diff options
| author | hallgren <hallgren@chalmers.se> | 2013-11-26 16:12:03 +0000 |
|---|---|---|
| committer | hallgren <hallgren@chalmers.se> | 2013-11-26 16:12:03 +0000 |
| commit | 3f57151cc346be0fbf0726d4953f3529ea45e7f4 (patch) | |
| tree | 6106269ff6ea7abb0c27d15cafdd818bb91b6bf7 /src/compiler/GF/Compile | |
| parent | 9d7fdf7c9a525a3b5659a566f76d26d151dcd664 (diff) | |
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
Diffstat (limited to 'src/compiler/GF/Compile')
| -rw-r--r-- | src/compiler/GF/Compile/CheckGrammar.hs | 6 | ||||
| -rw-r--r-- | src/compiler/GF/Compile/GrammarToPGF.hs | 4 |
2 files changed, 5 insertions, 5 deletions
diff --git a/src/compiler/GF/Compile/CheckGrammar.hs b/src/compiler/GF/Compile/CheckGrammar.hs index 568686f92..d924e413e 100644 --- a/src/compiler/GF/Compile/CheckGrammar.hs +++ b/src/compiler/GF/Compile/CheckGrammar.hs @@ -298,9 +298,9 @@ checkInfo opts sgr (m,mo) c info = do -- | for grammars obtained otherwise than by parsing ---- update!! checkReservedId :: Ident -> Check () -checkReservedId x - | isReservedWord (ident2bs x) = checkWarn (text "reserved word used as identifier:" <+> ppIdent x) - | otherwise = return () +checkReservedId x = + when (isReservedWord x) $ + checkWarn (text "reserved word used as identifier:" <+> ppIdent x) -- auxiliaries diff --git a/src/compiler/GF/Compile/GrammarToPGF.hs b/src/compiler/GF/Compile/GrammarToPGF.hs index 25db4bac7..5917b709c 100644 --- a/src/compiler/GF/Compile/GrammarToPGF.hs +++ b/src/compiler/GF/Compile/GrammarToPGF.hs @@ -5,7 +5,7 @@ module GF.Compile.GrammarToPGF (mkCanon2pgf) where import GF.Compile.GeneratePMCFG import GF.Compile.GenerateBC -import PGF(CId,mkCId,bsCId) +import PGF(CId,mkCId,utf8CId) import PGF.Data(fidInt,fidFloat,fidString,fidVar) import PGF.Optimize(updateProductionIndices) --import qualified PGF.Macros as CM @@ -103,7 +103,7 @@ mkCanon2pgf opts gr am = do return (seqs, ((m,id), info) : is) i2i :: Ident -> CId -i2i = bsCId . ident2bs +i2i = utf8CId . ident2utf8 mkType :: [Ident] -> A.Type -> C.Type mkType scope t = |