From 54889813cefe4f0978ecc87aea2c47551edbb3c5 Mon Sep 17 00:00:00 2001
From: Kerollmops <clement@meilisearch.com>
Date: Wed, 30 Jun 2021 10:43:12 +0200
Subject: [PATCH] Implement some debug functions on the ExternalDocumentsIds
 struct

---
 milli/src/external_documents_ids.rs | 34 ++++++++++++++++++++++++++---
 1 file changed, 31 insertions(+), 3 deletions(-)

diff --git a/milli/src/external_documents_ids.rs b/milli/src/external_documents_ids.rs
index 3dec638da..419105bd5 100644
--- a/milli/src/external_documents_ids.rs
+++ b/milli/src/external_documents_ids.rs
@@ -1,8 +1,12 @@
 use std::borrow::Cow;
+use std::collections::HashMap;
 use std::convert::TryInto;
+use std::{fmt, str};
 
 use fst::{IntoStreamer, Streamer};
 
+const DELETED_ID: u64 = u64::MAX;
+
 pub struct ExternalDocumentsIds<'a> {
     pub(crate) hard: fst::Map<Cow<'a, [u8]>>,
     pub(crate) soft: fst::Map<Cow<'a, [u8]>>,
@@ -32,7 +36,7 @@ impl<'a> ExternalDocumentsIds<'a> {
         let external_id = external_id.as_ref();
         match self.soft.get(external_id).or_else(|| self.hard.get(external_id)) {
             // u64 MAX means deleted in the soft fst map
-            Some(id) if id != u64::MAX => Some(id.try_into().unwrap()),
+            Some(id) if id != DELETED_ID => Some(id.try_into().unwrap()),
             _otherwise => None,
         }
     }
@@ -47,7 +51,7 @@ impl<'a> ExternalDocumentsIds<'a> {
             if docids.iter().any(|v| v.index == 1) {
                 // If the `other` set returns a value here it means
                 // that it must be marked as deleted.
-                new_soft_builder.insert(external_id, u64::MAX)?;
+                new_soft_builder.insert(external_id, DELETED_ID)?;
             } else {
                 new_soft_builder.insert(external_id, docids[0].value)?;
             }
@@ -77,6 +81,24 @@ impl<'a> ExternalDocumentsIds<'a> {
         self.merge_soft_into_hard()
     }
 
+    /// An helper function to debug this type, returns an `HashMap` of both,
+    /// soft and hard fst maps, combined.
+    pub fn to_hash_map(&self) -> HashMap<String, u32> {
+        let mut map = HashMap::new();
+
+        let union_op = self.hard.op().add(&self.soft).r#union();
+        let mut iter = union_op.into_stream();
+        while let Some((external_id, marked_docids)) = iter.next() {
+            let id = marked_docids.last().unwrap().value;
+            if id != DELETED_ID {
+                let external_id = str::from_utf8(external_id).unwrap();
+                map.insert(external_id.to_owned(), id.try_into().unwrap());
+            }
+        }
+
+        map
+    }
+
     fn merge_soft_into_hard(&mut self) -> fst::Result<()> {
         if self.soft.len() >= self.hard.len() / 2 {
             let union_op = self.hard.op().add(&self.soft).r#union();
@@ -85,7 +107,7 @@ impl<'a> ExternalDocumentsIds<'a> {
             let mut new_hard_builder = fst::MapBuilder::memory();
             while let Some((external_id, docids)) = iter.next() {
                 if docids.len() == 2 {
-                    if docids[1].value != u64::MAX {
+                    if docids[1].value != DELETED_ID {
                         new_hard_builder.insert(external_id, docids[1].value)?;
                     }
                 } else {
@@ -103,6 +125,12 @@ impl<'a> ExternalDocumentsIds<'a> {
     }
 }
 
+impl fmt::Debug for ExternalDocumentsIds<'_> {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        f.debug_tuple("ExternalDocumentsIds").field(&self.to_hash_map()).finish()
+    }
+}
+
 impl Default for ExternalDocumentsIds<'static> {
     fn default() -> Self {
         ExternalDocumentsIds {