Bug#564915: final patch

[Andreas B. Mundt]

Hi Holger,

here is now the final patch, I it think can be comitted. I removed some
redundancy and added a few comments. The "*-manual.xml" file is the
same as with the older patch. 

I cheched the pdf, anything seems to be ok (and the extra spaces are
gone :-) ).

Regards,
        Andi
  
PS: Do not forget to run 
        find . -name "*.po" | xargs sed -i "s/[ \t]*<\//<\//g"
after applying!

Index: documentation/scripts/get_images
===================================================================
--- documentation/scripts/get_images    (revision 62761)
+++ documentation/scripts/get_images    (working copy)
@@ -41,12 +41,12 @@
 }
 
 sub replace () {
-       open(FILE, "< $file") or die "Can't open $file perhaps not in the 
correct dir?";
+       open(FILE, "< $file") or die "Can't open $file perhaps not in the 
correct dir? Error: $!";
        undef $/;
        my $local = <FILE>;
        close(FILE);
        # look for images...
-       if ( $local =~ "m#<imagedata 
fileref='/".$path."/\w+\?action=AttachFile&amp;do=get&amp;target=([^']+)'/>#" ) 
{
+       if ( $local =~ "m#<imagedata 
fileref='/".$path."/\\w+\?action=AttachFile&amp;do=get&amp;target=([^']+)'/>#" 
) {
                # ..and replace the paths
                $local =~ s#<imagedata fileref='([^'"<>]+)'/>#create($1)#eg;
                open(FILE, "> $file") or die "Can't open $file for writing";
Index: documentation/scripts/get_manual
===================================================================
--- documentation/scripts/get_manual    (revision 62761)
+++ documentation/scripts/get_manual    (working copy)
@@ -36,7 +36,7 @@
 # the last but one sed "preserves" the 2nd matched regex
 # the last sed does the same as dos2unix
 # head at the end chops of the last two lines with the Category:Permalink entry
-GET "${url}AllInOne?action=raw"|sed "s%<<Include(%%g" | sed "s%)>>%%g" | sed 
"s%$path1%%g" |sed 's/.$//'|head -n -2> id
+GET -H User-Agent: "${url}AllInOne?action=raw"|sed "s%<<Include(%%g" | sed 
"s%)>>%%g" | sed "s%$path1%%g" |sed 's/.$//'|head -n -2> id
 
 for i in `cat id` ; do
        TARGET=`echo "${i}" |sed "s/\(.*\)\/\(.*\)/\2/" `.xml
@@ -51,23 +51,24 @@
        #   - the last sed command deletes the first 4 lines
        GET "${url}${i}?action=show&mimetype=text/docbook" | 
        sed 
"s/\$DEBIAN_EDU_DOC_BUILDDATE/<code>$DEBIAN_EDU_DOC_BUILDDATE<\/code>/" |
+       # replace tags:
        sed "s%code>%computeroutput>%g" |
        sed "s%/htdocs/rightsidebar/img/%./images/%g" |
+       # remove final tag:
        sed "s%</article>%%" |
-       sed "s#</revhistory>##g" |
-       sed "s%</authorinitials>%%" |
-       sed "s#<revremark>\(.*\)</revremark>##g" | 
-       sed "s#<authorinitials>\(.*\)</authorinitials>##g" | 
-       sed "s#</articleinfo>##g" |
-       sed "s#</revision>##g" |
+       # remove tags and enclosed content:
+       sed "s#<articleinfo>\(.*\)</articleinfo>##g" |
        sed "s%<para><ulink 
url='http://wiki.debian.org/CategoryPermalink#'>CategoryPermalink</ulink> 
</para>%%" |
-       sed "s%<\/%\n<\/%g" |
+       # introduce line breaks:
        sed "s%<title>%\n<title>%g" |
+       sed "s%<\/title>%\n<\/title>%g" |
        sed "s%<section>%\n\n<section>%g" |
+       sed "s%<\/section>%\n<\/section>%g" |
        sed "s%<para>%\n<para>%g" |
-       sed "s%</date>\(.*\)\$%%g" |
+       sed "s%<\/para>%\n<\/para>%g" |
        sed "s%FIXME%\nFIXME%g" |
-       sed '1,4d' > $TARGET
+       # cut off first line:
+       sed '1d' > $TARGET
        if [ "$(grep -v FIXMEs $TARGET |grep FIXME)" != "" ] ; then
                echo "----------------------------------" >> $TMPFILE
                echo ${url}${i} >> $TMPFILE
@@ -79,9 +80,10 @@
 # (replace with the second match of the regular expression)
 sed -i "s/\(.*\)\/\(.*\)/\2/" id
 
-# add id= to <section>s
+# add id= to <section>s and a linebreak at the end
 for i in `cat id` ; do
        sed -i "0,/<section>/ s/<section>/<section id=\"$i\">/" ${i}.xml 
+       sed -i "$ s#>#>\n#" ${i}.xml
 done
 
 # paste it together
@@ -104,8 +106,10 @@
 # make it a docbook article again
 sed -i "1,/</ s#<#<?xml version=\"1.0\" encoding=\"UTF-8\"?><!DOCTYPE article 
PUBLIC \"-//OASIS//DTD DocBook XML V4.4//EN\" 
\"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd\";><article><articleinfo><title>$DEBIAN_EDU_DOC_TITLE</title></articleinfo>\n<#"
 $xmlfile
 sed -i "$ s#>#>\n</article>#" $xmlfile
-# remove the first two empty lines
-sed -i "1,2d" $xmlfile
+
+# remove the first empty line
+sed -i "1d" $xmlfile
+
 # clean it further
 TMPFILE2=$(mktemp)
 xmllint $xmlfile > $TMPFILE2