Update warnings

PyThaiNLP · Sep 20, 2022 · 18c8c50 · 18c8c50
1 parent 296df1f
commit 18c8c50
Show file tree

Hide file tree

Showing 10 changed files with 21 additions and 9 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -1,4 +1,4 @@
-FROM python:3.7-slim-buster
+FROM python:3.8-slim-buster
 
 COPY . .
 

diff --git a/SECURITY.md b/SECURITY.md
@@ -4,6 +4,7 @@
 
 | Version | Supported          |
 | ------- | ------------------ |
+| 3.1.x   | :white_check_mark: |
 | 3.0.x   | :white_check_mark: |
 | 2.3.x   | :white_check_mark: |
 | 2.2.x   | :x:                |

diff --git a/pythainlp/corpus/ttc.py b/pythainlp/corpus/ttc.py
@@ -2,7 +2,7 @@
 """
 Thai Textbook Corpus (TTC) word frequency
 
-Credit: Korakot Chaovavanich‎
+Credit: Korakot Chaovavanich
 https://www.facebook.com/photo.php?fbid=363640477387469&set=gm.434330506948445&type=3&permPage=1
 """
 

diff --git a/pythainlp/parse/esupar_engine.py b/pythainlp/parse/esupar_engine.py
@@ -5,7 +5,10 @@
 GitHub: https://github.com/KoichiYasuoka/esupar
 """
 from typing import List, Union
-import esupar
+try:
+    import esupar
+except ImportError:
+    raise ImportError("Import Error; Install esupar by pip install esupar")
 
 
 class Parse:

diff --git a/pythainlp/tag/named_entity.py b/pythainlp/tag/named_entity.py
@@ -45,7 +45,7 @@ def load_engine(self, engine: str, corpus: str) -> None:
         elif engine == "wangchanberta":
             from pythainlp.wangchanberta import ThaiNameTagger
             if corpus=="lst20":
-                print("""
+                warnings.warn("""
                 LST20 corpus are free for research and open source only.\n
                 If you want to use in Commercial use, please contract NECTEC.\n
                 https://www.facebook.com/dancearmy/posts/10157641945708284

diff --git a/pythainlp/tag/perceptron.py b/pythainlp/tag/perceptron.py
@@ -4,6 +4,7 @@
 """
 import os
 from typing import List, Tuple
+import warnings
 
 from pythainlp.corpus import corpus_path, get_corpus_path
 from pythainlp.tag import PerceptronTagger, lst20, orchid
@@ -37,7 +38,7 @@ def _pud_tagger():
 
 def _lst20_tagger():
     global _LST20_TAGGER
-    print("""
+    warnings.warn("""
     LST20 corpus are free for research and open source only.\n
     If you want to use in Commercial use, please contract NECTEC.\n
     https://www.facebook.com/dancearmy/posts/10157641945708284

diff --git a/pythainlp/tag/unigram.py b/pythainlp/tag/unigram.py
@@ -5,6 +5,7 @@
 import json
 import os
 from typing import List, Tuple
+import warnings
 
 from pythainlp.corpus import corpus_path, get_corpus_path
 from pythainlp.tag import lst20, orchid
@@ -41,7 +42,7 @@ def _pud_tagger():
 
 def _lst20_tagger():
     global _LST20_TAGGER
-    print("""
+    warnings.warn("""
     LST20 corpus are free for research and open source only.\n
     If you want to use in Commercial use, please contract NECTEC.\n
     https://www.facebook.com/dancearmy/posts/10157641945708284

diff --git a/pythainlp/tokenize/crfcls.py b/pythainlp/tokenize/crfcls.py
@@ -3,6 +3,7 @@
 Clause segmenter
 """
 from typing import List
+import warnings
 
 import pycrfsuite
 from pythainlp.corpus import get_corpus_path
@@ -55,7 +56,7 @@ def _extract_features(doc):
 
 
 def segment(doc: List[str]) -> List[List[str]]:
-    print("""
+    warnings.warn("""
     LST20 corpus are free for research and open source only.\n
     If you want to use in Commercial use, please contract NECTEC.\n
     https://www.facebook.com/dancearmy/posts/10157641945708284

diff --git a/pythainlp/wangchanberta/postag.py b/pythainlp/wangchanberta/postag.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 from typing import Dict, List, Tuple, Union
 import re
+import warnings
 from transformers import (
     CamembertTokenizer,
     AutoTokenizer,
@@ -22,6 +23,12 @@ def __init__(
         grouped_word: bool = False
     ) -> None:
         self.corpus = corpus
+        if corpus=="lst20":
+            warnings.warn("""
+            LST20 corpus are free for research and open source only.\n
+            If you want to use in Commercial use, please contract NECTEC.\n
+            https://www.facebook.com/dancearmy/posts/10157641945708284
+            """)
         self.grouped_word = grouped_word
         self.load()
 

diff --git a/setup.py b/setup.py
@@ -92,7 +92,6 @@
         "transformers>=4.22.1",
     ],
     "dependency_parsing": [
-        "esupar>=1.3.8",
         "spacy_thai>=0.7.1",
         "ufal.chu-liu-edmonds>=1.0.2",
         "transformers>=4.22.1",
@@ -126,7 +125,6 @@
         "thai_nner",
         "wunsen>=0.0.3",
         "spacy_thai>=0.7.1",
-        "esupar>=1.3.8",
         "ufal.chu-liu-edmonds>=1.0.2",
     ],
 }