From 3f57151cc346be0fbf0726d4953f3529ea45e7f4 Mon Sep 17 00:00:00 2001 From: hallgren Date: Tue, 26 Nov 2013 16:12:03 +0000 Subject: Represent identifiers as UTF-8-encoded ByteStrings This was a fairly simple change thanks to previous work on making the Ident type abstract and the fact that PGF.CId already uses UTF-8-encoded ByteStrings. One potential pitfall is that Data.ByteString.UTF8 uses the same type for ByteStrings as Data.ByteString. I renamed ident2bs to ident2utf8 and bsCId to utf8CId, to make it clearer that they work with UTF-8-encoded ByteStrings. Since both the compiler input and identifiers are now UTF-8-encoded ByteStrings, the lexer now creates identifiers without copying any characters. **END OF DESCRIPTION*** Place the long patch description above the ***END OF DESCRIPTION*** marker. The first line of this file will be the patch name. This patch contains the following changes: M ./src/compiler/GF/Compile/CheckGrammar.hs -3 +3 M ./src/compiler/GF/Compile/GrammarToPGF.hs -2 +2 M ./src/compiler/GF/Grammar/Binary.hs -5 +1 M ./src/compiler/GF/Grammar/Lexer.x -11 +13 M ./src/compiler/GF/Infra/Ident.hs -19 +36 M ./src/runtime/haskell/PGF.hs -1 +1 M ./src/runtime/haskell/PGF/CId.hs -2 +3 --- src/runtime/haskell/PGF.hs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/runtime/haskell/PGF.hs') diff --git a/src/runtime/haskell/PGF.hs b/src/runtime/haskell/PGF.hs index 0e3c79f40..c1d903f4f 100644 --- a/src/runtime/haskell/PGF.hs +++ b/src/runtime/haskell/PGF.hs @@ -22,7 +22,7 @@ module PGF( CId, mkCId, wildCId, showCId, readCId, -- extra - ppCId, pIdent, bsCId, + ppCId, pIdent, utf8CId, -- * Languages Language, -- cgit v1.2.3