encoding.xml: update parser logic to skip BOM before prolog (#19858)

vlib/encoding/xml/parser.v

@@ -18,6 +18,9 @@ const (
 	double_dash                = '--'.bytes()
 	c_tag                      = '[C'.bytes()
 	data_chars                 = 'DATA'.bytes()
+
+	byte_order_marking_first   = u8(0xEF)
+	byte_order_marking_bytes   = [u8(0xBB), 0xBF]
 )
 
 // Helper types to assist in parsing
@@ -296,18 +299,30 @@ fn parse_doctype(mut reader io.Reader) !DocumentType {
 }
 
 fn parse_prolog(mut reader io.Reader) !(Prolog, u8) {
-	// Trim trailing whitespace
+	// Skip trailing whitespace and invalid characters
 	mut local_buf := [u8(0)]
 	mut ch := next_char(mut reader, mut local_buf)!
 	for {
 		match ch {
-			` `, `\t`, `\n` {
+			` `, `\t`, `\r`, `\n` {
 				ch = next_char(mut reader, mut local_buf)!
 				continue
 			}
 			`<` {
 				break
 			}
+			xml.byte_order_marking_first {
+				// UTF-8 BOM
+				mut bom_buf := [u8(0), 0]
+				if reader.read(mut bom_buf)! != 2 {
+					return error('Invalid UTF-8 BOM.')
+				}
+				if bom_buf != xml.byte_order_marking_bytes {
+					return error('Invalid UTF-8 BOM.')
+				}
+				ch = next_char(mut reader, mut local_buf)!
+				continue
+			}
 			else {
 				return error('Expecting a prolog or root node starting with "<".')
 			}

vlib/encoding/xml/test/local/20_bom_file/bom_test.v

@@ -0,0 +1,17 @@
+module main
+
+import os
+import encoding.xml
+
+fn test_valid_parsing() {
+	// We use a .bin file to avoid stripping the BOM from the XML file
+	path := os.join_path(os.dir(@FILE), 'workbook.bin')
+
+	doc := xml.XMLDocument.from_file(path) or {
+		assert false, 'Failed to parse workbook.bin'
+		exit(1)
+	}
+
+	sheets := doc.get_elements_by_tag('sheet')
+	assert sheets.len == 1, 'Expected 1 sheet, got ${sheets.len}'
+}

vlib/encoding/xml/test/local/20_bom_file/workbook.bin

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<workbook xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" mc:Ignorable="x15" xmlns:x15="http://schemas.microsoft.com/office/spreadsheetml/2010/11/main">
+    <fileVersion appName="xl" lastEdited="6" lowestEdited="6" rupBuild="14420"/>
+    <workbookPr defaultThemeVersion="164011"/>
+    <bookViews>
+        <workbookView xWindow="0" yWindow="0" windowWidth="22260" windowHeight="12645"/>
+    </bookViews>
+    <sheets>
+        <sheet name="Sheet1" sheetId="1" r:id="rId1"/>
+    </sheets>
+    <calcPr calcId="162913"/>
+    <extLst>
+        <ext uri="{140A7094-0E35-4892-8432-C4D2E57EDEB5}" xmlns:x15="http://schemas.microsoft.com/office/spreadsheetml/2010/11/main">
+            <x15:workbookPr chartTrackingRefBase="1"/>
+        </ext>
+    </extLst>
+</workbook>