From f4815eb60c2b87b9c5402bc157af9d5b3ed958a6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?F=C3=A9lix=20Baylac-Jacqu=C3=A9?= <felix@alternativebit.fr>
Date: Tue, 29 Jun 2021 21:02:27 +0200
Subject: [PATCH] Initial benchmark: comparing haskell's Text with icu on EN
 corpus

Run `make all` to run the benchmark.
---
 Makefile                   | 22 ++++++++++++++++++++++
 default.nix                | 24 ++++++++++++++++++++++++
 haskell/HaskellReadUTF8.hs |  7 +++++++
 icu/icu-read-utf8.c        | 12 ++++++++++++
 4 files changed, 65 insertions(+)
 create mode 100644 Makefile
 create mode 100644 default.nix
 create mode 100644 haskell/HaskellReadUTF8.hs
 create mode 100644 icu/icu-read-utf8.c

diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..5c98cdf
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,22 @@
+CFLAGS=-O2 -Wall $(shell pkgconf -cflags icu-io)
+LDFLAGS=$(shell pkgconf -libs icu-io)
+CC=gcc
+
+all: haskell-read-utf8 icu-read-utf8 bench
+.PHONY: all
+
+bench: haskell-read-utf8 icu-read-utf8
+	hyperfine ./haskell-read-utf8 ./icu-read-utf8
+.PHONE: bench
+
+haskell-read-utf8: ./haskell/HaskellReadUTF8.hs
+	ghc -o ./haskell-read-utf8 -O ./haskell/HaskellReadUTF8.hs
+
+icu-read-utf8: ./icu/icu-read-utf8.c
+	$(CC) $(CFLAGS) $(LDFLAGS) ./icu/icu-read-utf8.c -o ./icu-read-utf8
+
+clean:
+	rm -f ./haskell/*.{o,hi}
+	rm -f ./haskell-read-utf8
+	rm -f ./icu-read-utf8
+.PHONY: clean
diff --git a/default.nix b/default.nix
new file mode 100644
index 0000000..c882b00
--- /dev/null
+++ b/default.nix
@@ -0,0 +1,24 @@
+{ pkgs ? import <nixpkgs> {} }:
+
+let ghcClosure =
+  pkgs.haskellPackages.ghcWithPackages
+  (p:[
+    p.text
+  ]);
+
+in pkgs.stdenv.mkDerivation {
+  pname = "bench-my-utf8";
+  version = "0.0.1";
+  installPhase = ''
+    mkdir -p $out/bin
+    mv haskell-read-utf8 $out/bin
+  '';
+  nativeBuildInputs = [
+    pkgs.gnumake
+    ghcClosure
+    pkgs.gcc
+    pkgs.icu
+    pkgs.hyperfine
+    pkgs.pkgconf
+  ];
+}
diff --git a/haskell/HaskellReadUTF8.hs b/haskell/HaskellReadUTF8.hs
new file mode 100644
index 0000000..7f45316
--- /dev/null
+++ b/haskell/HaskellReadUTF8.hs
@@ -0,0 +1,7 @@
+module Main where
+
+import qualified Data.Text.IO as TIO
+import qualified Data.Text as T
+
+main :: IO ()
+main = TIO.readFile "text-test-data/english.txt" >> pure ()
diff --git a/icu/icu-read-utf8.c b/icu/icu-read-utf8.c
new file mode 100644
index 0000000..0f71069
--- /dev/null
+++ b/icu/icu-read-utf8.c
@@ -0,0 +1,12 @@
+#include <unicode/ustdio.h>
+#include <stdlib.h>
+#include <unicode/umachine.h>
+
+int main(void)
+{
+    UFILE *in = u_fopen("text-test-data/english.txt", "r", NULL, "UTF-8");
+    UChar *charBuff = malloc(100000000 * sizeof(UChar));
+    int32_t i = u_file_read(charBuff, 100000000, in);
+    u_printf("%s\n", charBuff);
+    u_printf("%i\n", i);
+}