From 7a72b0b4f9b96b005b4a87cec870d33af3b18f09 Mon Sep 17 00:00:00 2001
From: epriestley <git@epriestley.com>
Date: Wed, 10 Aug 2011 11:57:07 -0700
Subject: [PATCH] Be slightly less dumb about detecting "binary" files

Summary:
A better definition of "binary" is "not utf-8", instead of "has some characters
not in this arbitrary regexp". Principally, this makes files with windows
newlines not autodetect as binary.

This might fix some of the issues in T365.

Test Plan: @egillth applied this patch and verified that Diffusion now shows
file content instead of detecting everything as binary in his repo full of
Windows newlines.
Reviewed By: jungejason
Reviewers: egillth, tuomaspelkonen, jungejason, aran
CC: aran, jungejason
Differential Revision: 799
---
 src/parser/diff/ArcanistDiffParser.php | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/parser/diff/ArcanistDiffParser.php b/src/parser/diff/ArcanistDiffParser.php
index f7fece8f..28a7dd83 100644
--- a/src/parser/diff/ArcanistDiffParser.php
+++ b/src/parser/diff/ArcanistDiffParser.php
@@ -751,7 +751,7 @@ class ArcanistDiffParser {
 
       $is_binary = false;
       if ($this->detectBinaryFiles) {
-        $is_binary = preg_match('/([^\x09\x0A\x20-\x7E]+)/', $corpus);
+        $is_binary = !phutil_is_utf8($corpus);
       }
 
       if ($is_binary) {