Fixes #99: Add option to set file encoding to CSV reader.

beancount_reds_importers/libreader/csvreader.py

@@ -67,14 +67,15 @@ def initialize_reader(self, file):
         if getattr(self, "file", None) != file:
             self.file = file
             self.reader_ready = self.deep_identify(file)
+            self.file_encoding = getattr(self, "file_encoding", None)
             if self.reader_ready:
                 self.file_read_done = False
             # else:
             #     print("header_identifier failed---------------:")
             #     print(self.header_identifier, file.head())
 
     def deep_identify(self, file):
-        return re.match(self.header_identifier, file.head())
+        return re.match(self.header_identifier, file.head(encoding=self.file_encoding))
 
     def file_date(self, file):
         "Get the maximum date from the file."
@@ -135,7 +136,7 @@ def convert_date(d):
         return rdr
 
     def read_raw(self, file):
-        return etl.fromcsv(file.name)
+        return etl.fromcsv(file.name, encoding=self.file_encoding)
 
     def skip_until_main_table(self, rdr, col_labels=None):
         """Skip csv lines until the header line is found."""
@@ -186,7 +187,9 @@ def read_file(self, file):
             rdr = self.prepare_raw_file(rdr)
 
             # extract main table
-            rdr = rdr.skip(getattr(self, "skip_head_rows", 0))  # chop unwanted header rows
+            rdr = rdr.skip(
+                getattr(self, "skip_head_rows", 0)
+            )  # chop unwanted header rows
             rdr = rdr.head(
                 len(rdr) - getattr(self, "skip_tail_rows", 0) - 1
             )  # chop unwanted footer rows