* transcode.c (sym_partial_input): new variable.

  (econv_primitive_convert): accept a hash as 5th argument as well.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19131 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

3 files changed, 66 insertions, 42 deletions

diff --git a/ChangeLog b/ChangeLog
index a25bddd859..8e90c1e186 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+Thu Sep  4 21:46:21 2008  Tanaka Akira  <akr@fsij.org>
+
+	* transcode.c (sym_partial_input): new variable.
+	  (econv_primitive_convert): accept a hash as 5th argument as well.
+
 Thu Sep  4 21:04:27 2008  Tanaka Akira  <akr@fsij.org>
 
 	* transcode.c (sym_universal_newline_decoder): new variable.
diff --git a/test/ruby/test_econv.rb b/test/ruby/test_econv.rb
index e7256c12f3..2e4409dbc5 100644
--- a/test/ruby/test_econv.rb
+++ b/test/ruby/test_econv.rb
@@ -1,8 +1,8 @@
 require 'test/unit'
 
 class TestEncodingConverter < Test::Unit::TestCase
-  def check_ec(edst, esrc, eres, dst, src, ec, off, len, flags=0)
-    res = ec.primitive_convert(src, dst, off, len, flags)
+  def check_ec(edst, esrc, eres, dst, src, ec, off, len, opts=nil)
+    res = ec.primitive_convert(src, dst, off, len, opts)
     assert_equal([edst.dup.force_encoding("ASCII-8BIT"),
                   esrc.dup.force_encoding("ASCII-8BIT"),
                   eres],
@@ -11,11 +11,11 @@ class TestEncodingConverter < Test::Unit::TestCase
                   res])
   end
 
-  def assert_econv(converted, eres, obuf_bytesize, ec, consumed, rest, flags=0)
+  def assert_econv(converted, eres, obuf_bytesize, ec, consumed, rest, opts=nil)
     ec = Encoding::Converter.new(*ec) if Array === ec
     i = consumed + rest
     o = ""
-    ret = ec.primitive_convert(i, o, 0, obuf_bytesize, flags)
+    ret = ec.primitive_convert(i, o, 0, obuf_bytesize, opts)
     assert_equal([converted,    eres,       rest],
                  [o,            ret,           i])
   end
@@ -61,20 +61,20 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_output_region
     ec = Encoding::Converter.new("UTF-8", "EUC-JP")
-    ec.primitive_convert(src="a", dst="b", nil, 1, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert(src="a", dst="b", nil, 1, :partial_input=>true)
     assert_equal("ba", dst)
-    ec.primitive_convert(src="a", dst="b", 0, 1, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert(src="a", dst="b", 0, 1, :partial_input=>true)
     assert_equal("a", dst)
-    ec.primitive_convert(src="a", dst="b", 1, 1, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert(src="a", dst="b", 1, 1, :partial_input=>true)
     assert_equal("ba", dst)
     assert_raise(ArgumentError) {
-      ec.primitive_convert(src="a", dst="b", 2, 1, Encoding::Converter::PARTIAL_INPUT)
+      ec.primitive_convert(src="a", dst="b", 2, 1, :partial_input=>true)
     }
     assert_raise(ArgumentError) {
-      ec.primitive_convert(src="a", dst="b", -1, 1, Encoding::Converter::PARTIAL_INPUT)
+      ec.primitive_convert(src="a", dst="b", -1, 1, :partial_input=>true)
     }
     assert_raise(ArgumentError) {
-      ec.primitive_convert(src="a", dst="b", 1, -1, Encoding::Converter::PARTIAL_INPUT)
+      ec.primitive_convert(src="a", dst="b", 1, -1, :partial_input=>true)
     }
   end
 
@@ -114,7 +114,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_partial_input
     ec = Encoding::Converter.new("UTF-8", "EUC-JP")
-    ret = ec.primitive_convert(src="", dst="", nil, 10, Encoding::Converter::PARTIAL_INPUT)
+    ret = ec.primitive_convert(src="", dst="", nil, 10, :partial_input=>true)
     assert_equal(:source_buffer_empty, ret)
     ret = ec.primitive_convert(src="", dst="", nil, 10)
     assert_equal(:finished, ret)
@@ -153,7 +153,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_iso2022jp_encode
     ec = Encoding::Converter.new("EUC-JP", "ISO-2022-JP")
-    a = ["", src="", ec, nil, 50, Encoding::Converter::PARTIAL_INPUT]
+    a = ["", src="", ec, nil, 50, :partial_input=>true]
     src << "a";        check_ec("a",                           "", :source_buffer_empty, *a)
     src << "\xA2";     check_ec("a",                           "", :source_buffer_empty, *a)
     src << "\xA4";     check_ec("a\e$B\"$",                    "", :source_buffer_empty, *a)
@@ -166,7 +166,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_iso2022jp_decode
     ec = Encoding::Converter.new("ISO-2022-JP", "EUC-JP")
-    a = ["", src="", ec, nil, 50, Encoding::Converter::PARTIAL_INPUT]
+    a = ["", src="", ec, nil, 50, :partial_input=>true]
     src << "a";         check_ec("a",                   "", :source_buffer_empty, *a)
     src << "\e";        check_ec("a",                   "", :source_buffer_empty, *a)
     src << "$";         check_ec("a",                   "", :source_buffer_empty, *a)
@@ -212,7 +212,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_invalid4
     ec = Encoding::Converter.new("Shift_JIS", "EUC-JP")
-    a =     ["", "abc\xFFdef", ec, nil, 10, Encoding::Converter::OUTPUT_FOLLOWED_BY_INPUT]
+    a =     ["", "abc\xFFdef", ec, nil, 10, :output_followed_by_input=>true]
     check_ec("a", "bc\xFFdef", :output_followed_by_input, *a)
     check_ec("ab", "c\xFFdef", :output_followed_by_input, *a)
     check_ec("abc", "\xFFdef", :output_followed_by_input, *a)
@@ -225,7 +225,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_invalid_utf16le
     ec = Encoding::Converter.new("UTF-16LE", "UTF-8")
-    a = ["", src="", ec, nil, 50, Encoding::Converter::PARTIAL_INPUT]
+    a = ["", src="", ec, nil, 50, :partial_input=>true]
     src << "A";         check_ec("",                            "", :source_buffer_empty, *a)
     src << "\x00";      check_ec("A",                           "", :source_buffer_empty, *a)
     src << "\x00";      check_ec("A",                           "", :source_buffer_empty, *a)
@@ -244,7 +244,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_invalid_utf16be
     ec = Encoding::Converter.new("UTF-16BE", "UTF-8")
-    a = ["", src="", ec, nil, 50, Encoding::Converter::PARTIAL_INPUT]
+    a = ["", src="", ec, nil, 50, :partial_input=>true]
     src << "\x00";      check_ec("",                            "", :source_buffer_empty, *a)
     src << "A";         check_ec("A",                           "", :source_buffer_empty, *a)
     src << "\xd8";      check_ec("A",                           "", :source_buffer_empty, *a)
@@ -263,7 +263,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_invalid_utf32be
     ec = Encoding::Converter.new("UTF-32BE", "UTF-8")
-    a = ["", src="", ec, nil, 50, Encoding::Converter::PARTIAL_INPUT]
+    a = ["", src="", ec, nil, 50, :partial_input=>true]
     src << "\x00";      check_ec("",    "", :source_buffer_empty, *a)
     src << "\x00";      check_ec("",    "", :source_buffer_empty, *a)
     src << "\x00";      check_ec("",    "", :source_buffer_empty, *a)
@@ -287,7 +287,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_invalid_utf32le
     ec = Encoding::Converter.new("UTF-32LE", "UTF-8")
-    a = ["", src="", ec, nil, 50, Encoding::Converter::PARTIAL_INPUT]
+    a = ["", src="", ec, nil, 50, :partial_input=>true]
     src << "A";         check_ec("",    "", :source_buffer_empty, *a)
     src << "\x00";      check_ec("",    "", :source_buffer_empty, *a)
     src << "\x00";      check_ec("",    "", :source_buffer_empty, *a)
@@ -319,7 +319,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_errors2
     ec = Encoding::Converter.new("UTF-16BE", "EUC-JP")
-    a =     ["", "\xFF\xFE\x00A\xDC\x00\x00B", ec, nil, 10, Encoding::Converter::OUTPUT_FOLLOWED_BY_INPUT]
+    a =     ["", "\xFF\xFE\x00A\xDC\x00\x00B", ec, nil, 10, :output_followed_by_input=>true]
     check_ec("",         "\x00A\xDC\x00\x00B", :undefined_conversion, *a)
     check_ec("A",             "\xDC\x00\x00B", :output_followed_by_input, *a)
     check_ec("A",                     "\x00B", :invalid_byte_sequence, *a)
@@ -329,7 +329,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_universal_newline
     ec = Encoding::Converter.new("UTF-8", "EUC-JP", universal_newline_decoder: true)
-    a = ["", src="", ec, nil, 50, Encoding::Converter::PARTIAL_INPUT]
+    a = ["", src="", ec, nil, 50, :partial_input=>true]
     src << "abc\r\ndef"; check_ec("abc\ndef",                             "", :source_buffer_empty, *a)
     src << "ghi\njkl";   check_ec("abc\ndefghi\njkl",                     "", :source_buffer_empty, *a)
     src << "mno\rpqr";   check_ec("abc\ndefghi\njklmno\npqr",             "", :source_buffer_empty, *a)
@@ -340,7 +340,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_universal_newline2
     ec = Encoding::Converter.new("", "", universal_newline_decoder: true)
-    a = ["", src="", ec, nil, 50, Encoding::Converter::PARTIAL_INPUT]
+    a = ["", src="", ec, nil, 50, :partial_input=>true]
     src << "abc\r\ndef"; check_ec("abc\ndef",                             "", :source_buffer_empty, *a)
     src << "ghi\njkl";   check_ec("abc\ndefghi\njkl",                     "", :source_buffer_empty, *a)
     src << "mno\rpqr";   check_ec("abc\ndefghi\njklmno\npqr",             "", :source_buffer_empty, *a)
@@ -371,7 +371,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_output_followed_by_input
     ec = Encoding::Converter.new("UTF-8", "EUC-JP")
-    a =     ["",  "abc\u{3042}def", ec, nil, 100, Encoding::Converter::OUTPUT_FOLLOWED_BY_INPUT]
+    a =     ["",  "abc\u{3042}def", ec, nil, 100, :output_followed_by_input=>true]
     check_ec("a",  "bc\u{3042}def", :output_followed_by_input, *a)
     check_ec("ab",  "c\u{3042}def", :output_followed_by_input, *a)
     check_ec("abc",  "\u{3042}def", :output_followed_by_input, *a)
@@ -408,7 +408,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_errinfo_valid_partial_character
     ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
-    ec.primitive_convert(src="\xa4", dst="", nil, 10, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert(src="\xa4", dst="", nil, 10, :partial_input=>true)
     assert_errinfo(:source_buffer_empty, nil, nil, nil, nil, ec)
   end
 
@@ -428,23 +428,23 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_output_iso2022jp
     ec = Encoding::Converter.new("EUC-JP", "ISO-2022-JP")
-    ec.primitive_convert(src="\xa1\xa1", dst="", nil, 10, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert(src="\xa1\xa1", dst="", nil, 10, :partial_input=>true)
     assert_equal("\e$B!!".force_encoding("ISO-2022-JP"), dst)
     assert_equal(nil, ec.insert_output("???"))
-    ec.primitive_convert("", dst, nil, 10, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert("", dst, nil, 10, :partial_input=>true)
     assert_equal("\e$B!!\e(B???".force_encoding("ISO-2022-JP"), dst)
-    ec.primitive_convert(src="\xa1\xa2", dst, nil, 10, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert(src="\xa1\xa2", dst, nil, 10, :partial_input=>true)
     assert_equal("\e$B!!\e(B???\e$B!\"".force_encoding("ISO-2022-JP"), dst)
 
     assert_equal(nil, ec.insert_output("\xA1\xA1".force_encoding("EUC-JP")))
-    ec.primitive_convert("", dst, nil, 10, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert("", dst, nil, 10, :partial_input=>true)
     assert_equal("\e$B!!\e(B???\e$B!\"!!".force_encoding("ISO-2022-JP"), dst) 
 
-    ec.primitive_convert(src="\xa1\xa3", dst, nil, 10, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert(src="\xa1\xa3", dst, nil, 10, :partial_input=>true)
     assert_equal("\e$B!!\e(B???\e$B!\"!!!\#".force_encoding("ISO-2022-JP"), dst)
 
     assert_equal(nil, ec.insert_output("\u3042"))
-    ec.primitive_convert("", dst, nil, 10, Encoding::Converter::PARTIAL_INPUT)
+    ec.primitive_convert("", dst, nil, 10, :partial_input=>true)
     assert_equal("\e$B!!\e(B???\e$B!\"!!!\#$\"".force_encoding("ISO-2022-JP"), dst)
 
     assert_raise(Encoding::ConversionUndefined) {
@@ -561,7 +561,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_noconv_partial
     ec = Encoding::Converter.new("", "")
-    a =     ["", "abcdefg", ec, nil, 2, Encoding::Converter::PARTIAL_INPUT]
+    a =     ["", "abcdefg", ec, nil, 2, :partial_input=>true]
     check_ec("ab", "cdefg", :destination_buffer_full, *a)
     check_ec("abcd", "efg", :destination_buffer_full, *a)
     check_ec("abcdef", "g", :destination_buffer_full, *a)
@@ -570,7 +570,7 @@ class TestEncodingConverter < Test::Unit::TestCase
 
   def test_noconv_output_followed_by_input
     ec = Encoding::Converter.new("", "")
-    a =     ["", "abcdefg", ec, nil, 2, Encoding::Converter::OUTPUT_FOLLOWED_BY_INPUT]
+    a =     ["", "abcdefg", ec, nil, 2, :output_followed_by_input=>true]
     check_ec("a", "bcdefg", :output_followed_by_input, *a)
     check_ec("ab", "cdefg", :output_followed_by_input, *a)
     check_ec("abc", "defg", :output_followed_by_input, *a)
diff --git a/transcode.c b/transcode.c
index 7f3f0665b2..96b3666c62 100644
--- a/transcode.c
+++ b/transcode.c
@@ -24,6 +24,7 @@ static VALUE sym_invalid, sym_undef, sym_ignore, sym_replace;
 static VALUE sym_universal_newline_decoder;
 static VALUE sym_crlf_newline_encoder;
 static VALUE sym_cr_newline_encoder;
+static VALUE sym_partial_input;
 
 static VALUE sym_invalid_byte_sequence;
 static VALUE sym_undefined_conversion;
@@ -2527,11 +2528,15 @@ econv_result_to_symbol(rb_econv_result_t res)
  *   ec.primitive_convert(source_buffer, destination_buffer) -> symbol
  *   ec.primitive_convert(source_buffer, destination_buffer, destination_byteoffset) -> symbol
  *   ec.primitive_convert(source_buffer, destination_buffer, destination_byteoffset, destination_bytesize) -> symbol
- *   ec.primitive_convert(source_buffer, destination_buffer, destination_byteoffset, destination_bytesize, flags) -> symbol
+ *   ec.primitive_convert(source_buffer, destination_buffer, destination_byteoffset, destination_bytesize, opt) -> symbol
  *
- * possible flags:
- *   Encoding::Converter::PARTIAL_INPUT # source buffer may be part of larger source
- *   Encoding::Converter::OUTPUT_FOLLOWED_BY_INPUT # stop conversion after output before input
+ * possible opt elements:
+ *   hash form:
+ *     :partial_input => true           # source buffer may be part of larger source
+ *     output_followed_by_input => true # stop conversion after output before input
+ *   integer form:
+ *     Encoding::Converter::PARTIAL_INPUT
+ *     Encoding::Converter::OUTPUT_FOLLOWED_BY_INPUT
  *
  * possible results:
  *    :invalid_byte_sequence
@@ -2583,14 +2588,14 @@ econv_result_to_symbol(rb_econv_result_t res)
  * primitive_convert stops conversion when one of following condition met.
  * - invalid byte sequence found in source buffer (:invalid_byte_sequence)
  * - unexpected end of source buffer (:incomplete_input)
- *   this occur only when PARTIAL_INPUT is not specified.
+ *   this occur only when :partial_input is not specified.
  * - character not representable in output encoding (:undefined_conversion)
  * - after some output is generated, before input is done (:output_followed_by_input)
- *   this occur only when OUTPUT_FOLLOWED_BY_INPUT is specified.
+ *   this occur only when :output_followed_by_input is specified.
  * - destination buffer is full (:destination_buffer_full)
  *   this occur only when destination_bytesize is non-nil.
  * - source buffer is empty (:source_buffer_empty)
- *   this occur only when PARTIAL_INPUT is specified.
+ *   this occur only when :partial_input is specified.
  * - conversion is finished (:finished)
  *
  * example:
@@ -2612,7 +2617,7 @@ econv_result_to_symbol(rb_econv_result_t res)
 static VALUE
 econv_primitive_convert(int argc, VALUE *argv, VALUE self)
 {
-    VALUE input, output, output_byteoffset_v, output_bytesize_v, flags_v;
+    VALUE input, output, output_byteoffset_v, output_bytesize_v, opt, flags_v;
     rb_econv_t *ec = check_econv(self);
     rb_econv_result_t res;
     const unsigned char *ip, *is;
@@ -2621,7 +2626,7 @@ econv_primitive_convert(int argc, VALUE *argv, VALUE self)
     unsigned long output_byteend;
     int flags;
 
-    rb_scan_args(argc, argv, "23", &input, &output, &output_byteoffset_v, &output_bytesize_v, &flags_v);
+    rb_scan_args(argc, argv, "23", &input, &output, &output_byteoffset_v, &output_bytesize_v, &opt);
 
     if (NIL_P(output_byteoffset_v))
         output_byteoffset = 0; /* dummy */
@@ -2633,10 +2638,23 @@ econv_primitive_convert(int argc, VALUE *argv, VALUE self)
     else
         output_bytesize = NUM2LONG(output_bytesize_v);
 
-    if (NIL_P(flags_v))
+    if (NIL_P(opt)) {
         flags = 0;
-    else
+    }
+    else if (!NIL_P(flags_v = rb_check_to_integer(opt, "to_int"))) {
         flags = NUM2INT(flags_v);
+    }
+    else {
+        VALUE v;
+        opt = rb_convert_type(opt, T_HASH, "Hash", "to_hash");
+        flags = 0;
+        v = rb_hash_aref(opt, sym_partial_input);
+        if (RTEST(v))
+            flags |= ECONV_PARTIAL_INPUT;
+        v = rb_hash_aref(opt, sym_output_followed_by_input);
+        if (RTEST(v))
+            flags |= ECONV_OUTPUT_FOLLOWED_BY_INPUT;
+    }
 
     StringValue(output);
     if (!NIL_P(input))
@@ -3301,6 +3319,7 @@ Init_transcode(void)
     sym_universal_newline_decoder = ID2SYM(rb_intern("universal_newline_decoder"));
     sym_crlf_newline_encoder = ID2SYM(rb_intern("crlf_newline_encoder"));
     sym_cr_newline_encoder = ID2SYM(rb_intern("cr_newline_encoder"));
+    sym_partial_input = ID2SYM(rb_intern("partial_input"));
 
     rb_define_method(rb_cString, "encode", str_encode, -1);
     rb_define_method(rb_cString, "encode!", str_encode_bang, -1);