Added more parsers for escaped characters and links.

src/MdToHTML.hs

@@ -53,7 +53,7 @@ instance Show MdToken where
   show (OrdList tokens) = "ORD" ++ concatMap show tokens
   show (Code code) = show code
   show (Codeblock code) = show code
-  show (Link txt url) = "<a href=" ++ getUrl url ++ ">" ++ show txt ++ "</a>"
+  show (Link txt url) = "<a href=\"" ++ getUrl url ++ "\">" ++ show txt ++ "</a>"
   show (Image txt imgPath) = "<img src=" ++ getPath imgPath ++ ">" ++ show txt ++ "</img>"
   show (Bold token) = "<b>" ++ show token ++ "</b>"
   show (Italic token) = "<i>" ++ show token ++ "</i>"
@@ -83,6 +83,8 @@ lookaheadParse stringCmp = do
 lineToList :: MdToken -> [MdToken]
 lineToList (Line tokens) = tokens
 
+specialChars = "\\#*_[\n "
+
 -- ---------------
 
 -- Parse a markdown header, denoted by 1-6 #'s followed by some text, followed by EOL.
@@ -121,6 +123,14 @@ parseItalic = do
   let parsedText = fst $ leftmostLongestParse parseLine text
   return (Italic parsedText)
 
+-- Parse a link
+parseLink :: ReadP MdToken
+parseLink = do
+  linkText <- between (string "[") (string "]") (many1 get)
+  linkURL <- between (string "(") (string ")") (many1 get)
+  let parsedLinkText = fst $ leftmostLongestParse parseLine linkText
+  return $ Link parsedLinkText (URL linkURL)
+
 -- Parse a linebreak character
 parseLinebreak :: ReadP MdToken
 parseLinebreak = do
@@ -134,15 +144,30 @@ parseSingleNewline = do
   char '\n'
   return SingleNewline
 
+-- Parse an escaped character
+parseEscapedChar :: ReadP MdToken
+parseEscapedChar = do
+  char '\\'
+  escapedChar <- choice (map char specialChars)
+  return (Unit [escapedChar])
+
 -- Parse a regular string as a Unit.
 parseString :: ReadP MdToken
 parseString = do
   firstChar <- satisfy (/= '\n') -- Must parse at least one non-newline character here
-  text <- munch (`notElem` "#*_[\n ")
+  text <- munch (`notElem` specialChars)
   return (Unit (firstChar : text))
 
 lineParsers :: [ReadP MdToken]
-lineParsers = [parseLinebreak, parseSingleNewline, parseBold, parseItalic, parseString] -- A 'line' doesn't include a 'header'
+lineParsers =
+  [ parseLinebreak,
+    parseSingleNewline,
+    parseEscapedChar,
+    parseBold,
+    parseItalic,
+    parseLink,
+    parseString
+  ] -- A 'line' doesn't include a 'header'
 
 -- List of all parsers
 allParsers :: [ReadP MdToken]

src/Test.hs

@@ -26,19 +26,35 @@ boldTests =
       check_equal "Should convert bold and italic in a sentence" "<p>It <i>is</i> a <b>wonderful</b> day</p>" (convert "It _is_ a __wonderful__ day")
     ]
 
+linkTests =
+  TestList
+    [ check_equal "Should convert normal link" "<p><a href=\"https://example.com\">This is an example link.</a></p>" (convert "[This is an example link.](https://example.com)"),
+      check_equal "Should convert styled link" "<p><a href=\"https://example.com\"><b>Fancy</b>!!!</a></p>" (convert "[__Fancy__!!!](https://example.com)")
+    ]
+
+escapedCharTests =
+  TestList
+    [ check_equal "Should print literal underscore" "<p>This is an underscore - _</p>" (convert "This is an underscore - \\_"),
+      check_equal "Should print literal asterisk" "<p>This is an asterisk - *</p>" (convert "This is an asterisk - \\*"),
+      check_equal "Should print literal asterisk in bold" "<p>This is a bolded asterisk - <b>*</b></p>" (convert "This is a bolded asterisk - **\\***")
+    ]
+
 integrationTests =
   TestList
     [ check_equal "Integration 1" "<h1>Sample Markdown</h1><p>This is some basic, sample markdown.</p><h2><b>Second</b> <i>Heading</i></h2>" (convert "# Sample Markdown\n\n This is some basic, sample markdown.\n\n  ## __Second__ _Heading_"),
       check_equal "Integration 2" "<p><b>Hello</b> <i>World</i></p>" (convert "__Hello__\n_World_"),
       check_equal "Integration 3" "<h1>Hello</h1><p>World</p>" (convert "# Hello\nWorld"),
       check_equal "Integration 4" "<p>a b</p>" (convert "a\nb"),
-      check_equal "Integration 5" "<h1>Hello</h1>" (convert "# Hello\n")
+      check_equal "Integration 5" "<h1>Hello</h1>" (convert "# Hello\n"),
+      check_equal "Integration 6" "<p>First line<br>Second line</p>" (convert "First line  \nSecond line")
     ]
 
 tests =
   TestList
     [ headerTests,
       boldTests,
+      linkTests,
+      escapedCharTests,
       integrationTests
     ]