fixed #822 (remove BOM if present)

2 files changed, 2 insertions, 0 deletions

diff --git a/pygments/lexer.py b/pygments/lexer.py
index ad2c72d1..6f466a77 100644
--- a/pygments/lexer.py
+++ b/pygments/lexer.py
@@ -164,6 +164,7 @@ class Lexer(object):
             else:
                 text = text.decode(self.encoding)
         # text now *is* a unicode string
+        text = text.lstrip(u'\xef\xbb\xbf\ufeff') # remove BOM
         text = text.replace('\r\n', '\n')
         text = text.replace('\r', '\n')
         if self.stripall:
diff --git a/tests/test_examplefiles.py b/tests/test_examplefiles.py
index 41acf4ef..1d3515df 100644
--- a/tests/test_examplefiles.py
+++ b/tests/test_examplefiles.py
@@ -54,6 +54,7 @@ def check_lexer(lx, absfn, outfn):
         text = fp.read()
     finally:
         fp.close()
+    text = text.lstrip(u'\xef\xbb\xbf\ufeff') #remove BOM
     text = text.replace(b('\r\n'), b('\n'))
     text = text.strip(b('\n')) + b('\n')
     try: