diff --git a/modules/intermediate_format/markerset.xqm b/modules/intermediate_format/markerset.xqm
index a25714693780e436ea5098b295df9adb082001d3..bec33898ef8891337c33f4ffca29571b3087499e 100644
--- a/modules/intermediate_format/markerset.xqm
+++ b/modules/intermediate_format/markerset.xqm
@@ -1,5 +1,5 @@
xquery version "3.0";
-(:~
+(:~
: MARKERSET Module ("markerset", "http://bdn.edition.de/intermediate_format/markerset")
: *******************************************************************************************
: This module is a helper module and defines functions to collect and construct reading markers
@@ -14,32 +14,32 @@ declare default element namespace "http://www.tei-c.org/ns/1.0";
(:############################# Modules Functions #############################:)
-(:~
+(:~
: markerset:collect-markers()
: This function collect markers for a given reading.
: It destinguishes tei:lem and tei:rdg. In case of tei:lem it collects all sibling tei:rdgs. In case of tei:rdg it collect itself.
:
: @param $reading the reading node to collect readings for
: @return node() representing a markerset of readings for the given node
- :
+ :
: @version 2.0 (2018-01-29)
: @status working
: @author Uwe Sikora
:)
declare function markerset:collect-markers
( $reading as node()* ) as item() {
-
+
let $markers := (
if ($reading[self::lem]) then (
attribute {"count"}{count($reading/following-sibling::rdg)},
for $sibling in $reading/following-sibling::rdg
return(
element {name($sibling)} {
- $sibling/@*,
+ $sibling/@*,
attribute {"context"}{"lem"}
}
)
- )
+ )
else if ($reading[self::rdg]) then (
element {name($reading)} {
$reading/@*,
@@ -56,24 +56,24 @@ declare function markerset:collect-markers
};
-(:~
+(:~
: markerset:merge-markers()
: This function merges markers in a given set by the same type. It orders the merged markers according to an explicit ordering.
:
: @param $markerset node() including the markers that should be merged
: @return node()* representing the merged markerset
- :
+ :
: @version 2.0 (2018-01-29)
: @status working
: @author Uwe Sikora
:)
declare function markerset:merge-markers
( $markerset as node()* ) as item()* {
-
+
let $order := ("om","ppl", "ptl", "pp", "pt" , "v")
let $reading-types := distinct-values( $markerset[self::rdg or self::lem]/string(@type) )
-
- return (
+
+ return (
attribute {"order"}{distinct-values( ($order, $reading-types) ) },
for $type in distinct-values( ($order, $reading-types) )
let $rdgs := $markerset[@type = $type]
@@ -86,14 +86,14 @@ declare function markerset:merge-markers
attribute type {$type}
}
) else ()
-
+
)
};
-(:~
+(:~
: markerset:marker()
- : Constructor function which creates the marker element with name, mark-type and references
+ : Constructor function which creates the marker element with name, mark-type and references
:
: @param $name The name of the marker element
: @param $mark The mark type e.g. open or close
@@ -105,19 +105,20 @@ declare function markerset:merge-markers
:)
declare function markerset:marker
($name as xs:string, $type as xs:string, $reading as node()) as element(){
-
- element {$name} {
+ if($type = 'open' and data($reading/@type) = 'v' and $reading/@context = 'rdg')
+ then ()
+ else (element {$name} {
(:attribute bdnp_parent {$node/parent::node()/name()}, :)
attribute wit { replace(data($reading/@wit), '#', '') },
attribute type { data($reading/@type) },
attribute ref { data($reading/@id) },
attribute mark { $type },
attribute context { $reading/@context }
- }
+ })
};
-(:~
+(:~
: markerset:construct-marker-from-markerset
: Helping function to construct markers for a sequence of markersets
:
@@ -131,9 +132,9 @@ declare function markerset:marker
:)
declare function markerset:construct-marker-from-markerset
( $name as xs:string, $marker-type as xs:string, $marker-set as node()* ) as item()* {
-
+
for $marker in $marker-set/node()
return (
markerset:marker($name, $marker-type, $marker)
)
-};
\ No newline at end of file
+};
diff --git a/modules/intermediate_format/preprocessing.xqm b/modules/intermediate_format/preprocessing.xqm
index f9ddaf00b9e41e2f2f9df47bd9eb737caf49fd5a..061e16c723bf0af48b95276104252204e8d54a87 100644
--- a/modules/intermediate_format/preprocessing.xqm
+++ b/modules/intermediate_format/preprocessing.xqm
@@ -1,11 +1,11 @@
xquery version "3.0";
-(:~
+(:~
: PREPROCESSING Module ("pre", "http://bdn.edition.de/intermediate_format/preprocessing")
: *******************************************************************************************
: This module contains the preprocessing routines for the intermediate format
:
: It imports the whitespace handling helper module to make some whitespace handling duricng the preprocessing
-
+
: @version 2.0 (2018-01-29)
: @status working
: @author Uwe Sikora
@@ -18,20 +18,20 @@ declare default element namespace "http://www.tei-c.org/ns/1.0";
(:############################# Modules Functions #############################:)
-(:~
+(:~
: pre:preprocessing-textNode
: preprocessing function which converts each text() into a xml-node "textNode". This function is a experimental fall back solution and not the main preprocessing routine!
:
: @param $nodes the nodes to be converted
: @return item()* representing the converted node
- :
+ :
: @version 1.2 (2017-10-15)
: @status working
: @author Uwe Sikora
:)
declare function pre:preprocessing-textNode
($nodes as node()*) as item()* {
-
+
for $node in $nodes
return
typeswitch($node)
@@ -44,7 +44,7 @@ declare function pre:preprocessing-textNode
}
)
)
-
+
case element(TEI) return (
element{$node/name()}{
$node/@*,
@@ -54,7 +54,7 @@ declare function pre:preprocessing-textNode
}
}
)
-
+
case element(lem) return (
element{$node/name()}{
$node/@*,
@@ -62,7 +62,7 @@ declare function pre:preprocessing-textNode
pre:preprocessing-textNode($node/node())
}
)
-
+
case element(rdg) return (
element{$node/name()}{
$node/@*,
@@ -70,7 +70,7 @@ declare function pre:preprocessing-textNode
pre:preprocessing-textNode($node/node())
}
)
-
+
case element(note) return (
if ($node[@type eq "editorial"]) then (
) else (
@@ -80,8 +80,8 @@ declare function pre:preprocessing-textNode
}
)
)
-
- default return (
+
+ default return (
element{$node/name()}{
$node/@*,
pre:preprocessing-textNode($node/node())
@@ -90,7 +90,7 @@ declare function pre:preprocessing-textNode
};
-(:~
+(:~
: pre:pre:default-element
: function that suites as default element constructor for the preproseccing conversion.
: It is more or less a copy function, copying the elements name and its node and recurively leeds the conversion to its child-nodes
@@ -98,7 +98,7 @@ declare function pre:preprocessing-textNode
: @param $node the node to be copied
: @param $recursive-function the recursive function as some kind of call back to the main conversion
: @return item()* representing the converted node
- :
+ :
: @version 1.0 (2018-01-31)
: @note Would be great if $recursive-function would be a real function and not a node-sequence (TO-DO)
: @status working
@@ -106,39 +106,49 @@ declare function pre:preprocessing-textNode
:)
declare function pre:default-element
( $node as node(), $recursive-function as node()* ) as item()* {
-
- element{$node/name()}{
- $node/@*,
- $recursive-function
- }
+ let $following-node := $node/following-sibling::node()[1]
+ let $following-sibling := $node/following-sibling::*[1]
+ return
+ element{$node/name()}{
+ $node/@*,
+ (if($following-node[matches(., "[\s\n\r\t]") and normalize-space(.) = ""]
+ and $following-sibling[self::ref or self::app or self::hi or self::bibl
+ or self::foreign or self::choice or self::milestone or self::persName
+ or self::choice or self::index or self::seg]
+ and not($node[self::index]))
+ then
+ attribute {"break-after"}{"yes"}
+ else ()),
+ $recursive-function
+ }
};
-(:~
+(:~
: pre:preprocessing
: main preprocessing function.
:
: @param $nodes the nodes to be converted
: @return item()* representing the converted node
- :
+ :
: @version 2.0 (2018-02-01)
: @status working
: @author Uwe Sikora
:)
declare function pre:preprocessing
($nodes as node()*) as item()* {
-
+
for $node in $nodes
return
typeswitch($node)
case processing-instruction() return ()
-
+
case text() return (
whitespace:text($node, " ")
)
-
+
case comment() return ()
-
+
case element(TEI) return (
element{$node/name()}{
$node/@*,
@@ -150,19 +160,19 @@ declare function pre:preprocessing
}
}
)
-
+
case element(teiHeader) return ( $node )
-
+
case element(div) return (
if ($node[@type = 'section-group']) then (
pre:preprocessing($node/node())
- )
+ )
else (
pre:default-element( $node, pre:preprocessing($node/node()) )
)
-
+
)
-
+
case element(lem) return (
element{$node/name()}{
$node/@*,
@@ -170,7 +180,7 @@ declare function pre:preprocessing
pre:preprocessing($node/node())
}
)
-
+
case element(rdg) return (
element{$node/name()}{
$node/@*,
@@ -178,87 +188,84 @@ declare function pre:preprocessing
pre:preprocessing($node/node())
}
)
-
+
case element(note) return (
if ( $node[@type != "editorial"] or $node[ not(@type) ] ) then (
pre:default-element( $node, pre:preprocessing($node/node()) )
) else ( )
)
-
+
case element(pb) return (
let $preceding-sibling := $node/preceding-sibling::node()[1]
let $following-sibling := $node/following-sibling::node()[1]
- let $first := $node = $node/parent::node()/node()[not(self::text() and normalize-space(self::node()) = '')][1]
- let $ignore := ("docAuthor", "app", "index", "seg", "bibl")
return
element {$node/name()}{
$node/@*,
-
- if (
+
+ if (
( $preceding-sibling[self::text() and not(normalize-space(.) = '')] and ends-with($preceding-sibling, " ") = false() )
and
( $following-sibling[self::text() and not(normalize-space(.) = '')] and starts-with($following-sibling, " ") = false() )
- ) then ( attribute {"break"}{"no"} )
-
- (:else if (
- ( $preceeding-sibling[self::text() and not(normalize-space(.) = '')] and ends-with($preceeding-sibling, " ") = true() )
- and
- ( $following-sibling[self::text() and not(normalize-space(.) = '')] and starts-with($following-sibling, " ") = true() )
- ) then ( attribute {"clear"}{"left"} ) :)
-
- else if ( $following-sibling[self::docAuthor or self::app or self::index or self::seg or self::bibl] ) then (
- attribute {"break"}{"yes"}
- )
-
- else if (
- ( $preceding-sibling[self::text()][matches(., "[\s\n\r\t]") and normalize-space(.) = ""] )
+ ) then ( attribute {"break"}{"no"} )
+ else if (
+ ( $preceding-sibling[matches(., "[\s\n\r\t]") and normalize-space(.) = ""] )
and
- ( $following-sibling[self::text()][matches(., "[\s\n\r\t]") and normalize-space(.) = ""] )
+ ( $following-sibling[matches(., "[\s\n\r\t]") and normalize-space(.) = ""] )
) then (
- attribute {"break"}{"yes"}
+ attribute {"break-before"}{"yes"},
+ attribute {"break-after"}{"yes"}
+ )
+ else if (
+ $preceding-sibling[matches(., "[\s\n\r\t]") and normalize-space(.) = ""]
+ ) then (
+ attribute {"break-before"}{"yes"}
+ )
+ else if (
+ $following-sibling[matches(., "[\s\n\r\t]") and normalize-space(.) = ""]
+ ) then (
+ attribute {"break-after"}{"yes"}
)
-
else ( )
}
)
-
+
case element(hi) return (
- if($node[@rend = 'right-aligned' or @rend = 'center-aligned']) then(
+ if($node[@rend = 'right-aligned' or @rend = 'center-aligned']) then(
element {'aligned'} {
$node/@*,
pre:preprocessing($node/node())
- }
+ }
)
else (
pre:default-element( $node, pre:preprocessing($node/node()) )
)
)
-
+
case element(seg) return (
if($node[@type = 'item']) then(
element {'item'} {
$node/@*[name() != 'type'],
pre:preprocessing($node/node())
- }
+ }
)
else if($node[@type = 'head']) then(
element {'head'} {
$node/@*[name() != 'type'],
pre:preprocessing($node/node())
- }
+ }
)
else if($node[@type = 'row']) then(
element {'row'} {
$node/@*[name() != 'type'],
pre:preprocessing($node/node())
- }
+ }
)
else (
pre:default-element( $node, pre:preprocessing($node/node()) )
)
)
-
- default return (
+
+ default return (
pre:default-element( $node, pre:preprocessing($node/node()) )
)
-};
\ No newline at end of file
+};
diff --git a/modules/intermediate_format/whitespace-handling.xqm b/modules/intermediate_format/whitespace-handling.xqm
index dd7bee3d553dcdad37e57aada1cfd5ab5eea715c..4e797d5772be53852413093f2c18d048e88d1b1e 100644
--- a/modules/intermediate_format/whitespace-handling.xqm
+++ b/modules/intermediate_format/whitespace-handling.xqm
@@ -1,5 +1,5 @@
xquery version "3.0";
-(:~
+(:~
: WHITESPACE Module ("whitespace", "http://bdn.edition.de/intermediate_format/whitespace_handling")
: *******************************************************************************************
: This module contains the functions to handle different whitespace operations on text
@@ -9,12 +9,14 @@ xquery version "3.0";
: @author Uwe Sikora
:)
module namespace whitespace="http://bdn.edition.de/intermediate_format/whitespace_handling";
+import module namespace pre="http://bdn.edition.de/intermediate_format/preprocessing" at "preprocessing.xqm";
+
declare default element namespace "http://www.tei-c.org/ns/1.0";
(:############################# Modules Functions #############################:)
-(:~
+(:~
: whitespace:text()
: This function handles whitespace in defined text() nodes
:
@@ -28,26 +30,26 @@ declare default element namespace "http://www.tei-c.org/ns/1.0";
:)
declare function whitespace:text
( $text as text()*, $escape-char as xs:string? ) as text()* {
-
+
let $normalized := normalize-space($text)
let $whitespace-node := $text[matches(., "[\s\n\r\t]") and normalize-space(.) = ""]
let $single-whitespace-between-nodes := $text = ' '
- return
+ return
if ( not($whitespace-node) or $single-whitespace-between-nodes) then (
-
+
if ($escape-char) then (
- whitespace:escape-text($text, "#")
+ whitespace:escape-text($text, "@")
) else ( whitespace:escape-text($text, " ") )
-
- )
+
+ )
else ()
-
+
};
-(:~
+(:~
: whitespace:escape-text()
- : This function replaces whitespaces in a text()
+ : This function replaces whitespaces in a text()
: with a defined preservation character
:
: @param $text the text-node to be converted