Improve XML parser.

Add a whitespace preserving mode, for future use with XHTML.

Also parse XHTML entities. This is not strictly according to spec,
but for properly formed XML documents it should not matter.

1 files changed, 13 insertions, 1 deletions

diff --git a/include/mupdf/fitz/xml.h b/include/mupdf/fitz/xml.h
index ce391029..85ed4a2a 100644
--- a/include/mupdf/fitz/xml.h
+++ b/include/mupdf/fitz/xml.h
@@ -12,8 +12,15 @@ typedef struct fz_xml_s fz_xml;
 
 /*
 	fz_parse_xml: Parse a zero-terminated string into a tree of xml nodes.
+
+	preserve_white: whether to keep or delete all-whitespace nodes.
+*/
+fz_xml *fz_parse_xml(fz_context *ctx, unsigned char *buf, int len, int preserve_white);
+
+/*
+	fz_xml_prev: Return previous sibling of XML node.
 */
-fz_xml *fz_parse_xml(fz_context *ctx, unsigned char *buf, int len);
+fz_xml *fz_xml_prev(fz_xml *item);
 
 /*
 	fz_xml_next: Return next sibling of XML node.
@@ -21,6 +28,11 @@ fz_xml *fz_parse_xml(fz_context *ctx, unsigned char *buf, int len);
 fz_xml *fz_xml_next(fz_xml *item);
 
 /*
+	fz_xml_up: Return parent of XML node.
+*/
+fz_xml *fz_xml_up(fz_xml *item);
+
+/*
 	fz_xml_down: Return first child of XML node.
 */
 fz_xml *fz_xml_down(fz_xml *item);