From 275b043b8dffd404f3ecb378db150c5cd2ea63f1 Mon Sep 17 00:00:00 2001 From: Guillem Jover Date: Tue, 10 Jan 2017 09:29:45 +0100 Subject: [PATCH 3/4] Add new DebianDoc-SGML to DocBook conversion script This is a draft conversion script, that should automate the whole process so that it can hopefully be repeated at any later point and can handle modifications to the documents text. --- html.dsl | 42 +++++++++++++++++++ tools/sgml2docbook | 119 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 161 insertions(+) create mode 100644 html.dsl create mode 100755 tools/sgml2docbook diff --git a/html.dsl b/html.dsl new file mode 100644 index 0000000..fae6763 --- /dev/null +++ b/html.dsl @@ -0,0 +1,42 @@ + +]> + + + + + +(define %section-autolabel% #t) +(define %chunk-section-depth% 0) +(define %header-navigation% #t) +(define %footer-navigation% #t) +(define %use-id-as-filename% #t) +(define %html-ext% ".html") + +(define (article-titlepage-recto-elements) + (list + (normalize "title") + (normalize "subtitle") + (normalize "authorgroup") + (normalize "author") + (normalize "releaseinfo") + (normalize "copyright") + (normalize "pubdate") + (normalize "revhistory") + (normalize "legalnotice") + (normalize "abstract") +)) +(define (chunk-element-list) + (list + (normalize "book") + (normalize "chapter") + (normalize "appendix") + (normalize "footnotes") +)) + + + + + + + diff --git a/tools/sgml2docbook b/tools/sgml2docbook new file mode 100755 index 0000000..fa2e48c --- /dev/null +++ b/tools/sgml2docbook @@ -0,0 +1,119 @@ +#!/bin/sh + +set -e +set -x + +cleanup=yes +tidyxml=no + +files="menu-policy.sgml perl-policy.sgml upgrading-checklist.sgml policy.sgml" + +export LC_ALL=C + +# Generate fake entity files to be able to process the SGML and XML. +( + echo '' + echo '' +) >version.ent +( + echo '' + echo '' + echo '' +) >version.xml + +for sgml in $files; do + base=$(basename $sgml .sgml) + + # Remove invalid entities, encode other entities, and wrap + sed -e 's/ *© *//g' \ + -e 's/, &date;//g' \ + -e 's/&\([a-z]*\);/@@@\1@@@/g' <$sgml >$base.new.sgml + + # Do the conversion. + debiandoc2dbk -1 -l en $base.new.sgml + + # Recode, and fixup markup. + iconv -f iso-8859-15 -t utf-8 <$base.new.dbk | + sed -e 's/@@@\([a-z]*\)@@@/\&\1;/g' \ + -e 's/&version;/@@@version@@@/g' \ + -e 's//@@@date@@@/' \ + -e '//\1"version.xml"\2/g' \ + -e 's:\([^ ]*\) *\([^ ]*\):\1\2:g' \ + -e 's:\(.*The Debian Policy mailing List.*\):\1:gi' \ + -e 's/ *$//g' \ + >$base.xml + + if [ "$base" = "policy" ]; then + # Fixup IDs, and insert entity. + sed -i \ + -e '/^]>/i\ +' \ + -e 's:":&:' \ + -e 's/\(id\|linkend\)="\(pkg-alternatives\|pkg-binarypkg\|pkg-conffiles\|pkg-controlfields\|pkg-diversions\|pkg-scope\|pkg-sourcepkg\)"/\1="ap-\2"/g' \ + -e 's/\(id\|linkend\)="\(archive\|binary\|controlfields\|customized-programs\|docs\|files\|maintainerscripts\|opersys\|relationships\|scope\|sharedlibs\|source\)"/\1="ch-\2"/' \ + -e '/\(id\|linkend\)="\(ap-\|ch-\|s-\|s[0-9]\)[^"]*"/!s/\(id\|linkend\)="\([^"]*\)"/\1="s-\2"/g' \ + $base.xml + elif [ "$base" = "perl-policy" ]; then + # Fixup IDs. + sed -i \ + -e 's/\(id\|linkend\)="perl6"/\1="ap-perl6"/' \ + -e 's/\(id\|linkend\)="module-packages"/\1="ch-module_packages"/' \ + -e 's/\(id\|linkend\)="\(embed\|perl\|programs\|site\|files\)"/\1="ch-\2"/' \ + -e '/\(id\|linkend\)="\(ap-\|ch-\|ch[0-9]\|s-\|s[0-9]\)[^"]*"/!s/\(id\|linkend\)="\([^"]*\)"/\1="s-\2"/g' \ + $base.xml + elif [ "$base" = "upgrading-checklist" ]; then + # Fixup IDs. + sed -i -e 's/id="\([0-9]\)/id="s-\1/g' \ + $base.xml + fi + + case "$tidyxml" in + xmllint) + xmllint --encode utf-8 --format --nonet --postvalid $base.xml \ + | sponge $base.xml + ;; + pandoc) + # Converts from book to an article, does not preserve entity declarations, + # nice output. + pandoc --normalize --chapters -s -f docbook -t docbook $base.xml \ + | sponge $base.xml + ;; + tidy) + # Messes up spacing, and joins tags and words. + tidy -raw -wrap 76 --indent yes --quiet yes \ + -xml --input-xml yes --output-xml yes \ + --preserve-entities yes --vertical-space yes --add-xml-space yes \ + -i -m $base.xml + ;; + esac + + # Restore entities. + sed -i -e 's/@@@\([a-z]*\)@@@/\&\1;/g' $base.xml + + # Test generating single file. + openjade -V nochunks \ + -t sgml -d html.dsl /usr/share/xml/declaration/xml.dcl $base.xml \ + >"$base-1.html" + + # Test generating chunked files. + mkdir -p $base.html + openjade \ + -V use-output-dir -V %output-dir%=$base.html/ \ + -V %root-filename%=index \ + -t sgml -d html.dsl /usr/share/xml/declaration/xml.dcl $base.xml + + # Update git tree. + git add $base.xml + git rm $base.sgml + + # Cleanup temporary files. + if [ $cleanup = yes ]; then + rm -f $base.new.* + fi +done + +# Cleanup temporary files. +if [ $cleanup = yes ]; then + rm -f version.ent version.xml +fi -- 2.12.1.578.ge9c3154ca4