Add KUCut

Author: wannaphong

.github/workflows/kucut-build.yml

@@ -0,0 +1,64 @@
+name: KUCut-build
+
+on:
+  push:
+    # Publish `v1.2.3` tags as releases.
+    tags:
+      - kucut-v*
+
+  # Run tests for any PRs.
+  pull_request:
+
+env:
+  # TODO: Change variable to your image's name.
+  IMAGE_NAME: kucut
+
+jobs:
+  # Run tests.
+  # See also https://docs.docker.com/docker-hub/builds/automated-testing/
+  test:
+    runs-on: ubuntu-20.04
+
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Run tests
+        run: |
+          cd kucut
+          docker build . --file Dockerfile
+  # Push image to GitHub Packages.
+  # See also https://docs.docker.com/docker-hub/builds/
+  push:
+    # Ensure test job passes before pushing image.
+    needs: test
+
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push'
+
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Build image
+        run: |
+          cd kucut
+          docker build . --file Dockerfile --tag $IMAGE_NAME
+
+      - name: Log into registry
+        run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login docker.pkg.github.com -u ${{ github.actor }} --password-stdin
+
+      - name: Push image
+        run: |
+          IMAGE_ID=docker.pkg.github.com/${{ github.repository }}/$IMAGE_NAME
+
+          # Change all uppercase to lowercase
+          IMAGE_ID=$(echo $IMAGE_ID | tr '[A-Z]' '[a-z]')
+          # Strip git ref prefix from version
+          VERSION=$(echo "${{ github.ref }}" | sed -e 's,.*/\(.*\),\1,')
+          # Strip "v" prefix from tag name
+          [[ "${{ github.ref }}" == "refs/tags/"* ]] && VERSION=$(echo $VERSION | sed -e 's/^v//')
+          # Use Docker `latest` tag convention
+          [ "$VERSION" == "main" ] && VERSION=latest
+          echo IMAGE_ID=$IMAGE_ID
+          echo VERSION=$VERSION
+          docker tag $IMAGE_NAME $IMAGE_ID:$VERSION
+          docker push $IMAGE_ID:$VERSION

kucut/Dockerfile

@@ -0,0 +1,9 @@
+# Python 2.6 from https://gist.github.com/mjhea0/03fdaa4ff1e0311d7651e6a815d01583
+# base image
+FROM mjhea0/centos-6-python-2.6:latest
+
+RUN git clone https://github.com/Thanabhat/KUCut.git
+
+WORKDIR "/KUCut"
+
+RUN python setup.py install

kucut/README.md

@@ -0,0 +1,46 @@
+# KUCut
+
+This is dockerfile of KUCut.
+
+KU wordcut is thai word segmentor.
+
+GitHub: https://github.com/Thanabhat/KUCut
+
+KUCut License: GPL-2.0 License
+
+## How to build
+
+> docker build -t kucut:v1.4.3b2 .
+
+## Using
+
+> docker run --rm -it --entrypoint bash kucut:v1.4.3b2
+
+or when docker is running.
+
+> docker exec -it kucut:v1.4.3b2 bash
+
+using
+
+```sh
+# python
+Python 2.6.6 (r266:84292, Aug 18 2016, 15:13:37) 
+[GCC 4.4.7 20120313 (Red Hat 4.4.7-17)] on linux2
+Type "help", "copyright", "credits" or "license" for more information.
+>>> from kucut import SimpleKucutWrapper as KUCut
+kucut/AIMA/utils.py:7: DeprecationWarning: the sets module is deprecated
+  from sets import *
+>>> myKUCut = KUCut()
+
+>>> result = myKUCut.tokenize([u"ทดสอบทดสอบ"])
+>>> result 
+[[[u'\u0e17\u0e14\u0e2a\u0e2d\u0e1a', u'\u0e17\u0e14\u0e2a\u0e2d\u0e1a']]]
+>>> print result[0]
+[[u'\u0e17\u0e14\u0e2a\u0e2d\u0e1a', u'\u0e17\u0e14\u0e2a\u0e2d\u0e1a']]
+>>> print result[0][0]
+[u'\u0e17\u0e14\u0e2a\u0e2d\u0e1a', u'\u0e17\u0e14\u0e2a\u0e2d\u0e1a']
+>>> print result[0][0][0]
+ทดสอบ
+>>> print result[0][0][1]
+ทดสอบ
+```