Difference between revisions of "Cypher"
Jump to navigation
Jump to search
(Created page with " // Export TEI-Graph to Standoff-Property-JSON-Format match path=(d:XmlDocument)-[:NE*]->(e:XmlCharacters) where not (e)-[:NE]->() with tail(nodes(path)) as words, d with reduce(...") |
|||
| (5 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | + | <code> | |
| − | // Export TEI-Graph to Standoff-Property-JSON-Format | + | // Export TEI-Graph to Standoff-Property-JSON-Format by Stefan Armbruster |
| − | match path=(d:XmlDocument)-[:NE*]->(e:XmlCharacters) | + | match path=(d:XmlDocument)-[:NE*]->(e:XmlCharacters) |
| − | where not (e)-[:NE]->() | + | where not (e)-[:NE]->() |
| − | with tail(nodes(path)) as words, d | + | with tail(nodes(path)) as words, d |
| − | with reduce(s="", x in words| s + x.text ) as allText, d | + | with reduce(s="", x in words| s + x.text ) as allText, d |
| − | call apoc.path.expandConfig(d,{ | + | call apoc.path.expandConfig(d,{ |
| − | + | relationshipFilter: '<IS_CHILD_OF', | |
| − | + | labelFilter: 'XmlTag', | |
| − | + | bfs: false, | |
| − | + | minLevel: 1 | |
| − | }) yield path | + | }) yield path |
| − | with allText, path, nodes(path)[-1] as this | + | with allText, path, nodes(path)[-1] as this |
| − | MATCH p=(this)-[:NEXT*]->(x) | + | MATCH p=(this)-[:NEXT*]->(x) |
| − | where (x)-[:LAST_CHILD_OF*]->(this) and any(x in nodes(p) WHERE x:XmlCharacters) | + | 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, collect(p)[-1] as longest |
| − | with allText, this, [x in nodes(longest) where x:XmlCharacters] as xmlCharacters | + | with allText, this, [x in nodes(longest) where x:XmlCharacters] as xmlCharacters |
| − | with allText, this, | + | 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, { | + | 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 | + | } as standoffProperty |
| − | return {text: allText, properties: collect(standoffProperty)}; | + | return {text: allText, properties: collect(standoffProperty)}; |
| + | </code> | ||
Latest revision as of 12:55, 3 March 2022
// 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)};
