💥 Namespaces and other niceties

.github/workflows/lint.yml

@@ -1,9 +1,6 @@
 on:
   push:
-    branches: [ master ]
   pull_request:
-    branches: [ master ]
-
 
 name: Lint
 

.github/workflows/rust.yml

@@ -2,21 +2,18 @@ name: Rust
 
 on:
   push:
-    branches: [ master ]
   pull_request:
-    branches: [ master ]
 
 env:
   CARGO_TERM_COLOR: always
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v2
-    - name: Build
-      run: cargo build --verbose
-    - name: Run tests
-      run: cargo test --verbose
+      - uses: actions/checkout@v2
+      - name: Build
+        run: cargo build --verbose
+      - name: Run tests
+        run: cargo test --verbose

.gitignore

@@ -1,2 +1,109 @@
-target
+# Created by https://www.toptal.com/developers/gitignore/api/git,rust,linux,macos,windows
+# Edit at https://www.toptal.com/developers/gitignore?templates=git,rust,linux,macos,windows
+
+### Git ###
+# Created by git for backups. To disable backups in Git:
+# $ git config --global mergetool.keepBackup false
+*.orig
+
+# Created by git when using merge tools for conflicts
+*.BACKUP.*
+*.BASE.*
+*.LOCAL.*
+*.REMOTE.*
+*_BACKUP_*.txt
+*_BASE_*.txt
+*_LOCAL_*.txt
+*_REMOTE_*.txt
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Rust ###
+# Generated by Cargo
+# will have compiled files and executables
+debug/
+target/
+
+# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
+# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
 Cargo.lock
+
+# These are backup files generated by rustfmt
+**/*.rs.bk
+
+# MSVC Windows builds of rustc generate these, which store debugging information
+*.pdb
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# End of https://www.toptal.com/developers/gitignore/api/git,rust,linux,macos,windows

Cargo.toml

@@ -1,11 +1,14 @@
 [package]
-authors = ["Ingvar Stepanyan <me@rreverser.com>"]
+authors = [
+    "Ingvar Stepanyan <me@rreverser.com>",
+    "William Bartlett <bartlettstarman@gmail.com>",
+]
 description = "xml-rs based deserializer for Serde (compatible with 1.0)"
 license = "MIT"
 name = "serde-xml-rs"
 repository = "https://github.com/RReverser/serde-xml-rs"
-version = "0.7.1"
-edition = "2018"
+version = "0.8.0"
+edition = "2021"
 
 [dependencies]
 log = "0.4"
@@ -15,7 +18,9 @@ thiserror = "1.0"
 
 [dev-dependencies]
 serde = { version = "1.0", features = ["derive"] }
-simple_logger = "2.1"
-docmatic = "0.1"
-rstest = "0.12"
+rstest = "0.25"
 indoc = "2.0.6"
+test-log = "0.2.17"
+serde_bytes = "0.11.17"
+serde-query = "0.2.0"
+chrono = { version = "0.4.40", default-features = false, features = ["serde"] }

MIGRATION.md

@@ -0,0 +1,14 @@
+# Migration across breaking changes
+
+## From 0.6.x or 0.7.x to 0.8.0
+
+Breaking changes:
+- Element content is now deserialized to a field named `#content` instead of `$value`.
+- Attributes must now be deserialized to fields named `@...`, mirroring what was introduced in the serializer.
+- Tuples become string only. This will be addressed in a future release.
+- Namespace support means that namespace prefixes are now added to element names and attributes. You might have to rename some of your struct fields and enum variants to match.
+
+Tips for migrating:
+- Replace `$value` with `#content`.
+- Rename any fields that must be deserialized from attributes to include the `@` prefix. For example, field `foo` becomes `@foo`.
+- If complex tuples are important, please file an issue with details on the XML format you want to (de)serialize and the Rust types you would prefer to (de)serialize to/from.

README.md

@@ -1,8 +1,8 @@
 # serde-xml-rs
 
-[![Build Status](https://travis-ci.org/RReverser/serde-xml-rs.svg?branch=master)](https://travis-ci.org/RReverser/serde-xml-rs)
+[![Rust](https://github.com/RReverser/serde-xml-rs/actions/workflows/rust.yml/badge.svg)](https://github.com/RReverser/serde-xml-rs/actions/workflows/rust.yml)
 
-`xml-rs` based deserializer for Serde (compatible with 1.0)
+`xml-rs` based serializer and deserializer for Serde (compatible with 1.0)
 
 ## Example usage
 
@@ -30,3 +30,11 @@ fn main() {
     assert_eq!(src, reserialized_item);
 }
 ```
+
+## Breaking changes in version 0.8.0
+
+Notably:
+- The `$value` name has been changed to `#content` (could become configurable in the future).
+- Fields that are deserialized from attributes must now have a name that starts with a `@`. This aligns with what was introduced in the serializer.
+
+See MIGRATION.md for more details, and tips on how to migrate.

src/config.rs

@@ -0,0 +1,146 @@
+use crate::{error::Result, Deserializer, Serializer};
+use serde::{Deserialize, Serialize};
+use std::{
+    collections::BTreeMap,
+    io::{Read, Write},
+};
+use xml::{
+    namespace::NS_NO_PREFIX, writer::events::StartElementBuilder, EmitterConfig, ParserConfig,
+};
+
+pub const TEXT: &str = "#text";
+pub const CONTENT: &str = "#content";
+
+#[derive(Clone, Debug)]
+pub struct SerdeXml {
+    pub(crate) emitter: EmitterConfig,
+    pub(crate) parser: ParserConfig,
+    pub(crate) namespaces: Namespaces,
+    pub(crate) overlapping_sequences: bool,
+}
+
+impl Default for SerdeXml {
+    fn default() -> Self {
+        Self {
+            emitter: Default::default(),
+            parser: ParserConfig::new()
+                .trim_whitespace(true)
+                .whitespace_to_characters(true)
+                .cdata_to_characters(true)
+                .ignore_comments(true)
+                .coalesce_characters(true),
+            namespaces: Default::default(),
+            overlapping_sequences: false,
+        }
+    }
+}
+
+impl SerdeXml {
+    pub fn new() -> Self {
+        Default::default()
+    }
+
+    pub fn emitter(mut self, emitter: EmitterConfig) -> Self {
+        self.emitter = emitter;
+        self
+    }
+
+    pub fn parser(mut self, parser: ParserConfig) -> Self {
+        self.parser = parser;
+        self
+    }
+
+    pub fn default_namespace<S: ToString>(mut self, name: S) -> Self {
+        self.namespaces.put_default(name);
+        self
+    }
+
+    pub fn namespace<S: ToString>(mut self, prefix: S, name: S) -> Self {
+        self.namespaces.put(prefix, name);
+        self
+    }
+
+    /// Configures whether the deserializer should search all sibling elements when building a
+    /// sequence. Not required if all XML elements for sequences are adjacent. Disabled by
+    /// default. Enabling this option may incur additional memory usage.
+    ///
+    /// ```rust
+    /// # use serde::Deserialize;
+    /// # use serde_xml_rs::from_reader;
+    /// #[derive(Debug, Deserialize, PartialEq)]
+    /// struct Foo {
+    ///     bar: Vec<usize>,
+    ///     baz: String,
+    /// }
+    /// # fn main() {
+    /// let s = r##"
+    ///     <foo>
+    ///         <bar>1</bar>
+    ///         <bar>2</bar>
+    ///         <baz>Hello, world</baz>
+    ///         <bar>3</bar>
+    ///         <bar>4</bar>
+    ///     </foo>
+    /// "##;
+    /// let foo: Foo = serde_xml_rs::SerdeXml::new().overlapping_sequences(true).from_str(s).unwrap();
+    /// assert_eq!(foo, Foo { bar: vec![1, 2, 3, 4], baz: "Hello, world".to_string()});
+    /// # }
+    /// ```
+    pub fn overlapping_sequences(mut self, b: bool) -> Self {
+        self.overlapping_sequences = b;
+        self
+    }
+
+    pub fn from_str<'de, T: Deserialize<'de>>(self, s: &str) -> Result<T> {
+        self.from_reader(s.as_bytes())
+    }
+
+    pub fn from_reader<'de, T: Deserialize<'de>, R: Read>(self, reader: R) -> Result<T> {
+        T::deserialize(&mut Deserializer::from_config(self, reader))
+    }
+
+    pub fn to_string<S: Serialize>(self, value: &S) -> Result<String> {
+        let mut buffer = Vec::new();
+        self.to_writer(&mut buffer, value)?;
+        Ok(String::from_utf8(buffer)?)
+    }
+
+    pub fn to_writer<W, S>(self, writer: W, value: &S) -> Result<()>
+    where
+        W: Write,
+        S: Serialize,
+    {
+        let mut s = Serializer::from_config(self, writer);
+        value.serialize(&mut s)
+    }
+}
+
+#[derive(Clone, Debug, Default)]
+pub struct Namespaces {
+    mapping: BTreeMap<String, String>,
+}
+
+impl Namespaces {
+    pub fn put_default<S: ToString>(&mut self, name: S) {
+        self.mapping
+            .insert(NS_NO_PREFIX.to_string(), name.to_string());
+    }
+
+    pub fn put<S: ToString>(&mut self, prefix: S, name: S) {
+        self.mapping.insert(prefix.to_string(), name.to_string());
+    }
+
+    pub fn get<S: AsRef<str>>(&self, prefix: S) -> Option<&String> {
+        self.mapping.get(prefix.as_ref())
+    }
+
+    pub(crate) fn add_to_start_element<'a>(
+        &self,
+        mut start_element_builder: StartElementBuilder<'a>,
+    ) -> StartElementBuilder<'a> {
+        for (prefix, name) in &self.mapping {
+            start_element_builder = start_element_builder.ns(prefix, name);
+        }
+        start_element_builder
+    }
+}