Updating to rs-0.45 (#301)

Updating to rs-0.45

.github/workflows/docs.yaml

@@ -14,7 +14,7 @@ jobs:
       - name: Install latest Rust nightly
         uses: dtolnay/rust-toolchain@stable
         with:
-          toolchain: nightly-2024-10-28
+          toolchain: nightly-2024-11-28
           components: rustfmt, clippy
       - name: Install ghp-import
         uses: actions/setup-python@v5

.github/workflows/test-js.yaml

@@ -20,7 +20,7 @@ jobs:
       - name: Install latest Rust nightly
         uses: dtolnay/rust-toolchain@stable
         with:
-          toolchain: nightly-2024-10-28
+          toolchain: nightly-2024-11-28
           components: rustfmt, clippy
       - name: Check yarn version
         run: yarn --version
@@ -46,7 +46,7 @@ jobs:
       - name: Install latest Rust nightly
         uses: dtolnay/rust-toolchain@stable
         with:
-          toolchain: nightly-2024-10-28
+          toolchain: nightly-2024-11-28
           components: rustfmt, clippy
       - name: Bun version
         uses: oven-sh/setup-bun@v1

.yarnrc.yml

@@ -4,4 +4,4 @@ enableGlobalCache: false
 
 nodeLinker: node-modules
 
-yarnPath: .yarn/releases/yarn-4.5.0.cjs
+yarnPath: .yarn/releases/yarn-4.5.3.cjs

Cargo.toml

@@ -19,15 +19,15 @@ napi = { version = "2.16.13", default-features = false, features = [
     "napi8",
     "serde-json",
 ] }
-napi-derive = { version = "2.16.12", default-features = false }
-polars-core = { git = "https://github.com/pola-rs/polars.git", rev = "2dce3d3b5c80ae7522a3435f844fac8fed9dc9e8", default-features = false }
-polars-io = { git = "https://github.com/pola-rs/polars.git", rev = "2dce3d3b5c80ae7522a3435f844fac8fed9dc9e8", default-features = false }
-polars-lazy = { git = "https://github.com/pola-rs/polars.git", rev = "2dce3d3b5c80ae7522a3435f844fac8fed9dc9e8", default-features = false }
+napi-derive = { version = "2.16.13", default-features = false }
+polars-core = { git = "https://github.com/pola-rs/polars.git", rev = "58a38af21dccaf3326514494a1db118601c8c2ca", default-features = false }
+polars-io = { git = "https://github.com/pola-rs/polars.git", rev = "58a38af21dccaf3326514494a1db118601c8c2ca", default-features = false }
+polars-lazy = { git = "https://github.com/pola-rs/polars.git", rev = "58a38af21dccaf3326514494a1db118601c8c2ca", default-features = false }
 thiserror = "1"
 smartstring = { version = "1" }
 serde_json = { version = "1" }
 either = "1.13.0"
-hashbrown = { version = "0.15.0", features = ["rayon", "serde"] }
+hashbrown = { version = "0.15.2", features = ["rayon", "serde"] }
 
 [dependencies.polars]
 features = [
@@ -162,7 +162,7 @@ features = [
   "azure"
 ]
 git = "https://github.com/pola-rs/polars.git"
-rev = "2dce3d3b5c80ae7522a3435f844fac8fed9dc9e8"
+rev = "58a38af21dccaf3326514494a1db118601c8c2ca"
 
 [build-dependencies]
 napi-build = "2.1.3"

__tests__/dataframe.test.ts

@@ -1680,7 +1680,7 @@ describe("io", () => {
     expect(actual).toEqual(expected);
   });
   test("writeCSV:string:sep", () => {
-    const actual = df.clone().writeCSV({ sep: "X" }).toString();
+    const actual = df.clone().writeCSV({ separator: "X" }).toString();
     const expected = "fooXbar\n1X6\n2X2\n9X8\n";
     expect(actual).toEqual(expected);
   });
@@ -1689,14 +1689,14 @@ describe("io", () => {
       bar: ["a,b,c", "d,e,f", "g,h,i"],
       foo: [1, 2, 3],
     });
-    const actual = df.writeCSV({ quote: "^" }).toString();
+    const actual = df.writeCSV({ quoteChar: "^" }).toString();
     const expected = "bar,foo\n^a,b,c^,1.0\n^d,e,f^,2.0\n^g,h,i^,3.0\n";
     expect(actual).toEqual(expected);
   });
   test("writeCSV:string:header", () => {
     const actual = df
       .clone()
-      .writeCSV({ sep: "X", includeHeader: false, lineTerminator: "|" })
+      .writeCSV({ separator: "X", includeHeader: false, lineTerminator: "|" })
       .toString();
     const expected = "1X6|2X2|9X8|";
     expect(actual).toEqual(expected);

__tests__/io.test.ts

@@ -52,6 +52,21 @@ describe("read:csv", () => {
       csvString.slice(0, 22),
     );
   });
+  it("can read from a csv buffer with newline in the header", () => {
+    const csvBuffer = Buffer.from(
+      '"name\na","height\nb"\n"John",172.23\n"Anna",1653.34',
+    );
+    const df = pl.readCSV(csvBuffer, {
+      quoteChar: '"',
+      sep: ",",
+      hasHeader: false,
+      skipRows: 1,
+    });
+    expect(df.toRecords()).toEqual([
+      { column_1: "John", column_2: 172.23 },
+      { column_1: "Anna", column_2: 1653.34 },
+    ]);
+  });
   it("can read from a csv buffer", () => {
     const csvBuffer = Buffer.from("foo,bar,baz\n1,2,3\n4,5,6\n", "utf-8");
     const df = pl.readCSV(csvBuffer);

package.json

@@ -58,16 +58,16 @@
     "@napi-rs/cli": "^2.18.4",
     "@types/chance": "^1.1.6",
     "@types/jest": "^29.5.14",
-    "@types/node": "^22.8.6",
+    "@types/node": "^22.10.1",
     "chance": "^1.1.12",
     "jest": "^29.7.0",
     "source-map-support": "^0.5.21",
     "ts-jest": "^29.2.5",
     "ts-node": "^10.9.2",
-    "typedoc": "^0.26.10",
-    "typescript": "5.6.3"
+    "typedoc": "^0.27.3",
+    "typescript": "5.7.2"
   },
-  "packageManager": "[email protected].0",
+  "packageManager": "[email protected].3",
   "workspaces": [
     "benches"
   ]

polars/dataframe.ts

@@ -12,10 +12,10 @@ import { type LazyDataFrame, _LazyDataFrame } from "./lazy/dataframe";
 import { Expr } from "./lazy/expr";
 import { Series, _Series } from "./series";
 import type {
+  CsvWriterOptions,
   FillNullStrategy,
   JoinOptions,
   WriteAvroOptions,
-  WriteCsvOptions,
   WriteIPCOptions,
   WriteParquetOptions,
 } from "./types";
@@ -61,8 +61,8 @@ interface WriteMethods {
    * @param options.includeBom - Whether to include UTF-8 BOM in the CSV output.
    * @param options.lineTerminator - String used to end each row.
    * @param options.includeHeader - Whether or not to include header in the CSV output.
-   * @param options.sep - Separate CSV fields with this symbol. _defaults to `,`
-   * @param options.quote - Character to use for quoting. Default: \" Note: it will note be used when sep is used
+   * @param options.separator - Separate CSV fields with this symbol. _defaults to `,`
+   * @param options.quoteChar - Character to use for quoting. Default: \" Note: it will note be used when sep is used
    * @param options.batchSize - Number of rows that will be processed per thread.
    * @param options.datetimeFormat - A format string, with the specifiers defined by the
    *    `chrono <https://docs.rs/chrono/latest/chrono/format/strftime/index.html>`_
@@ -109,8 +109,8 @@ interface WriteMethods {
    * @category IO
    */
   writeCSV(): Buffer;
-  writeCSV(options: WriteCsvOptions): Buffer;
-  writeCSV(dest: string | Writable, options?: WriteCsvOptions): void;
+  writeCSV(options: CsvWriterOptions): Buffer;
+  writeCSV(dest: string | Writable, options?: CsvWriterOptions): void;
   /**
    * Write Dataframe to JSON string, file, or write stream
    * @param destination file or write stream

polars/io.ts

@@ -503,7 +503,7 @@ export function readAvro(pathOrBody, options = {}) {
    @param options.rechunk - In case of reading multiple files via a glob pattern rechunk the final DataFrame into contiguous memory chunks.
    @param options.lowMemory - Reduce memory pressure at the expense of performance.
    @param options.cache - Cache the result after reading.
-   @param options.storageOptions - Options that indicate how to connect to a cloud provider.
+   @param options.cloudOptions - Options that indicate how to connect to a cloud provider.
         If the cloud provider is not supported by Polars, the storage options are passed to `fsspec.open()`.
 
         The cloud providers currently supported are AWS, GCP, and Azure.
@@ -513,7 +513,7 @@ export function readAvro(pathOrBody, options = {}) {
         * `gcp <https://docs.rs/object_store/latest/object_store/gcp/enum.GoogleConfigKey.html>`_
         * `azure <https://docs.rs/object_store/latest/object_store/azure/enum.AzureConfigKey.html>`_
 
-        If `storage_options` is not provided, Polars will try to infer the information from environment variables.
+        If `cloudOptions` is not provided, Polars will try to infer the information from environment variables.
     @param retries - Number of retries if accessing a cloud instance fails.
     @param includeFilePaths - Include the path of the source file(s) as a column with this name.
  */

polars/lazy/dataframe.ts

@@ -3,9 +3,9 @@ import pli from "../internals/polars_internal";
 import type { Series } from "../series";
 import type { Deserialize, GroupByOps, Serialize } from "../shared_traits";
 import type {
+  CsvWriterOptions,
   LazyJoinOptions,
   LazyOptions,
-  SinkCsvOptions,
   SinkParquetOptions,
 } from "../types";
 import {
@@ -541,7 +541,7 @@ export interface LazyDataFrame extends Serialize, GroupByOps<LazyGroupBy> {
     >>> lf.sinkCsv("out.csv")
   */
 
-  sinkCSV(path: string, options?: SinkCsvOptions): void;
+  sinkCSV(path: string, options?: CsvWriterOptions): void;
 
   /***
    *
@@ -580,6 +580,18 @@ export interface LazyDataFrame extends Serialize, GroupByOps<LazyGroupBy> {
     @param simplifyExpression - Run simplify expressions optimization. Default -> true
     @param slicePushdown - Slice pushdown optimization. Default -> true
     @param noOptimization - Turn off (certain) optimizations. Default -> false
+    @param cloudOptions - Options that indicate how to connect to a cloud provider.
+        If the cloud provider is not supported by Polars, the storage options are passed to `fsspec.open()`.
+
+        The cloud providers currently supported are AWS, GCP, and Azure.
+        See supported keys here:
+
+        * `aws <https://docs.rs/object_store/latest/object_store/aws/enum.AmazonS3ConfigKey.html>`_
+        * `gcp <https://docs.rs/object_store/latest/object_store/gcp/enum.GoogleConfigKey.html>`_
+        * `azure <https://docs.rs/object_store/latest/object_store/azure/enum.AzureConfigKey.html>`_
+
+        If `cloudOptions` is not provided, Polars will try to infer the information from environment variables.
+    @param retries - Number of retries if accessing a cloud instance fails.
 
     Examples
     --------
@@ -1078,7 +1090,7 @@ export const _LazyDataFrame = (_ldf: any): LazyDataFrame => {
     withRowCount(name = "row_nr") {
       return _LazyDataFrame(_ldf.withRowCount(name));
     },
-    sinkCSV(path, options: SinkCsvOptions = {}) {
+    sinkCSV(path, options: CsvWriterOptions = {}) {
       options.maintainOrder = options.maintainOrder ?? false;
       _ldf.sinkCsv(path, options);
     },

polars/lazy/functions.ts

@@ -650,7 +650,7 @@ export function spearmanRankCorr(a: ExprOrString, b: ExprOrString): Expr {
   a = exprToLitOrExpr(a, false);
   b = exprToLitOrExpr(b, false);
 
-  return _Expr(pli.spearmanRankCorr(a, b, null, false));
+  return _Expr(pli.spearmanRankCorr(a, b, false));
 }
 
 /** Get the last n rows of an Expression. */
@@ -964,7 +964,7 @@ export function sumHorizontal(exprs: ExprOrString | ExprOrString[]): Expr {
 
   exprs = selectionToExprList(exprs);
 
-  return _Expr(pli.sumHorizontal(exprs));
+  return _Expr(pli.sumHorizontal(exprs, true));
 }
 
 // // export function collect_all() {}

polars/types.ts

@@ -39,33 +39,16 @@ export interface ConcatOptions {
   how?: "vertical" | "horizontal" | "diagonal";
 }
 /**
- * Options for {@link DataFrame.writeCSV}
- * @category Options
- */
-export interface WriteCsvOptions {
-  includeBom?: boolean;
-  includeHeader?: boolean;
-  sep?: string;
-  quote?: string;
-  lineTerminator?: string;
-  batchSize?: number;
-  datetimeFormat?: string;
-  dateFormat?: string;
-  timeFormat?: string;
-  floatPrecision?: number;
-  nullValue?: string;
-}
-/**
+ * Options for @see {@link DataFrame.writeCSV}
  * Options for @see {@link LazyDataFrame.sinkCSV}
  * @category Options
  */
-export interface SinkCsvOptions {
-  includeHeader?: boolean;
-  quote?: string;
+export interface CsvWriterOptions {
   includeBom?: boolean;
+  includeHeader?: boolean;
   separator?: string;
-  lineTerminator?: string;
   quoteChar?: string;
+  lineTerminator?: string;
   batchSize?: number;
   datetimeFormat?: string;
   dateFormat?: string;
@@ -91,6 +74,8 @@ export interface SinkParquetOptions {
   simplifyExpression?: boolean;
   slicePushdown?: boolean;
   noOptimization?: boolean;
+  cloudOptions?: Map<string, string>;
+  retries?: number;
 }
 /**
  * Options for {@link DataFrame.writeJSON}
@@ -153,7 +138,7 @@ export interface ScanParquetOptions {
   rechunk?: boolean;
   lowMemory?: boolean;
   useStatistics?: boolean;
-  cloudOptions?: unknown;
+  cloudOptions?: Map<string, string>;
   retries?: number;
   includeFilePaths?: string;
   allowMissingColumns?: boolean;

rust-toolchain

@@ -1 +1 @@
-nightly-2024-10-28
+nightly-2024-11-28