added maven pom model, reorganized tests, added namespace prefix support (wip)

.idea/.gitignore

@@ -1,8 +0,0 @@
-# Default ignored files
-/shelf/
-/workspace.xml
-# Editor-based HTTP Client requests
-/httpRequests/
-# Datasource local storage ignored files
-/dataSources/
-/dataSources.local.xml

.idea/modules.xml

@@ -2,7 +2,7 @@
 <project version="4">
   <component name="ProjectModuleManager">
     <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/undeepend2.iml" filepath="$PROJECT_DIR$/.idea/undeepend2.iml" />
+      <module fileurl="file://$PROJECT_DIR$/.idea/undeepend.iml" filepath="$PROJECT_DIR$/.idea/undeepend.iml" />
     </modules>
   </component>
 </project>

.idea/undeepend2.iml

@@ -1,11 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<module type="EMPTY_MODULE" version="4">
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$">
-      <sourceFolder url="file://$MODULE_DIR$/src" isTestSource="false" />
-      <excludeFolder url="file://$MODULE_DIR$/target" />
-    </content>
-    <orderEntry type="inheritedJdk" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-</module>

Cargo.lock

@@ -238,12 +238,13 @@ dependencies = [
 ]
 
 [[package]]
-name = "undeepend2"
+name = "undeepend"
 version = "0.1.0"
 dependencies = [
  "anyhow",
  "env_logger",
  "log",
+ "regex",
 ]
 
 [[package]]

Cargo.toml

@@ -1,9 +1,10 @@
 [package]
-name = "undeepend2"
+name = "undeepend"
 version = "0.1.0"
 edition = "2024"
 
 [dependencies]
 anyhow = "1.0"
 log = "0.4"
-env_logger = "0.11"
+env_logger = "0.11"
+regex="1.11"

src/lib.rs

@@ -1 +1,2 @@
-mod maven;
+pub mod maven;
+pub mod xml;

src/main.rs

@@ -1,3 +1,4 @@
 fn main() {
-    println!("Hello, world!");
+    let message = &"xmlns:Hello, world!"[6..];
+    println!("{}",message);
 }

src/maven/metadata.rs

@@ -0,0 +1,72 @@
+use crate::maven::pom::{ArtifactId, GroupId, Version};
+
+/// The Maven variant to parse poms
+/// These structs is directly modelled after the XML because that is what strong-xml plugin requires
+#[derive(PartialEq, Debug)]
+pub struct Metadata {
+    pub group_id: GroupId,
+    pub artifact_id: ArtifactId,
+    pub version: Version,
+    pub versioning: Versioning,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Versioning {
+    pub snapshot: Snapshot,
+    pub last_updated: LastUpdated,
+    pub snapshot_versions: SnapshotVersions,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Snapshot {
+    pub timestamp: Timestamp,
+    pub build_number: BuildNumber,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct SnapshotVersions {
+    pub snapshot_versions: Vec<SnapshotVersion>,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct SnapshotVersion {
+    pub classifier: Option<Classifier>,
+    pub extension: Extension,
+    pub value: Value,
+    pub updated: Updated,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Timestamp {
+    pub value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct BuildNumber {
+    pub value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct LastUpdated {
+    pub value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Updated {
+    pub value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Extension {
+    pub value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Classifier {
+    pub value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Value {
+    pub value: String,
+}

src/maven/mod.rs

@@ -1 +1,4 @@
-mod xml;
+pub mod metadata;
+pub mod pom;
+pub mod pom_view;
+mod pom_reader;

src/maven/pom.rs

@@ -0,0 +1,132 @@
+/// The Maven variant to parse poms
+/// These structs is directly modelled after the XML because that is what strong-xml plugin requires
+#[derive(PartialEq, Debug)]
+pub struct Pom {
+    pub(crate) model_version: ModelVersion,
+    pub(crate) parent: Option<Parent>,
+    pub(crate) group_id: Option<GroupId>,
+    pub(crate) artifact_id: ArtifactId,
+    pub(crate) version: Option<Version>,
+    pub(crate) name: Name,
+    pub(crate) packaging: Option<Packaging>,
+    pub(crate) url: Option<Url>,
+    pub(crate) description: Description,
+    pub(crate) licences: Option<Licenses>,
+    pub(crate) scm: Option<Scm>,
+    pub(crate) developers: Option<Developers>,
+    pub(crate) dependencies: Option<Dependencies>,
+    pub(crate) dependency_management: Option<DependencyManagement>,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct ModelVersion {
+    pub value: String,
+}
+
+#[derive(PartialEq, Debug, Clone)]
+pub struct GroupId {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug, Clone)]
+pub struct ArtifactId {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug, Clone)]
+pub struct Version {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Name {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Id {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Packaging {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Url {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Description {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Licenses {
+    pub(crate) licenses: Vec<License>,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Distribution {
+    pub(crate) value: String,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct License {
+    pub(crate) name: Name,
+    pub(crate) url: Url,
+    pub(crate) distribution: Option<Distribution>,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Parent {
+    pub(crate) group_id: GroupId,
+    pub(crate) artifact_id: ArtifactId,
+    pub(crate) version: Version,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Scm {
+    pub(crate) url: Url,
+}
+
+#[derive(PartialEq, Debug)]
+pub struct Developers {
+    pub(crate) developers: Vec<Developer>,
+}
+
+#[derive(PartialEq, Debug)]
+struct Developer {
+    pub(crate) id: Option<Id>,
+    pub(crate) name: Name,
+}
+
+#[derive(PartialEq, Debug, Clone)]
+pub struct Dependencies {
+    pub(crate) value: Vec<Dependency>,
+}
+
+#[derive(PartialEq, Debug, Clone)]
+pub struct DependencyManagement {
+    pub(crate) value: Dependencies,
+}
+
+#[derive(PartialEq, Debug, Clone)]
+pub struct Dependency {
+    pub(crate) group_id: GroupId,
+    pub(crate) artifact_id: ArtifactId,
+    pub(crate) version: Option<Version>,
+}
+
+#[cfg(test)]
+mod test {
+
+    use crate::maven::pom::Pom;
+
+    #[test]
+    fn parse_should_not_fail() {
+
+    }
+}

src/maven/pom_reader.rs

@@ -0,0 +1,44 @@
+use crate::maven::pom::Pom;
+use crate::xml::{Attribute, SaxHandler};
+
+fn read(xml: &str){
+
+}
+
+struct PomReader{
+
+}
+
+impl SaxHandler for PomReader{
+    fn start_document(&mut self) {
+        todo!()
+    }
+
+    fn end_document(&mut self) {
+        todo!()
+    }
+
+    fn start_prefix_mapping(&mut self, prefix: &str, uri: &str) {
+        todo!()
+    }
+
+    fn end_prefix_mapping(&mut self, prefix: &str, uri: &str) {
+        todo!()
+    }
+
+    fn start_element(&mut self, uri: Option<String>, local_name: &str, qualified_name: &str, attributes: Vec<Attribute>) {
+        todo!()
+    }
+
+    fn end_element(&mut self, uri: Option<String>, local_name: &str, qualified_name: &str) {
+        todo!()
+    }
+
+    fn characters(&mut self, chars: &[char]) {
+        todo!()
+    }
+
+    fn error(&mut self, error: &str) {
+        todo!()
+    }
+}

src/maven/pom_view.rs

@@ -0,0 +1,30 @@
+use regex::Regex;
+
+use crate::maven::pom::{Dependency, Parent, Pom};
+
+/// offers a (non-mutable) view on the pom-as-xml-representation
+/// the main use of this is that it resolves the parent information when needed
+///
+
+#[derive(Debug)]
+pub struct Artifact {
+    pub group: String,
+    pub name: String,
+    pub version: String,
+    pub path: String,
+}
+
+impl Artifact {
+    pub fn new(group: &str, name: &str, version: &str) -> Self {
+        Self {
+            group: group.into(),
+            name: name.into(),
+            version: version.into(),
+            path: format!("{}/{}/{}", group.replace(".", "/"), name, version),
+        }
+    }
+
+    pub fn is_snapshot(&self) -> bool {
+        self.version.ends_with("-SNAPSHOT")
+    }
+}

src/maven/xml/sax_parser_test.rs

@@ -1,192 +0,0 @@
-use crate::maven::xml::{Attribute, SaxHandler, SaxError};
-
-#[cfg(test)]
-mod tests {
-    use crate::maven::xml::sax_parser::parse_string;
-    use crate::maven::xml::sax_parser_test::TestHandler;
-    use crate::maven::xml::SaxError;
-
-    #[test]
-    fn test_xml_header() {
-        let test_xml = include_str!("test/header.xml");
-        let mut testhandler = TestHandler::new();
-        parse_string(test_xml.to_string(), Box::new(&mut testhandler))
-            .expect("Failed to parse test xml");
-        println!("{:?}", testhandler);
-        assert_eq!(testhandler.start_document_called, 1);
-        assert_eq!(testhandler.end_document_called, 1);
-    }
-
-    #[test]
-    fn test_single_element_short() {
-        let test_xml = include_str!("test/header.xml");
-        let mut testhandler = TestHandler::new();
-        parse_string(test_xml.to_string(), Box::new(&mut testhandler))
-            .expect("Failed to parse test xml");
-        assert_eq!(testhandler.start_document_called, 1);
-        assert_eq!(testhandler.start_element_called, 1);
-        assert!(!testhandler.elements.is_empty());
-        assert_eq!(testhandler.elements[0], "<xml>");
-        assert_eq!(testhandler.end_document_called, 1);
-    }
-
-    #[test]
-    fn test_single_element() {
-        let test_xml = include_str!("test/element.xml");
-        let mut testhandler = TestHandler::new();
-        parse_string(test_xml.to_string(), Box::new(&mut testhandler))
-            .expect("Failed to parse test xml");
-        assert_eq!(testhandler.start_document_called, 1);
-        assert_eq!(testhandler.start_element_called, 1);
-        assert!(!testhandler.elements.is_empty());
-        assert_eq!(testhandler.elements[0], "<element>");
-        assert_eq!(testhandler.end_document_called, 1);
-    }
-
-    #[test]
-    fn test_single_element_single_attribute() {
-        let test_xml = include_str!("test/element_with_attribute.xml");
-        let mut testhandler = TestHandler::new();
-        parse_string(test_xml.to_string(), Box::new(&mut testhandler))
-            .expect("Failed to parse test xml");
-        assert_eq!(testhandler.start_document_called, 1);
-        assert_eq!(testhandler.start_element_called, 1);
-        assert!(!testhandler.elements.is_empty());
-        assert_eq!(testhandler.elements[0], r#"<element a="1">"#);
-        assert_eq!(testhandler.end_element_called, 1);
-        assert_eq!(testhandler.end_document_called, 1);
-    }
-
-    #[test]
-    fn test_ignore_comment() {
-        let test_xml = include_str!("test/comment.xml");
-        let mut testhandler = TestHandler::new();
-        parse_string(test_xml.to_string(), Box::new(&mut testhandler))
-            .expect("Failed to parse test xml");
-        assert_eq!(testhandler.start_document_called, 1);
-        assert_eq!(testhandler.start_element_called, 1);
-        assert!(!testhandler.elements.is_empty());
-        assert_eq!(
-            testhandler.elements[0],
-            r#"<http://example.com/books:bookstore xmlns="http://example.com/books">"#
-        );
-        assert_eq!(testhandler.end_element_called, 1);
-        assert_eq!(testhandler.end_document_called, 1);
-    }
-
-    #[test]
-    fn test_bad_comment() {
-        let test_xml = include_str!("test/illegal_dashes_comment.xml");
-        let mut testhandler = TestHandler::new();
-        match parse_string(test_xml.to_string(), Box::new(&mut testhandler)){
-            Err(e)=> assert_eq!(e, SaxError::BadCharacter),
-            Ok(_) => assert!(false),
-        }
-
-    }
-
-    #[test]
-    fn test_namespaces() {
-        let test_xml = include_str!("test/namespaces.xml");
-        let mut testhandler = TestHandler::new();
-        parse_string(test_xml.to_string(), Box::new(&mut testhandler))
-            .expect("Failed to parse test xml");
-        assert_eq!(testhandler.start_document_called, 1);
-        assert_eq!(testhandler.start_element_called, 4);
-        assert!(!testhandler.elements.is_empty());
-        assert_eq!(
-            testhandler.elements[0],
-            r#"<bookstore>"#
-        );
-        assert_eq!(
-            testhandler.elements[1],
-            r#"<http://example.com/books:book xmlns="http://example.com/books" id="1" category="fiction">"#
-        );
-        assert_eq!(
-            testhandler.elements[2],
-            r#"<http://example.com/books:page>"#
-        );
-        assert_eq!(
-            testhandler.elements[3],
-            r#"<publisher>"#
-        );
-        assert_eq!(testhandler.end_element_called, 4);
-        assert_eq!(testhandler.end_document_called, 1);
-    }
-}
-
-#[derive(Debug)]
-struct TestHandler {
-    start_document_called: usize,
-    end_document_called: usize,
-    start_element_called: usize,
-    end_element_called: usize,
-    elements: Vec<String>,
-}
-
-impl TestHandler {
-    pub fn new() -> Self {
-        Self {
-            start_document_called: 0,
-            end_document_called: 0,
-            start_element_called: 0,
-            end_element_called: 0,
-            elements: vec![],
-        }
-    }
-}
-
-impl SaxHandler for TestHandler {
-    fn start_document(&mut self) {
-        self.start_document_called += 1;
-    }
-
-    fn end_document(&mut self) {
-        self.end_document_called += 1;
-    }
-
-    fn start_prefix_mapping(&mut self, _prefix: &str, _uri: &str) {
-        todo!()
-    }
-
-    fn end_prefix_mapping(&mut self, _prefix: &str, _uri: &str) {
-        todo!()
-    }
-
-    fn start_element(
-        &mut self,
-        uri: Option<String>,
-        local_name: &str,
-        _qualified_name: &str,
-        attributes: Vec<Attribute>,
-    ) {
-        self.start_element_called += 1;
-        let atts = attributes
-            .iter()
-            .map(|att| format!(r#"{}="{}""#, att.name, att.value))
-            .collect::<Vec<String>>()
-            .join(" ");
-
-        let uri = if let Some(uri) = uri {
-            format!("{}:", uri)
-        } else {
-            "".to_string()
-        };
-
-        let divider = if atts.is_empty() { "" } else { " " };
-        self.elements
-            .push(format!("<{}{}{}{}>", uri, local_name, divider, atts));
-    }
-
-    fn end_element(&mut self, _uri: Option<String>, _local_name: &str, _qualified_name: &str) {
-        self.end_element_called += 1;
-    }
-
-    fn characters(&mut self, _chars: &[char]) {
-        todo!()
-    }
-
-    fn error(&mut self, _error: &str) {
-        todo!()
-    }
-}

src/xml/debug.rs

@@ -1,5 +1,5 @@
 use log::debug;
-use crate::maven::xml::SaxHandler;
+use crate::xml::SaxHandler;
 
 pub struct DebugHandler {}
 
@@ -21,7 +21,7 @@ impl SaxHandler for DebugHandler {
         _uri: Option<String>,
         local_name: &str,
         _qualified_name: &str,
-        attributes: Vec<crate::maven::xml::Attribute>,
+        attributes: Vec<crate::xml::Attribute>,
     ) {
         debug!("start_element {}, {:?}", local_name, attributes);
     }

src/xml/mod.rs

@@ -1,12 +1,11 @@
-mod sax_parser;
+pub mod sax_parser;
-mod sax_parser_test;
 mod debug;
 
 #[derive(Debug)]
 pub struct Attribute {
-    name: String,
+    pub name: String,
-    namespace: Option<String>,
+    pub namespace: Option<String>,
-    value: String,
+    pub value: String,
 }
 
 pub trait SaxHandler {
@@ -33,6 +32,7 @@ pub enum SaxError {
     BadCharacter,
     UnexpectedEof,
     UnexpectedCharacter(String),
+    UndeclaredNamespacePrefix(String),
 }
 
 impl fmt::Display for SaxError {
@@ -41,6 +41,7 @@ impl fmt::Display for SaxError {
             SaxError::BadCharacter => write!(f, "Bad character"),
             SaxError::UnexpectedEof => write!(f, "Unexpected end of document"),
             SaxError::UnexpectedCharacter(c) => write!(f, "Unexpected character {}",c),
+            SaxError::UndeclaredNamespacePrefix(prefix) => write!(f, "Undeclared namespace prefix{}", prefix),
         }
     }
 }

src/xml/sax_parser.rs

@@ -1,17 +1,17 @@
-use crate::maven::xml::{Attribute, SaxError, SaxHandler};
+use crate::xml::{Attribute, SaxError, SaxHandler};
-use anyhow::anyhow;
+use std::collections::HashMap;
 
 pub fn parse_string(xml: String, handler: Box<&mut dyn SaxHandler>) -> Result<(), SaxError> {
-    let mut parser = SAXParser::new(xml, handler);
+    SAXParser::new(xml, handler).parse()
-    parser.parse()
 }
 
-struct SAXParser<'a> {
+pub struct SAXParser<'a> {
     xml: Vec<char>,
     handler: Box<&'a mut dyn SaxHandler>,
     position: usize,
     current: char,
     namespace_stack: Vec<(String, isize)>,
+    prefix_mapping: HashMap<String, String>,
 }
 
 impl<'a> SAXParser<'a> {
@@ -22,6 +22,7 @@ impl<'a> SAXParser<'a> {
             position: 0,
             current: '\0',
             namespace_stack: Vec::new(),
+            prefix_mapping: HashMap::new(),
         }
     }
 
@@ -36,7 +37,7 @@ impl<'a> SAXParser<'a> {
         self.parse_elements()
     }
 
-    fn parse_elements(&mut self) -> Result<(), SaxError>  {
+    fn parse_elements(&mut self) -> Result<(), SaxError> {
         while self.position < self.xml.len() {
             if self.current == '<' {
                 self.advance()?;
@@ -80,7 +81,8 @@ impl<'a> SAXParser<'a> {
     }
 
     fn parse_start_element(&mut self) -> Result<(), SaxError> {
-        let name = self.read_until(" \t\n/>")?;
+        let qname = self.read_until(" \t\n/>")?;
+
         let mut atts = vec![];
         let mut c = self.current;
 
@@ -90,21 +92,38 @@ impl<'a> SAXParser<'a> {
             c = self.advance()?;
         }
 
-        let namespace = if !self.namespace_stack.is_empty() {
+        let (namespace, lname) = if qname.contains(":") {
+            let tokens = qname.splitn(2, ":").collect::<Vec<&str>>();
+            let prefix = tokens[0].to_string();
+            let name = tokens[1].to_string();
+            let namespace = self.prefix_mapping.get(&prefix);
+            if let Some(namespace) = namespace {
+                (Some(namespace.to_string()), name)
+            } else {
+                return Err(SaxError::UndeclaredNamespacePrefix(prefix));
+            }
+        } else if !self.namespace_stack.is_empty() {
             let (name, count) = self.namespace_stack.pop().unwrap();
             self.namespace_stack.push((name.clone(), count + 1));
-            Some(name.clone())
+            (Some(name.clone()), qname)
         } else {
-            None
+            (None, qname)
+        };
+
+        let qualified_name = if let Some(namespace) = &namespace{
+            &format!("{}:{}", namespace.clone(), &lname)
+        } else {
+            &lname
         };
 
         self.handler
-            .start_element(namespace.clone(), name.as_str(), "", atts);
+            .start_element(namespace.clone(), lname.as_str(), qualified_name, atts);
         self.skip_whitespace()?;
+
         if self.current == '/' {
             self.advance()?;
             let namespace = self.pop_namespace();
-            self.handler.end_element(namespace, name.as_str(), "");
+            self.handler.end_element(namespace, lname.as_str(), qualified_name);
         }
         self.expect_char('>')?;
         self.skip_whitespace()?;
@@ -118,6 +137,11 @@ impl<'a> SAXParser<'a> {
         self.expect("\"", "Expected start of attribute value")?;
         let att_value = self.read_until("\"")?;
 
+        if att_name.starts_with("xmlns:") {
+            let prefix = att_name[6..].to_string();
+            self.prefix_mapping.insert(prefix, att_value.to_string());
+        }
+
         let namespace = if att_name == "xmlns" {
             self.namespace_stack.push((att_value.clone(), -1));
             Some(att_value.clone())
@@ -200,7 +224,7 @@ impl<'a> SAXParser<'a> {
     fn expect(&mut self, expected: &str, message: &str) -> Result<(), SaxError> {
         for c in expected.chars() {
             if !self.expect_char(c)? {
-                return Err(SaxError::UnexpectedCharacter(message.to_string()))
+                return Err(SaxError::UnexpectedCharacter(message.to_string()));
             }
         }
         Ok(())
@@ -216,4 +240,4 @@ impl<'a> SAXParser<'a> {
         }
         Ok(same)
     }
-}
+}

tests/mod.rs

@@ -0,0 +1 @@
+mod xml;

tests/pom/pom.xml

@@ -0,0 +1,40 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd ">
+    <modelVersion>4.0.0</modelVersion>
+    <groupId>org.mockito</groupId>
+    <artifactId>mockito-core</artifactId>
+    <version>1.9.5</version>
+    <name>Mockito</name>
+    <packaging>jar</packaging>
+    <url>http://www.mockito.org</url>
+    <description>Mock objects library for java</description>
+    <licenses>
+        <license>
+            <name>The MIT License</name>
+            <url>http://code.google.com/p/mockito/wiki/License</url>
+            <distribution>repo</distribution>
+        </license>
+    </licenses>
+    <scm>
+        <url>http://code.google.com/p/mockito/source/browse/</url>
+    </scm>
+    <developers>
+        <developer>
+            <id>szczepiq</id>
+            <name>Szczepan Faber</name>
+        </developer>
+    </developers>
+    <dependencies>
+        <dependency>
+            <groupId>org.hamcrest</groupId>
+            <artifactId>hamcrest-core</artifactId>
+            <version>1.1</version>
+        </dependency>
+        <dependency>
+            <groupId>org.objenesis</groupId>
+            <artifactId>objenesis</artifactId>
+            <version>1.0</version>
+        </dependency>
+    </dependencies>
+</project>

tests/xml/mod.rs

@@ -0,0 +1 @@
+mod sax_parser_test;

tests/xml/resources/namespaces-prefix.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- Test XML file for SAX parser -->
+<bookstore>
+    <book xmlns:books="http://example.com/books"
+          xmlns:covers="http://example.com/covers"
+          id="1" category="fiction">
+        <books:page/>
+        <covers:cover/>
+    </book>
+    <publisher/>
+</bookstore>

tests/xml/sax_parser_test.rs

@@ -0,0 +1,197 @@
+use undeepend::xml::sax_parser::parse_string;
+use undeepend::xml::{Attribute, SaxError, SaxHandler};
+
+#[test]
+fn test_xml_header() {
+    let test_xml = include_str!("resources/header.xml");
+    let mut testhandler = TestHandler::new();
+    parse_string(test_xml.to_string(), Box::new(&mut testhandler))
+        .expect("Failed to parse test xml");
+    println!("{:?}", testhandler);
+    assert_eq!(testhandler.start_document_called, 1);
+    assert_eq!(testhandler.end_document_called, 1);
+}
+
+#[test]
+fn test_single_element_short() {
+    let test_xml = include_str!("resources/header.xml");
+    let mut testhandler = TestHandler::new();
+    parse_string(test_xml.to_string(), Box::new(&mut testhandler))
+        .expect("Failed to parse test xml");
+    assert_eq!(testhandler.start_document_called, 1);
+    assert_eq!(testhandler.start_element_called, 1);
+    assert!(!testhandler.elements.is_empty());
+    assert_eq!(testhandler.elements[0], "<xml>");
+    assert_eq!(testhandler.end_document_called, 1);
+}
+
+#[test]
+fn test_single_element() {
+    let test_xml = include_str!("resources/element.xml");
+    let mut testhandler = TestHandler::new();
+    parse_string(test_xml.to_string(), Box::new(&mut testhandler))
+        .expect("Failed to parse test xml");
+    assert_eq!(testhandler.start_document_called, 1);
+    assert_eq!(testhandler.start_element_called, 1);
+    assert!(!testhandler.elements.is_empty());
+    assert_eq!(testhandler.elements[0], "<element>");
+    assert_eq!(testhandler.end_document_called, 1);
+}
+
+#[test]
+fn test_single_element_single_attribute() {
+    let test_xml = include_str!("resources/element_with_attribute.xml");
+    let mut testhandler = TestHandler::new();
+    parse_string(test_xml.to_string(), Box::new(&mut testhandler))
+        .expect("Failed to parse test xml");
+    assert_eq!(testhandler.start_document_called, 1);
+    assert_eq!(testhandler.start_element_called, 1);
+    assert!(!testhandler.elements.is_empty());
+    assert_eq!(testhandler.elements[0], r#"<element a="1">"#);
+    assert_eq!(testhandler.end_element_called, 1);
+    assert_eq!(testhandler.end_document_called, 1);
+}
+
+#[test]
+fn test_ignore_comment() {
+    let test_xml = include_str!("resources/comment.xml");
+    let mut testhandler = TestHandler::new();
+    parse_string(test_xml.to_string(), Box::new(&mut testhandler))
+        .expect("Failed to parse test xml");
+    assert_eq!(testhandler.start_document_called, 1);
+    assert_eq!(testhandler.start_element_called, 1);
+    assert!(!testhandler.elements.is_empty());
+    assert_eq!(
+        testhandler.elements[0],
+        r#"<http://example.com/books:bookstore xmlns="http://example.com/books">"#
+    );
+    assert_eq!(testhandler.end_element_called, 1);
+    assert_eq!(testhandler.end_document_called, 1);
+}
+
+#[test]
+fn test_bad_comment() {
+    let test_xml = include_str!("resources/illegal_dashes_comment.xml");
+    let mut testhandler = TestHandler::new();
+    match parse_string(test_xml.to_string(), Box::new(&mut testhandler)) {
+        Err(e) => assert_eq!(e, SaxError::BadCharacter),
+        Ok(_) => assert!(false),
+    }
+}
+
+#[test]
+fn test_namespaces() {
+    let test_xml = include_str!("resources/namespaces.xml");
+    let mut testhandler = TestHandler::new();
+    parse_string(test_xml.to_string(), Box::new(&mut testhandler))
+        .expect("Failed to parse test xml");
+    assert_eq!(testhandler.start_document_called, 1);
+    assert_eq!(testhandler.start_element_called, 4);
+    assert!(!testhandler.elements.is_empty());
+    assert_eq!(testhandler.elements[0], r#"<bookstore>"#);
+    assert_eq!(
+        testhandler.elements[1],
+        r#"<http://example.com/books:book xmlns="http://example.com/books" id="1" category="fiction">"#
+    );
+    assert_eq!(
+        testhandler.elements[2],
+        r#"<http://example.com/books:page>"#
+    );
+    assert_eq!(testhandler.elements[3], r#"<publisher>"#);
+    assert_eq!(testhandler.end_element_called, 4);
+    assert_eq!(testhandler.end_document_called, 1);
+}
+
+#[test]
+fn test_namespace_prefixes() {
+    let test_xml = include_str!("resources/namespaces-prefix.xml");
+    let mut testhandler = TestHandler::new();
+    parse_string(test_xml.to_string(), Box::new(&mut testhandler))
+        .expect("Failed to parse test xml");
+    assert_eq!(testhandler.start_document_called, 1);
+    assert_eq!(testhandler.start_element_called, 5);
+    assert!(!testhandler.elements.is_empty());
+    assert_eq!(testhandler.elements[0], r#"<bookstore>"#);
+    assert_eq!(
+        testhandler.elements[1],
+        r#"<book xmlns:books="http://example.com/books" xmlns:covers="http://example.com/covers" id="1" category="fiction">"#
+    );
+    assert_eq!(
+        testhandler.elements[2],
+        r#"<http://example.com/books:page>"#
+    );
+    assert_eq!(testhandler.elements[3], r#"<http://example.com/covers:cover>"#);
+    assert_eq!(testhandler.elements[4], r#"<publisher>"#);
+    assert_eq!(testhandler.end_element_called, 5);
+    assert_eq!(testhandler.end_document_called, 1);
+}
+
+#[derive(Debug)]
+struct TestHandler {
+    start_document_called: usize,
+    end_document_called: usize,
+    start_element_called: usize,
+    end_element_called: usize,
+    elements: Vec<String>,
+}
+
+impl TestHandler {
+    pub fn new() -> Self {
+        Self {
+            start_document_called: 0,
+            end_document_called: 0,
+            start_element_called: 0,
+            end_element_called: 0,
+            elements: vec![],
+        }
+    }
+}
+
+impl SaxHandler for TestHandler {
+    fn start_document(&mut self) {
+        self.start_document_called += 1;
+    }
+
+    fn end_document(&mut self) {
+        self.end_document_called += 1;
+    }
+
+    fn start_prefix_mapping(&mut self, _prefix: &str, _uri: &str) {
+        todo!()
+    }
+
+    fn end_prefix_mapping(&mut self, _prefix: &str, _uri: &str) {
+        todo!()
+    }
+
+    fn start_element(
+        &mut self,
+        uri: Option<String>,
+        _local_name: &str,
+        qualified_name: &str,
+        attributes: Vec<Attribute>,
+    ) {
+        self.start_element_called += 1;
+        let atts = attributes
+            .iter()
+            .map(|att| format!(r#"{}="{}""#, att.name, att.value))
+            .collect::<Vec<String>>()
+            .join(" ");
+
+        let divider = if atts.is_empty() { "" } else { " " };
+        self.elements
+            .push(format!("<{}{}{}>", qualified_name, divider, atts));
+    }
+
+    fn end_element(&mut self, _uri: Option<String>, _local_name: &str, _qualified_name: &str) {
+        self.end_element_called += 1;
+    }
+
+    fn characters(&mut self, _chars: &[char]) {
+        todo!()
+    }
+
+    fn error(&mut self, _error: &str) {
+        todo!()
+    }
+}