Add database migration for linecount statistics

This commit adds a new `JSONB` column called `linecounts` to the versions table to store Source Lines of Code statistics for each crate version. The column stores language breakdown and totals as structured `JSON` data, enabling flexible schema evolution without requiring additional migrations.

The database schema and test snapshots are updated accordingly to reflect this new column structure.

Author: Turbo87

crates/crates_io_database/src/schema.rs

@@ -1077,6 +1077,8 @@ diesel::table! {
         keywords -> Array<Nullable<Text>>,
         /// JSONB representation of the version number for sorting purposes.
         semver_ord -> Nullable<Jsonb>,
+        /// Source Lines of Code statistics for this version, stored as JSON with language breakdown and totals.
+        linecounts -> Nullable<Jsonb>,
     }
 }
 

crates/crates_io_database_dump/src/dump-db.toml

@@ -280,6 +280,8 @@ documentation = "public"
 repository = "public"
 categories = "public"
 keywords = "public"
+# The following column is private for now, until we can guarantee a stable data schema.
+linecounts = "private"
 
 [versions_published_by.columns]
 version_id = "private"

migrations/2025-06-26-183025_add-linecounts-column/down.sql

@@ -0,0 +1,3 @@
+-- Remove line count statistics column from versions table
+ALTER TABLE versions 
+DROP COLUMN linecounts;

migrations/2025-06-26-183025_add-linecounts-column/up.sql

@@ -0,0 +1,6 @@
+-- Add line count statistics column to versions table
+ALTER TABLE versions
+ADD COLUMN linecounts JSONB DEFAULT NULL;
+
+-- Add comment explaining the column
+COMMENT ON COLUMN versions.linecounts IS 'Source Lines of Code statistics for this version, stored as JSON with language breakdown and totals.';