Modify JATS reader to handle BITS too (#9138)

Add provision for title-group, book, book-part-wrapper, book-meta,
book-part-meta, book-title, book-title-group, index, toc, legend,
title, collection-meta
This commit is contained in:
Julia Diaz
2023-10-26 15:18:33 -07:00
committed by GitHub
parent b671e0dfe5
commit f2a22e71df
12 changed files with 1217 additions and 14 deletions
+49
View File
@@ -0,0 +1,49 @@
```
% pandoc -f jats -t native -s
<article-meta>
<title-group>
<article-title></article-title>
</title-group>
<permissions>
<copyright-statement>© 2023, Ellerman et al</copyright-statement>
<copyright-year>2023</copyright-year>
<copyright-holder>Ellerman et al</copyright-holder>
<license license-type="open-access">
<ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://creativecommons.org/licenses/by/4.0/</ali:license_ref>
<license-p>This document is distributed under a Creative Commons Attribution 4.0 International license.</license-p>
</license>
</permissions>
</article-meta>
^D
Pandoc
Meta
{ unMeta =
fromList
[ ( "copyright"
, MetaMap
(fromList
[ ( "holder" , MetaString "Ellerman et al" )
, ( "statement"
, MetaString "\169 2023, Ellerman et al"
)
, ( "year" , MetaString "2023" )
])
)
, ( "license"
, MetaMap
(fromList
[ ( "link"
, MetaString
"https://creativecommons.org/licenses/by/4.0/"
)
, ( "text"
, MetaString
"This document is distributed under a Creative Commons Attribution 4.0 International license."
)
, ( "type" , MetaString "open-access" )
])
)
]
}
[]
```
+104
View File
@@ -0,0 +1,104 @@
```
% pandoc -f jats -t native -s
<book>
<book-meta>
<book-id book-id-type="publisher">handbook-648</book-id>
<book-title-group>
<book-title>The NCBI Handbook</book-title>
</book-title-group>
<contrib-group>
<contrib contrib-type="author">
<name><surname>McEntyre</surname>
<given-names>Jo</given-names></name>
<xref ref-type="aff" rid="bid.m.1"/>
</contrib>
<contrib contrib-type="editor">
<name><surname>Ostell</surname>
<given-names>Jim</given-names></name>
<xref ref-type="aff" rid="bid.m.1"/>
</contrib>
</contrib-group>
<aff id="bid.m.1">
<institution>National Center for Biotechnology Information (NCBI), National Library of Medicine, National Institutes of Health</institution>, <addr-line>Bethesda, MD 20892-6510</addr-line>
</aff>
<pub-date iso-8601-date="2002-11">
<month>11</month>
<year>2002</year>
</pub-date>
<publisher>
<publisher-name>National Center for Biotechnology Information (NCBI), National Library of Medicine, National Institutes of Health</publisher-name>
<publisher-loc>Bethesda, MD</publisher-loc>
</publisher>
<edition>1</edition>
<counts>
<book-fig-count count="98"/>
<book-table-count count="40"/>
<book-equation-count count="0"/>
<book-ref-count count="115"/>
<book-page-count count="532"/>
<book-word-count count="149852"/>
</counts>
</book-meta>
</book>
^D
Pandoc
Meta
{ unMeta =
fromList
[ ( "author"
, MetaList
[ MetaInlines [ Str "Jo" , Space , Str "McEntyre" ] ]
)
, ( "date" , MetaInlines [ Str "2002-11" ] )
, ( "institute"
, MetaList
[ MetaInlines
[ Str "National"
, Space
, Str "Center"
, Space
, Str "for"
, Space
, Str "Biotechnology"
, Space
, Str "Information"
, Space
, Str "(NCBI),"
, Space
, Str "National"
, Space
, Str "Library"
, Space
, Str "of"
, Space
, Str "Medicine,"
, Space
, Str "National"
, Space
, Str "Institutes"
, Space
, Str "of"
, Space
, Str "Health,"
, Space
, Str "Bethesda,"
, Space
, Str "MD"
, Space
, Str "20892-6510"
]
]
)
, ( "title"
, MetaInlines
[ Str "The"
, Space
, Str "NCBI"
, Space
, Str "Handbook"
]
)
]
}
[]
```
@@ -0,0 +1,95 @@
```
% pandoc -f jats -t native -s
<book-part-wrapper
dtd-version="2.1"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:xi="http://www.w3.org/2001/XInclude"
xmlns:mml="http://www.w3.org/1998/Math/MathML"
xmlns:xlink="http://www.w3.org/1999/xlink">
<collection-meta>
<title-group>
<title>Balisage Series on Markup Technologies</title>
</title-group>
<abstract>
<p>The <italic>Balisage Series on Markup Technologies</italic>
is an occasional series...</p>
</abstract>
</collection-meta>
<book-meta>
<book-title-group>
<book-title>Proceedings of Balisage: The Markup Conference
2013</book-title>
</book-title-group>
<abstract>
<p>Balisage is a peer-reviewed conference...</p></abstract>
</book-meta>
</book-part-wrapper>
^D
Pandoc
Meta
{ unMeta =
fromList
[ ( "abstract"
, MetaBlocks
[ Para
[ Str "Balisage"
, Space
, Str "is"
, Space
, Str "a"
, Space
, Str "peer-reviewed"
, Space
, Str "conference..."
]
]
)
, ( "title"
, MetaInlines
[ Str "Proceedings"
, Space
, Str "of"
, Space
, Str "Balisage:"
, Space
, Str "The"
, Space
, Str "Markup"
, Space
, Str "Conference"
, SoftBreak
, Str "2013"
]
)
]
}
[ Para
[ Str "The"
, Space
, Emph
[ Str "Balisage"
, Space
, Str "Series"
, Space
, Str "on"
, Space
, Str "Markup"
, Space
, Str "Technologies"
]
, SoftBreak
, Str "is"
, Space
, Str "an"
, Space
, Str "occasional"
, Space
, Str "series..."
]
]
```
+149
View File
@@ -0,0 +1,149 @@
```
% pandoc -f jats -t native
<book-part-wrapper
dtd-version="2.1"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:xi="http://www.w3.org/2001/XInclude"
xmlns:mml="http://www.w3.org/1998/Math/MathML"
xmlns:xlink="http://www.w3.org/1999/xlink">
<collection-meta>
<title-group>
<title>Balisage Series on Markup Technologies</title>
</title-group>
<abstract>
<p>The <italic>Balisage Series on Markup Technologies</italic>
is an occasional series...</p>
</abstract>
</collection-meta>
<book-meta>
<book-title-group>
<book-title>Proceedings of Balisage: The Markup Conference
2013</book-title>
</book-title-group>
<abstract>
<p>Balisage is a peer-reviewed conference...</p></abstract>
</book-meta>
<book-part id="bid.1" book-part-type="part">
<book-part-meta>
<title-group>
<label>Part 1</label>
<title>The Databases</title>
</title-group>
</book-part-meta>
<body>
<sec id="bid.3">
<title>History</title>
<p>Initially, GenBank was built and maintained at Los Alamos
National Laboratory.</p>
</sec>
</body>
<back>
<title>Back matter of book part</title>
<ref-list>
<title>References</title>
<ref id="bid.41">
<label>1</label>
<element-citation>
<person-group>
<string-name>
<surname>Olson</surname>
<given-names>M</given-names>
</string-name>
<string-name>
<surname>Hood</surname>
<given-names>L</given-names>
</string-name>
<string-name>
<surname>Cantor</surname>
<given-names>C</given-names>
</string-name>
<string-name>
<surname>Botstein</surname>
<given-names>D</given-names>
</string-name>
</person-group>
<article-title>A common language for physical mapping of the human genome</article-title>
<source>Science</source>
<year iso-8601-date="1989">1989</year>
<volume>245</volume>
<issue>4925</issue>
<fpage>1434</fpage>
<lpage>1435</lpage>
<pub-id pub-id-type="pmid">2781285</pub-id>
</element-citation>
</ref>
</ref-list>
</back>
</book-part>
</book-part-wrapper>
^D
[ Para
[ Str "The"
, Space
, Emph
[ Str "Balisage"
, Space
, Str "Series"
, Space
, Str "on"
, Space
, Str "Markup"
, Space
, Str "Technologies"
]
, SoftBreak
, Str "is"
, Space
, Str "an"
, Space
, Str "occasional"
, Space
, Str "series..."
]
, Header 2 ( "bid.3" , [] , [] ) [ Str "History" ]
, Para
[ Str "Initially,"
, Space
, Str "GenBank"
, Space
, Str "was"
, Space
, Str "built"
, Space
, Str "and"
, Space
, Str "maintained"
, Space
, Str "at"
, Space
, Str "Los"
, Space
, Str "Alamos"
, SoftBreak
, Str "National"
, Space
, Str "Laboratory."
]
, Header
2
( "" , [] , [] )
[ Str "Back"
, Space
, Str "matter"
, Space
, Str "of"
, Space
, Str "book"
, Space
, Str "part"
]
, Header 1 ( "" , [] , [] ) [ Str "References" ]
, Div ( "refs" , [] , [] ) []
]
```
+186
View File
@@ -0,0 +1,186 @@
```
% pandoc -f jats -t native
<book dtd-version="2.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<front-matter>
<front-matter-part>
<book-part-meta>
<title-group>
<title>About this book</title>
</title-group>
</book-part-meta>
<named-book-part-body>
<sec sec-type="miscinfo">
<title>The NCBI Handbook</title>
<p>Bioinformatics consists of a computational approach
to biomedical information management and analysis.</p>
</sec>
</named-book-part-body>
</front-matter-part>
</front-matter>
<book-body>
<book-part id="bid.1" book-part-type="part">
<book-part-meta>
<title-group>
<label>Part 1</label>
<title>The Databases</title>
</title-group>
</book-part-meta>
<body>
<sec id="bid.3">
<title>History</title>
<p>Initially, GenBank was built and maintained at Los Alamos
National Laboratory.</p>
</sec>
</body>
<back>
<title>Back matter of book part</title>
<ref-list>
<title>References</title>
<ref id="bid.41">
<label>1</label>
<element-citation>
<person-group>
<string-name>
<surname>Olson</surname>
<given-names>M</given-names>
</string-name>
<string-name>
<surname>Hood</surname>
<given-names>L</given-names>
</string-name>
<string-name>
<surname>Cantor</surname>
<given-names>C</given-names>
</string-name>
<string-name>
<surname>Botstein</surname>
<given-names>D</given-names>
</string-name>
</person-group>
<article-title>A common language for physical mapping of the human genome</article-title>
<source>Science</source>
<year iso-8601-date="1989">1989</year>
<volume>245</volume>
<issue>4925</issue>
<fpage>1434</fpage>
<lpage>1435</lpage>
<pub-id pub-id-type="pmid">2781285</pub-id>
</element-citation>
</ref>
</ref-list>
</back>
</book-part>
</book-body>
<book-back>
<ack id="bid.394">
<title>Acknowledgments</title>
<p>We gratefully acknowledge the work of Vladimir Soussov,
as well as the entire NCBI Entrez team...</p>
</ack>
</book-back>
</book>
^D
[ Header
2
( "" , [] , [] )
[ Str "The" , Space , Str "NCBI" , Space , Str "Handbook" ]
, Para
[ Str "Bioinformatics"
, Space
, Str "consists"
, Space
, Str "of"
, Space
, Str "a"
, Space
, Str "computational"
, Space
, Str "approach"
, SoftBreak
, Str "to"
, Space
, Str "biomedical"
, Space
, Str "information"
, Space
, Str "management"
, Space
, Str "and"
, Space
, Str "analysis."
]
, Header 2 ( "bid.3" , [] , [] ) [ Str "History" ]
, Para
[ Str "Initially,"
, Space
, Str "GenBank"
, Space
, Str "was"
, Space
, Str "built"
, Space
, Str "and"
, Space
, Str "maintained"
, Space
, Str "at"
, Space
, Str "Los"
, Space
, Str "Alamos"
, SoftBreak
, Str "National"
, Space
, Str "Laboratory."
]
, Header
2
( "" , [] , [] )
[ Str "Back"
, Space
, Str "matter"
, Space
, Str "of"
, Space
, Str "book"
, Space
, Str "part"
]
, Header 1 ( "" , [] , [] ) [ Str "References" ]
, Div ( "refs" , [] , [] ) []
, Header 2 ( "bid.394" , [] , [] ) [ Str "Acknowledgments" ]
, Para
[ Str "We"
, Space
, Str "gratefully"
, Space
, Str "acknowledge"
, Space
, Str "the"
, Space
, Str "work"
, Space
, Str "of"
, Space
, Str "Vladimir"
, Space
, Str "Soussov,"
, SoftBreak
, Str "as"
, Space
, Str "well"
, Space
, Str "as"
, Space
, Str "the"
, Space
, Str "entire"
, Space
, Str "NCBI"
, Space
, Str "Entrez"
, Space
, Str "team..."
]
]
```
+83
View File
@@ -0,0 +1,83 @@
```
% pandoc -f jats -t native
<index-group>
<index-title-group>
<title>Index group</title>
</index-title-group>
<p>Content of index group</p>
<index>
<index-title-group>
<title>Index</title>
</index-title-group>
<p>Content of index</p>
<index-div>
<index-title-group>
<title>N</title>
</index-title-group>
<p>Content of index div</p>
<index-entry>
<term>Navy</term>
<x>.</x>
<see-entry>Armed forces</see-entry>
<x>.</x>
</index-entry>
<index-entry>
<term>Necessary and proper clause, congressional power</term>
</index-entry>
<index-entry>
<term>Newsgathering as commerce</term>
</index-entry>
</index-div>
</index>
</index-group>
^D
[ Header
1 ( "" , [] , [] ) [ Str "Index" , Space , Str "group" ]
, Para
[ Str "Content"
, Space
, Str "of"
, Space
, Str "index"
, Space
, Str "group"
]
, Header 2 ( "" , [] , [] ) [ Str "Index" ]
, Para
[ Str "Content" , Space , Str "of" , Space , Str "index" ]
, Header 3 ( "" , [] , [] ) [ Str "N" ]
, Para
[ Str "Content"
, Space
, Str "of"
, Space
, Str "index"
, Space
, Str "div"
]
, Plain [ Str "Navy" ]
, Plain [ Str "." ]
, Plain [ Str "Armed" , Space , Str "forces" ]
, Plain [ Str "." ]
, Plain
[ Str "Necessary"
, Space
, Str "and"
, Space
, Str "proper"
, Space
, Str "clause,"
, Space
, Str "congressional"
, Space
, Str "power"
]
, Plain
[ Str "Newsgathering"
, Space
, Str "as"
, Space
, Str "commerce"
]
]
```
+45
View File
@@ -0,0 +1,45 @@
```
% pandoc -f jats -t native
<fig id="fig_A.1" orientation="portrait">
<label>Figure A.1</label>
<caption>
<title>Field of Application</title>
</caption>
<legend>
<title>Key</title>
<def-list>
<def-item>
<term>I</term>
<def><p>input</p></def>
</def-item>
<def-item>
<term>O</term>
<def><p>output</p></def>
</def-item>
...
</def-list>
</legend>
<graphic xlink:href="1234"/>
</fig>
^D
[ Figure
( "fig_A.1" , [] , [] )
(Caption
Nothing
[ Plain
[ Str "Field"
, Space
, Str "of"
, Space
, Str "Application"
]
])
[ Header 1 ( "" , [] , [] ) [ Str "Key" ]
, DefinitionList
[ ( [ Str "I" ] , [ [ Para [ Str "input" ] ] ] )
, ( [ Str "O" ] , [ [ Para [ Str "output" ] ] ] )
]
, Para [ Image ( "" , [] , [] ) [] ( "1234" , "" ) ]
]
]
```
+68
View File
@@ -0,0 +1,68 @@
```
% pandoc -f jats -t native
<dedication>
<named-book-part-body>
<p>This is the dedication text.</p>
</named-book-part-body>
</dedication>
^D
[ Header 1 ( "" , [] , [] ) [ Str "Dedication" ]
, Para
[ Str "This"
, Space
, Str "is"
, Space
, Str "the"
, Space
, Str "dedication"
, Space
, Str "text."
]
]
```
```
% pandoc -f jats -t native
<foreword>
<named-book-part-body>
<p>This is the foreword text.</p>
</named-book-part-body>
</foreword>
^D
[ Header 1 ( "" , [] , [] ) [ Str "Foreword" ]
, Para
[ Str "This"
, Space
, Str "is"
, Space
, Str "the"
, Space
, Str "foreword"
, Space
, Str "text."
]
]
```
```
% pandoc -f jats -t native
<preface>
<named-book-part-body>
<p>This is the preface text.</p>
</named-book-part-body>
</preface>
^D
[ Header 1 ( "" , [] , [] ) [ Str "Preface" ]
, Para
[ Str "This"
, Space
, Str "is"
, Space
, Str "the"
, Space
, Str "preface"
, Space
, Str "text."
]
]
```
+175
View File
@@ -0,0 +1,175 @@
```
% pandoc -f jats -t native
<sec>
<title>THE EUROPEAN UNION EXPLAINED</title>
</sec>
^D
[ Header
1
( "" , [] , [] )
[ Str "THE"
, Space
, Str "EUROPEAN"
, Space
, Str "UNION"
, Space
, Str "EXPLAINED"
]
]
```
```
% pandoc -f jats -t native
<sec>
<title display-as="3">THE EUROPEAN UNION EXPLAINED</title>
</sec>
^D
[ Header
3
( "" , [] , [] )
[ Str "THE"
, Space
, Str "EUROPEAN"
, Space
, Str "UNION"
, Space
, Str "EXPLAINED"
]
]
```
```
% pandoc -f jats -t native
<body>
<sec>
<title>The European Parliament</title>
<p>Members of the European Parliament (MEPs) are directly elected by EU citizens.</p>
<sec>
<title display-as="3">Composition of the European Parliament</title>
<p>The seats in the European Parliament are allocated among the Member States.</p>
</sec>
<sec>
<title>Composition of the European Parliament - II </title>
<p>Most MEPs are associated with a national political party in their home country.</p>
</sec>
</sec>
</body>
^D
[ Header
1
( "" , [] , [] )
[ Str "The"
, Space
, Str "European"
, Space
, Str "Parliament"
]
, Para
[ Str "Members"
, Space
, Str "of"
, Space
, Str "the"
, Space
, Str "European"
, Space
, Str "Parliament"
, Space
, Str "(MEPs)"
, Space
, Str "are"
, Space
, Str "directly"
, Space
, Str "elected"
, Space
, Str "by"
, Space
, Str "EU"
, Space
, Str "citizens."
]
, Header
3
( "" , [] , [] )
[ Str "Composition"
, Space
, Str "of"
, Space
, Str "the"
, Space
, Str "European"
, Space
, Str "Parliament"
]
, Para
[ Str "The"
, Space
, Str "seats"
, Space
, Str "in"
, Space
, Str "the"
, Space
, Str "European"
, Space
, Str "Parliament"
, Space
, Str "are"
, Space
, Str "allocated"
, Space
, Str "among"
, Space
, Str "the"
, Space
, Str "Member"
, Space
, Str "States."
]
, Header
2
( "" , [] , [] )
[ Str "Composition"
, Space
, Str "of"
, Space
, Str "the"
, Space
, Str "European"
, Space
, Str "Parliament"
, Space
, Str "-"
, Space
, Str "II"
]
, Para
[ Str "Most"
, Space
, Str "MEPs"
, Space
, Str "are"
, Space
, Str "associated"
, Space
, Str "with"
, Space
, Str "a"
, Space
, Str "national"
, Space
, Str "political"
, Space
, Str "party"
, Space
, Str "in"
, Space
, Str "their"
, Space
, Str "home"
, Space
, Str "country."
]
]
```
+122
View File
@@ -0,0 +1,122 @@
```
% pandoc -f jats -t native
<sec>
<title>The European Parliament</title>
<p>Members of the European Parliament (MEPs) are directly elected by EU citizens.</p>
</sec>
^D
[ Header
1
( "" , [] , [] )
[ Str "The"
, Space
, Str "European"
, Space
, Str "Parliament"
]
, Para
[ Str "Members"
, Space
, Str "of"
, Space
, Str "the"
, Space
, Str "European"
, Space
, Str "Parliament"
, Space
, Str "(MEPs)"
, Space
, Str "are"
, Space
, Str "directly"
, Space
, Str "elected"
, Space
, Str "by"
, Space
, Str "EU"
, Space
, Str "citizens."
]
]
```
```
% pandoc -f jats -t native
<sec>
<title supress="no">The European Parliament</title>
<p>Members of the European Parliament (MEPs) are directly elected by EU citizens.</p>
</sec>
^D
[ Header
1
( "" , [] , [] )
[ Str "The"
, Space
, Str "European"
, Space
, Str "Parliament"
]
, Para
[ Str "Members"
, Space
, Str "of"
, Space
, Str "the"
, Space
, Str "European"
, Space
, Str "Parliament"
, Space
, Str "(MEPs)"
, Space
, Str "are"
, Space
, Str "directly"
, Space
, Str "elected"
, Space
, Str "by"
, Space
, Str "EU"
, Space
, Str "citizens."
]
]
```
```
% pandoc -f jats -t native
<sec>
<title supress="yes">The European Parliament</title>
<p>Members of the European Parliament (MEPs) are directly elected by EU citizens.</p>
</sec>
^D
[ Para
[ Str "Members"
, Space
, Str "of"
, Space
, Str "the"
, Space
, Str "European"
, Space
, Str "Parliament"
, Space
, Str "(MEPs)"
, Space
, Str "are"
, Space
, Str "directly"
, Space
, Str "elected"
, Space
, Str "by"
, Space
, Str "EU"
, Space
, Str "citizens."
]
]
```
+69
View File
@@ -0,0 +1,69 @@
```
% pandoc -f jats -t native
<toc-group>
<toc-title-group>
<title>TOC group</title>
</toc-title-group>
<p>Content of toc group</p>
<toc>
<toc-title-group>
<title>TOC</title>
</toc-title-group>
<p>Content of TOC</p>
<toc-div content-type="sections">
<toc-title-group>
<title>Mental Health Services</title>
</toc-title-group>
<toc-entry>
<label>Section 1</label>
<title>Introduction</title>
<nav-pointer rid="tc3"/>
</toc-entry>
<toc-entry>
<label>Section 2</label>
<title>Mental Health of the Population</title>
<nav-pointer rid="tc4"/>
</toc-entry>
</toc-div>
</toc>
</toc-group>
^D
[ Header
1 ( "" , [] , [] ) [ Str "TOC" , Space , Str "group" ]
, Para
[ Str "Content"
, Space
, Str "of"
, Space
, Str "toc"
, Space
, Str "group"
]
, Header 2 ( "" , [] , [] ) [ Str "TOC" ]
, Para
[ Str "Content" , Space , Str "of" , Space , Str "TOC" ]
, Header
3
( "" , [] , [] )
[ Str "Mental"
, Space
, Str "Health"
, Space
, Str "Services"
]
, Header 4 ( "" , [] , [] ) [ Str "Introduction" ]
, Header
4
( "" , [] , [] )
[ Str "Mental"
, Space
, Str "Health"
, Space
, Str "of"
, Space
, Str "the"
, Space
, Str "Population"
]
]
```