Merge pull request #1312 from bact/data-env-var

Update PYTHAINLP_DATA examples

Author: bact

README_TH.md

@@ -110,7 +110,7 @@ PyThaiNLP ดาวน์โหลดข้อมูล (ดูแค็ตต
 [pythainlp-corpus](https://github.com/PyThaiNLP/pythainlp-corpus))
 ไปที่ `~/pythainlp-data` ตามค่าเริ่มต้น
 ตั้งค่า environment variable `PYTHAINLP_DATA` เพื่อเปลี่ยนตำแหน่งนี้
-(`PYTHAINLP_DATA_DIR` ยังคงใช้ได้แต่เลิกใช้แล้ว)
+(`PYTHAINLP_DATA_DIR` ยังคงใช้ได้ แต่จะเลิกใช้ในอนาคต)
 
 เมื่อใช้ PyThaiNLP ในสภาพแวดล้อมการคำนวณแบบกระจาย
 (เช่น Apache Spark) ให้ตั้งค่า environment variable `PYTHAINLP_DATA`

docker-compose.yml

@@ -8,4 +8,4 @@ services:
     stdin_open: true
     tty: true
     environment:
-      - PYTHAINLP_DATA_DIR=/workspace/pythainlp-data
+      - PYTHAINLP_DATA=/workspace/pythainlp-data

examples/distributed_pyspark.py

@@ -5,7 +5,7 @@
 Example: Using PyThaiNLP in PySpark Distributed Environment
 
 This example demonstrates how to use PyThaiNLP in a distributed environment
-like Apache Spark. The key is to set the PYTHAINLP_DATA_DIR environment
+like Apache Spark. The key is to set the PYTHAINLP_DATA environment
 variable inside the function that will be distributed to executor nodes.
 
 PyThaiNLP's core tokenization engines are thread-safe, making them suitable
@@ -45,9 +45,9 @@ def tokenize_thai(text):
         """
         import os
 
-        # Set PYTHAINLP_DATA_DIR before importing pythainlp
+        # Set PYTHAINLP_DATA before importing pythainlp
         # Use './pythainlp-data' to store data in current working directory
-        os.environ["PYTHAINLP_DATA_DIR"] = "./pythainlp-data"
+        os.environ["PYTHAINLP_DATA"] = "./pythainlp-data"
 
         # Now import pythainlp modules
         from pythainlp.tokenize import word_tokenize
@@ -96,7 +96,7 @@ def tokenize_udf(text):
         """
         import os
 
-        os.environ["PYTHAINLP_DATA_DIR"] = "./pythainlp-data"
+        os.environ["PYTHAINLP_DATA"] = "./pythainlp-data"
 
         from pythainlp.tokenize import word_tokenize
 
@@ -134,7 +134,7 @@ def process_thai_text(text):
         import os
 
         # Configure data directory
-        os.environ["PYTHAINLP_DATA_DIR"] = "./pythainlp-data"
+        os.environ["PYTHAINLP_DATA"] = "./pythainlp-data"
 
         # Import required modules
         from pythainlp.tag import pos_tag
@@ -197,7 +197,7 @@ def safe_tokenize(text):
 
         try:
             # Set environment variables
-            os.environ["PYTHAINLP_DATA_DIR"] = "./pythainlp-data"
+            os.environ["PYTHAINLP_DATA"] = "./pythainlp-data"
 
             # Import modules
             from pythainlp.tokenize import word_tokenize