Release 0.9.22

added bootstrap.sh and Travis-CI continuous integration

.travis.yml

@@ -0,0 +1,5 @@
+language: cpp
+
+compiler:
+  - clang
+  - gcc

INSTALL.md

@@ -109,7 +109,9 @@ following files:
     |       |__ reflex.1
     |
     |__ examples/
-    |   |__ Makefile
+    |   |__ Make
+    |   |__ Makefile.am
+    |   |__ Makefile.in
     |   |__ ...
     |
     |__ include/
@@ -135,7 +137,9 @@ following files:
     |       |__ utf8.h
     |
     |__ lib/
-    |   |__ Makefile
+    |   |__ Make
+    |   |__ Makefile.am
+    |   |__ Makefile.in
     |   |__ convert.cpp
     |   |__ debug.cpp
     |   |__ error.cpp
@@ -147,16 +151,21 @@ following files:
     |   |__ utf8.cpp
     |
     |__ src/
-    |   |__ Makefile
+    |   |__ Make
+    |   |__ Makefile.am
+    |   |__ Makefile.in
     |   |__ reflex.cpp
     |   |__ reflex.h
     |
-    |__ test/
-    |   |__ Makefile
+    |__ tests/
+    |   |__ Make
+    |   |__ Makefile.am
+    |   |__ Makefile.in
+    |   |__ rtest.cpp
     |   |__ ...
     |
     |__ unicode/
-        |__ Makefile
+        |__ Make
         |__ Scripts.txt
         |__ UnicodeData.txt
         |__ language_scripts.cpp

Makefile.am

@@ -26,3 +26,8 @@ install-data-hook:
 		@echo "|             https://github.com/Genivia/RE-flex       |"; \
 		@echo "|             https://sourceforge.net/projects/re-flex |"; \
 		@echo "|______________________________________________________|";
+
+.PHONY:		test
+
+test:		$(abs_top_builddir)/src/reflex
+		-cd tests; $(MAKE) && ./rtest

Makefile.in

@@ -866,6 +866,11 @@ install-data-hook:
 		@echo "|             https://sourceforge.net/projects/re-flex |"; \
 		@echo "|______________________________________________________|";
 
+.PHONY:		test
+
+test:		$(abs_top_builddir)/src/reflex
+		-cd tests; $(MAKE) && ./rtest
+
 # Tell versions [3.59,3.63) of GNU make to not export all variables.
 # Otherwise a system limit (for SysV at least) may be exceeded.
 .NOEXPORT:

bootstrap.sh

@@ -0,0 +1,14 @@
+#!/bin/sh
+echo
+echo "Bootstrapping reflex Unicode scripts"
+./build.sh || exit 1
+mv -f unicode/language_scripts.cpp unicode/language_scripts.cpp.bak
+mv -f unicode/letter_scripts.cpp unicode/letter_scripts.cpp.bak
+cd unicode
+make -f Make || exit 1
+cd ..
+./build.sh || exit 1
+rm -f unicode/language_scripts.cpp.bak
+rm -f unicode/letter_scripts.cpp.bak
+
+

clean.sh

@@ -4,5 +4,5 @@ echo "Cleaning reflex"
 cd lib;      make -f Make distclean; cd -
 cd src;      make -f Make distclean; cd -
 cd unicode;  make -f Make clean; cd -
+cd tests;    make -f Make clean; cd -
 cd examples; make -f Make clean; cd -
-cd test;     make -f Make clean; cd -

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for reflex 0.9.21.
+# Generated by GNU Autoconf 2.69 for reflex 0.9.22.
 #
 #
 # Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -577,8 +577,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='reflex'
 PACKAGE_TARNAME='reflex'
-PACKAGE_VERSION='0.9.21'
-PACKAGE_STRING='reflex 0.9.21'
+PACKAGE_VERSION='0.9.22'
+PACKAGE_STRING='reflex 0.9.22'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1287,7 +1287,7 @@ 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 reflex 0.9.21 to adapt to many kinds of systems.
+\`configure' configures reflex 0.9.22 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1357,7 +1357,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of reflex 0.9.21:";;
+     short | recursive ) echo "Configuration of reflex 0.9.22:";;
    esac
   cat <<\_ACEOF
 
@@ -1456,7 +1456,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-reflex configure 0.9.21
+reflex configure 0.9.22
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1767,7 +1767,7 @@ 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 reflex $as_me 0.9.21, which was
+It was created by reflex $as_me 0.9.22, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -2630,7 +2630,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='reflex'
- VERSION='0.9.21'
+ VERSION='0.9.22'
 
 
 cat >>confdefs.h <<_ACEOF
@@ -5019,7 +5019,7 @@ fi
 done
 test -n "$YACC" || YACC="yacc"
 
-ac_config_files="$ac_config_files Makefile lib/Makefile src/Makefile examples/Makefile"
+ac_config_files="$ac_config_files Makefile lib/Makefile src/Makefile tests/Makefile examples/Makefile"
 
 PLATFORM=${host}
 
@@ -5593,7 +5593,7 @@ 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 reflex $as_me 0.9.21, which was
+This file was extended by reflex $as_me 0.9.22, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -5650,7 +5650,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-reflex config.status 0.9.21
+reflex config.status 0.9.22
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 
@@ -5772,6 +5772,7 @@ do
     "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;;
     "lib/Makefile") CONFIG_FILES="$CONFIG_FILES lib/Makefile" ;;
     "src/Makefile") CONFIG_FILES="$CONFIG_FILES src/Makefile" ;;
+    "tests/Makefile") CONFIG_FILES="$CONFIG_FILES tests/Makefile" ;;
     "examples/Makefile") CONFIG_FILES="$CONFIG_FILES examples/Makefile" ;;
 
   *) as_fn_error $? "invalid argument: \`$ac_config_target'" "$LINENO" 5;;

configure.ac

@@ -1,4 +1,4 @@
-AC_INIT(reflex,0.9.21)
+AC_INIT(reflex,0.9.22)
 AM_INIT_AUTOMAKE([-Wall foreign])
 AC_CANONICAL_HOST
 AC_HEADER_TIME
@@ -11,7 +11,7 @@ AC_PROG_CXX
 AM_PROG_AR
 AC_PROG_RANLIB
 AC_PROG_YACC
-AC_CONFIG_FILES([Makefile lib/Makefile src/Makefile examples/Makefile])
+AC_CONFIG_FILES([Makefile lib/Makefile src/Makefile tests/Makefile examples/Makefile])
 PLATFORM=${host}
 AC_SUBST(PLATFORM)
 AC_OUTPUT

doc/index.md

@@ -1321,7 +1321,7 @@ scanner.  The scanner reports the performance statistics on `std::cerr` when
 EOF is reached.  If your scanner does not reach EOF, then invoke the lexer's
 `perf_report()` method explicitly in your code.  Invoking this method also
 resets the statistics and timers, meaning that this method will report the
-statistics collected since its last call.
+statistics collected since it was last called.
 
 #### `-s`, `−−nodefault`
 
@@ -1968,7 +1968,7 @@ compilers will warn about trigraph translation before causing trouble.
 
 ### Character classes                                   {#reflex-pattern-class}
 
-Character classes in bracket lists are sets of characters.  Sets can be
+Character classes in bracket lists represent sets of characters.  Sets can be
 inverted, subtracted, intersected, and merged:
 
   Pattern           | Matches
@@ -1984,18 +1984,18 @@ first character after the bracket is always part of the list.  So `[][]` is a
 list that matches a `]` and a `[`, `[^][]` is a list that matches anything but
 `]` and `[`, and `[-^]` is a list that matches a `-` and a `^`.
 
-The character class sets may be Unicode character sets.  In that case
-\ref reflex-pattern-unicode should be enabled.
+Bracket lists may contain ASCII and Unicode \ref reflex-patterns-cat.
 
-Shorthands for character classes are character categories, discussed next.
+To add Unicode character categories and UTF-8 characters to bracket lists
+\ref reflex-pattern-unicode should be enabled.
 
 🔝 [Back to table of contents](#)
 
 ### Character categories                                 {#reflex-patterns-cat}
 
 The 7-bit ASCII character categories are:
 
-  Category     | List form      | Matches
+  Category     | POSIX form     | Matches
   ------------ | -------------- | ---------------------------------------------
   `\p{Space}`  | `[[:space:]]`  | matches a white space character `[ \t\n\v\f\r]` same as `\s`
   `\p{Xdigit}` | `[[:xdigit:]]` | matches a hex digit `[0-9A-Fa-f]`

doc/man/reflex.1

@@ -1,4 +1,4 @@
-.TH REFLEX "1" "April 10, 2017" "reflex 0.9.21" "User Commands"
+.TH REFLEX "1" "April 10, 2017" "reflex 0.9.22" "User Commands"
 .SH NAME
 reflex \- the regex\-centric fast and flexible lexical analyzer generator
 .SH SYNOPSIS

lib/Makefile.am

@@ -2,6 +2,6 @@ lib_LIBRARIES        = libreflex.a
 libreflex_a_CPPFLAGS = -I$(top_srcdir)/include
 libreflex_a_SOURCES  = convert.cpp debug.cpp error.cpp input.cpp matcher.cpp pattern.cpp posix.cpp unicode.cpp utf8.cpp $(top_srcdir)/unicode/language_scripts.cpp $(top_srcdir)/unicode/letter_scripts.cpp
 
-lib_LTLIBRARIES       = libreflex.la
-libreflex_la_CPPFLAGS = -I$(top_srcdir)/include
-libreflex_la_SOURCES  = convert.cpp debug.cpp error.cpp input.cpp matcher.cpp pattern.cpp posix.cpp unicode.cpp utf8.cpp $(top_srcdir)/unicode/language_scripts.cpp $(top_srcdir)/unicode/letter_scripts.cpp
+# lib_LTLIBRARIES       = libreflex.la
+# libreflex_la_CPPFLAGS = -I$(top_srcdir)/include
+# libreflex_la_SOURCES  = convert.cpp debug.cpp error.cpp input.cpp matcher.cpp pattern.cpp posix.cpp unicode.cpp utf8.cpp $(top_srcdir)/unicode/language_scripts.cpp $(top_srcdir)/unicode/letter_scripts.cpp

lib/Makefile.in

@@ -126,7 +126,6 @@ am__uninstall_files_from_dir = { \
   }
 am__installdirs = "$(DESTDIR)$(libdir)"
 LIBRARIES = $(lib_LIBRARIES)
-AR = ar
 ARFLAGS = cru
 AM_V_AR = $(am__v_AR_@AM_V@)
 am__v_AR_ = $(am__v_AR_@AM_DEFAULT_V@)
@@ -206,6 +205,7 @@ DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
 ACLOCAL = @ACLOCAL@
 AMTAR = @AMTAR@
 AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@
+AR = @AR@
 AUTOCONF = @AUTOCONF@
 AUTOHEADER = @AUTOHEADER@
 AUTOMAKE = @AUTOMAKE@
@@ -253,10 +253,13 @@ SET_MAKE = @SET_MAKE@
 SHELL = @SHELL@
 STRIP = @STRIP@
 VERSION = @VERSION@
+YACC = @YACC@
+YFLAGS = @YFLAGS@
 abs_builddir = @abs_builddir@
 abs_srcdir = @abs_srcdir@
 abs_top_builddir = @abs_top_builddir@
 abs_top_srcdir = @abs_top_srcdir@
+ac_ct_AR = @ac_ct_AR@
 ac_ct_CC = @ac_ct_CC@
 ac_ct_CXX = @ac_ct_CXX@
 am__include = @am__include@
@@ -769,6 +772,10 @@ uninstall-am: uninstall-libLIBRARIES
 .PRECIOUS: Makefile
 
 
+# lib_LTLIBRARIES       = libreflex.la
+# libreflex_la_CPPFLAGS = -I$(top_srcdir)/include
+# libreflex_la_SOURCES  = convert.cpp debug.cpp error.cpp input.cpp matcher.cpp pattern.cpp posix.cpp unicode.cpp utf8.cpp $(top_srcdir)/unicode/language_scripts.cpp $(top_srcdir)/unicode/letter_scripts.cpp
+
 # Tell versions [3.59,3.63) of GNU make to not export all variables.
 # Otherwise a system limit (for SysV at least) may be exceeded.
 .NOEXPORT:

lib/convert.cpp

@@ -255,7 +255,23 @@ static void convert_escape_char(const char *pattern, size_t& loc, size_t& pos, c
     }
     else if (!supports_escape(escapes, c))
     {
-      if (c == 'Z')
+      if (c == 'A')
+      {
+        if (!supports_escape(escapes, '`'))
+          throw regex_error(regex_error::invalid_anchor, pattern, pos);
+        // translate \A to \`
+        regex.append(&pattern[loc], pos - loc - 1).append("\\`");
+        loc = pos + 1;
+      }
+      else if (c == 'z')
+      {
+        if (!supports_escape(escapes, '\''))
+          throw regex_error(regex_error::invalid_anchor, pattern, pos);
+        // translate \z to \'
+        regex.append(&pattern[loc], pos - loc - 1).append("\\'");
+        loc = pos + 1;
+      }
+      else if (c == 'Z')
       {
         if (!supports_escape(escapes, 'z') || !supports_modifier(mod, '='))
           throw regex_error(regex_error::invalid_anchor, pattern, pos);

src/Makefile.in

@@ -167,6 +167,7 @@ DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
 ACLOCAL = @ACLOCAL@
 AMTAR = @AMTAR@
 AM_DEFAULT_VERBOSITY = @AM_DEFAULT_VERBOSITY@
+AR = @AR@
 AUTOCONF = @AUTOCONF@
 AUTOHEADER = @AUTOHEADER@
 AUTOMAKE = @AUTOMAKE@
@@ -214,10 +215,13 @@ SET_MAKE = @SET_MAKE@
 SHELL = @SHELL@
 STRIP = @STRIP@
 VERSION = @VERSION@
+YACC = @YACC@
+YFLAGS = @YFLAGS@
 abs_builddir = @abs_builddir@
 abs_srcdir = @abs_srcdir@
 abs_top_builddir = @abs_top_builddir@
 abs_top_srcdir = @abs_top_srcdir@
+ac_ct_AR = @ac_ct_AR@
 ac_ct_CC = @ac_ct_CC@
 ac_ct_CXX = @ac_ct_CXX@
 am__include = @am__include@

src/reflex.cpp

@@ -892,7 +892,8 @@ std::string Reflex::get_regex(size_t& pos)
       // eat [...]
       if (pos < linelen && line.at(pos) == '^')
         ++pos;
-      ++pos;
+      if (line.at(pos) != '\\')
+	++pos;
       while (pos < linelen && line.at(pos) != ']')
         pos += 1 + (line.at(pos) == '\\');
       ++pos;
@@ -1870,7 +1871,7 @@ void Reflex::write_perf_report()
       }
       if (options["nodefault"].empty())
         *out <<
-          "\n      \"    default rule matched \" << perf_report_" << conditions[start] << "_default << \" time(s)\\n\"";
+          "\n      \"    default rule accepted \" << perf_report_" << conditions[start] << "_default << \" times\\n\"";
       *out <<
         ";\n";
     }
@@ -2316,7 +2317,7 @@ void Reflex::write_lexer()
             *out <<
               "            if (debug()) std::cerr << \"--" <<
               SGR("\\033[1;35m") << "accepting rule at line " << rule->code.lineno << SGR("\\033[0m") <<
-              " (\\\"\" << matcher().text() << \"\\\")\\n\";\n";
+              " (\\\"" << SGR("\\033[1m") << "\" << matcher().text() << \"" << SGR("\\033[0m") << "\\\")\\n\";\n";
           if (!options["flex"].empty())
             *out <<
               "            YY_USER_ACTION\n";

src/reflex.h

@@ -64,7 +64,7 @@
 #endif
 
 // DO NOT ALTER THIS LINE: the makemake.sh script updates the version
-#define REFLEX_VERSION "0.9.21"
+#define REFLEX_VERSION "0.9.22"
 
 /// RE/flex scanner generator class, a variation of the classic "lex" tool to generate scanners.
 /**

tests/Makefile.am

@@ -0,0 +1,4 @@
+noinst_PROGRAMS = rtest
+rtest_CPPFLAGS  = -I$(top_srcdir)/include
+rtest_SOURCES   = rtest.cpp
+rtest_LDADD     = $(top_builddir)/lib/libreflex.a