webruby 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/bin/webruby +36 -0
- data/driver/driver.c +50 -0
- data/driver/main.c +40 -0
- data/lib/webruby/app.rb +13 -0
- data/lib/webruby/config.rb +61 -0
- data/lib/webruby/environment.rb +32 -0
- data/lib/webruby/rake/files.rake +66 -0
- data/lib/webruby/rake/general.rake +22 -0
- data/lib/webruby/rake/mruby.rake +44 -0
- data/lib/webruby/utility.rb +132 -0
- data/lib/webruby.rb +10 -0
- data/modules/emscripten/AUTHORS +89 -0
- data/modules/emscripten/LICENSE +68 -0
- data/modules/emscripten/README.markdown +14 -0
- data/modules/emscripten/cmake/Platform/Emscripten.cmake +61 -0
- data/modules/emscripten/cmake/Platform/Emscripten_unix.cmake +24 -0
- data/modules/emscripten/em++ +12 -0
- data/modules/emscripten/em++.bat +2 -0
- data/modules/emscripten/em-config +24 -0
- data/modules/emscripten/em-config.bat +2 -0
- data/modules/emscripten/emar +24 -0
- data/modules/emscripten/emar.bat +2 -0
- data/modules/emscripten/emcc +1744 -0
- data/modules/emscripten/emcc.bat +2 -0
- data/modules/emscripten/emcc.py +5 -0
- data/modules/emscripten/emconfigure +27 -0
- data/modules/emscripten/emconfigure.bat +2 -0
- data/modules/emscripten/emlibtool +11 -0
- data/modules/emscripten/emlibtool.bat +2 -0
- data/modules/emscripten/emlink.py +293 -0
- data/modules/emscripten/emmake +29 -0
- data/modules/emscripten/emmake.bat +2 -0
- data/modules/emscripten/emranlib +9 -0
- data/modules/emscripten/emranlib.bat +2 -0
- data/modules/emscripten/emscons +20 -0
- data/modules/emscripten/emscripten.py +835 -0
- data/modules/emscripten/patches/README +4 -0
- data/modules/emscripten/patches/series +2 -0
- data/modules/emscripten/scons-tools/closure.py +28 -0
- data/modules/emscripten/scons-tools/emscripten.py +359 -0
- data/modules/emscripten/scons-tools/llvm.py +33 -0
- data/modules/emscripten/src/analyzer.js +1695 -0
- data/modules/emscripten/src/compiler.html +48 -0
- data/modules/emscripten/src/compiler.js +298 -0
- data/modules/emscripten/src/corruptionCheck.js +98 -0
- data/modules/emscripten/src/determinstic.js +20 -0
- data/modules/emscripten/src/embind/embind.js +1677 -0
- data/modules/emscripten/src/embind/emval.js +283 -0
- data/modules/emscripten/src/experimental/allow_loopvars_from_memsetcpy_inasm.diff +97 -0
- data/modules/emscripten/src/experimental/batching.diff +44 -0
- data/modules/emscripten/src/experimental/functypeopt.diff +113 -0
- data/modules/emscripten/src/experimental/multiple_heaps.diff +175 -0
- data/modules/emscripten/src/experimental/noncallgraphprofiling.diff +197 -0
- data/modules/emscripten/src/experimental/optimize_memcpy_for_ta1.diff +124 -0
- data/modules/emscripten/src/experimental/remove__label__s.diff +140 -0
- data/modules/emscripten/src/experimental/renderer_cache_hash.diff +99 -0
- data/modules/emscripten/src/experimental/sdl_key_forwarding.diff +57 -0
- data/modules/emscripten/src/experimental/simplifyGeneratedFunctionsDetection.diff +336 -0
- data/modules/emscripten/src/experimental/stringCache.diff +147 -0
- data/modules/emscripten/src/fastLong.js +299 -0
- data/modules/emscripten/src/framework.js +257 -0
- data/modules/emscripten/src/gl-matrix.js +1952 -0
- data/modules/emscripten/src/headless.js +904 -0
- data/modules/emscripten/src/intertyper.js +1050 -0
- data/modules/emscripten/src/jsifier.js +1827 -0
- data/modules/emscripten/src/library.js +8270 -0
- data/modules/emscripten/src/library_browser.js +911 -0
- data/modules/emscripten/src/library_egl.js +491 -0
- data/modules/emscripten/src/library_gc.js +236 -0
- data/modules/emscripten/src/library_gl.js +4452 -0
- data/modules/emscripten/src/library_glfw.js +576 -0
- data/modules/emscripten/src/library_glut.js +449 -0
- data/modules/emscripten/src/library_jansson.js +320 -0
- data/modules/emscripten/src/library_openal.js +602 -0
- data/modules/emscripten/src/library_sdl.js +2024 -0
- data/modules/emscripten/src/library_strtok_r.c +97 -0
- data/modules/emscripten/src/library_xlib.js +23 -0
- data/modules/emscripten/src/long.js +1609 -0
- data/modules/emscripten/src/modules.js +491 -0
- data/modules/emscripten/src/parseTools.js +2474 -0
- data/modules/emscripten/src/postamble.js +170 -0
- data/modules/emscripten/src/postamble_sharedlib.js +16 -0
- data/modules/emscripten/src/preamble.js +914 -0
- data/modules/emscripten/src/preamble_sharedlib.js +25 -0
- data/modules/emscripten/src/relooper/README.markdown +14 -0
- data/modules/emscripten/src/relooper/Relooper.cpp +1236 -0
- data/modules/emscripten/src/relooper/Relooper.h +250 -0
- data/modules/emscripten/src/relooper/doit.sh +70 -0
- data/modules/emscripten/src/relooper/emscripten/glue.js +57 -0
- data/modules/emscripten/src/relooper/emscripten/test.js +44 -0
- data/modules/emscripten/src/relooper/fuzzer.py +116 -0
- data/modules/emscripten/src/relooper/ministring.h +35 -0
- data/modules/emscripten/src/relooper/paper.pdf +0 -0
- data/modules/emscripten/src/relooper/test.cpp +262 -0
- data/modules/emscripten/src/relooper/test.txt +155 -0
- data/modules/emscripten/src/relooper/test2.c +44 -0
- data/modules/emscripten/src/relooper/test2.txt +12 -0
- data/modules/emscripten/src/relooper/test3.c +42 -0
- data/modules/emscripten/src/relooper/test3.txt +27 -0
- data/modules/emscripten/src/relooper/test4.cpp +40 -0
- data/modules/emscripten/src/relooper/test4.txt +23 -0
- data/modules/emscripten/src/relooper/test5.cpp +40 -0
- data/modules/emscripten/src/relooper/test5.txt +32 -0
- data/modules/emscripten/src/relooper/test6.cpp +31 -0
- data/modules/emscripten/src/relooper/test6.txt +12 -0
- data/modules/emscripten/src/relooper/test_dead.cpp +28 -0
- data/modules/emscripten/src/relooper/test_dead.txt +9 -0
- data/modules/emscripten/src/relooper/test_debug.cpp +30 -0
- data/modules/emscripten/src/relooper/test_debug.txt +128 -0
- data/modules/emscripten/src/relooper/test_fuzz1.cpp +52 -0
- data/modules/emscripten/src/relooper/test_fuzz1.txt +32 -0
- data/modules/emscripten/src/relooper/test_fuzz2.cpp +34 -0
- data/modules/emscripten/src/relooper/test_fuzz2.txt +13 -0
- data/modules/emscripten/src/relooper/test_fuzz3.cpp +36 -0
- data/modules/emscripten/src/relooper/test_fuzz3.txt +9 -0
- data/modules/emscripten/src/relooper/test_fuzz4.cpp +38 -0
- data/modules/emscripten/src/relooper/test_fuzz4.txt +19 -0
- data/modules/emscripten/src/relooper/test_fuzz5.cpp +57 -0
- data/modules/emscripten/src/relooper/test_fuzz5.txt +52 -0
- data/modules/emscripten/src/relooper/test_fuzz6.cpp +322 -0
- data/modules/emscripten/src/relooper/test_fuzz6.txt +108 -0
- data/modules/emscripten/src/relooper/test_inf.cpp +813 -0
- data/modules/emscripten/src/relooper/test_inf.txt +385 -0
- data/modules/emscripten/src/relooper/testit.sh +62 -0
- data/modules/emscripten/src/relooper/updateit.sh +17 -0
- data/modules/emscripten/src/relooper.js +11516 -0
- data/modules/emscripten/src/relooper.js.raw.js +11511 -0
- data/modules/emscripten/src/runtime.js +546 -0
- data/modules/emscripten/src/settings.js +1284 -0
- data/modules/emscripten/src/shell.html +92 -0
- data/modules/emscripten/src/shell.js +153 -0
- data/modules/emscripten/src/shell_sharedlib.js +12 -0
- data/modules/emscripten/src/socket.io.js +3870 -0
- data/modules/emscripten/src/utility.js +379 -0
- data/modules/emscripten/src/wrtcp.js +821 -0
- data/modules/emscripten/system/include/AL/al.h +172 -0
- data/modules/emscripten/system/include/AL/alc.h +84 -0
- data/modules/emscripten/system/include/EGL/egl.h +329 -0
- data/modules/emscripten/system/include/EGL/eglext.h +398 -0
- data/modules/emscripten/system/include/EGL/eglplatform.h +141 -0
- data/modules/emscripten/system/include/GL/freeglut_std.h +628 -0
- data/modules/emscripten/system/include/GL/gl.h +2241 -0
- data/modules/emscripten/system/include/GL/glew.h +6 -0
- data/modules/emscripten/system/include/GL/glext.h +11127 -0
- data/modules/emscripten/system/include/GL/glfw.h +518 -0
- data/modules/emscripten/system/include/GL/glu.h +353 -0
- data/modules/emscripten/system/include/GL/glut.h +21 -0
- data/modules/emscripten/system/include/GLES/gl.h +770 -0
- data/modules/emscripten/system/include/GLES/glext.h +1278 -0
- data/modules/emscripten/system/include/GLES/glplatform.h +30 -0
- data/modules/emscripten/system/include/GLES2/gl2.h +621 -0
- data/modules/emscripten/system/include/GLES2/gl2ext.h +803 -0
- data/modules/emscripten/system/include/GLES2/gl2platform.h +30 -0
- data/modules/emscripten/system/include/KHR/khrplatform.h +277 -0
- data/modules/emscripten/system/include/SDL/COPYING +19 -0
- data/modules/emscripten/system/include/SDL/SDL.h +162 -0
- data/modules/emscripten/system/include/SDL/SDL_assert.h +241 -0
- data/modules/emscripten/system/include/SDL/SDL_atomic.h +318 -0
- data/modules/emscripten/system/include/SDL/SDL_audio.h +509 -0
- data/modules/emscripten/system/include/SDL/SDL_blendmode.h +60 -0
- data/modules/emscripten/system/include/SDL/SDL_clipboard.h +75 -0
- data/modules/emscripten/system/include/SDL/SDL_compat.h +365 -0
- data/modules/emscripten/system/include/SDL/SDL_config.h +48 -0
- data/modules/emscripten/system/include/SDL/SDL_config.h.in +297 -0
- data/modules/emscripten/system/include/SDL/SDL_config_android.h +133 -0
- data/modules/emscripten/system/include/SDL/SDL_config_iphoneos.h +148 -0
- data/modules/emscripten/system/include/SDL/SDL_config_macosx.h +172 -0
- data/modules/emscripten/system/include/SDL/SDL_config_minimal.h +74 -0
- data/modules/emscripten/system/include/SDL/SDL_config_nintendods.h +129 -0
- data/modules/emscripten/system/include/SDL/SDL_config_pandora.h +125 -0
- data/modules/emscripten/system/include/SDL/SDL_config_windows.h +207 -0
- data/modules/emscripten/system/include/SDL/SDL_config_wiz.h +119 -0
- data/modules/emscripten/system/include/SDL/SDL_copying.h +20 -0
- data/modules/emscripten/system/include/SDL/SDL_cpuinfo.h +150 -0
- data/modules/emscripten/system/include/SDL/SDL_endian.h +248 -0
- data/modules/emscripten/system/include/SDL/SDL_error.h +77 -0
- data/modules/emscripten/system/include/SDL/SDL_events.h +639 -0
- data/modules/emscripten/system/include/SDL/SDL_gesture.h +91 -0
- data/modules/emscripten/system/include/SDL/SDL_gfxPrimitives.h +246 -0
- data/modules/emscripten/system/include/SDL/SDL_haptic.h +1200 -0
- data/modules/emscripten/system/include/SDL/SDL_hints.h +206 -0
- data/modules/emscripten/system/include/SDL/SDL_image.h +138 -0
- data/modules/emscripten/system/include/SDL/SDL_input.h +87 -0
- data/modules/emscripten/system/include/SDL/SDL_joystick.h +208 -0
- data/modules/emscripten/system/include/SDL/SDL_keyboard.h +169 -0
- data/modules/emscripten/system/include/SDL/SDL_keycode.h +344 -0
- data/modules/emscripten/system/include/SDL/SDL_loadso.h +85 -0
- data/modules/emscripten/system/include/SDL/SDL_log.h +211 -0
- data/modules/emscripten/system/include/SDL/SDL_main.h +98 -0
- data/modules/emscripten/system/include/SDL/SDL_mixer.h +634 -0
- data/modules/emscripten/system/include/SDL/SDL_mouse.h +213 -0
- data/modules/emscripten/system/include/SDL/SDL_mutex.h +248 -0
- data/modules/emscripten/system/include/SDL/SDL_name.h +11 -0
- data/modules/emscripten/system/include/SDL/SDL_opengl.h +11116 -0
- data/modules/emscripten/system/include/SDL/SDL_opengles.h +38 -0
- data/modules/emscripten/system/include/SDL/SDL_opengles2.h +38 -0
- data/modules/emscripten/system/include/SDL/SDL_pixels.h +423 -0
- data/modules/emscripten/system/include/SDL/SDL_platform.h +160 -0
- data/modules/emscripten/system/include/SDL/SDL_power.h +79 -0
- data/modules/emscripten/system/include/SDL/SDL_quit.h +58 -0
- data/modules/emscripten/system/include/SDL/SDL_rect.h +136 -0
- data/modules/emscripten/system/include/SDL/SDL_render.h +615 -0
- data/modules/emscripten/system/include/SDL/SDL_revision.h +2 -0
- data/modules/emscripten/system/include/SDL/SDL_revision.h.orig +2 -0
- data/modules/emscripten/system/include/SDL/SDL_rotozoom.h +123 -0
- data/modules/emscripten/system/include/SDL/SDL_rwops.h +220 -0
- data/modules/emscripten/system/include/SDL/SDL_scancode.h +398 -0
- data/modules/emscripten/system/include/SDL/SDL_shape.h +147 -0
- data/modules/emscripten/system/include/SDL/SDL_stdinc.h +764 -0
- data/modules/emscripten/system/include/SDL/SDL_surface.h +499 -0
- data/modules/emscripten/system/include/SDL/SDL_syswm.h +241 -0
- data/modules/emscripten/system/include/SDL/SDL_thread.h +182 -0
- data/modules/emscripten/system/include/SDL/SDL_timer.h +108 -0
- data/modules/emscripten/system/include/SDL/SDL_touch.h +124 -0
- data/modules/emscripten/system/include/SDL/SDL_ttf.h +249 -0
- data/modules/emscripten/system/include/SDL/SDL_types.h +29 -0
- data/modules/emscripten/system/include/SDL/SDL_version.h +166 -0
- data/modules/emscripten/system/include/SDL/SDL_video.h +820 -0
- data/modules/emscripten/system/include/SDL/begin_code.h +135 -0
- data/modules/emscripten/system/include/SDL/close_code.h +37 -0
- data/modules/emscripten/system/include/X11/X.h +717 -0
- data/modules/emscripten/system/include/X11/Xatom.h +79 -0
- data/modules/emscripten/system/include/X11/Xfuncproto.h +127 -0
- data/modules/emscripten/system/include/X11/Xlib.h +4023 -0
- data/modules/emscripten/system/include/X11/Xosdefs.h +116 -0
- data/modules/emscripten/system/include/X11/Xutil.h +826 -0
- data/modules/emscripten/system/include/X11/keysym.h +73 -0
- data/modules/emscripten/system/include/X11/keysymdef.h +2389 -0
- data/modules/emscripten/system/include/bsd/float.h +91 -0
- data/modules/emscripten/system/include/bsd/readme.txt +2 -0
- data/modules/emscripten/system/include/bsd/sys/mman.h +180 -0
- data/modules/emscripten/system/include/bsd/sys/utsname.h +70 -0
- data/modules/emscripten/system/include/dlfcn.h +31 -0
- data/modules/emscripten/system/include/emscripten/bind.h +1210 -0
- data/modules/emscripten/system/include/emscripten/emscripten.h +388 -0
- data/modules/emscripten/system/include/emscripten/val.h +311 -0
- data/modules/emscripten/system/include/emscripten/wire.h +393 -0
- data/modules/emscripten/system/include/err.h +95 -0
- data/modules/emscripten/system/include/execinfo.h +44 -0
- data/modules/emscripten/system/include/features.h +3 -0
- data/modules/emscripten/system/include/gc.h +70 -0
- data/modules/emscripten/system/include/gfx/png.h +3798 -0
- data/modules/emscripten/system/include/gfx/pngconf.h +1665 -0
- data/modules/emscripten/system/include/gfx/tiff.h +654 -0
- data/modules/emscripten/system/include/gfx/tiffconf.h +104 -0
- data/modules/emscripten/system/include/gfx/tiffio.h +526 -0
- data/modules/emscripten/system/include/gfx/tiffvers.h +9 -0
- data/modules/emscripten/system/include/jansson.h +323 -0
- data/modules/emscripten/system/include/jansson_config.h +54 -0
- data/modules/emscripten/system/include/libc/_ansi.h +135 -0
- data/modules/emscripten/system/include/libc/_syslist.h +40 -0
- data/modules/emscripten/system/include/libc/alloca.h +21 -0
- data/modules/emscripten/system/include/libc/ar.h +69 -0
- data/modules/emscripten/system/include/libc/argz.h +33 -0
- data/modules/emscripten/system/include/libc/assert.h +46 -0
- data/modules/emscripten/system/include/libc/complex.h +124 -0
- data/modules/emscripten/system/include/libc/ctype.h +196 -0
- data/modules/emscripten/system/include/libc/dirent.h +16 -0
- data/modules/emscripten/system/include/libc/endian.h +3 -0
- data/modules/emscripten/system/include/libc/envlock.h +15 -0
- data/modules/emscripten/system/include/libc/envz.h +16 -0
- data/modules/emscripten/system/include/libc/errno.h +11 -0
- data/modules/emscripten/system/include/libc/fastmath.h +13 -0
- data/modules/emscripten/system/include/libc/fcntl.h +1 -0
- data/modules/emscripten/system/include/libc/fnmatch.h +55 -0
- data/modules/emscripten/system/include/libc/getopt.h +196 -0
- data/modules/emscripten/system/include/libc/glob.h +89 -0
- data/modules/emscripten/system/include/libc/grp.h +94 -0
- data/modules/emscripten/system/include/libc/iconv.h +62 -0
- data/modules/emscripten/system/include/libc/ieeefp.h +256 -0
- data/modules/emscripten/system/include/libc/ifaddrs.h +64 -0
- data/modules/emscripten/system/include/libc/inttypes.h +290 -0
- data/modules/emscripten/system/include/libc/iso646.h +43 -0
- data/modules/emscripten/system/include/libc/langinfo.h +316 -0
- data/modules/emscripten/system/include/libc/libgen.h +23 -0
- data/modules/emscripten/system/include/libc/limits.h +155 -0
- data/modules/emscripten/system/include/libc/locale.h +80 -0
- data/modules/emscripten/system/include/libc/machine/_default_types.h +121 -0
- data/modules/emscripten/system/include/libc/machine/_types.h +8 -0
- data/modules/emscripten/system/include/libc/machine/ansi.h +1 -0
- data/modules/emscripten/system/include/libc/machine/endian.h +31 -0
- data/modules/emscripten/system/include/libc/machine/fastmath.h +100 -0
- data/modules/emscripten/system/include/libc/machine/ieeefp.h +376 -0
- data/modules/emscripten/system/include/libc/machine/malloc.h +8 -0
- data/modules/emscripten/system/include/libc/machine/param.h +1 -0
- data/modules/emscripten/system/include/libc/machine/setjmp-dj.h +43 -0
- data/modules/emscripten/system/include/libc/machine/setjmp.h +361 -0
- data/modules/emscripten/system/include/libc/machine/stdlib.h +8 -0
- data/modules/emscripten/system/include/libc/machine/termios.h +1 -0
- data/modules/emscripten/system/include/libc/machine/time.h +19 -0
- data/modules/emscripten/system/include/libc/machine/types.h +30 -0
- data/modules/emscripten/system/include/libc/malloc.h +169 -0
- data/modules/emscripten/system/include/libc/math.h +594 -0
- data/modules/emscripten/system/include/libc/newlib.h +2 -0
- data/modules/emscripten/system/include/libc/paths.h +7 -0
- data/modules/emscripten/system/include/libc/process.h +44 -0
- data/modules/emscripten/system/include/libc/pthread.h +362 -0
- data/modules/emscripten/system/include/libc/pwd.h +78 -0
- data/modules/emscripten/system/include/libc/readme.txt +3 -0
- data/modules/emscripten/system/include/libc/reent.h +183 -0
- data/modules/emscripten/system/include/libc/regdef.h +7 -0
- data/modules/emscripten/system/include/libc/regex.h +102 -0
- data/modules/emscripten/system/include/libc/sched.h +97 -0
- data/modules/emscripten/system/include/libc/search.h +59 -0
- data/modules/emscripten/system/include/libc/setjmp.h +20 -0
- data/modules/emscripten/system/include/libc/signal.h +30 -0
- data/modules/emscripten/system/include/libc/stdarg.h +50 -0
- data/modules/emscripten/system/include/libc/stddef.h +64 -0
- data/modules/emscripten/system/include/libc/stdint.h +493 -0
- data/modules/emscripten/system/include/libc/stdio.h +694 -0
- data/modules/emscripten/system/include/libc/stdlib.h +230 -0
- data/modules/emscripten/system/include/libc/string.h +105 -0
- data/modules/emscripten/system/include/libc/strings.h +35 -0
- data/modules/emscripten/system/include/libc/sys/_default_fcntl.h +223 -0
- data/modules/emscripten/system/include/libc/sys/_types.h +93 -0
- data/modules/emscripten/system/include/libc/sys/cdefs.h +123 -0
- data/modules/emscripten/system/include/libc/sys/config.h +255 -0
- data/modules/emscripten/system/include/libc/sys/custom_file.h +2 -0
- data/modules/emscripten/system/include/libc/sys/dir.h +10 -0
- data/modules/emscripten/system/include/libc/sys/dirent.h +58 -0
- data/modules/emscripten/system/include/libc/sys/errno.h +190 -0
- data/modules/emscripten/system/include/libc/sys/fcntl.h +4 -0
- data/modules/emscripten/system/include/libc/sys/features.h +212 -0
- data/modules/emscripten/system/include/libc/sys/file.h +2 -0
- data/modules/emscripten/system/include/libc/sys/iconvnls.h +77 -0
- data/modules/emscripten/system/include/libc/sys/lock.h +24 -0
- data/modules/emscripten/system/include/libc/sys/param.h +25 -0
- data/modules/emscripten/system/include/libc/sys/queue.h +471 -0
- data/modules/emscripten/system/include/libc/sys/reent.h +843 -0
- data/modules/emscripten/system/include/libc/sys/resource.h +59 -0
- data/modules/emscripten/system/include/libc/sys/sched.h +67 -0
- data/modules/emscripten/system/include/libc/sys/signal.h +314 -0
- data/modules/emscripten/system/include/libc/sys/stat.h +222 -0
- data/modules/emscripten/system/include/libc/sys/stdio.h +27 -0
- data/modules/emscripten/system/include/libc/sys/string.h +2 -0
- data/modules/emscripten/system/include/libc/sys/syslimits.h +65 -0
- data/modules/emscripten/system/include/libc/sys/termios.h +280 -0
- data/modules/emscripten/system/include/libc/sys/time.h +85 -0
- data/modules/emscripten/system/include/libc/sys/timeb.h +39 -0
- data/modules/emscripten/system/include/libc/sys/times.h +28 -0
- data/modules/emscripten/system/include/libc/sys/ttydefaults.h +97 -0
- data/modules/emscripten/system/include/libc/sys/types.h +481 -0
- data/modules/emscripten/system/include/libc/sys/unistd.h +514 -0
- data/modules/emscripten/system/include/libc/sys/utime.h +26 -0
- data/modules/emscripten/system/include/libc/sys/wait.h +40 -0
- data/modules/emscripten/system/include/libc/tar.h +39 -0
- data/modules/emscripten/system/include/libc/termios.h +7 -0
- data/modules/emscripten/system/include/libc/time.h +273 -0
- data/modules/emscripten/system/include/libc/unctrl.h +46 -0
- data/modules/emscripten/system/include/libc/unistd.h +6 -0
- data/modules/emscripten/system/include/libc/utime.h +12 -0
- data/modules/emscripten/system/include/libc/utmp.h +8 -0
- data/modules/emscripten/system/include/libc/wchar.h +194 -0
- data/modules/emscripten/system/include/libc/wctype.h +47 -0
- data/modules/emscripten/system/include/libc/wordexp.h +53 -0
- data/modules/emscripten/system/include/libcxx/CREDITS.TXT +91 -0
- data/modules/emscripten/system/include/libcxx/LICENSE.txt +76 -0
- data/modules/emscripten/system/include/libcxx/__bit_reference +1268 -0
- data/modules/emscripten/system/include/libcxx/__config +485 -0
- data/modules/emscripten/system/include/libcxx/__debug +193 -0
- data/modules/emscripten/system/include/libcxx/__functional_03 +2130 -0
- data/modules/emscripten/system/include/libcxx/__functional_base +437 -0
- data/modules/emscripten/system/include/libcxx/__functional_base_03 +1087 -0
- data/modules/emscripten/system/include/libcxx/__hash_table +1945 -0
- data/modules/emscripten/system/include/libcxx/__locale +1435 -0
- data/modules/emscripten/system/include/libcxx/__mutex_base +438 -0
- data/modules/emscripten/system/include/libcxx/__split_buffer +654 -0
- data/modules/emscripten/system/include/libcxx/__sso_allocator +77 -0
- data/modules/emscripten/system/include/libcxx/__std_stream +317 -0
- data/modules/emscripten/system/include/libcxx/__tree +2293 -0
- data/modules/emscripten/system/include/libcxx/__tuple +305 -0
- data/modules/emscripten/system/include/libcxx/__tuple_03 +27 -0
- data/modules/emscripten/system/include/libcxx/__undef_min_max +19 -0
- data/modules/emscripten/system/include/libcxx/algorithm +5458 -0
- data/modules/emscripten/system/include/libcxx/array +341 -0
- data/modules/emscripten/system/include/libcxx/atomic +1521 -0
- data/modules/emscripten/system/include/libcxx/bitset +1081 -0
- data/modules/emscripten/system/include/libcxx/cassert +25 -0
- data/modules/emscripten/system/include/libcxx/ccomplex +29 -0
- data/modules/emscripten/system/include/libcxx/cctype +164 -0
- data/modules/emscripten/system/include/libcxx/cerrno +393 -0
- data/modules/emscripten/system/include/libcxx/cfenv +82 -0
- data/modules/emscripten/system/include/libcxx/cfloat +78 -0
- data/modules/emscripten/system/include/libcxx/chrono +898 -0
- data/modules/emscripten/system/include/libcxx/cinttypes +259 -0
- data/modules/emscripten/system/include/libcxx/ciso646 +25 -0
- data/modules/emscripten/system/include/libcxx/climits +48 -0
- data/modules/emscripten/system/include/libcxx/clocale +53 -0
- data/modules/emscripten/system/include/libcxx/cmath +1683 -0
- data/modules/emscripten/system/include/libcxx/codecvt +547 -0
- data/modules/emscripten/system/include/libcxx/complex +1526 -0
- data/modules/emscripten/system/include/libcxx/complex.h +35 -0
- data/modules/emscripten/system/include/libcxx/condition_variable +256 -0
- data/modules/emscripten/system/include/libcxx/csetjmp +52 -0
- data/modules/emscripten/system/include/libcxx/csignal +58 -0
- data/modules/emscripten/system/include/libcxx/cstdarg +48 -0
- data/modules/emscripten/system/include/libcxx/cstdbool +32 -0
- data/modules/emscripten/system/include/libcxx/cstddef +103 -0
- data/modules/emscripten/system/include/libcxx/cstdint +191 -0
- data/modules/emscripten/system/include/libcxx/cstdio +175 -0
- data/modules/emscripten/system/include/libcxx/cstdlib +172 -0
- data/modules/emscripten/system/include/libcxx/cstring +112 -0
- data/modules/emscripten/system/include/libcxx/ctgmath +29 -0
- data/modules/emscripten/system/include/libcxx/ctime +72 -0
- data/modules/emscripten/system/include/libcxx/cwchar +208 -0
- data/modules/emscripten/system/include/libcxx/cwctype +213 -0
- data/modules/emscripten/system/include/libcxx/deque +2846 -0
- data/modules/emscripten/system/include/libcxx/exception +250 -0
- data/modules/emscripten/system/include/libcxx/ext/__hash +46 -0
- data/modules/emscripten/system/include/libcxx/ext/hash_map +1003 -0
- data/modules/emscripten/system/include/libcxx/ext/hash_set +657 -0
- data/modules/emscripten/system/include/libcxx/forward_list +1636 -0
- data/modules/emscripten/system/include/libcxx/fstream +1415 -0
- data/modules/emscripten/system/include/libcxx/functional +2063 -0
- data/modules/emscripten/system/include/libcxx/future +2505 -0
- data/modules/emscripten/system/include/libcxx/initializer_list +105 -0
- data/modules/emscripten/system/include/libcxx/iomanip +504 -0
- data/modules/emscripten/system/include/libcxx/ios +988 -0
- data/modules/emscripten/system/include/libcxx/iosfwd +194 -0
- data/modules/emscripten/system/include/libcxx/iostream +60 -0
- data/modules/emscripten/system/include/libcxx/istream +1713 -0
- data/modules/emscripten/system/include/libcxx/iterator +1869 -0
- data/modules/emscripten/system/include/libcxx/limits +809 -0
- data/modules/emscripten/system/include/libcxx/list +2275 -0
- data/modules/emscripten/system/include/libcxx/locale +4591 -0
- data/modules/emscripten/system/include/libcxx/map +1924 -0
- data/modules/emscripten/system/include/libcxx/memory +5437 -0
- data/modules/emscripten/system/include/libcxx/mutex +566 -0
- data/modules/emscripten/system/include/libcxx/new +117 -0
- data/modules/emscripten/system/include/libcxx/numeric +197 -0
- data/modules/emscripten/system/include/libcxx/ostream +1286 -0
- data/modules/emscripten/system/include/libcxx/queue +717 -0
- data/modules/emscripten/system/include/libcxx/random +6750 -0
- data/modules/emscripten/system/include/libcxx/ratio +487 -0
- data/modules/emscripten/system/include/libcxx/readme.txt +1 -0
- data/modules/emscripten/system/include/libcxx/regex +6439 -0
- data/modules/emscripten/system/include/libcxx/scoped_allocator +578 -0
- data/modules/emscripten/system/include/libcxx/set +1025 -0
- data/modules/emscripten/system/include/libcxx/sstream +888 -0
- data/modules/emscripten/system/include/libcxx/stack +292 -0
- data/modules/emscripten/system/include/libcxx/stdexcept +162 -0
- data/modules/emscripten/system/include/libcxx/streambuf +564 -0
- data/modules/emscripten/system/include/libcxx/string +3987 -0
- data/modules/emscripten/system/include/libcxx/strstream +400 -0
- data/modules/emscripten/system/include/libcxx/support/solaris/floatingpoint.h +5 -0
- data/modules/emscripten/system/include/libcxx/support/solaris/wchar.h +38 -0
- data/modules/emscripten/system/include/libcxx/support/solaris/xlocale.h +146 -0
- data/modules/emscripten/system/include/libcxx/support/win32/limits_win32.h +79 -0
- data/modules/emscripten/system/include/libcxx/support/win32/locale_win32.h +116 -0
- data/modules/emscripten/system/include/libcxx/support/win32/math_win32.h +113 -0
- data/modules/emscripten/system/include/libcxx/support/win32/support.h +115 -0
- data/modules/emscripten/system/include/libcxx/system_error +636 -0
- data/modules/emscripten/system/include/libcxx/tgmath.h +29 -0
- data/modules/emscripten/system/include/libcxx/thread +459 -0
- data/modules/emscripten/system/include/libcxx/tuple +1092 -0
- data/modules/emscripten/system/include/libcxx/type_traits +3040 -0
- data/modules/emscripten/system/include/libcxx/typeindex +103 -0
- data/modules/emscripten/system/include/libcxx/typeinfo +124 -0
- data/modules/emscripten/system/include/libcxx/unordered_map +1864 -0
- data/modules/emscripten/system/include/libcxx/unordered_set +1144 -0
- data/modules/emscripten/system/include/libcxx/utility +583 -0
- data/modules/emscripten/system/include/libcxx/valarray +4779 -0
- data/modules/emscripten/system/include/libcxx/vector +3228 -0
- data/modules/emscripten/system/include/memory.h +10 -0
- data/modules/emscripten/system/include/mntent.h +23 -0
- data/modules/emscripten/system/include/net/arpa/inet.h +32 -0
- data/modules/emscripten/system/include/net/arpa/nameser.h +535 -0
- data/modules/emscripten/system/include/net/arpa/nameser_compat.h +187 -0
- data/modules/emscripten/system/include/net/if.h +87 -0
- data/modules/emscripten/system/include/net/netinet/in.h +166 -0
- data/modules/emscripten/system/include/net/netinet/tcp.h +246 -0
- data/modules/emscripten/system/include/net/resolv.h +389 -0
- data/modules/emscripten/system/include/netdb.h +94 -0
- data/modules/emscripten/system/include/nl_types.h +19 -0
- data/modules/emscripten/system/include/poll.h +3 -0
- data/modules/emscripten/system/include/pty.h +6 -0
- data/modules/emscripten/system/include/semaphore.h +31 -0
- data/modules/emscripten/system/include/spawn.h +105 -0
- data/modules/emscripten/system/include/stdbool.h +16 -0
- data/modules/emscripten/system/include/sys/bitypes.h +3 -0
- data/modules/emscripten/system/include/sys/io.h +14 -0
- data/modules/emscripten/system/include/sys/ioctl.h +26 -0
- data/modules/emscripten/system/include/sys/poll.h +31 -0
- data/modules/emscripten/system/include/sys/select.h +14 -0
- data/modules/emscripten/system/include/sys/socket.h +101 -0
- data/modules/emscripten/system/include/sys/socketvar.h +3 -0
- data/modules/emscripten/system/include/sys/statvfs.h +32 -0
- data/modules/emscripten/system/include/sys/sysctl.h +14 -0
- data/modules/emscripten/system/include/sys/uio.h +22 -0
- data/modules/emscripten/system/include/sys/un.h +66 -0
- data/modules/emscripten/system/include/sysexits.h +108 -0
- data/modules/emscripten/system/include/unwind.h +154 -0
- data/modules/emscripten/system/include/xlocale.h +47 -0
- data/modules/emscripten/system/include/zconf.h +428 -0
- data/modules/emscripten/system/include/zlib.h +1613 -0
- data/modules/emscripten/system/lib/compiler-rt/LICENSE.TXT +97 -0
- data/modules/emscripten/system/lib/compiler-rt/divdi3.c +47 -0
- data/modules/emscripten/system/lib/compiler-rt/int_endianness.h +116 -0
- data/modules/emscripten/system/lib/compiler-rt/int_lib.h +46 -0
- data/modules/emscripten/system/lib/compiler-rt/int_math.h +67 -0
- data/modules/emscripten/system/lib/compiler-rt/int_types.h +140 -0
- data/modules/emscripten/system/lib/compiler-rt/int_util.h +29 -0
- data/modules/emscripten/system/lib/compiler-rt/muldi3.c +56 -0
- data/modules/emscripten/system/lib/compiler-rt/readme.txt +20 -0
- data/modules/emscripten/system/lib/compiler-rt/udivdi3.c +36 -0
- data/modules/emscripten/system/lib/compiler-rt/udivmoddi4.c +251 -0
- data/modules/emscripten/system/lib/debugging.cpp +24 -0
- data/modules/emscripten/system/lib/dlmalloc.c +6299 -0
- data/modules/emscripten/system/lib/embind/bind.cpp +63 -0
- data/modules/emscripten/system/lib/libc/gen/err.c +49 -0
- data/modules/emscripten/system/lib/libc/gen/errx.c +49 -0
- data/modules/emscripten/system/lib/libc/gen/verr.c +58 -0
- data/modules/emscripten/system/lib/libc/gen/verrx.c +51 -0
- data/modules/emscripten/system/lib/libc/gen/vwarn.c +55 -0
- data/modules/emscripten/system/lib/libc/gen/vwarnx.c +48 -0
- data/modules/emscripten/system/lib/libc/gen/warn.c +49 -0
- data/modules/emscripten/system/lib/libc/gen/warnx.c +49 -0
- data/modules/emscripten/system/lib/libc/musl/COPYRIGHT +92 -0
- data/modules/emscripten/system/lib/libc/musl/readme.txt +1 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/alpha.h +125 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswalnum.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswalpha.c +14 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswblank.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswcntrl.c +10 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswctype.c +63 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswdigit.c +9 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswgraph.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswlower.c +6 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswprint.c +19 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswpunct.c +12 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswspace.c +19 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswupper.c +6 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/iswxdigit.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/nonspacing.h +62 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/punct.h +109 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/towctrans.c +268 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/wcswidth.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/wctrans.c +16 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/wcwidth.c +29 -0
- data/modules/emscripten/system/lib/libc/musl/src/ctype/wide.h +42 -0
- data/modules/emscripten/system/lib/libc/musl/src/internal/libc.c +22 -0
- data/modules/emscripten/system/lib/libc/musl/src/internal/libc.h +71 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/btowc.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/internal.c +38 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/internal.h +22 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/mblen.c +17 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/mbrlen.c +18 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/mbrtowc.c +57 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/mbsinit.c +17 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/mbsnrtowcs.c +65 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/mbsrtowcs.c +100 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/mbstowcs.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/mbtowc.c +53 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/wcrtomb.c +38 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/wcsnrtombs.c +52 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/wcsrtombs.c +58 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/wcstombs.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/wctob.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/multibyte/wctomb.c +18 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcpcpy.c +6 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcpncpy.c +6 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcscasecmp.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcscasecmp_l.c +6 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcscat.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcschr.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcscmp.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcscpy.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcscspn.c +10 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsdup.c +11 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcslen.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsncasecmp.c +9 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsncasecmp_l.c +6 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsncat.c +10 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsncmp.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsncpy.c +9 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsnlen.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcspbrk.c +7 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsrchr.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsspn.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcsstr.c +108 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcstok.c +12 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wcswcs.c +6 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wmemchr.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wmemcmp.c +8 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wmemcpy.c +9 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wmemmove.c +12 -0
- data/modules/emscripten/system/lib/libc/musl/src/string/wmemset.c +9 -0
- data/modules/emscripten/system/lib/libc/stdlib/getopt_long.c +511 -0
- data/modules/emscripten/system/lib/libc/stdlib/strtod.c +305 -0
- data/modules/emscripten/system/lib/libc.symbols +81 -0
- data/modules/emscripten/system/lib/libcextra.symbols +61 -0
- data/modules/emscripten/system/lib/libcxx/CREDITS.TXT +91 -0
- data/modules/emscripten/system/lib/libcxx/LICENSE.txt +76 -0
- data/modules/emscripten/system/lib/libcxx/algorithm.cpp +83 -0
- data/modules/emscripten/system/lib/libcxx/bind.cpp +30 -0
- data/modules/emscripten/system/lib/libcxx/chrono.cpp +132 -0
- data/modules/emscripten/system/lib/libcxx/condition_variable.cpp +81 -0
- data/modules/emscripten/system/lib/libcxx/debug.cpp +504 -0
- data/modules/emscripten/system/lib/libcxx/exception.cpp +226 -0
- data/modules/emscripten/system/lib/libcxx/future.cpp +285 -0
- data/modules/emscripten/system/lib/libcxx/hash.cpp +564 -0
- data/modules/emscripten/system/lib/libcxx/ios.cpp +455 -0
- data/modules/emscripten/system/lib/libcxx/iostream.cpp +68 -0
- data/modules/emscripten/system/lib/libcxx/locale.cpp +6093 -0
- data/modules/emscripten/system/lib/libcxx/memory.cpp +223 -0
- data/modules/emscripten/system/lib/libcxx/mutex.cpp +250 -0
- data/modules/emscripten/system/lib/libcxx/new.cpp +205 -0
- data/modules/emscripten/system/lib/libcxx/random.cpp +48 -0
- data/modules/emscripten/system/lib/libcxx/readme.txt +1 -0
- data/modules/emscripten/system/lib/libcxx/regex.cpp +325 -0
- data/modules/emscripten/system/lib/libcxx/stdexcept.cpp +196 -0
- data/modules/emscripten/system/lib/libcxx/string.cpp +687 -0
- data/modules/emscripten/system/lib/libcxx/strstream.cpp +329 -0
- data/modules/emscripten/system/lib/libcxx/support/solaris/README +4 -0
- data/modules/emscripten/system/lib/libcxx/support/solaris/mbsnrtowcs.inc +76 -0
- data/modules/emscripten/system/lib/libcxx/support/solaris/wcsnrtombs.inc +93 -0
- data/modules/emscripten/system/lib/libcxx/support/solaris/xlocale.c +245 -0
- data/modules/emscripten/system/lib/libcxx/support/win32/locale_win32.cpp +94 -0
- data/modules/emscripten/system/lib/libcxx/support/win32/support.cpp +70 -0
- data/modules/emscripten/system/lib/libcxx/symbols +2927 -0
- data/modules/emscripten/system/lib/libcxx/system_error.cpp +201 -0
- data/modules/emscripten/system/lib/libcxx/thread.cpp +208 -0
- data/modules/emscripten/system/lib/libcxx/typeinfo.cpp +60 -0
- data/modules/emscripten/system/lib/libcxx/utility.cpp +17 -0
- data/modules/emscripten/system/lib/libcxx/valarray.cpp +54 -0
- data/modules/emscripten/system/lib/libcxxabi/CREDITS.TXT +38 -0
- data/modules/emscripten/system/lib/libcxxabi/LICENSE.TXT +76 -0
- data/modules/emscripten/system/lib/libcxxabi/include/cxa_demangle.h +167 -0
- data/modules/emscripten/system/lib/libcxxabi/include/cxxabi.h +175 -0
- data/modules/emscripten/system/lib/libcxxabi/lib/buildit +99 -0
- data/modules/emscripten/system/lib/libcxxabi/readme.txt +1 -0
- data/modules/emscripten/system/lib/libcxxabi/src/abort_message.cpp +50 -0
- data/modules/emscripten/system/lib/libcxxabi/src/abort_message.h +33 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_aux_runtime.cpp +34 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_demangle.cpp +11036 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_exception.cpp +622 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_exception.hpp +123 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_exception_storage.cpp +91 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_guard.cpp +231 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_handlers.cpp +125 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_handlers.hpp +54 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_new_delete.cpp +242 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_personality.cpp +1055 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_unexpected.cpp +27 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_vector.cpp +367 -0
- data/modules/emscripten/system/lib/libcxxabi/src/cxa_virtual.cpp +31 -0
- data/modules/emscripten/system/lib/libcxxabi/src/exception.cpp +41 -0
- data/modules/emscripten/system/lib/libcxxabi/src/fallback_malloc.ipp +174 -0
- data/modules/emscripten/system/lib/libcxxabi/src/private_typeinfo.cpp +1146 -0
- data/modules/emscripten/system/lib/libcxxabi/src/private_typeinfo.h +248 -0
- data/modules/emscripten/system/lib/libcxxabi/src/stdexcept.cpp +169 -0
- data/modules/emscripten/system/lib/libcxxabi/src/typeinfo.cpp +53 -0
- data/modules/emscripten/system/lib/libcxxabi/symbols +236 -0
- data/modules/emscripten/system/lib/sdl.cpp +13 -0
- data/modules/emscripten/system/lib/sdl.symbols +1 -0
- data/modules/emscripten/tests/hello_world.js +92 -0
- data/modules/emscripten/third_party/CppHeaderParser/CppHeaderParser/CppHeaderParser.py +2347 -0
- data/modules/emscripten/third_party/CppHeaderParser/CppHeaderParser/__init__.py +4 -0
- data/modules/emscripten/third_party/CppHeaderParser/CppHeaderParser/doc/CppHeaderParser.html +657 -0
- data/modules/emscripten/third_party/CppHeaderParser/CppHeaderParser/examples/SampleClass.h +147 -0
- data/modules/emscripten/third_party/CppHeaderParser/CppHeaderParser/examples/readSampleClass.py +74 -0
- data/modules/emscripten/third_party/CppHeaderParser/PKG-INFO +249 -0
- data/modules/emscripten/third_party/CppHeaderParser/README.html +544 -0
- data/modules/emscripten/third_party/CppHeaderParser/README.txt +226 -0
- data/modules/emscripten/third_party/CppHeaderParser/setup.py +43 -0
- data/modules/emscripten/third_party/ansidecl.h +371 -0
- data/modules/emscripten/third_party/closure-compiler/COPYING +202 -0
- data/modules/emscripten/third_party/closure-compiler/README +292 -0
- data/modules/emscripten/third_party/closure-compiler/compiler.jar +0 -0
- data/modules/emscripten/third_party/closure-compiler/readme.txt +3 -0
- data/modules/emscripten/third_party/cp-demangle.h +161 -0
- data/modules/emscripten/third_party/demangle.h +549 -0
- data/modules/emscripten/third_party/demangler.py +49 -0
- data/modules/emscripten/third_party/gcc_demangler.c +4226 -0
- data/modules/emscripten/third_party/gcc_demangler.js +21282 -0
- data/modules/emscripten/third_party/jni/emjvm.cpp +133 -0
- data/modules/emscripten/third_party/jni/emjvm.h +8 -0
- data/modules/emscripten/third_party/jni/emjvm.js +185 -0
- data/modules/emscripten/third_party/jni/jni.h +1154 -0
- data/modules/emscripten/third_party/libiberty.h +634 -0
- data/modules/emscripten/third_party/lzma.js/README.markdown +37 -0
- data/modules/emscripten/third_party/lzma.js/doit.sh +37 -0
- data/modules/emscripten/third_party/lzma.js/lzip/AUTHORS +7 -0
- data/modules/emscripten/third_party/lzma.js/lzip/COPYING +676 -0
- data/modules/emscripten/third_party/lzma.js/lzip/ChangeLog +201 -0
- data/modules/emscripten/third_party/lzma.js/lzip/INSTALL +56 -0
- data/modules/emscripten/third_party/lzma.js/lzip/Makefile +160 -0
- data/modules/emscripten/third_party/lzma.js/lzip/Makefile.in +138 -0
- data/modules/emscripten/third_party/lzma.js/lzip/NEWS +22 -0
- data/modules/emscripten/third_party/lzma.js/lzip/README +77 -0
- data/modules/emscripten/third_party/lzma.js/lzip/arg_parser.cc +204 -0
- data/modules/emscripten/third_party/lzma.js/lzip/arg_parser.h +106 -0
- data/modules/emscripten/third_party/lzma.js/lzip/configure +192 -0
- data/modules/emscripten/third_party/lzma.js/lzip/decoder.cc +252 -0
- data/modules/emscripten/third_party/lzma.js/lzip/decoder.h +268 -0
- data/modules/emscripten/third_party/lzma.js/lzip/encoder.cc +643 -0
- data/modules/emscripten/third_party/lzma.js/lzip/encoder.h +582 -0
- data/modules/emscripten/third_party/lzma.js/lzip/fast_encoder.cc +378 -0
- data/modules/emscripten/third_party/lzma.js/lzip/fast_encoder.h +171 -0
- data/modules/emscripten/third_party/lzma.js/lzip/lzip.h +264 -0
- data/modules/emscripten/third_party/lzma.js/lzip/main.cc +545 -0
- data/modules/emscripten/third_party/lzma.js/lzma-decoder.js +27 -0
- data/modules/emscripten/third_party/lzma.js/lzma-full.js +27 -0
- data/modules/emscripten/third_party/lzma.js/native_test.sh +5 -0
- data/modules/emscripten/third_party/lzma.js/post.js +13 -0
- data/modules/emscripten/third_party/lzma.js/pre.js +13 -0
- data/modules/emscripten/third_party/lzma.js/test-decoder.js +39 -0
- data/modules/emscripten/third_party/lzma.js/test-full.html +9 -0
- data/modules/emscripten/third_party/lzma.js/test-full.js +78 -0
- data/modules/emscripten/third_party/ply/ANNOUNCE +40 -0
- data/modules/emscripten/third_party/ply/CHANGES +1093 -0
- data/modules/emscripten/third_party/ply/PKG-INFO +22 -0
- data/modules/emscripten/third_party/ply/README +271 -0
- data/modules/emscripten/third_party/ply/TODO +16 -0
- data/modules/emscripten/third_party/ply/doc/internal.html +874 -0
- data/modules/emscripten/third_party/ply/doc/makedoc.py +194 -0
- data/modules/emscripten/third_party/ply/doc/ply.html +3262 -0
- data/modules/emscripten/third_party/ply/example/BASIC/README +79 -0
- data/modules/emscripten/third_party/ply/example/BASIC/basic.py +71 -0
- data/modules/emscripten/third_party/ply/example/BASIC/basiclex.py +74 -0
- data/modules/emscripten/third_party/ply/example/BASIC/basiclog.py +79 -0
- data/modules/emscripten/third_party/ply/example/BASIC/basinterp.py +441 -0
- data/modules/emscripten/third_party/ply/example/BASIC/basparse.py +424 -0
- data/modules/emscripten/third_party/ply/example/BASIC/dim.bas +14 -0
- data/modules/emscripten/third_party/ply/example/BASIC/func.bas +5 -0
- data/modules/emscripten/third_party/ply/example/BASIC/gcd.bas +22 -0
- data/modules/emscripten/third_party/ply/example/BASIC/gosub.bas +13 -0
- data/modules/emscripten/third_party/ply/example/BASIC/hello.bas +4 -0
- data/modules/emscripten/third_party/ply/example/BASIC/linear.bas +17 -0
- data/modules/emscripten/third_party/ply/example/BASIC/maxsin.bas +12 -0
- data/modules/emscripten/third_party/ply/example/BASIC/powers.bas +13 -0
- data/modules/emscripten/third_party/ply/example/BASIC/rand.bas +4 -0
- data/modules/emscripten/third_party/ply/example/BASIC/sales.bas +20 -0
- data/modules/emscripten/third_party/ply/example/BASIC/sears.bas +18 -0
- data/modules/emscripten/third_party/ply/example/BASIC/sqrt1.bas +5 -0
- data/modules/emscripten/third_party/ply/example/BASIC/sqrt2.bas +4 -0
- data/modules/emscripten/third_party/ply/example/GardenSnake/GardenSnake.py +709 -0
- data/modules/emscripten/third_party/ply/example/GardenSnake/README +5 -0
- data/modules/emscripten/third_party/ply/example/README +10 -0
- data/modules/emscripten/third_party/ply/example/ansic/README +2 -0
- data/modules/emscripten/third_party/ply/example/ansic/clex.py +164 -0
- data/modules/emscripten/third_party/ply/example/ansic/cparse.py +863 -0
- data/modules/emscripten/third_party/ply/example/calc/calc.py +107 -0
- data/modules/emscripten/third_party/ply/example/calcdebug/calc.py +113 -0
- data/modules/emscripten/third_party/ply/example/classcalc/calc.py +157 -0
- data/modules/emscripten/third_party/ply/example/cleanup.sh +2 -0
- data/modules/emscripten/third_party/ply/example/closurecalc/calc.py +130 -0
- data/modules/emscripten/third_party/ply/example/hedit/hedit.py +48 -0
- data/modules/emscripten/third_party/ply/example/newclasscalc/calc.py +160 -0
- data/modules/emscripten/third_party/ply/example/optcalc/README +9 -0
- data/modules/emscripten/third_party/ply/example/optcalc/calc.py +119 -0
- data/modules/emscripten/third_party/ply/example/unicalc/calc.py +117 -0
- data/modules/emscripten/third_party/ply/example/yply/README +41 -0
- data/modules/emscripten/third_party/ply/example/yply/ylex.py +112 -0
- data/modules/emscripten/third_party/ply/example/yply/yparse.py +217 -0
- data/modules/emscripten/third_party/ply/example/yply/yply.py +53 -0
- data/modules/emscripten/third_party/ply/ply/__init__.py +4 -0
- data/modules/emscripten/third_party/ply/ply/cpp.py +898 -0
- data/modules/emscripten/third_party/ply/ply/ctokens.py +133 -0
- data/modules/emscripten/third_party/ply/ply/lex.py +1058 -0
- data/modules/emscripten/third_party/ply/ply/yacc.py +3276 -0
- data/modules/emscripten/third_party/ply/setup.py +31 -0
- data/modules/emscripten/third_party/ply/test/README +7 -0
- data/modules/emscripten/third_party/ply/test/calclex.py +49 -0
- data/modules/emscripten/third_party/ply/test/cleanup.sh +4 -0
- data/modules/emscripten/third_party/ply/test/lex_closure.py +54 -0
- data/modules/emscripten/third_party/ply/test/lex_doc1.py +26 -0
- data/modules/emscripten/third_party/ply/test/lex_dup1.py +29 -0
- data/modules/emscripten/third_party/ply/test/lex_dup2.py +33 -0
- data/modules/emscripten/third_party/ply/test/lex_dup3.py +31 -0
- data/modules/emscripten/third_party/ply/test/lex_empty.py +20 -0
- data/modules/emscripten/third_party/ply/test/lex_error1.py +24 -0
- data/modules/emscripten/third_party/ply/test/lex_error2.py +26 -0
- data/modules/emscripten/third_party/ply/test/lex_error3.py +27 -0
- data/modules/emscripten/third_party/ply/test/lex_error4.py +27 -0
- data/modules/emscripten/third_party/ply/test/lex_hedit.py +47 -0
- data/modules/emscripten/third_party/ply/test/lex_ignore.py +31 -0
- data/modules/emscripten/third_party/ply/test/lex_ignore2.py +29 -0
- data/modules/emscripten/third_party/ply/test/lex_literal1.py +25 -0
- data/modules/emscripten/third_party/ply/test/lex_literal2.py +25 -0
- data/modules/emscripten/third_party/ply/test/lex_many_tokens.py +27 -0
- data/modules/emscripten/third_party/ply/test/lex_module.py +10 -0
- data/modules/emscripten/third_party/ply/test/lex_module_import.py +42 -0
- data/modules/emscripten/third_party/ply/test/lex_object.py +55 -0
- data/modules/emscripten/third_party/ply/test/lex_opt_alias.py +54 -0
- data/modules/emscripten/third_party/ply/test/lex_optimize.py +50 -0
- data/modules/emscripten/third_party/ply/test/lex_optimize2.py +50 -0
- data/modules/emscripten/third_party/ply/test/lex_optimize3.py +52 -0
- data/modules/emscripten/third_party/ply/test/lex_re1.py +27 -0
- data/modules/emscripten/third_party/ply/test/lex_re2.py +27 -0
- data/modules/emscripten/third_party/ply/test/lex_re3.py +29 -0
- data/modules/emscripten/third_party/ply/test/lex_rule1.py +27 -0
- data/modules/emscripten/third_party/ply/test/lex_rule2.py +29 -0
- data/modules/emscripten/third_party/ply/test/lex_rule3.py +27 -0
- data/modules/emscripten/third_party/ply/test/lex_state1.py +40 -0
- data/modules/emscripten/third_party/ply/test/lex_state2.py +40 -0
- data/modules/emscripten/third_party/ply/test/lex_state3.py +42 -0
- data/modules/emscripten/third_party/ply/test/lex_state4.py +41 -0
- data/modules/emscripten/third_party/ply/test/lex_state5.py +40 -0
- data/modules/emscripten/third_party/ply/test/lex_state_noerror.py +39 -0
- data/modules/emscripten/third_party/ply/test/lex_state_norule.py +40 -0
- data/modules/emscripten/third_party/ply/test/lex_state_try.py +45 -0
- data/modules/emscripten/third_party/ply/test/lex_token1.py +19 -0
- data/modules/emscripten/third_party/ply/test/lex_token2.py +22 -0
- data/modules/emscripten/third_party/ply/test/lex_token3.py +24 -0
- data/modules/emscripten/third_party/ply/test/lex_token4.py +26 -0
- data/modules/emscripten/third_party/ply/test/lex_token5.py +31 -0
- data/modules/emscripten/third_party/ply/test/lex_token_dup.py +29 -0
- data/modules/emscripten/third_party/ply/test/testlex.py +606 -0
- data/modules/emscripten/third_party/ply/test/testyacc.py +347 -0
- data/modules/emscripten/third_party/ply/test/yacc_badargs.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_badid.py +77 -0
- data/modules/emscripten/third_party/ply/test/yacc_badprec.py +64 -0
- data/modules/emscripten/third_party/ply/test/yacc_badprec2.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_badprec3.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_badrule.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_badtok.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_dup.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_error1.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_error2.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_error3.py +67 -0
- data/modules/emscripten/third_party/ply/test/yacc_error4.py +72 -0
- data/modules/emscripten/third_party/ply/test/yacc_inf.py +56 -0
- data/modules/emscripten/third_party/ply/test/yacc_literal.py +69 -0
- data/modules/emscripten/third_party/ply/test/yacc_misplaced.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_missing1.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_nested.py +33 -0
- data/modules/emscripten/third_party/ply/test/yacc_nodoc.py +67 -0
- data/modules/emscripten/third_party/ply/test/yacc_noerror.py +66 -0
- data/modules/emscripten/third_party/ply/test/yacc_nop.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_notfunc.py +66 -0
- data/modules/emscripten/third_party/ply/test/yacc_notok.py +67 -0
- data/modules/emscripten/third_party/ply/test/yacc_prec1.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_rr.py +72 -0
- data/modules/emscripten/third_party/ply/test/yacc_rr_unused.py +30 -0
- data/modules/emscripten/third_party/ply/test/yacc_simple.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_sr.py +63 -0
- data/modules/emscripten/third_party/ply/test/yacc_term1.py +68 -0
- data/modules/emscripten/third_party/ply/test/yacc_unused.py +77 -0
- data/modules/emscripten/third_party/ply/test/yacc_unused_rule.py +72 -0
- data/modules/emscripten/third_party/ply/test/yacc_uprec.py +63 -0
- data/modules/emscripten/third_party/ply/test/yacc_uprec2.py +63 -0
- data/modules/emscripten/third_party/readme.txt +7 -0
- data/modules/emscripten/third_party/websockify/CHANGES.txt +23 -0
- data/modules/emscripten/third_party/websockify/LICENSE.txt +16 -0
- data/modules/emscripten/third_party/websockify/MANIFEST.in +1 -0
- data/modules/emscripten/third_party/websockify/Makefile +11 -0
- data/modules/emscripten/third_party/websockify/README.md +168 -0
- data/modules/emscripten/third_party/websockify/Windows/Windows Service Readme.txt +39 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/Program.cs +24 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/ProjectInstaller.Designer.cs +61 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/ProjectInstaller.cs +19 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/ProjectInstaller.resx +129 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/Properties/AssemblyInfo.cs +36 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/Service1.Designer.cs +37 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/Service1.cs +41 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/noVNC Websocket.csproj +75 -0
- data/modules/emscripten/third_party/websockify/Windows/noVNC Websocket Service Project/noVNC Websocket.sln +20 -0
- data/modules/emscripten/third_party/websockify/docs/LICENSE.GPL-3 +621 -0
- data/modules/emscripten/third_party/websockify/docs/LICENSE.LGPL-3 +165 -0
- data/modules/emscripten/third_party/websockify/docs/LICENSE.MPL-2.0 +373 -0
- data/modules/emscripten/third_party/websockify/docs/TODO +9 -0
- data/modules/emscripten/third_party/websockify/docs/flash_policy.txt +4 -0
- data/modules/emscripten/third_party/websockify/docs/latency_results.txt +114 -0
- data/modules/emscripten/third_party/websockify/docs/notes +17 -0
- data/modules/emscripten/third_party/websockify/docs/release.txt +9 -0
- data/modules/emscripten/third_party/websockify/docs/websockify.1 +110 -0
- data/modules/emscripten/third_party/websockify/include/VT100.js +919 -0
- data/modules/emscripten/third_party/websockify/include/base64.js +114 -0
- data/modules/emscripten/third_party/websockify/include/keysym.js +99 -0
- data/modules/emscripten/third_party/websockify/include/util.js +359 -0
- data/modules/emscripten/third_party/websockify/include/web-socket-js/README.txt +109 -0
- data/modules/emscripten/third_party/websockify/include/web-socket-js/WebSocketMain.swf +0 -0
- data/modules/emscripten/third_party/websockify/include/web-socket-js/swfobject.js +4 -0
- data/modules/emscripten/third_party/websockify/include/web-socket-js/web_socket.js +391 -0
- data/modules/emscripten/third_party/websockify/include/websock.js +422 -0
- data/modules/emscripten/third_party/websockify/include/webutil.js +216 -0
- data/modules/emscripten/third_party/websockify/include/wsirc.js +235 -0
- data/modules/emscripten/third_party/websockify/include/wstelnet.js +335 -0
- data/modules/emscripten/third_party/websockify/other/Makefile +14 -0
- data/modules/emscripten/third_party/websockify/other/README.md +51 -0
- data/modules/emscripten/third_party/websockify/other/launch.sh +108 -0
- data/modules/emscripten/third_party/websockify/other/project.clj +13 -0
- data/modules/emscripten/third_party/websockify/other/websocket.c +802 -0
- data/modules/emscripten/third_party/websockify/other/websocket.h +84 -0
- data/modules/emscripten/third_party/websockify/other/websocket.rb +456 -0
- data/modules/emscripten/third_party/websockify/other/websockify.c +385 -0
- data/modules/emscripten/third_party/websockify/other/websockify.clj +233 -0
- data/modules/emscripten/third_party/websockify/other/websockify.js +196 -0
- data/modules/emscripten/third_party/websockify/other/websockify.rb +171 -0
- data/modules/emscripten/third_party/websockify/other/wswrap +22 -0
- data/modules/emscripten/third_party/websockify/rebind +18 -0
- data/modules/emscripten/third_party/websockify/rebind.c +94 -0
- data/modules/emscripten/third_party/websockify/run +5 -0
- data/modules/emscripten/third_party/websockify/setup.py +30 -0
- data/modules/emscripten/third_party/websockify/tests/b64_vs_utf8.py +29 -0
- data/modules/emscripten/third_party/websockify/tests/base64.html +91 -0
- data/modules/emscripten/third_party/websockify/tests/base64.js +12 -0
- data/modules/emscripten/third_party/websockify/tests/echo.html +148 -0
- data/modules/emscripten/third_party/websockify/tests/echo.py +75 -0
- data/modules/emscripten/third_party/websockify/tests/echo.rb +62 -0
- data/modules/emscripten/third_party/websockify/tests/latency.html +290 -0
- data/modules/emscripten/third_party/websockify/tests/latency.py +75 -0
- data/modules/emscripten/third_party/websockify/tests/load.html +250 -0
- data/modules/emscripten/third_party/websockify/tests/load.py +167 -0
- data/modules/emscripten/third_party/websockify/tests/plain_echo.html +168 -0
- data/modules/emscripten/third_party/websockify/tests/simple.html +68 -0
- data/modules/emscripten/third_party/websockify/tests/utf8-list.py +22 -0
- data/modules/emscripten/third_party/websockify/websockify/__init__.py +2 -0
- data/modules/emscripten/third_party/websockify/websockify/websocket.py +982 -0
- data/modules/emscripten/third_party/websockify/websockify/websocketproxy.py +393 -0
- data/modules/emscripten/third_party/websockify/websockify.py +5 -0
- data/modules/emscripten/third_party/websockify/wsirc.html +99 -0
- data/modules/emscripten/third_party/websockify/wstelnet.html +74 -0
- data/modules/emscripten/tools/__init__.py +0 -0
- data/modules/emscripten/tools/__init__.pyc +0 -0
- data/modules/emscripten/tools/autodebugger.py +289 -0
- data/modules/emscripten/tools/autodebugger_c.py +37 -0
- data/modules/emscripten/tools/autodebugger_indenter.py +18 -0
- data/modules/emscripten/tools/autodebugger_js.py +47 -0
- data/modules/emscripten/tools/autodediffer.py +60 -0
- data/modules/emscripten/tools/bindings_generator.py +832 -0
- data/modules/emscripten/tools/bisect_pair.py +88 -0
- data/modules/emscripten/tools/cache.py +198 -0
- data/modules/emscripten/tools/cache.pyc +0 -0
- data/modules/emscripten/tools/clean_webconsole.py +34 -0
- data/modules/emscripten/tools/crunch-worker.js +124 -0
- data/modules/emscripten/tools/diff_autodebugger.py +15 -0
- data/modules/emscripten/tools/eliminator/asm-eliminator-test-output.js +5129 -0
- data/modules/emscripten/tools/eliminator/asm-eliminator-test.js +6861 -0
- data/modules/emscripten/tools/eliminator/eliminator-test-output.js +6122 -0
- data/modules/emscripten/tools/eliminator/eliminator-test.js +8856 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/README.html +888 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/README.org +463 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/bin/uglifyjs +317 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/docstyle.css +75 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/lib/object-ast.js +75 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/lib/parse-js.js +1363 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/lib/process.js +2005 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/lib/squeeze-more.js +51 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/package.json +22 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/beautify.js +28 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/testparser.js +402 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/array1.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/array2.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/array3.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/array4.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/assignment.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/concatstring.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/const.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/empty-blocks.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/forstatement.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/if.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/ifreturn.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/ifreturn2.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue10.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue11.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue13.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue14.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue16.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue17.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue20.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue21.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue25.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue27.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue28.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue29.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue30.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue34.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue4.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue48.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue50.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue53.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue54.1.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue68.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue69.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/issue9.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/mangle.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/strict-equals.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/var.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/expected/with.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/array1.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/array2.js +4 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/array3.js +4 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/array4.js +6 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/assignment.js +20 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/concatstring.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/const.js +5 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/empty-blocks.js +4 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/forstatement.js +10 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/if.js +6 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/ifreturn.js +9 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/ifreturn2.js +16 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue10.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue11.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue13.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue14.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue16.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue17.js +4 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue20.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue21.js +6 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue25.js +7 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue27.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue28.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue29.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue30.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue34.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue4.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue48.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue50.js +9 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue53.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue54.1.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue68.js +5 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue69.js +1 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/issue9.js +4 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/mangle.js +5 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/strict-equals.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/var.js +3 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/compress/test/with.js +2 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/test/unit/scripts.js +55 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/tmp/hoist.js +33 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/tmp/instrument.js +97 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/tmp/instrument2.js +138 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/tmp/test.js +16 -0
- data/modules/emscripten/tools/eliminator/node_modules/uglify-js/uglify-js.js +17 -0
- data/modules/emscripten/tools/eliminator/safe-eliminator-test-output.js +85 -0
- data/modules/emscripten/tools/eliminator/safe-eliminator-test.js +103 -0
- data/modules/emscripten/tools/emconfiguren.py +19 -0
- data/modules/emscripten/tools/emmaken.py +230 -0
- data/modules/emscripten/tools/emmakenxx.py +18 -0
- data/modules/emscripten/tools/exec_llvm.py +50 -0
- data/modules/emscripten/tools/file2json.py +49 -0
- data/modules/emscripten/tools/file_packager.py +649 -0
- data/modules/emscripten/tools/find_bigfuncs.py +23 -0
- data/modules/emscripten/tools/find_bigis.py +18 -0
- data/modules/emscripten/tools/fix_closure.py +88 -0
- data/modules/emscripten/tools/ie7_fix.py +14 -0
- data/modules/emscripten/tools/js-optimizer.js +3440 -0
- data/modules/emscripten/tools/js_optimizer.py +341 -0
- data/modules/emscripten/tools/js_optimizer.pyc +0 -0
- data/modules/emscripten/tools/jsrun.py +27 -0
- data/modules/emscripten/tools/jsrun.pyc +0 -0
- data/modules/emscripten/tools/ll-strip.py +56 -0
- data/modules/emscripten/tools/make_file.py +19 -0
- data/modules/emscripten/tools/make_minigzip.py +13 -0
- data/modules/emscripten/tools/namespacer.py +95 -0
- data/modules/emscripten/tools/nativize_llvm.py +34 -0
- data/modules/emscripten/tools/node_modules/source-map/CHANGELOG.md +58 -0
- data/modules/emscripten/tools/node_modules/source-map/LICENSE +28 -0
- data/modules/emscripten/tools/node_modules/source-map/Makefile.dryice.js +166 -0
- data/modules/emscripten/tools/node_modules/source-map/README.md +347 -0
- data/modules/emscripten/tools/node_modules/source-map/build/assert-shim.js +56 -0
- data/modules/emscripten/tools/node_modules/source-map/build/mini-require.js +152 -0
- data/modules/emscripten/tools/node_modules/source-map/build/prefix-source-map.jsm +20 -0
- data/modules/emscripten/tools/node_modules/source-map/build/prefix-utils.jsm +18 -0
- data/modules/emscripten/tools/node_modules/source-map/build/suffix-browser.js +8 -0
- data/modules/emscripten/tools/node_modules/source-map/build/suffix-source-map.jsm +6 -0
- data/modules/emscripten/tools/node_modules/source-map/build/suffix-utils.jsm +21 -0
- data/modules/emscripten/tools/node_modules/source-map/build/test-prefix.js +8 -0
- data/modules/emscripten/tools/node_modules/source-map/build/test-suffix.js +3 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map/array-set.js +96 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map/base64-vlq.js +144 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map/base64.js +42 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map/binary-search.js +81 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map/source-map-consumer.js +430 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map/source-map-generator.js +381 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map/source-node.js +353 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map/util.js +117 -0
- data/modules/emscripten/tools/node_modules/source-map/lib/source-map.js +8 -0
- data/modules/emscripten/tools/node_modules/source-map/node_modules/amdefine/LICENSE +58 -0
- data/modules/emscripten/tools/node_modules/source-map/node_modules/amdefine/README.md +119 -0
- data/modules/emscripten/tools/node_modules/source-map/node_modules/amdefine/amdefine.js +299 -0
- data/modules/emscripten/tools/node_modules/source-map/node_modules/amdefine/package.json +33 -0
- data/modules/emscripten/tools/node_modules/source-map/package.json +74 -0
- data/modules/emscripten/tools/node_modules/source-map/test/run-tests.js +73 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-api.js +26 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-array-set.js +71 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-base64-vlq.js +24 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-base64.js +35 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-binary-search.js +54 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-dog-fooding.js +72 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-source-map-consumer.js +306 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-source-map-generator.js +391 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/test-source-node.js +282 -0
- data/modules/emscripten/tools/node_modules/source-map/test/source-map/util.js +152 -0
- data/modules/emscripten/tools/reproduceriter.js +216 -0
- data/modules/emscripten/tools/reproduceriter.py +160 -0
- data/modules/emscripten/tools/response_file.py +28 -0
- data/modules/emscripten/tools/response_file.pyc +0 -0
- data/modules/emscripten/tools/scan_js.py +20 -0
- data/modules/emscripten/tools/scan_ll.py +18 -0
- data/modules/emscripten/tools/scons/site_scons/site_tools/emscripten/__init__.py +3 -0
- data/modules/emscripten/tools/scons/site_scons/site_tools/emscripten/emscripten.py +46 -0
- data/modules/emscripten/tools/settings_template_readonly.py +47 -0
- data/modules/emscripten/tools/shared.py +1437 -0
- data/modules/emscripten/tools/shared.pyc +0 -0
- data/modules/emscripten/tools/source-maps/sourcemap2json.js +15 -0
- data/modules/emscripten/tools/source-maps/sourcemapper.js +177 -0
- data/modules/emscripten/tools/split.py +97 -0
- data/modules/emscripten/tools/tempfiles.py +40 -0
- data/modules/emscripten/tools/tempfiles.pyc +0 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-last-output.js +75 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-last.js +91 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-outline-output.js +570 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-outline.js +606 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-pre-output.js +540 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-pre.js +550 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-regs-min-output.js +36 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-regs-min.js +37 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-regs-output.js +106 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-regs.js +110 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-relocate-output.js +9 -0
- data/modules/emscripten/tools/test-js-optimizer-asm-relocate.js +12 -0
- data/modules/emscripten/tools/test-js-optimizer-output.js +291 -0
- data/modules/emscripten/tools/test-js-optimizer-regs-output.js +232 -0
- data/modules/emscripten/tools/test-js-optimizer-regs.js +237 -0
- data/modules/emscripten/tools/test-js-optimizer-t2-output.js +91 -0
- data/modules/emscripten/tools/test-js-optimizer-t2.js +92 -0
- data/modules/emscripten/tools/test-js-optimizer-t2c-output.js +17 -0
- data/modules/emscripten/tools/test-js-optimizer-t2c.js +18 -0
- data/modules/emscripten/tools/test-js-optimizer-t3-output.js +49 -0
- data/modules/emscripten/tools/test-js-optimizer-t3.js +50 -0
- data/modules/emscripten/tools/test-js-optimizer.js +401 -0
- data/modules/mruby/AUTHORS +18 -0
- data/modules/mruby/CONTRIBUTING.md +65 -0
- data/modules/mruby/ChangeLog +15 -0
- data/modules/mruby/INSTALL +29 -0
- data/modules/mruby/LEGAL +6 -0
- data/modules/mruby/MITL +20 -0
- data/modules/mruby/Makefile +18 -0
- data/modules/mruby/NEWS +13 -0
- data/modules/mruby/README.md +116 -0
- data/modules/mruby/Rakefile +114 -0
- data/modules/mruby/TODO +11 -0
- data/modules/mruby/benchmark/ao-render.rb +315 -0
- data/modules/mruby/benchmark/bm_so_lists.rb +47 -0
- data/modules/mruby/benchmark/fib39.rb +8 -0
- data/modules/mruby/build_config.rb +88 -0
- data/modules/mruby/doc/compile/README.md +376 -0
- data/modules/mruby/doc/mrbgems/README.md +254 -0
- data/modules/mruby/examples/mrbgems/c_and_ruby_extension_example/README.md +4 -0
- data/modules/mruby/examples/mrbgems/c_and_ruby_extension_example/mrbgem.rake +23 -0
- data/modules/mruby/examples/mrbgems/c_and_ruby_extension_example/mrblib/example.rb +5 -0
- data/modules/mruby/examples/mrbgems/c_and_ruby_extension_example/src/example.c +20 -0
- data/modules/mruby/examples/mrbgems/c_and_ruby_extension_example/test/example.rb +7 -0
- data/modules/mruby/examples/mrbgems/c_extension_example/README.md +4 -0
- data/modules/mruby/examples/mrbgems/c_extension_example/mrbgem.rake +23 -0
- data/modules/mruby/examples/mrbgems/c_extension_example/src/example.c +20 -0
- data/modules/mruby/examples/mrbgems/c_extension_example/test/example.c +7 -0
- data/modules/mruby/examples/mrbgems/c_extension_example/test/example.rb +3 -0
- data/modules/mruby/examples/mrbgems/ruby_extension_example/README.md +4 -0
- data/modules/mruby/examples/mrbgems/ruby_extension_example/mrbgem.rake +23 -0
- data/modules/mruby/examples/mrbgems/ruby_extension_example/mrblib/example.rb +5 -0
- data/modules/mruby/examples/mrbgems/ruby_extension_example/test/example.rb +3 -0
- data/modules/mruby/examples/targets/ArduinoDue.rb +65 -0
- data/modules/mruby/examples/targets/chipKitMax32.rb +68 -0
- data/modules/mruby/include/mrbconf.h +87 -0
- data/modules/mruby/include/mruby/array.h +63 -0
- data/modules/mruby/include/mruby/class.h +75 -0
- data/modules/mruby/include/mruby/compile.h +176 -0
- data/modules/mruby/include/mruby/data.h +53 -0
- data/modules/mruby/include/mruby/dump.h +151 -0
- data/modules/mruby/include/mruby/gc.h +17 -0
- data/modules/mruby/include/mruby/hash.h +54 -0
- data/modules/mruby/include/mruby/irep.h +40 -0
- data/modules/mruby/include/mruby/khash.h +257 -0
- data/modules/mruby/include/mruby/numeric.h +32 -0
- data/modules/mruby/include/mruby/proc.h +62 -0
- data/modules/mruby/include/mruby/range.h +35 -0
- data/modules/mruby/include/mruby/string.h +78 -0
- data/modules/mruby/include/mruby/value.h +483 -0
- data/modules/mruby/include/mruby/variable.h +78 -0
- data/modules/mruby/include/mruby.h +388 -0
- data/modules/mruby/minirake +477 -0
- data/modules/mruby/mrbgems/default.gembox +61 -0
- data/modules/mruby/mrbgems/full-core.gembox +9 -0
- data/modules/mruby/mrbgems/mruby-array-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-array-ext/mrblib/array.rb +204 -0
- data/modules/mruby/mrbgems/mruby-array-ext/src/array.c +140 -0
- data/modules/mruby/mrbgems/mruby-array-ext/test/array.rb +109 -0
- data/modules/mruby/mrbgems/mruby-bin-mirb/mrbgem.rake +5 -0
- data/modules/mruby/mrbgems/mruby-bin-mirb/tools/mirb/mirb.c +365 -0
- data/modules/mruby/mrbgems/mruby-bin-mruby/mrbgem.rake +5 -0
- data/modules/mruby/mrbgems/mruby-bin-mruby/tools/mruby/mruby.c +243 -0
- data/modules/mruby/mrbgems/mruby-enum-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-enum-ext/mrblib/enum.rb +164 -0
- data/modules/mruby/mrbgems/mruby-enum-ext/test/enum.rb +44 -0
- data/modules/mruby/mrbgems/mruby-eval/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-eval/src/eval.c +23 -0
- data/modules/mruby/mrbgems/mruby-fiber/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-fiber/src/fiber.c +251 -0
- data/modules/mruby/mrbgems/mruby-fiber/test/fiber.rb +64 -0
- data/modules/mruby/mrbgems/mruby-hash-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-hash-ext/mrblib/hash.rb +13 -0
- data/modules/mruby/mrbgems/mruby-hash-ext/src/hash-ext.c +62 -0
- data/modules/mruby/mrbgems/mruby-hash-ext/test/hash.rb +26 -0
- data/modules/mruby/mrbgems/mruby-math/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-math/src/math.c +685 -0
- data/modules/mruby/mrbgems/mruby-math/test/math.rb +136 -0
- data/modules/mruby/mrbgems/mruby-numeric-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-numeric-ext/src/numeric_ext.c +31 -0
- data/modules/mruby/mrbgems/mruby-numeric-ext/test/numeric.rb +10 -0
- data/modules/mruby/mrbgems/mruby-object-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-object-ext/src/object.c +108 -0
- data/modules/mruby/mrbgems/mruby-object-ext/test/nil.rb +11 -0
- data/modules/mruby/mrbgems/mruby-object-ext/test/object.rb +9 -0
- data/modules/mruby/mrbgems/mruby-objectspace/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-objectspace/src/mruby_objectspace.c +117 -0
- data/modules/mruby/mrbgems/mruby-objectspace/test/objectspace.rb +38 -0
- data/modules/mruby/mrbgems/mruby-print/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-print/mrblib/print.rb +64 -0
- data/modules/mruby/mrbgems/mruby-print/src/print.c +44 -0
- data/modules/mruby/mrbgems/mruby-proc-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-proc-ext/mrblib/proc.rb +40 -0
- data/modules/mruby/mrbgems/mruby-proc-ext/src/proc.c +97 -0
- data/modules/mruby/mrbgems/mruby-proc-ext/test/proc.rb +41 -0
- data/modules/mruby/mrbgems/mruby-random/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-random/src/mt19937ar.c +193 -0
- data/modules/mruby/mrbgems/mruby-random/src/mt19937ar.h +48 -0
- data/modules/mruby/mrbgems/mruby-random/src/random.c +231 -0
- data/modules/mruby/mrbgems/mruby-random/src/random.h +12 -0
- data/modules/mruby/mrbgems/mruby-random/test/random.rb +32 -0
- data/modules/mruby/mrbgems/mruby-range-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-range-ext/src/range.c +141 -0
- data/modules/mruby/mrbgems/mruby-range-ext/test/range.rb +20 -0
- data/modules/mruby/mrbgems/mruby-sprintf/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-sprintf/src/kernel.c +30 -0
- data/modules/mruby/mrbgems/mruby-sprintf/src/sprintf.c +1102 -0
- data/modules/mruby/mrbgems/mruby-sprintf/test/sprintf.rb +3 -0
- data/modules/mruby/mrbgems/mruby-string-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-string-ext/mrblib/string.rb +52 -0
- data/modules/mruby/mrbgems/mruby-string-ext/src/string.c +175 -0
- data/modules/mruby/mrbgems/mruby-string-ext/test/string.rb +112 -0
- data/modules/mruby/mrbgems/mruby-struct/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-struct/mrblib/struct.rb +50 -0
- data/modules/mruby/mrbgems/mruby-struct/src/struct.c +818 -0
- data/modules/mruby/mrbgems/mruby-struct/test/struct.rb +77 -0
- data/modules/mruby/mrbgems/mruby-symbol-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-symbol-ext/mrblib/symbol.rb +9 -0
- data/modules/mruby/mrbgems/mruby-symbol-ext/src/symbol.c +55 -0
- data/modules/mruby/mrbgems/mruby-symbol-ext/test/symbol.rb +12 -0
- data/modules/mruby/mrbgems/mruby-time/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-time/src/time.c +749 -0
- data/modules/mruby/mrbgems/mruby-time/test/time.rb +201 -0
- data/modules/mruby/mrbgems/mruby-toplevel-ext/mrbgem.rake +4 -0
- data/modules/mruby/mrbgems/mruby-toplevel-ext/mrblib/toplevel.rb +11 -0
- data/modules/mruby/mrbgems/mruby-toplevel-ext/test/toplevel.rb +24 -0
- data/modules/mruby/mrblib/array.rb +111 -0
- data/modules/mruby/mrblib/class.rb +26 -0
- data/modules/mruby/mrblib/compar.rb +104 -0
- data/modules/mruby/mrblib/enum.rb +398 -0
- data/modules/mruby/mrblib/error.rb +66 -0
- data/modules/mruby/mrblib/hash.rb +193 -0
- data/modules/mruby/mrblib/init_mrblib.c +14 -0
- data/modules/mruby/mrblib/kernel.rb +46 -0
- data/modules/mruby/mrblib/mrblib.rake +18 -0
- data/modules/mruby/mrblib/numeric.rb +101 -0
- data/modules/mruby/mrblib/print.rb +18 -0
- data/modules/mruby/mrblib/range.rb +40 -0
- data/modules/mruby/mrblib/string.rb +145 -0
- data/modules/mruby/src/array.c +1150 -0
- data/modules/mruby/src/backtrace.c +73 -0
- data/modules/mruby/src/class.c +1942 -0
- data/modules/mruby/src/codegen.c +2864 -0
- data/modules/mruby/src/compar.c +13 -0
- data/modules/mruby/src/crc.c +38 -0
- data/modules/mruby/src/dump.c +542 -0
- data/modules/mruby/src/enum.c +14 -0
- data/modules/mruby/src/error.c +454 -0
- data/modules/mruby/src/error.h +18 -0
- data/modules/mruby/src/etc.c +204 -0
- data/modules/mruby/src/gc.c +1542 -0
- data/modules/mruby/src/hash.c +1261 -0
- data/modules/mruby/src/init.c +62 -0
- data/modules/mruby/src/kernel.c +1105 -0
- data/modules/mruby/src/keywords +50 -0
- data/modules/mruby/src/lex.def +212 -0
- data/modules/mruby/src/load.c +629 -0
- data/modules/mruby/src/mruby_core.rake +28 -0
- data/modules/mruby/src/node.h +117 -0
- data/modules/mruby/src/numeric.c +1418 -0
- data/modules/mruby/src/object.c +593 -0
- data/modules/mruby/src/opcode.h +160 -0
- data/modules/mruby/src/parse.y +6050 -0
- data/modules/mruby/src/pool.c +190 -0
- data/modules/mruby/src/print.c +71 -0
- data/modules/mruby/src/proc.c +209 -0
- data/modules/mruby/src/range.c +442 -0
- data/modules/mruby/src/re.h +13 -0
- data/modules/mruby/src/state.c +200 -0
- data/modules/mruby/src/string.c +2580 -0
- data/modules/mruby/src/symbol.c +456 -0
- data/modules/mruby/src/value_array.h +27 -0
- data/modules/mruby/src/variable.c +1147 -0
- data/modules/mruby/src/vm.c +2129 -0
- data/modules/mruby/tasks/libmruby.rake +18 -0
- data/modules/mruby/tasks/mrbgem_spec.rake +297 -0
- data/modules/mruby/tasks/mrbgems.rake +85 -0
- data/modules/mruby/tasks/mrbgems_test.rake +88 -0
- data/modules/mruby/tasks/mruby_build.rake +211 -0
- data/modules/mruby/tasks/mruby_build_commands.rake +287 -0
- data/modules/mruby/tasks/mruby_build_gem.rake +67 -0
- data/modules/mruby/tasks/ruby_ext.rake +70 -0
- data/modules/mruby/tasks/toolchains/androideabi.rake +126 -0
- data/modules/mruby/tasks/toolchains/clang.rake +8 -0
- data/modules/mruby/tasks/toolchains/gcc.rake +21 -0
- data/modules/mruby/tasks/toolchains/vs2010.rake +3 -0
- data/modules/mruby/tasks/toolchains/vs2012.rake +44 -0
- data/modules/mruby/test/README.md +7 -0
- data/modules/mruby/test/assert.rb +238 -0
- data/modules/mruby/test/driver.c +118 -0
- data/modules/mruby/test/init_mrbtest.c +24 -0
- data/modules/mruby/test/mrbtest.rake +47 -0
- data/modules/mruby/test/report.rb +4 -0
- data/modules/mruby/test/t/argumenterror.rb +21 -0
- data/modules/mruby/test/t/array.rb +309 -0
- data/modules/mruby/test/t/basicobject.rb +11 -0
- data/modules/mruby/test/t/bs_block.rb +489 -0
- data/modules/mruby/test/t/bs_literal.rb +38 -0
- data/modules/mruby/test/t/class.rb +219 -0
- data/modules/mruby/test/t/comparable.rb +72 -0
- data/modules/mruby/test/t/enumerable.rb +108 -0
- data/modules/mruby/test/t/exception.rb +337 -0
- data/modules/mruby/test/t/false.rb +33 -0
- data/modules/mruby/test/t/float.rb +145 -0
- data/modules/mruby/test/t/gc.rb +45 -0
- data/modules/mruby/test/t/hash.rb +310 -0
- data/modules/mruby/test/t/indexerror.rb +10 -0
- data/modules/mruby/test/t/integer.rb +222 -0
- data/modules/mruby/test/t/kernel.rb +425 -0
- data/modules/mruby/test/t/literals.rb +287 -0
- data/modules/mruby/test/t/localjumperror.rb +13 -0
- data/modules/mruby/test/t/methods.rb +109 -0
- data/modules/mruby/test/t/module.rb +344 -0
- data/modules/mruby/test/t/nameerror.rb +32 -0
- data/modules/mruby/test/t/nil.rb +29 -0
- data/modules/mruby/test/t/nomethoderror.rb +13 -0
- data/modules/mruby/test/t/numeric.rb +29 -0
- data/modules/mruby/test/t/object.rb +11 -0
- data/modules/mruby/test/t/proc.rb +56 -0
- data/modules/mruby/test/t/range.rb +82 -0
- data/modules/mruby/test/t/rangeerror.rb +10 -0
- data/modules/mruby/test/t/regexperror.rb +4 -0
- data/modules/mruby/test/t/runtimeerror.rb +6 -0
- data/modules/mruby/test/t/standarderror.rb +10 -0
- data/modules/mruby/test/t/string.rb +483 -0
- data/modules/mruby/test/t/symbol.rb +27 -0
- data/modules/mruby/test/t/syntax.rb +67 -0
- data/modules/mruby/test/t/true.rb +33 -0
- data/modules/mruby/test/t/typeerror.rb +11 -0
- data/modules/mruby/tools/mrbc/mrbc.c +318 -0
- data/modules/mruby/tools/mrbc/mrbc.rake +14 -0
- data/modules/mruby/travis_config.rb +6 -0
- data/modules/mrubymix/LICENSE +21 -0
- data/modules/mrubymix/README.md +6 -0
- data/modules/mrubymix/bin/mrubymix +29 -0
- data/modules/mrubymix/lib/mrubymix.rb +93 -0
- data/modules/mrubymix/mrubymix.gemspec +13 -0
- data/scripts/gen_gems_config.rb +185 -0
- data/scripts/gen_post.rb +104 -0
- data/templates/minimal/Rakefile +36 -0
- data/templates/minimal/app/app.rb +3 -0
- metadata +1408 -0
@@ -0,0 +1,3262 @@
|
|
1
|
+
<html>
|
2
|
+
<head>
|
3
|
+
<title>PLY (Python Lex-Yacc)</title>
|
4
|
+
</head>
|
5
|
+
<body bgcolor="#ffffff">
|
6
|
+
|
7
|
+
<h1>PLY (Python Lex-Yacc)</h1>
|
8
|
+
|
9
|
+
<b>
|
10
|
+
David M. Beazley <br>
|
11
|
+
dave@dabeaz.com<br>
|
12
|
+
</b>
|
13
|
+
|
14
|
+
<p>
|
15
|
+
<b>PLY Version: 3.4</b>
|
16
|
+
<p>
|
17
|
+
|
18
|
+
<!-- INDEX -->
|
19
|
+
<div class="sectiontoc">
|
20
|
+
<ul>
|
21
|
+
<li><a href="#ply_nn1">Preface and Requirements</a>
|
22
|
+
<li><a href="#ply_nn1">Introduction</a>
|
23
|
+
<li><a href="#ply_nn2">PLY Overview</a>
|
24
|
+
<li><a href="#ply_nn3">Lex</a>
|
25
|
+
<ul>
|
26
|
+
<li><a href="#ply_nn4">Lex Example</a>
|
27
|
+
<li><a href="#ply_nn5">The tokens list</a>
|
28
|
+
<li><a href="#ply_nn6">Specification of tokens</a>
|
29
|
+
<li><a href="#ply_nn7">Token values</a>
|
30
|
+
<li><a href="#ply_nn8">Discarded tokens</a>
|
31
|
+
<li><a href="#ply_nn9">Line numbers and positional information</a>
|
32
|
+
<li><a href="#ply_nn10">Ignored characters</a>
|
33
|
+
<li><a href="#ply_nn11">Literal characters</a>
|
34
|
+
<li><a href="#ply_nn12">Error handling</a>
|
35
|
+
<li><a href="#ply_nn13">Building and using the lexer</a>
|
36
|
+
<li><a href="#ply_nn14">The @TOKEN decorator</a>
|
37
|
+
<li><a href="#ply_nn15">Optimized mode</a>
|
38
|
+
<li><a href="#ply_nn16">Debugging</a>
|
39
|
+
<li><a href="#ply_nn17">Alternative specification of lexers</a>
|
40
|
+
<li><a href="#ply_nn18">Maintaining state</a>
|
41
|
+
<li><a href="#ply_nn19">Lexer cloning</a>
|
42
|
+
<li><a href="#ply_nn20">Internal lexer state</a>
|
43
|
+
<li><a href="#ply_nn21">Conditional lexing and start conditions</a>
|
44
|
+
<li><a href="#ply_nn21">Miscellaneous Issues</a>
|
45
|
+
</ul>
|
46
|
+
<li><a href="#ply_nn22">Parsing basics</a>
|
47
|
+
<li><a href="#ply_nn23">Yacc</a>
|
48
|
+
<ul>
|
49
|
+
<li><a href="#ply_nn24">An example</a>
|
50
|
+
<li><a href="#ply_nn25">Combining Grammar Rule Functions</a>
|
51
|
+
<li><a href="#ply_nn26">Character Literals</a>
|
52
|
+
<li><a href="#ply_nn26">Empty Productions</a>
|
53
|
+
<li><a href="#ply_nn28">Changing the starting symbol</a>
|
54
|
+
<li><a href="#ply_nn27">Dealing With Ambiguous Grammars</a>
|
55
|
+
<li><a href="#ply_nn28">The parser.out file</a>
|
56
|
+
<li><a href="#ply_nn29">Syntax Error Handling</a>
|
57
|
+
<ul>
|
58
|
+
<li><a href="#ply_nn30">Recovery and resynchronization with error rules</a>
|
59
|
+
<li><a href="#ply_nn31">Panic mode recovery</a>
|
60
|
+
<li><a href="#ply_nn35">Signaling an error from a production</a>
|
61
|
+
<li><a href="#ply_nn32">General comments on error handling</a>
|
62
|
+
</ul>
|
63
|
+
<li><a href="#ply_nn33">Line Number and Position Tracking</a>
|
64
|
+
<li><a href="#ply_nn34">AST Construction</a>
|
65
|
+
<li><a href="#ply_nn35">Embedded Actions</a>
|
66
|
+
<li><a href="#ply_nn36">Miscellaneous Yacc Notes</a>
|
67
|
+
</ul>
|
68
|
+
<li><a href="#ply_nn37">Multiple Parsers and Lexers</a>
|
69
|
+
<li><a href="#ply_nn38">Using Python's Optimized Mode</a>
|
70
|
+
<li><a href="#ply_nn44">Advanced Debugging</a>
|
71
|
+
<ul>
|
72
|
+
<li><a href="#ply_nn45">Debugging the lex() and yacc() commands</a>
|
73
|
+
<li><a href="#ply_nn46">Run-time Debugging</a>
|
74
|
+
</ul>
|
75
|
+
<li><a href="#ply_nn39">Where to go from here?</a>
|
76
|
+
</ul>
|
77
|
+
</div>
|
78
|
+
<!-- INDEX -->
|
79
|
+
|
80
|
+
|
81
|
+
|
82
|
+
<H2><a name="ply_nn1"></a>1. Preface and Requirements</H2>
|
83
|
+
|
84
|
+
|
85
|
+
<p>
|
86
|
+
This document provides an overview of lexing and parsing with PLY.
|
87
|
+
Given the intrinsic complexity of parsing, I would strongly advise
|
88
|
+
that you read (or at least skim) this entire document before jumping
|
89
|
+
into a big development project with PLY.
|
90
|
+
</p>
|
91
|
+
|
92
|
+
<p>
|
93
|
+
PLY-3.0 is compatible with both Python 2 and Python 3. Be aware that
|
94
|
+
Python 3 support is new and has not been extensively tested (although
|
95
|
+
all of the examples and unit tests pass under Python 3.0). If you are
|
96
|
+
using Python 2, you should try to use Python 2.4 or newer. Although PLY
|
97
|
+
works with versions as far back as Python 2.2, some of its optional features
|
98
|
+
require more modern library modules.
|
99
|
+
</p>
|
100
|
+
|
101
|
+
<H2><a name="ply_nn1"></a>2. Introduction</H2>
|
102
|
+
|
103
|
+
|
104
|
+
PLY is a pure-Python implementation of the popular compiler
|
105
|
+
construction tools lex and yacc. The main goal of PLY is to stay
|
106
|
+
fairly faithful to the way in which traditional lex/yacc tools work.
|
107
|
+
This includes supporting LALR(1) parsing as well as providing
|
108
|
+
extensive input validation, error reporting, and diagnostics. Thus,
|
109
|
+
if you've used yacc in another programming language, it should be
|
110
|
+
relatively straightforward to use PLY.
|
111
|
+
|
112
|
+
<p>
|
113
|
+
Early versions of PLY were developed to support an Introduction to
|
114
|
+
Compilers Course I taught in 2001 at the University of Chicago. In this course,
|
115
|
+
students built a fully functional compiler for a simple Pascal-like
|
116
|
+
language. Their compiler, implemented entirely in Python, had to
|
117
|
+
include lexical analysis, parsing, type checking, type inference,
|
118
|
+
nested scoping, and code generation for the SPARC processor.
|
119
|
+
Approximately 30 different compiler implementations were completed in
|
120
|
+
this course. Most of PLY's interface and operation has been influenced by common
|
121
|
+
usability problems encountered by students. Since 2001, PLY has
|
122
|
+
continued to be improved as feedback has been received from users.
|
123
|
+
PLY-3.0 represents a major refactoring of the original implementation
|
124
|
+
with an eye towards future enhancements.
|
125
|
+
|
126
|
+
<p>
|
127
|
+
Since PLY was primarily developed as an instructional tool, you will
|
128
|
+
find it to be fairly picky about token and grammar rule
|
129
|
+
specification. In part, this
|
130
|
+
added formality is meant to catch common programming mistakes made by
|
131
|
+
novice users. However, advanced users will also find such features to
|
132
|
+
be useful when building complicated grammars for real programming
|
133
|
+
languages. It should also be noted that PLY does not provide much in
|
134
|
+
the way of bells and whistles (e.g., automatic construction of
|
135
|
+
abstract syntax trees, tree traversal, etc.). Nor would I consider it
|
136
|
+
to be a parsing framework. Instead, you will find a bare-bones, yet
|
137
|
+
fully capable lex/yacc implementation written entirely in Python.
|
138
|
+
|
139
|
+
<p>
|
140
|
+
The rest of this document assumes that you are somewhat familar with
|
141
|
+
parsing theory, syntax directed translation, and the use of compiler
|
142
|
+
construction tools such as lex and yacc in other programming
|
143
|
+
languages. If you are unfamilar with these topics, you will probably
|
144
|
+
want to consult an introductory text such as "Compilers: Principles,
|
145
|
+
Techniques, and Tools", by Aho, Sethi, and Ullman. O'Reilly's "Lex
|
146
|
+
and Yacc" by John Levine may also be handy. In fact, the O'Reilly book can be
|
147
|
+
used as a reference for PLY as the concepts are virtually identical.
|
148
|
+
|
149
|
+
<H2><a name="ply_nn2"></a>3. PLY Overview</H2>
|
150
|
+
|
151
|
+
|
152
|
+
PLY consists of two separate modules; <tt>lex.py</tt> and
|
153
|
+
<tt>yacc.py</tt>, both of which are found in a Python package
|
154
|
+
called <tt>ply</tt>. The <tt>lex.py</tt> module is used to break input text into a
|
155
|
+
collection of tokens specified by a collection of regular expression
|
156
|
+
rules. <tt>yacc.py</tt> is used to recognize language syntax that has
|
157
|
+
been specified in the form of a context free grammar. <tt>yacc.py</tt> uses LR parsing and generates its parsing tables
|
158
|
+
using either the LALR(1) (the default) or SLR table generation algorithms.
|
159
|
+
|
160
|
+
<p>
|
161
|
+
The two tools are meant to work together. Specifically,
|
162
|
+
<tt>lex.py</tt> provides an external interface in the form of a
|
163
|
+
<tt>token()</tt> function that returns the next valid token on the
|
164
|
+
input stream. <tt>yacc.py</tt> calls this repeatedly to retrieve
|
165
|
+
tokens and invoke grammar rules. The output of <tt>yacc.py</tt> is
|
166
|
+
often an Abstract Syntax Tree (AST). However, this is entirely up to
|
167
|
+
the user. If desired, <tt>yacc.py</tt> can also be used to implement
|
168
|
+
simple one-pass compilers.
|
169
|
+
|
170
|
+
<p>
|
171
|
+
Like its Unix counterpart, <tt>yacc.py</tt> provides most of the
|
172
|
+
features you expect including extensive error checking, grammar
|
173
|
+
validation, support for empty productions, error tokens, and ambiguity
|
174
|
+
resolution via precedence rules. In fact, everything that is possible in traditional yacc
|
175
|
+
should be supported in PLY.
|
176
|
+
|
177
|
+
<p>
|
178
|
+
The primary difference between
|
179
|
+
<tt>yacc.py</tt> and Unix <tt>yacc</tt> is that <tt>yacc.py</tt>
|
180
|
+
doesn't involve a separate code-generation process.
|
181
|
+
Instead, PLY relies on reflection (introspection)
|
182
|
+
to build its lexers and parsers. Unlike traditional lex/yacc which
|
183
|
+
require a special input file that is converted into a separate source
|
184
|
+
file, the specifications given to PLY <em>are</em> valid Python
|
185
|
+
programs. This means that there are no extra source files nor is
|
186
|
+
there a special compiler construction step (e.g., running yacc to
|
187
|
+
generate Python code for the compiler). Since the generation of the
|
188
|
+
parsing tables is relatively expensive, PLY caches the results and
|
189
|
+
saves them to a file. If no changes are detected in the input source,
|
190
|
+
the tables are read from the cache. Otherwise, they are regenerated.
|
191
|
+
|
192
|
+
<H2><a name="ply_nn3"></a>4. Lex</H2>
|
193
|
+
|
194
|
+
|
195
|
+
<tt>lex.py</tt> is used to tokenize an input string. For example, suppose
|
196
|
+
you're writing a programming language and a user supplied the following input string:
|
197
|
+
|
198
|
+
<blockquote>
|
199
|
+
<pre>
|
200
|
+
x = 3 + 42 * (s - t)
|
201
|
+
</pre>
|
202
|
+
</blockquote>
|
203
|
+
|
204
|
+
A tokenizer splits the string into individual tokens
|
205
|
+
|
206
|
+
<blockquote>
|
207
|
+
<pre>
|
208
|
+
'x','=', '3', '+', '42', '*', '(', 's', '-', 't', ')'
|
209
|
+
</pre>
|
210
|
+
</blockquote>
|
211
|
+
|
212
|
+
Tokens are usually given names to indicate what they are. For example:
|
213
|
+
|
214
|
+
<blockquote>
|
215
|
+
<pre>
|
216
|
+
'ID','EQUALS','NUMBER','PLUS','NUMBER','TIMES',
|
217
|
+
'LPAREN','ID','MINUS','ID','RPAREN'
|
218
|
+
</pre>
|
219
|
+
</blockquote>
|
220
|
+
|
221
|
+
More specifically, the input is broken into pairs of token types and values. For example:
|
222
|
+
|
223
|
+
<blockquote>
|
224
|
+
<pre>
|
225
|
+
('ID','x'), ('EQUALS','='), ('NUMBER','3'),
|
226
|
+
('PLUS','+'), ('NUMBER','42), ('TIMES','*'),
|
227
|
+
('LPAREN','('), ('ID','s'), ('MINUS','-'),
|
228
|
+
('ID','t'), ('RPAREN',')'
|
229
|
+
</pre>
|
230
|
+
</blockquote>
|
231
|
+
|
232
|
+
The identification of tokens is typically done by writing a series of regular expression
|
233
|
+
rules. The next section shows how this is done using <tt>lex.py</tt>.
|
234
|
+
|
235
|
+
<H3><a name="ply_nn4"></a>4.1 Lex Example</H3>
|
236
|
+
|
237
|
+
|
238
|
+
The following example shows how <tt>lex.py</tt> is used to write a simple tokenizer.
|
239
|
+
|
240
|
+
<blockquote>
|
241
|
+
<pre>
|
242
|
+
# ------------------------------------------------------------
|
243
|
+
# calclex.py
|
244
|
+
#
|
245
|
+
# tokenizer for a simple expression evaluator for
|
246
|
+
# numbers and +,-,*,/
|
247
|
+
# ------------------------------------------------------------
|
248
|
+
import ply.lex as lex
|
249
|
+
|
250
|
+
# List of token names. This is always required
|
251
|
+
tokens = (
|
252
|
+
'NUMBER',
|
253
|
+
'PLUS',
|
254
|
+
'MINUS',
|
255
|
+
'TIMES',
|
256
|
+
'DIVIDE',
|
257
|
+
'LPAREN',
|
258
|
+
'RPAREN',
|
259
|
+
)
|
260
|
+
|
261
|
+
# Regular expression rules for simple tokens
|
262
|
+
t_PLUS = r'\+'
|
263
|
+
t_MINUS = r'-'
|
264
|
+
t_TIMES = r'\*'
|
265
|
+
t_DIVIDE = r'/'
|
266
|
+
t_LPAREN = r'\('
|
267
|
+
t_RPAREN = r'\)'
|
268
|
+
|
269
|
+
# A regular expression rule with some action code
|
270
|
+
def t_NUMBER(t):
|
271
|
+
r'\d+'
|
272
|
+
t.value = int(t.value)
|
273
|
+
return t
|
274
|
+
|
275
|
+
# Define a rule so we can track line numbers
|
276
|
+
def t_newline(t):
|
277
|
+
r'\n+'
|
278
|
+
t.lexer.lineno += len(t.value)
|
279
|
+
|
280
|
+
# A string containing ignored characters (spaces and tabs)
|
281
|
+
t_ignore = ' \t'
|
282
|
+
|
283
|
+
# Error handling rule
|
284
|
+
def t_error(t):
|
285
|
+
print "Illegal character '%s'" % t.value[0]
|
286
|
+
t.lexer.skip(1)
|
287
|
+
|
288
|
+
# Build the lexer
|
289
|
+
lexer = lex.lex()
|
290
|
+
|
291
|
+
</pre>
|
292
|
+
</blockquote>
|
293
|
+
To use the lexer, you first need to feed it some input text using
|
294
|
+
its <tt>input()</tt> method. After that, repeated calls
|
295
|
+
to <tt>token()</tt> produce tokens. The following code shows how this
|
296
|
+
works:
|
297
|
+
|
298
|
+
<blockquote>
|
299
|
+
<pre>
|
300
|
+
|
301
|
+
# Test it out
|
302
|
+
data = '''
|
303
|
+
3 + 4 * 10
|
304
|
+
+ -20 *2
|
305
|
+
'''
|
306
|
+
|
307
|
+
# Give the lexer some input
|
308
|
+
lexer.input(data)
|
309
|
+
|
310
|
+
# Tokenize
|
311
|
+
while True:
|
312
|
+
tok = lexer.token()
|
313
|
+
if not tok: break # No more input
|
314
|
+
print tok
|
315
|
+
</pre>
|
316
|
+
</blockquote>
|
317
|
+
|
318
|
+
When executed, the example will produce the following output:
|
319
|
+
|
320
|
+
<blockquote>
|
321
|
+
<pre>
|
322
|
+
$ python example.py
|
323
|
+
LexToken(NUMBER,3,2,1)
|
324
|
+
LexToken(PLUS,'+',2,3)
|
325
|
+
LexToken(NUMBER,4,2,5)
|
326
|
+
LexToken(TIMES,'*',2,7)
|
327
|
+
LexToken(NUMBER,10,2,10)
|
328
|
+
LexToken(PLUS,'+',3,14)
|
329
|
+
LexToken(MINUS,'-',3,16)
|
330
|
+
LexToken(NUMBER,20,3,18)
|
331
|
+
LexToken(TIMES,'*',3,20)
|
332
|
+
LexToken(NUMBER,2,3,21)
|
333
|
+
</pre>
|
334
|
+
</blockquote>
|
335
|
+
|
336
|
+
Lexers also support the iteration protocol. So, you can write the above loop as follows:
|
337
|
+
|
338
|
+
<blockquote>
|
339
|
+
<pre>
|
340
|
+
for tok in lexer:
|
341
|
+
print tok
|
342
|
+
</pre>
|
343
|
+
</blockquote>
|
344
|
+
|
345
|
+
The tokens returned by <tt>lexer.token()</tt> are instances
|
346
|
+
of <tt>LexToken</tt>. This object has
|
347
|
+
attributes <tt>tok.type</tt>, <tt>tok.value</tt>,
|
348
|
+
<tt>tok.lineno</tt>, and <tt>tok.lexpos</tt>. The following code shows an example of
|
349
|
+
accessing these attributes:
|
350
|
+
|
351
|
+
<blockquote>
|
352
|
+
<pre>
|
353
|
+
# Tokenize
|
354
|
+
while True:
|
355
|
+
tok = lexer.token()
|
356
|
+
if not tok: break # No more input
|
357
|
+
print tok.type, tok.value, tok.line, tok.lexpos
|
358
|
+
</pre>
|
359
|
+
</blockquote>
|
360
|
+
|
361
|
+
The <tt>tok.type</tt> and <tt>tok.value</tt> attributes contain the
|
362
|
+
type and value of the token itself.
|
363
|
+
<tt>tok.line</tt> and <tt>tok.lexpos</tt> contain information about
|
364
|
+
the location of the token. <tt>tok.lexpos</tt> is the index of the
|
365
|
+
token relative to the start of the input text.
|
366
|
+
|
367
|
+
<H3><a name="ply_nn5"></a>4.2 The tokens list</H3>
|
368
|
+
|
369
|
+
|
370
|
+
All lexers must provide a list <tt>tokens</tt> that defines all of the possible token
|
371
|
+
names that can be produced by the lexer. This list is always required
|
372
|
+
and is used to perform a variety of validation checks. The tokens list is also used by the
|
373
|
+
<tt>yacc.py</tt> module to identify terminals.
|
374
|
+
|
375
|
+
<p>
|
376
|
+
In the example, the following code specified the token names:
|
377
|
+
|
378
|
+
<blockquote>
|
379
|
+
<pre>
|
380
|
+
tokens = (
|
381
|
+
'NUMBER',
|
382
|
+
'PLUS',
|
383
|
+
'MINUS',
|
384
|
+
'TIMES',
|
385
|
+
'DIVIDE',
|
386
|
+
'LPAREN',
|
387
|
+
'RPAREN',
|
388
|
+
)
|
389
|
+
</pre>
|
390
|
+
</blockquote>
|
391
|
+
|
392
|
+
<H3><a name="ply_nn6"></a>4.3 Specification of tokens</H3>
|
393
|
+
|
394
|
+
|
395
|
+
Each token is specified by writing a regular expression rule. Each of these rules are
|
396
|
+
are defined by making declarations with a special prefix <tt>t_</tt> to indicate that it
|
397
|
+
defines a token. For simple tokens, the regular expression can
|
398
|
+
be specified as strings such as this (note: Python raw strings are used since they are the
|
399
|
+
most convenient way to write regular expression strings):
|
400
|
+
|
401
|
+
<blockquote>
|
402
|
+
<pre>
|
403
|
+
t_PLUS = r'\+'
|
404
|
+
</pre>
|
405
|
+
</blockquote>
|
406
|
+
|
407
|
+
In this case, the name following the <tt>t_</tt> must exactly match one of the
|
408
|
+
names supplied in <tt>tokens</tt>. If some kind of action needs to be performed,
|
409
|
+
a token rule can be specified as a function. For example, this rule matches numbers and
|
410
|
+
converts the string into a Python integer.
|
411
|
+
|
412
|
+
<blockquote>
|
413
|
+
<pre>
|
414
|
+
def t_NUMBER(t):
|
415
|
+
r'\d+'
|
416
|
+
t.value = int(t.value)
|
417
|
+
return t
|
418
|
+
</pre>
|
419
|
+
</blockquote>
|
420
|
+
|
421
|
+
When a function is used, the regular expression rule is specified in the function documentation string.
|
422
|
+
The function always takes a single argument which is an instance of
|
423
|
+
<tt>LexToken</tt>. This object has attributes of <tt>t.type</tt> which is the token type (as a string),
|
424
|
+
<tt>t.value</tt> which is the lexeme (the actual text matched), <tt>t.lineno</tt> which is the current line number, and <tt>t.lexpos</tt> which
|
425
|
+
is the position of the token relative to the beginning of the input text.
|
426
|
+
By default, <tt>t.type</tt> is set to the name following the <tt>t_</tt> prefix. The action
|
427
|
+
function can modify the contents of the <tt>LexToken</tt> object as appropriate. However,
|
428
|
+
when it is done, the resulting token should be returned. If no value is returned by the action
|
429
|
+
function, the token is simply discarded and the next token read.
|
430
|
+
|
431
|
+
<p>
|
432
|
+
Internally, <tt>lex.py</tt> uses the <tt>re</tt> module to do its patten matching. When building the master regular expression,
|
433
|
+
rules are added in the following order:
|
434
|
+
<p>
|
435
|
+
<ol>
|
436
|
+
<li>All tokens defined by functions are added in the same order as they appear in the lexer file.
|
437
|
+
<li>Tokens defined by strings are added next by sorting them in order of decreasing regular expression length (longer expressions
|
438
|
+
are added first).
|
439
|
+
</ol>
|
440
|
+
<p>
|
441
|
+
Without this ordering, it can be difficult to correctly match certain types of tokens. For example, if you
|
442
|
+
wanted to have separate tokens for "=" and "==", you need to make sure that "==" is checked first. By sorting regular
|
443
|
+
expressions in order of decreasing length, this problem is solved for rules defined as strings. For functions,
|
444
|
+
the order can be explicitly controlled since rules appearing first are checked first.
|
445
|
+
|
446
|
+
<p>
|
447
|
+
To handle reserved words, you should write a single rule to match an
|
448
|
+
identifier and do a special name lookup in a function like this:
|
449
|
+
|
450
|
+
<blockquote>
|
451
|
+
<pre>
|
452
|
+
reserved = {
|
453
|
+
'if' : 'IF',
|
454
|
+
'then' : 'THEN',
|
455
|
+
'else' : 'ELSE',
|
456
|
+
'while' : 'WHILE',
|
457
|
+
...
|
458
|
+
}
|
459
|
+
|
460
|
+
tokens = ['LPAREN','RPAREN',...,'ID'] + list(reserved.values())
|
461
|
+
|
462
|
+
def t_ID(t):
|
463
|
+
r'[a-zA-Z_][a-zA-Z_0-9]*'
|
464
|
+
t.type = reserved.get(t.value,'ID') # Check for reserved words
|
465
|
+
return t
|
466
|
+
</pre>
|
467
|
+
</blockquote>
|
468
|
+
|
469
|
+
This approach greatly reduces the number of regular expression rules and is likely to make things a little faster.
|
470
|
+
|
471
|
+
<p>
|
472
|
+
<b>Note:</b> You should avoid writing individual rules for reserved words. For example, if you write rules like this,
|
473
|
+
|
474
|
+
<blockquote>
|
475
|
+
<pre>
|
476
|
+
t_FOR = r'for'
|
477
|
+
t_PRINT = r'print'
|
478
|
+
</pre>
|
479
|
+
</blockquote>
|
480
|
+
|
481
|
+
those rules will be triggered for identifiers that include those words as a prefix such as "forget" or "printed". This is probably not
|
482
|
+
what you want.
|
483
|
+
|
484
|
+
<H3><a name="ply_nn7"></a>4.4 Token values</H3>
|
485
|
+
|
486
|
+
|
487
|
+
When tokens are returned by lex, they have a value that is stored in the <tt>value</tt> attribute. Normally, the value is the text
|
488
|
+
that was matched. However, the value can be assigned to any Python object. For instance, when lexing identifiers, you may
|
489
|
+
want to return both the identifier name and information from some sort of symbol table. To do this, you might write a rule like this:
|
490
|
+
|
491
|
+
<blockquote>
|
492
|
+
<pre>
|
493
|
+
def t_ID(t):
|
494
|
+
...
|
495
|
+
# Look up symbol table information and return a tuple
|
496
|
+
t.value = (t.value, symbol_lookup(t.value))
|
497
|
+
...
|
498
|
+
return t
|
499
|
+
</pre>
|
500
|
+
</blockquote>
|
501
|
+
|
502
|
+
It is important to note that storing data in other attribute names is <em>not</em> recommended. The <tt>yacc.py</tt> module only exposes the
|
503
|
+
contents of the <tt>value</tt> attribute. Thus, accessing other attributes may be unnecessarily awkward. If you
|
504
|
+
need to store multiple values on a token, assign a tuple, dictionary, or instance to <tt>value</tt>.
|
505
|
+
|
506
|
+
<H3><a name="ply_nn8"></a>4.5 Discarded tokens</H3>
|
507
|
+
|
508
|
+
|
509
|
+
To discard a token, such as a comment, simply define a token rule that returns no value. For example:
|
510
|
+
|
511
|
+
<blockquote>
|
512
|
+
<pre>
|
513
|
+
def t_COMMENT(t):
|
514
|
+
r'\#.*'
|
515
|
+
pass
|
516
|
+
# No return value. Token discarded
|
517
|
+
</pre>
|
518
|
+
</blockquote>
|
519
|
+
|
520
|
+
Alternatively, you can include the prefix "ignore_" in the token declaration to force a token to be ignored. For example:
|
521
|
+
|
522
|
+
<blockquote>
|
523
|
+
<pre>
|
524
|
+
t_ignore_COMMENT = r'\#.*'
|
525
|
+
</pre>
|
526
|
+
</blockquote>
|
527
|
+
|
528
|
+
Be advised that if you are ignoring many different kinds of text, you may still want to use functions since these provide more precise
|
529
|
+
control over the order in which regular expressions are matched (i.e., functions are matched in order of specification whereas strings are
|
530
|
+
sorted by regular expression length).
|
531
|
+
|
532
|
+
<H3><a name="ply_nn9"></a>4.6 Line numbers and positional information</H3>
|
533
|
+
|
534
|
+
|
535
|
+
<p>By default, <tt>lex.py</tt> knows nothing about line numbers. This is because <tt>lex.py</tt> doesn't know anything
|
536
|
+
about what constitutes a "line" of input (e.g., the newline character or even if the input is textual data).
|
537
|
+
To update this information, you need to write a special rule. In the example, the <tt>t_newline()</tt> rule shows how to do this.
|
538
|
+
|
539
|
+
<blockquote>
|
540
|
+
<pre>
|
541
|
+
# Define a rule so we can track line numbers
|
542
|
+
def t_newline(t):
|
543
|
+
r'\n+'
|
544
|
+
t.lexer.lineno += len(t.value)
|
545
|
+
</pre>
|
546
|
+
</blockquote>
|
547
|
+
Within the rule, the <tt>lineno</tt> attribute of the underlying lexer <tt>t.lexer</tt> is updated.
|
548
|
+
After the line number is updated, the token is simply discarded since nothing is returned.
|
549
|
+
|
550
|
+
<p>
|
551
|
+
<tt>lex.py</tt> does not perform and kind of automatic column tracking. However, it does record positional
|
552
|
+
information related to each token in the <tt>lexpos</tt> attribute. Using this, it is usually possible to compute
|
553
|
+
column information as a separate step. For instance, just count backwards until you reach a newline.
|
554
|
+
|
555
|
+
<blockquote>
|
556
|
+
<pre>
|
557
|
+
# Compute column.
|
558
|
+
# input is the input text string
|
559
|
+
# token is a token instance
|
560
|
+
def find_column(input,token):
|
561
|
+
last_cr = input.rfind('\n',0,token.lexpos)
|
562
|
+
if last_cr < 0:
|
563
|
+
last_cr = 0
|
564
|
+
column = (token.lexpos - last_cr) + 1
|
565
|
+
return column
|
566
|
+
</pre>
|
567
|
+
</blockquote>
|
568
|
+
|
569
|
+
Since column information is often only useful in the context of error handling, calculating the column
|
570
|
+
position can be performed when needed as opposed to doing it for each token.
|
571
|
+
|
572
|
+
<H3><a name="ply_nn10"></a>4.7 Ignored characters</H3>
|
573
|
+
|
574
|
+
|
575
|
+
<p>
|
576
|
+
The special <tt>t_ignore</tt> rule is reserved by <tt>lex.py</tt> for characters
|
577
|
+
that should be completely ignored in the input stream.
|
578
|
+
Usually this is used to skip over whitespace and other non-essential characters.
|
579
|
+
Although it is possible to define a regular expression rule for whitespace in a manner
|
580
|
+
similar to <tt>t_newline()</tt>, the use of <tt>t_ignore</tt> provides substantially better
|
581
|
+
lexing performance because it is handled as a special case and is checked in a much
|
582
|
+
more efficient manner than the normal regular expression rules.
|
583
|
+
|
584
|
+
<H3><a name="ply_nn11"></a>4.8 Literal characters</H3>
|
585
|
+
|
586
|
+
|
587
|
+
<p>
|
588
|
+
Literal characters can be specified by defining a variable <tt>literals</tt> in your lexing module. For example:
|
589
|
+
|
590
|
+
<blockquote>
|
591
|
+
<pre>
|
592
|
+
literals = [ '+','-','*','/' ]
|
593
|
+
</pre>
|
594
|
+
</blockquote>
|
595
|
+
|
596
|
+
or alternatively
|
597
|
+
|
598
|
+
<blockquote>
|
599
|
+
<pre>
|
600
|
+
literals = "+-*/"
|
601
|
+
</pre>
|
602
|
+
</blockquote>
|
603
|
+
|
604
|
+
A literal character is simply a single character that is returned "as is" when encountered by the lexer. Literals are checked
|
605
|
+
after all of the defined regular expression rules. Thus, if a rule starts with one of the literal characters, it will always
|
606
|
+
take precedence.
|
607
|
+
<p>
|
608
|
+
When a literal token is returned, both its <tt>type</tt> and <tt>value</tt> attributes are set to the character itself. For example, <tt>'+'</tt>.
|
609
|
+
|
610
|
+
<H3><a name="ply_nn12"></a>4.9 Error handling</H3>
|
611
|
+
|
612
|
+
|
613
|
+
<p>
|
614
|
+
Finally, the <tt>t_error()</tt>
|
615
|
+
function is used to handle lexing errors that occur when illegal
|
616
|
+
characters are detected. In this case, the <tt>t.value</tt> attribute contains the
|
617
|
+
rest of the input string that has not been tokenized. In the example, the error function
|
618
|
+
was defined as follows:
|
619
|
+
|
620
|
+
<blockquote>
|
621
|
+
<pre>
|
622
|
+
# Error handling rule
|
623
|
+
def t_error(t):
|
624
|
+
print "Illegal character '%s'" % t.value[0]
|
625
|
+
t.lexer.skip(1)
|
626
|
+
</pre>
|
627
|
+
</blockquote>
|
628
|
+
|
629
|
+
In this case, we simply print the offending character and skip ahead one character by calling <tt>t.lexer.skip(1)</tt>.
|
630
|
+
|
631
|
+
<H3><a name="ply_nn13"></a>4.10 Building and using the lexer</H3>
|
632
|
+
|
633
|
+
|
634
|
+
<p>
|
635
|
+
To build the lexer, the function <tt>lex.lex()</tt> is used. This function
|
636
|
+
uses Python reflection (or introspection) to read the the regular expression rules
|
637
|
+
out of the calling context and build the lexer. Once the lexer has been built, two methods can
|
638
|
+
be used to control the lexer.
|
639
|
+
|
640
|
+
<ul>
|
641
|
+
<li><tt>lexer.input(data)</tt>. Reset the lexer and store a new input string.
|
642
|
+
<li><tt>lexer.token()</tt>. Return the next token. Returns a special <tt>LexToken</tt> instance on success or
|
643
|
+
None if the end of the input text has been reached.
|
644
|
+
</ul>
|
645
|
+
|
646
|
+
The preferred way to use PLY is to invoke the above methods directly on the lexer object returned by the
|
647
|
+
<tt>lex()</tt> function. The legacy interface to PLY involves module-level functions <tt>lex.input()</tt> and <tt>lex.token()</tt>.
|
648
|
+
For example:
|
649
|
+
|
650
|
+
<blockquote>
|
651
|
+
<pre>
|
652
|
+
lex.lex()
|
653
|
+
lex.input(sometext)
|
654
|
+
while 1:
|
655
|
+
tok = lex.token()
|
656
|
+
if not tok: break
|
657
|
+
print tok
|
658
|
+
</pre>
|
659
|
+
</blockquote>
|
660
|
+
|
661
|
+
<p>
|
662
|
+
In this example, the module-level functions <tt>lex.input()</tt> and <tt>lex.token()</tt> are bound to the <tt>input()</tt>
|
663
|
+
and <tt>token()</tt> methods of the last lexer created by the lex module. This interface may go away at some point so
|
664
|
+
it's probably best not to use it.
|
665
|
+
|
666
|
+
<H3><a name="ply_nn14"></a>4.11 The @TOKEN decorator</H3>
|
667
|
+
|
668
|
+
|
669
|
+
In some applications, you may want to define build tokens from as a series of
|
670
|
+
more complex regular expression rules. For example:
|
671
|
+
|
672
|
+
<blockquote>
|
673
|
+
<pre>
|
674
|
+
digit = r'([0-9])'
|
675
|
+
nondigit = r'([_A-Za-z])'
|
676
|
+
identifier = r'(' + nondigit + r'(' + digit + r'|' + nondigit + r')*)'
|
677
|
+
|
678
|
+
def t_ID(t):
|
679
|
+
# want docstring to be identifier above. ?????
|
680
|
+
...
|
681
|
+
</pre>
|
682
|
+
</blockquote>
|
683
|
+
|
684
|
+
In this case, we want the regular expression rule for <tt>ID</tt> to be one of the variables above. However, there is no
|
685
|
+
way to directly specify this using a normal documentation string. To solve this problem, you can use the <tt>@TOKEN</tt>
|
686
|
+
decorator. For example:
|
687
|
+
|
688
|
+
<blockquote>
|
689
|
+
<pre>
|
690
|
+
from ply.lex import TOKEN
|
691
|
+
|
692
|
+
@TOKEN(identifier)
|
693
|
+
def t_ID(t):
|
694
|
+
...
|
695
|
+
</pre>
|
696
|
+
</blockquote>
|
697
|
+
|
698
|
+
This will attach <tt>identifier</tt> to the docstring for <tt>t_ID()</tt> allowing <tt>lex.py</tt> to work normally. An alternative
|
699
|
+
approach this problem is to set the docstring directly like this:
|
700
|
+
|
701
|
+
<blockquote>
|
702
|
+
<pre>
|
703
|
+
def t_ID(t):
|
704
|
+
...
|
705
|
+
|
706
|
+
t_ID.__doc__ = identifier
|
707
|
+
</pre>
|
708
|
+
</blockquote>
|
709
|
+
|
710
|
+
<b>NOTE:</b> Use of <tt>@TOKEN</tt> requires Python-2.4 or newer. If you're concerned about backwards compatibility with older
|
711
|
+
versions of Python, use the alternative approach of setting the docstring directly.
|
712
|
+
|
713
|
+
<H3><a name="ply_nn15"></a>4.12 Optimized mode</H3>
|
714
|
+
|
715
|
+
|
716
|
+
For improved performance, it may be desirable to use Python's
|
717
|
+
optimized mode (e.g., running Python with the <tt>-O</tt>
|
718
|
+
option). However, doing so causes Python to ignore documentation
|
719
|
+
strings. This presents special problems for <tt>lex.py</tt>. To
|
720
|
+
handle this case, you can create your lexer using
|
721
|
+
the <tt>optimize</tt> option as follows:
|
722
|
+
|
723
|
+
<blockquote>
|
724
|
+
<pre>
|
725
|
+
lexer = lex.lex(optimize=1)
|
726
|
+
</pre>
|
727
|
+
</blockquote>
|
728
|
+
|
729
|
+
Next, run Python in its normal operating mode. When you do
|
730
|
+
this, <tt>lex.py</tt> will write a file called <tt>lextab.py</tt> to
|
731
|
+
the current directory. This file contains all of the regular
|
732
|
+
expression rules and tables used during lexing. On subsequent
|
733
|
+
executions,
|
734
|
+
<tt>lextab.py</tt> will simply be imported to build the lexer. This
|
735
|
+
approach substantially improves the startup time of the lexer and it
|
736
|
+
works in Python's optimized mode.
|
737
|
+
|
738
|
+
<p>
|
739
|
+
To change the name of the lexer-generated file, use the <tt>lextab</tt> keyword argument. For example:
|
740
|
+
|
741
|
+
<blockquote>
|
742
|
+
<pre>
|
743
|
+
lexer = lex.lex(optimize=1,lextab="footab")
|
744
|
+
</pre>
|
745
|
+
</blockquote>
|
746
|
+
|
747
|
+
When running in optimized mode, it is important to note that lex disables most error checking. Thus, this is really only recommended
|
748
|
+
if you're sure everything is working correctly and you're ready to start releasing production code.
|
749
|
+
|
750
|
+
<H3><a name="ply_nn16"></a>4.13 Debugging</H3>
|
751
|
+
|
752
|
+
|
753
|
+
For the purpose of debugging, you can run <tt>lex()</tt> in a debugging mode as follows:
|
754
|
+
|
755
|
+
<blockquote>
|
756
|
+
<pre>
|
757
|
+
lexer = lex.lex(debug=1)
|
758
|
+
</pre>
|
759
|
+
</blockquote>
|
760
|
+
|
761
|
+
<p>
|
762
|
+
This will produce various sorts of debugging information including all of the added rules,
|
763
|
+
the master regular expressions used by the lexer, and tokens generating during lexing.
|
764
|
+
</p>
|
765
|
+
|
766
|
+
<p>
|
767
|
+
In addition, <tt>lex.py</tt> comes with a simple main function which
|
768
|
+
will either tokenize input read from standard input or from a file specified
|
769
|
+
on the command line. To use it, simply put this in your lexer:
|
770
|
+
</p>
|
771
|
+
|
772
|
+
<blockquote>
|
773
|
+
<pre>
|
774
|
+
if __name__ == '__main__':
|
775
|
+
lex.runmain()
|
776
|
+
</pre>
|
777
|
+
</blockquote>
|
778
|
+
|
779
|
+
Please refer to the "Debugging" section near the end for some more advanced details
|
780
|
+
of debugging.
|
781
|
+
|
782
|
+
<H3><a name="ply_nn17"></a>4.14 Alternative specification of lexers</H3>
|
783
|
+
|
784
|
+
|
785
|
+
As shown in the example, lexers are specified all within one Python module. If you want to
|
786
|
+
put token rules in a different module from the one in which you invoke <tt>lex()</tt>, use the
|
787
|
+
<tt>module</tt> keyword argument.
|
788
|
+
|
789
|
+
<p>
|
790
|
+
For example, you might have a dedicated module that just contains
|
791
|
+
the token rules:
|
792
|
+
|
793
|
+
<blockquote>
|
794
|
+
<pre>
|
795
|
+
# module: tokrules.py
|
796
|
+
# This module just contains the lexing rules
|
797
|
+
|
798
|
+
# List of token names. This is always required
|
799
|
+
tokens = (
|
800
|
+
'NUMBER',
|
801
|
+
'PLUS',
|
802
|
+
'MINUS',
|
803
|
+
'TIMES',
|
804
|
+
'DIVIDE',
|
805
|
+
'LPAREN',
|
806
|
+
'RPAREN',
|
807
|
+
)
|
808
|
+
|
809
|
+
# Regular expression rules for simple tokens
|
810
|
+
t_PLUS = r'\+'
|
811
|
+
t_MINUS = r'-'
|
812
|
+
t_TIMES = r'\*'
|
813
|
+
t_DIVIDE = r'/'
|
814
|
+
t_LPAREN = r'\('
|
815
|
+
t_RPAREN = r'\)'
|
816
|
+
|
817
|
+
# A regular expression rule with some action code
|
818
|
+
def t_NUMBER(t):
|
819
|
+
r'\d+'
|
820
|
+
t.value = int(t.value)
|
821
|
+
return t
|
822
|
+
|
823
|
+
# Define a rule so we can track line numbers
|
824
|
+
def t_newline(t):
|
825
|
+
r'\n+'
|
826
|
+
t.lexer.lineno += len(t.value)
|
827
|
+
|
828
|
+
# A string containing ignored characters (spaces and tabs)
|
829
|
+
t_ignore = ' \t'
|
830
|
+
|
831
|
+
# Error handling rule
|
832
|
+
def t_error(t):
|
833
|
+
print "Illegal character '%s'" % t.value[0]
|
834
|
+
t.lexer.skip(1)
|
835
|
+
</pre>
|
836
|
+
</blockquote>
|
837
|
+
|
838
|
+
Now, if you wanted to build a tokenizer from these rules from within a different module, you would do the following (shown for Python interactive mode):
|
839
|
+
|
840
|
+
<blockquote>
|
841
|
+
<pre>
|
842
|
+
>>> import tokrules
|
843
|
+
>>> <b>lexer = lex.lex(module=tokrules)</b>
|
844
|
+
>>> lexer.input("3 + 4")
|
845
|
+
>>> lexer.token()
|
846
|
+
LexToken(NUMBER,3,1,1,0)
|
847
|
+
>>> lexer.token()
|
848
|
+
LexToken(PLUS,'+',1,2)
|
849
|
+
>>> lexer.token()
|
850
|
+
LexToken(NUMBER,4,1,4)
|
851
|
+
>>> lexer.token()
|
852
|
+
None
|
853
|
+
>>>
|
854
|
+
</pre>
|
855
|
+
</blockquote>
|
856
|
+
|
857
|
+
The <tt>module</tt> option can also be used to define lexers from instances of a class. For example:
|
858
|
+
|
859
|
+
<blockquote>
|
860
|
+
<pre>
|
861
|
+
import ply.lex as lex
|
862
|
+
|
863
|
+
class MyLexer:
|
864
|
+
# List of token names. This is always required
|
865
|
+
tokens = (
|
866
|
+
'NUMBER',
|
867
|
+
'PLUS',
|
868
|
+
'MINUS',
|
869
|
+
'TIMES',
|
870
|
+
'DIVIDE',
|
871
|
+
'LPAREN',
|
872
|
+
'RPAREN',
|
873
|
+
)
|
874
|
+
|
875
|
+
# Regular expression rules for simple tokens
|
876
|
+
t_PLUS = r'\+'
|
877
|
+
t_MINUS = r'-'
|
878
|
+
t_TIMES = r'\*'
|
879
|
+
t_DIVIDE = r'/'
|
880
|
+
t_LPAREN = r'\('
|
881
|
+
t_RPAREN = r'\)'
|
882
|
+
|
883
|
+
# A regular expression rule with some action code
|
884
|
+
# Note addition of self parameter since we're in a class
|
885
|
+
def t_NUMBER(self,t):
|
886
|
+
r'\d+'
|
887
|
+
t.value = int(t.value)
|
888
|
+
return t
|
889
|
+
|
890
|
+
# Define a rule so we can track line numbers
|
891
|
+
def t_newline(self,t):
|
892
|
+
r'\n+'
|
893
|
+
t.lexer.lineno += len(t.value)
|
894
|
+
|
895
|
+
# A string containing ignored characters (spaces and tabs)
|
896
|
+
t_ignore = ' \t'
|
897
|
+
|
898
|
+
# Error handling rule
|
899
|
+
def t_error(self,t):
|
900
|
+
print "Illegal character '%s'" % t.value[0]
|
901
|
+
t.lexer.skip(1)
|
902
|
+
|
903
|
+
<b># Build the lexer
|
904
|
+
def build(self,**kwargs):
|
905
|
+
self.lexer = lex.lex(module=self, **kwargs)</b>
|
906
|
+
|
907
|
+
# Test it output
|
908
|
+
def test(self,data):
|
909
|
+
self.lexer.input(data)
|
910
|
+
while True:
|
911
|
+
tok = lexer.token()
|
912
|
+
if not tok: break
|
913
|
+
print tok
|
914
|
+
|
915
|
+
# Build the lexer and try it out
|
916
|
+
m = MyLexer()
|
917
|
+
m.build() # Build the lexer
|
918
|
+
m.test("3 + 4") # Test it
|
919
|
+
</pre>
|
920
|
+
</blockquote>
|
921
|
+
|
922
|
+
|
923
|
+
When building a lexer from class, <em>you should construct the lexer from
|
924
|
+
an instance of the class</em>, not the class object itself. This is because
|
925
|
+
PLY only works properly if the lexer actions are defined by bound-methods.
|
926
|
+
|
927
|
+
<p>
|
928
|
+
When using the <tt>module</tt> option to <tt>lex()</tt>, PLY collects symbols
|
929
|
+
from the underlying object using the <tt>dir()</tt> function. There is no
|
930
|
+
direct access to the <tt>__dict__</tt> attribute of the object supplied as a
|
931
|
+
module value.
|
932
|
+
|
933
|
+
<P>
|
934
|
+
Finally, if you want to keep things nicely encapsulated, but don't want to use a
|
935
|
+
full-fledged class definition, lexers can be defined using closures. For example:
|
936
|
+
|
937
|
+
<blockquote>
|
938
|
+
<pre>
|
939
|
+
import ply.lex as lex
|
940
|
+
|
941
|
+
# List of token names. This is always required
|
942
|
+
tokens = (
|
943
|
+
'NUMBER',
|
944
|
+
'PLUS',
|
945
|
+
'MINUS',
|
946
|
+
'TIMES',
|
947
|
+
'DIVIDE',
|
948
|
+
'LPAREN',
|
949
|
+
'RPAREN',
|
950
|
+
)
|
951
|
+
|
952
|
+
def MyLexer():
|
953
|
+
# Regular expression rules for simple tokens
|
954
|
+
t_PLUS = r'\+'
|
955
|
+
t_MINUS = r'-'
|
956
|
+
t_TIMES = r'\*'
|
957
|
+
t_DIVIDE = r'/'
|
958
|
+
t_LPAREN = r'\('
|
959
|
+
t_RPAREN = r'\)'
|
960
|
+
|
961
|
+
# A regular expression rule with some action code
|
962
|
+
def t_NUMBER(t):
|
963
|
+
r'\d+'
|
964
|
+
t.value = int(t.value)
|
965
|
+
return t
|
966
|
+
|
967
|
+
# Define a rule so we can track line numbers
|
968
|
+
def t_newline(t):
|
969
|
+
r'\n+'
|
970
|
+
t.lexer.lineno += len(t.value)
|
971
|
+
|
972
|
+
# A string containing ignored characters (spaces and tabs)
|
973
|
+
t_ignore = ' \t'
|
974
|
+
|
975
|
+
# Error handling rule
|
976
|
+
def t_error(t):
|
977
|
+
print "Illegal character '%s'" % t.value[0]
|
978
|
+
t.lexer.skip(1)
|
979
|
+
|
980
|
+
# Build the lexer from my environment and return it
|
981
|
+
return lex.lex()
|
982
|
+
</pre>
|
983
|
+
</blockquote>
|
984
|
+
|
985
|
+
|
986
|
+
<H3><a name="ply_nn18"></a>4.15 Maintaining state</H3>
|
987
|
+
|
988
|
+
|
989
|
+
In your lexer, you may want to maintain a variety of state
|
990
|
+
information. This might include mode settings, symbol tables, and
|
991
|
+
other details. As an example, suppose that you wanted to keep
|
992
|
+
track of how many NUMBER tokens had been encountered.
|
993
|
+
|
994
|
+
<p>
|
995
|
+
One way to do this is to keep a set of global variables in the module
|
996
|
+
where you created the lexer. For example:
|
997
|
+
|
998
|
+
<blockquote>
|
999
|
+
<pre>
|
1000
|
+
num_count = 0
|
1001
|
+
def t_NUMBER(t):
|
1002
|
+
r'\d+'
|
1003
|
+
global num_count
|
1004
|
+
num_count += 1
|
1005
|
+
t.value = int(t.value)
|
1006
|
+
return t
|
1007
|
+
</pre>
|
1008
|
+
</blockquote>
|
1009
|
+
|
1010
|
+
If you don't like the use of a global variable, another place to store
|
1011
|
+
information is inside the Lexer object created by <tt>lex()</tt>.
|
1012
|
+
To this, you can use the <tt>lexer</tt> attribute of tokens passed to
|
1013
|
+
the various rules. For example:
|
1014
|
+
|
1015
|
+
<blockquote>
|
1016
|
+
<pre>
|
1017
|
+
def t_NUMBER(t):
|
1018
|
+
r'\d+'
|
1019
|
+
t.lexer.num_count += 1 # Note use of lexer attribute
|
1020
|
+
t.value = int(t.value)
|
1021
|
+
return t
|
1022
|
+
|
1023
|
+
lexer = lex.lex()
|
1024
|
+
lexer.num_count = 0 # Set the initial count
|
1025
|
+
</pre>
|
1026
|
+
</blockquote>
|
1027
|
+
|
1028
|
+
This latter approach has the advantage of being simple and working
|
1029
|
+
correctly in applications where multiple instantiations of a given
|
1030
|
+
lexer exist in the same application. However, this might also feel
|
1031
|
+
like a gross violation of encapsulation to OO purists.
|
1032
|
+
Just to put your mind at some ease, all
|
1033
|
+
internal attributes of the lexer (with the exception of <tt>lineno</tt>) have names that are prefixed
|
1034
|
+
by <tt>lex</tt> (e.g., <tt>lexdata</tt>,<tt>lexpos</tt>, etc.). Thus,
|
1035
|
+
it is perfectly safe to store attributes in the lexer that
|
1036
|
+
don't have names starting with that prefix or a name that conlicts with one of the
|
1037
|
+
predefined methods (e.g., <tt>input()</tt>, <tt>token()</tt>, etc.).
|
1038
|
+
|
1039
|
+
<p>
|
1040
|
+
If you don't like assigning values on the lexer object, you can define your lexer as a class as
|
1041
|
+
shown in the previous section:
|
1042
|
+
|
1043
|
+
<blockquote>
|
1044
|
+
<pre>
|
1045
|
+
class MyLexer:
|
1046
|
+
...
|
1047
|
+
def t_NUMBER(self,t):
|
1048
|
+
r'\d+'
|
1049
|
+
self.num_count += 1
|
1050
|
+
t.value = int(t.value)
|
1051
|
+
return t
|
1052
|
+
|
1053
|
+
def build(self, **kwargs):
|
1054
|
+
self.lexer = lex.lex(object=self,**kwargs)
|
1055
|
+
|
1056
|
+
def __init__(self):
|
1057
|
+
self.num_count = 0
|
1058
|
+
</pre>
|
1059
|
+
</blockquote>
|
1060
|
+
|
1061
|
+
The class approach may be the easiest to manage if your application is
|
1062
|
+
going to be creating multiple instances of the same lexer and you need
|
1063
|
+
to manage a lot of state.
|
1064
|
+
|
1065
|
+
<p>
|
1066
|
+
State can also be managed through closures. For example, in Python 3:
|
1067
|
+
|
1068
|
+
<blockquote>
|
1069
|
+
<pre>
|
1070
|
+
def MyLexer():
|
1071
|
+
num_count = 0
|
1072
|
+
...
|
1073
|
+
def t_NUMBER(t):
|
1074
|
+
r'\d+'
|
1075
|
+
nonlocal num_count
|
1076
|
+
num_count += 1
|
1077
|
+
t.value = int(t.value)
|
1078
|
+
return t
|
1079
|
+
...
|
1080
|
+
</pre>
|
1081
|
+
</blockquote>
|
1082
|
+
|
1083
|
+
<H3><a name="ply_nn19"></a>4.16 Lexer cloning</H3>
|
1084
|
+
|
1085
|
+
|
1086
|
+
<p>
|
1087
|
+
If necessary, a lexer object can be duplicated by invoking its <tt>clone()</tt> method. For example:
|
1088
|
+
|
1089
|
+
<blockquote>
|
1090
|
+
<pre>
|
1091
|
+
lexer = lex.lex()
|
1092
|
+
...
|
1093
|
+
newlexer = lexer.clone()
|
1094
|
+
</pre>
|
1095
|
+
</blockquote>
|
1096
|
+
|
1097
|
+
When a lexer is cloned, the copy is exactly identical to the original lexer
|
1098
|
+
including any input text and internal state. However, the clone allows a
|
1099
|
+
different set of input text to be supplied which may be processed separately.
|
1100
|
+
This may be useful in situations when you are writing a parser/compiler that
|
1101
|
+
involves recursive or reentrant processing. For instance, if you
|
1102
|
+
needed to scan ahead in the input for some reason, you could create a
|
1103
|
+
clone and use it to look ahead. Or, if you were implementing some kind of preprocessor,
|
1104
|
+
cloned lexers could be used to handle different input files.
|
1105
|
+
|
1106
|
+
<p>
|
1107
|
+
Creating a clone is different than calling <tt>lex.lex()</tt> in that
|
1108
|
+
PLY doesn't regenerate any of the internal tables or regular expressions. So,
|
1109
|
+
|
1110
|
+
<p>
|
1111
|
+
Special considerations need to be made when cloning lexers that also
|
1112
|
+
maintain their own internal state using classes or closures. Namely,
|
1113
|
+
you need to be aware that the newly created lexers will share all of
|
1114
|
+
this state with the original lexer. For example, if you defined a
|
1115
|
+
lexer as a class and did this:
|
1116
|
+
|
1117
|
+
<blockquote>
|
1118
|
+
<pre>
|
1119
|
+
m = MyLexer()
|
1120
|
+
a = lex.lex(object=m) # Create a lexer
|
1121
|
+
|
1122
|
+
b = a.clone() # Clone the lexer
|
1123
|
+
</pre>
|
1124
|
+
</blockquote>
|
1125
|
+
|
1126
|
+
Then both <tt>a</tt> and <tt>b</tt> are going to be bound to the same
|
1127
|
+
object <tt>m</tt> and any changes to <tt>m</tt> will be reflected in both lexers. It's
|
1128
|
+
important to emphasize that <tt>clone()</tt> is only meant to create a new lexer
|
1129
|
+
that reuses the regular expressions and environment of another lexer. If you
|
1130
|
+
need to make a totally new copy of a lexer, then call <tt>lex()</tt> again.
|
1131
|
+
|
1132
|
+
<H3><a name="ply_nn20"></a>4.17 Internal lexer state</H3>
|
1133
|
+
|
1134
|
+
|
1135
|
+
A Lexer object <tt>lexer</tt> has a number of internal attributes that may be useful in certain
|
1136
|
+
situations.
|
1137
|
+
|
1138
|
+
<p>
|
1139
|
+
<tt>lexer.lexpos</tt>
|
1140
|
+
<blockquote>
|
1141
|
+
This attribute is an integer that contains the current position within the input text. If you modify
|
1142
|
+
the value, it will change the result of the next call to <tt>token()</tt>. Within token rule functions, this points
|
1143
|
+
to the first character <em>after</em> the matched text. If the value is modified within a rule, the next returned token will be
|
1144
|
+
matched at the new position.
|
1145
|
+
</blockquote>
|
1146
|
+
|
1147
|
+
<p>
|
1148
|
+
<tt>lexer.lineno</tt>
|
1149
|
+
<blockquote>
|
1150
|
+
The current value of the line number attribute stored in the lexer. PLY only specifies that the attribute
|
1151
|
+
exists---it never sets, updates, or performs any processing with it. If you want to track line numbers,
|
1152
|
+
you will need to add code yourself (see the section on line numbers and positional information).
|
1153
|
+
</blockquote>
|
1154
|
+
|
1155
|
+
<p>
|
1156
|
+
<tt>lexer.lexdata</tt>
|
1157
|
+
<blockquote>
|
1158
|
+
The current input text stored in the lexer. This is the string passed with the <tt>input()</tt> method. It
|
1159
|
+
would probably be a bad idea to modify this unless you really know what you're doing.
|
1160
|
+
</blockquote>
|
1161
|
+
|
1162
|
+
<P>
|
1163
|
+
<tt>lexer.lexmatch</tt>
|
1164
|
+
<blockquote>
|
1165
|
+
This is the raw <tt>Match</tt> object returned by the Python <tt>re.match()</tt> function (used internally by PLY) for the
|
1166
|
+
current token. If you have written a regular expression that contains named groups, you can use this to retrieve those values.
|
1167
|
+
Note: This attribute is only updated when tokens are defined and processed by functions.
|
1168
|
+
</blockquote>
|
1169
|
+
|
1170
|
+
<H3><a name="ply_nn21"></a>4.18 Conditional lexing and start conditions</H3>
|
1171
|
+
|
1172
|
+
|
1173
|
+
In advanced parsing applications, it may be useful to have different
|
1174
|
+
lexing states. For instance, you may want the occurrence of a certain
|
1175
|
+
token or syntactic construct to trigger a different kind of lexing.
|
1176
|
+
PLY supports a feature that allows the underlying lexer to be put into
|
1177
|
+
a series of different states. Each state can have its own tokens,
|
1178
|
+
lexing rules, and so forth. The implementation is based largely on
|
1179
|
+
the "start condition" feature of GNU flex. Details of this can be found
|
1180
|
+
at <a
|
1181
|
+
href="http://www.gnu.org/software/flex/manual/html_chapter/flex_11.html">http://www.gnu.org/software/flex/manual/html_chapter/flex_11.html.</a>.
|
1182
|
+
|
1183
|
+
<p>
|
1184
|
+
To define a new lexing state, it must first be declared. This is done by including a "states" declaration in your
|
1185
|
+
lex file. For example:
|
1186
|
+
|
1187
|
+
<blockquote>
|
1188
|
+
<pre>
|
1189
|
+
states = (
|
1190
|
+
('foo','exclusive'),
|
1191
|
+
('bar','inclusive'),
|
1192
|
+
)
|
1193
|
+
</pre>
|
1194
|
+
</blockquote>
|
1195
|
+
|
1196
|
+
This declaration declares two states, <tt>'foo'</tt>
|
1197
|
+
and <tt>'bar'</tt>. States may be of two types; <tt>'exclusive'</tt>
|
1198
|
+
and <tt>'inclusive'</tt>. An exclusive state completely overrides the
|
1199
|
+
default behavior of the lexer. That is, lex will only return tokens
|
1200
|
+
and apply rules defined specifically for that state. An inclusive
|
1201
|
+
state adds additional tokens and rules to the default set of rules.
|
1202
|
+
Thus, lex will return both the tokens defined by default in addition
|
1203
|
+
to those defined for the inclusive state.
|
1204
|
+
|
1205
|
+
<p>
|
1206
|
+
Once a state has been declared, tokens and rules are declared by including the
|
1207
|
+
state name in token/rule declaration. For example:
|
1208
|
+
|
1209
|
+
<blockquote>
|
1210
|
+
<pre>
|
1211
|
+
t_foo_NUMBER = r'\d+' # Token 'NUMBER' in state 'foo'
|
1212
|
+
t_bar_ID = r'[a-zA-Z_][a-zA-Z0-9_]*' # Token 'ID' in state 'bar'
|
1213
|
+
|
1214
|
+
def t_foo_newline(t):
|
1215
|
+
r'\n'
|
1216
|
+
t.lexer.lineno += 1
|
1217
|
+
</pre>
|
1218
|
+
</blockquote>
|
1219
|
+
|
1220
|
+
A token can be declared in multiple states by including multiple state names in the declaration. For example:
|
1221
|
+
|
1222
|
+
<blockquote>
|
1223
|
+
<pre>
|
1224
|
+
t_foo_bar_NUMBER = r'\d+' # Defines token 'NUMBER' in both state 'foo' and 'bar'
|
1225
|
+
</pre>
|
1226
|
+
</blockquote>
|
1227
|
+
|
1228
|
+
Alternative, a token can be declared in all states using the 'ANY' in the name.
|
1229
|
+
|
1230
|
+
<blockquote>
|
1231
|
+
<pre>
|
1232
|
+
t_ANY_NUMBER = r'\d+' # Defines a token 'NUMBER' in all states
|
1233
|
+
</pre>
|
1234
|
+
</blockquote>
|
1235
|
+
|
1236
|
+
If no state name is supplied, as is normally the case, the token is associated with a special state <tt>'INITIAL'</tt>. For example,
|
1237
|
+
these two declarations are identical:
|
1238
|
+
|
1239
|
+
<blockquote>
|
1240
|
+
<pre>
|
1241
|
+
t_NUMBER = r'\d+'
|
1242
|
+
t_INITIAL_NUMBER = r'\d+'
|
1243
|
+
</pre>
|
1244
|
+
</blockquote>
|
1245
|
+
|
1246
|
+
<p>
|
1247
|
+
States are also associated with the special <tt>t_ignore</tt> and <tt>t_error()</tt> declarations. For example, if a state treats
|
1248
|
+
these differently, you can declare:
|
1249
|
+
|
1250
|
+
<blockquote>
|
1251
|
+
<pre>
|
1252
|
+
t_foo_ignore = " \t\n" # Ignored characters for state 'foo'
|
1253
|
+
|
1254
|
+
def t_bar_error(t): # Special error handler for state 'bar'
|
1255
|
+
pass
|
1256
|
+
</pre>
|
1257
|
+
</blockquote>
|
1258
|
+
|
1259
|
+
By default, lexing operates in the <tt>'INITIAL'</tt> state. This state includes all of the normally defined tokens.
|
1260
|
+
For users who aren't using different states, this fact is completely transparent. If, during lexing or parsing, you want to change
|
1261
|
+
the lexing state, use the <tt>begin()</tt> method. For example:
|
1262
|
+
|
1263
|
+
<blockquote>
|
1264
|
+
<pre>
|
1265
|
+
def t_begin_foo(t):
|
1266
|
+
r'start_foo'
|
1267
|
+
t.lexer.begin('foo') # Starts 'foo' state
|
1268
|
+
</pre>
|
1269
|
+
</blockquote>
|
1270
|
+
|
1271
|
+
To get out of a state, you use <tt>begin()</tt> to switch back to the initial state. For example:
|
1272
|
+
|
1273
|
+
<blockquote>
|
1274
|
+
<pre>
|
1275
|
+
def t_foo_end(t):
|
1276
|
+
r'end_foo'
|
1277
|
+
t.lexer.begin('INITIAL') # Back to the initial state
|
1278
|
+
</pre>
|
1279
|
+
</blockquote>
|
1280
|
+
|
1281
|
+
The management of states can also be done with a stack. For example:
|
1282
|
+
|
1283
|
+
<blockquote>
|
1284
|
+
<pre>
|
1285
|
+
def t_begin_foo(t):
|
1286
|
+
r'start_foo'
|
1287
|
+
t.lexer.push_state('foo') # Starts 'foo' state
|
1288
|
+
|
1289
|
+
def t_foo_end(t):
|
1290
|
+
r'end_foo'
|
1291
|
+
t.lexer.pop_state() # Back to the previous state
|
1292
|
+
</pre>
|
1293
|
+
</blockquote>
|
1294
|
+
|
1295
|
+
<p>
|
1296
|
+
The use of a stack would be useful in situations where there are many ways of entering a new lexing state and you merely want to go back
|
1297
|
+
to the previous state afterwards.
|
1298
|
+
|
1299
|
+
<P>
|
1300
|
+
An example might help clarify. Suppose you were writing a parser and you wanted to grab sections of arbitrary C code enclosed by
|
1301
|
+
curly braces. That is, whenever you encounter a starting brace '{', you want to read all of the enclosed code up to the ending brace '}'
|
1302
|
+
and return it as a string. Doing this with a normal regular expression rule is nearly (if not actually) impossible. This is because braces can
|
1303
|
+
be nested and can be included in comments and strings. Thus, simply matching up to the first matching '}' character isn't good enough. Here is how
|
1304
|
+
you might use lexer states to do this:
|
1305
|
+
|
1306
|
+
<blockquote>
|
1307
|
+
<pre>
|
1308
|
+
# Declare the state
|
1309
|
+
states = (
|
1310
|
+
('ccode','exclusive'),
|
1311
|
+
)
|
1312
|
+
|
1313
|
+
# Match the first {. Enter ccode state.
|
1314
|
+
def t_ccode(t):
|
1315
|
+
r'\{'
|
1316
|
+
t.lexer.code_start = t.lexer.lexpos # Record the starting position
|
1317
|
+
t.lexer.level = 1 # Initial brace level
|
1318
|
+
t.lexer.begin('ccode') # Enter 'ccode' state
|
1319
|
+
|
1320
|
+
# Rules for the ccode state
|
1321
|
+
def t_ccode_lbrace(t):
|
1322
|
+
r'\{'
|
1323
|
+
t.lexer.level +=1
|
1324
|
+
|
1325
|
+
def t_ccode_rbrace(t):
|
1326
|
+
r'\}'
|
1327
|
+
t.lexer.level -=1
|
1328
|
+
|
1329
|
+
# If closing brace, return the code fragment
|
1330
|
+
if t.lexer.level == 0:
|
1331
|
+
t.value = t.lexer.lexdata[t.lexer.code_start:t.lexer.lexpos+1]
|
1332
|
+
t.type = "CCODE"
|
1333
|
+
t.lexer.lineno += t.value.count('\n')
|
1334
|
+
t.lexer.begin('INITIAL')
|
1335
|
+
return t
|
1336
|
+
|
1337
|
+
# C or C++ comment (ignore)
|
1338
|
+
def t_ccode_comment(t):
|
1339
|
+
r'(/\*(.|\n)*?*/)|(//.*)'
|
1340
|
+
pass
|
1341
|
+
|
1342
|
+
# C string
|
1343
|
+
def t_ccode_string(t):
|
1344
|
+
r'\"([^\\\n]|(\\.))*?\"'
|
1345
|
+
|
1346
|
+
# C character literal
|
1347
|
+
def t_ccode_char(t):
|
1348
|
+
r'\'([^\\\n]|(\\.))*?\''
|
1349
|
+
|
1350
|
+
# Any sequence of non-whitespace characters (not braces, strings)
|
1351
|
+
def t_ccode_nonspace(t):
|
1352
|
+
r'[^\s\{\}\'\"]+'
|
1353
|
+
|
1354
|
+
# Ignored characters (whitespace)
|
1355
|
+
t_ccode_ignore = " \t\n"
|
1356
|
+
|
1357
|
+
# For bad characters, we just skip over it
|
1358
|
+
def t_ccode_error(t):
|
1359
|
+
t.lexer.skip(1)
|
1360
|
+
</pre>
|
1361
|
+
</blockquote>
|
1362
|
+
|
1363
|
+
In this example, the occurrence of the first '{' causes the lexer to record the starting position and enter a new state <tt>'ccode'</tt>. A collection of rules then match
|
1364
|
+
various parts of the input that follow (comments, strings, etc.). All of these rules merely discard the token (by not returning a value).
|
1365
|
+
However, if the closing right brace is encountered, the rule <tt>t_ccode_rbrace</tt> collects all of the code (using the earlier recorded starting
|
1366
|
+
position), stores it, and returns a token 'CCODE' containing all of that text. When returning the token, the lexing state is restored back to its
|
1367
|
+
initial state.
|
1368
|
+
|
1369
|
+
<H3><a name="ply_nn21"></a>4.19 Miscellaneous Issues</H3>
|
1370
|
+
|
1371
|
+
|
1372
|
+
<P>
|
1373
|
+
<li>The lexer requires input to be supplied as a single input string. Since most machines have more than enough memory, this
|
1374
|
+
rarely presents a performance concern. However, it means that the lexer currently can't be used with streaming data
|
1375
|
+
such as open files or sockets. This limitation is primarily a side-effect of using the <tt>re</tt> module.
|
1376
|
+
|
1377
|
+
<p>
|
1378
|
+
<li>The lexer should work properly with both Unicode strings given as token and pattern matching rules as
|
1379
|
+
well as for input text.
|
1380
|
+
|
1381
|
+
<p>
|
1382
|
+
<li>If you need to supply optional flags to the re.compile() function, use the reflags option to lex. For example:
|
1383
|
+
|
1384
|
+
<blockquote>
|
1385
|
+
<pre>
|
1386
|
+
lex.lex(reflags=re.UNICODE)
|
1387
|
+
</pre>
|
1388
|
+
</blockquote>
|
1389
|
+
|
1390
|
+
<p>
|
1391
|
+
<li>Since the lexer is written entirely in Python, its performance is
|
1392
|
+
largely determined by that of the Python <tt>re</tt> module. Although
|
1393
|
+
the lexer has been written to be as efficient as possible, it's not
|
1394
|
+
blazingly fast when used on very large input files. If
|
1395
|
+
performance is concern, you might consider upgrading to the most
|
1396
|
+
recent version of Python, creating a hand-written lexer, or offloading
|
1397
|
+
the lexer into a C extension module.
|
1398
|
+
|
1399
|
+
<p>
|
1400
|
+
If you are going to create a hand-written lexer and you plan to use it with <tt>yacc.py</tt>,
|
1401
|
+
it only needs to conform to the following requirements:
|
1402
|
+
|
1403
|
+
<ul>
|
1404
|
+
<li>It must provide a <tt>token()</tt> method that returns the next token or <tt>None</tt> if no more
|
1405
|
+
tokens are available.
|
1406
|
+
<li>The <tt>token()</tt> method must return an object <tt>tok</tt> that has <tt>type</tt> and <tt>value</tt> attributes. If
|
1407
|
+
line number tracking is being used, then the token should also define a <tt>lineno</tt> attribute.
|
1408
|
+
</ul>
|
1409
|
+
|
1410
|
+
<H2><a name="ply_nn22"></a>5. Parsing basics</H2>
|
1411
|
+
|
1412
|
+
|
1413
|
+
<tt>yacc.py</tt> is used to parse language syntax. Before showing an
|
1414
|
+
example, there are a few important bits of background that must be
|
1415
|
+
mentioned. First, <em>syntax</em> is usually specified in terms of a BNF grammar.
|
1416
|
+
For example, if you wanted to parse
|
1417
|
+
simple arithmetic expressions, you might first write an unambiguous
|
1418
|
+
grammar specification like this:
|
1419
|
+
|
1420
|
+
<blockquote>
|
1421
|
+
<pre>
|
1422
|
+
expression : expression + term
|
1423
|
+
| expression - term
|
1424
|
+
| term
|
1425
|
+
|
1426
|
+
term : term * factor
|
1427
|
+
| term / factor
|
1428
|
+
| factor
|
1429
|
+
|
1430
|
+
factor : NUMBER
|
1431
|
+
| ( expression )
|
1432
|
+
</pre>
|
1433
|
+
</blockquote>
|
1434
|
+
|
1435
|
+
In the grammar, symbols such as <tt>NUMBER</tt>, <tt>+</tt>, <tt>-</tt>, <tt>*</tt>, and <tt>/</tt> are known
|
1436
|
+
as <em>terminals</em> and correspond to raw input tokens. Identifiers such as <tt>term</tt> and <tt>factor</tt> refer to
|
1437
|
+
grammar rules comprised of a collection of terminals and other rules. These identifiers are known as <em>non-terminals</em>.
|
1438
|
+
<P>
|
1439
|
+
|
1440
|
+
The semantic behavior of a language is often specified using a
|
1441
|
+
technique known as syntax directed translation. In syntax directed
|
1442
|
+
translation, attributes are attached to each symbol in a given grammar
|
1443
|
+
rule along with an action. Whenever a particular grammar rule is
|
1444
|
+
recognized, the action describes what to do. For example, given the
|
1445
|
+
expression grammar above, you might write the specification for a
|
1446
|
+
simple calculator like this:
|
1447
|
+
|
1448
|
+
<blockquote>
|
1449
|
+
<pre>
|
1450
|
+
Grammar Action
|
1451
|
+
-------------------------------- --------------------------------------------
|
1452
|
+
expression0 : expression1 + term expression0.val = expression1.val + term.val
|
1453
|
+
| expression1 - term expression0.val = expression1.val - term.val
|
1454
|
+
| term expression0.val = term.val
|
1455
|
+
|
1456
|
+
term0 : term1 * factor term0.val = term1.val * factor.val
|
1457
|
+
| term1 / factor term0.val = term1.val / factor.val
|
1458
|
+
| factor term0.val = factor.val
|
1459
|
+
|
1460
|
+
factor : NUMBER factor.val = int(NUMBER.lexval)
|
1461
|
+
| ( expression ) factor.val = expression.val
|
1462
|
+
</pre>
|
1463
|
+
</blockquote>
|
1464
|
+
|
1465
|
+
A good way to think about syntax directed translation is to
|
1466
|
+
view each symbol in the grammar as a kind of object. Associated
|
1467
|
+
with each symbol is a value representing its "state" (for example, the
|
1468
|
+
<tt>val</tt> attribute above). Semantic
|
1469
|
+
actions are then expressed as a collection of functions or methods
|
1470
|
+
that operate on the symbols and associated values.
|
1471
|
+
|
1472
|
+
<p>
|
1473
|
+
Yacc uses a parsing technique known as LR-parsing or shift-reduce parsing. LR parsing is a
|
1474
|
+
bottom up technique that tries to recognize the right-hand-side of various grammar rules.
|
1475
|
+
Whenever a valid right-hand-side is found in the input, the appropriate action code is triggered and the
|
1476
|
+
grammar symbols are replaced by the grammar symbol on the left-hand-side.
|
1477
|
+
|
1478
|
+
<p>
|
1479
|
+
LR parsing is commonly implemented by shifting grammar symbols onto a
|
1480
|
+
stack and looking at the stack and the next input token for patterns that
|
1481
|
+
match one of the grammar rules.
|
1482
|
+
The details of the algorithm can be found in a compiler textbook, but the
|
1483
|
+
following example illustrates the steps that are performed if you
|
1484
|
+
wanted to parse the expression
|
1485
|
+
<tt>3 + 5 * (10 - 20)</tt> using the grammar defined above. In the example,
|
1486
|
+
the special symbol <tt>$</tt> represents the end of input.
|
1487
|
+
|
1488
|
+
|
1489
|
+
<blockquote>
|
1490
|
+
<pre>
|
1491
|
+
Step Symbol Stack Input Tokens Action
|
1492
|
+
---- --------------------- --------------------- -------------------------------
|
1493
|
+
1 3 + 5 * ( 10 - 20 )$ Shift 3
|
1494
|
+
2 3 + 5 * ( 10 - 20 )$ Reduce factor : NUMBER
|
1495
|
+
3 factor + 5 * ( 10 - 20 )$ Reduce term : factor
|
1496
|
+
4 term + 5 * ( 10 - 20 )$ Reduce expr : term
|
1497
|
+
5 expr + 5 * ( 10 - 20 )$ Shift +
|
1498
|
+
6 expr + 5 * ( 10 - 20 )$ Shift 5
|
1499
|
+
7 expr + 5 * ( 10 - 20 )$ Reduce factor : NUMBER
|
1500
|
+
8 expr + factor * ( 10 - 20 )$ Reduce term : factor
|
1501
|
+
9 expr + term * ( 10 - 20 )$ Shift *
|
1502
|
+
10 expr + term * ( 10 - 20 )$ Shift (
|
1503
|
+
11 expr + term * ( 10 - 20 )$ Shift 10
|
1504
|
+
12 expr + term * ( 10 - 20 )$ Reduce factor : NUMBER
|
1505
|
+
13 expr + term * ( factor - 20 )$ Reduce term : factor
|
1506
|
+
14 expr + term * ( term - 20 )$ Reduce expr : term
|
1507
|
+
15 expr + term * ( expr - 20 )$ Shift -
|
1508
|
+
16 expr + term * ( expr - 20 )$ Shift 20
|
1509
|
+
17 expr + term * ( expr - 20 )$ Reduce factor : NUMBER
|
1510
|
+
18 expr + term * ( expr - factor )$ Reduce term : factor
|
1511
|
+
19 expr + term * ( expr - term )$ Reduce expr : expr - term
|
1512
|
+
20 expr + term * ( expr )$ Shift )
|
1513
|
+
21 expr + term * ( expr ) $ Reduce factor : (expr)
|
1514
|
+
22 expr + term * factor $ Reduce term : term * factor
|
1515
|
+
23 expr + term $ Reduce expr : expr + term
|
1516
|
+
24 expr $ Reduce expr
|
1517
|
+
25 $ Success!
|
1518
|
+
</pre>
|
1519
|
+
</blockquote>
|
1520
|
+
|
1521
|
+
When parsing the expression, an underlying state machine and the
|
1522
|
+
current input token determine what happens next. If the next token
|
1523
|
+
looks like part of a valid grammar rule (based on other items on the
|
1524
|
+
stack), it is generally shifted onto the stack. If the top of the
|
1525
|
+
stack contains a valid right-hand-side of a grammar rule, it is
|
1526
|
+
usually "reduced" and the symbols replaced with the symbol on the
|
1527
|
+
left-hand-side. When this reduction occurs, the appropriate action is
|
1528
|
+
triggered (if defined). If the input token can't be shifted and the
|
1529
|
+
top of stack doesn't match any grammar rules, a syntax error has
|
1530
|
+
occurred and the parser must take some kind of recovery step (or bail
|
1531
|
+
out). A parse is only successful if the parser reaches a state where
|
1532
|
+
the symbol stack is empty and there are no more input tokens.
|
1533
|
+
|
1534
|
+
<p>
|
1535
|
+
It is important to note that the underlying implementation is built
|
1536
|
+
around a large finite-state machine that is encoded in a collection of
|
1537
|
+
tables. The construction of these tables is non-trivial and
|
1538
|
+
beyond the scope of this discussion. However, subtle details of this
|
1539
|
+
process explain why, in the example above, the parser chooses to shift
|
1540
|
+
a token onto the stack in step 9 rather than reducing the
|
1541
|
+
rule <tt>expr : expr + term</tt>.
|
1542
|
+
|
1543
|
+
<H2><a name="ply_nn23"></a>6. Yacc</H2>
|
1544
|
+
|
1545
|
+
|
1546
|
+
The <tt>ply.yacc</tt> module implements the parsing component of PLY.
|
1547
|
+
The name "yacc" stands for "Yet Another Compiler Compiler" and is
|
1548
|
+
borrowed from the Unix tool of the same name.
|
1549
|
+
|
1550
|
+
<H3><a name="ply_nn24"></a>6.1 An example</H3>
|
1551
|
+
|
1552
|
+
|
1553
|
+
Suppose you wanted to make a grammar for simple arithmetic expressions as previously described. Here is
|
1554
|
+
how you would do it with <tt>yacc.py</tt>:
|
1555
|
+
|
1556
|
+
<blockquote>
|
1557
|
+
<pre>
|
1558
|
+
# Yacc example
|
1559
|
+
|
1560
|
+
import ply.yacc as yacc
|
1561
|
+
|
1562
|
+
# Get the token map from the lexer. This is required.
|
1563
|
+
from calclex import tokens
|
1564
|
+
|
1565
|
+
def p_expression_plus(p):
|
1566
|
+
'expression : expression PLUS term'
|
1567
|
+
p[0] = p[1] + p[3]
|
1568
|
+
|
1569
|
+
def p_expression_minus(p):
|
1570
|
+
'expression : expression MINUS term'
|
1571
|
+
p[0] = p[1] - p[3]
|
1572
|
+
|
1573
|
+
def p_expression_term(p):
|
1574
|
+
'expression : term'
|
1575
|
+
p[0] = p[1]
|
1576
|
+
|
1577
|
+
def p_term_times(p):
|
1578
|
+
'term : term TIMES factor'
|
1579
|
+
p[0] = p[1] * p[3]
|
1580
|
+
|
1581
|
+
def p_term_div(p):
|
1582
|
+
'term : term DIVIDE factor'
|
1583
|
+
p[0] = p[1] / p[3]
|
1584
|
+
|
1585
|
+
def p_term_factor(p):
|
1586
|
+
'term : factor'
|
1587
|
+
p[0] = p[1]
|
1588
|
+
|
1589
|
+
def p_factor_num(p):
|
1590
|
+
'factor : NUMBER'
|
1591
|
+
p[0] = p[1]
|
1592
|
+
|
1593
|
+
def p_factor_expr(p):
|
1594
|
+
'factor : LPAREN expression RPAREN'
|
1595
|
+
p[0] = p[2]
|
1596
|
+
|
1597
|
+
# Error rule for syntax errors
|
1598
|
+
def p_error(p):
|
1599
|
+
print "Syntax error in input!"
|
1600
|
+
|
1601
|
+
# Build the parser
|
1602
|
+
parser = yacc.yacc()
|
1603
|
+
|
1604
|
+
while True:
|
1605
|
+
try:
|
1606
|
+
s = raw_input('calc > ')
|
1607
|
+
except EOFError:
|
1608
|
+
break
|
1609
|
+
if not s: continue
|
1610
|
+
result = parser.parse(s)
|
1611
|
+
print result
|
1612
|
+
</pre>
|
1613
|
+
</blockquote>
|
1614
|
+
|
1615
|
+
In this example, each grammar rule is defined by a Python function
|
1616
|
+
where the docstring to that function contains the appropriate
|
1617
|
+
context-free grammar specification. The statements that make up the
|
1618
|
+
function body implement the semantic actions of the rule. Each function
|
1619
|
+
accepts a single argument <tt>p</tt> that is a sequence containing the
|
1620
|
+
values of each grammar symbol in the corresponding rule. The values
|
1621
|
+
of <tt>p[i]</tt> are mapped to grammar symbols as shown here:
|
1622
|
+
|
1623
|
+
<blockquote>
|
1624
|
+
<pre>
|
1625
|
+
def p_expression_plus(p):
|
1626
|
+
'expression : expression PLUS term'
|
1627
|
+
# ^ ^ ^ ^
|
1628
|
+
# p[0] p[1] p[2] p[3]
|
1629
|
+
|
1630
|
+
p[0] = p[1] + p[3]
|
1631
|
+
</pre>
|
1632
|
+
</blockquote>
|
1633
|
+
|
1634
|
+
<p>
|
1635
|
+
For tokens, the "value" of the corresponding <tt>p[i]</tt> is the
|
1636
|
+
<em>same</em> as the <tt>p.value</tt> attribute assigned in the lexer
|
1637
|
+
module. For non-terminals, the value is determined by whatever is
|
1638
|
+
placed in <tt>p[0]</tt> when rules are reduced. This value can be
|
1639
|
+
anything at all. However, it probably most common for the value to be
|
1640
|
+
a simple Python type, a tuple, or an instance. In this example, we
|
1641
|
+
are relying on the fact that the <tt>NUMBER</tt> token stores an
|
1642
|
+
integer value in its value field. All of the other rules simply
|
1643
|
+
perform various types of integer operations and propagate the result.
|
1644
|
+
</p>
|
1645
|
+
|
1646
|
+
<p>
|
1647
|
+
Note: The use of negative indices have a special meaning in
|
1648
|
+
yacc---specially <tt>p[-1]</tt> does not have the same value
|
1649
|
+
as <tt>p[3]</tt> in this example. Please see the section on "Embedded
|
1650
|
+
Actions" for further details.
|
1651
|
+
</p>
|
1652
|
+
|
1653
|
+
<p>
|
1654
|
+
The first rule defined in the yacc specification determines the
|
1655
|
+
starting grammar symbol (in this case, a rule for <tt>expression</tt>
|
1656
|
+
appears first). Whenever the starting rule is reduced by the parser
|
1657
|
+
and no more input is available, parsing stops and the final value is
|
1658
|
+
returned (this value will be whatever the top-most rule placed
|
1659
|
+
in <tt>p[0]</tt>). Note: an alternative starting symbol can be
|
1660
|
+
specified using the <tt>start</tt> keyword argument to
|
1661
|
+
<tt>yacc()</tt>.
|
1662
|
+
|
1663
|
+
<p>The <tt>p_error(p)</tt> rule is defined to catch syntax errors.
|
1664
|
+
See the error handling section below for more detail.
|
1665
|
+
|
1666
|
+
<p>
|
1667
|
+
To build the parser, call the <tt>yacc.yacc()</tt> function. This
|
1668
|
+
function looks at the module and attempts to construct all of the LR
|
1669
|
+
parsing tables for the grammar you have specified. The first
|
1670
|
+
time <tt>yacc.yacc()</tt> is invoked, you will get a message such as
|
1671
|
+
this:
|
1672
|
+
|
1673
|
+
<blockquote>
|
1674
|
+
<pre>
|
1675
|
+
$ python calcparse.py
|
1676
|
+
Generating LALR tables
|
1677
|
+
calc >
|
1678
|
+
</pre>
|
1679
|
+
</blockquote>
|
1680
|
+
|
1681
|
+
Since table construction is relatively expensive (especially for large
|
1682
|
+
grammars), the resulting parsing table is written to the current
|
1683
|
+
directory in a file called <tt>parsetab.py</tt>. In addition, a
|
1684
|
+
debugging file called <tt>parser.out</tt> is created. On subsequent
|
1685
|
+
executions, <tt>yacc</tt> will reload the table from
|
1686
|
+
<tt>parsetab.py</tt> unless it has detected a change in the underlying
|
1687
|
+
grammar (in which case the tables and <tt>parsetab.py</tt> file are
|
1688
|
+
regenerated). Note: The names of parser output files can be changed
|
1689
|
+
if necessary. See the <a href="reference.html">PLY Reference</a> for details.
|
1690
|
+
|
1691
|
+
<p>
|
1692
|
+
If any errors are detected in your grammar specification, <tt>yacc.py</tt> will produce
|
1693
|
+
diagnostic messages and possibly raise an exception. Some of the errors that can be detected include:
|
1694
|
+
|
1695
|
+
<ul>
|
1696
|
+
<li>Duplicated function names (if more than one rule function have the same name in the grammar file).
|
1697
|
+
<li>Shift/reduce and reduce/reduce conflicts generated by ambiguous grammars.
|
1698
|
+
<li>Badly specified grammar rules.
|
1699
|
+
<li>Infinite recursion (rules that can never terminate).
|
1700
|
+
<li>Unused rules and tokens
|
1701
|
+
<li>Undefined rules and tokens
|
1702
|
+
</ul>
|
1703
|
+
|
1704
|
+
The next few sections discuss grammar specification in more detail.
|
1705
|
+
|
1706
|
+
<p>
|
1707
|
+
The final part of the example shows how to actually run the parser
|
1708
|
+
created by
|
1709
|
+
<tt>yacc()</tt>. To run the parser, you simply have to call
|
1710
|
+
the <tt>parse()</tt> with a string of input text. This will run all
|
1711
|
+
of the grammar rules and return the result of the entire parse. This
|
1712
|
+
result return is the value assigned to <tt>p[0]</tt> in the starting
|
1713
|
+
grammar rule.
|
1714
|
+
|
1715
|
+
<H3><a name="ply_nn25"></a>6.2 Combining Grammar Rule Functions</H3>
|
1716
|
+
|
1717
|
+
|
1718
|
+
When grammar rules are similar, they can be combined into a single function.
|
1719
|
+
For example, consider the two rules in our earlier example:
|
1720
|
+
|
1721
|
+
<blockquote>
|
1722
|
+
<pre>
|
1723
|
+
def p_expression_plus(p):
|
1724
|
+
'expression : expression PLUS term'
|
1725
|
+
p[0] = p[1] + p[3]
|
1726
|
+
|
1727
|
+
def p_expression_minus(t):
|
1728
|
+
'expression : expression MINUS term'
|
1729
|
+
p[0] = p[1] - p[3]
|
1730
|
+
</pre>
|
1731
|
+
</blockquote>
|
1732
|
+
|
1733
|
+
Instead of writing two functions, you might write a single function like this:
|
1734
|
+
|
1735
|
+
<blockquote>
|
1736
|
+
<pre>
|
1737
|
+
def p_expression(p):
|
1738
|
+
'''expression : expression PLUS term
|
1739
|
+
| expression MINUS term'''
|
1740
|
+
if p[2] == '+':
|
1741
|
+
p[0] = p[1] + p[3]
|
1742
|
+
elif p[2] == '-':
|
1743
|
+
p[0] = p[1] - p[3]
|
1744
|
+
</pre>
|
1745
|
+
</blockquote>
|
1746
|
+
|
1747
|
+
In general, the doc string for any given function can contain multiple grammar rules. So, it would
|
1748
|
+
have also been legal (although possibly confusing) to write this:
|
1749
|
+
|
1750
|
+
<blockquote>
|
1751
|
+
<pre>
|
1752
|
+
def p_binary_operators(p):
|
1753
|
+
'''expression : expression PLUS term
|
1754
|
+
| expression MINUS term
|
1755
|
+
term : term TIMES factor
|
1756
|
+
| term DIVIDE factor'''
|
1757
|
+
if p[2] == '+':
|
1758
|
+
p[0] = p[1] + p[3]
|
1759
|
+
elif p[2] == '-':
|
1760
|
+
p[0] = p[1] - p[3]
|
1761
|
+
elif p[2] == '*':
|
1762
|
+
p[0] = p[1] * p[3]
|
1763
|
+
elif p[2] == '/':
|
1764
|
+
p[0] = p[1] / p[3]
|
1765
|
+
</pre>
|
1766
|
+
</blockquote>
|
1767
|
+
|
1768
|
+
When combining grammar rules into a single function, it is usually a good idea for all of the rules to have
|
1769
|
+
a similar structure (e.g., the same number of terms). Otherwise, the corresponding action code may be more
|
1770
|
+
complicated than necessary. However, it is possible to handle simple cases using len(). For example:
|
1771
|
+
|
1772
|
+
<blockquote>
|
1773
|
+
<pre>
|
1774
|
+
def p_expressions(p):
|
1775
|
+
'''expression : expression MINUS expression
|
1776
|
+
| MINUS expression'''
|
1777
|
+
if (len(p) == 4):
|
1778
|
+
p[0] = p[1] - p[3]
|
1779
|
+
elif (len(p) == 3):
|
1780
|
+
p[0] = -p[2]
|
1781
|
+
</pre>
|
1782
|
+
</blockquote>
|
1783
|
+
|
1784
|
+
If parsing performance is a concern, you should resist the urge to put
|
1785
|
+
too much conditional processing into a single grammar rule as shown in
|
1786
|
+
these examples. When you add checks to see which grammar rule is
|
1787
|
+
being handled, you are actually duplicating the work that the parser
|
1788
|
+
has already performed (i.e., the parser already knows exactly what rule it
|
1789
|
+
matched). You can eliminate this overhead by using a
|
1790
|
+
separate <tt>p_rule()</tt> function for each grammar rule.
|
1791
|
+
|
1792
|
+
<H3><a name="ply_nn26"></a>6.3 Character Literals</H3>
|
1793
|
+
|
1794
|
+
|
1795
|
+
If desired, a grammar may contain tokens defined as single character literals. For example:
|
1796
|
+
|
1797
|
+
<blockquote>
|
1798
|
+
<pre>
|
1799
|
+
def p_binary_operators(p):
|
1800
|
+
'''expression : expression '+' term
|
1801
|
+
| expression '-' term
|
1802
|
+
term : term '*' factor
|
1803
|
+
| term '/' factor'''
|
1804
|
+
if p[2] == '+':
|
1805
|
+
p[0] = p[1] + p[3]
|
1806
|
+
elif p[2] == '-':
|
1807
|
+
p[0] = p[1] - p[3]
|
1808
|
+
elif p[2] == '*':
|
1809
|
+
p[0] = p[1] * p[3]
|
1810
|
+
elif p[2] == '/':
|
1811
|
+
p[0] = p[1] / p[3]
|
1812
|
+
</pre>
|
1813
|
+
</blockquote>
|
1814
|
+
|
1815
|
+
A character literal must be enclosed in quotes such as <tt>'+'</tt>. In addition, if literals are used, they must be declared in the
|
1816
|
+
corresponding <tt>lex</tt> file through the use of a special <tt>literals</tt> declaration.
|
1817
|
+
|
1818
|
+
<blockquote>
|
1819
|
+
<pre>
|
1820
|
+
# Literals. Should be placed in module given to lex()
|
1821
|
+
literals = ['+','-','*','/' ]
|
1822
|
+
</pre>
|
1823
|
+
</blockquote>
|
1824
|
+
|
1825
|
+
<b>Character literals are limited to a single character</b>. Thus, it is not legal to specify literals such as <tt>'<='</tt> or <tt>'=='</tt>. For this, use
|
1826
|
+
the normal lexing rules (e.g., define a rule such as <tt>t_EQ = r'=='</tt>).
|
1827
|
+
|
1828
|
+
<H3><a name="ply_nn26"></a>6.4 Empty Productions</H3>
|
1829
|
+
|
1830
|
+
|
1831
|
+
<tt>yacc.py</tt> can handle empty productions by defining a rule like this:
|
1832
|
+
|
1833
|
+
<blockquote>
|
1834
|
+
<pre>
|
1835
|
+
def p_empty(p):
|
1836
|
+
'empty :'
|
1837
|
+
pass
|
1838
|
+
</pre>
|
1839
|
+
</blockquote>
|
1840
|
+
|
1841
|
+
Now to use the empty production, simply use 'empty' as a symbol. For example:
|
1842
|
+
|
1843
|
+
<blockquote>
|
1844
|
+
<pre>
|
1845
|
+
def p_optitem(p):
|
1846
|
+
'optitem : item'
|
1847
|
+
' | empty'
|
1848
|
+
...
|
1849
|
+
</pre>
|
1850
|
+
</blockquote>
|
1851
|
+
|
1852
|
+
Note: You can write empty rules anywhere by simply specifying an empty
|
1853
|
+
right hand side. However, I personally find that writing an "empty"
|
1854
|
+
rule and using "empty" to denote an empty production is easier to read
|
1855
|
+
and more clearly states your intentions.
|
1856
|
+
|
1857
|
+
<H3><a name="ply_nn28"></a>6.5 Changing the starting symbol</H3>
|
1858
|
+
|
1859
|
+
|
1860
|
+
Normally, the first rule found in a yacc specification defines the starting grammar rule (top level rule). To change this, simply
|
1861
|
+
supply a <tt>start</tt> specifier in your file. For example:
|
1862
|
+
|
1863
|
+
<blockquote>
|
1864
|
+
<pre>
|
1865
|
+
start = 'foo'
|
1866
|
+
|
1867
|
+
def p_bar(p):
|
1868
|
+
'bar : A B'
|
1869
|
+
|
1870
|
+
# This is the starting rule due to the start specifier above
|
1871
|
+
def p_foo(p):
|
1872
|
+
'foo : bar X'
|
1873
|
+
...
|
1874
|
+
</pre>
|
1875
|
+
</blockquote>
|
1876
|
+
|
1877
|
+
The use of a <tt>start</tt> specifier may be useful during debugging
|
1878
|
+
since you can use it to have yacc build a subset of a larger grammar.
|
1879
|
+
For this purpose, it is also possible to specify a starting symbol as
|
1880
|
+
an argument to <tt>yacc()</tt>. For example:
|
1881
|
+
|
1882
|
+
<blockquote>
|
1883
|
+
<pre>
|
1884
|
+
yacc.yacc(start='foo')
|
1885
|
+
</pre>
|
1886
|
+
</blockquote>
|
1887
|
+
|
1888
|
+
<H3><a name="ply_nn27"></a>6.6 Dealing With Ambiguous Grammars</H3>
|
1889
|
+
|
1890
|
+
|
1891
|
+
The expression grammar given in the earlier example has been written
|
1892
|
+
in a special format to eliminate ambiguity. However, in many
|
1893
|
+
situations, it is extremely difficult or awkward to write grammars in
|
1894
|
+
this format. A much more natural way to express the grammar is in a
|
1895
|
+
more compact form like this:
|
1896
|
+
|
1897
|
+
<blockquote>
|
1898
|
+
<pre>
|
1899
|
+
expression : expression PLUS expression
|
1900
|
+
| expression MINUS expression
|
1901
|
+
| expression TIMES expression
|
1902
|
+
| expression DIVIDE expression
|
1903
|
+
| LPAREN expression RPAREN
|
1904
|
+
| NUMBER
|
1905
|
+
</pre>
|
1906
|
+
</blockquote>
|
1907
|
+
|
1908
|
+
Unfortunately, this grammar specification is ambiguous. For example,
|
1909
|
+
if you are parsing the string "3 * 4 + 5", there is no way to tell how
|
1910
|
+
the operators are supposed to be grouped. For example, does the
|
1911
|
+
expression mean "(3 * 4) + 5" or is it "3 * (4+5)"?
|
1912
|
+
|
1913
|
+
<p>
|
1914
|
+
When an ambiguous grammar is given to <tt>yacc.py</tt> it will print
|
1915
|
+
messages about "shift/reduce conflicts" or "reduce/reduce conflicts".
|
1916
|
+
A shift/reduce conflict is caused when the parser generator can't
|
1917
|
+
decide whether or not to reduce a rule or shift a symbol on the
|
1918
|
+
parsing stack. For example, consider the string "3 * 4 + 5" and the
|
1919
|
+
internal parsing stack:
|
1920
|
+
|
1921
|
+
<blockquote>
|
1922
|
+
<pre>
|
1923
|
+
Step Symbol Stack Input Tokens Action
|
1924
|
+
---- --------------------- --------------------- -------------------------------
|
1925
|
+
1 $ 3 * 4 + 5$ Shift 3
|
1926
|
+
2 $ 3 * 4 + 5$ Reduce : expression : NUMBER
|
1927
|
+
3 $ expr * 4 + 5$ Shift *
|
1928
|
+
4 $ expr * 4 + 5$ Shift 4
|
1929
|
+
5 $ expr * 4 + 5$ Reduce: expression : NUMBER
|
1930
|
+
6 $ expr * expr + 5$ SHIFT/REDUCE CONFLICT ????
|
1931
|
+
</pre>
|
1932
|
+
</blockquote>
|
1933
|
+
|
1934
|
+
In this case, when the parser reaches step 6, it has two options. One
|
1935
|
+
is to reduce the rule <tt>expr : expr * expr</tt> on the stack. The
|
1936
|
+
other option is to shift the token <tt>+</tt> on the stack. Both
|
1937
|
+
options are perfectly legal from the rules of the
|
1938
|
+
context-free-grammar.
|
1939
|
+
|
1940
|
+
<p>
|
1941
|
+
By default, all shift/reduce conflicts are resolved in favor of
|
1942
|
+
shifting. Therefore, in the above example, the parser will always
|
1943
|
+
shift the <tt>+</tt> instead of reducing. Although this strategy
|
1944
|
+
works in many cases (for example, the case of
|
1945
|
+
"if-then" versus "if-then-else"), it is not enough for arithmetic expressions. In fact,
|
1946
|
+
in the above example, the decision to shift <tt>+</tt> is completely
|
1947
|
+
wrong---we should have reduced <tt>expr * expr</tt> since
|
1948
|
+
multiplication has higher mathematical precedence than addition.
|
1949
|
+
|
1950
|
+
<p>To resolve ambiguity, especially in expression
|
1951
|
+
grammars, <tt>yacc.py</tt> allows individual tokens to be assigned a
|
1952
|
+
precedence level and associativity. This is done by adding a variable
|
1953
|
+
<tt>precedence</tt> to the grammar file like this:
|
1954
|
+
|
1955
|
+
<blockquote>
|
1956
|
+
<pre>
|
1957
|
+
precedence = (
|
1958
|
+
('left', 'PLUS', 'MINUS'),
|
1959
|
+
('left', 'TIMES', 'DIVIDE'),
|
1960
|
+
)
|
1961
|
+
</pre>
|
1962
|
+
</blockquote>
|
1963
|
+
|
1964
|
+
This declaration specifies that <tt>PLUS</tt>/<tt>MINUS</tt> have the
|
1965
|
+
same precedence level and are left-associative and that
|
1966
|
+
<tt>TIMES</tt>/<tt>DIVIDE</tt> have the same precedence and are
|
1967
|
+
left-associative. Within the <tt>precedence</tt> declaration, tokens
|
1968
|
+
are ordered from lowest to highest precedence. Thus, this declaration
|
1969
|
+
specifies that <tt>TIMES</tt>/<tt>DIVIDE</tt> have higher precedence
|
1970
|
+
than <tt>PLUS</tt>/<tt>MINUS</tt> (since they appear later in the
|
1971
|
+
precedence specification).
|
1972
|
+
|
1973
|
+
<p>
|
1974
|
+
The precedence specification works by associating a numerical
|
1975
|
+
precedence level value and associativity direction to the listed
|
1976
|
+
tokens. For example, in the above example you get:
|
1977
|
+
|
1978
|
+
<blockquote>
|
1979
|
+
<pre>
|
1980
|
+
PLUS : level = 1, assoc = 'left'
|
1981
|
+
MINUS : level = 1, assoc = 'left'
|
1982
|
+
TIMES : level = 2, assoc = 'left'
|
1983
|
+
DIVIDE : level = 2, assoc = 'left'
|
1984
|
+
</pre>
|
1985
|
+
</blockquote>
|
1986
|
+
|
1987
|
+
These values are then used to attach a numerical precedence value and
|
1988
|
+
associativity direction to each grammar rule. <em>This is always
|
1989
|
+
determined by looking at the precedence of the right-most terminal
|
1990
|
+
symbol.</em> For example:
|
1991
|
+
|
1992
|
+
<blockquote>
|
1993
|
+
<pre>
|
1994
|
+
expression : expression PLUS expression # level = 1, left
|
1995
|
+
| expression MINUS expression # level = 1, left
|
1996
|
+
| expression TIMES expression # level = 2, left
|
1997
|
+
| expression DIVIDE expression # level = 2, left
|
1998
|
+
| LPAREN expression RPAREN # level = None (not specified)
|
1999
|
+
| NUMBER # level = None (not specified)
|
2000
|
+
</pre>
|
2001
|
+
</blockquote>
|
2002
|
+
|
2003
|
+
When shift/reduce conflicts are encountered, the parser generator resolves the conflict by
|
2004
|
+
looking at the precedence rules and associativity specifiers.
|
2005
|
+
|
2006
|
+
<p>
|
2007
|
+
<ol>
|
2008
|
+
<li>If the current token has higher precedence than the rule on the stack, it is shifted.
|
2009
|
+
<li>If the grammar rule on the stack has higher precedence, the rule is reduced.
|
2010
|
+
<li>If the current token and the grammar rule have the same precedence, the
|
2011
|
+
rule is reduced for left associativity, whereas the token is shifted for right associativity.
|
2012
|
+
<li>If nothing is known about the precedence, shift/reduce conflicts are resolved in
|
2013
|
+
favor of shifting (the default).
|
2014
|
+
</ol>
|
2015
|
+
|
2016
|
+
For example, if "expression PLUS expression" has been parsed and the
|
2017
|
+
next token is "TIMES", the action is going to be a shift because
|
2018
|
+
"TIMES" has a higher precedence level than "PLUS". On the other hand,
|
2019
|
+
if "expression TIMES expression" has been parsed and the next token is
|
2020
|
+
"PLUS", the action is going to be reduce because "PLUS" has a lower
|
2021
|
+
precedence than "TIMES."
|
2022
|
+
|
2023
|
+
<p>
|
2024
|
+
When shift/reduce conflicts are resolved using the first three
|
2025
|
+
techniques (with the help of precedence rules), <tt>yacc.py</tt> will
|
2026
|
+
report no errors or conflicts in the grammar (although it will print
|
2027
|
+
some information in the <tt>parser.out</tt> debugging file).
|
2028
|
+
|
2029
|
+
<p>
|
2030
|
+
One problem with the precedence specifier technique is that it is
|
2031
|
+
sometimes necessary to change the precedence of an operator in certain
|
2032
|
+
contexts. For example, consider a unary-minus operator in "3 + 4 *
|
2033
|
+
-5". Mathematically, the unary minus is normally given a very high
|
2034
|
+
precedence--being evaluated before the multiply. However, in our
|
2035
|
+
precedence specifier, MINUS has a lower precedence than TIMES. To
|
2036
|
+
deal with this, precedence rules can be given for so-called "fictitious tokens"
|
2037
|
+
like this:
|
2038
|
+
|
2039
|
+
<blockquote>
|
2040
|
+
<pre>
|
2041
|
+
precedence = (
|
2042
|
+
('left', 'PLUS', 'MINUS'),
|
2043
|
+
('left', 'TIMES', 'DIVIDE'),
|
2044
|
+
('right', 'UMINUS'), # Unary minus operator
|
2045
|
+
)
|
2046
|
+
</pre>
|
2047
|
+
</blockquote>
|
2048
|
+
|
2049
|
+
Now, in the grammar file, we can write our unary minus rule like this:
|
2050
|
+
|
2051
|
+
<blockquote>
|
2052
|
+
<pre>
|
2053
|
+
def p_expr_uminus(p):
|
2054
|
+
'expression : MINUS expression %prec UMINUS'
|
2055
|
+
p[0] = -p[2]
|
2056
|
+
</pre>
|
2057
|
+
</blockquote>
|
2058
|
+
|
2059
|
+
In this case, <tt>%prec UMINUS</tt> overrides the default rule precedence--setting it to that
|
2060
|
+
of UMINUS in the precedence specifier.
|
2061
|
+
|
2062
|
+
<p>
|
2063
|
+
At first, the use of UMINUS in this example may appear very confusing.
|
2064
|
+
UMINUS is not an input token or a grammer rule. Instead, you should
|
2065
|
+
think of it as the name of a special marker in the precedence table. When you use the <tt>%prec</tt> qualifier, you're simply
|
2066
|
+
telling yacc that you want the precedence of the expression to be the same as for this special marker instead of the usual precedence.
|
2067
|
+
|
2068
|
+
<p>
|
2069
|
+
It is also possible to specify non-associativity in the <tt>precedence</tt> table. This would
|
2070
|
+
be used when you <em>don't</em> want operations to chain together. For example, suppose
|
2071
|
+
you wanted to support comparison operators like <tt><</tt> and <tt>></tt> but you didn't want to allow
|
2072
|
+
combinations like <tt>a < b < c</tt>. To do this, simply specify a rule like this:
|
2073
|
+
|
2074
|
+
<blockquote>
|
2075
|
+
<pre>
|
2076
|
+
precedence = (
|
2077
|
+
('nonassoc', 'LESSTHAN', 'GREATERTHAN'), # Nonassociative operators
|
2078
|
+
('left', 'PLUS', 'MINUS'),
|
2079
|
+
('left', 'TIMES', 'DIVIDE'),
|
2080
|
+
('right', 'UMINUS'), # Unary minus operator
|
2081
|
+
)
|
2082
|
+
</pre>
|
2083
|
+
</blockquote>
|
2084
|
+
|
2085
|
+
<p>
|
2086
|
+
If you do this, the occurrence of input text such as <tt> a < b < c</tt> will result in a syntax error. However, simple
|
2087
|
+
expressions such as <tt>a < b</tt> will still be fine.
|
2088
|
+
|
2089
|
+
<p>
|
2090
|
+
Reduce/reduce conflicts are caused when there are multiple grammar
|
2091
|
+
rules that can be applied to a given set of symbols. This kind of
|
2092
|
+
conflict is almost always bad and is always resolved by picking the
|
2093
|
+
rule that appears first in the grammar file. Reduce/reduce conflicts
|
2094
|
+
are almost always caused when different sets of grammar rules somehow
|
2095
|
+
generate the same set of symbols. For example:
|
2096
|
+
|
2097
|
+
<blockquote>
|
2098
|
+
<pre>
|
2099
|
+
assignment : ID EQUALS NUMBER
|
2100
|
+
| ID EQUALS expression
|
2101
|
+
|
2102
|
+
expression : expression PLUS expression
|
2103
|
+
| expression MINUS expression
|
2104
|
+
| expression TIMES expression
|
2105
|
+
| expression DIVIDE expression
|
2106
|
+
| LPAREN expression RPAREN
|
2107
|
+
| NUMBER
|
2108
|
+
</pre>
|
2109
|
+
</blockquote>
|
2110
|
+
|
2111
|
+
In this case, a reduce/reduce conflict exists between these two rules:
|
2112
|
+
|
2113
|
+
<blockquote>
|
2114
|
+
<pre>
|
2115
|
+
assignment : ID EQUALS NUMBER
|
2116
|
+
expression : NUMBER
|
2117
|
+
</pre>
|
2118
|
+
</blockquote>
|
2119
|
+
|
2120
|
+
For example, if you wrote "a = 5", the parser can't figure out if this
|
2121
|
+
is supposed to be reduced as <tt>assignment : ID EQUALS NUMBER</tt> or
|
2122
|
+
whether it's supposed to reduce the 5 as an expression and then reduce
|
2123
|
+
the rule <tt>assignment : ID EQUALS expression</tt>.
|
2124
|
+
|
2125
|
+
<p>
|
2126
|
+
It should be noted that reduce/reduce conflicts are notoriously
|
2127
|
+
difficult to spot simply looking at the input grammer. When a
|
2128
|
+
reduce/reduce conflict occurs, <tt>yacc()</tt> will try to help by
|
2129
|
+
printing a warning message such as this:
|
2130
|
+
|
2131
|
+
<blockquote>
|
2132
|
+
<pre>
|
2133
|
+
WARNING: 1 reduce/reduce conflict
|
2134
|
+
WARNING: reduce/reduce conflict in state 15 resolved using rule (assignment -> ID EQUALS NUMBER)
|
2135
|
+
WARNING: rejected rule (expression -> NUMBER)
|
2136
|
+
</pre>
|
2137
|
+
</blockquote>
|
2138
|
+
|
2139
|
+
This message identifies the two rules that are in conflict. However,
|
2140
|
+
it may not tell you how the parser arrived at such a state. To try
|
2141
|
+
and figure it out, you'll probably have to look at your grammar and
|
2142
|
+
the contents of the
|
2143
|
+
<tt>parser.out</tt> debugging file with an appropriately high level of
|
2144
|
+
caffeination.
|
2145
|
+
|
2146
|
+
<H3><a name="ply_nn28"></a>6.7 The parser.out file</H3>
|
2147
|
+
|
2148
|
+
|
2149
|
+
Tracking down shift/reduce and reduce/reduce conflicts is one of the finer pleasures of using an LR
|
2150
|
+
parsing algorithm. To assist in debugging, <tt>yacc.py</tt> creates a debugging file called
|
2151
|
+
'parser.out' when it generates the parsing table. The contents of this file look like the following:
|
2152
|
+
|
2153
|
+
<blockquote>
|
2154
|
+
<pre>
|
2155
|
+
Unused terminals:
|
2156
|
+
|
2157
|
+
|
2158
|
+
Grammar
|
2159
|
+
|
2160
|
+
Rule 1 expression -> expression PLUS expression
|
2161
|
+
Rule 2 expression -> expression MINUS expression
|
2162
|
+
Rule 3 expression -> expression TIMES expression
|
2163
|
+
Rule 4 expression -> expression DIVIDE expression
|
2164
|
+
Rule 5 expression -> NUMBER
|
2165
|
+
Rule 6 expression -> LPAREN expression RPAREN
|
2166
|
+
|
2167
|
+
Terminals, with rules where they appear
|
2168
|
+
|
2169
|
+
TIMES : 3
|
2170
|
+
error :
|
2171
|
+
MINUS : 2
|
2172
|
+
RPAREN : 6
|
2173
|
+
LPAREN : 6
|
2174
|
+
DIVIDE : 4
|
2175
|
+
PLUS : 1
|
2176
|
+
NUMBER : 5
|
2177
|
+
|
2178
|
+
Nonterminals, with rules where they appear
|
2179
|
+
|
2180
|
+
expression : 1 1 2 2 3 3 4 4 6 0
|
2181
|
+
|
2182
|
+
|
2183
|
+
Parsing method: LALR
|
2184
|
+
|
2185
|
+
|
2186
|
+
state 0
|
2187
|
+
|
2188
|
+
S' -> . expression
|
2189
|
+
expression -> . expression PLUS expression
|
2190
|
+
expression -> . expression MINUS expression
|
2191
|
+
expression -> . expression TIMES expression
|
2192
|
+
expression -> . expression DIVIDE expression
|
2193
|
+
expression -> . NUMBER
|
2194
|
+
expression -> . LPAREN expression RPAREN
|
2195
|
+
|
2196
|
+
NUMBER shift and go to state 3
|
2197
|
+
LPAREN shift and go to state 2
|
2198
|
+
|
2199
|
+
|
2200
|
+
state 1
|
2201
|
+
|
2202
|
+
S' -> expression .
|
2203
|
+
expression -> expression . PLUS expression
|
2204
|
+
expression -> expression . MINUS expression
|
2205
|
+
expression -> expression . TIMES expression
|
2206
|
+
expression -> expression . DIVIDE expression
|
2207
|
+
|
2208
|
+
PLUS shift and go to state 6
|
2209
|
+
MINUS shift and go to state 5
|
2210
|
+
TIMES shift and go to state 4
|
2211
|
+
DIVIDE shift and go to state 7
|
2212
|
+
|
2213
|
+
|
2214
|
+
state 2
|
2215
|
+
|
2216
|
+
expression -> LPAREN . expression RPAREN
|
2217
|
+
expression -> . expression PLUS expression
|
2218
|
+
expression -> . expression MINUS expression
|
2219
|
+
expression -> . expression TIMES expression
|
2220
|
+
expression -> . expression DIVIDE expression
|
2221
|
+
expression -> . NUMBER
|
2222
|
+
expression -> . LPAREN expression RPAREN
|
2223
|
+
|
2224
|
+
NUMBER shift and go to state 3
|
2225
|
+
LPAREN shift and go to state 2
|
2226
|
+
|
2227
|
+
|
2228
|
+
state 3
|
2229
|
+
|
2230
|
+
expression -> NUMBER .
|
2231
|
+
|
2232
|
+
$ reduce using rule 5
|
2233
|
+
PLUS reduce using rule 5
|
2234
|
+
MINUS reduce using rule 5
|
2235
|
+
TIMES reduce using rule 5
|
2236
|
+
DIVIDE reduce using rule 5
|
2237
|
+
RPAREN reduce using rule 5
|
2238
|
+
|
2239
|
+
|
2240
|
+
state 4
|
2241
|
+
|
2242
|
+
expression -> expression TIMES . expression
|
2243
|
+
expression -> . expression PLUS expression
|
2244
|
+
expression -> . expression MINUS expression
|
2245
|
+
expression -> . expression TIMES expression
|
2246
|
+
expression -> . expression DIVIDE expression
|
2247
|
+
expression -> . NUMBER
|
2248
|
+
expression -> . LPAREN expression RPAREN
|
2249
|
+
|
2250
|
+
NUMBER shift and go to state 3
|
2251
|
+
LPAREN shift and go to state 2
|
2252
|
+
|
2253
|
+
|
2254
|
+
state 5
|
2255
|
+
|
2256
|
+
expression -> expression MINUS . expression
|
2257
|
+
expression -> . expression PLUS expression
|
2258
|
+
expression -> . expression MINUS expression
|
2259
|
+
expression -> . expression TIMES expression
|
2260
|
+
expression -> . expression DIVIDE expression
|
2261
|
+
expression -> . NUMBER
|
2262
|
+
expression -> . LPAREN expression RPAREN
|
2263
|
+
|
2264
|
+
NUMBER shift and go to state 3
|
2265
|
+
LPAREN shift and go to state 2
|
2266
|
+
|
2267
|
+
|
2268
|
+
state 6
|
2269
|
+
|
2270
|
+
expression -> expression PLUS . expression
|
2271
|
+
expression -> . expression PLUS expression
|
2272
|
+
expression -> . expression MINUS expression
|
2273
|
+
expression -> . expression TIMES expression
|
2274
|
+
expression -> . expression DIVIDE expression
|
2275
|
+
expression -> . NUMBER
|
2276
|
+
expression -> . LPAREN expression RPAREN
|
2277
|
+
|
2278
|
+
NUMBER shift and go to state 3
|
2279
|
+
LPAREN shift and go to state 2
|
2280
|
+
|
2281
|
+
|
2282
|
+
state 7
|
2283
|
+
|
2284
|
+
expression -> expression DIVIDE . expression
|
2285
|
+
expression -> . expression PLUS expression
|
2286
|
+
expression -> . expression MINUS expression
|
2287
|
+
expression -> . expression TIMES expression
|
2288
|
+
expression -> . expression DIVIDE expression
|
2289
|
+
expression -> . NUMBER
|
2290
|
+
expression -> . LPAREN expression RPAREN
|
2291
|
+
|
2292
|
+
NUMBER shift and go to state 3
|
2293
|
+
LPAREN shift and go to state 2
|
2294
|
+
|
2295
|
+
|
2296
|
+
state 8
|
2297
|
+
|
2298
|
+
expression -> LPAREN expression . RPAREN
|
2299
|
+
expression -> expression . PLUS expression
|
2300
|
+
expression -> expression . MINUS expression
|
2301
|
+
expression -> expression . TIMES expression
|
2302
|
+
expression -> expression . DIVIDE expression
|
2303
|
+
|
2304
|
+
RPAREN shift and go to state 13
|
2305
|
+
PLUS shift and go to state 6
|
2306
|
+
MINUS shift and go to state 5
|
2307
|
+
TIMES shift and go to state 4
|
2308
|
+
DIVIDE shift and go to state 7
|
2309
|
+
|
2310
|
+
|
2311
|
+
state 9
|
2312
|
+
|
2313
|
+
expression -> expression TIMES expression .
|
2314
|
+
expression -> expression . PLUS expression
|
2315
|
+
expression -> expression . MINUS expression
|
2316
|
+
expression -> expression . TIMES expression
|
2317
|
+
expression -> expression . DIVIDE expression
|
2318
|
+
|
2319
|
+
$ reduce using rule 3
|
2320
|
+
PLUS reduce using rule 3
|
2321
|
+
MINUS reduce using rule 3
|
2322
|
+
TIMES reduce using rule 3
|
2323
|
+
DIVIDE reduce using rule 3
|
2324
|
+
RPAREN reduce using rule 3
|
2325
|
+
|
2326
|
+
! PLUS [ shift and go to state 6 ]
|
2327
|
+
! MINUS [ shift and go to state 5 ]
|
2328
|
+
! TIMES [ shift and go to state 4 ]
|
2329
|
+
! DIVIDE [ shift and go to state 7 ]
|
2330
|
+
|
2331
|
+
state 10
|
2332
|
+
|
2333
|
+
expression -> expression MINUS expression .
|
2334
|
+
expression -> expression . PLUS expression
|
2335
|
+
expression -> expression . MINUS expression
|
2336
|
+
expression -> expression . TIMES expression
|
2337
|
+
expression -> expression . DIVIDE expression
|
2338
|
+
|
2339
|
+
$ reduce using rule 2
|
2340
|
+
PLUS reduce using rule 2
|
2341
|
+
MINUS reduce using rule 2
|
2342
|
+
RPAREN reduce using rule 2
|
2343
|
+
TIMES shift and go to state 4
|
2344
|
+
DIVIDE shift and go to state 7
|
2345
|
+
|
2346
|
+
! TIMES [ reduce using rule 2 ]
|
2347
|
+
! DIVIDE [ reduce using rule 2 ]
|
2348
|
+
! PLUS [ shift and go to state 6 ]
|
2349
|
+
! MINUS [ shift and go to state 5 ]
|
2350
|
+
|
2351
|
+
state 11
|
2352
|
+
|
2353
|
+
expression -> expression PLUS expression .
|
2354
|
+
expression -> expression . PLUS expression
|
2355
|
+
expression -> expression . MINUS expression
|
2356
|
+
expression -> expression . TIMES expression
|
2357
|
+
expression -> expression . DIVIDE expression
|
2358
|
+
|
2359
|
+
$ reduce using rule 1
|
2360
|
+
PLUS reduce using rule 1
|
2361
|
+
MINUS reduce using rule 1
|
2362
|
+
RPAREN reduce using rule 1
|
2363
|
+
TIMES shift and go to state 4
|
2364
|
+
DIVIDE shift and go to state 7
|
2365
|
+
|
2366
|
+
! TIMES [ reduce using rule 1 ]
|
2367
|
+
! DIVIDE [ reduce using rule 1 ]
|
2368
|
+
! PLUS [ shift and go to state 6 ]
|
2369
|
+
! MINUS [ shift and go to state 5 ]
|
2370
|
+
|
2371
|
+
state 12
|
2372
|
+
|
2373
|
+
expression -> expression DIVIDE expression .
|
2374
|
+
expression -> expression . PLUS expression
|
2375
|
+
expression -> expression . MINUS expression
|
2376
|
+
expression -> expression . TIMES expression
|
2377
|
+
expression -> expression . DIVIDE expression
|
2378
|
+
|
2379
|
+
$ reduce using rule 4
|
2380
|
+
PLUS reduce using rule 4
|
2381
|
+
MINUS reduce using rule 4
|
2382
|
+
TIMES reduce using rule 4
|
2383
|
+
DIVIDE reduce using rule 4
|
2384
|
+
RPAREN reduce using rule 4
|
2385
|
+
|
2386
|
+
! PLUS [ shift and go to state 6 ]
|
2387
|
+
! MINUS [ shift and go to state 5 ]
|
2388
|
+
! TIMES [ shift and go to state 4 ]
|
2389
|
+
! DIVIDE [ shift and go to state 7 ]
|
2390
|
+
|
2391
|
+
state 13
|
2392
|
+
|
2393
|
+
expression -> LPAREN expression RPAREN .
|
2394
|
+
|
2395
|
+
$ reduce using rule 6
|
2396
|
+
PLUS reduce using rule 6
|
2397
|
+
MINUS reduce using rule 6
|
2398
|
+
TIMES reduce using rule 6
|
2399
|
+
DIVIDE reduce using rule 6
|
2400
|
+
RPAREN reduce using rule 6
|
2401
|
+
</pre>
|
2402
|
+
</blockquote>
|
2403
|
+
|
2404
|
+
The different states that appear in this file are a representation of
|
2405
|
+
every possible sequence of valid input tokens allowed by the grammar.
|
2406
|
+
When receiving input tokens, the parser is building up a stack and
|
2407
|
+
looking for matching rules. Each state keeps track of the grammar
|
2408
|
+
rules that might be in the process of being matched at that point. Within each
|
2409
|
+
rule, the "." character indicates the current location of the parse
|
2410
|
+
within that rule. In addition, the actions for each valid input token
|
2411
|
+
are listed. When a shift/reduce or reduce/reduce conflict arises,
|
2412
|
+
rules <em>not</em> selected are prefixed with an !. For example:
|
2413
|
+
|
2414
|
+
<blockquote>
|
2415
|
+
<pre>
|
2416
|
+
! TIMES [ reduce using rule 2 ]
|
2417
|
+
! DIVIDE [ reduce using rule 2 ]
|
2418
|
+
! PLUS [ shift and go to state 6 ]
|
2419
|
+
! MINUS [ shift and go to state 5 ]
|
2420
|
+
</pre>
|
2421
|
+
</blockquote>
|
2422
|
+
|
2423
|
+
By looking at these rules (and with a little practice), you can usually track down the source
|
2424
|
+
of most parsing conflicts. It should also be stressed that not all shift-reduce conflicts are
|
2425
|
+
bad. However, the only way to be sure that they are resolved correctly is to look at <tt>parser.out</tt>.
|
2426
|
+
|
2427
|
+
<H3><a name="ply_nn29"></a>6.8 Syntax Error Handling</H3>
|
2428
|
+
|
2429
|
+
|
2430
|
+
If you are creating a parser for production use, the handling of
|
2431
|
+
syntax errors is important. As a general rule, you don't want a
|
2432
|
+
parser to simply throw up its hands and stop at the first sign of
|
2433
|
+
trouble. Instead, you want it to report the error, recover if possible, and
|
2434
|
+
continue parsing so that all of the errors in the input get reported
|
2435
|
+
to the user at once. This is the standard behavior found in compilers
|
2436
|
+
for languages such as C, C++, and Java.
|
2437
|
+
|
2438
|
+
In PLY, when a syntax error occurs during parsing, the error is immediately
|
2439
|
+
detected (i.e., the parser does not read any more tokens beyond the
|
2440
|
+
source of the error). However, at this point, the parser enters a
|
2441
|
+
recovery mode that can be used to try and continue further parsing.
|
2442
|
+
As a general rule, error recovery in LR parsers is a delicate
|
2443
|
+
topic that involves ancient rituals and black-magic. The recovery mechanism
|
2444
|
+
provided by <tt>yacc.py</tt> is comparable to Unix yacc so you may want
|
2445
|
+
consult a book like O'Reilly's "Lex and Yacc" for some of the finer details.
|
2446
|
+
|
2447
|
+
<p>
|
2448
|
+
When a syntax error occurs, <tt>yacc.py</tt> performs the following steps:
|
2449
|
+
|
2450
|
+
<ol>
|
2451
|
+
<li>On the first occurrence of an error, the user-defined <tt>p_error()</tt> function
|
2452
|
+
is called with the offending token as an argument. However, if the syntax error is due to
|
2453
|
+
reaching the end-of-file, <tt>p_error()</tt> is called with an argument of <tt>None</tt>.
|
2454
|
+
Afterwards, the parser enters
|
2455
|
+
an "error-recovery" mode in which it will not make future calls to <tt>p_error()</tt> until it
|
2456
|
+
has successfully shifted at least 3 tokens onto the parsing stack.
|
2457
|
+
|
2458
|
+
<p>
|
2459
|
+
<li>If no recovery action is taken in <tt>p_error()</tt>, the offending lookahead token is replaced
|
2460
|
+
with a special <tt>error</tt> token.
|
2461
|
+
|
2462
|
+
<p>
|
2463
|
+
<li>If the offending lookahead token is already set to <tt>error</tt>, the top item of the parsing stack is
|
2464
|
+
deleted.
|
2465
|
+
|
2466
|
+
<p>
|
2467
|
+
<li>If the entire parsing stack is unwound, the parser enters a restart state and attempts to start
|
2468
|
+
parsing from its initial state.
|
2469
|
+
|
2470
|
+
<p>
|
2471
|
+
<li>If a grammar rule accepts <tt>error</tt> as a token, it will be
|
2472
|
+
shifted onto the parsing stack.
|
2473
|
+
|
2474
|
+
<p>
|
2475
|
+
<li>If the top item of the parsing stack is <tt>error</tt>, lookahead tokens will be discarded until the
|
2476
|
+
parser can successfully shift a new symbol or reduce a rule involving <tt>error</tt>.
|
2477
|
+
</ol>
|
2478
|
+
|
2479
|
+
<H4><a name="ply_nn30"></a>6.8.1 Recovery and resynchronization with error rules</H4>
|
2480
|
+
|
2481
|
+
|
2482
|
+
The most well-behaved approach for handling syntax errors is to write grammar rules that include the <tt>error</tt>
|
2483
|
+
token. For example, suppose your language had a grammar rule for a print statement like this:
|
2484
|
+
|
2485
|
+
<blockquote>
|
2486
|
+
<pre>
|
2487
|
+
def p_statement_print(p):
|
2488
|
+
'statement : PRINT expr SEMI'
|
2489
|
+
...
|
2490
|
+
</pre>
|
2491
|
+
</blockquote>
|
2492
|
+
|
2493
|
+
To account for the possibility of a bad expression, you might write an additional grammar rule like this:
|
2494
|
+
|
2495
|
+
<blockquote>
|
2496
|
+
<pre>
|
2497
|
+
def p_statement_print_error(p):
|
2498
|
+
'statement : PRINT error SEMI'
|
2499
|
+
print "Syntax error in print statement. Bad expression"
|
2500
|
+
|
2501
|
+
</pre>
|
2502
|
+
</blockquote>
|
2503
|
+
|
2504
|
+
In this case, the <tt>error</tt> token will match any sequence of
|
2505
|
+
tokens that might appear up to the first semicolon that is
|
2506
|
+
encountered. Once the semicolon is reached, the rule will be
|
2507
|
+
invoked and the <tt>error</tt> token will go away.
|
2508
|
+
|
2509
|
+
<p>
|
2510
|
+
This type of recovery is sometimes known as parser resynchronization.
|
2511
|
+
The <tt>error</tt> token acts as a wildcard for any bad input text and
|
2512
|
+
the token immediately following <tt>error</tt> acts as a
|
2513
|
+
synchronization token.
|
2514
|
+
|
2515
|
+
<p>
|
2516
|
+
It is important to note that the <tt>error</tt> token usually does not appear as the last token
|
2517
|
+
on the right in an error rule. For example:
|
2518
|
+
|
2519
|
+
<blockquote>
|
2520
|
+
<pre>
|
2521
|
+
def p_statement_print_error(p):
|
2522
|
+
'statement : PRINT error'
|
2523
|
+
print "Syntax error in print statement. Bad expression"
|
2524
|
+
</pre>
|
2525
|
+
</blockquote>
|
2526
|
+
|
2527
|
+
This is because the first bad token encountered will cause the rule to
|
2528
|
+
be reduced--which may make it difficult to recover if more bad tokens
|
2529
|
+
immediately follow.
|
2530
|
+
|
2531
|
+
<H4><a name="ply_nn31"></a>6.8.2 Panic mode recovery</H4>
|
2532
|
+
|
2533
|
+
|
2534
|
+
An alternative error recovery scheme is to enter a panic mode recovery in which tokens are
|
2535
|
+
discarded to a point where the parser might be able to recover in some sensible manner.
|
2536
|
+
|
2537
|
+
<p>
|
2538
|
+
Panic mode recovery is implemented entirely in the <tt>p_error()</tt> function. For example, this
|
2539
|
+
function starts discarding tokens until it reaches a closing '}'. Then, it restarts the
|
2540
|
+
parser in its initial state.
|
2541
|
+
|
2542
|
+
<blockquote>
|
2543
|
+
<pre>
|
2544
|
+
def p_error(p):
|
2545
|
+
print "Whoa. You are seriously hosed."
|
2546
|
+
# Read ahead looking for a closing '}'
|
2547
|
+
while 1:
|
2548
|
+
tok = yacc.token() # Get the next token
|
2549
|
+
if not tok or tok.type == 'RBRACE': break
|
2550
|
+
yacc.restart()
|
2551
|
+
</pre>
|
2552
|
+
</blockquote>
|
2553
|
+
|
2554
|
+
<p>
|
2555
|
+
This function simply discards the bad token and tells the parser that the error was ok.
|
2556
|
+
|
2557
|
+
<blockquote>
|
2558
|
+
<pre>
|
2559
|
+
def p_error(p):
|
2560
|
+
print "Syntax error at token", p.type
|
2561
|
+
# Just discard the token and tell the parser it's okay.
|
2562
|
+
yacc.errok()
|
2563
|
+
</pre>
|
2564
|
+
</blockquote>
|
2565
|
+
|
2566
|
+
<P>
|
2567
|
+
Within the <tt>p_error()</tt> function, three functions are available to control the behavior
|
2568
|
+
of the parser:
|
2569
|
+
<p>
|
2570
|
+
<ul>
|
2571
|
+
<li><tt>yacc.errok()</tt>. This resets the parser state so it doesn't think it's in error-recovery
|
2572
|
+
mode. This will prevent an <tt>error</tt> token from being generated and will reset the internal
|
2573
|
+
error counters so that the next syntax error will call <tt>p_error()</tt> again.
|
2574
|
+
|
2575
|
+
<p>
|
2576
|
+
<li><tt>yacc.token()</tt>. This returns the next token on the input stream.
|
2577
|
+
|
2578
|
+
<p>
|
2579
|
+
<li><tt>yacc.restart()</tt>. This discards the entire parsing stack and resets the parser
|
2580
|
+
to its initial state.
|
2581
|
+
</ul>
|
2582
|
+
|
2583
|
+
Note: these functions are only available when invoking <tt>p_error()</tt> and are not available
|
2584
|
+
at any other time.
|
2585
|
+
|
2586
|
+
<p>
|
2587
|
+
To supply the next lookahead token to the parser, <tt>p_error()</tt> can return a token. This might be
|
2588
|
+
useful if trying to synchronize on special characters. For example:
|
2589
|
+
|
2590
|
+
<blockquote>
|
2591
|
+
<pre>
|
2592
|
+
def p_error(p):
|
2593
|
+
# Read ahead looking for a terminating ";"
|
2594
|
+
while 1:
|
2595
|
+
tok = yacc.token() # Get the next token
|
2596
|
+
if not tok or tok.type == 'SEMI': break
|
2597
|
+
yacc.errok()
|
2598
|
+
|
2599
|
+
# Return SEMI to the parser as the next lookahead token
|
2600
|
+
return tok
|
2601
|
+
</pre>
|
2602
|
+
</blockquote>
|
2603
|
+
|
2604
|
+
<H4><a name="ply_nn35"></a>6.8.3 Signaling an error from a production</H4>
|
2605
|
+
|
2606
|
+
|
2607
|
+
If necessary, a production rule can manually force the parser to enter error recovery. This
|
2608
|
+
is done by raising the <tt>SyntaxError</tt> exception like this:
|
2609
|
+
|
2610
|
+
<blockquote>
|
2611
|
+
<pre>
|
2612
|
+
def p_production(p):
|
2613
|
+
'production : some production ...'
|
2614
|
+
raise SyntaxError
|
2615
|
+
</pre>
|
2616
|
+
</blockquote>
|
2617
|
+
|
2618
|
+
The effect of raising <tt>SyntaxError</tt> is the same as if the last symbol shifted onto the
|
2619
|
+
parsing stack was actually a syntax error. Thus, when you do this, the last symbol shifted is popped off
|
2620
|
+
of the parsing stack and the current lookahead token is set to an <tt>error</tt> token. The parser
|
2621
|
+
then enters error-recovery mode where it tries to reduce rules that can accept <tt>error</tt> tokens.
|
2622
|
+
The steps that follow from this point are exactly the same as if a syntax error were detected and
|
2623
|
+
<tt>p_error()</tt> were called.
|
2624
|
+
|
2625
|
+
<P>
|
2626
|
+
One important aspect of manually setting an error is that the <tt>p_error()</tt> function will <b>NOT</b> be
|
2627
|
+
called in this case. If you need to issue an error message, make sure you do it in the production that
|
2628
|
+
raises <tt>SyntaxError</tt>.
|
2629
|
+
|
2630
|
+
<P>
|
2631
|
+
Note: This feature of PLY is meant to mimic the behavior of the YYERROR macro in yacc.
|
2632
|
+
|
2633
|
+
|
2634
|
+
<H4><a name="ply_nn32"></a>6.8.4 General comments on error handling</H4>
|
2635
|
+
|
2636
|
+
|
2637
|
+
For normal types of languages, error recovery with error rules and resynchronization characters is probably the most reliable
|
2638
|
+
technique. This is because you can instrument the grammar to catch errors at selected places where it is relatively easy
|
2639
|
+
to recover and continue parsing. Panic mode recovery is really only useful in certain specialized applications where you might want
|
2640
|
+
to discard huge portions of the input text to find a valid restart point.
|
2641
|
+
|
2642
|
+
<H3><a name="ply_nn33"></a>6.9 Line Number and Position Tracking</H3>
|
2643
|
+
|
2644
|
+
|
2645
|
+
Position tracking is often a tricky problem when writing compilers.
|
2646
|
+
By default, PLY tracks the line number and position of all tokens.
|
2647
|
+
This information is available using the following functions:
|
2648
|
+
|
2649
|
+
<ul>
|
2650
|
+
<li><tt>p.lineno(num)</tt>. Return the line number for symbol <em>num</em>
|
2651
|
+
<li><tt>p.lexpos(num)</tt>. Return the lexing position for symbol <em>num</em>
|
2652
|
+
</ul>
|
2653
|
+
|
2654
|
+
For example:
|
2655
|
+
|
2656
|
+
<blockquote>
|
2657
|
+
<pre>
|
2658
|
+
def p_expression(p):
|
2659
|
+
'expression : expression PLUS expression'
|
2660
|
+
line = p.lineno(2) # line number of the PLUS token
|
2661
|
+
index = p.lexpos(2) # Position of the PLUS token
|
2662
|
+
</pre>
|
2663
|
+
</blockquote>
|
2664
|
+
|
2665
|
+
As an optional feature, <tt>yacc.py</tt> can automatically track line
|
2666
|
+
numbers and positions for all of the grammar symbols as well.
|
2667
|
+
However, this extra tracking requires extra processing and can
|
2668
|
+
significantly slow down parsing. Therefore, it must be enabled by
|
2669
|
+
passing the
|
2670
|
+
<tt>tracking=True</tt> option to <tt>yacc.parse()</tt>. For example:
|
2671
|
+
|
2672
|
+
<blockquote>
|
2673
|
+
<pre>
|
2674
|
+
yacc.parse(data,tracking=True)
|
2675
|
+
</pre>
|
2676
|
+
</blockquote>
|
2677
|
+
|
2678
|
+
Once enabled, the <tt>lineno()</tt> and <tt>lexpos()</tt> methods work
|
2679
|
+
for all grammar symbols. In addition, two additional methods can be
|
2680
|
+
used:
|
2681
|
+
|
2682
|
+
<ul>
|
2683
|
+
<li><tt>p.linespan(num)</tt>. Return a tuple (startline,endline) with the starting and ending line number for symbol <em>num</em>.
|
2684
|
+
<li><tt>p.lexspan(num)</tt>. Return a tuple (start,end) with the starting and ending positions for symbol <em>num</em>.
|
2685
|
+
</ul>
|
2686
|
+
|
2687
|
+
For example:
|
2688
|
+
|
2689
|
+
<blockquote>
|
2690
|
+
<pre>
|
2691
|
+
def p_expression(p):
|
2692
|
+
'expression : expression PLUS expression'
|
2693
|
+
p.lineno(1) # Line number of the left expression
|
2694
|
+
p.lineno(2) # line number of the PLUS operator
|
2695
|
+
p.lineno(3) # line number of the right expression
|
2696
|
+
...
|
2697
|
+
start,end = p.linespan(3) # Start,end lines of the right expression
|
2698
|
+
starti,endi = p.lexspan(3) # Start,end positions of right expression
|
2699
|
+
|
2700
|
+
</pre>
|
2701
|
+
</blockquote>
|
2702
|
+
|
2703
|
+
Note: The <tt>lexspan()</tt> function only returns the range of values up to the start of the last grammar symbol.
|
2704
|
+
|
2705
|
+
<p>
|
2706
|
+
Although it may be convenient for PLY to track position information on
|
2707
|
+
all grammar symbols, this is often unnecessary. For example, if you
|
2708
|
+
are merely using line number information in an error message, you can
|
2709
|
+
often just key off of a specific token in the grammar rule. For
|
2710
|
+
example:
|
2711
|
+
|
2712
|
+
<blockquote>
|
2713
|
+
<pre>
|
2714
|
+
def p_bad_func(p):
|
2715
|
+
'funccall : fname LPAREN error RPAREN'
|
2716
|
+
# Line number reported from LPAREN token
|
2717
|
+
print "Bad function call at line", p.lineno(2)
|
2718
|
+
</pre>
|
2719
|
+
</blockquote>
|
2720
|
+
|
2721
|
+
<p>
|
2722
|
+
Similarly, you may get better parsing performance if you only
|
2723
|
+
selectively propagate line number information where it's needed using
|
2724
|
+
the <tt>p.set_lineno()</tt> method. For example:
|
2725
|
+
|
2726
|
+
<blockquote>
|
2727
|
+
<pre>
|
2728
|
+
def p_fname(p):
|
2729
|
+
'fname : ID'
|
2730
|
+
p[0] = p[1]
|
2731
|
+
p.set_lineno(0,p.lineno(1))
|
2732
|
+
</pre>
|
2733
|
+
</blockquote>
|
2734
|
+
|
2735
|
+
PLY doesn't retain line number information from rules that have already been
|
2736
|
+
parsed. If you are building an abstract syntax tree and need to have line numbers,
|
2737
|
+
you should make sure that the line numbers appear in the tree itself.
|
2738
|
+
|
2739
|
+
<H3><a name="ply_nn34"></a>6.10 AST Construction</H3>
|
2740
|
+
|
2741
|
+
|
2742
|
+
<tt>yacc.py</tt> provides no special functions for constructing an
|
2743
|
+
abstract syntax tree. However, such construction is easy enough to do
|
2744
|
+
on your own.
|
2745
|
+
|
2746
|
+
<p>A minimal way to construct a tree is to simply create and
|
2747
|
+
propagate a tuple or list in each grammar rule function. There
|
2748
|
+
are many possible ways to do this, but one example would be something
|
2749
|
+
like this:
|
2750
|
+
|
2751
|
+
<blockquote>
|
2752
|
+
<pre>
|
2753
|
+
def p_expression_binop(p):
|
2754
|
+
'''expression : expression PLUS expression
|
2755
|
+
| expression MINUS expression
|
2756
|
+
| expression TIMES expression
|
2757
|
+
| expression DIVIDE expression'''
|
2758
|
+
|
2759
|
+
p[0] = ('binary-expression',p[2],p[1],p[3])
|
2760
|
+
|
2761
|
+
def p_expression_group(p):
|
2762
|
+
'expression : LPAREN expression RPAREN'
|
2763
|
+
p[0] = ('group-expression',p[2])
|
2764
|
+
|
2765
|
+
def p_expression_number(p):
|
2766
|
+
'expression : NUMBER'
|
2767
|
+
p[0] = ('number-expression',p[1])
|
2768
|
+
</pre>
|
2769
|
+
</blockquote>
|
2770
|
+
|
2771
|
+
<p>
|
2772
|
+
Another approach is to create a set of data structure for different
|
2773
|
+
kinds of abstract syntax tree nodes and assign nodes to <tt>p[0]</tt>
|
2774
|
+
in each rule. For example:
|
2775
|
+
|
2776
|
+
<blockquote>
|
2777
|
+
<pre>
|
2778
|
+
class Expr: pass
|
2779
|
+
|
2780
|
+
class BinOp(Expr):
|
2781
|
+
def __init__(self,left,op,right):
|
2782
|
+
self.type = "binop"
|
2783
|
+
self.left = left
|
2784
|
+
self.right = right
|
2785
|
+
self.op = op
|
2786
|
+
|
2787
|
+
class Number(Expr):
|
2788
|
+
def __init__(self,value):
|
2789
|
+
self.type = "number"
|
2790
|
+
self.value = value
|
2791
|
+
|
2792
|
+
def p_expression_binop(p):
|
2793
|
+
'''expression : expression PLUS expression
|
2794
|
+
| expression MINUS expression
|
2795
|
+
| expression TIMES expression
|
2796
|
+
| expression DIVIDE expression'''
|
2797
|
+
|
2798
|
+
p[0] = BinOp(p[1],p[2],p[3])
|
2799
|
+
|
2800
|
+
def p_expression_group(p):
|
2801
|
+
'expression : LPAREN expression RPAREN'
|
2802
|
+
p[0] = p[2]
|
2803
|
+
|
2804
|
+
def p_expression_number(p):
|
2805
|
+
'expression : NUMBER'
|
2806
|
+
p[0] = Number(p[1])
|
2807
|
+
</pre>
|
2808
|
+
</blockquote>
|
2809
|
+
|
2810
|
+
The advantage to this approach is that it may make it easier to attach more complicated
|
2811
|
+
semantics, type checking, code generation, and other features to the node classes.
|
2812
|
+
|
2813
|
+
<p>
|
2814
|
+
To simplify tree traversal, it may make sense to pick a very generic
|
2815
|
+
tree structure for your parse tree nodes. For example:
|
2816
|
+
|
2817
|
+
<blockquote>
|
2818
|
+
<pre>
|
2819
|
+
class Node:
|
2820
|
+
def __init__(self,type,children=None,leaf=None):
|
2821
|
+
self.type = type
|
2822
|
+
if children:
|
2823
|
+
self.children = children
|
2824
|
+
else:
|
2825
|
+
self.children = [ ]
|
2826
|
+
self.leaf = leaf
|
2827
|
+
|
2828
|
+
def p_expression_binop(p):
|
2829
|
+
'''expression : expression PLUS expression
|
2830
|
+
| expression MINUS expression
|
2831
|
+
| expression TIMES expression
|
2832
|
+
| expression DIVIDE expression'''
|
2833
|
+
|
2834
|
+
p[0] = Node("binop", [p[1],p[3]], p[2])
|
2835
|
+
</pre>
|
2836
|
+
</blockquote>
|
2837
|
+
|
2838
|
+
<H3><a name="ply_nn35"></a>6.11 Embedded Actions</H3>
|
2839
|
+
|
2840
|
+
|
2841
|
+
The parsing technique used by yacc only allows actions to be executed at the end of a rule. For example,
|
2842
|
+
suppose you have a rule like this:
|
2843
|
+
|
2844
|
+
<blockquote>
|
2845
|
+
<pre>
|
2846
|
+
def p_foo(p):
|
2847
|
+
"foo : A B C D"
|
2848
|
+
print "Parsed a foo", p[1],p[2],p[3],p[4]
|
2849
|
+
</pre>
|
2850
|
+
</blockquote>
|
2851
|
+
|
2852
|
+
<p>
|
2853
|
+
In this case, the supplied action code only executes after all of the
|
2854
|
+
symbols <tt>A</tt>, <tt>B</tt>, <tt>C</tt>, and <tt>D</tt> have been
|
2855
|
+
parsed. Sometimes, however, it is useful to execute small code
|
2856
|
+
fragments during intermediate stages of parsing. For example, suppose
|
2857
|
+
you wanted to perform some action immediately after <tt>A</tt> has
|
2858
|
+
been parsed. To do this, write an empty rule like this:
|
2859
|
+
|
2860
|
+
<blockquote>
|
2861
|
+
<pre>
|
2862
|
+
def p_foo(p):
|
2863
|
+
"foo : A seen_A B C D"
|
2864
|
+
print "Parsed a foo", p[1],p[3],p[4],p[5]
|
2865
|
+
print "seen_A returned", p[2]
|
2866
|
+
|
2867
|
+
def p_seen_A(p):
|
2868
|
+
"seen_A :"
|
2869
|
+
print "Saw an A = ", p[-1] # Access grammar symbol to left
|
2870
|
+
p[0] = some_value # Assign value to seen_A
|
2871
|
+
|
2872
|
+
</pre>
|
2873
|
+
</blockquote>
|
2874
|
+
|
2875
|
+
<p>
|
2876
|
+
In this example, the empty <tt>seen_A</tt> rule executes immediately
|
2877
|
+
after <tt>A</tt> is shifted onto the parsing stack. Within this
|
2878
|
+
rule, <tt>p[-1]</tt> refers to the symbol on the stack that appears
|
2879
|
+
immediately to the left of the <tt>seen_A</tt> symbol. In this case,
|
2880
|
+
it would be the value of <tt>A</tt> in the <tt>foo</tt> rule
|
2881
|
+
immediately above. Like other rules, a value can be returned from an
|
2882
|
+
embedded action by simply assigning it to <tt>p[0]</tt>
|
2883
|
+
|
2884
|
+
<p>
|
2885
|
+
The use of embedded actions can sometimes introduce extra shift/reduce conflicts. For example,
|
2886
|
+
this grammar has no conflicts:
|
2887
|
+
|
2888
|
+
<blockquote>
|
2889
|
+
<pre>
|
2890
|
+
def p_foo(p):
|
2891
|
+
"""foo : abcd
|
2892
|
+
| abcx"""
|
2893
|
+
|
2894
|
+
def p_abcd(p):
|
2895
|
+
"abcd : A B C D"
|
2896
|
+
|
2897
|
+
def p_abcx(p):
|
2898
|
+
"abcx : A B C X"
|
2899
|
+
</pre>
|
2900
|
+
</blockquote>
|
2901
|
+
|
2902
|
+
However, if you insert an embedded action into one of the rules like this,
|
2903
|
+
|
2904
|
+
<blockquote>
|
2905
|
+
<pre>
|
2906
|
+
def p_foo(p):
|
2907
|
+
"""foo : abcd
|
2908
|
+
| abcx"""
|
2909
|
+
|
2910
|
+
def p_abcd(p):
|
2911
|
+
"abcd : A B C D"
|
2912
|
+
|
2913
|
+
def p_abcx(p):
|
2914
|
+
"abcx : A B seen_AB C X"
|
2915
|
+
|
2916
|
+
def p_seen_AB(p):
|
2917
|
+
"seen_AB :"
|
2918
|
+
</pre>
|
2919
|
+
</blockquote>
|
2920
|
+
|
2921
|
+
an extra shift-reduce conflict will be introduced. This conflict is
|
2922
|
+
caused by the fact that the same symbol <tt>C</tt> appears next in
|
2923
|
+
both the <tt>abcd</tt> and <tt>abcx</tt> rules. The parser can either
|
2924
|
+
shift the symbol (<tt>abcd</tt> rule) or reduce the empty
|
2925
|
+
rule <tt>seen_AB</tt> (<tt>abcx</tt> rule).
|
2926
|
+
|
2927
|
+
<p>
|
2928
|
+
A common use of embedded rules is to control other aspects of parsing
|
2929
|
+
such as scoping of local variables. For example, if you were parsing C code, you might
|
2930
|
+
write code like this:
|
2931
|
+
|
2932
|
+
<blockquote>
|
2933
|
+
<pre>
|
2934
|
+
def p_statements_block(p):
|
2935
|
+
"statements: LBRACE new_scope statements RBRACE"""
|
2936
|
+
# Action code
|
2937
|
+
...
|
2938
|
+
pop_scope() # Return to previous scope
|
2939
|
+
|
2940
|
+
def p_new_scope(p):
|
2941
|
+
"new_scope :"
|
2942
|
+
# Create a new scope for local variables
|
2943
|
+
s = new_scope()
|
2944
|
+
push_scope(s)
|
2945
|
+
...
|
2946
|
+
</pre>
|
2947
|
+
</blockquote>
|
2948
|
+
|
2949
|
+
In this case, the embedded action <tt>new_scope</tt> executes
|
2950
|
+
immediately after a <tt>LBRACE</tt> (<tt>{</tt>) symbol is parsed.
|
2951
|
+
This might adjust internal symbol tables and other aspects of the
|
2952
|
+
parser. Upon completion of the rule <tt>statements_block</tt>, code
|
2953
|
+
might undo the operations performed in the embedded action
|
2954
|
+
(e.g., <tt>pop_scope()</tt>).
|
2955
|
+
|
2956
|
+
<H3><a name="ply_nn36"></a>6.12 Miscellaneous Yacc Notes</H3>
|
2957
|
+
|
2958
|
+
|
2959
|
+
<ul>
|
2960
|
+
<li>The default parsing method is LALR. To use SLR instead, run yacc() as follows:
|
2961
|
+
|
2962
|
+
<blockquote>
|
2963
|
+
<pre>
|
2964
|
+
yacc.yacc(method="SLR")
|
2965
|
+
</pre>
|
2966
|
+
</blockquote>
|
2967
|
+
Note: LALR table generation takes approximately twice as long as SLR table generation. There is no
|
2968
|
+
difference in actual parsing performance---the same code is used in both cases. LALR is preferred when working
|
2969
|
+
with more complicated grammars since it is more powerful.
|
2970
|
+
|
2971
|
+
<p>
|
2972
|
+
|
2973
|
+
<li>By default, <tt>yacc.py</tt> relies on <tt>lex.py</tt> for tokenizing. However, an alternative tokenizer
|
2974
|
+
can be supplied as follows:
|
2975
|
+
|
2976
|
+
<blockquote>
|
2977
|
+
<pre>
|
2978
|
+
yacc.parse(lexer=x)
|
2979
|
+
</pre>
|
2980
|
+
</blockquote>
|
2981
|
+
in this case, <tt>x</tt> must be a Lexer object that minimally has a <tt>x.token()</tt> method for retrieving the next
|
2982
|
+
token. If an input string is given to <tt>yacc.parse()</tt>, the lexer must also have an <tt>x.input()</tt> method.
|
2983
|
+
|
2984
|
+
<p>
|
2985
|
+
<li>By default, the yacc generates tables in debugging mode (which produces the parser.out file and other output).
|
2986
|
+
To disable this, use
|
2987
|
+
|
2988
|
+
<blockquote>
|
2989
|
+
<pre>
|
2990
|
+
yacc.yacc(debug=0)
|
2991
|
+
</pre>
|
2992
|
+
</blockquote>
|
2993
|
+
|
2994
|
+
<p>
|
2995
|
+
<li>To change the name of the <tt>parsetab.py</tt> file, use:
|
2996
|
+
|
2997
|
+
<blockquote>
|
2998
|
+
<pre>
|
2999
|
+
yacc.yacc(tabmodule="foo")
|
3000
|
+
</pre>
|
3001
|
+
</blockquote>
|
3002
|
+
|
3003
|
+
<p>
|
3004
|
+
<li>To change the directory in which the <tt>parsetab.py</tt> file (and other output files) are written, use:
|
3005
|
+
<blockquote>
|
3006
|
+
<pre>
|
3007
|
+
yacc.yacc(tabmodule="foo",outputdir="somedirectory")
|
3008
|
+
</pre>
|
3009
|
+
</blockquote>
|
3010
|
+
|
3011
|
+
<p>
|
3012
|
+
<li>To prevent yacc from generating any kind of parser table file, use:
|
3013
|
+
<blockquote>
|
3014
|
+
<pre>
|
3015
|
+
yacc.yacc(write_tables=0)
|
3016
|
+
</pre>
|
3017
|
+
</blockquote>
|
3018
|
+
|
3019
|
+
Note: If you disable table generation, yacc() will regenerate the parsing tables
|
3020
|
+
each time it runs (which may take awhile depending on how large your grammar is).
|
3021
|
+
|
3022
|
+
<P>
|
3023
|
+
<li>To print copious amounts of debugging during parsing, use:
|
3024
|
+
|
3025
|
+
<blockquote>
|
3026
|
+
<pre>
|
3027
|
+
yacc.parse(debug=1)
|
3028
|
+
</pre>
|
3029
|
+
</blockquote>
|
3030
|
+
|
3031
|
+
<p>
|
3032
|
+
<li>The <tt>yacc.yacc()</tt> function really returns a parser object. If you want to support multiple
|
3033
|
+
parsers in the same application, do this:
|
3034
|
+
|
3035
|
+
<blockquote>
|
3036
|
+
<pre>
|
3037
|
+
p = yacc.yacc()
|
3038
|
+
...
|
3039
|
+
p.parse()
|
3040
|
+
</pre>
|
3041
|
+
</blockquote>
|
3042
|
+
|
3043
|
+
Note: The function <tt>yacc.parse()</tt> is bound to the last parser that was generated.
|
3044
|
+
|
3045
|
+
<p>
|
3046
|
+
<li>Since the generation of the LALR tables is relatively expensive, previously generated tables are
|
3047
|
+
cached and reused if possible. The decision to regenerate the tables is determined by taking an MD5
|
3048
|
+
checksum of all grammar rules and precedence rules. Only in the event of a mismatch are the tables regenerated.
|
3049
|
+
|
3050
|
+
<p>
|
3051
|
+
It should be noted that table generation is reasonably efficient, even for grammars that involve around a 100 rules
|
3052
|
+
and several hundred states. For more complex languages such as C, table generation may take 30-60 seconds on a slow
|
3053
|
+
machine. Please be patient.
|
3054
|
+
|
3055
|
+
<p>
|
3056
|
+
<li>Since LR parsing is driven by tables, the performance of the parser is largely independent of the
|
3057
|
+
size of the grammar. The biggest bottlenecks will be the lexer and the complexity of the code in your grammar rules.
|
3058
|
+
</ul>
|
3059
|
+
|
3060
|
+
<H2><a name="ply_nn37"></a>7. Multiple Parsers and Lexers</H2>
|
3061
|
+
|
3062
|
+
|
3063
|
+
In advanced parsing applications, you may want to have multiple
|
3064
|
+
parsers and lexers.
|
3065
|
+
|
3066
|
+
<p>
|
3067
|
+
As a general rules this isn't a problem. However, to make it work,
|
3068
|
+
you need to carefully make sure everything gets hooked up correctly.
|
3069
|
+
First, make sure you save the objects returned by <tt>lex()</tt> and
|
3070
|
+
<tt>yacc()</tt>. For example:
|
3071
|
+
|
3072
|
+
<blockquote>
|
3073
|
+
<pre>
|
3074
|
+
lexer = lex.lex() # Return lexer object
|
3075
|
+
parser = yacc.yacc() # Return parser object
|
3076
|
+
</pre>
|
3077
|
+
</blockquote>
|
3078
|
+
|
3079
|
+
Next, when parsing, make sure you give the <tt>parse()</tt> function a reference to the lexer it
|
3080
|
+
should be using. For example:
|
3081
|
+
|
3082
|
+
<blockquote>
|
3083
|
+
<pre>
|
3084
|
+
parser.parse(text,lexer=lexer)
|
3085
|
+
</pre>
|
3086
|
+
</blockquote>
|
3087
|
+
|
3088
|
+
If you forget to do this, the parser will use the last lexer
|
3089
|
+
created--which is not always what you want.
|
3090
|
+
|
3091
|
+
<p>
|
3092
|
+
Within lexer and parser rule functions, these objects are also
|
3093
|
+
available. In the lexer, the "lexer" attribute of a token refers to
|
3094
|
+
the lexer object that triggered the rule. For example:
|
3095
|
+
|
3096
|
+
<blockquote>
|
3097
|
+
<pre>
|
3098
|
+
def t_NUMBER(t):
|
3099
|
+
r'\d+'
|
3100
|
+
...
|
3101
|
+
print t.lexer # Show lexer object
|
3102
|
+
</pre>
|
3103
|
+
</blockquote>
|
3104
|
+
|
3105
|
+
In the parser, the "lexer" and "parser" attributes refer to the lexer
|
3106
|
+
and parser objects respectively.
|
3107
|
+
|
3108
|
+
<blockquote>
|
3109
|
+
<pre>
|
3110
|
+
def p_expr_plus(p):
|
3111
|
+
'expr : expr PLUS expr'
|
3112
|
+
...
|
3113
|
+
print p.parser # Show parser object
|
3114
|
+
print p.lexer # Show lexer object
|
3115
|
+
</pre>
|
3116
|
+
</blockquote>
|
3117
|
+
|
3118
|
+
If necessary, arbitrary attributes can be attached to the lexer or parser object.
|
3119
|
+
For example, if you wanted to have different parsing modes, you could attach a mode
|
3120
|
+
attribute to the parser object and look at it later.
|
3121
|
+
|
3122
|
+
<H2><a name="ply_nn38"></a>8. Using Python's Optimized Mode</H2>
|
3123
|
+
|
3124
|
+
|
3125
|
+
Because PLY uses information from doc-strings, parsing and lexing
|
3126
|
+
information must be gathered while running the Python interpreter in
|
3127
|
+
normal mode (i.e., not with the -O or -OO options). However, if you
|
3128
|
+
specify optimized mode like this:
|
3129
|
+
|
3130
|
+
<blockquote>
|
3131
|
+
<pre>
|
3132
|
+
lex.lex(optimize=1)
|
3133
|
+
yacc.yacc(optimize=1)
|
3134
|
+
</pre>
|
3135
|
+
</blockquote>
|
3136
|
+
|
3137
|
+
then PLY can later be used when Python runs in optimized mode. To make this work,
|
3138
|
+
make sure you first run Python in normal mode. Once the lexing and parsing tables
|
3139
|
+
have been generated the first time, run Python in optimized mode. PLY will use
|
3140
|
+
the tables without the need for doc strings.
|
3141
|
+
|
3142
|
+
<p>
|
3143
|
+
Beware: running PLY in optimized mode disables a lot of error
|
3144
|
+
checking. You should only do this when your project has stabilized
|
3145
|
+
and you don't need to do any debugging. One of the purposes of
|
3146
|
+
optimized mode is to substantially decrease the startup time of
|
3147
|
+
your compiler (by assuming that everything is already properly
|
3148
|
+
specified and works).
|
3149
|
+
|
3150
|
+
<H2><a name="ply_nn44"></a>9. Advanced Debugging</H2>
|
3151
|
+
|
3152
|
+
|
3153
|
+
<p>
|
3154
|
+
Debugging a compiler is typically not an easy task. PLY provides some
|
3155
|
+
advanced diagonistic capabilities through the use of Python's
|
3156
|
+
<tt>logging</tt> module. The next two sections describe this:
|
3157
|
+
|
3158
|
+
<H3><a name="ply_nn45"></a>9.1 Debugging the lex() and yacc() commands</H3>
|
3159
|
+
|
3160
|
+
|
3161
|
+
<p>
|
3162
|
+
Both the <tt>lex()</tt> and <tt>yacc()</tt> commands have a debugging
|
3163
|
+
mode that can be enabled using the <tt>debug</tt> flag. For example:
|
3164
|
+
|
3165
|
+
<blockquote>
|
3166
|
+
<pre>
|
3167
|
+
lex.lex(debug=True)
|
3168
|
+
yacc.yacc(debug=True)
|
3169
|
+
</pre>
|
3170
|
+
</blockquote>
|
3171
|
+
|
3172
|
+
Normally, the output produced by debugging is routed to either
|
3173
|
+
standard error or, in the case of <tt>yacc()</tt>, to a file
|
3174
|
+
<tt>parser.out</tt>. This output can be more carefully controlled
|
3175
|
+
by supplying a logging object. Here is an example that adds
|
3176
|
+
information about where different debugging messages are coming from:
|
3177
|
+
|
3178
|
+
<blockquote>
|
3179
|
+
<pre>
|
3180
|
+
# Set up a logging object
|
3181
|
+
import logging
|
3182
|
+
logging.basicConfig(
|
3183
|
+
level = logging.DEBUG,
|
3184
|
+
filename = "parselog.txt",
|
3185
|
+
filemode = "w",
|
3186
|
+
format = "%(filename)10s:%(lineno)4d:%(message)s"
|
3187
|
+
)
|
3188
|
+
log = logging.getLogger()
|
3189
|
+
|
3190
|
+
lex.lex(debug=True,debuglog=log)
|
3191
|
+
yacc.yacc(debug=True,debuglog=log)
|
3192
|
+
</pre>
|
3193
|
+
</blockquote>
|
3194
|
+
|
3195
|
+
If you supply a custom logger, the amount of debugging
|
3196
|
+
information produced can be controlled by setting the logging level.
|
3197
|
+
Typically, debugging messages are either issued at the <tt>DEBUG</tt>,
|
3198
|
+
<tt>INFO</tt>, or <tt>WARNING</tt> levels.
|
3199
|
+
|
3200
|
+
<p>
|
3201
|
+
PLY's error messages and warnings are also produced using the logging
|
3202
|
+
interface. This can be controlled by passing a logging object
|
3203
|
+
using the <tt>errorlog</tt> parameter.
|
3204
|
+
|
3205
|
+
<blockquote>
|
3206
|
+
<pre>
|
3207
|
+
lex.lex(errorlog=log)
|
3208
|
+
yacc.yacc(errorlog=log)
|
3209
|
+
</pre>
|
3210
|
+
</blockquote>
|
3211
|
+
|
3212
|
+
If you want to completely silence warnings, you can either pass in a
|
3213
|
+
logging object with an appropriate filter level or use the <tt>NullLogger</tt>
|
3214
|
+
object defined in either <tt>lex</tt> or <tt>yacc</tt>. For example:
|
3215
|
+
|
3216
|
+
<blockquote>
|
3217
|
+
<pre>
|
3218
|
+
yacc.yacc(errorlog=yacc.NullLogger())
|
3219
|
+
</pre>
|
3220
|
+
</blockquote>
|
3221
|
+
|
3222
|
+
<H3><a name="ply_nn46"></a>9.2 Run-time Debugging</H3>
|
3223
|
+
|
3224
|
+
|
3225
|
+
<p>
|
3226
|
+
To enable run-time debugging of a parser, use the <tt>debug</tt> option to parse. This
|
3227
|
+
option can either be an integer (which simply turns debugging on or off) or an instance
|
3228
|
+
of a logger object. For example:
|
3229
|
+
|
3230
|
+
<blockquote>
|
3231
|
+
<pre>
|
3232
|
+
log = logging.getLogger()
|
3233
|
+
parser.parse(input,debug=log)
|
3234
|
+
</pre>
|
3235
|
+
</blockquote>
|
3236
|
+
|
3237
|
+
If a logging object is passed, you can use its filtering level to control how much
|
3238
|
+
output gets generated. The <tt>INFO</tt> level is used to produce information
|
3239
|
+
about rule reductions. The <tt>DEBUG</tt> level will show information about the
|
3240
|
+
parsing stack, token shifts, and other details. The <tt>ERROR</tt> level shows information
|
3241
|
+
related to parsing errors.
|
3242
|
+
|
3243
|
+
<p>
|
3244
|
+
For very complicated problems, you should pass in a logging object that
|
3245
|
+
redirects to a file where you can more easily inspect the output after
|
3246
|
+
execution.
|
3247
|
+
|
3248
|
+
<H2><a name="ply_nn39"></a>10. Where to go from here?</H2>
|
3249
|
+
|
3250
|
+
|
3251
|
+
The <tt>examples</tt> directory of the PLY distribution contains several simple examples. Please consult a
|
3252
|
+
compilers textbook for the theory and underlying implementation details or LR parsing.
|
3253
|
+
|
3254
|
+
</body>
|
3255
|
+
</html>
|
3256
|
+
|
3257
|
+
|
3258
|
+
|
3259
|
+
|
3260
|
+
|
3261
|
+
|
3262
|
+
|