Merge pull request #220 from PyThaiNLP/dev

Merge from 2.0.5 release

Author: bact

CONTRIBUTING.md

@@ -60,6 +60,9 @@ Happy hacking! (;
 ## Docs
 - Peeradej Tanruangporn
 
+## Maintainers
+- Arthit Suriyawongkul
+
 ## Contributors
 - See more contributions here https://github.com/PyThaiNLP/pythainlp/graphs/contributors
 

README.md

@@ -16,7 +16,7 @@ PyThaiNLP is a Python package for text processing and linguistic analysis, simil
 
 **This is a document for development branch (post 2.0). Things will break.**
 
-- The latest stable release is [2.0.4](https://github.com/PyThaiNLP/pythainlp/tree/master)
+- The latest stable release is [2.0.5](https://github.com/PyThaiNLP/pythainlp/tree/master)
 - PyThaiNLP 2 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 [change log](https://github.com/PyThaiNLP/pythainlp/issues/118).
   - [Upgrading from 1.7](https://thainlp.org/pythainlp/docs/2.0/notes/pythainlp-1_7-2_0.html)
   - [Upgrade ThaiNER from 1.7](https://github.com/PyThaiNLP/pythainlp/wiki/Upgrade-ThaiNER-from-PyThaiNLP-1.7-to-PyThaiNLP-2.0)
@@ -106,7 +106,7 @@ PyThaiNLP เป็นไลบารีภาษาไพทอนเพื่
 
 **เอกสารนี้สำหรับรุ่นพัฒนา อาจมีการเปลี่ยนแปลงได้ตลอด**
 
-- รุ่นเสถียรล่าสุดคือรุ่น [2.0.4](https://github.com/PyThaiNLP/pythainlp/tree/master)
+- รุ่นเสถียรล่าสุดคือรุ่น [2.0.5](https://github.com/PyThaiNLP/pythainlp/tree/master)
 - PyThaiNLP 2 รองรับ Python 3.6 ขึ้นไป
 - ผู้ใช้ Python 2.7+ ยังสามารถใช้ PyThaiNLP 1.6 ได้
 

appveyor.yml

@@ -1,40 +1,50 @@
+# Use unofficial Windows Binaries for Python Extension Packages from
+# https://www.lfd.uci.edu/~gohlke/pythonlibs/
+
 build: off
 
 environment:
   matrix:
+#    - PYTHON: "C:/Python36"
+#      PYTHON_VERSION: "3.6"
+#      PYTHON_ARCH: "32"
+#      ARTAGGER_PKG: "https://github.com/wannaphongcom/artagger/tarball/master#egg=artagger"
+#      PYICU_PKG: "https://www.dropbox.com/s/pahorbq29y9cura/PyICU-2.3.1-cp36-cp36m-win32.whl?dl=1"
+
     - PYTHON: "C:/Python36-x64"
       PYTHON_VERSION: "3.6"
       PYTHON_ARCH: "64"
       ARTAGGER_PKG: "https://github.com/wannaphongcom/artagger/tarball/master#egg=artagger"
+      PYICU_PKG: "https://www.dropbox.com/s/7t0rrxwckqbgivi/PyICU-2.3.1-cp36-cp36m-win_amd64.whl?dl=1"
 
-    #- PYTHON: "C:/Python36-x64"
-    #  PYTHON_VERSION: "3.6"
-    #  PYTHON_ARCH: "64"
-    #  PYICU_PKG: ""
-
-    #- PYTHON: "C:/Python37"
-    #  PYTHON_VERSION: "3.7"
-    #  PYTHON_ARCH: "32"
-    #  PYICU_PKG: ""
+#    - PYTHON: "C:/Python37"
+#      PYTHON_VERSION: "3.7"
+#      PYTHON_ARCH: "32"
+#      ARTAGGER_PKG: "https://github.com/wannaphongcom/artagger/tarball/master#egg=artagger"
+#      PYICU_PKG: "https://www.dropbox.com/s/3xwdnwhdcu619x4/PyICU-2.3.1-cp37-cp37m-win32.whl?dl=1"
 
-    #- PYTHON: "C:/Python37-x64"
-    #  PYTHON_VERSION: "3.7"
-    #  PYTHON_ARCH: "64"
-    #  PYICU_PKG: ""
+    - PYTHON: "C:/Python37-x64"
+      PYTHON_VERSION: "3.7"
+      PYTHON_ARCH: "64"
+      ARTAGGER_PKG: "https://github.com/wannaphongcom/artagger/tarball/master#egg=artagger"
+      PYICU_PKG: "https://www.dropbox.com/s/le5dckc3231opqt/PyICU-2.3.1-cp37-cp37m-win_amd64.whl?dl=1"
 
 init:
   - "ECHO %PYTHON% %PYTHON_VERSION% %PYTHON_ARCH%"  
-  - ps: "ls C:/Python*"
+#  - ps: "ls C:/Python*"
 
 install:
   - "chcp 65001"
   - "set PYTHONIOENCODING=utf-8"
+  - "%PYTHON%/python.exe --version"
   # - "set ICU_VERSION=62"
   - "%PYTHON%/python.exe -m pip install --upgrade pip"
-  - "%PYTHON%/python.exe -m pip install https://www.dropbox.com/s/g84479l8yhv5ohi/PyICU-2.2-cp36-cp36m-win_amd64.whl?dl=1"
+  - "%PYTHON%/python.exe -m pip install coveralls[yaml]"
+  - "%PYTHON%/python.exe -m pip install coverage"
+  - "%PYTHON%/python.exe -m pip install %PYICU_PKG%"
   - "%PYTHON%/python.exe -m pip install %ARTAGGER_PKG%"
   - "%PYTHON%/python.exe -m pip install -e .[artagger,icu,ipa,ner,thai2fit,deepcut]"
 
 test_script:
   - "%PYTHON%/python.exe -m pip --version"
-  - "%PYTHON%/python.exe setup.py test"
+  - "%PYTHON%/python.exe -m coverage run --source=pythainlp setup.py test"

bin/pythainlp

@@ -1,7 +1,7 @@
 #!python3
 # -*- coding: utf-8 -*-
 
-_VERSION = "2.0.4"
+_VERSION = "2.0.5"
 
 import argparse
 

build.sh

@@ -1,2 +1,3 @@
-cd $RECIPE_DIR/..
+#!/bin/bash
+cd "$RECIPE_DIR"/.. || exit
 $PYTHON setup.py install --single-version-externally-managed --record=record.txt

conda.recipe/meta.yaml

@@ -1,4 +1,4 @@
-{% set version = "2.0.4" %}
+{% set version = "2.0.5" %}
 
 package:
   name: pythainlp

docs/api/spell.rst

@@ -7,5 +7,9 @@ The :class:`pythainlp.spell` finds the closest correctly spelled word to the giv
 Modules
 -------
 
-.. autofunction:: spell
 .. autofunction:: correct
+.. autofunction:: spell
+.. autoclass:: NorvigSpellChecker
+   :members:
+.. autodata:: DEFAULT_SPELL_CHECKER
+   :annotation: = Default instance of standard NorvigSpellChecker, using word list from Thai National Corpus

docs/api/tokenize.rst

@@ -14,4 +14,16 @@ Modules
 .. autofunction:: subword_tokenize
 .. autofunction:: dict_trie
 .. autoclass:: Tokenizer
-   :members: word_tokenize, set_tokenize_engine
+   :members:
+
+NEWMM
+-----
+.. autofunction:: pythainlp.tokenize.newmm.segment
+
+TCC
+---
+Thai Character Cluster
+
+.. autofunction:: pythainlp.tokenize.tcc.segment
+.. autofunction:: pythainlp.tokenize.tcc.tcc
+.. autofunction:: pythainlp.tokenize.tcc.tcc_pos

meta.yaml

@@ -1,4 +1,4 @@
-{% set version = "2.0.4" %}
+{% set version = "2.0.5" %}
 
 package:
   name: pythainlp