dirsql 0.4.54__tar.gz → 0.4.55__tar.gz

{dirsql-0.4.54 → dirsql-0.4.55}/Cargo.lock

@@ -552,7 +552,7 @@ checksum = "6184e33543162437515c2e2b48714794e37845ec9851711914eec9d308f6ebe8"
 
 [[package]]
 name = "dirsql"
-version = "0.4.54"
+version = "0.4.55"
 dependencies = [
  "assert_cmd",
  "axum",
@@ -599,7 +599,7 @@ dependencies = [
 
 [[package]]
 name = "dirsql-py-ext"
-version = "0.4.54"
+version = "0.4.55"
 dependencies = [
  "dirsql",
  "pyo3",
@@ -2451,6 +2451,7 @@ version = "1.0.149"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "83fc039473c5595ace860d8c4fafa220ff474b3fc6bfdb4293327f1a37e94d86"
 dependencies = [
+ "indexmap",
  "itoa",
  "memchr",
  "serde",

{dirsql-0.4.54 → dirsql-0.4.55}/Cargo.toml

@@ -16,7 +16,9 @@ repository = "https://github.com/thekevinscott/dirsql"
 [workspace.dependencies]
 dirsql = { path = "packages/rust" }
 serde = { version = "1", features = ["derive"] }
-serde_json = "1"
+# `preserve_order`: a serialized row must keep the projection order the SELECT
+# list asked for, which the default BTreeMap-backed object discards.
+serde_json = { version = "1", features = ["preserve_order"] }
 regex = "1"
 thiserror = "2"
 tokio = { version = "1", features = ["rt", "sync"] }

{dirsql-0.4.54 → dirsql-0.4.55}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dirsql
-Version: 0.4.54
+Version: 0.4.55
 Requires-Dist: bin-shim>=0.1
 Summary: Ephemeral SQL index over a local directory
 Keywords: sql,filesystem,directory,sqlite,index

{dirsql-0.4.54 → dirsql-0.4.55}/packages/python/Cargo.toml

@@ -4,7 +4,7 @@ name = "dirsql-py-ext"
 # pypi/maturin handler can rewrite it via `write-version` before
 # `maturin build`. `pyproject.toml` declares `dynamic = ["version"]`
 # and maturin reads this field. Mirrors `packages/rust/Cargo.toml`.
-version = "0.4.54"
+version = "0.4.55"
 # abi3 note: the `abi3-py310` pyo3 feature (below) builds ONE stable-ABI
 # `cp310-abi3` wheel per platform that loads on every CPython >= 3.10
 # (matching `pyproject.toml`'s `requires-python = ">=3.10"`), instead of

dirsql-0.4.55/packages/python/e2e-attestations/claude-1170-projection-order.json

@@ -0,0 +1,7 @@
+{
+  "command": "just test-e2e",
+  "ran_at": 1790181270,
+  "exit_code": 0,
+  "commit": "010d9772867fcb1e1b56ce4a77eb8b0223b0870a",
+  "branch": "claude/1170-projection-order"
+}

{dirsql-0.4.54 → dirsql-0.4.55}/packages/rust/Cargo.toml

@@ -6,7 +6,7 @@ description = "Ephemeral SQL index over a local directory"
 # version stays for the binding crates (publish = false). The literal
 # intentionally lags the published version: putitoutthere rewrites it to
 # the planned release version at build time and never commits it back.
-version = "0.4.54"
+version = "0.4.55"
 edition.workspace = true
 # Literal `license` (not `license.workspace = true`) because
 # putitoutthere's preflight check reads `[package].license` directly

{dirsql-0.4.54 → dirsql-0.4.55}/packages/rust/src/cli/execute.rs

@@ -15,7 +15,7 @@ use serde::Deserialize;
 use serde_json::Value;
 
 use super::AppState;
-use super::serialize::rows_to_json;
+use super::serialize::result_to_json;
 use crate::{DirSQL, DirSqlError};
 
 /// Why a query failed, classified independently of transport. The HTTP
@@ -66,10 +66,14 @@ pub async fn execute_query(
 
     let db = require_ready(state)?;
 
-    let join = run_bounded(timeout, tokio::task::spawn_blocking(move || db.query(&sql))).await?;
+    let join = run_bounded(
+        timeout,
+        tokio::task::spawn_blocking(move || db.query_ordered(&sql)),
+    )
+    .await?;
 
     match join {
-        Ok(Ok(rows)) => Ok(Value::Array(rows_to_json(&rows))),
+        Ok(Ok(result)) => Ok(Value::Array(result_to_json(&result))),
         Ok(Err(err)) => Err(classify_query_error(err)),
         Err(join_err) => Err(QueryFailure::Internal(join_err.to_string())),
     }

{dirsql-0.4.54 → dirsql-0.4.55}/packages/rust/src/cli/serialize.rs

@@ -2,13 +2,29 @@
 
 use serde_json::{Map, Value};
 
-use crate::Row;
 use crate::db::Value as CellValue;
 use crate::differ::RowEvent;
 use crate::row_event_flat::flatten_row_event;
+use crate::{QueryResult, Row};
+
+/// Serialize a query result, each object keyed in projection order. Row events
+/// carry no projection, so they keep going through [`row_to_json`].
+pub(super) fn result_to_json(result: &QueryResult) -> Vec<Value> {
+    result
+        .rows
+        .iter()
+        .map(|row| ordered_row_to_json(&result.columns, row))
+        .collect()
+}
 
-pub(super) fn rows_to_json(rows: &[Row]) -> Vec<Value> {
-    rows.iter().map(row_to_json).collect()
+fn ordered_row_to_json(columns: &[String], row: &Row) -> Value {
+    let mut map = Map::with_capacity(columns.len());
+    for column in columns {
+        if let Some(value) = row.get(column) {
+            map.insert(column.clone(), cell_to_json(value));
+        }
+    }
+    Value::Object(map)
 }
 
 pub(super) fn row_to_json(row: &Row) -> Value {
@@ -75,6 +91,35 @@ mod tests {
         assert_eq!(json.get("count").and_then(Value::as_i64), Some(3));
     }
 
+    #[test]
+    fn a_result_serializes_its_rows_in_projection_order() {
+        let mut row: Row = HashMap::new();
+        row.insert("title".into(), CellValue::Text("Hello".into()));
+        row.insert("count".into(), CellValue::Integer(3));
+        let result = QueryResult {
+            columns: vec!["count".into(), "title".into()],
+            rows: vec![row],
+        };
+
+        let json = result_to_json(&result);
+
+        assert_eq!(json[0].to_string(), r#"{"count":3,"title":"Hello"}"#);
+    }
+
+    #[test]
+    fn a_column_no_row_key_matches_is_left_out() {
+        let mut row: Row = HashMap::new();
+        row.insert("title".into(), CellValue::Text("Hello".into()));
+        let result = QueryResult {
+            columns: vec!["title".into(), "title".into()],
+            rows: vec![row],
+        };
+
+        let json = result_to_json(&result);
+
+        assert_eq!(json[0].to_string(), r#"{"title":"Hello"}"#);
+    }
+
     #[test]
     fn insert_event_emits_expected_shape() {
         let mut row: Row = HashMap::new();

{dirsql-0.4.54 → dirsql-0.4.55}/packages/rust/src/cli/table.rs

@@ -11,7 +11,7 @@
 //! swallowing the table; laying the table out to the terminal's width, and
 //! paging a long result, are both out of scope.
 
-use std::collections::BTreeSet;
+use std::collections::HashSet;
 
 use serde_json::Value;
 
@@ -53,16 +53,22 @@ pub(super) fn render(rows: &[Value]) -> String {
     out
 }
 
-/// Every column any row carries. Rows are JSON objects, so the keys arrive
-/// sorted and stay in step with the JSON rendering of the same result.
+/// Every column any row carries, first seen first. Rows are JSON objects
+/// serialized in projection order, so that is the order the SELECT list asked
+/// for -- and the same order the JSON rendering of this result prints.
 fn columns(rows: &[Value]) -> Vec<String> {
-    let mut names = BTreeSet::new();
+    let mut seen = HashSet::new();
+    let mut names = Vec::new();
     for row in rows {
         if let Value::Object(map) = row {
-            names.extend(map.keys().cloned());
+            for key in map.keys() {
+                if seen.insert(key.clone()) {
+                    names.push(key.clone());
+                }
+            }
         }
     }
-    names.into_iter().collect()
+    names
 }
 
 /// One row's cells, in column order. A row missing a column renders it as
@@ -242,6 +248,25 @@ mod tests {
         }
     }
 
+    #[test]
+    fn the_header_keeps_the_order_the_row_carries() {
+        // Rows arrive serialized in projection order; re-sorting them here is
+        // what made `SELECT size, basename` print `basename  size`.
+        let table = rendered([row([
+            ("size", Value::from(6)),
+            ("basename", Value::from("a.md")),
+        ])]);
+
+        assert!(table.starts_with("size  basename\n"), "{table:?}");
+    }
+
+    #[test]
+    fn a_later_rows_new_columns_come_after_the_earlier_ones() {
+        let table = rendered([row([("b", Value::from(1))]), row([("a", Value::from(2))])]);
+
+        assert!(table.starts_with("b     a\n"), "{table:?}");
+    }
+
     #[test]
     fn every_column_any_row_carries_is_shown() {
         // A ragged result must not silently drop the columns only some rows

{dirsql-0.4.54 → dirsql-0.4.55}/packages/rust/src/db.rs

@@ -244,6 +244,13 @@ pub fn ensure_internal_rows_table(conn: &Connection) -> rusqlite::Result<()> {
     )
 }
 
+/// One query's rows plus the column order the SELECT list asked for.
+#[derive(Debug, Clone, PartialEq)]
+pub struct QueryResult {
+    pub columns: Vec<String>,
+    pub rows: Vec<HashMap<String, Value>>,
+}
+
 pub struct Db {
     conn: Connection,
     /// The directory a path-table's glob is resolved against. `None` disables
@@ -714,6 +721,14 @@ impl Db {
     /// internal writes (`insert_row`, delete-by-file, persist), which never go
     /// through `query()`, are unaffected.
     pub fn query(&self, sql: &str) -> Result<Vec<HashMap<String, Value>>> {
+        self.query_ordered(sql).map(|result| result.rows)
+    }
+
+    /// [`query`](Self::query), plus the projection order. A row is a
+    /// `HashMap`, so the order the SELECT list asked for survives only in
+    /// [`QueryResult::columns`]; a renderer that re-derives its columns from
+    /// row keys prints them alphabetically instead.
+    pub fn query_ordered(&self, sql: &str) -> Result<QueryResult> {
         // Bracket the whole statement, prepare included: a worker-backed
         // function called on every row makes this the slowest thing dirsql
         // does, and the guard is what erases the counter before the caller
@@ -757,7 +772,10 @@ impl Db {
         for row in rows {
             results.push(row?);
         }
-        Ok(results)
+        Ok(QueryResult {
+            columns: column_names,
+            rows: results,
+        })
     }
 
     /// Prepare `sql` with the internal-table / ATTACH authorizer installed for
@@ -1026,6 +1044,40 @@ mod tests {
         assert!(!rows[0].contains_key("_dirsql_row_index"));
     }
 
+    #[test]
+    fn query_ordered_reports_the_select_list_order() {
+        let db = Db::new().unwrap();
+        db.create_table("docs", "CREATE TABLE docs (title TEXT, draft INTEGER)")
+            .unwrap();
+
+        let result = db.query_ordered("SELECT draft, title FROM docs").unwrap();
+
+        assert_eq!(
+            result.columns,
+            vec!["draft".to_string(), "title".to_string()]
+        );
+    }
+
+    #[test]
+    fn query_ordered_carries_the_same_rows_query_returns() {
+        let db = Db::new().unwrap();
+        db.create_table("docs", "CREATE TABLE docs (title TEXT, draft INTEGER)")
+            .unwrap();
+        let row = HashMap::from([
+            ("title".into(), Value::Text("Hello".into())),
+            ("draft".into(), Value::Integer(0)),
+        ]);
+        db.insert_row("docs", &row, "docs/hello.md", 0).unwrap();
+
+        let result = db.query_ordered("SELECT title, draft FROM docs").unwrap();
+
+        assert_eq!(
+            result.rows,
+            db.query("SELECT title, draft FROM docs").unwrap()
+        );
+        assert_eq!(result.rows[0]["title"], Value::Text("Hello".into()));
+    }
+
     #[test]
     fn pragma_table_info_matches_user_ddl_exactly() {
         let db = Db::new().unwrap();

{dirsql-0.4.54 → dirsql-0.4.55}/packages/rust/src/lib.rs

@@ -77,7 +77,7 @@ use std::time::Duration;
 use thiserror::Error;
 
 pub use crate::config::ExtensionSpec as Extension;
-pub use crate::db::{DbError, Value};
+pub use crate::db::{DbError, QueryResult, Value};
 pub use crate::differ::RowEvent;
 #[doc(hidden)]
 pub use crate::row_event_flat::{FlatRowEvent, flatten_row_event};
@@ -404,8 +404,15 @@ impl DirSQL {
     /// keeps the ephemeral index consistent with the on-disk files that back
     /// it: mutations only happen through the watcher/indexer pipeline.
     pub fn query(&self, sql: &str) -> Result<Vec<Row>> {
+        self.query_ordered(sql).map(|result| result.rows)
+    }
+
+    /// [`query`](Self::query), plus the projection order in
+    /// [`QueryResult::columns`]. A [`Row`] is a `HashMap`, so a caller that
+    /// renders columns in the order the user asked for needs this instead.
+    pub fn query_ordered(&self, sql: &str) -> Result<QueryResult> {
         let db = self.inner.db.lock().map_err(DirSqlError::lock)?;
-        db.query(sql).map_err(map_db_error)
+        db.query_ordered(sql).map_err(map_db_error)
     }
 
     /// Lazily create the filesystem watcher. Idempotent; subsequent calls are