From 188adf921ef6a0a3ec6b0ad323b37867644e50bc Mon Sep 17 00:00:00 2001
From: Eliran Wong <hkwebtech@gmail.com>
Date: Thu, 9 Aug 2018 13:42:39 +0100
Subject: [PATCH] script for updating OpenGNTGloss

---
 Script/updateOpenGNTGloss.py | 66 ++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)
 create mode 100644 Script/updateOpenGNTGloss.py

diff --git a/Script/updateOpenGNTGloss.py b/Script/updateOpenGNTGloss.py
new file mode 100644
index 0000000..d95b692
--- /dev/null
+++ b/Script/updateOpenGNTGloss.py
@@ -0,0 +1,66 @@
+# This file is created for merging latest work on OpenGNTGloss and NET2Words into main database file OpenGNT.csv
+
+import re
+
+inputFile = 'OpenGNTGloss_NET2Words_updating.csv'
+outputFile = 'OpenGNTGloss_NET2Words.csv'
+databaseFile = 'OpenGNT.csv'
+
+# export latest glosses
+
+f = open(inputFile,'r')
+newData = f.read()
+f.close()
+
+newData = re.sub('^.*?｛([^｛｝]*?)｝\t〈([^｜]*?)｜.*?$', r'\2\t\1＊', newData, flags=re.M)
+newData = re.sub('^.*?[^＊]\n', '', newData, flags=re.M)
+
+f = open(outputFile,'w')
+f.write(newData)
+f.close()
+
+# insert latest glosses into database
+
+f = open(databaseFile,'r')
+oldData = f.read()
+f.close()
+
+newData = newData + oldData
+
+f = open(databaseFile,'w')
+f.write(newData)
+f.close()
+
+# sort data
+
+lines = open(databaseFile, 'r').readlines()
+f = open(databaseFile, 'w')
+
+for line in sorted(lines, key=lambda line: line.split()[0]):
+    f.write(line)
+
+f.close()
+
+# merge glosses
+
+f = open(databaseFile,'r')
+newData = f.read()
+f.close()
+
+newData = re.sub('^.*?\t(.*?)＊\n([^〔]*?〔[^〔]*?〔[^〔]*?〔[^〔]*?〔[^〔]*?〔[^〔]*?〔[^｜]*?｜[^｜]*?｜)([^｜]*?｜[^｜]*?)〕', r'\2\1〕', newData, flags=re.M)
+
+f = open(databaseFile,'w')
+f.write(newData)
+f.close()
+
+# clean up OpenGNTGloss_NET2Words.csv
+
+f = open(outputFile,'r')
+newData = f.read()
+f.close()
+
+newData = re.sub('＊', '', newData)
+
+f = open(outputFile,'w')
+f.write(newData)
+f.close()