Add Unicode support for XML doc comment generation#948
Merged
Conversation
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
christianhelle
added
enhancement
Contributor
📝 WalkthroughWalkthroughThis PR decodes JSON-style escapes in NSwag-sourced response descriptions before XML-escaping, preventing \uXXXX sequences in generated XML doc comments. It adds DecodeJsonEscapedText() and SanitizeResponseDescription(), updates XmlDocumentationGenerator usage, and adds unit/integration tests plus documentation and orchestration notes. Changes
Sequence Diagram(s)(omitted) Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
There was a problem hiding this comment.
Pull request overview
Fixes #944 by ensuring Unicode response descriptions are rendered as readable characters (not \uXXXX) in generated XML documentation, while keeping intentional XML doc markup intact.
Changes:
- Decode JSON-style escape sequences (e.g.,
\uXXXX,\",\n) for OpenAPI-sourced response descriptions before XML-escaping reserved characters. - Apply sanitization only to user-sourced response text (e.g.,
method.ResultDescription,response.ExceptionDescription), preserving hardcoded XML doc fragments. - Add unit + integration regression tests to ensure Unicode remains readable and generated code compiles.
Reviewed changes
Copilot reviewed 14 out of 14 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| src/Refitter.Core/XmlDocumentationGenerator.cs | Decodes JSON-style escapes in response descriptions and XML-escapes reserved characters at insertion points. |
| src/Refitter.Tests/XmlDocumentationGeneratorTests.cs | Adds unit coverage verifying readable Unicode in status-code comments and absence of raw \uXXXX. |
| src/Refitter.Tests/Examples/GenerateStatusCodeCommentsTests.cs | Adds end-to-end generation + compilation tests for Unicode status-code comments; refactors helper to accept a spec string. |
| .squad/skills/xml-doc-description-sanitization/SKILL.md | Documents the sanitization pattern and scope (user text only, preserve XML markup). |
| .squad/skills/tunit-test-filtering/SKILL.md | Documents the repo’s TUnit-focused test execution pattern using --treenode-filter. |
| .squad/orchestration-log/2026-03-06T16-29-27Z-keaton.md | Records review/validation notes for the #944 patch. |
| .squad/orchestration-log/2026-03-06T16-29-27Z-hockney.md | Records added regression test coverage for #944. |
| .squad/orchestration-log/2026-03-06T16-29-27Z-fenster.md | Records implementation notes for the #944 production fix. |
| .squad/identity/now.md | Updates current focus to #944 implementation/validation. |
| .squad/decisions.md | Captures the consolidated decision/approval for the #944 fix and testing approach. |
| .squad/agents/mcmanus/history.md | Logs gate validation results for #944 (build/test/format). |
| .squad/agents/keaton/history.md | Logs review findings/validation details for #944. |
| .squad/agents/hockney/history.md | Updates testing framework notes and records #944 test additions. |
| .squad/agents/fenster/history.md | Logs the #944 sanitization approach and implementation summary. |
You can also share your feedback on Copilot code review. Take the survey.
Comment on lines
+399
to
+413
| case 'b': | ||
| result.Append('\b'); | ||
| break; | ||
| case 'f': | ||
| result.Append('\f'); | ||
| break; | ||
| case 'n': | ||
| result.Append('\n'); | ||
| break; | ||
| case 'r': | ||
| result.Append('\r'); | ||
| break; | ||
| case 't': | ||
| result.Append('\t'); | ||
| break; |
There was a problem hiding this comment.
DecodeJsonEscapedText() decodes \b and \f into backspace/form-feed control characters. Those characters (and many \u0000–\u001F code points) are not valid in XML 1.0 and can produce invalid XML documentation (compiler warnings, or errors for consumers treating warnings as errors). Consider keeping \b/\f as literal sequences, or post-filtering the decoded text to only XML-valid characters (e.g., allow \t, \n, \r and strip/replace other control chars) before EscapeSymbols().
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #948 +/- ##
==========================================
- Coverage 94.47% 93.37% -1.11%
==========================================
Files 26 26
Lines 1593 1645 +52
==========================================
+ Hits 1505 1536 +31
- Misses 20 40 +20
- Partials 68 69 +1
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 5
🧹 Nitpick comments (1)
.squad/skills/tunit-test-filtering/SKILL.md (1)
15-15: Consider noting platform-specific path syntax.The executable paths use Windows-style backslashes, which are appropriate for the PowerShell examples but won't work on Linux/macOS. Consider adding a note about platform differences or providing a cross-platform example using forward slashes.
Also applies to: 22-27
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.squad/skills/tunit-test-filtering/SKILL.md at line 15, Update the Windows-style path examples (e.g. the line containing "Test app path: `src\Refitter.Tests\bin\Release\net10.0\Refitter.Tests.exe`" and the similar entries around the section for lines 22-27) to call out platform-specific syntax: add a brief note that backslashes are Windows/PowerShell only and provide a cross-platform alternative using forward slashes (e.g. src/Refitter.Tests/bin/Release/net10.0/Refitter.Tests.exe) and mention which shells/examples use which syntax (PowerShell vs bash/zsh) so readers on Linux/macOS know to use the forward-slash form.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.squad/agents/hockney/history.md:
- Line 13: The documentation example in the test pattern currently uses the
xUnit attribute `[Fact]` but the actual test suite `Refitter.Tests.Examples` and
its async test methods (e.g., those calling `GenerateCode()` and asserting via
`BuildHelper.BuildCSharp(code).Should().BeTrue()`) use TUnit's `[Test]`
attribute; update the example on line 13 to replace `[Fact]` with `[Test]` so
the documented pattern matches the real tests and new examples compile.
In @.squad/decisions.md:
- Around line 339-343: Update the Gates summary to match the validated total of
1,451 tests: locate the "#### Gates" section and replace the hardcoded
"1415/1415" string with "1451/1451" (or the exact count shown in the 2026-03-06
validation gate entry in the consolidated history file) so the gate summary and
the consolidated validation record remain consistent.
In `@src/Refitter.Core/XmlDocumentationGenerator.cs`:
- Line 1: The DecodeJsonEscapedText method currently only escapes reserved XML
symbols but must also remove/filter XML-invalid control characters emitted by
JSON escapes (e.g., \u0008, \u000C); update DecodeJsonEscapedText (and the
post-decode handling around lines 352-355) to post-process the decoded string
and strip any characters illegal in XML 1.0 (allow only 0x9, 0xA, 0xD and
characters >= 0x20, and valid Unicode scalar ranges), then return the cleaned
string so generated XML documentation can't contain invalid control characters.
In `@src/Refitter.Tests/Examples/GenerateStatusCodeCommentsTests.cs`:
- Around line 58-76: Add a Swagger 2.0 variant of the Unicode status-code
comment test to cover the older parser: create a new constant (e.g.,
Swagger20SpecWithUnicodeStatusCodeComments) mirroring
OpenApiSpecWithUnicodeStatusCodeComments but using Swagger 2.0 syntax, then
update or add a test in GenerateStatusCodeCommentsTests (the same test cases
referenced around OpenApiSpecWithUnicodeStatusCodeComments and the block at
125-141) to run the existing assertion/assertions against both the OpenAPI 3.0
constant and the new Swagger 2.0 constant so the unicode status-code comments
path is exercised for both parsers.
In `@src/Refitter.Tests/XmlDocumentationGeneratorTests.cs`:
- Around line 224-244: The test currently only verifies sanitization of
response.ExceptionDescription; add coverage for the method's ResultDescription
(the code path in XmlDocumentationGenerator.AppendMethodDocumentation that
sanitizes method.ResultDescription) by setting method.ResultDescription to a
Unicode string (e.g., "Ошибка ответа") in the CreateOperationModel call or by
patching the operation model, call AppendMethodDocumentation as before, and
assert the resulting docs contain the readable Unicode inside the <returns>
block (e.g., contain "<description>Ошибка ответа</description>") and do NOT
contain escaped Unicode sequences like "\u041e\u0448"; reference
AppendMethodDocumentation and the method.ResultDescription property when
locating where to add the extra setup and assertions.
---
Nitpick comments:
In @.squad/skills/tunit-test-filtering/SKILL.md:
- Line 15: Update the Windows-style path examples (e.g. the line containing
"Test app path: `src\Refitter.Tests\bin\Release\net10.0\Refitter.Tests.exe`" and
the similar entries around the section for lines 22-27) to call out
platform-specific syntax: add a brief note that backslashes are
Windows/PowerShell only and provide a cross-platform alternative using forward
slashes (e.g. src/Refitter.Tests/bin/Release/net10.0/Refitter.Tests.exe) and
mention which shells/examples use which syntax (PowerShell vs bash/zsh) so
readers on Linux/macOS know to use the forward-slash form.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: ef32b870-b4a9-4776-9485-1fc726f592b1
📒 Files selected for processing (14)
.squad/agents/fenster/history.md.squad/agents/hockney/history.md.squad/agents/keaton/history.md.squad/agents/mcmanus/history.md.squad/decisions.md.squad/identity/now.md.squad/orchestration-log/2026-03-06T16-29-27Z-fenster.md.squad/orchestration-log/2026-03-06T16-29-27Z-hockney.md.squad/orchestration-log/2026-03-06T16-29-27Z-keaton.md.squad/skills/tunit-test-filtering/SKILL.md.squad/skills/xml-doc-description-sanitization/SKILL.mdsrc/Refitter.Core/XmlDocumentationGenerator.cssrc/Refitter.Tests/Examples/GenerateStatusCodeCommentsTests.cssrc/Refitter.Tests/XmlDocumentationGeneratorTests.cs
Owner
Author
|
@copilot open a new pull request to apply changes based on the comments in this thread |
Contributor
|
@christianhelle I've opened a new pull request, #949, to work on those changes. Once the pull request is ready, I'll request review from you. |
|
Contributor
There was a problem hiding this comment.
♻️ Duplicate comments (1)
.squad/decisions.md (1)
331-342:⚠️ Potential issue | 🟡 MinorInternal inconsistency: test count differs within the same section.
Line 331 states "All 1415 tests pass" while line 342 states "All tests passing (1451/1451)". These should be aligned to avoid an inconsistent audit trail.
📝 Proposed fix
- Surrogate pairs handled naturally via C# UTF-16 -- All 1415 tests pass; no regressions +- All 1451 tests pass; no regressions🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.squad/decisions.md around lines 331 - 342, Update the inconsistent test counts in the decision note so both statements match: replace "All 1415 tests pass" with the accurate test count used in the Gates line (or vice versa) so that "All ... tests pass" and "All tests passing (1451/1451)" use the same number; ensure both occurrences in the section are identical and reflect the actual test run total.
🧹 Nitpick comments (3)
src/Refitter.Core/XmlDocumentationGenerator.cs (3)
398-410: Loop index mutation is idiomatic but flagged by static analysis.Mutating
indexinside the loop body (lines 398, 410) is a common pattern for escape-sequence parsers. SonarCloud flags this as it can obscure control flow. If you refactor per the complexity suggestion, this would be resolved naturally. Otherwise, switching to awhileloop with explicit index advancement would silence the warning without changing behavior.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/Refitter.Core/XmlDocumentationGenerator.cs` around lines 398 - 410, The loop mutates the for-loop index variable `index` inside the body when parsing escape sequences (e.g., handling `'u'` hex escapes), which triggers static analysis; change the parsing loop to an explicit while-loop over `index` (e.g., `while (index < input.Length)`) and advance `index` only in one place (incrementing by 1 for normal characters and by 5 when consuming a `\uXXXX` sequence) so you no longer modify the loop control variable inside the body; keep the same logic using `input`, `result.Append`, `IsValidXmlChar`, and the hex parsing with `int.TryParse` but move index advancement out of the inner block to make control flow explicit and satisfy SonarCloud.
357-445: Consider extracting helper methods to reduce cognitive complexity.SonarCloud flags cognitive complexity of 37 (allowed 15). While the parsing logic is functionally correct, extracting helpers would improve maintainability:
TryDecodeUnicodeEscape(string input, int index, out char decoded, out int consumed)DecodeSimpleEscape(char escapedChar)Additionally, since
DecodeJsonEscapedTextdoesn't access instance state, it could be madestatic(along withIsValidXmlChar).♻️ Sketch of extracted helpers
- private string DecodeJsonEscapedText(string input) + private static string DecodeJsonEscapedText(string input) { // ... early returns unchanged ... for (var index = 0; index < input.Length; index++) { // ... use extracted helpers: - if (escapedCharacter == 'u' && index + 4 < input.Length) - { - var hexValue = input.Substring(index + 1, 4); - if (int.TryParse(hexValue, NumberStyles.HexNumber, CultureInfo.InvariantCulture, out var unicodeCodePoint)) - { - // ... - } - } + if (TryDecodeUnicodeEscape(input, index, out var decoded, out var consumed)) + { + if (IsValidXmlChar(decoded)) result.Append(decoded); + index += consumed; + continue; + } } } + + private static bool TryDecodeUnicodeEscape(string input, int index, out char decoded, out int consumed) + { + decoded = default; + consumed = 0; + if (index + 5 >= input.Length || input[index + 1] != 'u') return false; + var hex = input.Substring(index + 2, 4); + if (!int.TryParse(hex, NumberStyles.HexNumber, CultureInfo.InvariantCulture, out var cp)) return false; + decoded = (char)cp; + consumed = 5; // \uXXXX + return true; + }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/Refitter.Core/XmlDocumentationGenerator.cs` around lines 357 - 445, The DecodeJsonEscapedText method is too complex; refactor by extracting the Unicode and simple-escape parsing into helpers and making relevant methods static: add TryDecodeUnicodeEscape(string input, int index, out char decoded, out int consumed) to parse "\uXXXX" (return true and set consumed to number of chars consumed when successful), add DecodeSimpleEscape(char escapedChar) -> char? to map "n","t","r","b","f","\"", "\\", "/" to their char or null for unknowns, and change IsValidXmlChar to static; then simplify DecodeJsonEscapedText to call TryDecodeUnicodeEscape and DecodeSimpleEscape, update the loop to advance index by consumed (when unicode) or 0/1 as appropriate, and keep the existing sanitization behavior for unknown escapes by appending backslash + char only if IsValidXmlChar permits. Ensure signatures of new helpers are used in DecodeJsonEscapedText and mark all three methods static.
447-454: Minor:IsValidXmlChardoesn't exclude 0xFFFE/0xFFFF.XML 1.0 spec excludes
#xFFFEand#xFFFFas valid characters. The current checkc >= 0x20allows these. In practice, these codepoints are extremely rare in OpenAPI descriptions, so impact is minimal.🛡️ Strict XML 1.0 compliance (optional)
private static bool IsValidXmlChar(char c) { - return c == 0x09 || c == 0x0A || c == 0x0D || c >= 0x20; + return c == 0x09 || c == 0x0A || c == 0x0D || + (c >= 0x20 && c != 0xFFFE && c != 0xFFFF); }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/Refitter.Core/XmlDocumentationGenerator.cs` around lines 447 - 454, IsValidXmlChar currently allows all chars >= 0x20 which inadvertently permits the disallowed 0xFFFE and 0xFFFF; update IsValidXmlChar to only accept characters in the XML 1.0 allowed ranges (allow 0x09, 0x0A, 0x0D, and chars from 0x20 through 0xFFFD) and explicitly exclude 0xFFFE and 0xFFFF (i.e., ensure the check uses an upper bound of 0xFFFD and filters out 0xFFFE/0xFFFF) so the method enforces XML 1.0 compliance.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Duplicate comments:
In @.squad/decisions.md:
- Around line 331-342: Update the inconsistent test counts in the decision note
so both statements match: replace "All 1415 tests pass" with the accurate test
count used in the Gates line (or vice versa) so that "All ... tests pass" and
"All tests passing (1451/1451)" use the same number; ensure both occurrences in
the section are identical and reflect the actual test run total.
---
Nitpick comments:
In `@src/Refitter.Core/XmlDocumentationGenerator.cs`:
- Around line 398-410: The loop mutates the for-loop index variable `index`
inside the body when parsing escape sequences (e.g., handling `'u'` hex
escapes), which triggers static analysis; change the parsing loop to an explicit
while-loop over `index` (e.g., `while (index < input.Length)`) and advance
`index` only in one place (incrementing by 1 for normal characters and by 5 when
consuming a `\uXXXX` sequence) so you no longer modify the loop control variable
inside the body; keep the same logic using `input`, `result.Append`,
`IsValidXmlChar`, and the hex parsing with `int.TryParse` but move index
advancement out of the inner block to make control flow explicit and satisfy
SonarCloud.
- Around line 357-445: The DecodeJsonEscapedText method is too complex; refactor
by extracting the Unicode and simple-escape parsing into helpers and making
relevant methods static: add TryDecodeUnicodeEscape(string input, int index, out
char decoded, out int consumed) to parse "\uXXXX" (return true and set consumed
to number of chars consumed when successful), add DecodeSimpleEscape(char
escapedChar) -> char? to map "n","t","r","b","f","\"", "\\", "/" to their char
or null for unknowns, and change IsValidXmlChar to static; then simplify
DecodeJsonEscapedText to call TryDecodeUnicodeEscape and DecodeSimpleEscape,
update the loop to advance index by consumed (when unicode) or 0/1 as
appropriate, and keep the existing sanitization behavior for unknown escapes by
appending backslash + char only if IsValidXmlChar permits. Ensure signatures of
new helpers are used in DecodeJsonEscapedText and mark all three methods static.
- Around line 447-454: IsValidXmlChar currently allows all chars >= 0x20 which
inadvertently permits the disallowed 0xFFFE and 0xFFFF; update IsValidXmlChar to
only accept characters in the XML 1.0 allowed ranges (allow 0x09, 0x0A, 0x0D,
and chars from 0x20 through 0xFFFD) and explicitly exclude 0xFFFE and 0xFFFF
(i.e., ensure the check uses an upper bound of 0xFFFD and filters out
0xFFFE/0xFFFF) so the method enforces XML 1.0 compliance.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: da06f26f-cb0a-48a3-936b-6a4a0e48cc01
📒 Files selected for processing (6)
.squad/agents/hockney/history.md.squad/decisions.md.squad/skills/tunit-test-filtering/SKILL.mdsrc/Refitter.Core/XmlDocumentationGenerator.cssrc/Refitter.Tests/Examples/GenerateStatusCodeCommentsTests.cssrc/Refitter.Tests/XmlDocumentationGeneratorTests.cs
🚧 Files skipped from review as they are similar to previous changes (4)
- .squad/skills/tunit-test-filtering/SKILL.md
- src/Refitter.Tests/XmlDocumentationGeneratorTests.cs
- .squad/agents/hockney/history.md
- src/Refitter.Tests/Examples/GenerateStatusCodeCommentsTests.cs
This was referenced May 3, 2026
hwinther
pushed a commit
to hwinther/test
that referenced
this pull request
May 6, 2026
Updated [refitter](https://github.com/christianhelle/refitter) from 1.7.1 to 2.0.0. <details> <summary>Release notes</summary> _Sourced from [refitter's releases](https://github.com/christianhelle/refitter/releases)._ ## 2.0.0 ## What's Changed * Fix numeric format with pattern quirk - infer type from format for all numeric types by @Copilot in christianhelle/refitter#869 * Read group documentation from document tags. by @DJ4ddi in christianhelle/refitter#887 * Fix null reference and XML escaping in XmlDocumentationGenerator by @Copilot in christianhelle/refitter#890 * Fix build workflow: add dotnet restore before dotnet msbuild in Prepare step by @Copilot in christianhelle/refitter#892 christianhelle/refitter#895 * Fix MSBuild workflow by @christianhelle in christianhelle/refitter#898 * Add support for generating a single client from multiple OpenAPI specifications by @Copilot in christianhelle/refitter#904 * Migrate from Microsoft.OpenApi.Readers 1.x to Microsoft.OpenApi 3.x by @vgmello in christianhelle/refitter#907 * Improve Smoke Tests execution time by @christianhelle in christianhelle/refitter#915 * Fix #580: Nullable strings marked correctly by @christianhelle in christianhelle/refitter#921 * Fix #672: MultipleInterfaces ByTag method naming scoped per-interface by @christianhelle in christianhelle/refitter#922 * Fix #635: Refactor source generator to use context.AddSource() by @christianhelle in christianhelle/refitter#923 * Add custom format mappings configuration by @christianhelle in christianhelle/refitter#927 * Fix multipart form-data parameter extraction by @christianhelle in christianhelle/refitter#928 christianhelle/refitter#911 christianhelle/refitter#902 * Fix smoke tests: --interface-only variant missing using directive for contract types by @Copilot in christianhelle/refitter#933 * Fix SonarCloud Code Quality Issues by @Copilot in christianhelle/refitter#932 * Add debug logging for source generator when searching for .refitter files by @codymullins in christianhelle/refitter#743 * Fix: Base type not generated for types using oneOf with discriminator by @Copilot in christianhelle/refitter#906 * Add option for Method Level Authorization header attribute by @Roflincopter in christianhelle/refitter#897 * Fix PR #897 review feedback and add comprehensive bearer auth tests by @christianhelle in christianhelle/refitter#936 * Fix numeric suffix added to interface method names in ByTag mode by @Copilot in christianhelle/refitter#914 * Improve OpenAPI parse + codegen throughput by removing avoidable allocations and repeated regex work by @Copilot in christianhelle/refitter#937 * Move [JsonConverter] from enum properties to enum types by @christianhelle in christianhelle/refitter#938 * Fix broken CLI tool help text by @christianhelle in christianhelle/refitter#940 * Improve code coverage to >90% by @christianhelle in christianhelle/refitter#941 * Microsoft.OpenApi v3.4 by @christianhelle in christianhelle/refitter#945 * Add Unicode support for XML doc comment generation by @christianhelle in christianhelle/refitter#948 * Add PropertyNamingPolicy support for JSON property naming by @christianhelle in christianhelle/refitter#969 christianhelle/refitter#966 * Fix recursive schema stack overflows by @christianhelle in christianhelle/refitter#971 * Made Header Parameters for Security Schemes safe to use as C# variable name by @smoerijf in christianhelle/refitter#977 * Enhance schema alias handling and property name generation by @christianhelle in christianhelle/refitter#996 * Verify alias handling and sanitize PascalCase properties by @christianhelle in christianhelle/refitter#997 * Harden .refitter settings deserialization and output path handling by @christianhelle in christianhelle/refitter#1000 * Special-case the default .refitter filename before deriving OutputFilename by @coderabbitai[bot] in christianhelle/refitter#1002 * [v2.0 audit] Fix pre-release regressions from #1057 by @christianhelle in christianhelle/refitter#1064 * Resolve high-severity audit findings from #1057 by @christianhelle in christianhelle/refitter#1067 * [v2.0 audit] Close remaining verified #1057 regressions by @christianhelle in christianhelle/refitter#1070 * Harden generation flows by @christianhelle in christianhelle/refitter#1071 * Breaking changes and Migration Guide for v2.0.0 by @christianhelle in christianhelle/refitter#1009 * Handle equivalent duplicate schemas in multi-spec merge by @christianhelle in christianhelle/refitter#1076 * Tighten warning handling across Refitter builds by @christianhelle in christianhelle/refitter#1079 * Fix default solution path and update .NET version in VS Code config by @christianhelle in christianhelle/refitter#1082 * Fix docker smoke tests by @christianhelle in christianhelle/refitter#1081 * Sanitize malformed schema type names without renaming clean schemas by @christianhelle in christianhelle/refitter#1085 ... (truncated) ## 1.7.3 ## What's Changed * Add support for systems running only .NET 10.0 (without .NET 8.0 or 9.0) in Refitter.MSBuild by @christianhelle in christianhelle/refitter#882 * Update to return HttpResponseMessage for file downloads by @frogcrush in christianhelle/refitter#877 ## New Contributors * @frogcrush made their first contribution in christianhelle/refitter#877 **Full Changelog**: christianhelle/refitter@1.7.2...1.7.3 ## 1.7.2 **Implemented enhancements:** - Improve Immutable Records ergonomics [\#844](christianhelle/refitter#844) - Omit certain operation headers and include all others [\#840](christianhelle/refitter#840) - Create .refitter settings file as part of output [\#859](christianhelle/refitter#859) by @[christianhelle - Fix integerType enum deserialization issue [\#855](christianhelle/refitter#855) ([christianhelle](https://github.com/christianhelle)) - support custom nswag template directory \#844 [\#854](christianhelle/refitter#854) by @kmc059000 - Fix missing method parameter XML code-documentation [\#850](christianhelle/refitter#850) ([christianhelle](https://github.com/christianhelle)) **Fixed bugs:** - integerType parsing in settings file fails [\#851](christianhelle/refitter#851) - CS1573 : Method parameter has no matching XML comment [\#846](christianhelle/refitter#846) **Merged pull requests:** - docs: add frogcrush as a contributor for code [\#878](christianhelle/refitter#878) ([allcontributors[bot]](https://github.com/apps/allcontributors)) - Migrate solution files from .sln to .slnx format [\#876](christianhelle/refitter#876) ([Copilot](https://github.com/apps/copilot-swe-agent)) - Fix issue with randomly failing tests to due parallel execution [\#872](christianhelle/refitter#872) ([christianhelle](https://github.com/christianhelle)) - chore\(deps\): update dependency tunit to 1.9.2 [\#863](christianhelle/refitter#863) ([renovate[bot]](https://github.com/apps/renovate)) - chore\(deps\): update dependency tunit to 1.7.7 [\#862](christianhelle/refitter#862) ([renovate[bot]](https://github.com/apps/renovate)) - Add unit tests for WriteRefitterSettingsFile functionality [\#860](christianhelle/refitter#860) ([Copilot](https://github.com/apps/copilot-swe-agent)) - chore\(deps\): update dependency ruby to v4 [\#858](christianhelle/refitter#858) ([renovate[bot]](https://github.com/apps/renovate)) - chore\(deps\): update dependency tunit to 1.6.28 [\#857](christianhelle/refitter#857) ([renovate[bot]](https://github.com/apps/renovate)) - docs: add 0x2badc0de as a contributor for bug [\#856](christianhelle/refitter#856) ([allcontributors[bot]](https://github.com/apps/allcontributors)) - chore\(deps\): update dependency swashbuckle.aspnetcore to 10.1.0 [\#853](christianhelle/refitter#853) ([renovate[bot]](https://github.com/apps/renovate)) - chore\(deps\): update dependency tunit to 1.6.0 [\#852](christianhelle/refitter#852) ([renovate[bot]](https://github.com/apps/renovate)) - docs: add lilinus as a contributor for code [\#849](christianhelle/refitter#849) ([allcontributors[bot]](https://github.com/apps/allcontributors)) - chore\(deps\): update dependency ruby to v3.4.8 [\#845](christianhelle/refitter#845) ([renovate[bot]](https://github.com/apps/renovate)) - chore\(deps\): update dependency tunit to 1.5.70 [\#837](christianhelle/refitter#837) ([renovate[bot]](https://github.com/apps/renovate)) **Full Changelog**: christianhelle/refitter@1.7.1...1.7.2 Commits viewable in [compare view](christianhelle/refitter@1.7.1...2.0.0). </details> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
vgmello
pushed a commit
to vgmello/momentum
that referenced
this pull request
May 10, 2026
Updated [Refitter.MSBuild](https://github.com/christianhelle/refitter) from 1.7.3 to 2.0.0. <details> <summary>Release notes</summary> _Sourced from [Refitter.MSBuild's releases](https://github.com/christianhelle/refitter/releases)._ ## 2.0.0 ## What's Changed * Fix numeric format with pattern quirk - infer type from format for all numeric types by @Copilot in christianhelle/refitter#869 * Read group documentation from document tags. by @DJ4ddi in christianhelle/refitter#887 * Fix null reference and XML escaping in XmlDocumentationGenerator by @Copilot in christianhelle/refitter#890 * Fix build workflow: add dotnet restore before dotnet msbuild in Prepare step by @Copilot in christianhelle/refitter#892 christianhelle/refitter#895 * Fix MSBuild workflow by @christianhelle in christianhelle/refitter#898 * Add support for generating a single client from multiple OpenAPI specifications by @Copilot in christianhelle/refitter#904 * Migrate from Microsoft.OpenApi.Readers 1.x to Microsoft.OpenApi 3.x by @vgmello in christianhelle/refitter#907 * Improve Smoke Tests execution time by @christianhelle in christianhelle/refitter#915 * Fix #580: Nullable strings marked correctly by @christianhelle in christianhelle/refitter#921 * Fix #672: MultipleInterfaces ByTag method naming scoped per-interface by @christianhelle in christianhelle/refitter#922 * Fix #635: Refactor source generator to use context.AddSource() by @christianhelle in christianhelle/refitter#923 * Add custom format mappings configuration by @christianhelle in christianhelle/refitter#927 * Fix multipart form-data parameter extraction by @christianhelle in christianhelle/refitter#928 christianhelle/refitter#911 christianhelle/refitter#902 * Fix smoke tests: --interface-only variant missing using directive for contract types by @Copilot in christianhelle/refitter#933 * Fix SonarCloud Code Quality Issues by @Copilot in christianhelle/refitter#932 * Add debug logging for source generator when searching for .refitter files by @codymullins in christianhelle/refitter#743 * Fix: Base type not generated for types using oneOf with discriminator by @Copilot in christianhelle/refitter#906 * Add option for Method Level Authorization header attribute by @Roflincopter in christianhelle/refitter#897 * Fix PR #897 review feedback and add comprehensive bearer auth tests by @christianhelle in christianhelle/refitter#936 * Fix numeric suffix added to interface method names in ByTag mode by @Copilot in christianhelle/refitter#914 * Improve OpenAPI parse + codegen throughput by removing avoidable allocations and repeated regex work by @Copilot in christianhelle/refitter#937 * Move [JsonConverter] from enum properties to enum types by @christianhelle in christianhelle/refitter#938 * Fix broken CLI tool help text by @christianhelle in christianhelle/refitter#940 * Improve code coverage to >90% by @christianhelle in christianhelle/refitter#941 * Microsoft.OpenApi v3.4 by @christianhelle in christianhelle/refitter#945 * Add Unicode support for XML doc comment generation by @christianhelle in christianhelle/refitter#948 * Add PropertyNamingPolicy support for JSON property naming by @christianhelle in christianhelle/refitter#969 christianhelle/refitter#966 * Fix recursive schema stack overflows by @christianhelle in christianhelle/refitter#971 * Made Header Parameters for Security Schemes safe to use as C# variable name by @smoerijf in christianhelle/refitter#977 * Enhance schema alias handling and property name generation by @christianhelle in christianhelle/refitter#996 * Verify alias handling and sanitize PascalCase properties by @christianhelle in christianhelle/refitter#997 * Harden .refitter settings deserialization and output path handling by @christianhelle in christianhelle/refitter#1000 * Special-case the default .refitter filename before deriving OutputFilename by @coderabbitai[bot] in christianhelle/refitter#1002 * [v2.0 audit] Fix pre-release regressions from #1057 by @christianhelle in christianhelle/refitter#1064 * Resolve high-severity audit findings from #1057 by @christianhelle in christianhelle/refitter#1067 * [v2.0 audit] Close remaining verified #1057 regressions by @christianhelle in christianhelle/refitter#1070 * Harden generation flows by @christianhelle in christianhelle/refitter#1071 * Breaking changes and Migration Guide for v2.0.0 by @christianhelle in christianhelle/refitter#1009 * Handle equivalent duplicate schemas in multi-spec merge by @christianhelle in christianhelle/refitter#1076 * Tighten warning handling across Refitter builds by @christianhelle in christianhelle/refitter#1079 * Fix default solution path and update .NET version in VS Code config by @christianhelle in christianhelle/refitter#1082 * Fix docker smoke tests by @christianhelle in christianhelle/refitter#1081 * Sanitize malformed schema type names without renaming clean schemas by @christianhelle in christianhelle/refitter#1085 ... (truncated) Commits viewable in [compare view](christianhelle/refitter@1.7.3...2.0.0). </details> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore <dependency name> major version` will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself) - `@dependabot ignore <dependency name> minor version` will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself) - `@dependabot ignore <dependency name>` will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself) - `@dependabot unignore <dependency name>` will remove all of the ignore conditions of the specified dependency - `@dependabot unignore <dependency name> <ignore condition>` will remove the ignore condition of the specified dependency and ignore conditions </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request fixes #944 by improving the handling of Unicode and escape sequences in XML documentation generated from OpenAPI response descriptions. The main focus is on ensuring that non-ASCII characters are correctly rendered in XML status-code comments, and that only user-sourced text is sanitized, preserving hardcoded XML fragments.
Unicode and XML documentation improvements:
DecodeJsonEscapedText()method inXmlDocumentationGenerator.csto decode JSON-style escape sequences (like\uXXXX,\",\n) before inserting response descriptions into XML documentation.<see cref="Task"/>and<list>) remain untouched. Reserved XML characters (&,<,>) are escaped at insertion.Testing and validation:
Summary by CodeRabbit
Bug Fixes
Tests
Documentation