From fbda511a1a0e7ce494ab70ce91c16ad718bce049 Mon Sep 17 00:00:00 2001
From: Paul Masurel <paul@quickwit.io>
Date: Thu, 20 Apr 2023 11:37:45 +0900
Subject: [PATCH] Making more things public for quickwit. (#2005)

---
 src/core/json_utils.rs               |  5 ++---
 src/core/mod.rs                      |  1 +
 src/lib.rs                           |  2 ++
 src/query/range_query/range_query.rs | 24 ++++++++++++++++++++++++
 src/schema/term.rs                   |  3 ++-
 src/tokenizer/simple_tokenizer.rs    |  1 +
 6 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/src/core/json_utils.rs b/src/core/json_utils.rs
index 749045ea0..7f3cb2c8f 100644
--- a/src/core/json_utils.rs
+++ b/src/core/json_utils.rs
@@ -201,7 +201,7 @@ fn infer_type_from_str(text: &str) -> TextOrDateTime {
 }
 
 // Tries to infer a JSON type from a string.
-pub(crate) fn convert_to_fast_value_and_get_term(
+pub fn convert_to_fast_value_and_get_term(
     json_term_writer: &mut JsonTermWriter,
     phrase: &str,
 ) -> Option<Term> {
@@ -405,8 +405,7 @@ impl<'a> JsonTermWriter<'a> {
             .append_bytes(value.to_be_bytes().as_slice());
     }
 
-    #[cfg(test)]
-    pub(crate) fn set_str(&mut self, text: &str) {
+    pub fn set_str(&mut self, text: &str) {
         self.close_path_and_set_type(Type::Str);
         self.term_buffer.append_bytes(text.as_bytes());
     }
diff --git a/src/core/mod.rs b/src/core/mod.rs
index 38976378d..b0b674c2e 100644
--- a/src/core/mod.rs
+++ b/src/core/mod.rs
@@ -2,6 +2,7 @@ mod executor;
 pub mod index;
 mod index_meta;
 mod inverted_index_reader;
+#[doc(hidden)]
 pub mod json_utils;
 pub mod searcher;
 mod segment;
diff --git a/src/lib.rs b/src/lib.rs
index ac3c8e2b7..0940aa8b7 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -173,6 +173,8 @@ use once_cell::sync::Lazy;
 use serde::{Deserialize, Serialize};
 
 pub use self::docset::{DocSet, TERMINATED};
+#[doc(hidden)]
+pub use crate::core::json_utils;
 pub use crate::core::{
     Executor, Index, IndexBuilder, IndexMeta, IndexSettings, IndexSortByField, InvertedIndexReader,
     Order, Searcher, SearcherGeneration, Segment, SegmentComponent, SegmentId, SegmentMeta,
diff --git a/src/query/range_query/range_query.rs b/src/query/range_query/range_query.rs
index 83bf6ae8e..61b65f34c 100644
--- a/src/query/range_query/range_query.rs
+++ b/src/query/range_query/range_query.rs
@@ -1,4 +1,5 @@
 use std::io;
+use std::net::Ipv6Addr;
 use std::ops::{Bound, Range};
 
 use common::{BinarySerializable, BitSet};
@@ -196,6 +197,29 @@ impl RangeQuery {
         }
     }
 
+    /// Create a new `RangeQuery` over a `ip` field.
+    ///
+    /// If the field is not of the type `ip`, tantivy
+    /// will panic when the `Weight` object is created.
+    pub fn new_ip_bounds(
+        field: String,
+        left_bound: Bound<Ipv6Addr>,
+        right_bound: Bound<Ipv6Addr>,
+    ) -> RangeQuery {
+        let make_term_val = |val: &Ipv6Addr| {
+            Term::from_field_ip_addr(Field::from_field_id(0), *val)
+                .value_bytes()
+                .to_owned()
+        };
+        RangeQuery {
+            field,
+            value_type: Type::IpAddr,
+            left_bound: map_bound(&left_bound, &make_term_val),
+            right_bound: map_bound(&right_bound, &make_term_val),
+            limit: None,
+        }
+    }
+
     /// Create a new `RangeQuery` over a `u64` field.
     ///
     /// If the field is not of the type `u64`, tantivy
diff --git a/src/schema/term.rs b/src/schema/term.rs
index 747cb434e..da5d236e9 100644
--- a/src/schema/term.rs
+++ b/src/schema/term.rs
@@ -30,7 +30,8 @@ where B: AsRef<[u8]>;
 const TERM_METADATA_LENGTH: usize = 5;
 
 impl Term {
-    pub(crate) fn with_capacity(capacity: usize) -> Term {
+    /// Create a new Term with a buffer with a given capacity.
+    pub fn with_capacity(capacity: usize) -> Term {
         let mut data = Vec::with_capacity(TERM_METADATA_LENGTH + capacity);
         data.resize(TERM_METADATA_LENGTH, 0u8);
         Term(data)
diff --git a/src/tokenizer/simple_tokenizer.rs b/src/tokenizer/simple_tokenizer.rs
index 2b9163b23..dc9a3b126 100644
--- a/src/tokenizer/simple_tokenizer.rs
+++ b/src/tokenizer/simple_tokenizer.rs
@@ -6,6 +6,7 @@ use super::{Token, TokenStream, Tokenizer};
 #[derive(Clone)]
 pub struct SimpleTokenizer;
 
+/// TokenStream produced by the `SimpleTokenizer`.
 pub struct SimpleTokenStream<'a> {
     text: &'a str,
     chars: CharIndices<'a>,