Docs: improve discoverability of image compression (#5675)

### What
We often talk to customers that are unaware that we support logging
encoded/compressed images.
So I added some docs for this (in 3096c17).

This became a 🐰🕳️ because the doc tags (`\py` etc) didn't work as
expected: they would put all language-specific stuff _at the end_, but
in this case I wanted it interleaved into the rest of the docs. So I
fixed that, with a lot of effort.
Now `\cpp`, `\py`, `\rs` acts like a simple per-line filter.

In the meantime I removed some unused code, making everything shorter in
the process.

### Checklist
* [x] I have read and agree to [Contributor
Guide](https://github.com/rerun-io/rerun/blob/main/CONTRIBUTING.md) and
the [Code of
Conduct](https://github.com/rerun-io/rerun/blob/main/CODE_OF_CONDUCT.md)
* [x] I've included a screenshot or gif (if applicable)
* [x] I have tested the web demo (if applicable):
* Using newly built examples:
[app.rerun.io](https://app.rerun.io/pr/5675/index.html)
* Using examples from latest `main` build:
[app.rerun.io](https://app.rerun.io/pr/5675/index.html?manifest_url=https://app.rerun.io/version/main/examples_manifest.json)
* Using full set of examples from `nightly` build:
[app.rerun.io](https://app.rerun.io/pr/5675/index.html?manifest_url=https://app.rerun.io/version/nightly/examples_manifest.json)
* [x] The PR title and labels are set such as to maximize their
usefulness for the next release's CHANGELOG
* [x] If applicable, add a new check to the [release
checklist](https://github.com/rerun-io/rerun/blob/main/tests/python/release_checklist)!

- [PR Build Summary](https://build.rerun.io/pr/5675)
- [Docs
preview](https://rerun.io/preview/5e9c4730e352b2fa9ed32406937e317552387660/docs)
<!--DOCS-PREVIEW-->
- [Examples
preview](https://rerun.io/preview/5e9c4730e352b2fa9ed32406937e317552387660/examples)
<!--EXAMPLES-PREVIEW-->
- [Recent benchmark results](https://build.rerun.io/graphs/crates.html)
- [Wasm size tracking](https://build.rerun.io/graphs/sizes.html)

crates/re_types/definitions/rerun/archetypes/image.fbs

@@ -16,10 +16,16 @@ namespace rerun.archetypes;
 /// Leading and trailing unit-dimensions are ignored, so that
 /// `1x640x480x3x1` is treated as a `640x480x3` RGB image.
 ///
+/// Rerun also supports compressed image encoded as JPEG, N12, and YUY2.
+/// Using these formats can save a lot of bandwidth and memory.
+/// \py To compress an image, use [`rerun.Image.compress`][].
+/// \py To pass in an already encoded image, use  [`rerun.ImageEncoded`][].
+/// \rs See [`crate::components::TensorData`] for more.
+/// \cpp See [`rerun::datatypes::TensorBuffer`] for more.
+///
 /// \cpp Since the underlying `rerun::datatypes::TensorData` uses `rerun::Collection` internally,
 /// \cpp data can be passed in without a copy from raw pointers or by reference from `std::vector`/`std::array`/c-arrays.
 /// \cpp If needed, this "borrow-behavior" can be extended by defining your own `rerun::CollectionAdapter`.
-/// \python For an easy way to pass in image formats or encoded images, see [`rerun.ImageEncoded`][].
 ///
 /// \example image_simple image="https://static.rerun.io/image_simple/06ba7f8582acc1ffb42a7fd0006fad7816f3e4e4/1200w.png"
 table Image (

crates/re_types/definitions/rerun/archetypes/points2d.fbs

@@ -28,8 +28,8 @@ table Points2D (
 
   /// Optional colors for the points.
   ///
-  /// \python The colors are interpreted as RGB or RGBA in sRGB gamma-space,
-  /// \python As either 0-1 floats or 0-255 integers, with separate alpha.
+  /// \py The colors are interpreted as RGB or RGBA in sRGB gamma-space,
+  /// \py As either 0-1 floats or 0-255 integers, with separate alpha.
   colors: [rerun.components.Color] ("attr.rerun.component_recommended", nullable, order: 2100);
 
   // --- Optional ---

crates/re_types/definitions/rerun/archetypes/points3d.fbs

@@ -26,8 +26,8 @@ table Points3D (
 
   /// Optional colors for the points.
   ///
-  /// \python The colors are interpreted as RGB or RGBA in sRGB gamma-space,
-  /// \python As either 0-1 floats or 0-255 integers, with separate alpha.
+  /// \py The colors are interpreted as RGB or RGBA in sRGB gamma-space,
+  /// \py As either 0-1 floats or 0-255 integers, with separate alpha.
   colors: [rerun.components.Color] ("attr.rerun.component_recommended", nullable, order: 2100);
 
   // --- Optional ---

crates/re_types/definitions/rerun/datatypes/tensor_buffer.fbs

@@ -110,7 +110,7 @@ union TensorBuffer (
   /// First comes entire image in Y, followed by interleaved lines ordered as U0, V0, U1, V1, etc.
   NV12: NV12Buffer (transparent),
 
-  /// YUY2, also known as YUYV is a YUV 4:2:2 chrome downsampled format with 8 bits per channel.
+  /// YUY2, also known as YUYV is a YUV 4:2:2 chroma downsampled format with 8 bits per channel.
   ///
   /// The order of the channels is Y0, U0, Y1, V0.
   YUY2: YUY2Buffer (transparent),

crates/re_types_builder/src/codegen/common.rs

@@ -12,35 +12,6 @@ fn is_blank<T: AsRef<str>>(line: T) -> bool {
     line.as_ref().chars().all(char::is_whitespace)
 }
 
-/// Retrieves the global and tagged documentation from a [`Docs`] object.
-pub fn get_documentation(docs: &Docs, tags: &[&str]) -> Vec<String> {
-    let mut lines = docs.doc.clone();
-
-    for tag in tags {
-        lines.extend(
-            docs.tagged_docs
-                .get(*tag)
-                .unwrap_or(&Vec::new())
-                .iter()
-                .cloned(),
-        );
-    }
-
-    // NOTE: remove duplicated blank lines.
-    lines.dedup();
-
-    // NOTE: remove trailing blank lines.
-    while let Some(line) = lines.last() {
-        if line.is_empty() {
-            lines.pop();
-        } else {
-            break;
-        }
-    }
-
-    lines
-}
-
 #[derive(Clone)]
 pub struct ExampleInfo<'a> {
     /// The snake_case name of the example.
@@ -60,66 +31,62 @@ pub struct ExampleInfo<'a> {
 
 impl<'a> ExampleInfo<'a> {
     /// Parses e.g.  `// \example example_name title="Example Title" image="https://www.example.com/img.png"`
-    pub fn parse(tag_content: &'a impl AsRef<str>) -> Self {
-        fn mono(tag_content: &str) -> ExampleInfo<'_> {
-            fn find_keyed<'a>(tag: &str, args: &'a str) -> Option<&'a str> {
-                let mut prev_end = 0;
-                loop {
-                    if prev_end + tag.len() + "=\"\"".len() >= args.len() {
-                        return None;
-                    }
-                    let key_start = prev_end + args[prev_end..].find(tag)?;
-                    let key_end = key_start + tag.len();
-                    if !args[key_end..].starts_with("=\"") {
-                        prev_end = key_end;
-                        continue;
-                    };
-                    let value_start = key_end + "=\"".len();
-                    let Some(mut value_end) = args[value_start..].find('"') else {
-                        prev_end = value_start;
-                        continue;
-                    };
-                    value_end += value_start;
-                    return Some(&args[value_start..value_end]);
+    pub fn parse(tag_content: &'a str) -> Self {
+        fn find_keyed<'a>(tag: &str, args: &'a str) -> Option<&'a str> {
+            let mut prev_end = 0;
+            loop {
+                if prev_end + tag.len() + "=\"\"".len() >= args.len() {
+                    return None;
                 }
+                let key_start = prev_end + args[prev_end..].find(tag)?;
+                let key_end = key_start + tag.len();
+                if !args[key_end..].starts_with("=\"") {
+                    prev_end = key_end;
+                    continue;
+                };
+                let value_start = key_end + "=\"".len();
+                let Some(mut value_end) = args[value_start..].find('"') else {
+                    prev_end = value_start;
+                    continue;
+                };
+                value_end += value_start;
+                return Some(&args[value_start..value_end]);
             }
+        }
 
-            let tag_content = tag_content.trim();
-            let (name, args) = tag_content
-                .split_once(' ')
-                .map_or((tag_content, None), |(a, b)| (a, Some(b)));
-
-            let (mut title, mut image, mut exclude_from_api_docs) = (None, None, false);
+        let tag_content = tag_content.trim();
+        let (name, args) = tag_content
+            .split_once(' ')
+            .map_or((tag_content, None), |(a, b)| (a, Some(b)));
 
-            if let Some(args) = args {
-                let args = args.trim();
+        let (mut title, mut image, mut exclude_from_api_docs) = (None, None, false);
 
-                exclude_from_api_docs = args.contains("!api");
-                let args = if let Some(args_without_api_prefix) = args.strip_prefix("!api") {
-                    args_without_api_prefix.trim()
-                } else {
-                    args
-                };
+        if let Some(args) = args {
+            let args = args.trim();
 
-                if args.starts_with('"') {
-                    // \example example_name "Example Title"
-                    title = args.strip_prefix('"').and_then(|v| v.strip_suffix('"'));
-                } else {
-                    // \example example_name title="Example Title" image="https://static.rerun.io/annotation_context_rects/9b446c36011ed30fce7dc6ed03d5fd9557460f70/1200w.png"
-                    title = find_keyed("title", args);
-                    image = find_keyed("image", args).map(ImageUrl::parse);
-                }
-            }
+            exclude_from_api_docs = args.contains("!api");
+            let args = if let Some(args_without_api_prefix) = args.strip_prefix("!api") {
+                args_without_api_prefix.trim()
+            } else {
+                args
+            };
 
-            ExampleInfo {
-                name,
-                title,
-                image,
-                exclude_from_api_docs,
+            if args.starts_with('"') {
+                // \example example_name "Example Title"
+                title = args.strip_prefix('"').and_then(|v| v.strip_suffix('"'));
+            } else {
+                // \example example_name title="Example Title" image="https://static.rerun.io/annotation_context_rects/9b446c36011ed30fce7dc6ed03d5fd9557460f70/1200w.png"
+                title = find_keyed("title", args);
+                image = find_keyed("image", args).map(ImageUrl::parse);
             }
         }
 
-        mono(tag_content.as_ref())
+        ExampleInfo {
+            name,
+            title,
+            image,
+            exclude_from_api_docs,
+        }
     }
 }
 
@@ -314,46 +281,41 @@ pub fn collect_snippets_for_api_docs<'a>(
     extension: &str,
     required: bool,
 ) -> anyhow::Result<Vec<Example<'a>>> {
-    let mut out = Vec::new();
+    let base_path = crate::rerun_workspace_path().join("docs/snippets/all");
 
-    if let Some(examples) = docs.tagged_docs.get("example") {
-        let base_path = crate::rerun_workspace_path().join("docs/snippets/all");
+    let examples: Vec<&'a str> = docs.doc_lines_tagged("example");
 
-        for base @ ExampleInfo {
-            name,
-            exclude_from_api_docs,
-            ..
-        } in examples.iter().map(ExampleInfo::parse)
-        {
-            if exclude_from_api_docs {
-                continue;
-            }
+    let mut out: Vec<Example<'a>> = Vec::new();
 
-            let path = base_path.join(format!("{name}.{extension}"));
-            let content = match std::fs::read_to_string(&path) {
-                Ok(content) => content,
-                Err(_) if !required => continue,
-                Err(err) => {
-                    return Err(err).with_context(|| format!("couldn't open snippet {path:?}"))
-                }
-            };
-            let mut content = content
-                .split('\n')
-                .map(String::from)
-                .skip_while(|line| line.starts_with("//") || line.starts_with(r#"""""#)) // Skip leading comments.
-                .skip_while(|line| line.trim().is_empty()) // Strip leading empty lines.
-                .collect_vec();
-
-            // trim trailing blank lines
-            while content.last().is_some_and(is_blank) {
-                content.pop();
-            }
+    for example in &examples {
+        let base: ExampleInfo<'a> = ExampleInfo::parse(example);
+        let name = &base.name;
+        if base.exclude_from_api_docs {
+            continue;
+        }
 
-            out.push(Example {
-                base,
-                lines: content,
-            });
+        let path = base_path.join(format!("{name}.{extension}"));
+        let content = match std::fs::read_to_string(&path) {
+            Ok(content) => content,
+            Err(_) if !required => continue,
+            Err(err) => return Err(err).with_context(|| format!("couldn't open snippet {path:?}")),
+        };
+        let mut content = content
+            .split('\n')
+            .map(String::from)
+            .skip_while(|line| line.starts_with("//") || line.starts_with(r#"""""#)) // Skip leading comments.
+            .skip_while(|line| line.trim().is_empty()) // Strip leading empty lines.
+            .collect_vec();
+
+        // trim trailing blank lines
+        while content.last().is_some_and(is_blank) {
+            content.pop();
         }
+
+        out.push(Example {
+            base,
+            lines: content,
+        });
     }
 
     Ok(out)

crates/re_types_builder/src/codegen/cpp/mod.rs

@@ -2265,7 +2265,7 @@ fn quote_field_docs(field: &ObjectField) -> TokenStream {
 }
 
 fn lines_from_docs(docs: &Docs) -> Vec<String> {
-    let mut lines = crate::codegen::get_documentation(docs, &["cpp", "c++"]);
+    let mut lines = docs.doc_lines_for_untagged_and("cpp");
 
     let required = true;
     let examples = collect_snippets_for_api_docs(docs, "cpp", required).unwrap_or_default();

crates/re_types_builder/src/codegen/docs/mod.rs

@@ -9,8 +9,6 @@ use crate::{
 
 type ObjectMap = std::collections::BTreeMap<String, Object>;
 
-use super::common::get_documentation;
-
 macro_rules! putln {
     ($o:ident) => ( writeln!($o).ok() );
     ($o:ident, $($tt:tt)*) => ( writeln!($o, $($tt)*).ok() );
@@ -143,19 +141,16 @@ fn index_page(kind: ObjectKind, order: u64, prelude: &str, objects: &[&Object])
 fn object_page(reporter: &Reporter, object: &Object, object_map: &ObjectMap) -> String {
     let is_unreleased = object.is_attr_set(crate::ATTR_DOCS_UNRELEASED);
 
-    let top_level_docs = get_documentation(&object.docs, &[]);
+    let top_level_docs = object.docs.untagged();
 
     if top_level_docs.is_empty() {
         reporter.error(&object.virtpath, &object.fqname, "Undocumented object");
     }
 
-    let examples = object
-        .docs
-        .tagged_docs
-        .get("example")
+    let examples = &object.docs.doc_lines_tagged("example");
+    let examples = examples
         .iter()
-        .flat_map(|v| v.iter())
-        .map(ExampleInfo::parse)
+        .map(|line| ExampleInfo::parse(line))
         .collect::<Vec<_>>();
 
     let mut page = String::new();

crates/re_types_builder/src/codegen/mod.rs

@@ -32,7 +32,7 @@ pub(crate) use macros::autogen_warning; // Hack for declaring macros as `pub(cra
 // ---
 
 pub(crate) mod common;
-use self::common::{get_documentation, StringExt};
+use self::common::StringExt;
 
 mod cpp;
 mod docs;

crates/re_types_builder/src/codegen/python/mod.rs

@@ -1157,7 +1157,7 @@ fn quote_obj_docs(obj: &Object) -> String {
 }
 
 fn lines_from_docs(docs: &Docs) -> Vec<String> {
-    let mut lines = crate::codegen::get_documentation(docs, &["py", "python"]);
+    let mut lines = docs.doc_lines_for_untagged_and("py");
 
     let examples = collect_snippets_for_api_docs(docs, "py", true).unwrap();
     if !examples.is_empty() {
@@ -1208,7 +1208,7 @@ fn quote_doc_from_fields(objects: &Objects, fields: &Vec<ObjectField>) -> String
     let mut lines = vec!["Must be one of:".to_owned(), String::new()];
 
     for field in fields {
-        let mut content = crate::codegen::get_documentation(&field.docs, &["py", "python"]);
+        let mut content = field.docs.doc_lines_for_untagged_and("py");
         for line in &mut content {
             if line.starts_with(char::is_whitespace) {
                 line.remove(0);
@@ -1250,7 +1250,7 @@ fn quote_union_kind_from_fields(fields: &Vec<ObjectField>) -> String {
     let mut lines = vec!["Possible values:".to_owned(), String::new()];
 
     for field in fields {
-        let mut content = crate::codegen::get_documentation(&field.docs, &["py", "python"]);
+        let mut content = field.docs.doc_lines_for_untagged_and("py");
         for line in &mut content {
             if line.starts_with(char::is_whitespace) {
                 line.remove(0);
@@ -1950,7 +1950,8 @@ fn quote_init_method(
         obj.fields
             .iter()
             .filter_map(|field| {
-                if field.docs.doc.is_empty() {
+                let doc_content = field.docs.doc_lines_for_untagged_and("py");
+                if doc_content.is_empty() {
                     if !field.is_testing() && obj.fields.len() > 1 {
                         reporter.error(
                             &field.virtpath,
@@ -1960,8 +1961,6 @@ fn quote_init_method(
                     }
                     None
                 } else {
-                    let doc_content =
-                        crate::codegen::get_documentation(&field.docs, &["py", "python"]);
                     Some(format!(
                         "{}:\n    {}",
                         field.name,