Posted by LES on November 18, 2004
#!/usr/local/bin/tclsh
# char2ent.tcl - Opens an HTML or XML file with special characters
# (diacritics) written in plain text, replaces these special
# characters with appropriate HTML or XML entities and writes
# the output to a new file.
#
# Author: Luciano Espirito Santo
#
# History
#
# Version 1.0 2004-11-18 Luciano Espirito Santo
# First version. Alpha stage.
#
# KNOWN ISSUES:
# - No user-proof measures, no error or exception handling, no nothing!
# No guarantees! Use it at your own risk!
# - Tested on Windows 98 only. Permission issues are likely to come up
# in other operating systems. Permission issues are harmless. The
# program will just not be able to read the input file and/or write
# to the output file.
#
# TODO:
# - Make the ability to do the INVERSE operation (that would include
# the ability to tell non-escaped entities from escaped entities and
# NOT replace the escaped entities.
# - Make it handle STDIN.
#
# LICENSE: BSD
#
# How to use it:
#
# char2ent.tcl --help
# ----------------------------------------------------------------
# Do not change anything below this point unless you know what you're doing.
# Print help text and exit if '--help' is the only argument
if { [ llength $argc ] == 1 && [ lindex $argv 0 ] == "--help" } {
puts ""
puts "char2ent, by Luciano Espirito Santo - 2004"
puts ""
puts {Usage: char2ent -[option] "input file" "output file"}
puts ""
puts "Possible options:"
puts "-h: convert special characters to HTML entities"
puts "-x: convert special characters to XML entities"
puts ""
puts {"input file" MUST exist}
puts {"output file" is created automatically if it does not exist}
puts {"input file" and "output file" MUST NOT be the same file}
puts ""
puts {Example: char2ent -x "sample.xml" "converted.xml"}
puts ""
exit
}
# Complain and exit if option is neither '-h' nor '-x'
if { [ lindex $argv 0 ] != "-h" && [ lindex $argv 0 ] != "-x" } {
puts "Error! Try 'char2ent --help' to see how to use this program.\n"
exit
}
# Complain and exit if not exactly 3 arguments (option, input, output) found
if { $argc != 3 } {
puts "Error! Try 'char2ent --help' to see how to use this program.\n"
exit
}
# Complain and exit if input file does not exist
if {! [ file exists [ lindex $argv 1 ] ] } {
puts "Error! File \"[ lindex $argv 1 ]\" not found!\n"
exit
}
# Complain and exit if input file is not readable
if {! [ file readable [ lindex $argv 1 ] ] } {
puts "Error! Permission denied to read [ lindex $argv 1 ]!\n"
exit
}
# Complain if input file and output file are the same
if { [ lindex $argv 1 ] == [ lindex $argv 2 ] } {
puts "Error! \"input file\" and \"output file\" must not be the same.\n"
exit
}
# Try to open input file for reading.
# Complain and exit in case of errors.
if { [ catch { set myIF [ open [ lindex $argv 1 ] r ] } myIFError ] } {
puts "Error! $myIFError\n"
exit
}
# Try to open output file for writing.
# Complain, close input file and exit in case of errors.
if { [ catch { set myOF [ open [ lindex $argv 2 ] w ] } myOFError ] } {
close $myIF
puts "Error! $myOFError\n"
exit
}
# ===============================================
# Two files open. No errors this far. Let's replace.
set myChars {
��ª ��º ���� ���� ���� ���� ���� ���� ���� ����
���� ���� ���� ���� ���� ���� ���� ���� ���� ����
���� ���� ���� ���� ���� ���� ���� ���� ���� ����
���� ���� ���� �� ��¡ ��¢ ��£ ��¤ ��¥ ��¦
��§ ��¨ ��© ��ª ��« ��¬ ���� ��® ��¯ ��°
��± ��² ��³ ��´ ��µ ��¶ ��¸ ��¹ ��º ��»
��¼ ��½ ��¾ ��¿ OE oe Y
}
set myHTML {
ª º À Á Â Ã
Ä Å &Aelig; Ç È É
Ê Ë Ì Í Î Ï
Ð Ñ Ò Ó Ô
Õ Ö Ø Ù Ú
Û Ü Ý Þ ß à
á â ã ä å æ
ç è é ê ë ì
í î ï ð ñ ò
ó ô õ ö ø
ù ú û ü ý
þ ÿ &Oelig; œ Ÿ
}
set myXML {
ª º À Á Â Ã Ä Å Æ
Ç È É Ê Ë Ì Í Î Ï
Ð Ñ Ò Ó Ô Õ Ö Ø Ù
Ú Û Ü Ý Þ ß à á â
ã ä å æ ç è é ê ë
ì í î ï ð ñ ò ó ô
õ ö ø ù ú û ü ý þ
ÿ Œ œ Ÿ
}
set myText [ read $myIF ]
for { set i 0 } { $i < [ llength $myChars ] } { incr i } {
switch -- [ lindex $argv 0 ] {
"-h" { set myReplace [ lindex $myHTML $i ] }
"-x" { set myReplace [ lindex $myXML $i ] }
}
set myText [ string map "[ lindex $myChars $i ] $myReplace" $myText ]
}
puts -nonewline $myOF $myText
close $myIF
close $myOF
exitLES: Unfortunately, I can't make wikit display the numeric codes in the "set myXML" line... Jean-Claude?
RS Note that read includes the trailing newline; to write such a file-string out it is best to use puts -nonewline so you don't get an extra one. Also, string map is happy with long maps, so you can avoid the for loop by just coding
set XMLmap {& & < < > > ...}
set HTMLmap {���� Ä ...}
...
set myMap $XMLmap
...
set myText [string map $myMap $mytext]JSI 23feb05 The numeric codes in the "set myXML" line are preserved when requesting http://mini.net/tcl/13008.txt instead of http://mini.net/tcl/13008 , this will deliver the raw text unchanged. Doesn't exactly solve the problem, but is my best idea so far. Unformatted text is used here 1) for Tcl-code (where any "help" of the wikit-parser in most cases is unwanted) and 2) for a lot of lists like Tcl editors, where for example the automagic link generation is of good use. There has been discussion about moving Tcl-code elsewhere or using a special markup for Tcl-code. I assume and agree that searching and converting all already existing pages containing Tcl-code would generate a lot of work compared to adding ".txt" to an URL for those few pages which suffer from "parser-damaging" ;-)