zhpy-1.7.3.1.orig/0000755000000000000000000000000011323406236010500 5ustar zhpy-1.7.3.1.orig/setup.py0000644000000000000000000000367611307366262012234 0ustar try: from setuptools import setup, find_packages except ImportError: from ez_setup import use_setuptools use_setuptools() from setuptools import setup, find_packages from pkg_resources import DistributionNotFound import sys import os import glob execfile(os.path.join('zhpy', 'release.py')) # setup params # it's possible to remove chardet dependency while porting required_modules = ["chardet >=1.0.1"] #if mac, install readline #if(sys.platform=="darwin"): # required_modules.append("readline >= 2.6.4") # pyparsing already included in release # nose is used for test extra_modules = {'pyparsing': ["pyparsing >=1.5.2"], 'nose': ["nose>=0.9"]} setup( name="zhpy", version=version, author=author, author_email=email, download_url=download_url, license=license, keywords = "traditional, simplified, chinese", description=description, long_description=long_description, url=url, zip_safe=False, install_requires = required_modules, extras_require = extra_modules, include_package_data = True, packages=find_packages(exclude=["ez_setup", 'examples', 'apidocs', "tests"]), entry_points = """ [console_scripts] zhpy = zhpy.commandline:commandline [pygments.lexers] zhpy = zhpy.ext.pygmentplugin:ZhpyLexer """, classifiers = [ 'Development Status :: 5 - Production/Stable', 'Environment :: Console', 'Intended Audience :: Education', 'Intended Audience :: Developers', 'Intended Audience :: System Administrators', 'License :: OSI Approved :: MIT License', 'Natural Language :: Chinese (Traditional)', 'Natural Language :: Chinese (Simplified)', 'Operating System :: OS Independent', 'Programming Language :: Python', 'Topic :: Software Development :: Libraries :: Python Modules', 'Topic :: Software Development :: Code Generators'], test_suite = 'nose.collector', ) zhpy-1.7.3.1.orig/setup.cfg0000644000000000000000000000061011307367650012326 0ustar [epydoc] include-log = no name = ZHPY docformat = restructuredtext inheritance = listed url = http://zhpy.googlecode.com/ imports = no introspect = yes modules = zhpy private = no output = html parse = yes exclude = .*\.tests.*, pyparsing* target = apidocs/ [easy_install] find_links = http://code.google.com/p/zhpy/downloads/list [egg_info] tag_build = tag_date = 0 tag_svn_revision = 0 zhpy-1.7.3.1.orig/zhpy.egg-info/0000755000000000000000000000000011323406236013164 5ustar zhpy-1.7.3.1.orig/zhpy.egg-info/not-zip-safe0000644000000000000000000000000111307131422015404 0ustar zhpy-1.7.3.1.orig/zhpy.egg-info/top_level.txt0000644000000000000000000000000511307367636015725 0ustar zhpy zhpy-1.7.3.1.orig/zhpy.egg-info/requires.txt0000644000000000000000000000010011307367636015567 0ustar chardet >=1.0.1 [pyparsing] pyparsing >=1.5.2 [nose] nose>=0.9zhpy-1.7.3.1.orig/zhpy.egg-info/SOURCES.txt0000644000000000000000000000072211307367636015065 0ustar README.txt setup.cfg setup.py zhpy/__init__.py zhpy/commandline.py zhpy/import_hook.py zhpy/info.py zhpy/interpreter.py zhpy/plugcn.py zhpy/plugtw.py zhpy/pyparsing.py zhpy/pyzh.py zhpy/release.py zhpy/zhdc.py zhpy/zhpy.py zhpy.egg-info/PKG-INFO zhpy.egg-info/SOURCES.txt zhpy.egg-info/dependency_links.txt zhpy.egg-info/entry_points.txt zhpy.egg-info/not-zip-safe zhpy.egg-info/requires.txt zhpy.egg-info/top_level.txt zhpy/ext/__init__.py zhpy/ext/pygmentplugin.pyzhpy-1.7.3.1.orig/zhpy.egg-info/dependency_links.txt0000644000000000000000000000000111307367636017246 0ustar zhpy-1.7.3.1.orig/zhpy.egg-info/entry_points.txt0000644000000000000000000000020511307367636016473 0ustar [console_scripts] zhpy = zhpy.commandline:commandline [pygments.lexers] zhpy = zhpy.ext.pygmentplugin:ZhpyLexer zhpy-1.7.3.1.orig/zhpy.egg-info/PKG-INFO0000644000000000000000000001317611307367636014305 0ustar Metadata-Version: 1.0 Name: zhpy Version: 1.7.3.1 Summary: Write python language in chinese Home-page: http://zhpy.googlecode.com/ Author: Fred Lin Author-email: gasolin+zhpy@gmail.com License: MIT Download-URL: http://code.google.com/p/zhpy/ Description: .. contents:: :depth: 2 Introduction -------------- "If it walks like a duck and quacks like a duck, I would call it a duck." Zhpy on python is good for Taiwan and China beginners to learn python in our native language (Currently support Traditional and Simplified chinese). Zhpy acts like python and play like python, you (chinese users) could use it as python to educate yourself the program skills plus with your native language. Check examples here. * http://zhpy.googlecode.com/svn/trunk/examples Play Zhpy Online -------------------- Zhpy has online version (with limited feature) running with google app engine! * http://zhpy.appspot.com Play locally -------------- To play zhpy locally, you even don't need to install it. All you need to do is follow the 3 steps guide: 1. Download the source pack (the zip file) 2. Extract the pack with zip tool. Enter the folder 3. Run:: $ python interpreter.py Then you got the usable zhpy interpreter! Install ---------- If you'd like to play zhpy with full features, you should install zhpy. You could use easy_install command to install or upgrade zhpy:: $ easy_install -U zhpy or check instructions for detail. * http://code.google.com/p/zhpy/wiki/DownloadInstall Usage ------- You could use zhpy interpreter to test zhpy:: $ zhpy zhpy [version] in [platform] on top of Python [py_version] >>> print 'hello in chinese' hello in chinese Browse project homepage to get examples in chinese. * http://code.google.com/p/zhpy/ check the BasicUsage for detail. * http://code.google.com/p/zhpy/wiki/BasicUsage Programming Guide ------------------- You could freely view the C.C. licensed book "A Byte of python (Zhpy)" on zhpy website, which contained zhpy example codes as well. * http://code.google.com/p/zhpy/wiki/ByteOfZhpy There's the API document available in zhpy download list, too. * http://code.google.com/p/zhpy/downloads/list PS: The book is based on "A Byte of Python". * http://swaroopch.info/text/Byte_of_Python:Main_Page What is Zhpy -------------- Zhpy is the full feature python language with fully tested chinese keywords, variables, and parameters support. Zhpy is INDEPENDENT on python version(2.4, 2.5....), bundle with command line tool, interpreter, bi-directional zhpy <-> python code translation, chinese shell script capability, in-place ini reference feature for keyword reuse, and great document (the book Byte of Python with chinese examples). The core of zhpy is a lightweight python module and a chinese source convertor based on python, which provides interpreter and command line tool to translate zhpy code to python. See http://www.flickr.com/photos/gasolin/2064120327 You could invoke interpreter with 'zhpy' command instead of "python" in command line to execute source code wrote in either Chinese or English. The zhpy interpreter also support autocomplete function to save your typing. Zhpy provide a method 'zh_exec' that allow you to embed chinese script in python; Zhpy could be used as the chinese shell script as well. The zhpy code written in traditional and simplified chinese could be translated and converted to natual python code. Thus it could be execute as nature python code and be used in normal python programs. Bidirectional python-zhpy translation is possible. Normal python programs could be translated to traditional(.twpy) or simplified(.cnpy) chinese zhpy source via 'zhpy' command line tool. The framework is not hard to extend to another languages such as japenese or korean. Change Log ------------- You could view the ChangeLog to see what's new in these version. * http://zhpy.googlecode.com/svn/trunk/CHANGELOG.txt Keywords: traditional,simplified,chinese Platform: UNKNOWN Classifier: Development Status :: 5 - Production/Stable Classifier: Environment :: Console Classifier: Intended Audience :: Education Classifier: Intended Audience :: Developers Classifier: Intended Audience :: System Administrators Classifier: License :: OSI Approved :: MIT License Classifier: Natural Language :: Chinese (Traditional) Classifier: Natural Language :: Chinese (Simplified) Classifier: Operating System :: OS Independent Classifier: Programming Language :: Python Classifier: Topic :: Software Development :: Libraries :: Python Modules Classifier: Topic :: Software Development :: Code Generators zhpy-1.7.3.1.orig/README.txt0000644000000000000000000000114611307125272012200 0ustar zhpy ==== zhpy is the python on Chinese, which is good for Taiwan and China beginners to learn python in our native language. Install: http://code.google.com/p/zhpy/wiki/DownloadInstall Open the command line, enter the current source directory and type following command: $ python setup.py install Basic Usage: http://code.google.com/p/zhpy/wiki/BasicUsage To play zhpy you even don't need to install it. All you need to do is follow the 3 steps guide: 1. Download the source pack 2. Extract the pack with zip tool 3. Run:: $ python interpreter.py Then you got the usable zhpy interpreter! zhpy-1.7.3.1.orig/zhpy/0000755000000000000000000000000011323406236011472 5ustar zhpy-1.7.3.1.orig/zhpy/commandline.py0000644000000000000000000002416411307125272014341 0ustar #!/usr/bin/python # -*- coding: utf-8 -*- """zhpy command line tool This is the MIT license: http://www.opensource.org/licenses/mit-license.php Copyright (c) 2007~ Fred Lin and contributors. zhpy is a trademark of Fred Lin. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ import os import sys from zhpy import convertor, zh_ord, zh_exec def commandline(): """zhpy, the python language in chinese Accept options: -i --input: speficy the input source -o --output: speficy the output source -p --python: compile to python and run -c --cmp: input raw zhpy source and run -e --encoding: specify the encoding --info: zhpy information -v --verbose: show zhpy progress in detail -V --version show zhpy version --tw: convert python to twpy --cn: convert python to cnpy help: get information: zhpy --info interpreter usage: zhpy [--tw | --cn] command usage: zhpy [-i | -p] input [-o] [output] [-e] [encoding] [-v] :: $ zhpy input.py (.twpy, .cnpy) [arguments] $ zhpy -i input.py (.twpy, .cnpy) $ zhpy -i input.py -o output.py (.twpy, .cnpy) $ zhpy -p input.py script usage: zhpy [-c] source [-e] [encoding] [-v] convertor usage: zhpy [--tw | --cn] input.py [-v] :: $ zhpy --tw input.py [-v] $ zhpy --cn input.py [-v] """ argv = sys.argv[1:] os.chdir(os.getcwd()) source = None target = None encoding = None raw_source = None verbose = False python = False tw = False cn = False NonEnglish = False # run as interpreter if len(argv) == 0: from interpreter import interpreter import import_hook display = os.getenv("LANG") if display == None: interpreter() elif "zh_TW" in display: interpreter('tw') elif "zh_CN" in display: interpreter('cn') else: interpreter() sys.exit() # run as script # not accept any option elif not argv[0].startswith('-'): source = argv[0] sys.argv = argv # run as command elif len(argv)==1: if argv[0] == '--info': from info import info info() sys.exit() if argv[0] == '-V' or argv[0] == '--version': from release import version print "zhpy %s on python %s"%(version, sys.version.split()[0]) sys.exit() elif argv[0] == '-h' or argv[0] == '--help': print commandline.__doc__ sys.exit() # run as native interpreter elif argv[0] == '--tw': from interpreter import interpreter import import_hook interpreter('tw') sys.exit() elif argv[0] == '--cn': from interpreter import interpreter import import_hook interpreter('cn') sys.exit() else: print commandline.__doc__ sys.exit() # accept "-c -e -v" elif len(argv)>=2: if argv[0] == '-c' or argv[0] == '--cmp': raw_source = argv[1] del(argv[:2]) if len(argv)>=2 and (argv[0] == '-e' or argv[0] == '--encoding'): encoding = argv[1] del(argv[:2]) if (len(argv)!=0) and (argv[0] == '-v' or \ argv[0] == '--verbose'): verbose = True # python to twpy elif argv[0] == '--tw': from pyzh import zh_chr, rev_annotator rev_annotator() source = argv[1] filename = os.path.splitext(source)[0] # remove extra .tw in filename profix = os.path.splitext(filename)[-1] if profix =='.tw': filename = os.path.splitext(filename)[0] del(argv[:2]) tw = True target = "v_"+zh_chr(filename)+".twpy" if (len(argv)!=0) and (argv[0] == '-v' or argv[0] == '--verbose'): verbose = True # python to cnpy elif argv[0] == '--cn': from pyzh import zh_chr, rev_annotator rev_annotator() source = argv[1] filename = os.path.splitext(source)[0] # remove extra .cn in filename profix = os.path.splitext(filename)[-1] if profix == '.cn': filename = os.path.splitext(filename)[0] del(argv[:2]) cn = True target = "v_"+zh_chr(filename)+".cnpy" if (len(argv)!=0) and (argv[0] == '-v' or argv[0] == '--verbose'): verbose = True # accept "-i -o -e -v" or "-p -e" or "-c -e -v" elif argv[0] == '-i' or argv[0] == '--input': source = argv[1] del(argv[:2]) if (len(argv)!=0) and (argv[0] == '-v' or argv[0] == '--verbose'): verbose = True if len(argv)>=2 and (argv[0] == '-e' or argv[0] == '--encoding'): encoding = argv[1] del(argv[:2]) if (len(argv)!=0) and (argv[0] == '-v' or \ argv[0] == '--verbose'): verbose = True if len(argv)>=2 and (argv[0] == '-o' or argv[0] == '--output'): target = argv[1] del(argv[:2]) if len(argv)>=2 and (argv[0] == '-e' or \ argv[0] == '--encoding'): encoding = argv[1] del(argv[:2]) if (len(argv)!=0) and (argv[0] == '-v' or \ argv[0] == '--verbose'): verbose = True elif argv[0] == '-p' or argv[0] == '--python': source = argv[1] filename = os.path.splitext(source)[0] # remove extra .tw in filename profix = os.path.splitext(filename)[-1] if (profix =='.tw') or (profix =='.cn'): filename = os.path.splitext(filename)[0] del(argv[:2]) # chinese filename to uri filename for i in filename: if i not in \ list('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_.'): NonEnglish = True print i, "file name is not in english" break if NonEnglish: target = zh_ord(filename.decode('utf8'))+".py" print "compile to python and run: %s"%( zh_ord(filename.decode('utf8'))+".py") else: target = "n_"+filename+".py" print "compile to python and run: %s"%("n_"+filename+".py") python = True if (len(argv)!=0) and (argv[0] == '-v' or argv[0] == '--verbose'): verbose = True if len(argv)>=2 and (argv[0] == '-e' or argv[0] == '--encoding'): encoding = argv[1] del(argv[:2]) if (len(argv)!=0) and (argv[0] == '-v' or \ argv[0] == '--verbose'): verbose = True else: print commandline.__doc__ sys.exit() #convert if raw_source: if verbose: print "run raw_source", raw_source #annotator() if encoding: result = convertor(raw_source, verbose, encoding) else: result = convertor(raw_source, verbose) zh_exec(result) import import_hook sys.exit() if encoding: print "encoding", encoding if source: if verbose: print "input", source # convertor if(tw or cn): if verbose: print "convert python code to", try: from pyzh import rev_annotator, python_convertor test = file(source, "r").read() if tw: print "twpy" rev_annotator('tw', verbose) result = python_convertor(test, lang='tw') if cn: print "cnpy" rev_annotator('cn', verbose) result = python_convertor(test, lang='cn') except Exception, e: print "zhpy Exception: you may input unproper source" if verbose: print e sys.exit() else: try: test = file(source, "r").read() #annotator() import import_hook if encoding: result = convertor(test, verbose, encoding) else: result = convertor(test, verbose) except Exception, e: print "zhpy Exception: you may input unproper source" if verbose: print e sys.exit() if target: if verbose: print "output", target file(target,"w").write(result) if python: zh_exec(result) else: zh_exec(result) if __name__=="__main__": commandline() zhpy-1.7.3.1.orig/zhpy/plugcn.py0000644000000000000000000002243511307125272013342 0ustar #!/usr/bin/python # -*- coding: utf-8 -*- """Simplified Chinese keyword dictionaries This is the MIT license: http://www.opensource.org/licenses/mit-license.php Copyright (c) 2007~ Fred Lin and contributors. zhpy is a trademark of Fred Lin. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ from zhdc import ZhpyPlugin # Simplized chinese keywords class cn_keyword(ZhpyPlugin): """ python cn keyword """ title = "内建关键词" description = "Python 内建关键词" keyword = { # logic "和":"and", "且":"and", "或":"or", "真": "True", "假":"False", "实":"True", "虛":"False", "空":"None", # def "定义":"def", "类":"class", "我":"self", "自个儿":"self", "共用":"global", "全域":"global", # import "从":"from", "导入":"import", "作为":"as", # flow "返回":"return", "略过":"pass", "引发":"raise", "继续":"continue", # control "如果":"if", "假使":"elif", "否则如果":"elif", "否则":"else", # for loop "取":"for", "自":"in", "在":"in", "不在":"not in", # while loop "当":"while", "跳出":"break", "中断":"break", # try "尝试":"try", "异常":"except", "最后":"finally", "申明":"assert", # build in methods "执行":"exec", "函数":"lambda", "打印":"print", "伴隨":"with", "产生":"yield", } class cn_buildin_method(ZhpyPlugin): """ python cn methods """ title = "内部函数" description = "Python 内部函数" keyword = { "输入":"raw_input", # build-in types "字符串":"str", "布尔":"bool", "列表": "list", "字典":"dict", "元组":"tuple", "集合":"set", "定集合":"frozenset", "符号":"chr", "符号转整数":"ord", "档案":"file", # number methods "整数":"int", "浮点数":"float", "复数":"complex", "十六进制":"hex", "绝对值":"abs", "比较":"cmp", # string methods "开头为":"startswith", "结尾为":"endswith", "连接":"join", "分离":"split", "代换":"replace", "编码":"encoding", "解码":"decoding", # list methods "加入":"append", "追加":"append", "扩展":"extend", "插入":"insert", "弹出":"pop", "下一笔":"next", "移除":"remove", "反转":"reverse", "计数":"count", "索引":"index", "排序":"sort", # dict methods "键列表":"keys", "值列表":"values", "项目列表":"items", "更新":"update", "拷贝":"copy", # set methods "清除":"clear", "加":"add", "丢弃":"discard", "联集":"union", "交集":"intersection", "差集":"difference", "对称差集":"symmetric_difference", # file methods "打开":"open", "读取":"read", "写入":"write", "读一行":"readline", "读多行":"readlines", "关闭":"close", # OO "可调用":"callable", "列出属性":"dir", "取属性":"getattr", "有属性":"hasattr", "设定属性":"setattr", "属性":"property", # build in functions "长度":"len", "最大值":"max", "最小值":"min", # build in methods "列举":"enumerate", "评估":"eval", "过滤":"filter", "映射":"map", "范围":"range", "快速范围":"xrange", "总和":"sum", "类型":"type", "对象":"object", "打包":"zip", "帮助":"help", "说明":"help", "区域变量":"locals", "全域变量":"globals", "类方法":"classmethod", } class cn_exception(ZhpyPlugin): """ python cn exceptions """ title = "例外" description = "Python 内建例外关键词" keyword = { "例外":"Exception", "错误":"Error", # error "运算错误":"ArithmeticError", "申明错误":"AssertionError", "属性错误":"AttributeError", "相容性警示":"DeprecationWarning", "空值错误":"EOFError", "环境错误":"EnvironmentError", "浮点数错误":"FloatingPointError", "输出入错误":"IOError", "导入错误":"ImportError", "缩排错误":"IndentationError", "索引错误":"IndexError", "键错误":"KeyError", "键盘中断":"KeyboardInterrupt", "查找错误":"LookupError", "内存错误":"MemoryError", "名称错误":"NameError", "尚未实作":"NotImplemented", "尚未实作错误":"NotImplementedError", "操作系统错误":"OSError", "溢值错误":"OverflowError", "溢值警告":"OverflowWarning", "引用错误":"ReferenceError", "运行期错误":"RuntimeError", "运行期警告":"RuntimeWarning", "标准错误":"StandardError", "停止迭代":"StopIteration", "语法错误":"SyntaxError", "语法警告":"SyntaxWarning", "系统错误":"SystemError", "系统结束":"SystemExit", "型别错误":"TypeError", "跳格错误":"TabError", "未绑定区域参数错误":"UnboundLocalError", "万国码解码错误":"UnicodeError", "自订警告":"UserWarning", "值错误":"ValueError", "警告":"Warning", "Windows错误":"WindowsError", "除零错误":"ZeroDivisionError", "解码错误":"UnicodeDecodeError", } class cn_zhpy(ZhpyPlugin): """ zhpy cn keyword plugin """ title = "周蟒" description = "周蟒内建关键词" keyword = { "周蟒":"zhpy", "主程序":'if __name__=="__main__"', # must do 'from zhpy import zh_exec'/'从 周蟒 导入 中文执行' first "中文执行":"zh_exec", # logic "等于":"==", "不等于":"!=", "非": "not", "是":"is", "为":"is", "不是":"is not", "不为":"is not", # private "文件":"doc", "初始化":"init", "刪除":"del", "描述":"repr", "测试":"test", } #enter simplified chinese dict here class cn_sys(ZhpyPlugin): """ zhpy sys module simplified chinese plugin """ title = "系统" description = "系统模块" keyword = {"系统":"sys", "版本":"version", "参数":"argv", "结束":"exit", "取得档案系统编码":"getfilesystemencoding", "模块列表":"modules", "平台":"platform", "标准错误":"stderr", "标准输入":"stdin", "标准输出":"stdout", # sys path with list methods "路径":"path", } class cn_traceback(ZhpyPlugin): """ zhpy traceback simplified chinese plugin """ title = "系统" description = "系统模组" keyword = {"未定义":"is not defined", "名称":"name", "行":"line", "档案":"File", "不合法的":"invalid", "语法":"syntax", } # [zhpy.cndict] cnkeyword = cn_keyword() cnmethod = cn_buildin_method() cnexception = cn_exception() cnzhpy= cn_zhpy() cnsys = cn_sys() cntrace = cn_traceback() tools = [cnkeyword, cnmethod, cnexception, cnzhpy, cnsys] trace = [cnkeyword, cnmethod, cnexception, cntrace, cnsys]zhpy-1.7.3.1.orig/zhpy/release.py0000644000000000000000000001004711307367464013501 0ustar # -*- coding: utf-8 -*- """Release information""" version = "1.7.3.1" author = "Fred Lin" email = "gasolin+zhpy@gmail.com" copyright = "Copyright 2007~ Fred Lin and contributors" license = "MIT " url = "http://zhpy.googlecode.com/" download_url="http://code.google.com/p/zhpy/" description="Write python language in chinese" long_description = """ .. contents:: :depth: 2 Introduction -------------- "If it walks like a duck and quacks like a duck, I would call it a duck." Zhpy on python is good for Taiwan and China beginners to learn python in our native language (Currently support Traditional and Simplified chinese). Zhpy acts like python and play like python, you (chinese users) could use it as python to educate yourself the program skills plus with your native language. Check examples here. * http://zhpy.googlecode.com/svn/trunk/examples Play Zhpy Online -------------------- Zhpy has online version (with limited feature) running with google app engine! * http://zhpy.appspot.com Play locally -------------- To play zhpy locally, you even don't need to install it. All you need to do is follow the 3 steps guide: 1. Download the source pack (the zip file) 2. Extract the pack with zip tool. Enter the folder 3. Run:: $ python interpreter.py Then you got the usable zhpy interpreter! Install ---------- If you'd like to play zhpy with full features, you should install zhpy. You could use easy_install command to install or upgrade zhpy:: $ easy_install -U zhpy or check instructions for detail. * http://code.google.com/p/zhpy/wiki/DownloadInstall Usage ------- You could use zhpy interpreter to test zhpy:: $ zhpy zhpy [version] in [platform] on top of Python [py_version] >>> print 'hello in chinese' hello in chinese Browse project homepage to get examples in chinese. * http://code.google.com/p/zhpy/ check the BasicUsage for detail. * http://code.google.com/p/zhpy/wiki/BasicUsage Programming Guide ------------------- You could freely view the C.C. licensed book "A Byte of python (Zhpy)" on zhpy website, which contained zhpy example codes as well. * http://code.google.com/p/zhpy/wiki/ByteOfZhpy There's the API document available in zhpy download list, too. * http://code.google.com/p/zhpy/downloads/list PS: The book is based on "A Byte of Python". * http://swaroopch.info/text/Byte_of_Python:Main_Page What is Zhpy -------------- Zhpy is the full feature python language with fully tested chinese keywords, variables, and parameters support. Zhpy is INDEPENDENT on python version(2.4, 2.5....), bundle with command line tool, interpreter, bi-directional zhpy <-> python code translation, chinese shell script capability, in-place ini reference feature for keyword reuse, and great document (the book Byte of Python with chinese examples). The core of zhpy is a lightweight python module and a chinese source convertor based on python, which provides interpreter and command line tool to translate zhpy code to python. See http://www.flickr.com/photos/gasolin/2064120327 You could invoke interpreter with 'zhpy' command instead of "python" in command line to execute source code wrote in either Chinese or English. The zhpy interpreter also support autocomplete function to save your typing. Zhpy provide a method 'zh_exec' that allow you to embed chinese script in python; Zhpy could be used as the chinese shell script as well. The zhpy code written in traditional and simplified chinese could be translated and converted to natual python code. Thus it could be execute as nature python code and be used in normal python programs. Bidirectional python-zhpy translation is possible. Normal python programs could be translated to traditional(.twpy) or simplified(.cnpy) chinese zhpy source via 'zhpy' command line tool. The framework is not hard to extend to another languages such as japenese or korean. Change Log ------------- You could view the ChangeLog to see what's new in these version. * http://zhpy.googlecode.com/svn/trunk/CHANGELOG.txt """ zhpy-1.7.3.1.orig/zhpy/pyzh.py0000644000000000000000000001672711307125272013053 0ustar #!/usr/bin/python # -*- coding: utf-8 -*- """Transform python source to zhpy source This is the MIT license: http://www.opensource.org/licenses/mit-license.php Copyright (c) 2007~ Fred Lin and contributors. zhpy is a trademark of Fred Lin. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ from zhpy import annotator, merger, tripleQuote from zhdc import twdict, cndict, revert_dict annotator() #: make reverse traditional chinese dicts rev_twdict = revert_dict(twdict) #: make reverse simplified chinese dicts rev_cndict = revert_dict(cndict) #: Traceback keywords repository rev_tbdict = {} def _rev_ini_annotator(use_dict, verbose=True): """ update revert dict by ini files Accept args: use_dict: target dict to be merged verbose: show detail message, default: True """ # ini inifiles = [] import os import ConfigParser for x in os.listdir("."): if x.endswith(".ini"): inifiles.append(x) for f in inifiles: if verbose: print "file", f conf = ConfigParser.ConfigParser() try: conf.read(f) for sect in conf.sections(): if verbose: print "sect:", sect merger(conf.items(sect), use_dict, reverse=True) except: print "!%s is not a valid keyword file"%f def _rev_py_annotator(use_dict, entry_point, verbose=False): """ update revert dict by python plugins 'verbose' argument is only for debug(will generate too mush messages). """ for tool in entry_point: if verbose: print tool.title merger(tool.keyword, use_dict, reverse=True) def _trace_annotator(use_dict, entry_point, verbose=False): """ find python traceback keyword plugins and update to dicts """ for trace in entry_point: if verbose: print trace.title merger(trace.keyword, use_dict, reverse=True) def rev_annotator(lang='tw', verbose=True): """ To expand the reverse dict ther are 2 ways to extend the reverse dict 1. python keyword plugins 2. ini file in local directory Accept args: lang: 'tw' or 'cn' """ if lang == 'tw': use_dict = rev_twdict from plugtw import tools, trace # tw plugin _rev_py_annotator(use_dict, entry_point=tools, verbose=False) # tw trace _trace_annotator(rev_tbdict, entry_point=trace, verbose=False) if lang == 'cn': use_dict = rev_cndict from plugcn import tools, trace # cn plugin _rev_py_annotator(use_dict, entry_point=tools, verbose=False) # cn trace _trace_annotator(rev_tbdict, entry_point=trace, verbose=False) # ini _rev_ini_annotator(use_dict, verbose) import re def _val_matching(tmp): """ match and convert the identifiers """ tmp2 = '' for word in tmp.split('_')[1:]: if not ('v' in word and 'p' in word): tmp2 += unichr(int(word, 16)).encode('utf8') return tmp2 def zh_chr(tmp): """ convert number back to chinese variable >>> print zh_chr('p_7bc4_4f8b_v') 範例 >>> print zh_chr('p_7bc4_4f8b_v_1') 範例_1 >>> print zh_chr('p_7bc4_4f8b_v1') 範例1 >>> print zh_chr("p_6e2c_8a66_v_p_7bc4_4f8b_v") 測試_範例 >>> print zh_chr("p_6e2c_8a66_v_p_7bc4_4f8b_v2") 測試_範例2 """ if tmp.startswith("p_") and "_v" in tmp: tmp, profix = tmp.split('_v', 1) tmp2 = _val_matching(tmp) if not ('v' in profix and 'p' in profix): return tmp2 + profix else: # allow 2 cascade identifiers sep = profix[0:profix.index('p_')] tmp = profix[profix.index('p_')::] tmp, profix = tmp.split('_v', 1) tmp2 += sep + _val_matching(tmp) return tmp2 +profix else: return tmp # backward compatibility number_to_variable = zh_chr _pattern = r'^p_[_a-f\d]*_v\w*$' from pyparsing import Word, alphanums, \ quotedString, pythonStyleComment def convertToTW(s,l,t): """ search rev_twdict to match keywords """ tmp = t[0] if tmp in rev_twdict: return rev_twdict[tmp] elif re.match(_pattern, tmp): return zh_chr(tmp) else: return tmp def convertToCN(s,l,t): """ search rev_cndict to match keywords """ tmp = t[0] if tmp in rev_cndict: return rev_cndict[tmp] elif re.match(_pattern, tmp): return zh_chr(tmp) else: return tmp def convertToTraceBack(s,l,t): """ search rev_tbdict to match keywords """ tmp = t[0] if tmp in rev_tbdict: return rev_tbdict[tmp] elif re.match(_pattern, tmp): return zh_chr(tmp) else: return tmp #: basic parsing pattern baseWord = tripleQuote | quotedString | pythonStyleComment twenWord = Word(alphanums+"_") twenWord.setParseAction(convertToTW) #: Traditional Chinese parsing pattern twpyWord = baseWord | twenWord tbWord = Word(alphanums+"_") tbWord.setParseAction(convertToTraceBack) #: Traceback parsing pattern tbpyWord = baseWord | tbWord cnenWord = Word(alphanums+"_") cnenWord.setParseAction(convertToCN) #: Simplified Chinese parsing pattern cnpyWord = baseWord | cnenWord def python_convertor(text, lang='tw', traceback=False): """ convert python source to zhpy source Accept args: lang: 'tw' or 'cn' >>> print python_convertor("print 'hello'", 'tw') 印出 'hello' >>> print python_convertor("print 'hello'", 'cn') 打印 'hello' >>> print python_convertor("# print 'hello'", 'tw') # print 'hello' >>> print python_convertor("print '''哈囉, 世界'''", 'tw') 印出 '''哈囉, 世界''' >>> print python_convertor("p_6e2c_8a66_v_p_7bc4_4f8b_v2") 測試_範例2 >>> print python_convertor("p_6e2c_8a66_v2p_7bc4_4f8b_v") 測試2範例 >>> print python_convertor("p_6e2c_8a66_v2p_7bc4_4f8b_v2") 測試2範例2 """ if isinstance(text, unicode): text = text.encode('utf8') if lang == 'tw': if traceback==False: result = twpyWord.transformString(text) else: result = tbpyWord.transformString(text)#+str(rev_tbdict) elif lang == 'cn': if traceback==False: result = cnpyWord.transformString(text) else: result = tbpyWord.transformString(text) else: #TODO: auto detect coding print "not valid lang option in python_convertor" return text return result zhpy-1.7.3.1.orig/zhpy/interpreter.py0000644000000000000000000001552111307125272014413 0ustar # -*- coding: utf-8 -*- """zhpy interactive interpretor This is the MIT license: http://www.opensource.org/licenses/mit-license.php Copyright (c) 2007~ Fred Lin and contributors. zhpy is a trademark of Fred Lin. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ from code import InteractiveConsole from zhpy import convertor import sys class ZhPyConsole(InteractiveConsole): """ Wrapper around Python and filter input/output to the shell """ def push(self, line): self.buffer.append(line) source = "\n".join(self.buffer) #windows patch encoding = sys.stdout.encoding if encoding == 'cp950': encoding = '' more = self.runsource(convertor(source, encoding=encoding), self.filename) if not more: self.resetbuffer() return more try: from release import version except: version = 'core' def interpreter(lang=None): """ zhpy interpreter Accept args: lang: interpreter language """ try: import readline except ImportError: pass else: import rlcompleter """Indentable rlcompleter""" class irlcompleter(rlcompleter.Completer): def complete(self, text, state): #print text, state, str(type(text)) if text == "": #replace tab to 4 spaces return [' ', None][state] elif lang == 'tw': if text in ["印","pri","prin","print"]: return ['印出'][state] elif text == "for": return ['取'][state] elif text == 'in': return ['自'][state] elif text in ['範', 'ran', 'rang', 'range']: return ['範圍'][state] elif text in ["定","def"]: return ['定義'][state] elif text in ["類", "cla", "clas", "class"]: return ['類別'][state] elif text in ["導", "imp", "impo", "impor", "import"]: return ['導入'][state] elif text in ["返", "ret", "retu", "retur", "return"]: return ['返回'][state] elif text in ["fro", "from"]: return ['從'][state] elif text in ["作", "as"]: return ['作為'][state] elif text in ['如', 'if']: return ['如果'][state] elif text in ['假', 'eli', 'elif']: return ['假使'][state] elif text in ['否', 'els', 'else']: return ['否則'][state] elif text in ['Non', 'None']: return ['空'][state] elif lang == 'cn': if text in ["打","pri","prin","print"]: return ['打印'][state] elif text == "for": return ['取'][state] elif text == 'in': return ['自'][state] elif text in ['范', 'ran', 'rang', 'range']: return ['范围'][state] elif text in ["定","def"]: return ['定义'][state] elif text in ["类", "cla", "clas", "class"]: return ['类'][state] elif text in ["导", "imp", "impo", "impor", "import"]: return ['导入'][state] elif text in ["返", "ret", "retu", "retur", "return"]: return ['返回'][state] elif text in ["fro", "from"]: return ['从'][state] elif text in ["作", "as"]: return ['作为'][state] elif text in ['如', 'if']: return ['如果'][state] elif text in ['假', 'eli', 'elif']: return ['假使'][state] elif text in ['否', 'els', 'else']: return ['否则'][state] elif text in ['Non', 'None']: return ['空'][state] else: return rlcompleter.Completer.complete(self,text,state) #you could change this line to bind another key instead tab. readline.parse_and_bind("tab: complete") readline.set_completer(irlcompleter().complete) con = ZhPyConsole() if lang == 'tw': banner = '周蟒 %s 在 %s 基於 Python %s'%(version, sys.platform, sys.version.split()[0]) if sys.platform == 'win32': banner = unicode(banner, 'utf-8').encode(sys.stdout.encoding) elif lang == 'cn': banner = '周蟒 %s 在 %s 基于 Python %s'%(version, sys.platform, sys.version.split()[0]) if sys.platform == 'win32': banner = unicode(banner, 'utf-8').encode(sys.stdout.encoding) else: banner = 'zhpy %s in %s on top of Python %s'%(version, sys.platform, sys.version.split()[0]) #annotator() # able to import modules in current directory sys.path.insert(0, '') con.interact(banner) if __name__=="__main__": try: import import_hook except: print "There's no zhimport support" import sys argv = sys.argv[1:] #profiling if len(argv)!=0 and argv[0] =="--profile": import profile profile.run("interpreter()", "prof.txt") import pstats p = pstats.Stats("prof.txt") p.sort_stats("time").print_stats() else: interpreter()zhpy-1.7.3.1.orig/zhpy/import_hook.py0000644000000000000000000000364011307125272014401 0ustar #!/usr/bin/python # -*- coding: utf-8 -*- """zhpy import hook This is the MIT license: http://www.opensource.org/licenses/mit-license.php Copyright (c) 2007~ Fred Lin and contributors. zhpy is a trademark of Fred Lin. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ import __builtin__ try: if setup: import sys sys.stderr.write("reload(zhpy.import_hook) won't work!\n") except: from pyzh import zh_chr __trueimport__ = __builtin__.__import__ def chinese_import(modname, *arg): """chinese import convert uri file name back to chinese filename """ __builtin__.__import__ = __trueimport__ modname = zh_chr(modname).encode("utf8") __builtin__.__import__ = chinese_import return __trueimport__(modname, *arg) def setup(): if not getattr(chinese_import, "hooked", False): __builtin__.__import__ = chinese_import chinese_import.hooked=True setup()zhpy-1.7.3.1.orig/zhpy/pyparsing.py0000755000000000000000000045164411307125272014101 0ustar # module pyparsing.py # # Copyright (c) 2003-2009 Paul T. McGuire # # Permission is hereby granted, free of charge, to any person obtaining # a copy of this software and associated documentation files (the # "Software"), to deal in the Software without restriction, including # without limitation the rights to use, copy, modify, merge, publish, # distribute, sublicense, and/or sell copies of the Software, and to # permit persons to whom the Software is furnished to do so, subject to # the following conditions: # # The above copyright notice and this permission notice shall be # included in all copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. # IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY # CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. # #from __future__ import generators __doc__ = \ """ pyparsing module - Classes and methods to define and execute parsing grammars The pyparsing module is an alternative approach to creating and executing simple grammars, vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you don't need to learn a new syntax for defining grammars or matching expressions - the parsing module provides a library of classes that you use to construct the grammar directly in Python. Here is a program to parse "Hello, World!" (or any greeting of the form ", !"):: from pyparsing import Word, alphas # define grammar of a greeting greet = Word( alphas ) + "," + Word( alphas ) + "!" hello = "Hello, World!" print hello, "->", greet.parseString( hello ) The program outputs the following:: Hello, World! -> ['Hello', ',', 'World', '!'] The Python representation of the grammar is quite readable, owing to the self-explanatory class names, and the use of '+', '|' and '^' operators. The parsed results returned from parseString() can be accessed as a nested list, a dictionary, or an object with named attributes. The pyparsing module handles some of the problems that are typically vexing when writing text parsers: - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.) - quoted strings - embedded comments """ __version__ = "1.5.2" __versionTime__ = "17 February 2009 19:45" __author__ = "Paul McGuire " import string from weakref import ref as wkref import copy import sys import warnings import re import sre_constants #~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) ) __all__ = [ 'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty', 'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal', 'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or', 'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException', 'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException', 'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter', 'Upcase', 'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore', 'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col', 'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString', 'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'getTokensEndLoc', 'hexnums', 'htmlComment', 'javaStyleComment', 'keepOriginalText', 'line', 'lineEnd', 'lineStart', 'lineno', 'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral', 'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables', 'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity', 'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd', 'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute', 'indentedBlock', 'originalTextFor', ] """ Detect if we are running version 3.X and make appropriate changes Robert A. Clark """ if sys.version_info[0] > 2: _PY3K = True _MAX_INT = sys.maxsize basestring = str else: _PY3K = False _MAX_INT = sys.maxint if not _PY3K: def _ustr(obj): """Drop-in replacement for str(obj) that tries to be Unicode friendly. It first tries str(obj). If that fails with a UnicodeEncodeError, then it tries unicode(obj). It then < returns the unicode object | encodes it with the default encoding | ... >. """ if isinstance(obj,unicode): return obj try: # If this works, then _ustr(obj) has the same behaviour as str(obj), so # it won't break any existing code. return str(obj) except UnicodeEncodeError: # The Python docs (http://docs.python.org/ref/customization.html#l2h-182) # state that "The return value must be a string object". However, does a # unicode object (being a subclass of basestring) count as a "string # object"? # If so, then return a unicode object: return unicode(obj) # Else encode it... but how? There are many choices... :) # Replace unprintables with escape codes? #return unicode(obj).encode(sys.getdefaultencoding(), 'backslashreplace_errors') # Replace unprintables with question marks? #return unicode(obj).encode(sys.getdefaultencoding(), 'replace') # ... else: _ustr = str unichr = chr if not _PY3K: def _str2dict(strg): return dict( [(c,0) for c in strg] ) else: _str2dict = set def _xml_escape(data): """Escape &, <, >, ", ', etc. in a string of data.""" # ampersand must be replaced first from_symbols = '&><"\'' to_symbols = ['&'+s+';' for s in "amp gt lt quot apos".split()] for from_,to_ in zip(from_symbols, to_symbols): data = data.replace(from_, to_) return data class _Constants(object): pass if not _PY3K: alphas = string.lowercase + string.uppercase else: alphas = string.ascii_lowercase + string.ascii_uppercase nums = string.digits hexnums = nums + "ABCDEFabcdef" alphanums = alphas + nums _bslash = chr(92) printables = "".join( [ c for c in string.printable if c not in string.whitespace ] ) class ParseBaseException(Exception): """base exception class for all parsing runtime exceptions""" # Performance tuning: we construct a *lot* of these, so keep this # constructor as small and fast as possible def __init__( self, pstr, loc=0, msg=None, elem=None ): self.loc = loc if msg is None: self.msg = pstr self.pstr = "" else: self.msg = msg self.pstr = pstr self.parserElement = elem def __getattr__( self, aname ): """supported attributes by name are: - lineno - returns the line number of the exception text - col - returns the column number of the exception text - line - returns the line containing the exception text """ if( aname == "lineno" ): return lineno( self.loc, self.pstr ) elif( aname in ("col", "column") ): return col( self.loc, self.pstr ) elif( aname == "line" ): return line( self.loc, self.pstr ) else: raise AttributeError(aname) def __str__( self ): return "%s (at char %d), (line:%d, col:%d)" % \ ( self.msg, self.loc, self.lineno, self.column ) def __repr__( self ): return _ustr(self) def markInputline( self, markerString = ">!<" ): """Extracts the exception line from the input string, and marks the location of the exception with a special symbol. """ line_str = self.line line_column = self.column - 1 if markerString: line_str = "".join( [line_str[:line_column], markerString, line_str[line_column:]]) return line_str.strip() def __dir__(self): return "loc msg pstr parserElement lineno col line " \ "markInputLine __str__ __repr__".split() class ParseException(ParseBaseException): """exception thrown when parse expressions don't match class; supported attributes by name are: - lineno - returns the line number of the exception text - col - returns the column number of the exception text - line - returns the line containing the exception text """ pass class ParseFatalException(ParseBaseException): """user-throwable exception thrown when inconsistent parse content is found; stops all parsing immediately""" pass class ParseSyntaxException(ParseFatalException): """just like ParseFatalException, but thrown internally when an ErrorStop indicates that parsing is to stop immediately because an unbacktrackable syntax error has been found""" def __init__(self, pe): super(ParseSyntaxException, self).__init__( pe.pstr, pe.loc, pe.msg, pe.parserElement) #~ class ReparseException(ParseBaseException): #~ """Experimental class - parse actions can raise this exception to cause #~ pyparsing to reparse the input string: #~ - with a modified input string, and/or #~ - with a modified start location #~ Set the values of the ReparseException in the constructor, and raise the #~ exception in a parse action to cause pyparsing to use the new string/location. #~ Setting the values as None causes no change to be made. #~ """ #~ def __init_( self, newstring, restartLoc ): #~ self.newParseText = newstring #~ self.reparseLoc = restartLoc class RecursiveGrammarException(Exception): """exception thrown by validate() if the grammar could be improperly recursive""" def __init__( self, parseElementList ): self.parseElementTrace = parseElementList def __str__( self ): return "RecursiveGrammarException: %s" % self.parseElementTrace class _ParseResultsWithOffset(object): def __init__(self,p1,p2): self.tup = (p1,p2) def __getitem__(self,i): return self.tup[i] def __repr__(self): return repr(self.tup) def setOffset(self,i): self.tup = (self.tup[0],i) class ParseResults(object): """Structured parse results, to provide multiple means of access to the parsed data: - as a list (len(results)) - by list index (results[0], results[1], etc.) - by attribute (results.) """ __slots__ = ( "__toklist", "__tokdict", "__doinit", "__name", "__parent", "__accumNames", "__weakref__" ) def __new__(cls, toklist, name=None, asList=True, modal=True ): if isinstance(toklist, cls): return toklist retobj = object.__new__(cls) retobj.__doinit = True return retobj # Performance tuning: we construct a *lot* of these, so keep this # constructor as small and fast as possible def __init__( self, toklist, name=None, asList=True, modal=True ): if self.__doinit: self.__doinit = False self.__name = None self.__parent = None self.__accumNames = {} if isinstance(toklist, list): self.__toklist = toklist[:] else: self.__toklist = [toklist] self.__tokdict = dict() if name: if not modal: self.__accumNames[name] = 0 if isinstance(name,int): name = _ustr(name) # will always return a str, but use _ustr for consistency self.__name = name if not toklist in (None,'',[]): if isinstance(toklist,basestring): toklist = [ toklist ] if asList: if isinstance(toklist,ParseResults): self[name] = _ParseResultsWithOffset(toklist.copy(),0) else: self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]),0) self[name].__name = name else: try: self[name] = toklist[0] except (KeyError,TypeError,IndexError): self[name] = toklist def __getitem__( self, i ): if isinstance( i, (int,slice) ): return self.__toklist[i] else: if i not in self.__accumNames: return self.__tokdict[i][-1][0] else: return ParseResults([ v[0] for v in self.__tokdict[i] ]) def __setitem__( self, k, v ): if isinstance(v,_ParseResultsWithOffset): self.__tokdict[k] = self.__tokdict.get(k,list()) + [v] sub = v[0] elif isinstance(k,int): self.__toklist[k] = v sub = v else: self.__tokdict[k] = self.__tokdict.get(k,list()) + [_ParseResultsWithOffset(v,0)] sub = v if isinstance(sub,ParseResults): sub.__parent = wkref(self) def __delitem__( self, i ): if isinstance(i,(int,slice)): mylen = len( self.__toklist ) del self.__toklist[i] # convert int to slice if isinstance(i, int): if i < 0: i += mylen i = slice(i, i+1) # get removed indices removed = list(range(*i.indices(mylen))) removed.reverse() # fixup indices in token dictionary for name in self.__tokdict: occurrences = self.__tokdict[name] for j in removed: for k, (value, position) in enumerate(occurrences): occurrences[k] = _ParseResultsWithOffset(value, position - (position > j)) else: del self.__tokdict[i] def __contains__( self, k ): return k in self.__tokdict def __len__( self ): return len( self.__toklist ) def __bool__(self): return len( self.__toklist ) > 0 __nonzero__ = __bool__ def __iter__( self ): return iter( self.__toklist ) def __reversed__( self ): return iter( reversed(self.__toklist) ) def keys( self ): """Returns all named result keys.""" return self.__tokdict.keys() def pop( self, index=-1 ): """Removes and returns item at specified index (default=last). Will work with either numeric indices or dict-key indicies.""" ret = self[index] del self[index] return ret def get(self, key, defaultValue=None): """Returns named result matching the given key, or if there is no such name, then returns the given defaultValue or None if no defaultValue is specified.""" if key in self: return self[key] else: return defaultValue def insert( self, index, insStr ): self.__toklist.insert(index, insStr) # fixup indices in token dictionary for name in self.__tokdict: occurrences = self.__tokdict[name] for k, (value, position) in enumerate(occurrences): occurrences[k] = _ParseResultsWithOffset(value, position + (position > index)) def items( self ): """Returns all named result keys and values as a list of tuples.""" return [(k,self[k]) for k in self.__tokdict] def values( self ): """Returns all named result values.""" return [ v[-1][0] for v in self.__tokdict.values() ] def __getattr__( self, name ): if name not in self.__slots__: if name in self.__tokdict: if name not in self.__accumNames: return self.__tokdict[name][-1][0] else: return ParseResults([ v[0] for v in self.__tokdict[name] ]) else: return "" return None def __add__( self, other ): ret = self.copy() ret += other return ret def __iadd__( self, other ): if other.__tokdict: offset = len(self.__toklist) addoffset = ( lambda a: (a<0 and offset) or (a+offset) ) otheritems = other.__tokdict.items() otherdictitems = [(k, _ParseResultsWithOffset(v[0],addoffset(v[1])) ) for (k,vlist) in otheritems for v in vlist] for k,v in otherdictitems: self[k] = v if isinstance(v[0],ParseResults): v[0].__parent = wkref(self) self.__toklist += other.__toklist self.__accumNames.update( other.__accumNames ) del other return self def __repr__( self ): return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) ) def __str__( self ): out = "[" sep = "" for i in self.__toklist: if isinstance(i, ParseResults): out += sep + _ustr(i) else: out += sep + repr(i) sep = ", " out += "]" return out def _asStringList( self, sep='' ): out = [] for item in self.__toklist: if out and sep: out.append(sep) if isinstance( item, ParseResults ): out += item._asStringList() else: out.append( _ustr(item) ) return out def asList( self ): """Returns the parse results as a nested list of matching tokens, all converted to strings.""" out = [] for res in self.__toklist: if isinstance(res,ParseResults): out.append( res.asList() ) else: out.append( res ) return out def asDict( self ): """Returns the named parse results as dictionary.""" return dict( self.items() ) def copy( self ): """Returns a new copy of a ParseResults object.""" ret = ParseResults( self.__toklist ) ret.__tokdict = self.__tokdict.copy() ret.__parent = self.__parent ret.__accumNames.update( self.__accumNames ) ret.__name = self.__name return ret def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ): """Returns the parse results as XML. Tags are created for tokens and lists that have defined results names.""" nl = "\n" out = [] namedItems = dict( [ (v[1],k) for (k,vlist) in self.__tokdict.items() for v in vlist ] ) nextLevelIndent = indent + " " # collapse out indents if formatting is not desired if not formatted: indent = "" nextLevelIndent = "" nl = "" selfTag = None if doctag is not None: selfTag = doctag else: if self.__name: selfTag = self.__name if not selfTag: if namedItemsOnly: return "" else: selfTag = "ITEM" out += [ nl, indent, "<", selfTag, ">" ] worklist = self.__toklist for i,res in enumerate(worklist): if isinstance(res,ParseResults): if i in namedItems: out += [ res.asXML(namedItems[i], namedItemsOnly and doctag is None, nextLevelIndent, formatted)] else: out += [ res.asXML(None, namedItemsOnly and doctag is None, nextLevelIndent, formatted)] else: # individual token, see if there is a name for it resTag = None if i in namedItems: resTag = namedItems[i] if not resTag: if namedItemsOnly: continue else: resTag = "ITEM" xmlBodyText = _xml_escape(_ustr(res)) out += [ nl, nextLevelIndent, "<", resTag, ">", xmlBodyText, "" ] out += [ nl, indent, "" ] return "".join(out) def __lookup(self,sub): for k,vlist in self.__tokdict.items(): for v,loc in vlist: if sub is v: return k return None def getName(self): """Returns the results name for this token expression.""" if self.__name: return self.__name elif self.__parent: par = self.__parent() if par: return par.__lookup(self) else: return None elif (len(self) == 1 and len(self.__tokdict) == 1 and self.__tokdict.values()[0][0][1] in (0,-1)): return self.__tokdict.keys()[0] else: return None def dump(self,indent='',depth=0): """Diagnostic method for listing out the contents of a ParseResults. Accepts an optional indent argument so that this string can be embedded in a nested display of other data.""" out = [] out.append( indent+_ustr(self.asList()) ) keys = self.items() keys.sort() for k,v in keys: if out: out.append('\n') out.append( "%s%s- %s: " % (indent,(' '*depth), k) ) if isinstance(v,ParseResults): if v.keys(): #~ out.append('\n') out.append( v.dump(indent,depth+1) ) #~ out.append('\n') else: out.append(_ustr(v)) else: out.append(_ustr(v)) #~ out.append('\n') return "".join(out) # add support for pickle protocol def __getstate__(self): return ( self.__toklist, ( self.__tokdict.copy(), self.__parent is not None and self.__parent() or None, self.__accumNames, self.__name ) ) def __setstate__(self,state): self.__toklist = state[0] self.__tokdict, \ par, \ inAccumNames, \ self.__name = state[1] self.__accumNames = {} self.__accumNames.update(inAccumNames) if par is not None: self.__parent = wkref(par) else: self.__parent = None def __dir__(self): return dir(super(ParseResults,self)) + self.keys() def col (loc,strg): """Returns current column within a string, counting newlines as line separators. The first column is number 1. Note: the default parsing behavior is to expand tabs in the input string before starting the parsing process. See L{I{ParserElement.parseString}} for more information on parsing strings containing s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. """ return (loc} for more information on parsing strings containing s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. """ return strg.count("\n",0,loc) + 1 def line( loc, strg ): """Returns the line of text containing loc within a string, counting newlines as line separators. """ lastCR = strg.rfind("\n", 0, loc) nextCR = strg.find("\n", loc) if nextCR > 0: return strg[lastCR+1:nextCR] else: return strg[lastCR+1:] def _defaultStartDebugAction( instring, loc, expr ): print ("Match " + _ustr(expr) + " at loc " + _ustr(loc) + "(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )) def _defaultSuccessDebugAction( instring, startloc, endloc, expr, toks ): print ("Matched " + _ustr(expr) + " -> " + str(toks.asList())) def _defaultExceptionDebugAction( instring, loc, expr, exc ): print ("Exception raised:" + _ustr(exc)) def nullDebugAction(*args): """'Do-nothing' debug action, to suppress debugging output during parsing.""" pass class ParserElement(object): """Abstract base level parser element class.""" DEFAULT_WHITE_CHARS = " \n\t\r" def setDefaultWhitespaceChars( chars ): """Overrides the default whitespace chars """ ParserElement.DEFAULT_WHITE_CHARS = chars setDefaultWhitespaceChars = staticmethod(setDefaultWhitespaceChars) def __init__( self, savelist=False ): self.parseAction = list() self.failAction = None #~ self.name = "" # don't define self.name, let subclasses try/except upcall self.strRepr = None self.resultsName = None self.saveAsList = savelist self.skipWhitespace = True self.whiteChars = ParserElement.DEFAULT_WHITE_CHARS self.copyDefaultWhiteChars = True self.mayReturnEmpty = False # used when checking for left-recursion self.keepTabs = False self.ignoreExprs = list() self.debug = False self.streamlined = False self.mayIndexError = True # used to optimize exception handling for subclasses that don't advance parse index self.errmsg = "" self.modalResults = True # used to mark results names as modal (report only last) or cumulative (list all) self.debugActions = ( None, None, None ) #custom debug actions self.re = None self.callPreparse = True # used to avoid redundant calls to preParse self.callDuringTry = False def copy( self ): """Make a copy of this ParserElement. Useful for defining different parse actions for the same parsing pattern, using copies of the original parse element.""" cpy = copy.copy( self ) cpy.parseAction = self.parseAction[:] cpy.ignoreExprs = self.ignoreExprs[:] if self.copyDefaultWhiteChars: cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS return cpy def setName( self, name ): """Define name for this expression, for use in debugging.""" self.name = name self.errmsg = "Expected " + self.name if hasattr(self,"exception"): self.exception.msg = self.errmsg return self def setResultsName( self, name, listAllMatches=False ): """Define name for referencing matching tokens as a nested attribute of the returned parse results. NOTE: this returns a *copy* of the original ParserElement object; this is so that the client can define a basic element, such as an integer, and reference it in multiple places with different names. """ newself = self.copy() newself.resultsName = name newself.modalResults = not listAllMatches return newself def setBreak(self,breakFlag = True): """Method to invoke the Python pdb debugger when this element is about to be parsed. Set breakFlag to True to enable, False to disable. """ if breakFlag: _parseMethod = self._parse def breaker(instring, loc, doActions=True, callPreParse=True): import pdb pdb.set_trace() return _parseMethod( instring, loc, doActions, callPreParse ) breaker._originalParseMethod = _parseMethod self._parse = breaker else: if hasattr(self._parse,"_originalParseMethod"): self._parse = self._parse._originalParseMethod return self def _normalizeParseActionArgs( f ): """Internal method used to decorate parse actions that take fewer than 3 arguments, so that all parse actions can be called as f(s,l,t).""" STAR_ARGS = 4 try: restore = None if isinstance(f,type): restore = f f = f.__init__ if not _PY3K: codeObj = f.func_code else: codeObj = f.code if codeObj.co_flags & STAR_ARGS: return f numargs = codeObj.co_argcount if not _PY3K: if hasattr(f,"im_self"): numargs -= 1 else: if hasattr(f,"__self__"): numargs -= 1 if restore: f = restore except AttributeError: try: if not _PY3K: call_im_func_code = f.__call__.im_func.func_code else: call_im_func_code = f.__code__ # not a function, must be a callable object, get info from the # im_func binding of its bound __call__ method if call_im_func_code.co_flags & STAR_ARGS: return f numargs = call_im_func_code.co_argcount if not _PY3K: if hasattr(f.__call__,"im_self"): numargs -= 1 else: if hasattr(f.__call__,"__self__"): numargs -= 0 except AttributeError: if not _PY3K: call_func_code = f.__call__.func_code else: call_func_code = f.__call__.__code__ # not a bound method, get info directly from __call__ method if call_func_code.co_flags & STAR_ARGS: return f numargs = call_func_code.co_argcount if not _PY3K: if hasattr(f.__call__,"im_self"): numargs -= 1 else: if hasattr(f.__call__,"__self__"): numargs -= 1 #~ print ("adding function %s with %d args" % (f.func_name,numargs)) if numargs == 3: return f else: if numargs > 3: def tmp(s,l,t): return f(f.__call__.__self__, s,l,t) if numargs == 2: def tmp(s,l,t): return f(l,t) elif numargs == 1: def tmp(s,l,t): return f(t) else: #~ numargs == 0: def tmp(s,l,t): return f() try: tmp.__name__ = f.__name__ except (AttributeError,TypeError): # no need for special handling if attribute doesnt exist pass try: tmp.__doc__ = f.__doc__ except (AttributeError,TypeError): # no need for special handling if attribute doesnt exist pass try: tmp.__dict__.update(f.__dict__) except (AttributeError,TypeError): # no need for special handling if attribute doesnt exist pass return tmp _normalizeParseActionArgs = staticmethod(_normalizeParseActionArgs) def setParseAction( self, *fns, **kwargs ): """Define action to perform when successfully matching parse element definition. Parse action fn is a callable method with 0-3 arguments, called as fn(s,loc,toks), fn(loc,toks), fn(toks), or just fn(), where: - s = the original string being parsed (see note below) - loc = the location of the matching substring - toks = a list of the matched tokens, packaged as a ParseResults object If the functions in fns modify the tokens, they can return them as the return value from fn, and the modified list of tokens will replace the original. Otherwise, fn does not need to return any value. Note: the default parsing behavior is to expand tabs in the input string before starting the parsing process. See L{I{parseString}} for more information on parsing strings containing s, and suggested methods to maintain a consistent view of the parsed string, the parse location, and line and column positions within the parsed string. """ self.parseAction = list(map(self._normalizeParseActionArgs, list(fns))) self.callDuringTry = ("callDuringTry" in kwargs and kwargs["callDuringTry"]) return self def addParseAction( self, *fns, **kwargs ): """Add parse action to expression's list of parse actions. See L{I{setParseAction}}.""" self.parseAction += list(map(self._normalizeParseActionArgs, list(fns))) self.callDuringTry = self.callDuringTry or ("callDuringTry" in kwargs and kwargs["callDuringTry"]) return self def setFailAction( self, fn ): """Define action to perform if parsing fails at this expression. Fail acton fn is a callable function that takes the arguments fn(s,loc,expr,err) where: - s = string being parsed - loc = location where expression match was attempted and failed - expr = the parse expression that failed - err = the exception thrown The function returns no value. It may throw ParseFatalException if it is desired to stop parsing immediately.""" self.failAction = fn return self def _skipIgnorables( self, instring, loc ): exprsFound = True while exprsFound: exprsFound = False for e in self.ignoreExprs: try: while 1: loc,dummy = e._parse( instring, loc ) exprsFound = True except ParseException: pass return loc def preParse( self, instring, loc ): if self.ignoreExprs: loc = self._skipIgnorables( instring, loc ) if self.skipWhitespace: wt = self.whiteChars instrlen = len(instring) while loc < instrlen and instring[loc] in wt: loc += 1 return loc def parseImpl( self, instring, loc, doActions=True ): return loc, [] def postParse( self, instring, loc, tokenlist ): return tokenlist #~ @profile def _parseNoCache( self, instring, loc, doActions=True, callPreParse=True ): debugging = ( self.debug ) #and doActions ) if debugging or self.failAction: #~ print ("Match",self,"at loc",loc,"(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )) if (self.debugActions[0] ): self.debugActions[0]( instring, loc, self ) if callPreParse and self.callPreparse: preloc = self.preParse( instring, loc ) else: preloc = loc tokensStart = loc try: try: loc,tokens = self.parseImpl( instring, preloc, doActions ) except IndexError: raise ParseException( instring, len(instring), self.errmsg, self ) except ParseBaseException, err: #~ print ("Exception raised:", err) if self.debugActions[2]: self.debugActions[2]( instring, tokensStart, self, err ) if self.failAction: self.failAction( instring, tokensStart, self, err ) raise else: if callPreParse and self.callPreparse: preloc = self.preParse( instring, loc ) else: preloc = loc tokensStart = loc if self.mayIndexError or loc >= len(instring): try: loc,tokens = self.parseImpl( instring, preloc, doActions ) except IndexError: raise ParseException( instring, len(instring), self.errmsg, self ) else: loc,tokens = self.parseImpl( instring, preloc, doActions ) tokens = self.postParse( instring, loc, tokens ) retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults ) if self.parseAction and (doActions or self.callDuringTry): if debugging: try: for fn in self.parseAction: tokens = fn( instring, tokensStart, retTokens ) if tokens is not None: retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList and isinstance(tokens,(ParseResults,list)), modal=self.modalResults ) except ParseBaseException, err: #~ print "Exception raised in user parse action:", err if (self.debugActions[2] ): self.debugActions[2]( instring, tokensStart, self, err ) raise else: for fn in self.parseAction: tokens = fn( instring, tokensStart, retTokens ) if tokens is not None: retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList and isinstance(tokens,(ParseResults,list)), modal=self.modalResults ) if debugging: #~ print ("Matched",self,"->",retTokens.asList()) if (self.debugActions[1] ): self.debugActions[1]( instring, tokensStart, loc, self, retTokens ) return loc, retTokens def tryParse( self, instring, loc ): try: return self._parse( instring, loc, doActions=False )[0] except ParseFatalException: raise ParseException( instring, loc, self.errmsg, self) # this method gets repeatedly called during backtracking with the same arguments - # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression def _parseCache( self, instring, loc, doActions=True, callPreParse=True ): lookup = (self,instring,loc,callPreParse,doActions) if lookup in ParserElement._exprArgCache: value = ParserElement._exprArgCache[ lookup ] if isinstance(value,Exception): raise value return value else: try: value = self._parseNoCache( instring, loc, doActions, callPreParse ) ParserElement._exprArgCache[ lookup ] = (value[0],value[1].copy()) return value except ParseBaseException, pe: ParserElement._exprArgCache[ lookup ] = pe raise _parse = _parseNoCache # argument cache for optimizing repeated calls when backtracking through recursive expressions _exprArgCache = {} def resetCache(): ParserElement._exprArgCache.clear() resetCache = staticmethod(resetCache) _packratEnabled = False def enablePackrat(): """Enables "packrat" parsing, which adds memoizing to the parsing logic. Repeated parse attempts at the same string location (which happens often in many complex grammars) can immediately return a cached value, instead of re-executing parsing/validating code. Memoizing is done of both valid results and parsing exceptions. This speedup may break existing programs that use parse actions that have side-effects. For this reason, packrat parsing is disabled when you first import pyparsing. To activate the packrat feature, your program must call the class method ParserElement.enablePackrat(). If your program uses psyco to "compile as you go", you must call enablePackrat before calling psyco.full(). If you do not do this, Python will crash. For best results, call enablePackrat() immediately after importing pyparsing. """ if not ParserElement._packratEnabled: ParserElement._packratEnabled = True ParserElement._parse = ParserElement._parseCache enablePackrat = staticmethod(enablePackrat) def parseString( self, instring, parseAll=False ): """Execute the parse expression with the given string. This is the main interface to the client code, once the complete expression has been built. If you want the grammar to require that the entire input string be successfully parsed, then set parseAll to True (equivalent to ending the grammar with StringEnd()). Note: parseString implicitly calls expandtabs() on the input string, in order to report proper column numbers in parse actions. If the input string contains tabs and the grammar uses parse actions that use the loc argument to index into the string being parsed, you can ensure you have a consistent view of the input string by: - calling parseWithTabs on your grammar before calling parseString (see L{I{parseWithTabs}}) - define your parse action using the full (s,loc,toks) signature, and reference the input string using the parse action's s argument - explictly expand the tabs in your input string before calling parseString """ ParserElement.resetCache() if not self.streamlined: self.streamline() #~ self.saveAsList = True for e in self.ignoreExprs: e.streamline() if not self.keepTabs: instring = instring.expandtabs() try: loc, tokens = self._parse( instring, 0 ) if parseAll: loc = self.preParse( instring, loc ) StringEnd()._parse( instring, loc ) except ParseBaseException, exc: # catch and re-raise exception from here, clears out pyparsing internal stack trace raise exc else: return tokens def scanString( self, instring, maxMatches=_MAX_INT ): """Scan the input string for expression matches. Each match will return the matching tokens, start location, and end location. May be called with optional maxMatches argument, to clip scanning after 'n' matches are found. Note that the start and end locations are reported relative to the string being parsed. See L{I{parseString}} for more information on parsing strings with embedded tabs.""" if not self.streamlined: self.streamline() for e in self.ignoreExprs: e.streamline() if not self.keepTabs: instring = _ustr(instring).expandtabs() instrlen = len(instring) loc = 0 preparseFn = self.preParse parseFn = self._parse ParserElement.resetCache() matches = 0 try: while loc <= instrlen and matches < maxMatches: try: preloc = preparseFn( instring, loc ) nextLoc,tokens = parseFn( instring, preloc, callPreParse=False ) except ParseException: loc = preloc+1 else: matches += 1 yield tokens, preloc, nextLoc loc = nextLoc except ParseBaseException, pe: raise pe def transformString( self, instring ): """Extension to scanString, to modify matching text with modified tokens that may be returned from a parse action. To use transformString, define a grammar and attach a parse action to it that modifies the returned token list. Invoking transformString() on a target string will then scan for matches, and replace the matched text patterns according to the logic in the parse action. transformString() returns the resulting transformed string.""" out = [] lastE = 0 # force preservation of s, to minimize unwanted transformation of string, and to # keep string locs straight between transformString and scanString self.keepTabs = True try: for t,s,e in self.scanString( instring ): out.append( instring[lastE:s] ) if t: if isinstance(t,ParseResults): out += t.asList() elif isinstance(t,list): out += t else: out.append(t) lastE = e out.append(instring[lastE:]) return "".join(map(_ustr,out)) except ParseBaseException, pe: raise pe def searchString( self, instring, maxMatches=_MAX_INT ): """Another extension to scanString, simplifying the access to the tokens found to match the given parse expression. May be called with optional maxMatches argument, to clip searching after 'n' matches are found. """ try: return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ]) except ParseBaseException, pe: raise pe def __add__(self, other ): """Implementation of + operator - returns And""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return And( [ self, other ] ) def __radd__(self, other ): """Implementation of + operator when left operand is not a ParserElement""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return other + self def __sub__(self, other): """Implementation of - operator, returns And with error stop""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return And( [ self, And._ErrorStop(), other ] ) def __rsub__(self, other ): """Implementation of - operator when left operand is not a ParserElement""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return other - self def __mul__(self,other): if isinstance(other,int): minElements, optElements = other,0 elif isinstance(other,tuple): other = (other + (None, None))[:2] if other[0] is None: other = (0, other[1]) if isinstance(other[0],int) and other[1] is None: if other[0] == 0: return ZeroOrMore(self) if other[0] == 1: return OneOrMore(self) else: return self*other[0] + ZeroOrMore(self) elif isinstance(other[0],int) and isinstance(other[1],int): minElements, optElements = other optElements -= minElements else: raise TypeError("cannot multiply 'ParserElement' and ('%s','%s') objects", type(other[0]),type(other[1])) else: raise TypeError("cannot multiply 'ParserElement' and '%s' objects", type(other)) if minElements < 0: raise ValueError("cannot multiply ParserElement by negative value") if optElements < 0: raise ValueError("second tuple value must be greater or equal to first tuple value") if minElements == optElements == 0: raise ValueError("cannot multiply ParserElement by 0 or (0,0)") if (optElements): def makeOptionalList(n): if n>1: return Optional(self + makeOptionalList(n-1)) else: return Optional(self) if minElements: if minElements == 1: ret = self + makeOptionalList(optElements) else: ret = And([self]*minElements) + makeOptionalList(optElements) else: ret = makeOptionalList(optElements) else: if minElements == 1: ret = self else: ret = And([self]*minElements) return ret def __rmul__(self, other): return self.__mul__(other) def __or__(self, other ): """Implementation of | operator - returns MatchFirst""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return MatchFirst( [ self, other ] ) def __ror__(self, other ): """Implementation of | operator when left operand is not a ParserElement""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return other | self def __xor__(self, other ): """Implementation of ^ operator - returns Or""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return Or( [ self, other ] ) def __rxor__(self, other ): """Implementation of ^ operator when left operand is not a ParserElement""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return other ^ self def __and__(self, other ): """Implementation of & operator - returns Each""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return Each( [ self, other ] ) def __rand__(self, other ): """Implementation of & operator when left operand is not a ParserElement""" if isinstance( other, basestring ): other = Literal( other ) if not isinstance( other, ParserElement ): warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), SyntaxWarning, stacklevel=2) return None return other & self def __invert__( self ): """Implementation of ~ operator - returns NotAny""" return NotAny( self ) def __call__(self, name): """Shortcut for setResultsName, with listAllMatches=default:: userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno") could be written as:: userdata = Word(alphas)("name") + Word(nums+"-")("socsecno") """ return self.setResultsName(name) def suppress( self ): """Suppresses the output of this ParserElement; useful to keep punctuation from cluttering up returned output. """ return Suppress( self ) def leaveWhitespace( self ): """Disables the skipping of whitespace before matching the characters in the ParserElement's defined pattern. This is normally only used internally by the pyparsing module, but may be needed in some whitespace-sensitive grammars. """ self.skipWhitespace = False return self def setWhitespaceChars( self, chars ): """Overrides the default whitespace chars """ self.skipWhitespace = True self.whiteChars = chars self.copyDefaultWhiteChars = False return self def parseWithTabs( self ): """Overrides default behavior to expand s to spaces before parsing the input string. Must be called before parseString when the input grammar contains elements that match characters.""" self.keepTabs = True return self def ignore( self, other ): """Define expression to be ignored (e.g., comments) while doing pattern matching; may be called repeatedly, to define multiple comment or other ignorable patterns. """ if isinstance( other, Suppress ): if other not in self.ignoreExprs: self.ignoreExprs.append( other ) else: self.ignoreExprs.append( Suppress( other ) ) return self def setDebugActions( self, startAction, successAction, exceptionAction ): """Enable display of debugging messages while doing pattern matching.""" self.debugActions = (startAction or _defaultStartDebugAction, successAction or _defaultSuccessDebugAction, exceptionAction or _defaultExceptionDebugAction) self.debug = True return self def setDebug( self, flag=True ): """Enable display of debugging messages while doing pattern matching. Set flag to True to enable, False to disable.""" if flag: self.setDebugActions( _defaultStartDebugAction, _defaultSuccessDebugAction, _defaultExceptionDebugAction ) else: self.debug = False return self def __str__( self ): return self.name def __repr__( self ): return _ustr(self) def streamline( self ): self.streamlined = True self.strRepr = None return self def checkRecursion( self, parseElementList ): pass def validate( self, validateTrace=[] ): """Check defined expressions for valid structure, check for infinite recursive definitions.""" self.checkRecursion( [] ) def parseFile( self, file_or_filename, parseAll=False ): """Execute the parse expression on the given file or filename. If a filename is specified (instead of a file object), the entire file is opened, read, and closed before parsing. """ try: file_contents = file_or_filename.read() except AttributeError: f = open(file_or_filename, "rb") file_contents = f.read() f.close() try: return self.parseString(file_contents, parseAll) except ParseBaseException, exc: # catch and re-raise exception from here, clears out pyparsing internal stack trace raise exc def getException(self): return ParseException("",0,self.errmsg,self) def __getattr__(self,aname): if aname == "myException": self.myException = ret = self.getException(); return ret; else: raise AttributeError("no such attribute " + aname) def __eq__(self,other): if isinstance(other, ParserElement): return self is other or self.__dict__ == other.__dict__ elif isinstance(other, basestring): try: self.parseString(_ustr(other), parseAll=True) return True except ParseBaseException: return False else: return super(ParserElement,self)==other def __ne__(self,other): return not (self == other) def __hash__(self): return hash(id(self)) def __req__(self,other): return self == other def __rne__(self,other): return not (self == other) class Token(ParserElement): """Abstract ParserElement subclass, for defining atomic matching patterns.""" def __init__( self ): super(Token,self).__init__( savelist=False ) #self.myException = ParseException("",0,"",self) def setName(self, name): s = super(Token,self).setName(name) self.errmsg = "Expected " + self.name #s.myException.msg = self.errmsg return s class Empty(Token): """An empty token, will always match.""" def __init__( self ): super(Empty,self).__init__() self.name = "Empty" self.mayReturnEmpty = True self.mayIndexError = False class NoMatch(Token): """A token that will never match.""" def __init__( self ): super(NoMatch,self).__init__() self.name = "NoMatch" self.mayReturnEmpty = True self.mayIndexError = False self.errmsg = "Unmatchable token" #self.myException.msg = self.errmsg def parseImpl( self, instring, loc, doActions=True ): exc = self.myException exc.loc = loc exc.pstr = instring raise exc class Literal(Token): """Token to exactly match a specified string.""" def __init__( self, matchString ): super(Literal,self).__init__() self.match = matchString self.matchLen = len(matchString) try: self.firstMatchChar = matchString[0] except IndexError: warnings.warn("null string passed to Literal; use Empty() instead", SyntaxWarning, stacklevel=2) self.__class__ = Empty self.name = '"%s"' % _ustr(self.match) self.errmsg = "Expected " + self.name self.mayReturnEmpty = False #self.myException.msg = self.errmsg self.mayIndexError = False # Performance tuning: this routine gets called a *lot* # if this is a single character match string and the first character matches, # short-circuit as quickly as possible, and avoid calling startswith #~ @profile def parseImpl( self, instring, loc, doActions=True ): if (instring[loc] == self.firstMatchChar and (self.matchLen==1 or instring.startswith(self.match,loc)) ): return loc+self.matchLen, self.match #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc _L = Literal class Keyword(Token): """Token to exactly match a specified string as a keyword, that is, it must be immediately followed by a non-keyword character. Compare with Literal:: Literal("if") will match the leading 'if' in 'ifAndOnlyIf'. Keyword("if") will not; it will only match the leading 'if in 'if x=1', or 'if(y==2)' Accepts two optional constructor arguments in addition to the keyword string: identChars is a string of characters that would be valid identifier characters, defaulting to all alphanumerics + "_" and "$"; caseless allows case-insensitive matching, default is False. """ DEFAULT_KEYWORD_CHARS = alphanums+"_$" def __init__( self, matchString, identChars=DEFAULT_KEYWORD_CHARS, caseless=False ): super(Keyword,self).__init__() self.match = matchString self.matchLen = len(matchString) try: self.firstMatchChar = matchString[0] except IndexError: warnings.warn("null string passed to Keyword; use Empty() instead", SyntaxWarning, stacklevel=2) self.name = '"%s"' % self.match self.errmsg = "Expected " + self.name self.mayReturnEmpty = False #self.myException.msg = self.errmsg self.mayIndexError = False self.caseless = caseless if caseless: self.caselessmatch = matchString.upper() identChars = identChars.upper() self.identChars = _str2dict(identChars) def parseImpl( self, instring, loc, doActions=True ): if self.caseless: if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) and (loc == 0 or instring[loc-1].upper() not in self.identChars) ): return loc+self.matchLen, self.match else: if (instring[loc] == self.firstMatchChar and (self.matchLen==1 or instring.startswith(self.match,loc)) and (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen] not in self.identChars) and (loc == 0 or instring[loc-1] not in self.identChars) ): return loc+self.matchLen, self.match #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc def copy(self): c = super(Keyword,self).copy() c.identChars = Keyword.DEFAULT_KEYWORD_CHARS return c def setDefaultKeywordChars( chars ): """Overrides the default Keyword chars """ Keyword.DEFAULT_KEYWORD_CHARS = chars setDefaultKeywordChars = staticmethod(setDefaultKeywordChars) class CaselessLiteral(Literal): """Token to match a specified string, ignoring case of letters. Note: the matched results will always be in the case of the given match string, NOT the case of the input text. """ def __init__( self, matchString ): super(CaselessLiteral,self).__init__( matchString.upper() ) # Preserve the defining literal. self.returnString = matchString self.name = "'%s'" % self.returnString self.errmsg = "Expected " + self.name #self.myException.msg = self.errmsg def parseImpl( self, instring, loc, doActions=True ): if instring[ loc:loc+self.matchLen ].upper() == self.match: return loc+self.matchLen, self.returnString #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc class CaselessKeyword(Keyword): def __init__( self, matchString, identChars=Keyword.DEFAULT_KEYWORD_CHARS ): super(CaselessKeyword,self).__init__( matchString, identChars, caseless=True ) def parseImpl( self, instring, loc, doActions=True ): if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) ): return loc+self.matchLen, self.match #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc class Word(Token): """Token for matching words composed of allowed character sets. Defined with string containing all allowed initial characters, an optional string containing allowed body characters (if omitted, defaults to the initial character set), and an optional minimum, maximum, and/or exact length. The default value for min is 1 (a minimum value < 1 is not valid); the default values for max and exact are 0, meaning no maximum or exact length restriction. """ def __init__( self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False ): super(Word,self).__init__() self.initCharsOrig = initChars self.initChars = _str2dict(initChars) if bodyChars : self.bodyCharsOrig = bodyChars self.bodyChars = _str2dict(bodyChars) else: self.bodyCharsOrig = initChars self.bodyChars = _str2dict(initChars) self.maxSpecified = max > 0 if min < 1: raise ValueError("cannot specify a minimum length < 1; use Optional(Word()) if zero-length word is permitted") self.minLen = min if max > 0: self.maxLen = max else: self.maxLen = _MAX_INT if exact > 0: self.maxLen = exact self.minLen = exact self.name = _ustr(self) self.errmsg = "Expected " + self.name #self.myException.msg = self.errmsg self.mayIndexError = False self.asKeyword = asKeyword if ' ' not in self.initCharsOrig+self.bodyCharsOrig and (min==1 and max==0 and exact==0): if self.bodyCharsOrig == self.initCharsOrig: self.reString = "[%s]+" % _escapeRegexRangeChars(self.initCharsOrig) elif len(self.bodyCharsOrig) == 1: self.reString = "%s[%s]*" % \ (re.escape(self.initCharsOrig), _escapeRegexRangeChars(self.bodyCharsOrig),) else: self.reString = "[%s][%s]*" % \ (_escapeRegexRangeChars(self.initCharsOrig), _escapeRegexRangeChars(self.bodyCharsOrig),) if self.asKeyword: self.reString = r"\b"+self.reString+r"\b" try: self.re = re.compile( self.reString ) except: self.re = None def parseImpl( self, instring, loc, doActions=True ): if self.re: result = self.re.match(instring,loc) if not result: exc = self.myException exc.loc = loc exc.pstr = instring raise exc loc = result.end() return loc,result.group() if not(instring[ loc ] in self.initChars): #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc start = loc loc += 1 instrlen = len(instring) bodychars = self.bodyChars maxloc = start + self.maxLen maxloc = min( maxloc, instrlen ) while loc < maxloc and instring[loc] in bodychars: loc += 1 throwException = False if loc - start < self.minLen: throwException = True if self.maxSpecified and loc < instrlen and instring[loc] in bodychars: throwException = True if self.asKeyword: if (start>0 and instring[start-1] in bodychars) or (loc4: return s[:4]+"..." else: return s if ( self.initCharsOrig != self.bodyCharsOrig ): self.strRepr = "W:(%s,%s)" % ( charsAsStr(self.initCharsOrig), charsAsStr(self.bodyCharsOrig) ) else: self.strRepr = "W:(%s)" % charsAsStr(self.initCharsOrig) return self.strRepr class Regex(Token): """Token for matching strings that match a given regular expression. Defined with string specifying the regular expression in a form recognized by the inbuilt Python re module. """ def __init__( self, pattern, flags=0): """The parameters pattern and flags are passed to the re.compile() function as-is. See the Python re module for an explanation of the acceptable patterns and flags.""" super(Regex,self).__init__() if len(pattern) == 0: warnings.warn("null string passed to Regex; use Empty() instead", SyntaxWarning, stacklevel=2) self.pattern = pattern self.flags = flags try: self.re = re.compile(self.pattern, self.flags) self.reString = self.pattern except sre_constants.error: warnings.warn("invalid pattern (%s) passed to Regex" % pattern, SyntaxWarning, stacklevel=2) raise self.name = _ustr(self) self.errmsg = "Expected " + self.name #self.myException.msg = self.errmsg self.mayIndexError = False self.mayReturnEmpty = True def parseImpl( self, instring, loc, doActions=True ): result = self.re.match(instring,loc) if not result: exc = self.myException exc.loc = loc exc.pstr = instring raise exc loc = result.end() d = result.groupdict() ret = ParseResults(result.group()) if d: for k in d: ret[k] = d[k] return loc,ret def __str__( self ): try: return super(Regex,self).__str__() except: pass if self.strRepr is None: self.strRepr = "Re:(%s)" % repr(self.pattern) return self.strRepr class QuotedString(Token): """Token for matching strings that are delimited by quoting characters. """ def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None): """ Defined with the following parameters: - quoteChar - string of one or more characters defining the quote delimiting string - escChar - character to escape quotes, typically backslash (default=None) - escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=None) - multiline - boolean indicating whether quotes can span multiple lines (default=False) - unquoteResults - boolean indicating whether the matched text should be unquoted (default=True) - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=None => same as quoteChar) """ super(QuotedString,self).__init__() # remove white space from quote chars - wont work anyway quoteChar = quoteChar.strip() if len(quoteChar) == 0: warnings.warn("quoteChar cannot be the empty string",SyntaxWarning,stacklevel=2) raise SyntaxError() if endQuoteChar is None: endQuoteChar = quoteChar else: endQuoteChar = endQuoteChar.strip() if len(endQuoteChar) == 0: warnings.warn("endQuoteChar cannot be the empty string",SyntaxWarning,stacklevel=2) raise SyntaxError() self.quoteChar = quoteChar self.quoteCharLen = len(quoteChar) self.firstQuoteChar = quoteChar[0] self.endQuoteChar = endQuoteChar self.endQuoteCharLen = len(endQuoteChar) self.escChar = escChar self.escQuote = escQuote self.unquoteResults = unquoteResults if multiline: self.flags = re.MULTILINE | re.DOTALL self.pattern = r'%s(?:[^%s%s]' % \ ( re.escape(self.quoteChar), _escapeRegexRangeChars(self.endQuoteChar[0]), (escChar is not None and _escapeRegexRangeChars(escChar) or '') ) else: self.flags = 0 self.pattern = r'%s(?:[^%s\n\r%s]' % \ ( re.escape(self.quoteChar), _escapeRegexRangeChars(self.endQuoteChar[0]), (escChar is not None and _escapeRegexRangeChars(escChar) or '') ) if len(self.endQuoteChar) > 1: self.pattern += ( '|(?:' + ')|(?:'.join(["%s[^%s]" % (re.escape(self.endQuoteChar[:i]), _escapeRegexRangeChars(self.endQuoteChar[i])) for i in range(len(self.endQuoteChar)-1,0,-1)]) + ')' ) if escQuote: self.pattern += (r'|(?:%s)' % re.escape(escQuote)) if escChar: self.pattern += (r'|(?:%s.)' % re.escape(escChar)) self.escCharReplacePattern = re.escape(self.escChar)+"(.)" self.pattern += (r')*%s' % re.escape(self.endQuoteChar)) try: self.re = re.compile(self.pattern, self.flags) self.reString = self.pattern except sre_constants.error: warnings.warn("invalid pattern (%s) passed to Regex" % self.pattern, SyntaxWarning, stacklevel=2) raise self.name = _ustr(self) self.errmsg = "Expected " + self.name #self.myException.msg = self.errmsg self.mayIndexError = False self.mayReturnEmpty = True def parseImpl( self, instring, loc, doActions=True ): result = instring[loc] == self.firstQuoteChar and self.re.match(instring,loc) or None if not result: exc = self.myException exc.loc = loc exc.pstr = instring raise exc loc = result.end() ret = result.group() if self.unquoteResults: # strip off quotes ret = ret[self.quoteCharLen:-self.endQuoteCharLen] if isinstance(ret,basestring): # replace escaped characters if self.escChar: ret = re.sub(self.escCharReplacePattern,"\g<1>",ret) # replace escaped quotes if self.escQuote: ret = ret.replace(self.escQuote, self.endQuoteChar) return loc, ret def __str__( self ): try: return super(QuotedString,self).__str__() except: pass if self.strRepr is None: self.strRepr = "quoted string, starting with %s ending with %s" % (self.quoteChar, self.endQuoteChar) return self.strRepr class CharsNotIn(Token): """Token for matching words composed of characters *not* in a given set. Defined with string containing all disallowed characters, and an optional minimum, maximum, and/or exact length. The default value for min is 1 (a minimum value < 1 is not valid); the default values for max and exact are 0, meaning no maximum or exact length restriction. """ def __init__( self, notChars, min=1, max=0, exact=0 ): super(CharsNotIn,self).__init__() self.skipWhitespace = False self.notChars = notChars if min < 1: raise ValueError("cannot specify a minimum length < 1; use Optional(CharsNotIn()) if zero-length char group is permitted") self.minLen = min if max > 0: self.maxLen = max else: self.maxLen = _MAX_INT if exact > 0: self.maxLen = exact self.minLen = exact self.name = _ustr(self) self.errmsg = "Expected " + self.name self.mayReturnEmpty = ( self.minLen == 0 ) #self.myException.msg = self.errmsg self.mayIndexError = False def parseImpl( self, instring, loc, doActions=True ): if instring[loc] in self.notChars: #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc start = loc loc += 1 notchars = self.notChars maxlen = min( start+self.maxLen, len(instring) ) while loc < maxlen and \ (instring[loc] not in notchars): loc += 1 if loc - start < self.minLen: #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc return loc, instring[start:loc] def __str__( self ): try: return super(CharsNotIn, self).__str__() except: pass if self.strRepr is None: if len(self.notChars) > 4: self.strRepr = "!W:(%s...)" % self.notChars[:4] else: self.strRepr = "!W:(%s)" % self.notChars return self.strRepr class White(Token): """Special matching class for matching whitespace. Normally, whitespace is ignored by pyparsing grammars. This class is included when some whitespace structures are significant. Define with a string containing the whitespace characters to be matched; default is " \\t\\r\\n". Also takes optional min, max, and exact arguments, as defined for the Word class.""" whiteStrs = { " " : "", "\t": "", "\n": "", "\r": "", "\f": "", } def __init__(self, ws=" \t\r\n", min=1, max=0, exact=0): super(White,self).__init__() self.matchWhite = ws self.setWhitespaceChars( "".join([c for c in self.whiteChars if c not in self.matchWhite]) ) #~ self.leaveWhitespace() self.name = ("".join([White.whiteStrs[c] for c in self.matchWhite])) self.mayReturnEmpty = True self.errmsg = "Expected " + self.name #self.myException.msg = self.errmsg self.minLen = min if max > 0: self.maxLen = max else: self.maxLen = _MAX_INT if exact > 0: self.maxLen = exact self.minLen = exact def parseImpl( self, instring, loc, doActions=True ): if not(instring[ loc ] in self.matchWhite): #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc start = loc loc += 1 maxloc = start + self.maxLen maxloc = min( maxloc, len(instring) ) while loc < maxloc and instring[loc] in self.matchWhite: loc += 1 if loc - start < self.minLen: #~ raise ParseException( instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc return loc, instring[start:loc] class _PositionToken(Token): def __init__( self ): super(_PositionToken,self).__init__() self.name=self.__class__.__name__ self.mayReturnEmpty = True self.mayIndexError = False class GoToColumn(_PositionToken): """Token to advance to a specific column of input text; useful for tabular report scraping.""" def __init__( self, colno ): super(GoToColumn,self).__init__() self.col = colno def preParse( self, instring, loc ): if col(loc,instring) != self.col: instrlen = len(instring) if self.ignoreExprs: loc = self._skipIgnorables( instring, loc ) while loc < instrlen and instring[loc].isspace() and col( loc, instring ) != self.col : loc += 1 return loc def parseImpl( self, instring, loc, doActions=True ): thiscol = col( loc, instring ) if thiscol > self.col: raise ParseException( instring, loc, "Text not in expected column", self ) newloc = loc + self.col - thiscol ret = instring[ loc: newloc ] return newloc, ret class LineStart(_PositionToken): """Matches if current position is at the beginning of a line within the parse string""" def __init__( self ): super(LineStart,self).__init__() self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) self.errmsg = "Expected start of line" #self.myException.msg = self.errmsg def preParse( self, instring, loc ): preloc = super(LineStart,self).preParse(instring,loc) if instring[preloc] == "\n": loc += 1 return loc def parseImpl( self, instring, loc, doActions=True ): if not( loc==0 or (loc == self.preParse( instring, 0 )) or (instring[loc-1] == "\n") ): #col(loc, instring) != 1: #~ raise ParseException( instring, loc, "Expected start of line" ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc return loc, [] class LineEnd(_PositionToken): """Matches if current position is at the end of a line within the parse string""" def __init__( self ): super(LineEnd,self).__init__() self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) self.errmsg = "Expected end of line" #self.myException.msg = self.errmsg def parseImpl( self, instring, loc, doActions=True ): if loc len(instring): return loc, [] else: exc = self.myException exc.loc = loc exc.pstr = instring raise exc class WordStart(_PositionToken): """Matches if the current position is at the beginning of a Word, and is not preceded by any character in a given set of wordChars (default=printables). To emulate the \b behavior of regular expressions, use WordStart(alphanums). WordStart will also match at the beginning of the string being parsed, or at the beginning of a line. """ def __init__(self, wordChars = printables): super(WordStart,self).__init__() self.wordChars = _str2dict(wordChars) self.errmsg = "Not at the start of a word" def parseImpl(self, instring, loc, doActions=True ): if loc != 0: if (instring[loc-1] in self.wordChars or instring[loc] not in self.wordChars): exc = self.myException exc.loc = loc exc.pstr = instring raise exc return loc, [] class WordEnd(_PositionToken): """Matches if the current position is at the end of a Word, and is not followed by any character in a given set of wordChars (default=printables). To emulate the \b behavior of regular expressions, use WordEnd(alphanums). WordEnd will also match at the end of the string being parsed, or at the end of a line. """ def __init__(self, wordChars = printables): super(WordEnd,self).__init__() self.wordChars = _str2dict(wordChars) self.skipWhitespace = False self.errmsg = "Not at the end of a word" def parseImpl(self, instring, loc, doActions=True ): instrlen = len(instring) if instrlen>0 and loc maxExcLoc: maxException = err maxExcLoc = err.loc except IndexError: if len(instring) > maxExcLoc: maxException = ParseException(instring,len(instring),e.errmsg,self) maxExcLoc = len(instring) else: if loc2 > maxMatchLoc: maxMatchLoc = loc2 maxMatchExp = e if maxMatchLoc < 0: if maxException is not None: raise maxException else: raise ParseException(instring, loc, "no defined alternatives to match", self) return maxMatchExp._parse( instring, loc, doActions ) def __ixor__(self, other ): if isinstance( other, basestring ): other = Literal( other ) return self.append( other ) #Or( [ self, other ] ) def __str__( self ): if hasattr(self,"name"): return self.name if self.strRepr is None: self.strRepr = "{" + " ^ ".join( [ _ustr(e) for e in self.exprs ] ) + "}" return self.strRepr def checkRecursion( self, parseElementList ): subRecCheckList = parseElementList[:] + [ self ] for e in self.exprs: e.checkRecursion( subRecCheckList ) class MatchFirst(ParseExpression): """Requires that at least one ParseExpression is found. If two expressions match, the first one listed is the one that will match. May be constructed using the '|' operator. """ def __init__( self, exprs, savelist = False ): super(MatchFirst,self).__init__(exprs, savelist) if exprs: self.mayReturnEmpty = False for e in self.exprs: if e.mayReturnEmpty: self.mayReturnEmpty = True break else: self.mayReturnEmpty = True def parseImpl( self, instring, loc, doActions=True ): maxExcLoc = -1 maxException = None for e in self.exprs: try: ret = e._parse( instring, loc, doActions ) return ret except ParseException, err: if err.loc > maxExcLoc: maxException = err maxExcLoc = err.loc except IndexError: if len(instring) > maxExcLoc: maxException = ParseException(instring,len(instring),e.errmsg,self) maxExcLoc = len(instring) # only got here if no expression matched, raise exception for match that made it the furthest else: if maxException is not None: raise maxException else: raise ParseException(instring, loc, "no defined alternatives to match", self) def __ior__(self, other ): if isinstance( other, basestring ): other = Literal( other ) return self.append( other ) #MatchFirst( [ self, other ] ) def __str__( self ): if hasattr(self,"name"): return self.name if self.strRepr is None: self.strRepr = "{" + " | ".join( [ _ustr(e) for e in self.exprs ] ) + "}" return self.strRepr def checkRecursion( self, parseElementList ): subRecCheckList = parseElementList[:] + [ self ] for e in self.exprs: e.checkRecursion( subRecCheckList ) class Each(ParseExpression): """Requires all given ParseExpressions to be found, but in any order. Expressions may be separated by whitespace. May be constructed using the '&' operator. """ def __init__( self, exprs, savelist = True ): super(Each,self).__init__(exprs, savelist) self.mayReturnEmpty = True for e in self.exprs: if not e.mayReturnEmpty: self.mayReturnEmpty = False break self.skipWhitespace = True self.initExprGroups = True def parseImpl( self, instring, loc, doActions=True ): if self.initExprGroups: self.optionals = [ e.expr for e in self.exprs if isinstance(e,Optional) ] self.multioptionals = [ e.expr for e in self.exprs if isinstance(e,ZeroOrMore) ] self.multirequired = [ e.expr for e in self.exprs if isinstance(e,OneOrMore) ] self.required = [ e for e in self.exprs if not isinstance(e,(Optional,ZeroOrMore,OneOrMore)) ] self.required += self.multirequired self.initExprGroups = False tmpLoc = loc tmpReqd = self.required[:] tmpOpt = self.optionals[:] matchOrder = [] keepMatching = True while keepMatching: tmpExprs = tmpReqd + tmpOpt + self.multioptionals + self.multirequired failed = [] for e in tmpExprs: try: tmpLoc = e.tryParse( instring, tmpLoc ) except ParseException: failed.append(e) else: matchOrder.append(e) if e in tmpReqd: tmpReqd.remove(e) elif e in tmpOpt: tmpOpt.remove(e) if len(failed) == len(tmpExprs): keepMatching = False if tmpReqd: missing = ", ".join( [ _ustr(e) for e in tmpReqd ] ) raise ParseException(instring,loc,"Missing one or more required elements (%s)" % missing ) # add any unmatched Optionals, in case they have default values defined matchOrder += list(e for e in self.exprs if isinstance(e,Optional) and e.expr in tmpOpt) resultlist = [] for e in matchOrder: loc,results = e._parse(instring,loc,doActions) resultlist.append(results) finalResults = ParseResults([]) for r in resultlist: dups = {} for k in r.keys(): if k in finalResults.keys(): tmp = ParseResults(finalResults[k]) tmp += ParseResults(r[k]) dups[k] = tmp finalResults += ParseResults(r) for k,v in dups.items(): finalResults[k] = v return loc, finalResults def __str__( self ): if hasattr(self,"name"): return self.name if self.strRepr is None: self.strRepr = "{" + " & ".join( [ _ustr(e) for e in self.exprs ] ) + "}" return self.strRepr def checkRecursion( self, parseElementList ): subRecCheckList = parseElementList[:] + [ self ] for e in self.exprs: e.checkRecursion( subRecCheckList ) class ParseElementEnhance(ParserElement): """Abstract subclass of ParserElement, for combining and post-processing parsed tokens.""" def __init__( self, expr, savelist=False ): super(ParseElementEnhance,self).__init__(savelist) if isinstance( expr, basestring ): expr = Literal(expr) self.expr = expr self.strRepr = None if expr is not None: self.mayIndexError = expr.mayIndexError self.mayReturnEmpty = expr.mayReturnEmpty self.setWhitespaceChars( expr.whiteChars ) self.skipWhitespace = expr.skipWhitespace self.saveAsList = expr.saveAsList self.callPreparse = expr.callPreparse self.ignoreExprs.extend(expr.ignoreExprs) def parseImpl( self, instring, loc, doActions=True ): if self.expr is not None: return self.expr._parse( instring, loc, doActions, callPreParse=False ) else: raise ParseException("",loc,self.errmsg,self) def leaveWhitespace( self ): self.skipWhitespace = False self.expr = self.expr.copy() if self.expr is not None: self.expr.leaveWhitespace() return self def ignore( self, other ): if isinstance( other, Suppress ): if other not in self.ignoreExprs: super( ParseElementEnhance, self).ignore( other ) if self.expr is not None: self.expr.ignore( self.ignoreExprs[-1] ) else: super( ParseElementEnhance, self).ignore( other ) if self.expr is not None: self.expr.ignore( self.ignoreExprs[-1] ) return self def streamline( self ): super(ParseElementEnhance,self).streamline() if self.expr is not None: self.expr.streamline() return self def checkRecursion( self, parseElementList ): if self in parseElementList: raise RecursiveGrammarException( parseElementList+[self] ) subRecCheckList = parseElementList[:] + [ self ] if self.expr is not None: self.expr.checkRecursion( subRecCheckList ) def validate( self, validateTrace=[] ): tmp = validateTrace[:]+[self] if self.expr is not None: self.expr.validate(tmp) self.checkRecursion( [] ) def __str__( self ): try: return super(ParseElementEnhance,self).__str__() except: pass if self.strRepr is None and self.expr is not None: self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.expr) ) return self.strRepr class FollowedBy(ParseElementEnhance): """Lookahead matching of the given parse expression. FollowedBy does *not* advance the parsing position within the input string, it only verifies that the specified parse expression matches at the current position. FollowedBy always returns a null token list.""" def __init__( self, expr ): super(FollowedBy,self).__init__(expr) self.mayReturnEmpty = True def parseImpl( self, instring, loc, doActions=True ): self.expr.tryParse( instring, loc ) return loc, [] class NotAny(ParseElementEnhance): """Lookahead to disallow matching with the given parse expression. NotAny does *not* advance the parsing position within the input string, it only verifies that the specified parse expression does *not* match at the current position. Also, NotAny does *not* skip over leading whitespace. NotAny always returns a null token list. May be constructed using the '~' operator.""" def __init__( self, expr ): super(NotAny,self).__init__(expr) #~ self.leaveWhitespace() self.skipWhitespace = False # do NOT use self.leaveWhitespace(), don't want to propagate to exprs self.mayReturnEmpty = True self.errmsg = "Found unwanted token, "+_ustr(self.expr) #self.myException = ParseException("",0,self.errmsg,self) def parseImpl( self, instring, loc, doActions=True ): try: self.expr.tryParse( instring, loc ) except (ParseException,IndexError): pass else: #~ raise ParseException(instring, loc, self.errmsg ) exc = self.myException exc.loc = loc exc.pstr = instring raise exc return loc, [] def __str__( self ): if hasattr(self,"name"): return self.name if self.strRepr is None: self.strRepr = "~{" + _ustr(self.expr) + "}" return self.strRepr class ZeroOrMore(ParseElementEnhance): """Optional repetition of zero or more of the given expression.""" def __init__( self, expr ): super(ZeroOrMore,self).__init__(expr) self.mayReturnEmpty = True def parseImpl( self, instring, loc, doActions=True ): tokens = [] try: loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) hasIgnoreExprs = ( len(self.ignoreExprs) > 0 ) while 1: if hasIgnoreExprs: preloc = self._skipIgnorables( instring, loc ) else: preloc = loc loc, tmptokens = self.expr._parse( instring, preloc, doActions ) if tmptokens or tmptokens.keys(): tokens += tmptokens except (ParseException,IndexError): pass return loc, tokens def __str__( self ): if hasattr(self,"name"): return self.name if self.strRepr is None: self.strRepr = "[" + _ustr(self.expr) + "]..." return self.strRepr def setResultsName( self, name, listAllMatches=False ): ret = super(ZeroOrMore,self).setResultsName(name,listAllMatches) ret.saveAsList = True return ret class OneOrMore(ParseElementEnhance): """Repetition of one or more of the given expression.""" def parseImpl( self, instring, loc, doActions=True ): # must be at least one loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) try: hasIgnoreExprs = ( len(self.ignoreExprs) > 0 ) while 1: if hasIgnoreExprs: preloc = self._skipIgnorables( instring, loc ) else: preloc = loc loc, tmptokens = self.expr._parse( instring, preloc, doActions ) if tmptokens or tmptokens.keys(): tokens += tmptokens except (ParseException,IndexError): pass return loc, tokens def __str__( self ): if hasattr(self,"name"): return self.name if self.strRepr is None: self.strRepr = "{" + _ustr(self.expr) + "}..." return self.strRepr def setResultsName( self, name, listAllMatches=False ): ret = super(OneOrMore,self).setResultsName(name,listAllMatches) ret.saveAsList = True return ret class _NullToken(object): def __bool__(self): return False __nonzero__ = __bool__ def __str__(self): return "" _optionalNotMatched = _NullToken() class Optional(ParseElementEnhance): """Optional matching of the given expression. A default return string can also be specified, if the optional expression is not found. """ def __init__( self, exprs, default=_optionalNotMatched ): super(Optional,self).__init__( exprs, savelist=False ) self.defaultValue = default self.mayReturnEmpty = True def parseImpl( self, instring, loc, doActions=True ): try: loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) except (ParseException,IndexError): if self.defaultValue is not _optionalNotMatched: if self.expr.resultsName: tokens = ParseResults([ self.defaultValue ]) tokens[self.expr.resultsName] = self.defaultValue else: tokens = [ self.defaultValue ] else: tokens = [] return loc, tokens def __str__( self ): if hasattr(self,"name"): return self.name if self.strRepr is None: self.strRepr = "[" + _ustr(self.expr) + "]" return self.strRepr class SkipTo(ParseElementEnhance): """Token for skipping over all undefined text until the matched expression is found. If include is set to true, the matched expression is also parsed (the skipped text and matched expression are returned as a 2-element list). The ignore argument is used to define grammars (typically quoted strings and comments) that might contain false matches. """ def __init__( self, other, include=False, ignore=None, failOn=None ): super( SkipTo, self ).__init__( other ) self.ignoreExpr = ignore self.mayReturnEmpty = True self.mayIndexError = False self.includeMatch = include self.asList = False if failOn is not None and isinstance(failOn, basestring): self.failOn = Literal(failOn) else: self.failOn = failOn self.errmsg = "No match found for "+_ustr(self.expr) #self.myException = ParseException("",0,self.errmsg,self) def parseImpl( self, instring, loc, doActions=True ): startLoc = loc instrlen = len(instring) expr = self.expr failParse = False while loc <= instrlen: try: if self.failOn: try: self.failOn.tryParse(instring, loc) except ParseBaseException: pass else: failParse = True raise ParseException(instring, loc, "Found expression " + str(self.failOn)) failParse = False if self.ignoreExpr is not None: while 1: try: loc = self.ignoreExpr.tryParse(instring,loc) print "found ignoreExpr, advance to", loc except ParseBaseException: break expr._parse( instring, loc, doActions=False, callPreParse=False ) skipText = instring[startLoc:loc] if self.includeMatch: loc,mat = expr._parse(instring,loc,doActions,callPreParse=False) if mat: skipRes = ParseResults( skipText ) skipRes += mat return loc, [ skipRes ] else: return loc, [ skipText ] else: return loc, [ skipText ] except (ParseException,IndexError): if failParse: raise else: loc += 1 exc = self.myException exc.loc = loc exc.pstr = instring raise exc class Forward(ParseElementEnhance): """Forward declaration of an expression to be defined later - used for recursive grammars, such as algebraic infix notation. When the expression is known, it is assigned to the Forward variable using the '<<' operator. Note: take care when assigning to Forward not to overlook precedence of operators. Specifically, '|' has a lower precedence than '<<', so that:: fwdExpr << a | b | c will actually be evaluated as:: (fwdExpr << a) | b | c thereby leaving b and c out as parseable alternatives. It is recommended that you explicitly group the values inserted into the Forward:: fwdExpr << (a | b | c) """ def __init__( self, other=None ): super(Forward,self).__init__( other, savelist=False ) def __lshift__( self, other ): if isinstance( other, basestring ): other = Literal(other) self.expr = other self.mayReturnEmpty = other.mayReturnEmpty self.strRepr = None self.mayIndexError = self.expr.mayIndexError self.mayReturnEmpty = self.expr.mayReturnEmpty self.setWhitespaceChars( self.expr.whiteChars ) self.skipWhitespace = self.expr.skipWhitespace self.saveAsList = self.expr.saveAsList self.ignoreExprs.extend(self.expr.ignoreExprs) return None def leaveWhitespace( self ): self.skipWhitespace = False return self def streamline( self ): if not self.streamlined: self.streamlined = True if self.expr is not None: self.expr.streamline() return self def validate( self, validateTrace=[] ): if self not in validateTrace: tmp = validateTrace[:]+[self] if self.expr is not None: self.expr.validate(tmp) self.checkRecursion([]) def __str__( self ): if hasattr(self,"name"): return self.name self._revertClass = self.__class__ self.__class__ = _ForwardNoRecurse try: if self.expr is not None: retString = _ustr(self.expr) else: retString = "None" finally: self.__class__ = self._revertClass return self.__class__.__name__ + ": " + retString def copy(self): if self.expr is not None: return super(Forward,self).copy() else: ret = Forward() ret << self return ret class _ForwardNoRecurse(Forward): def __str__( self ): return "..." class TokenConverter(ParseElementEnhance): """Abstract subclass of ParseExpression, for converting parsed results.""" def __init__( self, expr, savelist=False ): super(TokenConverter,self).__init__( expr )#, savelist ) self.saveAsList = False class Upcase(TokenConverter): """Converter to upper case all matching tokens.""" def __init__(self, *args): super(Upcase,self).__init__(*args) warnings.warn("Upcase class is deprecated, use upcaseTokens parse action instead", DeprecationWarning,stacklevel=2) def postParse( self, instring, loc, tokenlist ): return list(map( string.upper, tokenlist )) class Combine(TokenConverter): """Converter to concatenate all matching tokens to a single string. By default, the matching patterns must also be contiguous in the input string; this can be disabled by specifying 'adjacent=False' in the constructor. """ def __init__( self, expr, joinString="", adjacent=True ): super(Combine,self).__init__( expr ) # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself if adjacent: self.leaveWhitespace() self.adjacent = adjacent self.skipWhitespace = True self.joinString = joinString def ignore( self, other ): if self.adjacent: ParserElement.ignore(self, other) else: super( Combine, self).ignore( other ) return self def postParse( self, instring, loc, tokenlist ): retToks = tokenlist.copy() del retToks[:] retToks += ParseResults([ "".join(tokenlist._asStringList(self.joinString)) ], modal=self.modalResults) if self.resultsName and len(retToks.keys())>0: return [ retToks ] else: return retToks class Group(TokenConverter): """Converter to return the matched tokens as a list - useful for returning tokens of ZeroOrMore and OneOrMore expressions.""" def __init__( self, expr ): super(Group,self).__init__( expr ) self.saveAsList = True def postParse( self, instring, loc, tokenlist ): return [ tokenlist ] class Dict(TokenConverter): """Converter to return a repetitive expression as a list, but also as a dictionary. Each element can also be referenced using the first token in the expression as its key. Useful for tabular report scraping when the first column can be used as a item key. """ def __init__( self, exprs ): super(Dict,self).__init__( exprs ) self.saveAsList = True def postParse( self, instring, loc, tokenlist ): for i,tok in enumerate(tokenlist): if len(tok) == 0: continue ikey = tok[0] if isinstance(ikey,int): ikey = _ustr(tok[0]).strip() if len(tok)==1: tokenlist[ikey] = _ParseResultsWithOffset("",i) elif len(tok)==2 and not isinstance(tok[1],ParseResults): tokenlist[ikey] = _ParseResultsWithOffset(tok[1],i) else: dictvalue = tok.copy() #ParseResults(i) del dictvalue[0] if len(dictvalue)!= 1 or (isinstance(dictvalue,ParseResults) and dictvalue.keys()): tokenlist[ikey] = _ParseResultsWithOffset(dictvalue,i) else: tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0],i) if self.resultsName: return [ tokenlist ] else: return tokenlist class Suppress(TokenConverter): """Converter for ignoring the results of a parsed expression.""" def postParse( self, instring, loc, tokenlist ): return [] def suppress( self ): return self class OnlyOnce(object): """Wrapper for parse actions, to ensure they are only called once.""" def __init__(self, methodCall): self.callable = ParserElement._normalizeParseActionArgs(methodCall) self.called = False def __call__(self,s,l,t): if not self.called: results = self.callable(s,l,t) self.called = True return results raise ParseException(s,l,"") def reset(self): self.called = False def traceParseAction(f): """Decorator for debugging parse actions.""" f = ParserElement._normalizeParseActionArgs(f) def z(*paArgs): thisFunc = f.func_name s,l,t = paArgs[-3:] if len(paArgs)>3: thisFunc = paArgs[0].__class__.__name__ + '.' + thisFunc sys.stderr.write( ">>entering %s(line: '%s', %d, %s)\n" % (thisFunc,line(l,s),l,t) ) try: ret = f(*paArgs) except Exception, exc: sys.stderr.write( "<", "|".join( [ _escapeRegexChars(sym) for sym in symbols] )) try: if len(symbols)==len("".join(symbols)): return Regex( "[%s]" % "".join( [ _escapeRegexRangeChars(sym) for sym in symbols] ) ) else: return Regex( "|".join( [ re.escape(sym) for sym in symbols] ) ) except: warnings.warn("Exception creating Regex for oneOf, building MatchFirst", SyntaxWarning, stacklevel=2) # last resort, just use MatchFirst return MatchFirst( [ parseElementClass(sym) for sym in symbols ] ) def dictOf( key, value ): """Helper to easily and clearly define a dictionary by specifying the respective patterns for the key and value. Takes care of defining the Dict, ZeroOrMore, and Group tokens in the proper order. The key pattern can include delimiting markers or punctuation, as long as they are suppressed, thereby leaving the significant key text. The value pattern can include named results, so that the Dict results can include named token fields. """ return Dict( ZeroOrMore( Group ( key + value ) ) ) def originalTextFor(expr, asString=True): """Helper to return the original, untokenized text for a given expression. Useful to restore the parsed fields of an HTML start tag into the raw tag text itself, or to revert separate tokens with intervening whitespace back to the original matching input text. Simpler to use than the parse action keepOriginalText, and does not require the inspect module to chase up the call stack. By default, returns a string containing the original parsed text. If the optional asString argument is passed as False, then the return value is a ParseResults containing any results names that were originally matched, and a single token containing the original matched text from the input string. So if the expression passed to originalTextFor contains expressions with defined results names, you must set asString to False if you want to preserve those results name values.""" locMarker = Empty().setParseAction(lambda s,loc,t: loc) matchExpr = locMarker("_original_start") + expr + locMarker("_original_end") if asString: extractText = lambda s,l,t: s[t._original_start:t._original_end] else: def extractText(s,l,t): del t[:] t.insert(0, s[t._original_start:t._original_end]) del t["_original_start"] del t["_original_end"] matchExpr.setParseAction(extractText) return matchExpr # convenience constants for positional expressions empty = Empty().setName("empty") lineStart = LineStart().setName("lineStart") lineEnd = LineEnd().setName("lineEnd") stringStart = StringStart().setName("stringStart") stringEnd = StringEnd().setName("stringEnd") _escapedPunc = Word( _bslash, r"\[]-*.$+^?()~ ", exact=2 ).setParseAction(lambda s,l,t:t[0][1]) _printables_less_backslash = "".join([ c for c in printables if c not in r"\]" ]) _escapedHexChar = Combine( Suppress(_bslash + "0x") + Word(hexnums) ).setParseAction(lambda s,l,t:unichr(int(t[0],16))) _escapedOctChar = Combine( Suppress(_bslash) + Word("0","01234567") ).setParseAction(lambda s,l,t:unichr(int(t[0],8))) _singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | Word(_printables_less_backslash,exact=1) _charRange = Group(_singleChar + Suppress("-") + _singleChar) _reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]" _expanded = lambda p: (isinstance(p,ParseResults) and ''.join([ unichr(c) for c in range(ord(p[0]),ord(p[1])+1) ]) or p) def srange(s): r"""Helper to easily define string ranges for use in Word construction. Borrows syntax from regexp '[]' string range definitions:: srange("[0-9]") -> "0123456789" srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" The input string must be enclosed in []'s, and the returned string is the expanded character set joined into a single string. The values enclosed in the []'s may be:: a single character an escaped character with a leading backslash (such as \- or \]) an escaped hex character with a leading '\0x' (\0x21, which is a '!' character) an escaped octal character with a leading '\0' (\041, which is a '!' character) a range of any of the above, separated by a dash ('a-z', etc.) any combination of the above ('aeiouy', 'a-zA-Z0-9_$', etc.) """ try: return "".join([_expanded(part) for part in _reBracketExpr.parseString(s).body]) except: return "" def matchOnlyAtCol(n): """Helper method for defining parse actions that require matching at a specific column in the input text. """ def verifyCol(strg,locn,toks): if col(locn,strg) != n: raise ParseException(strg,locn,"matched token not at column %d" % n) return verifyCol def replaceWith(replStr): """Helper method for common parse actions that simply return a literal value. Especially useful when used with transformString(). """ def _replFunc(*args): return [replStr] return _replFunc def removeQuotes(s,l,t): """Helper parse action for removing quotation marks from parsed quoted strings. To use, add this parse action to quoted string using:: quotedString.setParseAction( removeQuotes ) """ return t[0][1:-1] def upcaseTokens(s,l,t): """Helper parse action to convert tokens to upper case.""" return [ tt.upper() for tt in map(_ustr,t) ] def downcaseTokens(s,l,t): """Helper parse action to convert tokens to lower case.""" return [ tt.lower() for tt in map(_ustr,t) ] def keepOriginalText(s,startLoc,t): """Helper parse action to preserve original parsed text, overriding any nested parse actions.""" try: endloc = getTokensEndLoc() except ParseException: raise ParseFatalException("incorrect usage of keepOriginalText - may only be called as a parse action") del t[:] t += ParseResults(s[startLoc:endloc]) return t def getTokensEndLoc(): """Method to be called from within a parse action to determine the end location of the parsed tokens.""" import inspect fstack = inspect.stack() try: # search up the stack (through intervening argument normalizers) for correct calling routine for f in fstack[2:]: if f[3] == "_parseNoCache": endloc = f[0].f_locals["loc"] return endloc else: raise ParseFatalException("incorrect usage of getTokensEndLoc - may only be called from within a parse action") finally: del fstack def _makeTags(tagStr, xml): """Internal helper to construct opening and closing tag expressions, given a tag name""" if isinstance(tagStr,basestring): resname = tagStr tagStr = Keyword(tagStr, caseless=not xml) else: resname = tagStr.name tagAttrName = Word(alphas,alphanums+"_-:") if (xml): tagAttrValue = dblQuotedString.copy().setParseAction( removeQuotes ) openTag = Suppress("<") + tagStr + \ Dict(ZeroOrMore(Group( tagAttrName + Suppress("=") + tagAttrValue ))) + \ Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">") else: printablesLessRAbrack = "".join( [ c for c in printables if c not in ">" ] ) tagAttrValue = quotedString.copy().setParseAction( removeQuotes ) | Word(printablesLessRAbrack) openTag = Suppress("<") + tagStr + \ Dict(ZeroOrMore(Group( tagAttrName.setParseAction(downcaseTokens) + \ Optional( Suppress("=") + tagAttrValue ) ))) + \ Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">") closeTag = Combine(_L("") openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % tagStr) closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("" % tagStr) return openTag, closeTag def makeHTMLTags(tagStr): """Helper to construct opening and closing tag expressions for HTML, given a tag name""" return _makeTags( tagStr, False ) def makeXMLTags(tagStr): """Helper to construct opening and closing tag expressions for XML, given a tag name""" return _makeTags( tagStr, True ) def withAttribute(*args,**attrDict): """Helper to create a validating parse action to be used with start tags created with makeXMLTags or makeHTMLTags. Use withAttribute to qualify a starting tag with a required attribute value, to avoid false matches on common tags such as or
. Call withAttribute with a series of attribute names and values. Specify the list of filter attributes names and values as: - keyword arguments, as in (class="Customer",align="right"), or - a list of name-value tuples, as in ( ("ns1:class", "Customer"), ("ns2:align","right") ) For attribute names with a namespace prefix, you must use the second form. Attribute names are matched insensitive to upper/lower case. To verify that the attribute exists, but without specifying a value, pass withAttribute.ANY_VALUE as the value. """ if args: attrs = args[:] else: attrs = attrDict.items() attrs = [(k,v) for k,v in attrs] def pa(s,l,tokens): for attrName,attrValue in attrs: if attrName not in tokens: raise ParseException(s,l,"no matching attribute " + attrName) if attrValue != withAttribute.ANY_VALUE and tokens[attrName] != attrValue: raise ParseException(s,l,"attribute '%s' has value '%s', must be '%s'" % (attrName, tokens[attrName], attrValue)) return pa withAttribute.ANY_VALUE = object() opAssoc = _Constants() opAssoc.LEFT = object() opAssoc.RIGHT = object() def operatorPrecedence( baseExpr, opList ): """Helper method for constructing grammars of expressions made up of operators working in a precedence hierarchy. Operators may be unary or binary, left- or right-associative. Parse actions can also be attached to operator expressions. Parameters: - baseExpr - expression representing the most basic element for the nested - opList - list of tuples, one for each operator precedence level in the expression grammar; each tuple is of the form (opExpr, numTerms, rightLeftAssoc, parseAction), where: - opExpr is the pyparsing expression for the operator; may also be a string, which will be converted to a Literal; if numTerms is 3, opExpr is a tuple of two expressions, for the two operators separating the 3 terms - numTerms is the number of terms for this operator (must be 1, 2, or 3) - rightLeftAssoc is the indicator whether the operator is right or left associative, using the pyparsing-defined constants opAssoc.RIGHT and opAssoc.LEFT. - parseAction is the parse action to be associated with expressions matching this operator expression (the parse action tuple member may be omitted) """ ret = Forward() lastExpr = baseExpr | ( Suppress('(') + ret + Suppress(')') ) for i,operDef in enumerate(opList): opExpr,arity,rightLeftAssoc,pa = (operDef + (None,))[:4] if arity == 3: if opExpr is None or len(opExpr) != 2: raise ValueError("if numterms=3, opExpr must be a tuple or list of two expressions") opExpr1, opExpr2 = opExpr thisExpr = Forward()#.setName("expr%d" % i) if rightLeftAssoc == opAssoc.LEFT: if arity == 1: matchExpr = FollowedBy(lastExpr + opExpr) + Group( lastExpr + OneOrMore( opExpr ) ) elif arity == 2: if opExpr is not None: matchExpr = FollowedBy(lastExpr + opExpr + lastExpr) + Group( lastExpr + OneOrMore( opExpr + lastExpr ) ) else: matchExpr = FollowedBy(lastExpr+lastExpr) + Group( lastExpr + OneOrMore(lastExpr) ) elif arity == 3: matchExpr = FollowedBy(lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr) + \ Group( lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr ) else: raise ValueError("operator must be unary (1), binary (2), or ternary (3)") elif rightLeftAssoc == opAssoc.RIGHT: if arity == 1: # try to avoid LR with this extra test if not isinstance(opExpr, Optional): opExpr = Optional(opExpr) matchExpr = FollowedBy(opExpr.expr + thisExpr) + Group( opExpr + thisExpr ) elif arity == 2: if opExpr is not None: matchExpr = FollowedBy(lastExpr + opExpr + thisExpr) + Group( lastExpr + OneOrMore( opExpr + thisExpr ) ) else: matchExpr = FollowedBy(lastExpr + thisExpr) + Group( lastExpr + OneOrMore( thisExpr ) ) elif arity == 3: matchExpr = FollowedBy(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + \ Group( lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr ) else: raise ValueError("operator must be unary (1), binary (2), or ternary (3)") else: raise ValueError("operator must indicate right or left associativity") if pa: matchExpr.setParseAction( pa ) thisExpr << ( matchExpr | lastExpr ) lastExpr = thisExpr ret << lastExpr return ret dblQuotedString = Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*"').setName("string enclosed in double quotes") sglQuotedString = Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*'").setName("string enclosed in single quotes") quotedString = Regex(r'''(?:"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*")|(?:'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*')''').setName("quotedString using single or double quotes") unicodeString = Combine(_L('u') + quotedString.copy()) def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString): """Helper method for defining nested lists enclosed in opening and closing delimiters ("(" and ")" are the default). Parameters: - opener - opening character for a nested list (default="("); can also be a pyparsing expression - closer - closing character for a nested list (default=")"); can also be a pyparsing expression - content - expression for items within the nested lists (default=None) - ignoreExpr - expression for ignoring opening and closing delimiters (default=quotedString) If an expression is not provided for the content argument, the nested expression will capture all whitespace-delimited content between delimiters as a list of separate values. Use the ignoreExpr argument to define expressions that may contain opening or closing characters that should not be treated as opening or closing characters for nesting, such as quotedString or a comment expression. Specify multiple expressions using an Or or MatchFirst. The default is quotedString, but if no expressions are to be ignored, then pass None for this argument. """ if opener == closer: raise ValueError("opening and closing strings cannot be the same") if content is None: if isinstance(opener,basestring) and isinstance(closer,basestring): if len(opener) == 1 and len(closer)==1: if ignoreExpr is not None: content = (Combine(OneOrMore(~ignoreExpr + CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS,exact=1)) ).setParseAction(lambda t:t[0].strip())) else: content = (empty+CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS ).setParseAction(lambda t:t[0].strip())) else: if ignoreExpr is not None: content = (Combine(OneOrMore(~ignoreExpr + ~Literal(opener) + ~Literal(closer) + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1)) ).setParseAction(lambda t:t[0].strip())) else: content = (Combine(OneOrMore(~Literal(opener) + ~Literal(closer) + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1)) ).setParseAction(lambda t:t[0].strip())) else: raise ValueError("opening and closing arguments must be strings if no content expression is given") ret = Forward() if ignoreExpr is not None: ret << Group( Suppress(opener) + ZeroOrMore( ignoreExpr | ret | content ) + Suppress(closer) ) else: ret << Group( Suppress(opener) + ZeroOrMore( ret | content ) + Suppress(closer) ) return ret def indentedBlock(blockStatementExpr, indentStack, indent=True): """Helper method for defining space-delimited indentation blocks, such as those used to define block statements in Python source code. Parameters: - blockStatementExpr - expression defining syntax of statement that is repeated within the indented block - indentStack - list created by caller to manage indentation stack (multiple statementWithIndentedBlock expressions within a single grammar should share a common indentStack) - indent - boolean indicating whether block must be indented beyond the the current level; set to False for block of left-most statements (default=True) A valid block must contain at least one blockStatement. """ def checkPeerIndent(s,l,t): if l >= len(s): return curCol = col(l,s) if curCol != indentStack[-1]: if curCol > indentStack[-1]: raise ParseFatalException(s,l,"illegal nesting") raise ParseException(s,l,"not a peer entry") def checkSubIndent(s,l,t): curCol = col(l,s) if curCol > indentStack[-1]: indentStack.append( curCol ) else: raise ParseException(s,l,"not a subentry") def checkUnindent(s,l,t): if l >= len(s): return curCol = col(l,s) if not(indentStack and curCol < indentStack[-1] and curCol <= indentStack[-2]): raise ParseException(s,l,"not an unindent") indentStack.pop() NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress()) INDENT = Empty() + Empty().setParseAction(checkSubIndent) PEER = Empty().setParseAction(checkPeerIndent) UNDENT = Empty().setParseAction(checkUnindent) if indent: smExpr = Group( Optional(NL) + FollowedBy(blockStatementExpr) + INDENT + (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) + UNDENT) else: smExpr = Group( Optional(NL) + (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) ) blockStatementExpr.ignore(_bslash + LineEnd()) return smExpr alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]") punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]") anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:")) commonHTMLEntity = Combine(_L("&") + oneOf("gt lt amp nbsp quot").setResultsName("entity") +";").streamline() _htmlEntityMap = dict(zip("gt lt amp nbsp quot".split(),'><& "')) replaceHTMLEntity = lambda t : t.entity in _htmlEntityMap and _htmlEntityMap[t.entity] or None # it's easy to get these comment structures wrong - they're very common, so may as well make them available cStyleComment = Regex(r"/\*(?:[^*]*\*+)+?/").setName("C style comment") htmlComment = Regex(r"") restOfLine = Regex(r".*").leaveWhitespace() dblSlashComment = Regex(r"\/\/(\\\n|.)*").setName("// comment") cppStyleComment = Regex(r"/(?:\*(?:[^*]*\*+)+?/|/[^\n]*(?:\n[^\n]*)*?(?:(?" + str(tokenlist)) print ("tokens = " + str(tokens)) print ("tokens.columns = " + str(tokens.columns)) print ("tokens.tables = " + str(tokens.tables)) print (tokens.asXML("SQL",True)) except ParseBaseException,err: print (teststring + "->") print (err.line) print (" "*(err.column-1) + "^") print (err) print() selectToken = CaselessLiteral( "select" ) fromToken = CaselessLiteral( "from" ) ident = Word( alphas, alphanums + "_$" ) columnName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) columnNameList = Group( delimitedList( columnName ) )#.setName("columns") tableName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) tableNameList = Group( delimitedList( tableName ) )#.setName("tables") simpleSQL = ( selectToken + \ ( '*' | columnNameList ).setResultsName( "columns" ) + \ fromToken + \ tableNameList.setResultsName( "tables" ) ) test( "SELECT * from XYZZY, ABC" ) test( "select * from SYS.XYZZY" ) test( "Select A from Sys.dual" ) test( "Select AA,BB,CC from Sys.dual" ) test( "Select A, B, C from Sys.dual" ) test( "Select A, B, C from Sys.dual" ) test( "Xelect A, B, C from Sys.dual" ) test( "Select A, B, C frox Sys.dual" ) test( "Select" ) test( "Select ^^^ frox Sys.dual" ) test( "Select A, B, C from Sys.dual, Table2 " ) zhpy-1.7.3.1.orig/zhpy/zhdc.py0000644000000000000000000000362211307125272012777 0ustar #!/usr/bin/python # -*- coding: utf-8 -*- """zhpy keywords convertion library This is the MIT license: http://www.opensource.org/licenses/mit-license.php Copyright (c) 2007~ Fred Lin and contributors. zhpy is a trademark of Fred Lin. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ # Universal keywords repository #: always run annotator before access worddict worddict = {} #: Traditional Chinese keywords repository twdict = {} #: Simplified Chinese keywords repository cndict = {} class ZhpyPlugin(object): """ basic plugin class """ pass def revert_dict(lang_dict): """make a reverse dictionary from the input dictionary >>> revert_dict({'a':'1', 'b':'2'}) {'1': 'a', '2': 'b'} """ rev_dict = {} dict_keys = lang_dict.keys() dict_keys.reverse() #map(rev_dict.update, map(lambda i: {lang_dict[i]:i}, dict_keys)) for i in dict_keys: rev_dict.update({lang_dict[i]:i}) return rev_dict zhpy-1.7.3.1.orig/zhpy/__init__.py0000644000000000000000000000010611307125272013600 0ustar from release import version __version__ = version from zhpy import * zhpy-1.7.3.1.orig/zhpy/info.py0000644000000000000000000000464611307125272013011 0ustar """ zhpy package and plugin information This is the MIT license: http://www.opensource.org/licenses/mit-license.php Copyright (c) 2007~ Fred Lin and contributors. zhpy is a trademark of Fred Lin. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following consditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ import pkg_resources import sys entrypoints = {"Traditional Chinese Keywords":"plugtw.tools", "Simplified Chinese Keywords":"plugcn.tools"} def retrieve_info(): """ retrieve package and plugins info """ packages=['%s' % i for i in pkg_resources.require("zhpy")] #plugins = {} #for name, pointname in entrypoints.items(): # plugins[name] = ["%s (%s) - %d" % (entrypoint.name, \ # str(entrypoint.dist), \ # len(entrypoint.load().keyword)) # for entrypoint in pkg_resources.iter_entry_points(pointname) # ] return packages#, plugins def info(): """ show zhpy informations including version and plugins ported from TurboGears2 tginfo command """ print """ Complete zhpy Version Information zhpy requires: """ print " * python",sys.version.split()[0] #packages, plugins = retrieve_info() packages = retrieve_info() for p in packages: print ' *', p # print """\nzhpy extends:""" # for name, pluginlist in plugins.items(): # print "\n", name, "\n" # for plugin in pluginlist: # print ' *', plugin print ""zhpy-1.7.3.1.orig/zhpy/ext/0000755000000000000000000000000011323406236012272 5ustar zhpy-1.7.3.1.orig/zhpy/ext/pygmentplugin.py0000644000000000000000000001502511307125272015551 0ustar #coding=utf-8 import re try: set except NameError: from sets import Set as set #from pygments.lexers.agile import PythonLexer from pygments.lexer import Lexer, RegexLexer, ExtendedRegexLexer, \ LexerContext, include, combined, do_insertions, bygroups, using from pygments.token import Error, Text, \ Comment, Operator, Keyword, Name, String, Number, Generic, Punctuation from pygments.util import get_bool_opt, get_list_opt, shebang_matches from pygments import unistring as uni from pygments.lexers.functional import SchemeLexer line_re = re.compile('.*?\n') class ZhpyLexer(RegexLexer): """ for zhpy source code """ name = "Zhpy" aliases = ['zhpy'] filenames = ['*.twpy', '*.cnpy', '*.py'] tokens = { 'root': [ (r'\n', Text), (r'^(\s*)("""(?:.|\n)*?""")', bygroups(Text, String.Doc)), #docstring (r"^(\s*)('''(?:.|\n)*?''')", bygroups(Text, String.Doc)), #docstring (r'[^\S\n]+', Text), (r'#.*$', Comment), #comment (r'[]{}:(),;[]', Punctuation), (r'\\\n', Text), (r'\\', Text), (r'(in|is|and|or|not)\b', Operator.Word), (r'!=|==|<<|>>|[-~+/*%=<>&^|.]', Operator), include('keywords'), (r'(def)(\s+)', bygroups(Keyword, Text), 'funcname'), (r'(class)(\s+)', bygroups(Keyword, Text), 'classname'), (r'(from)(\s+)', bygroups(Keyword, Text), 'fromimport'), (r'(import)(\s+)', bygroups(Keyword, Text), 'import'), include('builtins'), include('backtick'), ('(?:[rR]|[uU][rR]|[rR][uU])"""', String, 'tdqs'), ("(?:[rR]|[uU][rR]|[rR][uU])'''", String, 'tsqs'), ('(?:[rR]|[uU][rR]|[rR][uU])"', String, 'dqs'), ("(?:[rR]|[uU][rR]|[rR][uU])'", String, 'sqs'), ('[uU]?"""', String, combined('stringescape', 'tdqs')), ("[uU]?'''", String, combined('stringescape', 'tsqs')), ('[uU]?"', String, combined('stringescape', 'dqs')), ("[uU]?'", String, combined('stringescape', 'sqs')), include('name'), include('numbers'), ], 'keywords': [ (r'(assert|break|continue|del|elif|else|except|exec|' r'finally|for|global|if|lambda|pass|print|raise|' r'return|try|while|yield|as|with|' r'印出|輸入)\b', Keyword), ], 'builtins': [ (r'(?>> keys = [('遊戲', 'pygame'), ('螢幕', 'screen')] >>> merger(keys) add 遊戲=pygame add 螢幕=screen >>> '遊戲' in worddict True merger could accept dict input: >>> keydic = {'作業系統':'os', '分支':'fork'} >>> merger(keydic) add 分支=fork add 作業系統=os >>> '作業系統' in worddict True """ if isinstance(anno_dict, dict): data_iter = anno_dict.iteritems() else: data_iter = anno_dict if reverse: #data_iter=((v,k) for (k,v) in data_iter) rev_iter = [] for (k,v) in data_iter: rev_iter.append((v,k)) data_iter = rev_iter for k,v in data_iter: if k not in use_dict: use_dict[k] = v if verbose: print "add %s=%s"%(k, v) else: if verbose: print "already has key: %s, %s" % (k, v) import os import ConfigParser def _ini_annotator(verbose=True, force=False): """ find ini files and use keywords defined in ini during convertion progress. Accept args: verbose: show detail message, default: True """ #lazy load if not force and getattr(_ini_annotator, "already", False): return _ini_annotator.already=True inifiles = [] for x in os.listdir("."): if x.endswith(".ini"): inifiles.append(x) for f in inifiles: if verbose: print "file", f conf = ConfigParser.ConfigParser() try: conf.read(f) for sect in conf.sections(): if verbose: print "sect:", sect merger(conf.items(sect)) except: print "!%s is not a valid keyword file"%f def _py_annotator(verbose=False,force=False): """ find python keyword plugins and update to dicts Accept args: verbose: show detail message, default: False 'verbose' argument is only for debug(will generate too mush messages). """ #lazy load if not force and getattr(_py_annotator, "already", False): return _py_annotator.already=True # parameter to check if there's any plugin available has_annotator = False # process plugins for plugin, use_dict in supported_dicts: try: #py2.4 doesn't have level argument load_dict=__import__(plugin, globals(), locals(), ['tools']) for tool in load_dict.tools: if verbose: print tool.title merger(tool.keyword, use_dict=use_dict, verbose=verbose) merger(use_dict, verbose=verbose) has_annotator = True except ImportError, e: if verbose: print "import plug%s error"%plugin, e if not has_annotator: raise ReferenceError("no plugin was referenced in annotator") _py_annotator.__loaded=False def annotator(verbose=True, force=False): """ provide two ways to expand the worddict: 1. ini files 2. python plugin system. Accept args: verbose: show detail message, default: True """ _ini_annotator(verbose, force) _py_annotator(False, force) def zh_ord(tmp): """ convert chinese variable to pseudo hex identifer >>> '範例'.decode("utf8") u'\u7bc4\u4f8b' >>> s = '範例'.decode("utf8") >>> zh_ord(s) 'p_7bc4_4f8b_v' """ word_list=[] for i in tmp: ori = str(hex(ord(i)))[2:] word_list.append(ori) return 'p_' + "_".join(word_list) + '_v' # backward compatibility variable_to_number = zh_ord from pyparsing import srange, Word, quotedString, pythonStyleComment, \ QuotedString def convertToEnglish(s,l,t): """search worddict to match keywords if not in keyword, replace the chinese variable/argument/ function name/class name/method name to a variable with prefix 'p' """ tmp = t[0].encode("utf8") if tmp in worddict: word = worddict[tmp].decode("utf8") else: word = zh_ord(t[0]) return word chineseChars = srange(r"[\0x0080-\0xfe00]") chineseWord = Word(chineseChars) chineseWord.setParseAction(convertToEnglish) tripleQuote = QuotedString('"""', multiline=True, unquoteResults=False) | \ QuotedString("'''", multiline=True, unquoteResults=False) pythonWord = tripleQuote | quotedString | pythonStyleComment | chineseWord try: import chardet has_chardet = True except: has_chardet = False print "chardet module is not installed" def convertor(text, verbose=False, encoding="", outcoding=""): """ convert zhpy source (Chinese) to Python Source. annotator will be called automatically. Accept args: test: source to be converted verbose: show detail message, default: False encoding: codec for encoding outcoding: codec for output encoding #annotator() >>> convertor("印出 'hello'") "print 'hello'" >>> convertor("印出 'hello'", encoding="utf8") "print 'hello'" >>> convertor('測試_範例') 'test_p_7bc4_4f8b_v' more keyword test cases are in /tests folder. """ # annotate if necessary annotator(force=False) #Use the provided encoding, if not exist select utf-8 as default. if encoding and encoding.lower() != 'utf-8': utext = text.decode(encoding) else: if has_chardet: try: #detect encoding det = chardet.detect(text) if verbose: print "chardet", det if det['confidence'] >= 0.8: encoding = chardet.detect(text)['encoding'] else: if verbose: print """low confidence encoding detection, use utf8 encoding""" encoding = 'utf8' #prepare for unicode type support if isinstance(text, unicode): utext = text else: utext = text.decode(encoding) except UnicodeDecodeError, e: print "can't recognize your language, \ set to sys.stdout.encoding" utext = text.decode('utf8') except ImportError, e: if verbose: print "proceed no chardet mode" utext = text.decode('utf8') else: utext = text result = pythonWord.transformString(utext) if outcoding: return result.encode(outcoding) elif isinstance(text, unicode): return result else: if encoding: return result.encode(encoding) else: return result import sys # parameter to control if support chinese traceback has_zhtraceback=None try: import traceback from pyzh import python_convertor, rev_annotator has_zhtraceback=True except: print "not support chinese traceback" has_zhtraceback=None def try_run(result, global_ns={}, local_ns={}, verbose=True, zhtrace=True): """ execute result and catch exceptions in specified namespace Accept args: result: the converted source to be executed global_ns: Global namespace, deafult is {} local_ns: Local namespace, default is: {} >>> global_ns = {'x':'g'} >>> local_ns = {'x':'l'} >>> global_ns.update( {"__name__": "__main__", "__doc__": None}) >>> try_run("print 'hello'", {}, {}) hello >>> try_run("print x", global_ns, local_ns) l >>> try_run("print x", global_ns) g """ try: # able to import modules in current directory sys.path.insert(0, '') exec result in global_ns, local_ns except Exception, e: # Print error and track back. if has_zhtraceback and zhtrace: display = os.getenv("LANG") if display == None: lang = None elif "zh_TW" in display: lang = "tw" elif "zh_CN" in display: lang = "cn" else: lang = None stack = traceback.format_exc() if lang: rev_annotator(lang) print python_convertor(stack, lang, traceback=True).decode("utf-8") else: # Standard English output print stack else: if verbose: print result print e def zh_exec(content, global_ns={"__name__": "__main__", "__doc__": None}, local_ns={}, outcoding=""): """ the zhpy exec Accept args: content: the source to be converted and executed with zhpy in specified namespace global_ns: Global namespace, deafult is {"__name__": "__main__", "__doc__": None} local_ns: Local namespace, default is: {} >>> zh_exec("印出 'hello'") hello """ #annotator() result = convertor(content, outcoding=outcoding) if local_ns == {}: local_ns = global_ns try_run(result, global_ns, local_ns) zhpy-1.7.3.1.orig/zhpy/plugtw.py0000644000000000000000000002241511307125272013372 0ustar #!/usr/bin/python # -*- coding: utf-8 -*- """Traditional Chinese keyword dictionaries This is the MIT license: http://www.opensource.org/licenses/mit-license.php Copyright (c) 2007~ Fred Lin and contributors. zhpy is a trademark of Fred Lin. Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ from zhdc import ZhpyPlugin # Traditional chinese keywords class tw_keyword(ZhpyPlugin): """ python tw keyword """ title = "內建關鍵詞" description = "Python 內建關鍵詞" keyword = { # logic "和":"and", "且":"and", "或":"or", "真":"True", "假":"False", "實":"True", "虛":"False", "空":"None", # def "定義":"def", "類別":"class", "我":"self", "共用":"global", "全域":"global", # import "從":"from", "導入":"import", "作為":"as", # flow "返回":"return", "略過":"pass", "引發":"raise", "繼續":"continue", # control "如果":"if", "假使":"elif", "否則如果":"elif", "否則":"else", # for loop "取":"for", "自":"in", "在":"in", "不在":"not in", # while loop "當":"while", "跳出":"break", "中斷":"break", # try "嘗試":"try", "異常":"except", "最後":"finally", "申明":"assert", # build in methods "執行":"exec", "方程式":"lambda", "印出":"print", "伴隨":"with", "產生":"yield", } class tw_buildin_method(ZhpyPlugin): """ python tw methods """ title = "內部函數" description = "Python 內部函數" keyword = { "輸入":"raw_input", # build-in types "字串":"str", "布林":"bool", "列表":"list", "字典":"dict", "元組":"tuple", "集合":"set", "定集合":"frozenset", "符號":"chr", "符號轉整數":"ord", "檔案":"file", # number methods "整數":"int", "浮點數":"float", "複數":"complex", "十六進位":"hex", "絕對值":"abs", "比較":"cmp", # string methods "開頭為":"startswith", "結尾為":"endswith", "連接":"join", "分離":"split", "代換":"replace", "編碼":"encoding", "解碼":"decoding", # list methods "加入":"append", "追加":"append", "擴展":"extend", "插入":"insert", "彈出":"pop", "下一筆":"next", "移除":"remove", "反轉":"reverse", "計數":"count", "索引":"index", "排序":"sort", # dict methods "鍵列表":"keys", "值列表":"values", "項目列表": "items", "更新":"update", "複製":"copy", # set methods "清除":"clear", "加":"add", "丟棄":"discard", "聯集":"union", "交集":"intersection", "差集":"difference", "對稱差集":"symmetric_difference", # file methods "打開":"open", "讀取":"read", "寫入":"write", "讀一行":"readline", "讀多行":"readlines", "關閉":"close", # OO "可調用":"callable", "列出屬性":"dir", "取屬性":"getattr", "有屬性":"hasattr", "設定屬性":"setattr", "屬性":"property", # build in functions "長度":"len", "最大值":"max", "最小值":"min", # build in methods "列舉":"enumerate", "評估":"eval", "過濾":"filter", "映射":"map", "範圍":"range", "快速範圍":"xrange", "總和":"sum", "型別":"type", "物件":"object", "打包":"zip", "說明":"help", "幫助":"help", "區域變量":"locals", "全域變量":"globals", "類別方法":"classmethod", } class tw_exception(ZhpyPlugin): """ python tw exceptions """ title = "例外" description = "Python 內建例外關鍵詞" keyword = { "例外":"Exception", "錯誤":"Error", # error "運算錯誤":"ArithmeticError", "申明錯誤":"AssertionError", "屬性錯誤":"AttributeError", "相容性警示":"DeprecationWarning", "空值錯誤":"EOFError", "環境錯誤":"EnvironmentError", "浮點數錯誤":"FloatingPointError", "輸出入錯誤":"IOError", "導入錯誤":"ImportError", "縮排錯誤":"IndentationError", "索引錯誤":"IndexError", "鍵錯誤":"KeyError", "鍵盤中斷":"KeyboardInterrupt", "查找錯誤":"LookupError", "記憶體錯誤":"MemoryError", "名稱錯誤":"NameError", "尚未實作":"NotImplemented", "尚未實作錯誤":"NotImplementedError", "作業系統錯誤":"OSError", "溢值錯誤":"OverflowError", "溢值警告":"OverflowWarning", "引用錯誤":"ReferenceError", "運行期錯誤":"RuntimeError", "運行期警告":"RuntimeWarning", "標準錯誤":"StandardError", "停止迭代":"StopIteration", "語法錯誤":"SyntaxError", "語法警告":"SyntaxWarning", "系統錯誤":"SystemError", "系統結束":"SystemExit", "型別錯誤":"TypeError", "跳格錯誤":"TabError", "未綁定區域變量錯誤":"UnboundLocalError", "萬國碼解碼錯誤":"UnicodeError", "自訂警告":"UserWarning", "值錯誤":"ValueError", "警告":"Warning", "Windows錯誤":"WindowsError", "除零錯誤":"ZeroDivisionError", "解碼錯誤":"UnicodeDecodeError", } class tw_zhpy(ZhpyPlugin): """ zhpy tw keyword plugin """ title = "周蟒" description = "周蟒內建關鍵詞" keyword = { "周蟒":"zhpy", "主程式":'if __name__=="__main__"', # must do 'from zhpy import zh_exec'/'從 周蟒 導入 中文執行' first "中文執行":"zh_exec", # logic "等於":"==", "不等於":"!=", "非":"not", "是":"is", "為":"is", "不是":"is not", "不為":"is not", # private "文件":"doc", "初始化":"init", "刪除":"del", "描述":"repr", "測試":"test", } #enter traditional chinese dict here class tw_sys(ZhpyPlugin): """ zhpy sys module traditional chinese plugin """ title = "系統" description = "系統模組" keyword = {"系統":"sys", "版本":"version", "參數":"argv", "結束":"exit", "取得檔案系統編碼":"getfilesystemencoding", "模組列表":"modules", "平台":"platform", "標準錯誤":"stderr", "標準輸入":"stdin", "標準輸出":"stdout", # sys path with list methods "路徑":"path", } class tw_traceback(ZhpyPlugin): """ zhpy traceback traditional chinese plugin """ title = "系統" description = "系統模組" keyword = {"未定義":"is not defined", "名稱":"name", "行":"line", "檔案":"File", "不合法的":"invalid", "語法":"syntax", } # [zhpy.twdict] twkeyword = tw_keyword() twmethod = tw_buildin_method() twexception = tw_exception() twzhpy= tw_zhpy() twsys = tw_sys() twtrace = tw_traceback() tools = [twkeyword, twmethod, twexception, twzhpy, twsys] trace = [twkeyword, twmethod, twexception, twtrace, twsys] zhpy-1.7.3.1.orig/PKG-INFO0000644000000000000000000001317611307367650011615 0ustar Metadata-Version: 1.0 Name: zhpy Version: 1.7.3.1 Summary: Write python language in chinese Home-page: http://zhpy.googlecode.com/ Author: Fred Lin Author-email: gasolin+zhpy@gmail.com License: MIT Download-URL: http://code.google.com/p/zhpy/ Description: .. contents:: :depth: 2 Introduction -------------- "If it walks like a duck and quacks like a duck, I would call it a duck." Zhpy on python is good for Taiwan and China beginners to learn python in our native language (Currently support Traditional and Simplified chinese). Zhpy acts like python and play like python, you (chinese users) could use it as python to educate yourself the program skills plus with your native language. Check examples here. * http://zhpy.googlecode.com/svn/trunk/examples Play Zhpy Online -------------------- Zhpy has online version (with limited feature) running with google app engine! * http://zhpy.appspot.com Play locally -------------- To play zhpy locally, you even don't need to install it. All you need to do is follow the 3 steps guide: 1. Download the source pack (the zip file) 2. Extract the pack with zip tool. Enter the folder 3. Run:: $ python interpreter.py Then you got the usable zhpy interpreter! Install ---------- If you'd like to play zhpy with full features, you should install zhpy. You could use easy_install command to install or upgrade zhpy:: $ easy_install -U zhpy or check instructions for detail. * http://code.google.com/p/zhpy/wiki/DownloadInstall Usage ------- You could use zhpy interpreter to test zhpy:: $ zhpy zhpy [version] in [platform] on top of Python [py_version] >>> print 'hello in chinese' hello in chinese Browse project homepage to get examples in chinese. * http://code.google.com/p/zhpy/ check the BasicUsage for detail. * http://code.google.com/p/zhpy/wiki/BasicUsage Programming Guide ------------------- You could freely view the C.C. licensed book "A Byte of python (Zhpy)" on zhpy website, which contained zhpy example codes as well. * http://code.google.com/p/zhpy/wiki/ByteOfZhpy There's the API document available in zhpy download list, too. * http://code.google.com/p/zhpy/downloads/list PS: The book is based on "A Byte of Python". * http://swaroopch.info/text/Byte_of_Python:Main_Page What is Zhpy -------------- Zhpy is the full feature python language with fully tested chinese keywords, variables, and parameters support. Zhpy is INDEPENDENT on python version(2.4, 2.5....), bundle with command line tool, interpreter, bi-directional zhpy <-> python code translation, chinese shell script capability, in-place ini reference feature for keyword reuse, and great document (the book Byte of Python with chinese examples). The core of zhpy is a lightweight python module and a chinese source convertor based on python, which provides interpreter and command line tool to translate zhpy code to python. See http://www.flickr.com/photos/gasolin/2064120327 You could invoke interpreter with 'zhpy' command instead of "python" in command line to execute source code wrote in either Chinese or English. The zhpy interpreter also support autocomplete function to save your typing. Zhpy provide a method 'zh_exec' that allow you to embed chinese script in python; Zhpy could be used as the chinese shell script as well. The zhpy code written in traditional and simplified chinese could be translated and converted to natual python code. Thus it could be execute as nature python code and be used in normal python programs. Bidirectional python-zhpy translation is possible. Normal python programs could be translated to traditional(.twpy) or simplified(.cnpy) chinese zhpy source via 'zhpy' command line tool. The framework is not hard to extend to another languages such as japenese or korean. Change Log ------------- You could view the ChangeLog to see what's new in these version. * http://zhpy.googlecode.com/svn/trunk/CHANGELOG.txt Keywords: traditional,simplified,chinese Platform: UNKNOWN Classifier: Development Status :: 5 - Production/Stable Classifier: Environment :: Console Classifier: Intended Audience :: Education Classifier: Intended Audience :: Developers Classifier: Intended Audience :: System Administrators Classifier: License :: OSI Approved :: MIT License Classifier: Natural Language :: Chinese (Traditional) Classifier: Natural Language :: Chinese (Simplified) Classifier: Operating System :: OS Independent Classifier: Programming Language :: Python Classifier: Topic :: Software Development :: Libraries :: Python Modules Classifier: Topic :: Software Development :: Code Generators