[ruby-core:102751] [Ruby master Bug#17673] sysseek(0) and '1A' in header return "EOFError (end of file reached)"

[ruby-core:102751] [Ruby master Bug#17673] sysseek(0) and '1A' in header return "EOFError (end of file reached)"

[cart4for1]

Issue #17673 has been reported by stiuna (Juan Gregorio).

----------------------------------------
Bug #17673: sysseek(0)  and '1A' in header return "EOFError (end of file reached)"
https://bugs.ruby-lang.org/issues/17673

* Author: stiuna (Juan Gregorio)
* Status: Open
* Priority: Normal
* ruby -v: ruby 3.0.0p0 (2020-12-25 revision 95aff21468)
* Backport: 2.5: UNKNOWN, 2.6: UNKNOWN, 2.7: UNKNOWN, 3.0: UNKNOWN
----------------------------------------

The first byte of my file starts with the value **'1A'** .

Then:

``` ruby
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
#=> "EOFError (end of file reached)"
```

But when I change the first byte of my file to 'AA' for example.
Then:
``` ruby
#=> "aa45"
```


Is it a bug or am I missing something? I thought sysseek only changed the cursor and nothing else.

This error only occurs with byte **'1A'** I did the test with the rest of the bytes [00..FF] and there is no problem except with "1A".



-- 
https://bugs.ruby-lang.org/

[ruby-core:102752] [Ruby master Bug#17673] sysseek(0) and '1A' in header return "EOFError (end of file reached)"

[merch-redmine]

Issue #17673 has been updated by jeremyevans0 (Jeremy Evans).

Status changed from Open to Feedback

I tried your example and was unable to reproduce your problem:

```ruby
filePath = 'test.txt'
File.binwrite(filePath, "\x1A\x45")
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
# => ["1a45"]
```

Can you try on a different machine to check if this is a local problem?

----------------------------------------
Bug #17673: sysseek(0)  and '1A' in header return "EOFError (end of file reached)"
https://bugs.ruby-lang.org/issues/17673#change-90765

* Author: stiuna (Juan Gregorio)
* Status: Feedback
* Priority: Normal
* ruby -v: ruby 3.0.0p0 (2020-12-25 revision 95aff21468)
* Backport: 2.5: UNKNOWN, 2.6: UNKNOWN, 2.7: UNKNOWN, 3.0: UNKNOWN
----------------------------------------

The first byte of my file starts with the value **'1A'** .

Then:

``` ruby
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
#=> "EOFError (end of file reached)"
```

But when I change the first byte of my file to **'AA'** for example.
Then:
``` ruby
#=> "aa45"
```


Is it a bug or am I missing something? I thought sysseek only changed the cursor and nothing else.

This error only occurs with byte **'1A'** I did the test with the rest of the bytes **[00..FF]** and there is no problem except with **'1A'** .



-- 
https://bugs.ruby-lang.org/

[ruby-core:102753] [Ruby master Bug#17673] sysseek(0) and '1A' in header return "EOFError (end of file reached)"

[cart4for1]

Issue #17673 has been updated by stiuna (Juan Gregorio).


Can you try on a different machine to check if this is a local problem?

Unfortunately I don't have another computer to test the bug with, what version of ruby do you use?

----------------------------------------
Bug #17673: sysseek(0)  and '1A' in header return "EOFError (end of file reached)"
https://bugs.ruby-lang.org/issues/17673#change-90766

* Author: stiuna (Juan Gregorio)
* Status: Feedback
* Priority: Normal
* ruby -v: ruby 3.0.0p0 (2020-12-25 revision 95aff21468)
* Backport: 2.5: UNKNOWN, 2.6: UNKNOWN, 2.7: UNKNOWN, 3.0: UNKNOWN
----------------------------------------

The first byte of my file starts with the value **'1A'** .

Then:

``` ruby
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
#=> "EOFError (end of file reached)"
```

But when I change the first byte of my file to **'AA'** for example.
Then:
``` ruby
#=> "aa45"
```


Is it a bug or am I missing something? I thought sysseek only changed the cursor and nothing else.

This error only occurs with byte **'1A'** I did the test with the rest of the bytes **[00..FF]** and there is no problem except with **'1A'** .



-- 
https://bugs.ruby-lang.org/

[ruby-core:102754] [Ruby master Bug#17673] sysseek(0) and '1A' in header return "EOFError (end of file reached)"

[cart4for1]

Issue #17673 has been updated by stiuna (Juan Gregorio).


Aaah! I don't know if it matters but I use Windows, did you run it on Linux all of a sudden?

----------------------------------------
Bug #17673: sysseek(0)  and '1A' in header return "EOFError (end of file reached)"
https://bugs.ruby-lang.org/issues/17673#change-90767

* Author: stiuna (Juan Gregorio)
* Status: Feedback
* Priority: Normal
* ruby -v: ruby 3.0.0p0 (2020-12-25 revision 95aff21468)
* Backport: 2.5: UNKNOWN, 2.6: UNKNOWN, 2.7: UNKNOWN, 3.0: UNKNOWN
----------------------------------------

The first byte of my file starts with the value **'1A'** .

Then:

``` ruby
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
#=> "EOFError (end of file reached)"
```

But when I change the first byte of my file to **'AA'** for example.
Then:
``` ruby
#=> "aa45"
```


Is it a bug or am I missing something? I thought sysseek only changed the cursor and nothing else.

This error only occurs with byte **'1A'** I did the test with the rest of the bytes **[00..FF]** and there is no problem except with **'1A'** .



-- 
https://bugs.ruby-lang.org/

[ruby-core:102755] [Ruby master Bug#17673] sysseek(0) and '1A' in header return "EOFError (end of file reached)"

[merch-redmine]

Issue #17673 has been updated by jeremyevans0 (Jeremy Evans).

Status changed from Feedback to Closed

I tried on Windows and I was able to reproduce the issue:

```
C:\Users\jeremye>c:\Ruby30-x64\bin\ruby

filePath = 'test.txt'
File.binwrite(filePath, "\x1A\x45")
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
__END__
-:7:in `sysread': end of file reached (EOFError)
        from -:7:in `<main>'
```

From some brief research, this is expected behavior on Windows for text files.  You need to put the file in binary mode (IO#binmode):

```
:\Users\jeremye>c:\Ruby30-x64\bin\ruby
filePath = 'test.txt'
File.binwrite(filePath, "\x1A\x45")
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.binmode
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
__END__
["1a45"]
```

----------------------------------------
Bug #17673: sysseek(0)  and '1A' in header return "EOFError (end of file reached)"
https://bugs.ruby-lang.org/issues/17673#change-90768

* Author: stiuna (Juan Gregorio)
* Status: Closed
* Priority: Normal
* ruby -v: ruby 3.0.0p0 (2020-12-25 revision 95aff21468)
* Backport: 2.5: UNKNOWN, 2.6: UNKNOWN, 2.7: UNKNOWN, 3.0: UNKNOWN
----------------------------------------

The first byte of my file starts with the value **'1A'** .

Then:

``` ruby
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
#=> "EOFError (end of file reached)"
```

But when I change the first byte of my file to **'AA'** for example.
Then:
``` ruby
#=> "aa45"
```


Is it a bug or am I missing something? I thought sysseek only changed the cursor and nothing else.

This error only occurs with byte **'1A'** I did the test with the rest of the bytes **[00..FF]** and there is no problem except with **'1A'** .



-- 
https://bugs.ruby-lang.org/

[ruby-core:102756] [Ruby master Bug#17673] sysseek(0) and '1A' in header return "EOFError (end of file reached)"

[cart4for1]

Issue #17673 has been updated by stiuna (Juan Gregorio).


Right, that solved it, the Ruby documentation should specify that. Ok, thanks.

----------------------------------------
Bug #17673: sysseek(0)  and '1A' in header return "EOFError (end of file reached)"
https://bugs.ruby-lang.org/issues/17673#change-90769

* Author: stiuna (Juan Gregorio)
* Status: Closed
* Priority: Normal
* ruby -v: ruby 3.0.0p0 (2020-12-25 revision 95aff21468)
* Backport: 2.5: UNKNOWN, 2.6: UNKNOWN, 2.7: UNKNOWN, 3.0: UNKNOWN
----------------------------------------

The first byte of my file starts with the value **'1A'** .

Then:

``` ruby
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
#=> "EOFError (end of file reached)"
```

But when I change the first byte of my file to **'AA'** for example.
Then:
``` ruby
#=> "aa45"
```


Is it a bug or am I missing something? I thought sysseek only changed the cursor and nothing else.

This error only occurs with byte **'1A'** I did the test with the rest of the bytes **[00..FF]** and there is no problem except with **'1A'** .



-- 
https://bugs.ruby-lang.org/

[ruby-core:102773] [Ruby master Bug#17673] sysseek(0) and '1A' in header return "EOFError (end of file reached)"

[nobu]

Issue #17673 has been updated by nobu (Nobuyoshi Nakada).


This is not specific to Ruby, but the very (in)famous text mode spec of Windows (and other dosish systems).

----------------------------------------
Bug #17673: sysseek(0)  and '1A' in header return "EOFError (end of file reached)"
https://bugs.ruby-lang.org/issues/17673#change-90793

* Author: stiuna (Juan Gregorio)
* Status: Closed
* Priority: Normal
* ruby -v: ruby 3.0.0p0 (2020-12-25 revision 95aff21468)
* Backport: 2.5: UNKNOWN, 2.6: UNKNOWN, 2.7: UNKNOWN, 3.0: UNKNOWN
----------------------------------------

The first byte of my file starts with the value **'1A'** .

Then:

``` ruby
descriptor = IO.sysopen(filePath)
file2Read = IO.new(descriptor)
file2Read.sysseek(0)
p file2Read.sysread(2).unpack('H*')
#=> "EOFError (end of file reached)"
```

But when I change the first byte of my file to **'AA'** for example.
Then:
``` ruby
#=> "aa45"
```


Is it a bug or am I missing something? I thought sysseek only changed the cursor and nothing else.

This error only occurs with byte **'1A'** I did the test with the rest of the bytes **[00..FF]** and there is no problem except with **'1A'** .



-- 
https://bugs.ruby-lang.org/