From cffdb6de59ceb3fd9983a1c19476e5109da8db97 Mon Sep 17 00:00:00 2001
From: Joe Wilm <joe@jwilm.com>
Date: Sat, 17 Sep 2016 15:51:45 -0700
Subject: Add support for UTF-8

This adds a table-driven UTF-8 parser which only has a single branch for
the entire parser. UTF-8 support is essentially bolted onto the VTE
parser. Not the most elegant, but it does prevent the transition tables
from blowing up.

Instead of refactoring the syntax extension to handle both table
definitions, I've opted to copy/paste now for both simplicities sake and
because I can't see a clear path to a minimal shared solution.
---
 src/table.rs | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'src/table.rs')

diff --git a/src/table.rs b/src/table.rs
index 923c7eb..d2034b8 100644
--- a/src/table.rs
+++ b/src/table.rs
@@ -6,6 +6,9 @@ use definitions::Action;
 pub static STATE_CHANGE: [[u8; 256]; 16] =
     [
 
+     // Beginning of UTF-8 2 byte sequence
+     // Beginning of UTF-8 3 byte sequence
+     // Beginning of UTF-8 4 byte sequence
 
 
 
@@ -280,11 +283,13 @@ pub static STATE_CHANGE: [[u8; 256]; 16] =
       80u8, 80u8, 80u8, 80u8, 80u8, 80u8, 0u8, 80u8, 0u8, 0u8, 0u8, 0u8, 0u8,
       0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8,
       0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8,
-      0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8,
-      0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8,
-      0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8,
-      0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8,
-      0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8],
+      0u8, 0u8, 0u8, 0u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8,
+      255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8,
+      255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8,
+      255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8,
+      255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8, 255u8,
+      255u8, 255u8, 255u8, 255u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8, 0u8,
+      0u8, 0u8],
      [112u8, 112u8, 112u8, 112u8, 112u8, 112u8, 112u8, 112u8, 112u8, 112u8,
       112u8, 112u8, 112u8, 112u8, 112u8, 112u8, 112u8, 112u8, 112u8, 112u8,
       112u8, 112u8, 112u8, 112u8, 0u8, 112u8, 0u8, 0u8, 112u8, 112u8, 112u8,
@@ -366,7 +371,7 @@ pub static ENTRY_ACTIONS: &'static [Action] =
       Action::OscStart, // State::OscString
       Action::None, // State::SosPmApcString
       Action::None];
- // State::Unused__
+ // State::Utf8
 
 pub static EXIT_ACTIONS: &'static [Action] =
     &[Action::None, // State::Anywhere
@@ -384,4 +389,4 @@ pub static EXIT_ACTIONS: &'static [Action] =
       Action::None, // State::Ground
       Action::OscEnd, // State::OscString
       Action::None, // State::SosPmApcString
-      Action::None]; // State::Unused__
+      Action::None]; // State::Utf8
-- 
cgit