Release v0.1.7

nshkrdotcom · nshkrdotcom · commit 1aa60aa985f5 · 2025-10-27T11:47:14.000-10:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.1.7] - 2025-10-27
+
+### Fixed
+- **Windows HTML payloads**: Layer 3's binary optimization now trims HTML fragments using byte-accurate offsets, ensuring CRLF-terminated bodies are quoted without leaving stray delimiters.
+- **Regression coverage**: Added a direct regression test mirroring the reporter's `CRLF_html.json` sample so Windows-style newlines stay guarded.
+
+### Added
+- **Examples**: Extended `examples/html_content_examples.exs` with a Windows newline scenario to demonstrate the repaired behaviour via `mix run`.
+- **Documentation**: HexDocs now surfaces grouped README, changelog, and license pages for easier navigation.
+
 ## [0.1.6] - 2025-10-24
 
 ### Added
@@ -297,7 +307,7 @@ This is a **100% rewrite** - all previous code has been replaced with the new la
   - Incomplete objects and arrays
   - Boolean variants (True/False/TRUE/FALSE)
   - Null variants (None/NULL/Null)
-  - Code fence removal (```json blocks)
+  - Code fence removal (triple-backtick `json` fences)
   - Comment stripping (// and /* */)
 - Core API functions:
   - `JsonRemedy.repair/2` - Parse and repair JSON to Elixir terms
@@ -318,11 +328,12 @@ This is a **100% rewrite** - all previous code has been replaced with the new la
 - Minimal memory overhead (< 8KB for repairs)
 - All operations pass performance thresholds
 
-[Unreleased]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.6...HEAD
+[Unreleased]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.7...HEAD
+[0.1.7]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.6...v0.1.7
 [0.1.6]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.5...v0.1.6
 [0.1.5]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.4...v0.1.5
 [0.1.4]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.3...v0.1.4
 [0.1.3]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.2...v0.1.3
 [0.1.2]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.1...v0.1.2
 [0.1.1]: https://github.com/nshkrdotcom/json_remedy/compare/v0.1.0...v0.1.1
-[0.1.0]: https://github.com/nshkrdotcom/json_remedy/releases/tag/v0.1.0
+[0.1.0]: https://github.com/nshkrdotcom/json_remedy/releases/tag/v0.1.0
diff --git a/README.md b/README.md
@@ -158,7 +158,7 @@ Add JsonRemedy to your `mix.exs`:
 ```elixir
 def deps do
   [
-    {:json_remedy, "~> 0.1.6"}
+    {:json_remedy, "~> 0.1.7"}
   ]
 end
 ```
diff --git a/examples/html_content_examples.exs b/examples/html_content_examples.exs
@@ -32,6 +32,9 @@ defmodule HtmlContentExamples do
     # Example 5: Complex nested HTML with JSON-like content
     example_5_complex_nested_html()
 
+    # Example 6: Windows-style CRLF HTML body
+    example_6_api_503_error_windows()
+
     IO.puts("\n=== All HTML content examples completed! ===")
   end
 
@@ -240,7 +243,32 @@ defmodule HtmlContentExamples do
 
     IO.puts("\n" <> String.duplicate("-", 80) <> "\n")
   end
+
+  defp example_6_api_503_error_windows do
+    IO.puts("Example 6: API 503 Error Page with Windows Newlines")
+    IO.puts("====================================================")
+
+    malformed =
+      ~s({"responses": [{"id":"33","status":503,"headers":{"Content-Type":"text/html; charset=us-ascii"},"body":<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN""http://www.w3.org/TR/html4/strict.dtd"><HTML><HEAD><TITLE>Service Unavailable</TITLE><META HTTP-EQUIV="Content-Type" Content="text/html; charset=us-ascii"></HEAD><BODY><h2>Application Request Queue Full</h2><hr><p>HTTP Error 503. The application request queue is full.</p>\r\n</BODY></HTML>}]} )
+
+    IO.puts("Input (API response with CRLF-terminated HTML body):")
+    IO.puts(String.slice(malformed, 0, 200) <> "...\n")
+
+    case JsonRemedy.repair(malformed) do
+      {:ok, result} ->
+        IO.puts("✓ Successfully repaired!")
+        [response] = result["responses"]
+        IO.puts("\nParsed response:")
+        IO.inspect(response, pretty: true, limit: :infinity)
+        IO.puts("\n✓ HTML body retains CRLF sequence:")
+        IO.puts(String.replace(response["body"], "\r\n", "\\r\\n"))
+
+      {:error, reason} ->
+        IO.puts("✗ Failed to repair: #{reason}")
+    end
+
+    IO.puts("\n" <> String.duplicate("-", 80) <> "\n")
+  end
 end
 
-# Run all examples
 HtmlContentExamples.run_all_examples()
diff --git a/lib/json_remedy/layer3/syntax_normalization.ex b/lib/json_remedy/layer3/syntax_normalization.ex
@@ -805,13 +805,27 @@ defmodule JsonRemedy.Layer3.SyntaxNormalization do
       char == ?< and expecting == :value and
           HtmlHandlers.is_html_start?(<<char::utf8, rest::binary>>, 0) ->
         # Start of HTML content - quote it
-        {html_content, chars_consumed} =
-          HtmlHandlers.extract_html_content(<<char::utf8, rest::binary>>, 0)
+        fragment = <<char::utf8, rest::binary>>
+        {html_content, chars_consumed} = HtmlHandlers.extract_html_content(fragment, 0)
 
         {quoted_html, html_repairs} = HtmlHandlers.quote_html_content(html_content, pos)
 
-        # Calculate remaining binary after consuming HTML
-        remaining = binary_part(rest, chars_consumed - 1, byte_size(rest) - (chars_consumed - 1))
+        consumed_fragment = String.slice(fragment, 0, chars_consumed)
+        bytes_consumed = byte_size(consumed_fragment)
+        bytes_for_rest = max(bytes_consumed - byte_size(<<char::utf8>>), 0)
+
+        remaining =
+          if bytes_for_rest <= 0 do
+            rest
+          else
+            rest_size = byte_size(rest)
+
+            if bytes_for_rest >= rest_size do
+              <<>>
+            else
+              binary_part(rest, bytes_for_rest, rest_size - bytes_for_rest)
+            end
+          end
 
         normalize_syntax_binary_simple(
           remaining,
diff --git a/mix.exs b/mix.exs
@@ -1,7 +1,7 @@
 defmodule JsonRemedy.MixProject do
   use Mix.Project
 
-  @version "0.1.6"
+  @version "0.1.7"
   @source_url "https://github.com/nshkrdotcom/json_remedy"
 
   def project do
@@ -11,6 +11,9 @@ defmodule JsonRemedy.MixProject do
       elixir: "~> 1.14",
       start_permanent: Mix.env() == :prod,
       deps: deps(),
+      name: "JsonRemedy",
+      source_url: @source_url,
+      homepage_url: @source_url,
       description:
         "A blazingly fast Elixir library for repairing malformed JSON using binary pattern matching. Handles LLM outputs, legacy data, and broken JSON with intelligent context-aware fixes.",
       package: package(),
@@ -55,18 +58,29 @@ defmodule JsonRemedy.MixProject do
         "GitHub" => @source_url,
         "Documentation" => "https://hexdocs.pm/json_remedy"
       },
-      files: ~w(lib .formatter.exs mix.exs README.md LICENSE assets)
+      files: ~w(lib .formatter.exs mix.exs README.md CHANGELOG.md LICENSE assets)
     ]
   end
 
   defp docs do
     [
-      main: "JsonRemedy",
+      main: "readme",
+      name: "JsonRemedy",
       source_ref: "v#{@version}",
       source_url: @source_url,
+      homepage_url: @source_url,
       assets: %{"assets" => "assets"},
       logo: "assets/json_remedy_logo.svg",
-      extras: ["README.md", "LICENSE"]
+      extras: [
+        {"README.md", [title: "Overview"]},
+        {"CHANGELOG.md", [title: "Changelog"]},
+        {"LICENSE", [title: "License"]}
+      ],
+      groups_for_extras: [
+        "Getting Started": ["README.md"],
+        "Release Notes": ["CHANGELOG.md"],
+        Reference: ["LICENSE"]
+      ]
     ]
   end
 end
diff --git a/test/unit/layer3_html_content_test.exs b/test/unit/layer3_html_content_test.exs
@@ -93,6 +93,17 @@ defmodule JsonRemedy.Layer3HtmlContentTest do
       assert String.contains?(result["snippet"], ~s(User said: "Hello World"))
     end
 
+    test "handles HTML with Windows-style newlines" do
+      malformed = ~s(
+        {"responses": [{"id":"33","status":503,"headers":{"Content-Type":"text/html; charset=us-ascii"},"body":<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN""http://www.w3.org/TR/html4/strict.dtd"><HTML><HEAD><TITLE>Service Unavailable</TITLE><META HTTP-EQUIV="Content-Type" Content="text/html; charset=us-ascii"></HEAD><BODY><h2>Application Request Queue Full</h2><hr><p>HTTP Error 503. The application request queue is full.</p>\r\n</BODY></HTML>}]}
+      )
+
+      assert {:ok, result} = JsonRemedy.repair(malformed)
+      [response] = result["responses"]
+      assert String.contains?(response["body"], "\r\n")
+      assert String.contains?(response["body"], "Application Request Queue Full")
+    end
+
     test "handles HTML with special entities" do
       malformed = ~s({"content":<p>Read more &raquo; or &amp; continue</p>})
 

Original file line number	Diff line number	Diff line change
@@ -158,7 +158,7 @@ Add JsonRemedy to your `mix.exs`:
`158`	`158`	```elixir
`159`	`159`	`def deps do`
`160`	`160`	`[`
`161`		`- {:json_remedy, "~> 0.1.6"}`
	`161`	`+ {:json_remedy, "~> 0.1.7"}`
`162`	`162`	`]`
`163`	`163`	`end`
`164`	`164`	```