From 9473b8468c2c979f69017be4eff9df80edc16c31 Mon Sep 17 00:00:00 2001
From: Zhao Yuting <91456992+THUzyt21@users.noreply.github.com>
Date: Wed, 24 Aug 2022 14:42:31 +0800
Subject: [PATCH] Create preprocess.py

If there are no spaces between sentences in your text file, use this file to generate a new file, which adds spaces between each token.
---
 examples/iwslt2012/punc0/local/preprocess.py | 27 ++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 examples/iwslt2012/punc0/local/preprocess.py

diff --git a/examples/iwslt2012/punc0/local/preprocess.py b/examples/iwslt2012/punc0/local/preprocess.py
new file mode 100644
index 00000000..03b27e89
--- /dev/null
+++ b/examples/iwslt2012/punc0/local/preprocess.py
@@ -0,0 +1,27 @@
+import argparse
+import os
+
+def process_sentence(line):
+   if line == '': return ''
+   res = line[0]
+   for i in range(1, len(line)):
+       res += (' ' + line[i])
+   return res
+
+if __name__ == "__main__":
+   paser = argparse.ArgumentParser(description = "Input filename")
+   paser.add_argument('-input_file')
+   paser.add_argument('-output_file')
+   sentence_cnt = 0
+   args = paser.parse_args()
+   with open(args.input_file, 'r') as f:
+       with open(args.output_file, 'w') as write_f:
+           while True:
+               line = f.readline()
+               if line:
+                   sentence_cnt += 1 
+                   write_f.write(process_sentence(line))
+               else:
+                   break
+   print('preprocess over')
+   print('total sentences number:', sentence_cnt)