* Compile the lexer as C++ code. Remove all the redundant C/C++

  marshalling code.

4 files changed, 234 insertions, 276 deletions

diff --git a/src/libexpr/Makefile.am b/src/libexpr/Makefile.am
index 3696e99d54f6..e80adaf02283 100644
--- a/src/libexpr/Makefile.am
+++ b/src/libexpr/Makefile.am
@@ -1,14 +1,14 @@
 pkglib_LTLIBRARIES = libexpr.la
 
-libexpr_la_SOURCES = nixexpr.cc nixexpr.hh parser.cc parser.hh \
+libexpr_la_SOURCES = nixexpr.cc nixexpr.hh \
  eval.cc eval.hh primops.cc \
- lexer-tab.c lexer-tab.h parser-tab.cc parser-tab.hh \
+ lexer-tab.cc lexer-tab.hh parser-tab.cc parser-tab.hh \
  get-drvs.cc get-drvs.hh \
  attr-path.cc attr-path.hh \
  expr-to-xml.cc expr-to-xml.hh 
 
 BUILT_SOURCES = nixexpr-ast.cc nixexpr-ast.hh \
- parser-tab.hh lexer-tab.h parser-tab.cc lexer-tab.c
+ parser-tab.hh lexer-tab.hh parser-tab.cc lexer-tab.cc
 
 EXTRA_DIST = lexer.l parser.y nixexpr-ast.def nixexpr-ast.cc
 
@@ -24,8 +24,8 @@ AM_CFLAGS = \
 parser-tab.cc parser-tab.hh: parser.y
 	$(bison) -v -o parser-tab.cc $(srcdir)/parser.y -d
 
-lexer-tab.c lexer-tab.h: lexer.l
-	$(flex) --outfile lexer-tab.c --header-file=lexer-tab.h $(srcdir)/lexer.l 
+lexer-tab.cc lexer-tab.hh: lexer.l
+	$(flex) --outfile lexer-tab.cc --header-file=lexer-tab.hh $(srcdir)/lexer.l 
 
 
 # ATerm helper function generation.
diff --git a/src/libexpr/lexer.l b/src/libexpr/lexer.l
index bbf872ff6ec8..625e044b682f 100644
--- a/src/libexpr/lexer.l
+++ b/src/libexpr/lexer.l
@@ -7,16 +7,23 @@
 
 
 %{
-#include <string.h>
-#include <aterm2.h>
+#include "aterm.hh"
+#include "nixexpr.hh"
+#include "nixexpr-ast.hh"
 #include "parser-tab.hh"
 
+using namespace nix;
+
+namespace nix {
+
+    
 static void initLoc(YYLTYPE * loc)
 {
     loc->first_line = 1;
     loc->first_column = 1;
 }
 
+    
 static void adjustLoc(YYLTYPE * loc, const char * s, size_t len)
 {
     while (len--) {
@@ -35,12 +42,32 @@ static void adjustLoc(YYLTYPE * loc, const char * s, size_t len)
     }
 }
 
-ATerm toATerm(const char * s)
+
+static Expr unescapeStr(const char * s)
 {
-    return (ATerm) ATmakeAppl0(ATmakeAFun((char *) s, 0, ATtrue));
+    string t;
+    char c;
+    while ((c = *s++)) {
+        if (c == '\\') {
+            assert(*s);
+            c = *s++;
+            if (c == 'n') t += '\n';
+            else if (c == 'r') t += '\r';
+            else if (c == 't') t += '\t';
+            else t += c;
+        }
+        else if (c == '\r') {
+            /* Normalise CR and CR/LF into LF. */
+            t += '\n';
+            if (*s == '\n') s++; /* cr/lf */
+        }
+        else t += c;
+    }
+    return makeStr(toATerm(t));
 }
 
-ATerm unescapeStr(const char * s);
+ 
+}
 
 #define YY_USER_INIT initLoc(yylloc)
 #define YY_USER_ACTION adjustLoc(yylloc, yytext, yyleng);
@@ -106,12 +133,17 @@ inherit     { return INHERIT; }
 
 %%
 
+
+namespace nix {
+    
 /* Horrible, disgusting hack: allow the parser to set the scanner
    start condition back to STRING.  Necessary in interpolations like
    "foo${expr}bar"; after the close brace we have to go back to the
    STRING state. */
 void backToString(yyscan_t scanner)
 {
-    struct yyguts_t * yyg = (struct yyguts_t*) scanner;
+    struct yyguts_t * yyg = (struct yyguts_t *) scanner;
     BEGIN(STRING);
 }
+
+}
diff --git a/src/libexpr/parser.cc b/src/libexpr/parser.cc
deleted file mode 100644
index 20a6c9be2efd..000000000000
--- a/src/libexpr/parser.cc
+++ /dev/null
@@ -1,244 +0,0 @@
-#include "parser.hh"
-#include "aterm.hh"
-#include "util.hh"
-#include "nixexpr-ast.hh"
-    
-#include <sstream>
-
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include <unistd.h>
-
-
-extern "C" {
-
-#include "parser-tab.hh"
-#include "lexer-tab.h"
-    
-}
-
-namespace nix {
-
-
-struct ParseData 
-{
-    Expr result;
-    Path basePath;
-    Path path;
-    string error;
-};
- 
-}
-
-
-int yyparse(yyscan_t scanner, nix::ParseData * data);
-
-
-namespace nix {
-
-
-void setParseResult(ParseData * data, ATerm t)
-{
-    data->result = t;
-}
-
-ATerm absParsedPath(ParseData * data, ATerm t)
-{
-    return toATerm(absPath(aterm2String(t), data->basePath));
-}
-    
-void parseError(ParseData * data, char * error, int line, int column)
-{
-    data->error = (format("%1%, at `%2%':%3%:%4%")
-        % error % data->path % line % column).str();
-}
-        
-ATerm fixAttrs(int recursive, ATermList as)
-{
-    ATermList bs = ATempty, cs = ATempty;
-    ATermList * is = recursive ? &cs : &bs;
-    for (ATermIterator i(as); i; ++i) {
-        ATermList names;
-        Expr src;
-        ATerm pos;
-        if (matchInherit(*i, src, names, pos)) {
-            bool fromScope = matchScope(src);
-            for (ATermIterator j(names); j; ++j) {
-                Expr rhs = fromScope ? makeVar(*j) : makeSelect(src, *j);
-                *is = ATinsert(*is, makeBind(*j, rhs, pos));
-            }
-        } else bs = ATinsert(bs, *i);
-    }
-    if (recursive)
-        return makeRec(bs, cs);
-    else
-        return makeAttrs(bs);
-}
-
-const char * getPath(ParseData * data)
-{
-    return data->path.c_str();
-}
-
-extern "C" {
-Expr unescapeStr(const char * s)
-{
-    string t;
-    char c;
-    while ((c = *s++)) {
-        if (c == '\\') {
-            assert(*s);
-            c = *s++;
-            if (c == 'n') t += '\n';
-            else if (c == 'r') t += '\r';
-            else if (c == 't') t += '\t';
-            else t += c;
-        }
-        else if (c == '\r') {
-            /* Normalise CR and CR/LF into LF. */
-            t += '\n';
-            if (*s == '\n') s++; /* cr/lf */
-        }
-        else t += c;
-    }
-    return makeStr(toATerm(t));
-}
-}
-
-
-static void checkAttrs(ATermMap & names, ATermList bnds)
-{
-    for (ATermIterator i(bnds); i; ++i) {
-        ATerm name;
-        Expr e;
-        ATerm pos;
-        if (!matchBind(*i, name, e, pos)) abort(); /* can't happen */
-        if (names.get(name))
-            throw EvalError(format("duplicate attribute `%1%' at %2%")
-                % aterm2String(name) % showPos(pos));
-        names.set(name, name);
-    }
-}
-
-
-static void checkAttrSets(ATerm e)
-{
-    ATermList formals;
-    ATerm body, pos;
-    if (matchFunction(e, formals, body, pos)) {
-        ATermMap names(ATgetLength(formals));
-        for (ATermIterator i(formals); i; ++i) {
-            ATerm name;
-            ATerm d1, d2;
-            if (!matchFormal(*i, name, d1, d2)) abort();
-            if (names.get(name))
-                throw EvalError(format("duplicate formal function argument `%1%' at %2%")
-                    % aterm2String(name) % showPos(pos));
-            names.set(name, name);
-        }
-    }
-
-    ATermList bnds;
-    if (matchAttrs(e, bnds)) {
-        ATermMap names(ATgetLength(bnds));
-        checkAttrs(names, bnds);
-    }
-    
-    ATermList rbnds, nrbnds;
-    if (matchRec(e, rbnds, nrbnds)) {
-        ATermMap names(ATgetLength(rbnds) + ATgetLength(nrbnds));
-        checkAttrs(names, rbnds);
-        checkAttrs(names, nrbnds);
-    }
-    
-    if (ATgetType(e) == AT_APPL) {
-        int arity = ATgetArity(ATgetAFun(e));
-        for (int i = 0; i < arity; ++i)
-            checkAttrSets(ATgetArgument(e, i));
-    }
-
-    else if (ATgetType(e) == AT_LIST)
-        for (ATermIterator i((ATermList) e); i; ++i)
-            checkAttrSets(*i);
-}
-
-
-static Expr parse(EvalState & state,
-    const char * text, const Path & path,
-    const Path & basePath)
-{
-    yyscan_t scanner;
-    ParseData data;
-    data.basePath = basePath;
-    data.path = path;
-
-    yylex_init(&scanner);
-    yy_scan_string(text, scanner);
-    int res = yyparse(scanner, &data);
-    yylex_destroy(scanner);
-    
-    if (res) throw EvalError(data.error);
-
-    try {
-        checkVarDefs(state.primOps, data.result);
-    } catch (Error & e) {
-        throw EvalError(format("%1%, in `%2%'") % e.msg() % path);
-    }
-    
-    checkAttrSets(data.result);
-
-    return data.result;
-}
-
-
-Expr parseExprFromFile(EvalState & state, Path path)
-{
-    SwitchToOriginalUser sw;
-
-    assert(path[0] == '/');
-
-#if 0
-    /* Perhaps this is already an imploded parse tree? */
-    Expr e = ATreadFromNamedFile(path.c_str());
-    if (e) return e;
-#endif
-
-    /* If `path' is a symlink, follow it.  This is so that relative
-       path references work. */
-    struct stat st;
-    if (lstat(path.c_str(), &st))
-        throw SysError(format("getting status of `%1%'") % path);
-    if (S_ISLNK(st.st_mode)) path = absPath(readLink(path), dirOf(path));
-
-    /* If `path' refers to a directory, append `/default.nix'. */
-    if (stat(path.c_str(), &st))
-        throw SysError(format("getting status of `%1%'") % path);
-    if (S_ISDIR(st.st_mode))
-        path = canonPath(path + "/default.nix");
-
-    /* Read the input file.  We can't use SGparseFile() because it's
-       broken, so we read the input ourselves and call
-       SGparseString(). */
-    AutoCloseFD fd = open(path.c_str(), O_RDONLY);
-    if (fd == -1) throw SysError(format("opening `%1%'") % path);
-
-    if (fstat(fd, &st) == -1)
-        throw SysError(format("statting `%1%'") % path);
-
-    char text[st.st_size + 1];
-    readFull(fd, (unsigned char *) text, st.st_size);
-    text[st.st_size] = 0;
-
-    return parse(state, text, path, dirOf(path));
-}
-
-
-Expr parseExprFromString(EvalState & state,
-    const string & s, const Path & basePath)
-{
-    return parse(state, s.c_str(), "(string)", basePath);
-}
-
- 
-}
diff --git a/src/libexpr/parser.y b/src/libexpr/parser.y
index 7714a5911165..1f141c7bb09a 100644
--- a/src/libexpr/parser.y
+++ b/src/libexpr/parser.y
@@ -6,6 +6,7 @@
 %parse-param { ParseData * data }
 %lex-param { yyscan_t scanner }
 
+
 %{
 #include <stdio.h>
 #include <stdlib.h>
@@ -13,19 +14,21 @@
 #include <aterm2.h>
 
 #include "parser-tab.hh"
-extern "C" {
-#include "lexer-tab.h"
-}
+#include "lexer-tab.hh"
 
 #include "aterm.hh"
+#include "util.hh"
     
 #include "nixexpr.hh"
 #include "nixexpr-ast.hh"
 
+
 using namespace nix;
 
+
 namespace nix {
- 
+
+    
 struct ParseData 
 {
     Expr result;
@@ -34,33 +37,52 @@ struct ParseData
     string error;
 };
 
-void setParseResult(ParseData * data, ATerm t);
-void parseError(ParseData * data, char * error, int line, int column);
-ATerm absParsedPath(ParseData * data, ATerm t);
-ATerm fixAttrs(int recursive, ATermList as);
-const char * getPath(ParseData * data);
-Expr unescapeStr(const char * s);
- 
-extern "C" {
-    void backToString(yyscan_t scanner);
-}
- 
-}
 
-void yyerror(YYLTYPE * loc, yyscan_t scanner, ParseData * data, char * s)
+static ATerm fixAttrs(int recursive, ATermList as)
 {
-    parseError(data, s, loc->first_line, loc->first_column);
+    ATermList bs = ATempty, cs = ATempty;
+    ATermList * is = recursive ? &cs : &bs;
+    for (ATermIterator i(as); i; ++i) {
+        ATermList names;
+        Expr src;
+        ATerm pos;
+        if (matchInherit(*i, src, names, pos)) {
+            bool fromScope = matchScope(src);
+            for (ATermIterator j(names); j; ++j) {
+                Expr rhs = fromScope ? makeVar(*j) : makeSelect(src, *j);
+                *is = ATinsert(*is, makeBind(*j, rhs, pos));
+            }
+        } else bs = ATinsert(bs, *i);
+    }
+    if (recursive)
+        return makeRec(bs, cs);
+    else
+        return makeAttrs(bs);
 }
 
+
+void backToString(yyscan_t scanner);
+
+ 
 static Pos makeCurPos(YYLTYPE * loc, ParseData * data)
 {
-    return makePos(toATerm(getPath(data)),
+    return makePos(toATerm(data->path),
         loc->first_line, loc->first_column);
 }
 
 #define CUR_POS makeCurPos(yylocp, data)
 
 
+}
+
+
+void yyerror(YYLTYPE * loc, yyscan_t scanner, ParseData * data, char * error)
+{
+    data->error = (format("%1%, at `%2%':%3%:%4%")
+        % error % data->path % loc->first_line % loc->first_column).str();
+}
+
+
 /* Make sure that the parse stack is scanned by the ATerm garbage
    collector. */
 static void * mallocAndProtect(size_t size)
@@ -107,7 +129,7 @@ static void freeAndUnprotect(void * p)
 
 %%
 
-start: expr { setParseResult(data, $1); };
+start: expr { data->result = $1; };
 
 expr: expr_function;
 
@@ -165,7 +187,7 @@ expr_simple
       else if (ATgetNext($2) == ATempty) $$ = ATgetFirst($2);
       else $$ = makeConcatStrings(ATreverse($2));
   }
-  | PATH { $$ = makePath(absParsedPath(data, $1)); }
+  | PATH { $$ = makePath(toATerm(absPath(aterm2String($1), data->basePath))); }
   | URI { $$ = makeUri($1); }
   | '(' expr ')' { $$ = $2; }
   /* Let expressions `let {..., body = ...}' are just desugared
@@ -224,3 +246,151 @@ formal
   ;
   
 %%
+
+
+#include "eval.hh"  
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+
+namespace nix {
+      
+
+static void checkAttrs(ATermMap & names, ATermList bnds)
+{
+    for (ATermIterator i(bnds); i; ++i) {
+        ATerm name;
+        Expr e;
+        ATerm pos;
+        if (!matchBind(*i, name, e, pos)) abort(); /* can't happen */
+        if (names.get(name))
+            throw EvalError(format("duplicate attribute `%1%' at %2%")
+                % aterm2String(name) % showPos(pos));
+        names.set(name, name);
+    }
+}
+
+
+static void checkAttrSets(ATerm e)
+{
+    ATermList formals;
+    ATerm body, pos;
+    if (matchFunction(e, formals, body, pos)) {
+        ATermMap names(ATgetLength(formals));
+        for (ATermIterator i(formals); i; ++i) {
+            ATerm name;
+            ATerm d1, d2;
+            if (!matchFormal(*i, name, d1, d2)) abort();
+            if (names.get(name))
+                throw EvalError(format("duplicate formal function argument `%1%' at %2%")
+                    % aterm2String(name) % showPos(pos));
+            names.set(name, name);
+        }
+    }
+
+    ATermList bnds;
+    if (matchAttrs(e, bnds)) {
+        ATermMap names(ATgetLength(bnds));
+        checkAttrs(names, bnds);
+    }
+    
+    ATermList rbnds, nrbnds;
+    if (matchRec(e, rbnds, nrbnds)) {
+        ATermMap names(ATgetLength(rbnds) + ATgetLength(nrbnds));
+        checkAttrs(names, rbnds);
+        checkAttrs(names, nrbnds);
+    }
+    
+    if (ATgetType(e) == AT_APPL) {
+        int arity = ATgetArity(ATgetAFun(e));
+        for (int i = 0; i < arity; ++i)
+            checkAttrSets(ATgetArgument(e, i));
+    }
+
+    else if (ATgetType(e) == AT_LIST)
+        for (ATermIterator i((ATermList) e); i; ++i)
+            checkAttrSets(*i);
+}
+
+
+static Expr parse(EvalState & state,
+    const char * text, const Path & path,
+    const Path & basePath)
+{
+    yyscan_t scanner;
+    ParseData data;
+    data.basePath = basePath;
+    data.path = path;
+
+    yylex_init(&scanner);
+    yy_scan_string(text, scanner);
+    int res = yyparse(scanner, &data);
+    yylex_destroy(scanner);
+    
+    if (res) throw EvalError(data.error);
+
+    try {
+        checkVarDefs(state.primOps, data.result);
+    } catch (Error & e) {
+        throw EvalError(format("%1%, in `%2%'") % e.msg() % path);
+    }
+    
+    checkAttrSets(data.result);
+
+    return data.result;
+}
+
+
+Expr parseExprFromFile(EvalState & state, Path path)
+{
+    SwitchToOriginalUser sw;
+
+    assert(path[0] == '/');
+
+#if 0
+    /* Perhaps this is already an imploded parse tree? */
+    Expr e = ATreadFromNamedFile(path.c_str());
+    if (e) return e;
+#endif
+
+    /* If `path' is a symlink, follow it.  This is so that relative
+       path references work. */
+    struct stat st;
+    if (lstat(path.c_str(), &st))
+        throw SysError(format("getting status of `%1%'") % path);
+    if (S_ISLNK(st.st_mode)) path = absPath(readLink(path), dirOf(path));
+
+    /* If `path' refers to a directory, append `/default.nix'. */
+    if (stat(path.c_str(), &st))
+        throw SysError(format("getting status of `%1%'") % path);
+    if (S_ISDIR(st.st_mode))
+        path = canonPath(path + "/default.nix");
+
+    /* Read the input file.  We can't use SGparseFile() because it's
+       broken, so we read the input ourselves and call
+       SGparseString(). */
+    AutoCloseFD fd = open(path.c_str(), O_RDONLY);
+    if (fd == -1) throw SysError(format("opening `%1%'") % path);
+
+    if (fstat(fd, &st) == -1)
+        throw SysError(format("statting `%1%'") % path);
+
+    char text[st.st_size + 1];
+    readFull(fd, (unsigned char *) text, st.st_size);
+    text[st.st_size] = 0;
+
+    return parse(state, text, path, dirOf(path));
+}
+
+
+Expr parseExprFromString(EvalState & state,
+    const string & s, const Path & basePath)
+{
+    return parse(state, s.c_str(), "(string)", basePath);
+}
+
+ 
+}