PyThaiNLP
diff --git a/‎Dockerfile
+1 b/‎Dockerfile
+1
diff --git a/‎docs/conf.py
+1 b/‎docs/conf.py
+1
diff --git a/‎examples/khavee.py
+4-3 b/‎examples/khavee.py
+4-3
diff --git a/‎pyproject.toml
+1 b/‎pyproject.toml
+1
diff --git a/‎pythainlp/__init__.py
+1 b/‎pythainlp/__init__.py
+1
diff --git a/‎pythainlp/ancient/__init__.py
+1 b/‎pythainlp/ancient/__init__.py
+1
diff --git a/‎pythainlp/ancient/aksonhan.py
+2 b/‎pythainlp/ancient/aksonhan.py
+2
diff --git a/‎pythainlp/augment/__init__.py
+1 b/‎pythainlp/augment/__init__.py
+1
diff --git a/‎pythainlp/augment/lm/__init__.py
+1 b/‎pythainlp/augment/lm/__init__.py
+1
diff --git a/‎pythainlp/augment/lm/fasttext.py
+1 b/‎pythainlp/augment/lm/fasttext.py
+1
diff --git a/‎pythainlp/augment/lm/phayathaibert.py
+1 b/‎pythainlp/augment/lm/phayathaibert.py
+1
diff --git a/‎pythainlp/augment/lm/wangchanberta.py
+1 b/‎pythainlp/augment/lm/wangchanberta.py
+1
diff --git a/‎pythainlp/augment/word2vec/__init__.py
+1 b/‎pythainlp/augment/word2vec/__init__.py
+1
diff --git a/‎pythainlp/augment/word2vec/bpemb_wv.py
+1 b/‎pythainlp/augment/word2vec/bpemb_wv.py
+1
diff --git a/‎pythainlp/augment/word2vec/core.py
+1 b/‎pythainlp/augment/word2vec/core.py
+1
diff --git a/‎pythainlp/augment/word2vec/ltw2v.py
+1 b/‎pythainlp/augment/word2vec/ltw2v.py
+1
diff --git a/‎pythainlp/augment/word2vec/thai2fit.py
+1 b/‎pythainlp/augment/word2vec/thai2fit.py
+1
diff --git a/‎pythainlp/augment/wordnet.py
+1 b/‎pythainlp/augment/wordnet.py
+1
diff --git a/‎pythainlp/benchmarks/__init__.py
+1 b/‎pythainlp/benchmarks/__init__.py
+1
diff --git a/‎pythainlp/benchmarks/word_tokenization.py
+1 b/‎pythainlp/benchmarks/word_tokenization.py
+1
diff --git a/‎pythainlp/chat/__init__.py
+1 b/‎pythainlp/chat/__init__.py
+1
diff --git a/‎pythainlp/chat/core.py
+1 b/‎pythainlp/chat/core.py
+1
diff --git a/‎pythainlp/classify/__init__.py
+1 b/‎pythainlp/classify/__init__.py
+1
diff --git a/‎pythainlp/classify/param_free.py
+1 b/‎pythainlp/classify/param_free.py
+1
diff --git a/‎pythainlp/cli/__init__.py
+1 b/‎pythainlp/cli/__init__.py
+1
diff --git a/‎pythainlp/cli/benchmark.py
+1 b/‎pythainlp/cli/benchmark.py
+1
diff --git a/‎pythainlp/cli/data.py
+1 b/‎pythainlp/cli/data.py
+1
diff --git a/‎pythainlp/cli/soundex.py
+1 b/‎pythainlp/cli/soundex.py
+1
diff --git a/‎pythainlp/cli/tag.py
+1 b/‎pythainlp/cli/tag.py
+1
diff --git a/‎pythainlp/cli/tokenize.py
+1 b/‎pythainlp/cli/tokenize.py
+1
diff --git a/‎pythainlp/cls/__init__.py
+1 b/‎pythainlp/cls/__init__.py
+1
diff --git a/‎pythainlp/coref/__init__.py
+1 b/‎pythainlp/coref/__init__.py
+1
diff --git a/‎pythainlp/coref/_fastcoref.py
+1 b/‎pythainlp/coref/_fastcoref.py
+1
diff --git a/‎pythainlp/coref/core.py
+1 b/‎pythainlp/coref/core.py
+1
diff --git a/‎pythainlp/coref/han_coref.py
+1 b/‎pythainlp/coref/han_coref.py
+1
diff --git a/‎pythainlp/corpus/__init__.py
+1 b/‎pythainlp/corpus/__init__.py
+1
diff --git a/‎pythainlp/corpus/common.py
+1 b/‎pythainlp/corpus/common.py
+1
diff --git a/‎pythainlp/corpus/conceptnet.py
+1 b/‎pythainlp/corpus/conceptnet.py
+1
diff --git a/‎pythainlp/corpus/core.py
+1 b/‎pythainlp/corpus/core.py
+1
diff --git a/‎pythainlp/corpus/icu.py
+1 b/‎pythainlp/corpus/icu.py
+1
diff --git a/‎pythainlp/corpus/oscar.py
+1 b/‎pythainlp/corpus/oscar.py
+1
diff --git a/‎pythainlp/corpus/th_en_translit.py
+1 b/‎pythainlp/corpus/th_en_translit.py
+1
diff --git a/‎pythainlp/corpus/ttc.py
+1 b/‎pythainlp/corpus/ttc.py
+1
diff --git a/‎pythainlp/corpus/util.py
+1 b/‎pythainlp/corpus/util.py
+1
diff --git a/‎pythainlp/corpus/volubilis.py
+1 b/‎pythainlp/corpus/volubilis.py
+1
diff --git a/‎pythainlp/corpus/wikipedia.py
+1 b/‎pythainlp/corpus/wikipedia.py
+1
diff --git a/‎pythainlp/corpus/wordnet.py
+1 b/‎pythainlp/corpus/wordnet.py
+1
diff --git a/‎pythainlp/el/__init__.py
+1 b/‎pythainlp/el/__init__.py
+1
diff --git a/‎pythainlp/el/_multiel.py
+1 b/‎pythainlp/el/_multiel.py
+1
diff --git a/‎pythainlp/el/core.py
+1 b/‎pythainlp/el/core.py
+1
diff --git a/‎pythainlp/generate/__init__.py
+1 b/‎pythainlp/generate/__init__.py
+1
diff --git a/‎pythainlp/generate/core.py
+1 b/‎pythainlp/generate/core.py
+1
diff --git a/‎pythainlp/generate/thai2fit.py
+1 b/‎pythainlp/generate/thai2fit.py
+1
diff --git a/‎pythainlp/generate/wangchanglm.py
+1 b/‎pythainlp/generate/wangchanglm.py
+1
diff --git a/‎pythainlp/khavee/__init__.py
+1 b/‎pythainlp/khavee/__init__.py
+1
@@ -1,4 +1,5 @@
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 FROM python:3.8-slim-buster
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 #
 # Configuration file for the Sphinx documentation builder.
 
@@ -1,15 +1,16 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-
-# Example of using KhaveeVerifier from pythainlp.khavee
+"""
+Example of using KhaveeVerifier from pythainlp.khavee
+"""
 
 from pythainlp.khavee import KhaveeVerifier
 
 
 kv = KhaveeVerifier()
 
-
 # การเช็คสระ
 print("เออ", kv.check_sara("เมอ"))
 # 'เออ'
 
@@ -1,4 +1,5 @@
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 [tool.ruff]
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 __version__ = "5.0.5-dev"
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Ancient versions of the Thai language
 
@@ -1,6 +1,8 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
+
 from pythainlp import thai_consonants, thai_tonemarks
 from pythainlp.corpus import thai_orst_words
 from pythainlp.tokenize import Tokenizer
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Thai text augment
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Language Models
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 import itertools
 from typing import List, Tuple
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 import random
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 from typing import List
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Word2Vec
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 from typing import List, Tuple
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 import itertools
 from typing import List, Tuple
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 from typing import List, Tuple
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 from typing import List, Tuple
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Thank https://dev.to/ton_ami/text-data-augmentation-synonym-replacement-4h8l
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Performance benchmarking.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 import re
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 pythainlp.chat
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 import torch
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 pythainlp.classify
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 import gzip
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """Command line helpers."""
 
 
@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 import argparse
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Command line for PyThaiNLP's dataset/corpus management.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Command line for PyThaiNLP's soundex.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Command line for PyThaiNLP's taggers.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Command line for PyThaiNLP's tokenizers.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 pythainlp.cls
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 PyThaiNLP Coreference Resolution
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 from typing import List
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 from typing import List
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 import spacy
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Corpus related functions.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 """
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Get data from ConceptNet API at http://conceptnet.io
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Corpus related functions.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Provides an optional word list from International Components for Unicode (ICU) dictionary.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Thai unigram word frequency from OSCAR Corpus (words tokenized using ICU)
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Thai-English Transliteration Dictionary v1.4
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Thai Textbook Corpus (TTC) word frequency
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Tool for creating word lists
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Provides an optional word list from the Volubilis dictionary.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Provides an optional word list from Thai Wikipedia titles.
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 NLTK WordNet wrapper
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 pythainlp.el
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 from typing import List, Union
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Thai Text Generation
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Text generator using n-gram language model
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 """
 Thai2fit: Thai Wikipeida Language Model for Text Generation
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 import re
 
 
@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project
+# SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
 
 __all__ = ["KhaveeVerifier"]
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,5 @@`
`1`	`1`	`# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project`
	`2`	`+# SPDX-FileType: SOURCE`
`2`	`3`	`# SPDX-License-Identifier: Apache-2.0`
`3`	`4`
`4`	`5`	`FROM python:3.8-slim-buster`
Original file line number	Diff line number	Diff line change
`@@ -1,5 +1,6 @@`
`1`	`1`	`# -- coding: utf-8 --`
`2`	`2`	`# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project`
	`3`	`+# SPDX-FileType: SOURCE`
`3`	`4`	`# SPDX-License-Identifier: Apache-2.0`
`4`	`5`	`#`
`5`	`6`	`# Configuration file for the Sphinx documentation builder.`