diff --git a/CHANGELOG.md b/CHANGELOG.md index c441f21..acd099f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Added +- XInclude range inclusion (#87), completing the XInclude audit. An `xi:include` whose `xpointer` selects a range (`xpointer(range(...))`, `range-to`, or `string-range`) now includes that range's content: when no node-selecting scheme matches, the processor falls back to the XPointer range model and substitutes each range's spanned nodes (or the matched text for a `string-range`). - XPointer `range()` model (#88), completing the XPath/XPointer audit. `PureXML.XPointer.evaluateRanges(_:over:)` (and `Pointer.evaluateRanges(over:)`) evaluate the range forms inside an `xpointer()`/`xpath1()` scheme: `range(expr)` (the covering range of each location), `start/range-to(end)` (one range spanning from the first location of `start` to the first of `end`, the sibling run when they share a parent), and `string-range(location, "search"[, offset[, length]])` (a character range per occurrence, with the XPointer offset/length adjustment). Each `Range` materializes to the whole `nodes` it spans and the `text` it covers, and `xmlns()` bindings apply to the range parts that follow, so this also unblocks XInclude range inclusion (#87). - C14N node-subset canonicalization and Canonical XML 2.0 parameters (#85), completing the canonicalization audit. `Canonicalizer.canonicalize(_ subtree: TreeNode)` canonicalizes a fragment in place: the apex element renders the namespace context in scope from its omitted ancestors and inherits their `xml:base`/`xml:lang`/`xml:space` when it does not set them, so a signed fragment is independent of where it sat. `canonicalize(_:including:)` canonicalizes a node-set selected by a `TreeNode` predicate (XPath/position-based selection): an excluded element's tags are omitted but its selected descendants are kept and re-declare their in-scope namespaces. `Options.prefixRewrite = .sequential` rewrites every prefix to a canonical `n0`/`n1`/... in document order (eliminating the default namespace and placing declarations at first use), and `Options.qnameAwareLabels` extends that rewrite into QName-valued attributes and elements, so documents differing only in prefix spelling canonicalize to identical bytes. - Serialization `textEscaping` round-trip option (#91), completing the serialization audit. `Options.textEscaping` defaults to `.standard` (escape only `&`, `<`, `>`); `.roundTrip` also escapes a carriage return as ` ` in text and CDATA-as-text output, so a literal `\r` survives the parser's end-of-line normalization and the document round-trips byte for byte. (The CDATA-section vs escaped-text toggle, `cdataAsText`, was already present.) diff --git a/README.md b/README.md index 4c82bef..ab0be66 100644 --- a/README.md +++ b/README.md @@ -77,21 +77,19 @@ flowchart TB classDef epic fill:#f2e5ff,stroke:#af52de,color:#111827 classDef todo fill:#f2f4f7,stroke:#8e8e93,color:#111827 Epic71["#71 Beyond-parity libxml2 audit"]:::epic - AuditDone["Closed in main: DTD #72 #73, XSD #75 #76 #77 #78, parsing #95 #96 #98 #100, regex #89, catalog #86, XSLT #81 #82, RELAX NG #79, Schematron #80, DOM #90, serialization #91, C14N #85, XPath/XPointer #88"]:::done + AuditDone["Closed in main: DTD #72 #73, XSD #75 #76 #77 #78, parsing #95 #96 #98 #100, regex #89, catalog #86, XSLT #81 #82, RELAX NG #79, Schematron #80, DOM #90, serialization #91, C14N #85, XPath/XPointer #88, XInclude #87"]:::done Epic74["#74 Parser-breadth sub-epic: standalone/decl #95, XML 1.1 #96, reader #98, recovery #100 done; encodings #97 #99 open"]:::epic - Partial["Partial in main: XInclude #87"]:::todo Open["Open: HTML5 #83 #84, encoding tables #97 #99, validator decomposition #101"]:::todo Epic71 --> AuditDone AuditDone --> Epic74 - Epic74 --> Partial - Partial --> Open + Epic74 --> Open ``` ## Status PureXML is a working, dependency-free XML library today: parse, emit, validate, query, and stream documents on macOS, Linux, Windows, and WASM. The test suite -currently runs **697 tests in 111 suites** (`swift test`). +currently runs **699 tests in 111 suites** (`swift test`). ### Shipped (libxml2-aligned surface) diff --git a/Sources/XInclude/XIncludeProcessor.swift b/Sources/XInclude/XIncludeProcessor.swift index 5a07b6d..65d6777 100644 --- a/Sources/XInclude/XIncludeProcessor.swift +++ b/Sources/XInclude/XIncludeProcessor.swift @@ -67,11 +67,13 @@ private struct XIncludeRun { } private func selectedNodes(from parsed: Node, xpointer: String?) -> [Node] { - if let xpointer { - let selections = (try? PureXML.XPointer.evaluate(xpointer, over: parsed)) ?? [] - return selections.map(Self.node) - } - return [documentElement(of: parsed) ?? parsed] + guard let xpointer else { return [documentElement(of: parsed) ?? parsed] } + let selections = (try? PureXML.XPointer.evaluate(xpointer, over: parsed)) ?? [] + if !selections.isEmpty { return selections.map(Self.node) } + // No node-selecting scheme matched: fall back to the XPointer range model + // (range()/range-to()/string-range()) and include each range's content. + let ranges = (try? PureXML.XPointer.evaluateRanges(xpointer, over: parsed)) ?? [] + return ranges.flatMap(\.nodes) } private func documentElement(of parsed: Node) -> Node? { diff --git a/Tests/XIncludeTests.swift b/Tests/XIncludeTests.swift index 732972a..26e7b80 100644 --- a/Tests/XIncludeTests.swift +++ b/Tests/XIncludeTests.swift @@ -48,6 +48,22 @@ struct XIncludeTests { #expect(result == "two") } + @Test("xi:include with an xpointer range() includes the covering range") + func test_includeRange() throws { + let xml = "" + + "" + let result = try process(xml) { _ in "onetwo" } + #expect(result == "two") + } + + @Test("xi:include with a string-range xpointer includes the matched text") + func test_includeStringRange() throws { + let xml = "" + + "" + let result = try process(xml) { _ in "onetwo" } + #expect(result == "wo") + } + @Test("href resolves against an xml:base on an ancestor") func test_xmlBase() throws { let xml = ""