Add files

RA-sec-titles.xq

@@ -0,0 +1,2 @@
+distinct-values(for $x in collection('articles')//*:article[(descendant::*:subject[text() = ('Research Article', 'Short Report', 'Tools and Resources', 'Research Advance', 'Registered Report', 'Replication Study', 'Research Communication')])]/*:body/*:sec/*:title
+return normalize-space($x))

acceptance-summaries.xq

@@ -0,0 +1,87 @@
+for $x in collection('articles')//*:article/*:sub-article[1]//*:p
+let $no := substring-before(substring-after($x/base-uri(),'/articles/elife-'),'-v')
+return
+if (matches($x,'^[Aa]cceptance summary[:]?$')) then 
+  if (matches($x/following-sibling::*:p[2],'^Decision letter after peer review[:]?$')) 
+      then (
+            ($no||' - '||('https://elifesciences.org/articles/'||$no||'#'||$x/ancestor::*:sub-article/@id)),
+            '
',
+            $x/following-sibling::*:p[1]/data(),
+            '
',
+            '  ----  ',
+            '
'
+           )
+  else if (matches($x/following-sibling::*:p[3],'^Decision letter after peer review[:]?$'))
+      then (
+            ($no||' - '||('https://elifesciences.org/articles/'||$no||'#'||$x/ancestor::*:sub-article/@id)),
+            '
',
+            $x/following-sibling::*:p[1]/data(),
+            $x/following-sibling::*:p[2]/data(),
+            '
',
+            '  ----  ',
+            '
'
+           )
+  else if (matches($x/following-sibling::*:p[4],'^Decision letter after peer review[:]?$'))
+     then (
+            ($no||' - '||('https://elifesciences.org/articles/'||$no||'#'||$x/ancestor::*:sub-article/@id)),
+            '
',
+            $x/following-sibling::*:p[1]/data(),
+            $x/following-sibling::*:p[2]/data(),
+            $x/following-sibling::*:p[3]/data(),
+            '
',
+            '  ----  ',
+            '
'
+           )
+    else if (matches($x/following-sibling::*:p[5],'^Decision letter after peer review[:]?$'))
+     then (
+            ($no||' - '||('https://elifesciences.org/articles/'||$no||'#'||$x/ancestor::*:sub-article/@id)),
+            '
',
+            $x/following-sibling::*:p[1]/data(),
+            $x/following-sibling::*:p[2]/data(),
+            $x/following-sibling::*:p[3]/data(),
+            $x/following-sibling::*:p[4]/data(),
+            '
',
+            '  ----  ',
+            '
'
+           )
+
+    else if (matches($x/following-sibling::*:p[6],'^Decision letter after peer review[:]?$'))
+     then (
+            ($no||' - '||('https://elifesciences.org/articles/'||$no||'#'||$x/ancestor::*:sub-article/@id)),
+            '
',
+            $x/following-sibling::*:p[1]/data(),
+            $x/following-sibling::*:p[2]/data(),
+            $x/following-sibling::*:p[3]/data(),
+            $x/following-sibling::*:p[4]/data(),
+            $x/following-sibling::*:p[5]/data(),
+            '
',
+            '  ----  ',
+            '
'
+           )
+     else if (matches($x/following-sibling::*:p[7],'^Decision letter after peer review[:]?$'))
+     then (
+            ($no||' - '||('https://elifesciences.org/articles/'||$no||'#'||$x/ancestor::*:sub-article/@id)),
+            '
',
+            $x/following-sibling::*:p[1]/data(),
+            $x/following-sibling::*:p[2]/data(),
+            $x/following-sibling::*:p[3]/data(),
+            $x/following-sibling::*:p[4]/data(),
+            $x/following-sibling::*:p[5]/data(),
+            $x/following-sibling::*:p[6]/data(),
+            '
',
+            '  ----  ',
+            '
'
+           )
+   else if (count($x/following-sibling::*:p)lt 3) 
+       then (
+            ($no||' - '||('https://elifesciences.org/articles/'||$no||'#'||$x/ancestor::*:sub-article/@id)),
+            '
',
+            for $y in $x/following-sibling::*:p
+            return $y/data(),
+            '
',
+            '  ----  ',
+            '
'
+           )  
+   else (($no||' - '||'ERROR'))
+else ()
+

add-ids-to-support.xq

@@ -0,0 +1,18 @@
+let $x := doc('/Users/fredatherden/Documents/GitHub/jats-support/src/support.sch')
+
+return copy $copy := $x
+modify(
+
+  for $x in $copy//(*:assert|*:report)
+  let $r := $x/ancestor::*:pattern/@id
+  let $pos := count($x/ancestor::*:pattern//*[local-name() = $x/local-name()]) - count($x/following::*[(local-name() = $x/local-name()) and (ancestor::*:pattern/@id = $r)])
+  return
+  insert node attribute id {concat($x/ancestor::*:pattern/@id,'-',$x/local-name(),'-',$pos)} as last into $x
+
+
+
+)
+
+return 
+
+file:write('/Users/fredatherden/Desktop/support.sch',$copy, map{'indent':'no'})

add-org-name-tests.xq

@@ -0,0 +1,59 @@
+declare variable $sch := doc('/Users/fredatherden/Documents/GitHub/eLife-JATS-schematron/schematron.sch');
+declare variable $base-uri := substring-before(base-uri($sch),'/schematron.sch');
+
+for $x in $sch//*:pattern[@id="org-pattern"]//(*:report|*:assert)
+let $org-name := substring-before(substring-after($x,"an organism - '"),"' - but there is n")
+let $rule-id := $x/parent::*:rule/@id
+let $path := concat($base-uri,'/tests/',$rule-id,'/',$x/@id,'/')
+let $pass := concat($path,'pass.xml')
+let $fail := concat($path,'fail.xml')
+let $pass-element := if ($rule-id = 'org-ref-article-book-title') then
+                <element-citation publication-type="journal">
+                  <article-title> test <italic>{$org-name}</italic> test </article-title>
+                </element-citation>
+                else 
+                <article-meta>
+                  <title-group>
+                    <article-title> test <italic>{$org-name}</italic> test </article-title>
+                  </title-group>
+                </article-meta>
+
+let $fail-element := if ($rule-id = 'org-ref-article-book-title') then
+                <element-citation publication-type="journal">
+                  <article-title>{concat(' test ',lower-case($org-name),' test ')}</article-title>
+                </element-citation>
+                else 
+                <article-meta>
+                  <title-group>
+                    <article-title>{concat(' test ',lower-case($org-name),' test ')}</article-title>
+                  </title-group>
+                </article-meta>
+
+let $pi-content := ('SCHSchema="'||$x/@id||'.sch'||'"') 
+let $comment := comment{concat('Context: ',$x/parent::*:rule/@context/string(),'
+Test: ',normalize-space($x/@test/string()))}
+
+let $pass-new := 
+(processing-instruction {'oxygen'}{$pi-content},
+$comment,
+  <root xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:ali="http://www.niso.org/schemas/ali/1.0">
+  <article>
+    {$pass-element}
+  </article>
+</root>)
+
+let $fail-new := 
+(processing-instruction {'oxygen'}{$pi-content},
+$comment,
+<root xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:ali="http://www.niso.org/schemas/ali/1.0">
+  <article>
+    {$fail-element}
+  </article>
+</root>
+)
+return
+(
+  file:write($pass,$pass-new),
+  file:write($fail,$fail-new)
+)
+

aff-edit-test.xq

@@ -0,0 +1,16 @@
+let $xml := doc('/Users/fredatherden/Desktop/elife-49920-vor-r2/elife-49920.xml')
+
+let $new-xml := copy $copy := $xml
+modify(
+  for $x in $copy//*:contrib-group[not(@content-type)]//*:aff
+  let $dept := $x/*:institution[@content-type="dept"]
+  let $inst := $x/*:institution[not(@content-type)]
+  return if ($inst = 'University of Kentucky') then (
+    replace node $inst with <institution>{concat($dept,', ',$inst)}</institution>,
+    delete node $dept
+  )
+  else ()
+)
+return $copy
+
+return file:write('Desktop/elife-49920.xml',$new-xml,map{'indent':'no'})

aff-tests.xq

@@ -0,0 +1,12 @@
+for $x in collection('articles')//*:contrib-group[not(@content-type)]
+let $list := 
+<list>{
+  for $aff in $x/*:aff
+  let $i := $aff/*:institution[not(@content-type)]
+  return 
+  if ($i=$aff/preceding-sibling::*:aff/institution[not(@content-type)]) then <item>{$aff}</item>
+  else ()
+}</list>
+return 
+if (count($list//*:item)>4) then $x/base-uri()
+else ()

alt-group-markup.xq

@@ -0,0 +1,24 @@
+let $xml :=  doc('/Users/fredatherden/Desktop/elife-42463-v1.xml')
+
+let $copy := copy $copy1 := $xml
+modify(
+  for $x in $copy1//*:contrib-group[@content-type="collab-list"]//*:aff
+  let $id := generate-id($x)
+  return insert node attribute id {$id} as first into $x
+)
+
+
+return copy $copy2 := $copy1
+modify(
+  for $x in $copy2//*:contrib-group[@content-type="collab-list"]//*:contrib
+  return replace value of node $x/@contrib-type with 'collaborator',
+
+  for $y in $copy2//*:contrib-group[@content-type="collab-list"]//*:contrib//*:aff
+  return 
+  (replace node $y with <xref ref-type="aff" rid="{$y/@id}"/>,
+   insert node $y as last into $y/ancestor::*:contrib-group[@content-type="collab-list"])
+
+)
+return $copy2
+
+return $copy

article.xq

@@ -0,0 +1,2 @@
+for $x in collection('articles')//*:article[(descendant::*:article-id[@pub-id-type="publisher-id"]= '42955') and descendant::*:body]
+return $x

award-ids.xq

@@ -0,0 +1,28 @@
+declare function local:get-doi($a){
+  let $id := $a/ancestor::*:article/descendant::*:article-id[@pub-id-type="publisher-id"][1]
+  let $version := substring-before(substring-after($a/base-uri(),concat($id,'-')),'.xml')
+  let $url := concat('https://elifesciences.org/articles/',$id,$version)
+  return copy $copy := $a
+  modify(
+    for $x in $copy/descendant-or-self::*:award-group
+    return insert node attribute {'url'}{$url} as last into $x
+  )
+  return $copy
+};
+
+
+
+
+<list xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:ali="http://www.niso.org/schemas/ali/1.0/">{
+for $x in collection('articles')//*:article//*:funding-group//*:award-group[*:award-id]
+let $id := $x/*:award-id
+let $y := replace($id,'[\p{P}\p{N}]|[Gg]rant','')
+let $new-x := local:get-doi($x)
+return
+if (matches($id,'\p{Ll}')) then (
+  if (string-length($y) < 10) then ()
+  else $new-x)
+else ()
+}</list>
+
+

batch-biorxiv-tranformation-2.xq

@@ -0,0 +1,78 @@
+declare namespace xlink="http://www.w3.org/1999/xlink";
+declare namespace mml="http://www.w3.org/1998/Math/MathML";
+
+
+declare variable $dir := '/Users/fredatherden/Desktop/biorxiv-tranformed/';
+declare variable $xsl := doc('/Users/fredatherden/Documents/xsl/biorxiv.xsl');
+
+
+for $x in collection('biorxiv-xml')//*:article[not(descendant::*:media[@mimetype="video"]) and not(descendant::mml:math) and not(descendant::table) and not(descendant::fig-group) and not(descendant::disp-quote) and (count(descendant::*:mixed-citation[@publication-type!='journal']) le 3)]
+let $filename := concat(substring-after($x//*:article-meta/*:article-id[@pub-id-type="doi"],'10.1101/'),'.xml')
+let $file := xslt:transform($x, $xsl)
+
+let $file2 := 
+copy $copy := $file
+modify(
+
+    for $x in $copy//*:fig
+    let $label := if (ends-with($x/*:label,'.')) then concat($x/*:label/text(),' ')
+                  else if (ends-with($x/*:label,'.')) then concat($x/*:label/text(),' ')
+                  else concat($x/*:label,'. ')
+    return 
+    replace node $x with 
+    <fig id="{$x/@id}">
+    <caption>
+    <title>{$label,
+            $x/*:caption/*:p/(*|text())}</title>
+    </caption>
+    <graphic xlink:href="{$x/*:graphic/@xlink:href/string()}" mimetype="image" mime-subtype="tiff" />
+    </fig>,
+
+    for $x in $copy//*:table-wrap
+    let $label := if (ends-with($x/*:label,'.')) then $x/*:label/text()
+                  else concat($x/*:label,'. ')
+    return 
+    replace node $x with 
+    <table-wrap id="{$x/@id}">
+    <caption>
+    <title>{$label,
+            $x/*:caption/*:p/(*|text())}</title>
+    </caption>
+    <graphic xlink:href="{$x/*:graphic/@xlink:href/string()}" mimetype="image" mime-subtype="tiff" />
+    </table-wrap>,
+
+    for $x in $copy//*:sec[(@sec-type="supplementary-material") and not(child::*[local-name()!='title' and local-name()!='supplementary-material'])]  
+    return 
+    delete node $x,
+
+    for $x in $copy//*:article-meta//*:contrib//*:xref[@ref-type="aff"]
+    let $a := $x/ancestor::*:article-meta//*:aff[@id = $x/@rid]
+    let $aff := <aff id="{generate-id($x/@rid)}">{
+      for $y in $a/(*|text())
+      return 
+      if ($y/local-name()='label') then ()
+      else $y/data() 
+    }</aff>
+    return 
+    replace node $x with $aff,
+
+    for $x in $copy//*:article-meta//*:aff
+    return delete node $x,
+
+    for $x in $copy//*:back/*:ack
+    return 
+     if ($x/*:title) then (delete node $x,
+     insert node <sec>{$x/*}</sec> as last into $x/preceding::body[1])
+     else (delete node $x,
+     insert node <sec><title>Acknowledgements</title>{$x/*}</sec> as last into $x/preceding::body[1]),
+
+    for $x in $copy//*:abstract
+    return 
+    (delete node $x,
+     insert node <sec>{$x/*}</sec> as first into $x/following::body[1])
+
+)
+return $copy
+
+return file:write(concat($dir,$filename),$file2, map {'indent':'no'})
+

batch-biorxiv-transform.xq

@@ -0,0 +1,14 @@
+declare namespace xlink="http://www.w3.org/1999/xlink";
+declare namespace mml="http://www.w3.org/1998/Math/MathML";
+
+
+declare variable $dir := '/Users/fredatherden/Desktop/biorxiv-tranformed/';
+declare variable $xsl := doc('/Users/fredatherden/Documents/xsl/mixed-2-element-citation.xsl');
+
+
+
+for $x in collection('biorxiv-xml')//*:article
+let $filename := concat(substring-after($x//*:article-meta/*:article-id[@pub-id-type="doi"],'10.1101/'),'.xml')
+let $file := xslt:transform($x, $xsl)
+return file:write(concat($dir,$filename),$file, map {'indent':'no'})
+

batch-normalise-test.xq

@@ -0,0 +1,8 @@
+let $xsl := doc('/Users/fredatherden/Documents/xsl/normalise.xsl')
+
+for $x in collection('ijm-xml')//*:article
+let $t := xslt:transform($x,$xsl)
+let $name :=  for $y in tokenize($x/base-uri(),'/')[last()]
+              return $y
+
+return file:write(concat('/Users/fredatherden/Desktop/output/',$name),$t)

batch-rdf-test.xq

@@ -0,0 +1,8 @@
+let $xsl := doc('/Users/fredatherden/Documents/xsl/jats2rdf.xsl')
+
+for $x in collection('ijm-xml')//*:article
+let $t := xslt:transform($x,$xsl)
+let $name :=  for $y in tokenize($x/base-uri(),'/')[last()]
+              return $y
+
+return file:write(concat('/Users/fredatherden/Desktop/output/',$name),$t)

batch-validate-test.xq

@@ -0,0 +1,15 @@
+import module namespace schematron = "http://github.com/Schematron/schematron-basex";
+
+declare variable $sch := schematron:compile(doc('/Users/fredatherden/Documents/GitHub/eLife-JATS-schematron/src/final-JATS-schematron.sch'));
+
+for $x in collection('articles')//*:article[matches(descendant::*:article-id[@pub-id-type="publisher-id"],'^4222')]
+let $article-id := $x//*:article-id[@pub-id-type="publisher-id"]/text()
+let $folder := concat('/articles/elife-',$article-id,'-v')
+let $v-no := number(substring-before(substring-after($x/base-uri(),$folder),'.xml'))
+let $count := count(collection('articles')//*:article[descendant::*:article-id[@pub-id-type="publisher-id"]/text() = $article-id])
+return if ($count != $v-no) then ()
+else 
+
+let $svrl := schematron:validate($x, $sch)
+return if ($svrl//*:successful-report[@id="unlinked-url-2"]) then $x/base-uri()
+else ()