Merge pull request #646 from PyThaiNLP/Fixed-#645

Add PYTHAINLP_READ_MODE

Author: wannaphong

docs/notes/installation.rst

@@ -67,6 +67,9 @@ Runtime Configurations
 
    Type `thainlp data path` at command line to see current PYTHAINLP_DATA_DIR.
 
+.. envvar:: PYTHAINLP_READ_MODE
+
+   This environment variable specifies config PyThaiNLP to read-only mode. (0 = False, 1 = True)
 
 FAQ
 ===
@@ -76,3 +79,6 @@ A: For Python 3.10+, We have python-crfsuite problem in pythainlp, so you can re
 
 Q: How to set the environment variables of each executor node in a distributed environment?
 A: You can read `PermissionError: [Errno 13] Permission denied: /home/pythainlp-data <https://github.com/PyThaiNLP/pythainlp/issues/475>`_.
+
+Q: How to fixed PyThaiNLP to read-only mode?
+A: You can config PYTHAINLP_READ_MODE.

pythainlp/corpus/__init__.py

@@ -38,6 +38,7 @@
 
 _CORPUS_DIRNAME = "corpus"
 _CORPUS_PATH = os.path.join(get_pythainlp_path(), _CORPUS_DIRNAME)
+_CHECK_MODE = os.getenv("PYTHAINLP_READ_MODE")
 
 # remote corpus catalog URL
 _CORPUS_DB_URL = (
@@ -51,7 +52,7 @@
 _CORPUS_DB_PATH = get_full_data_path(_CORPUS_DB_FILENAME)
 
 # create a local corpus database if it does not already exist
-if not os.path.exists(_CORPUS_DB_PATH):
+if not os.path.exists(_CORPUS_DB_PATH) and _CHECK_MODE != "1":
     TinyDB(_CORPUS_DB_PATH).close()
 
 

pythainlp/corpus/core.py

@@ -17,6 +17,9 @@
 from pythainlp import __version__
 
 
+_CHECK_MODE = os.getenv("PYTHAINLP_READ_MODE")
+
+
 def get_corpus_db(url: str) -> requests.Response:
     """
     Get corpus catalog from server.
@@ -42,7 +45,10 @@ def get_corpus_db_detail(name: str, version: str = None) -> dict:
     :return: details about a corpus
     :rtype: dict
     """
-    local_db = TinyDB(corpus_db_path())
+    if _CHECK_MODE == "1":
+        local_db = TinyDB(corpus_db_path(), access_mode='r')
+    else:
+        local_db = TinyDB(corpus_db_path(), access_mode='r')
     query = Query()
     if version is None:
         res = local_db.search(query.name == name)
@@ -354,6 +360,9 @@ def download(
     ``$HOME/pythainlp-data/``
     (e.g. ``/Users/bact/pythainlp-data/wiki_lm_lstm.pth``).
     """
+    if _CHECK_MODE == "1":
+        print("PyThaiNLP is read-only mode. It can't download.")
+        return False
     if not url:
         url = corpus_db_url()
 
@@ -453,6 +462,9 @@ def remove(name: str) -> bool:
         # FileNotFoundError: [Errno 2] No such file or directory:
         # '/usr/local/lib/python3.6/dist-packages/pythainlp/corpus/ttc'
     """
+    if _CHECK_MODE == "1":
+        print("PyThaiNLP is read-only mode. It can't remove corpus.")
+        return False
     db = TinyDB(corpus_db_path())
     query = Query()
     data = db.search(query.name == name)