Document pageSetup.

diff --git a/parse-all-xml b/parse-all-xml
index 0dfd8102500184356c46daafdbdc4d2055a1e226..c4146fc0194b17b7c82cb3c038f104e068d6d686 100755 (executable)
--- a/parse-all-xml
+++ b/parse-all-xml
@@ -5,18 +5,10 @@
 # Also skip those with borderProperties, which indicate the non-"light"
 # format.
 lightTables=`ls -1 unzipped/*/*.xml |grep -vE 'notes|table|warning|chart|model' \
-          | xargs grep -EL '<([a-z]*:)?(model|graph|pageSetup|borderProperties)'`
-#printf 'Structure:\n'
-#for d in $lightTables; do
-#    ./parse-xml $d containment
-#done | sort | uniq -c | sort -rn
+          | xargs grep -EL '<([a-z]*:)?(model|graph)'`
 
-printf '\nAttributes:\n'
-for d in $lightTables; do
-    ./parse-xml $d text
-done | sort | uniq -c | sort -rn
-
-#printf '\nLabels:\n'
-#for d in $lightTables; do
-#    ./parse-xml $d labels
-#done | sort | uniq -c | sort -rn
+if test -n "$1"; then
+    for d in $lightTables; do
+       ./parse-xml $d $1
+    done | sort | uniq -c | sort -rn
+fi

diff --git a/parse-xml.c b/parse-xml.c
index 9304e8b0dcc5f0e4dac0de070ade6ae058318e7c..7fc3da2ed1ba84acd2c6867d957129cc2c3f156b 100644 (file)
--- a/parse-xml.c
+++ b/parse-xml.c
@@ -111,12 +111,27 @@ print_attribute (xmlNode *node, const char *attr)
     {
       const char *s = (char *) xmlGetProp (node, (xmlChar *) attr);
       if (s)
-        printf ("%s %s\n", node->name, s);
+        printf ("%s %s=%s\n", node->name, attr, s);
 
       print_attribute (node->children, attr);
     }
 }
 
+static xmlNode *
+find_page_setup (xmlNode *node)
+{
+  for (; node; node = node->next)
+    {
+      if (node->name && !strcmp ((char *) node->name, "pageSetup"))
+        return node;
+
+      xmlNode *ps = find_page_setup (node->children);
+      if (ps)
+        return ps;
+    }
+  return NULL;
+}
+
 static void
 print_text (xmlNode *node)
 {
@@ -161,6 +176,10 @@ main (int argc, char **argv)
     }
 
   xmlNode *root = xmlDocGetRootElement(doc);
+  root = find_page_setup(root);
+  if (!root)
+    return 0;
+  root->next = NULL;
 
   if (!strcmp(argv[2], "containment"))
     print_containment (root);

diff --git a/spv-file-format.texi b/spv-file-format.texi
index 15f195623d83f3b50ba41be88a72eb0ffb6c07e5..5e95b53a9e1491acc15326e297c70c47a5a07ba8 100644 (file)
--- a/spv-file-format.texi
+++ b/spv-file-format.texi
@@ -93,12 +93,14 @@ require a reader to take schemas or namespaces into account.
 @table @code
 @item heading
 Parent: Document root or @code{heading} @*
-Contents: @code{label} [@code{container} | @code{heading}]*
+Contents: [@code{pageSetup}] @code{label} [@code{container} | @code{heading}]*
 
 The root of a structure member is a @code{heading}, which represents a
 section of output beginning with a title (the @code{label}) and
-ordinarily followed by a container for content and possibly further
-nested (sub)-sections of output.
+ordinarily followed by content containers or further nested
+(sub)-sections of output.
+
+The document root heading may also contain a @code{pageSetup} element.
 
 The following attributes have been observed on both document root and
 nested @code{heading} elements:
@@ -202,6 +204,10 @@ The width of the container in the form @code{@var{n}px}, e.g.@:
 Parent: @code{container} @*
 Contents: @code{html}
 
+This @code{text} element is nested inside a @code{container}.  There
+is a different @code{text} element that is nested inside a
+@code{pageParagraph}.
+
 @table @asis
 @item Required attribute: @code{type}
 One of @code{title}, @code{log}, or @code{text}.
@@ -268,4 +274,82 @@ Contents: text
 
 Contains the name of the Zip member that holds the table details,
 e.g.@: @code{0000000001437_lightTableData.bin}.
+
+@item pageSetup
+Parent: @code{heading} @*
+Contents: @code{pageHeader} @code{pageFooter}
+
+@table @asis
+@item Required attribute: @code{initial-page-number}
+Always @code{1}.
+
+@item Optional attribute: @code{chart-size}
+Always @code{as-is} or a localization (!) of it (e.g.@: @code{dimensione
+attuale}, @code{Wie vorgegeben}).
+
+@item Optional attribute: @code{margin-left}
+@itemx Optional attribute: @code{margin-right}
+@itemx Optional attribute: @code{margin-top}
+@itemx Optional attribute: @code{margin-bottom}
+Margin sizes in the form @code{@var{size}in}, e.g.@: @code{0.25in}.
+
+@item Optional attribute: @code{paper-height}
+@itemx Optional attribute: @code{paper-width}
+Paper sizes in the form @code{@var{size}in}, e.g.@: @code{8.5in} by
+@code{11in} for letter paper or @code{8.267in} by @code{11.692in} for
+A4 paper.
+
+@item Optional attribute: @code{reference-orientation}
+Always @code{0deg}.
+
+@item Optional attribute: @code{space-after}
+Always @code{12pt}.
+@end table
+
+@item pageHeader
+@itemx pageFooter
+Parent: @code{pageSetup} @*
+Contents: @code{pageParagraph}*
+
+No attributes.
+
+@item pageParagraph
+Parent: @code{pageHeader} or @code{pageFooter} @*
+Contents: @code{text}
+
+Text to go at the top or bottom of a page, respectively.
+
+@item text
+Parent: @code{pageParagraph} @*
+Contents: [cdata]
+
+This @code{text} element is nested inside a @code{pageParagraph}.  There
+is a different @code{text} element that is nested inside a
+@code{container}.
+
+The element is either empty, or contains cdata that holds almost-XHTML
+text: in the corpus, either an @code{html} or @code{p} element.  It is
+@emph{almost}-XHTML because the @code{html} element designates the
+default namespace as
+@code{http://xml.spss.com/spss/viewer/viewer-tree} instead of an XHTML
+namespace.
+
+The cdata can contain substitution variables: @code{&[Page]} for the
+page number and @code{&[PageTitle]} for the page title.
+
+Typical contents (indented for clarity):
+
+@example
+<html xmlns="http://xml.spss.com/spss/viewer/viewer-tree">
+    <head></head>
+    <body>
+        <p style="text-align:right; margin-top: 0">Page &[Page]</p>
+    </body>
+</html>
+@end example
+
+@table @asis
+@item Required attribute: @code{type}
+Always @code{text}.
+@end table
 @end table