require "date"
require "nokogiri"
require "htmlentities"
require "json"
require "pathname"
require "open-uri"
require "isodoc"
require "relaton"
require "fileutils"
module Asciidoctor
module Standoc
module Base
XML_ROOT_TAG = "standard-document".freeze
XML_NAMESPACE = "https://www.metanorma.org/ns/standoc".freeze
def xml_root_tag
self.class::XML_ROOT_TAG
end
def xml_namespace
self.class::XML_NAMESPACE
end
def content(node)
node.content
end
def skip(node, name = nil)
name = name || node.node_name
w = "converter missing for #{name} node in Metanorma backend"
@log.add("AsciiDoc Input", node, w)
nil
end
def html_extract_attributes(node)
{
script: node.attr("script"),
bodyfont: node.attr("body-font"),
headerfont: node.attr("header-font"),
monospacefont: node.attr("monospace-font"),
i18nyaml: node.attr("i18nyaml"),
scope: node.attr("scope"),
htmlstylesheet: node.attr("htmlstylesheet"),
htmlcoverpage: node.attr("htmlcoverpage"),
htmlintropage: node.attr("htmlintropage"),
scripts: node.attr("scripts"),
scripts_pdf: node.attr("scripts-pdf"),
datauriimage: node.attr("data-uri-image"),
htmltoclevels: node.attr("htmltoclevels") || node.attr("toclevels"),
doctoclevels: node.attr("doctoclevels") || node.attr("toclevels"),
break_up_urls_in_tables: node.attr("break-up-urls-in-tables"),
}
end
def html_converter(node)
IsoDoc::HtmlConvert.new(html_extract_attributes(node))
end
def doc_extract_attributes(node)
{
script: node.attr("script"),
bodyfont: node.attr("body-font"),
headerfont: node.attr("header-font"),
monospacefont: node.attr("monospace-font"),
i18nyaml: node.attr("i18nyaml"),
scope: node.attr("scope"),
wordstylesheet: node.attr("wordstylesheet"),
standardstylesheet: node.attr("standardstylesheet"),
header: node.attr("header"),
wordcoverpage: node.attr("wordcoverpage"),
wordintropage: node.attr("wordintropage"),
ulstyle: node.attr("ulstyle"),
olstyle: node.attr("olstyle"),
htmltoclevels: node.attr("htmltoclevels") || node.attr("toclevels"),
doctoclevels: node.attr("doctoclevels") || node.attr("toclevels"),
break_up_urls_in_tables: node.attr("break-up-urls-in-tables"),
}
end
def doc_converter(node)
IsoDoc::WordConvert.new(doc_extract_attributes(node))
end
def presentation_xml_converter(node)
IsoDoc::PresentationXMLConvert.new(html_extract_attributes(node))
end
def init(node)
@fn_number ||= 0
@draft = false
@refids = Set.new
@anchors = {}
@draft = node.attributes.has_key?("draft")
@novalid = node.attr("novalid")
@smartquotes = node.attr("smartquotes") != "false"
@keepasciimath = node.attr("mn-keep-asciimath") &&
node.attr("mn-keep-asciimath") != "false"
@fontheader = default_fonts(node)
@files_to_delete = []
@filename = node.attr("docfile") ?
File.basename(node.attr("docfile")).gsub(/\.adoc$/, "") : ""
@localdir = Utils::localdir(node)
@output_dir = outputdir node
@no_isobib_cache = node.attr("no-isobib-cache")
@no_isobib = node.attr("no-isobib")
@bibdb = nil
@seen_headers = []
@datauriimage = node.attr("data-uri-image")
@boilerplateauthority = node.attr("boilerplate-authority")
@log = Asciidoctor::Standoc::Log.new
init_bib_caches(node)
init_iev_caches(node)
lang = (node.attr("language") || "en")
script = (node.attr("script") || "en")
i18n_init(lang, script)
end
def default_fonts(node)
b = node.attr("body-font") ||
(node.attr("script") == "Hans" ? '"SimSun",serif' :
'"Cambria",serif')
h = node.attr("header-font") ||
(node.attr("script") == "Hans" ? '"SimHei",sans-serif' :
'"Cambria",serif')
m = node.attr("monospace-font") || '"Courier New",monospace'
"$bodyfont: #{b};\n$headerfont: #{h};\n$monospacefont: #{m};\n"
end
def outputs(node, ret)
File.open(@filename + ".xml", "w:UTF-8") { |f| f.write(ret) }
presentation_xml_converter(node).convert(@filename + ".xml")
html_converter(node).convert(@filename + ".presentation.xml", nil, false, "#{@filename}.html")
doc_converter(node).convert(@filename + ".presentation.xml", nil, false, "#{@filename}.doc")
end
def document(node)
init(node)
ret = makexml(node).to_xml(indent: 2)
outputs(node, ret) unless node.attr("nodoc") || !node.attr("docfile")
clean_exit
ret
end
def clean_exit
@log.write(@output_dir + @filename + ".err") unless @novalid
@files_to_delete.each { |f| FileUtils.rm f }
end
def makexml1(node)
result = ["",
"<#{xml_root_tag}>"]
result << noko { |ixml| front node, ixml }
result << noko { |ixml| middle node, ixml }
result << "#{xml_root_tag}>"
textcleanup(result)
end
def makexml(node)
result = makexml1(node)
ret1 = cleanup(Nokogiri::XML(result))
ret1.root.add_namespace(nil, xml_namespace)
validate(ret1) unless @novalid
ret1
end
def draft?
@draft
end
def doctype(node)
node.attr("doctype")
end
def front(node, xml)
xml.bibdata **attr_code(type: "standard") do |b|
metadata node, b
end
end
def middle(node, xml)
xml.sections do |s|
s << node.content if node.blocks?
end
end
def term_source_attrs(seen_xref)
{ bibitemid: seen_xref.children[0]["target"],
format: seen_xref.children[0]["format"],
type: "inline" }
end
def add_term_source(xml_t, seen_xref, m)
if seen_xref.children[0].name == "concept"
xml_t.origin { |o| o << seen_xref.children[0].to_xml }
else
xml_t.origin seen_xref.children[0].content,
**attr_code(term_source_attrs(seen_xref))
end
m[:text] && xml_t.modification do |mod|
mod.p { |p| p << m[:text].sub(/^\s+/, "") }
end
end
TERM_REFERENCE_RE_STR = <<~REGEXP.freeze
^(?<(xref|concept)[^>]+>([^<]*(xref|concept)>)?)
(,\s(?.*))?
$
REGEXP
TERM_REFERENCE_RE =
Regexp.new(TERM_REFERENCE_RE_STR.gsub(/\s/, "").gsub(/_/, "\\s"),
Regexp::IGNORECASE | Regexp::MULTILINE)
def extract_termsource_refs(text, node)
matched = TERM_REFERENCE_RE.match text
matched.nil? and
@log.add("AsciiDoc Input", node, "term reference not in expected format: #{text}")
matched
end
def termsource(node)
matched = extract_termsource_refs(node.content, node) || return
noko do |xml|
attrs = { status: matched[:text] ? "modified" : "identical" }
xml.termsource **attrs do |xml_t|
seen_xref = Nokogiri::XML.fragment(matched[:xref])
add_term_source(xml_t, seen_xref, matched)
end
end.join("\n")
end
private
def outputdir(node)
if node.attr("output_dir").nil_or_empty? then Utils::localdir(node)
else File.join(node.attr("output_dir"), "")
end
end
end
end
end