X-Git-Url: http://git.indexdata.com/?p=mp-sparql-moved-to-github.git;a=blobdiff_plain;f=doc%2Fsparql.xml;h=afce82bb23e27620cea6b4bea3f21864f41966c9;hp=ba4eca7f8526e783ded7eca44ecdc2585f757e5e;hb=876978c2d978e86cc7bae354ae356e07a2bf389e;hpb=e5b5ae2b4836f76d84aae25c0edf4312b761dae4 diff --git a/doc/sparql.xml b/doc/sparql.xml index ba4eca7..afce82b 100644 --- a/doc/sparql.xml +++ b/doc/sparql.xml @@ -70,13 +70,33 @@ Section used to declare RPN use attribute strings (indexes) and map them to BIBFRAME graph patterns. Items in this section are expanded during RPN query processing and - placeholders (%s, %d) are substituted with query terms. + placeholders (%s, %d, + %t) are substituted with query terms. To map a given CQL index (e.g the default keyword index) into multiple entity properties, SPARQL constructs like `OPTIONAL` or `UNION` could be used. + <present type="attribute"/> + + + Section used to declare retrieval for a given element-set + (SRU schema). The CDATA is SPARQL where %u holds + the URI of the record. This can be used to construct the resulting + record. + + + + <modifier/> + + + Optional section that allows you to add solution sequences or + modifiers. + + + + @@ -89,7 +109,7 @@ - EXAMPLES + EXAMPLE Configuration for database "Default" that allows searching works. Only the field (use attribute) "bf.wtitle" is supported. @@ -97,11 +117,10 @@ + schema="sparql-results"> rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns bf: http://bibframe.org/vocab/ - SELECT ?work ?wtitle +
SELECT ?work ?wtitle
?work a bf:Work ?work bf:workTitle ?wt ?wt bf:titleValue ?wtitle @@ -110,9 +129,123 @@ ]]> + The matching is done by a simple case-sensitive substring match. There is + no deduplication, so if a work has two titles, we get two rows. + + + + EXAMPLE + + A more complex configuration for database "work". This could be included in + the same filter section as the "Default" db above. + + rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns + bf: http://bibframe.org/vocab/ +
SELECT + ?work + (sql:GROUP_DIGEST (?wtitle, ' ; ', 1000, 1)) AS ?title + (sql:GROUP_DIGEST (?creatorlabel, ' ; ', 1000, 1))AS ?creator + (sql:GROUP_DIGEST (?subjectlabel, ' ; ', 1000, 1))AS ?subject +
+ ?work a bf:Work + + OPTIONAL { + ?work bf:workTitle ?wt . + ?wt bf:titleValue ?wtitle } + + OPTIONAL { + ?work bf:creator ?creator . + ?creator bf:label ?creatorlabel } + + OPTIONAL { + ?work bf:subject ?subject . + ?subject bf:label ?subjectlabel } + + ?wt bf:titleValue %v FILTER(contains(%v, %s)) + ?creator bf:label %v FILTER(contains(%v, %s)) + ?subject bf:label %v FILTER(contains(%v, %s)) + { + ?work ?op1 ?child . + ?child ?op2 %v FILTER(contains(STR(%v), %s)) + } + + GROUP BY $work + +]]> + + + + This returns one row for each work. Titles, authors, and subjects + are all optional. If they repeat, the repeated values are concatenated into + a single field, separated by semicolons. This is done by the GROUP_DIGEST + function that is specific to the Virtuoso back end. + + + This example supports use attributes 4 (title), 1003 (author), 21 (subject), + and 1016 (keyword) which matches any literal in a triplet that refers to the + work, so it works for the titleValue in the workTitle, as well as the label + in the subject, and what ever else there may be. Like the preceding example, + the matching is by a simple substring, case sensitive. A more realistic term + matching could be done with regular expressions, at the cost of some readability + portability, and performance. + + + + EXAMPLE + + Configuration for database "works". This uses CONSTRUCT to produce rdf. + + rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns + bf: http://bibframe.org/vocab/ +
CONSTRUCT { + ?work bf:title ?wtitle . + ?work bf:instanceTitle ?title . + ?work bf:author ?creator . + ?work bf:subject ?subjectlabel } +
+ ?work a bf:Work + + ?work bf:workTitle ?wt + ?wt bf:titleValue ?wtitle + ?wt bf:titleValue %v FILTER(contains(%v, %s)) + ?work bf:creator ?creator + ?creator bf:label ?creatorlabel + ?creator bf:label %v FILTER(contains(%v, %s)) + ?work bf:subject ?subject + ?subject bf:label ?subjectlabel + ?subject bf:label %v FILTER(contains(%v, %s)) + + ]]> + + EXAMPLE + + Configuration for database "instance". Like "work" above this uses SELECT + to return row-based data, this time from the instances. This is not deduplicated, + so if an instance has two titles, we get two rows, and if it also has + two formats, we get four rows. The DISTINCT in the SELECT + + rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns + bf: http://bibframe.org/vocab/ +
SELECT DISTINCT ?instance ?title ?format
+ ?instance a bf:Instance + ?instance bf:title ?title + ?instance bf:title %v FILTER(contains(%v, %s)) + ?instance bf:format ?format + ?instance bf:format %s + + ]]> + + + + + + SEE ALSO