From f8e9938f4ac96ed64a05e24404f6fe86da4451dc Mon Sep 17 00:00:00 2001 From: Mihaela Mihaljevic Date: Wed, 10 Jun 2026 02:24:30 +0200 Subject: [PATCH] test(conformance): add a C14N exclusive/2.0 modes corpus Grow the Tier-2 conformance corpus with 4 Canonical XML mode cases: exclusive drops an unused namespace and renders one at its point of use; Canonical XML 2.0 drops whitespace-only text nodes and trims surrounding whitespace. Its own suite (ConformanceCanonicalModesTests). Part of #105 (Tier 2) --- CHANGELOG.md | 2 +- README.md | 2 +- Tests/ConformanceCanonicalModesTests.swift | 35 ++++++++++++++++++++++ 3 files changed, 37 insertions(+), 2 deletions(-) create mode 100644 Tests/ConformanceCanonicalModesTests.swift diff --git a/CHANGELOG.md b/CHANGELOG.md index 1db895d..8b24ca2 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -14,7 +14,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Added -- Conformance corpus harness (#105, Tier 2): the start of conformance-suite checking, expressed through the validation framework (the OpenAPIKit idiom). A `PureXML.Validation.ConformanceCase` is a `Validatable` named expectation (actual vs spec-authoritative expected output), and `Conformance.matchesExpected` is a `Validation` rule that emits one located `ValidationError` per diverging case, so a whole suite reports every failure at once with the case name as its coding path. Seeded with a Canonical XML 1.0 corpus (attribute ordering, empty-element expansion, comment removal, CDATA-to-escaped-text, processing instructions, namespace rendering) an XPath 1.0 core-function corpus, and an XSD datatype/facet corpus (length, range, pattern, enumeration, lexical space), a RELAX NG pattern corpus (text, optional, repetition, choice, ordered group, attribute, interleave, empty), an XSLT 1.0 transformation corpus (value-of, for-each, if, choose, sort, variable, format-number, apply-templates, call-template), an HTML5 tree-construction corpus (void elements, implied tag closing, case normalization, the adoption agency, entities), and a Schematron corpus (assert, report, rule context). The HTML corpus surfaced its first divergence (the fragment parser does not reconstruct active formatting elements like the document parser, tracked as #109). Growing the corpora against the official W3C/OASIS suites is the ongoing Tier-2 work. +- Conformance corpus harness (#105, Tier 2): the start of conformance-suite checking, expressed through the validation framework (the OpenAPIKit idiom). A `PureXML.Validation.ConformanceCase` is a `Validatable` named expectation (actual vs spec-authoritative expected output), and `Conformance.matchesExpected` is a `Validation` rule that emits one located `ValidationError` per diverging case, so a whole suite reports every failure at once with the case name as its coding path. Seeded with a Canonical XML 1.0 corpus (attribute ordering, empty-element expansion, comment removal, CDATA-to-escaped-text, processing instructions, namespace rendering) an XPath 1.0 core-function corpus, and an XSD datatype/facet corpus (length, range, pattern, enumeration, lexical space), a RELAX NG pattern corpus (text, optional, repetition, choice, ordered group, attribute, interleave, empty), an XSLT 1.0 transformation corpus (value-of, for-each, if, choose, sort, variable, format-number, apply-templates, call-template), an HTML5 tree-construction corpus (void elements, implied tag closing, case normalization, the adoption agency, entities), a Schematron corpus (assert, report, rule context), and a C14N exclusive/2.0 corpus (unused-namespace dropping, render-at-use, whitespace trimming). The HTML corpus surfaced its first divergence (the fragment parser does not reconstruct active formatting elements like the document parser, tracked as #109). Growing the corpora against the official W3C/OASIS suites is the ongoing Tier-2 work. - EXSLT extension functions (#105, Tier 3): the `common`, `math`, and `sets` EXSLT modules, dispatched by resolving a function's prefix to its namespace (so any prefix bound to an EXSLT namespace works). `math:min`, `math:max`, `math:highest`, `math:lowest`, `math:abs`, `math:sqrt` (with the EXSLT NaN rule for non-numeric nodes); `set:distinct`, `set:difference`, `set:intersection`, `set:has-same-node`, `set:leading`, `set:trailing` (by node identity and document order); `exsl:object-type`. `math:power` and the other transcendentals are omitted because they need a C math library, which the pure-Swift, Foundation-free target excludes; `exsl:node-set` awaits result-tree-fragment support. - Canonical XML 1.1 (#105, Tier 3): a `Canonical.Options.canonical11` preset and a `mergeInheritedBase` option. When canonicalizing a document subset, the `xml:base` values of the apex's omitted ancestors are merged into the apex by RFC 3986 reference resolution (vs. 1.0's nearest-ancestor rule), the apex's own relative `xml:base` is resolved against that chain, and `xml:id` is no longer inherited; `xml:lang` and `xml:space` still inherit the nearest. A self-contained RFC 3986 resolver (scheme/authority/path parsing, path merging, dot-segment removal) backs the merge. - Single-byte legacy encodings (#97): the byte decoder gains a table-based single-byte path and the full set of single-byte legacy encodings, selected by the XML declaration's `encoding` name for both the whole-buffer and streaming decoders: the complete ISO-8859 family (parts 2 through 16), Windows-1250/1251/1253/1254/1255/1256/1257/1258, and KOI8-R/U. Most are vendored verbatim from the authoritative `unicode.org` mapping files; ISO-8859-5/9/15 are derived exactly; Windows-1254 composes from Windows-1252. Multi-byte CJK encodings (#99) are tracked separately. diff --git a/README.md b/README.md index 8587336..35626d5 100644 --- a/README.md +++ b/README.md @@ -99,7 +99,7 @@ flowchart TB 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 **817 tests in 126 suites** (`swift test`). +currently runs **818 tests in 127 suites** (`swift test`). ### Shipped (libxml2-aligned surface) diff --git a/Tests/ConformanceCanonicalModesTests.swift b/Tests/ConformanceCanonicalModesTests.swift new file mode 100644 index 0000000..1273c69 --- /dev/null +++ b/Tests/ConformanceCanonicalModesTests.swift @@ -0,0 +1,35 @@ +@testable import PureXML +import Testing + +/// Canonical XML exclusive and 2.0 mode conformance, driven through the +/// validation framework (its own suite to keep the main corpus under the cap). +@Suite("Conformance corpus: C14N exclusive and 2.0") +struct ConformanceCanonicalModesTests { + private struct ModeSpec { + let name: String + let input: String + let options: PureXML.Canonical.Options + let expected: String + } + + /// Exclusive C14N renders a namespace only where it is visibly used; Canonical + /// XML 2.0 trims and drops ignorable whitespace text. + private func corpus() throws -> [PureXML.Validation.ConformanceCase] { + let specs = [ + ModeSpec(name: "exclusive-drops-unused-ns", input: "", options: .exclusive, expected: ""), + ModeSpec(name: "exclusive-renders-at-use", input: "", options: .exclusive, expected: ""), + ModeSpec(name: "c2-drops-whitespace-nodes", input: " ", options: .canonical2, expected: ""), + ModeSpec(name: "c2-trims-text", input: " hi ", options: .canonical2, expected: "hi"), + ] + return try specs.map { spec in + let actual = try PureXML.Canonical.canonicalize(PureXML.parse(spec.input), options: spec.options) + return PureXML.Validation.ConformanceCase(name: spec.name, actual: actual, expected: spec.expected) + } + } + + @Test("The C14N exclusive/2.0 conformance corpus passes with no located failures") + func test_canonicalModesCorpusConforms() throws { + let failures = try PureXML.Validation.Conformance.failures(in: corpus()) + #expect(failures.isEmpty, "\(failures.map(\.reason))") + } +}