mirror of
git://git.code.sf.net/p/cdesktopenv/code
synced 2025-02-15 04:32:24 +00:00
dtdocbook: Migrate doc2sdl to UTF-8.
This commit is contained in:
Liang Chang
parent
f2623acbe7
commit
6f952545fb
3 changed files with 72 additions and 29 deletions
|
|
@ -2,23 +2,20 @@
|
|||
|
||||
CHARSET
|
||||
|
||||
BASESET "ISO 646:1983//CHARSET
|
||||
International Reference Version (IRV)//ESC 2/5 4/0"
|
||||
DESCSET
|
||||
0 9 UNUSED
|
||||
9 2 9
|
||||
11 2 UNUSED
|
||||
13 1 13
|
||||
14 18 UNUSED
|
||||
32 95 32
|
||||
127 1 UNUSED
|
||||
|
||||
BASESET "ISO Registration Number 100//CHARSET
|
||||
ECMA-94 Right Part of Latin Alphabet Nr. 1//ESC 2/13 4/1"
|
||||
DESCSET
|
||||
128 32 UNUSED
|
||||
160 96 32
|
||||
|
||||
BASESET "ISO Registration Number 177//CHARSET
|
||||
ISO/IEC 10646-1:1993 UCS-4 with
|
||||
implementation level 3//ESC 2/5 2/15 4/6"
|
||||
DESCSET 0 9 UNUSED
|
||||
9 2 9
|
||||
11 2 UNUSED
|
||||
13 1 13
|
||||
14 18 UNUSED
|
||||
32 95 32
|
||||
127 1 UNUSED
|
||||
128 32 UNUSED
|
||||
160 55136 160
|
||||
55296 2048 UNUSED -- SURROGATES --
|
||||
57344 1056768 57344
|
||||
|
||||
CAPACITY SGMLREF
|
||||
|
||||
|
|
|
|||
|
|
@ -77,6 +77,32 @@ set snbLocation 0
|
|||
# EXAMPLE, for instance, we need to default to TYPE="LITERAL"
|
||||
set defaultParaType ""
|
||||
|
||||
proc TrimWhiteSpaces {str} {
|
||||
set characters [split $str ""]
|
||||
|
||||
for {set i 0} {$i < 2} {incr i} {
|
||||
set tmp ""
|
||||
set trimmed 0
|
||||
|
||||
foreach c $characters {
|
||||
if {$trimmed == 0} {
|
||||
if {[string is ascii -strict $c]} {
|
||||
if {[string is space -strict $c]} {
|
||||
continue
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
set trimmed 1
|
||||
|
||||
lappend tmp $c
|
||||
}
|
||||
|
||||
set characters [lreverse $tmp]
|
||||
}
|
||||
|
||||
return [join $characters ""]
|
||||
}
|
||||
|
||||
# print internal error message and exit
|
||||
proc InternalError {what} {
|
||||
|
|
@ -255,7 +281,7 @@ proc AddToMarkArray {mark} {
|
|||
global validMarkArray
|
||||
|
||||
set m [string range $mark 1 6]
|
||||
set m [string trim $m]
|
||||
set m [TrimWhiteSpaces $m]
|
||||
|
||||
set validMarkArray($m) $mark
|
||||
|
||||
|
|
@ -1987,13 +2013,13 @@ proc EndAGlossedTerm {id role} {
|
|||
# trim whitespace from the front and back of the string to be
|
||||
# glossed, also turn line feeds into spaces and compress out
|
||||
# duplicate whitespace
|
||||
set glossString [string trim $glossString]
|
||||
set glossString [TrimWhiteSpaces $glossString]
|
||||
set glossString [split $glossString '\n']
|
||||
set tmpGlossString $glossString
|
||||
set glossString [lindex $tmpGlossString 0]
|
||||
foreach str [lrange $tmpGlossString 1 end] {
|
||||
if {$str != ""} {
|
||||
append glossString " " [string trim $str]
|
||||
append glossString " " [TrimWhiteSpaces $str]
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -2045,7 +2071,7 @@ proc EndATermInAGlossary {id} {
|
|||
set glossString [lindex $tmpGlossString 0]
|
||||
foreach str [lrange $tmpGlossString 1 end] {
|
||||
if {$str != ""} {
|
||||
append glossString " " [string trim $str]
|
||||
append glossString " " [TrimWhiteSpaces $str]
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -2347,7 +2373,7 @@ proc AddIndexEntry {loc} {
|
|||
|
||||
# trim superfluous whitespace at the beginning and end of the
|
||||
# indexed term
|
||||
set indexBuffer [string trim $indexBuffer]
|
||||
set indexBuffer [TrimWhiteSpaces $indexBuffer]
|
||||
|
||||
# get an array index and determine whether 1st, 2nd or 3rd level
|
||||
set index [join $indexVals ", "]
|
||||
|
|
@ -2411,7 +2437,7 @@ proc EndIndexTerm {} {
|
|||
proc StartPrimaryIndexEntry {id cdata} {
|
||||
global indexVals
|
||||
|
||||
set indexVals [list [string trim $cdata]]
|
||||
set indexVals [list [TrimWhiteSpaces $cdata]]
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -2425,7 +2451,7 @@ proc StartSecondaryIndexEntry {id cdata} {
|
|||
global indexVals
|
||||
|
||||
AddIndexEntry "" ;# make sure our primary is defined
|
||||
lappend indexVals [string trim $cdata]
|
||||
lappend indexVals [TrimWhiteSpaces $cdata]
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -2439,7 +2465,7 @@ proc StartTertiaryIndexEntry {id cdata} {
|
|||
global indexVals
|
||||
|
||||
AddIndexEntry "" ;# make sure our secondary is defined
|
||||
lappend indexVals [string trim $cdata]
|
||||
lappend indexVals [TrimWhiteSpaces $cdata]
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -4692,7 +4718,9 @@ proc IncludeTOSS {} {
|
|||
proc GetLocalizedAutoGeneratedStringArray {filename} {
|
||||
global localizedAutoGeneratedStringArray
|
||||
|
||||
set buffer [ReadLocaleStrings $filename]
|
||||
set fp [open $filename]
|
||||
set buffer [read $fp]
|
||||
close $fp
|
||||
|
||||
set regExp {^(".*")[ ]*(".*")$} ;# look for 2 quoted strings
|
||||
|
||||
|
|
@ -4701,7 +4729,7 @@ proc GetLocalizedAutoGeneratedStringArray {filename} {
|
|||
set index 0
|
||||
while {$listLength > 0} {
|
||||
set line [lindex $stringList $index]
|
||||
set line [string trim $line]
|
||||
set line [TrimWhiteSpaces $line]
|
||||
if {([string length $line] > 0) && ([string index $line 0] != "#")} {
|
||||
if {[regexp $regExp $line match match1 match2]} {
|
||||
set match1 [string trim $match1 \"]
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
#!/bin/ksh
|
||||
|
||||
export LC_CTYPE="${LANG}"
|
||||
|
||||
# get the name of this command for errors, warnings and messages
|
||||
command_name=`basename $0`
|
||||
|
||||
|
|
@ -86,6 +88,7 @@ do
|
|||
esac
|
||||
done
|
||||
|
||||
default_charset='UTF-8'
|
||||
dbk_lib="${dbk_lib:-/usr/dt/dthelp/dtdocbook}" # if no -t, use installed dir
|
||||
sgml_dir="${sgml_dir:-${dbk_lib}}" # if no -s, use -t
|
||||
info_dir="${info_dir:-/usr/dt/infolib}" # if no -i, use installed dir
|
||||
|
|
@ -99,12 +102,24 @@ if [[ ${#sgmls} -eq 0 ]] then # if no -S, use installed one
|
|||
fi
|
||||
sgmls="${sgmls:-${info_dir}/etc/sgmls}" # if no -S, use installed one
|
||||
instant="${instant:-${dbk_lib}/instant}" # if no -I, use installed one
|
||||
x_locale="${x_locale:-${dbk_lib}/xlate_locale}" # if no -L, use installed one
|
||||
x_locale="${x_locale:-${LANG}}" # if no -L, use installed one
|
||||
helptag2="${helptag2:-dthelp_htag2}" # if no -H, use one in PATH
|
||||
|
||||
if [[ "$x_locale" == *.* ]] then
|
||||
x_lang="${x_locale%%.*}"
|
||||
x_charset="${x_locale##*.}"
|
||||
|
||||
if [[ "$x_charset" != "$default_charset" ]] then
|
||||
x_locale="${x_lang}.$default_charset"
|
||||
echo "Warning: charset is changed to ${default_charset}."
|
||||
fi
|
||||
else
|
||||
x_locale="${x_locale}.$default_charset"
|
||||
fi
|
||||
|
||||
# Set the environment variables for instant(1) to find its files
|
||||
export TPT_LIB="${dbk_lib}"
|
||||
export LOCALE_DIR="${dbk_lib}/$($x_locale)"
|
||||
export LOCALE_DIR="${dbk_lib}/${x_locale}"
|
||||
|
||||
# Determine whether we are using sgmls or nsgmls
|
||||
parser=`basename $sgmls`
|
||||
|
|
@ -123,6 +138,9 @@ elif ([[ "$SGML_CATALOG_FILES" = "" ]]) then
|
|||
export SGML_CATALOG_FILES="${SGML_CATALOG_FILES}:${sgml_cat}/catalog"
|
||||
fi
|
||||
|
||||
export SP_CHARSET_FIXED=1
|
||||
export SP_ENCODING="$default_charset"
|
||||
|
||||
# Set the environment variable to be picked up inside instant(1) when it
|
||||
# goes to call Tcl.
|
||||
export DBKTCL_DIR="${dbk_lib}/"
|
||||
|
|
|
|||
Loading…
Reference in a new issue