Remove unicode BOM from SSA files.

4 files changed, 18 insertions, 13 deletions

diff --git a/src/ssa_reader.cc b/src/ssa_reader.cc
index bac893b..859a00e 100644
--- a/src/ssa_reader.cc
+++ b/src/ssa_reader.cc
@@ -227,6 +227,7 @@ SSAReader::read (function<optional<string> ()> get_line)
 		}
 
 		trim (*line);
+		remove_unicode_bom (line);
 
 		if (starts_with (*line, ";") || line->empty ()) {
 			continue;
diff --git a/src/subrip_reader.cc b/src/subrip_reader.cc
index a82862c..f71843e 100644
--- a/src/subrip_reader.cc
+++ b/src/subrip_reader.cc
@@ -81,17 +81,7 @@ SubripReader::read (function<optional<string> ()> get_line)
 		}
 
 		trim_right_if (*line, boost::is_any_of ("\n\r"));
-
-		if (
-			line->length() >= 3 &&
-			static_cast<unsigned char> (line.get()[0]) == 0xef &&
-			static_cast<unsigned char> (line.get()[1]) == 0xbb &&
-			static_cast<unsigned char> (line.get()[2]) == 0xbf
-			) {
-
-			/* Skip Unicode byte order mark */
-			line = line->substr (3);
-		}
+		remove_unicode_bom (line);
 
 		switch (state) {
 		case COUNTER:
diff --git a/src/util.cc b/src/util.cc
index 5510d8e..a736a91 100644
--- a/src/util.cc
+++ b/src/util.cc
@@ -65,3 +65,18 @@ sub::get_line_file (FILE* f)
 
 	return string (buffer);
 }
+
+void
+sub::remove_unicode_bom (optional<string>& line)
+{
+	if (
+		line->length() >= 3 &&
+		static_cast<unsigned char> (line.get()[0]) == 0xef &&
+		static_cast<unsigned char> (line.get()[1]) == 0xbb &&
+		static_cast<unsigned char> (line.get()[2]) == 0xbf
+		) {
+
+		/* Skip Unicode byte order mark */
+		line = line->substr (3);
+	}
+}
diff --git a/src/util.h b/src/util.h
index 9d3edc2..dea8023 100644
--- a/src/util.h
+++ b/src/util.h
@@ -23,9 +23,8 @@
 namespace sub {
 
 extern bool empty_or_white_space (std::string s);
+extern void remove_unicode_bom (boost::optional<std::string>& line);
 extern boost::optional<std::string> get_line_stringstream (std::stringstream* str);
 extern boost::optional<std::string> get_line_file (FILE* f);
 
 }
-
-