Merge pull request #327 from pitrou/fundable-arrow-decimal32

Add Decimal32/64 in Arrow C++ as a fundable project

Author: SylvainCorlay

src/components/fundable/descriptions/Decimal32InArrowCpp.md

@@ -0,0 +1,40 @@
+#### Overview
+
+Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics.
+
+Fixed-width decimal data in Arrow is usually represented the Decimal128 data type.
+This data type has non-trivial memory costs (16 bytes per value) and computational costs (operations on 128-bit integers must be emulated on most if not all architectures).
+
+Arrow recently gained Decimal32 and Decimal64 data types which, as their names suggest, encode fixed-width decimal data more compactly.
+Decimal32 (resp. Decimal64) is able to represent up to 9 (resp. 18) decimal digits of precision, which is sufficient in many applications.
+
+However, while basic support is present, Decimal32 and Decimal64 are not universally supported by all Arrow components.
+
+We propose to finish implementing support for Decimal32 and Decimal64 types in all components of Arrow C++:
+
+* scalar compute kernels:
+    - `abs`
+    - `round`
+    - `is_in`, `index_in`
+    - `coalesce`
+    - `min_element_wise`, `max_element_wise`
+
+* vector compute kernels:
+    - `dictionary_encode`, `unique`, `value_counts`
+    - `pairwise_diff`
+    - `select_k_unstable`
+    - `replace_with_mask`
+    - `fill_null_forward`, `fill_null_backward`
+
+* aggregate compute kernels:
+    - `sum`, `mean`, `mode`, `tdigest`
+    - `first`, `last`, `min`, `max`
+    - `index`
+
+* CSV reader and writer
+
+* ORC reader and writer
+
+Funders can decide to fund the entire package, or choose the components they are interested in.
+
+##### Are you interested in this project? Either entirely or partially, contact us for more information on how to help us fund it

src/components/fundable/projectsDetails.ts

@@ -3,9 +3,9 @@ import JupyterGISRasterProcessingMD from "@site/src/components/fundable/descript
 import JupyterGISToolsForPythonAPIMD from "@site/src/components/fundable/descriptions/JupyterGISToolsForPythonAPI.md"
 import EmscriptenForgePackageRequestsMD from "@site/src/components/fundable/descriptions/EmscriptenForgePackageRequests.md"
 import SVE2SupportInXsimdMD from "@site/src/components/fundable/descriptions/SVE2SupportInXsimd.md"
-import MatrixOperationsInXtensor from "@site/src/components/fundable/descriptions/MatrixOperationsInXtensor.md"
-import BinaryViewInArrowCpp from "@site/src/components/fundable/descriptions/BinaryViewInArrowCpp.md"
-
+import MatrixOperationsInXtensorMD from "@site/src/components/fundable/descriptions/MatrixOperationsInXtensor.md"
+import BinaryViewInArrowCppMD from "@site/src/components/fundable/descriptions/BinaryViewInArrowCpp.md"
+import Decimal32InArrowCppMD from"@site/src/components/fundable/descriptions/Decimal32InArrowCpp.md"
 export const fundableProjectsDetails = {
     jupyterEcosystem: [
         {
@@ -78,7 +78,7 @@ export const fundableProjectsDetails = {
             title: "Implementing Kazushige Goto Algorithms for Matrix Operations in xtensor",
             pageName: "MatrixOperationsInXtensor",
             shortDescription: "This project aims to integrate Kazushige Goto’s highly optimized matrix multiplication algorithms into the xtensor framework, leveraging the xsimd library for SIMD acceleration.",
-            description: MatrixOperationsInXtensor,
+            description: MatrixOperationsInXtensorMD,
             price: "45 000 €",
             maxNbOfFunders: 1,
             currentNbOfFunders: 0,
@@ -93,12 +93,24 @@ export const fundableProjectsDetails = {
             title: "Complete BinaryView / StringView support in Arrow C++",
             pageName: "BinaryViewInApacheArrow",
             shortDescription: "BinaryView is a more recent and more efficient alternative to Arrow's standard Binary type. It allows for inlined storage of short strings and fast prefix comparison.",
-            description: BinaryViewInArrowCpp,
+            description: BinaryViewInArrowCppMD,
             price: "TBD",
             maxNbOfFunders: 4,
             currentNbOfFunders: 0,
             currentFundingPercentage: 0,
             repoLink: "https://github.com/apache/arrow"
+        },
+        {
+            category: "Apache Arrow and Parquet",
+            title: "Complete Decimal32 / Decimal64 support in Arrow C++",
+            pageName: "Decimal32InApacheArrow",
+            shortDescription: "Decimal32 and Decimal64 are more compact and computationally more efficient data types than the standard Decimal128.",
+            description: Decimal32InArrowCppMD,
+            price: "TBD",
+            maxNbOfFunders: 2,
+            currentNbOfFunders: 0,
+            currentFundingPercentage: 0,
+            repoLink: "https://github.com/apache/arrow"
         }
     ]
 

src/pages/fundable/Decimal32InApacheArrow/GetAQuote.tsx

@@ -0,0 +1,9 @@
+import useDocusaurusContext from '@docusaurus/useDocusaurusContext';
+import GetAQuotePage from '@site/src/components/fundable/GetAQuotePage';
+
+export default function FundablePage() {
+    const { siteConfig } = useDocusaurusContext();
+    return (
+      <GetAQuotePage/>
+    );
+}

src/pages/fundable/Decimal32InApacheArrow/index.tsx

@@ -0,0 +1,9 @@
+import useDocusaurusContext from '@docusaurus/useDocusaurusContext';
+import LargeProjectCardPage from '@site/src/components/fundable/LargeProjectCardPage';
+
+export default function FundablePage() {
+    const { siteConfig } = useDocusaurusContext();
+    return (
+       <LargeProjectCardPage/>
+    );
+}