selma 0.4.6 → 0.4.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 704b9ef380d21adb07f72fcaf0dda936158514932d9e034f0e5b58ec44ff2e68
-  data.tar.gz: 3c7155aef5f4be4a08c9fd517f8ea1223431431e95baefa885851a77e1b129bd
+  metadata.gz: 04f8ef6623b5a28c62d64f3077842e262321580e998e90ba458735e5d7a13395
+  data.tar.gz: 132e7e538f36ad7399fb6edb7c09ece5fb16a9bd94da3a3a18339c0ad4057888
 SHA512:
-  metadata.gz: '01719b4c1679e91655fc3b29c8923b2bfcbc64e1633867a11bf53242849b75f5013068feaf59affc5c0cd7aee9d799bc6e4b44fd40eadfe0b301ba7607069fae'
-  data.tar.gz: 986c81e769ff2aa1a648e1d428c139d9f5dee1e716ca9b67764ca7ec7cba12846bf1fa2df0e22d573263d053e34a0e707bf2bca0f35c4e8ad173a829d6036b5b
+  metadata.gz: 06a3709aed3c7793b4010174866d4866bedd848cd2e2ca1553dff603e21790c8982d79a0ba72b6c2c5668639da76efd745aff2fbfe496442bbbb5c14cdf0a431
+  data.tar.gz: 86a393c4df2090cdba7f75001ebb81f9262c3f65e9fc897bc5d6fa6a8147e3f37e97118f7787fac22acd86baa241ba3b934e42062df1888e774c768cf3a24729

data/Cargo.lock

@@ -426,12 +426,11 @@ dependencies = [
 
 [[package]]
 name = "ppv-lite86"
-version = "0.2.19"
+version = "0.2.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2288c0e17cc8d342c712bb43a257a80ebffce59cdb33d5000d8348f3ec02528b"
+checksum = "77957b295656769bb8ad2b6a6b09d897d94f05c41b069aede1fcdaa675eaea04"
 dependencies = [
  "zerocopy",
- "zerocopy-derive",
 ]
 
 [[package]]
@@ -517,18 +516,18 @@ dependencies = [
 
 [[package]]
 name = "rb-sys"
-version = "0.9.99"
+version = "0.9.101"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d83151cfea2b67db2444f68c53b119ff77cff235ad711c765072e4daf8f3185b"
+checksum = "1ba2704ccfa7875c91792c57a9aa7c3caac524d3036c122e36eeddad6f6e7c6f"
 dependencies = [
  "rb-sys-build",
 ]
 
 [[package]]
 name = "rb-sys-build"
-version = "0.9.99"
+version = "0.9.101"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "32d038214c118ad4a75db555ccb78672e17e1c5c10f344456cd129008dbaa7de"
+checksum = "c73585ec80c217b7a81257ca9bb89b191b5e452ec4b9106dc4c2e4e96a822242"
 dependencies = [
  "bindgen",
  "lazy_static",
@@ -547,9 +546,9 @@ checksum = "a35802679f07360454b418a5d1735c89716bde01d35b1560fc953c1415a0b3bb"
 
 [[package]]
 name = "regex"
-version = "1.10.5"
+version = "1.10.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b91213439dad192326a0d7c6ee3955910425f441d7038e0d6933b0aec5c4517f"
+checksum = "4219d74c6b67a3654a9fbebc4b419e22126d13d2f3c4a07ee0cb61ff79a79619"
 dependencies = [
  "aho-corasick",
  "memchr",

data/ext/selma/src/html/text_chunk.rs

@@ -6,6 +6,26 @@ use magnus::{exception, method, Error, Module, RClass, Symbol, Value};
 
 struct HTMLTextChunk {
     text_chunk: NativeRefWrap<TextChunk<'static>>,
+    buffer: String,
+}
+
+macro_rules! clone_buffer_if_not_empty {
+    ($binding:expr, $buffer:expr) => {
+        if !$binding.buffer.is_empty() {
+            $buffer.clone_from(&$binding.buffer);
+        }
+    };
+}
+
+// if this is the first time we're processing this text chunk (buffer is empty),
+// we carry on. Otherwise, we need to use the buffer text, not the text chunk,
+// because lol-html is not designed in such a way to keep track of text chunks.
+macro_rules! set_text_chunk_to_buffer {
+    ($text_chunk:expr, $buffer:expr) => {
+        if !$buffer.is_empty() {
+            $text_chunk.set_str($buffer);
+        }
+    };
 }
 
 #[magnus::wrap(class = "Selma::HTML::TextChunk")]
@@ -18,6 +38,7 @@ impl SelmaHTMLTextChunk {
     pub fn new(ref_wrap: NativeRefWrap<TextChunk<'static>>) -> Self {
         Self(RefCell::new(HTMLTextChunk {
             text_chunk: ref_wrap,
+            buffer: String::new(),
         }))
     }
 
@@ -96,16 +117,25 @@ impl SelmaHTMLTextChunk {
 
     fn replace(&self, args: &[Value]) -> Result<String, Error> {
         let mut binding = self.0.borrow_mut();
+        let mut buffer = String::new();
+
+        clone_buffer_if_not_empty!(binding, buffer);
+
         let text_chunk = binding.text_chunk.get_mut().unwrap();
 
+        set_text_chunk_to_buffer!(text_chunk, buffer);
+
         let (text_str, content_type) = match crate::scan_text_args(args) {
             Ok((text_str, content_type)) => (text_str, content_type),
             Err(err) => return Err(err),
         };
-
         text_chunk.replace(&text_str, content_type);
 
-        Ok(text_chunk.as_str().to_string())
+        text_chunk.set_str(text_str.clone());
+
+        binding.buffer = text_chunk.as_str().to_string();
+
+        Ok(text_str)
     }
 }
 

data/ext/selma/src/rewriter.rs

@@ -540,7 +540,8 @@ impl SelmaRewriter {
         // prevents missing `handle_text_chunk` function
         let content = text_chunk.as_str();
 
-        // seems that sometimes lol-html returns blank text / EOLs?
+        // lol-html sometimes returns blank text if
+        // last_in_text_node() is true
         if content.is_empty() {
             return Ok(());
         }

data/lib/selma/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Selma
-  VERSION = "0.4.6"
+  VERSION = "0.4.7"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: selma
 version: !ruby/object:Gem::Version
-  version: 0.4.6
+  version: 0.4.7
 platform: ruby
 authors:
 - Garen J. Torikian
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-08-04 00:00:00.000000000 Z
+date: 2024-08-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys