Set encoding on SubprocessTabula initialization

chezou · Nov 20, 2023 · 5c23bb2 · 5c23bb2
1 parent 76db276
commit 5c23bb2
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/tabula/backend.py b/tabula/backend.py
@@ -89,6 +89,10 @@ def __init__(
                 )
             )
 
+        if encoding == "utf-8":
+            if not any("file.encoding" in opt for opt in java_options):
+                java_options += ["-Dfile.encoding=UTF8"]
+
         self.java_options = java_options
         self.encoding = encoding
 

diff --git a/tabula/io.py b/tabula/io.py
@@ -391,10 +391,6 @@ def read_pdf(
         if not any("java.awt.headless" in opt for opt in java_options):
             java_options += ["-Djava.awt.headless=true"]
 
-    if encoding == "utf-8":
-        if not any("file.encoding" in opt for opt in java_options):
-            java_options += ["-Dfile.encoding=UTF8"]
-
     path, temporary = localize_file(input_path, user_agent, use_raw_url=use_raw_url)
 
     if not os.path.exists(path):