From 760ccffdbd2a1bb51b95de3c024e77e09f46f475 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20Renault?= <clement@meilisearch.com>
Date: Thu, 17 Jul 2025 17:12:18 +0200
Subject: [PATCH] Expose the documents files from the dumps

---
 crates/dump/src/reader/compat/v1_to_v2.rs | 5 +++++
 crates/dump/src/reader/compat/v2_to_v3.rs | 8 ++++++++
 crates/dump/src/reader/compat/v3_to_v4.rs | 9 +++++++++
 crates/dump/src/reader/compat/v4_to_v5.rs | 9 +++++++++
 crates/dump/src/reader/compat/v5_to_v6.rs | 8 ++++++++
 crates/dump/src/reader/mod.rs             | 7 +++++++
 crates/dump/src/reader/v1/mod.rs          | 4 ++++
 crates/dump/src/reader/v2/mod.rs          | 4 ++++
 crates/dump/src/reader/v3/mod.rs          | 4 ++++
 crates/dump/src/reader/v4/mod.rs          | 4 ++++
 crates/dump/src/reader/v5/mod.rs          | 4 ++++
 crates/dump/src/reader/v6/mod.rs          | 4 ++++
 12 files changed, 70 insertions(+)

diff --git a/crates/dump/src/reader/compat/v1_to_v2.rs b/crates/dump/src/reader/compat/v1_to_v2.rs
index 0d050497b..35d369c3a 100644
--- a/crates/dump/src/reader/compat/v1_to_v2.rs
+++ b/crates/dump/src/reader/compat/v1_to_v2.rs
@@ -1,3 +1,4 @@
+use std::fs::File;
 use std::str::FromStr;
 
 use super::v2_to_v3::CompatV2ToV3;
@@ -94,6 +95,10 @@ impl CompatIndexV1ToV2 {
         self.from.documents().map(|it| Box::new(it) as Box<dyn Iterator<Item = _>>)
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.from.documents_file()
+    }
+
     pub fn settings(&mut self) -> Result<v2::settings::Settings<v2::settings::Checked>> {
         Ok(v2::settings::Settings::<v2::settings::Unchecked>::from(self.from.settings()?).check())
     }
diff --git a/crates/dump/src/reader/compat/v2_to_v3.rs b/crates/dump/src/reader/compat/v2_to_v3.rs
index e7516e708..62326040e 100644
--- a/crates/dump/src/reader/compat/v2_to_v3.rs
+++ b/crates/dump/src/reader/compat/v2_to_v3.rs
@@ -1,3 +1,4 @@
+use std::fs::File;
 use std::str::FromStr;
 
 use time::OffsetDateTime;
@@ -122,6 +123,13 @@ impl CompatIndexV2ToV3 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV2ToV3::V2(v2) => v2.documents_file(),
+            CompatIndexV2ToV3::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v3::Settings<v3::Checked>> {
         let settings = match self {
             CompatIndexV2ToV3::V2(from) => from.settings()?,
diff --git a/crates/dump/src/reader/compat/v3_to_v4.rs b/crates/dump/src/reader/compat/v3_to_v4.rs
index 5bb70e9b2..1dba37771 100644
--- a/crates/dump/src/reader/compat/v3_to_v4.rs
+++ b/crates/dump/src/reader/compat/v3_to_v4.rs
@@ -1,3 +1,5 @@
+use std::fs::File;
+
 use super::v2_to_v3::{CompatIndexV2ToV3, CompatV2ToV3};
 use super::v4_to_v5::CompatV4ToV5;
 use crate::reader::{v3, v4, UpdateFile};
@@ -252,6 +254,13 @@ impl CompatIndexV3ToV4 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV3ToV4::V3(v3) => v3.documents_file(),
+            CompatIndexV3ToV4::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v4::Settings<v4::Checked>> {
         Ok(match self {
             CompatIndexV3ToV4::V3(v3) => {
diff --git a/crates/dump/src/reader/compat/v4_to_v5.rs b/crates/dump/src/reader/compat/v4_to_v5.rs
index e52acb176..3f47b5b48 100644
--- a/crates/dump/src/reader/compat/v4_to_v5.rs
+++ b/crates/dump/src/reader/compat/v4_to_v5.rs
@@ -1,3 +1,5 @@
+use std::fs::File;
+
 use super::v3_to_v4::{CompatIndexV3ToV4, CompatV3ToV4};
 use super::v5_to_v6::CompatV5ToV6;
 use crate::reader::{v4, v5, Document};
@@ -241,6 +243,13 @@ impl CompatIndexV4ToV5 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV4ToV5::V4(v4) => v4.documents_file(),
+            CompatIndexV4ToV5::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v5::Settings<v5::Checked>> {
         match self {
             CompatIndexV4ToV5::V4(v4) => Ok(v5::Settings::from(v4.settings()?).check()),
diff --git a/crates/dump/src/reader/compat/v5_to_v6.rs b/crates/dump/src/reader/compat/v5_to_v6.rs
index f7bda81c6..f173bb6bd 100644
--- a/crates/dump/src/reader/compat/v5_to_v6.rs
+++ b/crates/dump/src/reader/compat/v5_to_v6.rs
@@ -1,3 +1,4 @@
+use std::fs::File;
 use std::num::NonZeroUsize;
 use std::str::FromStr;
 
@@ -243,6 +244,13 @@ impl CompatIndexV5ToV6 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV5ToV6::V5(v5) => v5.documents_file(),
+            CompatIndexV5ToV6::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v6::Settings<v6::Checked>> {
         match self {
             CompatIndexV5ToV6::V5(v5) => Ok(v6::Settings::from(v5.settings()?).check()),
diff --git a/crates/dump/src/reader/mod.rs b/crates/dump/src/reader/mod.rs
index 23e7eec9e..91c6d5880 100644
--- a/crates/dump/src/reader/mod.rs
+++ b/crates/dump/src/reader/mod.rs
@@ -192,6 +192,13 @@ impl DumpIndexReader {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            DumpIndexReader::Current(v6) => v6.documents_file(),
+            DumpIndexReader::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v6::Settings<v6::Checked>> {
         match self {
             DumpIndexReader::Current(v6) => v6.settings(),
diff --git a/crates/dump/src/reader/v1/mod.rs b/crates/dump/src/reader/v1/mod.rs
index ac7324d9a..d86ede62c 100644
--- a/crates/dump/src/reader/v1/mod.rs
+++ b/crates/dump/src/reader/v1/mod.rs
@@ -72,6 +72,10 @@ impl V1IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<self::settings::Settings> {
         Ok(serde_json::from_reader(&mut self.settings)?)
     }
diff --git a/crates/dump/src/reader/v2/mod.rs b/crates/dump/src/reader/v2/mod.rs
index 14a643c2d..a74687381 100644
--- a/crates/dump/src/reader/v2/mod.rs
+++ b/crates/dump/src/reader/v2/mod.rs
@@ -203,6 +203,10 @@ impl V2IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }
diff --git a/crates/dump/src/reader/v3/mod.rs b/crates/dump/src/reader/v3/mod.rs
index 920e1dc6e..5f89eb861 100644
--- a/crates/dump/src/reader/v3/mod.rs
+++ b/crates/dump/src/reader/v3/mod.rs
@@ -215,6 +215,10 @@ impl V3IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }
diff --git a/crates/dump/src/reader/v4/mod.rs b/crates/dump/src/reader/v4/mod.rs
index 585786ae4..16a1e27c2 100644
--- a/crates/dump/src/reader/v4/mod.rs
+++ b/crates/dump/src/reader/v4/mod.rs
@@ -210,6 +210,10 @@ impl V4IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }
diff --git a/crates/dump/src/reader/v5/mod.rs b/crates/dump/src/reader/v5/mod.rs
index dfbc6346c..0123db433 100644
--- a/crates/dump/src/reader/v5/mod.rs
+++ b/crates/dump/src/reader/v5/mod.rs
@@ -247,6 +247,10 @@ impl V5IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }
diff --git a/crates/dump/src/reader/v6/mod.rs b/crates/dump/src/reader/v6/mod.rs
index 449a7e5fe..08d4700e5 100644
--- a/crates/dump/src/reader/v6/mod.rs
+++ b/crates/dump/src/reader/v6/mod.rs
@@ -284,6 +284,10 @@ impl V6IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         let mut settings: Settings<Unchecked> = serde_json::from_reader(&mut self.settings)?;
         patch_embedders(&mut settings);