From d3d0b6b87e50ae9ed102eac245b1d01d7928d431 Mon Sep 17 00:00:00 2001
From: Eliran Wong <hkwebtech@gmail.com>
Date: Fri, 17 Aug 2018 20:31:55 +0100
Subject: [PATCH] updated to align with new database format

---
 Script/updateOpenGNTGloss.py | 55 ++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 Script/updateOpenGNTGloss.py

diff --git a/Script/updateOpenGNTGloss.py b/Script/updateOpenGNTGloss.py
new file mode 100644
index 0000000..8cc59cf
--- /dev/null
+++ b/Script/updateOpenGNTGloss.py
@@ -0,0 +1,55 @@
+# 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)
+newData = re.sub('＊', '', newData)
+
+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(r'^(.*?\t)(.*?)\n\1([^\n〔]*?〔[^\n〔]*?〔[^\n〔]*?〔[^\n〔]*?〔[^\n〔]*?〔[^\n〔]*?〔[^\n〔]*?〔[^\n｜]*?｜[^\n｜]*?｜)([^\n｜]*?｜[^\n｜]*?)〕', r'\1\3\2〕', newData, flags=re.M)
+
+f = open(databaseFile,'w')
+f.write(newData)
+f.close()