header file. */
#undef HAVE_STDINT_H
diff --git a/configure b/configure
index ec79279fdf..b130e22aee 100755
--- a/configure
+++ b/configure
@@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for sqlcipher 3.11.0.
+# Generated by GNU Autoconf 2.69 for sqlcipher 3.15.2.
#
#
# Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -587,8 +587,8 @@ MAKEFLAGS=
# Identity of this package.
PACKAGE_NAME='sqlcipher'
PACKAGE_TARNAME='sqlcipher'
-PACKAGE_VERSION='3.11.0'
-PACKAGE_STRING='sqlcipher 3.11.0'
+PACKAGE_VERSION='3.15.2'
+PACKAGE_STRING='sqlcipher 3.15.2'
PACKAGE_BUGREPORT=''
PACKAGE_URL=''
@@ -773,11 +773,14 @@ with_readline_inc
enable_debug
enable_amalgamation
enable_load_extension
+enable_memsys5
+enable_memsys3
enable_fts3
enable_fts4
enable_fts5
enable_json1
enable_rtree
+enable_session
enable_gcov
'
ac_precious_vars='build_alias
@@ -1331,7 +1334,7 @@ if test "$ac_init_help" = "long"; then
# Omit some internal or obsolete options to make the list less imposing.
# This message is too long to be a string in the A/UX 3.1 sh.
cat <<_ACEOF
-\`configure' configures sqlcipher 3.11.0 to adapt to many kinds of systems.
+\`configure' configures sqlcipher 3.15.2 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@@ -1396,7 +1399,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
- short | recursive ) echo "Configuration of sqlcipher 3.11.0:";;
+ short | recursive ) echo "Configuration of sqlcipher 3.15.2:";;
esac
cat <<\_ACEOF
@@ -1424,11 +1427,14 @@ Optional Features:
separately
--disable-load-extension
Disable loading of external extensions
+ --enable-memsys5 Enable MEMSYS5
+ --enable-memsys3 Enable MEMSYS3
--enable-fts3 Enable the FTS3 extension
--enable-fts4 Enable the FTS4 extension
--enable-fts5 Enable the FTS5 extension
--enable-json1 Enable the JSON1 extension
--enable-rtree Enable the RTREE extension
+ --enable-session Enable the SESSION extension
--enable-gcov Enable coverage testing using gcov
Optional Packages:
@@ -1527,7 +1533,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
-sqlcipher configure 3.11.0
+sqlcipher configure 3.15.2
generated by GNU Autoconf 2.69
Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1946,7 +1952,7 @@ cat >config.log <<_ACEOF
This file contains any messages produced by compilers while
running configure, to aid debugging if configure makes a mistake.
-It was created by sqlcipher $as_me 3.11.0, which was
+It was created by sqlcipher $as_me 3.15.2, which was
generated by GNU Autoconf 2.69. Invocation command line was
$ $0 $@
@@ -11642,7 +11648,7 @@ done
#########
# Figure out whether or not we have these functions
#
-for ac_func in fdatasync gmtime_r isnan localtime_r localtime_s malloc_usable_size strchrnul usleep utime
+for ac_func in fdatasync gmtime_r isnan localtime_r localtime_s malloc_usable_size strchrnul usleep utime pread pread64 pwrite pwrite64
do :
as_ac_var=`$as_echo "ac_cv_func_$ac_func" | $as_tr_sh`
ac_fn_c_check_func "$LINENO" "$ac_func" "$as_ac_var"
@@ -12277,6 +12283,20 @@ else
fi
fi
+ # Recent versions of Xcode on Macs hid the tclConfig.sh file
+ # in a strange place.
+ if test x"${ac_cv_c_tclconfig}" = x ; then
+ if test x"$cross_compiling" = xno; then
+ for i in /Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX*.sdk/usr/lib
+ do
+ if test -f "$i/tclConfig.sh" ; then
+ ac_cv_c_tclconfig="$i"
+ break
+ fi
+ done
+ fi
+ fi
+
# then check for a private Tcl installation
if test x"${ac_cv_c_tclconfig}" = x ; then
for i in \
@@ -12845,6 +12865,44 @@ else
OPT_FEATURE_FLAGS="-DSQLITE_OMIT_LOAD_EXTENSION=1"
fi
+##########
+# Do we want to support memsys3 and/or memsys5
+#
+# Check whether --enable-memsys5 was given.
+if test "${enable_memsys5+set}" = set; then :
+ enableval=$enable_memsys5; enable_memsys5=yes
+else
+ enable_memsys5=no
+fi
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to support MEMSYS5" >&5
+$as_echo_n "checking whether to support MEMSYS5... " >&6; }
+if test "${enable_memsys5}" = "yes"; then
+ OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_MEMSYS5"
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+$as_echo "yes" >&6; }
+else
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+# Check whether --enable-memsys3 was given.
+if test "${enable_memsys3+set}" = set; then :
+ enableval=$enable_memsys3; enable_memsys3=yes
+else
+ enable_memsys3=no
+fi
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to support MEMSYS3" >&5
+$as_echo_n "checking whether to support MEMSYS3... " >&6; }
+if test "${enable_memsys3}" = "yes" -a "${enable_memsys5}" = "no"; then
+ OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_MEMSYS3"
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+$as_echo "yes" >&6; }
+else
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
#########
# See whether we should enable Full Text Search extensions
# Check whether --enable-fts3 was given.
@@ -13016,6 +13074,20 @@ if test "${enable_rtree}" = "yes" ; then
OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_RTREE"
fi
+#########
+# See whether we should enable the SESSION extension
+# Check whether --enable-session was given.
+if test "${enable_session+set}" = set; then :
+ enableval=$enable_session; enable_session=yes
+else
+ enable_session=no
+fi
+
+if test "${enable_session}" = "yes" ; then
+ OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_SESSION"
+ OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_PREUPDATE_HOOK"
+fi
+
#########
# attempt to duplicate any OMITS and ENABLES into the $(OPT_FEATURE_FLAGS) parameter
for option in $CFLAGS $CPPFLAGS
@@ -13601,7 +13673,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
# report actual input values of CONFIG_FILES etc. instead of their
# values after options handling.
ac_log="
-This file was extended by sqlcipher $as_me 3.11.0, which was
+This file was extended by sqlcipher $as_me 3.15.2, which was
generated by GNU Autoconf 2.69. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@@ -13667,7 +13739,7 @@ _ACEOF
cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
ac_cs_version="\\
-sqlcipher config.status 3.11.0
+sqlcipher config.status 3.15.2
configured by $0, generated by GNU Autoconf 2.69,
with options \\"\$ac_cs_config\\"
diff --git a/configure.ac b/configure.ac
index 9a1fe1a415..1452aaa4da 100644
--- a/configure.ac
+++ b/configure.ac
@@ -108,7 +108,7 @@ AC_CHECK_HEADERS([sys/types.h stdlib.h stdint.h inttypes.h malloc.h])
#########
# Figure out whether or not we have these functions
#
-AC_CHECK_FUNCS([fdatasync gmtime_r isnan localtime_r localtime_s malloc_usable_size strchrnul usleep utime])
+AC_CHECK_FUNCS([fdatasync gmtime_r isnan localtime_r localtime_s malloc_usable_size strchrnul usleep utime pread pread64 pwrite pwrite64])
#########
# By default, we use the amalgamation (this may be changed below...)
@@ -381,6 +381,20 @@ if test "${use_tcl}" = "yes" ; then
fi
fi
+ # Recent versions of Xcode on Macs hid the tclConfig.sh file
+ # in a strange place.
+ if test x"${ac_cv_c_tclconfig}" = x ; then
+ if test x"$cross_compiling" = xno; then
+ for i in /Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX*.sdk/usr/lib
+ do
+ if test -f "$i/tclConfig.sh" ; then
+ ac_cv_c_tclconfig="$i"
+ break
+ fi
+ done
+ fi
+ fi
+
# then check for a private Tcl installation
if test x"${ac_cv_c_tclconfig}" = x ; then
for i in \
@@ -621,6 +635,30 @@ else
OPT_FEATURE_FLAGS="-DSQLITE_OMIT_LOAD_EXTENSION=1"
fi
+##########
+# Do we want to support memsys3 and/or memsys5
+#
+AC_ARG_ENABLE(memsys5,
+ AC_HELP_STRING([--enable-memsys5],[Enable MEMSYS5]),
+ [enable_memsys5=yes],[enable_memsys5=no])
+AC_MSG_CHECKING([whether to support MEMSYS5])
+if test "${enable_memsys5}" = "yes"; then
+ OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_MEMSYS5"
+ AC_MSG_RESULT([yes])
+else
+ AC_MSG_RESULT([no])
+fi
+AC_ARG_ENABLE(memsys3,
+ AC_HELP_STRING([--enable-memsys3],[Enable MEMSYS3]),
+ [enable_memsys3=yes],[enable_memsys3=no])
+AC_MSG_CHECKING([whether to support MEMSYS3])
+if test "${enable_memsys3}" = "yes" -a "${enable_memsys5}" = "no"; then
+ OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_MEMSYS3"
+ AC_MSG_RESULT([yes])
+else
+ AC_MSG_RESULT([no])
+fi
+
#########
# See whether we should enable Full Text Search extensions
AC_ARG_ENABLE(fts3, AC_HELP_STRING([--enable-fts3],
@@ -662,6 +700,16 @@ if test "${enable_rtree}" = "yes" ; then
OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_RTREE"
fi
+#########
+# See whether we should enable the SESSION extension
+AC_ARG_ENABLE(session, AC_HELP_STRING([--enable-session],
+ [Enable the SESSION extension]),
+ [enable_session=yes],[enable_session=no])
+if test "${enable_session}" = "yes" ; then
+ OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_SESSION"
+ OPT_FEATURE_FLAGS+=" -DSQLITE_ENABLE_PREUPDATE_HOOK"
+fi
+
#########
# attempt to duplicate any OMITS and ENABLES into the $(OPT_FEATURE_FLAGS) parameter
for option in $CFLAGS $CPPFLAGS
diff --git a/doc/lemon.html b/doc/lemon.html
index b16e35960e..114526f372 100644
--- a/doc/lemon.html
+++ b/doc/lemon.html
@@ -5,14 +5,17 @@
The Lemon Parser Generator
-Lemon is an LALR(1) parser generator for C or C++.
-It does the same job as ``bison'' and ``yacc''.
-But lemon is not another bison or yacc clone. It
+
Lemon is an LALR(1) parser generator for C.
+It does the same job as "bison" and "yacc".
+But lemon is not a bison or yacc clone. Lemon
uses a different grammar syntax which is designed to
-reduce the number of coding errors. Lemon also uses a more
-sophisticated parsing engine that is faster than yacc and
-bison and which is both reentrant and thread-safe.
-Furthermore, Lemon implements features that can be used
+reduce the number of coding errors. Lemon also uses a
+parsing engine that is faster than yacc and
+bison and which is both reentrant and threadsafe.
+(Update: Since the previous sentence was written, bison
+has also been updated so that it too can generate a
+reentrant and threadsafe parser.)
+Lemon also implements features that can be used
to eliminate resource leaks, making is suitable for use
in long-running programs such as graphical user interfaces
or embedded controllers.
@@ -44,18 +47,18 @@ Theory of Operation
automaton.
By default, all three of these output files are generated.
-The header file is suppressed if the ``-m'' command-line option is
-used and the report file is omitted when ``-q'' is selected.
+The header file is suppressed if the "-m" command-line option is
+used and the report file is omitted when "-q" is selected.
-The grammar specification file uses a ``.y'' suffix, by convention.
+
The grammar specification file uses a ".y" suffix, by convention.
In the examples used in this document, we'll assume the name of the
-grammar file is ``gram.y''. A typical use of Lemon would be the
+grammar file is "gram.y". A typical use of Lemon would be the
following command:
lemon gram.y
-This command will generate three output files named ``gram.c'',
-``gram.h'' and ``gram.out''.
+This command will generate three output files named "gram.c",
+"gram.h" and "gram.out".
The first is C code to implement the parser. The second
is the header file that defines numerical values for all
terminal symbols, and the last is the report that explains
@@ -71,39 +74,35 @@ Command Line Options
As of this writing, the following command-line options are supported:
-- -b
-
- -c
-
- -g
-
- -m
-
- -q
-
- -s
-
- -x
+
- -b
+Show only the basis for each parser state in the report file.
+
- -c
+Do not compress the generated action tables.
+
- -Dname
+Define C preprocessor macro name. This macro is useable by
+"%ifdef" lines in the grammar file.
+
- -g
+Do not generate a parser. Instead write the input grammar to standard
+output with all comments, actions, and other extraneous text removed.
+
- -l
+Omit "#line" directives in the generated parser C code.
+
- -m
+Cause the output C source code to be compatible with the "makeheaders"
+program.
+
- -p
+Display all conflicts that are resolved by
+precedence rules.
+
- -q
+Suppress generation of the report file.
+
- -r
+Do not sort or renumber the parser states as part of optimization.
+
- -s
+Show parser statistics before existing.
+
- -Tfile
+Use file as the template for the generated C-code parser implementation.
+
- -x
+Print the Lemon version number.
-The ``-b'' option reduces the amount of text in the report file by
-printing only the basis of each parser state, rather than the full
-configuration.
-The ``-c'' option suppresses action table compression. Using -c
-will make the parser a little larger and slower but it will detect
-syntax errors sooner.
-The ``-g'' option causes no output files to be generated at all.
-Instead, the input grammar file is printed on standard output but
-with all comments, actions and other extraneous text deleted. This
-is a useful way to get a quick summary of a grammar.
-The ``-m'' option causes the output C source file to be compatible
-with the ``makeheaders'' program.
-Makeheaders is a program that automatically generates header files
-from C source code. When the ``-m'' option is used, the header
-file is not output since the makeheaders program will take care
-of generated all header files automatically.
-The ``-q'' option suppresses the report file.
-Using ``-s'' causes a brief summary of parser statistics to be
-printed. Like this:
-
- Parser statistics: 74 terminals, 70 nonterminals, 179 rules
- 340 states, 2026 parser table entries, 0 conflicts
-
-Finally, the ``-x'' option causes Lemon to print its version number
-and then stops without attempting to read the grammar or generate a parser.
The Parser Interface
@@ -121,12 +120,12 @@ The Parser Interface
The ParseAlloc() routine allocates and initializes a new parser and
returns a pointer to it.
-The actual data structure used to represent a parser is opaque --
+The actual data structure used to represent a parser is opaque —
its internal structure is not visible or usable by the calling routine.
For this reason, the ParseAlloc() routine returns a pointer to void
rather than a pointer to some particular structure.
The sole argument to the ParseAlloc() routine is a pointer to the
-subroutine used to allocate memory. Typically this means ``malloc()''.
+subroutine used to allocate memory. Typically this means malloc().
After a program is finished using a parser, it can reclaim all
memory allocated by that parser by calling
@@ -151,18 +150,19 @@
The Parser Interface
There is one token type for each terminal symbol in the grammar.
The gram.h file generated by Lemon contains #define statements that
map symbolic terminal symbol names into appropriate integer values.
-(A value of 0 for the second argument is a special flag to the
-parser to indicate that the end of input has been reached.)
+A value of 0 for the second argument is a special flag to the
+parser to indicate that the end of input has been reached.
The third argument is the value of the given token. By default,
the type of the third argument is integer, but the grammar will
usually redefine this type to be some kind of structure.
Typically the second argument will be a broad category of tokens
-such as ``identifier'' or ``number'' and the third argument will
+such as "identifier" or "number" and the third argument will
be the name of the identifier or the value of the number.
The Parse() function may have either three or four arguments,
-depending on the grammar. If the grammar specification file request
-it, the Parse() function will have a fourth parameter that can be
+depending on the grammar. If the grammar specification file requests
+it (via the extra_argument directive),
+the Parse() function will have a fourth parameter that can be
of any type chosen by the programmer. The parser doesn't do anything
with this argument except to pass it through to action routines.
This is a convenient mechanism for passing state information down
@@ -192,7 +192,7 @@
The Parser Interface
This example shows a user-written routine that parses a file of
text and returns a pointer to the parse tree.
-(We've omitted all error-handling from this example to keep it
+(All error-handling code is omitted from this example to keep it
simple.)
We assume the existence of some kind of tokenizer which is created
using TokenizerCreate() on line 8 and deleted by TokenizerFree()
@@ -263,6 +263,12 @@ Differences With YACC and BISON
But after years of experience using Lemon, I firmly
believe that the Lemon way of doing things is better.
+Updated as of 2016-02-16:
+The text above was written in the 1990s.
+We are told that Bison has lately been enhanced to support the
+tokenizer-calls-parser paradigm used by Lemon, and to obviate the
+need for global variables.
+
Input File Syntax
The main purpose of the grammar specification file for Lemon is
@@ -280,7 +286,7 @@
Input File Syntax
Terminals and Nonterminals
A terminal symbol (token) is any string of alphanumeric
-and underscore characters
+and/or underscore characters
that begins with an upper case letter.
A terminal can contain lowercase letters after the first character,
but the usual convention is to make terminals all upper case.
@@ -307,7 +313,7 @@
Grammar Rules
The main component of a Lemon grammar file is a sequence of grammar
rules.
Each grammar rule consists of a nonterminal symbol followed by
-the special symbol ``::='' and then a list of terminals and/or nonterminals.
+the special symbol "::=" and then a list of terminals and/or nonterminals.
The rule is terminated by a period.
The list of terminals and nonterminals on the right-hand side of the
rule can be empty.
@@ -323,9 +329,9 @@
Grammar Rules
-There is one non-terminal in this example, ``expr'', and five
-terminal symbols or tokens: ``PLUS'', ``TIMES'', ``LPAREN'',
-``RPAREN'' and ``VALUE''.
+There is one non-terminal in this example, "expr", and five
+terminal symbols or tokens: "PLUS", "TIMES", "LPAREN",
+"RPAREN" and "VALUE".
Like yacc and bison, Lemon allows the grammar to specify a block
of C code that will be executed whenever a grammar rule is reduced
@@ -341,15 +347,15 @@
Grammar Rules
In order to be useful, grammar actions must normally be linked to
their associated grammar rules.
-In yacc and bison, this is accomplished by embedding a ``$$'' in the
+In yacc and bison, this is accomplished by embedding a "$$" in the
action to stand for the value of the left-hand side of the rule and
-symbols ``$1'', ``$2'', and so forth to stand for the value of
+symbols "$1", "$2", and so forth to stand for the value of
the terminal or nonterminal at position 1, 2 and so forth on the
right-hand side of the rule.
This idea is very powerful, but it is also very error-prone. The
single most common source of errors in a yacc or bison grammar is
to miscount the number of symbols on the right-hand side of a grammar
-rule and say ``$7'' when you really mean ``$8''.
+rule and say "$7" when you really mean "$8".
Lemon avoids the need to count grammar symbols by assigning symbolic
names to each symbol in a grammar rule and then using those symbolic
@@ -379,7 +385,7 @@
Grammar Rules
expr(A) ::= expr(B) PLUS expr(C). { A = B; }
-will generate an error because the linking symbol ``C'' is used
+will generate an error because the linking symbol "C" is used
in the grammar rule but not in the reduce action.
The Lemon notation for linking grammar rules to reduce actions
@@ -387,6 +393,7 @@
Grammar Rules
allocated by the values of terminals and nonterminals on the
right-hand side of a rule.
+
Precedence Rules
Lemon resolves parsing ambiguities in exactly the same way as
@@ -398,7 +405,10 @@
Precedence Rules
yacc and bison, Lemon allows a measure of control
over the resolution of paring conflicts using precedence rules.
A precedence value can be assigned to any terminal symbol
-using the %left, %right or %nonassoc directives. Terminal symbols
+using the
+%left,
+%right or
+%nonassoc directives. Terminal symbols
mentioned in earlier directives have a lower precedence that
terminal symbols mentioned in later directives. For example:
@@ -518,7 +528,11 @@ Special Directives
%default_destructor
%default_type
%destructor
+%endif
%extra_argument
+%fallback
+%ifdef
+%ifndef
%include
%left
%name
@@ -530,49 +544,57 @@ Special Directives
%stack_size
%start_symbol
%syntax_error
+%token_class
%token_destructor
%token_prefix
%token_type
%type
+%wildcard
Each of these directives will be described separately in the
following sections:
+
The %code directive
-The %code directive is used to specify addition C/C++ code that
+
The %code directive is used to specify addition C code that
is added to the end of the main output file. This is similar to
-the %include directive except that %include is inserted at the
-beginning of the main output file.
+the %include directive except that %include
+is inserted at the beginning of the main output file.
%code is typically used to include some action routines or perhaps
-a tokenizer as part of the output file.
+a tokenizer or even the "main()" function
+as part of the output file.
+
The %default_destructor directive
The %default_destructor directive specifies a destructor to
use for non-terminals that do not have their own destructor
specified by a separate %destructor directive. See the documentation
-on the %destructor directive below for additional information.
+on the %destructor directive below for
+additional information.
In some grammers, many different non-terminal symbols have the
same datatype and hence the same destructor. This directive is
a convenience way to specify the same destructor for all those
non-terminals using a single statement.
+
The %default_type directive
The %default_type directive specifies the datatype of non-terminal
symbols that do no have their own datatype defined using a separate
-%type directive. See the documentation on %type below for addition
-information.
+%type directive.
+
+
The %destructor directive
The %destructor directive is used to specify a destructor for
a non-terminal symbol.
-(See also the %token_destructor directive which is used to
-specify a destructor for terminal symbols.)
+(See also the %token_destructor
+directive which is used to specify a destructor for terminal symbols.)
A non-terminal's destructor is called to dispose of the
non-terminal's value whenever the non-terminal is popped from
@@ -595,28 +617,28 @@
The %destructor directive
This example is a bit contrived but it serves to illustrate how
destructors work. The example shows a non-terminal named
-``nt'' that holds values of type ``void*''. When the rule for
-an ``nt'' reduces, it sets the value of the non-terminal to
+"nt" that holds values of type "void*". When the rule for
+an "nt" reduces, it sets the value of the non-terminal to
space obtained from malloc(). Later, when the nt non-terminal
is popped from the stack, the destructor will fire and call
free() on this malloced space, thus avoiding a memory leak.
-(Note that the symbol ``$$'' in the destructor code is replaced
+(Note that the symbol "$$" in the destructor code is replaced
by the value of the non-terminal.)
It is important to note that the value of a non-terminal is passed
to the destructor whenever the non-terminal is removed from the
stack, unless the non-terminal is used in a C-code action. If
the non-terminal is used by C-code, then it is assumed that the
-C-code will take care of destroying it if it should really
-be destroyed. More commonly, the value is used to build some
+C-code will take care of destroying it.
+More commonly, the value is used to build some
larger structure and we don't want to destroy it, which is why
the destructor is not called in this circumstance.
-By appropriate use of destructors, it is possible to
-build a parser using Lemon that can be used within a long-running
-program, such as a GUI, that will not leak memory or other resources.
+
Destructors help avoid memory leaks by automatically freeing
+allocated objects when they go out of scope.
To do the same using yacc or bison is much more difficult.
+
The %extra_argument directive
The %extra_argument directive instructs Lemon to add a 4th parameter
@@ -630,17 +652,66 @@ The %extra_argument directive
Then the Parse() function generated will have an 4th parameter
-of type ``MyStruct*'' and all action routines will have access to
-a variable named ``pAbc'' that is the value of the 4th parameter
+of type "MyStruct*" and all action routines will have access to
+a variable named "pAbc" that is the value of the 4th parameter
in the most recent call to Parse().
+
+The %fallback directive
+
+The %fallback directive specifies an alternative meaning for one
+or more tokens. The alternative meaning is tried if the original token
+would have generated a syntax error.
+
+
The %fallback directive was added to support robust parsing of SQL
+syntax in SQLite.
+The SQL language contains a large assortment of keywords, each of which
+appears as a different token to the language parser. SQL contains so
+many keywords, that it can be difficult for programmers to keep up with
+them all. Programmers will, therefore, sometimes mistakenly use an
+obscure language keyword for an identifier. The %fallback directive
+provides a mechanism to tell the parser: "If you are unable to parse
+this keyword, try treating it as an identifier instead."
+
+
The syntax of %fallback is as follows:
+
+
+%fallback ID TOKEN... .
+
+
+In words, the %fallback directive is followed by a list of token names
+terminated by a period. The first token name is the fallback token - the
+token to which all the other tokens fall back to. The second and subsequent
+arguments are tokens which fall back to the token identified by the first
+argument.
+
+
+
The %ifdef, %ifndef, and %endif directives.
+
+The %ifdef, %ifndef, and %endif directives are similar to
+#ifdef, #ifndef, and #endif in the C-preprocessor, just not as general.
+Each of these directives must begin at the left margin. No whitespace
+is allowed between the "%" and the directive name.
+
+
Grammar text in between "%ifdef MACRO" and the next nested "%endif" is
+ignored unless the "-DMACRO" command-line option is used. Grammar text
+betwen "%ifndef MACRO" and the next nested "%endif" is included except when
+the "-DMACRO" command-line option is used.
+
+
Note that the argument to %ifdef and %ifndef must be a single
+preprocessor symbol name, not a general expression. There is no "%else"
+directive.
+
+
+
The %include directive
The %include directive specifies C code that is included at the
top of the generated parser. You can include any text you want --
the Lemon parser generator copies it blindly. If you have multiple
-%include directives in your grammar file the value of the last
-%include directive overwrites all the others.
The %include directive is very handy for getting some extra #include
preprocessor statements at the beginning of the generated parser.
@@ -653,12 +724,13 @@
The %include directive
This might be needed, for example, if some of the C actions in the
grammar call functions that are prototyed in unistd.h.
+
The %left directive
-The %left directive is used (along with the %right and
-%nonassoc directives) to declare precedences of terminal
-symbols. Every terminal symbol whose name appears after
-a %left directive but before the next period (``.'') is
+The %left directive is used (along with the %right and
+%nonassoc directives) to declare precedences of
+terminal symbols. Every terminal symbol whose name appears after
+a %left directive but before the next period (".") is
given the same left-associative precedence value. Subsequent
%left directives have higher precedence. For example:
@@ -679,10 +751,11 @@ The %left directive
operators. For this reason, it is recommended that you use %left
rather than %right whenever possible.
+
The %name directive
By default, the functions generated by Lemon all begin with the
-five-character string ``Parse''. You can change this string to something
+five-character string "Parse". You can change this string to something
different using the %name directive. For instance:
@@ -701,16 +774,19 @@ The %name directive
parsers and link them all into the same executable.
+
The %nonassoc directive
This directive is used to assign non-associative precedence to
-one or more terminal symbols. See the section on precedence rules
-or on the %left directive for additional information.
+one or more terminal symbols. See the section on
+precedence rules
+or on the %left directive for additional information.
+
The %parse_accept directive
The %parse_accept directive specifies a block of C code that is
-executed whenever the parser accepts its input string. To ``accept''
+executed whenever the parser accepts its input string. To "accept"
an input string means that the parser was able to process all tokens
without error.
@@ -722,7 +798,7 @@ The %parse_accept directive
}
-
+
The %parse_failure directive
The %parse_failure directive specifies a block of C code that
@@ -737,12 +813,15 @@
The %parse_failure directive
}
+
The %right directive
This directive is used to assign right-associative precedence to
-one or more terminal symbols. See the section on precedence rules
-or on the %left directive for additional information.
+one or more terminal symbols. See the section on
+precedence rules
+or on the %left directive for additional information.
+
The %stack_overflow directive
The %stack_overflow directive specifies a block of C code that
@@ -771,6 +850,7 @@
The %stack_overflow directive
list ::= .
+
The %stack_size directive
If stack overflow is a problem and you can't resolve the trouble
@@ -783,6 +863,7 @@
The %stack_size directive
%stack_size 2000
+
The %start_symbol directive
By default, the start-symbol for the grammar that Lemon generates
@@ -793,6 +874,7 @@
The %start_symbol directive
%start_symbol prog
+
The %token_destructor directive
The %destructor directive assigns a destructor to a non-terminal
@@ -805,6 +887,7 @@
The %token_destructor directive
than that, the token destructor works just like the non-terminal
destructors.
+
The %token_prefix directive
Lemon generates #defines that assign small integer constants
@@ -830,6 +913,7 @@
The %token_prefix directive
#define TOKEN_PLUS 4
+
The %token_type and %type directives
These directives are used to specify the data types for values
@@ -845,7 +929,7 @@
The %token_type and %type directives
If the data type of terminals is not specified, the default value
-is ``int''.
+is "void*".
Non-terminal symbols can each have their own data types. Typically
the data type of a non-terminal is a pointer to the root of a parse-tree
@@ -866,6 +950,17 @@
The %token_type and %type directives
entry parser stack will require 100K of heap space. If you are willing
and able to pay that price, fine. You just need to know.
+
+The %wildcard directive
+
+The %wildcard directive is followed by a single token name and a
+period. This directive specifies that the identified token should
+match any input token.
+
+
When the generated parser has the choice of matching an input against
+the wildcard token and some other token, the other token is always used.
+The wildcard token is only matched if there are no other alternatives.
+
Error Processing
After extensive experimentation over several years, it has been
@@ -877,7 +972,7 @@
Error Processing
any. It then enters its error recovery strategy. The error recovery
strategy is to begin popping the parsers stack until it enters a
state where it is permitted to shift a special non-terminal symbol
-named ``error''. It then shifts this non-terminal and continues
+named "error". It then shifts this non-terminal and continues
parsing. But the %syntax_error routine will not be called again
until at least three new tokens have been successfully shifted.
@@ -886,7 +981,7 @@ Error Processing
is invoked and the parser resets itself to its start state, ready
to begin parsing a new file. This is what will happen at the very
first syntax error, of course, if there are no instances of the
-``error'' non-terminal in your grammar.
+"error" non-terminal in your grammar.