2.0 รองรับ Python 3.6 ขึ้นไป
+- ผู้ใช้ Python 2.7+ ยังสามารถใช้ PyThaiNLP 1.6 ได้
 
-- ตั้งแต่รุ่น 1.7 PyThaiNLP จะเลิกสนับสนุน Python 2 (บางฟังก์ชันอาจยังทำงานได้ แต่จะไม่ได้รับการสนับสนุน)
-- ตั้งแต่รุ่น 2.0 จะยุติการรองรับ Python 2 ทั้งหมด
-- ผู้ใช้ Python 2 ยังสามารถใช้ PyThaiNLP 1.6 ได้
-
-**เอกสารนี้สำหรับรุ่นพัฒนา (หลัง 1.7.x) อาจมีการเปลี่ยนแปลงได้ตลอด สำหรับเอกสารรุ่นเสถียร ดูที่ [master](https://github.com/PyThaiNLP/pythainlp/tree/master).**
+**เอกสารนี้สำหรับรุ่นพัฒนา (หลัง 2.0) อาจมีการเปลี่ยนแปลงได้ตลอด สำหรับเอกสารรุ่นเสถียร ดูที่ [master](https://github.com/PyThaiNLP/pythainlp/tree/master).**
 
 📫 ติดตามข่าวสารได้ที่ Facebook [Pythainlp](https://www.facebook.com/pythainlp/)
 

diff --git a/bin/pythainlp b/bin/pythainlp
@@ -45,4 +45,4 @@ elif args.soundex!=None:
         args.engine="lk82"
     print(soundex(args.soundex, engine=args.engine))
 else:
-    print("PyThaiNLP 2.0")
+    print("PyThaiNLP 2.0.2")
diff --git a/conda.recipe/meta.yaml b/conda.recipe/meta.yaml
@@ -1,4 +1,4 @@
-{% set version = "2.0.1" %}
+{% set version = "2.0.2" %}
 
 package:
   name: pythainlp

diff --git a/meta.yaml b/meta.yaml
@@ -1,4 +1,4 @@
-{% set version = "2.0.1" %}
+{% set version = "2.0.2" %}
 
 package:
   name: pythainlp

diff --git a/pythainlp/__init__.py b/pythainlp/__init__.py
@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-__version__ = "2.0.1"
+__version__ = "2.0.2"
 
 thai_consonants = "กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรลวศษสหฬอฮ"  # 44 chars
 thai_vowels = "ฤฦะ\u0e31าำ\u0e34\u0e35\u0e36\u0e37\u0e38\u0e39เแโใไ\u0e45\u0e47"  # 19

diff --git a/pythainlp/tag/__init__.py b/pythainlp/tag/__init__.py
@@ -54,7 +54,6 @@
     "DIAC": "DET",
     "DIBQ": "DET",
     "DIAQ": "DET",
-    "DCNM": "DET",
     # NUM
     "NUM": "NUM",
     "NCNM": "NUM",

diff --git a/pythainlp/tokenize/__init__.py b/pythainlp/tokenize/__init__.py
@@ -122,17 +122,25 @@ def sent_tokenize(text: str, engine: str = "whitespace+newline") -> List[str]:
 def subword_tokenize(text: str, engine: str = "tcc") -> List[str]:
     """
     :param str text: text to be tokenized
-    :param str engine: choosing 'tcc' uses the Thai Character Cluster rule to segment words into the smallest unique units.
+    :param str engine: subword tokenizer 
+    :Parameters for engine:
+        * tcc (default) -  Thai Character Cluster (Theeramunkong et al. 2000)
+        * etcc - Enhanced Thai Character Cluster (Inrut et al. 2001) [In development] 
     :return: a list of tokenized strings.
     """
     if not text:
         return ""
 
     from .tcc import tcc
+    from .etcc import etcc
 
+    if engine == "tcc":
+        return tcc(text) 
+    elif engine == "etcc":
+        return etcc(text).split("/")
+    #default
     return tcc(text)
 
-
 def syllable_tokenize(text: str) -> List[str]:
     """
     :param str text: input string to be tokenized

diff --git a/pythainlp/tokenize/etcc.py b/pythainlp/tokenize/etcc.py
@@ -3,6 +3,8 @@
 โปรแกรม ETCC ใน Python
 พัฒนาโดย นาย วรรณพงษ์  ภัททิยไพบูลย์
 19 มิ.ย. 2560
+Reference: Inrut, Jeeragone, Patiroop Yuanghirun, Sarayut Paludkong, Supot Nitsuwat, and Para Limmaneepraserth. "Thai word segmentation using combination of forward and backward longest matching techniques." In International Symposium on Communications and Information Technology (ISCIT), pp. 37-40. 2001.
+
 
 วิธีใช้งาน
 etcc(คำ)

diff --git a/pythainlp/tokenize/tcc.py b/pythainlp/tokenize/tcc.py
@@ -1,8 +1,9 @@
 # -*- coding: utf-8 -*-
 """
 Separate Thai text into Thai Character Cluster (TCC).
-Based on "Character cluster based Thai information retrieval" (Theeramunkong et al. 2002)
-http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.2548
+Based on "Character cluster based Thai information retrieval" (Theeramunkong et al. 2000)
+https://dl.acm.org/citation.cfm?id=355225
+http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.2548 
 
 Credits:
 - TCC: Jakkrit TeCho

diff --git a/setup.cfg b/setup.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 2.0.1
+current_version = 2.0.2
 commit = True
 tag = True
 

diff --git a/setup.py b/setup.py
@@ -34,7 +34,7 @@
 
 setup(
     name="pythainlp",
-    version="2.0.1",
+    version="2.0.2",
     description="Thai Natural Language Processing library",
     long_description=readme,
     long_description_content_type="text/markdown",