From: Tanaka Akira <akr@...17n.org>
Date: 2005-05-07T18:47:00+09:00
Subject: Re: reading and EOF on Win2K vs. OS X

In article <3c110c14125e11f40819bf4bd8401b85@visibleworkings.com>,
  Brian Marick <marick@visibleworkings.com> writes:

> I'm writing a book on Ruby for testers. The first example is writing a 
> souped-up "tail -f" program that'll be useful for exploratory testing. 
> Here's the very first implementation:
>
> open_file = File.open('the-log')
> loop do
>    puts open_file.readlines
>    sleep 1
> end
>
> This works on Windows (Win2K, Ruby 1.8.1). If another program is 
> writing steadily to 'the-log', this program steadily prints out new 
> lines.
>
> It does not work on OS X (and, I'm guessing, other versions of Unix). 

It depends on stdio implementation.

Some stdio implementations such as 4.4BSD's causes EOF if EOF is
already occured.  In same situatoin, some other stdio implementations
such as glibc and Solaris 2.8 doesn't cause EOF.

#include <stdio.h>

int main()
{
  FILE *f, *t;

  if ((f = fopen("tst.tmp", "w")) == NULL) {
    perror("fopen");
    return 1;
  }
  fclose(f);

  if ((t = fopen("tst.tmp", "r")) == NULL) {
    perror("fopen");
    return 1;
  }

  printf("feof: %d  ", feof(t));
  printf("getc: %d\n", getc(t));

  if ((f = fopen("tst.tmp", "a")) == NULL) {
    perror("fopen");
    return 1;
  }
  putc('a', f);
  fclose(f);

  printf("feof: %d  ", feof(t));
  printf("getc: %d\n", getc(t));  
  
  fclose(t);
  
  return 0;
}

NetBSD 2.0:
feof: 0  getc: -1
feof: 1  getc: -1

Debian GNU/Linux (sarge):
feof: 0  getc: -1
feof: 1  getc: 97

Solaris 2.8:
feof: 0  getc: -1
feof: 16  getc: 97

I expect OS X just behaves like NetBSD 2.0.

> Once readlines hits the end of file, it never returns anything but []. 
> I believe this happens because readlines() eventually ends up in 
> io.c/appendline and calls getc(3). Because feof(3), once set, is sticky 
> until clearerr(3) is called, any additions to the file are ignored.

Some stdio implementations reads file contents even if feof(3) is true.

> There's a workaround: do something that calls clearerr(3) by side 
> effect. This is the first one I found, though there may be more:
>
> 	open_file.pos = open_file.pos
>
> I don't want to have to explain that to a tester just learning 
> programming. I can hide this inside a required file that overrides 
> File#readlines, but it's still kludgy and some set of readers will 
> discover the kludge quickly.

Agreed.

> It doesn't seem like the behavior should be inconsistent on Unix and 
> Windows - you can't write a portable program that depends on either 
> behavior. Of the two behaviors, the Windows one seems better to me: it 
> lets you do more things more easily.

Ruby 1.9 should work well even on 4.4BSD because Ruby 1.9 doesn't rely
stdio buffering.

For Ruby 1.8, how about following patch?

Index: io.c
===================================================================
RCS file: /src/ruby/io.c,v
retrieving revision 1.246.2.72
diff -u -r1.246.2.72 io.c
--- io.c	28 Feb 2005 02:45:19 -0000	1.246.2.72
+++ io.c	7 May 2005 09:43:30 -0000
@@ -742,7 +742,6 @@
     GetOpenFile(io, fptr);
     rb_io_check_readable(fptr);
 
-    if (feof(fptr->f)) return Qtrue;
     if (READ_DATA_PENDING(fptr->f)) return Qfalse;
     READ_CHECK(fptr->f);
     TRAP_BEG;
@@ -1045,7 +1044,6 @@
     off_t siz = BUFSIZ;
     off_t pos;
 
-    if (feof(fptr->f)) return 0;
     if (fstat(fileno(fptr->f), &st) == 0  && S_ISREG(st.st_mode)
 #ifdef __BEOS__
 	&& (st.st_dev > 3)
@@ -1086,7 +1084,10 @@
 	rb_str_unlocktmp(str);
 	if (n == 0 && bytes == 0) {
 	    if (!fptr->f) break;
-	    if (feof(fptr->f)) break;
+	    if (feof(fptr->f)) {
+		clearerr(fptr->f);
+		break;
+	    }
 	    if (!ferror(fptr->f)) break;
 	    rb_sys_fail(fptr->path);
 	}
@@ -1275,7 +1276,6 @@
 
     GetOpenFile(io, fptr);
     rb_io_check_readable(fptr);
-    if (feof(fptr->f)) return Qnil;
     if (len == 0) return str;
 
     rb_str_locktmp(str);
@@ -1288,6 +1288,7 @@
     if (n == 0) {
 	if (!fptr->f) return Qnil;
 	if (feof(fptr->f)) {
+	    clearerr(fptr->f);
 	    rb_str_resize(str, 0);
 	    return Qnil;
 	}
@@ -1365,6 +1366,7 @@
 		    rb_sys_fail(fptr->path);
 		continue;
 	    }
+	    clearerr(fptr->f);
 #ifdef READ_DATA_PENDING_PTR
 	    return c;
 #endif
@@ -1440,6 +1442,9 @@
 	    return Qtrue;
 	}
     } while (c != EOF);
+    if (!ferror(f)) {
+	clearerr(f);
+    }
     return Qfalse;
 }
 
@@ -1806,6 +1811,7 @@
 		    rb_sys_fail(fptr->path);
 		continue;
 	    }
+	    clearerr(f);
 	    break;
 	}
 	rb_yield(INT2FIX(c & 0xff));
@@ -1851,6 +1857,7 @@
 		rb_sys_fail(fptr->path);
 	    goto retry;
 	}
+	clearerr(f);
 	return Qnil;
     }
     return INT2FIX(c & 0xff);
-- 
Tanaka Akira