الفرق بين المراجعتين لصفحة: «Ruby/Encoding/Converter/primitive errinfo»

من موسوعة حسوب
< Ruby‏ | Encoding‏ | Converter
طلا ملخص تعديل
طلا ملخص تعديل
 
سطر 29: سطر 29:
مثالٌ عن استخدام التابع <code>primitive_errinfo</code>:<syntaxhighlight lang="ruby">
مثالٌ عن استخدام التابع <code>primitive_errinfo</code>:<syntaxhighlight lang="ruby">
# \xff is invalid as EUC-JP.
# \xff is invalid as EUC-JP.
ec = Encoding::Converter.new("EUC-JP", "Shift_JIS")
ec = Encoding::Converter.new("EUC-JP", "Shift_JIS")
ec.primitive_convert(src="\xff", dst="", nil, 10)
ec.primitive_convert(src="\xff", dst="", nil, 10)
p ec.primitive_errinfo
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "EUC-JP", "UTF-8", "\xFF", ""]
#=> [:invalid_byte_sequence, "EUC-JP", "UTF-8", "\xFF", ""]


# HIRAGANA LETTER A (\xa4\xa2 in EUC-JP) is not representable in ISO-8859-1.
# HIRAGANA LETTER A (\xa4\xa2 in EUC-JP) is not representable in ISO-8859-1.
# Since this error is occur in UTF-8 to ISO-8859-1 conversion,
# Since this error is occur in UTF-8 to ISO-8859-1 conversion,
# error_bytes is HIRAGANA LETTER A in UTF-8 (\xE3\x81\x82).
# error_bytes is HIRAGANA LETTER A in UTF-8 (\xE3\x81\x82).
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec.primitive_convert(src="\xa4\xa2", dst="", nil, 10)
ec.primitive_convert(src="\xa4\xa2", dst="", nil, 10)
p ec.primitive_errinfo
p ec.primitive_errinfo
#=> [:undefined_conversion, "UTF-8", "ISO-8859-1", "\xE3\x81\x82", ""]
#=> [:undefined_conversion, "UTF-8", "ISO-8859-1", "\xE3\x81\x82", ""]


# partial character is invalid
# partial character is invalid
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec.primitive_convert(src="\xa4", dst="", nil, 10)
ec.primitive_convert(src="\xa4", dst="", nil, 10)
p ec.primitive_errinfo
p ec.primitive_errinfo
#=> [:incomplete_input, "EUC-JP", "UTF-8", "\xA4", ""]
#=> [:incomplete_input, "EUC-JP", "UTF-8", "\xA4", ""]


# Encoding::Converter::PARTIAL_INPUT prevents invalid errors by
# Encoding::Converter::PARTIAL_INPUT prevents invalid errors by
# partial characters.
# partial characters.
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
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, Encoding::Converter::PARTIAL_INPUT)
p ec.primitive_errinfo
p ec.primitive_errinfo
#=> [:source_buffer_empty, nil, nil, nil, nil]
#=> [:source_buffer_empty, nil, nil, nil, nil]


# \xd8\x00\x00@ is invalid as UTF-16BE because
# \xd8\x00\x00@ is invalid as UTF-16BE because
# no low surrogate after high surrogate (\xd8\x00).
# no low surrogate after high surrogate (\xd8\x00).
# It is detected by 3rd byte (\00) which is part of next character.
# It is detected by 3rd byte (\00) which is part of next character.
# So the high surrogate (\xd8\x00) is discarded and
# So the high surrogate (\xd8\x00) is discarded and
# the 3rd byte is read again later.
# the 3rd byte is read again later.
# Since the byte is buffered in ec, it is dropped from src.
# Since the byte is buffered in ec, it is dropped from src.
ec = Encoding::Converter.new("UTF-16BE", "UTF-8")
ec = Encoding::Converter.new("UTF-16BE", "UTF-8")
ec.primitive_convert(src="\xd8\x00\x00@", dst="", nil, 10)
ec.primitive_convert(src="\xd8\x00\x00@", dst="", nil, 10)
p ec.primitive_errinfo
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "UTF-16BE", "UTF-8", "\xD8\x00", "\x00"]
#=> [:invalid_byte_sequence, "UTF-16BE", "UTF-8", "\xD8\x00", "\x00"]
p src
p src
#=> "@"
#=> "@"


# Similar to UTF-16BE, \x00\xd8@\x00 is invalid as UTF-16LE.
# Similar to UTF-16BE, \x00\xd8@\x00 is invalid as UTF-16LE.
# The problem is detected by 4th byte.
# The problem is detected by 4th byte.
ec = Encoding::Converter.new("UTF-16LE", "UTF-8")
ec = Encoding::Converter.new("UTF-16LE", "UTF-8")
ec.primitive_convert(src="\x00\xd8@\x00", dst="", nil, 10)
ec.primitive_convert(src="\x00\xd8@\x00", dst="", nil, 10)
p ec.primitive_errinfo
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "UTF-16LE", "UTF-8", "\x00\xD8", "@\x00"]
#=> [:invalid_byte_sequence, "UTF-16LE", "UTF-8", "\x00\xD8", "@\x00"]
p src
p src
#=> ""
#=> ""


</syntaxhighlight>
</syntaxhighlight>

المراجعة الحالية بتاريخ 10:43، 18 أكتوبر 2018

يُعيد التّابع primitive_errinfo معلوماتٍ مهمّةً حول آخر خطأٍ حدث في مصفوفة مكونة من خمسة عناصر مثل:

[result, enc1, enc2, error_bytes, readagain_bytes]

تكون result هي آخر نتيجة تحويل للتّابع primitive_convert.

تكون العناصر الأخرى ذات معنى فقط عندما تكون result هي invalid_byte_sequence:، أو incomplete_input:، أو undefined_conversion:.

تدلُّ القيمتان enc1 و enc2 على خطوة التحويل على شكل زوجٍ من السلاسل النصيّة. على سبيل المثال، يحول محولٌ (converter) من التّرميز EUC-JP إلى الترميز ISO-8859-1 سلسلة نصية بالشكل التالي: EUC-JP -> UTF-8 -> ISO-8859-1. إذًا، تكون القيمتان enc1 و enc2 إما “EUC-JP” و “UTF-8” أو “UTF-8” و “ISO-8859-1”.

تُشير القيمتان error_bytes و readagain_bytes إلى سلاسل البايت التي سببت الخطأ. يكون error_bytes هو الجزء المهمل، و readagain_bytes هو الجزء المخزَّن مؤقتًا الذي سيُقرأ مجدّدًا في عملية التحويل التالية.

البنية العامة

primitive_errinfo  array

القيم المعادة

تُعاد مصفوفة ذات 5 عناصر:

[result, enc1, enc2, error_bytes, readagain_bytes]

القيمة result: آخر نتيجة من التّابع primitive_errinfo.

القيمتان enc1 و enc2: يدلّان على خطوة التحويل على شكل زوجٍ من السلاسل النصيّة.

القيمتان error_bytes و readagain_bytes: تشيران إلى سلاسل البايت التي سببت الخطأ.

أمثلة

مثالٌ عن استخدام التابع primitive_errinfo:

# \xff is invalid as EUC-JP.
ec = Encoding::Converter.new("EUC-JP", "Shift_JIS")
ec.primitive_convert(src="\xff", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "EUC-JP", "UTF-8", "\xFF", ""]

# HIRAGANA LETTER A (\xa4\xa2 in EUC-JP) is not representable in ISO-8859-1.
# Since this error is occur in UTF-8 to ISO-8859-1 conversion,
# error_bytes is HIRAGANA LETTER A in UTF-8 (\xE3\x81\x82).
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec.primitive_convert(src="\xa4\xa2", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:undefined_conversion, "UTF-8", "ISO-8859-1", "\xE3\x81\x82", ""]

# partial character is invalid
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec.primitive_convert(src="\xa4", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:incomplete_input, "EUC-JP", "UTF-8", "\xA4", ""]

# Encoding::Converter::PARTIAL_INPUT prevents invalid errors by
# partial characters.
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec.primitive_convert(src="\xa4", dst="", nil, 10, Encoding::Converter::PARTIAL_INPUT)
p ec.primitive_errinfo
#=> [:source_buffer_empty, nil, nil, nil, nil]

# \xd8\x00\x00@ is invalid as UTF-16BE because
# no low surrogate after high surrogate (\xd8\x00).
# It is detected by 3rd byte (\00) which is part of next character.
# So the high surrogate (\xd8\x00) is discarded and
# the 3rd byte is read again later.
# Since the byte is buffered in ec, it is dropped from src.
ec = Encoding::Converter.new("UTF-16BE", "UTF-8")
ec.primitive_convert(src="\xd8\x00\x00@", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "UTF-16BE", "UTF-8", "\xD8\x00", "\x00"]
p src
#=> "@"

# Similar to UTF-16BE, \x00\xd8@\x00 is invalid as UTF-16LE.
# The problem is detected by 4th byte.
ec = Encoding::Converter.new("UTF-16LE", "UTF-8")
ec.primitive_convert(src="\x00\xd8@\x00", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "UTF-16LE", "UTF-8", "\x00\xD8", "@\x00"]
p src
#=> ""

انظر أيضًا

  • التابع primitive_convert: يحوّل ترميز جميع المحتويات المخزَّنة مؤقتًا (buffer) في مخزن معين أو مجال محدد منها ثم يضع الناتج في مخزَّن محدَّد.
  • التّابع asciicompat_encoding: يُعيد التّرميز المتوافق مع ASCII المقابل للترميز المعطى.
  • التّابع destination_encoding: يُعيد التّرميز الوجهة على شكل كائنٍ من الصنف Encoding.
  • التّابع source_encoding: يُعيد الترميز المصدر على شكل كائن من الصنف Encoding.
  • التّابع insert_output: يضيف سلسلةً نصيّةً إلى محوِّل التّرميز، إذ سيحويل ترميز هذه السلسلة إلى ترميز الوجهة نفسه وتوضع في نهاية مخرجات عملية التحويل.
  • التّابع finish: يُنهي محوّل الترميز، ويُعيد الجزء الأخير من السلسلة النصيّة التي يحول ترميزها حينذاك.

مصادر