Bernd Kreimeier wrote:
> I need an SGML/XML-aware version of wc to count words, lines, etc.
> directly onm SGML source. I used some db2txt right now, is there a
> a direct way to do this (in the way of sgrep)?
I wrote 'xmlwc' (attached) as an example program for TclXML.
Takes the same command line parameters as the Unix wc
command.
To run it you'll need ActiveState Tcl -
http://aspn.activestate.com/ASPN/Downloads/ActiveTcl/
HTHs,
Steve Ball
--
Steve Ball | XSLT Standard Library | Training & Seminars
Zveno Pty Ltd | Web Tcl Complete | XML XSL Schemas
http://www.zveno.com/ | TclXML TclDOM | Tcl, Web Development
[EMAIL PROTECTED] +---------------------------+---------------------
Ph. +61 2 6242 4099 | Mobile (0413) 594 462 | Fax +61 2 6242 4099
#!/bin/sh
# \
exec tclsh8.3 "$0" "$@"
package require xml
set bytes 0
set chars 0
set words 0
set lines 0
proc cdata {data args} {
global bytes chars words lines
incr bytes [string bytelength $data]
incr chars [string length $data]
incr lines [regsub -all \n $data {} discard]
regsub -all "\[ \t\r\n\]+" [string trim $data] { } data
incr words [regsub -all { } $data {} discard]
return {}
}
set format {%1$7d%2$8d%3$8d %5$10s}
set input {}
foreach opt $argv {
switch -- $opt {
--bytes {
set format {%4$7d}
}
-c -
--chars {
set format {%3$7d}
}
-w -
--words {
set format {%2$7d}
}
-l -
--lines {
set format {%1$7d}
}
-h -
--help {
puts stderr "$argv0 \[-clw\] \[--bytes\] \[--chars\] \[--words\]
\[--lines\] \[--help\] \[--version\] \[file...\]"
puts stderr "Counts number of bytes, characters, words and lines in an XML
document"
}
--version {
puts stderr "xmlwc version 1.0"
}
default {
lappend input $opt
}
}
}
if {![llength $input]} {
set p [xml::parser -characterdatacommand cdata]
if {[catch {$p parse [read stdin]} err]} {
puts stderr $err
exit 1
}
} else {
foreach in $input {
if {[catch {open $in} ch]} {
puts stderr "unable to open file \"$in\""
exit 1
}
set p [xml::parser -characterdatacommand cdata]
if {[catch {$p parse [read $ch]} err]} {
puts stderr $err
exit 1
}
catch {close $ch}
}
}
puts [format $format $lines $words $chars $bytes $input]
exit 0
