From 349e18c4072e3dc8cd715664ea586327ec0dddbe Mon Sep 17 00:00:00 2001
From: Mikko Ahlroth <mikko@ahlroth.fi>
Date: Sun, 28 May 2023 17:19:30 +0300
Subject: [PATCH] Add HTMLBody encoding mode that doesn't encode quite so many
 characters

---
 CHANGELOG                  |  5 ++++
 README.md                  |  9 +++----
 gleam.toml                 |  2 +-
 src/glentities.gleam       | 49 +++++++++++++++++++++++++++++++-------
 test/glentities_test.gleam | 10 ++++++++
 5 files changed, 61 insertions(+), 14 deletions(-)

diff --git a/CHANGELOG b/CHANGELOG
index f05d930..79ac0e6 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -1,3 +1,8 @@
+3.1.0
+-----
+
+* Add "HTMLBody" encoding mode that doesn't encode everything.
+
 3.0.0
 -----
 
diff --git a/README.md b/README.md
index fca547e..e40be53 100644
--- a/README.md
+++ b/README.md
@@ -12,11 +12,12 @@ Entities can be encoded using named or hex entity references. Named entity refer
 ```gleam
 import glentities
 
-glentities.encode("</html>", glentities.Named) // "&lt;&sol;html&gt;"
-glentities.encode("</html>", glentities.Hex)   // "&#x3C;&#x2F;html&#x3E;"
+glentities.encode("</html>", glentities.HTMLBody) // "&lt;/html&gt;"
+glentities.encode("</html>", glentities.Named)    // "&lt;&sol;html&gt;"
+glentities.encode("</html>", glentities.Hex)      // "&#x3C;&#x2F;html&#x3E;"
 
-glentities.decode("&#x3C;&#x2F;html&#x3E;")    // "</html>"
-glentities.decode("&lt;&sol;html&gt;")         // "</html>"
+glentities.decode("&#x3C;&#x2F;html&#x3E;")       // "</html>"
+glentities.decode("&lt;&sol;html&gt;")            // "</html>"
 ```
 
 ## Development
diff --git a/gleam.toml b/gleam.toml
index 830a5b6..0c23e68 100644
--- a/gleam.toml
+++ b/gleam.toml
@@ -1,5 +1,5 @@
 name = "glentities"
-version = "3.0.0"
+version = "3.1.0"
 description = "HTML entity encoder/decoder for Gleam"
 
 # Fill out these fields if you intend to generate HTML documentation or publish
diff --git a/src/glentities.gleam b/src/glentities.gleam
index 57366b1..b97e2c2 100644
--- a/src/glentities.gleam
+++ b/src/glentities.gleam
@@ -10,6 +10,13 @@ pub type EncodeMode {
 
   /// Encode all characters using hex entities, except a-z, A-Z, 0-9, newline, tab, carriage return, and space.
   Hex
+
+  /// Encode only the necessary characters when the output target is HTML element or attribute content.
+  ///
+  /// This means `&`, `<`, `>`, `'`, and `"`.
+  ///
+  /// Note! Not suitable for outputting inside `<style>`, `<script>` elements.
+  HTMLBody
 }
 
 /// Decode any HTML entities in the given string.
@@ -2294,6 +2301,7 @@ pub fn encode(text: String, mode: EncodeMode) {
   case mode {
     Named -> encode_named(input, string_builder.new())
     Hex -> encode_hex(input)
+    HTMLBody -> encode_html_body(input, string_builder.new())
   }
 }
 
@@ -2311,7 +2319,24 @@ pub fn encode_hex(text: String) {
   |> string.join("")
 }
 
-/// Encoded text using named HTML entities, except newline and tab. Characters without a named entity are untouched.
+/// Encode text to be safe in the HTML body, inside element or attribute content.
+///
+/// `&`, `<`, `>`, `'`, and `"` are encoded.
+///
+/// Note! Not suitable for outputting inside `<style>`, `<script>` elements.
+pub fn encode_html_body(text: String, acc: StringBuilder) -> String {
+  case text {
+    "" -> string_builder.to_string(acc)
+    "&" <> rest -> encode_html_body(rest, string_builder.append(acc, "&amp;"))
+    "<" <> rest -> encode_html_body(rest, string_builder.append(acc, "&lt;"))
+    ">" <> rest -> encode_html_body(rest, string_builder.append(acc, "&gt;"))
+    "\"" <> rest -> encode_html_body(rest, string_builder.append(acc, "&quot;"))
+    "'" <> rest -> encode_html_body(rest, string_builder.append(acc, "&#39;"))
+    other -> encode_other_case(other, acc, encode_html_body)
+  }
+}
+
+/// Encode text using named HTML entities, except newline and tab. Characters without a named entity are untouched.
 pub fn encode_named(text: String, acc: StringBuilder) -> String {
   case text {
     "" -> string_builder.to_string(acc)
@@ -4049,13 +4074,19 @@ pub fn encode_named(text: String, acc: StringBuilder) -> String {
     "𝓏" <> rest -> encode_named(rest, string_builder.append(acc, "&zscr;"))
     "‍" <> rest -> encode_named(rest, string_builder.append(acc, "&zwj;"))
     "‌" <> rest -> encode_named(rest, string_builder.append(acc, "&zwnj;"))
-    _other -> {
-      let maybe_grapheme = string.pop_grapheme(text)
-      case maybe_grapheme {
-        Ok(#(grapheme, rest)) ->
-          encode_named(rest, string_builder.append(acc, grapheme))
-        Error(Nil) -> string_builder.to_string(acc)
-      }
-    }
+    other -> encode_other_case(other, acc, encode_named)
+  }
+}
+
+fn encode_other_case(
+  text: String,
+  acc: StringBuilder,
+  continue_callback: fn(String, StringBuilder) -> String,
+) -> String {
+  let maybe_grapheme = string.pop_grapheme(text)
+  case maybe_grapheme {
+    Ok(#(grapheme, rest)) ->
+      continue_callback(rest, string_builder.append(acc, grapheme))
+    Error(Nil) -> string_builder.to_string(acc)
   }
 }
diff --git a/test/glentities_test.gleam b/test/glentities_test.gleam
index c172875..852a629 100644
--- a/test/glentities_test.gleam
+++ b/test/glentities_test.gleam
@@ -37,6 +37,16 @@ pub fn encode_hex_test() {
   )
 }
 
+pub fn encode_html_body_test() {
+  let input =
+    "This &amp 'string' contains    many Θ \"encoded\" <characters>. ☃"
+
+  should.equal(
+    glentities.encode(input, glentities.HTMLBody),
+    "This &amp;amp &#39;string&#39; contains    many Θ &quot;encoded&quot; &lt;characters&gt;. ☃",
+  )
+}
+
 pub fn roundtrip_named_test() {
   let input =
     string_utils.normalise(