kreuzberg 4.0.0.pre.rc.6

data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs

@@ -0,0 +1,247 @@
+//! Core properties extraction from docProps/core.xml
+//!
+//! Extracts Dublin Core metadata from Office Open XML documents.
+
+use crate::error::{KreuzbergError, Result};
+use std::io::Read;
+use zip::ZipArchive;
+
+/// Dublin Core metadata from docProps/core.xml
+///
+/// Contains standard metadata fields defined by the Dublin Core standard
+/// and Office-specific extensions.
+#[derive(Debug, Clone, Default, PartialEq)]
+pub struct CoreProperties {
+    /// Document title
+    pub title: Option<String>,
+    /// Document subject/topic
+    pub subject: Option<String>,
+    /// Document creator/author
+    pub creator: Option<String>,
+    /// Keywords or tags
+    pub keywords: Option<String>,
+    /// Document description/abstract
+    pub description: Option<String>,
+    /// User who last modified the document
+    pub last_modified_by: Option<String>,
+    /// Revision number
+    pub revision: Option<String>,
+    /// Creation timestamp (ISO 8601)
+    pub created: Option<String>,
+    /// Last modification timestamp (ISO 8601)
+    pub modified: Option<String>,
+    /// Document category
+    pub category: Option<String>,
+    /// Content status (Draft, Final, etc.)
+    pub content_status: Option<String>,
+    /// Document language
+    pub language: Option<String>,
+    /// Unique identifier
+    pub identifier: Option<String>,
+    /// Document version
+    pub version: Option<String>,
+    /// Last print timestamp (ISO 8601)
+    pub last_printed: Option<String>,
+}
+
+/// Extract core properties from an Office Open XML document
+///
+/// Parses `docProps/core.xml` from the ZIP archive and extracts Dublin Core metadata.
+///
+/// # Arguments
+///
+/// * `archive` - ZIP archive containing the Office document
+///
+/// # Returns
+///
+/// Returns `CoreProperties` with extracted metadata. Fields that are not present
+/// in the document will be `None`.
+///
+/// # Errors
+///
+/// Returns an error if:
+/// - The ZIP archive cannot be read
+/// - The core.xml file is malformed
+/// - XML parsing fails
+///
+/// # Example
+///
+/// ```no_run
+/// use kreuzberg::extraction::office_metadata::extract_core_properties;
+/// use std::fs::File;
+/// use zip::ZipArchive;
+///
+/// let file = File::open("document.docx")?;
+/// let mut archive = ZipArchive::new(file)?;
+/// let core = extract_core_properties(&mut archive)?;
+///
+/// println!("Title: {:?}", core.title);
+/// println!("Creator: {:?}", core.creator);
+/// println!("Created: {:?}", core.created);
+/// # Ok::<(), Box<dyn std::error::Error>>(())
+/// ```
+pub fn extract_core_properties<R: Read + std::io::Seek>(archive: &mut ZipArchive<R>) -> Result<CoreProperties> {
+    let mut xml_content = String::new();
+
+    match archive.by_name("docProps/core.xml") {
+        Ok(mut file) => {
+            file.read_to_string(&mut xml_content)
+                .map_err(|e| KreuzbergError::parsing(format!("Failed to read core.xml: {}", e)))?;
+        }
+        Err(_) => {
+            return Ok(CoreProperties::default());
+        }
+    }
+
+    let doc = roxmltree::Document::parse(&xml_content)
+        .map_err(|e| KreuzbergError::parsing(format!("Failed to parse core.xml: {}", e)))?;
+
+    let root = doc.root_element();
+
+    let title = super::parse_xml_text(root, "title");
+    let subject = super::parse_xml_text(root, "subject");
+    let creator = super::parse_xml_text(root, "creator");
+    let description = super::parse_xml_text(root, "description");
+    let language = super::parse_xml_text(root, "language");
+    let identifier = super::parse_xml_text(root, "identifier");
+
+    let keywords = super::parse_xml_text(root, "keywords");
+    let last_modified_by = super::parse_xml_text(root, "lastModifiedBy");
+    let revision = super::parse_xml_text(root, "revision");
+    let category = super::parse_xml_text(root, "category");
+    let content_status = super::parse_xml_text(root, "contentStatus");
+    let version = super::parse_xml_text(root, "version");
+
+    let created = super::parse_xml_text(root, "created");
+    let modified = super::parse_xml_text(root, "modified");
+    let last_printed = super::parse_xml_text(root, "lastPrinted");
+
+    Ok(CoreProperties {
+        title,
+        subject,
+        creator,
+        keywords,
+        description,
+        last_modified_by,
+        revision,
+        created,
+        modified,
+        category,
+        content_status,
+        language,
+        identifier,
+        version,
+        last_printed,
+    })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::io::{Cursor, Write};
+
+    fn create_test_zip_with_core_xml(core_xml: &str) -> ZipArchive<Cursor<Vec<u8>>> {
+        let buffer = Vec::new();
+        let cursor = Cursor::new(buffer);
+        let mut zip = zip::ZipWriter::new(cursor);
+
+        let options = zip::write::FileOptions::<()>::default().compression_method(zip::CompressionMethod::Stored);
+
+        zip.start_file("docProps/core.xml", options).unwrap();
+        zip.write_all(core_xml.as_bytes()).unwrap();
+
+        let cursor = zip.finish().unwrap();
+        ZipArchive::new(cursor).unwrap()
+    }
+
+    #[test]
+    fn test_extract_core_properties_full() {
+        let core_xml = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<cp:coreProperties xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
+                   xmlns:dc="http://purl.org/dc/elements/1.1/"
+                   xmlns:dcterms="http://purl.org/dc/terms/"
+                   xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+    <dc:title>Test Document</dc:title>
+    <dc:subject>Testing</dc:subject>
+    <dc:creator>John Doe</dc:creator>
+    <cp:keywords>test, metadata</cp:keywords>
+    <dc:description>A test document</dc:description>
+    <cp:lastModifiedBy>Jane Doe</cp:lastModifiedBy>
+    <cp:revision>5</cp:revision>
+    <dcterms:created xsi:type="dcterms:W3CDTF">2024-01-01T10:00:00Z</dcterms:created>
+    <dcterms:modified xsi:type="dcterms:W3CDTF">2024-01-02T15:30:00Z</dcterms:modified>
+    <cp:category>Documents</cp:category>
+    <cp:contentStatus>Final</cp:contentStatus>
+    <dc:language>en-US</dc:language>
+</cp:coreProperties>"#;
+
+        let mut archive = create_test_zip_with_core_xml(core_xml);
+        let props = extract_core_properties(&mut archive).unwrap();
+
+        assert_eq!(props.title, Some("Test Document".to_string()));
+        assert_eq!(props.subject, Some("Testing".to_string()));
+        assert_eq!(props.creator, Some("John Doe".to_string()));
+        assert_eq!(props.keywords, Some("test, metadata".to_string()));
+        assert_eq!(props.description, Some("A test document".to_string()));
+        assert_eq!(props.last_modified_by, Some("Jane Doe".to_string()));
+        assert_eq!(props.revision, Some("5".to_string()));
+        assert_eq!(props.created, Some("2024-01-01T10:00:00Z".to_string()));
+        assert_eq!(props.modified, Some("2024-01-02T15:30:00Z".to_string()));
+        assert_eq!(props.category, Some("Documents".to_string()));
+        assert_eq!(props.content_status, Some("Final".to_string()));
+        assert_eq!(props.language, Some("en-US".to_string()));
+    }
+
+    #[test]
+    fn test_extract_core_properties_minimal() {
+        let core_xml = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<cp:coreProperties xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
+                   xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:creator>Alice</dc:creator>
+</cp:coreProperties>"#;
+
+        let mut archive = create_test_zip_with_core_xml(core_xml);
+        let props = extract_core_properties(&mut archive).unwrap();
+
+        assert_eq!(props.creator, Some("Alice".to_string()));
+        assert_eq!(props.title, None);
+        assert_eq!(props.keywords, None);
+    }
+
+    #[test]
+    fn test_extract_core_properties_empty_elements() {
+        let core_xml = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<cp:coreProperties xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
+                   xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:title></dc:title>
+    <dc:creator>Bob</dc:creator>
+</cp:coreProperties>"#;
+
+        let mut archive = create_test_zip_with_core_xml(core_xml);
+        let props = extract_core_properties(&mut archive).unwrap();
+
+        assert_eq!(props.title, None);
+        assert_eq!(props.creator, Some("Bob".to_string()));
+    }
+
+    #[test]
+    fn test_extract_core_properties_missing_file() {
+        let buffer = Vec::new();
+        let cursor = Cursor::new(buffer);
+        let zip = zip::ZipWriter::new(cursor);
+        let cursor = zip.finish().unwrap();
+        let mut archive = ZipArchive::new(cursor).unwrap();
+
+        let props = extract_core_properties(&mut archive).unwrap();
+        assert_eq!(props, CoreProperties::default());
+    }
+
+    #[test]
+    fn test_extract_core_properties_malformed_xml() {
+        let core_xml = "not valid xml <";
+        let mut archive = create_test_zip_with_core_xml(core_xml);
+
+        let result = extract_core_properties(&mut archive);
+        assert!(result.is_err());
+    }
+}

data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs

@@ -0,0 +1,240 @@
+//! Custom properties extraction from docProps/custom.xml
+//!
+//! Extracts user-defined custom metadata from Office Open XML documents.
+
+use crate::error::{KreuzbergError, Result};
+use serde_json::Value;
+use std::collections::HashMap;
+use std::io::Read;
+use zip::ZipArchive;
+
+/// Custom properties from docProps/custom.xml
+///
+/// Maps property names to their values. Values are converted to JSON types
+/// based on the VT (Variant Type) specified in the XML.
+pub type CustomProperties = HashMap<String, Value>;
+
+/// Extract custom properties from an Office Open XML document
+///
+/// Parses `docProps/custom.xml` and extracts user-defined or application-defined
+/// custom metadata.
+///
+/// # Arguments
+///
+/// * `archive` - ZIP archive containing the Office document
+///
+/// # Returns
+///
+/// Returns a `HashMap` of property names to JSON values. Supported VT types:
+/// - `vt:lpwstr` / `vt:lpstr` → String
+/// - `vt:i4` → Number (integer)
+/// - `vt:r8` → Number (float)
+/// - `vt:bool` → Boolean
+/// - `vt:filetime` → String (ISO 8601 timestamp)
+///
+/// # Example
+///
+/// ```no_run
+/// use kreuzberg::extraction::office_metadata::extract_custom_properties;
+/// use std::fs::File;
+/// use zip::ZipArchive;
+///
+/// let file = File::open("document.docx")?;
+/// let mut archive = ZipArchive::new(file)?;
+/// let custom = extract_custom_properties(&mut archive)?;
+///
+/// for (name, value) in custom {
+///     println!("{}: {:?}", name, value);
+/// }
+/// # Ok::<(), Box<dyn std::error::Error>>(())
+/// ```
+pub fn extract_custom_properties<R: Read + std::io::Seek>(archive: &mut ZipArchive<R>) -> Result<CustomProperties> {
+    let mut xml_content = String::new();
+
+    match archive.by_name("docProps/custom.xml") {
+        Ok(mut file) => {
+            file.read_to_string(&mut xml_content)
+                .map_err(|e| KreuzbergError::parsing(format!("Failed to read custom.xml: {}", e)))?;
+        }
+        Err(_) => {
+            return Ok(HashMap::new());
+        }
+    }
+
+    let doc = roxmltree::Document::parse(&xml_content)
+        .map_err(|e| KreuzbergError::parsing(format!("Failed to parse custom.xml: {}", e)))?;
+
+    let root = doc.root_element();
+    let mut properties = HashMap::new();
+
+    for property_node in root.descendants().filter(|n| n.has_tag_name("property")) {
+        if let Some(name) = property_node.attribute("name")
+            && let Some(value) = extract_vt_value(property_node)
+        {
+            properties.insert(name.to_string(), value);
+        }
+    }
+
+    Ok(properties)
+}
+
+/// Extract value from a VT (Variant Type) element
+///
+/// Handles various VT types and converts them to appropriate JSON values.
+fn extract_vt_value(node: roxmltree::Node) -> Option<Value> {
+    for child in node.children().filter(|n| n.is_element()) {
+        let tag = child.tag_name().name();
+
+        match tag {
+            "lpwstr" | "lpstr" => {
+                return child.text().map(|s| Value::String(s.to_string()));
+            }
+            "i4" => {
+                return child
+                    .text()
+                    .and_then(|s| s.trim().parse::<i64>().ok().map(|n| Value::Number(n.into())));
+            }
+            "r8" => {
+                return child.text().and_then(|s| {
+                    s.trim()
+                        .parse::<f64>()
+                        .ok()
+                        .and_then(|f| serde_json::Number::from_f64(f).map(Value::Number))
+                });
+            }
+            "bool" => {
+                return child.text().and_then(|s| match s.trim().to_lowercase().as_str() {
+                    "true" | "1" => Some(Value::Bool(true)),
+                    "false" | "0" => Some(Value::Bool(false)),
+                    _ => None,
+                });
+            }
+            "filetime" => {
+                return child.text().map(|s| Value::String(s.to_string()));
+            }
+            _ => {
+                continue;
+            }
+        }
+    }
+
+    None
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::io::{Cursor, Write};
+
+    fn create_test_zip_with_custom_xml(custom_xml: &str) -> ZipArchive<Cursor<Vec<u8>>> {
+        let buffer = Vec::new();
+        let cursor = Cursor::new(buffer);
+        let mut zip = zip::ZipWriter::new(cursor);
+
+        let options = zip::write::FileOptions::<()>::default().compression_method(zip::CompressionMethod::Stored);
+
+        zip.start_file("docProps/custom.xml", options).unwrap();
+        zip.write_all(custom_xml.as_bytes()).unwrap();
+
+        let cursor = zip.finish().unwrap();
+        ZipArchive::new(cursor).unwrap()
+    }
+
+    #[test]
+    fn test_extract_custom_properties_string() {
+        let custom_xml = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Properties xmlns="http://schemas.openxmlformats.org/officeDocument/2006/custom-properties"
+            xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+    <property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="2" name="ProjectName">
+        <vt:lpwstr>Alpha Project</vt:lpwstr>
+    </property>
+</Properties>"#;
+
+        let mut archive = create_test_zip_with_custom_xml(custom_xml);
+        let props = extract_custom_properties(&mut archive).unwrap();
+
+        assert_eq!(
+            props.get("ProjectName"),
+            Some(&Value::String("Alpha Project".to_string()))
+        );
+    }
+
+    #[test]
+    fn test_extract_custom_properties_multiple_types() {
+        let custom_xml = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Properties xmlns="http://schemas.openxmlformats.org/officeDocument/2006/custom-properties"
+            xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+    <property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="2" name="StringProp">
+        <vt:lpwstr>Test String</vt:lpwstr>
+    </property>
+    <property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="3" name="IntProp">
+        <vt:i4>42</vt:i4>
+    </property>
+    <property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="4" name="BoolProp">
+        <vt:bool>true</vt:bool>
+    </property>
+    <property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="5" name="FloatProp">
+        <vt:r8>3.14159</vt:r8>
+    </property>
+</Properties>"#;
+
+        let mut archive = create_test_zip_with_custom_xml(custom_xml);
+        let props = extract_custom_properties(&mut archive).unwrap();
+
+        assert_eq!(props.get("StringProp"), Some(&Value::String("Test String".to_string())));
+        assert_eq!(props.get("IntProp"), Some(&Value::Number(42.into())));
+        assert_eq!(props.get("BoolProp"), Some(&Value::Bool(true)));
+        assert!(matches!(props.get("FloatProp"), Some(Value::Number(_))));
+    }
+
+    #[test]
+    fn test_extract_custom_properties_missing_file() {
+        let buffer = Vec::new();
+        let cursor = Cursor::new(buffer);
+        let zip = zip::ZipWriter::new(cursor);
+        let cursor = zip.finish().unwrap();
+        let mut archive = ZipArchive::new(cursor).unwrap();
+
+        let props = extract_custom_properties(&mut archive).unwrap();
+        assert_eq!(props, HashMap::new());
+    }
+
+    #[test]
+    fn test_extract_vt_value_lpstr() {
+        let xml = r#"<property xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+            <vt:lpstr>Test</vt:lpstr>
+        </property>"#;
+
+        let doc = roxmltree::Document::parse(xml).unwrap();
+        let value = extract_vt_value(doc.root_element()).unwrap();
+        assert_eq!(value, Value::String("Test".to_string()));
+    }
+
+    #[test]
+    fn test_extract_vt_value_bool_variants() {
+        let xml_true1 = r#"<property xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+            <vt:bool>true</vt:bool>
+        </property>"#;
+        let xml_true2 = r#"<property xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+            <vt:bool>1</vt:bool>
+        </property>"#;
+        let xml_false1 = r#"<property xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+            <vt:bool>false</vt:bool>
+        </property>"#;
+        let xml_false2 = r#"<property xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+            <vt:bool>0</vt:bool>
+        </property>"#;
+
+        let doc1 = roxmltree::Document::parse(xml_true1).unwrap();
+        assert_eq!(extract_vt_value(doc1.root_element()), Some(Value::Bool(true)));
+
+        let doc2 = roxmltree::Document::parse(xml_true2).unwrap();
+        assert_eq!(extract_vt_value(doc2.root_element()), Some(Value::Bool(true)));
+
+        let doc3 = roxmltree::Document::parse(xml_false1).unwrap();
+        assert_eq!(extract_vt_value(doc3.root_element()), Some(Value::Bool(false)));
+
+        let doc4 = roxmltree::Document::parse(xml_false2).unwrap();
+        assert_eq!(extract_vt_value(doc4.root_element()), Some(Value::Bool(false)));
+    }
+}

data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs

@@ -0,0 +1,130 @@
+//! Office Open XML metadata extraction
+//!
+//! This module provides functionality to extract comprehensive metadata from Office Open XML
+//! documents (DOCX, XLSX, PPTX) by parsing the `docProps/core.xml`, `docProps/app.xml`,
+//! and `docProps/custom.xml` files within the ZIP container.
+//!
+//! # Overview
+//!
+//! Office documents store metadata in three XML files:
+//! - `docProps/core.xml` - Dublin Core metadata (title, creator, dates, keywords, etc.)
+//! - `docProps/app.xml` - Application-specific properties (page count, word count, etc.)
+//! - `docProps/custom.xml` - Custom properties defined by users or applications
+//!
+//! # Example
+//!
+//! ```no_run
+//! use kreuzberg::extraction::office_metadata::{extract_core_properties, extract_docx_app_properties};
+//! use std::fs::File;
+//! use zip::ZipArchive;
+//!
+//! let file = File::open("document.docx")?;
+//! let mut archive = ZipArchive::new(file)?;
+//!
+//! // Extract core properties
+//! let core = extract_core_properties(&mut archive)?;
+//! println!("Title: {:?}", core.title);
+//! println!("Created: {:?}", core.created);
+//!
+//! // Extract DOCX app properties
+//! let app = extract_docx_app_properties(&mut archive)?;
+//! println!("Word count: {:?}", app.words);
+//! # Ok::<(), Box<dyn std::error::Error>>(())
+//! ```
+
+pub mod app_properties;
+pub mod core_properties;
+pub mod custom_properties;
+pub mod odt_properties;
+
+pub use app_properties::{
+    DocxAppProperties, PptxAppProperties, XlsxAppProperties, extract_docx_app_properties, extract_pptx_app_properties,
+    extract_xlsx_app_properties,
+};
+pub use core_properties::{CoreProperties, extract_core_properties};
+pub use custom_properties::{CustomProperties, extract_custom_properties};
+pub use odt_properties::{OdtProperties, extract_odt_properties};
+
+use roxmltree::Node;
+
+/// Parse text content from an XML element by tag name
+///
+/// Returns the text content if the element exists and has non-empty text.
+pub(crate) fn parse_xml_text(node: Node, name: &str) -> Option<String> {
+    node.descendants()
+        .find(|n| n.has_tag_name(name))
+        .and_then(|n| n.text())
+        .map(|s| s.trim())
+        .filter(|s| !s.is_empty())
+        .map(String::from)
+}
+
+/// Parse integer content from an XML element by tag name
+///
+/// Returns the parsed integer if the element exists and contains valid integer text.
+pub(crate) fn parse_xml_int(node: Node, name: &str) -> Option<i32> {
+    node.descendants()
+        .find(|n| n.has_tag_name(name))
+        .and_then(|n| n.text())
+        .and_then(|s| s.trim().parse::<i32>().ok())
+}
+
+/// Parse boolean content from an XML element by tag name
+///
+/// Handles "true"/"false" string values and converts to boolean.
+pub(crate) fn parse_xml_bool(node: Node, name: &str) -> Option<bool> {
+    node.descendants()
+        .find(|n| n.has_tag_name(name))
+        .and_then(|n| n.text())
+        .map(|s| s.trim())
+        .and_then(|s| match s.to_lowercase().as_str() {
+            "true" => Some(true),
+            "false" => Some(false),
+            _ => None,
+        })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_parse_xml_text() {
+        let xml = r#"<root><title>Test Document</title></root>"#;
+        let doc = roxmltree::Document::parse(xml).unwrap();
+        let root = doc.root_element();
+
+        assert_eq!(parse_xml_text(root, "title"), Some("Test Document".to_string()));
+        assert_eq!(parse_xml_text(root, "missing"), None);
+    }
+
+    #[test]
+    fn test_parse_xml_text_empty() {
+        let xml = r#"<root><title></title></root>"#;
+        let doc = roxmltree::Document::parse(xml).unwrap();
+        let root = doc.root_element();
+
+        assert_eq!(parse_xml_text(root, "title"), None);
+    }
+
+    #[test]
+    fn test_parse_xml_int() {
+        let xml = r#"<root><count>42</count></root>"#;
+        let doc = roxmltree::Document::parse(xml).unwrap();
+        let root = doc.root_element();
+
+        assert_eq!(parse_xml_int(root, "count"), Some(42));
+        assert_eq!(parse_xml_int(root, "missing"), None);
+    }
+
+    #[test]
+    fn test_parse_xml_bool() {
+        let xml = r#"<root><flag>true</flag><other>false</other></root>"#;
+        let doc = roxmltree::Document::parse(xml).unwrap();
+        let root = doc.root_element();
+
+        assert_eq!(parse_xml_bool(root, "flag"), Some(true));
+        assert_eq!(parse_xml_bool(root, "other"), Some(false));
+        assert_eq!(parse_xml_bool(root, "missing"), None);
+    }
+}