Move the main types to a separate library

meilidb-types/src/lib.rs

@@ -0,0 +1,72 @@
+use serde::{Deserialize, Serialize};
+use zerocopy::{AsBytes, FromBytes};
+
+/// Represent an internally generated document unique identifier.
+///
+/// It is used to inform the database the document you want to deserialize.
+/// Helpful for custom ranking.
+#[derive(
+    Debug,
+    Copy,
+    Clone,
+    Eq,
+    PartialEq,
+    PartialOrd,
+    Ord,
+    Hash,
+    Serialize,
+    Deserialize,
+    AsBytes,
+    FromBytes,
+)]
+#[repr(C)]
+pub struct DocumentId(pub u64);
+
+/// This structure represent the position of a word
+/// in a document and its attributes.
+///
+/// This is stored in the map, generated at index time,
+/// extracted and interpreted at search time.
+#[derive(Debug, Copy, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, AsBytes, FromBytes)]
+#[repr(C)]
+pub struct DocIndex {
+    /// The document identifier where the word was found.
+    pub document_id: DocumentId,
+
+    /// The attribute in the document where the word was found
+    /// along with the index in it.
+    pub attribute: u16,
+    pub word_index: u16,
+
+    /// The position in bytes where the word was found
+    /// along with the length of it.
+    ///
+    /// It informs on the original word area in the text indexed
+    /// without needing to run the tokenizer again.
+    pub char_index: u16,
+    pub char_length: u16,
+}
+
+/// This structure represent a matching word with informations
+/// on the location of the word in the document.
+///
+/// The order of the field is important because it defines
+/// the way these structures are ordered between themselves.
+#[derive(Debug, Copy, Clone, PartialEq, Eq, PartialOrd, Ord, Hash)]
+pub struct Highlight {
+    /// The attribute in the document where the word was found
+    /// along with the index in it.
+    pub attribute: u16,
+
+    /// The position in bytes where the word was found.
+    ///
+    /// It informs on the original word area in the text indexed
+    /// without needing to run the tokenizer again.
+    pub char_index: u16,
+
+    /// The length in bytes of the found word.
+    ///
+    /// It informs on the original word area in the text indexed
+    /// without needing to run the tokenizer again.
+    pub char_length: u16,
+}