read+discard on archive recursion

.vscode/launch.json

@@ -1,78 +1,84 @@
 {
-	// Use IntelliSense to learn about possible attributes.
-	// Hover to view descriptions of existing attributes.
-	// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
-	"version": "0.2.0",
-	"configurations": [
-		{
-			"type": "lldb",
-			"request": "launch",
-			"name": "Debug unit tests in library 'rga'",
-			"cargo": {
-				"args": ["test", "--no-run", "--lib", "--package=rga"],
-				"filter": {
-					"name": "rga",
-					"kind": "lib"
-				}
-			},
-			"args": [],
-			"cwd": "${workspaceFolder}"
-		},
-		{
-			"type": "lldb",
-			"request": "launch",
-			"name": "Debug executable 'rga'",
-			"cargo": {
-				"args": ["build", "--bin=rga", "--package=rga"],
-				"filter": {
-					"name": "rga",
-					"kind": "bin"
-				}
-			},
-			"args": [],
-			"cwd": "${workspaceFolder}"
-		},
-		{
-			"type": "lldb",
-			"request": "launch",
-			"name": "Debug unit tests in executable 'rga'",
-			"cargo": {
-				"args": ["test", "--no-run", "--bin=rga", "--package=rga"],
-				"filter": {
-					"name": "rga",
-					"kind": "bin"
-				}
-			},
-			"args": [],
-			"cwd": "${workspaceFolder}"
-		},
-		{
-			"type": "lldb",
-			"request": "launch",
-			"name": "Debug executable 'rga-preproc'",
-			"cargo": {
-				"args": ["build", "--bin=rga-preproc", "--package=rga"],
-				"filter": {
-					"name": "rga-preproc",
-					"kind": "bin"
-				}
-			},
-			"args": ["exampledir/short.pdf"],
-			"cwd": "${workspaceFolder}"
-		},
-		{
-			"type": "lldb",
-			"request": "launch",
-			"name": "Debug unit tests in executable 'rga-preproc'",
-			"cargo": {
-				"args": ["test", "--no-run", "--bin=rga-preproc", "--package=rga"],
-				"filter": {
-					"name": "rga-preproc",
-					"kind": "bin"
-				}
-			},
-			"args": [],
-			"cwd": "${workspaceFolder}"
-		}
-	]
+  // Use IntelliSense to learn about possible attributes.
+  // Hover to view descriptions of existing attributes.
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "type": "lldb",
+      "request": "attach",
+      "name": "Attach",
+      "program": "${workspaceFolder}/target/release/rga-preproc"
+    },
+    {
+      "type": "lldb",
+      "request": "launch",
+      "name": "Debug unit tests in library 'rga'",
+      "cargo": {
+        "args": ["test", "--no-run", "--lib", "--package=rga"],
+        "filter": {
+          "name": "rga",
+          "kind": "lib"
+        }
+      },
+      "args": [],
+      "cwd": "${workspaceFolder}"
+    },
+    {
+      "type": "lldb",
+      "request": "launch",
+      "name": "Debug executable 'rga'",
+      "cargo": {
+        "args": ["build", "--bin=rga"],
+        "filter": {
+          "name": "rga",
+          "kind": "bin"
+        }
+      },
+      "args": [],
+      "cwd": "${workspaceFolder}"
+    },
+    {
+      "type": "lldb",
+      "request": "launch",
+      "name": "Debug unit tests in executable 'rga'",
+      "cargo": {
+        "args": ["test", "--no-run", "--bin=rga", "--package=ripgrep-all"],
+        "filter": {
+          "name": "rga",
+          "kind": "bin"
+        }
+      },
+      "args": [],
+      "cwd": "${workspaceFolder}"
+    },
+    {
+      "type": "lldb",
+      "request": "launch",
+      "name": "Debug executable 'rga-preproc'",
+      "cargo": {
+        "args": ["build", "--bin=rga-preproc"],
+        "filter": {
+          "name": "rga-preproc",
+          "kind": "bin"
+        }
+      },
+      "args": ["exampledir/tar/test.tar.bz2"],
+      "cwd": "${workspaceFolder}"
+    },
+    {
+      "type": "lldb",
+      "request": "launch",
+      "name": "Debug unit tests in executable 'rga-preproc'",
+      "cargo": {
+        "args": ["test", "--no-run", "--bin=rga-preproc", "--package=rga"],
+        "filter": {
+          "name": "rga-preproc",
+          "kind": "bin"
+        }
+      },
+      "args": [],
+      "cwd": "${workspaceFolder}"
+    }
+  ]
 }

Cargo.toml

@@ -62,3 +62,7 @@ ctor = "0.2.0"
 pretty_assertions = "1.3.0"
 tempfile = "3.5.0"
 tokio-test = "0.4.2"
+
+[profile.release]
+debug = true
+split-debuginfo = "packed"

src/adapters/zip.rs

@@ -103,7 +103,9 @@ impl FileAdapter for ZipAdapter {
             let mut zip = ZipFileReader::new(inp);
 
             let s = stream! {
+                    trace!("begin zip");
                     while let Some(mut entry) = zip.next_entry().await? {
+                        trace!("zip next entry");
                         let file = entry.entry();
                         if file.filename().ends_with('/') {
                             zip = entry.skip().await?;
@@ -143,6 +145,7 @@ impl FileAdapter for ZipAdapter {
                         zip = entry.done().await.context("going to next file in zip but entry was not read fully")?;
 
                 }
+                trace!("zip over");
             };
 
             Ok(Box::pin(s))

src/caching_writer.rs

@@ -33,6 +33,7 @@ pub fn async_read_and_write_to_cache<'a>(
     let s = stream! {
         let mut stream = ReaderStream::new(inp);
         while let Some(bytes) = stream.next().await {
+            trace!("read bytes: {:?}", bytes);
             if let Ok(bytes) = &bytes {
                 if let Some(writer) = zstd_writer.as_mut() {
                     writer.write_all(bytes).await?;
@@ -48,14 +49,18 @@ pub fn async_read_and_write_to_cache<'a>(
             }
             yield bytes;
         }
+        trace!("eof");
         // EOF, call on_finish
         let finish = {
             if let Some(mut writer) = zstd_writer.take() {
                 writer.shutdown().await?;
                 let res = writer.into_inner();
+                trace!("EOF");
                 if res.len() <= max_cache_size {
+                    trace!("writing {} bytes to cache", res.len());
                     (bytes_written, Some(res))
                 } else {
+                    trace!("cache longer than max, dropping");
                     (bytes_written, None)
                 }
             } else {

src/preproc.rs

@@ -20,9 +20,9 @@ use std::io::Cursor;
 use std::path::Path;
 use std::pin::Pin;
 use std::sync::Arc;
-use tokio::io::AsyncBufRead;
 use tokio::io::AsyncBufReadExt;
 use tokio::io::BufReader;
+use tokio::io::{AsyncBufRead, AsyncReadExt};
 
 pub type ActiveAdapters = Vec<Arc<dyn FileAdapter>>;
 
@@ -185,6 +185,17 @@ async fn adapt_caching(
     }
 }
 
+async fn read_discard(mut x: ReadBox) -> Result<()> {
+    let mut buf = [0u8; 1 << 16];
+    loop {
+        let n = x.read(&mut buf).await?;
+        if n == 0 {
+            break;
+        }
+    }
+    Ok(())
+}
+
 pub fn loop_adapt(
     adapter: &dyn FileAdapter,
     detection_reason: FileMatcher,
@@ -213,9 +224,12 @@ pub async fn loop_adapt_inner(
     };
     let s = stream! {
         for await file in inp {
+            trace!("next file");
             match buf_choose_adapter(file?).await? {
                 Ret::Recurse(ai, adapter, detection_reason, _active_adapters) => {
                     if ai.archive_recursion_depth >= ai.config.max_archive_recursion.0 {
+                        // some adapters (esp. zip) assume that the entry is read fully and might hang otherwise
+                        read_discard(ai.inp).await?;
                         let s = format!("{}[rga: max archive recursion reached ({})]\n", ai.line_prefix, ai.archive_recursion_depth).into_bytes();
                         yield Ok(AdaptInfo {
                             inp: Box::pin(Cursor::new(s)),
@@ -241,7 +255,9 @@ pub async fn loop_adapt_inner(
                     yield Ok(ai);
                 }
             }
+            trace!("done with files");
         }
+        trace!("stream ended");
     };
     Ok(Box::pin(s))
 }

src/preproc_cache.rs

@@ -2,10 +2,7 @@ use crate::{adapters::FileAdapter, preproc::ActiveAdapters};
 use anyhow::{Context, Result};
 use path_clean::PathClean;
 use rusqlite::{named_params, OptionalExtension};
-use std::{
-    path::Path,
-    time::{Duration, UNIX_EPOCH},
-};
+use std::{path::Path, time::UNIX_EPOCH};
 use tokio_rusqlite::Connection;
 
 #[derive(Clone)]
@@ -58,7 +55,7 @@ async fn connect_pragmas(db: &Connection) -> Result<()> {
     //db.execute(&format!("pragma page_size = {};", want_page_size))
     //    .context("setup pragma 1")?;
     db.call(|db| {
-        db.busy_timeout(Duration::from_secs(10))?;
+        // db.busy_timeout(Duration::from_secs(10))?;
         db.pragma_update(None, "journal_mode", "wal")?;
         db.pragma_update(None, "foreign_keys", "on")?;
         db.pragma_update(None, "temp_store", "memory")?;
@@ -145,6 +142,12 @@ impl PreprocCache for SqliteCache {
 
     async fn set(&mut self, key: &CacheKey, value: Vec<u8>) -> Result<()> {
         let key = (*key).clone(); // todo: without cloning
+        log::trace!(
+            "Writing to cache: {}, {}, {} byte",
+            key.adapter,
+            key.file_path,
+            value.len()
+        );
         Ok(self
             .db
             .call(move |db| {