Fix dockerfile format (opea-project#363)

Signed-off-by: zepan <[email protected]>

.github/workflows/docker/code-scan.dockerfile

@@ -4,7 +4,7 @@
 ARG UBUNTU_VER=22.04
 FROM ubuntu:${UBUNTU_VER} as devel
 
-ENV LANG C.UTF-8
+ENV LANG=C.UTF-8
 
 RUN apt-get update && apt-get install -y --no-install-recommends --fix-missing \
     aspell \

.github/workflows/docker/ut.dockerfile

@@ -4,7 +4,7 @@
 ARG UBUNTU_VER=22.04
 FROM ubuntu:${UBUNTU_VER} as devel
 
-ENV LANG C.UTF-8
+ENV LANG=C.UTF-8
 
 RUN apt-get update && apt-get install -y --no-install-recommends --fix-missing \
     aspell \

.github/workflows/scripts/codeScan/bandit.sh

@@ -6,7 +6,7 @@
 source /GenAIComps/.github/workflows/scripts/change_color
 pip install bandit==1.7.8
 log_dir=/GenAIComps/.github/workflows/scripts/codeScan
-python -m bandit -r -lll -iii /GenAIComps 2>&1 | tee ${log_dir}/bandit.log
+python -m bandit -r -lll -iii /GenAIComps > ${log_dir}/bandit.log
 exit_code=$?
 
 $BOLD_YELLOW && echo " -----------------  Current log file output start --------------------------"

comps/agent/langchain/docker/Dockerfile

@@ -3,7 +3,7 @@
 
 FROM python:3.11-slim
 
-ENV LANG C.UTF-8
+ENV LANG=C.UTF-8
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     build-essential \

comps/chathistory/mongo/docker/Dockerfile

@@ -3,7 +3,7 @@
 
 FROM python:3.11-slim
 
-ENV LANG C.UTF-8
+ENV LANG=C.UTF-8
 
 RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
     build-essential \

comps/dataprep/redis/langchain_ray/prepare_doc_redis_on_ray.py

@@ -75,7 +75,7 @@ def prepare_env(enable_ray=False, pip_requirements=None):
 def generate_log_name(file_list):
     file_set = f"{sorted(file_list)}"
     # print(f"file_set: {file_set}")
-    md5_str = hashlib.md5(file_set.encode()).hexdigest()
+    md5_str = hashlib.md5(file_set.encode(), usedforsecurity=False).hexdigest()
     return f"status/status_{md5_str}.log"
 
 

comps/dataprep/utils.py

@@ -11,6 +11,7 @@
 import re
 import shutil
 import signal
+import subprocess
 import timeit
 import unicodedata
 import urllib.parse
@@ -157,7 +158,19 @@ def load_doc(doc_path):
     """Load doc file."""
     print("Converting doc file to docx file...")
     docx_path = doc_path + "x"
-    os.system(f"libreoffice --headless --invisible --convert-to docx --outdir {os.path.dirname(docx_path)} {doc_path}")
+    subprocess.run(
+        [
+            "libreoffice",
+            "--headless",
+            "--invisible",
+            "--convert-to",
+            "docx",
+            "--outdir",
+            os.path.dirname(docx_path),
+            doc_path,
+        ],
+        check=True,
+    )
     print("Converted doc file to docx file.")
     text = load_docx(docx_path)
     os.remove(docx_path)
@@ -196,7 +209,19 @@ def load_ppt(ppt_path):
     """Load ppt file."""
     print("Converting ppt file to pptx file...")
     pptx_path = ppt_path + "x"
-    os.system(f"libreoffice --headless --invisible --convert-to pptx --outdir {os.path.dirname(pptx_path)} {ppt_path}")
+    subprocess.run(
+        [
+            "libreoffice",
+            "--headless",
+            "--invisible",
+            "--convert-to",
+            "docx",
+            "--outdir",
+            os.path.dirname(pptx_path),
+            ppt_path,
+        ],
+        check=True,
+    )
     print("Converted ppt file to pptx file.")
     text = load_pptx(pptx_path)
     os.remove(pptx_path)

comps/guardrails/pii_detection/data_utils.py

@@ -6,6 +6,7 @@
 import multiprocessing
 import os
 import re
+import subprocess
 import unicodedata
 from urllib.parse import urlparse, urlunparse
 
@@ -79,7 +80,8 @@ def load_doc(doc_path):
     """Load doc file."""
     txt_path = doc_path.replace(".doc", ".txt")
     try:
-        os.system(f'antiword "{doc_path}" > "{txt_path}"')
+        with open(txt_path, "w") as outfile:
+            subprocess.run(["antiword", doc_path], stdout=outfile, check=True)
     except:
         raise AssertionError(
             "antiword failed or not installed, if not installed,"

comps/guardrails/pii_detection/utils.py

@@ -74,7 +74,7 @@ def wrapper(*args, **kwargs):
 def generate_log_name(file_list):
     file_set = f"{sorted(file_list)}"
     # print(f"file_set: {file_set}")
-    md5_str = hashlib.md5(file_set.encode()).hexdigest()
+    md5_str = hashlib.md5(file_set.encode(), usedforsecurity=False).hexdigest()
     return f"status/status_{md5_str}.log"