From e2c0acf1a7c44218550964412b452e1e95a367fd Mon Sep 17 00:00:00 2001
From: Ed Guloien <edgul@mozilla.com>
Date: Thu, 28 May 2026 10:11:07 -0400
Subject: [PATCH] init blob storage: added basic Blob and Range, testing wip

---
 .gitignore  |  1 +
 Cargo.lock  |  7 ++++
 Cargo.toml  |  6 ++++
 src/main.rs | 95 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 109 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 Cargo.lock
 create mode 100644 Cargo.toml
 create mode 100644 src/main.rs

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..ea8c4bf
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+/target
diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..f826051
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,7 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "blob-storage"
+version = "0.1.0"
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..612cd1e
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,6 @@
+[package]
+name = "blob-storage"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..f13262b
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,95 @@
+
+#[derive(PartialEq, Debug)]
+struct Range {
+    start: usize,
+    end: usize, // exclusive
+}
+
+impl Range {
+    pub fn contains(&self, index: usize) -> bool {
+        index >= self.start && index < self.end
+    }
+} 
+
+pub struct Blob {
+    bytes: Vec<u8>,
+    valid_ranges: Vec<Range>,
+}
+
+impl Blob {
+    pub fn new() -> Self { Self {bytes: Vec::new(), valid_ranges: Vec::new()} }
+
+    pub fn append(&mut self, input: &[u8]) {
+        self.bytes.extend_from_slice(input);
+
+        // we are appending so only have to check the last range
+        let new_range = Range {start: self.bytes.len(), end: self.bytes.len() + input.len()};
+        match self.valid_ranges.last_mut() {
+            Some(range) if range.contains(new_range.start) => range.end = new_range.end,
+            _ => self.valid_ranges.push(new_range),
+        }
+    }
+
+    // todo: better way to do the return type?
+    pub fn read(&mut self, start: usize, len: usize, output: &mut [u8]) {
+        assert!(len == output.len()); // todo: add error handling
+        let slice = &mut self.bytes[start..start+len];
+        slice.swap_with_slice(output);
+
+        // update the valid array
+        let clear_range = Range{ start: start, end: start + len };
+        for range in  self.valid_ranges.iter_mut() {
+            if range.contains(clear_range.start) {
+                range.end = clear_range.start; 
+            }
+            if range.contains(clear_range.end) {
+                range.start = clear_range.end;
+            }
+        }
+    }
+}
+
+fn main() {
+    println!("run cargo test instead")
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_range() {
+        let range = Range{start:0, end:3};
+        assert_eq!(range, range); // identity
+        
+        let range2 = Range{start:0, end:3};
+        assert_eq!(range, range2); // similar
+
+        // basic contains
+        assert!(range.contains(0));
+        assert!(range.contains(1));
+        assert!(range.contains(2));
+        assert!(!range.contains(3));
+        assert!(!range.contains(4));
+    }
+
+    #[test]
+    fn test_blob() {
+        let mut b = Blob::new();
+        b.append(&[b'a', b'b', b'c']);
+
+        let mut read = vec![0; 1];
+        b.read(0,1, &mut read);
+        // todo make some asserts
+        //assert!(&read, Vec<u8>::new([b'a']));
+        println!("blob (0,1): {}", str::from_utf8(&read).unwrap());
+
+        let mut read = vec![0; 1];
+        b.read(0,1, &mut read);
+        println!("blob (0,1) again: {}", str::from_utf8(&read).unwrap());
+
+        let mut read = vec![0; 2];
+        b.read(1,2, &mut read);
+        println!("blob (1,2) again: {}", str::from_utf8(&read).unwrap());
+    }
+}