Merge pull request #921 from tantivy-search/more-pub-for-hot-directory

Exposing API for the hot directory

src/directory/file_slice.rs

@@ -16,6 +16,9 @@ pub type BoxedData = Box<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
 /// Despite its name, a `FileSlice` may or may not directly map to an actual file
 /// on the filesystem.
 pub trait FileHandle: 'static + Send + Sync + HasLen {
+    /// Reads a slice of bytes.
+    ///
+    /// This method may panic if the range requested is invalid.
     fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes>;
 }
 
@@ -53,7 +56,7 @@ pub struct FileSlice {
 }
 
 impl FileSlice {
-    /// Wraps a new `Deref<Target = [u8]>`
+    /// Wraps a FileHandle.
     pub fn new<D>(data: D) -> Self
     where
         D: FileHandle,
@@ -69,6 +72,7 @@ impl FileSlice {
     /// Creates a fileslice that is just a view over a slice of the data.
     ///
     /// # Panics
+    ///
     /// Panics if `to < from` or if `to` exceeds the filesize.
     pub fn slice(&self, from: usize, to: usize) -> FileSlice {
         assert!(to <= self.len());
@@ -96,6 +100,18 @@ impl FileSlice {
         self.data.read_bytes(self.start, self.stop)
     }
 
+    /// Reads a specific slice of data.
+    ///
+    /// This is equivalent to running `file_slice.slice(from, to).read_bytes()`.
+    pub fn read_bytes_slice(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
+        assert!(from <= to);
+        assert!(
+            self.start + to <= self.stop,
+            "`to` exceeds the fileslice length"
+        );
+        self.data.read_bytes(self.start + from, self.start + to)
+    }
+
     /// Splits the FileSlice at the given offset and return two file slices.
     /// `file_slice[..split_offset]` and `file_slice[split_offset..]`.
     ///
@@ -187,11 +203,35 @@ mod tests {
     }
 
     #[test]
-    fn test_slice_deref() -> io::Result<()> {
-        let slice_deref = FileSlice::new(&b"abcdef"[..]);
-        assert_eq!(slice_deref.len(), 6);
-        assert_eq!(slice_deref.read_bytes()?.as_ref(), b"abcdef");
-        assert_eq!(slice_deref.slice(1, 4).read_bytes()?.as_ref(), b"bcd");
+    fn test_slice_simple_read() -> io::Result<()> {
+        let slice = FileSlice::new(&b"abcdef"[..]);
+        assert_eq!(slice.len(), 6);
+        assert_eq!(slice.read_bytes()?.as_ref(), b"abcdef");
+        assert_eq!(slice.slice(1, 4).read_bytes()?.as_ref(), b"bcd");
         Ok(())
     }
+
+    #[test]
+    fn test_slice_read_slice() -> io::Result<()> {
+        let slice_deref = FileSlice::new(&b"abcdef"[..]);
+        assert_eq!(slice_deref.read_bytes_slice(1, 4)?.as_ref(), b"bcd");
+        Ok(())
+    }
+
+    #[test]
+    #[should_panic(expected = "assertion failed: from <= to")]
+    fn test_slice_read_slice_invalid_range() {
+        let slice_deref = FileSlice::new(&b"abcdef"[..]);
+        assert_eq!(slice_deref.read_bytes_slice(1, 0).unwrap().as_ref(), b"bcd");
+    }
+
+    #[test]
+    #[should_panic(expected = "`to` exceeds the fileslice length")]
+    fn test_slice_read_slice_invalid_range_exceeds() {
+        let slice_deref = FileSlice::new(&b"abcdef"[..]);
+        assert_eq!(
+            slice_deref.read_bytes_slice(0, 10).unwrap().as_ref(),
+            b"bcd"
+        );
+    }
 }

src/directory/mod.rs

@@ -23,12 +23,13 @@ pub use self::directory::DirectoryLock;
 pub use self::directory::{Directory, DirectoryClone};
 pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
 pub(crate) use self::file_slice::BoxedData;
-pub use self::file_slice::FileSlice;
+pub use self::file_slice::{FileHandle, FileSlice};
 pub use self::owned_bytes::OwnedBytes;
 pub use self::ram_directory::RAMDirectory;
 pub use self::watch_event_router::{WatchCallback, WatchCallbackList, WatchHandle};
 use std::io::{self, BufWriter, Write};
 use std::path::PathBuf;
+
 /// Outcome of the Garbage collection
 pub struct GarbageCollectionResult {
     /// List of files that were deleted in this cycle

src/directory/owned_bytes.rs

@@ -1,11 +1,10 @@
+use crate::directory::FileHandle;
 use stable_deref_trait::StableDeref;
 use std::mem;
 use std::ops::Deref;
 use std::sync::Arc;
 use std::{fmt, io};
 
-use super::file_slice::FileHandle;
-
 /// An OwnedBytes simply wraps an object that owns a slice of data and exposes
 /// this data as a static slice.
 ///

src/directory/watch_event_router.rs

@@ -29,6 +29,13 @@ impl WatchHandle {
     pub fn new(watch_callback: Arc<WatchCallback>) -> WatchHandle {
         WatchHandle(watch_callback)
     }
+
+    /// Returns an empty watch handle.
+    ///
+    /// This function is only useful when implementing a readonly directory.
+    pub fn empty() -> WatchHandle {
+        WatchHandle::new(Arc::new(Box::new(|| {})))
+    }
 }
 
 impl WatchCallbackList {

src/error.rs

@@ -13,12 +13,16 @@ use std::fmt;
 use std::path::PathBuf;
 use std::sync::PoisonError;
 
+/// Represents a `DataCorruption` error.
+///
+/// When facing data corruption, tantivy  actually panic or return this error.
 pub struct DataCorruption {
     filepath: Option<PathBuf>,
     comment: String,
 }
 
 impl DataCorruption {
+    /// Creates a `DataCorruption` Error.
     pub fn new(filepath: PathBuf, comment: String) -> DataCorruption {
         DataCorruption {
             filepath: Some(filepath),
@@ -26,10 +30,11 @@ impl DataCorruption {
         }
     }
 
-    pub fn comment_only(comment: String) -> DataCorruption {
+    /// Creates a `DataCorruption` Error, when the filepath is irrelevant.
+    pub fn comment_only<TStr: ToString>(comment: TStr) -> DataCorruption {
         DataCorruption {
             filepath: None,
-            comment,
+            comment: comment.to_string(),
         }
     }
 }

src/lib.rs

@@ -134,7 +134,7 @@ mod core;
 mod indexer;
 
 #[allow(unused_doc_comments)]
-mod error;
+pub mod error;
 pub mod tokenizer;
 
 pub mod collector;