opensource/pandoc
3
0
Fork 0
mirror of https://github.com/jgm/pandoc.git synced 2026-08-28 17:20:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

DocBook reader: support "role" attribute (#11255)

Browse Source 
The `role` attribute is parsed and added to Pandoc AST elements,
using a wrapper Div if needed.
This commit is contained in:
Yann Trividic
2026-01-03 18:36:19 +01:00
committed by GitHub
parent 12ad483674
commit 2a426718bc
3 changed files with 173 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/Text/Pandoc/Readers/DocBook.hs
+28 -22
View File
@@ -46,7 +46,7 @@ import Text.Pandoc.Builder
import Text.Pandoc.Class.PandocMonad (PandocMonad, report)
import Text.Pandoc.Options
import Text.Pandoc.Logging (LogMessage(..))
import Text.Pandoc.Shared (safeRead, extractSpaces)
import Text.Pandoc.Shared (safeRead, extractSpaces, addPandocAttributes)
import Text.Pandoc.Sources (ToSources(..), sourcesToText)
import Text.Pandoc.Transforms (headerShift)
import Text.TeXMath (readMathML, writeTeX)
@@ -731,9 +731,7 @@ blockTags = Set.fromList $
, "articleinfo"
, "attribution"
, "authorinitials"
, "bibliodiv"
, "biblioentry"
, "bibliography"
, "bibliomisc"
, "bibliomixed"
, "blockquote"
@@ -772,31 +770,19 @@ blockTags = Set.fromList $
, "preface"
, "procedure"
, "programlisting"
, "qandadiv"
, "question"
, "refsect1"
, "refsect1info"
, "refsect2"
, "refsect2info"
, "refsect3"
, "refsect3info"
, "refsection"
, "refsectioninfo"
, "screen"
, "sect1"
, "sect1info"
, "sect2"
, "sect2info"
, "sect3"
, "sect3info"
, "sect4"
, "sect4info"
, "sect5"
, "sect5info"
, "section"
, "sectioninfo"
, "simpara"
, "simplesect"
, "substeps"
, "subtitle"
, "table"
@@ -804,7 +790,13 @@ blockTags = Set.fromList $
, "titleabbrev"
, "toc"
, "variablelist"
] ++ admonitionTags
] ++ sectionTags ++ admonitionTags
sectionTags :: [Text]
sectionTags = ["bibliography", "bibliodiv"
, "sect1", "sect2", "sect3", "sect4", "sect5", "section", "simplesect"
, "refsect1", "refsect2", "refsect3", "refsection", "qandadiv"
]
admonitionTags :: [Text]
admonitionTags = ["caution","danger","important","note","tip","warning"]
@@ -866,14 +858,19 @@ getBlocks e = do
modify (\st -> st{ dbElementStack = drop 1 $ dbElementStack st })
return blocks
getRoleAttr :: Element -> [(Text, Text)] -- extract role attribute and add it to the attribute list
getRoleAttr e = case attrValue "role" e of
"" -> []
r -> [("role", r)]
parseBlock :: PandocMonad m => Content -> DB m Blocks
parseBlock (Text (CData CDataRaw _ _)) = return mempty -- DOCTYPE
parseBlock (Text (CData _ s _)) = if T.all isSpace s
then return mempty
else return $ plain $ trimInlines $ text s
parseBlock (CRef x) = return $ plain $ str $ T.toUpper x
parseBlock (Elem e) =
case qName (elName e) of
parseBlock (Elem e) = do
parsedBlock <- case qName (elName e) of
"toc" -> skip -- skip TOC, since in pandoc it's autogenerated
"index" -> skip -- skip index, since page numbers meaningless
"para" -> parseMixed para (elContent e)
@@ -985,6 +982,9 @@ parseBlock (Elem e) =
"title" -> return mempty -- handled in parent element
"subtitle" -> return mempty -- handled in parent element
_ -> skip >> getBlocks e
if qName (elName e) `elem` sectionTags
then return parsedBlock
else return $ addPandocAttributes (getRoleAttr e) parsedBlock
where skip = do
let qn = qName $ elName e
let name = if "pi-" `T.isPrefixOf` qn
@@ -1120,7 +1120,10 @@ parseBlock (Elem e) =
modify $ \st -> st{ dbSectionLevel = n }
b <- getBlocks e
modify $ \st -> st{ dbSectionLevel = n - 1 }
return $ headerWith (elId, classes, maybeToList titleabbrevElAsAttr++attrs) n' headerText <> b
let hdr = addPandocAttributes (getRoleAttr e)
$ headerWith (elId, classes, maybeToList titleabbrevElAsAttr ++ attrs)
n' headerText
return $ hdr <> b
titleabbrevElAsAttr =
case filterChild (named "titleabbrev") e `mplus`
(filterChild (named "info") e >>=
@@ -1143,7 +1146,7 @@ parseBlock (Elem e) =
b <- p
case mbt of
Nothing -> return b
Just t -> return $ divWith (attrValue "id" e,[],[])
Just t -> return $ divWith (attrValue "id" e, [], getRoleAttr e)
(divWith ("", ["title"], []) (plain t) <> b)
-- Admonitions are parsed into a div. Following other Docbook tools that output HTML,
@@ -1243,8 +1246,8 @@ parseInline (Text (CData _ s _)) = do
else return $ text s
parseInline (CRef ref) =
return $ text $ fromMaybe (T.toUpper ref) $ lookupEntity ref
parseInline (Elem e) =
case qName (elName e) of
parseInline (Elem e) = do
parsedInline <- case qName (elName e) of
"anchor" -> do
return $ spanWith (attrValue "id" e, [], []) mempty
"phrase" -> do
@@ -1366,6 +1369,9 @@ parseInline (Elem e) =
-- <?asciidor-br?> to in handleInstructions, above.
"pi-asciidoc-br" -> return linebreak
_ -> skip >> innerInlines id
return $ case qName (elName e) of
"emphasis" -> parsedInline
_ -> addPandocAttributes (getRoleAttr e) parsedInline
where skip = do
let qn = qName $ elName e
let name = if "pi-" `T.isPrefixOf` qn
test/docbook-reader.docbook
+38 -4
View File
@@ -27,9 +27,9 @@
This is a set of tests for pandoc. Most of them are adapted from John
Gruber’s markdown test suite.
</para>
<sect1 id="headers">
<sect1 id="headers" role="sect1role">
<title>Headers</title>
<sect2 id="level-2-with-an-embedded-link">
<sect2 id="level-2-with-an-embedded-link" role="sect2role">
<title>Level 2 with an <ulink url="/url">embedded link</ulink></title>
<sect3 id="level-3-with-emphasis">
<title>Level 3 with <emphasis>emphasis</emphasis></title>
@@ -74,6 +74,9 @@
<para>
Here’s a regular paragraph.
</para>
<para role="pararole">
And here’s a regular paragraph with a role.
</para>
<para>
In Markdown 1.0.0 and earlier. Version 8. This line turns into a list
item. Because a hard-wrapped line in the middle of a paragraph looked like
@@ -93,6 +96,11 @@
This is a block quote. It is pretty short.
</para>
</blockquote>
<blockquote role="roleblockquote">
<para>
This is a block quote with a role.
</para>
</blockquote>
<blockquote>
<para>
Code in a block quote:
@@ -233,6 +241,26 @@ These should not be escaped: \$ \\ \&gt; \[ \{
</para>
</listitem>
</orderedlist>
<para>
with role:
</para>
<orderedlist role="listrole" numeration="arabic">
<listitem>
<para>
First
</para>
</listitem>
<listitem>
<para>
Second
</para>
</listitem>
<listitem>
<para>
Third
</para>
</listitem>
</orderedlist>
<para>
and tight:
</para>
@@ -702,6 +730,12 @@ These should not be escaped: \$ \\ \&gt; \[ \{
<para>
So is <emphasis role="strong"><emphasis>this</emphasis></emphasis> word.
</para>
<para>
So is <emphasis role="emphasisrole"><emphasis>this</emphasis></emphasis> word with a role.
</para>
<para>
So is <phrase role="phraserole"><phrase>this</phrase></phrase> phrase with a role.
</para>
<para>
This is code: <literal>&gt;</literal>, <literal>$</literal>,
<literal>\</literal>, <literal>\$</literal>,
@@ -1408,7 +1442,7 @@ or here: &lt;http://example.com/&gt;
<para>
Table with attributes
</para>
<table xml:id="mytableid1" class="mytableclass1 mytableclass2" tabstyle="mytabstyle1">
<table xml:id="mytableid1" class="mytableclass1 mytableclass2" tabstyle="mytabstyle1" role="tablerole1">
<title>
Attribute table caption
</title>
@@ -1444,7 +1478,7 @@ or here: &lt;http://example.com/&gt;
<para>
Table with attributes, without caption
</para>
<informaltable xml:id="mytableid2" class="mytableclass3 mytableclass4" tabstyle="mytabstyle2">
<informaltable xml:id="mytableid2" class="mytableclass3 mytableclass4" tabstyle="mytabstyle2" role="tablerole2">
<tgroup>
<thead>
<th>
test/docbook-reader.native
+107 -4
View File
@@ -62,10 +62,16 @@ Pandoc
, Space
, Str "suite."
]
, Header 1 ( "headers" , [] , [] ) [ Str "Headers" ]
, Header
1
( "headers" , [] , [ ( "role" , "sect1role" ) ] )
[ Str "Headers" ]
, Header
2
( "level-2-with-an-embedded-link" , [] , [] )
( "level-2-with-an-embedded-link"
, []
, [ ( "role" , "sect2role" ) ]
)
[ Str "Level"
, Space
, Str "2"
@@ -151,6 +157,29 @@ Pandoc
, Space
, Str "paragraph."
]
, Div
( ""
, []
, [ ( "wrapper" , "1" ) , ( "role" , "pararole" ) ]
)
[ Para
[ Str "And"
, Space
, Str "here\8217s"
, Space
, Str "a"
, Space
, Str "regular"
, Space
, Str "paragraph"
, Space
, Str "with"
, Space
, Str "a"
, Space
, Str "role."
]
]
, Para
[ Str "In"
, Space
@@ -251,6 +280,31 @@ Pandoc
, Str "short."
]
]
, Div
( ""
, []
, [ ( "wrapper" , "1" ) , ( "role" , "roleblockquote" ) ]
)
[ BlockQuote
[ Para
[ Str "This"
, Space
, Str "is"
, Space
, Str "a"
, Space
, Str "block"
, Space
, Str "quote"
, Space
, Str "with"
, Space
, Str "a"
, Space
, Str "role."
]
]
]
, BlockQuote
[ Para
[ Str "Code"
@@ -348,6 +402,19 @@ Pandoc
, [ Para [ Str "Second" ] ]
, [ Para [ Str "Third" ] ]
]
, Para [ Str "with" , Space , Str "role:" ]
, Div
( ""
, []
, [ ( "wrapper" , "1" ) , ( "role" , "listrole" ) ]
)
[ OrderedList
( 1 , Decimal , DefaultDelim )
[ [ Para [ Str "First" ] ]
, [ Para [ Str "Second" ] ]
, [ Para [ Str "Third" ] ]
]
]
, Para [ Str "and" , Space , Str "tight:" ]
, OrderedList
( 1 , Decimal , DefaultDelim )
@@ -931,6 +998,38 @@ Pandoc
, Space
, Str "word."
]
, Para
[ Str "So"
, Space
, Str "is"
, Space
, Emph [ Emph [ Str "this" ] ]
, Space
, Str "word"
, Space
, Str "with"
, Space
, Str "a"
, Space
, Str "role."
]
, Para
[ Str "So"
, Space
, Str "is"
, Space
, Span
( "" , [ "phraserole" ] , [ ( "role" , "phraserole" ) ] )
[ Str "this" ]
, Space
, Str "phrase"
, Space
, Str "with"
, Space
, Str "a"
, Space
, Str "role."
]
, Para
[ Str "This"
, Space
@@ -2570,7 +2669,9 @@ Pandoc
, Table
( "mytableid1"
, [ "mytableclass1" , "mytableclass2" ]
, [ ( "custom-style" , "mytabstyle1" ) ]
, [ ( "role" , "tablerole1" )
, ( "custom-style" , "mytabstyle1" )
]
)
(Caption
Nothing
@@ -2636,7 +2737,9 @@ Pandoc
, Table
( "mytableid2"
, [ "mytableclass3" , "mytableclass4" ]
, [ ( "custom-style" , "mytabstyle2" ) ]
, [ ( "role" , "tablerole2" )
, ( "custom-style" , "mytabstyle2" )
]
)
(Caption Nothing [])
[ ( AlignDefault , ColWidthDefault )