Better emphasis

.github/workflows/run-tests.yml

@@ -12,8 +12,8 @@ jobs:
       - uses: actions/checkout@v6
       - uses: lukka/get-cmake@latest
         with:
-          cmakeVersion: "~3.25.0"
-          ninjaVersion: "^1.11.1"
+          cmakeVersion: "~4.2.0"  # <--= optional, use most recent 4.2.x version
+          ninjaVersion: "^1.11.1"  # <--= optional, use most recent 1.x version
       - name: build
         run: |
           mkdir tmp
@@ -39,13 +39,13 @@ jobs:
       - uses: actions/checkout@v6
       - uses: lukka/get-cmake@latest
         with:
-          cmakeVersion: "~3.25.0"
-          ninjaVersion: "^1.11.1"
+          cmakeVersion: "~4.2.0"  # <--= optional, use most recent 4.2.x version
+          ninjaVersion: "^1.11.1"  # <--= optional, use most recent 1.x version
       - name: build
         run: |
           mkdir tmp
           cd tmp
-          cmake -G "Visual Studio 17 2022" -A x64 -DMADDY_BUILD_WITH_TESTS=ON ..
+          cmake -G "Visual Studio 18 2026" -A x64 -DMADDY_BUILD_WITH_TESTS=ON ..
           cmake --build . --config Debug
       - name: run tests
         run: |
@@ -57,8 +57,8 @@ jobs:
       - uses: actions/checkout@v6
       - uses: lukka/get-cmake@latest
         with:
-          cmakeVersion: "~3.25.0"
-          ninjaVersion: "^1.11.1"
+          cmakeVersion: "~4.2.0"  # <--= optional, use most recent 4.2.x version
+          ninjaVersion: "^1.11.1"  # <--= optional, use most recent 1.x version
       - name: build
         run: |
           mkdir tmp

CHANGELOG.md

@@ -14,6 +14,8 @@ maddy uses [semver versioning](https://semver.org/).
 
 ## Upcoming
 
+* ![**FIXED**](https://img.shields.io/badge/-FIXED-%23090) Only create strong and emphasis tags at word boundaries, i.e. `not only_internal_underscores`.
+* ![**FIXED**](https://img.shields.io/badge/-FIXED-%23090) Correctly leave any leftover strong or emphasis delimiters outside the tag on either side, however many there are, i.e. `___text__` becomes `_<strong>text</strong>` and `_text_______` becomes `<em>text</em>______`.
 * ...
 
 ## version 1.6.0 2025-07-26

include/maddy/emphasizedparser.h

@@ -40,10 +40,13 @@ class EmphasizedParser : public LineParser
    */
   void Parse(std::string& line) override
   {
+    // The leading and trailing `(_*)` groups absorb any leftover underscores
+    // from an unbalanced run (e.g. `__foo_` or `_foo____`), re-emitted
+    // outside the <em> tag instead of into its content.
     static std::regex re(
-      R"((?!.*`.*|.*<code>.*)_(?!.*`.*|.*<\/code>.*)([^_]*)_(?!.*`.*|.*<\/code>.*))"
+      R"((?!.*`.*|.*<code>.*)\b(_*)_(?![\s_])(?!.*`.*|.*<\/code>.*)(.*?[^\s])_(_*)\b(?!.*`.*|.*<\/code>.*))"
     );
-    static std::string replacement = "<em>$1</em>";
+    static std::string replacement = "$1<em>$2</em>$3";
 
     line = std::regex_replace(line, re, replacement);
   }

include/maddy/strongparser.h

@@ -40,19 +40,21 @@ class StrongParser : public LineParser
    */
   void Parse(std::string& line) override
   {
-    static std::vector<std::regex> res{
-      std::regex{
-        R"((?!.*`.*|.*<code>.*)\*\*(?!.*`.*|.*<\/code>.*)([^\*\*]*)\*\*(?!.*`.*|.*<\/code>.*))"
-      },
-      std::regex{
-        R"((?!.*`.*|.*<code>.*)__(?!.*`.*|.*<\/code>.*)([^__]*)__(?!.*`.*|.*<\/code>.*))"
-      }
+    // `*` is not a word character, so `\b` next to it does not mean
+    // "edge of a delimiter run" the way it does for `_`; the asterisk
+    // variant is left without a word-boundary anchor.
+    static std::regex reAsterisk{
+      R"((?!.*`.*|.*<code>.*)\*\*(?![\s])(?!.*`.*|.*<\/code>.*)(.*?[^\s])\*\*(?!.*`.*|.*<\/code>.*))"
     };
-    static std::string replacement = "<strong>$1</strong>";
-    for (const auto& re : res)
-    {
-      line = std::regex_replace(line, re, replacement);
-    }
+    // The leading and trailing `(_*)` groups absorb any leftover underscores
+    // from an unbalanced run on either side (e.g. `___text__` or
+    // `__text_______`), re-emitted outside the <strong> tag by the caller
+    // instead of being swallowed into its content.
+    static std::regex reUnderscore{
+      R"((?!.*`.*|.*<code>.*)\b(_*)__(?![\s_])(?!.*`.*|.*<\/code>.*)(.*?[^\s])__(_*)\b(?!.*`.*|.*<\/code>.*))"
+    };
+    line = std::regex_replace(line, reAsterisk, "<strong>$1</strong>");
+    line = std::regex_replace(line, reUnderscore, "$1<strong>$2</strong>$3");
   }
 }; // class StrongParser
 

tests/maddy/test_maddy_emphasizedparser.cpp

@@ -21,6 +21,121 @@ TEST(MADDY_EMPHASIZEDPARSER, ItReplacesMarkdownWithEmphasizedHTML)
   ASSERT_EQ(expected, text);
 }
 
+TEST(MADDY_EMPHASIZEDPARSER, ItReplacesUnderscoresAtStringEdges)
+{
+  std::string text = "_some text_";
+  std::string expected = "<em>some text</em>";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItDoesNotReplaceMarkdownWithInlineUnderscores)
+{
+  std::string text = "some text_bla_text testing _it_ out";
+  std::string expected = "some text_bla_text testing <em>it</em> out";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItOnlyReplacesUnderscoresAtWordBreaks)
+{
+  std::string text = "some _text_bla_ testing _it_ out";
+  std::string expected = "some <em>text_bla</em> testing <em>it</em> out";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItReplacesUnderscoresWithMultipleWords)
+{
+  std::string text = "some _text testing it_ out";
+  std::string expected = "some <em>text testing it</em> out";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItAllowsDoubleUnderscores)
+{
+  // Per CommonMark, a leftover delimiter from an unbalanced run renders
+  // outside the tag it didn't pair into, not inside it.
+  std::string text = "some __text testing it_ out";
+  std::string expected = "some _<em>text testing it</em> out";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItAllowsTrailingDoubleUnderscores)
+{
+  std::string text = "some _text testing it__ out";
+  std::string expected = "some <em>text testing it</em>_ out";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItAllowsManyLeadingLeftoverUnderscores)
+{
+  std::string text = "some ____text testing it_ out";
+  std::string expected = "some ___<em>text testing it</em> out";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItAllowsManyTrailingLeftoverUnderscores)
+{
+  std::string text = "some _text testing it____ out";
+  std::string expected = "some <em>text testing it</em>___ out";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItDoesntReplaceUnderscoresInsideCodeBlocks)
+{
+  std::string text =
+    "Stuff inside <code> blocks _shouldn't be emphasized_ </code> at all";
+  std::string expected =
+    "Stuff inside <code> blocks _shouldn't be emphasized_ </code> at all";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItDoesNotReplaceUnderscoresInURLs)
+{
+  std::string text = "[Link Title](http://example.com/what_you_didn't_know)";
+  std::string expected =
+    "[Link Title](http://example.com/what_you_didn't_know)";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
 TEST(MADDY_EMPHASIZEDPARSER, ItDoesNotParseInsideInlineCode)
 {
   std::string text = "some text `*bla*` `/**text*/` testing _it_ out";
@@ -32,3 +147,33 @@ TEST(MADDY_EMPHASIZEDPARSER, ItDoesNotParseInsideInlineCode)
 
   ASSERT_EQ(expected, text);
 }
+
+TEST(MADDY_EMPHASIZEDPARSER, ItParsesOutsideCodeBlocks)
+{
+  std::string text =
+    "Stuff inside <code> blocks _shouldn't be emphasized_ </code>"
+    " but outside _should_.";
+  std::string expected =
+    "Stuff inside <code> blocks _shouldn't be emphasized_ </code>"
+    " but outside <em>should</em>.";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}
+
+TEST(MADDY_EMPHASIZEDPARSER, ItParsesOutsideTickBlocks)
+{
+  std::string text =
+    "Stuff inside `blocks _shouldn't be emphasized_ `"
+    " but outside _should_.";
+  std::string expected =
+    "Stuff inside `blocks _shouldn't be emphasized_ `"
+    " but outside <em>should</em>.";
+  auto emphasizedParser = std::make_shared<maddy::EmphasizedParser>();
+
+  emphasizedParser->Parse(text);
+
+  ASSERT_EQ(expected, text);
+}