From 63b0fc6269b38edf7234b9f151b80d81f614c0a3 Mon Sep 17 00:00:00 2001
From: Filipp Lepalaan <filipp@mac.com>
Date: Tue, 4 Aug 2015 10:11:24 +0300
Subject: Initial commit

First public commit
---
 servo/lib/ucsv.py | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)
 create mode 100644 servo/lib/ucsv.py

(limited to 'servo/lib/ucsv.py')

diff --git a/servo/lib/ucsv.py b/servo/lib/ucsv.py
new file mode 100644
index 0000000..91b2acf
--- /dev/null
+++ b/servo/lib/ucsv.py
@@ -0,0 +1,49 @@
+"""
+Borrwed from
+http://stackoverflow.com/questions/1846135/python-csv-library-with-unicode-utf-8-support-that-just-works
+"""
+
+import csv
+import codecs
+
+class UnicodeCsvReader(object):
+    def __init__(self, f, encoding="utf-8", **kwargs):
+        self.csv_reader = csv.reader(f, **kwargs)
+        self.encoding = encoding
+
+    def __iter__(self):
+        return self
+
+    def next(self):
+        # read and split the csv row into fields
+        row = self.csv_reader.next() 
+        # now decode
+        return [unicode(cell, self.encoding) for cell in row]
+
+    @property
+    def line_num(self):
+        return self.csv_reader.line_num
+
+
+class UnicodeDictReader(csv.DictReader):
+    def __init__(self, f, encoding="utf-8", fieldnames=None, **kwargs):
+        csv.DictReader.__init__(self, f, fieldnames=fieldnames, **kwargs)
+        self.reader = UnicodeCsvReader(f, encoding=encoding, **kwargs)
+
+
+def read_excel_file(f):
+    dialect = csv.Sniffer().sniff(codecs.EncodedFile(f, "utf-8").read(1024))
+    #f.open()
+    return UnicodeCsvReader(codecs.EncodedFile(f, "utf-8"),
+                            "utf-8", dialect=dialect)
+
+def main():
+    import sys
+    with codecs.open(sys.argv[1], 'rUb') as csvfile:
+        reader = read_excel_file(csvfile)
+        for row in reader:
+            print u', '.join(row)
+
+
+if __name__ == '__main__':
+    main()
-- 
cgit v1.2.3