[arrow-rs] branch master updated: Fix data corruption in json decoder f64-to-i64 cast (#652)

[nevime]

This is an automated email from the ASF dual-hosted git repository.

nevime pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git


The following commit(s) were added to refs/heads/master by this push:
     new b075c3c  Fix data corruption in json decoder f64-to-i64 cast (#652)
b075c3c is described below

commit b075c3cef6d48e1e5ffce7e5c555d9c740885fae
Author: Christian Williams <christianwilliam...@gmail.com>
AuthorDate: Mon Aug 2 13:29:09 2021 -0400

    Fix data corruption in json decoder f64-to-i64 cast (#652)
    
    * Add failing test for JSON writer i64 bug
    
    * Add special handling for i64/u64 to json decoder array builder
    
    * Fix linter error - linter wants .flatten on a new line
---
 arrow/src/json/reader.rs    | 13 +++++++++++--
 arrow/test/data/arrays.json |  2 +-
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/arrow/src/json/reader.rs b/arrow/src/json/reader.rs
index c4e8470..4912c5e 100644
--- a/arrow/src/json/reader.rs
+++ b/arrow/src/json/reader.rs
@@ -927,8 +927,16 @@ impl Decoder {
             rows.iter()
                 .map(|row| {
                     row.get(&col_name)
-                        .and_then(|value| value.as_f64())
-                        .and_then(num::cast::cast)
+                        .and_then(|value| {
+                            if value.is_i64() {
+                                value.as_i64().map(num::cast::cast)
+                            } else if value.is_u64() {
+                                value.as_u64().map(num::cast::cast)
+                            } else {
+                                value.as_f64().map(num::cast::cast)
+                            }
+                        })
+                        .flatten()
                 })
                 .collect::<PrimitiveArray<T>>(),
         ))
@@ -1933,6 +1941,7 @@ mod tests {
             .unwrap();
         assert_eq!(1, aa.value(0));
         assert_eq!(-10, aa.value(1));
+        assert_eq!(1627668684594000000, aa.value(2));
         let bb = batch
             .column(b.0)
             .as_any()
diff --git a/arrow/test/data/arrays.json b/arrow/test/data/arrays.json
index 5dbdd19..6de2b03 100644
--- a/arrow/test/data/arrays.json
+++ b/arrow/test/data/arrays.json
@@ -1,3 +1,3 @@
 {"a":1, "b":[2.0, 1.3, -6.1], "c":[false, true], "d":"4"}
 {"a":-10, "b":[2.0, 1.3, -6.1], "c":[true, true], "d":"4"}
-{"a":2, "b":[2.0, null, -6.1], "c":[false, null], "d":"text"}
+{"a":1627668684594000000, "b":[2.0, null, -6.1], "c":[false, null], "d":"text"}