Cypher

From TEIWiki
Revision as of 13:55, 3 March 2022 by Andreas Kuczera (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

// Export TEI-Graph to Standoff-Property-JSON-Format by Stefan Armbruster
match path=(d:XmlDocument)-[:NE*]->(e:XmlCharacters)
where not (e)-[:NE]->()
with tail(nodes(path)) as words, d
with reduce(s="", x in words| s + x.text ) as allText, d
call apoc.path.expandConfig(d,{
relationshipFilter: '<IS_CHILD_OF',
labelFilter: 'XmlTag',
bfs: false,
minLevel: 1
}) yield path
with allText, path, nodes(path)[-1] as this
MATCH p=(this)-[:NEXT*]->(x)
where (x)-[:LAST_CHILD_OF*]->(this) and any(x in nodes(p) WHERE x:XmlCharacters)
with allText, this, collect(p)[-1] as longest
with allText, this, [x in nodes(longest) where x:XmlCharacters] as xmlCharacters
with allText, this, 
apoc.coll.min([x in xmlCharacters | x.startIndex]) as min, 
apoc.coll.max([x in xmlCharacters | x.endIndex]) as max, 
apoc.text.join([x in xmlCharacters | x.text], "") as text
with allText, {
index:id(this), 
startIndex: min, 
endIndex: max,
text: text,
type: this._name,
attributes: apoc.map.fromPairs([x in keys(this) WHERE not x starts with "_" | [x, this[x]] ])
} as standoffProperty
return {text: allText, properties: collect(standoffProperty)};