From 51a9ef72c7e32f06d2413a5aea5751df2780063b Mon Sep 17 00:00:00 2001
From: "kr.angelov" <kr.angelov@gmail.com>
Date: Fri, 21 Mar 2014 21:25:05 +0000
Subject: refactor the compilation of CFG and EBNF grammars. Now they are
 parsed by using GF.Grammar.Parser just like the ordinary GF grammars.
 Furthermore now GF.Speech.CFG is moved to GF.Grammar.CFG. The new module is
 used by both the speech conversion utils and by the compiler for CFG
 grammars. The parser for CFG now consumes a lot less memory and can be used
 with grammars with more than 4 000 000 productions.

---
 src/compiler/GF/Compile/GetGrammar.hs | 38 ++++++++++++++++++++---------------
 1 file changed, 22 insertions(+), 16 deletions(-)

(limited to 'src/compiler/GF/Compile/GetGrammar.hs')

diff --git a/src/compiler/GF/Compile/GetGrammar.hs b/src/compiler/GF/Compile/GetGrammar.hs
index 6393d51d2..4647cfcb4 100644
--- a/src/compiler/GF/Compile/GetGrammar.hs
+++ b/src/compiler/GF/Compile/GetGrammar.hs
@@ -12,27 +12,25 @@
 -- this module builds the internal GF grammar that is sent to the type checker
 -----------------------------------------------------------------------------
 
-module GF.Compile.GetGrammar (getSourceModule) where
+module GF.Compile.GetGrammar (getSourceModule, getCFRules, getEBNFRules) where
 
 import Prelude hiding (catch)
 
 import GF.Data.Operations
 
---import GF.System.Catch
 import GF.Infra.UseIO
 import GF.Infra.Option(Options,optPreprocessors,addOptions,renameEncoding,optEncoding,flag,defaultEncoding)
 import GF.Grammar.Lexer
 import GF.Grammar.Parser
 import GF.Grammar.Grammar
---import GF.Compile.Coding
+import GF.Grammar.CFG
+import GF.Grammar.EBNF
 import GF.Compile.ReadFiles(parseSource,lift)
---import GF.Text.Coding(decodeUnicodeIO)
 
 import qualified Data.ByteString.Char8 as BS
 import Data.Char(isAscii)
 import Control.Monad (foldM,when,unless)
 import System.Cmd (system)
---import System.IO(mkTextEncoding) --,utf8
 import System.Directory(removeFile,getCurrentDirectory)
 import System.FilePath(makeRelative)
 
@@ -64,17 +62,25 @@ getSourceModule opts file0 =
           --lift $ transcodeModule' (i,mi) -- old lexer
             return (i,mi) -- new lexer
 
-{-
-transcodeModule sm00 =
-  do enc <- mkTextEncoding (getEncoding (mflags (snd sm00)))
-     let sm = decodeStringsInModule enc sm00
-     return sm
-
-transcodeModule' sm00 =
-  do let enc = utf8
-     let sm = decodeStringsInModule enc sm00
-     return sm
--}
+getCFRules :: Options -> FilePath -> IOE [CFRule]
+getCFRules opts fpath = do
+  raw <- liftIO (BS.readFile fpath)
+  (optCoding,parsed) <- parseSource opts pCFRules raw
+  case parsed of
+    Left (Pn l c,msg) -> do cwd <- lift $ getCurrentDirectory
+                            let location = makeRelative cwd fpath++":"++show l++":"++show c
+                            raise (location++":\n   "++msg)
+    Right rules       -> return rules
+
+getEBNFRules :: Options -> FilePath -> IOE [ERule]
+getEBNFRules opts fpath = do
+  raw <- liftIO (BS.readFile fpath)
+  (optCoding,parsed) <- parseSource opts pEBNFRules raw
+  case parsed of
+    Left (Pn l c,msg) -> do cwd <- lift $ getCurrentDirectory
+                            let location = makeRelative cwd fpath++":"++show l++":"++show c
+                            raise (location++":\n   "++msg)
+    Right rules       -> return rules
 
 runPreprocessor :: Temporary -> String -> IO Temporary
 runPreprocessor tmp0 p =
-- 
cgit v1.2.3