Changeset 23285

Show
Ignore:
Timestamp:
03.11.2010 17:52:09 (9 years ago)
Author:
sjm84
Message:

Moving subroutine committed previously to util.pm to unicode.pm where it belongs: Dr Bainbridge's modification of nice-string subroutine which will print the unicode strings for debugging (printable ASCII chars are shown as-is, other chars are shown with their hex values for their unicode code points.

Location:
main/trunk/greenstone2/perllib
Files:
2 modified

Legend:

Unmodified
Added
Removed
  • main/trunk/greenstone2/perllib/unicode.pm

    r18410 r23285  
    701701} 
    702702 
     703# Useful method to print UTF8 (or other unicode) for debugging. 
     704# Characters that are easily displayed (that is, printable ASCII)  
     705# are shown as-is, whereas hex values of the unicode code points  
     706# are shown for all other chars. 
     707sub debug_unicode_string 
     708{ 
     709    join("", 
     710         map { $_ > 128 ?                      # if wide character... 
     711                   sprintf("\\x{%04X}", $_) :  # \x{...} 
     712                   chr($_)           
     713               } unpack("U*", $_[0]));         # unpack Unicode characters 
     714} 
    703715 
    7047161; 
  • main/trunk/greenstone2/perllib/util.pm

    r23284 r23285  
    13741374} 
    13751375 
    1376 # To print UTF8 (unicode) for debugging: 
    1377 # Characters that are easily displayed (that is, printable ASCII)  
    1378 # are shown as-is, whereas hexcodes are shown for all other chars. 
    1379 # Useful method for debugging when doing encoding related work. 
    1380 sub debug_unicode_string 
    1381 { 
    1382     join("", 
    1383          map { $_ > 128 ?                      # if wide character... 
    1384                    sprintf("\\x{%04X}", $_) :  # \x{...} 
    1385                    chr($_)           
    1386                } unpack("U*", $_[0]));         # unpack Unicode characters 
    1387 } 
    1388  
    138913761;