From ffe96f7c8745d03dc85a39fabff84a919744c7fe Mon Sep 17 00:00:00 2001
From: Judith Jeong <calliope1226@hotmail.com>
Date: Sun, 27 Jun 2021 18:45:19 +0900
Subject: [PATCH] Fix several lines to make working in Windows

---
 wikiextractor/WikiExtractor.py | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/wikiextractor/WikiExtractor.py b/wikiextractor/WikiExtractor.py
index 509158a0..c8c05b92 100755
--- a/wikiextractor/WikiExtractor.py
+++ b/wikiextractor/WikiExtractor.py
@@ -160,6 +160,9 @@ def __init__(self, nextFile, max_file_size=0, compress=True):
         self.nextFile = nextFile
         self.compress = compress
         self.max_file_size = max_file_size
+        self.file = None
+
+    def open_file(self):
         self.file = self.open(self.nextFile.next())
 
     def reserve(self, size):
@@ -181,7 +184,7 @@ def open(self, filename):
         if self.compress:
             return bz2.BZ2File(filename + '.bz2', 'w')
         else:
-            return open(filename, 'w')
+            return open(filename, 'w', encoding='utf-8')
 
 
 # ----------------------------------------------------------------------
@@ -445,8 +448,6 @@ def process_dump(input_file, template_file, out_file, file_size, file_compress,
     # wait for it to finish
     reduce.join()
 
-    if output != sys.stdout:
-        output.close()
     extract_duration = default_timer() - extract_start
     extract_rate = ordinal / extract_duration
     logging.info("Finished %d-process extraction of %d articles in %.1fs (%.1f art/s)",
@@ -481,6 +482,9 @@ def reduce_process(output_queue, output):
     :param output: file object where to print.
     """
 
+    if isinstance(output, OutputSplitter):
+        output.open_file()
+
     interval_start = default_timer()
     period = 100000
     # FIXME: use a heap
@@ -504,6 +508,9 @@ def reduce_process(output_queue, output):
             ordinal, text = pair
             ordering_buffer[ordinal] = text
 
+    if isinstance(output, OutputSplitter):
+        output.close()
+
 
 # ----------------------------------------------------------------------