add support for streaming stdin changes

Cargo.lock

@@ -2,6 +2,15 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "aho-corasick"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "anstream"
 version = "0.6.13"
@@ -126,6 +135,7 @@ dependencies = [
 name = "gerrit-filter-branch"
 version = "0.1.0"
 dependencies = [
+ "aho-corasick",
  "clap",
  "git2",
 ]
@@ -222,6 +232,12 @@ version = "0.4.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
 
+[[package]]
+name = "memchr"
+version = "2.7.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c8640c5d730cb13ebd907d8d04b52f55ac9a2eec55b440c8892f40d56c76c1d"
+
 [[package]]
 name = "once_cell"
 version = "1.19.0"

Cargo.toml

@@ -6,5 +6,6 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+aho-corasick = "1.1.3"
 clap = { version = "4.5.4", features = ["derive"] }
 git2 = "0.18.3"

src/main.rs

@@ -1,5 +1,9 @@
-use std::collections::{HashMap, HashSet};
+use std::{
+    collections::{HashMap, HashSet},
+    io::{stdin, stdout},
+};
 
+use aho_corasick::AhoCorasick;
 use clap::Parser;
 use git2::{Oid, Repository, Signature, Time};
 
@@ -25,6 +29,10 @@ struct Args {
     #[arg(short, long)]
     /// A timestamp (in seconds since the epoch) at which point commits should be considered unchanged, even if it or its parents have aforementioned email.
     cutoff: String,
+
+    #[arg(short, long)]
+    /// If the list of rewritten OIDs should be rewritten in the stdin stream, rather than the Git repo.
+    rewrite_stdin: bool,
 }
 
 struct State {
@@ -232,33 +240,51 @@ fn main() {
 
         let refoid = state.repo.find_reference(&gref).unwrap().target().unwrap();
         let newoid = state.rewrite(refoid);
-        if refoid != newoid {
+
-            println!("{:?}: {:?} -> {:?}", gref, refoid, newoid);
+        if !state.args.rewrite_stdin {
-            state
+            if refoid != newoid {
-                .repo
+                println!("{:?}: {:?} -> {:?}", gref, refoid, newoid);
-                .reference(&gref, newoid, true, "filter-branch rewrite")
+                state
-                .unwrap();
+                    .repo
-        } else {
+                    .reference(&gref, newoid, true, "filter-branch rewrite")
-            println!("{:?}: {:?} (unchanged)", gref, refoid);
+                    .unwrap();
+            } else {
+                println!("{:?}: {:?} (unchanged)", gref, refoid);
+            }
         }
     }
 
-    for gref in &refs {
+    if state.args.rewrite_stdin {
-        if !gref.ends_with("/meta") {
+        let data: Vec<_> = state
-            continue;
+            .rewritten
-        }
+            .iter()
+            .map(|f| (f.0.to_string(), f.1.to_string()))
+            .collect();
 
-        let refoid = state.repo.find_reference(&gref).unwrap().target().unwrap();
+        let to_replace: Vec<&[u8]> = data.iter().map(|f| f.1.as_bytes()).collect();
-        let newoid = state.rewrite_meta(refoid);
+        let matcher = AhoCorasick::new(data.iter().map(|f| f.0.as_bytes())).unwrap();
 
-        if refoid != newoid {
+        matcher
-            println!("{:?}: {:?} -> {:?}", gref, refoid, newoid);
+            .try_stream_replace_all(stdin().lock(), stdout().lock(), &to_replace[..])
-            state
+            .unwrap();
-                .repo
+    } else {
-                .reference(&gref, newoid, true, "filter-branch rewrite")
+        for gref in &refs {
-                .unwrap();
+            if !gref.ends_with("/meta") {
-        } else {
+                continue;
-            println!("{:?}: {:?} (unchanged)", gref, refoid);
+            }
+
+            let refoid = state.repo.find_reference(&gref).unwrap().target().unwrap();
+            let newoid = state.rewrite_meta(refoid);
+
+            if refoid != newoid {
+                println!("{:?}: {:?} -> {:?}", gref, refoid, newoid);
+                state
+                    .repo
+                    .reference(&gref, newoid, true, "filter-branch rewrite")
+                    .unwrap();
+            } else {
+                println!("{:?}: {:?} (unchanged)", gref, refoid);
+            }
         }
     }
 }